diff --git a/.github/ISSUE_TEMPLATE/feature_request.md b/.github/ISSUE_TEMPLATE/feature_request.md index edd7681a..73586eaa 100644 --- a/.github/ISSUE_TEMPLATE/feature_request.md +++ b/.github/ISSUE_TEMPLATE/feature_request.md @@ -10,7 +10,7 @@ assignees: '' ### Please read this first - **Have you read the docs?**[Agents SDK docs](https://openai.github.io/openai-agents-python/) -- **Have you searched for related issues?** Others may have had similar requesrs +- **Have you searched for related issues?** Others may have had similar requests ### Describe the feature What is the feature you're requesting? How would it work? Please provide examples and details if possible. diff --git a/.github/ISSUE_TEMPLATE/question.md b/.github/ISSUE_TEMPLATE/question.md index cb4a05dc..6c639d72 100644 --- a/.github/ISSUE_TEMPLATE/question.md +++ b/.github/ISSUE_TEMPLATE/question.md @@ -10,7 +10,7 @@ assignees: '' ### Please read this first - **Have you read the docs?**[Agents SDK docs](https://openai.github.io/openai-agents-python/) -- **Have you searched for related issues?** Others may have had similar requesrs +- **Have you searched for related issues?** Others may have had similar requests ### Question Describe your question. Provide details if available. diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml index 4f93980a..edd0d898 100644 --- a/.github/workflows/tests.yml +++ b/.github/workflows/tests.yml @@ -5,8 +5,7 @@ on: branches: - main pull_request: - branches: - - main + # All PRs, including stacked PRs env: UV_FROZEN: "1" diff --git a/.gitignore b/.gitignore index 7dd22b88..2e9b9237 100644 --- a/.gitignore +++ b/.gitignore @@ -141,4 +141,5 @@ cython_debug/ .ruff_cache/ # PyPI configuration file -.pypirc \ No newline at end of file +.pypirc +.aider* diff --git a/.vscode/settings.json b/.vscode/settings.json new file mode 100644 index 00000000..9b388533 --- /dev/null +++ b/.vscode/settings.json @@ -0,0 +1,7 @@ +{ + "python.testing.pytestArgs": [ + "tests" + ], + "python.testing.unittestEnabled": false, + "python.testing.pytestEnabled": true +} \ No newline at end of file diff --git a/AGENTS.md b/AGENTS.md new file mode 100644 index 00000000..ff37db32 --- /dev/null +++ b/AGENTS.md @@ -0,0 +1,69 @@ +Welcome to the OpenAI Agents SDK repository. This file contains the main points for new contributors. + +## Repository overview + +- **Source code**: `src/agents/` contains the implementation. +- **Tests**: `tests/` with a short guide in `tests/README.md`. +- **Examples**: under `examples/`. +- **Documentation**: markdown pages live in `docs/` with `mkdocs.yml` controlling the site. +- **Utilities**: developer commands are defined in the `Makefile`. +- **PR template**: `.github/PULL_REQUEST_TEMPLATE/pull_request_template.md` describes the information every PR must include. + +## Local workflow + +1. Format, lint and type‑check your changes: + + ```bash + make format + make lint + make mypy + ``` + +2. Run the tests: + + ```bash + make tests + ``` + + To run a single test, use `uv run pytest -s -k `. + +3. Build the documentation (optional but recommended for docs changes): + + ```bash + make build-docs + ``` + + Coverage can be generated with `make coverage`. + +## Snapshot tests + +Some tests rely on inline snapshots. See `tests/README.md` for details on updating them: + +```bash +make snapshots-fix # update existing snapshots +make snapshots-create # create new snapshots +``` + +Run `make tests` again after updating snapshots to ensure they pass. + +## Style notes + +- Write comments as full sentences and end them with a period. + +## Pull request expectations + +PRs should use the template located at `.github/PULL_REQUEST_TEMPLATE/pull_request_template.md`. Provide a summary, test plan and issue number if applicable, then check that: + +- New tests are added when needed. +- Documentation is updated. +- `make lint` and `make format` have been run. +- The full test suite passes. + +Commit messages should be concise and written in the imperative mood. Small, focused commits are preferred. + +## What reviewers look for + +- Tests covering new behaviour. +- Consistent style: code formatted with `ruff format`, imports sorted, and type hints passing `mypy`. +- Clear documentation for any public API changes. +- Clean history and a helpful PR description. diff --git a/Makefile b/Makefile index accf2d91..5c6aba42 100644 --- a/Makefile +++ b/Makefile @@ -42,6 +42,11 @@ old_version_tests: build-docs: uv run mkdocs build +.PHONY: build-full-docs +build-full-docs: + uv run docs/scripts/translate_docs.py + uv run mkdocs build + .PHONY: serve-docs serve-docs: uv run mkdocs serve diff --git a/README.md b/README.md index bbd4a5a0..7dcd97b3 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,6 @@ # OpenAI Agents SDK -The OpenAI Agents SDK is a lightweight yet powerful framework for building multi-agent workflows. +The OpenAI Agents SDK is a lightweight yet powerful framework for building multi-agent workflows. It is provider-agnostic, supporting the OpenAI Responses and Chat Completions APIs, as well as 100+ other LLMs. Image of the Agents Tracing UI @@ -13,8 +13,6 @@ The OpenAI Agents SDK is a lightweight yet powerful framework for building multi Explore the [examples](examples) directory to see the SDK in action, and read our [documentation](https://openai.github.io/openai-agents-python/) for more details. -Notably, our SDK [is compatible](https://openai.github.io/openai-agents-python/models/) with any model providers that support the OpenAI Chat Completions API format. - ## Get started 1. Set up your Python environment diff --git a/docs/agents.md b/docs/agents.md index 23b18b64..39d4afd5 100644 --- a/docs/agents.md +++ b/docs/agents.md @@ -32,11 +32,11 @@ Agents are generic on their `context` type. Context is a dependency-injection to ```python @dataclass class UserContext: - uid: str - is_pro_user: bool + uid: str + is_pro_user: bool - async def fetch_purchases() -> list[Purchase]: - return ... + async def fetch_purchases() -> list[Purchase]: + return ... agent = Agent[UserContext]( ..., diff --git a/docs/config.md b/docs/config.md index 3cf83730..bfaf90e8 100644 --- a/docs/config.md +++ b/docs/config.md @@ -63,7 +63,7 @@ Alternatively, you can customize the logs by adding handlers, filters, formatter ```python import logging -logger = logging.getLogger("openai.agents") # or openai.agents.tracing for the Tracing logger +logger = logging.getLogger("openai.agents") # or openai.agents.tracing for the Tracing logger # To make all logs show up logger.setLevel(logging.DEBUG) diff --git a/docs/examples.md b/docs/examples.md index 1d3ebde7..30d60282 100644 --- a/docs/examples.md +++ b/docs/examples.md @@ -5,32 +5,38 @@ Check out a variety of sample implementations of the SDK in the examples section ## Categories -- **agent_patterns:** +- **[agent_patterns](https://github.com/openai/openai-agents-python/tree/main/examples/agent_patterns):** Examples in this category illustrate common agent design patterns, such as - + - Deterministic workflows - Agents as tools - Parallel agent execution -- **basic:** +- **[basic](https://github.com/openai/openai-agents-python/tree/main/examples/basic):** These examples showcase foundational capabilities of the SDK, such as - + - Dynamic system prompts - Streaming outputs - Lifecycle events -- **tool examples:** +- **[tool examples](https://github.com/openai/openai-agents-python/tree/main/examples/tools):** Learn how to implement OAI hosted tools such as web search and file search, and integrate them into your agents. -- **model providers:** +- **[model providers](https://github.com/openai/openai-agents-python/tree/main/examples/model_providers):** Explore how to use non-OpenAI models with the SDK. -- **handoffs:** +- **[handoffs](https://github.com/openai/openai-agents-python/tree/main/examples/handoffs):** See practical examples of agent handoffs. -- **customer_service** and **research_bot:** +- **[mcp](https://github.com/openai/openai-agents-python/tree/main/examples/mcp):** + Learn how to build agents with MCP. + +- **[customer_service](https://github.com/openai/openai-agents-python/tree/main/examples/customer_service)** and **[research_bot](https://github.com/openai/openai-agents-python/tree/main/examples/research_bot):** Two more built-out examples that illustrate real-world applications - + - **customer_service**: Example customer service system for an airline. - **research_bot**: Simple deep research clone. + +- **[voice](https://github.com/openai/openai-agents-python/tree/main/examples/voice):** + See examples of voice agents, using our TTS and STT models. diff --git a/docs/ja/agents.md b/docs/ja/agents.md new file mode 100644 index 00000000..828b3635 --- /dev/null +++ b/docs/ja/agents.md @@ -0,0 +1,151 @@ +--- +search: + exclude: true +--- +# エージェント + +エージェントはアプリの主要な構成ブロックです。エージェントは、大規模言語モデル ( LLM ) に instructions と tools を設定したものです。 + +## 基本設定 + +エージェントで最も一般的に設定するプロパティは次のとおりです。 + +- `instructions`: 開発者メッセージまたは system prompt とも呼ばれます。 +- `model`: 使用する LLM と、temperature や top_p などのモデル調整パラメーターを指定する任意の `model_settings`。 +- `tools`: エージェントがタスクを達成するために利用できるツール。 + +```python +from agents import Agent, ModelSettings, function_tool + +@function_tool +def get_weather(city: str) -> str: + return f"The weather in {city} is sunny" + +agent = Agent( + name="Haiku agent", + instructions="Always respond in haiku form", + model="o3-mini", + tools=[get_weather], +) +``` + +## コンテキスト + +エージェントはその `context` 型について汎用的です。コンテキストは依存性注入の手段で、`Runner.run()` に渡すオブジェクトです。これはすべてのエージェント、ツール、ハンドオフなどに渡され、エージェント実行時の依存関係や状態をまとめて保持します。任意の Python オブジェクトをコンテキストとして渡せます。 + +```python +@dataclass +class UserContext: + uid: str + is_pro_user: bool + + async def fetch_purchases() -> list[Purchase]: + return ... + +agent = Agent[UserContext]( + ..., +) +``` + +## 出力タイプ + +デフォルトでは、エージェントはプレーンテキスト ( つまり `str` ) を出力します。特定の型で出力させたい場合は `output_type` パラメーターを使用します。一般的には [Pydantic](https://docs.pydantic.dev/) オブジェクトを利用しますが、Pydantic の [TypeAdapter](https://docs.pydantic.dev/latest/api/type_adapter/) でラップ可能な型であれば何でも対応します。たとえば dataclass、list、TypedDict などです。 + +```python +from pydantic import BaseModel +from agents import Agent + + +class CalendarEvent(BaseModel): + name: str + date: str + participants: list[str] + +agent = Agent( + name="Calendar extractor", + instructions="Extract calendar events from text", + output_type=CalendarEvent, +) +``` + +!!! note + + `output_type` を渡すと、モデルは通常のプレーンテキスト応答の代わりに [structured outputs](https://platform.openai.com/docs/guides/structured-outputs) を使用するよう指示されます。 + +## ハンドオフ + +ハンドオフは、エージェントが委譲できるサブエージェントです。ハンドオフのリストを渡しておくと、エージェントは必要に応じてそれらに処理を委譲できます。これにより、単一のタスクに特化したモジュール式エージェントを編成できる強力なパターンが実現します。詳細は [handoffs](handoffs.md) ドキュメントをご覧ください。 + +```python +from agents import Agent + +booking_agent = Agent(...) +refund_agent = Agent(...) + +triage_agent = Agent( + name="Triage agent", + instructions=( + "Help the user with their questions." + "If they ask about booking, handoff to the booking agent." + "If they ask about refunds, handoff to the refund agent." + ), + handoffs=[booking_agent, refund_agent], +) +``` + +## 動的 instructions + +通常はエージェント作成時に instructions を指定しますが、関数を介して動的に instructions を提供することもできます。その関数はエージェントとコンテキストを受け取り、プロンプトを返す必要があります。同期関数と `async` 関数の両方に対応しています。 + +```python +def dynamic_instructions( + context: RunContextWrapper[UserContext], agent: Agent[UserContext] +) -> str: + return f"The user's name is {context.context.name}. Help them with their questions." + + +agent = Agent[UserContext]( + name="Triage agent", + instructions=dynamic_instructions, +) +``` + +## ライフサイクルイベント (hooks) + +場合によっては、エージェントのライフサイクルを観察したいことがあります。たとえば、イベントをログに記録したり、特定のイベント発生時にデータを事前取得したりする場合です。`hooks` プロパティを使ってエージェントのライフサイクルにフックできます。[`AgentHooks`][agents.lifecycle.AgentHooks] クラスをサブクラス化し、関心のあるメソッドをオーバーライドしてください。 + +## ガードレール + +ガードレールを使うと、エージェントの実行と並行してユーザー入力に対するチェックやバリデーションを実行できます。たとえば、ユーザーの入力内容が関連しているかをスクリーニングできます。詳細は [guardrails](guardrails.md) ドキュメントをご覧ください。 + +## エージェントの複製 + +`clone()` メソッドを使用すると、エージェントを複製し、必要に応じて任意のプロパティを変更できます。 + +```python +pirate_agent = Agent( + name="Pirate", + instructions="Write like a pirate", + model="o3-mini", +) + +robot_agent = pirate_agent.clone( + name="Robot", + instructions="Write like a robot", +) +``` + +## ツール使用の強制 + +ツールの一覧を渡しても、LLM が必ずツールを使用するとは限りません。[`ModelSettings.tool_choice`][agents.model_settings.ModelSettings.tool_choice] を設定することでツール使用を強制できます。有効な値は次のとおりです。 + +1. `auto` — ツールを使用するかどうかを LLM が判断します。 +2. `required` — LLM にツール使用を必須化します ( ただし使用するツールは自動選択 )。 +3. `none` — LLM にツールを使用しないことを要求します。 +4. 特定の文字列 ( 例: `my_tool` ) — その特定のツールを LLM に使用させます。 + +!!! note + + 無限ループを防ぐため、フレームワークはツール呼び出し後に `tool_choice` を自動的に "auto" にリセットします。この動作は [`agent.reset_tool_choice`][agents.agent.Agent.reset_tool_choice] で設定できます。無限ループが起こる理由は、ツールの結果が LLM に送られ、`tool_choice` により再びツール呼び出しが生成される、という流れが繰り返されるからです。 + + ツール呼び出し後にエージェントを完全に停止させたい場合 ( auto モードで続行させたくない場合 ) は、[`Agent.tool_use_behavior="stop_on_first_tool"`] を設定してください。これにより、ツールの出力を LL M の追加処理なしにそのまま最終応答として返します。 \ No newline at end of file diff --git a/docs/ja/config.md b/docs/ja/config.md new file mode 100644 index 00000000..bf76b9fb --- /dev/null +++ b/docs/ja/config.md @@ -0,0 +1,98 @@ +--- +search: + exclude: true +--- +# SDK の設定 + +## API キーとクライアント + +デフォルトでは、 SDK はインポートされた時点で LLM リクエストとトレーシングに使用する `OPENAI_API_KEY` 環境変数を探します。アプリ起動前にこの環境変数を設定できない場合は、 [set_default_openai_key()][agents.set_default_openai_key] 関数を利用してキーを設定できます。 + +```python +from agents import set_default_openai_key + +set_default_openai_key("sk-...") +``` + +また、使用する OpenAI クライアントを構成することも可能です。デフォルトでは、 SDK は環境変数または上記で設定したデフォルトキーを用いて `AsyncOpenAI` インスタンスを作成します。これを変更するには、 [set_default_openai_client()][agents.set_default_openai_client] 関数を使用します。 + +```python +from openai import AsyncOpenAI +from agents import set_default_openai_client + +custom_client = AsyncOpenAI(base_url="...", api_key="...") +set_default_openai_client(custom_client) +``` + +さらに、使用する OpenAI API をカスタマイズすることもできます。既定では OpenAI Responses API を利用します。これを Chat Completions API に変更するには、 [set_default_openai_api()][agents.set_default_openai_api] 関数を使用してください。 + +```python +from agents import set_default_openai_api + +set_default_openai_api("chat_completions") +``` + +## トレーシング + +トレーシングはデフォルトで有効になっています。前述の OpenAI API キー（環境変数または設定したデフォルトキー）が自動的に使用されます。トレーシングで使用する API キーを個別に設定したい場合は、 [`set_tracing_export_api_key`][agents.set_tracing_export_api_key] 関数を利用してください。 + +```python +from agents import set_tracing_export_api_key + +set_tracing_export_api_key("sk-...") +``` + +トレーシングを完全に無効化するには、 [`set_tracing_disabled()`][agents.set_tracing_disabled] 関数を呼び出します。 + +```python +from agents import set_tracing_disabled + +set_tracing_disabled(True) +``` + +## デバッグログ + + SDK にはハンドラーが設定されていない Python ロガーが 2 つあります。デフォルトでは、警告とエラーは `stdout` に出力されますが、それ以外のログは抑制されます。 + +詳細なログを有効にするには、 [`enable_verbose_stdout_logging()`][agents.enable_verbose_stdout_logging] 関数を使用します。 + +```python +from agents import enable_verbose_stdout_logging + +enable_verbose_stdout_logging() +``` + +必要に応じて、ハンドラー、フィルター、フォーマッターなどを追加してログをカスタマイズすることも可能です。詳しくは [Python ロギングガイド](https://docs.python.org/3/howto/logging.html) を参照してください。 + +```python +import logging + +logger = logging.getLogger("openai.agents") # or openai.agents.tracing for the Tracing logger + +# To make all logs show up +logger.setLevel(logging.DEBUG) +# To make info and above show up +logger.setLevel(logging.INFO) +# To make warning and above show up +logger.setLevel(logging.WARNING) +# etc + +# You can customize this as needed, but this will output to `stderr` by default +logger.addHandler(logging.StreamHandler()) +``` + +### ログに含まれる機微情報 + +特定のログには機微情報（たとえば ユーザー データ）が含まれる場合があります。この情報が記録されるのを防ぎたい場合は、次の環境変数を設定してください。 + +LLM の入力および出力のログを無効にする: + +```bash +export OPENAI_AGENTS_DONT_LOG_MODEL_DATA=1 +``` + +ツールの入力および出力のログを無効にする: + +```bash +export OPENAI_AGENTS_DONT_LOG_TOOL_DATA=1 +``` \ No newline at end of file diff --git a/docs/ja/context.md b/docs/ja/context.md new file mode 100644 index 00000000..72c0938c --- /dev/null +++ b/docs/ja/context.md @@ -0,0 +1,81 @@ +--- +search: + exclude: true +--- +# コンテキスト管理 + +コンテキストという言葉には複数の意味があります。ここでは主に 2 つのコンテキストについて説明します。 + +1. コード内でローカルに利用できるコンテキスト: ツール関数の実行時や `on_handoff` などのコールバック、ライフサイクルフックで必要となるデータや依存関係です。 +2. LLM が参照できるコンテキスト: LLM がレスポンスを生成する際に見えるデータです。 + +## ローカルコンテキスト + +ローカルコンテキストは [`RunContextWrapper`][agents.run_context.RunContextWrapper] クラスと、その中の [`context`][agents.run_context.RunContextWrapper.context] プロパティで表現されます。仕組みは次のとおりです。 + +1. 任意の Python オブジェクトを作成します。一般的なパターンとして dataclass や Pydantic オブジェクトを使用します。 +2. そのオブジェクトを各種 run メソッド（例: `Runner.run(..., **context=whatever** )`）に渡します。 +3. すべてのツール呼び出しやライフサイクルフックには、ラッパーオブジェクト `RunContextWrapper[T]` が渡されます。ここで `T` はコンテキストオブジェクトの型で、`wrapper.context` からアクセスできます。 + +**最重要ポイント**: あるエージェントの実行において、エージェント・ツール関数・ライフサイクルフックなどはすべて同じ _型_ のコンテキストを使用しなければなりません。 + +コンテキストでは次のような用途が考えられます。 + +- 実行に関するデータ（例: ユーザー名 / uid やその他のユーザー情報） +- 依存オブジェクト（例: ロガー、データフェッチャーなど） +- ヘルパー関数 + +!!! danger "Note" + + コンテキストオブジェクトは LLM には送信されません。あくまでローカルのオブジェクトであり、読み書きやメソッド呼び出しが可能です。 + +```python +import asyncio +from dataclasses import dataclass + +from agents import Agent, RunContextWrapper, Runner, function_tool + +@dataclass +class UserInfo: # (1)! + name: str + uid: int + +@function_tool +async def fetch_user_age(wrapper: RunContextWrapper[UserInfo]) -> str: # (2)! + return f"User {wrapper.context.name} is 47 years old" + +async def main(): + user_info = UserInfo(name="John", uid=123) + + agent = Agent[UserInfo]( # (3)! + name="Assistant", + tools=[fetch_user_age], + ) + + result = await Runner.run( # (4)! + starting_agent=agent, + input="What is the age of the user?", + context=user_info, + ) + + print(result.final_output) # (5)! + # The user John is 47 years old. + +if __name__ == "__main__": + asyncio.run(main()) +``` + +1. これがコンテキストオブジェクトです。ここでは dataclass を使っていますが、任意の型を使用できます。 +2. これはツールです。`RunContextWrapper[UserInfo]` を受け取り、実装内でコンテキストを参照しています。 +3. エージェントにジェネリック `UserInfo` を付与することで、型チェッカーが誤りを検出できます（たとえば別のコンテキスト型を受け取るツールを渡した場合など）。 +4. `run` 関数にコンテキストを渡します。 +5. エージェントはツールを正しく呼び出し、年齢を取得します。 + +## エージェント / LLM コンテキスト + +LLM が呼び出されるとき、LLM が参照できるデータは会話履歴に含まれるものだけです。したがって、新しいデータを LLM に渡したい場合は、そのデータを履歴に含める形で提供する必要があります。方法はいくつかあります。 + +1. Agent の `instructions` に追加する。いわゆる「system prompt」や「developer message」と呼ばれるものです。システムプロンプトは静的な文字列でも、コンテキストを受け取って文字列を返す動的な関数でも構いません。ユーザー名や現在の日付など、常に有用な情報を渡す際によく使われます。 +2. `Runner.run` 呼び出し時の `input` に追加する。`instructions` と似ていますが、[chain of command](https://cdn.openai.com/spec/model-spec-2024-05-08.html#follow-the-chain-of-command) の下位レイヤーにメッセージを配置できます。 +3. 関数ツール経由で公開する。オンデマンドで取得するコンテキストに適しており、LLM が必要に応じてツールを呼び出してデータを取得します。 +4. retrieval や web search を使う。これらは特別なツールで、ファイルやデータベースから関連データを取得する（retrieval）、もしくは Web から取得する（web search）ことができます。レスポンスを関連コンテキストで「グラウンディング」するのに有効です。 \ No newline at end of file diff --git a/docs/ja/examples.md b/docs/ja/examples.md new file mode 100644 index 00000000..00f634ec --- /dev/null +++ b/docs/ja/examples.md @@ -0,0 +1,45 @@ +--- +search: + exclude: true +--- +# コード例 + +リポジトリの [examples セクション](https://github.com/openai/openai-agents-python/tree/main/examples) には、 SDK のさまざまなサンプル実装が用意されています。これらの例は、異なるパターンや機能を示す複数のカテゴリーに整理されています。 + + +## カテゴリー + +- **[agent_patterns](https://github.com/openai/openai-agents-python/tree/main/examples/agent_patterns):** + このカテゴリーの例では、一般的なエージェント設計パターンを紹介しています。 + + - 決定論的ワークフロー + - ツールとしてのエージェント + - エージェントの並列実行 + +- **[basic](https://github.com/openai/openai-agents-python/tree/main/examples/basic):** + SDK の基礎的な機能を示す例です。 + + - 動的なシステムプロンプト + - ストリーミング出力 + - ライフサイクルイベント + +- **[tool examples](https://github.com/openai/openai-agents-python/tree/main/examples/tools):** + Web 検索やファイル検索など、 OpenAI がホストするツールの実装方法と、それらをエージェントに統合する方法を学べます。 + +- **[model providers](https://github.com/openai/openai-agents-python/tree/main/examples/model_providers):** + OpenAI 以外のモデルを SDK で利用する方法を探ります。 + +- **[handoffs](https://github.com/openai/openai-agents-python/tree/main/examples/handoffs):** + エージェントのハンドオフを実践的に示す例です。 + +- **[mcp](https://github.com/openai/openai-agents-python/tree/main/examples/mcp):** + MCP を使ったエージェントの構築方法を学べます。 + +- **[customer_service](https://github.com/openai/openai-agents-python/tree/main/examples/customer_service)** と **[research_bot](https://github.com/openai/openai-agents-python/tree/main/examples/research_bot):** + より実践的なユースケースを示す、拡張された 2 つの例です。 + + - **customer_service**: 航空会社向けカスタマーサービスシステムの例 + - **research_bot**: シンプルなディープリサーチクローン + +- **[voice](https://github.com/openai/openai-agents-python/tree/main/examples/voice):** + TTS と STT モデルを用いた音声エージェントの例をご覧ください。 \ No newline at end of file diff --git a/docs/ja/guardrails.md b/docs/ja/guardrails.md new file mode 100644 index 00000000..e7b02a6e --- /dev/null +++ b/docs/ja/guardrails.md @@ -0,0 +1,158 @@ +--- +search: + exclude: true +--- +# ガードレール + +ガードレールは エージェント と _並列_ に実行され、 ユーザー入力 のチェックとバリデーションを行います。たとえば、顧客からのリクエストを支援するために非常に賢い (そのため遅く / 高価な) モデルを使うエージェントがあるとします。悪意のある ユーザー がモデルに数学の宿題を手伝わせようとするのは避けたいですよね。その場合、 高速 / 低コスト のモデルでガードレールを実行できます。ガードレールが悪意のある利用を検知した場合、即座にエラーを送出して高価なモデルの実行を停止し、時間と費用を節約できます。 + +ガードレールには 2 種類あります。 + +1. Input ガードレールは最初の ユーザー入力 に対して実行されます +2. Output ガードレールは最終的なエージェント出力に対して実行されます + +## Input ガードレール + +Input ガードレールは 3 つのステップで実行されます。 + +1. まず、ガードレールはエージェントに渡されたものと同じ入力を受け取ります。 +2. 次に、ガードレール関数が実行され [`GuardrailFunctionOutput`][agents.guardrail.GuardrailFunctionOutput] を生成し、それが [`InputGuardrailResult`][agents.guardrail.InputGuardrailResult] でラップされます。 +3. 最後に [`.tripwire_triggered`][agents.guardrail.GuardrailFunctionOutput.tripwire_triggered] が true かどうかを確認します。true の場合、[`InputGuardrailTripwireTriggered`][agents.exceptions.InputGuardrailTripwireTriggered] 例外が送出されるので、 ユーザー への適切な応答や例外処理を行えます。 + +!!! Note + + Input ガードレールは ユーザー入力 に対して実行されることを想定しているため、エージェントのガードレールが実行されるのはそのエージェントが *最初* のエージェントである場合だけです。「なぜ `guardrails` プロパティがエージェントにあり、 `Runner.run` に渡さないのか？」と思うかもしれません。ガードレールは実際の エージェント に密接に関連する場合が多く、エージェントごとに異なるガードレールを実行するため、コードを同じ場所に置くことで可読性が向上するからです。 + +## Output ガードレール + +Output ガードレールは 3 つのステップで実行されます。 + +1. まず、ガードレールはエージェントに渡されたものと同じ入力を受け取ります。 +2. 次に、ガードレール関数が実行され [`GuardrailFunctionOutput`][agents.guardrail.GuardrailFunctionOutput] を生成し、それが [`OutputGuardrailResult`][agents.guardrail.OutputGuardrailResult] でラップされます。 +3. 最後に [`.tripwire_triggered`][agents.guardrail.GuardrailFunctionOutput.tripwire_triggered] が true かどうかを確認します。true の場合、[`OutputGuardrailTripwireTriggered`][agents.exceptions.OutputGuardrailTripwireTriggered] 例外が送出されるので、 ユーザー への適切な応答や例外処理を行えます。 + +!!! Note + + Output ガードレールは最終的なエージェント出力に対して実行されることを想定しているため、エージェントのガードレールが実行されるのはそのエージェントが *最後* のエージェントである場合だけです。Input ガードレール同様、ガードレールは実際の エージェント に密接に関連するため、コードを同じ場所に置くことで可読性が向上します。 + +## トリップワイヤ + +入力または出力がガードレールに失敗した場合、ガードレールはトリップワイヤを用いてそれを通知できます。ガードレールがトリップワイヤを発火したことを検知すると、ただちに `{Input,Output}GuardrailTripwireTriggered` 例外を送出してエージェントの実行を停止します。 + +## ガードレールの実装 + +入力を受け取り、[`GuardrailFunctionOutput`][agents.guardrail.GuardrailFunctionOutput] を返す関数を用意する必要があります。次の例では、内部で エージェント を実行してこれを行います。 + +```python +from pydantic import BaseModel +from agents import ( + Agent, + GuardrailFunctionOutput, + InputGuardrailTripwireTriggered, + RunContextWrapper, + Runner, + TResponseInputItem, + input_guardrail, +) + +class MathHomeworkOutput(BaseModel): + is_math_homework: bool + reasoning: str + +guardrail_agent = Agent( # (1)! + name="Guardrail check", + instructions="Check if the user is asking you to do their math homework.", + output_type=MathHomeworkOutput, +) + + +@input_guardrail +async def math_guardrail( # (2)! + ctx: RunContextWrapper[None], agent: Agent, input: str | list[TResponseInputItem] +) -> GuardrailFunctionOutput: + result = await Runner.run(guardrail_agent, input, context=ctx.context) + + return GuardrailFunctionOutput( + output_info=result.final_output, # (3)! + tripwire_triggered=result.final_output.is_math_homework, + ) + + +agent = Agent( # (4)! + name="Customer support agent", + instructions="You are a customer support agent. You help customers with their questions.", + input_guardrails=[math_guardrail], +) + +async def main(): + # This should trip the guardrail + try: + await Runner.run(agent, "Hello, can you help me solve for x: 2x + 3 = 11?") + print("Guardrail didn't trip - this is unexpected") + + except InputGuardrailTripwireTriggered: + print("Math homework guardrail tripped") +``` + +1. この エージェント をガードレール関数内で使用します。 +2. これはエージェントの入力 / コンテキストを受け取り、結果を返すガードレール関数です。 +3. ガードレール結果に追加情報を含めることができます。 +4. これはワークフローを定義する実際のエージェントです。 + +Output ガードレールも同様です。 + +```python +from pydantic import BaseModel +from agents import ( + Agent, + GuardrailFunctionOutput, + OutputGuardrailTripwireTriggered, + RunContextWrapper, + Runner, + output_guardrail, +) +class MessageOutput(BaseModel): # (1)! + response: str + +class MathOutput(BaseModel): # (2)! + reasoning: str + is_math: bool + +guardrail_agent = Agent( + name="Guardrail check", + instructions="Check if the output includes any math.", + output_type=MathOutput, +) + +@output_guardrail +async def math_guardrail( # (3)! + ctx: RunContextWrapper, agent: Agent, output: MessageOutput +) -> GuardrailFunctionOutput: + result = await Runner.run(guardrail_agent, output.response, context=ctx.context) + + return GuardrailFunctionOutput( + output_info=result.final_output, + tripwire_triggered=result.final_output.is_math, + ) + +agent = Agent( # (4)! + name="Customer support agent", + instructions="You are a customer support agent. You help customers with their questions.", + output_guardrails=[math_guardrail], + output_type=MessageOutput, +) + +async def main(): + # This should trip the guardrail + try: + await Runner.run(agent, "Hello, can you help me solve for x: 2x + 3 = 11?") + print("Guardrail didn't trip - this is unexpected") + + except OutputGuardrailTripwireTriggered: + print("Math output guardrail tripped") +``` + +1. これは実際のエージェントの出力型です。 +2. これはガードレールの出力型です。 +3. これはエージェントの出力を受け取り、結果を返すガードレール関数です。 +4. これはワークフローを定義する実際のエージェントです。 \ No newline at end of file diff --git a/docs/ja/handoffs.md b/docs/ja/handoffs.md new file mode 100644 index 00000000..c0e99556 --- /dev/null +++ b/docs/ja/handoffs.md @@ -0,0 +1,117 @@ +--- +search: + exclude: true +--- +# ハンドオフ + +ハンドオフを使用すると、エージェント がタスクを別の エージェント に委譲できます。これは、複数の エージェント がそれぞれ異なる分野を専門とするシナリオで特に便利です。たとえばカスタマーサポートアプリでは、注文状況、返金、 FAQ などのタスクを個別に担当する エージェント を用意できます。 + +ハンドオフは LLM からはツールとして認識されます。そのため、`Refund Agent` という エージェント へのハンドオフであれば、ツール名は `transfer_to_refund_agent` になります。 + +## ハンドオフの作成 + +すべての エージェント には [`handoffs`][agents.agent.Agent.handoffs] パラメーターがあり、直接 `Agent` を渡すことも、ハンドオフをカスタマイズする `Handoff` オブジェクトを渡すこともできます。 + +Agents SDK が提供する [`handoff()`][agents.handoffs.handoff] 関数を使ってハンドオフを作成できます。この関数では、引き継ぎ先の エージェント を指定し、オーバーライドや入力フィルターをオプションで設定できます。 + +### 基本的な使い方 + +シンプルなハンドオフを作成する例を示します。 + +```python +from agents import Agent, handoff + +billing_agent = Agent(name="Billing agent") +refund_agent = Agent(name="Refund agent") + +# (1)! +triage_agent = Agent(name="Triage agent", handoffs=[billing_agent, handoff(refund_agent)]) +``` + +1. `billing_agent` のように エージェント を直接指定することも、`handoff()` 関数を使用することもできます。 + +### `handoff()` 関数によるハンドオフのカスタマイズ + +[`handoff()`][agents.handoffs.handoff] 関数を使うと、ハンドオフを細かくカスタマイズできます。 + +- `agent`: ここで指定した エージェント に処理が引き渡されます。 +- `tool_name_override`: デフォルトでは `Handoff.default_tool_name()` が使用され、`transfer_to_` という名前になります。これを上書きできます。 +- `tool_description_override`: `Handoff.default_tool_description()` が返すデフォルトのツール説明を上書きします。 +- `on_handoff`: ハンドオフ実行時に呼び出されるコールバック関数です。ハンドオフが呼ばれたタイミングでデータ取得を開始するなどに便利です。この関数は エージェント のコンテキストを受け取り、オプションで LLM が生成した入力も受け取れます。渡されるデータは `input_type` パラメーターで制御します。 +- `input_type`: ハンドオフが受け取る入力の型（任意）。 +- `input_filter`: 次の エージェント が受け取る入力をフィルタリングできます。詳細は後述します。 + +```python +from agents import Agent, handoff, RunContextWrapper + +def on_handoff(ctx: RunContextWrapper[None]): + print("Handoff called") + +agent = Agent(name="My agent") + +handoff_obj = handoff( + agent=agent, + on_handoff=on_handoff, + tool_name_override="custom_handoff_tool", + tool_description_override="Custom description", +) +``` + +## ハンドオフ入力 + +場合によっては、 LLM がハンドオフを呼び出す際に追加のデータを渡してほしいことがあります。たとえば「Escalation エージェント」へのハンドオフでは、ログ用に理由を渡してもらいたいかもしれません。 + +```python +from pydantic import BaseModel + +from agents import Agent, handoff, RunContextWrapper + +class EscalationData(BaseModel): + reason: str + +async def on_handoff(ctx: RunContextWrapper[None], input_data: EscalationData): + print(f"Escalation agent called with reason: {input_data.reason}") + +agent = Agent(name="Escalation agent") + +handoff_obj = handoff( + agent=agent, + on_handoff=on_handoff, + input_type=EscalationData, +) +``` + +## 入力フィルター + +ハンドオフが発生すると、新しい エージェント が会話を引き継ぎ、これまでの会話履歴全体を閲覧できる状態になります。これを変更したい場合は [`input_filter`][agents.handoffs.Handoff.input_filter] を設定してください。入力フィルターは、[`HandoffInputData`][agents.handoffs.HandoffInputData] として渡される既存の入力を受け取り、新しい `HandoffInputData` を返す関数です。 + +よくあるパターン（たとえば履歴からすべてのツール呼び出しを削除するなど）は [`agents.extensions.handoff_filters`][] に実装済みです。 + +```python +from agents import Agent, handoff +from agents.extensions import handoff_filters + +agent = Agent(name="FAQ agent") + +handoff_obj = handoff( + agent=agent, + input_filter=handoff_filters.remove_all_tools, # (1)! +) +``` + +1. これにより `FAQ agent` が呼ばれた際に、履歴からすべてのツール呼び出しが自動で削除されます。 + +## 推奨プロンプト + +LLM がハンドオフを正しく理解できるよう、エージェント にハンドオフに関する情報を含めることを推奨します。事前に用意したプレフィックス [`agents.extensions.handoff_prompt.RECOMMENDED_PROMPT_PREFIX`][] を利用するか、[`agents.extensions.handoff_prompt.prompt_with_handoff_instructions`][] を呼び出してプロンプトに推奨情報を自動で追加できます。 + +```python +from agents import Agent +from agents.extensions.handoff_prompt import RECOMMENDED_PROMPT_PREFIX + +billing_agent = Agent( + name="Billing agent", + instructions=f"""{RECOMMENDED_PROMPT_PREFIX} + .""", +) +``` \ No newline at end of file diff --git a/docs/ja/index.md b/docs/ja/index.md new file mode 100644 index 00000000..39692a16 --- /dev/null +++ b/docs/ja/index.md @@ -0,0 +1,56 @@ +--- +search: + exclude: true +--- +# OpenAI Agents SDK + +[OpenAI Agents SDK](https://github.com/openai/openai-agents-python) は、抽象化をほとんど排した軽量で使いやすいパッケージにより、エージェントベースの AI アプリを構築できるようにします。これは、以前のエージェント向け実験プロジェクトである [Swarm](https://github.com/openai/swarm/tree/main) をプロダクションレベルへとアップグレードしたものです。Agents SDK にはごく少数の基本コンポーネントがあります。 + +- **エージェント**: instructions と tools を備えた LLM +- **ハンドオフ**: エージェントが特定タスクを他のエージェントへ委任するしくみ +- **ガードレール**: エージェントへの入力を検証する機能 + +Python と組み合わせることで、これらのコンポーネントはツールとエージェント間の複雑な関係を表現でき、学習コストを抑えつつ実際のアプリケーションを構築できます。さらに SDK には、エージェントフローを可視化・デバッグできる **トレーシング** が標準搭載されており、評価やファインチューニングにも活用可能です。 + +## Agents SDK を使用する理由 + +SDK には 2 つの設計原則があります。 + +1. 使う価値のある十分な機能を備えつつ、学習が早いようコンポーネント数を絞る。 +2. すぐに使い始められる初期設定で動作しつつ、挙動を細かくカスタマイズできる。 + +主な機能は次のとおりです。 + +- エージェントループ: ツール呼び出し、結果を LLM に送信、LLM が完了するまでのループを自動で処理。 +- Python ファースト: 新しい抽象化を学ばずに、言語標準機能でエージェントをオーケストレーション。 +- ハンドオフ: 複数エージェント間の協調と委譲を実現する強力な機能。 +- ガードレール: エージェントと並列で入力バリデーションを実行し、失敗時に早期終了。 +- 関数ツール: 任意の Python 関数をツール化し、自動スキーマ生成と Pydantic での検証を提供。 +- トレーシング: フローの可視化・デバッグ・モニタリングに加え、OpenAI の評価・ファインチューニング・蒸留ツールを利用可能。 + +## インストール + +```bash +pip install openai-agents +``` + +## Hello World の例 + +```python +from agents import Agent, Runner + +agent = Agent(name="Assistant", instructions="You are a helpful assistant") + +result = Runner.run_sync(agent, "Write a haiku about recursion in programming.") +print(result.final_output) + +# Code within the code, +# Functions calling themselves, +# Infinite loop's dance. +``` + +(_これを実行する場合は、`OPENAI_API_KEY` 環境変数を設定してください_) + +```bash +export OPENAI_API_KEY=sk-... +``` \ No newline at end of file diff --git a/docs/ja/mcp.md b/docs/ja/mcp.md new file mode 100644 index 00000000..7cdaa57e --- /dev/null +++ b/docs/ja/mcp.md @@ -0,0 +1,64 @@ +--- +search: + exclude: true +--- +# Model context protocol (MCP) + +[Model context protocol](https://modelcontextprotocol.io/introduction)（通称 MCP）は、 LLM にツールとコンテキストを提供するための仕組みです。MCP のドキュメントでは次のように説明されています。 + +> MCP は、アプリケーションが LLM にコンテキストを提供する方法を標準化するオープンプロトコルです。MCP は AI アプリケーションにとっての USB‑C ポートのようなものと考えてください。USB‑C が各種デバイスを周辺機器と接続するための標準化された方法を提供するのと同様に、MCP は AI モデルをさまざまなデータソースやツールと接続するための標準化された方法を提供します。 + +Agents SDK は MCP をサポートしており、これにより幅広い MCP サーバーをエージェントにツールとして追加できます。 + +## MCP サーバー + +現在、MCP 仕様では使用するトランスポート方式に基づき 2 種類のサーバーが定義されています。 + +1. **stdio** サーバー: アプリケーションのサブプロセスとして実行されます。ローカルで動かすイメージです。 +2. **HTTP over SSE** サーバー: リモートで動作し、 URL 経由で接続します。 + +これらのサーバーへは [`MCPServerStdio`][agents.mcp.server.MCPServerStdio] と [`MCPServerSse`][agents.mcp.server.MCPServerSse] クラスを使用して接続できます。 + +たとえば、[公式 MCP filesystem サーバー](https://www.npmjs.com/package/@modelcontextprotocol/server-filesystem)を利用する場合は次のようになります。 + +```python +async with MCPServerStdio( + params={ + "command": "npx", + "args": ["-y", "@modelcontextprotocol/server-filesystem", samples_dir], + } +) as server: + tools = await server.list_tools() +``` + +## MCP サーバーの利用 + +MCP サーバーはエージェントに追加できます。Agents SDK はエージェント実行時に毎回 MCP サーバーへ `list_tools()` を呼び出し、 LLM に MCP サーバーのツールを認識させます。LLM が MCP サーバーのツールを呼び出すと、SDK はそのサーバーへ `call_tool()` を実行します。 + +```python + +agent=Agent( + name="Assistant", + instructions="Use the tools to achieve the task", + mcp_servers=[mcp_server_1, mcp_server_2] +) +``` + +## キャッシュ + +エージェントが実行されるたびに、MCP サーバーへ `list_tools()` が呼び出されます。サーバーがリモートの場合は特にレイテンシが発生します。ツール一覧を自動でキャッシュしたい場合は、[`MCPServerStdio`][agents.mcp.server.MCPServerStdio] と [`MCPServerSse`][agents.mcp.server.MCPServerSse] の両方に `cache_tools_list=True` を渡してください。ツール一覧が変更されないと確信できる場合のみ使用してください。 + +キャッシュを無効化したい場合は、サーバーで `invalidate_tools_cache()` を呼び出します。 + +## エンドツーエンドのコード例 + +完全な動作例は [examples/mcp](https://github.com/openai/openai-agents-python/tree/main/examples/mcp) をご覧ください。 + +## トレーシング + +[トレーシング](./tracing.md) は MCP の操作を自動的にキャプチャします。具体的には次の内容が含まれます。 + +1. ツール一覧取得のための MCP サーバー呼び出し +2. 関数呼び出しに関する MCP 情報 + +![MCP Tracing Screenshot](../assets/images/mcp-tracing.jpg) \ No newline at end of file diff --git a/docs/ja/models.md b/docs/ja/models.md new file mode 100644 index 00000000..5a76d60e --- /dev/null +++ b/docs/ja/models.md @@ -0,0 +1,106 @@ +# モデル + +Agents SDK には、OpenAI モデルの 2 種類のサポートが標準で用意されています。 + +- **推奨**: [`OpenAIResponsesModel`][agents.models.openai_responses.OpenAIResponsesModel] は、新しい [Responses API](https://platform.openai.com/docs/api-reference/responses) を使って OpenAI API を呼び出します。 +- [`OpenAIChatCompletionsModel`][agents.models.openai_chatcompletions.OpenAIChatCompletionsModel] は、[Chat Completions API](https://platform.openai.com/docs/api-reference/chat) を使って OpenAI API を呼び出します。 + +## モデルの組み合わせ + +1 つのワークフロー内で、各エージェントごとに異なるモデルを使いたい場合があります。たとえば、トリアージには小型で高速なモデルを使い、複雑なタスクにはより大きく高性能なモデルを使うことができます。[`Agent`][agents.Agent] を設定する際、以下のいずれかの方法で特定のモデルを選択できます。 + +1. OpenAI モデル名を直接渡す。 +2. 任意のモデル名と、その名前を Model インスタンスにマッピングできる [`ModelProvider`][agents.models.interface.ModelProvider] を渡す。 +3. [`Model`][agents.models.interface.Model] 実装を直接指定する。 + +!!!note + + SDK は [`OpenAIResponsesModel`][agents.models.openai_responses.OpenAIResponsesModel] と [`OpenAIChatCompletionsModel`][agents.models.openai_chatcompletions.OpenAIChatCompletionsModel] の両方の形状をサポートしていますが、各ワークフローで 1 つのモデル形状のみを使うことを推奨します。なぜなら、2 つの形状はサポートする機能やツールが異なるためです。ワークフローでモデル形状を組み合わせて使う場合は、利用するすべての機能が両方で利用可能かご確認ください。 + +```python +from agents import Agent, Runner, AsyncOpenAI, OpenAIChatCompletionsModel +import asyncio + +spanish_agent = Agent( + name="Spanish agent", + instructions="You only speak Spanish.", + model="o3-mini", # (1)! +) + +english_agent = Agent( + name="English agent", + instructions="You only speak English", + model=OpenAIChatCompletionsModel( # (2)! + model="gpt-4o", + openai_client=AsyncOpenAI() + ), +) + +triage_agent = Agent( + name="Triage agent", + instructions="Handoff to the appropriate agent based on the language of the request.", + handoffs=[spanish_agent, english_agent], + model="gpt-3.5-turbo", +) + +async def main(): + result = await Runner.run(triage_agent, input="Hola, ¿cómo estás?") + print(result.final_output) +``` + +1. OpenAI モデル名を直接設定します。 +2. [`Model`][agents.models.interface.Model] 実装を指定します。 + +エージェントで使用するモデルをさらに細かく設定したい場合は、[`ModelSettings`][agents.models.interface.ModelSettings] を渡すことができます。これにより、temperature などのオプションのモデル設定パラメーターを指定できます。 + +```python +from agents import Agent, ModelSettings + +english_agent = Agent( + name="English agent", + instructions="You only speak English", + model="gpt-4o", + model_settings=ModelSettings(temperature=0.1), +) +``` + +## 他の LLM プロバイダーの利用 + +他の LLM プロバイダーは、3 つの方法で利用できます（[こちら](https://github.com/openai/openai-agents-python/tree/main/examples/model_providers/) に code examples があります）。 + +1. [`set_default_openai_client`][agents.set_default_openai_client] は、`AsyncOpenAI` のインスタンスを LLM クライアントとしてグローバルに利用したい場合に便利です。これは、LLM プロバイダーが OpenAI 互換の API エンドポイントを持ち、`base_url` と `api_key` を設定できる場合に使います。[examples/model_providers/custom_example_global.py](https://github.com/openai/openai-agents-python/tree/main/examples/model_providers/custom_example_global.py) に設定例があります。 +2. [`ModelProvider`][agents.models.interface.ModelProvider] は `Runner.run` レベルで利用します。これにより、「この実行のすべてのエージェントでカスタムモデルプロバイダーを使う」と指定できます。[examples/model_providers/custom_example_provider.py](https://github.com/openai/openai-agents-python/tree/main/examples/model_providers/custom_example_provider.py) に設定例があります。 +3. [`Agent.model`][agents.agent.Agent.model] で、特定のエージェントインスタンスにモデルを指定できます。これにより、エージェントごとに異なるプロバイダーを組み合わせて使うことができます。[examples/model_providers/custom_example_agent.py](https://github.com/openai/openai-agents-python/tree/main/examples/model_providers/custom_example_agent.py) に設定例があります。 + +`platform.openai.com` の API キーがない場合は、`set_tracing_disabled()` でトレーシングを無効にするか、[別のトレーシングプロセッサー](tracing.md) を設定することを推奨します。 + +!!! note + + これらの code examples では Chat Completions API/モデルを使っています。なぜなら、ほとんどの LLM プロバイダーはまだ Responses API をサポートしていないためです。もし LLM プロバイダーが Responses API をサポートしている場合は、Responses の利用を推奨します。 + +## 他の LLM プロバイダー利用時のよくある問題 + +### Tracing クライアントの 401 エラー + +トレーシングに関連するエラーが発生した場合、これはトレースが OpenAI サーバーにアップロードされるため、OpenAI API キーがないことが原因です。解決方法は 3 つあります。 + +1. トレーシングを完全に無効化する: [`set_tracing_disabled(True)`][agents.set_tracing_disabled]。 +2. トレーシング用の OpenAI キーを設定する: [`set_tracing_export_api_key(...)`][agents.set_tracing_export_api_key]。この API キーはトレースのアップロードのみに使われ、[platform.openai.com](https://platform.openai.com/) のものが必要です。 +3. OpenAI 以外のトレースプロセッサーを使う。[トレーシングのドキュメント](tracing.md#custom-tracing-processors) をご覧ください。 + +### Responses API サポート + +SDK はデフォルトで Responses API を使いますが、ほとんどの他の LLM プロバイダーはまだ対応していません。そのため、404 エラーなどが発生する場合があります。解決方法は 2 つあります。 + +1. [`set_default_openai_api("chat_completions")`][agents.set_default_openai_api] を呼び出します。これは、環境変数で `OPENAI_API_KEY` と `OPENAI_BASE_URL` を設定している場合に有効です。 +2. [`OpenAIChatCompletionsModel`][agents.models.openai_chatcompletions.OpenAIChatCompletionsModel] を使います。[こちら](https://github.com/openai/openai-agents-python/tree/main/examples/model_providers/) に code examples があります。 + +### structured outputs サポート + +一部のモデルプロバイダーは [structured outputs](https://platform.openai.com/docs/guides/structured-outputs) をサポートしていません。その場合、次のようなエラーが発生することがあります。 + +``` +BadRequestError: Error code: 400 - {'error': {'message': "'response_format.type' : value is not one of the allowed values ['text','json_object']", 'type': 'invalid_request_error'}} +``` + +これは一部のモデルプロバイダーの制限で、JSON 出力には対応していても、出力に使う `json_schema` を指定できない場合があります。現在この問題の修正に取り組んでいますが、JSON schema 出力をサポートしているプロバイダーの利用を推奨します。そうでない場合、不正な JSON によりアプリが頻繁に動作しなくなる可能性があります。 \ No newline at end of file diff --git a/docs/ja/models/index.md b/docs/ja/models/index.md new file mode 100644 index 00000000..a40ae38f --- /dev/null +++ b/docs/ja/models/index.md @@ -0,0 +1,116 @@ +--- +search: + exclude: true +--- +# モデル + +Agents SDK には、標準で 2 種類の OpenAI モデルサポートが含まれています。 + +- **推奨**: [`OpenAIResponsesModel`][agents.models.openai_responses.OpenAIResponsesModel] — 新しい [Responses API](https://platform.openai.com/docs/api-reference/responses) を利用して OpenAI API を呼び出します。 +- [`OpenAIChatCompletionsModel`][agents.models.openai_chatcompletions.OpenAIChatCompletionsModel] — [Chat Completions API](https://platform.openai.com/docs/api-reference/chat) を利用して OpenAI API を呼び出します。 + +## モデルの組み合わせ + +1 つのワークフロー内で、エージェントごとに異なるモデルを使用したい場合があります。たとえば、振り分けには小さく高速なモデルを、複雑なタスクには大きく高性能なモデルを使う、といった使い分けです。[`Agent`][agents.Agent] を設定する際は、以下のいずれかで特定のモデルを指定できます。 + +1. OpenAI モデル名を直接渡す +2. 任意のモデル名と、それを `Model` インスタンスへマッピングできる [`ModelProvider`][agents.models.interface.ModelProvider] を渡す +3. [`Model`][agents.models.interface.Model] 実装を直接渡す + +!!!note + SDK は [`OpenAIResponsesModel`][agents.models.openai_responses.OpenAIResponsesModel] と [`OpenAIChatCompletionsModel`][agents.models.openai_chatcompletions.OpenAIChatCompletionsModel] の両方の形に対応していますが、ワークフローごとに 1 つのモデル形を使用することを推奨します。2 つの形ではサポートする機能・ツールが異なるためです。どうしても混在させる場合は、利用するすべての機能が両方で利用可能であることを確認してください。 + +```python +from agents import Agent, Runner, AsyncOpenAI, OpenAIChatCompletionsModel +import asyncio + +spanish_agent = Agent( + name="Spanish agent", + instructions="You only speak Spanish.", + model="o3-mini", # (1)! +) + +english_agent = Agent( + name="English agent", + instructions="You only speak English", + model=OpenAIChatCompletionsModel( # (2)! + model="gpt-4o", + openai_client=AsyncOpenAI() + ), +) + +triage_agent = Agent( + name="Triage agent", + instructions="Handoff to the appropriate agent based on the language of the request.", + handoffs=[spanish_agent, english_agent], + model="gpt-3.5-turbo", +) + +async def main(): + result = await Runner.run(triage_agent, input="Hola, ¿cómo estás?") + print(result.final_output) +``` + +1. OpenAI モデル名を直接指定 +2. [`Model`][agents.models.interface.Model] 実装を提供 + +エージェントで使用するモデルをさらに細かく設定したい場合は、`temperature` などのオプションを指定できる [`ModelSettings`][agents.models.interface.ModelSettings] を渡します。 + +```python +from agents import Agent, ModelSettings + +english_agent = Agent( + name="English agent", + instructions="You only speak English", + model="gpt-4o", + model_settings=ModelSettings(temperature=0.1), +) +``` + +## 他の LLM プロバイダーの利用 + +他の LLM プロバイダーは 3 通りの方法で利用できます（コード例は [こちら](https://github.com/openai/openai-agents-python/tree/main/examples/model_providers/)）。 + +1. [`set_default_openai_client`][agents.set_default_openai_client] + OpenAI 互換の API エンドポイントを持つ場合に、`AsyncOpenAI` インスタンスをグローバルに LLM クライアントとして設定できます。`base_url` と `api_key` を設定するケースです。設定例は [examples/model_providers/custom_example_global.py](https://github.com/openai/openai-agents-python/tree/main/examples/model_providers/custom_example_global.py)。 + +2. [`ModelProvider`][agents.models.interface.ModelProvider] + `Runner.run` レベルで「この実行中のすべてのエージェントにカスタムモデルプロバイダーを使う」と宣言できます。設定例は [examples/model_providers/custom_example_provider.py](https://github.com/openai/openai-agents-python/tree/main/examples/model_providers/custom_example_provider.py)。 + +3. [`Agent.model`][agents.agent.Agent.model] + 特定の Agent インスタンスにモデルを指定できます。エージェントごとに異なるプロバイダーを組み合わせられます。設定例は [examples/model_providers/custom_example_agent.py](https://github.com/openai/openai-agents-python/tree/main/examples/model_providers/custom_example_agent.py)。多くのモデルを簡単に使う方法として [LiteLLM 連携](./litellm.md) があります。 + +`platform.openai.com` の API キーを持たない場合は、`set_tracing_disabled()` でトレーシングを無効化するか、[別のトレーシングプロセッサー](../tracing.md) を設定することを推奨します。 + +!!! note + これらの例では Chat Completions API/モデルを使用しています。多くの LLM プロバイダーがまだ Responses API をサポートしていないためです。もしプロバイダーが Responses API をサポートしている場合は、Responses の使用を推奨します。 + +## 他の LLM プロバイダーでよくある問題 + +### Tracing クライアントの 401 エラー + +トレースは OpenAI サーバーへアップロードされるため、OpenAI API キーがない場合にエラーになります。解決策は次の 3 つです。 + +1. トレーシングを完全に無効化する: [`set_tracing_disabled(True)`][agents.set_tracing_disabled] +2. トレーシング用の OpenAI キーを設定する: [`set_tracing_export_api_key(...)`][agents.set_tracing_export_api_key] + このキーはトレースのアップロードにのみ使用され、[platform.openai.com](https://platform.openai.com/) のものが必要です。 +3. OpenAI 以外のトレースプロセッサーを使う。詳しくは [tracing ドキュメント](../tracing.md#custom-tracing-processors) を参照してください。 + +### Responses API サポート + +SDK は既定で Responses API を使用しますが、多くの LLM プロバイダーはまだ対応していません。そのため 404 などのエラーが発生する場合があります。対処方法は 2 つです。 + +1. [`set_default_openai_api("chat_completions")`][agents.set_default_openai_api] を呼び出す + 環境変数 `OPENAI_API_KEY` と `OPENAI_BASE_URL` を設定している場合に機能します。 +2. [`OpenAIChatCompletionsModel`][agents.models.openai_chatcompletions.OpenAIChatCompletionsModel] を使用する + コード例は [こちら](https://github.com/openai/openai-agents-python/tree/main/examples/model_providers/) にあります。 + +### structured outputs のサポート + +一部のモデルプロバイダーは [structured outputs](https://platform.openai.com/docs/guides/structured-outputs) をサポートしていません。その場合、次のようなエラーが発生することがあります。 + +``` +BadRequestError: Error code: 400 - {'error': {'message': "'response_format.type' : value is not one of the allowed values ['text','json_object']", 'type': 'invalid_request_error'}} +``` + +これは一部プロバイダーの制限で、JSON 出力はサポートしていても `json_schema` を指定できません。現在修正に取り組んでいますが、JSON スキーマ出力をサポートしているプロバイダーを利用することを推奨します。そうでない場合、不正な JSON によりアプリが頻繁に壊れる可能性があります。 \ No newline at end of file diff --git a/docs/ja/models/litellm.md b/docs/ja/models/litellm.md new file mode 100644 index 00000000..651d7a51 --- /dev/null +++ b/docs/ja/models/litellm.md @@ -0,0 +1,77 @@ +--- +search: + exclude: true +--- +# LiteLLM 経由でのモデル利用 + +!!! note + + LiteLLM との統合は現在ベータ版です。特に小規模なモデルプロバイダーでは問題が発生する可能性があります。問題を見つけた場合は、[GitHub Issues](https://github.com/openai/openai-agents-python/issues) からご報告ください。迅速に対応いたします。 + +[LiteLLM](https://docs.litellm.ai/docs/) は、1 つのインターフェースで 100 以上のモデルを利用できるライブラリです。Agents SDK では LiteLLM との統合により、任意の AI モデルを使用できます。 + +## セットアップ + +`litellm` がインストールされていることを確認してください。オプションの `litellm` 依存関係グループをインストールすることで対応できます。 + +```bash +pip install "openai-agents[litellm]" +``` + +インストール後、任意のエージェントで [`LitellmModel`][agents.extensions.models.litellm_model.LitellmModel] を利用できます。 + +## 例 + +以下は動作する完全なサンプルです。実行するとモデル名と API キーの入力を求められます。例えば次のように入力できます。 + +- `openai/gpt-4.1` をモデル名に、OpenAI API キーを入力 +- `anthropic/claude-3-5-sonnet-20240620` をモデル名に、Anthropic API キーを入力 +- その他 + +LiteLLM でサポートされているモデルの全リストは、[litellm providers docs](https://docs.litellm.ai/docs/providers) を参照してください。 + +```python +from __future__ import annotations + +import asyncio + +from agents import Agent, Runner, function_tool, set_tracing_disabled +from agents.extensions.models.litellm_model import LitellmModel + +@function_tool +def get_weather(city: str): + print(f"[debug] getting weather for {city}") + return f"The weather in {city} is sunny." + + +async def main(model: str, api_key: str): + agent = Agent( + name="Assistant", + instructions="You only respond in haikus.", + model=LitellmModel(model=model, api_key=api_key), + tools=[get_weather], + ) + + result = await Runner.run(agent, "What's the weather in Tokyo?") + print(result.final_output) + + +if __name__ == "__main__": + # First try to get model/api key from args + import argparse + + parser = argparse.ArgumentParser() + parser.add_argument("--model", type=str, required=False) + parser.add_argument("--api-key", type=str, required=False) + args = parser.parse_args() + + model = args.model + if not model: + model = input("Enter a model name for Litellm: ") + + api_key = args.api_key + if not api_key: + api_key = input("Enter an API key for Litellm: ") + + asyncio.run(main(model, api_key)) +``` \ No newline at end of file diff --git a/docs/ja/multi_agent.md b/docs/ja/multi_agent.md new file mode 100644 index 00000000..a179fed3 --- /dev/null +++ b/docs/ja/multi_agent.md @@ -0,0 +1,41 @@ +--- +search: + exclude: true +--- +# 複数エージェントのオーケストレーション + +オーケストレーションとは、アプリ内でエージェントがどのように流れるかを指します。どのエージェントが、どの順序で実行され、その後どう決定するかを制御します。エージェントをオーケストレーションする主な方法は次の 2 つです。 + +1. LLM に判断させる: LLM の知能を活用し、計画・推論を行い、その結果に基づいて次のステップを決定します。 +2. コードでオーケストレーションする: コード側でエージェントの流れを定義します。 + +これらのパターンは組み合わせて使用できます。それぞれにトレードオフがあり、以下で説明します。 + +## LLM によるオーケストレーション + +エージェントとは、 instructions、ツール、ハンドオフを備えた LLM です。オープンエンドなタスクが与えられた場合、 LLM はタスクをどのように進めるかを自律的に計画し、ツールを使ってアクションやデータ取得を行い、ハンドオフでサブエージェントへタスクを委譲できます。たとえば、リサーチエージェントには次のようなツールを装備できます。 + +- Web 検索でオンライン情報を取得する +- ファイル検索で独自データや接続を調べる +- コンピュータ操作でコンピュータ上のアクションを実行する +- コード実行でデータ分析を行う +- 計画立案やレポート作成などに長けた専門エージェントへのハンドオフ + +このパターンはタスクがオープンエンドで、 LLM の知能に頼りたい場合に最適です。重要な戦術は次のとおりです。 + +1. 良いプロンプトに投資する。利用可能なツール、使い方、守るべきパラメーターを明確に示します。 +2. アプリを監視し、改善を繰り返す。問題が起きた箇所を特定し、プロンプトを改善します。 +3. エージェントに内省と改善を許可する。たとえばループで実行し自己批評させたり、エラーメッセージを渡して修正させたりします。 +4. 何でもこなす汎用エージェントより、特定タスクに特化したエージェントを用意します。 +5. [evals](https://platform.openai.com/docs/guides/evals) に投資する。これによりエージェントを訓練し、タスク性能を向上できます。 + +## コードによるオーケストレーション + +LLM によるオーケストレーションは強力ですが、コードでオーケストレーションすると速度・コスト・性能の面でより決定的かつ予測可能になります。よく使われるパターンは次のとおりです。 + +- [structured outputs](https://platform.openai.com/docs/guides/structured-outputs) を使って、コード側で検査できる 適切な形式のデータ を生成する。たとえばエージェントにタスクをいくつかのカテゴリーに分類させ、そのカテゴリーに応じて次のエージェントを選択します。 +- あるエージェントの出力を次のエージェントの入力に変換して複数エージェントをチェーンする。ブログ記事執筆を「リサーチ → アウトライン作成 → 記事執筆 → 批評 → 改善」という一連のステップに分解できます。 +- タスクを実行するエージェントを `while` ループで回し、評価とフィードバックを行うエージェントと組み合わせ、評価者が基準を満たしたと判断するまで繰り返します。 +- `asyncio.gather` など Python の基本コンポーネントを用いて複数エージェントを並列実行する。互いに依存しない複数タスクがある場合に高速化できます。 + +[`examples/agent_patterns`](https://github.com/openai/openai-agents-python/tree/main/examples/agent_patterns) には多数のコード例があります。 \ No newline at end of file diff --git a/docs/ja/quickstart.md b/docs/ja/quickstart.md new file mode 100644 index 00000000..30c3219d --- /dev/null +++ b/docs/ja/quickstart.md @@ -0,0 +1,193 @@ +--- +search: + exclude: true +--- +# クイックスタート + +## プロジェクトと仮想環境の作成 + +これは一度だけ行えば十分です。 + +```bash +mkdir my_project +cd my_project +python -m venv .venv +``` + +### 仮想環境の有効化 + +新しいターミナルセッションを開始するたびに実行してください。 + +```bash +source .venv/bin/activate +``` + +### Agents SDK のインストール + +```bash +pip install openai-agents # or `uv add openai-agents`, etc +``` + +### OpenAI API キーの設定 + +まだお持ちでない場合は、[こちらの手順](https://platform.openai.com/docs/quickstart#create-and-export-an-api-key)に従って OpenAI API キーを作成してください。 + +```bash +export OPENAI_API_KEY=sk-... +``` + +## 最初のエージェントの作成 + +エージェントは instructions 、名前、`model_config` などのオプション設定で定義します。 + +```python +from agents import Agent + +agent = Agent( + name="Math Tutor", + instructions="You provide help with math problems. Explain your reasoning at each step and include examples", +) +``` + +## さらにエージェントを追加 + +追加のエージェントも同様の方法で定義できます。`handoff_descriptions` はハンドオフのルーティングを判断するための追加コンテキストを提供します。 + +```python +from agents import Agent + +history_tutor_agent = Agent( + name="History Tutor", + handoff_description="Specialist agent for historical questions", + instructions="You provide assistance with historical queries. Explain important events and context clearly.", +) + +math_tutor_agent = Agent( + name="Math Tutor", + handoff_description="Specialist agent for math questions", + instructions="You provide help with math problems. Explain your reasoning at each step and include examples", +) +``` + +## ハンドオフの定義 + +各エージェントに対して、タスクを進める際に選択できるハンドオフ先の一覧を定義できます。 + +```python +triage_agent = Agent( + name="Triage Agent", + instructions="You determine which agent to use based on the user's homework question", + handoffs=[history_tutor_agent, math_tutor_agent] +) +``` + +## エージェントオーケストレーションの実行 + +ワークフローが実行され、トリアージエージェントが 2 つの専門エージェント間で正しくルーティングすることを確認しましょう。 + +```python +from agents import Runner + +async def main(): + result = await Runner.run(triage_agent, "What is the capital of France?") + print(result.final_output) +``` + +## ガードレールの追加 + +入力または出力に対して実行されるカスタムガードレールを定義できます。 + +```python +from agents import GuardrailFunctionOutput, Agent, Runner +from pydantic import BaseModel + +class HomeworkOutput(BaseModel): + is_homework: bool + reasoning: str + +guardrail_agent = Agent( + name="Guardrail check", + instructions="Check if the user is asking about homework.", + output_type=HomeworkOutput, +) + +async def homework_guardrail(ctx, agent, input_data): + result = await Runner.run(guardrail_agent, input_data, context=ctx.context) + final_output = result.final_output_as(HomeworkOutput) + return GuardrailFunctionOutput( + output_info=final_output, + tripwire_triggered=not final_output.is_homework, + ) +``` + +## すべてをまとめる + +ハンドオフと入力ガードレールを組み合わせて、ワークフロー全体を実行してみましょう。 + +```python +from agents import Agent, InputGuardrail, GuardrailFunctionOutput, Runner +from pydantic import BaseModel +import asyncio + +class HomeworkOutput(BaseModel): + is_homework: bool + reasoning: str + +guardrail_agent = Agent( + name="Guardrail check", + instructions="Check if the user is asking about homework.", + output_type=HomeworkOutput, +) + +math_tutor_agent = Agent( + name="Math Tutor", + handoff_description="Specialist agent for math questions", + instructions="You provide help with math problems. Explain your reasoning at each step and include examples", +) + +history_tutor_agent = Agent( + name="History Tutor", + handoff_description="Specialist agent for historical questions", + instructions="You provide assistance with historical queries. Explain important events and context clearly.", +) + + +async def homework_guardrail(ctx, agent, input_data): + result = await Runner.run(guardrail_agent, input_data, context=ctx.context) + final_output = result.final_output_as(HomeworkOutput) + return GuardrailFunctionOutput( + output_info=final_output, + tripwire_triggered=not final_output.is_homework, + ) + +triage_agent = Agent( + name="Triage Agent", + instructions="You determine which agent to use based on the user's homework question", + handoffs=[history_tutor_agent, math_tutor_agent], + input_guardrails=[ + InputGuardrail(guardrail_function=homework_guardrail), + ], +) + +async def main(): + result = await Runner.run(triage_agent, "who was the first president of the united states?") + print(result.final_output) + + result = await Runner.run(triage_agent, "what is life") + print(result.final_output) + +if __name__ == "__main__": + asyncio.run(main()) +``` + +## トレースの表示 + +エージェントの実行内容を確認するには、[OpenAI ダッシュボードの Trace viewer](https://platform.openai.com/traces) に移動してトレースを閲覧してください。 + +## 次のステップ + +より複雑なエージェントフローの構築方法を学びましょう。 + +- [エージェント](agents.md) の設定方法を学ぶ。 +- [エージェントの実行](running_agents.md) について学ぶ。 +- [ツール](tools.md)、[ガードレール](guardrails.md)、[モデル](models/index.md) について学ぶ。 \ No newline at end of file diff --git a/docs/ja/results.md b/docs/ja/results.md new file mode 100644 index 00000000..cedd9240 --- /dev/null +++ b/docs/ja/results.md @@ -0,0 +1,56 @@ +--- +search: + exclude: true +--- +# 結果 + +`Runner.run` メソッドを呼び出すと、以下のいずれかが返されます。 + +- `run` または `run_sync` を呼び出した場合は [`RunResult`][agents.result.RunResult] +- `run_streamed` を呼び出した場合は [`RunResultStreaming`][agents.result.RunResultStreaming] + +これらはどちらも [`RunResultBase`][agents.result.RunResultBase] を継承しており、ほとんどの有用な情報はここに格納されています。 + +## 最終出力 + +[`final_output`][agents.result.RunResultBase.final_output] プロパティには、最後に実行されたエージェントの最終出力が格納されます。内容は以下のいずれかです。 + +- `output_type` が定義されていない場合は `str` +- `output_type` が定義されている場合は `last_agent.output_type` 型のオブジェクト + +!!! note + + `final_output` の型は `Any` です。ハンドオフが発生する可能性があるため、静的に型付けできません。ハンドオフが発生すると、どのエージェントでも最後になり得るため、可能性のある出力型を静的に特定できないのです。 + +## 次のターンへの入力 + +[`result.to_input_list()`][agents.result.RunResultBase.to_input_list] を使用すると、エージェント実行中に生成されたアイテムを元の入力に連結した入力リストへ変換できます。これにより、あるエージェント実行の出力を別の実行へ渡したり、ループで実行して毎回新しいユーザー入力を追加したりすることが容易になります。 + +## 最後のエージェント + +[`last_agent`][agents.result.RunResultBase.last_agent] プロパティには、最後に実行されたエージェントが格納されています。アプリケーションによっては、次回ユーザーが入力する際にこれが役立つことがよくあります。例えば、フロントラインのトリアージ エージェントが言語専用のエージェントにハンドオフする場合、最後のエージェントを保存しておき、ユーザーが次にメッセージを送ったときに再利用できます。 + +## 新しいアイテム + +[`new_items`][agents.result.RunResultBase.new_items] プロパティには、実行中に生成された新しいアイテムが含まれます。これらのアイテムは [`RunItem`][agents.items.RunItem] です。RunItem は、 LLM が生成した raw アイテムをラップします。 + +- [`MessageOutputItem`][agents.items.MessageOutputItem] — LLM からのメッセージを示します。 raw アイテムは生成されたメッセージです。 +- [`HandoffCallItem`][agents.items.HandoffCallItem] — LLM がハンドオフ ツールを呼び出したことを示します。 raw アイテムは LLM からのツール呼び出しアイテムです。 +- [`HandoffOutputItem`][agents.items.HandoffOutputItem] — ハンドオフが発生したことを示します。 raw アイテムはハンドオフ ツール呼び出しに対するツール応答です。また、アイテムから送信元 / 送信先エージェントにもアクセスできます。 +- [`ToolCallItem`][agents.items.ToolCallItem] — LLM がツールを呼び出したことを示します。 +- [`ToolCallOutputItem`][agents.items.ToolCallOutputItem] — ツールが呼び出されたことを示します。 raw アイテムはツール応答です。また、アイテムからツール出力にもアクセスできます。 +- [`ReasoningItem`][agents.items.ReasoningItem] — LLM からの推論アイテムを示します。 raw アイテムは生成された推論内容です。 + +## その他の情報 + +### ガードレール結果 + +[`input_guardrail_results`][agents.result.RunResultBase.input_guardrail_results] と [`output_guardrail_results`][agents.result.RunResultBase.output_guardrail_results] プロパティには、ガードレールの結果が存在する場合に格納されます。ガードレール結果には、ログや保存を行いたい有用な情報が含まれることがあるため、これらを参照できるようにしています。 + +### raw レスポンス + +[`raw_responses`][agents.result.RunResultBase.raw_responses] プロパティには、 LLM が生成した [`ModelResponse`][agents.items.ModelResponse] が格納されます。 + +### 元の入力 + +[`input`][agents.result.RunResultBase.input] プロパティには、`run` メソッドに渡した元の入力が格納されます。ほとんどの場合は必要ありませんが、必要に応じて参照できるように用意されています。 \ No newline at end of file diff --git a/docs/ja/running_agents.md b/docs/ja/running_agents.md new file mode 100644 index 00000000..83d5bec6 --- /dev/null +++ b/docs/ja/running_agents.md @@ -0,0 +1,99 @@ +--- +search: + exclude: true +--- +# エージェントの実行 + +`Runner` クラス [`Runner`][agents.run.Runner] を使用して エージェント を実行できます。方法は 3 つあります。 + +1. 非同期で実行し、[`RunResult`][agents.result.RunResult] を返す [`Runner.run()`][agents.run.Runner.run] +2. 同期メソッドで、内部的には `.run()` を呼び出す [`Runner.run_sync()`][agents.run.Runner.run_sync] +3. 非同期で実行し、[`RunResultStreaming`][agents.result.RunResultStreaming] を返す [`Runner.run_streamed()`][agents.run.Runner.run_streamed] + LLM をストリーミングモードで呼び出し、受信したイベントを逐次 ストリーミング します。 + +```python +from agents import Agent, Runner + +async def main(): + agent = Agent(name="Assistant", instructions="You are a helpful assistant") + + result = await Runner.run(agent, "Write a haiku about recursion in programming.") + print(result.final_output) + # Code within the code, + # Functions calling themselves, + # Infinite loop's dance. +``` + +詳細は [結果ガイド](results.md) を参照してください。 + +## エージェントループ + +`Runner` の run メソッドを使用する際は、開始 エージェント と入力を渡します。入力は文字列（ユーザー メッセージと見なされます）または入力項目のリスト（OpenAI Responses API の項目）です。 + +Runner は以下のループを実行します。 + +1. 現在の エージェント と現在の入力で LLM を呼び出します。 +2. LLM が出力を生成します。 + 1. `final_output` が返された場合、ループを終了して結果を返します。 + 2. ハンドオフ が発生した場合、現在の エージェント と入力を更新し、ループを再実行します。 + 3. ツール呼び出し がある場合、それらを実行し、結果を追加してループを再実行します。 +3. 指定した `max_turns` を超えた場合、[`MaxTurnsExceeded`][agents.exceptions.MaxTurnsExceeded] 例外を送出します。 + +!!! note + LLM の出力が「最終出力」と見なされる条件は、望ましい型のテキスト出力であり、ツール呼び出しがないことです。 + +## ストリーミング + +ストリーミング を使用すると、LLM の実行中に ストリーミング イベントを受け取れます。ストリーム完了後、[`RunResultStreaming`][agents.result.RunResultStreaming] には実行に関する完全な情報（新しく生成されたすべての出力を含む）が格納されます。`.stream_events()` を呼び出して ストリーミング イベントを取得できます。詳しくは [ストリーミングガイド](streaming.md) をご覧ください。 + +## Run 設定 + +`run_config` パラメーターにより、エージェント実行のグローバル設定を行えます。 + +- [`model`][agents.run.RunConfig.model]: 各 Agent の `model` 設定に関わらず使用するグローバル LLM モデルを指定します。 +- [`model_provider`][agents.run.RunConfig.model_provider]: モデル名を解決する モデルプロバイダー。デフォルトは OpenAI です。 +- [`model_settings`][agents.run.RunConfig.model_settings]: エージェント固有設定を上書きします。例としてグローバル `temperature` や `top_p` の設定など。 +- [`input_guardrails`][agents.run.RunConfig.input_guardrails], [`output_guardrails`][agents.run.RunConfig.output_guardrails]: すべての実行に適用する入力 / 出力 ガードレール のリスト。 +- [`handoff_input_filter`][agents.run.RunConfig.handoff_input_filter]: ハンドオフ に入力フィルターが設定されていない場合に適用されるグローバル入力フィルター。新しい エージェント へ送信される入力を編集できます。詳細は [`Handoff.input_filter`][agents.handoffs.Handoff.input_filter] を参照してください。 +- [`tracing_disabled`][agents.run.RunConfig.tracing_disabled]: 実行全体の [トレーシング](tracing.md) を無効化します。 +- [`trace_include_sensitive_data`][agents.run.RunConfig.trace_include_sensitive_data]: トレースに LLM やツール呼び出しの入出力など、機微なデータを含めるかどうかを設定します。 +- [`workflow_name`][agents.run.RunConfig.workflow_name], [`trace_id`][agents.run.RunConfig.trace_id], [`group_id`][agents.run.RunConfig.group_id]: 実行のトレーシング ワークフロー名、トレース ID、トレース グループ ID を設定します。少なくとも `workflow_name` の設定を推奨します。`group_id` を設定すると、複数の実行にまたがるトレースをリンクできます。 +- [`trace_metadata`][agents.run.RunConfig.trace_metadata]: すべてのトレースに付与するメタデータ。 + +## 会話 / チャットスレッド + +いずれかの run メソッドを呼び出すと、1 つ以上の エージェント が実行され（つまり 1 つ以上の LLM 呼び出しが行われ）、チャット会話の 1 つの論理ターンを表します。例: + +1. ユーザーターン: ユーザー がテキストを入力 +2. Runner 実行: 最初の エージェント が LLM を呼び出し、ツールを実行し、2 番目の エージェント へハンドオフ。2 番目の エージェント がさらにツールを実行し、最終出力を生成。 + +エージェント実行の終了時に、ユーザー に何を表示するかは自由です。たとえば、エージェント が生成したすべての新しい項目を表示する、または最終出力のみを表示する等です。いずれの場合でも、ユーザー がフォローアップ質問をしたら、再度 run メソッドを呼び出せます。 + +次ターンの入力は、基底クラス [`RunResultBase.to_input_list()`][agents.result.RunResultBase.to_input_list] を使用して取得できます。 + +```python +async def main(): + agent = Agent(name="Assistant", instructions="Reply very concisely.") + + with trace(workflow_name="Conversation", group_id=thread_id): + # First turn + result = await Runner.run(agent, "What city is the Golden Gate Bridge in?") + print(result.final_output) + # San Francisco + + # Second turn + new_input = result.to_input_list() + [{"role": "user", "content": "What state is it in?"}] + result = await Runner.run(agent, new_input) + print(result.final_output) + # California +``` + +## 例外 + +特定の状況で SDK は例外を送出します。完全な一覧は [`agents.exceptions`][] にあります。概要は以下のとおりです。 + +- [`AgentsException`][agents.exceptions.AgentsException]: SDK が送出するすべての例外の基底クラス +- [`MaxTurnsExceeded`][agents.exceptions.MaxTurnsExceeded]: 実行が `max_turns` を超えた場合に送出 +- [`ModelBehaviorError`][agents.exceptions.ModelBehaviorError]: モデルが不正な出力（例: JSON 形式違反、存在しないツールの呼び出しなど）を生成した場合に送出 +- [`UserError`][agents.exceptions.UserError]: SDK の使用方法に誤りがある場合に送出 +- [`InputGuardrailTripwireTriggered`][agents.exceptions.InputGuardrailTripwireTriggered], [`OutputGuardrailTripwireTriggered`][agents.exceptions.OutputGuardrailTripwireTriggered]: [ガードレール](guardrails.md) が発火した場合に送出 \ No newline at end of file diff --git a/docs/ja/streaming.md b/docs/ja/streaming.md new file mode 100644 index 00000000..a8a46cca --- /dev/null +++ b/docs/ja/streaming.md @@ -0,0 +1,91 @@ +--- +search: + exclude: true +--- +# ストリーミング + +ストリーミングを使用すると、 エージェント の実行が進行するにつれて発生する更新を購読できます。これにより、エンド ユーザーに進捗状況や部分的な応答を表示するのに役立ちます。 + +ストリーミングを行うには、 [`Runner.run_streamed()`][agents.run.Runner.run_streamed] を呼び出します。これにより [`RunResultStreaming`][agents.result.RunResultStreaming] が返されます。続いて `result.stream_events()` を呼び出すと、後述する [`StreamEvent`][agents.stream_events.StreamEvent] オブジェクトの非同期ストリームを取得できます。 + +## raw response イベント + +[`RawResponsesStreamEvent`][agents.stream_events.RawResponsesStreamEvent] は、 LLM から直接渡される raw なイベントです。これらは OpenAI Responses API 形式であり、各イベントには `response.created` や `response.output_text.delta` などの type とデータが含まれます。生成されたメッセージを即座にユーザーへストリーミングしたい場合に便利です。 + +たとえば、以下のコードは LLM が生成したテキストをトークンごとに出力します。 + +```python +import asyncio +from openai.types.responses import ResponseTextDeltaEvent +from agents import Agent, Runner + +async def main(): + agent = Agent( + name="Joker", + instructions="You are a helpful assistant.", + ) + + result = Runner.run_streamed(agent, input="Please tell me 5 jokes.") + async for event in result.stream_events(): + if event.type == "raw_response_event" and isinstance(event.data, ResponseTextDeltaEvent): + print(event.data.delta, end="", flush=True) + + +if __name__ == "__main__": + asyncio.run(main()) +``` + +## Run item イベントと エージェント イベント + +[`RunItemStreamEvent`][agents.stream_events.RunItemStreamEvent] は、より高レベルなイベントです。アイテムが完全に生成されたタイミングを通知するため、トークン単位ではなく「メッセージが生成された」「ツールが実行された」といったレベルで進捗をプッシュできます。同様に、 [`AgentUpdatedStreamEvent`][agents.stream_events.AgentUpdatedStreamEvent] はハンドオフなどで現在の エージェント が変わった際に更新を提供します。 + +たとえば、以下のコードは raw イベントを無視し、ユーザーへ更新のみをストリーミングします。 + +```python +import asyncio +import random +from agents import Agent, ItemHelpers, Runner, function_tool + +@function_tool +def how_many_jokes() -> int: + return random.randint(1, 10) + + +async def main(): + agent = Agent( + name="Joker", + instructions="First call the `how_many_jokes` tool, then tell that many jokes.", + tools=[how_many_jokes], + ) + + result = Runner.run_streamed( + agent, + input="Hello", + ) + print("=== Run starting ===") + + async for event in result.stream_events(): + # We'll ignore the raw responses event deltas + if event.type == "raw_response_event": + continue + # When the agent updates, print that + elif event.type == "agent_updated_stream_event": + print(f"Agent updated: {event.new_agent.name}") + continue + # When items are generated, print them + elif event.type == "run_item_stream_event": + if event.item.type == "tool_call_item": + print("-- Tool was called") + elif event.item.type == "tool_call_output_item": + print(f"-- Tool output: {event.item.output}") + elif event.item.type == "message_output_item": + print(f"-- Message output:\n {ItemHelpers.text_message_output(event.item)}") + else: + pass # Ignore other event types + + print("=== Run complete ===") + + +if __name__ == "__main__": + asyncio.run(main()) +``` \ No newline at end of file diff --git a/docs/ja/tools.md b/docs/ja/tools.md new file mode 100644 index 00000000..7ab15e47 --- /dev/null +++ b/docs/ja/tools.md @@ -0,0 +1,295 @@ +--- +search: + exclude: true +--- +# ツール + +ツールはエージェントがアクションを実行できるようにします。たとえばデータの取得、コードの実行、外部 API の呼び出し、さらにはコンピュータ操作などです。Agents SDK には次の 3 種類のツールがあります。 + +- ホストツール: これらは LLM サーバー上で AI モデルと一緒に実行されます。OpenAI は retrieval、Web 検索、コンピュータ操作をホストツールとして提供しています。 +- 関数呼び出し: 任意の Python 関数をツールとして利用できます。 +- ツールとしてのエージェント: ハンドオフせずに、エージェントから他のエージェントを呼び出すことができます。 + +## ホストツール + +OpenAI は [`OpenAIResponsesModel`][agents.models.openai_responses.OpenAIResponsesModel] を使用する際に、いくつかの組み込みツールを提供しています。 + +- [`WebSearchTool`][agents.tool.WebSearchTool] はエージェントに Web 検索を行わせます。 +- [`FileSearchTool`][agents.tool.FileSearchTool] は OpenAI ベクトルストアから情報を取得します。 +- [`ComputerTool`][agents.tool.ComputerTool] はコンピュータ操作タスクを自動化します。 + +```python +from agents import Agent, FileSearchTool, Runner, WebSearchTool + +agent = Agent( + name="Assistant", + tools=[ + WebSearchTool(), + FileSearchTool( + max_num_results=3, + vector_store_ids=["VECTOR_STORE_ID"], + ), + ], +) + +async def main(): + result = await Runner.run(agent, "Which coffee shop should I go to, taking into account my preferences and the weather today in SF?") + print(result.final_output) +``` + +## 関数ツール + +任意の Python 関数をツールとして使用できます。Agents SDK が自動的に設定を行います。 + +- ツールの名前は Python 関数の名前になります（任意で名前を指定することも可能です） +- ツールの説明は関数の docstring から取得されます（任意で説明を指定することも可能です） +- 関数の引数から自動的に入力スキーマを生成します +- 各入力の説明は、無効化しない限り docstring から取得されます + +Python の `inspect` モジュールを使用して関数シグネチャを抽出し、[`griffe`](https://mkdocstrings.github.io/griffe/) で docstring を解析し、`pydantic` でスキーマを作成します。 + +```python +import json + +from typing_extensions import TypedDict, Any + +from agents import Agent, FunctionTool, RunContextWrapper, function_tool + + +class Location(TypedDict): + lat: float + long: float + +@function_tool # (1)! +async def fetch_weather(location: Location) -> str: + # (2)! + """Fetch the weather for a given location. + + Args: + location: The location to fetch the weather for. + """ + # In real life, we'd fetch the weather from a weather API + return "sunny" + + +@function_tool(name_override="fetch_data") # (3)! +def read_file(ctx: RunContextWrapper[Any], path: str, directory: str | None = None) -> str: + """Read the contents of a file. + + Args: + path: The path to the file to read. + directory: The directory to read the file from. + """ + # In real life, we'd read the file from the file system + return "" + + +agent = Agent( + name="Assistant", + tools=[fetch_weather, read_file], # (4)! +) + +for tool in agent.tools: + if isinstance(tool, FunctionTool): + print(tool.name) + print(tool.description) + print(json.dumps(tool.params_json_schema, indent=2)) + print() + +``` + +1. 関数の引数には任意の Python 型を使用でき、同期・非同期どちらの関数も利用できます。 +2. docstring が存在する場合、ツールと引数の説明を取得します。 +3. 関数はオプションで `context` を受け取れます（最初の引数である必要があります）。ツール名、説明、docstring のスタイルなどを上書き設定することも可能です。 +4. デコレートされた関数をツールのリストに渡してください。 + +??? note "展開して出力を確認" + + ``` + fetch_weather + Fetch the weather for a given location. + { + "$defs": { + "Location": { + "properties": { + "lat": { + "title": "Lat", + "type": "number" + }, + "long": { + "title": "Long", + "type": "number" + } + }, + "required": [ + "lat", + "long" + ], + "title": "Location", + "type": "object" + } + }, + "properties": { + "location": { + "$ref": "#/$defs/Location", + "description": "The location to fetch the weather for." + } + }, + "required": [ + "location" + ], + "title": "fetch_weather_args", + "type": "object" + } + + fetch_data + Read the contents of a file. + { + "properties": { + "path": { + "description": "The path to the file to read.", + "title": "Path", + "type": "string" + }, + "directory": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The directory to read the file from.", + "title": "Directory" + } + }, + "required": [ + "path" + ], + "title": "fetch_data_args", + "type": "object" + } + ``` + +### カスタム関数ツール + +Python 関数をそのままツールにしたくない場合は、[`FunctionTool`][agents.tool.FunctionTool] を直接作成できます。次を指定する必要があります。 + +- `name` +- `description` +- `params_json_schema`（引数の JSON スキーマ） +- `on_invoke_tool`（context と引数の JSON 文字列を受け取り、ツールの出力を文字列で返す async 関数） + +```python +from typing import Any + +from pydantic import BaseModel + +from agents import RunContextWrapper, FunctionTool + + + +def do_some_work(data: str) -> str: + return "done" + + +class FunctionArgs(BaseModel): + username: str + age: int + + +async def run_function(ctx: RunContextWrapper[Any], args: str) -> str: + parsed = FunctionArgs.model_validate_json(args) + return do_some_work(data=f"{parsed.username} is {parsed.age} years old") + + +tool = FunctionTool( + name="process_user", + description="Processes extracted user data", + params_json_schema=FunctionArgs.model_json_schema(), + on_invoke_tool=run_function, +) +``` + +### 引数と docstring の自動解析 + +前述のとおり、関数シグネチャを自動解析してツールのスキーマを生成し、docstring を解析してツールおよび個別引数の説明を抽出します。主な注意点は次のとおりです。 + +1. シグネチャ解析は `inspect` モジュールで行います。型アノテーションを用いて引数の型を認識し、Pydantic モデルを動的に構築して全体のスキーマを表現します。Python の基本型、Pydantic モデル、TypedDict などほとんどの型をサポートします。 +2. `griffe` を使用して docstring を解析します。対応する docstring 形式は `google`、`sphinx`、`numpy` です。形式は自動検出を試みますが、`function_tool` 呼び出し時に明示的に指定することもできます。`use_docstring_info` を `False` に設定すると docstring 解析を無効化できます。 + +スキーマ抽出のコードは [`agents.function_schema`][] にあります。 + +## ツールとしてのエージェント + +一部のワークフローでは、ハンドオフせずに中央のエージェントが複数の専門エージェントをオーケストレーションしたい場合があります。そのような場合、エージェントをツールとしてモデル化できます。 + +```python +from agents import Agent, Runner +import asyncio + +spanish_agent = Agent( + name="Spanish agent", + instructions="You translate the user's message to Spanish", +) + +french_agent = Agent( + name="French agent", + instructions="You translate the user's message to French", +) + +orchestrator_agent = Agent( + name="orchestrator_agent", + instructions=( + "You are a translation agent. You use the tools given to you to translate." + "If asked for multiple translations, you call the relevant tools." + ), + tools=[ + spanish_agent.as_tool( + tool_name="translate_to_spanish", + tool_description="Translate the user's message to Spanish", + ), + french_agent.as_tool( + tool_name="translate_to_french", + tool_description="Translate the user's message to French", + ), + ], +) + +async def main(): + result = await Runner.run(orchestrator_agent, input="Say 'Hello, how are you?' in Spanish.") + print(result.final_output) +``` + +### ツールエージェントのカスタマイズ + +`agent.as_tool` 関数はエージェントを簡単にツール化するためのヘルパーです。ただし、すべての設定に対応しているわけではありません（例: `max_turns` は設定不可）。高度なユースケースでは、ツール実装内で `Runner.run` を直接使用してください。 + +```python +@function_tool +async def run_my_agent() -> str: + """A tool that runs the agent with custom configs". + + agent = Agent(name="My agent", instructions="...") + + result = await Runner.run( + agent, + input="...", + max_turns=5, + run_config=... + ) + + return str(result.final_output) +``` + +## 関数ツールでのエラー処理 + +`@function_tool` で関数ツールを作成する際、`failure_error_function` を渡せます。これはツール呼び出しが失敗した場合に LLM へ返すエラーレスポンスを生成する関数です。 + +- 何も指定しない場合、`default_tool_error_function` が実行され、LLM にエラー発生を伝えます。 +- 独自のエラー関数を渡した場合はそちらが実行され、そのレスポンスが LLM へ送信されます。 +- 明示的に `None` を渡すと、ツール呼び出し時のエラーは再送出されます。モデルが無効な JSON を生成した場合は `ModelBehaviorError`、コードがクラッシュした場合は `UserError` などになります。 + +`FunctionTool` オブジェクトを手動で作成する場合は、`on_invoke_tool` 関数内でエラーを処理する必要があります。 \ No newline at end of file diff --git a/docs/ja/tracing.md b/docs/ja/tracing.md new file mode 100644 index 00000000..0e0d0e77 --- /dev/null +++ b/docs/ja/tracing.md @@ -0,0 +1,122 @@ +--- +search: + exclude: true +--- +# トレーシング + +Agents SDK にはビルトインのトレーシング機能があり、エージェントの実行中に発生するイベント―― LLM 生成、ツール呼び出し、ハンドオフ、ガードレール、さらにカスタムイベントまで――を網羅的に記録します。開発時と本番環境の両方で [Traces dashboard](https://platform.openai.com/traces) を使用すると、ワークフローをデバッグ・可視化・モニタリングできます。 + +!!!note + + トレーシングはデフォルトで有効です。無効化する方法は次の 2 つです: + + 1. 環境変数 `OPENAI_AGENTS_DISABLE_TRACING=1` を設定してグローバルに無効化する + 2. 単一の実行に対しては [`agents.run.RunConfig.tracing_disabled`][] を `True` に設定する + +***OpenAI の API を Zero Data Retention (ZDR) ポリシーで利用している組織では、トレーシングを利用できません。*** + +## トレースとスパン + +- **トレース** は 1 度のワークフロー全体を表します。複数のスパンで構成され、次のプロパティを持ちます: + - `workflow_name`: 論理的なワークフローまたはアプリ名。例: 「Code generation」や「Customer service」 + - `trace_id`: トレースを一意に識別する ID。指定しない場合は自動生成されます。形式は `trace_<32_alphanumeric>` である必要があります。 + - `group_id`: オプションのグループ ID。会話内の複数トレースを関連付けます。たとえばチャットスレッド ID など。 + - `disabled`: `True` の場合、このトレースは記録されません。 + - `metadata`: トレースに付随する任意のメタデータ。 +- **スパン** は開始時刻と終了時刻を持つ個々の処理を表します。スパンは以下を保持します: + - `started_at` と `ended_at` タイムスタンプ + - 所属トレースを示す `trace_id` + - 親スパンを指す `parent_id` (存在する場合) + - スパンに関する情報を格納する `span_data`。たとえば `AgentSpanData` にはエージェント情報が、`GenerationSpanData` には LLM 生成情報が含まれます。 + +## デフォルトのトレーシング + +デフォルトで SDK は以下をトレースします: + +- `Runner.{run, run_sync, run_streamed}()` 全体を `trace()` でラップ +- エージェントが実行されるたびに `agent_span()` でラップ +- LLM 生成を `generation_span()` でラップ +- 関数ツール呼び出しを `function_span()` でラップ +- ガードレールを `guardrail_span()` でラップ +- ハンドオフを `handoff_span()` でラップ +- 音声入力 (speech‑to‑text) を `transcription_span()` でラップ +- 音声出力 (text‑to‑speech) を `speech_span()` でラップ +- 関連する音声スパンは `speech_group_span()` の下にネストされる場合があります + +トレース名はデフォルトで「Agent trace」です。`trace` を使用して指定したり、[`RunConfig`][agents.run.RunConfig] で名前やその他のプロパティを設定できます。 + +さらに [カスタムトレーシングプロセッサー](#custom-tracing-processors) を設定して、トレースを別の送信先に出力（置き換えまたは追加）することも可能です。 + +## 上位レベルのトレース + +複数回の `run()` 呼び出しを 1 つのトレースにまとめたい場合があります。その場合、コード全体を `trace()` でラップします。 + +```python +from agents import Agent, Runner, trace + +async def main(): + agent = Agent(name="Joke generator", instructions="Tell funny jokes.") + + with trace("Joke workflow"): # (1)! + first_result = await Runner.run(agent, "Tell me a joke") + second_result = await Runner.run(agent, f"Rate this joke: {first_result.final_output}") + print(f"Joke: {first_result.final_output}") + print(f"Rating: {second_result.final_output}") +``` + +1. `with trace()` で 2 つの `Runner.run` 呼び出しをラップしているため、それぞれが個別のトレースを作成せず、全体で 1 つのトレースになります。 + +## トレースの作成 + +[`trace()`][agents.tracing.trace] 関数を使ってトレースを作成できます。開始と終了が必要で、方法は 2 つあります。 + +1. **推奨**: `with trace(...) as my_trace` のようにコンテキストマネージャーとして使用する。開始と終了が自動で行われます。 +2. [`trace.start()`][agents.tracing.Trace.start] と [`trace.finish()`][agents.tracing.Trace.finish] を手動で呼び出す。 + +現在のトレースは Python の [`contextvar`](https://docs.python.org/3/library/contextvars.html) で管理されているため、並行処理でも自動で機能します。手動で開始／終了する場合は `start()`／`finish()` に `mark_as_current` と `reset_current` を渡して現在のトレースを更新してください。 + +## スパンの作成 + +各種 [`*_span()`][agents.tracing.create] メソッドでスパンを作成できます。一般的には手動で作成する必要はありません。カスタム情報を追跡するための [`custom_span()`][agents.tracing.custom_span] も利用できます。 + +スパンは自動的に現在のトレースの一部となり、最も近い現在のスパンの下にネストされます。これも Python の [`contextvar`](https://docs.python.org/3/library/contextvars.html) で管理されています。 + +## 機密データ + +一部のスパンでは機密データが収集される可能性があります。 + +`generation_span()` には LLM の入力と出力、`function_span()` には関数呼び出しの入力と出力が保存されます。これらに機密データが含まれる場合、[`RunConfig.trace_include_sensitive_data`][agents.run.RunConfig.trace_include_sensitive_data] を使用して記録を無効化できます。 + +同様に、音声スパンにはデフォルトで base64 エンコードされた PCM 音声データが含まれます。[`VoicePipelineConfig.trace_include_sensitive_audio_data`][agents.voice.pipeline_config.VoicePipelineConfig.trace_include_sensitive_audio_data] を設定して音声データの記録を無効化できます。 + +## カスタムトレーシングプロセッサー + +トレーシングの高レベル構成は次のとおりです。 + +- 初期化時にグローバルな [`TraceProvider`][agents.tracing.setup.TraceProvider] を作成し、トレースを生成。 +- `TraceProvider` は [`BatchTraceProcessor`][agents.tracing.processors.BatchTraceProcessor] を用いてスパン／トレースをバッチ送信し、[`BackendSpanExporter`][agents.tracing.processors.BackendSpanExporter] が OpenAI バックエンドへバッチでエクスポートします。 + +デフォルト設定を変更して別のバックエンドへ送信したり、エクスポーターの挙動を修正するには次の 2 通りがあります。 + +1. [`add_trace_processor()`][agents.tracing.add_trace_processor] + 既定の送信に加え、**追加** のトレースプロセッサーを登録できます。これにより OpenAI バックエンドへの送信に加えて独自処理が可能です。 +2. [`set_trace_processors()`][agents.tracing.set_trace_processors] + 既定のプロセッサーを置き換え、**独自** のトレースプロセッサーだけを使用します。OpenAI バックエンドへ送信する場合は、その機能を持つ `TracingProcessor` を含める必要があります。 + +## 外部トレーシングプロセッサー一覧 + +- [Weights & Biases](https://weave-docs.wandb.ai/guides/integrations/openai_agents) +- [Arize‑Phoenix](https://docs.arize.com/phoenix/tracing/integrations-tracing/openai-agents-sdk) +- [MLflow (self‑hosted/OSS](https://mlflow.org/docs/latest/tracing/integrations/openai-agent) +- [MLflow (Databricks hosted](https://docs.databricks.com/aws/en/mlflow/mlflow-tracing#-automatic-tracing) +- [Braintrust](https://braintrust.dev/docs/guides/traces/integrations#openai-agents-sdk) +- [Pydantic Logfire](https://logfire.pydantic.dev/docs/integrations/llms/openai/#openai-agents) +- [AgentOps](https://docs.agentops.ai/v1/integrations/agentssdk) +- [Scorecard](https://docs.scorecard.io/docs/documentation/features/tracing#openai-agents-sdk-integration) +- [Keywords AI](https://docs.keywordsai.co/integration/development-frameworks/openai-agent) +- [LangSmith](https://docs.smith.langchain.com/observability/how_to_guides/trace_with_openai_agents_sdk) +- [Maxim AI](https://www.getmaxim.ai/docs/observe/integrations/openai-agents-sdk) +- [Comet Opik](https://www.comet.com/docs/opik/tracing/integrations/openai_agents) +- [Langfuse](https://langfuse.com/docs/integrations/openaiagentssdk/openai-agents) +- [Langtrace](https://docs.langtrace.ai/supported-integrations/llm-frameworks/openai-agents-sdk) +- [Okahu‑Monocle](https://github.com/monocle2ai/monocle) \ No newline at end of file diff --git a/docs/ja/visualization.md b/docs/ja/visualization.md new file mode 100644 index 00000000..9093bb65 --- /dev/null +++ b/docs/ja/visualization.md @@ -0,0 +1,87 @@ +--- +search: + exclude: true +--- +# エージェントの可視化 + +エージェントの可視化を使用すると、 ** Graphviz ** を用いてエージェントとその関係を構造化されたグラフィカル表現として生成できます。これは、アプリケーション内でエージェント、ツール、handoffs がどのように相互作用するかを理解するのに役立ちます。 + +## インストール + +オプションの `viz` 依存関係グループをインストールします: + +```bash +pip install "openai-agents[viz]" +``` + +## グラフの生成 + +`draw_graph` 関数を使用してエージェントの可視化を生成できます。この関数は有向グラフを作成し、以下のように表現します。 + +- **エージェント** は黄色のボックスで表されます。 +- **ツール** は緑色の楕円で表されます。 +- **handoffs** はエージェント間の有向エッジで示されます。 + +### 使用例 + +```python +from agents import Agent, function_tool +from agents.extensions.visualization import draw_graph + +@function_tool +def get_weather(city: str) -> str: + return f"The weather in {city} is sunny." + +spanish_agent = Agent( + name="Spanish agent", + instructions="You only speak Spanish.", +) + +english_agent = Agent( + name="English agent", + instructions="You only speak English", +) + +triage_agent = Agent( + name="Triage agent", + instructions="Handoff to the appropriate agent based on the language of the request.", + handoffs=[spanish_agent, english_agent], + tools=[get_weather], +) + +draw_graph(triage_agent) +``` + +![Agent Graph](../assets/images/graph.png) + +これにより、 **triage agent** の構造と、それがサブエージェントやツールとどのようにつながっているかを視覚的に表すグラフが生成されます。 + +## 可視化の理解 + +生成されたグラフには次の要素が含まれます。 + +- エントリーポイントを示す **start node** (`__start__`) +- 黄色の塗りつぶしを持つ **矩形** のエージェント +- 緑色の塗りつぶしを持つ **楕円** のツール +- 相互作用を示す有向エッジ + - エージェント間の handoffs には **実線の矢印** + - ツール呼び出しには **破線の矢印** +- 実行が終了する位置を示す **end node** (`__end__`) + +## グラフのカスタマイズ + +### グラフの表示 +デフォルトでは、`draw_graph` はグラフをインラインで表示します。別ウィンドウでグラフを表示するには、次のように記述します。 + +```python +draw_graph(triage_agent).view() +``` + +### グラフの保存 +デフォルトでは、`draw_graph` はグラフをインラインで表示します。ファイルとして保存するには、ファイル名を指定します: + +```python +draw_graph(triage_agent, filename="agent_graph") +``` + +これにより、作業ディレクトリに `agent_graph.png` が生成されます。 diff --git a/docs/ja/voice/pipeline.md b/docs/ja/voice/pipeline.md new file mode 100644 index 00000000..d52fb77f --- /dev/null +++ b/docs/ja/voice/pipeline.md @@ -0,0 +1,81 @@ +--- +search: + exclude: true +--- +# パイプラインと ワークフロー + +[`VoicePipeline`][agents.voice.pipeline.VoicePipeline] は、エージェント的なワークフローを音声アプリに簡単に変換できるクラスです。ワークフローを渡すと、パイプラインが入力音声の文字起こし、音声終了の検知、適切なタイミングでのワークフロー呼び出し、そしてワークフロー出力を音声へ変換する処理を担当します。 + +```mermaid +graph LR + %% Input + A["🎤 Audio Input"] + + %% Voice Pipeline + subgraph Voice_Pipeline [Voice Pipeline] + direction TB + B["Transcribe (speech-to-text)"] + C["Your Code"]:::highlight + D["Text-to-speech"] + B --> C --> D + end + + %% Output + E["🎧 Audio Output"] + + %% Flow + A --> Voice_Pipeline + Voice_Pipeline --> E + + %% Custom styling + classDef highlight fill:#ffcc66,stroke:#333,stroke-width:1px,font-weight:700; + +``` + +## パイプラインの設定 + +パイプラインを作成する際に、以下を設定できます。 + +1. [`workflow`][agents.voice.workflow.VoiceWorkflowBase] ‐ 新しい音声が文字起こしされるたびに実行されるコード +2. 使用する [`speech-to-text`][agents.voice.model.STTModel] および [`text-to-speech`][agents.voice.model.TTSModel] モデル +3. [`config`][agents.voice.pipeline_config.VoicePipelineConfig] ‐ 以下のような内容を設定可能 + - モデルプロバイダー。モデル名をモデルにマッピングします + - トレーシング。トレーシングの無効化、音声ファイルのアップロード可否、ワークフロー名、トレース ID など + - TTS と STT モデルの設定。プロンプト、言語、使用するデータ型など + +## パイプラインの実行 + +パイプラインは [`run()`][agents.voice.pipeline.VoicePipeline.run] メソッドで実行できます。音声入力は次の 2 形式で渡せます。 + +1. [`AudioInput`][agents.voice.input.AudioInput] + 完全な音声トランスクリプトがある場合に使用し、その結果だけを生成したいときに便利です。話者の発話終了を検知する必要がないケース、たとえば録音済み音声やプッシュトゥートーク型アプリのようにユーザーが話し終えたタイミングが明確な場合に向いています。 +2. [`StreamedAudioInput`][agents.voice.input.StreamedAudioInput] + ユーザーの発話終了検知が必要な場合に使用します。検出された音声チャンクを順次プッシュでき、音声パイプラインが「アクティビティ検知」と呼ばれるプロセスを通じて適切なタイミングでエージェント ワークフローを自動的に実行します。 + +## 結果 + +音声パイプライン実行の結果は [`StreamedAudioResult`][agents.voice.result.StreamedAudioResult] です。これは発生したイベントをストリーミングで受け取れるオブジェクトです。いくつかの [`VoiceStreamEvent`][agents.voice.events.VoiceStreamEvent] があり、主なものは次のとおりです。 + +1. [`VoiceStreamEventAudio`][agents.voice.events.VoiceStreamEventAudio] ‐ 音声チャンクを含みます +2. [`VoiceStreamEventLifecycle`][agents.voice.events.VoiceStreamEventLifecycle] ‐ ターンの開始や終了などのライフサイクルイベントを通知します +3. [`VoiceStreamEventError`][agents.voice.events.VoiceStreamEventError] ‐ エラーイベントです + +```python + +result = await pipeline.run(input) + +async for event in result.stream(): + if event.type == "voice_stream_event_audio": + # play audio + elif event.type == "voice_stream_event_lifecycle": + # lifecycle + elif event.type == "voice_stream_event_error" + # error + ... +``` + +## ベストプラクティス + +### 割り込み + +Agents SDK は現在 [`StreamedAudioInput`][agents.voice.input.StreamedAudioInput] に対して、組み込みの割り込み処理をサポートしていません。そのため、検出された各ターンごとにワークフローが個別に実行されます。アプリケーション内で割り込みを処理したい場合は、[`VoiceStreamEventLifecycle`][agents.voice.events.VoiceStreamEventLifecycle] イベントを監視できます。`turn_started` は新しいターンが文字起こしされ、処理が開始されたことを示します。`turn_ended` は該当ターンのすべての音声が送信された後にトリガーされます。たとえば、モデルがターンを開始した際にスピーカーのマイクをミュートし、そのターンに関連する音声をすべて送信し終えた後にアンミュートするといった制御に、これらのイベントを利用できます。 \ No newline at end of file diff --git a/docs/ja/voice/quickstart.md b/docs/ja/voice/quickstart.md new file mode 100644 index 00000000..291b9882 --- /dev/null +++ b/docs/ja/voice/quickstart.md @@ -0,0 +1,198 @@ +--- +search: + exclude: true +--- +# クイックスタート + +## 前提条件 + +まずは [クイックスタート手順](../quickstart.md) に従って Agents SDK をセットアップし、仮想環境を作成してください。その後、SDK の音声関連のオプション依存関係をインストールします: + +```bash +pip install 'openai-agents[voice]' +``` + +## コンセプト + +押さえておくべき主な概念は [`VoicePipeline`][agents.voice.pipeline.VoicePipeline] です。これは次の 3 ステップから成るプロセスです。 + +1. speech-to-text モデルを実行して音声をテキストに変換します。 +2. 通常はエージェント的ワークフローであるあなたのコードを実行し、結果を生成します。 +3. text-to-speech モデルを実行して結果のテキストを再び音声に変換します。 + +```mermaid +graph LR + %% Input + A["🎤 Audio Input"] + + %% Voice Pipeline + subgraph Voice_Pipeline [Voice Pipeline] + direction TB + B["Transcribe (speech-to-text)"] + C["Your Code"]:::highlight + D["Text-to-speech"] + B --> C --> D + end + + %% Output + E["🎧 Audio Output"] + + %% Flow + A --> Voice_Pipeline + Voice_Pipeline --> E + + %% Custom styling + classDef highlight fill:#ffcc66,stroke:#333,stroke-width:1px,font-weight:700; + +``` + +## エージェント + +まず、いくつかの エージェント をセットアップしましょう。この SDK でエージェントを構築したことがあれば、見覚えがあるはずです。ここでは複数の エージェント、ハンドオフ、そしてツールを用意します。 + +```python +import asyncio +import random + +from agents import ( + Agent, + function_tool, +) +from agents.extensions.handoff_prompt import prompt_with_handoff_instructions + + + +@function_tool +def get_weather(city: str) -> str: + """Get the weather for a given city.""" + print(f"[debug] get_weather called with city: {city}") + choices = ["sunny", "cloudy", "rainy", "snowy"] + return f"The weather in {city} is {random.choice(choices)}." + + +spanish_agent = Agent( + name="Spanish", + handoff_description="A spanish speaking agent.", + instructions=prompt_with_handoff_instructions( + "You're speaking to a human, so be polite and concise. Speak in Spanish.", + ), + model="gpt-4o-mini", +) + +agent = Agent( + name="Assistant", + instructions=prompt_with_handoff_instructions( + "You're speaking to a human, so be polite and concise. If the user speaks in Spanish, handoff to the spanish agent.", + ), + model="gpt-4o-mini", + handoffs=[spanish_agent], + tools=[get_weather], +) +``` + +## 音声パイプライン + +[`SingleAgentVoiceWorkflow`][agents.voice.workflow.SingleAgentVoiceWorkflow] をワークフローとして、シンプルな音声パイプラインを構築します。 + +```python +from agents.voice import SingleAgentVoiceWorkflow, VoicePipeline +pipeline = VoicePipeline(workflow=SingleAgentVoiceWorkflow(agent)) +``` + +## パイプラインの実行 + +```python +import numpy as np +import sounddevice as sd +from agents.voice import AudioInput + +# For simplicity, we'll just create 3 seconds of silence +# In reality, you'd get microphone data +buffer = np.zeros(24000 * 3, dtype=np.int16) +audio_input = AudioInput(buffer=buffer) + +result = await pipeline.run(audio_input) + +# Create an audio player using `sounddevice` +player = sd.OutputStream(samplerate=24000, channels=1, dtype=np.int16) +player.start() + +# Play the audio stream as it comes in +async for event in result.stream(): + if event.type == "voice_stream_event_audio": + player.write(event.data) + +``` + +## まとめて実行 + +```python +import asyncio +import random + +import numpy as np +import sounddevice as sd + +from agents import ( + Agent, + function_tool, + set_tracing_disabled, +) +from agents.voice import ( + AudioInput, + SingleAgentVoiceWorkflow, + VoicePipeline, +) +from agents.extensions.handoff_prompt import prompt_with_handoff_instructions + + +@function_tool +def get_weather(city: str) -> str: + """Get the weather for a given city.""" + print(f"[debug] get_weather called with city: {city}") + choices = ["sunny", "cloudy", "rainy", "snowy"] + return f"The weather in {city} is {random.choice(choices)}." + + +spanish_agent = Agent( + name="Spanish", + handoff_description="A spanish speaking agent.", + instructions=prompt_with_handoff_instructions( + "You're speaking to a human, so be polite and concise. Speak in Spanish.", + ), + model="gpt-4o-mini", +) + +agent = Agent( + name="Assistant", + instructions=prompt_with_handoff_instructions( + "You're speaking to a human, so be polite and concise. If the user speaks in Spanish, handoff to the spanish agent.", + ), + model="gpt-4o-mini", + handoffs=[spanish_agent], + tools=[get_weather], +) + + +async def main(): + pipeline = VoicePipeline(workflow=SingleAgentVoiceWorkflow(agent)) + buffer = np.zeros(24000 * 3, dtype=np.int16) + audio_input = AudioInput(buffer=buffer) + + result = await pipeline.run(audio_input) + + # Create an audio player using `sounddevice` + player = sd.OutputStream(samplerate=24000, channels=1, dtype=np.int16) + player.start() + + # Play the audio stream as it comes in + async for event in result.stream(): + if event.type == "voice_stream_event_audio": + player.write(event.data) + + +if __name__ == "__main__": + asyncio.run(main()) +``` + +この例を実行すると、エージェントがあなたに話しかけます。実際にエージェントと会話できるデモは、[examples/voice/static](https://github.com/openai/openai-agents-python/tree/main/examples/voice/static) をご覧ください。 \ No newline at end of file diff --git a/docs/ja/voice/tracing.md b/docs/ja/voice/tracing.md new file mode 100644 index 00000000..21f4788f --- /dev/null +++ b/docs/ja/voice/tracing.md @@ -0,0 +1,18 @@ +--- +search: + exclude: true +--- +# トレーシング + +[エージェントのトレーシング](../tracing.md) と同様に、音声パイプラインも自動的にトレーシングされます。 + +基本的なトレーシング情報については上記のドキュメントを参照してください。さらに、[`VoicePipelineConfig`][agents.voice.pipeline_config.VoicePipelineConfig] でパイプラインのトレーシング設定を行えます。 + +主なトレーシング関連フィールドは次のとおりです。 + +- [`tracing_disabled`][agents.voice.pipeline_config.VoicePipelineConfig.tracing_disabled]：トレーシングを無効にするかどうかを制御します。デフォルトではトレーシングは有効です。 +- [`trace_include_sensitive_data`][agents.voice.pipeline_config.VoicePipelineConfig.trace_include_sensitive_data]：トレースに音声テキストなどの機微なデータを含めるかどうかを制御します。これは音声パイプライン専用であり、Workflow 内部で発生する処理には影響しません。 +- [`trace_include_sensitive_audio_data`][agents.voice.pipeline_config.VoicePipelineConfig.trace_include_sensitive_audio_data]：トレースに音声データを含めるかどうかを制御します。 +- [`workflow_name`][agents.voice.pipeline_config.VoicePipelineConfig.workflow_name]：トレース Workflow の名前です。 +- [`group_id`][agents.voice.pipeline_config.VoicePipelineConfig.group_id]：複数のトレースを関連付けるための `group_id` です。 +- [`trace_metadata`][agents.voice.pipeline_config.VoicePipelineConfig.tracing_disabled]：トレースに追加するメタデータです。 \ No newline at end of file diff --git a/docs/models.md b/docs/models/index.md similarity index 74% rename from docs/models.md rename to docs/models/index.md index ab4cefb8..1c89d778 100644 --- a/docs/models.md +++ b/docs/models/index.md @@ -5,11 +5,40 @@ The Agents SDK comes with out-of-the-box support for OpenAI models in two flavor - **Recommended**: the [`OpenAIResponsesModel`][agents.models.openai_responses.OpenAIResponsesModel], which calls OpenAI APIs using the new [Responses API](https://platform.openai.com/docs/api-reference/responses). - The [`OpenAIChatCompletionsModel`][agents.models.openai_chatcompletions.OpenAIChatCompletionsModel], which calls OpenAI APIs using the [Chat Completions API](https://platform.openai.com/docs/api-reference/chat). +## Non-OpenAI models + +You can use most other non-OpenAI models via the [LiteLLM integration](./litellm.md). First, install the litellm dependency group: + +```bash +pip install "openai-agents[litellm]" +``` + +Then, use any of the [supported models](https://docs.litellm.ai/docs/providers) with the `litellm/` prefix: + +```python +claude_agent = Agent(model="litellm/anthropic/claude-3-5-sonnet-20240620", ...) +gemini_agent = Agent(model="litellm/gemini/gemini-2.5-flash-preview-04-17", ...) +``` + +### Other ways to use non-OpenAI models + +You can integrate other LLM providers in 3 more ways (examples [here](https://github.com/openai/openai-agents-python/tree/main/examples/model_providers/)): + +1. [`set_default_openai_client`][agents.set_default_openai_client] is useful in cases where you want to globally use an instance of `AsyncOpenAI` as the LLM client. This is for cases where the LLM provider has an OpenAI compatible API endpoint, and you can set the `base_url` and `api_key`. See a configurable example in [examples/model_providers/custom_example_global.py](https://github.com/openai/openai-agents-python/tree/main/examples/model_providers/custom_example_global.py). +2. [`ModelProvider`][agents.models.interface.ModelProvider] is at the `Runner.run` level. This lets you say "use a custom model provider for all agents in this run". See a configurable example in [examples/model_providers/custom_example_provider.py](https://github.com/openai/openai-agents-python/tree/main/examples/model_providers/custom_example_provider.py). +3. [`Agent.model`][agents.agent.Agent.model] lets you specify the model on a specific Agent instance. This enables you to mix and match different providers for different agents. See a configurable example in [examples/model_providers/custom_example_agent.py](https://github.com/openai/openai-agents-python/tree/main/examples/model_providers/custom_example_agent.py). An easy way to use most available models is via the [LiteLLM integration](./litellm.md). + +In cases where you do not have an API key from `platform.openai.com`, we recommend disabling tracing via `set_tracing_disabled()`, or setting up a [different tracing processor](../tracing.md). + +!!! note + + In these examples, we use the Chat Completions API/model, because most LLM providers don't yet support the Responses API. If your LLM provider does support it, we recommend using Responses. + ## Mixing and matching models Within a single workflow, you may want to use different models for each agent. For example, you could use a smaller, faster model for triage, while using a larger, more capable model for complex tasks. When configuring an [`Agent`][agents.Agent], you can select a specific model by either: -1. Passing the name of an OpenAI model. +1. Passing the name of a model. 2. Passing any model name + a [`ModelProvider`][agents.models.interface.ModelProvider] that can map that name to a Model instance. 3. Directly providing a [`Model`][agents.models.interface.Model] implementation. @@ -51,19 +80,18 @@ async def main(): 1. Sets the name of an OpenAI model directly. 2. Provides a [`Model`][agents.models.interface.Model] implementation. -## Using other LLM providers +When you want to further configure the model used for an agent, you can pass [`ModelSettings`][agents.models.interface.ModelSettings], which provides optional model configuration parameters such as temperature. -You can use other LLM providers in 3 ways (examples [here](https://github.com/openai/openai-agents-python/tree/main/examples/model_providers/)): - -1. [`set_default_openai_client`][agents.set_default_openai_client] is useful in cases where you want to globally use an instance of `AsyncOpenAI` as the LLM client. This is for cases where the LLM provider has an OpenAI compatible API endpoint, and you can set the `base_url` and `api_key`. See a configurable example in [examples/model_providers/custom_example_global.py](https://github.com/openai/openai-agents-python/tree/main/examples/model_providers/custom_example_global.py). -2. [`ModelProvider`][agents.models.interface.ModelProvider] is at the `Runner.run` level. This lets you say "use a custom model provider for all agents in this run". See a configurable example in [examples/model_providers/custom_example_provider.py](https://github.com/openai/openai-agents-python/tree/main/examples/model_providers/custom_example_provider.py). -3. [`Agent.model`][agents.agent.Agent.model] lets you specify the model on a specific Agent instance. This enables you to mix and match different providers for different agents. See a configurable example in [examples/model_providers/custom_example_agent.py](https://github.com/openai/openai-agents-python/tree/main/examples/model_providers/custom_example_agent.py). - -In cases where you do not have an API key from `platform.openai.com`, we recommend disabling tracing via `set_tracing_disabled()`, or setting up a [different tracing processor](tracing.md). - -!!! note +```python +from agents import Agent, ModelSettings - In these examples, we use the Chat Completions API/model, because most LLM providers don't yet support the Responses API. If your LLM provider does support it, we recommend using Responses. +english_agent = Agent( + name="English agent", + instructions="You only speak English", + model="gpt-4o", + model_settings=ModelSettings(temperature=0.1), +) +``` ## Common issues with using other LLM providers @@ -73,7 +101,7 @@ If you get errors related to tracing, this is because traces are uploaded to Ope 1. Disable tracing entirely: [`set_tracing_disabled(True)`][agents.set_tracing_disabled]. 2. Set an OpenAI key for tracing: [`set_tracing_export_api_key(...)`][agents.set_tracing_export_api_key]. This API key will only be used for uploading traces, and must be from [platform.openai.com](https://platform.openai.com/). -3. Use a non-OpenAI trace processor. See the [tracing docs](tracing.md#custom-tracing-processors). +3. Use a non-OpenAI trace processor. See the [tracing docs](../tracing.md#custom-tracing-processors). ### Responses API support @@ -87,7 +115,17 @@ The SDK uses the Responses API by default, but most other LLM providers don't ye Some model providers don't have support for [structured outputs](https://platform.openai.com/docs/guides/structured-outputs). This sometimes results in an error that looks something like this: ``` + BadRequestError: Error code: 400 - {'error': {'message': "'response_format.type' : value is not one of the allowed values ['text','json_object']", 'type': 'invalid_request_error'}} + ``` This is a shortcoming of some model providers - they support JSON outputs, but don't allow you to specify the `json_schema` to use for the output. We are working on a fix for this, but we suggest relying on providers that do have support for JSON schema output, because otherwise your app will often break because of malformed JSON. + +## Mixing models across providers + +You need to be aware of feature differences between model providers, or you may run into errors. For example, OpenAI supports structured outputs, multimodal input, and hosted file search and web search, but many other providers don't support these features. Be aware of these limitations: + +- Don't send unsupported `tools` to providers that don't understand them +- Filter out multimodal inputs before calling models that are text-only +- Be aware that providers that don't support structured JSON outputs will occasionally produce invalid JSON. diff --git a/docs/models/litellm.md b/docs/models/litellm.md new file mode 100644 index 00000000..90572a28 --- /dev/null +++ b/docs/models/litellm.md @@ -0,0 +1,73 @@ +# Using any model via LiteLLM + +!!! note + + The LiteLLM integration is in beta. You may run into issues with some model providers, especially smaller ones. Please report any issues via [Github issues](https://github.com/openai/openai-agents-python/issues) and we'll fix quickly. + +[LiteLLM](https://docs.litellm.ai/docs/) is a library that allows you to use 100+ models via a single interface. We've added a LiteLLM integration to allow you to use any AI model in the Agents SDK. + +## Setup + +You'll need to ensure `litellm` is available. You can do this by installing the optional `litellm` dependency group: + +```bash +pip install "openai-agents[litellm]" +``` + +Once done, you can use [`LitellmModel`][agents.extensions.models.litellm_model.LitellmModel] in any agent. + +## Example + +This is a fully working example. When you run it, you'll be prompted for a model name and API key. For example, you could enter: + +- `openai/gpt-4.1` for the model, and your OpenAI API key +- `anthropic/claude-3-5-sonnet-20240620` for the model, and your Anthropic API key +- etc + +For a full list of models supported in LiteLLM, see the [litellm providers docs](https://docs.litellm.ai/docs/providers). + +```python +from __future__ import annotations + +import asyncio + +from agents import Agent, Runner, function_tool, set_tracing_disabled +from agents.extensions.models.litellm_model import LitellmModel + +@function_tool +def get_weather(city: str): + print(f"[debug] getting weather for {city}") + return f"The weather in {city} is sunny." + + +async def main(model: str, api_key: str): + agent = Agent( + name="Assistant", + instructions="You only respond in haikus.", + model=LitellmModel(model=model, api_key=api_key), + tools=[get_weather], + ) + + result = await Runner.run(agent, "What's the weather in Tokyo?") + print(result.final_output) + + +if __name__ == "__main__": + # First try to get model/api key from args + import argparse + + parser = argparse.ArgumentParser() + parser.add_argument("--model", type=str, required=False) + parser.add_argument("--api-key", type=str, required=False) + args = parser.parse_args() + + model = args.model + if not model: + model = input("Enter a model name for Litellm: ") + + api_key = args.api_key + if not api_key: + api_key = input("Enter an API key for Litellm: ") + + asyncio.run(main(model, api_key)) +``` diff --git a/docs/quickstart.md b/docs/quickstart.md index f8eca5ca..213d16e5 100644 --- a/docs/quickstart.md +++ b/docs/quickstart.md @@ -121,7 +121,7 @@ async def homework_guardrail(ctx, agent, input_data): Let's put it all together and run the entire workflow, using handoffs and the input guardrail. ```python -from agents import Agent, InputGuardrail,GuardrailFunctionOutput, Runner +from agents import Agent, InputGuardrail, GuardrailFunctionOutput, Runner from pydantic import BaseModel import asyncio @@ -186,4 +186,4 @@ Learn how to build more complex agentic flows: - Learn about how to configure [Agents](agents.md). - Learn about [running agents](running_agents.md). -- Learn about [tools](tools.md), [guardrails](guardrails.md) and [models](models.md). +- Learn about [tools](tools.md), [guardrails](guardrails.md) and [models](models/index.md). diff --git a/docs/ref/extensions/litellm.md b/docs/ref/extensions/litellm.md new file mode 100644 index 00000000..7bd67fde --- /dev/null +++ b/docs/ref/extensions/litellm.md @@ -0,0 +1,3 @@ +# `LiteLLM Models` + +::: agents.extensions.models.litellm_model diff --git a/docs/running_agents.md b/docs/running_agents.md index 32abf9d5..f631cf46 100644 --- a/docs/running_agents.md +++ b/docs/running_agents.md @@ -53,7 +53,7 @@ The `run_config` parameter lets you configure some global settings for the agent - [`handoff_input_filter`][agents.run.RunConfig.handoff_input_filter]: A global input filter to apply to all handoffs, if the handoff doesn't already have one. The input filter allows you to edit the inputs that are sent to the new agent. See the documentation in [`Handoff.input_filter`][agents.handoffs.Handoff.input_filter] for more details. - [`tracing_disabled`][agents.run.RunConfig.tracing_disabled]: Allows you to disable [tracing](tracing.md) for the entire run. - [`trace_include_sensitive_data`][agents.run.RunConfig.trace_include_sensitive_data]: Configures whether traces will include potentially sensitive data, such as LLM and tool call inputs/outputs. -- [`workflow_name`][agents.run.RunConfig.workflow_name], [`trace_id`][agents.run.RunConfig.trace_id], [`group_id`][agents.run.RunConfig.group_id]: Sets the tracing workflow name, trace ID and trace group ID for the run. We recommend at least setting `workflow_name`. The session ID is an optional field that lets you link traces across multiple runs. +- [`workflow_name`][agents.run.RunConfig.workflow_name], [`trace_id`][agents.run.RunConfig.trace_id], [`group_id`][agents.run.RunConfig.group_id]: Sets the tracing workflow name, trace ID and trace group ID for the run. We recommend at least setting `workflow_name`. The group ID is an optional field that lets you link traces across multiple runs. - [`trace_metadata`][agents.run.RunConfig.trace_metadata]: Metadata to include on all traces. ## Conversations/chat threads diff --git a/docs/scripts/translate_docs.py b/docs/scripts/translate_docs.py new file mode 100644 index 00000000..b2e8b44f --- /dev/null +++ b/docs/scripts/translate_docs.py @@ -0,0 +1,288 @@ +# ruff: noqa +import os +from openai import OpenAI +from concurrent.futures import ThreadPoolExecutor + +# import logging +# logging.basicConfig(level=logging.INFO) +# logging.getLogger("openai").setLevel(logging.DEBUG) + +OPENAI_MODEL = os.environ.get("OPENAI_MODEL", "o3") + +ENABLE_CODE_SNIPPET_EXCLUSION = True +# gpt-4.5 needed this for better quality +ENABLE_SMALL_CHUNK_TRANSLATION = False + +SEARCH_EXCLUSION = """--- +search: + exclude: true +--- +""" + + +# Define the source and target directories +source_dir = "docs" +languages = { + "ja": "Japanese", + # Add more languages here, e.g., "fr": "French" +} + +# Initialize OpenAI client +openai_client = OpenAI(api_key=os.getenv("OPENAI_API_KEY")) + +# Define dictionaries for translation control +do_not_translate = [ + "OpenAI", + "Agents SDK", + "Hello World", + "Model context protocol", + "MCP", + "structured outputs", + "Chain-of-Thought", + "Chat Completions", + "Computer-Using Agent", + "Code Interpreter", + "Function Calling", + "LLM", + "Operator", + "Playground", + "Realtime API", + "Sora", + # Add more terms here +] + +eng_to_non_eng_mapping = { + "ja": { + "agents": "エージェント", + "computer use": "コンピュータ操作", + "OAI hosted tools": "OpenAI がホストするツール", + "well formed data": "適切な形式のデータ", + "guardrail": "ガードレール", + "handoffs": "ハンドオフ", + "function tools": "関数ツール", + "tracing": "トレーシング", + "code examples": "コード例", + "vector store": "ベクトルストア", + "deep research": "ディープリサーチ", + "category": "カテゴリー", + "user": "ユーザー", + "parameter": "パラメーター", + "processor": "プロセッサー", + "server": "サーバー", + "web search": "Web 検索", + "file search": "ファイル検索", + "streaming": "ストリーミング", + "system prompt": "システムプロンプト", + "Python first": "Python ファースト", + # Add more Japanese mappings here + }, + # Add more languages here +} +eng_to_non_eng_instructions = { + "common": [ + "* The term 'examples' must be code examples when the page mentions the code examples in the repo, it can be translated as either 'code examples' or 'sample code'.", + "* The term 'primitives' can be translated as basic components.", + "* When the terms 'instructions' and 'tools' are mentioned as API parameter names, they must be kept as is.", + "* The terms 'temperature', 'top_p', 'max_tokens', 'presence_penalty', 'frequency_penalty' as parameter names must be kept as is.", + ], + "ja": [ + "* The term 'result' in the Runner guide context must be translated like 'execution results'", + "* The term 'raw' in 'raw response events' must be kept as is", + "* You must consistently use polite wording such as です/ます rather than である/なのだ.", + # Add more Japanese mappings here + ], + # Add more languages here +} + + +def built_instructions(target_language: str, lang_code: str) -> str: + do_not_translate_terms = "\n".join(do_not_translate) + specific_terms = "\n".join( + [f"* {k} -> {v}" for k, v in eng_to_non_eng_mapping.get(lang_code, {}).items()] + ) + specific_instructions = "\n".join( + eng_to_non_eng_instructions.get("common", []) + + eng_to_non_eng_instructions.get(lang_code, []) + ) + return f"""You are an expert technical translator. + +Your task: translate the markdown passed as a user input from English into {target_language}. +The inputs are the official OpenAI Agents SDK framework documentation, and your translation outputs'll be used for serving the official {target_language} version of them. Thus, accuracy, clarity, and fidelity to the original are critical. + +############################ +## OUTPUT REQUIREMENTS ## +############################ +You must return **only** the translated markdown. Do not include any commentary, metadata, or explanations. The original markdown structure must be strictly preserved. + +######################### +## GENERAL RULES ## +######################### +- Be professional and polite. +- Keep the tone **natural** and concise. +- Do not omit any content. If a segment should stay in English, copy it verbatim. +- Do not change the markdown data structure, including the indentations. +- Section titles starting with # or ## must be a noun form rather than a sentence. +- Section titles must be translated except for the Do-Not-Translate list. +- Keep all placeholders such as `CODE_BLOCK_*` and `CODE_LINE_PREFIX` unchanged. +- Convert asset paths: `./assets/…` → `../assets/…`. + *Example:* `![img](./assets/pic.png)` → `![img](../assets/pic.png)` +- Treat the **Do‑Not‑Translate list** and **Term‑Specific list** as case‑insensitive; preserve the original casing you see. +- Skip translation for: + - Inline code surrounded by single back‑ticks ( `like_this` ). + - Fenced code blocks delimited by ``` or ~~~, including all comments inside them. + - Link URLs inside `[label](URL)` – translate the label, never the URL. + +######################### +## LANGUAGE‑SPECIFIC ## +######################### +*(applies only when {target_language} = Japanese)* +- Insert a half‑width space before and after all alphanumeric terms. +- Add a half‑width space just outside markdown emphasis markers: ` **太字** ` (good) vs `** 太字 **` (bad). + +######################### +## DO NOT TRANSLATE ## +######################### +When replacing the following terms, do not have extra spaces before/after them: +{do_not_translate_terms} + +######################### +## TERM‑SPECIFIC ## +######################### +Translate these terms exactly as provided (no extra spaces): +{specific_terms} + +######################### +## EXTRA GUIDELINES ## +######################### +{specific_instructions} + +######################### +## IF UNSURE ## +######################### +If you are uncertain about a term, leave the original English term in parentheses after your translation. + +######################### +## WORKFLOW ## +######################### + +Follow the following workflow to translate the given markdown text data: + +1. Read the input markdown text given by the user. +2. Translate the markdown file into {target_language}, carefully following the requirements above. +3. Perform a self-review to evaluate the quality of the translation, focusing on naturalness, accuracy, and consistency in detail. +4. If improvements are necessary, refine the content without changing the original meaning. +5. Continue improving the translation until you are fully satisfied with the result. +6. Once the final output is ready, return **only** the translated markdown text. No extra commentary. +""" + + +# Function to translate and save files +def translate_file(file_path: str, target_path: str, lang_code: str) -> None: + print(f"Translating {file_path} into a different language: {lang_code}") + with open(file_path, encoding="utf-8") as f: + content = f.read() + + # Split content into lines + lines: list[str] = content.splitlines() + chunks: list[str] = [] + current_chunk: list[str] = [] + + # Split content into chunks of up to 120 lines, ensuring splits occur before section titles + in_code_block = False + code_blocks: list[str] = [] + code_block_chunks: list[str] = [] + for line in lines: + if ( + ENABLE_SMALL_CHUNK_TRANSLATION is True + and len(current_chunk) >= 120 # required for gpt-4.5 + and not in_code_block + and line.startswith("#") + ): + chunks.append("\n".join(current_chunk)) + current_chunk = [] + if ENABLE_CODE_SNIPPET_EXCLUSION is True and line.strip().startswith("```"): + code_block_chunks.append(line) + if in_code_block is True: + code_blocks.append("\n".join(code_block_chunks)) + current_chunk.append(f"CODE_BLOCK_{(len(code_blocks) - 1):02}") + code_block_chunks.clear() + in_code_block = not in_code_block + continue + if in_code_block is True: + code_block_chunks.append(line) + else: + current_chunk.append(line) + if current_chunk: + chunks.append("\n".join(current_chunk)) + + # Translate each chunk separately and combine results + translated_content: list[str] = [] + for chunk in chunks: + instructions = built_instructions(languages[lang_code], lang_code) + if OPENAI_MODEL.startswith("o"): + response = openai_client.responses.create( + model=OPENAI_MODEL, + instructions=instructions, + input=chunk, + ) + translated_content.append(response.output_text) + else: + response = openai_client.responses.create( + model=OPENAI_MODEL, + instructions=instructions, + input=chunk, + temperature=0.0, + ) + translated_content.append(response.output_text) + + translated_text = "\n".join(translated_content) + for idx, code_block in enumerate(code_blocks): + translated_text = translated_text.replace(f"CODE_BLOCK_{idx:02}", code_block) + + # FIXME: enable mkdocs search plugin to seamlessly work with i18n plugin + translated_text = SEARCH_EXCLUSION + translated_text + # Save the combined translated content + with open(target_path, "w", encoding="utf-8") as f: + f.write(translated_text) + + +def translate_single_source_file(file_path: str) -> None: + relative_path = os.path.relpath(file_path, source_dir) + if "ref/" in relative_path or not file_path.endswith(".md"): + return + + for lang_code in languages: + target_dir = os.path.join(source_dir, lang_code) + target_path = os.path.join(target_dir, relative_path) + + # Ensure the target directory exists + os.makedirs(os.path.dirname(target_path), exist_ok=True) + + # Translate and save the file + translate_file(file_path, target_path, lang_code) + + +def main(): + # Traverse the source directory + for root, _, file_names in os.walk(source_dir): + # Skip the target directories + if any(lang in root for lang in languages): + continue + # Increasing this will make the translation faster; you can decide considering the model's capacity + concurrency = 6 + with ThreadPoolExecutor(max_workers=concurrency) as executor: + futures = [] + for file_name in file_names: + filepath = os.path.join(root, file_name) + futures.append(executor.submit(translate_single_source_file, filepath)) + if len(futures) >= concurrency: + for future in futures: + future.result() + futures.clear() + + print("Translation completed.") + + +if __name__ == "__main__": + # translate_single_source_file("docs/index.md") + main() diff --git a/docs/tools.md b/docs/tools.md index f7a88691..5fe2eced 100644 --- a/docs/tools.md +++ b/docs/tools.md @@ -259,6 +259,27 @@ async def main(): print(result.final_output) ``` +### Customizing tool-agents + +The `agent.as_tool` function is a convenience method to make it easy to turn an agent into a tool. It doesn't support all configuration though; for example, you can't set `max_turns`. For advanced use cases, use `Runner.run` directly in your tool implementation: + +```python +@function_tool +async def run_my_agent() -> str: + """A tool that runs the agent with custom configs". + + agent = Agent(name="My agent", instructions="...") + + result = await Runner.run( + agent, + input="...", + max_turns=5, + run_config=... + ) + + return str(result.final_output) +``` + ## Handling errors in function tools When you create a function tool via `@function_tool`, you can pass a `failure_error_function`. This is a function that provides an error response to the LLM in case the tool call crashes. diff --git a/docs/tracing.md b/docs/tracing.md index 8c68c208..4a9c1bd9 100644 --- a/docs/tracing.md +++ b/docs/tracing.md @@ -101,7 +101,9 @@ To customize this default setup, to send traces to alternative or additional bac - [Weights & Biases](https://weave-docs.wandb.ai/guides/integrations/openai_agents) - [Arize-Phoenix](https://docs.arize.com/phoenix/tracing/integrations-tracing/openai-agents-sdk) -- [MLflow](https://mlflow.org/docs/latest/tracing/integrations/openai-agent) +- [Future AGI](https://docs.futureagi.com/future-agi/products/observability/auto-instrumentation/openai_agents) +- [MLflow (self-hosted/OSS](https://mlflow.org/docs/latest/tracing/integrations/openai-agent) +- [MLflow (Databricks hosted](https://docs.databricks.com/aws/en/mlflow/mlflow-tracing#-automatic-tracing) - [Braintrust](https://braintrust.dev/docs/guides/traces/integrations#openai-agents-sdk) - [Pydantic Logfire](https://logfire.pydantic.dev/docs/integrations/llms/openai/#openai-agents) - [AgentOps](https://docs.agentops.ai/v1/integrations/agentssdk) @@ -111,3 +113,6 @@ To customize this default setup, to send traces to alternative or additional bac - [Maxim AI](https://www.getmaxim.ai/docs/observe/integrations/openai-agents-sdk) - [Comet Opik](https://www.comet.com/docs/opik/tracing/integrations/openai_agents) - [Langfuse](https://langfuse.com/docs/integrations/openaiagentssdk/openai-agents) +- [Langtrace](https://docs.langtrace.ai/supported-integrations/llm-frameworks/openai-agents-sdk) +- [Okahu-Monocle](https://github.com/monocle2ai/monocle) +- [Galileo](https://v2docs.galileo.ai/integrations/openai-agent-integration#openai-agent-integration) diff --git a/docs/visualization.md b/docs/visualization.md index 00f3126d..409803f7 100644 --- a/docs/visualization.md +++ b/docs/visualization.md @@ -78,9 +78,7 @@ draw_graph(triage_agent).view() By default, `draw_graph` displays the graph inline. To save it as a file, specify a filename: ```python -draw_graph(triage_agent, filename="agent_graph.png") +draw_graph(triage_agent, filename="agent_graph") ``` This will generate `agent_graph.png` in the working directory. - - diff --git a/examples/agent_patterns/streaming_guardrails.py b/examples/agent_patterns/streaming_guardrails.py new file mode 100644 index 00000000..f4db2869 --- /dev/null +++ b/examples/agent_patterns/streaming_guardrails.py @@ -0,0 +1,93 @@ +from __future__ import annotations + +import asyncio + +from openai.types.responses import ResponseTextDeltaEvent +from pydantic import BaseModel, Field + +from agents import Agent, Runner + +""" +This example shows how to use guardrails as the model is streaming. Output guardrails run after the +final output has been generated; this example runs guardails every N tokens, allowing for early +termination if bad output is detected. + +The expected output is that you'll see a bunch of tokens stream in, then the guardrail will trigger +and stop the streaming. +""" + + +agent = Agent( + name="Assistant", + instructions=( + "You are a helpful assistant. You ALWAYS write long responses, making sure to be verbose " + "and detailed." + ), +) + + +class GuardrailOutput(BaseModel): + reasoning: str = Field( + description="Reasoning about whether the response could be understood by a ten year old." + ) + is_readable_by_ten_year_old: bool = Field( + description="Whether the response is understandable by a ten year old." + ) + + +guardrail_agent = Agent( + name="Checker", + instructions=( + "You will be given a question and a response. Your goal is to judge whether the response " + "is simple enough to be understood by a ten year old." + ), + output_type=GuardrailOutput, + model="gpt-4o-mini", +) + + +async def check_guardrail(text: str) -> GuardrailOutput: + result = await Runner.run(guardrail_agent, text) + return result.final_output_as(GuardrailOutput) + + +async def main(): + question = "What is a black hole, and how does it behave?" + result = Runner.run_streamed(agent, question) + current_text = "" + + # We will check the guardrail every N characters + next_guardrail_check_len = 300 + guardrail_task = None + + async for event in result.stream_events(): + if event.type == "raw_response_event" and isinstance(event.data, ResponseTextDeltaEvent): + print(event.data.delta, end="", flush=True) + current_text += event.data.delta + + # Check if it's time to run the guardrail check + # Note that we don't run the guardrail check if there's already a task running. An + # alternate implementation is to have N guardrails running, or cancel the previous + # one. + if len(current_text) >= next_guardrail_check_len and not guardrail_task: + print("Running guardrail check") + guardrail_task = asyncio.create_task(check_guardrail(current_text)) + next_guardrail_check_len += 300 + + # Every iteration of the loop, check if the guardrail has been triggered + if guardrail_task and guardrail_task.done(): + guardrail_result = guardrail_task.result() + if not guardrail_result.is_readable_by_ten_year_old: + print("\n\n================\n\n") + print(f"Guardrail triggered. Reasoning:\n{guardrail_result.reasoning}") + break + + # Do one final check on the final output + guardrail_result = await check_guardrail(current_text) + if not guardrail_result.is_readable_by_ten_year_old: + print("\n\n================\n\n") + print(f"Guardrail triggered. Reasoning:\n{guardrail_result.reasoning}") + + +if __name__ == "__main__": + asyncio.run(main()) diff --git a/examples/basic/local_image.py b/examples/basic/local_image.py new file mode 100644 index 00000000..d4a784ba --- /dev/null +++ b/examples/basic/local_image.py @@ -0,0 +1,48 @@ +import asyncio +import base64 +import os + +from agents import Agent, Runner + +FILEPATH = os.path.join(os.path.dirname(__file__), "media/image_bison.jpg") + + +def image_to_base64(image_path): + with open(image_path, "rb") as image_file: + encoded_string = base64.b64encode(image_file.read()).decode("utf-8") + return encoded_string + + +async def main(): + # Print base64-encoded image + b64_image = image_to_base64(FILEPATH) + + agent = Agent( + name="Assistant", + instructions="You are a helpful assistant.", + ) + + result = await Runner.run( + agent, + [ + { + "role": "user", + "content": [ + { + "type": "input_image", + "detail": "auto", + "image_url": f"data:image/jpeg;base64,{b64_image}", + } + ], + }, + { + "role": "user", + "content": "What do you see in this image?", + }, + ], + ) + print(result.final_output) + + +if __name__ == "__main__": + asyncio.run(main()) diff --git a/examples/basic/media/image_bison.jpg b/examples/basic/media/image_bison.jpg new file mode 100644 index 00000000..b113c91f Binary files /dev/null and b/examples/basic/media/image_bison.jpg differ diff --git a/examples/basic/non_strict_output_type.py b/examples/basic/non_strict_output_type.py new file mode 100644 index 00000000..49fcc4e2 --- /dev/null +++ b/examples/basic/non_strict_output_type.py @@ -0,0 +1,81 @@ +import asyncio +import json +from dataclasses import dataclass +from typing import Any + +from agents import Agent, AgentOutputSchema, AgentOutputSchemaBase, Runner + +"""This example demonstrates how to use an output type that is not in strict mode. Strict mode +allows us to guarantee valid JSON output, but some schemas are not strict-compatible. + +In this example, we define an output type that is not strict-compatible, and then we run the +agent with strict_json_schema=False. + +We also demonstrate a custom output type. + +To understand which schemas are strict-compatible, see: +https://platform.openai.com/docs/guides/structured-outputs?api-mode=responses#supported-schemas +""" + + +@dataclass +class OutputType: + jokes: dict[int, str] + """A list of jokes, indexed by joke number.""" + + +class CustomOutputSchema(AgentOutputSchemaBase): + """A demonstration of a custom output schema.""" + + def is_plain_text(self) -> bool: + return False + + def name(self) -> str: + return "CustomOutputSchema" + + def json_schema(self) -> dict[str, Any]: + return { + "type": "object", + "properties": {"jokes": {"type": "object", "properties": {"joke": {"type": "string"}}}}, + } + + def is_strict_json_schema(self) -> bool: + return False + + def validate_json(self, json_str: str) -> Any: + json_obj = json.loads(json_str) + # Just for demonstration, we'll return a list. + return list(json_obj["jokes"].values()) + + +async def main(): + agent = Agent( + name="Assistant", + instructions="You are a helpful assistant.", + output_type=OutputType, + ) + + input = "Tell me 3 short jokes." + + # First, let's try with a strict output type. This should raise an exception. + try: + result = await Runner.run(agent, input) + raise AssertionError("Should have raised an exception") + except Exception as e: + print(f"Error (expected): {e}") + + # Now let's try again with a non-strict output type. This should work. + # In some cases, it will raise an error - the schema isn't strict, so the model may + # produce an invalid JSON object. + agent.output_type = AgentOutputSchema(OutputType, strict_json_schema=False) + result = await Runner.run(agent, input) + print(result.final_output) + + # Finally, let's try a custom output type. + agent.output_type = CustomOutputSchema() + result = await Runner.run(agent, input) + print(result.final_output) + + +if __name__ == "__main__": + asyncio.run(main()) diff --git a/examples/basic/previous_response_id.py b/examples/basic/previous_response_id.py new file mode 100644 index 00000000..b00bf3aa --- /dev/null +++ b/examples/basic/previous_response_id.py @@ -0,0 +1,66 @@ +import asyncio + +from agents import Agent, Runner + +"""This demonstrates usage of the `previous_response_id` parameter to continue a conversation. +The second run passes the previous response ID to the model, which allows it to continue the +conversation without re-sending the previous messages. + +Notes: +1. This only applies to the OpenAI Responses API. Other models will ignore this parameter. +2. Responses are only stored for 30 days as of this writing, so in production you should +store the response ID along with an expiration date; if the response is no longer valid, +you'll need to re-send the previous conversation history. +""" + + +async def main(): + agent = Agent( + name="Assistant", + instructions="You are a helpful assistant. be VERY concise.", + ) + + result = await Runner.run(agent, "What is the largest country in South America?") + print(result.final_output) + # Brazil + + result = await Runner.run( + agent, + "What is the capital of that country?", + previous_response_id=result.last_response_id, + ) + print(result.final_output) + # Brasilia + + +async def main_stream(): + agent = Agent( + name="Assistant", + instructions="You are a helpful assistant. be VERY concise.", + ) + + result = Runner.run_streamed(agent, "What is the largest country in South America?") + + async for event in result.stream_events(): + if event.type == "raw_response_event" and event.data.type == "response.output_text.delta": + print(event.data.delta, end="", flush=True) + + print() + + result = Runner.run_streamed( + agent, + "What is the capital of that country?", + previous_response_id=result.last_response_id, + ) + + async for event in result.stream_events(): + if event.type == "raw_response_event" and event.data.type == "response.output_text.delta": + print(event.data.delta, end="", flush=True) + + +if __name__ == "__main__": + is_stream = input("Run in stream mode? (y/n): ") + if is_stream == "y": + asyncio.run(main_stream()) + else: + asyncio.run(main()) diff --git a/examples/basic/remote_image.py b/examples/basic/remote_image.py new file mode 100644 index 00000000..948a22d9 --- /dev/null +++ b/examples/basic/remote_image.py @@ -0,0 +1,31 @@ +import asyncio + +from agents import Agent, Runner + +URL = "https://upload.wikimedia.org/wikipedia/commons/0/0c/GoldenGateBridge-001.jpg" + + +async def main(): + agent = Agent( + name="Assistant", + instructions="You are a helpful assistant.", + ) + + result = await Runner.run( + agent, + [ + { + "role": "user", + "content": [{"type": "input_image", "detail": "auto", "image_url": URL}], + }, + { + "role": "user", + "content": "What do you see in this image?", + }, + ], + ) + print(result.final_output) + + +if __name__ == "__main__": + asyncio.run(main()) diff --git a/examples/financial_research_agent/main.py b/examples/financial_research_agent/main.py index 3fa8a7e0..b5b6cfdf 100644 --- a/examples/financial_research_agent/main.py +++ b/examples/financial_research_agent/main.py @@ -4,7 +4,7 @@ # Entrypoint for the financial bot example. -# Run this as `python -m examples.financial_bot.main` and enter a +# Run this as `python -m examples.financial_research_agent.main` and enter a # financial research query, for example: # "Write up an analysis of Apple Inc.'s most recent quarter." async def main() -> None: diff --git a/examples/financial_research_agent/manager.py b/examples/financial_research_agent/manager.py index a996296d..58ec11bf 100644 --- a/examples/financial_research_agent/manager.py +++ b/examples/financial_research_agent/manager.py @@ -38,7 +38,7 @@ async def run(self, query: str) -> None: with trace("Financial research trace", trace_id=trace_id): self.printer.update_item( "trace_id", - f"View trace: https://platform.openai.com/traces/{trace_id}", + f"View trace: https://platform.openai.com/traces/trace?trace_id={trace_id}", is_done=True, hide_checkmark=True, ) diff --git a/examples/hosted_mcp/__init__.py b/examples/hosted_mcp/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/examples/hosted_mcp/approvals.py b/examples/hosted_mcp/approvals.py new file mode 100644 index 00000000..2cabb3ee --- /dev/null +++ b/examples/hosted_mcp/approvals.py @@ -0,0 +1,61 @@ +import argparse +import asyncio + +from agents import ( + Agent, + HostedMCPTool, + MCPToolApprovalFunctionResult, + MCPToolApprovalRequest, + Runner, +) + +"""This example demonstrates how to use the hosted MCP support in the OpenAI Responses API, with +approval callbacks.""" + + +def approval_callback(request: MCPToolApprovalRequest) -> MCPToolApprovalFunctionResult: + answer = input(f"Approve running the tool `{request.data.name}`? (y/n) ") + result: MCPToolApprovalFunctionResult = {"approve": answer == "y"} + if not result["approve"]: + result["reason"] = "User denied" + return result + + +async def main(verbose: bool, stream: bool): + agent = Agent( + name="Assistant", + tools=[ + HostedMCPTool( + tool_config={ + "type": "mcp", + "server_label": "gitmcp", + "server_url": "https://gitmcp.io/openai/codex", + "require_approval": "always", + }, + on_approval_request=approval_callback, + ) + ], + ) + + if stream: + result = Runner.run_streamed(agent, "Which language is this repo written in?") + async for event in result.stream_events(): + if event.type == "run_item_stream_event": + print(f"Got event of type {event.item.__class__.__name__}") + print(f"Done streaming; final result: {result.final_output}") + else: + res = await Runner.run(agent, "Which language is this repo written in?") + print(res.final_output) + + if verbose: + for item in result.new_items: + print(item) + + +if __name__ == "__main__": + parser = argparse.ArgumentParser() + parser.add_argument("--verbose", action="store_true", default=False) + parser.add_argument("--stream", action="store_true", default=False) + args = parser.parse_args() + + asyncio.run(main(args.verbose, args.stream)) diff --git a/examples/hosted_mcp/simple.py b/examples/hosted_mcp/simple.py new file mode 100644 index 00000000..508c3a7a --- /dev/null +++ b/examples/hosted_mcp/simple.py @@ -0,0 +1,47 @@ +import argparse +import asyncio + +from agents import Agent, HostedMCPTool, Runner + +"""This example demonstrates how to use the hosted MCP support in the OpenAI Responses API, with +approvals not required for any tools. You should only use this for trusted MCP servers.""" + + +async def main(verbose: bool, stream: bool): + agent = Agent( + name="Assistant", + tools=[ + HostedMCPTool( + tool_config={ + "type": "mcp", + "server_label": "gitmcp", + "server_url": "https://gitmcp.io/openai/codex", + "require_approval": "never", + } + ) + ], + ) + + if stream: + result = Runner.run_streamed(agent, "Which language is this repo written in?") + async for event in result.stream_events(): + if event.type == "run_item_stream_event": + print(f"Got event of type {event.item.__class__.__name__}") + print(f"Done streaming; final result: {result.final_output}") + else: + res = await Runner.run(agent, "Which language is this repo written in?") + print(res.final_output) + # The repository is primarily written in multiple languages, including Rust and TypeScript... + + if verbose: + for item in result.new_items: + print(item) + + +if __name__ == "__main__": + parser = argparse.ArgumentParser() + parser.add_argument("--verbose", action="store_true", default=False) + parser.add_argument("--stream", action="store_true", default=False) + args = parser.parse_args() + + asyncio.run(main(args.verbose, args.stream)) diff --git a/examples/mcp/filesystem_example/README.md b/examples/mcp/filesystem_example/README.md index 83183fb4..4ed6ac46 100644 --- a/examples/mcp/filesystem_example/README.md +++ b/examples/mcp/filesystem_example/README.md @@ -5,7 +5,7 @@ This example uses the [filesystem MCP server](https://github.com/modelcontextpro Run it via: ``` -uv run python python examples/mcp/filesystem_example/main.py +uv run python examples/mcp/filesystem_example/main.py ``` ## Details diff --git a/examples/mcp/filesystem_example/main.py b/examples/mcp/filesystem_example/main.py index ae6fadd2..92c2b2db 100644 --- a/examples/mcp/filesystem_example/main.py +++ b/examples/mcp/filesystem_example/main.py @@ -45,7 +45,7 @@ async def main(): ) as server: trace_id = gen_trace_id() with trace(workflow_name="MCP Filesystem Example", trace_id=trace_id): - print(f"View trace: https://platform.openai.com/traces/{trace_id}\n") + print(f"View trace: https://platform.openai.com/traces/trace?trace_id={trace_id}\n") await run(server) diff --git a/examples/mcp/sse_example/README.md b/examples/mcp/sse_example/README.md index 605c2cc9..9a667d31 100644 --- a/examples/mcp/sse_example/README.md +++ b/examples/mcp/sse_example/README.md @@ -5,7 +5,7 @@ This example uses a local SSE server in [server.py](server.py). Run the example via: ``` -uv run python python examples/mcp/sse_example/main.py +uv run python examples/mcp/sse_example/main.py ``` ## Details diff --git a/examples/mcp/sse_example/main.py b/examples/mcp/sse_example/main.py index 024b087e..7c1137d2 100644 --- a/examples/mcp/sse_example/main.py +++ b/examples/mcp/sse_example/main.py @@ -46,7 +46,7 @@ async def main(): ) as server: trace_id = gen_trace_id() with trace(workflow_name="SSE Example", trace_id=trace_id): - print(f"View trace: https://platform.openai.com/traces/{trace_id}\n") + print(f"View trace: https://platform.openai.com/traces/trace?trace_id={trace_id}\n") await run(server) diff --git a/examples/mcp/streamablehttp_example/README.md b/examples/mcp/streamablehttp_example/README.md new file mode 100644 index 00000000..a07fe19b --- /dev/null +++ b/examples/mcp/streamablehttp_example/README.md @@ -0,0 +1,13 @@ +# MCP Streamable HTTP Example + +This example uses a local Streamable HTTP server in [server.py](server.py). + +Run the example via: + +``` +uv run python examples/mcp/streamablehttp_example/main.py +``` + +## Details + +The example uses the `MCPServerStreamableHttp` class from `agents.mcp`. The server runs in a sub-process at `https://localhost:8000/mcp`. diff --git a/examples/mcp/streamablehttp_example/main.py b/examples/mcp/streamablehttp_example/main.py new file mode 100644 index 00000000..cc95e798 --- /dev/null +++ b/examples/mcp/streamablehttp_example/main.py @@ -0,0 +1,83 @@ +import asyncio +import os +import shutil +import subprocess +import time +from typing import Any + +from agents import Agent, Runner, gen_trace_id, trace +from agents.mcp import MCPServer, MCPServerStreamableHttp +from agents.model_settings import ModelSettings + + +async def run(mcp_server: MCPServer): + agent = Agent( + name="Assistant", + instructions="Use the tools to answer the questions.", + mcp_servers=[mcp_server], + model_settings=ModelSettings(tool_choice="required"), + ) + + # Use the `add` tool to add two numbers + message = "Add these numbers: 7 and 22." + print(f"Running: {message}") + result = await Runner.run(starting_agent=agent, input=message) + print(result.final_output) + + # Run the `get_weather` tool + message = "What's the weather in Tokyo?" + print(f"\n\nRunning: {message}") + result = await Runner.run(starting_agent=agent, input=message) + print(result.final_output) + + # Run the `get_secret_word` tool + message = "What's the secret word?" + print(f"\n\nRunning: {message}") + result = await Runner.run(starting_agent=agent, input=message) + print(result.final_output) + + +async def main(): + async with MCPServerStreamableHttp( + name="Streamable HTTP Python Server", + params={ + "url": "http://localhost:8000/mcp", + }, + ) as server: + trace_id = gen_trace_id() + with trace(workflow_name="Streamable HTTP Example", trace_id=trace_id): + print(f"View trace: https://platform.openai.com/traces/trace?trace_id={trace_id}\n") + await run(server) + + +if __name__ == "__main__": + # Let's make sure the user has uv installed + if not shutil.which("uv"): + raise RuntimeError( + "uv is not installed. Please install it: https://docs.astral.sh/uv/getting-started/installation/" + ) + + # We'll run the Streamable HTTP server in a subprocess. Usually this would be a remote server, but for this + # demo, we'll run it locally at http://localhost:8000/mcp + process: subprocess.Popen[Any] | None = None + try: + this_dir = os.path.dirname(os.path.abspath(__file__)) + server_file = os.path.join(this_dir, "server.py") + + print("Starting Streamable HTTP server at http://localhost:8000/mcp ...") + + # Run `uv run server.py` to start the Streamable HTTP server + process = subprocess.Popen(["uv", "run", server_file]) + # Give it 3 seconds to start + time.sleep(3) + + print("Streamable HTTP server started. Running example...\n\n") + except Exception as e: + print(f"Error starting Streamable HTTP server: {e}") + exit(1) + + try: + asyncio.run(main()) + finally: + if process: + process.terminate() diff --git a/examples/mcp/streamablehttp_example/server.py b/examples/mcp/streamablehttp_example/server.py new file mode 100644 index 00000000..d8f83965 --- /dev/null +++ b/examples/mcp/streamablehttp_example/server.py @@ -0,0 +1,33 @@ +import random + +import requests +from mcp.server.fastmcp import FastMCP + +# Create server +mcp = FastMCP("Echo Server") + + +@mcp.tool() +def add(a: int, b: int) -> int: + """Add two numbers""" + print(f"[debug-server] add({a}, {b})") + return a + b + + +@mcp.tool() +def get_secret_word() -> str: + print("[debug-server] get_secret_word()") + return random.choice(["apple", "banana", "cherry"]) + + +@mcp.tool() +def get_current_weather(city: str) -> str: + print(f"[debug-server] get_current_weather({city})") + + endpoint = "https://wttr.in" + response = requests.get(f"{endpoint}/{city}") + return response.text + + +if __name__ == "__main__": + mcp.run(transport="streamable-http") diff --git a/examples/model_providers/litellm_auto.py b/examples/model_providers/litellm_auto.py new file mode 100644 index 00000000..12b1e891 --- /dev/null +++ b/examples/model_providers/litellm_auto.py @@ -0,0 +1,41 @@ +from __future__ import annotations + +import asyncio + +from agents import Agent, Runner, function_tool, set_tracing_disabled + +"""This example uses the built-in support for LiteLLM. To use this, ensure you have the +ANTHROPIC_API_KEY environment variable set. +""" + +set_tracing_disabled(disabled=True) + + +@function_tool +def get_weather(city: str): + print(f"[debug] getting weather for {city}") + return f"The weather in {city} is sunny." + + +async def main(): + agent = Agent( + name="Assistant", + instructions="You only respond in haikus.", + # We prefix with litellm/ to tell the Runner to use the LitellmModel + model="litellm/anthropic/claude-3-5-sonnet-20240620", + tools=[get_weather], + ) + + result = await Runner.run(agent, "What's the weather in Tokyo?") + print(result.final_output) + + +if __name__ == "__main__": + import os + + if os.getenv("ANTHROPIC_API_KEY") is None: + raise ValueError( + "ANTHROPIC_API_KEY is not set. Please set it the environment variable and try again." + ) + + asyncio.run(main()) diff --git a/examples/model_providers/litellm_provider.py b/examples/model_providers/litellm_provider.py new file mode 100644 index 00000000..4a1a696f --- /dev/null +++ b/examples/model_providers/litellm_provider.py @@ -0,0 +1,55 @@ +from __future__ import annotations + +import asyncio + +from agents import Agent, Runner, function_tool, set_tracing_disabled +from agents.extensions.models.litellm_model import LitellmModel + +"""This example uses the LitellmModel directly, to hit any model provider. +You can run it like this: +uv run examples/model_providers/litellm_provider.py --model anthropic/claude-3-5-sonnet-20240620 +or +uv run examples/model_providers/litellm_provider.py --model gemini/gemini-2.0-flash + +Find more providers here: https://docs.litellm.ai/docs/providers +""" + +set_tracing_disabled(disabled=True) + + +@function_tool +def get_weather(city: str): + print(f"[debug] getting weather for {city}") + return f"The weather in {city} is sunny." + + +async def main(model: str, api_key: str): + agent = Agent( + name="Assistant", + instructions="You only respond in haikus.", + model=LitellmModel(model=model, api_key=api_key), + tools=[get_weather], + ) + + result = await Runner.run(agent, "What's the weather in Tokyo?") + print(result.final_output) + + +if __name__ == "__main__": + # First try to get model/api key from args + import argparse + + parser = argparse.ArgumentParser() + parser.add_argument("--model", type=str, required=False) + parser.add_argument("--api-key", type=str, required=False) + args = parser.parse_args() + + model = args.model + if not model: + model = input("Enter a model name for Litellm: ") + + api_key = args.api_key + if not api_key: + api_key = input("Enter an API key for Litellm: ") + + asyncio.run(main(model, api_key)) diff --git a/examples/research_bot/agents/search_agent.py b/examples/research_bot/agents/search_agent.py index f69cfda8..61f91701 100644 --- a/examples/research_bot/agents/search_agent.py +++ b/examples/research_bot/agents/search_agent.py @@ -2,11 +2,11 @@ from agents.model_settings import ModelSettings INSTRUCTIONS = ( - "You are a research assistant. Given a search term, you search the web for that term and" - "produce a concise summary of the results. The summary must 2-3 paragraphs and less than 300" - "words. Capture the main points. Write succinctly, no need to have complete sentences or good" - "grammar. This will be consumed by someone synthesizing a report, so its vital you capture the" - "essence and ignore any fluff. Do not include any additional commentary other than the summary" + "You are a research assistant. Given a search term, you search the web for that term and " + "produce a concise summary of the results. The summary must be 2-3 paragraphs and less than 300 " + "words. Capture the main points. Write succinctly, no need to have complete sentences or good " + "grammar. This will be consumed by someone synthesizing a report, so its vital you capture the " + "essence and ignore any fluff. Do not include any additional commentary other than the summary " "itself." ) diff --git a/examples/research_bot/manager.py b/examples/research_bot/manager.py index 47306f14..dab68569 100644 --- a/examples/research_bot/manager.py +++ b/examples/research_bot/manager.py @@ -23,7 +23,7 @@ async def run(self, query: str) -> None: with trace("Research trace", trace_id=trace_id): self.printer.update_item( "trace_id", - f"View trace: https://platform.openai.com/traces/{trace_id}", + f"View trace: https://platform.openai.com/traces/trace?trace_id={trace_id}", is_done=True, hide_checkmark=True, ) diff --git a/examples/research_bot/sample_outputs/product_recs.txt b/examples/research_bot/sample_outputs/product_recs.txt index 78865f23..fd14d533 100644 --- a/examples/research_bot/sample_outputs/product_recs.txt +++ b/examples/research_bot/sample_outputs/product_recs.txt @@ -3,7 +3,7 @@ $ uv run python -m examples.research_bot.main What would you like to research? Best surfboards for beginners. I can catch my own waves, but previously used an 11ft board. What should I look for, what are my options? Various budget ranges. -View trace: https://platform.openai.com/traces/trace_... +View trace: https://platform.openai.com/traces/trace?trace_id=trace_... Starting research... ✅ Will perform 15 searches ✅ Searching... 15/15 completed diff --git a/examples/research_bot/sample_outputs/vacation.txt b/examples/research_bot/sample_outputs/vacation.txt index b2649981..491c0005 100644 --- a/examples/research_bot/sample_outputs/vacation.txt +++ b/examples/research_bot/sample_outputs/vacation.txt @@ -2,7 +2,7 @@ $ uv run python -m examples.research_bot.main What would you like to research? Caribbean vacation spots in April, optimizing for surfing, hiking and water sports -View trace: https://platform.openai.com/traces/trace_.... +View trace: https://platform.openai.com/traces/trace?trace_id=trace_.... Starting research... ✅ Will perform 15 searches ✅ Searching... 15/15 completed diff --git a/examples/tools/code_interpreter.py b/examples/tools/code_interpreter.py new file mode 100644 index 00000000..a5843ce3 --- /dev/null +++ b/examples/tools/code_interpreter.py @@ -0,0 +1,34 @@ +import asyncio + +from agents import Agent, CodeInterpreterTool, Runner, trace + + +async def main(): + agent = Agent( + name="Code interpreter", + instructions="You love doing math.", + tools=[ + CodeInterpreterTool( + tool_config={"type": "code_interpreter", "container": {"type": "auto"}}, + ) + ], + ) + + with trace("Code interpreter example"): + print("Solving math problem...") + result = Runner.run_streamed(agent, "What is the square root of273 * 312821 plus 1782?") + async for event in result.stream_events(): + if ( + event.type == "run_item_stream_event" + and event.item.type == "tool_call_item" + and event.item.raw_item.type == "code_interpreter_call" + ): + print(f"Code interpreter code:\n```\n{event.item.raw_item.code}\n```\n") + elif event.type == "run_item_stream_event": + print(f"Other event: {event.item.type}") + + print(f"Final output: {result.final_output}") + + +if __name__ == "__main__": + asyncio.run(main()) diff --git a/examples/tools/computer_use.py b/examples/tools/computer_use.py index 832255e8..0c17cf95 100644 --- a/examples/tools/computer_use.py +++ b/examples/tools/computer_use.py @@ -148,9 +148,11 @@ async def move(self, x: int, y: int) -> None: await self.page.mouse.move(x, y) async def keypress(self, keys: list[str]) -> None: - for key in keys: - mapped_key = CUA_KEY_TO_PLAYWRIGHT_KEY.get(key.lower(), key) - await self.page.keyboard.press(mapped_key) + mapped_keys = [CUA_KEY_TO_PLAYWRIGHT_KEY.get(key.lower(), key) for key in keys] + for key in mapped_keys: + await self.page.keyboard.down(key) + for key in reversed(mapped_keys): + await self.page.keyboard.up(key) async def drag(self, path: list[tuple[int, int]]) -> None: if not path: diff --git a/examples/tools/image_generator.py b/examples/tools/image_generator.py new file mode 100644 index 00000000..fd6fcc6b --- /dev/null +++ b/examples/tools/image_generator.py @@ -0,0 +1,54 @@ +import asyncio +import base64 +import os +import subprocess +import sys +import tempfile + +from agents import Agent, ImageGenerationTool, Runner, trace + + +def open_file(path: str) -> None: + if sys.platform.startswith("darwin"): + subprocess.run(["open", path], check=False) # macOS + elif os.name == "nt": # Windows + os.astartfile(path) # type: ignore + elif os.name == "posix": + subprocess.run(["xdg-open", path], check=False) # Linux/Unix + else: + print(f"Don't know how to open files on this platform: {sys.platform}") + + +async def main(): + agent = Agent( + name="Image generator", + instructions="You are a helpful agent.", + tools=[ + ImageGenerationTool( + tool_config={"type": "image_generation", "quality": "low"}, + ) + ], + ) + + with trace("Image generation example"): + print("Generating image, this may take a while...") + result = await Runner.run( + agent, "Create an image of a frog eating a pizza, comic book style." + ) + print(result.final_output) + for item in result.new_items: + if ( + item.type == "tool_call_item" + and item.raw_item.type == "image_generation_call" + and (img_result := item.raw_item.result) + ): + with tempfile.NamedTemporaryFile(suffix=".png", delete=False) as tmp: + tmp.write(base64.b64decode(img_result)) + temp_path = tmp.name + + # Open the image + open_file(temp_path) + + +if __name__ == "__main__": + asyncio.run(main()) diff --git a/mkdocs.yml b/mkdocs.yml index 5e08e321..ad719670 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -18,79 +18,9 @@ theme: primary: black logo: assets/logo.svg favicon: images/favicon-platform.svg -nav: - - Intro: index.md - - Quickstart: quickstart.md - - Examples: examples.md - - Documentation: - - agents.md - - running_agents.md - - results.md - - streaming.md - - tools.md - - mcp.md - - handoffs.md - - tracing.md - - context.md - - guardrails.md - - multi_agent.md - - models.md - - config.md - - visualization.md - - Voice agents: - - voice/quickstart.md - - voice/pipeline.md - - voice/tracing.md - - API Reference: - - Agents: - - ref/index.md - - ref/agent.md - - ref/run.md - - ref/tool.md - - ref/result.md - - ref/stream_events.md - - ref/handoffs.md - - ref/lifecycle.md - - ref/items.md - - ref/run_context.md - - ref/usage.md - - ref/exceptions.md - - ref/guardrail.md - - ref/model_settings.md - - ref/agent_output.md - - ref/function_schema.md - - ref/models/interface.md - - ref/models/openai_chatcompletions.md - - ref/models/openai_responses.md - - ref/mcp/server.md - - ref/mcp/util.md - - Tracing: - - ref/tracing/index.md - - ref/tracing/create.md - - ref/tracing/traces.md - - ref/tracing/spans.md - - ref/tracing/processor_interface.md - - ref/tracing/processors.md - - ref/tracing/scope.md - - ref/tracing/setup.md - - ref/tracing/span_data.md - - ref/tracing/util.md - - Voice: - - ref/voice/pipeline.md - - ref/voice/workflow.md - - ref/voice/input.md - - ref/voice/result.md - - ref/voice/pipeline_config.md - - ref/voice/events.md - - ref/voice/exceptions.md - - ref/voice/model.md - - ref/voice/utils.md - - ref/voice/models/openai_provider.md - - ref/voice/models/openai_stt.md - - ref/voice/models/openai_tts.md - - Extensions: - - ref/extensions/handoff_filters.md - - ref/extensions/handoff_prompt.md + +repo_name: openai-agents-python +repo_url: https://github.com/openai/openai-agents-python plugins: - search @@ -113,10 +43,130 @@ plugins: heading_level: 3 # Show inherited members inherited_members: true + - i18n: + docs_structure: folder + languages: + - locale: en + default: true + name: English + build: true + nav: + - Intro: index.md + - Quickstart: quickstart.md + - Examples: examples.md + - Documentation: + - agents.md + - running_agents.md + - results.md + - streaming.md + - tools.md + - mcp.md + - handoffs.md + - tracing.md + - context.md + - guardrails.md + - multi_agent.md + - Models: + - models/index.md + - models/litellm.md + - config.md + - visualization.md + - Voice agents: + - voice/quickstart.md + - voice/pipeline.md + - voice/tracing.md + - API Reference: + - Agents: + - ref/index.md + - ref/agent.md + - ref/run.md + - ref/tool.md + - ref/result.md + - ref/stream_events.md + - ref/handoffs.md + - ref/lifecycle.md + - ref/items.md + - ref/run_context.md + - ref/usage.md + - ref/exceptions.md + - ref/guardrail.md + - ref/model_settings.md + - ref/agent_output.md + - ref/function_schema.md + - ref/models/interface.md + - ref/models/openai_chatcompletions.md + - ref/models/openai_responses.md + - ref/mcp/server.md + - ref/mcp/util.md + - Tracing: + - ref/tracing/index.md + - ref/tracing/create.md + - ref/tracing/traces.md + - ref/tracing/spans.md + - ref/tracing/processor_interface.md + - ref/tracing/processors.md + - ref/tracing/scope.md + - ref/tracing/setup.md + - ref/tracing/span_data.md + - ref/tracing/util.md + - Voice: + - ref/voice/pipeline.md + - ref/voice/workflow.md + - ref/voice/input.md + - ref/voice/result.md + - ref/voice/pipeline_config.md + - ref/voice/events.md + - ref/voice/exceptions.md + - ref/voice/model.md + - ref/voice/utils.md + - ref/voice/models/openai_provider.md + - ref/voice/models/openai_stt.md + - ref/voice/models/openai_tts.md + - Extensions: + - ref/extensions/handoff_filters.md + - ref/extensions/handoff_prompt.md + - ref/extensions/litellm.md + + - locale: ja + name: 日本語 + build: true + nav: + - はじめに: index.md + - クイックスタート: quickstart.md + - コード例: examples.md + - ドキュメント: + - agents.md + - running_agents.md + - results.md + - streaming.md + - tools.md + - mcp.md + - handoffs.md + - tracing.md + - context.md + - guardrails.md + - multi_agent.md + - モデル: + - models/index.md + - models/litellm.md + - config.md + - visualization.md + - 音声エージェント: + - voice/quickstart.md + - voice/pipeline.md + - voice/tracing.md extra: # Remove material generation message in footer generator: false + language: en + alternate: + - name: English + link: /openai-agents-python/ + lang: en + - name: 日本語 + link: /openai-agents-python/ja/ + lang: ja markdown_extensions: - pymdownx.superfences: diff --git a/pyproject.toml b/pyproject.toml index ab1be5ed..38a2f2b6 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,19 +1,19 @@ [project] name = "openai-agents" -version = "0.0.7" +version = "0.0.16" description = "OpenAI Agents SDK" readme = "README.md" requires-python = ">=3.9" license = "MIT" authors = [{ name = "OpenAI", email = "support@openai.com" }] dependencies = [ - "openai>=1.66.5", + "openai>=1.81.0", "pydantic>=2.10, <3", "griffe>=1.5.6, <2", "typing-extensions>=4.12.2, <5", "requests>=2.0, <3", "types-requests>=2.0, <3", - "mcp; python_version >= '3.10'", + "mcp>=1.8.0, <2; python_version >= '3.10'", ] classifiers = [ "Typing :: Typed", @@ -36,6 +36,7 @@ Repository = "https://github.com/openai/openai-agents-python" [project.optional-dependencies] voice = ["numpy>=2.2.0, <3; python_version>='3.10'", "websockets>=15.0, <16"] viz = ["graphviz>=0.17"] +litellm = ["litellm>=1.67.4.post1, <2"] [dependency-groups] dev = [ @@ -44,20 +45,23 @@ dev = [ "pytest", "pytest-asyncio", "pytest-mock>=3.14.0", - "rich", + "rich>=13.1.0, <14", "mkdocs>=1.6.0", "mkdocs-material>=9.6.0", "mkdocstrings[python]>=0.28.0", + "mkdocs-static-i18n", "coverage>=7.6.12", "playwright==1.50.0", "inline-snapshot>=0.20.7", "pynput", "types-pynput", "sounddevice", - "pynput", "textual", "websockets", "graphviz", + "mkdocs-static-i18n>=1.3.0", + "eval-type-backport>=0.2.2", + "fastapi >= 0.110.0, <1", ] [tool.uv.workspace] diff --git a/src/agents/__init__.py b/src/agents/__init__.py index 242f5649..58949157 100644 --- a/src/agents/__init__.py +++ b/src/agents/__init__.py @@ -6,7 +6,7 @@ from . import _config from .agent import Agent, ToolsToFinalOutputFunction, ToolsToFinalOutputResult -from .agent_output import AgentOutputSchema +from .agent_output import AgentOutputSchema, AgentOutputSchemaBase from .computer import AsyncComputer, Button, Computer, Environment from .exceptions import ( AgentsException, @@ -54,10 +54,19 @@ StreamEvent, ) from .tool import ( + CodeInterpreterTool, ComputerTool, FileSearchTool, FunctionTool, FunctionToolResult, + HostedMCPTool, + ImageGenerationTool, + LocalShellCommandRequest, + LocalShellExecutor, + LocalShellTool, + MCPToolApprovalFunction, + MCPToolApprovalFunctionResult, + MCPToolApprovalRequest, Tool, WebSearchTool, default_tool_error_function, @@ -100,6 +109,7 @@ transcription_span, ) from .usage import Usage +from .version import __version__ def set_default_openai_key(key: str, use_for_tracing: bool = True) -> None: @@ -157,6 +167,7 @@ def enable_verbose_stdout_logging(): "OpenAIProvider", "OpenAIResponsesModel", "AgentOutputSchema", + "AgentOutputSchemaBase", "Computer", "AsyncComputer", "Environment", @@ -204,8 +215,17 @@ def enable_verbose_stdout_logging(): "FunctionToolResult", "ComputerTool", "FileSearchTool", + "CodeInterpreterTool", + "ImageGenerationTool", + "LocalShellCommandRequest", + "LocalShellExecutor", + "LocalShellTool", "Tool", "WebSearchTool", + "HostedMCPTool", + "MCPToolApprovalFunction", + "MCPToolApprovalRequest", + "MCPToolApprovalFunctionResult", "function_tool", "Usage", "add_trace_processor", @@ -247,4 +267,5 @@ def enable_verbose_stdout_logging(): "gen_trace_id", "gen_span_id", "default_tool_error_function", + "__version__", ] diff --git a/src/agents/_run_impl.py b/src/agents/_run_impl.py index 94c181b7..2cfa270e 100644 --- a/src/agents/_run_impl.py +++ b/src/agents/_run_impl.py @@ -14,6 +14,9 @@ ResponseFunctionWebSearch, ResponseOutputMessage, ) +from openai.types.responses.response_code_interpreter_tool_call import ( + ResponseCodeInterpreterToolCall, +) from openai.types.responses.response_computer_tool_call import ( ActionClick, ActionDoubleClick, @@ -25,11 +28,17 @@ ActionType, ActionWait, ) -from openai.types.responses.response_input_param import ComputerCallOutput +from openai.types.responses.response_input_param import ComputerCallOutput, McpApprovalResponse +from openai.types.responses.response_output_item import ( + ImageGenerationCall, + LocalShellCall, + McpApprovalRequest, + McpListTools, +) from openai.types.responses.response_reasoning_item import ResponseReasoningItem from .agent import Agent, ToolsToFinalOutputResult -from .agent_output import AgentOutputSchema +from .agent_output import AgentOutputSchemaBase from .computer import AsyncComputer, Computer from .exceptions import AgentsException, ModelBehaviorError, UserError from .guardrail import InputGuardrail, InputGuardrailResult, OutputGuardrail, OutputGuardrailResult @@ -38,6 +47,9 @@ HandoffCallItem, HandoffOutputItem, ItemHelpers, + MCPApprovalRequestItem, + MCPApprovalResponseItem, + MCPListToolsItem, MessageOutputItem, ModelResponse, ReasoningItem, @@ -52,7 +64,16 @@ from .models.interface import ModelTracing from .run_context import RunContextWrapper, TContext from .stream_events import RunItemStreamEvent, StreamEvent -from .tool import ComputerTool, FunctionTool, FunctionToolResult, Tool +from .tool import ( + ComputerTool, + FunctionTool, + FunctionToolResult, + HostedMCPTool, + LocalShellCommandRequest, + LocalShellTool, + MCPToolApprovalRequest, + Tool, +) from .tracing import ( SpanError, Trace, @@ -112,15 +133,29 @@ class ToolRunComputerAction: computer_tool: ComputerTool +@dataclass +class ToolRunMCPApprovalRequest: + request_item: McpApprovalRequest + mcp_tool: HostedMCPTool + + +@dataclass +class ToolRunLocalShellCall: + tool_call: LocalShellCall + local_shell_tool: LocalShellTool + + @dataclass class ProcessedResponse: new_items: list[RunItem] handoffs: list[ToolRunHandoff] functions: list[ToolRunFunction] computer_actions: list[ToolRunComputerAction] + local_shell_calls: list[ToolRunLocalShellCall] tools_used: list[str] # Names of all tools used, including hosted tools + mcp_approval_requests: list[ToolRunMCPApprovalRequest] # Only requests with callbacks - def has_tools_to_run(self) -> bool: + def has_tools_or_approvals_to_run(self) -> bool: # Handoffs, functions and computer actions need local processing # Hosted tools have already run, so there's nothing to do. return any( @@ -128,6 +163,8 @@ def has_tools_to_run(self) -> bool: self.handoffs, self.functions, self.computer_actions, + self.local_shell_calls, + self.mcp_approval_requests, ] ) @@ -195,7 +232,7 @@ async def execute_tools_and_side_effects( pre_step_items: list[RunItem], new_response: ModelResponse, processed_response: ProcessedResponse, - output_schema: AgentOutputSchema | None, + output_schema: AgentOutputSchemaBase | None, hooks: RunHooks[TContext], context_wrapper: RunContextWrapper[TContext], run_config: RunConfig, @@ -226,7 +263,16 @@ async def execute_tools_and_side_effects( new_step_items.extend([result.run_item for result in function_results]) new_step_items.extend(computer_results) - # Second, check if there are any handoffs + # Next, run the MCP approval requests + if processed_response.mcp_approval_requests: + approval_results = await cls.execute_mcp_approval_requests( + agent=agent, + approval_requests=processed_response.mcp_approval_requests, + context_wrapper=context_wrapper, + ) + new_step_items.extend(approval_results) + + # Next, check if there are any handoffs if run_handoffs := processed_response.handoffs: return await cls.execute_handoffs( agent=agent, @@ -240,7 +286,7 @@ async def execute_tools_and_side_effects( run_config=run_config, ) - # Third, we'll check if the tool use should result in a final output + # Next, we'll check if the tool use should result in a final output check_tool_use = await cls._check_for_final_output_from_tools( agent=agent, tool_results=function_results, @@ -295,7 +341,7 @@ async def execute_tools_and_side_effects( ) elif ( not output_schema or output_schema.is_plain_text() - ) and not processed_response.has_tools_to_run(): + ) and not processed_response.has_tools_or_approvals_to_run(): return await cls.execute_final_output( agent=agent, original_input=original_input, @@ -335,7 +381,7 @@ def process_model_response( agent: Agent[Any], all_tools: list[Tool], response: ModelResponse, - output_schema: AgentOutputSchema | None, + output_schema: AgentOutputSchemaBase | None, handoffs: list[Handoff], ) -> ProcessedResponse: items: list[RunItem] = [] @@ -343,10 +389,20 @@ def process_model_response( run_handoffs = [] functions = [] computer_actions = [] + local_shell_calls = [] + mcp_approval_requests = [] tools_used: list[str] = [] handoff_map = {handoff.tool_name: handoff for handoff in handoffs} function_map = {tool.name: tool for tool in all_tools if isinstance(tool, FunctionTool)} computer_tool = next((tool for tool in all_tools if isinstance(tool, ComputerTool)), None) + local_shell_tool = next( + (tool for tool in all_tools if isinstance(tool, LocalShellTool)), None + ) + hosted_mcp_server_map = { + tool.tool_config["server_label"]: tool + for tool in all_tools + if isinstance(tool, HostedMCPTool) + } for output in response.output: if isinstance(output, ResponseOutputMessage): @@ -375,6 +431,54 @@ def process_model_response( computer_actions.append( ToolRunComputerAction(tool_call=output, computer_tool=computer_tool) ) + elif isinstance(output, McpApprovalRequest): + items.append(MCPApprovalRequestItem(raw_item=output, agent=agent)) + if output.server_label not in hosted_mcp_server_map: + _error_tracing.attach_error_to_current_span( + SpanError( + message="MCP server label not found", + data={"server_label": output.server_label}, + ) + ) + raise ModelBehaviorError(f"MCP server label {output.server_label} not found") + else: + server = hosted_mcp_server_map[output.server_label] + if server.on_approval_request: + mcp_approval_requests.append( + ToolRunMCPApprovalRequest( + request_item=output, + mcp_tool=server, + ) + ) + else: + logger.warning( + f"MCP server {output.server_label} has no on_approval_request hook" + ) + elif isinstance(output, McpListTools): + items.append(MCPListToolsItem(raw_item=output, agent=agent)) + elif isinstance(output, ImageGenerationCall): + items.append(ToolCallItem(raw_item=output, agent=agent)) + tools_used.append("image_generation") + elif isinstance(output, ResponseCodeInterpreterToolCall): + items.append(ToolCallItem(raw_item=output, agent=agent)) + tools_used.append("code_interpreter") + elif isinstance(output, LocalShellCall): + items.append(ToolCallItem(raw_item=output, agent=agent)) + tools_used.append("local_shell") + if not local_shell_tool: + _error_tracing.attach_error_to_current_span( + SpanError( + message="Local shell tool not found", + data={}, + ) + ) + raise ModelBehaviorError( + "Model produced local shell call without a local shell tool." + ) + local_shell_calls.append( + ToolRunLocalShellCall(tool_call=output, local_shell_tool=local_shell_tool) + ) + elif not isinstance(output, ResponseFunctionToolCall): logger.warning(f"Unexpected output type, ignoring: {type(output)}") continue @@ -416,7 +520,9 @@ def process_model_response( handoffs=run_handoffs, functions=functions, computer_actions=computer_actions, + local_shell_calls=local_shell_calls, tools_used=tools_used, + mcp_approval_requests=mcp_approval_requests, ) @classmethod @@ -489,6 +595,30 @@ async def run_single_tool( for tool_run, result in zip(tool_runs, results) ] + @classmethod + async def execute_local_shell_calls( + cls, + *, + agent: Agent[TContext], + calls: list[ToolRunLocalShellCall], + context_wrapper: RunContextWrapper[TContext], + hooks: RunHooks[TContext], + config: RunConfig, + ) -> list[RunItem]: + results: list[RunItem] = [] + # Need to run these serially, because each call can affect the local shell state + for call in calls: + results.append( + await LocalShellAction.execute( + agent=agent, + call=call, + hooks=hooks, + context_wrapper=context_wrapper, + config=config, + ) + ) + return results + @classmethod async def execute_computer_actions( cls, @@ -643,6 +773,40 @@ async def execute_handoffs( next_step=NextStepHandoff(new_agent), ) + @classmethod + async def execute_mcp_approval_requests( + cls, + *, + agent: Agent[TContext], + approval_requests: list[ToolRunMCPApprovalRequest], + context_wrapper: RunContextWrapper[TContext], + ) -> list[RunItem]: + async def run_single_approval(approval_request: ToolRunMCPApprovalRequest) -> RunItem: + callback = approval_request.mcp_tool.on_approval_request + assert callback is not None, "Callback is required for MCP approval requests" + maybe_awaitable_result = callback( + MCPToolApprovalRequest(context_wrapper, approval_request.request_item) + ) + if inspect.isawaitable(maybe_awaitable_result): + result = await maybe_awaitable_result + else: + result = maybe_awaitable_result + reason = result.get("reason", None) + raw_item: McpApprovalResponse = { + "approval_request_id": approval_request.request_item.id, + "approve": result["approve"], + "type": "mcp_approval_response", + } + if not result["approve"] and reason: + raw_item["reason"] = reason + return MCPApprovalResponseItem( + raw_item=raw_item, + agent=agent, + ) + + tasks = [run_single_approval(approval_request) for approval_request in approval_requests] + return await asyncio.gather(*tasks) + @classmethod async def execute_final_output( cls, @@ -727,6 +891,11 @@ def stream_step_result_to_queue( event = RunItemStreamEvent(item=item, name="tool_output") elif isinstance(item, ReasoningItem): event = RunItemStreamEvent(item=item, name="reasoning_item_created") + elif isinstance(item, MCPApprovalRequestItem): + event = RunItemStreamEvent(item=item, name="mcp_approval_requested") + elif isinstance(item, MCPListToolsItem): + event = RunItemStreamEvent(item=item, name="mcp_list_tools") + else: logger.warning(f"Unexpected item type: {type(item)}") event = None @@ -919,3 +1088,54 @@ async def _get_screenshot_async( await computer.wait() return await computer.screenshot() + + +class LocalShellAction: + @classmethod + async def execute( + cls, + *, + agent: Agent[TContext], + call: ToolRunLocalShellCall, + hooks: RunHooks[TContext], + context_wrapper: RunContextWrapper[TContext], + config: RunConfig, + ) -> RunItem: + await asyncio.gather( + hooks.on_tool_start(context_wrapper, agent, call.local_shell_tool), + ( + agent.hooks.on_tool_start(context_wrapper, agent, call.local_shell_tool) + if agent.hooks + else _coro.noop_coroutine() + ), + ) + + request = LocalShellCommandRequest( + ctx_wrapper=context_wrapper, + data=call.tool_call, + ) + output = call.local_shell_tool.executor(request) + if inspect.isawaitable(output): + result = await output + else: + result = output + + await asyncio.gather( + hooks.on_tool_end(context_wrapper, agent, call.local_shell_tool, result), + ( + agent.hooks.on_tool_end(context_wrapper, agent, call.local_shell_tool, result) + if agent.hooks + else _coro.noop_coroutine() + ), + ) + + return ToolCallOutputItem( + agent=agent, + output=output, + raw_item={ + "type": "local_shell_call_output", + "id": call.tool_call.call_id, + "output": result, + # "id": "out" + call.tool_call.id, # TODO remove this, it should be optional + }, + ) diff --git a/src/agents/agent.py b/src/agents/agent.py index 13bb464e..e22f579f 100644 --- a/src/agents/agent.py +++ b/src/agents/agent.py @@ -6,8 +6,9 @@ from dataclasses import dataclass, field from typing import TYPE_CHECKING, Any, Callable, Generic, Literal, cast -from typing_extensions import TypeAlias, TypedDict +from typing_extensions import NotRequired, TypeAlias, TypedDict +from .agent_output import AgentOutputSchemaBase from .guardrail import InputGuardrail, OutputGuardrail from .handoffs import Handoff from .items import ItemHelpers @@ -44,7 +45,7 @@ class ToolsToFinalOutputResult: MaybeAwaitable[ToolsToFinalOutputResult], ] """A function that takes a run context and a list of tool results, and returns a -`ToolToFinalOutputResult`. +`ToolsToFinalOutputResult`. """ @@ -53,6 +54,15 @@ class StopAtTools(TypedDict): """A list of tool names, any of which will stop the agent from running further.""" +class MCPConfig(TypedDict): + """Configuration for MCP servers.""" + + convert_schemas_to_strict: NotRequired[bool] + """If True, we will attempt to convert the MCP schemas to strict-mode schemas. This is a + best-effort conversion, so some schemas may not be convertible. Defaults to False. + """ + + @dataclass class Agent(Generic[TContext]): """An agent is an AI model configured with instructions, tools, guardrails, handoffs and more. @@ -99,7 +109,7 @@ class Agent(Generic[TContext]): """The model implementation to use when invoking the LLM. By default, if not set, the agent will use the default model configured in - `model_settings.DEFAULT_MODEL`. + `openai_provider.DEFAULT_MODEL` (currently "gpt-4o"). """ model_settings: ModelSettings = field(default_factory=ModelSettings) @@ -119,6 +129,9 @@ class Agent(Generic[TContext]): longer needed. """ + mcp_config: MCPConfig = field(default_factory=lambda: MCPConfig()) + """Configuration for MCP servers.""" + input_guardrails: list[InputGuardrail[TContext]] = field(default_factory=list) """A list of checks that run in parallel to the agent's execution, before generating a response. Runs only if the agent is the first agent in the chain. @@ -129,8 +142,14 @@ class Agent(Generic[TContext]): Runs only if the agent produces a final output. """ - output_type: type[Any] | None = None - """The type of the output object. If not provided, the output will be `str`.""" + output_type: type[Any] | AgentOutputSchemaBase | None = None + """The type of the output object. If not provided, the output will be `str`. In most cases, + you should pass a regular Python type (e.g. a dataclass, Pydantic model, TypedDict, etc). + You can customize this in two ways: + 1. If you want non-strict schemas, pass `AgentOutputSchema(MyClass, strict_json_schema=False)`. + 2. If you want to use a custom JSON schema (i.e. without using the SDK's automatic schema) + creation, subclass and pass an `AgentOutputSchemaBase` subclass. + """ hooks: AgentHooks[TContext] | None = None """A class that receives callbacks on various lifecycle events for this agent. @@ -224,7 +243,8 @@ async def get_system_prompt(self, run_context: RunContextWrapper[TContext]) -> s async def get_mcp_tools(self) -> list[Tool]: """Fetches the available tools from the MCP servers.""" - return await MCPUtil.get_all_function_tools(self.mcp_servers) + convert_schemas_to_strict = self.mcp_config.get("convert_schemas_to_strict", False) + return await MCPUtil.get_all_function_tools(self.mcp_servers, convert_schemas_to_strict) async def get_all_tools(self) -> list[Tool]: """All agent tools, including MCP tools and function tools.""" diff --git a/src/agents/agent_output.py b/src/agents/agent_output.py index 3262c57d..066bbd83 100644 --- a/src/agents/agent_output.py +++ b/src/agents/agent_output.py @@ -1,3 +1,4 @@ +import abc from dataclasses import dataclass from typing import Any @@ -12,8 +13,46 @@ _WRAPPER_DICT_KEY = "response" +class AgentOutputSchemaBase(abc.ABC): + """An object that captures the JSON schema of the output, as well as validating/parsing JSON + produced by the LLM into the output type. + """ + + @abc.abstractmethod + def is_plain_text(self) -> bool: + """Whether the output type is plain text (versus a JSON object).""" + pass + + @abc.abstractmethod + def name(self) -> str: + """The name of the output type.""" + pass + + @abc.abstractmethod + def json_schema(self) -> dict[str, Any]: + """Returns the JSON schema of the output. Will only be called if the output type is not + plain text. + """ + pass + + @abc.abstractmethod + def is_strict_json_schema(self) -> bool: + """Whether the JSON schema is in strict mode. Strict mode constrains the JSON schema + features, but guarantees valis JSON. See here for details: + https://platform.openai.com/docs/guides/structured-outputs#supported-schemas + """ + pass + + @abc.abstractmethod + def validate_json(self, json_str: str) -> Any: + """Validate a JSON string against the output type. You must return the validated object, + or raise a `ModelBehaviorError` if the JSON is invalid. + """ + pass + + @dataclass(init=False) -class AgentOutputSchema: +class AgentOutputSchema(AgentOutputSchemaBase): """An object that captures the JSON schema of the output, as well as validating/parsing JSON produced by the LLM into the output type. """ @@ -32,7 +71,7 @@ class AgentOutputSchema: _output_schema: dict[str, Any] """The JSON schema of the output.""" - strict_json_schema: bool + _strict_json_schema: bool """Whether the JSON schema is in strict mode. We **strongly** recommend setting this to True, as it increases the likelihood of correct JSON input. """ @@ -45,7 +84,7 @@ def __init__(self, output_type: type[Any], strict_json_schema: bool = True): setting this to True, as it increases the likelihood of correct JSON input. """ self.output_type = output_type - self.strict_json_schema = strict_json_schema + self._strict_json_schema = strict_json_schema if output_type is None or output_type is str: self._is_wrapped = False @@ -70,24 +109,35 @@ def __init__(self, output_type: type[Any], strict_json_schema: bool = True): self._type_adapter = TypeAdapter(output_type) self._output_schema = self._type_adapter.json_schema() - if self.strict_json_schema: - self._output_schema = ensure_strict_json_schema(self._output_schema) + if self._strict_json_schema: + try: + self._output_schema = ensure_strict_json_schema(self._output_schema) + except UserError as e: + raise UserError( + "Strict JSON schema is enabled, but the output type is not valid. " + "Either make the output type strict, or pass output_schema_strict=False to " + "your Agent()" + ) from e def is_plain_text(self) -> bool: """Whether the output type is plain text (versus a JSON object).""" return self.output_type is None or self.output_type is str + def is_strict_json_schema(self) -> bool: + """Whether the JSON schema is in strict mode.""" + return self._strict_json_schema + def json_schema(self) -> dict[str, Any]: """The JSON schema of the output type.""" if self.is_plain_text(): raise UserError("Output type is plain text, so no JSON schema is available") return self._output_schema - def validate_json(self, json_str: str, partial: bool = False) -> Any: + def validate_json(self, json_str: str) -> Any: """Validate a JSON string against the output type. Returns the validated object, or raises a `ModelBehaviorError` if the JSON is invalid. """ - validated = _json.validate_json(json_str, self._type_adapter, partial) + validated = _json.validate_json(json_str, self._type_adapter, partial=False) if self._is_wrapped: if not isinstance(validated, dict): _error_tracing.attach_error_to_current_span( @@ -113,7 +163,7 @@ def validate_json(self, json_str: str, partial: bool = False) -> Any: return validated[_WRAPPER_DICT_KEY] return validated - def output_type_name(self) -> str: + def name(self) -> str: """The name of the output type.""" return _type_to_str(self.output_type) diff --git a/src/agents/extensions/models/__init__.py b/src/agents/extensions/models/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/src/agents/extensions/models/litellm_model.py b/src/agents/extensions/models/litellm_model.py new file mode 100644 index 00000000..49e2d42d --- /dev/null +++ b/src/agents/extensions/models/litellm_model.py @@ -0,0 +1,394 @@ +from __future__ import annotations + +import json +import time +from collections.abc import AsyncIterator +from typing import Any, Literal, cast, overload + +import litellm.types +from openai.types.responses.response_usage import InputTokensDetails, OutputTokensDetails + +from agents.exceptions import ModelBehaviorError + +try: + import litellm +except ImportError as _e: + raise ImportError( + "`litellm` is required to use the LitellmModel. You can install it via the optional " + "dependency group: `pip install 'openai-agents[litellm]'`." + ) from _e + +from openai import NOT_GIVEN, AsyncStream, NotGiven +from openai.types.chat import ChatCompletionChunk, ChatCompletionMessageToolCall +from openai.types.chat.chat_completion_message import ( + Annotation, + AnnotationURLCitation, + ChatCompletionMessage, +) +from openai.types.chat.chat_completion_message_tool_call import Function +from openai.types.responses import Response + +from ... import _debug +from ...agent_output import AgentOutputSchemaBase +from ...handoffs import Handoff +from ...items import ModelResponse, TResponseInputItem, TResponseStreamEvent +from ...logger import logger +from ...model_settings import ModelSettings +from ...models.chatcmpl_converter import Converter +from ...models.chatcmpl_helpers import HEADERS +from ...models.chatcmpl_stream_handler import ChatCmplStreamHandler +from ...models.fake_id import FAKE_RESPONSES_ID +from ...models.interface import Model, ModelTracing +from ...tool import Tool +from ...tracing import generation_span +from ...tracing.span_data import GenerationSpanData +from ...tracing.spans import Span +from ...usage import Usage + + +class LitellmModel(Model): + """This class enables using any model via LiteLLM. LiteLLM allows you to acess OpenAPI, + Anthropic, Gemini, Mistral, and many other models. + See supported models here: [litellm models](https://docs.litellm.ai/docs/providers). + """ + + def __init__( + self, + model: str, + base_url: str | None = None, + api_key: str | None = None, + ): + self.model = model + self.base_url = base_url + self.api_key = api_key + + async def get_response( + self, + system_instructions: str | None, + input: str | list[TResponseInputItem], + model_settings: ModelSettings, + tools: list[Tool], + output_schema: AgentOutputSchemaBase | None, + handoffs: list[Handoff], + tracing: ModelTracing, + previous_response_id: str | None, + ) -> ModelResponse: + with generation_span( + model=str(self.model), + model_config=model_settings.to_json_dict() + | {"base_url": str(self.base_url or ""), "model_impl": "litellm"}, + disabled=tracing.is_disabled(), + ) as span_generation: + response = await self._fetch_response( + system_instructions, + input, + model_settings, + tools, + output_schema, + handoffs, + span_generation, + tracing, + stream=False, + ) + + assert isinstance(response.choices[0], litellm.types.utils.Choices) + + if _debug.DONT_LOG_MODEL_DATA: + logger.debug("Received model response") + else: + logger.debug( + f"LLM resp:\n{json.dumps(response.choices[0].message.model_dump(), indent=2)}\n" + ) + + if hasattr(response, "usage"): + response_usage = response.usage + usage = ( + Usage( + requests=1, + input_tokens=response_usage.prompt_tokens, + output_tokens=response_usage.completion_tokens, + total_tokens=response_usage.total_tokens, + input_tokens_details=InputTokensDetails( + cached_tokens=getattr( + response_usage.prompt_tokens_details, "cached_tokens", 0 + ) or 0 + ), + output_tokens_details=OutputTokensDetails( + reasoning_tokens=getattr( + response_usage.completion_tokens_details, "reasoning_tokens", 0 + ) or 0 + ), + ) + if response.usage + else Usage() + ) + else: + usage = Usage() + logger.warning("No usage information returned from Litellm") + + if tracing.include_data(): + span_generation.span_data.output = [response.choices[0].message.model_dump()] + span_generation.span_data.usage = { + "input_tokens": usage.input_tokens, + "output_tokens": usage.output_tokens, + } + + items = Converter.message_to_output_items( + LitellmConverter.convert_message_to_openai(response.choices[0].message) + ) + + return ModelResponse( + output=items, + usage=usage, + response_id=None, + ) + + async def stream_response( + self, + system_instructions: str | None, + input: str | list[TResponseInputItem], + model_settings: ModelSettings, + tools: list[Tool], + output_schema: AgentOutputSchemaBase | None, + handoffs: list[Handoff], + tracing: ModelTracing, + *, + previous_response_id: str | None, + ) -> AsyncIterator[TResponseStreamEvent]: + with generation_span( + model=str(self.model), + model_config=model_settings.to_json_dict() + | {"base_url": str(self.base_url or ""), "model_impl": "litellm"}, + disabled=tracing.is_disabled(), + ) as span_generation: + response, stream = await self._fetch_response( + system_instructions, + input, + model_settings, + tools, + output_schema, + handoffs, + span_generation, + tracing, + stream=True, + ) + + final_response: Response | None = None + async for chunk in ChatCmplStreamHandler.handle_stream(response, stream): + yield chunk + + if chunk.type == "response.completed": + final_response = chunk.response + + if tracing.include_data() and final_response: + span_generation.span_data.output = [final_response.model_dump()] + + if final_response and final_response.usage: + span_generation.span_data.usage = { + "input_tokens": final_response.usage.input_tokens, + "output_tokens": final_response.usage.output_tokens, + } + + @overload + async def _fetch_response( + self, + system_instructions: str | None, + input: str | list[TResponseInputItem], + model_settings: ModelSettings, + tools: list[Tool], + output_schema: AgentOutputSchemaBase | None, + handoffs: list[Handoff], + span: Span[GenerationSpanData], + tracing: ModelTracing, + stream: Literal[True], + ) -> tuple[Response, AsyncStream[ChatCompletionChunk]]: ... + + @overload + async def _fetch_response( + self, + system_instructions: str | None, + input: str | list[TResponseInputItem], + model_settings: ModelSettings, + tools: list[Tool], + output_schema: AgentOutputSchemaBase | None, + handoffs: list[Handoff], + span: Span[GenerationSpanData], + tracing: ModelTracing, + stream: Literal[False], + ) -> litellm.types.utils.ModelResponse: ... + + async def _fetch_response( + self, + system_instructions: str | None, + input: str | list[TResponseInputItem], + model_settings: ModelSettings, + tools: list[Tool], + output_schema: AgentOutputSchemaBase | None, + handoffs: list[Handoff], + span: Span[GenerationSpanData], + tracing: ModelTracing, + stream: bool = False, + ) -> litellm.types.utils.ModelResponse | tuple[Response, AsyncStream[ChatCompletionChunk]]: + converted_messages = Converter.items_to_messages(input) + + if system_instructions: + converted_messages.insert( + 0, + { + "content": system_instructions, + "role": "system", + }, + ) + if tracing.include_data(): + span.span_data.input = converted_messages + + parallel_tool_calls = ( + True + if model_settings.parallel_tool_calls and tools and len(tools) > 0 + else False + if model_settings.parallel_tool_calls is False + else None + ) + tool_choice = Converter.convert_tool_choice(model_settings.tool_choice) + response_format = Converter.convert_response_format(output_schema) + + converted_tools = [Converter.tool_to_openai(tool) for tool in tools] if tools else [] + + for handoff in handoffs: + converted_tools.append(Converter.convert_handoff_tool(handoff)) + + if _debug.DONT_LOG_MODEL_DATA: + logger.debug("Calling LLM") + else: + logger.debug( + f"Calling Litellm model: {self.model}\n" + f"{json.dumps(converted_messages, indent=2)}\n" + f"Tools:\n{json.dumps(converted_tools, indent=2)}\n" + f"Stream: {stream}\n" + f"Tool choice: {tool_choice}\n" + f"Response format: {response_format}\n" + ) + + reasoning_effort = model_settings.reasoning.effort if model_settings.reasoning else None + + stream_options = None + if stream and model_settings.include_usage is not None: + stream_options = {"include_usage": model_settings.include_usage} + + extra_kwargs = {} + if model_settings.extra_query: + extra_kwargs["extra_query"] = model_settings.extra_query + if model_settings.metadata: + extra_kwargs["metadata"] = model_settings.metadata + if model_settings.extra_body and isinstance(model_settings.extra_body, dict): + extra_kwargs.update(model_settings.extra_body) + + ret = await litellm.acompletion( + model=self.model, + messages=converted_messages, + tools=converted_tools or None, + temperature=model_settings.temperature, + top_p=model_settings.top_p, + frequency_penalty=model_settings.frequency_penalty, + presence_penalty=model_settings.presence_penalty, + max_tokens=model_settings.max_tokens, + tool_choice=self._remove_not_given(tool_choice), + response_format=self._remove_not_given(response_format), + parallel_tool_calls=parallel_tool_calls, + stream=stream, + stream_options=stream_options, + reasoning_effort=reasoning_effort, + extra_headers={**HEADERS, **(model_settings.extra_headers or {})}, + api_key=self.api_key, + base_url=self.base_url, + **extra_kwargs, + ) + + if isinstance(ret, litellm.types.utils.ModelResponse): + return ret + + response = Response( + id=FAKE_RESPONSES_ID, + created_at=time.time(), + model=self.model, + object="response", + output=[], + tool_choice=cast(Literal["auto", "required", "none"], tool_choice) + if tool_choice != NOT_GIVEN + else "auto", + top_p=model_settings.top_p, + temperature=model_settings.temperature, + tools=[], + parallel_tool_calls=parallel_tool_calls or False, + reasoning=model_settings.reasoning, + ) + return response, ret + + def _remove_not_given(self, value: Any) -> Any: + if isinstance(value, NotGiven): + return None + return value + + +class LitellmConverter: + @classmethod + def convert_message_to_openai( + cls, message: litellm.types.utils.Message + ) -> ChatCompletionMessage: + if message.role != "assistant": + raise ModelBehaviorError(f"Unsupported role: {message.role}") + + tool_calls = ( + [LitellmConverter.convert_tool_call_to_openai(tool) for tool in message.tool_calls] + if message.tool_calls + else None + ) + + provider_specific_fields = message.get("provider_specific_fields", None) + refusal = ( + provider_specific_fields.get("refusal", None) if provider_specific_fields else None + ) + + return ChatCompletionMessage( + content=message.content, + refusal=refusal, + role="assistant", + annotations=cls.convert_annotations_to_openai(message), + audio=message.get("audio", None), # litellm deletes audio if not present + tool_calls=tool_calls, + ) + + @classmethod + def convert_annotations_to_openai( + cls, message: litellm.types.utils.Message + ) -> list[Annotation] | None: + annotations: list[litellm.types.llms.openai.ChatCompletionAnnotation] | None = message.get( + "annotations", None + ) + if not annotations: + return None + + return [ + Annotation( + type="url_citation", + url_citation=AnnotationURLCitation( + start_index=annotation["url_citation"]["start_index"], + end_index=annotation["url_citation"]["end_index"], + url=annotation["url_citation"]["url"], + title=annotation["url_citation"]["title"], + ), + ) + for annotation in annotations + ] + + @classmethod + def convert_tool_call_to_openai( + cls, tool_call: litellm.types.utils.ChatCompletionMessageToolCall + ) -> ChatCompletionMessageToolCall: + return ChatCompletionMessageToolCall( + id=tool_call.id, + type="function", + function=Function( + name=tool_call.function.name or "", arguments=tool_call.function.arguments + ), + ) diff --git a/src/agents/extensions/models/litellm_provider.py b/src/agents/extensions/models/litellm_provider.py new file mode 100644 index 00000000..5a2dc166 --- /dev/null +++ b/src/agents/extensions/models/litellm_provider.py @@ -0,0 +1,21 @@ +from ...models.interface import Model, ModelProvider +from .litellm_model import LitellmModel + +DEFAULT_MODEL: str = "gpt-4.1" + + +class LitellmProvider(ModelProvider): + """A ModelProvider that uses LiteLLM to route to any model provider. You can use it via: + ```python + Runner.run(agent, input, run_config=RunConfig(model_provider=LitellmProvider())) + ``` + See supported models here: [litellm models](https://docs.litellm.ai/docs/providers). + + NOTE: API keys must be set via environment variables. If you're using models that require + additional configuration (e.g. Azure API base or version), those must also be set via the + environment variables that LiteLLM expects. If you have more advanced needs, we recommend + copy-pasting this class and making any modifications you need. + """ + + def get_model(self, model_name: str | None) -> Model: + return LitellmModel(model_name or DEFAULT_MODEL) diff --git a/src/agents/extensions/visualization.py b/src/agents/extensions/visualization.py index 5fb35062..888e262c 100644 --- a/src/agents/extensions/visualization.py +++ b/src/agents/extensions/visualization.py @@ -132,6 +132,6 @@ def draw_graph(agent: Agent, filename: Optional[str] = None) -> graphviz.Source: graph = graphviz.Source(dot_code) if filename: - graph.render(filename, format="png") + graph.render(filename, format="png", cleanup=True) return graph diff --git a/src/agents/function_schema.py b/src/agents/function_schema.py index 681affce..0e586896 100644 --- a/src/agents/function_schema.py +++ b/src/agents/function_schema.py @@ -131,7 +131,7 @@ def _detect_docstring_style(doc: str) -> DocstringStyle: @contextlib.contextmanager def _suppress_griffe_logging(): - # Supresses warnings about missing annotations for params + # Suppresses warnings about missing annotations for params logger = logging.getLogger("griffe") previous_level = logger.getEffectiveLevel() logger.setLevel(logging.ERROR) diff --git a/src/agents/items.py b/src/agents/items.py index c2af0dfc..64797ad2 100644 --- a/src/agents/items.py +++ b/src/agents/items.py @@ -18,7 +18,22 @@ ResponseOutputText, ResponseStreamEvent, ) -from openai.types.responses.response_input_item_param import ComputerCallOutput, FunctionCallOutput +from openai.types.responses.response_code_interpreter_tool_call import ( + ResponseCodeInterpreterToolCall, +) +from openai.types.responses.response_input_item_param import ( + ComputerCallOutput, + FunctionCallOutput, + LocalShellCallOutput, + McpApprovalResponse, +) +from openai.types.responses.response_output_item import ( + ImageGenerationCall, + LocalShellCall, + McpApprovalRequest, + McpCall, + McpListTools, +) from openai.types.responses.response_reasoning_item import ResponseReasoningItem from pydantic import BaseModel from typing_extensions import TypeAlias @@ -108,6 +123,10 @@ class HandoffOutputItem(RunItemBase[TResponseInputItem]): ResponseComputerToolCall, ResponseFileSearchToolCall, ResponseFunctionWebSearch, + McpCall, + ResponseCodeInterpreterToolCall, + ImageGenerationCall, + LocalShellCall, ] """A type that represents a tool call item.""" @@ -123,10 +142,12 @@ class ToolCallItem(RunItemBase[ToolCallItemTypes]): @dataclass -class ToolCallOutputItem(RunItemBase[Union[FunctionCallOutput, ComputerCallOutput]]): +class ToolCallOutputItem( + RunItemBase[Union[FunctionCallOutput, ComputerCallOutput, LocalShellCallOutput]] +): """Represents the output of a tool call.""" - raw_item: FunctionCallOutput | ComputerCallOutput + raw_item: FunctionCallOutput | ComputerCallOutput | LocalShellCallOutput """The raw item from the model.""" output: Any @@ -147,6 +168,36 @@ class ReasoningItem(RunItemBase[ResponseReasoningItem]): type: Literal["reasoning_item"] = "reasoning_item" +@dataclass +class MCPListToolsItem(RunItemBase[McpListTools]): + """Represents a call to an MCP server to list tools.""" + + raw_item: McpListTools + """The raw MCP list tools call.""" + + type: Literal["mcp_list_tools_item"] = "mcp_list_tools_item" + + +@dataclass +class MCPApprovalRequestItem(RunItemBase[McpApprovalRequest]): + """Represents a request for MCP approval.""" + + raw_item: McpApprovalRequest + """The raw MCP approval request.""" + + type: Literal["mcp_approval_request_item"] = "mcp_approval_request_item" + + +@dataclass +class MCPApprovalResponseItem(RunItemBase[McpApprovalResponse]): + """Represents a response to an MCP approval request.""" + + raw_item: McpApprovalResponse + """The raw MCP approval response.""" + + type: Literal["mcp_approval_response_item"] = "mcp_approval_response_item" + + RunItem: TypeAlias = Union[ MessageOutputItem, HandoffCallItem, @@ -154,6 +205,9 @@ class ReasoningItem(RunItemBase[ResponseReasoningItem]): ToolCallItem, ToolCallOutputItem, ReasoningItem, + MCPListToolsItem, + MCPApprovalRequestItem, + MCPApprovalResponseItem, ] """An item generated by an agent.""" @@ -166,9 +220,11 @@ class ModelResponse: usage: Usage """The usage information for the response.""" - referenceable_id: str | None + response_id: str | None """An ID for the response which can be used to refer to the response in subsequent calls to the model. Not supported by all model providers. + If using OpenAI models via the Responses API, this is the `response_id` parameter, and it can + be passed to `Runner.run`. """ def to_input_items(self) -> list[TResponseInputItem]: diff --git a/src/agents/mcp/__init__.py b/src/agents/mcp/__init__.py index 1a72a89f..d4eb8fa6 100644 --- a/src/agents/mcp/__init__.py +++ b/src/agents/mcp/__init__.py @@ -5,6 +5,8 @@ MCPServerSseParams, MCPServerStdio, MCPServerStdioParams, + MCPServerStreamableHttp, + MCPServerStreamableHttpParams, ) except ImportError: pass @@ -17,5 +19,7 @@ "MCPServerSseParams", "MCPServerStdio", "MCPServerStdioParams", + "MCPServerStreamableHttp", + "MCPServerStreamableHttpParams", "MCPUtil", ] diff --git a/src/agents/mcp/server.py b/src/agents/mcp/server.py index e70d7ce6..414b517a 100644 --- a/src/agents/mcp/server.py +++ b/src/agents/mcp/server.py @@ -3,13 +3,16 @@ import abc import asyncio from contextlib import AbstractAsyncContextManager, AsyncExitStack +from datetime import timedelta from pathlib import Path from typing import Any, Literal from anyio.streams.memory import MemoryObjectReceiveStream, MemoryObjectSendStream from mcp import ClientSession, StdioServerParameters, Tool as MCPTool, stdio_client from mcp.client.sse import sse_client -from mcp.types import CallToolResult, JSONRPCMessage +from mcp.client.streamable_http import GetSessionIdCallback, streamablehttp_client +from mcp.shared.message import SessionMessage +from mcp.types import CallToolResult, InitializeResult from typing_extensions import NotRequired, TypedDict from ..exceptions import UserError @@ -54,7 +57,7 @@ async def call_tool(self, tool_name: str, arguments: dict[str, Any] | None) -> C class _MCPServerWithClientSession(MCPServer, abc.ABC): """Base class for MCP servers that use a `ClientSession` to communicate with the server.""" - def __init__(self, cache_tools_list: bool): + def __init__(self, cache_tools_list: bool, client_session_timeout_seconds: float | None): """ Args: cache_tools_list: Whether to cache the tools list. If `True`, the tools list will be @@ -63,11 +66,16 @@ def __init__(self, cache_tools_list: bool): by calling `invalidate_tools_cache()`. You should set this to `True` if you know the server will not change its tools list, because it can drastically improve latency (by avoiding a round-trip to the server every time). + + client_session_timeout_seconds: the read timeout passed to the MCP ClientSession. """ self.session: ClientSession | None = None self.exit_stack: AsyncExitStack = AsyncExitStack() self._cleanup_lock: asyncio.Lock = asyncio.Lock() self.cache_tools_list = cache_tools_list + self.server_initialize_result: InitializeResult | None = None + + self.client_session_timeout_seconds = client_session_timeout_seconds # The cache is always dirty at startup, so that we fetch tools at least once self._cache_dirty = True @@ -78,8 +86,9 @@ def create_streams( self, ) -> AbstractAsyncContextManager[ tuple[ - MemoryObjectReceiveStream[JSONRPCMessage | Exception], - MemoryObjectSendStream[JSONRPCMessage], + MemoryObjectReceiveStream[SessionMessage | Exception], + MemoryObjectSendStream[SessionMessage], + GetSessionIdCallback | None ] ]: """Create the streams for the server.""" @@ -100,9 +109,22 @@ async def connect(self): """Connect to the server.""" try: transport = await self.exit_stack.enter_async_context(self.create_streams()) - read, write = transport - session = await self.exit_stack.enter_async_context(ClientSession(read, write)) - await session.initialize() + # streamablehttp_client returns (read, write, get_session_id) + # sse_client returns (read, write) + + read, write, *_ = transport + + session = await self.exit_stack.enter_async_context( + ClientSession( + read, + write, + timedelta(seconds=self.client_session_timeout_seconds) + if self.client_session_timeout_seconds + else None, + ) + ) + server_result = await session.initialize() + self.server_initialize_result = server_result self.session = session except Exception as e: logger.error(f"Error initializing MCP server: {e}") @@ -137,9 +159,10 @@ async def cleanup(self): async with self._cleanup_lock: try: await self.exit_stack.aclose() - self.session = None except Exception as e: logger.error(f"Error cleaning up server: {e}") + finally: + self.session = None class MCPServerStdioParams(TypedDict): @@ -182,6 +205,7 @@ def __init__( params: MCPServerStdioParams, cache_tools_list: bool = False, name: str | None = None, + client_session_timeout_seconds: float | None = 5, ): """Create a new MCP server based on the stdio transport. @@ -198,8 +222,9 @@ def __init__( improve latency (by avoiding a round-trip to the server every time). name: A readable name for the server. If not provided, we'll create one from the command. + client_session_timeout_seconds: the read timeout passed to the MCP ClientSession. """ - super().__init__(cache_tools_list) + super().__init__(cache_tools_list, client_session_timeout_seconds) self.params = StdioServerParameters( command=params["command"], @@ -216,8 +241,9 @@ def create_streams( self, ) -> AbstractAsyncContextManager[ tuple[ - MemoryObjectReceiveStream[JSONRPCMessage | Exception], - MemoryObjectSendStream[JSONRPCMessage], + MemoryObjectReceiveStream[SessionMessage | Exception], + MemoryObjectSendStream[SessionMessage], + GetSessionIdCallback | None ] ]: """Create the streams for the server.""" @@ -256,6 +282,7 @@ def __init__( params: MCPServerSseParams, cache_tools_list: bool = False, name: str | None = None, + client_session_timeout_seconds: float | None = 5, ): """Create a new MCP server based on the HTTP with SSE transport. @@ -273,8 +300,10 @@ def __init__( name: A readable name for the server. If not provided, we'll create one from the URL. + + client_session_timeout_seconds: the read timeout passed to the MCP ClientSession. """ - super().__init__(cache_tools_list) + super().__init__(cache_tools_list, client_session_timeout_seconds) self.params = params self._name = name or f"sse: {self.params['url']}" @@ -283,8 +312,9 @@ def create_streams( self, ) -> AbstractAsyncContextManager[ tuple[ - MemoryObjectReceiveStream[JSONRPCMessage | Exception], - MemoryObjectSendStream[JSONRPCMessage], + MemoryObjectReceiveStream[SessionMessage | Exception], + MemoryObjectSendStream[SessionMessage], + GetSessionIdCallback | None ] ]: """Create the streams for the server.""" @@ -299,3 +329,84 @@ def create_streams( def name(self) -> str: """A readable name for the server.""" return self._name + + +class MCPServerStreamableHttpParams(TypedDict): + """Mirrors the params in`mcp.client.streamable_http.streamablehttp_client`.""" + + url: str + """The URL of the server.""" + + headers: NotRequired[dict[str, str]] + """The headers to send to the server.""" + + timeout: NotRequired[timedelta] + """The timeout for the HTTP request. Defaults to 5 seconds.""" + + sse_read_timeout: NotRequired[timedelta] + """The timeout for the SSE connection, in seconds. Defaults to 5 minutes.""" + + terminate_on_close: NotRequired[bool] + """Terminate on close""" + + +class MCPServerStreamableHttp(_MCPServerWithClientSession): + """MCP server implementation that uses the Streamable HTTP transport. See the [spec] + (https://modelcontextprotocol.io/specification/2025-03-26/basic/transports#streamable-http) + for details. + """ + + def __init__( + self, + params: MCPServerStreamableHttpParams, + cache_tools_list: bool = False, + name: str | None = None, + client_session_timeout_seconds: float | None = 5, + ): + """Create a new MCP server based on the Streamable HTTP transport. + + Args: + params: The params that configure the server. This includes the URL of the server, + the headers to send to the server, the timeout for the HTTP request, and the + timeout for the Streamable HTTP connection and whether we need to + terminate on close. + + cache_tools_list: Whether to cache the tools list. If `True`, the tools list will be + cached and only fetched from the server once. If `False`, the tools list will be + fetched from the server on each call to `list_tools()`. The cache can be + invalidated by calling `invalidate_tools_cache()`. You should set this to `True` + if you know the server will not change its tools list, because it can drastically + improve latency (by avoiding a round-trip to the server every time). + + name: A readable name for the server. If not provided, we'll create one from the + URL. + + client_session_timeout_seconds: the read timeout passed to the MCP ClientSession. + """ + super().__init__(cache_tools_list, client_session_timeout_seconds) + + self.params = params + self._name = name or f"streamable_http: {self.params['url']}" + + def create_streams( + self, + ) -> AbstractAsyncContextManager[ + tuple[ + MemoryObjectReceiveStream[SessionMessage | Exception], + MemoryObjectSendStream[SessionMessage], + GetSessionIdCallback | None + ] + ]: + """Create the streams for the server.""" + return streamablehttp_client( + url=self.params["url"], + headers=self.params.get("headers", None), + timeout=self.params.get("timeout", timedelta(seconds=30)), + sse_read_timeout=self.params.get("sse_read_timeout", timedelta(seconds=60 * 5)), + terminate_on_close=self.params.get("terminate_on_close", True) + ) + + @property + def name(self) -> str: + """A readable name for the server.""" + return self._name diff --git a/src/agents/mcp/util.py b/src/agents/mcp/util.py index 36c18bea..bbfe1885 100644 --- a/src/agents/mcp/util.py +++ b/src/agents/mcp/util.py @@ -2,6 +2,8 @@ import json from typing import TYPE_CHECKING, Any +from agents.strict_schema import ensure_strict_json_schema + from .. import _debug from ..exceptions import AgentsException, ModelBehaviorError, UserError from ..logger import logger @@ -19,12 +21,14 @@ class MCPUtil: """Set of utilities for interop between MCP and Agents SDK tools.""" @classmethod - async def get_all_function_tools(cls, servers: list["MCPServer"]) -> list[Tool]: + async def get_all_function_tools( + cls, servers: list["MCPServer"], convert_schemas_to_strict: bool + ) -> list[Tool]: """Get all function tools from a list of MCP servers.""" tools = [] tool_names: set[str] = set() for server in servers: - server_tools = await cls.get_function_tools(server) + server_tools = await cls.get_function_tools(server, convert_schemas_to_strict) server_tool_names = {tool.name for tool in server_tools} if len(server_tool_names & tool_names) > 0: raise UserError( @@ -37,25 +41,42 @@ async def get_all_function_tools(cls, servers: list["MCPServer"]) -> list[Tool]: return tools @classmethod - async def get_function_tools(cls, server: "MCPServer") -> list[Tool]: + async def get_function_tools( + cls, server: "MCPServer", convert_schemas_to_strict: bool + ) -> list[Tool]: """Get all function tools from a single MCP server.""" with mcp_tools_span(server=server.name) as span: tools = await server.list_tools() span.span_data.result = [tool.name for tool in tools] - return [cls.to_function_tool(tool, server) for tool in tools] + return [cls.to_function_tool(tool, server, convert_schemas_to_strict) for tool in tools] @classmethod - def to_function_tool(cls, tool: "MCPTool", server: "MCPServer") -> FunctionTool: + def to_function_tool( + cls, tool: "MCPTool", server: "MCPServer", convert_schemas_to_strict: bool + ) -> FunctionTool: """Convert an MCP tool to an Agents SDK function tool.""" invoke_func = functools.partial(cls.invoke_mcp_tool, server, tool) + schema, is_strict = tool.inputSchema, False + + # MCP spec doesn't require the inputSchema to have `properties`, but OpenAI spec does. + if "properties" not in schema: + schema["properties"] = {} + + if convert_schemas_to_strict: + try: + schema = ensure_strict_json_schema(schema) + is_strict = True + except Exception as e: + logger.info(f"Error converting MCP schema to strict mode: {e}") + return FunctionTool( name=tool.name, description=tool.description or "", - params_json_schema=tool.inputSchema, + params_json_schema=schema, on_invoke_tool=invoke_func, - strict_json_schema=False, + strict_json_schema=is_strict, ) @classmethod diff --git a/src/agents/model_settings.py b/src/agents/model_settings.py index 2b0885ab..7b016c98 100644 --- a/src/agents/model_settings.py +++ b/src/agents/model_settings.py @@ -1,7 +1,12 @@ from __future__ import annotations +import dataclasses from dataclasses import dataclass, fields, replace -from typing import Literal +from typing import Any, Literal + +from openai._types import Body, Headers, Query +from openai.types.shared import Reasoning +from pydantic import BaseModel @dataclass @@ -40,10 +45,34 @@ class ModelSettings: max_tokens: int | None = None """The maximum number of output tokens to generate.""" + reasoning: Reasoning | None = None + """Configuration options for + [reasoning models](https://platform.openai.com/docs/guides/reasoning). + """ + + metadata: dict[str, str] | None = None + """Metadata to include with the model response call.""" + store: bool | None = None """Whether to store the generated model response for later retrieval. Defaults to True if not provided.""" + include_usage: bool | None = None + """Whether to include usage chunk. + Defaults to True if not provided.""" + + extra_query: Query | None = None + """Additional query fields to provide with the request. + Defaults to None if not provided.""" + + extra_body: Body | None = None + """Additional body fields to provide with the request. + Defaults to None if not provided.""" + + extra_headers: Headers | None = None + """Additional headers to provide with the request. + Defaults to None if not provided.""" + def resolve(self, override: ModelSettings | None) -> ModelSettings: """Produce a new ModelSettings by overlaying any non-None values from the override on top of this instance.""" @@ -56,3 +85,16 @@ def resolve(self, override: ModelSettings | None) -> ModelSettings: if getattr(override, field.name) is not None } return replace(self, **changes) + + def to_json_dict(self) -> dict[str, Any]: + dataclass_dict = dataclasses.asdict(self) + + json_dict: dict[str, Any] = {} + + for field_name, value in dataclass_dict.items(): + if isinstance(value, BaseModel): + json_dict[field_name] = value.model_dump(mode="json") + else: + json_dict[field_name] = value + + return json_dict diff --git a/src/agents/models/chatcmpl_converter.py b/src/agents/models/chatcmpl_converter.py new file mode 100644 index 00000000..1d599e8c --- /dev/null +++ b/src/agents/models/chatcmpl_converter.py @@ -0,0 +1,466 @@ +from __future__ import annotations + +import json +from collections.abc import Iterable +from typing import Any, Literal, cast + +from openai import NOT_GIVEN, NotGiven +from openai.types.chat import ( + ChatCompletionAssistantMessageParam, + ChatCompletionContentPartImageParam, + ChatCompletionContentPartParam, + ChatCompletionContentPartTextParam, + ChatCompletionDeveloperMessageParam, + ChatCompletionMessage, + ChatCompletionMessageParam, + ChatCompletionMessageToolCallParam, + ChatCompletionSystemMessageParam, + ChatCompletionToolChoiceOptionParam, + ChatCompletionToolMessageParam, + ChatCompletionUserMessageParam, +) +from openai.types.chat.chat_completion_tool_param import ChatCompletionToolParam +from openai.types.chat.completion_create_params import ResponseFormat +from openai.types.responses import ( + EasyInputMessageParam, + ResponseFileSearchToolCallParam, + ResponseFunctionToolCall, + ResponseFunctionToolCallParam, + ResponseInputContentParam, + ResponseInputImageParam, + ResponseInputTextParam, + ResponseOutputMessage, + ResponseOutputMessageParam, + ResponseOutputRefusal, + ResponseOutputText, +) +from openai.types.responses.response_input_param import FunctionCallOutput, ItemReference, Message + +from ..agent_output import AgentOutputSchemaBase +from ..exceptions import AgentsException, UserError +from ..handoffs import Handoff +from ..items import TResponseInputItem, TResponseOutputItem +from ..tool import FunctionTool, Tool +from .fake_id import FAKE_RESPONSES_ID + + +class Converter: + @classmethod + def convert_tool_choice( + cls, tool_choice: Literal["auto", "required", "none"] | str | None + ) -> ChatCompletionToolChoiceOptionParam | NotGiven: + if tool_choice is None: + return NOT_GIVEN + elif tool_choice == "auto": + return "auto" + elif tool_choice == "required": + return "required" + elif tool_choice == "none": + return "none" + else: + return { + "type": "function", + "function": { + "name": tool_choice, + }, + } + + @classmethod + def convert_response_format( + cls, final_output_schema: AgentOutputSchemaBase | None + ) -> ResponseFormat | NotGiven: + if not final_output_schema or final_output_schema.is_plain_text(): + return NOT_GIVEN + + return { + "type": "json_schema", + "json_schema": { + "name": "final_output", + "strict": final_output_schema.is_strict_json_schema(), + "schema": final_output_schema.json_schema(), + }, + } + + @classmethod + def message_to_output_items(cls, message: ChatCompletionMessage) -> list[TResponseOutputItem]: + items: list[TResponseOutputItem] = [] + + message_item = ResponseOutputMessage( + id=FAKE_RESPONSES_ID, + content=[], + role="assistant", + type="message", + status="completed", + ) + if message.content: + message_item.content.append( + ResponseOutputText(text=message.content, type="output_text", annotations=[]) + ) + if message.refusal: + message_item.content.append( + ResponseOutputRefusal(refusal=message.refusal, type="refusal") + ) + if message.audio: + raise AgentsException("Audio is not currently supported") + + if message_item.content: + items.append(message_item) + + if message.tool_calls: + for tool_call in message.tool_calls: + items.append( + ResponseFunctionToolCall( + id=FAKE_RESPONSES_ID, + call_id=tool_call.id, + arguments=tool_call.function.arguments, + name=tool_call.function.name, + type="function_call", + ) + ) + + return items + + @classmethod + def maybe_easy_input_message(cls, item: Any) -> EasyInputMessageParam | None: + if not isinstance(item, dict): + return None + + keys = item.keys() + # EasyInputMessageParam only has these two keys + if keys != {"content", "role"}: + return None + + role = item.get("role", None) + if role not in ("user", "assistant", "system", "developer"): + return None + + if "content" not in item: + return None + + return cast(EasyInputMessageParam, item) + + @classmethod + def maybe_input_message(cls, item: Any) -> Message | None: + if ( + isinstance(item, dict) + and item.get("type") == "message" + and item.get("role") + in ( + "user", + "system", + "developer", + ) + ): + return cast(Message, item) + + return None + + @classmethod + def maybe_file_search_call(cls, item: Any) -> ResponseFileSearchToolCallParam | None: + if isinstance(item, dict) and item.get("type") == "file_search_call": + return cast(ResponseFileSearchToolCallParam, item) + return None + + @classmethod + def maybe_function_tool_call(cls, item: Any) -> ResponseFunctionToolCallParam | None: + if isinstance(item, dict) and item.get("type") == "function_call": + return cast(ResponseFunctionToolCallParam, item) + return None + + @classmethod + def maybe_function_tool_call_output( + cls, + item: Any, + ) -> FunctionCallOutput | None: + if isinstance(item, dict) and item.get("type") == "function_call_output": + return cast(FunctionCallOutput, item) + return None + + @classmethod + def maybe_item_reference(cls, item: Any) -> ItemReference | None: + if isinstance(item, dict) and item.get("type") == "item_reference": + return cast(ItemReference, item) + return None + + @classmethod + def maybe_response_output_message(cls, item: Any) -> ResponseOutputMessageParam | None: + # ResponseOutputMessage is only used for messages with role assistant + if ( + isinstance(item, dict) + and item.get("type") == "message" + and item.get("role") == "assistant" + ): + return cast(ResponseOutputMessageParam, item) + return None + + @classmethod + def extract_text_content( + cls, content: str | Iterable[ResponseInputContentParam] + ) -> str | list[ChatCompletionContentPartTextParam]: + all_content = cls.extract_all_content(content) + if isinstance(all_content, str): + return all_content + out: list[ChatCompletionContentPartTextParam] = [] + for c in all_content: + if c.get("type") == "text": + out.append(cast(ChatCompletionContentPartTextParam, c)) + return out + + @classmethod + def extract_all_content( + cls, content: str | Iterable[ResponseInputContentParam] + ) -> str | list[ChatCompletionContentPartParam]: + if isinstance(content, str): + return content + out: list[ChatCompletionContentPartParam] = [] + + for c in content: + if isinstance(c, dict) and c.get("type") == "input_text": + casted_text_param = cast(ResponseInputTextParam, c) + out.append( + ChatCompletionContentPartTextParam( + type="text", + text=casted_text_param["text"], + ) + ) + elif isinstance(c, dict) and c.get("type") == "input_image": + casted_image_param = cast(ResponseInputImageParam, c) + if "image_url" not in casted_image_param or not casted_image_param["image_url"]: + raise UserError( + f"Only image URLs are supported for input_image {casted_image_param}" + ) + out.append( + ChatCompletionContentPartImageParam( + type="image_url", + image_url={ + "url": casted_image_param["image_url"], + "detail": casted_image_param.get("detail", "auto"), + }, + ) + ) + elif isinstance(c, dict) and c.get("type") == "input_file": + raise UserError(f"File uploads are not supported for chat completions {c}") + else: + raise UserError(f"Unknown content: {c}") + return out + + @classmethod + def items_to_messages( + cls, + items: str | Iterable[TResponseInputItem], + ) -> list[ChatCompletionMessageParam]: + """ + Convert a sequence of 'Item' objects into a list of ChatCompletionMessageParam. + + Rules: + - EasyInputMessage or InputMessage (role=user) => ChatCompletionUserMessageParam + - EasyInputMessage or InputMessage (role=system) => ChatCompletionSystemMessageParam + - EasyInputMessage or InputMessage (role=developer) => ChatCompletionDeveloperMessageParam + - InputMessage (role=assistant) => Start or flush a ChatCompletionAssistantMessageParam + - response_output_message => Also produces/flushes a ChatCompletionAssistantMessageParam + - tool calls get attached to the *current* assistant message, or create one if none. + - tool outputs => ChatCompletionToolMessageParam + """ + + if isinstance(items, str): + return [ + ChatCompletionUserMessageParam( + role="user", + content=items, + ) + ] + + result: list[ChatCompletionMessageParam] = [] + current_assistant_msg: ChatCompletionAssistantMessageParam | None = None + + def flush_assistant_message() -> None: + nonlocal current_assistant_msg + if current_assistant_msg is not None: + # The API doesn't support empty arrays for tool_calls + if not current_assistant_msg.get("tool_calls"): + del current_assistant_msg["tool_calls"] + result.append(current_assistant_msg) + current_assistant_msg = None + + def ensure_assistant_message() -> ChatCompletionAssistantMessageParam: + nonlocal current_assistant_msg + if current_assistant_msg is None: + current_assistant_msg = ChatCompletionAssistantMessageParam(role="assistant") + current_assistant_msg["tool_calls"] = [] + return current_assistant_msg + + for item in items: + # 1) Check easy input message + if easy_msg := cls.maybe_easy_input_message(item): + role = easy_msg["role"] + content = easy_msg["content"] + + if role == "user": + flush_assistant_message() + msg_user: ChatCompletionUserMessageParam = { + "role": "user", + "content": cls.extract_all_content(content), + } + result.append(msg_user) + elif role == "system": + flush_assistant_message() + msg_system: ChatCompletionSystemMessageParam = { + "role": "system", + "content": cls.extract_text_content(content), + } + result.append(msg_system) + elif role == "developer": + flush_assistant_message() + msg_developer: ChatCompletionDeveloperMessageParam = { + "role": "developer", + "content": cls.extract_text_content(content), + } + result.append(msg_developer) + elif role == "assistant": + flush_assistant_message() + msg_assistant: ChatCompletionAssistantMessageParam = { + "role": "assistant", + "content": cls.extract_text_content(content), + } + result.append(msg_assistant) + else: + raise UserError(f"Unexpected role in easy_input_message: {role}") + + # 2) Check input message + elif in_msg := cls.maybe_input_message(item): + role = in_msg["role"] + content = in_msg["content"] + flush_assistant_message() + + if role == "user": + msg_user = { + "role": "user", + "content": cls.extract_all_content(content), + } + result.append(msg_user) + elif role == "system": + msg_system = { + "role": "system", + "content": cls.extract_text_content(content), + } + result.append(msg_system) + elif role == "developer": + msg_developer = { + "role": "developer", + "content": cls.extract_text_content(content), + } + result.append(msg_developer) + else: + raise UserError(f"Unexpected role in input_message: {role}") + + # 3) response output message => assistant + elif resp_msg := cls.maybe_response_output_message(item): + flush_assistant_message() + new_asst = ChatCompletionAssistantMessageParam(role="assistant") + contents = resp_msg["content"] + + text_segments = [] + for c in contents: + if c["type"] == "output_text": + text_segments.append(c["text"]) + elif c["type"] == "refusal": + new_asst["refusal"] = c["refusal"] + elif c["type"] == "output_audio": + # Can't handle this, b/c chat completions expects an ID which we dont have + raise UserError( + f"Only audio IDs are supported for chat completions, but got: {c}" + ) + else: + raise UserError(f"Unknown content type in ResponseOutputMessage: {c}") + + if text_segments: + combined = "\n".join(text_segments) + new_asst["content"] = combined + + new_asst["tool_calls"] = [] + current_assistant_msg = new_asst + + # 4) function/file-search calls => attach to assistant + elif file_search := cls.maybe_file_search_call(item): + asst = ensure_assistant_message() + tool_calls = list(asst.get("tool_calls", [])) + new_tool_call = ChatCompletionMessageToolCallParam( + id=file_search["id"], + type="function", + function={ + "name": "file_search_call", + "arguments": json.dumps( + { + "queries": file_search.get("queries", []), + "status": file_search.get("status"), + } + ), + }, + ) + tool_calls.append(new_tool_call) + asst["tool_calls"] = tool_calls + + elif func_call := cls.maybe_function_tool_call(item): + asst = ensure_assistant_message() + tool_calls = list(asst.get("tool_calls", [])) + arguments = func_call["arguments"] if func_call["arguments"] else "{}" + new_tool_call = ChatCompletionMessageToolCallParam( + id=func_call["call_id"], + type="function", + function={ + "name": func_call["name"], + "arguments": arguments, + }, + ) + tool_calls.append(new_tool_call) + asst["tool_calls"] = tool_calls + # 5) function call output => tool message + elif func_output := cls.maybe_function_tool_call_output(item): + flush_assistant_message() + msg: ChatCompletionToolMessageParam = { + "role": "tool", + "tool_call_id": func_output["call_id"], + "content": func_output["output"], + } + result.append(msg) + + # 6) item reference => handle or raise + elif item_ref := cls.maybe_item_reference(item): + raise UserError( + f"Encountered an item_reference, which is not supported: {item_ref}" + ) + + # 7) If we haven't recognized it => fail or ignore + else: + raise UserError(f"Unhandled item type or structure: {item}") + + flush_assistant_message() + return result + + @classmethod + def tool_to_openai(cls, tool: Tool) -> ChatCompletionToolParam: + if isinstance(tool, FunctionTool): + return { + "type": "function", + "function": { + "name": tool.name, + "description": tool.description or "", + "parameters": tool.params_json_schema, + }, + } + + raise UserError( + f"Hosted tools are not supported with the ChatCompletions API. Got tool type: " + f"{type(tool)}, tool: {tool}" + ) + + @classmethod + def convert_handoff_tool(cls, handoff: Handoff[Any]) -> ChatCompletionToolParam: + return { + "type": "function", + "function": { + "name": handoff.tool_name, + "description": handoff.tool_description, + "parameters": handoff.input_json_schema, + }, + } diff --git a/src/agents/models/chatcmpl_helpers.py b/src/agents/models/chatcmpl_helpers.py new file mode 100644 index 00000000..0cee21ec --- /dev/null +++ b/src/agents/models/chatcmpl_helpers.py @@ -0,0 +1,37 @@ +from __future__ import annotations + +from openai import AsyncOpenAI + +from ..model_settings import ModelSettings +from ..version import __version__ + +_USER_AGENT = f"Agents/Python {__version__}" +HEADERS = {"User-Agent": _USER_AGENT} + + +class ChatCmplHelpers: + @classmethod + def is_openai(cls, client: AsyncOpenAI): + return str(client.base_url).startswith("https://api.openai.com") + + @classmethod + def get_store_param(cls, client: AsyncOpenAI, model_settings: ModelSettings) -> bool | None: + # Match the behavior of Responses where store is True when not given + default_store = True if cls.is_openai(client) else None + return model_settings.store if model_settings.store is not None else default_store + + @classmethod + def get_stream_options_param( + cls, client: AsyncOpenAI, model_settings: ModelSettings, stream: bool + ) -> dict[str, bool] | None: + if not stream: + return None + + default_include_usage = True if cls.is_openai(client) else None + include_usage = ( + model_settings.include_usage + if model_settings.include_usage is not None + else default_include_usage + ) + stream_options = {"include_usage": include_usage} if include_usage is not None else None + return stream_options diff --git a/src/agents/models/chatcmpl_stream_handler.py b/src/agents/models/chatcmpl_stream_handler.py new file mode 100644 index 00000000..d18f5912 --- /dev/null +++ b/src/agents/models/chatcmpl_stream_handler.py @@ -0,0 +1,316 @@ +from __future__ import annotations + +from collections.abc import AsyncIterator +from dataclasses import dataclass, field + +from openai import AsyncStream +from openai.types.chat import ChatCompletionChunk +from openai.types.completion_usage import CompletionUsage +from openai.types.responses import ( + Response, + ResponseCompletedEvent, + ResponseContentPartAddedEvent, + ResponseContentPartDoneEvent, + ResponseCreatedEvent, + ResponseFunctionCallArgumentsDeltaEvent, + ResponseFunctionToolCall, + ResponseOutputItem, + ResponseOutputItemAddedEvent, + ResponseOutputItemDoneEvent, + ResponseOutputMessage, + ResponseOutputRefusal, + ResponseOutputText, + ResponseRefusalDeltaEvent, + ResponseTextDeltaEvent, + ResponseUsage, +) +from openai.types.responses.response_usage import InputTokensDetails, OutputTokensDetails + +from ..items import TResponseStreamEvent +from .fake_id import FAKE_RESPONSES_ID + + +@dataclass +class StreamingState: + started: bool = False + text_content_index_and_output: tuple[int, ResponseOutputText] | None = None + refusal_content_index_and_output: tuple[int, ResponseOutputRefusal] | None = None + function_calls: dict[int, ResponseFunctionToolCall] = field(default_factory=dict) + + +class SequenceNumber: + def __init__(self): + self._sequence_number = 0 + + def get_and_increment(self) -> int: + num = self._sequence_number + self._sequence_number += 1 + return num + + +class ChatCmplStreamHandler: + @classmethod + async def handle_stream( + cls, + response: Response, + stream: AsyncStream[ChatCompletionChunk], + ) -> AsyncIterator[TResponseStreamEvent]: + usage: CompletionUsage | None = None + state = StreamingState() + sequence_number = SequenceNumber() + async for chunk in stream: + if not state.started: + state.started = True + yield ResponseCreatedEvent( + response=response, + type="response.created", + sequence_number=sequence_number.get_and_increment(), + ) + + # This is always set by the OpenAI API, but not by others e.g. LiteLLM + usage = chunk.usage if hasattr(chunk, "usage") else None + + if not chunk.choices or not chunk.choices[0].delta: + continue + + delta = chunk.choices[0].delta + + # Handle text + if delta.content: + if not state.text_content_index_and_output: + # Initialize a content tracker for streaming text + state.text_content_index_and_output = ( + 0 if not state.refusal_content_index_and_output else 1, + ResponseOutputText( + text="", + type="output_text", + annotations=[], + ), + ) + # Start a new assistant message stream + assistant_item = ResponseOutputMessage( + id=FAKE_RESPONSES_ID, + content=[], + role="assistant", + type="message", + status="in_progress", + ) + # Notify consumers of the start of a new output message + first content part + yield ResponseOutputItemAddedEvent( + item=assistant_item, + output_index=0, + type="response.output_item.added", + sequence_number=sequence_number.get_and_increment(), + ) + yield ResponseContentPartAddedEvent( + content_index=state.text_content_index_and_output[0], + item_id=FAKE_RESPONSES_ID, + output_index=0, + part=ResponseOutputText( + text="", + type="output_text", + annotations=[], + ), + type="response.content_part.added", + sequence_number=sequence_number.get_and_increment(), + ) + # Emit the delta for this segment of content + yield ResponseTextDeltaEvent( + content_index=state.text_content_index_and_output[0], + delta=delta.content, + item_id=FAKE_RESPONSES_ID, + output_index=0, + type="response.output_text.delta", + sequence_number=sequence_number.get_and_increment(), + ) + # Accumulate the text into the response part + state.text_content_index_and_output[1].text += delta.content + + # Handle refusals (model declines to answer) + # This is always set by the OpenAI API, but not by others e.g. LiteLLM + if hasattr(delta, "refusal") and delta.refusal: + if not state.refusal_content_index_and_output: + # Initialize a content tracker for streaming refusal text + state.refusal_content_index_and_output = ( + 0 if not state.text_content_index_and_output else 1, + ResponseOutputRefusal(refusal="", type="refusal"), + ) + # Start a new assistant message if one doesn't exist yet (in-progress) + assistant_item = ResponseOutputMessage( + id=FAKE_RESPONSES_ID, + content=[], + role="assistant", + type="message", + status="in_progress", + ) + # Notify downstream that assistant message + first content part are starting + yield ResponseOutputItemAddedEvent( + item=assistant_item, + output_index=0, + type="response.output_item.added", + sequence_number=sequence_number.get_and_increment(), + ) + yield ResponseContentPartAddedEvent( + content_index=state.refusal_content_index_and_output[0], + item_id=FAKE_RESPONSES_ID, + output_index=0, + part=ResponseOutputText( + text="", + type="output_text", + annotations=[], + ), + type="response.content_part.added", + sequence_number=sequence_number.get_and_increment(), + ) + # Emit the delta for this segment of refusal + yield ResponseRefusalDeltaEvent( + content_index=state.refusal_content_index_and_output[0], + delta=delta.refusal, + item_id=FAKE_RESPONSES_ID, + output_index=0, + type="response.refusal.delta", + sequence_number=sequence_number.get_and_increment(), + ) + # Accumulate the refusal string in the output part + state.refusal_content_index_and_output[1].refusal += delta.refusal + + # Handle tool calls + # Because we don't know the name of the function until the end of the stream, we'll + # save everything and yield events at the end + if delta.tool_calls: + for tc_delta in delta.tool_calls: + if tc_delta.index not in state.function_calls: + state.function_calls[tc_delta.index] = ResponseFunctionToolCall( + id=FAKE_RESPONSES_ID, + arguments="", + name="", + type="function_call", + call_id="", + ) + tc_function = tc_delta.function + + state.function_calls[tc_delta.index].arguments += ( + tc_function.arguments if tc_function else "" + ) or "" + state.function_calls[tc_delta.index].name += ( + tc_function.name if tc_function else "" + ) or "" + state.function_calls[tc_delta.index].call_id += tc_delta.id or "" + + function_call_starting_index = 0 + if state.text_content_index_and_output: + function_call_starting_index += 1 + # Send end event for this content part + yield ResponseContentPartDoneEvent( + content_index=state.text_content_index_and_output[0], + item_id=FAKE_RESPONSES_ID, + output_index=0, + part=state.text_content_index_and_output[1], + type="response.content_part.done", + sequence_number=sequence_number.get_and_increment(), + ) + + if state.refusal_content_index_and_output: + function_call_starting_index += 1 + # Send end event for this content part + yield ResponseContentPartDoneEvent( + content_index=state.refusal_content_index_and_output[0], + item_id=FAKE_RESPONSES_ID, + output_index=0, + part=state.refusal_content_index_and_output[1], + type="response.content_part.done", + sequence_number=sequence_number.get_and_increment(), + ) + + # Actually send events for the function calls + for function_call in state.function_calls.values(): + # First, a ResponseOutputItemAdded for the function call + yield ResponseOutputItemAddedEvent( + item=ResponseFunctionToolCall( + id=FAKE_RESPONSES_ID, + call_id=function_call.call_id, + arguments=function_call.arguments, + name=function_call.name, + type="function_call", + ), + output_index=function_call_starting_index, + type="response.output_item.added", + sequence_number=sequence_number.get_and_increment(), + ) + # Then, yield the args + yield ResponseFunctionCallArgumentsDeltaEvent( + delta=function_call.arguments, + item_id=FAKE_RESPONSES_ID, + output_index=function_call_starting_index, + type="response.function_call_arguments.delta", + sequence_number=sequence_number.get_and_increment(), + ) + # Finally, the ResponseOutputItemDone + yield ResponseOutputItemDoneEvent( + item=ResponseFunctionToolCall( + id=FAKE_RESPONSES_ID, + call_id=function_call.call_id, + arguments=function_call.arguments, + name=function_call.name, + type="function_call", + ), + output_index=function_call_starting_index, + type="response.output_item.done", + sequence_number=sequence_number.get_and_increment(), + ) + + # Finally, send the Response completed event + outputs: list[ResponseOutputItem] = [] + if state.text_content_index_and_output or state.refusal_content_index_and_output: + assistant_msg = ResponseOutputMessage( + id=FAKE_RESPONSES_ID, + content=[], + role="assistant", + type="message", + status="completed", + ) + if state.text_content_index_and_output: + assistant_msg.content.append(state.text_content_index_and_output[1]) + if state.refusal_content_index_and_output: + assistant_msg.content.append(state.refusal_content_index_and_output[1]) + outputs.append(assistant_msg) + + # send a ResponseOutputItemDone for the assistant message + yield ResponseOutputItemDoneEvent( + item=assistant_msg, + output_index=0, + type="response.output_item.done", + sequence_number=sequence_number.get_and_increment(), + ) + + for function_call in state.function_calls.values(): + outputs.append(function_call) + + final_response = response.model_copy() + final_response.output = outputs + final_response.usage = ( + ResponseUsage( + input_tokens=usage.prompt_tokens, + output_tokens=usage.completion_tokens, + total_tokens=usage.total_tokens, + output_tokens_details=OutputTokensDetails( + reasoning_tokens=usage.completion_tokens_details.reasoning_tokens + if usage.completion_tokens_details + and usage.completion_tokens_details.reasoning_tokens + else 0 + ), + input_tokens_details=InputTokensDetails( + cached_tokens=usage.prompt_tokens_details.cached_tokens + if usage.prompt_tokens_details and usage.prompt_tokens_details.cached_tokens + else 0 + ), + ) + if usage + else None + ) + + yield ResponseCompletedEvent( + response=final_response, + type="response.completed", + sequence_number=sequence_number.get_and_increment(), + ) diff --git a/src/agents/models/interface.py b/src/agents/models/interface.py index e9a8700c..3a79e564 100644 --- a/src/agents/models/interface.py +++ b/src/agents/models/interface.py @@ -5,7 +5,7 @@ from collections.abc import AsyncIterator from typing import TYPE_CHECKING -from ..agent_output import AgentOutputSchema +from ..agent_output import AgentOutputSchemaBase from ..handoffs import Handoff from ..items import ModelResponse, TResponseInputItem, TResponseStreamEvent from ..tool import Tool @@ -41,9 +41,11 @@ async def get_response( input: str | list[TResponseInputItem], model_settings: ModelSettings, tools: list[Tool], - output_schema: AgentOutputSchema | None, + output_schema: AgentOutputSchemaBase | None, handoffs: list[Handoff], tracing: ModelTracing, + *, + previous_response_id: str | None, ) -> ModelResponse: """Get a response from the model. @@ -55,6 +57,8 @@ async def get_response( output_schema: The output schema to use. handoffs: The handoffs available to the model. tracing: Tracing configuration. + previous_response_id: the ID of the previous response. Generally not used by the model, + except for the OpenAI Responses API. Returns: The full model response. @@ -68,9 +72,11 @@ def stream_response( input: str | list[TResponseInputItem], model_settings: ModelSettings, tools: list[Tool], - output_schema: AgentOutputSchema | None, + output_schema: AgentOutputSchemaBase | None, handoffs: list[Handoff], tracing: ModelTracing, + *, + previous_response_id: str | None, ) -> AsyncIterator[TResponseStreamEvent]: """Stream a response from the model. @@ -82,6 +88,8 @@ def stream_response( output_schema: The output schema to use. handoffs: The handoffs available to the model. tracing: Tracing configuration. + previous_response_id: the ID of the previous response. Generally not used by the model, + except for the OpenAI Responses API. Returns: An iterator of response stream events, in OpenAI Responses format. diff --git a/src/agents/models/multi_provider.py b/src/agents/models/multi_provider.py new file mode 100644 index 00000000..d075ac9b --- /dev/null +++ b/src/agents/models/multi_provider.py @@ -0,0 +1,144 @@ +from __future__ import annotations + +from openai import AsyncOpenAI + +from ..exceptions import UserError +from .interface import Model, ModelProvider +from .openai_provider import OpenAIProvider + + +class MultiProviderMap: + """A map of model name prefixes to ModelProviders.""" + + def __init__(self): + self._mapping: dict[str, ModelProvider] = {} + + def has_prefix(self, prefix: str) -> bool: + """Returns True if the given prefix is in the mapping.""" + return prefix in self._mapping + + def get_mapping(self) -> dict[str, ModelProvider]: + """Returns a copy of the current prefix -> ModelProvider mapping.""" + return self._mapping.copy() + + def set_mapping(self, mapping: dict[str, ModelProvider]): + """Overwrites the current mapping with a new one.""" + self._mapping = mapping + + def get_provider(self, prefix: str) -> ModelProvider | None: + """Returns the ModelProvider for the given prefix. + + Args: + prefix: The prefix of the model name e.g. "openai" or "my_prefix". + """ + return self._mapping.get(prefix) + + def add_provider(self, prefix: str, provider: ModelProvider): + """Adds a new prefix -> ModelProvider mapping. + + Args: + prefix: The prefix of the model name e.g. "openai" or "my_prefix". + provider: The ModelProvider to use for the given prefix. + """ + self._mapping[prefix] = provider + + def remove_provider(self, prefix: str): + """Removes the mapping for the given prefix. + + Args: + prefix: The prefix of the model name e.g. "openai" or "my_prefix". + """ + del self._mapping[prefix] + + +class MultiProvider(ModelProvider): + """This ModelProvider maps to a Model based on the prefix of the model name. By default, the + mapping is: + - "openai/" prefix or no prefix -> OpenAIProvider. e.g. "openai/gpt-4.1", "gpt-4.1" + - "litellm/" prefix -> LitellmProvider. e.g. "litellm/openai/gpt-4.1" + + You can override or customize this mapping. + """ + + def __init__( + self, + *, + provider_map: MultiProviderMap | None = None, + openai_api_key: str | None = None, + openai_base_url: str | None = None, + openai_client: AsyncOpenAI | None = None, + openai_organization: str | None = None, + openai_project: str | None = None, + openai_use_responses: bool | None = None, + ) -> None: + """Create a new OpenAI provider. + + Args: + provider_map: A MultiProviderMap that maps prefixes to ModelProviders. If not provided, + we will use a default mapping. See the documentation for this class to see the + default mapping. + openai_api_key: The API key to use for the OpenAI provider. If not provided, we will use + the default API key. + openai_base_url: The base URL to use for the OpenAI provider. If not provided, we will + use the default base URL. + openai_client: An optional OpenAI client to use. If not provided, we will create a new + OpenAI client using the api_key and base_url. + openai_organization: The organization to use for the OpenAI provider. + openai_project: The project to use for the OpenAI provider. + openai_use_responses: Whether to use the OpenAI responses API. + """ + self.provider_map = provider_map + self.openai_provider = OpenAIProvider( + api_key=openai_api_key, + base_url=openai_base_url, + openai_client=openai_client, + organization=openai_organization, + project=openai_project, + use_responses=openai_use_responses, + ) + + self._fallback_providers: dict[str, ModelProvider] = {} + + def _get_prefix_and_model_name(self, model_name: str | None) -> tuple[str | None, str | None]: + if model_name is None: + return None, None + elif "/" in model_name: + prefix, model_name = model_name.split("/", 1) + return prefix, model_name + else: + return None, model_name + + def _create_fallback_provider(self, prefix: str) -> ModelProvider: + if prefix == "litellm": + from ..extensions.models.litellm_provider import LitellmProvider + + return LitellmProvider() + else: + raise UserError(f"Unknown prefix: {prefix}") + + def _get_fallback_provider(self, prefix: str | None) -> ModelProvider: + if prefix is None or prefix == "openai": + return self.openai_provider + elif prefix in self._fallback_providers: + return self._fallback_providers[prefix] + else: + self._fallback_providers[prefix] = self._create_fallback_provider(prefix) + return self._fallback_providers[prefix] + + def get_model(self, model_name: str | None) -> Model: + """Returns a Model based on the model name. The model name can have a prefix, ending with + a "/", which will be used to look up the ModelProvider. If there is no prefix, we will use + the OpenAI provider. + + Args: + model_name: The name of the model to get. + + Returns: + A Model. + """ + prefix, model_name = self._get_prefix_and_model_name(model_name) + + if prefix and self.provider_map and (provider := self.provider_map.get_provider(prefix)): + return provider.get_model(model_name) + else: + return self._get_fallback_provider(prefix).get_model(model_name) diff --git a/src/agents/models/openai_chatcompletions.py b/src/agents/models/openai_chatcompletions.py index de7b1ae4..4465ff2f 100644 --- a/src/agents/models/openai_chatcompletions.py +++ b/src/agents/models/openai_chatcompletions.py @@ -1,73 +1,29 @@ from __future__ import annotations -import dataclasses import json import time -from collections.abc import AsyncIterator, Iterable -from dataclasses import dataclass, field +from collections.abc import AsyncIterator from typing import TYPE_CHECKING, Any, Literal, cast, overload -from openai import NOT_GIVEN, AsyncOpenAI, AsyncStream, NotGiven +from openai import NOT_GIVEN, AsyncOpenAI, AsyncStream from openai.types import ChatModel -from openai.types.chat import ( - ChatCompletion, - ChatCompletionAssistantMessageParam, - ChatCompletionChunk, - ChatCompletionContentPartImageParam, - ChatCompletionContentPartParam, - ChatCompletionContentPartTextParam, - ChatCompletionDeveloperMessageParam, - ChatCompletionMessage, - ChatCompletionMessageParam, - ChatCompletionMessageToolCallParam, - ChatCompletionSystemMessageParam, - ChatCompletionToolChoiceOptionParam, - ChatCompletionToolMessageParam, - ChatCompletionUserMessageParam, -) -from openai.types.chat.chat_completion_tool_param import ChatCompletionToolParam -from openai.types.chat.completion_create_params import ResponseFormat -from openai.types.completion_usage import CompletionUsage -from openai.types.responses import ( - EasyInputMessageParam, - Response, - ResponseCompletedEvent, - ResponseContentPartAddedEvent, - ResponseContentPartDoneEvent, - ResponseCreatedEvent, - ResponseFileSearchToolCallParam, - ResponseFunctionCallArgumentsDeltaEvent, - ResponseFunctionToolCall, - ResponseFunctionToolCallParam, - ResponseInputContentParam, - ResponseInputImageParam, - ResponseInputTextParam, - ResponseOutputItem, - ResponseOutputItemAddedEvent, - ResponseOutputItemDoneEvent, - ResponseOutputMessage, - ResponseOutputMessageParam, - ResponseOutputRefusal, - ResponseOutputText, - ResponseRefusalDeltaEvent, - ResponseTextDeltaEvent, - ResponseUsage, -) -from openai.types.responses.response_input_param import FunctionCallOutput, ItemReference, Message +from openai.types.chat import ChatCompletion, ChatCompletionChunk +from openai.types.responses import Response from openai.types.responses.response_usage import InputTokensDetails, OutputTokensDetails from .. import _debug -from ..agent_output import AgentOutputSchema -from ..exceptions import AgentsException, UserError +from ..agent_output import AgentOutputSchemaBase from ..handoffs import Handoff -from ..items import ModelResponse, TResponseInputItem, TResponseOutputItem, TResponseStreamEvent +from ..items import ModelResponse, TResponseInputItem, TResponseStreamEvent from ..logger import logger -from ..tool import FunctionTool, Tool +from ..tool import Tool from ..tracing import generation_span from ..tracing.span_data import GenerationSpanData from ..tracing.spans import Span from ..usage import Usage -from ..version import __version__ +from .chatcmpl_converter import Converter +from .chatcmpl_helpers import HEADERS, ChatCmplHelpers +from .chatcmpl_stream_handler import ChatCmplStreamHandler from .fake_id import FAKE_RESPONSES_ID from .interface import Model, ModelTracing @@ -75,18 +31,6 @@ from ..model_settings import ModelSettings -_USER_AGENT = f"Agents/Python {__version__}" -_HEADERS = {"User-Agent": _USER_AGENT} - - -@dataclass -class _StreamingState: - started: bool = False - text_content_index_and_output: tuple[int, ResponseOutputText] | None = None - refusal_content_index_and_output: tuple[int, ResponseOutputRefusal] | None = None - function_calls: dict[int, ResponseFunctionToolCall] = field(default_factory=dict) - - class OpenAIChatCompletionsModel(Model): def __init__( self, @@ -105,14 +49,14 @@ async def get_response( input: str | list[TResponseInputItem], model_settings: ModelSettings, tools: list[Tool], - output_schema: AgentOutputSchema | None, + output_schema: AgentOutputSchemaBase | None, handoffs: list[Handoff], tracing: ModelTracing, + previous_response_id: str | None, ) -> ModelResponse: with generation_span( model=str(self.model), - model_config=dataclasses.asdict(model_settings) - | {"base_url": str(self._client.base_url)}, + model_config=model_settings.to_json_dict() | {"base_url": str(self._client.base_url)}, disabled=tracing.is_disabled(), ) as span_generation: response = await self._fetch_response( @@ -140,6 +84,18 @@ async def get_response( input_tokens=response.usage.prompt_tokens, output_tokens=response.usage.completion_tokens, total_tokens=response.usage.total_tokens, + input_tokens_details=InputTokensDetails( + cached_tokens=getattr( + response.usage.prompt_tokens_details, "cached_tokens", 0 + ) + or 0, + ), + output_tokens_details=OutputTokensDetails( + reasoning_tokens=getattr( + response.usage.completion_tokens_details, "reasoning_tokens", 0 + ) + or 0, + ), ) if response.usage else Usage() @@ -151,12 +107,12 @@ async def get_response( "output_tokens": usage.output_tokens, } - items = _Converter.message_to_output_items(response.choices[0].message) + items = Converter.message_to_output_items(response.choices[0].message) return ModelResponse( output=items, usage=usage, - referenceable_id=None, + response_id=None, ) async def stream_response( @@ -165,17 +121,18 @@ async def stream_response( input: str | list[TResponseInputItem], model_settings: ModelSettings, tools: list[Tool], - output_schema: AgentOutputSchema | None, + output_schema: AgentOutputSchemaBase | None, handoffs: list[Handoff], tracing: ModelTracing, + *, + previous_response_id: str | None, ) -> AsyncIterator[TResponseStreamEvent]: """ Yields a partial message as it is generated, as well as the usage information. """ with generation_span( model=str(self.model), - model_config=dataclasses.asdict(model_settings) - | {"base_url": str(self._client.base_url)}, + model_config=model_settings.to_json_dict() | {"base_url": str(self._client.base_url)}, disabled=tracing.is_disabled(), ) as span_generation: response, stream = await self._fetch_response( @@ -190,257 +147,20 @@ async def stream_response( stream=True, ) - usage: CompletionUsage | None = None - state = _StreamingState() - - async for chunk in stream: - if not state.started: - state.started = True - yield ResponseCreatedEvent( - response=response, - type="response.created", - ) - - # The usage is only available in the last chunk - usage = chunk.usage + final_response: Response | None = None + async for chunk in ChatCmplStreamHandler.handle_stream(response, stream): + yield chunk - if not chunk.choices or not chunk.choices[0].delta: - continue + if chunk.type == "response.completed": + final_response = chunk.response - delta = chunk.choices[0].delta - - # Handle text - if delta.content: - if not state.text_content_index_and_output: - # Initialize a content tracker for streaming text - state.text_content_index_and_output = ( - 0 if not state.refusal_content_index_and_output else 1, - ResponseOutputText( - text="", - type="output_text", - annotations=[], - ), - ) - # Start a new assistant message stream - assistant_item = ResponseOutputMessage( - id=FAKE_RESPONSES_ID, - content=[], - role="assistant", - type="message", - status="in_progress", - ) - # Notify consumers of the start of a new output message + first content part - yield ResponseOutputItemAddedEvent( - item=assistant_item, - output_index=0, - type="response.output_item.added", - ) - yield ResponseContentPartAddedEvent( - content_index=state.text_content_index_and_output[0], - item_id=FAKE_RESPONSES_ID, - output_index=0, - part=ResponseOutputText( - text="", - type="output_text", - annotations=[], - ), - type="response.content_part.added", - ) - # Emit the delta for this segment of content - yield ResponseTextDeltaEvent( - content_index=state.text_content_index_and_output[0], - delta=delta.content, - item_id=FAKE_RESPONSES_ID, - output_index=0, - type="response.output_text.delta", - ) - # Accumulate the text into the response part - state.text_content_index_and_output[1].text += delta.content - - # Handle refusals (model declines to answer) - if delta.refusal: - if not state.refusal_content_index_and_output: - # Initialize a content tracker for streaming refusal text - state.refusal_content_index_and_output = ( - 0 if not state.text_content_index_and_output else 1, - ResponseOutputRefusal(refusal="", type="refusal"), - ) - # Start a new assistant message if one doesn't exist yet (in-progress) - assistant_item = ResponseOutputMessage( - id=FAKE_RESPONSES_ID, - content=[], - role="assistant", - type="message", - status="in_progress", - ) - # Notify downstream that assistant message + first content part are starting - yield ResponseOutputItemAddedEvent( - item=assistant_item, - output_index=0, - type="response.output_item.added", - ) - yield ResponseContentPartAddedEvent( - content_index=state.refusal_content_index_and_output[0], - item_id=FAKE_RESPONSES_ID, - output_index=0, - part=ResponseOutputText( - text="", - type="output_text", - annotations=[], - ), - type="response.content_part.added", - ) - # Emit the delta for this segment of refusal - yield ResponseRefusalDeltaEvent( - content_index=state.refusal_content_index_and_output[0], - delta=delta.refusal, - item_id=FAKE_RESPONSES_ID, - output_index=0, - type="response.refusal.delta", - ) - # Accumulate the refusal string in the output part - state.refusal_content_index_and_output[1].refusal += delta.refusal - - # Handle tool calls - # Because we don't know the name of the function until the end of the stream, we'll - # save everything and yield events at the end - if delta.tool_calls: - for tc_delta in delta.tool_calls: - if tc_delta.index not in state.function_calls: - state.function_calls[tc_delta.index] = ResponseFunctionToolCall( - id=FAKE_RESPONSES_ID, - arguments="", - name="", - type="function_call", - call_id="", - ) - tc_function = tc_delta.function - - state.function_calls[tc_delta.index].arguments += ( - tc_function.arguments if tc_function else "" - ) or "" - state.function_calls[tc_delta.index].name += ( - tc_function.name if tc_function else "" - ) or "" - state.function_calls[tc_delta.index].call_id += tc_delta.id or "" - - function_call_starting_index = 0 - if state.text_content_index_and_output: - function_call_starting_index += 1 - # Send end event for this content part - yield ResponseContentPartDoneEvent( - content_index=state.text_content_index_and_output[0], - item_id=FAKE_RESPONSES_ID, - output_index=0, - part=state.text_content_index_and_output[1], - type="response.content_part.done", - ) - - if state.refusal_content_index_and_output: - function_call_starting_index += 1 - # Send end event for this content part - yield ResponseContentPartDoneEvent( - content_index=state.refusal_content_index_and_output[0], - item_id=FAKE_RESPONSES_ID, - output_index=0, - part=state.refusal_content_index_and_output[1], - type="response.content_part.done", - ) - - # Actually send events for the function calls - for function_call in state.function_calls.values(): - # First, a ResponseOutputItemAdded for the function call - yield ResponseOutputItemAddedEvent( - item=ResponseFunctionToolCall( - id=FAKE_RESPONSES_ID, - call_id=function_call.call_id, - arguments=function_call.arguments, - name=function_call.name, - type="function_call", - ), - output_index=function_call_starting_index, - type="response.output_item.added", - ) - # Then, yield the args - yield ResponseFunctionCallArgumentsDeltaEvent( - delta=function_call.arguments, - item_id=FAKE_RESPONSES_ID, - output_index=function_call_starting_index, - type="response.function_call_arguments.delta", - ) - # Finally, the ResponseOutputItemDone - yield ResponseOutputItemDoneEvent( - item=ResponseFunctionToolCall( - id=FAKE_RESPONSES_ID, - call_id=function_call.call_id, - arguments=function_call.arguments, - name=function_call.name, - type="function_call", - ), - output_index=function_call_starting_index, - type="response.output_item.done", - ) - - # Finally, send the Response completed event - outputs: list[ResponseOutputItem] = [] - if state.text_content_index_and_output or state.refusal_content_index_and_output: - assistant_msg = ResponseOutputMessage( - id=FAKE_RESPONSES_ID, - content=[], - role="assistant", - type="message", - status="completed", - ) - if state.text_content_index_and_output: - assistant_msg.content.append(state.text_content_index_and_output[1]) - if state.refusal_content_index_and_output: - assistant_msg.content.append(state.refusal_content_index_and_output[1]) - outputs.append(assistant_msg) - - # send a ResponseOutputItemDone for the assistant message - yield ResponseOutputItemDoneEvent( - item=assistant_msg, - output_index=0, - type="response.output_item.done", - ) - - for function_call in state.function_calls.values(): - outputs.append(function_call) - - final_response = response.model_copy() - final_response.output = outputs - final_response.usage = ( - ResponseUsage( - input_tokens=usage.prompt_tokens, - output_tokens=usage.completion_tokens, - total_tokens=usage.total_tokens, - output_tokens_details=OutputTokensDetails( - reasoning_tokens=usage.completion_tokens_details.reasoning_tokens - if usage.completion_tokens_details - and usage.completion_tokens_details.reasoning_tokens - else 0 - ), - input_tokens_details=InputTokensDetails( - cached_tokens=usage.prompt_tokens_details.cached_tokens - if usage.prompt_tokens_details and usage.prompt_tokens_details.cached_tokens - else 0 - ), - ) - if usage - else None - ) - - yield ResponseCompletedEvent( - response=final_response, - type="response.completed", - ) - if tracing.include_data(): + if tracing.include_data() and final_response: span_generation.span_data.output = [final_response.model_dump()] - if usage: + if final_response and final_response.usage: span_generation.span_data.usage = { - "input_tokens": usage.prompt_tokens, - "output_tokens": usage.completion_tokens, + "input_tokens": final_response.usage.input_tokens, + "output_tokens": final_response.usage.output_tokens, } @overload @@ -450,7 +170,7 @@ async def _fetch_response( input: str | list[TResponseInputItem], model_settings: ModelSettings, tools: list[Tool], - output_schema: AgentOutputSchema | None, + output_schema: AgentOutputSchemaBase | None, handoffs: list[Handoff], span: Span[GenerationSpanData], tracing: ModelTracing, @@ -464,7 +184,7 @@ async def _fetch_response( input: str | list[TResponseInputItem], model_settings: ModelSettings, tools: list[Tool], - output_schema: AgentOutputSchema | None, + output_schema: AgentOutputSchemaBase | None, handoffs: list[Handoff], span: Span[GenerationSpanData], tracing: ModelTracing, @@ -477,13 +197,13 @@ async def _fetch_response( input: str | list[TResponseInputItem], model_settings: ModelSettings, tools: list[Tool], - output_schema: AgentOutputSchema | None, + output_schema: AgentOutputSchemaBase | None, handoffs: list[Handoff], span: Span[GenerationSpanData], tracing: ModelTracing, stream: bool = False, ) -> ChatCompletion | tuple[Response, AsyncStream[ChatCompletionChunk]]: - converted_messages = _Converter.items_to_messages(input) + converted_messages = Converter.items_to_messages(input) if system_instructions: converted_messages.insert( @@ -497,15 +217,19 @@ async def _fetch_response( span.span_data.input = converted_messages parallel_tool_calls = ( - True if model_settings.parallel_tool_calls and tools and len(tools) > 0 else NOT_GIVEN + True + if model_settings.parallel_tool_calls and tools and len(tools) > 0 + else False + if model_settings.parallel_tool_calls is False + else NOT_GIVEN ) - tool_choice = _Converter.convert_tool_choice(model_settings.tool_choice) - response_format = _Converter.convert_response_format(output_schema) + tool_choice = Converter.convert_tool_choice(model_settings.tool_choice) + response_format = Converter.convert_response_format(output_schema) - converted_tools = [ToolConverter.to_openai(tool) for tool in tools] if tools else [] + converted_tools = [Converter.tool_to_openai(tool) for tool in tools] if tools else [] for handoff in handoffs: - converted_tools.append(ToolConverter.convert_handoff_tool(handoff)) + converted_tools.append(Converter.convert_handoff_tool(handoff)) if _debug.DONT_LOG_MODEL_DATA: logger.debug("Calling LLM") @@ -518,8 +242,12 @@ async def _fetch_response( f"Response format: {response_format}\n" ) - # Match the behavior of Responses where store is True when not given - store = model_settings.store if model_settings.store is not None else True + reasoning_effort = model_settings.reasoning.effort if model_settings.reasoning else None + store = ChatCmplHelpers.get_store_param(self._get_client(), model_settings) + + stream_options = ChatCmplHelpers.get_stream_options_param( + self._get_client(), model_settings, stream=stream + ) ret = await self._get_client().chat.completions.create( model=self.model, @@ -534,9 +262,13 @@ async def _fetch_response( response_format=response_format, parallel_tool_calls=parallel_tool_calls, stream=stream, - stream_options={"include_usage": True} if stream else NOT_GIVEN, - store=store, - extra_headers=_HEADERS, + stream_options=self._non_null_or_not_given(stream_options), + store=self._non_null_or_not_given(store), + reasoning_effort=self._non_null_or_not_given(reasoning_effort), + extra_headers={**HEADERS, **(model_settings.extra_headers or {})}, + extra_query=model_settings.extra_query, + extra_body=model_settings.extra_body, + metadata=self._non_null_or_not_given(model_settings.metadata), ) if isinstance(ret, ChatCompletion): @@ -555,6 +287,7 @@ async def _fetch_response( temperature=model_settings.temperature, tools=[], parallel_tool_calls=parallel_tool_calls or False, + reasoning=model_settings.reasoning, ) return response, ret @@ -562,426 +295,3 @@ def _get_client(self) -> AsyncOpenAI: if self._client is None: self._client = AsyncOpenAI() return self._client - - -class _Converter: - @classmethod - def convert_tool_choice( - cls, tool_choice: Literal["auto", "required", "none"] | str | None - ) -> ChatCompletionToolChoiceOptionParam | NotGiven: - if tool_choice is None: - return NOT_GIVEN - elif tool_choice == "auto": - return "auto" - elif tool_choice == "required": - return "required" - elif tool_choice == "none": - return "none" - else: - return { - "type": "function", - "function": { - "name": tool_choice, - }, - } - - @classmethod - def convert_response_format( - cls, final_output_schema: AgentOutputSchema | None - ) -> ResponseFormat | NotGiven: - if not final_output_schema or final_output_schema.is_plain_text(): - return NOT_GIVEN - - return { - "type": "json_schema", - "json_schema": { - "name": "final_output", - "strict": final_output_schema.strict_json_schema, - "schema": final_output_schema.json_schema(), - }, - } - - @classmethod - def message_to_output_items(cls, message: ChatCompletionMessage) -> list[TResponseOutputItem]: - items: list[TResponseOutputItem] = [] - - message_item = ResponseOutputMessage( - id=FAKE_RESPONSES_ID, - content=[], - role="assistant", - type="message", - status="completed", - ) - if message.content: - message_item.content.append( - ResponseOutputText(text=message.content, type="output_text", annotations=[]) - ) - if message.refusal: - message_item.content.append( - ResponseOutputRefusal(refusal=message.refusal, type="refusal") - ) - if message.audio: - raise AgentsException("Audio is not currently supported") - - if message_item.content: - items.append(message_item) - - if message.tool_calls: - for tool_call in message.tool_calls: - items.append( - ResponseFunctionToolCall( - id=FAKE_RESPONSES_ID, - call_id=tool_call.id, - arguments=tool_call.function.arguments, - name=tool_call.function.name, - type="function_call", - ) - ) - - return items - - @classmethod - def maybe_easy_input_message(cls, item: Any) -> EasyInputMessageParam | None: - if not isinstance(item, dict): - return None - - keys = item.keys() - # EasyInputMessageParam only has these two keys - if keys != {"content", "role"}: - return None - - role = item.get("role", None) - if role not in ("user", "assistant", "system", "developer"): - return None - - if "content" not in item: - return None - - return cast(EasyInputMessageParam, item) - - @classmethod - def maybe_input_message(cls, item: Any) -> Message | None: - if ( - isinstance(item, dict) - and item.get("type") == "message" - and item.get("role") - in ( - "user", - "system", - "developer", - ) - ): - return cast(Message, item) - - return None - - @classmethod - def maybe_file_search_call(cls, item: Any) -> ResponseFileSearchToolCallParam | None: - if isinstance(item, dict) and item.get("type") == "file_search_call": - return cast(ResponseFileSearchToolCallParam, item) - return None - - @classmethod - def maybe_function_tool_call(cls, item: Any) -> ResponseFunctionToolCallParam | None: - if isinstance(item, dict) and item.get("type") == "function_call": - return cast(ResponseFunctionToolCallParam, item) - return None - - @classmethod - def maybe_function_tool_call_output( - cls, - item: Any, - ) -> FunctionCallOutput | None: - if isinstance(item, dict) and item.get("type") == "function_call_output": - return cast(FunctionCallOutput, item) - return None - - @classmethod - def maybe_item_reference(cls, item: Any) -> ItemReference | None: - if isinstance(item, dict) and item.get("type") == "item_reference": - return cast(ItemReference, item) - return None - - @classmethod - def maybe_response_output_message(cls, item: Any) -> ResponseOutputMessageParam | None: - # ResponseOutputMessage is only used for messages with role assistant - if ( - isinstance(item, dict) - and item.get("type") == "message" - and item.get("role") == "assistant" - ): - return cast(ResponseOutputMessageParam, item) - return None - - @classmethod - def extract_text_content( - cls, content: str | Iterable[ResponseInputContentParam] - ) -> str | list[ChatCompletionContentPartTextParam]: - all_content = cls.extract_all_content(content) - if isinstance(all_content, str): - return all_content - out: list[ChatCompletionContentPartTextParam] = [] - for c in all_content: - if c.get("type") == "text": - out.append(cast(ChatCompletionContentPartTextParam, c)) - return out - - @classmethod - def extract_all_content( - cls, content: str | Iterable[ResponseInputContentParam] - ) -> str | list[ChatCompletionContentPartParam]: - if isinstance(content, str): - return content - out: list[ChatCompletionContentPartParam] = [] - - for c in content: - if isinstance(c, dict) and c.get("type") == "input_text": - casted_text_param = cast(ResponseInputTextParam, c) - out.append( - ChatCompletionContentPartTextParam( - type="text", - text=casted_text_param["text"], - ) - ) - elif isinstance(c, dict) and c.get("type") == "input_image": - casted_image_param = cast(ResponseInputImageParam, c) - if "image_url" not in casted_image_param or not casted_image_param["image_url"]: - raise UserError( - f"Only image URLs are supported for input_image {casted_image_param}" - ) - out.append( - ChatCompletionContentPartImageParam( - type="image_url", - image_url={ - "url": casted_image_param["image_url"], - "detail": casted_image_param["detail"], - }, - ) - ) - elif isinstance(c, dict) and c.get("type") == "input_file": - raise UserError(f"File uploads are not supported for chat completions {c}") - else: - raise UserError(f"Unknown content: {c}") - return out - - @classmethod - def items_to_messages( - cls, - items: str | Iterable[TResponseInputItem], - ) -> list[ChatCompletionMessageParam]: - """ - Convert a sequence of 'Item' objects into a list of ChatCompletionMessageParam. - - Rules: - - EasyInputMessage or InputMessage (role=user) => ChatCompletionUserMessageParam - - EasyInputMessage or InputMessage (role=system) => ChatCompletionSystemMessageParam - - EasyInputMessage or InputMessage (role=developer) => ChatCompletionDeveloperMessageParam - - InputMessage (role=assistant) => Start or flush a ChatCompletionAssistantMessageParam - - response_output_message => Also produces/flushes a ChatCompletionAssistantMessageParam - - tool calls get attached to the *current* assistant message, or create one if none. - - tool outputs => ChatCompletionToolMessageParam - """ - - if isinstance(items, str): - return [ - ChatCompletionUserMessageParam( - role="user", - content=items, - ) - ] - - result: list[ChatCompletionMessageParam] = [] - current_assistant_msg: ChatCompletionAssistantMessageParam | None = None - - def flush_assistant_message() -> None: - nonlocal current_assistant_msg - if current_assistant_msg is not None: - # The API doesn't support empty arrays for tool_calls - if not current_assistant_msg.get("tool_calls"): - del current_assistant_msg["tool_calls"] - result.append(current_assistant_msg) - current_assistant_msg = None - - def ensure_assistant_message() -> ChatCompletionAssistantMessageParam: - nonlocal current_assistant_msg - if current_assistant_msg is None: - current_assistant_msg = ChatCompletionAssistantMessageParam(role="assistant") - current_assistant_msg["tool_calls"] = [] - return current_assistant_msg - - for item in items: - # 1) Check easy input message - if easy_msg := cls.maybe_easy_input_message(item): - role = easy_msg["role"] - content = easy_msg["content"] - - if role == "user": - flush_assistant_message() - msg_user: ChatCompletionUserMessageParam = { - "role": "user", - "content": cls.extract_all_content(content), - } - result.append(msg_user) - elif role == "system": - flush_assistant_message() - msg_system: ChatCompletionSystemMessageParam = { - "role": "system", - "content": cls.extract_text_content(content), - } - result.append(msg_system) - elif role == "developer": - flush_assistant_message() - msg_developer: ChatCompletionDeveloperMessageParam = { - "role": "developer", - "content": cls.extract_text_content(content), - } - result.append(msg_developer) - elif role == "assistant": - flush_assistant_message() - msg_assistant: ChatCompletionAssistantMessageParam = { - "role": "assistant", - "content": cls.extract_text_content(content), - } - result.append(msg_assistant) - else: - raise UserError(f"Unexpected role in easy_input_message: {role}") - - # 2) Check input message - elif in_msg := cls.maybe_input_message(item): - role = in_msg["role"] - content = in_msg["content"] - flush_assistant_message() - - if role == "user": - msg_user = { - "role": "user", - "content": cls.extract_all_content(content), - } - result.append(msg_user) - elif role == "system": - msg_system = { - "role": "system", - "content": cls.extract_text_content(content), - } - result.append(msg_system) - elif role == "developer": - msg_developer = { - "role": "developer", - "content": cls.extract_text_content(content), - } - result.append(msg_developer) - else: - raise UserError(f"Unexpected role in input_message: {role}") - - # 3) response output message => assistant - elif resp_msg := cls.maybe_response_output_message(item): - flush_assistant_message() - new_asst = ChatCompletionAssistantMessageParam(role="assistant") - contents = resp_msg["content"] - - text_segments = [] - for c in contents: - if c["type"] == "output_text": - text_segments.append(c["text"]) - elif c["type"] == "refusal": - new_asst["refusal"] = c["refusal"] - elif c["type"] == "output_audio": - # Can't handle this, b/c chat completions expects an ID which we dont have - raise UserError( - f"Only audio IDs are supported for chat completions, but got: {c}" - ) - else: - raise UserError(f"Unknown content type in ResponseOutputMessage: {c}") - - if text_segments: - combined = "\n".join(text_segments) - new_asst["content"] = combined - - new_asst["tool_calls"] = [] - current_assistant_msg = new_asst - - # 4) function/file-search calls => attach to assistant - elif file_search := cls.maybe_file_search_call(item): - asst = ensure_assistant_message() - tool_calls = list(asst.get("tool_calls", [])) - new_tool_call = ChatCompletionMessageToolCallParam( - id=file_search["id"], - type="function", - function={ - "name": "file_search_call", - "arguments": json.dumps( - { - "queries": file_search.get("queries", []), - "status": file_search.get("status"), - } - ), - }, - ) - tool_calls.append(new_tool_call) - asst["tool_calls"] = tool_calls - - elif func_call := cls.maybe_function_tool_call(item): - asst = ensure_assistant_message() - tool_calls = list(asst.get("tool_calls", [])) - new_tool_call = ChatCompletionMessageToolCallParam( - id=func_call["call_id"], - type="function", - function={ - "name": func_call["name"], - "arguments": func_call["arguments"], - }, - ) - tool_calls.append(new_tool_call) - asst["tool_calls"] = tool_calls - # 5) function call output => tool message - elif func_output := cls.maybe_function_tool_call_output(item): - flush_assistant_message() - msg: ChatCompletionToolMessageParam = { - "role": "tool", - "tool_call_id": func_output["call_id"], - "content": func_output["output"], - } - result.append(msg) - - # 6) item reference => handle or raise - elif item_ref := cls.maybe_item_reference(item): - raise UserError( - f"Encountered an item_reference, which is not supported: {item_ref}" - ) - - # 7) If we haven't recognized it => fail or ignore - else: - raise UserError(f"Unhandled item type or structure: {item}") - - flush_assistant_message() - return result - - -class ToolConverter: - @classmethod - def to_openai(cls, tool: Tool) -> ChatCompletionToolParam: - if isinstance(tool, FunctionTool): - return { - "type": "function", - "function": { - "name": tool.name, - "description": tool.description or "", - "parameters": tool.params_json_schema, - }, - } - - raise UserError( - f"Hosted tools are not supported with the ChatCompletions API. FGot tool type: " - f"{type(tool)}, tool: {tool}" - ) - - @classmethod - def convert_handoff_tool(cls, handoff: Handoff[Any]) -> ChatCompletionToolParam: - return { - "type": "function", - "function": { - "name": handoff.tool_name, - "description": handoff.tool_description, - "parameters": handoff.input_json_schema, - }, - } diff --git a/src/agents/models/openai_responses.py b/src/agents/models/openai_responses.py index 17803fda..86c8e69c 100644 --- a/src/agents/models/openai_responses.py +++ b/src/agents/models/openai_responses.py @@ -10,6 +10,7 @@ from openai.types.responses import ( Response, ResponseCompletedEvent, + ResponseIncludable, ResponseStreamEvent, ResponseTextConfigParam, ToolParam, @@ -18,12 +19,22 @@ ) from .. import _debug -from ..agent_output import AgentOutputSchema +from ..agent_output import AgentOutputSchemaBase from ..exceptions import UserError from ..handoffs import Handoff from ..items import ItemHelpers, ModelResponse, TResponseInputItem from ..logger import logger -from ..tool import ComputerTool, FileSearchTool, FunctionTool, Tool, WebSearchTool +from ..tool import ( + CodeInterpreterTool, + ComputerTool, + FileSearchTool, + FunctionTool, + HostedMCPTool, + ImageGenerationTool, + LocalShellTool, + Tool, + WebSearchTool, +) from ..tracing import SpanError, response_span from ..usage import Usage from ..version import __version__ @@ -36,13 +47,6 @@ _USER_AGENT = f"Agents/Python {__version__}" _HEADERS = {"User-Agent": _USER_AGENT} -# From the Responses API -IncludeLiteral = Literal[ - "file_search_call.results", - "message.input_image.image_url", - "computer_call_output.output.image_url", -] - class OpenAIResponsesModel(Model): """ @@ -66,9 +70,10 @@ async def get_response( input: str | list[TResponseInputItem], model_settings: ModelSettings, tools: list[Tool], - output_schema: AgentOutputSchema | None, + output_schema: AgentOutputSchemaBase | None, handoffs: list[Handoff], tracing: ModelTracing, + previous_response_id: str | None, ) -> ModelResponse: with response_span(disabled=tracing.is_disabled()) as span_response: try: @@ -79,6 +84,7 @@ async def get_response( tools, output_schema, handoffs, + previous_response_id, stream=False, ) @@ -96,6 +102,8 @@ async def get_response( input_tokens=response.usage.input_tokens, output_tokens=response.usage.output_tokens, total_tokens=response.usage.total_tokens, + input_tokens_details=response.usage.input_tokens_details, + output_tokens_details=response.usage.output_tokens_details, ) if response.usage else Usage() @@ -120,7 +128,7 @@ async def get_response( return ModelResponse( output=response.output, usage=usage, - referenceable_id=response.id, + response_id=response.id, ) async def stream_response( @@ -129,9 +137,10 @@ async def stream_response( input: str | list[TResponseInputItem], model_settings: ModelSettings, tools: list[Tool], - output_schema: AgentOutputSchema | None, + output_schema: AgentOutputSchemaBase | None, handoffs: list[Handoff], tracing: ModelTracing, + previous_response_id: str | None, ) -> AsyncIterator[ResponseStreamEvent]: """ Yields a partial message as it is generated, as well as the usage information. @@ -145,6 +154,7 @@ async def stream_response( tools, output_schema, handoffs, + previous_response_id, stream=True, ) @@ -178,8 +188,9 @@ async def _fetch_response( input: str | list[TResponseInputItem], model_settings: ModelSettings, tools: list[Tool], - output_schema: AgentOutputSchema | None, + output_schema: AgentOutputSchemaBase | None, handoffs: list[Handoff], + previous_response_id: str | None, stream: Literal[True], ) -> AsyncStream[ResponseStreamEvent]: ... @@ -190,8 +201,9 @@ async def _fetch_response( input: str | list[TResponseInputItem], model_settings: ModelSettings, tools: list[Tool], - output_schema: AgentOutputSchema | None, + output_schema: AgentOutputSchemaBase | None, handoffs: list[Handoff], + previous_response_id: str | None, stream: Literal[False], ) -> Response: ... @@ -201,8 +213,9 @@ async def _fetch_response( input: str | list[TResponseInputItem], model_settings: ModelSettings, tools: list[Tool], - output_schema: AgentOutputSchema | None, + output_schema: AgentOutputSchemaBase | None, handoffs: list[Handoff], + previous_response_id: str | None, stream: Literal[True] | Literal[False] = False, ) -> Response | AsyncStream[ResponseStreamEvent]: list_input = ItemHelpers.input_to_new_input_list(input) @@ -229,9 +242,11 @@ async def _fetch_response( f"Stream: {stream}\n" f"Tool choice: {tool_choice}\n" f"Response format: {response_format}\n" + f"Previous response id: {previous_response_id}\n" ) return await self._client.responses.create( + previous_response_id=self._non_null_or_not_given(previous_response_id), instructions=self._non_null_or_not_given(system_instructions), model=self.model, input=list_input, @@ -244,9 +259,13 @@ async def _fetch_response( tool_choice=tool_choice, parallel_tool_calls=parallel_tool_calls, stream=stream, - extra_headers=_HEADERS, + extra_headers={**_HEADERS, **(model_settings.extra_headers or {})}, + extra_query=model_settings.extra_query, + extra_body=model_settings.extra_body, text=response_format, store=self._non_null_or_not_given(model_settings.store), + reasoning=self._non_null_or_not_given(model_settings.reasoning), + metadata=self._non_null_or_not_given(model_settings.metadata), ) def _get_client(self) -> AsyncOpenAI: @@ -258,7 +277,7 @@ def _get_client(self) -> AsyncOpenAI: @dataclass class ConvertedTools: tools: list[ToolParam] - includes: list[IncludeLiteral] + includes: list[ResponseIncludable] class Converter: @@ -286,6 +305,18 @@ def convert_tool_choice( return { "type": "computer_use_preview", } + elif tool_choice == "image_generation": + return { + "type": "image_generation", + } + elif tool_choice == "code_interpreter": + return { + "type": "code_interpreter", + } + elif tool_choice == "mcp": + return { + "type": "mcp", + } else: return { "type": "function", @@ -294,7 +325,7 @@ def convert_tool_choice( @classmethod def get_response_format( - cls, output_schema: AgentOutputSchema | None + cls, output_schema: AgentOutputSchemaBase | None ) -> ResponseTextConfigParam | NotGiven: if output_schema is None or output_schema.is_plain_text(): return NOT_GIVEN @@ -304,7 +335,7 @@ def get_response_format( "type": "json_schema", "name": "final_output", "schema": output_schema.json_schema(), - "strict": output_schema.strict_json_schema, + "strict": output_schema.is_strict_json_schema(), } } @@ -315,7 +346,7 @@ def convert_tools( handoffs: list[Handoff[Any]], ) -> ConvertedTools: converted_tools: list[ToolParam] = [] - includes: list[IncludeLiteral] = [] + includes: list[ResponseIncludable] = [] computer_tools = [tool for tool in tools if isinstance(tool, ComputerTool)] if len(computer_tools) > 1: @@ -333,7 +364,7 @@ def convert_tools( return ConvertedTools(tools=converted_tools, includes=includes) @classmethod - def _convert_tool(cls, tool: Tool) -> tuple[ToolParam, IncludeLiteral | None]: + def _convert_tool(cls, tool: Tool) -> tuple[ToolParam, ResponseIncludable | None]: """Returns converted tool and includes""" if isinstance(tool, FunctionTool): @@ -344,7 +375,7 @@ def _convert_tool(cls, tool: Tool) -> tuple[ToolParam, IncludeLiteral | None]: "type": "function", "description": tool.description, } - includes: IncludeLiteral | None = None + includes: ResponseIncludable | None = None elif isinstance(tool, WebSearchTool): ws: WebSearchToolParam = { "type": "web_search_preview", @@ -374,7 +405,20 @@ def _convert_tool(cls, tool: Tool) -> tuple[ToolParam, IncludeLiteral | None]: "display_height": tool.computer.dimensions[1], } includes = None - + elif isinstance(tool, HostedMCPTool): + converted_tool = tool.tool_config + includes = None + elif isinstance(tool, ImageGenerationTool): + converted_tool = tool.tool_config + includes = None + elif isinstance(tool, CodeInterpreterTool): + converted_tool = tool.tool_config + includes = None + elif isinstance(tool, LocalShellTool): + converted_tool = { + "type": "local_shell", + } + includes = None else: raise UserError(f"Unknown tool type: {type(tool)}, tool") diff --git a/src/agents/result.py b/src/agents/result.py index 40a64806..243db155 100644 --- a/src/agents/result.py +++ b/src/agents/result.py @@ -10,11 +10,12 @@ from ._run_impl import QueueCompleteSentinel from .agent import Agent -from .agent_output import AgentOutputSchema +from .agent_output import AgentOutputSchemaBase from .exceptions import InputGuardrailTripwireTriggered, MaxTurnsExceeded from .guardrail import InputGuardrailResult, OutputGuardrailResult from .items import ItemHelpers, ModelResponse, RunItem, TResponseInputItem from .logger import logger +from .run_context import RunContextWrapper from .stream_events import StreamEvent from .tracing import Trace from .util._pretty_print import pretty_print_result, pretty_print_run_result_streaming @@ -50,6 +51,9 @@ class RunResultBase(abc.ABC): output_guardrail_results: list[OutputGuardrailResult] """Guardrail results for the final output of the agent.""" + context_wrapper: RunContextWrapper[Any] + """The context wrapper for the agent run.""" + @property @abc.abstractmethod def last_agent(self) -> Agent[Any]: @@ -80,6 +84,14 @@ def to_input_list(self) -> list[TResponseInputItem]: return original_items + new_items + @property + def last_response_id(self) -> str | None: + """Convenience method to get the response ID of the last model response.""" + if not self.raw_responses: + return None + + return self.raw_responses[-1].response_id + @dataclass class RunResult(RunResultBase): @@ -116,9 +128,9 @@ class RunResultStreaming(RunResultBase): final_output: Any """The final output of the agent. This is None until the agent has finished running.""" - _current_agent_output_schema: AgentOutputSchema | None = field(repr=False) + _current_agent_output_schema: AgentOutputSchemaBase | None = field(repr=False) - _trace: Trace | None = field(repr=False) + trace: Trace | None = field(repr=False) is_complete: bool = False """Whether the agent has finished running.""" @@ -144,6 +156,18 @@ def last_agent(self) -> Agent[Any]: """ return self.current_agent + def cancel(self) -> None: + """Cancels the streaming run, stopping all background tasks and marking the run as + complete.""" + self._cleanup_tasks() # Cancel all running tasks + self.is_complete = True # Mark the run as complete to stop event streaming + + # Optionally, clear the event queue to prevent processing stale events + while not self._event_queue.empty(): + self._event_queue.get_nowait() + while not self._input_guardrail_queue.empty(): + self._input_guardrail_queue.get_nowait() + async def stream_events(self) -> AsyncIterator[StreamEvent]: """Stream deltas for new items as they are generated. We're using the types from the OpenAI Responses API, so these are semantic events: each event has a `type` field that @@ -177,9 +201,6 @@ async def stream_events(self) -> AsyncIterator[StreamEvent]: yield item self._event_queue.task_done() - if self._trace: - self._trace.finish(reset_current=True) - self._cleanup_tasks() if self._stored_exception: diff --git a/src/agents/run.py b/src/agents/run.py index 0159822a..b196c3bf 100644 --- a/src/agents/run.py +++ b/src/agents/run.py @@ -19,7 +19,7 @@ get_model_tracing_impl, ) from .agent import Agent -from .agent_output import AgentOutputSchema +from .agent_output import AgentOutputSchema, AgentOutputSchemaBase from .exceptions import ( AgentsException, InputGuardrailTripwireTriggered, @@ -34,7 +34,7 @@ from .logger import logger from .model_settings import ModelSettings from .models.interface import Model, ModelProvider -from .models.openai_provider import OpenAIProvider +from .models.multi_provider import MultiProvider from .result import RunResult, RunResultStreaming from .run_context import RunContextWrapper, TContext from .stream_events import AgentUpdatedStreamEvent, RawResponsesStreamEvent @@ -56,7 +56,7 @@ class RunConfig: agent. The model_provider passed in below must be able to resolve this model name. """ - model_provider: ModelProvider = field(default_factory=OpenAIProvider) + model_provider: ModelProvider = field(default_factory=MultiProvider) """The model provider to use when looking up string model names. Defaults to OpenAI.""" model_settings: ModelSettings | None = None @@ -117,6 +117,7 @@ async def run( max_turns: int = DEFAULT_MAX_TURNS, hooks: RunHooks[TContext] | None = None, run_config: RunConfig | None = None, + previous_response_id: str | None = None, ) -> RunResult: """Run a workflow starting at the given agent. The agent will run in a loop until a final output is generated. The loop runs like so: @@ -141,6 +142,8 @@ async def run( AI invocation (including any tool calls that might occur). hooks: An object that receives callbacks on various lifecycle events. run_config: Global settings for the entire agent run. + previous_response_id: The ID of the previous response, if using OpenAI models via the + Responses API, this allows you to skip passing in input from the previous turn. Returns: A run result containing all the inputs, guardrail results and the output of the last @@ -182,7 +185,7 @@ async def run( if current_span is None: handoff_names = [h.agent_name for h in cls._get_handoffs(current_agent)] if output_schema := cls._get_output_schema(current_agent): - output_type_name = output_schema.output_type_name() + output_type_name = output_schema.name() else: output_type_name = "str" @@ -230,6 +233,7 @@ async def run( run_config=run_config, should_run_agent_start_hooks=should_run_agent_start_hooks, tool_use_tracker=tool_use_tracker, + previous_response_id=previous_response_id, ), ) else: @@ -243,6 +247,7 @@ async def run( run_config=run_config, should_run_agent_start_hooks=should_run_agent_start_hooks, tool_use_tracker=tool_use_tracker, + previous_response_id=previous_response_id, ) should_run_agent_start_hooks = False @@ -265,6 +270,7 @@ async def run( _last_agent=current_agent, input_guardrail_results=input_guardrail_results, output_guardrail_results=output_guardrail_results, + context_wrapper=context_wrapper, ) elif isinstance(turn_result.next_step, NextStepHandoff): current_agent = cast(Agent[TContext], turn_result.next_step.new_agent) @@ -291,6 +297,7 @@ def run_sync( max_turns: int = DEFAULT_MAX_TURNS, hooks: RunHooks[TContext] | None = None, run_config: RunConfig | None = None, + previous_response_id: str | None = None, ) -> RunResult: """Run a workflow synchronously, starting at the given agent. Note that this just wraps the `run` method, so it will not work if there's already an event loop (e.g. inside an async @@ -319,6 +326,8 @@ def run_sync( AI invocation (including any tool calls that might occur). hooks: An object that receives callbacks on various lifecycle events. run_config: Global settings for the entire agent run. + previous_response_id: The ID of the previous response, if using OpenAI models via the + Responses API, this allows you to skip passing in input from the previous turn. Returns: A run result containing all the inputs, guardrail results and the output of the last @@ -332,6 +341,7 @@ def run_sync( max_turns=max_turns, hooks=hooks, run_config=run_config, + previous_response_id=previous_response_id, ) ) @@ -344,6 +354,7 @@ def run_streamed( max_turns: int = DEFAULT_MAX_TURNS, hooks: RunHooks[TContext] | None = None, run_config: RunConfig | None = None, + previous_response_id: str | None = None, ) -> RunResultStreaming: """Run a workflow starting at the given agent in streaming mode. The returned result object contains a method you can use to stream semantic events as they are generated. @@ -370,7 +381,8 @@ def run_streamed( AI invocation (including any tool calls that might occur). hooks: An object that receives callbacks on various lifecycle events. run_config: Global settings for the entire agent run. - + previous_response_id: The ID of the previous response, if using OpenAI models via the + Responses API, this allows you to skip passing in input from the previous turn. Returns: A result object that contains data about the run, as well as a method to stream events. """ @@ -393,10 +405,6 @@ def run_streamed( disabled=run_config.tracing_disabled, ) ) - # Need to start the trace here, because the current trace contextvar is captured at - # asyncio.create_task time - if new_trace: - new_trace.start(mark_as_current=True) output_schema = cls._get_output_schema(starting_agent) context_wrapper: RunContextWrapper[TContext] = RunContextWrapper( @@ -415,7 +423,8 @@ def run_streamed( input_guardrail_results=[], output_guardrail_results=[], _current_agent_output_schema=output_schema, - _trace=new_trace, + trace=new_trace, + context_wrapper=context_wrapper, ) # Kick off the actual agent loop in the background and return the streamed result object. @@ -428,6 +437,7 @@ def run_streamed( hooks=hooks, context_wrapper=context_wrapper, run_config=run_config, + previous_response_id=previous_response_id, ) ) return streamed_result @@ -485,7 +495,11 @@ async def _run_streamed_impl( hooks: RunHooks[TContext], context_wrapper: RunContextWrapper[TContext], run_config: RunConfig, + previous_response_id: str | None, ): + if streamed_result.trace: + streamed_result.trace.start(mark_as_current=True) + current_span: Span[AgentSpanData] | None = None current_agent = starting_agent current_turn = 0 @@ -504,7 +518,7 @@ async def _run_streamed_impl( if current_span is None: handoff_names = [h.agent_name for h in cls._get_handoffs(current_agent)] if output_schema := cls._get_output_schema(current_agent): - output_type_name = output_schema.output_type_name() + output_type_name = output_schema.name() else: output_type_name = "str" @@ -554,6 +568,7 @@ async def _run_streamed_impl( should_run_agent_start_hooks, tool_use_tracker, all_tools, + previous_response_id, ) should_run_agent_start_hooks = False @@ -611,6 +626,8 @@ async def _run_streamed_impl( finally: if current_span: current_span.finish(reset_current=True) + if streamed_result.trace: + streamed_result.trace.finish(reset_current=True) @classmethod async def _run_single_turn_streamed( @@ -623,6 +640,7 @@ async def _run_single_turn_streamed( should_run_agent_start_hooks: bool, tool_use_tracker: AgentToolUseTracker, all_tools: list[Tool], + previous_response_id: str | None, ) -> SingleStepResult: if should_run_agent_start_hooks: await asyncio.gather( @@ -662,6 +680,7 @@ async def _run_single_turn_streamed( get_model_tracing_impl( run_config.tracing_disabled, run_config.trace_include_sensitive_data ), + previous_response_id=previous_response_id, ): if isinstance(event, ResponseCompletedEvent): usage = ( @@ -670,6 +689,8 @@ async def _run_single_turn_streamed( input_tokens=event.response.usage.input_tokens, output_tokens=event.response.usage.output_tokens, total_tokens=event.response.usage.total_tokens, + input_tokens_details=event.response.usage.input_tokens_details, + output_tokens_details=event.response.usage.output_tokens_details, ) if event.response.usage else Usage() @@ -677,8 +698,9 @@ async def _run_single_turn_streamed( final_response = ModelResponse( output=event.response.output, usage=usage, - referenceable_id=event.response.id, + response_id=event.response.id, ) + context_wrapper.usage.add(usage) streamed_result._event_queue.put_nowait(RawResponsesStreamEvent(data=event)) @@ -717,6 +739,7 @@ async def _run_single_turn( run_config: RunConfig, should_run_agent_start_hooks: bool, tool_use_tracker: AgentToolUseTracker, + previous_response_id: str | None, ) -> SingleStepResult: # Ensure we run the hooks before anything else if should_run_agent_start_hooks: @@ -746,6 +769,7 @@ async def _run_single_turn( context_wrapper, run_config, tool_use_tracker, + previous_response_id, ) return await cls._get_single_step_result_from_response( @@ -771,7 +795,7 @@ async def _get_single_step_result_from_response( original_input: str | list[TResponseInputItem], pre_step_items: list[RunItem], new_response: ModelResponse, - output_schema: AgentOutputSchema | None, + output_schema: AgentOutputSchemaBase | None, handoffs: list[Handoff], hooks: RunHooks[TContext], context_wrapper: RunContextWrapper[TContext], @@ -882,12 +906,13 @@ async def _get_new_response( agent: Agent[TContext], system_prompt: str | None, input: list[TResponseInputItem], - output_schema: AgentOutputSchema | None, + output_schema: AgentOutputSchemaBase | None, all_tools: list[Tool], handoffs: list[Handoff], context_wrapper: RunContextWrapper[TContext], run_config: RunConfig, tool_use_tracker: AgentToolUseTracker, + previous_response_id: str | None, ) -> ModelResponse: model = cls._get_model(agent, run_config) model_settings = agent.model_settings.resolve(run_config.model_settings) @@ -903,6 +928,7 @@ async def _get_new_response( tracing=get_model_tracing_impl( run_config.tracing_disabled, run_config.trace_include_sensitive_data ), + previous_response_id=previous_response_id, ) context_wrapper.usage.add(new_response.usage) @@ -910,9 +936,11 @@ async def _get_new_response( return new_response @classmethod - def _get_output_schema(cls, agent: Agent[Any]) -> AgentOutputSchema | None: + def _get_output_schema(cls, agent: Agent[Any]) -> AgentOutputSchemaBase | None: if agent.output_type is None or agent.output_type is str: return None + elif isinstance(agent.output_type, AgentOutputSchemaBase): + return agent.output_type return AgentOutputSchema(agent.output_type) diff --git a/src/agents/stream_events.py b/src/agents/stream_events.py index bd37d11f..111d0b95 100644 --- a/src/agents/stream_events.py +++ b/src/agents/stream_events.py @@ -35,6 +35,8 @@ class RunItemStreamEvent: "tool_called", "tool_output", "reasoning_item_created", + "mcp_approval_requested", + "mcp_list_tools", ] """The name of the event.""" diff --git a/src/agents/tool.py b/src/agents/tool.py index c1c16242..fd5a21c8 100644 --- a/src/agents/tool.py +++ b/src/agents/tool.py @@ -7,9 +7,11 @@ from typing import Any, Callable, Literal, Union, overload from openai.types.responses.file_search_tool_param import Filters, RankingOptions +from openai.types.responses.response_output_item import LocalShellCall, McpApprovalRequest +from openai.types.responses.tool_param import CodeInterpreter, ImageGeneration, Mcp from openai.types.responses.web_search_tool_param import UserLocation from pydantic import ValidationError -from typing_extensions import Concatenate, ParamSpec +from typing_extensions import Concatenate, NotRequired, ParamSpec, TypedDict from . import _debug from .computer import AsyncComputer, Computer @@ -130,7 +132,115 @@ def name(self): return "computer_use_preview" -Tool = Union[FunctionTool, FileSearchTool, WebSearchTool, ComputerTool] +@dataclass +class MCPToolApprovalRequest: + """A request to approve a tool call.""" + + ctx_wrapper: RunContextWrapper[Any] + """The run context.""" + + data: McpApprovalRequest + """The data from the MCP tool approval request.""" + + +class MCPToolApprovalFunctionResult(TypedDict): + """The result of an MCP tool approval function.""" + + approve: bool + """Whether to approve the tool call.""" + + reason: NotRequired[str] + """An optional reason, if rejected.""" + + +MCPToolApprovalFunction = Callable[ + [MCPToolApprovalRequest], MaybeAwaitable[MCPToolApprovalFunctionResult] +] +"""A function that approves or rejects a tool call.""" + + +@dataclass +class HostedMCPTool: + """A tool that allows the LLM to use a remote MCP server. The LLM will automatically list and + call tools, without requiring a a round trip back to your code. + If you want to run MCP servers locally via stdio, in a VPC or other non-publicly-accessible + environment, or you just prefer to run tool calls locally, then you can instead use the servers + in `agents.mcp` and pass `Agent(mcp_servers=[...])` to the agent.""" + + tool_config: Mcp + """The MCP tool config, which includes the server URL and other settings.""" + + on_approval_request: MCPToolApprovalFunction | None = None + """An optional function that will be called if approval is requested for an MCP tool. If not + provided, you will need to manually add approvals/rejections to the input and call + `Runner.run(...)` again.""" + + @property + def name(self): + return "hosted_mcp" + + +@dataclass +class CodeInterpreterTool: + """A tool that allows the LLM to execute code in a sandboxed environment.""" + + tool_config: CodeInterpreter + """The tool config, which includes the container and other settings.""" + + @property + def name(self): + return "code_interpreter" + + +@dataclass +class ImageGenerationTool: + """A tool that allows the LLM to generate images.""" + + tool_config: ImageGeneration + """The tool config, which image generation settings.""" + + @property + def name(self): + return "image_generation" + + +@dataclass +class LocalShellCommandRequest: + """A request to execute a command on a shell.""" + + ctx_wrapper: RunContextWrapper[Any] + """The run context.""" + + data: LocalShellCall + """The data from the local shell tool call.""" + + +LocalShellExecutor = Callable[[LocalShellCommandRequest], MaybeAwaitable[str]] +"""A function that executes a command on a shell.""" + + +@dataclass +class LocalShellTool: + """A tool that allows the LLM to execute commands on a shell.""" + + executor: LocalShellExecutor + """A function that executes a command on a shell.""" + + @property + def name(self): + return "local_shell" + + +Tool = Union[ + FunctionTool, + FileSearchTool, + WebSearchTool, + ComputerTool, + HostedMCPTool, + LocalShellTool, + ImageGenerationTool, + CodeInterpreterTool, +] """A tool that can be used in an agent.""" diff --git a/src/agents/tracing/processors.py b/src/agents/tracing/processors.py index 5d8f4d8a..2913b11a 100644 --- a/src/agents/tracing/processors.py +++ b/src/agents/tracing/processors.py @@ -102,6 +102,12 @@ def export(self, items: list[Trace | Span[Any]]) -> None: "OpenAI-Beta": "traces=v1", } + if self.organization: + headers["OpenAI-Organization"] = self.organization + + if self.project: + headers["OpenAI-Project"] = self.project + # Exponential backoff loop attempt = 0 delay = self.base_delay @@ -182,7 +188,6 @@ def __init__( # Track when we next *must* perform a scheduled export self._next_export_time = time.time() + self._schedule_delay - self._shutdown_event = threading.Event() self._worker_thread = threading.Thread(target=self._run, daemon=True) self._worker_thread.start() diff --git a/src/agents/tracing/scope.py b/src/agents/tracing/scope.py index 513ca8c0..1d31c1bd 100644 --- a/src/agents/tracing/scope.py +++ b/src/agents/tracing/scope.py @@ -18,6 +18,10 @@ class Scope: + """ + Manages the current span and trace in the context. + """ + @classmethod def get_current_span(cls) -> "Span[Any] | None": return _current_span.get() diff --git a/src/agents/tracing/setup.py b/src/agents/tracing/setup.py index 3a7c6ade..9e27d210 100644 --- a/src/agents/tracing/setup.py +++ b/src/agents/tracing/setup.py @@ -201,6 +201,9 @@ def create_span( ) def shutdown(self) -> None: + if self._disabled: + return + try: logger.debug("Shutting down trace provider") self._multi_processor.shutdown() diff --git a/src/agents/tracing/span_data.py b/src/agents/tracing/span_data.py index ed2a3f2d..cb3e8491 100644 --- a/src/agents/tracing/span_data.py +++ b/src/agents/tracing/span_data.py @@ -9,17 +9,28 @@ class SpanData(abc.ABC): + """ + Represents span data in the trace. + """ + @abc.abstractmethod def export(self) -> dict[str, Any]: + """Export the span data as a dictionary.""" pass @property @abc.abstractmethod def type(self) -> str: + """Return the type of the span.""" pass class AgentSpanData(SpanData): + """ + Represents an Agent Span in the trace. + Includes name, handoffs, tools, and output type. + """ + __slots__ = ("name", "handoffs", "tools", "output_type") def __init__( @@ -49,6 +60,11 @@ def export(self) -> dict[str, Any]: class FunctionSpanData(SpanData): + """ + Represents a Function Span in the trace. + Includes input, output and MCP data (if applicable). + """ + __slots__ = ("name", "input", "output", "mcp_data") def __init__( @@ -78,6 +94,11 @@ def export(self) -> dict[str, Any]: class GenerationSpanData(SpanData): + """ + Represents a Generation Span in the trace. + Includes input, output, model, model configuration, and usage. + """ + __slots__ = ( "input", "output", @@ -116,6 +137,11 @@ def export(self) -> dict[str, Any]: class ResponseSpanData(SpanData): + """ + Represents a Response Span in the trace. + Includes response and input. + """ + __slots__ = ("response", "input") def __init__( @@ -140,6 +166,11 @@ def export(self) -> dict[str, Any]: class HandoffSpanData(SpanData): + """ + Represents a Handoff Span in the trace. + Includes source and destination agents. + """ + __slots__ = ("from_agent", "to_agent") def __init__(self, from_agent: str | None, to_agent: str | None): @@ -159,6 +190,11 @@ def export(self) -> dict[str, Any]: class CustomSpanData(SpanData): + """ + Represents a Custom Span in the trace. + Includes name and data property bag. + """ + __slots__ = ("name", "data") def __init__(self, name: str, data: dict[str, Any]): @@ -178,6 +214,11 @@ def export(self) -> dict[str, Any]: class GuardrailSpanData(SpanData): + """ + Represents a Guardrail Span in the trace. + Includes name and triggered status. + """ + __slots__ = ("name", "triggered") def __init__(self, name: str, triggered: bool = False): @@ -197,6 +238,11 @@ def export(self) -> dict[str, Any]: class TranscriptionSpanData(SpanData): + """ + Represents a Transcription Span in the trace. + Includes input, output, model, and model configuration. + """ + __slots__ = ( "input", "output", @@ -236,7 +282,12 @@ def export(self) -> dict[str, Any]: class SpeechSpanData(SpanData): - __slots__ = ("input", "output", "model", "model_config", "first_byte_at") + """ + Represents a Speech Span in the trace. + Includes input, output, model, model configuration, and first content timestamp. + """ + + __slots__ = ("input", "output", "model", "model_config", "first_content_at") def __init__( self, @@ -273,6 +324,10 @@ def export(self) -> dict[str, Any]: class SpeechGroupSpanData(SpanData): + """ + Represents a Speech Group Span in the trace. + """ + __slots__ = "input" def __init__( @@ -283,7 +338,7 @@ def __init__( @property def type(self) -> str: - return "speech-group" + return "speech_group" def export(self) -> dict[str, Any]: return { @@ -293,6 +348,11 @@ def export(self) -> dict[str, Any]: class MCPListToolsSpanData(SpanData): + """ + Represents an MCP List Tools Span in the trace. + Includes server and result. + """ + __slots__ = ( "server", "result", diff --git a/src/agents/usage.py b/src/agents/usage.py index 23d989b4..843f6293 100644 --- a/src/agents/usage.py +++ b/src/agents/usage.py @@ -1,4 +1,6 @@ -from dataclasses import dataclass +from dataclasses import dataclass, field + +from openai.types.responses.response_usage import InputTokensDetails, OutputTokensDetails @dataclass @@ -9,9 +11,18 @@ class Usage: input_tokens: int = 0 """Total input tokens sent, across all requests.""" + input_tokens_details: InputTokensDetails = field( + default_factory=lambda: InputTokensDetails(cached_tokens=0) + ) + """Details about the input tokens, matching responses API usage details.""" output_tokens: int = 0 """Total output tokens received, across all requests.""" + output_tokens_details: OutputTokensDetails = field( + default_factory=lambda: OutputTokensDetails(reasoning_tokens=0) + ) + """Details about the output tokens, matching responses API usage details.""" + total_tokens: int = 0 """Total tokens sent and received, across all requests.""" @@ -20,3 +31,12 @@ def add(self, other: "Usage") -> None: self.input_tokens += other.input_tokens if other.input_tokens else 0 self.output_tokens += other.output_tokens if other.output_tokens else 0 self.total_tokens += other.total_tokens if other.total_tokens else 0 + self.input_tokens_details = InputTokensDetails( + cached_tokens=self.input_tokens_details.cached_tokens + + other.input_tokens_details.cached_tokens + ) + + self.output_tokens_details = OutputTokensDetails( + reasoning_tokens=self.output_tokens_details.reasoning_tokens + + other.output_tokens_details.reasoning_tokens + ) diff --git a/src/agents/version.py b/src/agents/version.py index a0b7e9be..9b22499e 100644 --- a/src/agents/version.py +++ b/src/agents/version.py @@ -1,7 +1,7 @@ import importlib.metadata try: - __version__ = importlib.metadata.version("agents") + __version__ = importlib.metadata.version("openai-agents") except importlib.metadata.PackageNotFoundError: # Fallback if running from source without being installed __version__ = "0.0.0" diff --git a/src/agents/voice/__init__.py b/src/agents/voice/__init__.py index 499c064c..e11ee446 100644 --- a/src/agents/voice/__init__.py +++ b/src/agents/voice/__init__.py @@ -7,6 +7,7 @@ STTModelSettings, TTSModel, TTSModelSettings, + TTSVoice, VoiceModelProvider, ) from .models.openai_model_provider import OpenAIVoiceModelProvider @@ -30,6 +31,7 @@ "STTModelSettings", "TTSModel", "TTSModelSettings", + "TTSVoice", "VoiceModelProvider", "StreamedAudioResult", "SingleAgentVoiceWorkflow", diff --git a/src/agents/voice/model.py b/src/agents/voice/model.py index 220d4b48..c36a4de7 100644 --- a/src/agents/voice/model.py +++ b/src/agents/voice/model.py @@ -14,14 +14,13 @@ ) DEFAULT_TTS_BUFFER_SIZE = 120 +TTSVoice = Literal["alloy", "ash", "coral", "echo", "fable", "onyx", "nova", "sage", "shimmer"] +"""Exportable type for the TTSModelSettings voice enum""" @dataclass class TTSModelSettings: """Settings for a TTS model.""" - - voice: ( - Literal["alloy", "ash", "coral", "echo", "fable", "onyx", "nova", "sage", "shimmer"] | None - ) = None + voice: TTSVoice | None = None """ The voice to use for the TTS model. If not provided, the default voice for the respective model will be used. diff --git a/tests/fake_model.py b/tests/fake_model.py index ecbb7583..9f0c83a2 100644 --- a/tests/fake_model.py +++ b/tests/fake_model.py @@ -3,9 +3,10 @@ from collections.abc import AsyncIterator from typing import Any -from openai.types.responses import Response, ResponseCompletedEvent +from openai.types.responses import Response, ResponseCompletedEvent, ResponseUsage +from openai.types.responses.response_usage import InputTokensDetails, OutputTokensDetails -from agents.agent_output import AgentOutputSchema +from agents.agent_output import AgentOutputSchemaBase from agents.handoffs import Handoff from agents.items import ( ModelResponse, @@ -33,6 +34,10 @@ def __init__( ) self.tracing_enabled = tracing_enabled self.last_turn_args: dict[str, Any] = {} + self.hardcoded_usage: Usage | None = None + + def set_hardcoded_usage(self, usage: Usage): + self.hardcoded_usage = usage def set_next_output(self, output: list[TResponseOutputItem] | Exception): self.turn_outputs.append(output) @@ -51,9 +56,11 @@ async def get_response( input: str | list[TResponseInputItem], model_settings: ModelSettings, tools: list[Tool], - output_schema: AgentOutputSchema | None, + output_schema: AgentOutputSchemaBase | None, handoffs: list[Handoff], tracing: ModelTracing, + *, + previous_response_id: str | None, ) -> ModelResponse: self.last_turn_args = { "system_instructions": system_instructions, @@ -61,6 +68,7 @@ async def get_response( "model_settings": model_settings, "tools": tools, "output_schema": output_schema, + "previous_response_id": previous_response_id, } with generation_span(disabled=not self.tracing_enabled) as span: @@ -80,8 +88,8 @@ async def get_response( return ModelResponse( output=output, - usage=Usage(), - referenceable_id=None, + usage=self.hardcoded_usage or Usage(), + response_id=None, ) async def stream_response( @@ -90,10 +98,20 @@ async def stream_response( input: str | list[TResponseInputItem], model_settings: ModelSettings, tools: list[Tool], - output_schema: AgentOutputSchema | None, + output_schema: AgentOutputSchemaBase | None, handoffs: list[Handoff], tracing: ModelTracing, + *, + previous_response_id: str | None, ) -> AsyncIterator[TResponseStreamEvent]: + self.last_turn_args = { + "system_instructions": system_instructions, + "input": input, + "model_settings": model_settings, + "tools": tools, + "output_schema": output_schema, + "previous_response_id": previous_response_id, + } with generation_span(disabled=not self.tracing_enabled) as span: output = self.get_next_output() if isinstance(output, Exception): @@ -110,11 +128,16 @@ async def stream_response( yield ResponseCompletedEvent( type="response.completed", - response=get_response_obj(output), + response=get_response_obj(output, usage=self.hardcoded_usage), + sequence_number=0, ) -def get_response_obj(output: list[TResponseOutputItem], response_id: str | None = None) -> Response: +def get_response_obj( + output: list[TResponseOutputItem], + response_id: str | None = None, + usage: Usage | None = None, +) -> Response: return Response( id=response_id or "123", created_at=123, @@ -125,4 +148,11 @@ def get_response_obj(output: list[TResponseOutputItem], response_id: str | None tools=[], top_p=None, parallel_tool_calls=False, + usage=ResponseUsage( + input_tokens=usage.input_tokens if usage else 0, + output_tokens=usage.output_tokens if usage else 0, + total_tokens=usage.total_tokens if usage else 0, + input_tokens_details=InputTokensDetails(cached_tokens=0), + output_tokens_details=OutputTokensDetails(reasoning_tokens=0), + ), ) diff --git a/tests/fastapi/__init__.py b/tests/fastapi/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/tests/fastapi/streaming_app.py b/tests/fastapi/streaming_app.py new file mode 100644 index 00000000..b93ccf3f --- /dev/null +++ b/tests/fastapi/streaming_app.py @@ -0,0 +1,30 @@ +from collections.abc import AsyncIterator + +from fastapi import FastAPI +from starlette.responses import StreamingResponse + +from agents import Agent, Runner, RunResultStreaming + +agent = Agent( + name="Assistant", + instructions="You are a helpful assistant.", +) + + +app = FastAPI() + + +@app.post("/stream") +async def stream(): + result = Runner.run_streamed(agent, input="Tell me a joke") + stream_handler = StreamHandler(result) + return StreamingResponse(stream_handler.stream_events(), media_type="application/x-ndjson") + + +class StreamHandler: + def __init__(self, result: RunResultStreaming): + self.result = result + + async def stream_events(self) -> AsyncIterator[str]: + async for event in self.result.stream_events(): + yield f"{event.type}\n\n" diff --git a/tests/fastapi/test_streaming_context.py b/tests/fastapi/test_streaming_context.py new file mode 100644 index 00000000..ee13045e --- /dev/null +++ b/tests/fastapi/test_streaming_context.py @@ -0,0 +1,29 @@ +import pytest +from httpx import ASGITransport, AsyncClient +from inline_snapshot import snapshot + +from ..fake_model import FakeModel +from ..test_responses import get_text_message +from .streaming_app import agent, app + + +@pytest.mark.asyncio +async def test_streaming_context(): + """This ensures that FastAPI streaming works. The context for this test is that the Runner + method was called in one async context, and the streaming was ended in another context, + leading to a tracing error because the context was closed in the wrong context. This test + ensures that this actually works. + """ + model = FakeModel() + agent.model = model + model.set_next_output([get_text_message("done")]) + + transport = ASGITransport(app) + async with AsyncClient(transport=transport, base_url="http://test") as ac: + async with ac.stream("POST", "/stream") as r: + assert r.status_code == 200 + body = (await r.aread()).decode("utf-8") + lines = [line for line in body.splitlines() if line] + assert lines == snapshot( + ["agent_updated_stream_event", "raw_response_event", "run_item_stream_event"] + ) diff --git a/tests/mcp/test_mcp_util.py b/tests/mcp/test_mcp_util.py index 345df996..74356a16 100644 --- a/tests/mcp/test_mcp_util.py +++ b/tests/mcp/test_mcp_util.py @@ -2,10 +2,11 @@ from typing import Any import pytest +from inline_snapshot import snapshot from mcp.types import Tool as MCPTool -from pydantic import BaseModel +from pydantic import BaseModel, TypeAdapter -from agents import FunctionTool, RunContextWrapper +from agents import Agent, FunctionTool, RunContextWrapper from agents.exceptions import AgentsException, ModelBehaviorError from agents.mcp import MCPServer, MCPUtil @@ -18,7 +19,16 @@ class Foo(BaseModel): class Bar(BaseModel): - qux: str + qux: dict[str, str] + + +Baz = TypeAdapter(dict[str, str]) + + +def _convertible_schema() -> dict[str, Any]: + schema = Foo.model_json_schema() + schema["additionalProperties"] = False + return schema @pytest.mark.asyncio @@ -47,15 +57,23 @@ async def test_get_all_function_tools(): server3.add_tool(names[4], schemas[4]) servers: list[MCPServer] = [server1, server2, server3] - tools = await MCPUtil.get_all_function_tools(servers) + tools = await MCPUtil.get_all_function_tools(servers, convert_schemas_to_strict=False) assert len(tools) == 5 assert all(tool.name in names for tool in tools) for idx, tool in enumerate(tools): assert isinstance(tool, FunctionTool) - assert tool.params_json_schema == schemas[idx] + if schemas[idx] == {}: + assert tool.params_json_schema == snapshot({"properties": {}}) + else: + assert tool.params_json_schema == schemas[idx] assert tool.name == names[idx] + # Also make sure it works with strict schemas + tools = await MCPUtil.get_all_function_tools(servers, convert_schemas_to_strict=True) + assert len(tools) == 5 + assert all(tool.name in names for tool in tools) + @pytest.mark.asyncio async def test_invoke_mcp_tool(): @@ -107,3 +125,167 @@ async def test_mcp_invocation_crash_causes_error(caplog: pytest.LogCaptureFixtur await MCPUtil.invoke_mcp_tool(server, tool, ctx, "") assert "Error invoking MCP tool test_tool_1" in caplog.text + + +@pytest.mark.asyncio +async def test_agent_convert_schemas_true(): + """Test that setting convert_schemas_to_strict to True converts non-strict schemas to strict. + - 'foo' tool is already strict and remains strict. + - 'bar' tool is non-strict and becomes strict (additionalProperties set to False, etc). + """ + strict_schema = Foo.model_json_schema() + non_strict_schema = Baz.json_schema() + possible_to_convert_schema = _convertible_schema() + + server = FakeMCPServer() + server.add_tool("foo", strict_schema) + server.add_tool("bar", non_strict_schema) + server.add_tool("baz", possible_to_convert_schema) + agent = Agent( + name="test_agent", mcp_servers=[server], mcp_config={"convert_schemas_to_strict": True} + ) + tools = await agent.get_mcp_tools() + + foo_tool = next(tool for tool in tools if tool.name == "foo") + assert isinstance(foo_tool, FunctionTool) + bar_tool = next(tool for tool in tools if tool.name == "bar") + assert isinstance(bar_tool, FunctionTool) + baz_tool = next(tool for tool in tools if tool.name == "baz") + assert isinstance(baz_tool, FunctionTool) + + # Checks that additionalProperties is set to False + assert foo_tool.params_json_schema == snapshot( + { + "properties": { + "bar": {"title": "Bar", "type": "string"}, + "baz": {"title": "Baz", "type": "integer"}, + }, + "required": ["bar", "baz"], + "title": "Foo", + "type": "object", + "additionalProperties": False, + } + ) + assert foo_tool.strict_json_schema is True, "foo_tool should be strict" + + # Checks that additionalProperties is set to False + assert bar_tool.params_json_schema == snapshot( + {"type": "object", "additionalProperties": {"type": "string"}, "properties": {}} + ) + assert bar_tool.strict_json_schema is False, "bar_tool should not be strict" + + # Checks that additionalProperties is set to False + assert baz_tool.params_json_schema == snapshot( + { + "properties": { + "bar": {"title": "Bar", "type": "string"}, + "baz": {"title": "Baz", "type": "integer"}, + }, + "required": ["bar", "baz"], + "title": "Foo", + "type": "object", + "additionalProperties": False, + } + ) + assert baz_tool.strict_json_schema is True, "baz_tool should be strict" + + +@pytest.mark.asyncio +async def test_agent_convert_schemas_false(): + """Test that setting convert_schemas_to_strict to False leaves tool schemas as non-strict. + - 'foo' tool remains strict. + - 'bar' tool remains non-strict (additionalProperties remains True). + """ + strict_schema = Foo.model_json_schema() + non_strict_schema = Baz.json_schema() + possible_to_convert_schema = _convertible_schema() + + server = FakeMCPServer() + server.add_tool("foo", strict_schema) + server.add_tool("bar", non_strict_schema) + server.add_tool("baz", possible_to_convert_schema) + + agent = Agent( + name="test_agent", mcp_servers=[server], mcp_config={"convert_schemas_to_strict": False} + ) + tools = await agent.get_mcp_tools() + + foo_tool = next(tool for tool in tools if tool.name == "foo") + assert isinstance(foo_tool, FunctionTool) + bar_tool = next(tool for tool in tools if tool.name == "bar") + assert isinstance(bar_tool, FunctionTool) + baz_tool = next(tool for tool in tools if tool.name == "baz") + assert isinstance(baz_tool, FunctionTool) + + assert foo_tool.params_json_schema == strict_schema + assert foo_tool.strict_json_schema is False, "Shouldn't be converted unless specified" + + assert bar_tool.params_json_schema == snapshot( + {"type": "object", "additionalProperties": {"type": "string"}, "properties": {}} + ) + assert bar_tool.strict_json_schema is False + + assert baz_tool.params_json_schema == possible_to_convert_schema + assert baz_tool.strict_json_schema is False, "Shouldn't be converted unless specified" + + +@pytest.mark.asyncio +async def test_agent_convert_schemas_unset(): + """Test that leaving convert_schemas_to_strict unset (defaulting to False) leaves tool schemas + as non-strict. + - 'foo' tool remains strict. + - 'bar' tool remains non-strict. + """ + strict_schema = Foo.model_json_schema() + non_strict_schema = Baz.json_schema() + possible_to_convert_schema = _convertible_schema() + + server = FakeMCPServer() + server.add_tool("foo", strict_schema) + server.add_tool("bar", non_strict_schema) + server.add_tool("baz", possible_to_convert_schema) + agent = Agent(name="test_agent", mcp_servers=[server]) + tools = await agent.get_mcp_tools() + + foo_tool = next(tool for tool in tools if tool.name == "foo") + assert isinstance(foo_tool, FunctionTool) + bar_tool = next(tool for tool in tools if tool.name == "bar") + assert isinstance(bar_tool, FunctionTool) + baz_tool = next(tool for tool in tools if tool.name == "baz") + assert isinstance(baz_tool, FunctionTool) + + assert foo_tool.params_json_schema == strict_schema + assert foo_tool.strict_json_schema is False, "Shouldn't be converted unless specified" + + assert bar_tool.params_json_schema == snapshot( + {"type": "object", "additionalProperties": {"type": "string"}, "properties": {}} + ) + assert bar_tool.strict_json_schema is False + + assert baz_tool.params_json_schema == possible_to_convert_schema + assert baz_tool.strict_json_schema is False, "Shouldn't be converted unless specified" + + +@pytest.mark.asyncio +async def test_util_adds_properties(): + """The MCP spec doesn't require the inputSchema to have `properties`, so we need to add it + if it's missing. + """ + schema = { + "type": "object", + "description": "Test tool", + } + + server = FakeMCPServer() + server.add_tool("test_tool", schema) + + tools = await MCPUtil.get_all_function_tools([server], convert_schemas_to_strict=False) + tool = next(tool for tool in tools if tool.name == "test_tool") + + assert isinstance(tool, FunctionTool) + assert "properties" in tool.params_json_schema + assert tool.params_json_schema["properties"] == {} + + assert tool.params_json_schema == snapshot( + {"type": "object", "description": "Test tool", "properties": {}} + ) diff --git a/tests/mcp/test_server_errors.py b/tests/mcp/test_server_errors.py index bdca7ce6..fbd8db17 100644 --- a/tests/mcp/test_server_errors.py +++ b/tests/mcp/test_server_errors.py @@ -6,7 +6,7 @@ class CrashingClientSessionServer(_MCPServerWithClientSession): def __init__(self): - super().__init__(cache_tools_list=False) + super().__init__(cache_tools_list=False, client_session_timeout_seconds=5) self.cleanup_called = False def create_streams(self): diff --git a/tests/model_settings/test_serialization.py b/tests/model_settings/test_serialization.py new file mode 100644 index 00000000..d76a58d1 --- /dev/null +++ b/tests/model_settings/test_serialization.py @@ -0,0 +1,59 @@ +import json +from dataclasses import fields + +from openai.types.shared import Reasoning + +from agents.model_settings import ModelSettings + + +def verify_serialization(model_settings: ModelSettings) -> None: + """Verify that ModelSettings can be serialized to a JSON string.""" + json_dict = model_settings.to_json_dict() + json_string = json.dumps(json_dict) + assert json_string is not None + + +def test_basic_serialization() -> None: + """Tests whether ModelSettings can be serialized to a JSON string.""" + + # First, lets create a ModelSettings instance + model_settings = ModelSettings( + temperature=0.5, + top_p=0.9, + max_tokens=100, + ) + + # Now, lets serialize the ModelSettings instance to a JSON string + verify_serialization(model_settings) + + +def test_all_fields_serialization() -> None: + """Tests whether ModelSettings can be serialized to a JSON string.""" + + # First, lets create a ModelSettings instance + model_settings = ModelSettings( + temperature=0.5, + top_p=0.9, + frequency_penalty=0.0, + presence_penalty=0.0, + tool_choice="auto", + parallel_tool_calls=True, + truncation="auto", + max_tokens=100, + reasoning=Reasoning(), + metadata={"foo": "bar"}, + store=False, + include_usage=False, + extra_query={"foo": "bar"}, + extra_body={"foo": "bar"}, + extra_headers={"foo": "bar"}, + ) + + # Verify that every single field is set to a non-None value + for field in fields(model_settings): + assert getattr(model_settings, field.name) is not None, ( + f"You must set the {field.name} field" + ) + + # Now, lets serialize the ModelSettings instance to a JSON string + verify_serialization(model_settings) diff --git a/tests/models/__init__.py b/tests/models/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/tests/models/conftest.py b/tests/models/conftest.py new file mode 100644 index 00000000..79d85d8b --- /dev/null +++ b/tests/models/conftest.py @@ -0,0 +1,11 @@ +import os +import sys + + +# Skip voice tests on Python 3.9 +def pytest_ignore_collect(collection_path, config): + if sys.version_info[:2] == (3, 9): + this_dir = os.path.dirname(__file__) + + if str(collection_path).startswith(this_dir): + return True diff --git a/tests/models/test_litellm_chatcompletions_stream.py b/tests/models/test_litellm_chatcompletions_stream.py new file mode 100644 index 00000000..06e46b39 --- /dev/null +++ b/tests/models/test_litellm_chatcompletions_stream.py @@ -0,0 +1,298 @@ +from collections.abc import AsyncIterator + +import pytest +from openai.types.chat.chat_completion_chunk import ( + ChatCompletionChunk, + Choice, + ChoiceDelta, + ChoiceDeltaToolCall, + ChoiceDeltaToolCallFunction, +) +from openai.types.completion_usage import ( + CompletionTokensDetails, + CompletionUsage, + PromptTokensDetails, +) +from openai.types.responses import ( + Response, + ResponseFunctionToolCall, + ResponseOutputMessage, + ResponseOutputRefusal, + ResponseOutputText, +) + +from agents.extensions.models.litellm_model import LitellmModel +from agents.extensions.models.litellm_provider import LitellmProvider +from agents.model_settings import ModelSettings +from agents.models.interface import ModelTracing + + +@pytest.mark.allow_call_model_methods +@pytest.mark.asyncio +async def test_stream_response_yields_events_for_text_content(monkeypatch) -> None: + """ + Validate that `stream_response` emits the correct sequence of events when + streaming a simple assistant message consisting of plain text content. + We simulate two chunks of text returned from the chat completion stream. + """ + # Create two chunks that will be emitted by the fake stream. + chunk1 = ChatCompletionChunk( + id="chunk-id", + created=1, + model="fake", + object="chat.completion.chunk", + choices=[Choice(index=0, delta=ChoiceDelta(content="He"))], + ) + # Mark last chunk with usage so stream_response knows this is final. + chunk2 = ChatCompletionChunk( + id="chunk-id", + created=1, + model="fake", + object="chat.completion.chunk", + choices=[Choice(index=0, delta=ChoiceDelta(content="llo"))], + usage=CompletionUsage( + completion_tokens=5, + prompt_tokens=7, + total_tokens=12, + completion_tokens_details=CompletionTokensDetails(reasoning_tokens=2), + prompt_tokens_details=PromptTokensDetails(cached_tokens=6), + ), + ) + + async def fake_stream() -> AsyncIterator[ChatCompletionChunk]: + for c in (chunk1, chunk2): + yield c + + # Patch _fetch_response to inject our fake stream + async def patched_fetch_response(self, *args, **kwargs): + # `_fetch_response` is expected to return a Response skeleton and the async stream + resp = Response( + id="resp-id", + created_at=0, + model="fake-model", + object="response", + output=[], + tool_choice="none", + tools=[], + parallel_tool_calls=False, + ) + return resp, fake_stream() + + monkeypatch.setattr(LitellmModel, "_fetch_response", patched_fetch_response) + model = LitellmProvider().get_model("gpt-4") + output_events = [] + async for event in model.stream_response( + system_instructions=None, + input="", + model_settings=ModelSettings(), + tools=[], + output_schema=None, + handoffs=[], + tracing=ModelTracing.DISABLED, + previous_response_id=None, + ): + output_events.append(event) + # We expect a response.created, then a response.output_item.added, content part added, + # two content delta events (for "He" and "llo"), a content part done, the assistant message + # output_item.done, and finally response.completed. + # There should be 8 events in total. + assert len(output_events) == 8 + # First event indicates creation. + assert output_events[0].type == "response.created" + # The output item added and content part added events should mark the assistant message. + assert output_events[1].type == "response.output_item.added" + assert output_events[2].type == "response.content_part.added" + # Two text delta events. + assert output_events[3].type == "response.output_text.delta" + assert output_events[3].delta == "He" + assert output_events[4].type == "response.output_text.delta" + assert output_events[4].delta == "llo" + # After streaming, the content part and item should be marked done. + assert output_events[5].type == "response.content_part.done" + assert output_events[6].type == "response.output_item.done" + # Last event indicates completion of the stream. + assert output_events[7].type == "response.completed" + # The completed response should have one output message with full text. + completed_resp = output_events[7].response + assert isinstance(completed_resp.output[0], ResponseOutputMessage) + assert isinstance(completed_resp.output[0].content[0], ResponseOutputText) + assert completed_resp.output[0].content[0].text == "Hello" + + assert completed_resp.usage, "usage should not be None" + assert completed_resp.usage.input_tokens == 7 + assert completed_resp.usage.output_tokens == 5 + assert completed_resp.usage.total_tokens == 12 + assert completed_resp.usage.input_tokens_details.cached_tokens == 6 + assert completed_resp.usage.output_tokens_details.reasoning_tokens == 2 + + +@pytest.mark.allow_call_model_methods +@pytest.mark.asyncio +async def test_stream_response_yields_events_for_refusal_content(monkeypatch) -> None: + """ + Validate that when the model streams a refusal string instead of normal content, + `stream_response` emits the appropriate sequence of events including + `response.refusal.delta` events for each chunk of the refusal message and + constructs a completed assistant message with a `ResponseOutputRefusal` part. + """ + # Simulate refusal text coming in two pieces, like content but using the `refusal` + # field on the delta rather than `content`. + chunk1 = ChatCompletionChunk( + id="chunk-id", + created=1, + model="fake", + object="chat.completion.chunk", + choices=[Choice(index=0, delta=ChoiceDelta(refusal="No"))], + ) + chunk2 = ChatCompletionChunk( + id="chunk-id", + created=1, + model="fake", + object="chat.completion.chunk", + choices=[Choice(index=0, delta=ChoiceDelta(refusal="Thanks"))], + usage=CompletionUsage(completion_tokens=2, prompt_tokens=2, total_tokens=4), + ) + + async def fake_stream() -> AsyncIterator[ChatCompletionChunk]: + for c in (chunk1, chunk2): + yield c + + async def patched_fetch_response(self, *args, **kwargs): + resp = Response( + id="resp-id", + created_at=0, + model="fake-model", + object="response", + output=[], + tool_choice="none", + tools=[], + parallel_tool_calls=False, + ) + return resp, fake_stream() + + monkeypatch.setattr(LitellmModel, "_fetch_response", patched_fetch_response) + model = LitellmProvider().get_model("gpt-4") + output_events = [] + async for event in model.stream_response( + system_instructions=None, + input="", + model_settings=ModelSettings(), + tools=[], + output_schema=None, + handoffs=[], + tracing=ModelTracing.DISABLED, + previous_response_id=None, + ): + output_events.append(event) + # Expect sequence similar to text: created, output_item.added, content part added, + # two refusal delta events, content part done, output_item.done, completed. + assert len(output_events) == 8 + assert output_events[0].type == "response.created" + assert output_events[1].type == "response.output_item.added" + assert output_events[2].type == "response.content_part.added" + assert output_events[3].type == "response.refusal.delta" + assert output_events[3].delta == "No" + assert output_events[4].type == "response.refusal.delta" + assert output_events[4].delta == "Thanks" + assert output_events[5].type == "response.content_part.done" + assert output_events[6].type == "response.output_item.done" + assert output_events[7].type == "response.completed" + completed_resp = output_events[7].response + assert isinstance(completed_resp.output[0], ResponseOutputMessage) + refusal_part = completed_resp.output[0].content[0] + assert isinstance(refusal_part, ResponseOutputRefusal) + assert refusal_part.refusal == "NoThanks" + + +@pytest.mark.allow_call_model_methods +@pytest.mark.asyncio +async def test_stream_response_yields_events_for_tool_call(monkeypatch) -> None: + """ + Validate that `stream_response` emits the correct sequence of events when + the model is streaming a function/tool call instead of plain text. + The function call will be split across two chunks. + """ + # Simulate a single tool call whose ID stays constant and function name/args built over chunks. + tool_call_delta1 = ChoiceDeltaToolCall( + index=0, + id="tool-id", + function=ChoiceDeltaToolCallFunction(name="my_", arguments="arg1"), + type="function", + ) + tool_call_delta2 = ChoiceDeltaToolCall( + index=0, + id="tool-id", + function=ChoiceDeltaToolCallFunction(name="func", arguments="arg2"), + type="function", + ) + chunk1 = ChatCompletionChunk( + id="chunk-id", + created=1, + model="fake", + object="chat.completion.chunk", + choices=[Choice(index=0, delta=ChoiceDelta(tool_calls=[tool_call_delta1]))], + ) + chunk2 = ChatCompletionChunk( + id="chunk-id", + created=1, + model="fake", + object="chat.completion.chunk", + choices=[Choice(index=0, delta=ChoiceDelta(tool_calls=[tool_call_delta2]))], + usage=CompletionUsage(completion_tokens=1, prompt_tokens=1, total_tokens=2), + ) + + async def fake_stream() -> AsyncIterator[ChatCompletionChunk]: + for c in (chunk1, chunk2): + yield c + + async def patched_fetch_response(self, *args, **kwargs): + resp = Response( + id="resp-id", + created_at=0, + model="fake-model", + object="response", + output=[], + tool_choice="none", + tools=[], + parallel_tool_calls=False, + ) + return resp, fake_stream() + + monkeypatch.setattr(LitellmModel, "_fetch_response", patched_fetch_response) + model = LitellmProvider().get_model("gpt-4") + output_events = [] + async for event in model.stream_response( + system_instructions=None, + input="", + model_settings=ModelSettings(), + tools=[], + output_schema=None, + handoffs=[], + tracing=ModelTracing.DISABLED, + previous_response_id=None, + ): + output_events.append(event) + # Sequence should be: response.created, then after loop we expect function call-related events: + # one response.output_item.added for function call, a response.function_call_arguments.delta, + # a response.output_item.done, and finally response.completed. + assert output_events[0].type == "response.created" + # The next three events are about the tool call. + assert output_events[1].type == "response.output_item.added" + # The added item should be a ResponseFunctionToolCall. + added_fn = output_events[1].item + assert isinstance(added_fn, ResponseFunctionToolCall) + assert added_fn.name == "my_func" # Name should be concatenation of both chunks. + assert added_fn.arguments == "arg1arg2" + assert output_events[2].type == "response.function_call_arguments.delta" + assert output_events[2].delta == "arg1arg2" + assert output_events[3].type == "response.output_item.done" + assert output_events[4].type == "response.completed" + assert output_events[2].delta == "arg1arg2" + assert output_events[3].type == "response.output_item.done" + assert output_events[4].type == "response.completed" + assert added_fn.name == "my_func" # Name should be concatenation of both chunks. + assert added_fn.arguments == "arg1arg2" + assert output_events[2].type == "response.function_call_arguments.delta" + assert output_events[2].delta == "arg1arg2" + assert output_events[3].type == "response.output_item.done" + assert output_events[4].type == "response.completed" diff --git a/tests/models/test_litellm_extra_body.py b/tests/models/test_litellm_extra_body.py new file mode 100644 index 00000000..ac56c25c --- /dev/null +++ b/tests/models/test_litellm_extra_body.py @@ -0,0 +1,45 @@ +import litellm +import pytest +from litellm.types.utils import Choices, Message, ModelResponse, Usage + +from agents.extensions.models.litellm_model import LitellmModel +from agents.model_settings import ModelSettings +from agents.models.interface import ModelTracing + + +@pytest.mark.allow_call_model_methods +@pytest.mark.asyncio +async def test_extra_body_is_forwarded(monkeypatch): + """ + Forward `extra_body` entries into litellm.acompletion kwargs. + + This ensures that user-provided parameters (e.g. cached_content) + arrive alongside default arguments. + """ + captured: dict[str, object] = {} + + async def fake_acompletion(model, messages=None, **kwargs): + captured.update(kwargs) + msg = Message(role="assistant", content="ok") + choice = Choices(index=0, message=msg) + return ModelResponse(choices=[choice], usage=Usage(0, 0, 0)) + + monkeypatch.setattr(litellm, "acompletion", fake_acompletion) + settings = ModelSettings( + temperature=0.1, + extra_body={"cached_content": "some_cache", "foo": 123} + ) + model = LitellmModel(model="test-model") + + await model.get_response( + system_instructions=None, + input=[], + model_settings=settings, + tools=[], + output_schema=None, + handoffs=[], + tracing=ModelTracing.DISABLED, + previous_response_id=None, + ) + + assert {"cached_content": "some_cache", "foo": 123}.items() <= captured.items() diff --git a/tests/models/test_map.py b/tests/models/test_map.py new file mode 100644 index 00000000..6b65fc09 --- /dev/null +++ b/tests/models/test_map.py @@ -0,0 +1,20 @@ +from agents import Agent, OpenAIResponsesModel, RunConfig, Runner +from agents.extensions.models.litellm_model import LitellmModel + + +def test_no_prefix_is_openai(): + agent = Agent(model="gpt-4o", instructions="", name="test") + model = Runner._get_model(agent, RunConfig()) + assert isinstance(model, OpenAIResponsesModel) + + +def openai_prefix_is_openai(): + agent = Agent(model="openai/gpt-4o", instructions="", name="test") + model = Runner._get_model(agent, RunConfig()) + assert isinstance(model, OpenAIResponsesModel) + + +def test_litellm_prefix_is_litellm(): + agent = Agent(model="litellm/foo/bar", instructions="", name="test") + model = Runner._get_model(agent, RunConfig()) + assert isinstance(model, LitellmModel) diff --git a/tests/test_agent_config.py b/tests/test_agent_config.py index 44339dad..f79c0cf8 100644 --- a/tests/test_agent_config.py +++ b/tests/test_agent_config.py @@ -1,7 +1,7 @@ import pytest from pydantic import BaseModel -from agents import Agent, Handoff, RunContextWrapper, Runner, handoff +from agents import Agent, AgentOutputSchema, Handoff, RunContextWrapper, Runner, handoff @pytest.mark.asyncio @@ -160,8 +160,9 @@ async def test_agent_final_output(): ) schema = Runner._get_output_schema(agent) + assert isinstance(schema, AgentOutputSchema) assert schema is not None assert schema.output_type == Foo - assert schema.strict_json_schema is True + assert schema.is_strict_json_schema() is True assert schema.json_schema() is not None assert not schema.is_plain_text() diff --git a/tests/test_agent_hooks.py b/tests/test_agent_hooks.py index 33107cba..a6c302dc 100644 --- a/tests/test_agent_hooks.py +++ b/tests/test_agent_hooks.py @@ -224,7 +224,7 @@ class Foo(TypedDict): @pytest.mark.asyncio -async def test_structed_output_non_streamed_agent_hooks(): +async def test_structured_output_non_streamed_agent_hooks(): hooks = AgentHooksForTests() model = FakeModel() agent_1 = Agent(name="test_1", model=model) @@ -295,7 +295,7 @@ async def test_structed_output_non_streamed_agent_hooks(): @pytest.mark.asyncio -async def test_structed_output_streamed_agent_hooks(): +async def test_structured_output_streamed_agent_hooks(): hooks = AgentHooksForTests() model = FakeModel() agent_1 = Agent(name="test_1", model=model) diff --git a/tests/test_agent_runner.py b/tests/test_agent_runner.py index ce0c5804..14a278a9 100644 --- a/tests/test_agent_runner.py +++ b/tests/test_agent_runner.py @@ -642,9 +642,7 @@ async def test_tool_use_behavior_custom_function(): async def test_model_settings_override(): model = FakeModel() agent = Agent( - name="test", - model=model, - model_settings=ModelSettings(temperature=1.0, max_tokens=1000) + name="test", model=model, model_settings=ModelSettings(temperature=1.0, max_tokens=1000) ) model.add_multiple_turn_outputs( @@ -664,3 +662,86 @@ async def test_model_settings_override(): # temperature is overridden by Runner.run, but max_tokens is not assert model.last_turn_args["model_settings"].temperature == 0.5 assert model.last_turn_args["model_settings"].max_tokens == 1000 + + +@pytest.mark.asyncio +async def test_previous_response_id_passed_between_runs(): + """Test that previous_response_id is passed to the model on subsequent runs.""" + model = FakeModel() + model.set_next_output([get_text_message("done")]) + agent = Agent(name="test", model=model) + + assert model.last_turn_args.get("previous_response_id") is None + await Runner.run(agent, input="test", previous_response_id="resp-non-streamed-test") + assert model.last_turn_args.get("previous_response_id") == "resp-non-streamed-test" + + +@pytest.mark.asyncio +async def test_multi_turn_previous_response_id_passed_between_runs(): + """Test that previous_response_id is passed to the model on subsequent runs.""" + + model = FakeModel() + agent = Agent( + name="test", + model=model, + tools=[get_function_tool("foo", "tool_result")], + ) + + model.add_multiple_turn_outputs( + [ + # First turn: a message and tool call + [get_text_message("a_message"), get_function_tool_call("foo", json.dumps({"a": "b"}))], + # Second turn: text message + [get_text_message("done")], + ] + ) + + assert model.last_turn_args.get("previous_response_id") is None + await Runner.run(agent, input="test", previous_response_id="resp-test-123") + assert model.last_turn_args.get("previous_response_id") == "resp-test-123" + + +@pytest.mark.asyncio +async def test_previous_response_id_passed_between_runs_streamed(): + """Test that previous_response_id is passed to the model on subsequent streamed runs.""" + model = FakeModel() + model.set_next_output([get_text_message("done")]) + agent = Agent( + name="test", + model=model, + ) + + assert model.last_turn_args.get("previous_response_id") is None + result = Runner.run_streamed(agent, input="test", previous_response_id="resp-stream-test") + async for _ in result.stream_events(): + pass + + assert model.last_turn_args.get("previous_response_id") == "resp-stream-test" + + +@pytest.mark.asyncio +async def test_previous_response_id_passed_between_runs_streamed_multi_turn(): + """Test that previous_response_id is passed to the model on subsequent streamed runs.""" + + model = FakeModel() + agent = Agent( + name="test", + model=model, + tools=[get_function_tool("foo", "tool_result")], + ) + + model.add_multiple_turn_outputs( + [ + # First turn: a message and tool call + [get_text_message("a_message"), get_function_tool_call("foo", json.dumps({"a": "b"}))], + # Second turn: text message + [get_text_message("done")], + ] + ) + + assert model.last_turn_args.get("previous_response_id") is None + result = Runner.run_streamed(agent, input="test", previous_response_id="resp-stream-test") + async for _ in result.stream_events(): + pass + + assert model.last_turn_args.get("previous_response_id") == "resp-stream-test" diff --git a/tests/test_cancel_streaming.py b/tests/test_cancel_streaming.py new file mode 100644 index 00000000..3417a3c5 --- /dev/null +++ b/tests/test_cancel_streaming.py @@ -0,0 +1,116 @@ +import json + +import pytest + +from agents import Agent, Runner + +from .fake_model import FakeModel +from .test_responses import get_function_tool, get_function_tool_call, get_text_message + + +@pytest.mark.asyncio +async def test_simple_streaming_with_cancel(): + model = FakeModel() + agent = Agent(name="Joker", model=model) + + result = Runner.run_streamed(agent, input="Please tell me 5 jokes.") + num_events = 0 + stop_after = 1 # There are two that the model gives back. + + async for _event in result.stream_events(): + num_events += 1 + if num_events == stop_after: + result.cancel() + + assert num_events == 1, f"Expected {stop_after} visible events, but got {num_events}" + + +@pytest.mark.asyncio +async def test_multiple_events_streaming_with_cancel(): + model = FakeModel() + agent = Agent( + name="Joker", + model=model, + tools=[get_function_tool("foo", "tool_result")], + ) + + model.add_multiple_turn_outputs( + [ + # First turn: a message and tool call + [ + get_text_message("a_message"), + get_function_tool_call("foo", json.dumps({"a": "b"})), + ], + # Second turn: text message + [get_text_message("done")], + ] + ) + + result = Runner.run_streamed(agent, input="Please tell me 5 jokes.") + num_events = 0 + stop_after = 2 + + async for _ in result.stream_events(): + num_events += 1 + if num_events == stop_after: + result.cancel() + + assert num_events == stop_after, f"Expected {stop_after} visible events, but got {num_events}" + + +@pytest.mark.asyncio +async def test_cancel_prevents_further_events(): + model = FakeModel() + agent = Agent(name="Joker", model=model) + result = Runner.run_streamed(agent, input="Please tell me 5 jokes.") + events = [] + async for event in result.stream_events(): + events.append(event) + result.cancel() + break # Cancel after first event + # Try to get more events after cancel + more_events = [e async for e in result.stream_events()] + assert len(events) == 1 + assert more_events == [], "No events should be yielded after cancel()" + + +@pytest.mark.asyncio +async def test_cancel_is_idempotent(): + model = FakeModel() + agent = Agent(name="Joker", model=model) + result = Runner.run_streamed(agent, input="Please tell me 5 jokes.") + events = [] + async for event in result.stream_events(): + events.append(event) + result.cancel() + result.cancel() # Call cancel again + break + # Should not raise or misbehave + assert len(events) == 1 + + +@pytest.mark.asyncio +async def test_cancel_before_streaming(): + model = FakeModel() + agent = Agent(name="Joker", model=model) + result = Runner.run_streamed(agent, input="Please tell me 5 jokes.") + result.cancel() # Cancel before streaming + events = [e async for e in result.stream_events()] + assert events == [], "No events should be yielded if cancel() is called before streaming." + + +@pytest.mark.asyncio +async def test_cancel_cleans_up_resources(): + model = FakeModel() + agent = Agent(name="Joker", model=model) + result = Runner.run_streamed(agent, input="Please tell me 5 jokes.") + # Start streaming, then cancel + async for _ in result.stream_events(): + result.cancel() + break + # After cancel, queues should be empty and is_complete True + assert result.is_complete, "Result should be marked complete after cancel." + assert result._event_queue.empty(), "Event queue should be empty after cancel." + assert result._input_guardrail_queue.empty(), ( + "Input guardrail queue should be empty after cancel." + ) diff --git a/tests/test_extra_headers.py b/tests/test_extra_headers.py new file mode 100644 index 00000000..a6af3007 --- /dev/null +++ b/tests/test_extra_headers.py @@ -0,0 +1,100 @@ +import pytest +from openai.types.chat.chat_completion import ChatCompletion, Choice +from openai.types.chat.chat_completion_message import ChatCompletionMessage +from openai.types.responses.response_usage import InputTokensDetails, OutputTokensDetails + +from agents import ModelSettings, ModelTracing, OpenAIChatCompletionsModel, OpenAIResponsesModel + + +@pytest.mark.allow_call_model_methods +@pytest.mark.asyncio +async def test_extra_headers_passed_to_openai_responses_model(): + """ + Ensure extra_headers in ModelSettings is passed to the OpenAIResponsesModel client. + """ + called_kwargs = {} + + class DummyResponses: + async def create(self, **kwargs): + nonlocal called_kwargs + called_kwargs = kwargs + + class DummyResponse: + id = "dummy" + output = [] + usage = type( + "Usage", + (), + { + "input_tokens": 0, + "output_tokens": 0, + "total_tokens": 0, + "input_tokens_details": InputTokensDetails(cached_tokens=0), + "output_tokens_details": OutputTokensDetails(reasoning_tokens=0), + }, + )() + + return DummyResponse() + + class DummyClient: + def __init__(self): + self.responses = DummyResponses() + + model = OpenAIResponsesModel(model="gpt-4", openai_client=DummyClient()) # type: ignore + extra_headers = {"X-Test-Header": "test-value"} + await model.get_response( + system_instructions=None, + input="hi", + model_settings=ModelSettings(extra_headers=extra_headers), + tools=[], + output_schema=None, + handoffs=[], + tracing=ModelTracing.DISABLED, + previous_response_id=None, + ) + assert "extra_headers" in called_kwargs + assert called_kwargs["extra_headers"]["X-Test-Header"] == "test-value" + + +@pytest.mark.allow_call_model_methods +@pytest.mark.asyncio +async def test_extra_headers_passed_to_openai_client(): + """ + Ensure extra_headers in ModelSettings is passed to the OpenAI client. + """ + called_kwargs = {} + + class DummyCompletions: + async def create(self, **kwargs): + nonlocal called_kwargs + called_kwargs = kwargs + msg = ChatCompletionMessage(role="assistant", content="Hello") + choice = Choice(index=0, finish_reason="stop", message=msg) + return ChatCompletion( + id="resp-id", + created=0, + model="fake", + object="chat.completion", + choices=[choice], + usage=None, + ) + + class DummyClient: + def __init__(self): + self.chat = type("_Chat", (), {"completions": DummyCompletions()})() + self.base_url = "https://api.openai.com" + + model = OpenAIChatCompletionsModel(model="gpt-4", openai_client=DummyClient()) # type: ignore + extra_headers = {"X-Test-Header": "test-value"} + await model.get_response( + system_instructions=None, + input="hi", + model_settings=ModelSettings(extra_headers=extra_headers), + tools=[], + output_schema=None, + handoffs=[], + tracing=ModelTracing.DISABLED, + previous_response_id=None, + ) + assert "extra_headers" in called_kwargs + assert called_kwargs["extra_headers"]["X-Test-Header"] == "test-value" diff --git a/tests/test_function_schema.py b/tests/test_function_schema.py index ef1e9c22..5618d8ae 100644 --- a/tests/test_function_schema.py +++ b/tests/test_function_schema.py @@ -99,7 +99,7 @@ def varargs_function(x: int, *numbers: float, flag: bool = False, **kwargs: Any) def test_varargs_function(): """Test a function that uses *args and **kwargs.""" - func_schema = function_schema(varargs_function) + func_schema = function_schema(varargs_function, strict_json_schema=False) # Check JSON schema structure assert isinstance(func_schema.params_json_schema, dict) assert func_schema.params_json_schema.get("title") == "varargs_function_args" diff --git a/tests/test_function_tool_decorator.py b/tests/test_function_tool_decorator.py index 903dd123..3b52788f 100644 --- a/tests/test_function_tool_decorator.py +++ b/tests/test_function_tool_decorator.py @@ -3,6 +3,7 @@ from typing import Any, Optional import pytest +from inline_snapshot import snapshot from agents import function_tool from agents.run_context import RunContextWrapper @@ -198,3 +199,37 @@ async def test_all_optional_params_function(): input_data = {"x": 10, "y": "world", "z": 99} output = await tool.on_invoke_tool(ctx_wrapper(), json.dumps(input_data)) assert output == "10_world_99" + + +@function_tool +def get_weather(city: str) -> str: + """Get the weather for a given city. + + Args: + city: The city to get the weather for. + """ + return f"The weather in {city} is sunny." + + +@pytest.mark.asyncio +async def test_extract_descriptions_from_docstring(): + """Ensure that we extract function and param descriptions from docstrings.""" + + tool = get_weather + assert tool.description == "Get the weather for a given city." + params_json_schema = tool.params_json_schema + assert params_json_schema == snapshot( + { + "type": "object", + "properties": { + "city": { + "description": "The city to get the weather for.", + "title": "City", + "type": "string", + } + }, + "title": "get_weather_args", + "required": ["city"], + "additionalProperties": False, + } + ) diff --git a/tests/test_items_helpers.py b/tests/test_items_helpers.py index 90fe6475..5dba21d8 100644 --- a/tests/test_items_helpers.py +++ b/tests/test_items_helpers.py @@ -168,7 +168,7 @@ def test_to_input_items_for_message() -> None: message = ResponseOutputMessage( id="m1", content=[content], role="assistant", status="completed", type="message" ) - resp = ModelResponse(output=[message], usage=Usage(), referenceable_id=None) + resp = ModelResponse(output=[message], usage=Usage(), response_id=None) input_items = resp.to_input_items() assert isinstance(input_items, list) and len(input_items) == 1 # The dict should contain exactly the primitive values of the message @@ -193,7 +193,7 @@ def test_to_input_items_for_function_call() -> None: tool_call = ResponseFunctionToolCall( id="f1", arguments="{}", call_id="c1", name="func", type="function_call" ) - resp = ModelResponse(output=[tool_call], usage=Usage(), referenceable_id=None) + resp = ModelResponse(output=[tool_call], usage=Usage(), response_id=None) input_items = resp.to_input_items() assert isinstance(input_items, list) and len(input_items) == 1 expected: ResponseFunctionToolCallParam = { @@ -211,7 +211,7 @@ def test_to_input_items_for_file_search_call() -> None: fs_call = ResponseFileSearchToolCall( id="fs1", queries=["query"], status="completed", type="file_search_call" ) - resp = ModelResponse(output=[fs_call], usage=Usage(), referenceable_id=None) + resp = ModelResponse(output=[fs_call], usage=Usage(), response_id=None) input_items = resp.to_input_items() assert isinstance(input_items, list) and len(input_items) == 1 expected: ResponseFileSearchToolCallParam = { @@ -226,7 +226,7 @@ def test_to_input_items_for_file_search_call() -> None: def test_to_input_items_for_web_search_call() -> None: """A web search tool call output should produce the same dict as a web search input.""" ws_call = ResponseFunctionWebSearch(id="w1", status="completed", type="web_search_call") - resp = ModelResponse(output=[ws_call], usage=Usage(), referenceable_id=None) + resp = ModelResponse(output=[ws_call], usage=Usage(), response_id=None) input_items = resp.to_input_items() assert isinstance(input_items, list) and len(input_items) == 1 expected: ResponseFunctionWebSearchParam = { @@ -248,7 +248,7 @@ def test_to_input_items_for_computer_call_click() -> None: pending_safety_checks=[], status="completed", ) - resp = ModelResponse(output=[comp_call], usage=Usage(), referenceable_id=None) + resp = ModelResponse(output=[comp_call], usage=Usage(), response_id=None) input_items = resp.to_input_items() assert isinstance(input_items, list) and len(input_items) == 1 converted_dict = input_items[0] @@ -268,7 +268,7 @@ def test_to_input_items_for_reasoning() -> None: """A reasoning output should produce the same dict as a reasoning input item.""" rc = Summary(text="why", type="summary_text") reasoning = ResponseReasoningItem(id="rid1", summary=[rc], type="reasoning") - resp = ModelResponse(output=[reasoning], usage=Usage(), referenceable_id=None) + resp = ModelResponse(output=[reasoning], usage=Usage(), response_id=None) input_items = resp.to_input_items() assert isinstance(input_items, list) and len(input_items) == 1 converted_dict = input_items[0] diff --git a/tests/test_openai_chatcompletions.py b/tests/test_openai_chatcompletions.py index 9a53e2b7..ba4605d0 100644 --- a/tests/test_openai_chatcompletions.py +++ b/tests/test_openai_chatcompletions.py @@ -5,7 +5,7 @@ import httpx import pytest -from openai import NOT_GIVEN +from openai import NOT_GIVEN, AsyncOpenAI from openai.types.chat.chat_completion import ChatCompletion, Choice from openai.types.chat.chat_completion_chunk import ChatCompletionChunk from openai.types.chat.chat_completion_message import ChatCompletionMessage @@ -13,7 +13,10 @@ ChatCompletionMessageToolCall, Function, ) -from openai.types.completion_usage import CompletionUsage +from openai.types.completion_usage import ( + CompletionUsage, + PromptTokensDetails, +) from openai.types.responses import ( Response, ResponseFunctionToolCall, @@ -30,6 +33,7 @@ OpenAIProvider, generation_span, ) +from agents.models.chatcmpl_helpers import ChatCmplHelpers from agents.models.fake_id import FAKE_RESPONSES_ID @@ -50,7 +54,13 @@ async def test_get_response_with_text_message(monkeypatch) -> None: model="fake", object="chat.completion", choices=[choice], - usage=CompletionUsage(completion_tokens=5, prompt_tokens=7, total_tokens=12), + usage=CompletionUsage( + completion_tokens=5, + prompt_tokens=7, + total_tokens=12, + # completion_tokens_details left blank to test default + prompt_tokens_details=PromptTokensDetails(cached_tokens=3), + ), ) async def patched_fetch_response(self, *args, **kwargs): @@ -66,6 +76,7 @@ async def patched_fetch_response(self, *args, **kwargs): output_schema=None, handoffs=[], tracing=ModelTracing.DISABLED, + previous_response_id=None, ) # Should have produced exactly one output message with one text part assert isinstance(resp, ModelResponse) @@ -79,7 +90,9 @@ async def patched_fetch_response(self, *args, **kwargs): assert resp.usage.input_tokens == 7 assert resp.usage.output_tokens == 5 assert resp.usage.total_tokens == 12 - assert resp.referenceable_id is None + assert resp.usage.input_tokens_details.cached_tokens == 3 + assert resp.usage.output_tokens_details.reasoning_tokens == 0 + assert resp.response_id is None @pytest.mark.allow_call_model_methods @@ -114,6 +127,7 @@ async def patched_fetch_response(self, *args, **kwargs): output_schema=None, handoffs=[], tracing=ModelTracing.DISABLED, + previous_response_id=None, ) assert len(resp.output) == 1 assert isinstance(resp.output[0], ResponseOutputMessage) @@ -124,6 +138,8 @@ async def patched_fetch_response(self, *args, **kwargs): assert resp.usage.requests == 0 assert resp.usage.input_tokens == 0 assert resp.usage.output_tokens == 0 + assert resp.usage.input_tokens_details.cached_tokens == 0 + assert resp.usage.output_tokens_details.reasoning_tokens == 0 @pytest.mark.allow_call_model_methods @@ -163,6 +179,7 @@ async def patched_fetch_response(self, *args, **kwargs): output_schema=None, handoffs=[], tracing=ModelTracing.DISABLED, + previous_response_id=None, ) # Expect a message item followed by a function tool call item. assert len(resp.output) == 2 @@ -226,7 +243,7 @@ def __init__(self, completions: DummyCompletions) -> None: # Ensure expected args were passed through to OpenAI client. kwargs = completions.kwargs assert kwargs["stream"] is False - assert kwargs["store"] is True + assert kwargs["store"] is NOT_GIVEN assert kwargs["model"] == "gpt-4" assert kwargs["messages"][0]["role"] == "system" assert kwargs["messages"][0]["content"] == "sys" @@ -280,8 +297,8 @@ def __init__(self, completions: DummyCompletions) -> None: ) # Check OpenAI client was called for streaming assert completions.kwargs["stream"] is True - assert completions.kwargs["store"] is True - assert completions.kwargs["stream_options"] == {"include_usage": True} + assert completions.kwargs["store"] is NOT_GIVEN + assert completions.kwargs["stream_options"] is NOT_GIVEN # Response is a proper openai Response assert isinstance(response, Response) assert response.id == FAKE_RESPONSES_ID @@ -290,3 +307,39 @@ def __init__(self, completions: DummyCompletions) -> None: assert response.output == [] # We returned the async iterator produced by our dummy. assert hasattr(stream, "__aiter__") + + +def test_store_param(): + """Should default to True for OpenAI API calls, and False otherwise.""" + + model_settings = ModelSettings() + client = AsyncOpenAI() + assert ChatCmplHelpers.get_store_param(client, model_settings) is True, ( + "Should default to True for OpenAI API calls" + ) + + model_settings = ModelSettings(store=False) + assert ChatCmplHelpers.get_store_param(client, model_settings) is False, ( + "Should respect explicitly set store=False" + ) + + model_settings = ModelSettings(store=True) + assert ChatCmplHelpers.get_store_param(client, model_settings) is True, ( + "Should respect explicitly set store=True" + ) + + client = AsyncOpenAI(base_url="http://www.notopenai.com") + model_settings = ModelSettings() + assert ChatCmplHelpers.get_store_param(client, model_settings) is None, ( + "Should default to None for non-OpenAI API calls" + ) + + model_settings = ModelSettings(store=False) + assert ChatCmplHelpers.get_store_param(client, model_settings) is False, ( + "Should respect explicitly set store=False" + ) + + model_settings = ModelSettings(store=True) + assert ChatCmplHelpers.get_store_param(client, model_settings) is True, ( + "Should respect explicitly set store=True" + ) diff --git a/tests/test_openai_chatcompletions_converter.py b/tests/test_openai_chatcompletions_converter.py index 73acb8ab..bcfca549 100644 --- a/tests/test_openai_chatcompletions_converter.py +++ b/tests/test_openai_chatcompletions_converter.py @@ -4,7 +4,7 @@ # See LICENSE file in the project root for full license information. """ -Unit tests for the internal `_Converter` class defined in +Unit tests for the internal `Converter` class defined in `agents.models.openai_chatcompletions`. The converter is responsible for translating between internal "item" structures (e.g., `ResponseOutputMessage` and related types from `openai.types.responses`) and the ChatCompletion message @@ -12,10 +12,10 @@ These tests exercise both conversion directions: -- `_Converter.message_to_output_items` turns a `ChatCompletionMessage` (as +- `Converter.message_to_output_items` turns a `ChatCompletionMessage` (as returned by the OpenAI API) into a list of `ResponseOutputItem` instances. -- `_Converter.items_to_messages` takes in either a simple string prompt, or a +- `Converter.items_to_messages` takes in either a simple string prompt, or a list of input/output items such as `ResponseOutputMessage` and `ResponseFunctionToolCallParam` dicts, and constructs a list of `ChatCompletionMessageParam` dicts suitable for sending back to the API. @@ -41,8 +41,8 @@ from agents.agent_output import AgentOutputSchema from agents.exceptions import UserError from agents.items import TResponseInputItem +from agents.models.chatcmpl_converter import Converter from agents.models.fake_id import FAKE_RESPONSES_ID -from agents.models.openai_chatcompletions import _Converter def test_message_to_output_items_with_text_only(): @@ -51,7 +51,7 @@ def test_message_to_output_items_with_text_only(): into a single ResponseOutputMessage containing one ResponseOutputText. """ msg = ChatCompletionMessage(role="assistant", content="Hello") - items = _Converter.message_to_output_items(msg) + items = Converter.message_to_output_items(msg) # Expect exactly one output item (the message) assert len(items) == 1 message_item = cast(ResponseOutputMessage, items[0]) @@ -72,7 +72,7 @@ def test_message_to_output_items_with_refusal(): with a ResponseOutputRefusal content part. """ msg = ChatCompletionMessage(role="assistant", refusal="I'm sorry") - items = _Converter.message_to_output_items(msg) + items = Converter.message_to_output_items(msg) assert len(items) == 1 message_item = cast(ResponseOutputMessage, items[0]) assert len(message_item.content) == 1 @@ -93,7 +93,7 @@ def test_message_to_output_items_with_tool_call(): function=Function(name="myfn", arguments='{"x":1}'), ) msg = ChatCompletionMessage(role="assistant", content="Hi", tool_calls=[tool_call]) - items = _Converter.message_to_output_items(msg) + items = Converter.message_to_output_items(msg) # Should produce a message item followed by one function tool call item assert len(items) == 2 message_item = cast(ResponseOutputMessage, items[0]) @@ -111,7 +111,7 @@ def test_items_to_messages_with_string_user_content(): A simple string as the items argument should be converted into a user message param dict with the same content. """ - result = _Converter.items_to_messages("Ask me anything") + result = Converter.items_to_messages("Ask me anything") assert isinstance(result, list) assert len(result) == 1 msg = result[0] @@ -130,7 +130,7 @@ def test_items_to_messages_with_easy_input_message(): "content": "How are you?", } ] - messages = _Converter.items_to_messages(items) + messages = Converter.items_to_messages(items) assert len(messages) == 1 out = messages[0] assert out["role"] == "user" @@ -174,7 +174,7 @@ def test_items_to_messages_with_output_message_and_function_call(): resp_msg.model_dump(), # type:ignore func_item, ] - messages = _Converter.items_to_messages(items) + messages = Converter.items_to_messages(items) # Should return a single assistant message assert len(messages) == 1 assistant = messages[0] @@ -197,16 +197,16 @@ def test_items_to_messages_with_output_message_and_function_call(): def test_convert_tool_choice_handles_standard_and_named_options() -> None: """ - The `_Converter.convert_tool_choice` method should return NOT_GIVEN + The `Converter.convert_tool_choice` method should return NOT_GIVEN if no choice is provided, pass through values like "auto", "required", or "none" unchanged, and translate any other string into a function selection dict. """ - assert _Converter.convert_tool_choice(None).__class__.__name__ == "NotGiven" - assert _Converter.convert_tool_choice("auto") == "auto" - assert _Converter.convert_tool_choice("required") == "required" - assert _Converter.convert_tool_choice("none") == "none" - tool_choice_dict = _Converter.convert_tool_choice("mytool") + assert Converter.convert_tool_choice(None).__class__.__name__ == "NotGiven" + assert Converter.convert_tool_choice("auto") == "auto" + assert Converter.convert_tool_choice("required") == "required" + assert Converter.convert_tool_choice("none") == "none" + tool_choice_dict = Converter.convert_tool_choice("mytool") assert isinstance(tool_choice_dict, dict) assert tool_choice_dict["type"] == "function" assert tool_choice_dict["function"]["name"] == "mytool" @@ -214,25 +214,25 @@ def test_convert_tool_choice_handles_standard_and_named_options() -> None: def test_convert_response_format_returns_not_given_for_plain_text_and_dict_for_schemas() -> None: """ - The `_Converter.convert_response_format` method should return NOT_GIVEN + The `Converter.convert_response_format` method should return NOT_GIVEN when no output schema is provided or if the output schema indicates plain text. For structured output schemas, it should return a dict with type `json_schema` and include the generated JSON schema and strict flag from the provided `AgentOutputSchema`. """ # when output is plain text (schema None or output_type str), do not include response_format - assert _Converter.convert_response_format(None).__class__.__name__ == "NotGiven" + assert Converter.convert_response_format(None).__class__.__name__ == "NotGiven" assert ( - _Converter.convert_response_format(AgentOutputSchema(str)).__class__.__name__ == "NotGiven" + Converter.convert_response_format(AgentOutputSchema(str)).__class__.__name__ == "NotGiven" ) # For e.g. integer output, we expect a response_format dict schema = AgentOutputSchema(int) - resp_format = _Converter.convert_response_format(schema) + resp_format = Converter.convert_response_format(schema) assert isinstance(resp_format, dict) assert resp_format["type"] == "json_schema" assert resp_format["json_schema"]["name"] == "final_output" assert "strict" in resp_format["json_schema"] - assert resp_format["json_schema"]["strict"] == schema.strict_json_schema + assert resp_format["json_schema"]["strict"] == schema.is_strict_json_schema() assert "schema" in resp_format["json_schema"] assert resp_format["json_schema"]["schema"] == schema.json_schema() @@ -247,7 +247,7 @@ def test_items_to_messages_with_function_output_item(): "call_id": "somecall", "output": '{"foo": "bar"}', } - messages = _Converter.items_to_messages([func_output_item]) + messages = Converter.items_to_messages([func_output_item]) assert len(messages) == 1 tool_msg = messages[0] assert tool_msg["role"] == "tool" @@ -266,16 +266,16 @@ def test_extract_all_and_text_content_for_strings_and_lists(): should filter to only the textual parts. """ prompt = "just text" - assert _Converter.extract_all_content(prompt) == prompt - assert _Converter.extract_text_content(prompt) == prompt + assert Converter.extract_all_content(prompt) == prompt + assert Converter.extract_text_content(prompt) == prompt text1: ResponseInputTextParam = {"type": "input_text", "text": "one"} text2: ResponseInputTextParam = {"type": "input_text", "text": "two"} - all_parts = _Converter.extract_all_content([text1, text2]) + all_parts = Converter.extract_all_content([text1, text2]) assert isinstance(all_parts, list) assert len(all_parts) == 2 assert all_parts[0]["type"] == "text" and all_parts[0]["text"] == "one" assert all_parts[1]["type"] == "text" and all_parts[1]["text"] == "two" - text_parts = _Converter.extract_text_content([text1, text2]) + text_parts = Converter.extract_text_content([text1, text2]) assert isinstance(text_parts, list) assert all(p["type"] == "text" for p in text_parts) assert [p["text"] for p in text_parts] == ["one", "two"] @@ -288,12 +288,12 @@ def test_items_to_messages_handles_system_and_developer_roles(): `message` typed dicts. """ sys_items: list[TResponseInputItem] = [{"role": "system", "content": "setup"}] - sys_msgs = _Converter.items_to_messages(sys_items) + sys_msgs = Converter.items_to_messages(sys_items) assert len(sys_msgs) == 1 assert sys_msgs[0]["role"] == "system" assert sys_msgs[0]["content"] == "setup" dev_items: list[TResponseInputItem] = [{"role": "developer", "content": "debug"}] - dev_msgs = _Converter.items_to_messages(dev_items) + dev_msgs = Converter.items_to_messages(dev_items) assert len(dev_msgs) == 1 assert dev_msgs[0]["role"] == "developer" assert dev_msgs[0]["content"] == "debug" @@ -301,7 +301,7 @@ def test_items_to_messages_handles_system_and_developer_roles(): def test_maybe_input_message_allows_message_typed_dict(): """ - The `_Converter.maybe_input_message` should recognize a dict with + The `Converter.maybe_input_message` should recognize a dict with "type": "message" and a supported role as an input message. Ensure that such dicts are passed through by `items_to_messages`. """ @@ -311,9 +311,9 @@ def test_maybe_input_message_allows_message_typed_dict(): "role": "user", "content": "hi", } - assert _Converter.maybe_input_message(message_dict) is not None + assert Converter.maybe_input_message(message_dict) is not None # items_to_messages should process this correctly - msgs = _Converter.items_to_messages([message_dict]) + msgs = Converter.items_to_messages([message_dict]) assert len(msgs) == 1 assert msgs[0]["role"] == "user" assert msgs[0]["content"] == "hi" @@ -331,7 +331,7 @@ def test_tool_call_conversion(): type="function_call", ) - messages = _Converter.items_to_messages([function_call]) + messages = Converter.items_to_messages([function_call]) assert len(messages) == 1 tool_msg = messages[0] assert tool_msg["role"] == "assistant" @@ -348,7 +348,7 @@ def test_tool_call_conversion(): @pytest.mark.parametrize("role", ["user", "system", "developer"]) def test_input_message_with_all_roles(role: str): """ - The `_Converter.maybe_input_message` should recognize a dict with + The `Converter.maybe_input_message` should recognize a dict with "type": "message" and a supported role as an input message. Ensure that such dicts are passed through by `items_to_messages`. """ @@ -359,9 +359,9 @@ def test_input_message_with_all_roles(role: str): "role": casted_role, "content": "hi", } - assert _Converter.maybe_input_message(message_dict) is not None + assert Converter.maybe_input_message(message_dict) is not None # items_to_messages should process this correctly - msgs = _Converter.items_to_messages([message_dict]) + msgs = Converter.items_to_messages([message_dict]) assert len(msgs) == 1 assert msgs[0]["role"] == casted_role assert msgs[0]["content"] == "hi" @@ -372,7 +372,7 @@ def test_item_reference_errors(): Test that item references are converted correctly. """ with pytest.raises(UserError): - _Converter.items_to_messages( + Converter.items_to_messages( [ { "type": "item_reference", @@ -392,14 +392,14 @@ def test_unknown_object_errors(): """ with pytest.raises(UserError, match="Unhandled item type or structure"): # Purposely ignore the type error - _Converter.items_to_messages([TestObject()]) # type: ignore + Converter.items_to_messages([TestObject()]) # type: ignore def test_assistant_messages_in_history(): """ Test that assistant messages are added to the history. """ - messages = _Converter.items_to_messages( + messages = Converter.items_to_messages( [ { "role": "user", diff --git a/tests/test_openai_chatcompletions_stream.py b/tests/test_openai_chatcompletions_stream.py index 7add92a6..5c8bb9e3 100644 --- a/tests/test_openai_chatcompletions_stream.py +++ b/tests/test_openai_chatcompletions_stream.py @@ -8,7 +8,11 @@ ChoiceDeltaToolCall, ChoiceDeltaToolCallFunction, ) -from openai.types.completion_usage import CompletionUsage +from openai.types.completion_usage import ( + CompletionTokensDetails, + CompletionUsage, + PromptTokensDetails, +) from openai.types.responses import ( Response, ResponseFunctionToolCall, @@ -46,7 +50,13 @@ async def test_stream_response_yields_events_for_text_content(monkeypatch) -> No model="fake", object="chat.completion.chunk", choices=[Choice(index=0, delta=ChoiceDelta(content="llo"))], - usage=CompletionUsage(completion_tokens=5, prompt_tokens=7, total_tokens=12), + usage=CompletionUsage( + completion_tokens=5, + prompt_tokens=7, + total_tokens=12, + prompt_tokens_details=PromptTokensDetails(cached_tokens=2), + completion_tokens_details=CompletionTokensDetails(reasoning_tokens=3), + ), ) async def fake_stream() -> AsyncIterator[ChatCompletionChunk]: @@ -79,6 +89,7 @@ async def patched_fetch_response(self, *args, **kwargs): output_schema=None, handoffs=[], tracing=ModelTracing.DISABLED, + previous_response_id=None, ): output_events.append(event) # We expect a response.created, then a response.output_item.added, content part added, @@ -111,6 +122,8 @@ async def patched_fetch_response(self, *args, **kwargs): assert completed_resp.usage.input_tokens == 7 assert completed_resp.usage.output_tokens == 5 assert completed_resp.usage.total_tokens == 12 + assert completed_resp.usage.input_tokens_details.cached_tokens == 2 + assert completed_resp.usage.output_tokens_details.reasoning_tokens == 3 @pytest.mark.allow_call_model_methods @@ -168,6 +181,7 @@ async def patched_fetch_response(self, *args, **kwargs): output_schema=None, handoffs=[], tracing=ModelTracing.DISABLED, + previous_response_id=None, ): output_events.append(event) # Expect sequence similar to text: created, output_item.added, content part added, @@ -255,6 +269,7 @@ async def patched_fetch_response(self, *args, **kwargs): output_schema=None, handoffs=[], tracing=ModelTracing.DISABLED, + previous_response_id=None, ): output_events.append(event) # Sequence should be: response.created, then after loop we expect function call-related events: diff --git a/tests/test_openai_responses_converter.py b/tests/test_openai_responses_converter.py index 34cbac5c..8e486665 100644 --- a/tests/test_openai_responses_converter.py +++ b/tests/test_openai_responses_converter.py @@ -92,7 +92,7 @@ class OutModel(BaseModel): assert inner.get("name") == "final_output" assert isinstance(inner.get("schema"), dict) # Should include a strict flag matching the schema's strictness setting. - assert inner.get("strict") == out_schema.strict_json_schema + assert inner.get("strict") == out_schema.is_strict_json_schema() def test_convert_tools_basic_types_and_includes(): diff --git a/tests/test_output_tool.py b/tests/test_output_tool.py index 86c4b3b5..37c1b1b6 100644 --- a/tests/test_output_tool.py +++ b/tests/test_output_tool.py @@ -1,10 +1,18 @@ import json +from typing import Any import pytest from pydantic import BaseModel from typing_extensions import TypedDict -from agents import Agent, AgentOutputSchema, ModelBehaviorError, Runner, UserError +from agents import ( + Agent, + AgentOutputSchema, + AgentOutputSchemaBase, + ModelBehaviorError, + Runner, + UserError, +) from agents.agent_output import _WRAPPER_DICT_KEY from agents.util import _json @@ -27,6 +35,7 @@ def test_structured_output_pydantic(): output_schema = Runner._get_output_schema(agent) assert output_schema, "Should have an output tool config with a structured output type" + assert isinstance(output_schema, AgentOutputSchema) assert output_schema.output_type == Foo, "Should have the correct output type" assert not output_schema._is_wrapped, "Pydantic objects should not be wrapped" for key, value in Foo.model_json_schema().items(): @@ -45,6 +54,7 @@ def test_structured_output_typed_dict(): agent = Agent(name="test", output_type=Bar) output_schema = Runner._get_output_schema(agent) assert output_schema, "Should have an output tool config with a structured output type" + assert isinstance(output_schema, AgentOutputSchema) assert output_schema.output_type == Bar, "Should have the correct output type" assert not output_schema._is_wrapped, "TypedDicts should not be wrapped" @@ -57,6 +67,7 @@ def test_structured_output_list(): agent = Agent(name="test", output_type=list[str]) output_schema = Runner._get_output_schema(agent) assert output_schema, "Should have an output tool config with a structured output type" + assert isinstance(output_schema, AgentOutputSchema) assert output_schema.output_type == list[str], "Should have the correct output type" assert output_schema._is_wrapped, "Lists should be wrapped" @@ -98,7 +109,7 @@ def test_plain_text_obj_doesnt_produce_schema(): def test_structured_output_is_strict(): output_wrapper = AgentOutputSchema(output_type=Foo) - assert output_wrapper.strict_json_schema + assert output_wrapper.is_strict_json_schema() for key, value in Foo.model_json_schema().items(): assert output_wrapper.json_schema()[key] == value @@ -110,6 +121,48 @@ def test_structured_output_is_strict(): def test_setting_strict_false_works(): output_wrapper = AgentOutputSchema(output_type=Foo, strict_json_schema=False) - assert not output_wrapper.strict_json_schema + assert not output_wrapper.is_strict_json_schema() assert output_wrapper.json_schema() == Foo.model_json_schema() assert output_wrapper.json_schema() == Foo.model_json_schema() + + +_CUSTOM_OUTPUT_SCHEMA_JSON_SCHEMA = { + "type": "object", + "properties": { + "foo": {"type": "string"}, + }, + "required": ["foo"], +} + + +class CustomOutputSchema(AgentOutputSchemaBase): + def is_plain_text(self) -> bool: + return False + + def name(self) -> str: + return "FooBarBaz" + + def json_schema(self) -> dict[str, Any]: + return _CUSTOM_OUTPUT_SCHEMA_JSON_SCHEMA + + def is_strict_json_schema(self) -> bool: + return False + + def validate_json(self, json_str: str) -> Any: + return ["some", "output"] + + +def test_custom_output_schema(): + custom_output_schema = CustomOutputSchema() + agent = Agent(name="test", output_type=custom_output_schema) + output_schema = Runner._get_output_schema(agent) + + assert output_schema, "Should have an output tool config with a structured output type" + assert isinstance(output_schema, CustomOutputSchema) + assert output_schema.json_schema() == _CUSTOM_OUTPUT_SCHEMA_JSON_SCHEMA + assert not output_schema.is_strict_json_schema() + assert not output_schema.is_plain_text() + + json_str = json.dumps({"foo": "bar"}) + validated = output_schema.validate_json(json_str) + assert validated == ["some", "output"] diff --git a/tests/test_responses_tracing.py b/tests/test_responses_tracing.py index 40bdfafb..db24fe49 100644 --- a/tests/test_responses_tracing.py +++ b/tests/test_responses_tracing.py @@ -1,7 +1,10 @@ +from typing import Optional + import pytest from inline_snapshot import snapshot from openai import AsyncOpenAI from openai.types.responses import ResponseCompletedEvent +from openai.types.responses.response_usage import InputTokensDetails, OutputTokensDetails from agents import ModelSettings, ModelTracing, OpenAIResponsesModel, trace from agents.tracing.span_data import ResponseSpanData @@ -16,10 +19,25 @@ def is_disabled(self): class DummyUsage: - def __init__(self, input_tokens=1, output_tokens=1, total_tokens=2): + def __init__( + self, + input_tokens: int = 1, + input_tokens_details: Optional[InputTokensDetails] = None, + output_tokens: int = 1, + output_tokens_details: Optional[OutputTokensDetails] = None, + total_tokens: int = 2, + ): self.input_tokens = input_tokens self.output_tokens = output_tokens self.total_tokens = total_tokens + self.input_tokens_details = ( + input_tokens_details if input_tokens_details else InputTokensDetails(cached_tokens=0) + ) + self.output_tokens_details = ( + output_tokens_details + if output_tokens_details + else OutputTokensDetails(reasoning_tokens=0) + ) class DummyResponse: @@ -32,6 +50,7 @@ def __aiter__(self): yield ResponseCompletedEvent( type="response.completed", response=fake_model.get_response_obj(self.output), + sequence_number=0, ) @@ -44,7 +63,14 @@ async def test_get_response_creates_trace(monkeypatch): # Mock _fetch_response to return a dummy response with a known id async def dummy_fetch_response( - system_instructions, input, model_settings, tools, output_schema, handoffs, stream + system_instructions, + input, + model_settings, + tools, + output_schema, + handoffs, + prev_response_id, + stream, ): return DummyResponse() @@ -52,7 +78,14 @@ async def dummy_fetch_response( # Call get_response await model.get_response( - "instr", "input", ModelSettings(), [], None, [], ModelTracing.ENABLED + "instr", + "input", + ModelSettings(), + [], + None, + [], + ModelTracing.ENABLED, + previous_response_id=None, ) assert fetch_normalized_spans() == snapshot( @@ -74,7 +107,14 @@ async def test_non_data_tracing_doesnt_set_response_id(monkeypatch): # Mock _fetch_response to return a dummy response with a known id async def dummy_fetch_response( - system_instructions, input, model_settings, tools, output_schema, handoffs, stream + system_instructions, + input, + model_settings, + tools, + output_schema, + handoffs, + prev_response_id, + stream, ): return DummyResponse() @@ -82,7 +122,14 @@ async def dummy_fetch_response( # Call get_response await model.get_response( - "instr", "input", ModelSettings(), [], None, [], ModelTracing.ENABLED_WITHOUT_DATA + "instr", + "input", + ModelSettings(), + [], + None, + [], + ModelTracing.ENABLED_WITHOUT_DATA, + previous_response_id=None, ) assert fetch_normalized_spans() == snapshot( @@ -102,7 +149,14 @@ async def test_disable_tracing_does_not_create_span(monkeypatch): # Mock _fetch_response to return a dummy response with a known id async def dummy_fetch_response( - system_instructions, input, model_settings, tools, output_schema, handoffs, stream + system_instructions, + input, + model_settings, + tools, + output_schema, + handoffs, + prev_response_id, + stream, ): return DummyResponse() @@ -110,7 +164,14 @@ async def dummy_fetch_response( # Call get_response await model.get_response( - "instr", "input", ModelSettings(), [], None, [], ModelTracing.DISABLED + "instr", + "input", + ModelSettings(), + [], + None, + [], + ModelTracing.DISABLED, + previous_response_id=None, ) assert fetch_normalized_spans() == snapshot([{"workflow_name": "test"}]) @@ -127,13 +188,21 @@ async def test_stream_response_creates_trace(monkeypatch): # Define a dummy fetch function that returns an async stream with a dummy response async def dummy_fetch_response( - system_instructions, input, model_settings, tools, output_schema, handoffs, stream + system_instructions, + input, + model_settings, + tools, + output_schema, + handoffs, + prev_response_id, + stream, ): class DummyStream: async def __aiter__(self): yield ResponseCompletedEvent( type="response.completed", response=fake_model.get_response_obj([], "dummy-id-123"), + sequence_number=0, ) return DummyStream() @@ -142,7 +211,14 @@ async def __aiter__(self): # Consume the stream to trigger processing of the final response async for _ in model.stream_response( - "instr", "input", ModelSettings(), [], None, [], ModelTracing.ENABLED + "instr", + "input", + ModelSettings(), + [], + None, + [], + ModelTracing.ENABLED, + previous_response_id=None, ): pass @@ -165,13 +241,21 @@ async def test_stream_non_data_tracing_doesnt_set_response_id(monkeypatch): # Define a dummy fetch function that returns an async stream with a dummy response async def dummy_fetch_response( - system_instructions, input, model_settings, tools, output_schema, handoffs, stream + system_instructions, + input, + model_settings, + tools, + output_schema, + handoffs, + prev_response_id, + stream, ): class DummyStream: async def __aiter__(self): yield ResponseCompletedEvent( type="response.completed", response=fake_model.get_response_obj([], "dummy-id-123"), + sequence_number=0, ) return DummyStream() @@ -180,7 +264,14 @@ async def __aiter__(self): # Consume the stream to trigger processing of the final response async for _ in model.stream_response( - "instr", "input", ModelSettings(), [], None, [], ModelTracing.ENABLED_WITHOUT_DATA + "instr", + "input", + ModelSettings(), + [], + None, + [], + ModelTracing.ENABLED_WITHOUT_DATA, + previous_response_id=None, ): pass @@ -202,13 +293,21 @@ async def test_stream_disabled_tracing_doesnt_create_span(monkeypatch): # Define a dummy fetch function that returns an async stream with a dummy response async def dummy_fetch_response( - system_instructions, input, model_settings, tools, output_schema, handoffs, stream + system_instructions, + input, + model_settings, + tools, + output_schema, + handoffs, + prev_response_id, + stream, ): class DummyStream: async def __aiter__(self): yield ResponseCompletedEvent( type="response.completed", response=fake_model.get_response_obj([], "dummy-id-123"), + sequence_number=0, ) return DummyStream() @@ -217,7 +316,14 @@ async def __aiter__(self): # Consume the stream to trigger processing of the final response async for _ in model.stream_response( - "instr", "input", ModelSettings(), [], None, [], ModelTracing.DISABLED + "instr", + "input", + ModelSettings(), + [], + None, + [], + ModelTracing.DISABLED, + previous_response_id=None, ): pass diff --git a/tests/test_result_cast.py b/tests/test_result_cast.py index ec17e327..c621e735 100644 --- a/tests/test_result_cast.py +++ b/tests/test_result_cast.py @@ -3,7 +3,7 @@ import pytest from pydantic import BaseModel -from agents import Agent, RunResult +from agents import Agent, RunContextWrapper, RunResult def create_run_result(final_output: Any) -> RunResult: @@ -15,6 +15,7 @@ def create_run_result(final_output: Any) -> RunResult: input_guardrail_results=[], output_guardrail_results=[], _last_agent=Agent(name="test"), + context_wrapper=RunContextWrapper(context=None), ) diff --git a/tests/test_run_step_execution.py b/tests/test_run_step_execution.py index 16c62c84..6ae25fbd 100644 --- a/tests/test_run_step_execution.py +++ b/tests/test_run_step_execution.py @@ -43,7 +43,7 @@ async def test_empty_response_is_final_output(): response = ModelResponse( output=[], usage=Usage(), - referenceable_id=None, + response_id=None, ) result = await get_execute_result(agent, response) @@ -59,7 +59,7 @@ async def test_plaintext_agent_no_tool_calls_is_final_output(): response = ModelResponse( output=[get_text_message("hello_world")], usage=Usage(), - referenceable_id=None, + response_id=None, ) result = await get_execute_result(agent, response) @@ -79,7 +79,7 @@ async def test_plaintext_agent_no_tool_calls_multiple_messages_is_final_output() get_text_message("bye"), ], usage=Usage(), - referenceable_id=None, + response_id=None, ) result = await get_execute_result( agent, @@ -105,7 +105,7 @@ async def test_plaintext_agent_with_tool_call_is_run_again(): response = ModelResponse( output=[get_text_message("hello_world"), get_function_tool_call("test", "")], usage=Usage(), - referenceable_id=None, + response_id=None, ) result = await get_execute_result(agent, response) @@ -140,7 +140,7 @@ async def test_multiple_tool_calls(): get_function_tool_call("test_2"), ], usage=Usage(), - referenceable_id=None, + response_id=None, ) result = await get_execute_result(agent, response) @@ -166,7 +166,7 @@ async def test_handoff_output_leads_to_handoff_next_step(): response = ModelResponse( output=[get_text_message("Hello, world!"), get_handoff_tool_call(agent_1)], usage=Usage(), - referenceable_id=None, + response_id=None, ) result = await get_execute_result(agent_3, response) @@ -186,7 +186,7 @@ async def test_final_output_without_tool_runs_again(): response = ModelResponse( output=[get_function_tool_call("tool_1")], usage=Usage(), - referenceable_id=None, + response_id=None, ) result = await get_execute_result(agent, response) @@ -203,7 +203,7 @@ async def test_final_output_leads_to_final_output_next_step(): get_final_output_message(Foo(bar="123").model_dump_json()), ], usage=Usage(), - referenceable_id=None, + response_id=None, ) result = await get_execute_result(agent, response) @@ -222,7 +222,7 @@ async def test_handoff_and_final_output_leads_to_handoff_next_step(): get_handoff_tool_call(agent_1), ], usage=Usage(), - referenceable_id=None, + response_id=None, ) result = await get_execute_result(agent_3, response) @@ -241,7 +241,7 @@ async def test_multiple_final_output_leads_to_final_output_next_step(): get_final_output_message(Foo(bar="456").model_dump_json()), ], usage=Usage(), - referenceable_id=None, + response_id=None, ) result = await get_execute_result(agent_3, response) diff --git a/tests/test_run_step_processing.py b/tests/test_run_step_processing.py index 2a6634ac..2ea98f06 100644 --- a/tests/test_run_step_processing.py +++ b/tests/test_run_step_processing.py @@ -39,7 +39,7 @@ def test_empty_response(): response = ModelResponse( output=[], usage=Usage(), - referenceable_id=None, + response_id=None, ) result = RunImpl.process_model_response( @@ -58,7 +58,7 @@ def test_no_tool_calls(): response = ModelResponse( output=[get_text_message("Hello, world!")], usage=Usage(), - referenceable_id=None, + response_id=None, ) result = RunImpl.process_model_response( agent=agent, response=response, output_schema=None, handoffs=[], all_tools=[] @@ -76,7 +76,7 @@ async def test_single_tool_call(): get_function_tool_call("test", ""), ], usage=Usage(), - referenceable_id=None, + response_id=None, ) result = RunImpl.process_model_response( agent=agent, @@ -102,7 +102,7 @@ async def test_missing_tool_call_raises_error(): get_function_tool_call("missing", ""), ], usage=Usage(), - referenceable_id=None, + response_id=None, ) with pytest.raises(ModelBehaviorError): @@ -132,7 +132,7 @@ async def test_multiple_tool_calls(): get_function_tool_call("test_2", "xyz"), ], usage=Usage(), - referenceable_id=None, + response_id=None, ) result = RunImpl.process_model_response( @@ -162,7 +162,7 @@ async def test_handoffs_parsed_correctly(): response = ModelResponse( output=[get_text_message("Hello, world!")], usage=Usage(), - referenceable_id=None, + response_id=None, ) result = RunImpl.process_model_response( agent=agent_3, @@ -176,7 +176,7 @@ async def test_handoffs_parsed_correctly(): response = ModelResponse( output=[get_text_message("Hello, world!"), get_handoff_tool_call(agent_1)], usage=Usage(), - referenceable_id=None, + response_id=None, ) result = RunImpl.process_model_response( agent=agent_3, @@ -205,7 +205,7 @@ async def test_missing_handoff_fails(): response = ModelResponse( output=[get_text_message("Hello, world!"), get_handoff_tool_call(agent_2)], usage=Usage(), - referenceable_id=None, + response_id=None, ) with pytest.raises(ModelBehaviorError): RunImpl.process_model_response( @@ -229,7 +229,7 @@ async def test_multiple_handoffs_doesnt_error(): get_handoff_tool_call(agent_2), ], usage=Usage(), - referenceable_id=None, + response_id=None, ) result = RunImpl.process_model_response( agent=agent_3, @@ -254,7 +254,7 @@ async def test_final_output_parsed_correctly(): get_final_output_message(Foo(bar="123").model_dump_json()), ], usage=Usage(), - referenceable_id=None, + response_id=None, ) RunImpl.process_model_response( @@ -281,7 +281,7 @@ async def test_file_search_tool_call_parsed_correctly(): response = ModelResponse( output=[get_text_message("hello"), file_search_call], usage=Usage(), - referenceable_id=None, + response_id=None, ) result = RunImpl.process_model_response( agent=agent, @@ -306,7 +306,7 @@ async def test_function_web_search_tool_call_parsed_correctly(): response = ModelResponse( output=[get_text_message("hello"), web_search_call], usage=Usage(), - referenceable_id=None, + response_id=None, ) result = RunImpl.process_model_response( agent=agent, @@ -333,7 +333,7 @@ async def test_reasoning_item_parsed_correctly(): response = ModelResponse( output=[reasoning], usage=Usage(), - referenceable_id=None, + response_id=None, ) result = RunImpl.process_model_response( agent=Agent(name="test"), @@ -401,7 +401,7 @@ async def test_computer_tool_call_without_computer_tool_raises_error(): response = ModelResponse( output=[computer_call], usage=Usage(), - referenceable_id=None, + response_id=None, ) with pytest.raises(ModelBehaviorError): RunImpl.process_model_response( @@ -430,7 +430,7 @@ async def test_computer_tool_call_with_computer_tool_parsed_correctly(): response = ModelResponse( output=[computer_call], usage=Usage(), - referenceable_id=None, + response_id=None, ) result = RunImpl.process_model_response( agent=agent, @@ -460,7 +460,7 @@ async def test_tool_and_handoff_parsed_correctly(): get_handoff_tool_call(agent_1), ], usage=Usage(), - referenceable_id=None, + response_id=None, ) result = RunImpl.process_model_response( diff --git a/tests/test_tool_converter.py b/tests/test_tool_converter.py index 1b6ebcf9..918de015 100644 --- a/tests/test_tool_converter.py +++ b/tests/test_tool_converter.py @@ -3,7 +3,7 @@ from agents import Agent, Handoff, function_tool, handoff from agents.exceptions import UserError -from agents.models.openai_chatcompletions import ToolConverter +from agents.models.chatcmpl_converter import Converter from agents.tool import FileSearchTool, WebSearchTool @@ -15,7 +15,7 @@ def test_to_openai_with_function_tool(): some_function(a="foo", b=[1, 2, 3]) tool = function_tool(some_function) - result = ToolConverter.to_openai(tool) + result = Converter.tool_to_openai(tool) assert result["type"] == "function" assert result["function"]["name"] == "some_function" @@ -34,7 +34,7 @@ class Foo(BaseModel): def test_convert_handoff_tool(): agent = Agent(name="test_1", handoff_description="test_2") handoff_obj = handoff(agent=agent) - result = ToolConverter.convert_handoff_tool(handoff_obj) + result = Converter.convert_handoff_tool(handoff_obj) assert result["type"] == "function" assert result["function"]["name"] == Handoff.default_tool_name(agent) @@ -48,7 +48,7 @@ def test_convert_handoff_tool(): def test_tool_converter_hosted_tools_errors(): with pytest.raises(UserError): - ToolConverter.to_openai(WebSearchTool()) + Converter.tool_to_openai(WebSearchTool()) with pytest.raises(UserError): - ToolConverter.to_openai(FileSearchTool(vector_store_ids=["abc"], max_num_results=1)) + Converter.tool_to_openai(FileSearchTool(vector_store_ids=["abc"], max_num_results=1)) diff --git a/tests/test_tracing_errors.py b/tests/test_tracing_errors.py index 6d698bcc..72bd39ed 100644 --- a/tests/test_tracing_errors.py +++ b/tests/test_tracing_errors.py @@ -244,9 +244,10 @@ async def test_multiple_handoff_doesnt_error(): }, }, {"type": "generation"}, - {"type": "handoff", - "data": {"from_agent": "test", "to_agent": "test"}, - "error": { + { + "type": "handoff", + "data": {"from_agent": "test", "to_agent": "test"}, + "error": { "data": { "requested_agents": [ "test", @@ -255,7 +256,7 @@ async def test_multiple_handoff_doesnt_error(): }, "message": "Multiple handoffs requested", }, - }, + }, ], }, { @@ -383,10 +384,7 @@ async def test_handoffs_lead_to_correct_agent_spans(): {"type": "generation"}, { "type": "handoff", - "data": { - "from_agent": "test_agent_3", - "to_agent": "test_agent_1" - }, + "data": {"from_agent": "test_agent_3", "to_agent": "test_agent_1"}, "error": { "data": { "requested_agents": [ diff --git a/tests/test_usage.py b/tests/test_usage.py new file mode 100644 index 00000000..405f99dd --- /dev/null +++ b/tests/test_usage.py @@ -0,0 +1,52 @@ +from openai.types.responses.response_usage import InputTokensDetails, OutputTokensDetails + +from agents.usage import Usage + + +def test_usage_add_aggregates_all_fields(): + u1 = Usage( + requests=1, + input_tokens=10, + input_tokens_details=InputTokensDetails(cached_tokens=3), + output_tokens=20, + output_tokens_details=OutputTokensDetails(reasoning_tokens=5), + total_tokens=30, + ) + u2 = Usage( + requests=2, + input_tokens=7, + input_tokens_details=InputTokensDetails(cached_tokens=4), + output_tokens=8, + output_tokens_details=OutputTokensDetails(reasoning_tokens=6), + total_tokens=15, + ) + + u1.add(u2) + + assert u1.requests == 3 + assert u1.input_tokens == 17 + assert u1.output_tokens == 28 + assert u1.total_tokens == 45 + assert u1.input_tokens_details.cached_tokens == 7 + assert u1.output_tokens_details.reasoning_tokens == 11 + + +def test_usage_add_aggregates_with_none_values(): + u1 = Usage() + u2 = Usage( + requests=2, + input_tokens=7, + input_tokens_details=InputTokensDetails(cached_tokens=4), + output_tokens=8, + output_tokens_details=OutputTokensDetails(reasoning_tokens=6), + total_tokens=15, + ) + + u1.add(u2) + + assert u1.requests == 2 + assert u1.input_tokens == 7 + assert u1.output_tokens == 8 + assert u1.total_tokens == 15 + assert u1.input_tokens_details.cached_tokens == 4 + assert u1.output_tokens_details.reasoning_tokens == 6 diff --git a/tests/voice/conftest.py b/tests/voice/conftest.py index 7eeb9cec..79d85d8b 100644 --- a/tests/voice/conftest.py +++ b/tests/voice/conftest.py @@ -1,14 +1,11 @@ import os import sys -import pytest - -def pytest_collection_modifyitems(config, items): +# Skip voice tests on Python 3.9 +def pytest_ignore_collect(collection_path, config): if sys.version_info[:2] == (3, 9): this_dir = os.path.dirname(__file__) - skip_marker = pytest.mark.skip(reason="Skipped on Python 3.9") - for item in items: - if item.fspath.dirname.startswith(this_dir): - item.add_marker(skip_marker) + if str(collection_path).startswith(this_dir): + return True diff --git a/tests/voice/test_workflow.py b/tests/voice/test_workflow.py index 3f18c049..035a05d5 100644 --- a/tests/voice/test_workflow.py +++ b/tests/voice/test_workflow.py @@ -9,7 +9,7 @@ from openai.types.responses.response_text_delta_event import ResponseTextDeltaEvent from agents import Agent, Model, ModelSettings, ModelTracing, Tool -from agents.agent_output import AgentOutputSchema +from agents.agent_output import AgentOutputSchemaBase from agents.handoffs import Handoff from agents.items import ( ModelResponse, @@ -48,9 +48,11 @@ async def get_response( input: str | list[TResponseInputItem], model_settings: ModelSettings, tools: list[Tool], - output_schema: AgentOutputSchema | None, + output_schema: AgentOutputSchemaBase | None, handoffs: list[Handoff], tracing: ModelTracing, + *, + previous_response_id: str | None, ) -> ModelResponse: raise NotImplementedError("Not implemented") @@ -60,9 +62,11 @@ async def stream_response( input: str | list[TResponseInputItem], model_settings: ModelSettings, tools: list[Tool], - output_schema: AgentOutputSchema | None, + output_schema: AgentOutputSchemaBase | None, handoffs: list[Handoff], tracing: ModelTracing, + *, + previous_response_id: str | None, ) -> AsyncIterator[TResponseStreamEvent]: output = self.get_next_output() for item in output: @@ -77,11 +81,13 @@ async def stream_response( type="response.output_text.delta", output_index=0, item_id=item.id, + sequence_number=0, ) yield ResponseCompletedEvent( type="response.completed", response=get_response_obj(output), + sequence_number=1, ) diff --git a/uv.lock b/uv.lock index a9e8f1e7..6f2f3f84 100644 --- a/uv.lock +++ b/uv.lock @@ -1,10 +1,130 @@ version = 1 +revision = 1 requires-python = ">=3.9" resolution-markers = [ "python_full_version >= '3.10'", "python_full_version < '3.10'", ] +[[package]] +name = "aiohappyeyeballs" +version = "2.6.1" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/26/30/f84a107a9c4331c14b2b586036f40965c128aa4fee4dda5d3d51cb14ad54/aiohappyeyeballs-2.6.1.tar.gz", hash = "sha256:c3f9d0113123803ccadfdf3f0faa505bc78e6a72d1cc4806cbd719826e943558", size = 22760 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/0f/15/5bf3b99495fb160b63f95972b81750f18f7f4e02ad051373b669d17d44f2/aiohappyeyeballs-2.6.1-py3-none-any.whl", hash = "sha256:f349ba8f4b75cb25c99c5c2d84e997e485204d2902a9597802b0371f09331fb8", size = 15265 }, +] + +[[package]] +name = "aiohttp" +version = "3.11.16" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "aiohappyeyeballs" }, + { name = "aiosignal" }, + { name = "async-timeout", marker = "python_full_version < '3.11'" }, + { name = "attrs" }, + { name = "frozenlist" }, + { name = "multidict" }, + { name = "propcache" }, + { name = "yarl" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/f1/d9/1c4721d143e14af753f2bf5e3b681883e1f24b592c0482df6fa6e33597fa/aiohttp-3.11.16.tar.gz", hash = "sha256:16f8a2c9538c14a557b4d309ed4d0a7c60f0253e8ed7b6c9a2859a7582f8b1b8", size = 7676826 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/b8/21/6bd4cb580a323b64cda3b11fcb3f68deba77568e97806727a858de57349d/aiohttp-3.11.16-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:fb46bb0f24813e6cede6cc07b1961d4b04f331f7112a23b5e21f567da4ee50aa", size = 708259 }, + { url = "https://files.pythonhosted.org/packages/96/8c/7b4b9debe90ffc31931b85ee8612a5c83f34d8fdc6d90ee3eb27b43639e4/aiohttp-3.11.16-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:54eb3aead72a5c19fad07219acd882c1643a1027fbcdefac9b502c267242f955", size = 468886 }, + { url = "https://files.pythonhosted.org/packages/13/da/a7fcd68e62acacf0a1930060afd2c970826f989265893082b6fb9eb25cb5/aiohttp-3.11.16-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:38bea84ee4fe24ebcc8edeb7b54bf20f06fd53ce4d2cc8b74344c5b9620597fd", size = 455846 }, + { url = "https://files.pythonhosted.org/packages/5d/12/b73d9423253f4c872d276a3771decb0722cb5f962352593bd617445977ba/aiohttp-3.11.16-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d0666afbe984f6933fe72cd1f1c3560d8c55880a0bdd728ad774006eb4241ecd", size = 1587183 }, + { url = "https://files.pythonhosted.org/packages/75/d3/291b57d54719d996e6cb8c1db8b13d01bdb24dca90434815ac7e6a70393f/aiohttp-3.11.16-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:7ba92a2d9ace559a0a14b03d87f47e021e4fa7681dc6970ebbc7b447c7d4b7cd", size = 1634937 }, + { url = "https://files.pythonhosted.org/packages/be/85/4229eba92b433173065b0b459ab677ca11ead4a179f76ccfe55d8738b188/aiohttp-3.11.16-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3ad1d59fd7114e6a08c4814983bb498f391c699f3c78712770077518cae63ff7", size = 1667980 }, + { url = "https://files.pythonhosted.org/packages/2b/0d/d2423936962e3c711fafd5bb9172a99e6b07dd63e086515aa957d8a991fd/aiohttp-3.11.16-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:98b88a2bf26965f2015a771381624dd4b0839034b70d406dc74fd8be4cc053e3", size = 1590365 }, + { url = "https://files.pythonhosted.org/packages/ea/93/04209affc20834982c1ef4214b1afc07743667998a9975d69413e9c1e1c1/aiohttp-3.11.16-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:576f5ca28d1b3276026f7df3ec841ae460e0fc3aac2a47cbf72eabcfc0f102e1", size = 1547614 }, + { url = "https://files.pythonhosted.org/packages/f6/fb/194ad4e4cae98023ae19556e576347f402ce159e80d74cc0713d460c4a39/aiohttp-3.11.16-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:a2a450bcce4931b295fc0848f384834c3f9b00edfc2150baafb4488c27953de6", size = 1532815 }, + { url = "https://files.pythonhosted.org/packages/33/6d/a4da7adbac90188bf1228c73b6768a607dd279c146721a9ff7dcb75c5ac6/aiohttp-3.11.16-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:37dcee4906454ae377be5937ab2a66a9a88377b11dd7c072df7a7c142b63c37c", size = 1559005 }, + { url = "https://files.pythonhosted.org/packages/7e/88/2fa9fbfd23fc16cb2cfdd1f290343e085e7e327438041e9c6aa0208a854d/aiohttp-3.11.16-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:4d0c970c0d602b1017e2067ff3b7dac41c98fef4f7472ec2ea26fd8a4e8c2149", size = 1535231 }, + { url = "https://files.pythonhosted.org/packages/f5/8f/9623cd2558e3e182d02dcda8b480643e1c48a0550a86e3050210e98dba27/aiohttp-3.11.16-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:004511d3413737700835e949433536a2fe95a7d0297edd911a1e9705c5b5ea43", size = 1609985 }, + { url = "https://files.pythonhosted.org/packages/f8/a2/53a8d1bfc67130710f1c8091f623cdefe7f85cd5d09e14637ed2ed6e1a6d/aiohttp-3.11.16-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:c15b2271c44da77ee9d822552201180779e5e942f3a71fb74e026bf6172ff287", size = 1628842 }, + { url = "https://files.pythonhosted.org/packages/49/3a/35fb43d07489573c6c1f8c6a3e6c657196124a63223705b7feeddaea06f1/aiohttp-3.11.16-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:ad9509ffb2396483ceacb1eee9134724443ee45b92141105a4645857244aecc8", size = 1566929 }, + { url = "https://files.pythonhosted.org/packages/d5/82/bb3f4f2cc7677e790ba4c040db7dd8445c234a810ef893a858e217647d38/aiohttp-3.11.16-cp310-cp310-win32.whl", hash = "sha256:634d96869be6c4dc232fc503e03e40c42d32cfaa51712aee181e922e61d74814", size = 416935 }, + { url = "https://files.pythonhosted.org/packages/df/ad/a64db1c18063569d6dff474c46a7d4de7ab85ff55e2a35839b149b1850ea/aiohttp-3.11.16-cp310-cp310-win_amd64.whl", hash = "sha256:938f756c2b9374bbcc262a37eea521d8a0e6458162f2a9c26329cc87fdf06534", size = 442168 }, + { url = "https://files.pythonhosted.org/packages/b1/98/be30539cd84260d9f3ea1936d50445e25aa6029a4cb9707f3b64cfd710f7/aiohttp-3.11.16-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:8cb0688a8d81c63d716e867d59a9ccc389e97ac7037ebef904c2b89334407180", size = 708664 }, + { url = "https://files.pythonhosted.org/packages/e6/27/d51116ce18bdfdea7a2244b55ad38d7b01a4298af55765eed7e8431f013d/aiohttp-3.11.16-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:0ad1fb47da60ae1ddfb316f0ff16d1f3b8e844d1a1e154641928ea0583d486ed", size = 468953 }, + { url = "https://files.pythonhosted.org/packages/34/23/eedf80ec42865ea5355b46265a2433134138eff9a4fea17e1348530fa4ae/aiohttp-3.11.16-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:df7db76400bf46ec6a0a73192b14c8295bdb9812053f4fe53f4e789f3ea66bbb", size = 456065 }, + { url = "https://files.pythonhosted.org/packages/36/23/4a5b1ef6cff994936bf96d981dd817b487d9db755457a0d1c2939920d620/aiohttp-3.11.16-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cc3a145479a76ad0ed646434d09216d33d08eef0d8c9a11f5ae5cdc37caa3540", size = 1687976 }, + { url = "https://files.pythonhosted.org/packages/d0/5d/c7474b4c3069bb35276d54c82997dff4f7575e4b73f0a7b1b08a39ece1eb/aiohttp-3.11.16-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d007aa39a52d62373bd23428ba4a2546eed0e7643d7bf2e41ddcefd54519842c", size = 1752711 }, + { url = "https://files.pythonhosted.org/packages/64/4c/ee416987b6729558f2eb1b727c60196580aafdb141e83bd78bb031d1c000/aiohttp-3.11.16-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f6ddd90d9fb4b501c97a4458f1c1720e42432c26cb76d28177c5b5ad4e332601", size = 1791305 }, + { url = "https://files.pythonhosted.org/packages/58/28/3e1e1884070b95f1f69c473a1995852a6f8516670bb1c29d6cb2dbb73e1c/aiohttp-3.11.16-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0a2f451849e6b39e5c226803dcacfa9c7133e9825dcefd2f4e837a2ec5a3bb98", size = 1674499 }, + { url = "https://files.pythonhosted.org/packages/ad/55/a032b32fa80a662d25d9eb170ed1e2c2be239304ca114ec66c89dc40f37f/aiohttp-3.11.16-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8df6612df74409080575dca38a5237282865408016e65636a76a2eb9348c2567", size = 1622313 }, + { url = "https://files.pythonhosted.org/packages/b1/df/ca775605f72abbda4e4746e793c408c84373ca2c6ce7a106a09f853f1e89/aiohttp-3.11.16-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:78e6e23b954644737e385befa0deb20233e2dfddf95dd11e9db752bdd2a294d3", size = 1658274 }, + { url = "https://files.pythonhosted.org/packages/cc/6c/21c45b66124df5b4b0ab638271ecd8c6402b702977120cb4d5be6408e15d/aiohttp-3.11.16-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:696ef00e8a1f0cec5e30640e64eca75d8e777933d1438f4facc9c0cdf288a810", size = 1666704 }, + { url = "https://files.pythonhosted.org/packages/1d/e2/7d92adc03e3458edd18a21da2575ab84e58f16b1672ae98529e4eeee45ab/aiohttp-3.11.16-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:e3538bc9fe1b902bef51372462e3d7c96fce2b566642512138a480b7adc9d508", size = 1652815 }, + { url = "https://files.pythonhosted.org/packages/3a/52/7549573cd654ad651e3c5786ec3946d8f0ee379023e22deb503ff856b16c/aiohttp-3.11.16-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:3ab3367bb7f61ad18793fea2ef71f2d181c528c87948638366bf1de26e239183", size = 1735669 }, + { url = "https://files.pythonhosted.org/packages/d5/54/dcd24a23c7a5a2922123e07a296a5f79ea87ce605f531be068415c326de6/aiohttp-3.11.16-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:56a3443aca82abda0e07be2e1ecb76a050714faf2be84256dae291182ba59049", size = 1760422 }, + { url = "https://files.pythonhosted.org/packages/a7/53/87327fe982fa310944e1450e97bf7b2a28015263771931372a1dfe682c58/aiohttp-3.11.16-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:61c721764e41af907c9d16b6daa05a458f066015abd35923051be8705108ed17", size = 1694457 }, + { url = "https://files.pythonhosted.org/packages/ce/6d/c5ccf41059267bcf89853d3db9d8d217dacf0a04f4086cb6bf278323011f/aiohttp-3.11.16-cp311-cp311-win32.whl", hash = "sha256:3e061b09f6fa42997cf627307f220315e313ece74907d35776ec4373ed718b86", size = 416817 }, + { url = "https://files.pythonhosted.org/packages/e7/dd/01f6fe028e054ef4f909c9d63e3a2399e77021bb2e1bb51d56ca8b543989/aiohttp-3.11.16-cp311-cp311-win_amd64.whl", hash = "sha256:745f1ed5e2c687baefc3c5e7b4304e91bf3e2f32834d07baaee243e349624b24", size = 442986 }, + { url = "https://files.pythonhosted.org/packages/db/38/100d01cbc60553743baf0fba658cb125f8ad674a8a771f765cdc155a890d/aiohttp-3.11.16-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:911a6e91d08bb2c72938bc17f0a2d97864c531536b7832abee6429d5296e5b27", size = 704881 }, + { url = "https://files.pythonhosted.org/packages/21/ed/b4102bb6245e36591209e29f03fe87e7956e54cb604ee12e20f7eb47f994/aiohttp-3.11.16-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:6ac13b71761e49d5f9e4d05d33683bbafef753e876e8e5a7ef26e937dd766713", size = 464564 }, + { url = "https://files.pythonhosted.org/packages/3b/e1/a9ab6c47b62ecee080eeb33acd5352b40ecad08fb2d0779bcc6739271745/aiohttp-3.11.16-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:fd36c119c5d6551bce374fcb5c19269638f8d09862445f85a5a48596fd59f4bb", size = 456548 }, + { url = "https://files.pythonhosted.org/packages/80/ad/216c6f71bdff2becce6c8776f0aa32cb0fa5d83008d13b49c3208d2e4016/aiohttp-3.11.16-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d489d9778522fbd0f8d6a5c6e48e3514f11be81cb0a5954bdda06f7e1594b321", size = 1691749 }, + { url = "https://files.pythonhosted.org/packages/bd/ea/7df7bcd3f4e734301605f686ffc87993f2d51b7acb6bcc9b980af223f297/aiohttp-3.11.16-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:69a2cbd61788d26f8f1e626e188044834f37f6ae3f937bd9f08b65fc9d7e514e", size = 1736874 }, + { url = "https://files.pythonhosted.org/packages/51/41/c7724b9c87a29b7cfd1202ec6446bae8524a751473d25e2ff438bc9a02bf/aiohttp-3.11.16-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:cd464ba806e27ee24a91362ba3621bfc39dbbb8b79f2e1340201615197370f7c", size = 1786885 }, + { url = "https://files.pythonhosted.org/packages/86/b3/f61f8492fa6569fa87927ad35a40c159408862f7e8e70deaaead349e2fba/aiohttp-3.11.16-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1ce63ae04719513dd2651202352a2beb9f67f55cb8490c40f056cea3c5c355ce", size = 1698059 }, + { url = "https://files.pythonhosted.org/packages/ce/be/7097cf860a9ce8bbb0e8960704e12869e111abcd3fbd245153373079ccec/aiohttp-3.11.16-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:09b00dd520d88eac9d1768439a59ab3d145065c91a8fab97f900d1b5f802895e", size = 1626527 }, + { url = "https://files.pythonhosted.org/packages/1d/1d/aaa841c340e8c143a8d53a1f644c2a2961c58cfa26e7b398d6bf75cf5d23/aiohttp-3.11.16-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:7f6428fee52d2bcf96a8aa7b62095b190ee341ab0e6b1bcf50c615d7966fd45b", size = 1644036 }, + { url = "https://files.pythonhosted.org/packages/2c/88/59d870f76e9345e2b149f158074e78db457985c2b4da713038d9da3020a8/aiohttp-3.11.16-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:13ceac2c5cdcc3f64b9015710221ddf81c900c5febc505dbd8f810e770011540", size = 1685270 }, + { url = "https://files.pythonhosted.org/packages/2b/b1/c6686948d4c79c3745595efc469a9f8a43cab3c7efc0b5991be65d9e8cb8/aiohttp-3.11.16-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:fadbb8f1d4140825069db3fedbbb843290fd5f5bc0a5dbd7eaf81d91bf1b003b", size = 1650852 }, + { url = "https://files.pythonhosted.org/packages/fe/94/3e42a6916fd3441721941e0f1b8438e1ce2a4c49af0e28e0d3c950c9b3c9/aiohttp-3.11.16-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:6a792ce34b999fbe04a7a71a90c74f10c57ae4c51f65461a411faa70e154154e", size = 1704481 }, + { url = "https://files.pythonhosted.org/packages/b1/6d/6ab5854ff59b27075c7a8c610597d2b6c38945f9a1284ee8758bc3720ff6/aiohttp-3.11.16-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:f4065145bf69de124accdd17ea5f4dc770da0a6a6e440c53f6e0a8c27b3e635c", size = 1735370 }, + { url = "https://files.pythonhosted.org/packages/73/2a/08a68eec3c99a6659067d271d7553e4d490a0828d588e1daa3970dc2b771/aiohttp-3.11.16-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:fa73e8c2656a3653ae6c307b3f4e878a21f87859a9afab228280ddccd7369d71", size = 1697619 }, + { url = "https://files.pythonhosted.org/packages/61/d5/fea8dbbfb0cd68fbb56f0ae913270a79422d9a41da442a624febf72d2aaf/aiohttp-3.11.16-cp312-cp312-win32.whl", hash = "sha256:f244b8e541f414664889e2c87cac11a07b918cb4b540c36f7ada7bfa76571ea2", size = 411710 }, + { url = "https://files.pythonhosted.org/packages/33/fb/41cde15fbe51365024550bf77b95a4fc84ef41365705c946da0421f0e1e0/aiohttp-3.11.16-cp312-cp312-win_amd64.whl", hash = "sha256:23a15727fbfccab973343b6d1b7181bfb0b4aa7ae280f36fd2f90f5476805682", size = 438012 }, + { url = "https://files.pythonhosted.org/packages/52/52/7c712b2d9fb4d5e5fd6d12f9ab76e52baddfee71e3c8203ca7a7559d7f51/aiohttp-3.11.16-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:a3814760a1a700f3cfd2f977249f1032301d0a12c92aba74605cfa6ce9f78489", size = 698005 }, + { url = "https://files.pythonhosted.org/packages/51/3e/61057814f7247666d43ac538abcd6335b022869ade2602dab9bf33f607d2/aiohttp-3.11.16-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:9b751a6306f330801665ae69270a8a3993654a85569b3469662efaad6cf5cc50", size = 461106 }, + { url = "https://files.pythonhosted.org/packages/4f/85/6b79fb0ea6e913d596d5b949edc2402b20803f51b1a59e1bbc5bb7ba7569/aiohttp-3.11.16-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:ad497f38a0d6c329cb621774788583ee12321863cd4bd9feee1effd60f2ad133", size = 453394 }, + { url = "https://files.pythonhosted.org/packages/4b/04/e1bb3fcfbd2c26753932c759593a32299aff8625eaa0bf8ff7d9c0c34a36/aiohttp-3.11.16-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ca37057625693d097543bd88076ceebeb248291df9d6ca8481349efc0b05dcd0", size = 1666643 }, + { url = "https://files.pythonhosted.org/packages/0e/27/97bc0fdd1f439b8f060beb3ba8fb47b908dc170280090801158381ad7942/aiohttp-3.11.16-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a5abcbba9f4b463a45c8ca8b7720891200658f6f46894f79517e6cd11f3405ca", size = 1721948 }, + { url = "https://files.pythonhosted.org/packages/2c/4f/bc4c5119e75c05ef15c5670ef1563bbe25d4ed4893b76c57b0184d815e8b/aiohttp-3.11.16-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f420bfe862fb357a6d76f2065447ef6f484bc489292ac91e29bc65d2d7a2c84d", size = 1774454 }, + { url = "https://files.pythonhosted.org/packages/73/5b/54b42b2150bb26fdf795464aa55ceb1a49c85f84e98e6896d211eabc6670/aiohttp-3.11.16-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:58ede86453a6cf2d6ce40ef0ca15481677a66950e73b0a788917916f7e35a0bb", size = 1677785 }, + { url = "https://files.pythonhosted.org/packages/10/ee/a0fe68916d3f82eae199b8535624cf07a9c0a0958c7a76e56dd21140487a/aiohttp-3.11.16-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6fdec0213244c39973674ca2a7f5435bf74369e7d4e104d6c7473c81c9bcc8c4", size = 1608456 }, + { url = "https://files.pythonhosted.org/packages/8b/48/83afd779242b7cf7e1ceed2ff624a86d3221e17798061cf9a79e0b246077/aiohttp-3.11.16-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:72b1b03fb4655c1960403c131740755ec19c5898c82abd3961c364c2afd59fe7", size = 1622424 }, + { url = "https://files.pythonhosted.org/packages/6f/27/452f1d5fca1f516f9f731539b7f5faa9e9d3bf8a3a6c3cd7c4b031f20cbd/aiohttp-3.11.16-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:780df0d837276276226a1ff803f8d0fa5f8996c479aeef52eb040179f3156cbd", size = 1660943 }, + { url = "https://files.pythonhosted.org/packages/d6/e1/5c7d63143b8d00c83b958b9e78e7048c4a69903c760c1e329bf02bac57a1/aiohttp-3.11.16-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:ecdb8173e6c7aa09eee342ac62e193e6904923bd232e76b4157ac0bfa670609f", size = 1622797 }, + { url = "https://files.pythonhosted.org/packages/46/9e/2ac29cca2746ee8e449e73cd2fcb3d454467393ec03a269d50e49af743f1/aiohttp-3.11.16-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:a6db7458ab89c7d80bc1f4e930cc9df6edee2200127cfa6f6e080cf619eddfbd", size = 1687162 }, + { url = "https://files.pythonhosted.org/packages/ad/6b/eaa6768e02edebaf37d77f4ffb74dd55f5cbcbb6a0dbf798ccec7b0ac23b/aiohttp-3.11.16-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:2540ddc83cc724b13d1838026f6a5ad178510953302a49e6d647f6e1de82bc34", size = 1718518 }, + { url = "https://files.pythonhosted.org/packages/e5/18/dda87cbad29472a51fa058d6d8257dfce168289adaeb358b86bd93af3b20/aiohttp-3.11.16-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:3b4e6db8dc4879015b9955778cfb9881897339c8fab7b3676f8433f849425913", size = 1675254 }, + { url = "https://files.pythonhosted.org/packages/32/d9/d2fb08c614df401d92c12fcbc60e6e879608d5e8909ef75c5ad8d4ad8aa7/aiohttp-3.11.16-cp313-cp313-win32.whl", hash = "sha256:493910ceb2764f792db4dc6e8e4b375dae1b08f72e18e8f10f18b34ca17d0979", size = 410698 }, + { url = "https://files.pythonhosted.org/packages/ce/ed/853e36d5a33c24544cfa46585895547de152dfef0b5c79fa675f6e4b7b87/aiohttp-3.11.16-cp313-cp313-win_amd64.whl", hash = "sha256:42864e70a248f5f6a49fdaf417d9bc62d6e4d8ee9695b24c5916cb4bb666c802", size = 436395 }, + { url = "https://files.pythonhosted.org/packages/4b/6e/a423a6fd07e651f6078da862128031cff2f333e995f5efe30bb110c97041/aiohttp-3.11.16-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:bbcba75fe879ad6fd2e0d6a8d937f34a571f116a0e4db37df8079e738ea95c71", size = 709172 }, + { url = "https://files.pythonhosted.org/packages/bf/8d/925f3c893523118e5dc729d340df2283d68e7adfa77192908ae63f1ec904/aiohttp-3.11.16-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:87a6e922b2b2401e0b0cf6b976b97f11ec7f136bfed445e16384fbf6fd5e8602", size = 469390 }, + { url = "https://files.pythonhosted.org/packages/49/57/8a27b793480887bd23288364138c9db2f58cd3cff28945809aa062d019dc/aiohttp-3.11.16-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:ccf10f16ab498d20e28bc2b5c1306e9c1512f2840f7b6a67000a517a4b37d5ee", size = 456246 }, + { url = "https://files.pythonhosted.org/packages/e8/e5/e8114c5b1336357089cacf5a4ff298335429f0a0e75dea3ffefd3d4d82e5/aiohttp-3.11.16-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fb3d0cc5cdb926090748ea60172fa8a213cec728bd6c54eae18b96040fcd6227", size = 1590764 }, + { url = "https://files.pythonhosted.org/packages/db/49/ec13c0ad70c4843169111265c47dd568437be354aea4ac732dc6f2e79842/aiohttp-3.11.16-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d07502cc14ecd64f52b2a74ebbc106893d9a9717120057ea9ea1fd6568a747e7", size = 1638375 }, + { url = "https://files.pythonhosted.org/packages/0f/0d/78a64579b054fa3c0e72083912d4410f5514dc0cd03bef5644d4f1e4e6ed/aiohttp-3.11.16-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:776c8e959a01e5e8321f1dec77964cb6101020a69d5a94cd3d34db6d555e01f7", size = 1672027 }, + { url = "https://files.pythonhosted.org/packages/54/11/06602ab3446fe96519998b79c762cf0921b620e702bd7659a5e8b998d0e0/aiohttp-3.11.16-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0902e887b0e1d50424112f200eb9ae3dfed6c0d0a19fc60f633ae5a57c809656", size = 1589609 }, + { url = "https://files.pythonhosted.org/packages/34/1b/6bdebdf702d7f339579e9d3c2e784ca6e5867e247dd7b8690c004431ab57/aiohttp-3.11.16-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e87fd812899aa78252866ae03a048e77bd11b80fb4878ce27c23cade239b42b2", size = 1547540 }, + { url = "https://files.pythonhosted.org/packages/88/dd/5d0c0a936baaabbf7467851c0cc9f1aedab67428479a528ea14ab852c730/aiohttp-3.11.16-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:0a950c2eb8ff17361abd8c85987fd6076d9f47d040ebffce67dce4993285e973", size = 1534880 }, + { url = "https://files.pythonhosted.org/packages/a8/ff/2245148b047833eb7b37f5754ece17ade561a46c40d6fecc3ed3f5eae1c1/aiohttp-3.11.16-cp39-cp39-musllinux_1_2_armv7l.whl", hash = "sha256:c10d85e81d0b9ef87970ecbdbfaeec14a361a7fa947118817fcea8e45335fa46", size = 1557692 }, + { url = "https://files.pythonhosted.org/packages/c4/1c/fe0dd097427c295ae49b6c10e37eda546036fd8de75bc43d69df392b9377/aiohttp-3.11.16-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:7951decace76a9271a1ef181b04aa77d3cc309a02a51d73826039003210bdc86", size = 1538918 }, + { url = "https://files.pythonhosted.org/packages/94/58/10af247fb0084327579ebaccfd1f9c2f759ec972b204b31598debfa0829a/aiohttp-3.11.16-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:14461157d8426bcb40bd94deb0450a6fa16f05129f7da546090cebf8f3123b0f", size = 1609351 }, + { url = "https://files.pythonhosted.org/packages/d3/91/b1f0928b6d2eb0c47ecee7122067a8ad330f812795d8f16343d206394040/aiohttp-3.11.16-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:9756d9b9d4547e091f99d554fbba0d2a920aab98caa82a8fb3d3d9bee3c9ae85", size = 1630514 }, + { url = "https://files.pythonhosted.org/packages/88/51/3319add72ea4053bee66825aef3e691ee4b26d0a22b7f817d73b0af02d38/aiohttp-3.11.16-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:87944bd16b7fe6160607f6a17808abd25f17f61ae1e26c47a491b970fb66d8cb", size = 1567084 }, + { url = "https://files.pythonhosted.org/packages/e5/93/e90a84c263f02f01efd6f32042c08d7f7d88338cb18d91c5b1752accffeb/aiohttp-3.11.16-cp39-cp39-win32.whl", hash = "sha256:92b7ee222e2b903e0a4b329a9943d432b3767f2d5029dbe4ca59fb75223bbe2e", size = 417187 }, + { url = "https://files.pythonhosted.org/packages/11/b8/7200f637f223199d8f3e7add720ab19843b9969ffa89b758b5649cab8099/aiohttp-3.11.16-cp39-cp39-win_amd64.whl", hash = "sha256:17ae4664031aadfbcb34fd40ffd90976671fa0c0286e6c4113989f78bebab37a", size = 442378 }, +] + +[[package]] +name = "aiosignal" +version = "1.3.2" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "frozenlist" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/ba/b5/6d55e80f6d8a08ce22b982eafa278d823b541c925f11ee774b0b9c43473d/aiosignal-1.3.2.tar.gz", hash = "sha256:a8c255c66fafb1e499c9351d0bf32ff2d8a0321595ebac3b93713656d2436f54", size = 19424 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/ec/6a/bc7e17a3e87a2985d3e8f4da4cd0f481060eb78fb08596c42be62c90a4d9/aiosignal-1.3.2-py2.py3-none-any.whl", hash = "sha256:45cde58e409a301715980c2b01d0c28bdde3770d8290b5eb2173759d9acb31a5", size = 7597 }, +] + [[package]] name = "annotated-types" version = "0.7.0" @@ -38,6 +158,24 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/25/8a/c46dcc25341b5bce5472c718902eb3d38600a903b14fa6aeecef3f21a46f/asttokens-3.0.0-py3-none-any.whl", hash = "sha256:e3078351a059199dd5138cb1c706e6430c05eff2ff136af5eb4790f9d28932e2", size = 26918 }, ] +[[package]] +name = "async-timeout" +version = "5.0.1" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/a5/ae/136395dfbfe00dfc94da3f3e136d0b13f394cba8f4841120e34226265780/async_timeout-5.0.1.tar.gz", hash = "sha256:d9321a7a3d5a6a5e187e824d2fa0793ce379a202935782d555d6e9d2735677d3", size = 9274 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/fe/ba/e2081de779ca30d473f21f5b30e0e737c438205440784c7dfc81efc2b029/async_timeout-5.0.1-py3-none-any.whl", hash = "sha256:39e3809566ff85354557ec2398b55e096c8364bacac9405a7a1fa429e77fe76c", size = 6233 }, +] + +[[package]] +name = "attrs" +version = "25.3.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/5a/b0/1367933a8532ee6ff8d63537de4f1177af4bff9f3e829baf7331f595bb24/attrs-25.3.0.tar.gz", hash = "sha256:75d7cefc7fb576747b2c81b4442d4d4a1ce0900973527c011d1030fd3bf4af1b", size = 812032 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/77/06/bb80f5f86020c4551da315d78b3ab75e8228f89f0162f2c3a819e407941a/attrs-25.3.0-py3-none-any.whl", hash = "sha256:427318ce031701fea540783410126f03899a97ffc6f61596ad581ac2e40e3bc3", size = 63815 }, +] + [[package]] name = "babel" version = "2.17.0" @@ -235,72 +373,72 @@ wheels = [ [[package]] name = "coverage" -version = "7.7.0" -source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/02/36/465f5492443265e1278f9a82ffe6aeed3f1db779da0d6e7d4611a5cfb6af/coverage-7.7.0.tar.gz", hash = "sha256:cd879d4646055a573775a1cec863d00c9ff8c55860f8b17f6d8eee9140c06166", size = 809969 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/10/f5/2b801fe88f199707cf9ec66dcee036e7073b5a208a4a161b64371b3f1e35/coverage-7.7.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:a538a23119d1e2e2ce077e902d02ea3d8e0641786ef6e0faf11ce82324743944", size = 210608 }, - { url = "https://files.pythonhosted.org/packages/07/44/bcc030cf977d1069a28742c0a67284c6e831ef172f914055b3d45da83f89/coverage-7.7.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:1586ad158523f4133499a4f322b230e2cfef9cc724820dbd58595a5a236186f4", size = 211042 }, - { url = "https://files.pythonhosted.org/packages/2c/3f/b427f17e1bcf3e1f5ac42fc0b6cb623616f2aedcfc7fde17a058afb62568/coverage-7.7.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7b6c96d69928a3a6767fab8dc1ce8a02cf0156836ccb1e820c7f45a423570d98", size = 240168 }, - { url = "https://files.pythonhosted.org/packages/58/92/6e8d71c5e651f152ffc518ec4cd7add87035533e88af29e233635c0f0dfb/coverage-7.7.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7f18d47641282664276977c604b5a261e51fefc2980f5271d547d706b06a837f", size = 238079 }, - { url = "https://files.pythonhosted.org/packages/40/33/1c25ae35c16972dc379c24cd7dde20359d076dee00687825c92a53e43b02/coverage-7.7.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f2a1e18a85bd066c7c556d85277a7adf4651f259b2579113844835ba1a74aafd", size = 239216 }, - { url = "https://files.pythonhosted.org/packages/4d/3d/adf40bdd07a49e1880632c1bc6b31f42d32cf0bfe6b4d294a8f706d70078/coverage-7.7.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:70f0925c4e2bfc965369f417e7cc72538fd1ba91639cf1e4ef4b1a6b50439b3b", size = 239126 }, - { url = "https://files.pythonhosted.org/packages/72/a5/51e39811cd0ec0569a25fe8e6bac0a00efa222a3e49d51d64f5ba0dce24a/coverage-7.7.0-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:b0fac2088ec4aaeb5468b814bd3ff5e5978364bfbce5e567c44c9e2854469f6c", size = 237842 }, - { url = "https://files.pythonhosted.org/packages/ab/b7/c5796906cd9eed6d258138f1fddc8d6af01b6d07b3c183bac4a9731ac383/coverage-7.7.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:b3e212a894d8ae07fde2ca8b43d666a6d49bbbddb10da0f6a74ca7bd31f20054", size = 238136 }, - { url = "https://files.pythonhosted.org/packages/d7/8a/bd34ea3c602b3ef323a001d375f9b1d663e901079bb26b5f9b8f96fae32b/coverage-7.7.0-cp310-cp310-win32.whl", hash = "sha256:f32b165bf6dfea0846a9c9c38b7e1d68f313956d60a15cde5d1709fddcaf3bee", size = 213320 }, - { url = "https://files.pythonhosted.org/packages/94/60/6e7efe849e305a233623a80aaeba7ebb02809fa63ab8a1e49c4323b8083b/coverage-7.7.0-cp310-cp310-win_amd64.whl", hash = "sha256:a2454b12a3f12cc4698f3508912e6225ec63682e2ca5a96f80a2b93cef9e63f3", size = 214219 }, - { url = "https://files.pythonhosted.org/packages/e8/ec/9e0c9358a3bd56b1ddbf266b889ea9d51ee29e58fb72712d5600663fa806/coverage-7.7.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:a0a207c87a9f743c8072d059b4711f8d13c456eb42dac778a7d2e5d4f3c253a7", size = 210722 }, - { url = "https://files.pythonhosted.org/packages/be/bd/7b47a4302423a13960ee30682900d7ca20cee15c978b1d9ea9594d59d352/coverage-7.7.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:2d673e3add00048215c2cc507f1228a7523fd8bf34f279ac98334c9b07bd2656", size = 211154 }, - { url = "https://files.pythonhosted.org/packages/c6/7c/ae54d9022440196bf9f3fad535388678a3db186980ff58a4956ddeb849a2/coverage-7.7.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f81fe93dc1b8e5673f33443c0786c14b77e36f1025973b85e07c70353e46882b", size = 243787 }, - { url = "https://files.pythonhosted.org/packages/2d/21/913a2a2d89a2221f4410fbea4ff84e64ddf4367a4b9eb2c328bd01a1a401/coverage-7.7.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d8c7524779003d59948c51b4fcbf1ca4e27c26a7d75984f63488f3625c328b9b", size = 241473 }, - { url = "https://files.pythonhosted.org/packages/40/f1/5ae36fffd542fb86ab3b2d5e012af0840265f3dd001ad0ffabe9e4dbdcf6/coverage-7.7.0-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4c124025430249118d018dcedc8b7426f39373527c845093132196f2a483b6dd", size = 243259 }, - { url = "https://files.pythonhosted.org/packages/47/1b/abc87bad7f606a4df321bd8300413fe13700099a163e7d63453c7c70c1b2/coverage-7.7.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:e7f559c36d5cdc448ee13e7e56ed7b6b5d44a40a511d584d388a0f5d940977ba", size = 242904 }, - { url = "https://files.pythonhosted.org/packages/e0/b3/ff0cf15f5709996727dda2fa00af6f4da92ea3e16168400346f2f742341a/coverage-7.7.0-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:37cbc7b0d93dfd133e33c7ec01123fbb90401dce174c3b6661d8d36fb1e30608", size = 241079 }, - { url = "https://files.pythonhosted.org/packages/05/c9/fcad82aad05b1eb8040e6c25ae7a1303716cc05718d4dd326e0fab31aa14/coverage-7.7.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:7d2a65876274acf544703e943c010b60bd79404e3623a1e5d52b64a6e2728de5", size = 241617 }, - { url = "https://files.pythonhosted.org/packages/59/9f/d1efe149afa5c3a459c08bf04f7e6917ef4ee8e3440df5c3e87d6b972870/coverage-7.7.0-cp311-cp311-win32.whl", hash = "sha256:f5a2f71d6a91238e7628f23538c26aa464d390cbdedf12ee2a7a0fb92a24482a", size = 213372 }, - { url = "https://files.pythonhosted.org/packages/88/d2/4b58f03e399185b01fb3168d4b870882de9c7a10e273f99c8f25ec690302/coverage-7.7.0-cp311-cp311-win_amd64.whl", hash = "sha256:ae8006772c6b0fa53c33747913473e064985dac4d65f77fd2fdc6474e7cd54e4", size = 214285 }, - { url = "https://files.pythonhosted.org/packages/b7/47/f7b870caa26082ff8033be074ac61dc175a6b0c965adf7b910f92a6d7cfe/coverage-7.7.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:056d3017ed67e7ddf266e6f57378ece543755a4c9231e997789ab3bd11392c94", size = 210907 }, - { url = "https://files.pythonhosted.org/packages/ea/eb/40b39bdc6c1da403257f0fcb2c1b2fd81ff9f66c13abbe3862f42780e1c1/coverage-7.7.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:33c1394d8407e2771547583b66a85d07ed441ff8fae5a4adb4237ad39ece60db", size = 211162 }, - { url = "https://files.pythonhosted.org/packages/53/08/42a2db41b4646d6261122773e222dd7105e2306526f2d7846de6fee808ec/coverage-7.7.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4fbb7a0c3c21908520149d7751cf5b74eb9b38b54d62997b1e9b3ac19a8ee2fe", size = 245223 }, - { url = "https://files.pythonhosted.org/packages/78/2a/0ceb328a7e67e8639d5c7800b8161d4b5f489073ac8d5ac33b11eadee218/coverage-7.7.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:bb356e7ae7c2da13f404bf8f75be90f743c6df8d4607022e759f5d7d89fe83f8", size = 242114 }, - { url = "https://files.pythonhosted.org/packages/ba/68/42b13b849d40af1581830ff06c60f4ec84649764f4a58d5c6e20ae11cbd4/coverage-7.7.0-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bce730d484038e97f27ea2dbe5d392ec5c2261f28c319a3bb266f6b213650135", size = 244371 }, - { url = "https://files.pythonhosted.org/packages/68/66/ab7c3b9fdbeb8bdd322f5b67b1886463834dba2014a534caba60fb0075ea/coverage-7.7.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:aa4dff57fc21a575672176d5ab0ef15a927199e775c5e8a3d75162ab2b0c7705", size = 244134 }, - { url = "https://files.pythonhosted.org/packages/01/74/b833d299a479681957d6b238e16a0725586e1d56ec1e43658f3184550bb0/coverage-7.7.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:b667b91f4f714b17af2a18e220015c941d1cf8b07c17f2160033dbe1e64149f0", size = 242353 }, - { url = "https://files.pythonhosted.org/packages/f9/c5/0ed656d65da39bbab8e8fc367dc3d465a7501fea0f2b1caccfb4f6361c9f/coverage-7.7.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:693d921621a0c8043bfdc61f7d4df5ea6d22165fe8b807cac21eb80dd94e4bbd", size = 243543 }, - { url = "https://files.pythonhosted.org/packages/87/b5/142bcff3828e4cce5d4c9ddc9222de1664464263acca09638e4eb0dbda7c/coverage-7.7.0-cp312-cp312-win32.whl", hash = "sha256:52fc89602cde411a4196c8c6894afb384f2125f34c031774f82a4f2608c59d7d", size = 213543 }, - { url = "https://files.pythonhosted.org/packages/29/74/99d226985def03284bad6a9aff27a1079a8881ec7523b5980b00a5260527/coverage-7.7.0-cp312-cp312-win_amd64.whl", hash = "sha256:0ce8cf59e09d31a4915ff4c3b94c6514af4c84b22c4cc8ad7c3c546a86150a92", size = 214344 }, - { url = "https://files.pythonhosted.org/packages/45/2f/df6235ec963b9eb6b6b2f3c24f70448f1ffa13b9a481c155a6caff176395/coverage-7.7.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:4545485fef7a8a2d8f30e6f79ce719eb154aab7e44217eb444c1d38239af2072", size = 210934 }, - { url = "https://files.pythonhosted.org/packages/f3/85/ff19510bf642e334845318ddb73a550d2b17082831fa9ae053ce72288be7/coverage-7.7.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:1393e5aa9441dafb0162c36c8506c648b89aea9565b31f6bfa351e66c11bcd82", size = 211212 }, - { url = "https://files.pythonhosted.org/packages/2d/6a/af6582a419550d35eacc3e1bf9f4a936dda0ae559632a0bc4e3aef694ac8/coverage-7.7.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:316f29cc3392fa3912493ee4c83afa4a0e2db04ff69600711f8c03997c39baaa", size = 244727 }, - { url = "https://files.pythonhosted.org/packages/55/62/7c49526111c91f3d7d27e111c22c8d08722f5b661c3f031b625b4d7bc4d9/coverage-7.7.0-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e1ffde1d6bc2a92f9c9207d1ad808550873748ac2d4d923c815b866baa343b3f", size = 241768 }, - { url = "https://files.pythonhosted.org/packages/62/4b/2dc27700782be9795cbbbe98394dd19ef74815d78d5027ed894972cd1b4a/coverage-7.7.0-cp313-cp313-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:416e2a8845eaff288f97eaf76ab40367deafb9073ffc47bf2a583f26b05e5265", size = 243790 }, - { url = "https://files.pythonhosted.org/packages/d3/11/9cc1ae56d3015edca69437f3121c2b44de309f6828980b29e4cc9b13246d/coverage-7.7.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:5efdeff5f353ed3352c04e6b318ab05c6ce9249c25ed3c2090c6e9cadda1e3b2", size = 243861 }, - { url = "https://files.pythonhosted.org/packages/db/e4/2398ed93edcf42ff43002d91c37be11514d825cec382606654fd44f4b8fa/coverage-7.7.0-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:57f3bd0d29bf2bd9325c0ff9cc532a175110c4bf8f412c05b2405fd35745266d", size = 241942 }, - { url = "https://files.pythonhosted.org/packages/ec/fe/b6bd35b17a2b8d26bdb21d5ea4351a837ec01edf552655e833629af05b90/coverage-7.7.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:3ab7090f04b12dc6469882ce81244572779d3a4b67eea1c96fb9ecc8c607ef39", size = 243228 }, - { url = "https://files.pythonhosted.org/packages/6d/06/d8701bae1e5d865edeb00a6c2a71bd7659ca6af349789271c6fd16a57909/coverage-7.7.0-cp313-cp313-win32.whl", hash = "sha256:180e3fc68ee4dc5af8b33b6ca4e3bb8aa1abe25eedcb958ba5cff7123071af68", size = 213572 }, - { url = "https://files.pythonhosted.org/packages/d7/c1/7e67780bfcaed6bed20100c9e1b2645e3414577b4bdad169578325249045/coverage-7.7.0-cp313-cp313-win_amd64.whl", hash = "sha256:55143aa13c49491f5606f05b49ed88663446dce3a4d3c5d77baa4e36a16d3573", size = 214372 }, - { url = "https://files.pythonhosted.org/packages/ed/25/50b0447442a415ad3da33093c589d9ef945dd6933225f1ce0ac97476397e/coverage-7.7.0-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:cc41374d2f27d81d6558f8a24e5c114580ffefc197fd43eabd7058182f743322", size = 211774 }, - { url = "https://files.pythonhosted.org/packages/13/cc/3daddc707e934d3c0aafaa4a9b217f53fcf4133d4e40cc6ae63aa51243b8/coverage-7.7.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:89078312f06237417adda7c021c33f80f7a6d2db8572a5f6c330d89b080061ce", size = 211995 }, - { url = "https://files.pythonhosted.org/packages/98/99/c92f43355d3d67f6bf8c946a350f2174e18f9ea7c8a1e36c9eb84ab7d20b/coverage-7.7.0-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5b2f144444879363ea8834cd7b6869d79ac796cb8f864b0cfdde50296cd95816", size = 256226 }, - { url = "https://files.pythonhosted.org/packages/25/62/65f0f33c08e0a1632f1e487b9c2d252e8bad6a77a942836043972b0ba6d2/coverage-7.7.0-cp313-cp313t-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:60e6347d1ed882b1159ffea172cb8466ee46c665af4ca397edbf10ff53e9ffaf", size = 251937 }, - { url = "https://files.pythonhosted.org/packages/b2/10/99a9565aaeb159aade178c6509c8324a9c9e825b01f02242a37c2a8869f8/coverage-7.7.0-cp313-cp313t-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cb203c0afffaf1a8f5b9659a013f8f16a1b2cad3a80a8733ceedc968c0cf4c57", size = 254276 }, - { url = "https://files.pythonhosted.org/packages/a7/12/206196edbf0b82250b11bf5c252fe25ebaa2b7c8d66edb0c194e7b3403fe/coverage-7.7.0-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:ad0edaa97cb983d9f2ff48cadddc3e1fb09f24aa558abeb4dc9a0dbacd12cbb4", size = 255366 }, - { url = "https://files.pythonhosted.org/packages/a5/82/a2abb8d4cdd99c6a443ab6682c0eee5797490a2113a45ffaa8b6b31c5dcc/coverage-7.7.0-cp313-cp313t-musllinux_1_2_i686.whl", hash = "sha256:c5f8a5364fc37b2f172c26a038bc7ec4885f429de4a05fc10fdcb53fb5834c5c", size = 253536 }, - { url = "https://files.pythonhosted.org/packages/4d/7d/3747e000e60ad5dd8157bd978f99979967d56cb35c55235980c85305db86/coverage-7.7.0-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:c4e09534037933bf6eb31d804e72c52ec23219b32c1730f9152feabbd7499463", size = 254344 }, - { url = "https://files.pythonhosted.org/packages/45/56/7c33f8a6de1b3b079374d2ae490ccf76fb7c094a23f72d10f071989fc3ef/coverage-7.7.0-cp313-cp313t-win32.whl", hash = "sha256:1b336d06af14f8da5b1f391e8dec03634daf54dfcb4d1c4fb6d04c09d83cef90", size = 214284 }, - { url = "https://files.pythonhosted.org/packages/95/ab/657bfa6171800a67bd1c005402f06d6b78610820ef1364ea4f85b04bbb5b/coverage-7.7.0-cp313-cp313t-win_amd64.whl", hash = "sha256:b54a1ee4c6f1905a436cbaa04b26626d27925a41cbc3a337e2d3ff7038187f07", size = 215445 }, - { url = "https://files.pythonhosted.org/packages/d1/42/0e77be6f2fafe7f3de88ddf9f8d9a0d8e9a75f9517081d261d31439908c7/coverage-7.7.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:1c8fbce80b2b8bf135d105aa8f5b36eae0c57d702a1cc3ebdea2a6f03f6cdde5", size = 210604 }, - { url = "https://files.pythonhosted.org/packages/0e/62/a82adc7818545fca3987367c6b20f239645678438f7da5827a4960bcbe7f/coverage-7.7.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:d9710521f07f526de30ccdead67e6b236fe996d214e1a7fba8b36e2ba2cd8261", size = 211031 }, - { url = "https://files.pythonhosted.org/packages/a6/50/a98b418fcaf531b2829b2a06f47f8c5cbc0dcce4a9aa63c5f30bf47d1a92/coverage-7.7.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7789e700f33f2b133adae582c9f437523cd5db8de845774988a58c360fc88253", size = 239791 }, - { url = "https://files.pythonhosted.org/packages/58/f7/0a8f891fce6f389b1062a520aff130fa6974433efeb549dd19cbdccc76b3/coverage-7.7.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b8c36093aca722db73633cf2359026ed7782a239eb1c6db2abcff876012dc4cf", size = 237718 }, - { url = "https://files.pythonhosted.org/packages/a9/8f/362c91661e6c43ff86b65b15bbb60ad1ad4924e9d1e35a0d5f08eb3337c4/coverage-7.7.0-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c075d167a6ec99b798c1fdf6e391a1d5a2d054caffe9593ba0f97e3df2c04f0e", size = 238820 }, - { url = "https://files.pythonhosted.org/packages/dd/4b/56520dba6f38ad59e96cdeb8c7eafa47781576d2baabdfa10f8c1813b37b/coverage-7.7.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:d013c07061751ae81861cae6ec3a4fe04e84781b11fd4b6b4201590234b25c7b", size = 238595 }, - { url = "https://files.pythonhosted.org/packages/4d/e6/acfae468bd1f9b691b29d42f93bfd7080c05021103f03580934c066a3844/coverage-7.7.0-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:104bf640f408f4e115b85110047c7f27377e1a8b7ba86f7db4fa47aa49dc9a8e", size = 236820 }, - { url = "https://files.pythonhosted.org/packages/22/4f/9b65332326b0c5b7de197a52e766e2bd547beec6948e1d5c4063289e3281/coverage-7.7.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:39abcacd1ed54e2c33c54bdc488b310e8ef6705833f7148b6eb9a547199d375d", size = 237800 }, - { url = "https://files.pythonhosted.org/packages/bb/99/1c2214678731517d91774b75ed5c0f72feefee3270c232c286b314518d7d/coverage-7.7.0-cp39-cp39-win32.whl", hash = "sha256:8e336b56301774ace6be0017ff85c3566c556d938359b61b840796a0202f805c", size = 213341 }, - { url = "https://files.pythonhosted.org/packages/21/30/4d9ae5544f839da30e42e03850d1dfe4ab184d6307ed971e70178760a68d/coverage-7.7.0-cp39-cp39-win_amd64.whl", hash = "sha256:8c938c6ae59be67ac19a7204e079efc94b38222cd7d0269f96e45e18cddeaa59", size = 214227 }, - { url = "https://files.pythonhosted.org/packages/cb/69/6a5eac32d2e8721274ef75df1b9fd6a8f7e8231e41ff7bc5501f19835f25/coverage-7.7.0-pp39.pp310.pp311-none-any.whl", hash = "sha256:3b0e6e54591ae0d7427def8a4d40fca99df6b899d10354bab73cd5609807261c", size = 202813 }, - { url = "https://files.pythonhosted.org/packages/2a/ac/60f409a448e5b0e9b8539716f683568aa5848c1be903cdbbc805a552cdf8/coverage-7.7.0-py3-none-any.whl", hash = "sha256:708f0a1105ef2b11c79ed54ed31f17e6325ac936501fc373f24be3e6a578146a", size = 202803 }, +version = "7.8.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/19/4f/2251e65033ed2ce1e68f00f91a0294e0f80c80ae8c3ebbe2f12828c4cd53/coverage-7.8.0.tar.gz", hash = "sha256:7a3d62b3b03b4b6fd41a085f3574874cf946cb4604d2b4d3e8dca8cd570ca501", size = 811872 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/78/01/1c5e6ee4ebaaa5e079db933a9a45f61172048c7efa06648445821a201084/coverage-7.8.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:2931f66991175369859b5fd58529cd4b73582461877ecfd859b6549869287ffe", size = 211379 }, + { url = "https://files.pythonhosted.org/packages/e9/16/a463389f5ff916963471f7c13585e5f38c6814607306b3cb4d6b4cf13384/coverage-7.8.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:52a523153c568d2c0ef8826f6cc23031dc86cffb8c6aeab92c4ff776e7951b28", size = 211814 }, + { url = "https://files.pythonhosted.org/packages/b8/b1/77062b0393f54d79064dfb72d2da402657d7c569cfbc724d56ac0f9c67ed/coverage-7.8.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5c8a5c139aae4c35cbd7cadca1df02ea8cf28a911534fc1b0456acb0b14234f3", size = 240937 }, + { url = "https://files.pythonhosted.org/packages/d7/54/c7b00a23150083c124e908c352db03bcd33375494a4beb0c6d79b35448b9/coverage-7.8.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5a26c0c795c3e0b63ec7da6efded5f0bc856d7c0b24b2ac84b4d1d7bc578d676", size = 238849 }, + { url = "https://files.pythonhosted.org/packages/f7/ec/a6b7cfebd34e7b49f844788fda94713035372b5200c23088e3bbafb30970/coverage-7.8.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:821f7bcbaa84318287115d54becb1915eece6918136c6f91045bb84e2f88739d", size = 239986 }, + { url = "https://files.pythonhosted.org/packages/21/8c/c965ecef8af54e6d9b11bfbba85d4f6a319399f5f724798498387f3209eb/coverage-7.8.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:a321c61477ff8ee705b8a5fed370b5710c56b3a52d17b983d9215861e37b642a", size = 239896 }, + { url = "https://files.pythonhosted.org/packages/40/83/070550273fb4c480efa8381735969cb403fa8fd1626d74865bfaf9e4d903/coverage-7.8.0-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:ed2144b8a78f9d94d9515963ed273d620e07846acd5d4b0a642d4849e8d91a0c", size = 238613 }, + { url = "https://files.pythonhosted.org/packages/07/76/fbb2540495b01d996d38e9f8897b861afed356be01160ab4e25471f4fed1/coverage-7.8.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:042e7841a26498fff7a37d6fda770d17519982f5b7d8bf5278d140b67b61095f", size = 238909 }, + { url = "https://files.pythonhosted.org/packages/a3/7e/76d604db640b7d4a86e5dd730b73e96e12a8185f22b5d0799025121f4dcb/coverage-7.8.0-cp310-cp310-win32.whl", hash = "sha256:f9983d01d7705b2d1f7a95e10bbe4091fabc03a46881a256c2787637b087003f", size = 213948 }, + { url = "https://files.pythonhosted.org/packages/5c/a7/f8ce4aafb4a12ab475b56c76a71a40f427740cf496c14e943ade72e25023/coverage-7.8.0-cp310-cp310-win_amd64.whl", hash = "sha256:5a570cd9bd20b85d1a0d7b009aaf6c110b52b5755c17be6962f8ccd65d1dbd23", size = 214844 }, + { url = "https://files.pythonhosted.org/packages/2b/77/074d201adb8383addae5784cb8e2dac60bb62bfdf28b2b10f3a3af2fda47/coverage-7.8.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:e7ac22a0bb2c7c49f441f7a6d46c9c80d96e56f5a8bc6972529ed43c8b694e27", size = 211493 }, + { url = "https://files.pythonhosted.org/packages/a9/89/7a8efe585750fe59b48d09f871f0e0c028a7b10722b2172dfe021fa2fdd4/coverage-7.8.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:bf13d564d310c156d1c8e53877baf2993fb3073b2fc9f69790ca6a732eb4bfea", size = 211921 }, + { url = "https://files.pythonhosted.org/packages/e9/ef/96a90c31d08a3f40c49dbe897df4f1fd51fb6583821a1a1c5ee30cc8f680/coverage-7.8.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a5761c70c017c1b0d21b0815a920ffb94a670c8d5d409d9b38857874c21f70d7", size = 244556 }, + { url = "https://files.pythonhosted.org/packages/89/97/dcd5c2ce72cee9d7b0ee8c89162c24972fb987a111b92d1a3d1d19100c61/coverage-7.8.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e5ff52d790c7e1628241ffbcaeb33e07d14b007b6eb00a19320c7b8a7024c040", size = 242245 }, + { url = "https://files.pythonhosted.org/packages/b2/7b/b63cbb44096141ed435843bbb251558c8e05cc835c8da31ca6ffb26d44c0/coverage-7.8.0-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d39fc4817fd67b3915256af5dda75fd4ee10621a3d484524487e33416c6f3543", size = 244032 }, + { url = "https://files.pythonhosted.org/packages/97/e3/7fa8c2c00a1ef530c2a42fa5df25a6971391f92739d83d67a4ee6dcf7a02/coverage-7.8.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:b44674870709017e4b4036e3d0d6c17f06a0e6d4436422e0ad29b882c40697d2", size = 243679 }, + { url = "https://files.pythonhosted.org/packages/4f/b3/e0a59d8df9150c8a0c0841d55d6568f0a9195692136c44f3d21f1842c8f6/coverage-7.8.0-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:8f99eb72bf27cbb167b636eb1726f590c00e1ad375002230607a844d9e9a2318", size = 241852 }, + { url = "https://files.pythonhosted.org/packages/9b/82/db347ccd57bcef150c173df2ade97976a8367a3be7160e303e43dd0c795f/coverage-7.8.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:b571bf5341ba8c6bc02e0baeaf3b061ab993bf372d982ae509807e7f112554e9", size = 242389 }, + { url = "https://files.pythonhosted.org/packages/21/f6/3f7d7879ceb03923195d9ff294456241ed05815281f5254bc16ef71d6a20/coverage-7.8.0-cp311-cp311-win32.whl", hash = "sha256:e75a2ad7b647fd8046d58c3132d7eaf31b12d8a53c0e4b21fa9c4d23d6ee6d3c", size = 213997 }, + { url = "https://files.pythonhosted.org/packages/28/87/021189643e18ecf045dbe1e2071b2747901f229df302de01c998eeadf146/coverage-7.8.0-cp311-cp311-win_amd64.whl", hash = "sha256:3043ba1c88b2139126fc72cb48574b90e2e0546d4c78b5299317f61b7f718b78", size = 214911 }, + { url = "https://files.pythonhosted.org/packages/aa/12/4792669473297f7973518bec373a955e267deb4339286f882439b8535b39/coverage-7.8.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:bbb5cc845a0292e0c520656d19d7ce40e18d0e19b22cb3e0409135a575bf79fc", size = 211684 }, + { url = "https://files.pythonhosted.org/packages/be/e1/2a4ec273894000ebedd789e8f2fc3813fcaf486074f87fd1c5b2cb1c0a2b/coverage-7.8.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:4dfd9a93db9e78666d178d4f08a5408aa3f2474ad4d0e0378ed5f2ef71640cb6", size = 211935 }, + { url = "https://files.pythonhosted.org/packages/f8/3a/7b14f6e4372786709a361729164125f6b7caf4024ce02e596c4a69bccb89/coverage-7.8.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f017a61399f13aa6d1039f75cd467be388d157cd81f1a119b9d9a68ba6f2830d", size = 245994 }, + { url = "https://files.pythonhosted.org/packages/54/80/039cc7f1f81dcbd01ea796d36d3797e60c106077e31fd1f526b85337d6a1/coverage-7.8.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0915742f4c82208ebf47a2b154a5334155ed9ef9fe6190674b8a46c2fb89cb05", size = 242885 }, + { url = "https://files.pythonhosted.org/packages/10/e0/dc8355f992b6cc2f9dcd5ef6242b62a3f73264893bc09fbb08bfcab18eb4/coverage-7.8.0-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8a40fcf208e021eb14b0fac6bdb045c0e0cab53105f93ba0d03fd934c956143a", size = 245142 }, + { url = "https://files.pythonhosted.org/packages/43/1b/33e313b22cf50f652becb94c6e7dae25d8f02e52e44db37a82de9ac357e8/coverage-7.8.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:a1f406a8e0995d654b2ad87c62caf6befa767885301f3b8f6f73e6f3c31ec3a6", size = 244906 }, + { url = "https://files.pythonhosted.org/packages/05/08/c0a8048e942e7f918764ccc99503e2bccffba1c42568693ce6955860365e/coverage-7.8.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:77af0f6447a582fdc7de5e06fa3757a3ef87769fbb0fdbdeba78c23049140a47", size = 243124 }, + { url = "https://files.pythonhosted.org/packages/5b/62/ea625b30623083c2aad645c9a6288ad9fc83d570f9adb913a2abdba562dd/coverage-7.8.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:f2d32f95922927186c6dbc8bc60df0d186b6edb828d299ab10898ef3f40052fe", size = 244317 }, + { url = "https://files.pythonhosted.org/packages/62/cb/3871f13ee1130a6c8f020e2f71d9ed269e1e2124aa3374d2180ee451cee9/coverage-7.8.0-cp312-cp312-win32.whl", hash = "sha256:769773614e676f9d8e8a0980dd7740f09a6ea386d0f383db6821df07d0f08545", size = 214170 }, + { url = "https://files.pythonhosted.org/packages/88/26/69fe1193ab0bfa1eb7a7c0149a066123611baba029ebb448500abd8143f9/coverage-7.8.0-cp312-cp312-win_amd64.whl", hash = "sha256:e5d2b9be5b0693cf21eb4ce0ec8d211efb43966f6657807f6859aab3814f946b", size = 214969 }, + { url = "https://files.pythonhosted.org/packages/f3/21/87e9b97b568e223f3438d93072479c2f36cc9b3f6b9f7094b9d50232acc0/coverage-7.8.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:5ac46d0c2dd5820ce93943a501ac5f6548ea81594777ca585bf002aa8854cacd", size = 211708 }, + { url = "https://files.pythonhosted.org/packages/75/be/882d08b28a0d19c9c4c2e8a1c6ebe1f79c9c839eb46d4fca3bd3b34562b9/coverage-7.8.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:771eb7587a0563ca5bb6f622b9ed7f9d07bd08900f7589b4febff05f469bea00", size = 211981 }, + { url = "https://files.pythonhosted.org/packages/7a/1d/ce99612ebd58082fbe3f8c66f6d8d5694976c76a0d474503fa70633ec77f/coverage-7.8.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:42421e04069fb2cbcbca5a696c4050b84a43b05392679d4068acbe65449b5c64", size = 245495 }, + { url = "https://files.pythonhosted.org/packages/dc/8d/6115abe97df98db6b2bd76aae395fcc941d039a7acd25f741312ced9a78f/coverage-7.8.0-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:554fec1199d93ab30adaa751db68acec2b41c5602ac944bb19187cb9a41a8067", size = 242538 }, + { url = "https://files.pythonhosted.org/packages/cb/74/2f8cc196643b15bc096d60e073691dadb3dca48418f08bc78dd6e899383e/coverage-7.8.0-cp313-cp313-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5aaeb00761f985007b38cf463b1d160a14a22c34eb3f6a39d9ad6fc27cb73008", size = 244561 }, + { url = "https://files.pythonhosted.org/packages/22/70/c10c77cd77970ac965734fe3419f2c98665f6e982744a9bfb0e749d298f4/coverage-7.8.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:581a40c7b94921fffd6457ffe532259813fc68eb2bdda60fa8cc343414ce3733", size = 244633 }, + { url = "https://files.pythonhosted.org/packages/38/5a/4f7569d946a07c952688debee18c2bb9ab24f88027e3d71fd25dbc2f9dca/coverage-7.8.0-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:f319bae0321bc838e205bf9e5bc28f0a3165f30c203b610f17ab5552cff90323", size = 242712 }, + { url = "https://files.pythonhosted.org/packages/bb/a1/03a43b33f50475a632a91ea8c127f7e35e53786dbe6781c25f19fd5a65f8/coverage-7.8.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:04bfec25a8ef1c5f41f5e7e5c842f6b615599ca8ba8391ec33a9290d9d2db3a3", size = 244000 }, + { url = "https://files.pythonhosted.org/packages/6a/89/ab6c43b1788a3128e4d1b7b54214548dcad75a621f9d277b14d16a80d8a1/coverage-7.8.0-cp313-cp313-win32.whl", hash = "sha256:dd19608788b50eed889e13a5d71d832edc34fc9dfce606f66e8f9f917eef910d", size = 214195 }, + { url = "https://files.pythonhosted.org/packages/12/12/6bf5f9a8b063d116bac536a7fb594fc35cb04981654cccb4bbfea5dcdfa0/coverage-7.8.0-cp313-cp313-win_amd64.whl", hash = "sha256:a9abbccd778d98e9c7e85038e35e91e67f5b520776781d9a1e2ee9d400869487", size = 214998 }, + { url = "https://files.pythonhosted.org/packages/2a/e6/1e9df74ef7a1c983a9c7443dac8aac37a46f1939ae3499424622e72a6f78/coverage-7.8.0-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:18c5ae6d061ad5b3e7eef4363fb27a0576012a7447af48be6c75b88494c6cf25", size = 212541 }, + { url = "https://files.pythonhosted.org/packages/04/51/c32174edb7ee49744e2e81c4b1414ac9df3dacfcb5b5f273b7f285ad43f6/coverage-7.8.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:95aa6ae391a22bbbce1b77ddac846c98c5473de0372ba5c463480043a07bff42", size = 212767 }, + { url = "https://files.pythonhosted.org/packages/e9/8f/f454cbdb5212f13f29d4a7983db69169f1937e869a5142bce983ded52162/coverage-7.8.0-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e013b07ba1c748dacc2a80e69a46286ff145935f260eb8c72df7185bf048f502", size = 256997 }, + { url = "https://files.pythonhosted.org/packages/e6/74/2bf9e78b321216d6ee90a81e5c22f912fc428442c830c4077b4a071db66f/coverage-7.8.0-cp313-cp313t-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d766a4f0e5aa1ba056ec3496243150698dc0481902e2b8559314368717be82b1", size = 252708 }, + { url = "https://files.pythonhosted.org/packages/92/4d/50d7eb1e9a6062bee6e2f92e78b0998848a972e9afad349b6cdde6fa9e32/coverage-7.8.0-cp313-cp313t-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ad80e6b4a0c3cb6f10f29ae4c60e991f424e6b14219d46f1e7d442b938ee68a4", size = 255046 }, + { url = "https://files.pythonhosted.org/packages/40/9e/71fb4e7402a07c4198ab44fc564d09d7d0ffca46a9fb7b0a7b929e7641bd/coverage-7.8.0-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:b87eb6fc9e1bb8f98892a2458781348fa37e6925f35bb6ceb9d4afd54ba36c73", size = 256139 }, + { url = "https://files.pythonhosted.org/packages/49/1a/78d37f7a42b5beff027e807c2843185961fdae7fe23aad5a4837c93f9d25/coverage-7.8.0-cp313-cp313t-musllinux_1_2_i686.whl", hash = "sha256:d1ba00ae33be84066cfbe7361d4e04dec78445b2b88bdb734d0d1cbab916025a", size = 254307 }, + { url = "https://files.pythonhosted.org/packages/58/e9/8fb8e0ff6bef5e170ee19d59ca694f9001b2ec085dc99b4f65c128bb3f9a/coverage-7.8.0-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:f3c38e4e5ccbdc9198aecc766cedbb134b2d89bf64533973678dfcf07effd883", size = 255116 }, + { url = "https://files.pythonhosted.org/packages/56/b0/d968ecdbe6fe0a863de7169bbe9e8a476868959f3af24981f6a10d2b6924/coverage-7.8.0-cp313-cp313t-win32.whl", hash = "sha256:379fe315e206b14e21db5240f89dc0774bdd3e25c3c58c2c733c99eca96f1ada", size = 214909 }, + { url = "https://files.pythonhosted.org/packages/87/e9/d6b7ef9fecf42dfb418d93544af47c940aa83056c49e6021a564aafbc91f/coverage-7.8.0-cp313-cp313t-win_amd64.whl", hash = "sha256:2e4b6b87bb0c846a9315e3ab4be2d52fac905100565f4b92f02c445c8799e257", size = 216068 }, + { url = "https://files.pythonhosted.org/packages/60/0c/5da94be095239814bf2730a28cffbc48d6df4304e044f80d39e1ae581997/coverage-7.8.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:fa260de59dfb143af06dcf30c2be0b200bed2a73737a8a59248fcb9fa601ef0f", size = 211377 }, + { url = "https://files.pythonhosted.org/packages/d5/cb/b9e93ebf193a0bb89dbcd4f73d7b0e6ecb7c1b6c016671950e25f041835e/coverage-7.8.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:96121edfa4c2dfdda409877ea8608dd01de816a4dc4a0523356067b305e4e17a", size = 211803 }, + { url = "https://files.pythonhosted.org/packages/78/1a/cdbfe9e1bb14d3afcaf6bb6e1b9ba76c72666e329cd06865bbd241efd652/coverage-7.8.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6b8af63b9afa1031c0ef05b217faa598f3069148eeee6bb24b79da9012423b82", size = 240561 }, + { url = "https://files.pythonhosted.org/packages/59/04/57f1223f26ac018d7ce791bfa65b0c29282de3e041c1cd3ed430cfeac5a5/coverage-7.8.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:89b1f4af0d4afe495cd4787a68e00f30f1d15939f550e869de90a86efa7e0814", size = 238488 }, + { url = "https://files.pythonhosted.org/packages/b7/b1/0f25516ae2a35e265868670384feebe64e7857d9cffeeb3887b0197e2ba2/coverage-7.8.0-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:94ec0be97723ae72d63d3aa41961a0b9a6f5a53ff599813c324548d18e3b9e8c", size = 239589 }, + { url = "https://files.pythonhosted.org/packages/e0/a4/99d88baac0d1d5a46ceef2dd687aac08fffa8795e4c3e71b6f6c78e14482/coverage-7.8.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:8a1d96e780bdb2d0cbb297325711701f7c0b6f89199a57f2049e90064c29f6bd", size = 239366 }, + { url = "https://files.pythonhosted.org/packages/ea/9e/1db89e135feb827a868ed15f8fc857160757f9cab140ffee21342c783ceb/coverage-7.8.0-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:f1d8a2a57b47142b10374902777e798784abf400a004b14f1b0b9eaf1e528ba4", size = 237591 }, + { url = "https://files.pythonhosted.org/packages/1b/6d/ac4d6fdfd0e201bc82d1b08adfacb1e34b40d21a22cdd62cfaf3c1828566/coverage-7.8.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:cf60dd2696b457b710dd40bf17ad269d5f5457b96442f7f85722bdb16fa6c899", size = 238572 }, + { url = "https://files.pythonhosted.org/packages/25/5e/917cbe617c230f7f1745b6a13e780a3a1cd1cf328dbcd0fd8d7ec52858cd/coverage-7.8.0-cp39-cp39-win32.whl", hash = "sha256:be945402e03de47ba1872cd5236395e0f4ad635526185a930735f66710e1bd3f", size = 213966 }, + { url = "https://files.pythonhosted.org/packages/bd/93/72b434fe550135869f9ea88dd36068af19afce666db576e059e75177e813/coverage-7.8.0-cp39-cp39-win_amd64.whl", hash = "sha256:90e7fbc6216ecaffa5a880cdc9c77b7418c1dcb166166b78dbc630d07f278cc3", size = 214852 }, + { url = "https://files.pythonhosted.org/packages/c4/f1/1da77bb4c920aa30e82fa9b6ea065da3467977c2e5e032e38e66f1c57ffd/coverage-7.8.0-pp39.pp310.pp311-none-any.whl", hash = "sha256:b8194fb8e50d556d5849753de991d390c5a1edeeba50f68e3a9253fbd8bf8ccd", size = 203443 }, + { url = "https://files.pythonhosted.org/packages/59/f1/4da7717f0063a222db253e7121bd6a56f6fb1ba439dcc36659088793347c/coverage-7.8.0-py3-none-any.whl", hash = "sha256:dbf364b4c5e7bae9250528167dfe40219b62e2d573c854d74be213e1e52069f7", size = 203435 }, ] [[package]] @@ -312,6 +450,15 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/12/b3/231ffd4ab1fc9d679809f356cebee130ac7daa00d6d6f3206dd4fd137e9e/distro-1.9.0-py3-none-any.whl", hash = "sha256:7bffd925d65168f85027d8da9af6bddab658135b840670a223589bc0c8ef02b2", size = 20277 }, ] +[[package]] +name = "eval-type-backport" +version = "0.2.2" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/30/ea/8b0ac4469d4c347c6a385ff09dc3c048c2d021696664e26c7ee6791631b5/eval_type_backport-0.2.2.tar.gz", hash = "sha256:f0576b4cf01ebb5bd358d02314d31846af5e07678387486e2c798af0e7d849c1", size = 9079 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/ce/31/55cd413eaccd39125368be33c46de24a1f639f2e12349b0361b4678f3915/eval_type_backport-0.2.2-py3-none-any.whl", hash = "sha256:cb6ad7c393517f476f96d456d0412ea80f0a8cf96f6892834cd9340149111b0a", size = 5830 }, +] + [[package]] name = "evdev" version = "1.9.1" @@ -336,6 +483,122 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/7b/8f/c4d9bafc34ad7ad5d8dc16dd1347ee0e507a52c3adb6bfa8887e1c6a26ba/executing-2.2.0-py2.py3-none-any.whl", hash = "sha256:11387150cad388d62750327a53d3339fad4888b39a6fe233c3afbb54ecffd3aa", size = 26702 }, ] +[[package]] +name = "fastapi" +version = "0.115.12" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "pydantic" }, + { name = "starlette" }, + { name = "typing-extensions" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/f4/55/ae499352d82338331ca1e28c7f4a63bfd09479b16395dce38cf50a39e2c2/fastapi-0.115.12.tar.gz", hash = "sha256:1e2c2a2646905f9e83d32f04a3f86aff4a286669c6c950ca95b5fd68c2602681", size = 295236 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/50/b3/b51f09c2ba432a576fe63758bddc81f78f0c6309d9e5c10d194313bf021e/fastapi-0.115.12-py3-none-any.whl", hash = "sha256:e94613d6c05e27be7ffebdd6ea5f388112e5e430c8f7d6494a9d1d88d43e814d", size = 95164 }, +] + +[[package]] +name = "filelock" +version = "3.18.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/0a/10/c23352565a6544bdc5353e0b15fc1c563352101f30e24bf500207a54df9a/filelock-3.18.0.tar.gz", hash = "sha256:adbc88eabb99d2fec8c9c1b229b171f18afa655400173ddc653d5d01501fb9f2", size = 18075 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/4d/36/2a115987e2d8c300a974597416d9de88f2444426de9571f4b59b2cca3acc/filelock-3.18.0-py3-none-any.whl", hash = "sha256:c401f4f8377c4464e6db25fff06205fd89bdd83b65eb0488ed1b160f780e21de", size = 16215 }, +] + +[[package]] +name = "frozenlist" +version = "1.5.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/8f/ed/0f4cec13a93c02c47ec32d81d11c0c1efbadf4a471e3f3ce7cad366cbbd3/frozenlist-1.5.0.tar.gz", hash = "sha256:81d5af29e61b9c8348e876d442253723928dce6433e0e76cd925cd83f1b4b817", size = 39930 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/54/79/29d44c4af36b2b240725dce566b20f63f9b36ef267aaaa64ee7466f4f2f8/frozenlist-1.5.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:5b6a66c18b5b9dd261ca98dffcb826a525334b2f29e7caa54e182255c5f6a65a", size = 94451 }, + { url = "https://files.pythonhosted.org/packages/47/47/0c999aeace6ead8a44441b4f4173e2261b18219e4ad1fe9a479871ca02fc/frozenlist-1.5.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d1b3eb7b05ea246510b43a7e53ed1653e55c2121019a97e60cad7efb881a97bb", size = 54301 }, + { url = "https://files.pythonhosted.org/packages/8d/60/107a38c1e54176d12e06e9d4b5d755b677d71d1219217cee063911b1384f/frozenlist-1.5.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:15538c0cbf0e4fa11d1e3a71f823524b0c46299aed6e10ebb4c2089abd8c3bec", size = 52213 }, + { url = "https://files.pythonhosted.org/packages/17/62/594a6829ac5679c25755362a9dc93486a8a45241394564309641425d3ff6/frozenlist-1.5.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e79225373c317ff1e35f210dd5f1344ff31066ba8067c307ab60254cd3a78ad5", size = 240946 }, + { url = "https://files.pythonhosted.org/packages/7e/75/6c8419d8f92c80dd0ee3f63bdde2702ce6398b0ac8410ff459f9b6f2f9cb/frozenlist-1.5.0-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9272fa73ca71266702c4c3e2d4a28553ea03418e591e377a03b8e3659d94fa76", size = 264608 }, + { url = "https://files.pythonhosted.org/packages/88/3e/82a6f0b84bc6fb7e0be240e52863c6d4ab6098cd62e4f5b972cd31e002e8/frozenlist-1.5.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:498524025a5b8ba81695761d78c8dd7382ac0b052f34e66939c42df860b8ff17", size = 261361 }, + { url = "https://files.pythonhosted.org/packages/fd/85/14e5f9ccac1b64ff2f10c927b3ffdf88772aea875882406f9ba0cec8ad84/frozenlist-1.5.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:92b5278ed9d50fe610185ecd23c55d8b307d75ca18e94c0e7de328089ac5dcba", size = 231649 }, + { url = "https://files.pythonhosted.org/packages/ee/59/928322800306f6529d1852323014ee9008551e9bb027cc38d276cbc0b0e7/frozenlist-1.5.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7f3c8c1dacd037df16e85227bac13cca58c30da836c6f936ba1df0c05d046d8d", size = 241853 }, + { url = "https://files.pythonhosted.org/packages/7d/bd/e01fa4f146a6f6c18c5d34cab8abdc4013774a26c4ff851128cd1bd3008e/frozenlist-1.5.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:f2ac49a9bedb996086057b75bf93538240538c6d9b38e57c82d51f75a73409d2", size = 243652 }, + { url = "https://files.pythonhosted.org/packages/a5/bd/e4771fd18a8ec6757033f0fa903e447aecc3fbba54e3630397b61596acf0/frozenlist-1.5.0-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:e66cc454f97053b79c2ab09c17fbe3c825ea6b4de20baf1be28919460dd7877f", size = 241734 }, + { url = "https://files.pythonhosted.org/packages/21/13/c83821fa5544af4f60c5d3a65d054af3213c26b14d3f5f48e43e5fb48556/frozenlist-1.5.0-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:5a3ba5f9a0dfed20337d3e966dc359784c9f96503674c2faf015f7fe8e96798c", size = 260959 }, + { url = "https://files.pythonhosted.org/packages/71/f3/1f91c9a9bf7ed0e8edcf52698d23f3c211d8d00291a53c9f115ceb977ab1/frozenlist-1.5.0-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:6321899477db90bdeb9299ac3627a6a53c7399c8cd58d25da094007402b039ab", size = 262706 }, + { url = "https://files.pythonhosted.org/packages/4c/22/4a256fdf5d9bcb3ae32622c796ee5ff9451b3a13a68cfe3f68e2c95588ce/frozenlist-1.5.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:76e4753701248476e6286f2ef492af900ea67d9706a0155335a40ea21bf3b2f5", size = 250401 }, + { url = "https://files.pythonhosted.org/packages/af/89/c48ebe1f7991bd2be6d5f4ed202d94960c01b3017a03d6954dd5fa9ea1e8/frozenlist-1.5.0-cp310-cp310-win32.whl", hash = "sha256:977701c081c0241d0955c9586ffdd9ce44f7a7795df39b9151cd9a6fd0ce4cfb", size = 45498 }, + { url = "https://files.pythonhosted.org/packages/28/2f/cc27d5f43e023d21fe5c19538e08894db3d7e081cbf582ad5ed366c24446/frozenlist-1.5.0-cp310-cp310-win_amd64.whl", hash = "sha256:189f03b53e64144f90990d29a27ec4f7997d91ed3d01b51fa39d2dbe77540fd4", size = 51622 }, + { url = "https://files.pythonhosted.org/packages/79/43/0bed28bf5eb1c9e4301003b74453b8e7aa85fb293b31dde352aac528dafc/frozenlist-1.5.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:fd74520371c3c4175142d02a976aee0b4cb4a7cc912a60586ffd8d5929979b30", size = 94987 }, + { url = "https://files.pythonhosted.org/packages/bb/bf/b74e38f09a246e8abbe1e90eb65787ed745ccab6eaa58b9c9308e052323d/frozenlist-1.5.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:2f3f7a0fbc219fb4455264cae4d9f01ad41ae6ee8524500f381de64ffaa077d5", size = 54584 }, + { url = "https://files.pythonhosted.org/packages/2c/31/ab01375682f14f7613a1ade30149f684c84f9b8823a4391ed950c8285656/frozenlist-1.5.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:f47c9c9028f55a04ac254346e92977bf0f166c483c74b4232bee19a6697e4778", size = 52499 }, + { url = "https://files.pythonhosted.org/packages/98/a8/d0ac0b9276e1404f58fec3ab6e90a4f76b778a49373ccaf6a563f100dfbc/frozenlist-1.5.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0996c66760924da6e88922756d99b47512a71cfd45215f3570bf1e0b694c206a", size = 276357 }, + { url = "https://files.pythonhosted.org/packages/ad/c9/c7761084fa822f07dac38ac29f841d4587570dd211e2262544aa0b791d21/frozenlist-1.5.0-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a2fe128eb4edeabe11896cb6af88fca5346059f6c8d807e3b910069f39157869", size = 287516 }, + { url = "https://files.pythonhosted.org/packages/a1/ff/cd7479e703c39df7bdab431798cef89dc75010d8aa0ca2514c5b9321db27/frozenlist-1.5.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1a8ea951bbb6cacd492e3948b8da8c502a3f814f5d20935aae74b5df2b19cf3d", size = 283131 }, + { url = "https://files.pythonhosted.org/packages/59/a0/370941beb47d237eca4fbf27e4e91389fd68699e6f4b0ebcc95da463835b/frozenlist-1.5.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:de537c11e4aa01d37db0d403b57bd6f0546e71a82347a97c6a9f0dcc532b3a45", size = 261320 }, + { url = "https://files.pythonhosted.org/packages/b8/5f/c10123e8d64867bc9b4f2f510a32042a306ff5fcd7e2e09e5ae5100ee333/frozenlist-1.5.0-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9c2623347b933fcb9095841f1cc5d4ff0b278addd743e0e966cb3d460278840d", size = 274877 }, + { url = "https://files.pythonhosted.org/packages/fa/79/38c505601ae29d4348f21706c5d89755ceded02a745016ba2f58bd5f1ea6/frozenlist-1.5.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:cee6798eaf8b1416ef6909b06f7dc04b60755206bddc599f52232606e18179d3", size = 269592 }, + { url = "https://files.pythonhosted.org/packages/19/e2/39f3a53191b8204ba9f0bb574b926b73dd2efba2a2b9d2d730517e8f7622/frozenlist-1.5.0-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:f5f9da7f5dbc00a604fe74aa02ae7c98bcede8a3b8b9666f9f86fc13993bc71a", size = 265934 }, + { url = "https://files.pythonhosted.org/packages/d5/c9/3075eb7f7f3a91f1a6b00284af4de0a65a9ae47084930916f5528144c9dd/frozenlist-1.5.0-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:90646abbc7a5d5c7c19461d2e3eeb76eb0b204919e6ece342feb6032c9325ae9", size = 283859 }, + { url = "https://files.pythonhosted.org/packages/05/f5/549f44d314c29408b962fa2b0e69a1a67c59379fb143b92a0a065ffd1f0f/frozenlist-1.5.0-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:bdac3c7d9b705d253b2ce370fde941836a5f8b3c5c2b8fd70940a3ea3af7f4f2", size = 287560 }, + { url = "https://files.pythonhosted.org/packages/9d/f8/cb09b3c24a3eac02c4c07a9558e11e9e244fb02bf62c85ac2106d1eb0c0b/frozenlist-1.5.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:03d33c2ddbc1816237a67f66336616416e2bbb6beb306e5f890f2eb22b959cdf", size = 277150 }, + { url = "https://files.pythonhosted.org/packages/37/48/38c2db3f54d1501e692d6fe058f45b6ad1b358d82cd19436efab80cfc965/frozenlist-1.5.0-cp311-cp311-win32.whl", hash = "sha256:237f6b23ee0f44066219dae14c70ae38a63f0440ce6750f868ee08775073f942", size = 45244 }, + { url = "https://files.pythonhosted.org/packages/ca/8c/2ddffeb8b60a4bce3b196c32fcc30d8830d4615e7b492ec2071da801b8ad/frozenlist-1.5.0-cp311-cp311-win_amd64.whl", hash = "sha256:0cc974cc93d32c42e7b0f6cf242a6bd941c57c61b618e78b6c0a96cb72788c1d", size = 51634 }, + { url = "https://files.pythonhosted.org/packages/79/73/fa6d1a96ab7fd6e6d1c3500700963eab46813847f01ef0ccbaa726181dd5/frozenlist-1.5.0-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:31115ba75889723431aa9a4e77d5f398f5cf976eea3bdf61749731f62d4a4a21", size = 94026 }, + { url = "https://files.pythonhosted.org/packages/ab/04/ea8bf62c8868b8eada363f20ff1b647cf2e93377a7b284d36062d21d81d1/frozenlist-1.5.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:7437601c4d89d070eac8323f121fcf25f88674627505334654fd027b091db09d", size = 54150 }, + { url = "https://files.pythonhosted.org/packages/d0/9a/8e479b482a6f2070b26bda572c5e6889bb3ba48977e81beea35b5ae13ece/frozenlist-1.5.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:7948140d9f8ece1745be806f2bfdf390127cf1a763b925c4a805c603df5e697e", size = 51927 }, + { url = "https://files.pythonhosted.org/packages/e3/12/2aad87deb08a4e7ccfb33600871bbe8f0e08cb6d8224371387f3303654d7/frozenlist-1.5.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:feeb64bc9bcc6b45c6311c9e9b99406660a9c05ca8a5b30d14a78555088b0b3a", size = 282647 }, + { url = "https://files.pythonhosted.org/packages/77/f2/07f06b05d8a427ea0060a9cef6e63405ea9e0d761846b95ef3fb3be57111/frozenlist-1.5.0-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:683173d371daad49cffb8309779e886e59c2f369430ad28fe715f66d08d4ab1a", size = 289052 }, + { url = "https://files.pythonhosted.org/packages/bd/9f/8bf45a2f1cd4aa401acd271b077989c9267ae8463e7c8b1eb0d3f561b65e/frozenlist-1.5.0-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:7d57d8f702221405a9d9b40f9da8ac2e4a1a8b5285aac6100f3393675f0a85ee", size = 291719 }, + { url = "https://files.pythonhosted.org/packages/41/d1/1f20fd05a6c42d3868709b7604c9f15538a29e4f734c694c6bcfc3d3b935/frozenlist-1.5.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:30c72000fbcc35b129cb09956836c7d7abf78ab5416595e4857d1cae8d6251a6", size = 267433 }, + { url = "https://files.pythonhosted.org/packages/af/f2/64b73a9bb86f5a89fb55450e97cd5c1f84a862d4ff90d9fd1a73ab0f64a5/frozenlist-1.5.0-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:000a77d6034fbad9b6bb880f7ec073027908f1b40254b5d6f26210d2dab1240e", size = 283591 }, + { url = "https://files.pythonhosted.org/packages/29/e2/ffbb1fae55a791fd6c2938dd9ea779509c977435ba3940b9f2e8dc9d5316/frozenlist-1.5.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:5d7f5a50342475962eb18b740f3beecc685a15b52c91f7d975257e13e029eca9", size = 273249 }, + { url = "https://files.pythonhosted.org/packages/2e/6e/008136a30798bb63618a114b9321b5971172a5abddff44a100c7edc5ad4f/frozenlist-1.5.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:87f724d055eb4785d9be84e9ebf0f24e392ddfad00b3fe036e43f489fafc9039", size = 271075 }, + { url = "https://files.pythonhosted.org/packages/ae/f0/4e71e54a026b06724cec9b6c54f0b13a4e9e298cc8db0f82ec70e151f5ce/frozenlist-1.5.0-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:6e9080bb2fb195a046e5177f10d9d82b8a204c0736a97a153c2466127de87784", size = 285398 }, + { url = "https://files.pythonhosted.org/packages/4d/36/70ec246851478b1c0b59f11ef8ade9c482ff447c1363c2bd5fad45098b12/frozenlist-1.5.0-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:9b93d7aaa36c966fa42efcaf716e6b3900438632a626fb09c049f6a2f09fc631", size = 294445 }, + { url = "https://files.pythonhosted.org/packages/37/e0/47f87544055b3349b633a03c4d94b405956cf2437f4ab46d0928b74b7526/frozenlist-1.5.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:52ef692a4bc60a6dd57f507429636c2af8b6046db8b31b18dac02cbc8f507f7f", size = 280569 }, + { url = "https://files.pythonhosted.org/packages/f9/7c/490133c160fb6b84ed374c266f42800e33b50c3bbab1652764e6e1fc498a/frozenlist-1.5.0-cp312-cp312-win32.whl", hash = "sha256:29d94c256679247b33a3dc96cce0f93cbc69c23bf75ff715919332fdbb6a32b8", size = 44721 }, + { url = "https://files.pythonhosted.org/packages/b1/56/4e45136ffc6bdbfa68c29ca56ef53783ef4c2fd395f7cbf99a2624aa9aaa/frozenlist-1.5.0-cp312-cp312-win_amd64.whl", hash = "sha256:8969190d709e7c48ea386db202d708eb94bdb29207a1f269bab1196ce0dcca1f", size = 51329 }, + { url = "https://files.pythonhosted.org/packages/da/3b/915f0bca8a7ea04483622e84a9bd90033bab54bdf485479556c74fd5eaf5/frozenlist-1.5.0-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:7a1a048f9215c90973402e26c01d1cff8a209e1f1b53f72b95c13db61b00f953", size = 91538 }, + { url = "https://files.pythonhosted.org/packages/c7/d1/a7c98aad7e44afe5306a2b068434a5830f1470675f0e715abb86eb15f15b/frozenlist-1.5.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:dd47a5181ce5fcb463b5d9e17ecfdb02b678cca31280639255ce9d0e5aa67af0", size = 52849 }, + { url = "https://files.pythonhosted.org/packages/3a/c8/76f23bf9ab15d5f760eb48701909645f686f9c64fbb8982674c241fbef14/frozenlist-1.5.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:1431d60b36d15cda188ea222033eec8e0eab488f39a272461f2e6d9e1a8e63c2", size = 50583 }, + { url = "https://files.pythonhosted.org/packages/1f/22/462a3dd093d11df623179d7754a3b3269de3b42de2808cddef50ee0f4f48/frozenlist-1.5.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6482a5851f5d72767fbd0e507e80737f9c8646ae7fd303def99bfe813f76cf7f", size = 265636 }, + { url = "https://files.pythonhosted.org/packages/80/cf/e075e407fc2ae7328155a1cd7e22f932773c8073c1fc78016607d19cc3e5/frozenlist-1.5.0-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:44c49271a937625619e862baacbd037a7ef86dd1ee215afc298a417ff3270608", size = 270214 }, + { url = "https://files.pythonhosted.org/packages/a1/58/0642d061d5de779f39c50cbb00df49682832923f3d2ebfb0fedf02d05f7f/frozenlist-1.5.0-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:12f78f98c2f1c2429d42e6a485f433722b0061d5c0b0139efa64f396efb5886b", size = 273905 }, + { url = "https://files.pythonhosted.org/packages/ab/66/3fe0f5f8f2add5b4ab7aa4e199f767fd3b55da26e3ca4ce2cc36698e50c4/frozenlist-1.5.0-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ce3aa154c452d2467487765e3adc730a8c153af77ad84096bc19ce19a2400840", size = 250542 }, + { url = "https://files.pythonhosted.org/packages/f6/b8/260791bde9198c87a465224e0e2bb62c4e716f5d198fc3a1dacc4895dbd1/frozenlist-1.5.0-cp313-cp313-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9b7dc0c4338e6b8b091e8faf0db3168a37101943e687f373dce00959583f7439", size = 267026 }, + { url = "https://files.pythonhosted.org/packages/2e/a4/3d24f88c527f08f8d44ade24eaee83b2627793fa62fa07cbb7ff7a2f7d42/frozenlist-1.5.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:45e0896250900b5aa25180f9aec243e84e92ac84bd4a74d9ad4138ef3f5c97de", size = 257690 }, + { url = "https://files.pythonhosted.org/packages/de/9a/d311d660420b2beeff3459b6626f2ab4fb236d07afbdac034a4371fe696e/frozenlist-1.5.0-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:561eb1c9579d495fddb6da8959fd2a1fca2c6d060d4113f5844b433fc02f2641", size = 253893 }, + { url = "https://files.pythonhosted.org/packages/c6/23/e491aadc25b56eabd0f18c53bb19f3cdc6de30b2129ee0bc39cd387cd560/frozenlist-1.5.0-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:df6e2f325bfee1f49f81aaac97d2aa757c7646534a06f8f577ce184afe2f0a9e", size = 267006 }, + { url = "https://files.pythonhosted.org/packages/08/c4/ab918ce636a35fb974d13d666dcbe03969592aeca6c3ab3835acff01f79c/frozenlist-1.5.0-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:140228863501b44b809fb39ec56b5d4071f4d0aa6d216c19cbb08b8c5a7eadb9", size = 276157 }, + { url = "https://files.pythonhosted.org/packages/c0/29/3b7a0bbbbe5a34833ba26f686aabfe982924adbdcafdc294a7a129c31688/frozenlist-1.5.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:7707a25d6a77f5d27ea7dc7d1fc608aa0a478193823f88511ef5e6b8a48f9d03", size = 264642 }, + { url = "https://files.pythonhosted.org/packages/ab/42/0595b3dbffc2e82d7fe658c12d5a5bafcd7516c6bf2d1d1feb5387caa9c1/frozenlist-1.5.0-cp313-cp313-win32.whl", hash = "sha256:31a9ac2b38ab9b5a8933b693db4939764ad3f299fcaa931a3e605bc3460e693c", size = 44914 }, + { url = "https://files.pythonhosted.org/packages/17/c4/b7db1206a3fea44bf3b838ca61deb6f74424a8a5db1dd53ecb21da669be6/frozenlist-1.5.0-cp313-cp313-win_amd64.whl", hash = "sha256:11aabdd62b8b9c4b84081a3c246506d1cddd2dd93ff0ad53ede5defec7886b28", size = 51167 }, + { url = "https://files.pythonhosted.org/packages/da/4d/d94ff0fb0f5313902c132817c62d19cdc5bdcd0c195d392006ef4b779fc6/frozenlist-1.5.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:9bbcdfaf4af7ce002694a4e10a0159d5a8d20056a12b05b45cea944a4953f972", size = 95319 }, + { url = "https://files.pythonhosted.org/packages/8c/1b/d90e554ca2b483d31cb2296e393f72c25bdc38d64526579e95576bfda587/frozenlist-1.5.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:1893f948bf6681733aaccf36c5232c231e3b5166d607c5fa77773611df6dc336", size = 54749 }, + { url = "https://files.pythonhosted.org/packages/f8/66/7fdecc9ef49f8db2aa4d9da916e4ecf357d867d87aea292efc11e1b2e932/frozenlist-1.5.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:2b5e23253bb709ef57a8e95e6ae48daa9ac5f265637529e4ce6b003a37b2621f", size = 52718 }, + { url = "https://files.pythonhosted.org/packages/08/04/e2fddc92135276e07addbc1cf413acffa0c2d848b3e54cacf684e146df49/frozenlist-1.5.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0f253985bb515ecd89629db13cb58d702035ecd8cfbca7d7a7e29a0e6d39af5f", size = 241756 }, + { url = "https://files.pythonhosted.org/packages/c6/52/be5ff200815d8a341aee5b16b6b707355e0ca3652953852238eb92b120c2/frozenlist-1.5.0-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:04a5c6babd5e8fb7d3c871dc8b321166b80e41b637c31a995ed844a6139942b6", size = 267718 }, + { url = "https://files.pythonhosted.org/packages/88/be/4bd93a58be57a3722fc544c36debdf9dcc6758f761092e894d78f18b8f20/frozenlist-1.5.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a9fe0f1c29ba24ba6ff6abf688cb0b7cf1efab6b6aa6adc55441773c252f7411", size = 263494 }, + { url = "https://files.pythonhosted.org/packages/32/ba/58348b90193caa096ce9e9befea6ae67f38dabfd3aacb47e46137a6250a8/frozenlist-1.5.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:226d72559fa19babe2ccd920273e767c96a49b9d3d38badd7c91a0fdeda8ea08", size = 232838 }, + { url = "https://files.pythonhosted.org/packages/f6/33/9f152105227630246135188901373c4f322cc026565ca6215b063f4c82f4/frozenlist-1.5.0-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:15b731db116ab3aedec558573c1a5eec78822b32292fe4f2f0345b7f697745c2", size = 242912 }, + { url = "https://files.pythonhosted.org/packages/a0/10/3db38fb3ccbafadd80a1b0d6800c987b0e3fe3ef2d117c6ced0246eea17a/frozenlist-1.5.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:366d8f93e3edfe5a918c874702f78faac300209a4d5bf38352b2c1bdc07a766d", size = 244763 }, + { url = "https://files.pythonhosted.org/packages/e2/cd/1df468fdce2f66a4608dffe44c40cdc35eeaa67ef7fd1d813f99a9a37842/frozenlist-1.5.0-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:1b96af8c582b94d381a1c1f51ffaedeb77c821c690ea5f01da3d70a487dd0a9b", size = 242841 }, + { url = "https://files.pythonhosted.org/packages/ee/5f/16097a5ca0bb6b6779c02cc9379c72fe98d56115d4c54d059fb233168fb6/frozenlist-1.5.0-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:c03eff4a41bd4e38415cbed054bbaff4a075b093e2394b6915dca34a40d1e38b", size = 263407 }, + { url = "https://files.pythonhosted.org/packages/0f/f7/58cd220ee1c2248ee65a32f5b4b93689e3fe1764d85537eee9fc392543bc/frozenlist-1.5.0-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:50cf5e7ee9b98f22bdecbabf3800ae78ddcc26e4a435515fc72d97903e8488e0", size = 265083 }, + { url = "https://files.pythonhosted.org/packages/62/b8/49768980caabf81ac4a2d156008f7cbd0107e6b36d08a313bb31035d9201/frozenlist-1.5.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:1e76bfbc72353269c44e0bc2cfe171900fbf7f722ad74c9a7b638052afe6a00c", size = 251564 }, + { url = "https://files.pythonhosted.org/packages/cb/83/619327da3b86ef957ee7a0cbf3c166a09ed1e87a3f7f1ff487d7d0284683/frozenlist-1.5.0-cp39-cp39-win32.whl", hash = "sha256:666534d15ba8f0fda3f53969117383d5dc021266b3c1a42c9ec4855e4b58b9d3", size = 45691 }, + { url = "https://files.pythonhosted.org/packages/8b/28/407bc34a745151ed2322c690b6e7d83d7101472e81ed76e1ebdac0b70a78/frozenlist-1.5.0-cp39-cp39-win_amd64.whl", hash = "sha256:5c28f4b5dbef8a0d8aad0d4de24d1e9e981728628afaf4ea0792f5d0939372f0", size = 51767 }, + { url = "https://files.pythonhosted.org/packages/c6/c8/a5be5b7550c10858fcf9b0ea054baccab474da77d37f1e828ce043a3a5d4/frozenlist-1.5.0-py3-none-any.whl", hash = "sha256:d994863bba198a4a518b467bb971c56e1db3f180a25c6cf7bb1949c267f748c3", size = 11901 }, +] + +[[package]] +name = "fsspec" +version = "2025.3.2" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/45/d8/8425e6ba5fcec61a1d16e41b1b71d2bf9344f1fe48012c2b48b9620feae5/fsspec-2025.3.2.tar.gz", hash = "sha256:e52c77ef398680bbd6a98c0e628fbc469491282981209907bbc8aea76a04fdc6", size = 299281 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/44/4b/e0cfc1a6f17e990f3e64b7d941ddc4acdc7b19d6edd51abf495f32b1a9e4/fsspec-2025.3.2-py3-none-any.whl", hash = "sha256:2daf8dc3d1dfa65b6aa37748d112773a7a08416f6c70d96b264c96476ecaf711", size = 194435 }, +] + [[package]] name = "ghp-import" version = "2.1.0" @@ -359,75 +622,76 @@ wheels = [ [[package]] name = "greenlet" -version = "3.1.1" -source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/2f/ff/df5fede753cc10f6a5be0931204ea30c35fa2f2ea7a35b25bdaf4fe40e46/greenlet-3.1.1.tar.gz", hash = "sha256:4ce3ac6cdb6adf7946475d7ef31777c26d94bccc377e070a7986bd2d5c515467", size = 186022 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/25/90/5234a78dc0ef6496a6eb97b67a42a8e96742a56f7dc808cb954a85390448/greenlet-3.1.1-cp310-cp310-macosx_11_0_universal2.whl", hash = "sha256:0bbae94a29c9e5c7e4a2b7f0aae5c17e8e90acbfd3bf6270eeba60c39fce3563", size = 271235 }, - { url = "https://files.pythonhosted.org/packages/7c/16/cd631fa0ab7d06ef06387135b7549fdcc77d8d859ed770a0d28e47b20972/greenlet-3.1.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0fde093fb93f35ca72a556cf72c92ea3ebfda3d79fc35bb19fbe685853869a83", size = 637168 }, - { url = "https://files.pythonhosted.org/packages/2f/b1/aed39043a6fec33c284a2c9abd63ce191f4f1a07319340ffc04d2ed3256f/greenlet-3.1.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:36b89d13c49216cadb828db8dfa6ce86bbbc476a82d3a6c397f0efae0525bdd0", size = 648826 }, - { url = "https://files.pythonhosted.org/packages/76/25/40e0112f7f3ebe54e8e8ed91b2b9f970805143efef16d043dfc15e70f44b/greenlet-3.1.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:94b6150a85e1b33b40b1464a3f9988dcc5251d6ed06842abff82e42632fac120", size = 644443 }, - { url = "https://files.pythonhosted.org/packages/fb/2f/3850b867a9af519794784a7eeed1dd5bc68ffbcc5b28cef703711025fd0a/greenlet-3.1.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:93147c513fac16385d1036b7e5b102c7fbbdb163d556b791f0f11eada7ba65dc", size = 643295 }, - { url = "https://files.pythonhosted.org/packages/cf/69/79e4d63b9387b48939096e25115b8af7cd8a90397a304f92436bcb21f5b2/greenlet-3.1.1-cp310-cp310-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:da7a9bff22ce038e19bf62c4dd1ec8391062878710ded0a845bcf47cc0200617", size = 599544 }, - { url = "https://files.pythonhosted.org/packages/46/1d/44dbcb0e6c323bd6f71b8c2f4233766a5faf4b8948873225d34a0b7efa71/greenlet-3.1.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:b2795058c23988728eec1f36a4e5e4ebad22f8320c85f3587b539b9ac84128d7", size = 1125456 }, - { url = "https://files.pythonhosted.org/packages/e0/1d/a305dce121838d0278cee39d5bb268c657f10a5363ae4b726848f833f1bb/greenlet-3.1.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:ed10eac5830befbdd0c32f83e8aa6288361597550ba669b04c48f0f9a2c843c6", size = 1149111 }, - { url = "https://files.pythonhosted.org/packages/96/28/d62835fb33fb5652f2e98d34c44ad1a0feacc8b1d3f1aecab035f51f267d/greenlet-3.1.1-cp310-cp310-win_amd64.whl", hash = "sha256:77c386de38a60d1dfb8e55b8c1101d68c79dfdd25c7095d51fec2dd800892b80", size = 298392 }, - { url = "https://files.pythonhosted.org/packages/28/62/1c2665558618553c42922ed47a4e6d6527e2fa3516a8256c2f431c5d0441/greenlet-3.1.1-cp311-cp311-macosx_11_0_universal2.whl", hash = "sha256:e4d333e558953648ca09d64f13e6d8f0523fa705f51cae3f03b5983489958c70", size = 272479 }, - { url = "https://files.pythonhosted.org/packages/76/9d/421e2d5f07285b6e4e3a676b016ca781f63cfe4a0cd8eaecf3fd6f7a71ae/greenlet-3.1.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:09fc016b73c94e98e29af67ab7b9a879c307c6731a2c9da0db5a7d9b7edd1159", size = 640404 }, - { url = "https://files.pythonhosted.org/packages/e5/de/6e05f5c59262a584e502dd3d261bbdd2c97ab5416cc9c0b91ea38932a901/greenlet-3.1.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d5e975ca70269d66d17dd995dafc06f1b06e8cb1ec1e9ed54c1d1e4a7c4cf26e", size = 652813 }, - { url = "https://files.pythonhosted.org/packages/49/93/d5f93c84241acdea15a8fd329362c2c71c79e1a507c3f142a5d67ea435ae/greenlet-3.1.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3b2813dc3de8c1ee3f924e4d4227999285fd335d1bcc0d2be6dc3f1f6a318ec1", size = 648517 }, - { url = "https://files.pythonhosted.org/packages/15/85/72f77fc02d00470c86a5c982b8daafdf65d38aefbbe441cebff3bf7037fc/greenlet-3.1.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e347b3bfcf985a05e8c0b7d462ba6f15b1ee1c909e2dcad795e49e91b152c383", size = 647831 }, - { url = "https://files.pythonhosted.org/packages/f7/4b/1c9695aa24f808e156c8f4813f685d975ca73c000c2a5056c514c64980f6/greenlet-3.1.1-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:9e8f8c9cb53cdac7ba9793c276acd90168f416b9ce36799b9b885790f8ad6c0a", size = 602413 }, - { url = "https://files.pythonhosted.org/packages/76/70/ad6e5b31ef330f03b12559d19fda2606a522d3849cde46b24f223d6d1619/greenlet-3.1.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:62ee94988d6b4722ce0028644418d93a52429e977d742ca2ccbe1c4f4a792511", size = 1129619 }, - { url = "https://files.pythonhosted.org/packages/f4/fb/201e1b932e584066e0f0658b538e73c459b34d44b4bd4034f682423bc801/greenlet-3.1.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:1776fd7f989fc6b8d8c8cb8da1f6b82c5814957264d1f6cf818d475ec2bf6395", size = 1155198 }, - { url = "https://files.pythonhosted.org/packages/12/da/b9ed5e310bb8b89661b80cbcd4db5a067903bbcd7fc854923f5ebb4144f0/greenlet-3.1.1-cp311-cp311-win_amd64.whl", hash = "sha256:48ca08c771c268a768087b408658e216133aecd835c0ded47ce955381105ba39", size = 298930 }, - { url = "https://files.pythonhosted.org/packages/7d/ec/bad1ac26764d26aa1353216fcbfa4670050f66d445448aafa227f8b16e80/greenlet-3.1.1-cp312-cp312-macosx_11_0_universal2.whl", hash = "sha256:4afe7ea89de619adc868e087b4d2359282058479d7cfb94970adf4b55284574d", size = 274260 }, - { url = "https://files.pythonhosted.org/packages/66/d4/c8c04958870f482459ab5956c2942c4ec35cac7fe245527f1039837c17a9/greenlet-3.1.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f406b22b7c9a9b4f8aa9d2ab13d6ae0ac3e85c9a809bd590ad53fed2bf70dc79", size = 649064 }, - { url = "https://files.pythonhosted.org/packages/51/41/467b12a8c7c1303d20abcca145db2be4e6cd50a951fa30af48b6ec607581/greenlet-3.1.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c3a701fe5a9695b238503ce5bbe8218e03c3bcccf7e204e455e7462d770268aa", size = 663420 }, - { url = "https://files.pythonhosted.org/packages/27/8f/2a93cd9b1e7107d5c7b3b7816eeadcac2ebcaf6d6513df9abaf0334777f6/greenlet-3.1.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2846930c65b47d70b9d178e89c7e1a69c95c1f68ea5aa0a58646b7a96df12441", size = 658035 }, - { url = "https://files.pythonhosted.org/packages/57/5c/7c6f50cb12be092e1dccb2599be5a942c3416dbcfb76efcf54b3f8be4d8d/greenlet-3.1.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:99cfaa2110534e2cf3ba31a7abcac9d328d1d9f1b95beede58294a60348fba36", size = 660105 }, - { url = "https://files.pythonhosted.org/packages/f1/66/033e58a50fd9ec9df00a8671c74f1f3a320564c6415a4ed82a1c651654ba/greenlet-3.1.1-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:1443279c19fca463fc33e65ef2a935a5b09bb90f978beab37729e1c3c6c25fe9", size = 613077 }, - { url = "https://files.pythonhosted.org/packages/19/c5/36384a06f748044d06bdd8776e231fadf92fc896bd12cb1c9f5a1bda9578/greenlet-3.1.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:b7cede291382a78f7bb5f04a529cb18e068dd29e0fb27376074b6d0317bf4dd0", size = 1135975 }, - { url = "https://files.pythonhosted.org/packages/38/f9/c0a0eb61bdf808d23266ecf1d63309f0e1471f284300ce6dac0ae1231881/greenlet-3.1.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:23f20bb60ae298d7d8656c6ec6db134bca379ecefadb0b19ce6f19d1f232a942", size = 1163955 }, - { url = "https://files.pythonhosted.org/packages/43/21/a5d9df1d21514883333fc86584c07c2b49ba7c602e670b174bd73cfc9c7f/greenlet-3.1.1-cp312-cp312-win_amd64.whl", hash = "sha256:7124e16b4c55d417577c2077be379514321916d5790fa287c9ed6f23bd2ffd01", size = 299655 }, - { url = "https://files.pythonhosted.org/packages/f3/57/0db4940cd7bb461365ca8d6fd53e68254c9dbbcc2b452e69d0d41f10a85e/greenlet-3.1.1-cp313-cp313-macosx_11_0_universal2.whl", hash = "sha256:05175c27cb459dcfc05d026c4232f9de8913ed006d42713cb8a5137bd49375f1", size = 272990 }, - { url = "https://files.pythonhosted.org/packages/1c/ec/423d113c9f74e5e402e175b157203e9102feeb7088cee844d735b28ef963/greenlet-3.1.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:935e943ec47c4afab8965954bf49bfa639c05d4ccf9ef6e924188f762145c0ff", size = 649175 }, - { url = "https://files.pythonhosted.org/packages/a9/46/ddbd2db9ff209186b7b7c621d1432e2f21714adc988703dbdd0e65155c77/greenlet-3.1.1-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:667a9706c970cb552ede35aee17339a18e8f2a87a51fba2ed39ceeeb1004798a", size = 663425 }, - { url = "https://files.pythonhosted.org/packages/bc/f9/9c82d6b2b04aa37e38e74f0c429aece5eeb02bab6e3b98e7db89b23d94c6/greenlet-3.1.1-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b8a678974d1f3aa55f6cc34dc480169d58f2e6d8958895d68845fa4ab566509e", size = 657736 }, - { url = "https://files.pythonhosted.org/packages/d9/42/b87bc2a81e3a62c3de2b0d550bf91a86939442b7ff85abb94eec3fc0e6aa/greenlet-3.1.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:efc0f674aa41b92da8c49e0346318c6075d734994c3c4e4430b1c3f853e498e4", size = 660347 }, - { url = "https://files.pythonhosted.org/packages/37/fa/71599c3fd06336cdc3eac52e6871cfebab4d9d70674a9a9e7a482c318e99/greenlet-3.1.1-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:0153404a4bb921f0ff1abeb5ce8a5131da56b953eda6e14b88dc6bbc04d2049e", size = 615583 }, - { url = "https://files.pythonhosted.org/packages/4e/96/e9ef85de031703ee7a4483489b40cf307f93c1824a02e903106f2ea315fe/greenlet-3.1.1-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:275f72decf9932639c1c6dd1013a1bc266438eb32710016a1c742df5da6e60a1", size = 1133039 }, - { url = "https://files.pythonhosted.org/packages/87/76/b2b6362accd69f2d1889db61a18c94bc743e961e3cab344c2effaa4b4a25/greenlet-3.1.1-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:c4aab7f6381f38a4b42f269057aee279ab0fc7bf2e929e3d4abfae97b682a12c", size = 1160716 }, - { url = "https://files.pythonhosted.org/packages/1f/1b/54336d876186920e185066d8c3024ad55f21d7cc3683c856127ddb7b13ce/greenlet-3.1.1-cp313-cp313-win_amd64.whl", hash = "sha256:b42703b1cf69f2aa1df7d1030b9d77d3e584a70755674d60e710f0af570f3761", size = 299490 }, - { url = "https://files.pythonhosted.org/packages/5f/17/bea55bf36990e1638a2af5ba10c1640273ef20f627962cf97107f1e5d637/greenlet-3.1.1-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f1695e76146579f8c06c1509c7ce4dfe0706f49c6831a817ac04eebb2fd02011", size = 643731 }, - { url = "https://files.pythonhosted.org/packages/78/d2/aa3d2157f9ab742a08e0fd8f77d4699f37c22adfbfeb0c610a186b5f75e0/greenlet-3.1.1-cp313-cp313t-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:7876452af029456b3f3549b696bb36a06db7c90747740c5302f74a9e9fa14b13", size = 649304 }, - { url = "https://files.pythonhosted.org/packages/f1/8e/d0aeffe69e53ccff5a28fa86f07ad1d2d2d6537a9506229431a2a02e2f15/greenlet-3.1.1-cp313-cp313t-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:4ead44c85f8ab905852d3de8d86f6f8baf77109f9da589cb4fa142bd3b57b475", size = 646537 }, - { url = "https://files.pythonhosted.org/packages/05/79/e15408220bbb989469c8871062c97c6c9136770657ba779711b90870d867/greenlet-3.1.1-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8320f64b777d00dd7ccdade271eaf0cad6636343293a25074cc5566160e4de7b", size = 642506 }, - { url = "https://files.pythonhosted.org/packages/18/87/470e01a940307796f1d25f8167b551a968540fbe0551c0ebb853cb527dd6/greenlet-3.1.1-cp313-cp313t-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:6510bf84a6b643dabba74d3049ead221257603a253d0a9873f55f6a59a65f822", size = 602753 }, - { url = "https://files.pythonhosted.org/packages/e2/72/576815ba674eddc3c25028238f74d7b8068902b3968cbe456771b166455e/greenlet-3.1.1-cp313-cp313t-musllinux_1_1_aarch64.whl", hash = "sha256:04b013dc07c96f83134b1e99888e7a79979f1a247e2a9f59697fa14b5862ed01", size = 1122731 }, - { url = "https://files.pythonhosted.org/packages/ac/38/08cc303ddddc4b3d7c628c3039a61a3aae36c241ed01393d00c2fd663473/greenlet-3.1.1-cp313-cp313t-musllinux_1_1_x86_64.whl", hash = "sha256:411f015496fec93c1c8cd4e5238da364e1da7a124bcb293f085bf2860c32c6f6", size = 1142112 }, - { url = "https://files.pythonhosted.org/packages/8c/82/8051e82af6d6b5150aacb6789a657a8afd48f0a44d8e91cb72aaaf28553a/greenlet-3.1.1-cp39-cp39-macosx_11_0_universal2.whl", hash = "sha256:396979749bd95f018296af156201d6211240e7a23090f50a8d5d18c370084dc3", size = 270027 }, - { url = "https://files.pythonhosted.org/packages/f9/74/f66de2785880293780eebd18a2958aeea7cbe7814af1ccef634f4701f846/greenlet-3.1.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ca9d0ff5ad43e785350894d97e13633a66e2b50000e8a183a50a88d834752d42", size = 634822 }, - { url = "https://files.pythonhosted.org/packages/68/23/acd9ca6bc412b02b8aa755e47b16aafbe642dde0ad2f929f836e57a7949c/greenlet-3.1.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f6ff3b14f2df4c41660a7dec01045a045653998784bf8cfcb5a525bdffffbc8f", size = 646866 }, - { url = "https://files.pythonhosted.org/packages/a9/ab/562beaf8a53dc9f6b2459f200e7bc226bb07e51862a66351d8b7817e3efd/greenlet-3.1.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:94ebba31df2aa506d7b14866fed00ac141a867e63143fe5bca82a8e503b36437", size = 641985 }, - { url = "https://files.pythonhosted.org/packages/03/d3/1006543621f16689f6dc75f6bcf06e3c23e044c26fe391c16c253623313e/greenlet-3.1.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:73aaad12ac0ff500f62cebed98d8789198ea0e6f233421059fa68a5aa7220145", size = 641268 }, - { url = "https://files.pythonhosted.org/packages/2f/c1/ad71ce1b5f61f900593377b3f77b39408bce5dc96754790311b49869e146/greenlet-3.1.1-cp39-cp39-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:63e4844797b975b9af3a3fb8f7866ff08775f5426925e1e0bbcfe7932059a12c", size = 597376 }, - { url = "https://files.pythonhosted.org/packages/f7/ff/183226685b478544d61d74804445589e069d00deb8ddef042699733950c7/greenlet-3.1.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:7939aa3ca7d2a1593596e7ac6d59391ff30281ef280d8632fa03d81f7c5f955e", size = 1123359 }, - { url = "https://files.pythonhosted.org/packages/c0/8b/9b3b85a89c22f55f315908b94cd75ab5fed5973f7393bbef000ca8b2c5c1/greenlet-3.1.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:d0028e725ee18175c6e422797c407874da24381ce0690d6b9396c204c7f7276e", size = 1147458 }, - { url = "https://files.pythonhosted.org/packages/b8/1c/248fadcecd1790b0ba793ff81fa2375c9ad6442f4c748bf2cc2e6563346a/greenlet-3.1.1-cp39-cp39-win32.whl", hash = "sha256:5e06afd14cbaf9e00899fae69b24a32f2196c19de08fcb9f4779dd4f004e5e7c", size = 281131 }, - { url = "https://files.pythonhosted.org/packages/ae/02/e7d0aef2354a38709b764df50b2b83608f0621493e47f47694eb80922822/greenlet-3.1.1-cp39-cp39-win_amd64.whl", hash = "sha256:3319aa75e0e0639bc15ff54ca327e8dc7a6fe404003496e3c6925cd3142e0e22", size = 298306 }, +version = "3.2.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/b0/9c/666d8c71b18d0189cf801c0e0b31c4bfc609ac823883286045b1f3ae8994/greenlet-3.2.0.tar.gz", hash = "sha256:1d2d43bd711a43db8d9b9187500e6432ddb4fafe112d082ffabca8660a9e01a7", size = 183685 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/96/bd/1d330ca53f844c463cb63cf4ca1ed1798a50b8fd1e1db576cbb473b8c1b3/greenlet-3.2.0-cp310-cp310-macosx_11_0_universal2.whl", hash = "sha256:b7a7b7f2bad3ca72eb2fa14643f1c4ca11d115614047299d89bc24a3b11ddd09", size = 267375 }, + { url = "https://files.pythonhosted.org/packages/a3/a7/7ec4461f7a6a9f8963f2be793a99763e9cd66bc07599011620a75bb3900e/greenlet-3.2.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:60e77242e38e99ecaede853755bbd8165e0b20a2f1f3abcaa6f0dceb826a7411", size = 625728 }, + { url = "https://files.pythonhosted.org/packages/59/8a/70b63c74b3e27df7827777e206395ee190a0cf8f85cd1b3674b7992651f1/greenlet-3.2.0-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d3f32d7c70b1c26844fd0e4e56a1da852b493e4e1c30df7b07274a1e5a9b599e", size = 636992 }, + { url = "https://files.pythonhosted.org/packages/5e/d8/dc3e8157b045423f75e2fb327d4c6f20246b5cc12a09f0c7f28860be5dea/greenlet-3.2.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d97bc1be4bad83b70d8b8627ada6724091af41139616696e59b7088f358583b9", size = 632888 }, + { url = "https://files.pythonhosted.org/packages/2c/fb/6868c1c796ff6f9893d5b312c36c6c9d31c8be98e435210bfe1e5e6f8624/greenlet-3.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:23f56a0103deb5570c8d6a0bb4ddf8a7a28931973ad7ed7a883460a67e599b32", size = 631647 }, + { url = "https://files.pythonhosted.org/packages/56/54/a4bdefd2664382c7652fde5d7c2d8851b88161c65fbeeed15b351e5d9fc6/greenlet-3.2.0-cp310-cp310-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2919b126eeb63ca5fa971501cd20cd6cdb5522369a8e39548bbc73a3e10b8b41", size = 580585 }, + { url = "https://files.pythonhosted.org/packages/e9/20/53a45e165c228b4d490a15918377a6ef16cf4ea9ddf5974d4b49e5c81650/greenlet-3.2.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:844acfd479ee380f3810415e682c9ee941725fb90b45e139bb7fd6f85c6c9a30", size = 1109798 }, + { url = "https://files.pythonhosted.org/packages/95/c4/f9be6264cc19b8ea2c868e1a0b06546de7da2aa296400845cd4abdbb877b/greenlet-3.2.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:2b986f1a6467710e7ffeeeac1777da0318c95bbfcc467acbd0bd35abc775f558", size = 1133421 }, + { url = "https://files.pythonhosted.org/packages/0a/d6/14648d06627db2db62d633d5d6af96866cea7e38b02b8e4992cd33c58e00/greenlet-3.2.0-cp310-cp310-win_amd64.whl", hash = "sha256:29449a2b82ed7ce11f8668c31ef20d31e9d88cd8329eb933098fab5a8608a93a", size = 294968 }, + { url = "https://files.pythonhosted.org/packages/2d/d3/0a25528e54eca3c57524d2ef1f63283c8c6db466c785218036ab7fc2d4ff/greenlet-3.2.0-cp311-cp311-macosx_11_0_universal2.whl", hash = "sha256:b99de16560097b9984409ded0032f101f9555e1ab029440fc6a8b5e76dbba7ac", size = 268620 }, + { url = "https://files.pythonhosted.org/packages/ff/40/f937eb7c1e641ca12089265c57874fcdd173c6c8aabdec3a494641d81eb9/greenlet-3.2.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a0bc5776ac2831c022e029839bf1b9d3052332dcf5f431bb88c8503e27398e31", size = 628787 }, + { url = "https://files.pythonhosted.org/packages/12/8d/f248691502cb85ce8b18d442032dbde5d3dd16ff2d15593cbee33c40f29c/greenlet-3.2.0-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1dcb1108449b55ff6bc0edac9616468f71db261a4571f27c47ccf3530a7f8b97", size = 640838 }, + { url = "https://files.pythonhosted.org/packages/d5/f1/2a572bf4fc667e8835ed8c4ef8b729eccd0666ed9e6db8c61c5796fd2dc9/greenlet-3.2.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:82a68a25a08f51fc8b66b113d1d9863ee123cdb0e8f1439aed9fc795cd6f85cf", size = 636760 }, + { url = "https://files.pythonhosted.org/packages/12/d6/f9ecc8dcb17516a0f4ab91df28497303e8d2d090d509fe3e1b1a85b23e90/greenlet-3.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7fee6f518868e8206c617f4084a83ad4d7a3750b541bf04e692dfa02e52e805d", size = 636001 }, + { url = "https://files.pythonhosted.org/packages/fc/b2/28ab943ff898d6aad3e0ab88fad722c892a43375fabb9789dcc29075da36/greenlet-3.2.0-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:6fad8a9ca98b37951a053d7d2d2553569b151cd8c4ede744806b94d50d7f8f73", size = 583936 }, + { url = "https://files.pythonhosted.org/packages/44/a8/dedd1517fae684c3c08ff53ab8b03e328015da4b52d2bd993279ac3a8c3d/greenlet-3.2.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:0e14541f9024a280adb9645143d6a0a51fda6f7c5695fd96cb4d542bb563442f", size = 1112901 }, + { url = "https://files.pythonhosted.org/packages/45/23/15cf5d4bc864c3dc0dcb708bcaa81cd1a3dc2012326d32ad8a46d77a645e/greenlet-3.2.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:7f163d04f777e7bd229a50b937ecc1ae2a5b25296e6001445e5433e4f51f5191", size = 1138328 }, + { url = "https://files.pythonhosted.org/packages/ba/82/c7cf91e89451a922c049ac1f0123de091260697e26e8b98d299555ad96a5/greenlet-3.2.0-cp311-cp311-win_amd64.whl", hash = "sha256:39801e633a978c3f829f21022501e7b0c3872683d7495c1850558d1a6fb95ed0", size = 295415 }, + { url = "https://files.pythonhosted.org/packages/0e/8d/3c55e88ab01866fb696f68d6c94587a1b7ec8c8a9c56b1383ad05bc14811/greenlet-3.2.0-cp312-cp312-macosx_11_0_universal2.whl", hash = "sha256:7d08b88ee8d506ca1f5b2a58744e934d33c6a1686dd83b81e7999dfc704a912f", size = 270391 }, + { url = "https://files.pythonhosted.org/packages/8b/6f/4a15185a386992ba4fbb55f88c1a189b75c7ce6e145b43ae4e50754d1969/greenlet-3.2.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:58ef3d637c54e2f079064ca936556c4af3989144e4154d80cfd4e2a59fc3769c", size = 637202 }, + { url = "https://files.pythonhosted.org/packages/71/f8/60214debfe3b9670bafac97bfc40e318cbddb4ff4b5cf07df119c4a56dcd/greenlet-3.2.0-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:33ea7e7269d6f7275ce31f593d6dcfedd97539c01f63fbdc8d84e493e20b1b2c", size = 651391 }, + { url = "https://files.pythonhosted.org/packages/a9/44/fb5e067a728a4df73a30863973912ba6eb01f3d910caaf129ef789ca222d/greenlet-3.2.0-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e61d426969b68b2170a9f853cc36d5318030494576e9ec0bfe2dc2e2afa15a68", size = 646118 }, + { url = "https://files.pythonhosted.org/packages/f0/3e/f329b452869d8bc07dbaa112c0175de5e666a7d15eb243781481fb59b863/greenlet-3.2.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:04e781447a4722e30b4861af728cb878d73a3df79509dc19ea498090cea5d204", size = 648079 }, + { url = "https://files.pythonhosted.org/packages/56/e5/813a2e8e842289579391cbd3ae6e6e6a3d2fcad8bdd89bd549a4035ab057/greenlet-3.2.0-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:b2392cc41eeed4055978c6b52549ccd9effd263bb780ffd639c0e1e7e2055ab0", size = 603825 }, + { url = "https://files.pythonhosted.org/packages/4a/11/0bad66138622d0c1463b0b87935cefd397f9f04fac325a838525a3aa4da7/greenlet-3.2.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:430cba962c85e339767235a93450a6aaffed6f9c567e73874ea2075f5aae51e1", size = 1119582 }, + { url = "https://files.pythonhosted.org/packages/17/26/0f8a4d222b9014af88bb8b5d921305308dd44de667c01714817dc9fb91fb/greenlet-3.2.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:5e57ff52315bfc0c5493917f328b8ba3ae0c0515d94524453c4d24e7638cbb53", size = 1147452 }, + { url = "https://files.pythonhosted.org/packages/8a/d4/70d262492338c4939f97dca310c45b002a3af84b265720f0e9b135bc85b2/greenlet-3.2.0-cp312-cp312-win_amd64.whl", hash = "sha256:211a9721f540e454a02e62db7956263e9a28a6cf776d4b9a7213844e36426333", size = 296217 }, + { url = "https://files.pythonhosted.org/packages/c9/43/c0b655d4d7eae19282b028bcec449e5c80626ad0d8d0ca3703f9b1c29258/greenlet-3.2.0-cp313-cp313-macosx_11_0_universal2.whl", hash = "sha256:b86a3ccc865ae601f446af042707b749eebc297928ea7bd0c5f60c56525850be", size = 269131 }, + { url = "https://files.pythonhosted.org/packages/7c/7d/c8f51c373c7f7ac0f73d04a6fd77ab34f6f643cb41a0d186d05ba96708e7/greenlet-3.2.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:144283ad88ed77f3ebd74710dd419b55dd15d18704b0ae05935766a93f5671c5", size = 637323 }, + { url = "https://files.pythonhosted.org/packages/89/65/c3ee41b2e56586737d6e124b250583695628ffa6b324855b3a1267a8d1d9/greenlet-3.2.0-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5be69cd50994b8465c3ad1467f9e63001f76e53a89440ad4440d1b6d52591280", size = 651430 }, + { url = "https://files.pythonhosted.org/packages/f0/07/33bd7a3dcde1db7259371d026ce76be1eb653d2d892334fc79a500b3c5ee/greenlet-3.2.0-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:47aeadd1e8fbdef8fdceb8fb4edc0cbb398a57568d56fd68f2bc00d0d809e6b6", size = 645798 }, + { url = "https://files.pythonhosted.org/packages/35/5b/33c221a6a867030b0b770513a1b78f6c30e04294131dafdc8da78906bbe6/greenlet-3.2.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:18adc14ab154ca6e53eecc9dc50ff17aeb7ba70b7e14779b26e16d71efa90038", size = 648271 }, + { url = "https://files.pythonhosted.org/packages/4d/dd/d6452248fa6093504e3b7525dc2bdc4e55a4296ec6ee74ba241a51d852e2/greenlet-3.2.0-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:e8622b33d8694ec373ad55050c3d4e49818132b44852158442e1931bb02af336", size = 606779 }, + { url = "https://files.pythonhosted.org/packages/9d/24/160f04d2589bcb15b8661dcd1763437b22e01643626899a4139bf98f02af/greenlet-3.2.0-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:e8ac9a2c20fbff3d0b853e9ef705cdedb70d9276af977d1ec1cde86a87a4c821", size = 1117968 }, + { url = "https://files.pythonhosted.org/packages/6c/ff/c6e3f3a5168fef5209cfd9498b2b5dd77a0bf29dfc686a03dcc614cf4432/greenlet-3.2.0-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:cd37273dc7ca1d5da149b58c8b3ce0711181672ba1b09969663905a765affe21", size = 1145510 }, + { url = "https://files.pythonhosted.org/packages/dc/62/5215e374819052e542b5bde06bd7d4a171454b6938c96a2384f21cb94279/greenlet-3.2.0-cp313-cp313-win_amd64.whl", hash = "sha256:8a8940a8d301828acd8b9f3f85db23069a692ff2933358861b19936e29946b95", size = 296004 }, + { url = "https://files.pythonhosted.org/packages/62/6d/dc9c909cba5cbf4b0833fce69912927a8ca74791c23c47b9fd4f28092108/greenlet-3.2.0-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ee59db626760f1ca8da697a086454210d36a19f7abecc9922a2374c04b47735b", size = 629900 }, + { url = "https://files.pythonhosted.org/packages/5e/a9/f3f304fbbbd604858ff3df303d7fa1d8f7f9e45a6ef74481aaf03aaac021/greenlet-3.2.0-cp313-cp313t-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:7154b13ef87a8b62fc05419f12d75532d7783586ad016c57b5de8a1c6feeb517", size = 635270 }, + { url = "https://files.pythonhosted.org/packages/34/92/4b7b4e2e23ecc723cceef9fe3898e78c8e14e106cc7ba2f276a66161da3e/greenlet-3.2.0-cp313-cp313t-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:199453d64b02d0c9d139e36d29681efd0e407ed8e2c0bf89d88878d6a787c28f", size = 632534 }, + { url = "https://files.pythonhosted.org/packages/da/7f/91f0ecbe72c9d789fb7f400b39da9d1e87fcc2cf8746a9636479ba79ab01/greenlet-3.2.0-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0010e928e1901d36625f21d008618273f9dda26b516dbdecf873937d39c9dff0", size = 628826 }, + { url = "https://files.pythonhosted.org/packages/9f/59/e449a44ce52b13751f55376d85adc155dd311608f6d2aa5b6bd2c8d15486/greenlet-3.2.0-cp313-cp313t-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:6005f7a86de836a1dc4b8d824a2339cdd5a1ca7cb1af55ea92575401f9952f4c", size = 593697 }, + { url = "https://files.pythonhosted.org/packages/bb/09/cca3392927c5c990b7a8ede64ccd0712808438d6490d63ce6b8704d6df5f/greenlet-3.2.0-cp313-cp313t-musllinux_1_1_aarch64.whl", hash = "sha256:17fd241c0d50bacb7ce8ff77a30f94a2d0ca69434ba2e0187cf95a5414aeb7e1", size = 1105762 }, + { url = "https://files.pythonhosted.org/packages/4d/b9/3d201f819afc3b7a8cd7ebe645f1a17799603e2d62c968154518f79f4881/greenlet-3.2.0-cp313-cp313t-musllinux_1_1_x86_64.whl", hash = "sha256:7b17a26abc6a1890bf77d5d6b71c0999705386b00060d15c10b8182679ff2790", size = 1125173 }, + { url = "https://files.pythonhosted.org/packages/80/7b/773a30602234597fc2882091f8e1d1a38ea0b4419d99ca7ed82c827e2c3a/greenlet-3.2.0-cp314-cp314-macosx_11_0_universal2.whl", hash = "sha256:397b6bbda06f8fe895893d96218cd6f6d855a6701dc45012ebe12262423cec8b", size = 269908 }, + { url = "https://files.pythonhosted.org/packages/e6/35/06d5fca767ae4660d0f8087bd0552bf7a70e590bad16d0dbd94e1628f4ba/greenlet-3.2.0-cp39-cp39-macosx_11_0_universal2.whl", hash = "sha256:4174fa6fa214e8924cedf332b6f2395ba2b9879f250dacd3c361b2fca86f58af", size = 266169 }, + { url = "https://files.pythonhosted.org/packages/00/0a/009c70774c23dd5c353cff5da84320f3c3e92a4e7ee39cf42e0ae2186030/greenlet-3.2.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6017a4d430fad5229e397ad464db504ae70cb7b903757c4688cee6c25d6ce8d8", size = 623864 }, + { url = "https://files.pythonhosted.org/packages/04/e2/df53870438ec52e9a1a0fe7da97d25292dd11e1626a13496e27c18eced0d/greenlet-3.2.0-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:78b721dfadc60e3639141c0e1f19d23953c5b4b98bfcaf04ce40f79e4f01751c", size = 635665 }, + { url = "https://files.pythonhosted.org/packages/c0/c5/ec035ba7b6c66b475ac12a06d544cae211d65afb6ac3af39215d422bf679/greenlet-3.2.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8fd2583024ff6cd5d4f842d446d001de4c4fe1264fdb5f28ddea28f6488866df", size = 630948 }, + { url = "https://files.pythonhosted.org/packages/c5/06/3d98e958b27c06b23c531761eef75f2efea7c3a446ab1eb57b70bad8528e/greenlet-3.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:598da3bd464c2cc411b723e3d4afc27b13c219ac077ba897bac88443ae45f5ec", size = 630224 }, + { url = "https://files.pythonhosted.org/packages/28/68/bba631f01f3a4df8f45fb4cd3888c54a113829df0612fc380bef20d35664/greenlet-3.2.0-cp39-cp39-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2688b3bd3198cc4bad7a79648a95fee088c24a0f6abd05d3639e6c3040ded015", size = 579090 }, + { url = "https://files.pythonhosted.org/packages/4b/8a/bf0a3c944b446716954a9a6f97f51fdd64ed38864d4fba16835e95be0f06/greenlet-3.2.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:1cf89e2d92bae0d7e2d6093ce0bed26feeaf59a5d588e3984e35fcd46fc41090", size = 1108320 }, + { url = "https://files.pythonhosted.org/packages/1e/fe/4c2daea17f56d41df38af74a7e50fed718a618bfb7e86ac9399560c48d97/greenlet-3.2.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:8b3538711e7c0efd5f7a8fc1096c4db9598d6ed99dc87286b31e4ce9f8a8da67", size = 1132392 }, + { url = "https://files.pythonhosted.org/packages/98/96/c44981a880025a1731ac0c5d83bdb36b1a184c59266c22a4d19041aef19b/greenlet-3.2.0-cp39-cp39-win32.whl", hash = "sha256:ce531d7c424ef327a391de7a9777a6c93a38e1f89e18efa903a1c4ba11f85905", size = 277720 }, + { url = "https://files.pythonhosted.org/packages/7b/9d/7448f8ba7cc29c7113aeb06b70b28be910a3d19a112e5c56885cff7977e5/greenlet-3.2.0-cp39-cp39-win_amd64.whl", hash = "sha256:7b162de2fb61b4c7f4b5d749408bf3280cae65db9b5a6aaf7f922ac829faa67c", size = 294842 }, ] [[package]] name = "griffe" -version = "1.6.2" +version = "1.7.2" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "colorama" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/2f/f2/b00eb72b853ecb5bf31dd47857cdf6767e380ca24ec2910d43b3fa7cc500/griffe-1.6.2.tar.gz", hash = "sha256:3a46fa7bd83280909b63c12b9a975732a927dd97809efe5b7972290b606c5d91", size = 392836 } +sdist = { url = "https://files.pythonhosted.org/packages/59/08/7df7e90e34d08ad890bd71d7ba19451052f88dc3d2c483d228d1331a4736/griffe-1.7.2.tar.gz", hash = "sha256:98d396d803fab3b680c2608f300872fd57019ed82f0672f5b5323a9ad18c540c", size = 394919 } wheels = [ - { url = "https://files.pythonhosted.org/packages/4e/bc/bd8b7de5e748e078b6be648e76b47189a9182b1ac1eb7791ff7969f39f27/griffe-1.6.2-py3-none-any.whl", hash = "sha256:6399f7e663150e4278a312a8e8a14d2f3d7bd86e2ef2f8056a1058e38579c2ee", size = 128638 }, + { url = "https://files.pythonhosted.org/packages/b1/5e/38b408f41064c9fcdbb0ea27c1bd13a1c8657c4846e04dab9f5ea770602c/griffe-1.7.2-py3-none-any.whl", hash = "sha256:1ed9c2e338a75741fc82083fe5a1bc89cb6142efe126194cc313e34ee6af5423", size = 129187 }, ] [[package]] @@ -441,15 +705,15 @@ wheels = [ [[package]] name = "httpcore" -version = "1.0.7" +version = "1.0.8" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "certifi" }, { name = "h11" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/6a/41/d7d0a89eb493922c37d343b607bc1b5da7f5be7e383740b4753ad8943e90/httpcore-1.0.7.tar.gz", hash = "sha256:8551cb62a169ec7162ac7be8d4817d561f60e08eaa485234898414bb5a8a0b4c", size = 85196 } +sdist = { url = "https://files.pythonhosted.org/packages/9f/45/ad3e1b4d448f22c0cff4f5692f5ed0666658578e358b8d58a19846048059/httpcore-1.0.8.tar.gz", hash = "sha256:86e94505ed24ea06514883fd44d2bc02d90e77e7979c8eb71b90f41d364a1bad", size = 85385 } wheels = [ - { url = "https://files.pythonhosted.org/packages/87/f5/72347bc88306acb359581ac4d52f23c0ef445b57157adedb9aee0cd689d2/httpcore-1.0.7-py3-none-any.whl", hash = "sha256:a3fff8f43dc260d5bd363d9f9cf1830fa3a458b332856f34282de498ed420edd", size = 78551 }, + { url = "https://files.pythonhosted.org/packages/18/8d/f052b1e336bb2c1fc7ed1aaed898aa570c0b61a09707b108979d9fc6e308/httpcore-1.0.8-py3-none-any.whl", hash = "sha256:5254cf149bcb5f75e9d1b2b9f729ea4a4b883d1ad7379fc632b727cec23674be", size = 78732 }, ] [[package]] @@ -476,6 +740,24 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/e1/9b/a181f281f65d776426002f330c31849b86b31fc9d848db62e16f03ff739f/httpx_sse-0.4.0-py3-none-any.whl", hash = "sha256:f329af6eae57eaa2bdfd962b42524764af68075ea87370a2de920af5341e318f", size = 7819 }, ] +[[package]] +name = "huggingface-hub" +version = "0.30.2" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "filelock" }, + { name = "fsspec" }, + { name = "packaging" }, + { name = "pyyaml" }, + { name = "requests" }, + { name = "tqdm" }, + { name = "typing-extensions" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/df/22/8eb91736b1dcb83d879bd49050a09df29a57cc5cd9f38e48a4b1c45ee890/huggingface_hub-0.30.2.tar.gz", hash = "sha256:9a7897c5b6fd9dad3168a794a8998d6378210f5b9688d0dfc180b1a228dc2466", size = 400868 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/93/27/1fb384a841e9661faad1c31cbfa62864f59632e876df5d795234da51c395/huggingface_hub-0.30.2-py3-none-any.whl", hash = "sha256:68ff05969927058cfa41df4f2155d4bb48f5f54f719dd0390103eefa9b191e28", size = 481433 }, +] + [[package]] name = "idna" version = "3.10" @@ -490,7 +772,7 @@ name = "importlib-metadata" version = "8.6.1" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "zipp", marker = "python_full_version < '3.10'" }, + { name = "zipp" }, ] sdist = { url = "https://files.pythonhosted.org/packages/33/08/c1395a292bb23fd03bdf572a1357c5a733d3eecbab877641ceacab23db6e/importlib_metadata-8.6.1.tar.gz", hash = "sha256:310b41d755445d74569f993ccfc22838295d9fe005425094fad953d7f15c8580", size = 55767 } wheels = [ @@ -508,17 +790,18 @@ wheels = [ [[package]] name = "inline-snapshot" -version = "0.20.8" +version = "0.22.3" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "asttokens" }, { name = "executing" }, + { name = "pytest" }, { name = "rich" }, { name = "tomli", marker = "python_full_version < '3.11'" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/5a/69/79babd0f6ad54c430fba36fb7677774398225287482cf494a15394c75894/inline_snapshot-0.20.8.tar.gz", hash = "sha256:52373c15b63097215d1136f292962553f325a5e966957b489fe4326d6fbc77c0", size = 92748 } +sdist = { url = "https://files.pythonhosted.org/packages/f9/a9/f5c35bdf19f4a93adc281a89cd6cbc19114db649fee5d509257712c6c5b2/inline_snapshot-0.22.3.tar.gz", hash = "sha256:34c02a8567dafc88bb720872edde792ff5e665c8726f6af3bfc5fa85dd0016be", size = 259515 } wheels = [ - { url = "https://files.pythonhosted.org/packages/76/74/5222a632fd8d3202ddef383b71c8b6c31a9d77989030efba5be561163d41/inline_snapshot-0.20.8-py3-none-any.whl", hash = "sha256:bded4e142b8817930e4df428b88c462308a8f01ad699852e7574a54bad7ea9f2", size = 48157 }, + { url = "https://files.pythonhosted.org/packages/d8/35/dde6c4fcc46ba87cfe8521ac909174d51d46f1c2490673e0077c3bb0091d/inline_snapshot-0.22.3-py3-none-any.whl", hash = "sha256:2e3f076664a61742a615aa769d30f560acf37c640340a93caf0fe410b4ab8495", size = 50291 }, ] [[package]] @@ -604,6 +887,33 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/4b/13/c10f17dcddd1b4c1313418e64ace5e77cc4f7313246140fb09044516a62c/jiter-0.9.0-cp39-cp39-win_amd64.whl", hash = "sha256:e8b36d8a16a61993be33e75126ad3d8aa29cf450b09576f3c427d27647fcb4aa", size = 208879 }, ] +[[package]] +name = "jsonschema" +version = "4.23.0" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "attrs" }, + { name = "jsonschema-specifications" }, + { name = "referencing" }, + { name = "rpds-py" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/38/2e/03362ee4034a4c917f697890ccd4aec0800ccf9ded7f511971c75451deec/jsonschema-4.23.0.tar.gz", hash = "sha256:d71497fef26351a33265337fa77ffeb82423f3ea21283cd9467bb03999266bc4", size = 325778 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/69/4a/4f9dbeb84e8850557c02365a0eee0649abe5eb1d84af92a25731c6c0f922/jsonschema-4.23.0-py3-none-any.whl", hash = "sha256:fbadb6f8b144a8f8cf9f0b89ba94501d143e50411a1278633f56a7acf7fd5566", size = 88462 }, +] + +[[package]] +name = "jsonschema-specifications" +version = "2024.10.1" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "referencing" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/10/db/58f950c996c793472e336ff3655b13fbcf1e3b359dcf52dcf3ed3b52c352/jsonschema_specifications-2024.10.1.tar.gz", hash = "sha256:0f38b83639958ce1152d02a7f062902c41c8fd20d558b0c34344292d417ae272", size = 15561 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/d1/0f/8910b19ac0670a0f80ce1008e5e751c4a57e14d2c4c13a482aa6079fa9d6/jsonschema_specifications-2024.10.1-py3-none-any.whl", hash = "sha256:a09a0680616357d9a0ecf05c12ad234479f549239d0f5b55f3deea67475da9bf", size = 18459 }, +] + [[package]] name = "linkify-it-py" version = "2.0.3" @@ -616,16 +926,35 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/04/1e/b832de447dee8b582cac175871d2f6c3d5077cc56d5575cadba1fd1cccfa/linkify_it_py-2.0.3-py3-none-any.whl", hash = "sha256:6bcbc417b0ac14323382aef5c5192c0075bf8a9d6b41820a2b66371eac6b6d79", size = 19820 }, ] +[[package]] +name = "litellm" +version = "1.67.4.post1" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "aiohttp" }, + { name = "click" }, + { name = "httpx" }, + { name = "importlib-metadata" }, + { name = "jinja2" }, + { name = "jsonschema" }, + { name = "openai" }, + { name = "pydantic" }, + { name = "python-dotenv" }, + { name = "tiktoken" }, + { name = "tokenizers" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/4d/89/bacf75633dd43d6c5536380fb652c4af25046c29f5c6e5fdb4e8fe5af505/litellm-1.67.4.post1.tar.gz", hash = "sha256:057f2505f82d8c3f83d705c375b0d1931de998b13e239a6b06e16ee351fda648", size = 7243930 } + [[package]] name = "markdown" -version = "3.7" +version = "3.8" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "importlib-metadata", marker = "python_full_version < '3.10'" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/54/28/3af612670f82f4c056911fbbbb42760255801b3068c48de792d354ff4472/markdown-3.7.tar.gz", hash = "sha256:2ae2471477cfd02dbbf038d5d9bc226d40def84b4fe2986e49b59b6b472bbed2", size = 357086 } +sdist = { url = "https://files.pythonhosted.org/packages/2f/15/222b423b0b88689c266d9eac4e61396fe2cc53464459d6a37618ac863b24/markdown-3.8.tar.gz", hash = "sha256:7df81e63f0df5c4b24b7d156eb81e4690595239b7d70937d0409f1b0de319c6f", size = 360906 } wheels = [ - { url = "https://files.pythonhosted.org/packages/3f/08/83871f3c50fc983b88547c196d11cf8c3340e37c32d2e9d6152abe2c61f7/Markdown-3.7-py3-none-any.whl", hash = "sha256:7eb6df5690b81a1d7942992c97fad2938e956e79df20cbc6186e9c3a77b1c803", size = 106349 }, + { url = "https://files.pythonhosted.org/packages/51/3f/afe76f8e2246ffbc867440cbcf90525264df0e658f8a5ca1f872b3f6192a/markdown-3.8-py3-none-any.whl", hash = "sha256:794a929b79c5af141ef5ab0f2f642d0f7b1872981250230e72682346f7cc90dc", size = 106210 }, ] [[package]] @@ -718,7 +1047,7 @@ wheels = [ [[package]] name = "mcp" -version = "1.5.0" +version = "1.8.1" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "anyio", marker = "python_full_version >= '3.10'" }, @@ -726,13 +1055,14 @@ dependencies = [ { name = "httpx-sse", marker = "python_full_version >= '3.10'" }, { name = "pydantic", marker = "python_full_version >= '3.10'" }, { name = "pydantic-settings", marker = "python_full_version >= '3.10'" }, + { name = "python-multipart", marker = "python_full_version >= '3.10'" }, { name = "sse-starlette", marker = "python_full_version >= '3.10'" }, { name = "starlette", marker = "python_full_version >= '3.10'" }, - { name = "uvicorn", marker = "python_full_version >= '3.10'" }, + { name = "uvicorn", marker = "python_full_version >= '3.10' and sys_platform != 'emscripten'" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/6d/c9/c55764824e893fdebe777ac7223200986a275c3191dba9169f8eb6d7c978/mcp-1.5.0.tar.gz", hash = "sha256:5b2766c05e68e01a2034875e250139839498c61792163a7b221fc170c12f5aa9", size = 159128 } +sdist = { url = "https://files.pythonhosted.org/packages/7c/13/16b712e8a3be6a736b411df2fc6b4e75eb1d3e99b1cd57a3a1decf17f612/mcp-1.8.1.tar.gz", hash = "sha256:ec0646271d93749f784d2316fb5fe6102fb0d1be788ec70a9e2517e8f2722c0e", size = 265605 } wheels = [ - { url = "https://files.pythonhosted.org/packages/c1/d1/3ff566ecf322077d861f1a68a1ff025cad337417bd66ad22a7c6f7dfcfaf/mcp-1.5.0-py3-none-any.whl", hash = "sha256:51c3f35ce93cb702f7513c12406bbea9665ef75a08db909200b07da9db641527", size = 73734 }, + { url = "https://files.pythonhosted.org/packages/1c/5d/91cf0d40e40ae9ecf8d4004e0f9611eea86085aa0b5505493e0ff53972da/mcp-1.8.1-py3-none-any.whl", hash = "sha256:948e03783859fa35abe05b9b6c0a1d5519be452fc079dc8d7f682549591c1770", size = 119761 }, ] [[package]] @@ -821,7 +1151,7 @@ wheels = [ [[package]] name = "mkdocs-material" -version = "9.6.9" +version = "9.6.11" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "babel" }, @@ -836,9 +1166,9 @@ dependencies = [ { name = "pymdown-extensions" }, { name = "requests" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/11/cb/6dd3b6a7925429c0229738098ee874dbf7fa02db55558adb2c5bf86077b2/mkdocs_material-9.6.9.tar.gz", hash = "sha256:a4872139715a1f27b2aa3f3dc31a9794b7bbf36333c0ba4607cf04786c94f89c", size = 3948083 } +sdist = { url = "https://files.pythonhosted.org/packages/5b/7e/c65e330e99daa5813e7594e57a09219ad041ed631604a72588ec7c11b34b/mkdocs_material-9.6.11.tar.gz", hash = "sha256:0b7f4a0145c5074cdd692e4362d232fb25ef5b23328d0ec1ab287af77cc0deff", size = 3951595 } wheels = [ - { url = "https://files.pythonhosted.org/packages/db/7c/ea5a671b2ff5d0e3f3108a7f7d75b541d683e4969aaead2a8f3e59e0fc27/mkdocs_material-9.6.9-py3-none-any.whl", hash = "sha256:6e61b7fb623ce2aa4622056592b155a9eea56ff3487d0835075360be45a4c8d1", size = 8697935 }, + { url = "https://files.pythonhosted.org/packages/19/91/79a15a772151aca0d505f901f6bbd4b85ee1fe54100256a6702056bab121/mkdocs_material-9.6.11-py3-none-any.whl", hash = "sha256:47f21ef9cbf4f0ebdce78a2ceecaa5d413581a55141e4464902224ebbc0b1263", size = 8703720 }, ] [[package]] @@ -850,9 +1180,21 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/5b/54/662a4743aa81d9582ee9339d4ffa3c8fd40a4965e033d77b9da9774d3960/mkdocs_material_extensions-1.3.1-py3-none-any.whl", hash = "sha256:adff8b62700b25cb77b53358dad940f3ef973dd6db797907c49e3c2ef3ab4e31", size = 8728 }, ] +[[package]] +name = "mkdocs-static-i18n" +version = "1.3.0" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "mkdocs" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/03/2b/59652a2550465fde25ae6a009cb6d74d0f7e724d272fc952685807b29ca1/mkdocs_static_i18n-1.3.0.tar.gz", hash = "sha256:65731e1e4ec6d719693e24fee9340f5516460b2b7244d2a89bed4ce3cfa6a173", size = 1370450 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/ca/f7/ef222a7a2f96ecf79c7c00bfc9dde3b22cd2cc1bd2b7472c7b204fc64225/mkdocs_static_i18n-1.3.0-py3-none-any.whl", hash = "sha256:7905d52fff71d2c108b6c344fd223e848ca7e39ddf319b70864dfa47dba85d6b", size = 21660 }, +] + [[package]] name = "mkdocstrings" -version = "0.29.0" +version = "0.29.1" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "importlib-metadata", marker = "python_full_version < '3.10'" }, @@ -862,11 +1204,10 @@ dependencies = [ { name = "mkdocs" }, { name = "mkdocs-autorefs" }, { name = "pymdown-extensions" }, - { name = "typing-extensions", marker = "python_full_version < '3.10'" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/8e/4d/a9484dc5d926295bdf308f1f6c4f07fcc99735b970591edc414d401fcc91/mkdocstrings-0.29.0.tar.gz", hash = "sha256:3657be1384543ce0ee82112c3e521bbf48e41303aa0c229b9ffcccba057d922e", size = 1212185 } +sdist = { url = "https://files.pythonhosted.org/packages/41/e8/d22922664a627a0d3d7ff4a6ca95800f5dde54f411982591b4621a76225d/mkdocstrings-0.29.1.tar.gz", hash = "sha256:8722f8f8c5cd75da56671e0a0c1bbed1df9946c0cef74794d6141b34011abd42", size = 1212686 } wheels = [ - { url = "https://files.pythonhosted.org/packages/15/47/eb876dfd84e48f31ff60897d161b309cf6a04ca270155b0662aae562b3fb/mkdocstrings-0.29.0-py3-none-any.whl", hash = "sha256:8ea98358d2006f60befa940fdebbbc88a26b37ecbcded10be726ba359284f73d", size = 1630824 }, + { url = "https://files.pythonhosted.org/packages/98/14/22533a578bf8b187e05d67e2c1721ce10e3f526610eebaf7a149d557ea7a/mkdocstrings-0.29.1-py3-none-any.whl", hash = "sha256:37a9736134934eea89cbd055a513d40a020d87dfcae9e3052c2a6b8cd4af09b6", size = 1631075 }, ] [package.optional-dependencies] @@ -876,7 +1217,7 @@ python = [ [[package]] name = "mkdocstrings-python" -version = "1.16.7" +version = "1.16.10" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "griffe" }, @@ -884,9 +1225,123 @@ dependencies = [ { name = "mkdocstrings" }, { name = "typing-extensions", marker = "python_full_version < '3.11'" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/52/e0/cc35acb47593c138efbfc9dc296ccc26b7ad4452e868fd309f05f6ba0ded/mkdocstrings_python-1.16.7.tar.gz", hash = "sha256:cdfc1a99fe5f6f0d90446a364ef7cac12014a4ef46114b2677a58cec84007117", size = 1475398 } +sdist = { url = "https://files.pythonhosted.org/packages/44/c8/600c4201b6b9e72bab16802316d0c90ce04089f8e6bb5e064cd2a5abba7e/mkdocstrings_python-1.16.10.tar.gz", hash = "sha256:f9eedfd98effb612ab4d0ed6dd2b73aff6eba5215e0a65cea6d877717f75502e", size = 205771 } wheels = [ - { url = "https://files.pythonhosted.org/packages/ab/5e/dc978b9fd6331e2070369579ad8f52145e9ef22a69bfc2811110be95e6d4/mkdocstrings_python-1.16.7-py3-none-any.whl", hash = "sha256:a5589a5be247a28ba651287f83630c69524042f8055d93b5c203d804a3409333", size = 1998312 }, + { url = "https://files.pythonhosted.org/packages/53/37/19549c5e0179785308cc988a68e16aa7550e4e270ec8a9878334e86070c6/mkdocstrings_python-1.16.10-py3-none-any.whl", hash = "sha256:63bb9f01f8848a644bdb6289e86dc38ceddeaa63ecc2e291e3b2ca52702a6643", size = 124112 }, +] + +[[package]] +name = "multidict" +version = "6.4.3" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "typing-extensions", marker = "python_full_version < '3.11'" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/da/2c/e367dfb4c6538614a0c9453e510d75d66099edf1c4e69da1b5ce691a1931/multidict-6.4.3.tar.gz", hash = "sha256:3ada0b058c9f213c5f95ba301f922d402ac234f1111a7d8fd70f1b99f3c281ec", size = 89372 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/83/44/45e798d4cd1b5dfe41ddf36266c7aca6d954e3c7a8b0d599ad555ce2b4f8/multidict-6.4.3-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:32a998bd8a64ca48616eac5a8c1cc4fa38fb244a3facf2eeb14abe186e0f6cc5", size = 65822 }, + { url = "https://files.pythonhosted.org/packages/10/fb/9ea024f928503f8c758f8463759d21958bf27b1f7a1103df73e5022e6a7c/multidict-6.4.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:a54ec568f1fc7f3c313c2f3b16e5db346bf3660e1309746e7fccbbfded856188", size = 38706 }, + { url = "https://files.pythonhosted.org/packages/6d/eb/7013316febca37414c0e1469fccadcb1a0e4315488f8f57ca5d29b384863/multidict-6.4.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:a7be07e5df178430621c716a63151165684d3e9958f2bbfcb644246162007ab7", size = 37979 }, + { url = "https://files.pythonhosted.org/packages/64/28/5a7bf4e7422613ea80f9ebc529d3845b20a422cfa94d4355504ac98047ee/multidict-6.4.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b128dbf1c939674a50dd0b28f12c244d90e5015e751a4f339a96c54f7275e291", size = 220233 }, + { url = "https://files.pythonhosted.org/packages/52/05/b4c58850f71befde6a16548968b48331a155a80627750b150bb5962e4dea/multidict-6.4.3-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:b9cb19dfd83d35b6ff24a4022376ea6e45a2beba8ef3f0836b8a4b288b6ad685", size = 217762 }, + { url = "https://files.pythonhosted.org/packages/99/a3/393e23bba1e9a00f95b3957acd8f5e3ee3446e78c550f593be25f9de0483/multidict-6.4.3-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3cf62f8e447ea2c1395afa289b332e49e13d07435369b6f4e41f887db65b40bf", size = 230699 }, + { url = "https://files.pythonhosted.org/packages/9c/a7/52c63069eb1a079f824257bb8045d93e692fa2eb34d08323d1fdbdfc398a/multidict-6.4.3-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:909f7d43ff8f13d1adccb6a397094adc369d4da794407f8dd592c51cf0eae4b1", size = 226801 }, + { url = "https://files.pythonhosted.org/packages/2c/e9/40d2b73e7d6574d91074d83477a990e3701affbe8b596010d4f5e6c7a6fa/multidict-6.4.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0bb8f8302fbc7122033df959e25777b0b7659b1fd6bcb9cb6bed76b5de67afef", size = 219833 }, + { url = "https://files.pythonhosted.org/packages/e4/6a/0572b22fe63c632254f55a1c1cb7d29f644002b1d8731d6103a290edc754/multidict-6.4.3-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:224b79471b4f21169ea25ebc37ed6f058040c578e50ade532e2066562597b8a9", size = 212920 }, + { url = "https://files.pythonhosted.org/packages/33/fe/c63735db9dece0053868b2d808bcc2592a83ce1830bc98243852a2b34d42/multidict-6.4.3-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:a7bd27f7ab3204f16967a6f899b3e8e9eb3362c0ab91f2ee659e0345445e0078", size = 225263 }, + { url = "https://files.pythonhosted.org/packages/47/c2/2db296d64d41525110c27ed38fadd5eb571c6b936233e75a5ea61b14e337/multidict-6.4.3-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:99592bd3162e9c664671fd14e578a33bfdba487ea64bcb41d281286d3c870ad7", size = 214249 }, + { url = "https://files.pythonhosted.org/packages/7e/74/8bc26e54c79f9a0f111350b1b28a9cacaaee53ecafccd53c90e59754d55a/multidict-6.4.3-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:a62d78a1c9072949018cdb05d3c533924ef8ac9bcb06cbf96f6d14772c5cd451", size = 221650 }, + { url = "https://files.pythonhosted.org/packages/af/d7/2ce87606e3799d9a08a941f4c170930a9895886ea8bd0eca75c44baeebe3/multidict-6.4.3-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:3ccdde001578347e877ca4f629450973c510e88e8865d5aefbcb89b852ccc666", size = 231235 }, + { url = "https://files.pythonhosted.org/packages/07/e1/d191a7ad3b90c613fc4b130d07a41c380e249767586148709b54d006ca17/multidict-6.4.3-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:eccb67b0e78aa2e38a04c5ecc13bab325a43e5159a181a9d1a6723db913cbb3c", size = 226056 }, + { url = "https://files.pythonhosted.org/packages/24/05/a57490cf6a8d5854f4af2d17dfc54924f37fbb683986e133b76710a36079/multidict-6.4.3-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:8b6fcf6054fc4114a27aa865f8840ef3d675f9316e81868e0ad5866184a6cba5", size = 220014 }, + { url = "https://files.pythonhosted.org/packages/5c/b1/be04fa9f08c684e9e27cca85b4ab94c10f017ec07c4c631af9c8c10bb275/multidict-6.4.3-cp310-cp310-win32.whl", hash = "sha256:f92c7f62d59373cd93bc9969d2da9b4b21f78283b1379ba012f7ee8127b3152e", size = 35042 }, + { url = "https://files.pythonhosted.org/packages/d9/ca/8888f99892513001fa900eef11bafbf38ff3485109510487de009da85748/multidict-6.4.3-cp310-cp310-win_amd64.whl", hash = "sha256:b57e28dbc031d13916b946719f213c494a517b442d7b48b29443e79610acd887", size = 38506 }, + { url = "https://files.pythonhosted.org/packages/16/e0/53cf7f27eda48fffa53cfd4502329ed29e00efb9e4ce41362cbf8aa54310/multidict-6.4.3-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:f6f19170197cc29baccd33ccc5b5d6a331058796485857cf34f7635aa25fb0cd", size = 65259 }, + { url = "https://files.pythonhosted.org/packages/44/79/1dcd93ce7070cf01c2ee29f781c42b33c64fce20033808f1cc9ec8413d6e/multidict-6.4.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:f2882bf27037eb687e49591690e5d491e677272964f9ec7bc2abbe09108bdfb8", size = 38451 }, + { url = "https://files.pythonhosted.org/packages/f4/35/2292cf29ab5f0d0b3613fad1b75692148959d3834d806be1885ceb49a8ff/multidict-6.4.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:fbf226ac85f7d6b6b9ba77db4ec0704fde88463dc17717aec78ec3c8546c70ad", size = 37706 }, + { url = "https://files.pythonhosted.org/packages/f6/d1/6b157110b2b187b5a608b37714acb15ee89ec773e3800315b0107ea648cd/multidict-6.4.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2e329114f82ad4b9dd291bef614ea8971ec119ecd0f54795109976de75c9a852", size = 226669 }, + { url = "https://files.pythonhosted.org/packages/40/7f/61a476450651f177c5570e04bd55947f693077ba7804fe9717ee9ae8de04/multidict-6.4.3-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:1f4e0334d7a555c63f5c8952c57ab6f1c7b4f8c7f3442df689fc9f03df315c08", size = 223182 }, + { url = "https://files.pythonhosted.org/packages/51/7b/eaf7502ac4824cdd8edcf5723e2e99f390c879866aec7b0c420267b53749/multidict-6.4.3-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:740915eb776617b57142ce0bb13b7596933496e2f798d3d15a20614adf30d229", size = 235025 }, + { url = "https://files.pythonhosted.org/packages/3b/f6/facdbbd73c96b67a93652774edd5778ab1167854fa08ea35ad004b1b70ad/multidict-6.4.3-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:255dac25134d2b141c944b59a0d2f7211ca12a6d4779f7586a98b4b03ea80508", size = 231481 }, + { url = "https://files.pythonhosted.org/packages/70/57/c008e861b3052405eebf921fd56a748322d8c44dcfcab164fffbccbdcdc4/multidict-6.4.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d4e8535bd4d741039b5aad4285ecd9b902ef9e224711f0b6afda6e38d7ac02c7", size = 223492 }, + { url = "https://files.pythonhosted.org/packages/30/4d/7d8440d3a12a6ae5d6b202d6e7f2ac6ab026e04e99aaf1b73f18e6bc34bc/multidict-6.4.3-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:30c433a33be000dd968f5750722eaa0991037be0be4a9d453eba121774985bc8", size = 217279 }, + { url = "https://files.pythonhosted.org/packages/7f/e7/bca0df4dd057597b94138d2d8af04eb3c27396a425b1b0a52e082f9be621/multidict-6.4.3-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:4eb33b0bdc50acd538f45041f5f19945a1f32b909b76d7b117c0c25d8063df56", size = 228733 }, + { url = "https://files.pythonhosted.org/packages/88/f5/383827c3f1c38d7c92dbad00a8a041760228573b1c542fbf245c37bbca8a/multidict-6.4.3-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:75482f43465edefd8a5d72724887ccdcd0c83778ded8f0cb1e0594bf71736cc0", size = 218089 }, + { url = "https://files.pythonhosted.org/packages/36/8a/a5174e8a7d8b94b4c8f9c1e2cf5d07451f41368ffe94d05fc957215b8e72/multidict-6.4.3-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:ce5b3082e86aee80b3925ab4928198450d8e5b6466e11501fe03ad2191c6d777", size = 225257 }, + { url = "https://files.pythonhosted.org/packages/8c/76/1d4b7218f0fd00b8e5c90b88df2e45f8af127f652f4e41add947fa54c1c4/multidict-6.4.3-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:e413152e3212c4d39f82cf83c6f91be44bec9ddea950ce17af87fbf4e32ca6b2", size = 234728 }, + { url = "https://files.pythonhosted.org/packages/64/44/18372a4f6273fc7ca25630d7bf9ae288cde64f29593a078bff450c7170b6/multidict-6.4.3-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:8aac2eeff69b71f229a405c0a4b61b54bade8e10163bc7b44fcd257949620618", size = 230087 }, + { url = "https://files.pythonhosted.org/packages/0f/ae/28728c314a698d8a6d9491fcacc897077348ec28dd85884d09e64df8a855/multidict-6.4.3-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:ab583ac203af1d09034be41458feeab7863c0635c650a16f15771e1386abf2d7", size = 223137 }, + { url = "https://files.pythonhosted.org/packages/22/50/785bb2b3fe16051bc91c70a06a919f26312da45c34db97fc87441d61e343/multidict-6.4.3-cp311-cp311-win32.whl", hash = "sha256:1b2019317726f41e81154df636a897de1bfe9228c3724a433894e44cd2512378", size = 34959 }, + { url = "https://files.pythonhosted.org/packages/2f/63/2a22e099ae2f4d92897618c00c73a09a08a2a9aa14b12736965bf8d59fd3/multidict-6.4.3-cp311-cp311-win_amd64.whl", hash = "sha256:43173924fa93c7486402217fab99b60baf78d33806af299c56133a3755f69589", size = 38541 }, + { url = "https://files.pythonhosted.org/packages/fc/bb/3abdaf8fe40e9226ce8a2ba5ecf332461f7beec478a455d6587159f1bf92/multidict-6.4.3-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:1f1c2f58f08b36f8475f3ec6f5aeb95270921d418bf18f90dffd6be5c7b0e676", size = 64019 }, + { url = "https://files.pythonhosted.org/packages/7e/b5/1b2e8de8217d2e89db156625aa0fe4a6faad98972bfe07a7b8c10ef5dd6b/multidict-6.4.3-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:26ae9ad364fc61b936fb7bf4c9d8bd53f3a5b4417142cd0be5c509d6f767e2f1", size = 37925 }, + { url = "https://files.pythonhosted.org/packages/b4/e2/3ca91c112644a395c8eae017144c907d173ea910c913ff8b62549dcf0bbf/multidict-6.4.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:659318c6c8a85f6ecfc06b4e57529e5a78dfdd697260cc81f683492ad7e9435a", size = 37008 }, + { url = "https://files.pythonhosted.org/packages/60/23/79bc78146c7ac8d1ac766b2770ca2e07c2816058b8a3d5da6caed8148637/multidict-6.4.3-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e1eb72c741fd24d5a28242ce72bb61bc91f8451877131fa3fe930edb195f7054", size = 224374 }, + { url = "https://files.pythonhosted.org/packages/86/35/77950ed9ebd09136003a85c1926ba42001ca5be14feb49710e4334ee199b/multidict-6.4.3-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:3cd06d88cb7398252284ee75c8db8e680aa0d321451132d0dba12bc995f0adcc", size = 230869 }, + { url = "https://files.pythonhosted.org/packages/49/97/2a33c6e7d90bc116c636c14b2abab93d6521c0c052d24bfcc231cbf7f0e7/multidict-6.4.3-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4543d8dc6470a82fde92b035a92529317191ce993533c3c0c68f56811164ed07", size = 231949 }, + { url = "https://files.pythonhosted.org/packages/56/ce/e9b5d9fcf854f61d6686ada7ff64893a7a5523b2a07da6f1265eaaea5151/multidict-6.4.3-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:30a3ebdc068c27e9d6081fca0e2c33fdf132ecea703a72ea216b81a66860adde", size = 231032 }, + { url = "https://files.pythonhosted.org/packages/f0/ac/7ced59dcdfeddd03e601edb05adff0c66d81ed4a5160c443e44f2379eef0/multidict-6.4.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b038f10e23f277153f86f95c777ba1958bcd5993194fda26a1d06fae98b2f00c", size = 223517 }, + { url = "https://files.pythonhosted.org/packages/db/e6/325ed9055ae4e085315193a1b58bdb4d7fc38ffcc1f4975cfca97d015e17/multidict-6.4.3-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c605a2b2dc14282b580454b9b5d14ebe0668381a3a26d0ac39daa0ca115eb2ae", size = 216291 }, + { url = "https://files.pythonhosted.org/packages/fa/84/eeee6d477dd9dcb7691c3bb9d08df56017f5dd15c730bcc9383dcf201cf4/multidict-6.4.3-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:8bd2b875f4ca2bb527fe23e318ddd509b7df163407b0fb717df229041c6df5d3", size = 228982 }, + { url = "https://files.pythonhosted.org/packages/82/94/4d1f3e74e7acf8b0c85db350e012dcc61701cd6668bc2440bb1ecb423c90/multidict-6.4.3-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:c2e98c840c9c8e65c0e04b40c6c5066c8632678cd50c8721fdbcd2e09f21a507", size = 226823 }, + { url = "https://files.pythonhosted.org/packages/09/f0/1e54b95bda7cd01080e5732f9abb7b76ab5cc795b66605877caeb2197476/multidict-6.4.3-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:66eb80dd0ab36dbd559635e62fba3083a48a252633164857a1d1684f14326427", size = 222714 }, + { url = "https://files.pythonhosted.org/packages/e7/a2/f6cbca875195bd65a3e53b37ab46486f3cc125bdeab20eefe5042afa31fb/multidict-6.4.3-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:c23831bdee0a2a3cf21be057b5e5326292f60472fb6c6f86392bbf0de70ba731", size = 233739 }, + { url = "https://files.pythonhosted.org/packages/79/68/9891f4d2b8569554723ddd6154375295f789dc65809826c6fb96a06314fd/multidict-6.4.3-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:1535cec6443bfd80d028052e9d17ba6ff8a5a3534c51d285ba56c18af97e9713", size = 230809 }, + { url = "https://files.pythonhosted.org/packages/e6/72/a7be29ba1e87e4fc5ceb44dabc7940b8005fd2436a332a23547709315f70/multidict-6.4.3-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:3b73e7227681f85d19dec46e5b881827cd354aabe46049e1a61d2f9aaa4e285a", size = 226934 }, + { url = "https://files.pythonhosted.org/packages/12/c1/259386a9ad6840ff7afc686da96808b503d152ac4feb3a96c651dc4f5abf/multidict-6.4.3-cp312-cp312-win32.whl", hash = "sha256:8eac0c49df91b88bf91f818e0a24c1c46f3622978e2c27035bfdca98e0e18124", size = 35242 }, + { url = "https://files.pythonhosted.org/packages/06/24/c8fdff4f924d37225dc0c56a28b1dca10728fc2233065fafeb27b4b125be/multidict-6.4.3-cp312-cp312-win_amd64.whl", hash = "sha256:11990b5c757d956cd1db7cb140be50a63216af32cd6506329c2c59d732d802db", size = 38635 }, + { url = "https://files.pythonhosted.org/packages/6c/4b/86fd786d03915c6f49998cf10cd5fe6b6ac9e9a071cb40885d2e080fb90d/multidict-6.4.3-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:7a76534263d03ae0cfa721fea40fd2b5b9d17a6f85e98025931d41dc49504474", size = 63831 }, + { url = "https://files.pythonhosted.org/packages/45/05/9b51fdf7aef2563340a93be0a663acba2c428c4daeaf3960d92d53a4a930/multidict-6.4.3-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:805031c2f599eee62ac579843555ed1ce389ae00c7e9f74c2a1b45e0564a88dd", size = 37888 }, + { url = "https://files.pythonhosted.org/packages/0b/43/53fc25394386c911822419b522181227ca450cf57fea76e6188772a1bd91/multidict-6.4.3-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:c56c179839d5dcf51d565132185409d1d5dd8e614ba501eb79023a6cab25576b", size = 36852 }, + { url = "https://files.pythonhosted.org/packages/8a/68/7b99c751e822467c94a235b810a2fd4047d4ecb91caef6b5c60116991c4b/multidict-6.4.3-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9c64f4ddb3886dd8ab71b68a7431ad4aa01a8fa5be5b11543b29674f29ca0ba3", size = 223644 }, + { url = "https://files.pythonhosted.org/packages/80/1b/d458d791e4dd0f7e92596667784fbf99e5c8ba040affe1ca04f06b93ae92/multidict-6.4.3-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:3002a856367c0b41cad6784f5b8d3ab008eda194ed7864aaa58f65312e2abcac", size = 230446 }, + { url = "https://files.pythonhosted.org/packages/e2/46/9793378d988905491a7806d8987862dc5a0bae8a622dd896c4008c7b226b/multidict-6.4.3-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3d75e621e7d887d539d6e1d789f0c64271c250276c333480a9e1de089611f790", size = 231070 }, + { url = "https://files.pythonhosted.org/packages/a7/b8/b127d3e1f8dd2a5bf286b47b24567ae6363017292dc6dec44656e6246498/multidict-6.4.3-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:995015cf4a3c0d72cbf453b10a999b92c5629eaf3a0c3e1efb4b5c1f602253bb", size = 229956 }, + { url = "https://files.pythonhosted.org/packages/0c/93/f70a4c35b103fcfe1443059a2bb7f66e5c35f2aea7804105ff214f566009/multidict-6.4.3-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a2b0fabae7939d09d7d16a711468c385272fa1b9b7fb0d37e51143585d8e72e0", size = 222599 }, + { url = "https://files.pythonhosted.org/packages/63/8c/e28e0eb2fe34921d6aa32bfc4ac75b09570b4d6818cc95d25499fe08dc1d/multidict-6.4.3-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:61ed4d82f8a1e67eb9eb04f8587970d78fe7cddb4e4d6230b77eda23d27938f9", size = 216136 }, + { url = "https://files.pythonhosted.org/packages/72/f5/fbc81f866585b05f89f99d108be5d6ad170e3b6c4d0723d1a2f6ba5fa918/multidict-6.4.3-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:062428944a8dc69df9fdc5d5fc6279421e5f9c75a9ee3f586f274ba7b05ab3c8", size = 228139 }, + { url = "https://files.pythonhosted.org/packages/bb/ba/7d196bad6b85af2307d81f6979c36ed9665f49626f66d883d6c64d156f78/multidict-6.4.3-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:b90e27b4674e6c405ad6c64e515a505c6d113b832df52fdacb6b1ffd1fa9a1d1", size = 226251 }, + { url = "https://files.pythonhosted.org/packages/cc/e2/fae46a370dce79d08b672422a33df721ec8b80105e0ea8d87215ff6b090d/multidict-6.4.3-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:7d50d4abf6729921e9613d98344b74241572b751c6b37feed75fb0c37bd5a817", size = 221868 }, + { url = "https://files.pythonhosted.org/packages/26/20/bbc9a3dec19d5492f54a167f08546656e7aef75d181d3d82541463450e88/multidict-6.4.3-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:43fe10524fb0a0514be3954be53258e61d87341008ce4914f8e8b92bee6f875d", size = 233106 }, + { url = "https://files.pythonhosted.org/packages/ee/8d/f30ae8f5ff7a2461177f4d8eb0d8f69f27fb6cfe276b54ec4fd5a282d918/multidict-6.4.3-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:236966ca6c472ea4e2d3f02f6673ebfd36ba3f23159c323f5a496869bc8e47c9", size = 230163 }, + { url = "https://files.pythonhosted.org/packages/15/e9/2833f3c218d3c2179f3093f766940ded6b81a49d2e2f9c46ab240d23dfec/multidict-6.4.3-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:422a5ec315018e606473ba1f5431e064cf8b2a7468019233dcf8082fabad64c8", size = 225906 }, + { url = "https://files.pythonhosted.org/packages/f1/31/6edab296ac369fd286b845fa5dd4c409e63bc4655ed8c9510fcb477e9ae9/multidict-6.4.3-cp313-cp313-win32.whl", hash = "sha256:f901a5aace8e8c25d78960dcc24c870c8d356660d3b49b93a78bf38eb682aac3", size = 35238 }, + { url = "https://files.pythonhosted.org/packages/23/57/2c0167a1bffa30d9a1383c3dab99d8caae985defc8636934b5668830d2ef/multidict-6.4.3-cp313-cp313-win_amd64.whl", hash = "sha256:1c152c49e42277bc9a2f7b78bd5fa10b13e88d1b0328221e7aef89d5c60a99a5", size = 38799 }, + { url = "https://files.pythonhosted.org/packages/c9/13/2ead63b9ab0d2b3080819268acb297bd66e238070aa8d42af12b08cbee1c/multidict-6.4.3-cp313-cp313t-macosx_10_13_universal2.whl", hash = "sha256:be8751869e28b9c0d368d94f5afcb4234db66fe8496144547b4b6d6a0645cfc6", size = 68642 }, + { url = "https://files.pythonhosted.org/packages/85/45/f1a751e1eede30c23951e2ae274ce8fad738e8a3d5714be73e0a41b27b16/multidict-6.4.3-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:0d4b31f8a68dccbcd2c0ea04f0e014f1defc6b78f0eb8b35f2265e8716a6df0c", size = 40028 }, + { url = "https://files.pythonhosted.org/packages/a7/29/fcc53e886a2cc5595cc4560df333cb9630257bda65003a7eb4e4e0d8f9c1/multidict-6.4.3-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:032efeab3049e37eef2ff91271884303becc9e54d740b492a93b7e7266e23756", size = 39424 }, + { url = "https://files.pythonhosted.org/packages/f6/f0/056c81119d8b88703971f937b371795cab1407cd3c751482de5bfe1a04a9/multidict-6.4.3-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9e78006af1a7c8a8007e4f56629d7252668344442f66982368ac06522445e375", size = 226178 }, + { url = "https://files.pythonhosted.org/packages/a3/79/3b7e5fea0aa80583d3a69c9d98b7913dfd4fbc341fb10bb2fb48d35a9c21/multidict-6.4.3-cp313-cp313t-manylinux_2_17_armv7l.manylinux2014_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:daeac9dd30cda8703c417e4fddccd7c4dc0c73421a0b54a7da2713be125846be", size = 222617 }, + { url = "https://files.pythonhosted.org/packages/06/db/3ed012b163e376fc461e1d6a67de69b408339bc31dc83d39ae9ec3bf9578/multidict-6.4.3-cp313-cp313t-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1f6f90700881438953eae443a9c6f8a509808bc3b185246992c4233ccee37fea", size = 227919 }, + { url = "https://files.pythonhosted.org/packages/b1/db/0433c104bca380989bc04d3b841fc83e95ce0c89f680e9ea4251118b52b6/multidict-6.4.3-cp313-cp313t-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f84627997008390dd15762128dcf73c3365f4ec0106739cde6c20a07ed198ec8", size = 226097 }, + { url = "https://files.pythonhosted.org/packages/c2/95/910db2618175724dd254b7ae635b6cd8d2947a8b76b0376de7b96d814dab/multidict-6.4.3-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3307b48cd156153b117c0ea54890a3bdbf858a5b296ddd40dc3852e5f16e9b02", size = 220706 }, + { url = "https://files.pythonhosted.org/packages/d1/af/aa176c6f5f1d901aac957d5258d5e22897fe13948d1e69063ae3d5d0ca01/multidict-6.4.3-cp313-cp313t-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ead46b0fa1dcf5af503a46e9f1c2e80b5d95c6011526352fa5f42ea201526124", size = 211728 }, + { url = "https://files.pythonhosted.org/packages/e7/42/d51cc5fc1527c3717d7f85137d6c79bb7a93cd214c26f1fc57523774dbb5/multidict-6.4.3-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:1748cb2743bedc339d63eb1bca314061568793acd603a6e37b09a326334c9f44", size = 226276 }, + { url = "https://files.pythonhosted.org/packages/28/6b/d836dea45e0b8432343ba4acf9a8ecaa245da4c0960fb7ab45088a5e568a/multidict-6.4.3-cp313-cp313t-musllinux_1_2_armv7l.whl", hash = "sha256:acc9fa606f76fc111b4569348cc23a771cb52c61516dcc6bcef46d612edb483b", size = 212069 }, + { url = "https://files.pythonhosted.org/packages/55/34/0ee1a7adb3560e18ee9289c6e5f7db54edc312b13e5c8263e88ea373d12c/multidict-6.4.3-cp313-cp313t-musllinux_1_2_i686.whl", hash = "sha256:31469d5832b5885adeb70982e531ce86f8c992334edd2f2254a10fa3182ac504", size = 217858 }, + { url = "https://files.pythonhosted.org/packages/04/08/586d652c2f5acefe0cf4e658eedb4d71d4ba6dfd4f189bd81b400fc1bc6b/multidict-6.4.3-cp313-cp313t-musllinux_1_2_ppc64le.whl", hash = "sha256:ba46b51b6e51b4ef7bfb84b82f5db0dc5e300fb222a8a13b8cd4111898a869cf", size = 226988 }, + { url = "https://files.pythonhosted.org/packages/82/e3/cc59c7e2bc49d7f906fb4ffb6d9c3a3cf21b9f2dd9c96d05bef89c2b1fd1/multidict-6.4.3-cp313-cp313t-musllinux_1_2_s390x.whl", hash = "sha256:389cfefb599edf3fcfd5f64c0410da686f90f5f5e2c4d84e14f6797a5a337af4", size = 220435 }, + { url = "https://files.pythonhosted.org/packages/e0/32/5c3a556118aca9981d883f38c4b1bfae646f3627157f70f4068e5a648955/multidict-6.4.3-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:64bc2bbc5fba7b9db5c2c8d750824f41c6994e3882e6d73c903c2afa78d091e4", size = 221494 }, + { url = "https://files.pythonhosted.org/packages/b9/3b/1599631f59024b75c4d6e3069f4502409970a336647502aaf6b62fb7ac98/multidict-6.4.3-cp313-cp313t-win32.whl", hash = "sha256:0ecdc12ea44bab2807d6b4a7e5eef25109ab1c82a8240d86d3c1fc9f3b72efd5", size = 41775 }, + { url = "https://files.pythonhosted.org/packages/e8/4e/09301668d675d02ca8e8e1a3e6be046619e30403f5ada2ed5b080ae28d02/multidict-6.4.3-cp313-cp313t-win_amd64.whl", hash = "sha256:7146a8742ea71b5d7d955bffcef58a9e6e04efba704b52a460134fefd10a8208", size = 45946 }, + { url = "https://files.pythonhosted.org/packages/62/41/609ef2253da5d1686a85456b8315dec648a45a1d547074db225e94b3dd61/multidict-6.4.3-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:5427a2679e95a642b7f8b0f761e660c845c8e6fe3141cddd6b62005bd133fc21", size = 65724 }, + { url = "https://files.pythonhosted.org/packages/b5/4e/3a2daf9ccbdb503df7b91cbee240fccc96dd3287397b05ed59673b196cde/multidict-6.4.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:24a8caa26521b9ad09732972927d7b45b66453e6ebd91a3c6a46d811eeb7349b", size = 38659 }, + { url = "https://files.pythonhosted.org/packages/04/f8/3a7ec724c51ad9c1534ebb0a60020e24c12b1fe4c60a4fdd0c97a3383cf4/multidict-6.4.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:6b5a272bc7c36a2cd1b56ddc6bff02e9ce499f9f14ee4a45c45434ef083f2459", size = 37927 }, + { url = "https://files.pythonhosted.org/packages/7f/c5/76c9a8cd657b3a44daf08f14faebb558b00fa22698f58ee7fa3876ade2e4/multidict-6.4.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:edf74dc5e212b8c75165b435c43eb0d5e81b6b300a938a4eb82827119115e840", size = 217990 }, + { url = "https://files.pythonhosted.org/packages/ac/b9/6ccb5bfc3747546e096f34c8b2ee91ccab0a92fefe7a9addc4ef9055ab4d/multidict-6.4.3-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:9f35de41aec4b323c71f54b0ca461ebf694fb48bec62f65221f52e0017955b39", size = 213431 }, + { url = "https://files.pythonhosted.org/packages/0b/e9/95af61c79ffabb4a4331fe0736280ef30b324b67772fd018faf408d73f7d/multidict-6.4.3-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ae93e0ff43b6f6892999af64097b18561691ffd835e21a8348a441e256592e1f", size = 228087 }, + { url = "https://files.pythonhosted.org/packages/04/d2/bd7454b40e4d0f21771b2aa077c0e3f4dfb965f209ffce21112743cdadaa/multidict-6.4.3-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5e3929269e9d7eff905d6971d8b8c85e7dbc72c18fb99c8eae6fe0a152f2e343", size = 224061 }, + { url = "https://files.pythonhosted.org/packages/7a/f9/b50679179dd909ba28ce49dca551b40a8349aaed64beececd8ab64589b65/multidict-6.4.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fb6214fe1750adc2a1b801a199d64b5a67671bf76ebf24c730b157846d0e90d2", size = 216133 }, + { url = "https://files.pythonhosted.org/packages/8f/47/9b77c483a5183ed734d1272cbe685d7313922806d686c63748997374afc1/multidict-6.4.3-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6d79cf5c0c6284e90f72123f4a3e4add52d6c6ebb4a9054e88df15b8d08444c6", size = 209868 }, + { url = "https://files.pythonhosted.org/packages/6e/b1/c621ed6098e81404098236a08f7be9274e364cdb0fed12de837030235d19/multidict-6.4.3-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:2427370f4a255262928cd14533a70d9738dfacadb7563bc3b7f704cc2360fc4e", size = 221723 }, + { url = "https://files.pythonhosted.org/packages/3a/9f/77f41726c1a3e5651e37c67aea5736645484834efd06795b2f8d38318890/multidict-6.4.3-cp39-cp39-musllinux_1_2_armv7l.whl", hash = "sha256:fbd8d737867912b6c5f99f56782b8cb81f978a97b4437a1c476de90a3e41c9a1", size = 211008 }, + { url = "https://files.pythonhosted.org/packages/00/66/eec0484c1de91439ce4e054f754f0ecb1c9d1a5fa09a1c12952fb3717ce9/multidict-6.4.3-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:0ee1bf613c448997f73fc4efb4ecebebb1c02268028dd4f11f011f02300cf1e8", size = 216800 }, + { url = "https://files.pythonhosted.org/packages/95/58/a8f07841c6db4bdd8d1ae50cc8910cc63b5078b6dae3b196ec654d888060/multidict-6.4.3-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:578568c4ba5f2b8abd956baf8b23790dbfdc953e87d5b110bce343b4a54fc9e7", size = 227661 }, + { url = "https://files.pythonhosted.org/packages/2a/a5/c50b9430fe79d4b04efda204f22450a23cb4ae895734940541141a858089/multidict-6.4.3-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:a059ad6b80de5b84b9fa02a39400319e62edd39d210b4e4f8c4f1243bdac4752", size = 221821 }, + { url = "https://files.pythonhosted.org/packages/99/4c/2b69c52c4b1357d197c38a913fcf45b4200af79adfcdf96d88cb02d18f5b/multidict-6.4.3-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:dd53893675b729a965088aaadd6a1f326a72b83742b056c1065bdd2e2a42b4df", size = 216332 }, + { url = "https://files.pythonhosted.org/packages/1b/39/63d9bd977aed6a053955b30aad38bbfe1f0f8d7462f80760b498387c91ee/multidict-6.4.3-cp39-cp39-win32.whl", hash = "sha256:abcfed2c4c139f25c2355e180bcc077a7cae91eefbb8b3927bb3f836c9586f1f", size = 35087 }, + { url = "https://files.pythonhosted.org/packages/8f/d4/c6b8936fa9ff5e77fbba9ba431bc380ad0f8e6442a05c7fb6bfe35fdff60/multidict-6.4.3-cp39-cp39-win_amd64.whl", hash = "sha256:b1b389ae17296dd739015d5ddb222ee99fd66adeae910de21ac950e00979d897", size = 38680 }, + { url = "https://files.pythonhosted.org/packages/96/10/7d526c8974f017f1e7ca584c71ee62a638e9334d8d33f27d7cdfc9ae79e4/multidict-6.4.3-py3-none-any.whl", hash = "sha256:59fe01ee8e2a1e8ceb3f6dbb216b09c8d9f4ef1c22c4fc825d045a147fa2ebc9", size = 10400 }, ] [[package]] @@ -942,68 +1397,10 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/2a/e2/5d3f6ada4297caebe1a2add3b126fe800c96f56dbe5d1988a2cbe0b267aa/mypy_extensions-1.0.0-py3-none-any.whl", hash = "sha256:4392f6c0eb8a5668a69e23d168ffa70f0be9ccfd32b5cc2d26a34ae5b844552d", size = 4695 }, ] -[[package]] -name = "numpy" -version = "2.0.2" -source = { registry = "https://pypi.org/simple" } -resolution-markers = [ - "python_full_version < '3.10'", -] -sdist = { url = "https://files.pythonhosted.org/packages/a9/75/10dd1f8116a8b796cb2c737b674e02d02e80454bda953fa7e65d8c12b016/numpy-2.0.2.tar.gz", hash = "sha256:883c987dee1880e2a864ab0dc9892292582510604156762362d9326444636e78", size = 18902015 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/21/91/3495b3237510f79f5d81f2508f9f13fea78ebfdf07538fc7444badda173d/numpy-2.0.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:51129a29dbe56f9ca83438b706e2e69a39892b5eda6cedcb6b0c9fdc9b0d3ece", size = 21165245 }, - { url = "https://files.pythonhosted.org/packages/05/33/26178c7d437a87082d11019292dce6d3fe6f0e9026b7b2309cbf3e489b1d/numpy-2.0.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:f15975dfec0cf2239224d80e32c3170b1d168335eaedee69da84fbe9f1f9cd04", size = 13738540 }, - { url = "https://files.pythonhosted.org/packages/ec/31/cc46e13bf07644efc7a4bf68df2df5fb2a1a88d0cd0da9ddc84dc0033e51/numpy-2.0.2-cp310-cp310-macosx_14_0_arm64.whl", hash = "sha256:8c5713284ce4e282544c68d1c3b2c7161d38c256d2eefc93c1d683cf47683e66", size = 5300623 }, - { url = "https://files.pythonhosted.org/packages/6e/16/7bfcebf27bb4f9d7ec67332ffebee4d1bf085c84246552d52dbb548600e7/numpy-2.0.2-cp310-cp310-macosx_14_0_x86_64.whl", hash = "sha256:becfae3ddd30736fe1889a37f1f580e245ba79a5855bff5f2a29cb3ccc22dd7b", size = 6901774 }, - { url = "https://files.pythonhosted.org/packages/f9/a3/561c531c0e8bf082c5bef509d00d56f82e0ea7e1e3e3a7fc8fa78742a6e5/numpy-2.0.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2da5960c3cf0df7eafefd806d4e612c5e19358de82cb3c343631188991566ccd", size = 13907081 }, - { url = "https://files.pythonhosted.org/packages/fa/66/f7177ab331876200ac7563a580140643d1179c8b4b6a6b0fc9838de2a9b8/numpy-2.0.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:496f71341824ed9f3d2fd36cf3ac57ae2e0165c143b55c3a035ee219413f3318", size = 19523451 }, - { url = "https://files.pythonhosted.org/packages/25/7f/0b209498009ad6453e4efc2c65bcdf0ae08a182b2b7877d7ab38a92dc542/numpy-2.0.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:a61ec659f68ae254e4d237816e33171497e978140353c0c2038d46e63282d0c8", size = 19927572 }, - { url = "https://files.pythonhosted.org/packages/3e/df/2619393b1e1b565cd2d4c4403bdd979621e2c4dea1f8532754b2598ed63b/numpy-2.0.2-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:d731a1c6116ba289c1e9ee714b08a8ff882944d4ad631fd411106a30f083c326", size = 14400722 }, - { url = "https://files.pythonhosted.org/packages/22/ad/77e921b9f256d5da36424ffb711ae79ca3f451ff8489eeca544d0701d74a/numpy-2.0.2-cp310-cp310-win32.whl", hash = "sha256:984d96121c9f9616cd33fbd0618b7f08e0cfc9600a7ee1d6fd9b239186d19d97", size = 6472170 }, - { url = "https://files.pythonhosted.org/packages/10/05/3442317535028bc29cf0c0dd4c191a4481e8376e9f0db6bcf29703cadae6/numpy-2.0.2-cp310-cp310-win_amd64.whl", hash = "sha256:c7b0be4ef08607dd04da4092faee0b86607f111d5ae68036f16cc787e250a131", size = 15905558 }, - { url = "https://files.pythonhosted.org/packages/8b/cf/034500fb83041aa0286e0fb16e7c76e5c8b67c0711bb6e9e9737a717d5fe/numpy-2.0.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:49ca4decb342d66018b01932139c0961a8f9ddc7589611158cb3c27cbcf76448", size = 21169137 }, - { url = "https://files.pythonhosted.org/packages/4a/d9/32de45561811a4b87fbdee23b5797394e3d1504b4a7cf40c10199848893e/numpy-2.0.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:11a76c372d1d37437857280aa142086476136a8c0f373b2e648ab2c8f18fb195", size = 13703552 }, - { url = "https://files.pythonhosted.org/packages/c1/ca/2f384720020c7b244d22508cb7ab23d95f179fcfff33c31a6eeba8d6c512/numpy-2.0.2-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:807ec44583fd708a21d4a11d94aedf2f4f3c3719035c76a2bbe1fe8e217bdc57", size = 5298957 }, - { url = "https://files.pythonhosted.org/packages/0e/78/a3e4f9fb6aa4e6fdca0c5428e8ba039408514388cf62d89651aade838269/numpy-2.0.2-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:8cafab480740e22f8d833acefed5cc87ce276f4ece12fdaa2e8903db2f82897a", size = 6905573 }, - { url = "https://files.pythonhosted.org/packages/a0/72/cfc3a1beb2caf4efc9d0b38a15fe34025230da27e1c08cc2eb9bfb1c7231/numpy-2.0.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a15f476a45e6e5a3a79d8a14e62161d27ad897381fecfa4a09ed5322f2085669", size = 13914330 }, - { url = "https://files.pythonhosted.org/packages/ba/a8/c17acf65a931ce551fee11b72e8de63bf7e8a6f0e21add4c937c83563538/numpy-2.0.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:13e689d772146140a252c3a28501da66dfecd77490b498b168b501835041f951", size = 19534895 }, - { url = "https://files.pythonhosted.org/packages/ba/86/8767f3d54f6ae0165749f84648da9dcc8cd78ab65d415494962c86fac80f/numpy-2.0.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:9ea91dfb7c3d1c56a0e55657c0afb38cf1eeae4544c208dc465c3c9f3a7c09f9", size = 19937253 }, - { url = "https://files.pythonhosted.org/packages/df/87/f76450e6e1c14e5bb1eae6836478b1028e096fd02e85c1c37674606ab752/numpy-2.0.2-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:c1c9307701fec8f3f7a1e6711f9089c06e6284b3afbbcd259f7791282d660a15", size = 14414074 }, - { url = "https://files.pythonhosted.org/packages/5c/ca/0f0f328e1e59f73754f06e1adfb909de43726d4f24c6a3f8805f34f2b0fa/numpy-2.0.2-cp311-cp311-win32.whl", hash = "sha256:a392a68bd329eafac5817e5aefeb39038c48b671afd242710b451e76090e81f4", size = 6470640 }, - { url = "https://files.pythonhosted.org/packages/eb/57/3a3f14d3a759dcf9bf6e9eda905794726b758819df4663f217d658a58695/numpy-2.0.2-cp311-cp311-win_amd64.whl", hash = "sha256:286cd40ce2b7d652a6f22efdfc6d1edf879440e53e76a75955bc0c826c7e64dc", size = 15910230 }, - { url = "https://files.pythonhosted.org/packages/45/40/2e117be60ec50d98fa08c2f8c48e09b3edea93cfcabd5a9ff6925d54b1c2/numpy-2.0.2-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:df55d490dea7934f330006d0f81e8551ba6010a5bf035a249ef61a94f21c500b", size = 20895803 }, - { url = "https://files.pythonhosted.org/packages/46/92/1b8b8dee833f53cef3e0a3f69b2374467789e0bb7399689582314df02651/numpy-2.0.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:8df823f570d9adf0978347d1f926b2a867d5608f434a7cff7f7908c6570dcf5e", size = 13471835 }, - { url = "https://files.pythonhosted.org/packages/7f/19/e2793bde475f1edaea6945be141aef6c8b4c669b90c90a300a8954d08f0a/numpy-2.0.2-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:9a92ae5c14811e390f3767053ff54eaee3bf84576d99a2456391401323f4ec2c", size = 5038499 }, - { url = "https://files.pythonhosted.org/packages/e3/ff/ddf6dac2ff0dd50a7327bcdba45cb0264d0e96bb44d33324853f781a8f3c/numpy-2.0.2-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:a842d573724391493a97a62ebbb8e731f8a5dcc5d285dfc99141ca15a3302d0c", size = 6633497 }, - { url = "https://files.pythonhosted.org/packages/72/21/67f36eac8e2d2cd652a2e69595a54128297cdcb1ff3931cfc87838874bd4/numpy-2.0.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c05e238064fc0610c840d1cf6a13bf63d7e391717d247f1bf0318172e759e692", size = 13621158 }, - { url = "https://files.pythonhosted.org/packages/39/68/e9f1126d757653496dbc096cb429014347a36b228f5a991dae2c6b6cfd40/numpy-2.0.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0123ffdaa88fa4ab64835dcbde75dcdf89c453c922f18dced6e27c90d1d0ec5a", size = 19236173 }, - { url = "https://files.pythonhosted.org/packages/d1/e9/1f5333281e4ebf483ba1c888b1d61ba7e78d7e910fdd8e6499667041cc35/numpy-2.0.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:96a55f64139912d61de9137f11bf39a55ec8faec288c75a54f93dfd39f7eb40c", size = 19634174 }, - { url = "https://files.pythonhosted.org/packages/71/af/a469674070c8d8408384e3012e064299f7a2de540738a8e414dcfd639996/numpy-2.0.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:ec9852fb39354b5a45a80bdab5ac02dd02b15f44b3804e9f00c556bf24b4bded", size = 14099701 }, - { url = "https://files.pythonhosted.org/packages/d0/3d/08ea9f239d0e0e939b6ca52ad403c84a2bce1bde301a8eb4888c1c1543f1/numpy-2.0.2-cp312-cp312-win32.whl", hash = "sha256:671bec6496f83202ed2d3c8fdc486a8fc86942f2e69ff0e986140339a63bcbe5", size = 6174313 }, - { url = "https://files.pythonhosted.org/packages/b2/b5/4ac39baebf1fdb2e72585c8352c56d063b6126be9fc95bd2bb5ef5770c20/numpy-2.0.2-cp312-cp312-win_amd64.whl", hash = "sha256:cfd41e13fdc257aa5778496b8caa5e856dc4896d4ccf01841daee1d96465467a", size = 15606179 }, - { url = "https://files.pythonhosted.org/packages/43/c1/41c8f6df3162b0c6ffd4437d729115704bd43363de0090c7f913cfbc2d89/numpy-2.0.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9059e10581ce4093f735ed23f3b9d283b9d517ff46009ddd485f1747eb22653c", size = 21169942 }, - { url = "https://files.pythonhosted.org/packages/39/bc/fd298f308dcd232b56a4031fd6ddf11c43f9917fbc937e53762f7b5a3bb1/numpy-2.0.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:423e89b23490805d2a5a96fe40ec507407b8ee786d66f7328be214f9679df6dd", size = 13711512 }, - { url = "https://files.pythonhosted.org/packages/96/ff/06d1aa3eeb1c614eda245c1ba4fb88c483bee6520d361641331872ac4b82/numpy-2.0.2-cp39-cp39-macosx_14_0_arm64.whl", hash = "sha256:2b2955fa6f11907cf7a70dab0d0755159bca87755e831e47932367fc8f2f2d0b", size = 5306976 }, - { url = "https://files.pythonhosted.org/packages/2d/98/121996dcfb10a6087a05e54453e28e58694a7db62c5a5a29cee14c6e047b/numpy-2.0.2-cp39-cp39-macosx_14_0_x86_64.whl", hash = "sha256:97032a27bd9d8988b9a97a8c4d2c9f2c15a81f61e2f21404d7e8ef00cb5be729", size = 6906494 }, - { url = "https://files.pythonhosted.org/packages/15/31/9dffc70da6b9bbf7968f6551967fc21156207366272c2a40b4ed6008dc9b/numpy-2.0.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1e795a8be3ddbac43274f18588329c72939870a16cae810c2b73461c40718ab1", size = 13912596 }, - { url = "https://files.pythonhosted.org/packages/b9/14/78635daab4b07c0930c919d451b8bf8c164774e6a3413aed04a6d95758ce/numpy-2.0.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f26b258c385842546006213344c50655ff1555a9338e2e5e02a0756dc3e803dd", size = 19526099 }, - { url = "https://files.pythonhosted.org/packages/26/4c/0eeca4614003077f68bfe7aac8b7496f04221865b3a5e7cb230c9d055afd/numpy-2.0.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:5fec9451a7789926bcf7c2b8d187292c9f93ea30284802a0ab3f5be8ab36865d", size = 19932823 }, - { url = "https://files.pythonhosted.org/packages/f1/46/ea25b98b13dccaebddf1a803f8c748680d972e00507cd9bc6dcdb5aa2ac1/numpy-2.0.2-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:9189427407d88ff25ecf8f12469d4d39d35bee1db5d39fc5c168c6f088a6956d", size = 14404424 }, - { url = "https://files.pythonhosted.org/packages/c8/a6/177dd88d95ecf07e722d21008b1b40e681a929eb9e329684d449c36586b2/numpy-2.0.2-cp39-cp39-win32.whl", hash = "sha256:905d16e0c60200656500c95b6b8dca5d109e23cb24abc701d41c02d74c6b3afa", size = 6476809 }, - { url = "https://files.pythonhosted.org/packages/ea/2b/7fc9f4e7ae5b507c1a3a21f0f15ed03e794c1242ea8a242ac158beb56034/numpy-2.0.2-cp39-cp39-win_amd64.whl", hash = "sha256:a3f4ab0caa7f053f6797fcd4e1e25caee367db3112ef2b6ef82d749530768c73", size = 15911314 }, - { url = "https://files.pythonhosted.org/packages/8f/3b/df5a870ac6a3be3a86856ce195ef42eec7ae50d2a202be1f5a4b3b340e14/numpy-2.0.2-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:7f0a0c6f12e07fa94133c8a67404322845220c06a9e80e85999afe727f7438b8", size = 21025288 }, - { url = "https://files.pythonhosted.org/packages/2c/97/51af92f18d6f6f2d9ad8b482a99fb74e142d71372da5d834b3a2747a446e/numpy-2.0.2-pp39-pypy39_pp73-macosx_14_0_x86_64.whl", hash = "sha256:312950fdd060354350ed123c0e25a71327d3711584beaef30cdaa93320c392d4", size = 6762793 }, - { url = "https://files.pythonhosted.org/packages/12/46/de1fbd0c1b5ccaa7f9a005b66761533e2f6a3e560096682683a223631fe9/numpy-2.0.2-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:26df23238872200f63518dd2aa984cfca675d82469535dc7162dc2ee52d9dd5c", size = 19334885 }, - { url = "https://files.pythonhosted.org/packages/cc/dc/d330a6faefd92b446ec0f0dfea4c3207bb1fef3c4771d19cf4543efd2c78/numpy-2.0.2-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:a46288ec55ebbd58947d31d72be2c63cbf839f0a63b49cb755022310792a3385", size = 15828784 }, -] - [[package]] name = "numpy" version = "2.2.4" source = { registry = "https://pypi.org/simple" } -resolution-markers = [ - "python_full_version >= '3.10'", -] sdist = { url = "https://files.pythonhosted.org/packages/e1/78/31103410a57bc2c2b93a3597340a8119588571f6a4539067546cb9a0bfac/numpy-2.2.4.tar.gz", hash = "sha256:9ba03692a45d3eef66559efe1d1096c4b9b75c0986b5dff5530c378fb8331d4f", size = 20270701 } wheels = [ { url = "https://files.pythonhosted.org/packages/04/89/a79e86e5c1433926ed7d60cb267fb64aa578b6101ab645800fd43b4801de/numpy-2.2.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:8146f3550d627252269ac42ae660281d673eb6f8b32f113538e0cc2a9aed42b9", size = 21250661 }, @@ -1064,29 +1461,26 @@ wheels = [ [[package]] name = "openai" -version = "1.68.0" +version = "1.81.0" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "anyio" }, { name = "distro" }, { name = "httpx" }, { name = "jiter" }, - { name = "numpy", version = "2.0.2", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.10'" }, - { name = "numpy", version = "2.2.4", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.10'" }, { name = "pydantic" }, { name = "sniffio" }, - { name = "sounddevice" }, { name = "tqdm" }, { name = "typing-extensions" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/58/ea/58102e9bfda09edc963e6e877e39cca12706b46ebf35d5fc9da7b8af10f2/openai-1.68.0.tar.gz", hash = "sha256:c570c06c9ba10f98b891ac30a3dd7b5c89ed48094c711c7a3f35fb5ade6c0757", size = 413039 } +sdist = { url = "https://files.pythonhosted.org/packages/1c/89/a1e4f3fa7ca4f7fec90dbf47d93b7cd5ff65924926733af15044e302a192/openai-1.81.0.tar.gz", hash = "sha256:349567a8607e0bcffd28e02f96b5c2397d0d25d06732d90ab3ecbf97abf030f9", size = 456861 } wheels = [ - { url = "https://files.pythonhosted.org/packages/a5/b6/bd67b7031572cba7d8451d82ac4a990b3a96bbd3b037634726b48ac972c8/openai-1.68.0-py3-none-any.whl", hash = "sha256:20e279b0f3a78cb4a95f3eab2a180f3ee30c6a196aeebd6bf642a4f88ab85ee1", size = 605645 }, + { url = "https://files.pythonhosted.org/packages/02/66/bcc7f9bf48e8610a33e3b5c96a5a644dad032d92404ea2a5e8b43ba067e8/openai-1.81.0-py3-none-any.whl", hash = "sha256:1c71572e22b43876c5d7d65ade0b7b516bb527c3d44ae94111267a09125f7bae", size = 717529 }, ] [[package]] name = "openai-agents" -version = "0.0.7" +version = "0.0.16" source = { editable = "." } dependencies = [ { name = "griffe" }, @@ -1099,21 +1493,27 @@ dependencies = [ ] [package.optional-dependencies] +litellm = [ + { name = "litellm" }, +] viz = [ { name = "graphviz" }, ] voice = [ - { name = "numpy", version = "2.2.4", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.10'" }, + { name = "numpy", marker = "python_full_version >= '3.10'" }, { name = "websockets" }, ] [package.dev-dependencies] dev = [ { name = "coverage" }, + { name = "eval-type-backport" }, + { name = "fastapi" }, { name = "graphviz" }, { name = "inline-snapshot" }, { name = "mkdocs" }, { name = "mkdocs-material" }, + { name = "mkdocs-static-i18n" }, { name = "mkdocstrings", extra = ["python"] }, { name = "mypy" }, { name = "playwright" }, @@ -1133,23 +1533,29 @@ dev = [ requires-dist = [ { name = "graphviz", marker = "extra == 'viz'", specifier = ">=0.17" }, { name = "griffe", specifier = ">=1.5.6,<2" }, - { name = "mcp", marker = "python_full_version >= '3.10'" }, + { name = "litellm", marker = "extra == 'litellm'", specifier = ">=1.67.4.post1,<2" }, + { name = "mcp", marker = "python_full_version >= '3.10'", specifier = ">=1.8.0,<2" }, { name = "numpy", marker = "python_full_version >= '3.10' and extra == 'voice'", specifier = ">=2.2.0,<3" }, - { name = "openai", specifier = ">=1.66.5" }, + { name = "openai", specifier = ">=1.81.0" }, { name = "pydantic", specifier = ">=2.10,<3" }, { name = "requests", specifier = ">=2.0,<3" }, { name = "types-requests", specifier = ">=2.0,<3" }, { name = "typing-extensions", specifier = ">=4.12.2,<5" }, { name = "websockets", marker = "extra == 'voice'", specifier = ">=15.0,<16" }, ] +provides-extras = ["voice", "viz", "litellm"] [package.metadata.requires-dev] dev = [ { name = "coverage", specifier = ">=7.6.12" }, + { name = "eval-type-backport", specifier = ">=0.2.2" }, + { name = "fastapi", specifier = ">=0.110.0,<1" }, { name = "graphviz" }, { name = "inline-snapshot", specifier = ">=0.20.7" }, { name = "mkdocs", specifier = ">=1.6.0" }, { name = "mkdocs-material", specifier = ">=9.6.0" }, + { name = "mkdocs-static-i18n" }, + { name = "mkdocs-static-i18n", specifier = ">=1.3.0" }, { name = "mkdocstrings", extras = ["python"], specifier = ">=0.28.0" }, { name = "mypy" }, { name = "playwright", specifier = "==1.50.0" }, @@ -1157,7 +1563,7 @@ dev = [ { name = "pytest" }, { name = "pytest-asyncio" }, { name = "pytest-mock", specifier = ">=3.14.0" }, - { name = "rich" }, + { name = "rich", specifier = ">=13.1.0,<14" }, { name = "ruff", specifier = "==0.9.2" }, { name = "sounddevice" }, { name = "textual" }, @@ -1228,6 +1634,111 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/88/5f/e351af9a41f866ac3f1fac4ca0613908d9a41741cfcf2228f4ad853b697d/pluggy-1.5.0-py3-none-any.whl", hash = "sha256:44e1ad92c8ca002de6377e165f3e0f1be63266ab4d554740532335b9d75ea669", size = 20556 }, ] +[[package]] +name = "propcache" +version = "0.3.1" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/07/c8/fdc6686a986feae3541ea23dcaa661bd93972d3940460646c6bb96e21c40/propcache-0.3.1.tar.gz", hash = "sha256:40d980c33765359098837527e18eddefc9a24cea5b45e078a7f3bb5b032c6ecf", size = 43651 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/20/56/e27c136101addf877c8291dbda1b3b86ae848f3837ce758510a0d806c92f/propcache-0.3.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:f27785888d2fdd918bc36de8b8739f2d6c791399552333721b58193f68ea3e98", size = 80224 }, + { url = "https://files.pythonhosted.org/packages/63/bd/88e98836544c4f04db97eefd23b037c2002fa173dd2772301c61cd3085f9/propcache-0.3.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d4e89cde74154c7b5957f87a355bb9c8ec929c167b59c83d90654ea36aeb6180", size = 46491 }, + { url = "https://files.pythonhosted.org/packages/15/43/0b8eb2a55753c4a574fc0899885da504b521068d3b08ca56774cad0bea2b/propcache-0.3.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:730178f476ef03d3d4d255f0c9fa186cb1d13fd33ffe89d39f2cda4da90ceb71", size = 45927 }, + { url = "https://files.pythonhosted.org/packages/ad/6c/d01f9dfbbdc613305e0a831016844987a1fb4861dd221cd4c69b1216b43f/propcache-0.3.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:967a8eec513dbe08330f10137eacb427b2ca52118769e82ebcfcab0fba92a649", size = 206135 }, + { url = "https://files.pythonhosted.org/packages/9a/8a/e6e1c77394088f4cfdace4a91a7328e398ebed745d59c2f6764135c5342d/propcache-0.3.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5b9145c35cc87313b5fd480144f8078716007656093d23059e8993d3a8fa730f", size = 220517 }, + { url = "https://files.pythonhosted.org/packages/19/3b/6c44fa59d6418f4239d5db8b1ece757351e85d6f3ca126dfe37d427020c8/propcache-0.3.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9e64e948ab41411958670f1093c0a57acfdc3bee5cf5b935671bbd5313bcf229", size = 218952 }, + { url = "https://files.pythonhosted.org/packages/7c/e4/4aeb95a1cd085e0558ab0de95abfc5187329616193a1012a6c4c930e9f7a/propcache-0.3.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:319fa8765bfd6a265e5fa661547556da381e53274bc05094fc9ea50da51bfd46", size = 206593 }, + { url = "https://files.pythonhosted.org/packages/da/6a/29fa75de1cbbb302f1e1d684009b969976ca603ee162282ae702287b6621/propcache-0.3.1-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c66d8ccbc902ad548312b96ed8d5d266d0d2c6d006fd0f66323e9d8f2dd49be7", size = 196745 }, + { url = "https://files.pythonhosted.org/packages/19/7e/2237dad1dbffdd2162de470599fa1a1d55df493b16b71e5d25a0ac1c1543/propcache-0.3.1-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:2d219b0dbabe75e15e581fc1ae796109b07c8ba7d25b9ae8d650da582bed01b0", size = 203369 }, + { url = "https://files.pythonhosted.org/packages/a4/bc/a82c5878eb3afb5c88da86e2cf06e1fe78b7875b26198dbb70fe50a010dc/propcache-0.3.1-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:cd6a55f65241c551eb53f8cf4d2f4af33512c39da5d9777694e9d9c60872f519", size = 198723 }, + { url = "https://files.pythonhosted.org/packages/17/76/9632254479c55516f51644ddbf747a45f813031af5adcb8db91c0b824375/propcache-0.3.1-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:9979643ffc69b799d50d3a7b72b5164a2e97e117009d7af6dfdd2ab906cb72cd", size = 200751 }, + { url = "https://files.pythonhosted.org/packages/3e/c3/a90b773cf639bd01d12a9e20c95be0ae978a5a8abe6d2d343900ae76cd71/propcache-0.3.1-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:4cf9e93a81979f1424f1a3d155213dc928f1069d697e4353edb8a5eba67c6259", size = 210730 }, + { url = "https://files.pythonhosted.org/packages/ed/ec/ad5a952cdb9d65c351f88db7c46957edd3d65ffeee72a2f18bd6341433e0/propcache-0.3.1-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:2fce1df66915909ff6c824bbb5eb403d2d15f98f1518e583074671a30fe0c21e", size = 213499 }, + { url = "https://files.pythonhosted.org/packages/83/c0/ea5133dda43e298cd2010ec05c2821b391e10980e64ee72c0a76cdbb813a/propcache-0.3.1-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:4d0dfdd9a2ebc77b869a0b04423591ea8823f791293b527dc1bb896c1d6f1136", size = 207132 }, + { url = "https://files.pythonhosted.org/packages/79/dd/71aae9dec59333064cfdd7eb31a63fa09f64181b979802a67a90b2abfcba/propcache-0.3.1-cp310-cp310-win32.whl", hash = "sha256:1f6cc0ad7b4560e5637eb2c994e97b4fa41ba8226069c9277eb5ea7101845b42", size = 40952 }, + { url = "https://files.pythonhosted.org/packages/31/0a/49ff7e5056c17dfba62cbdcbb90a29daffd199c52f8e65e5cb09d5f53a57/propcache-0.3.1-cp310-cp310-win_amd64.whl", hash = "sha256:47ef24aa6511e388e9894ec16f0fbf3313a53ee68402bc428744a367ec55b833", size = 45163 }, + { url = "https://files.pythonhosted.org/packages/90/0f/5a5319ee83bd651f75311fcb0c492c21322a7fc8f788e4eef23f44243427/propcache-0.3.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:7f30241577d2fef2602113b70ef7231bf4c69a97e04693bde08ddab913ba0ce5", size = 80243 }, + { url = "https://files.pythonhosted.org/packages/ce/84/3db5537e0879942783e2256616ff15d870a11d7ac26541336fe1b673c818/propcache-0.3.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:43593c6772aa12abc3af7784bff4a41ffa921608dd38b77cf1dfd7f5c4e71371", size = 46503 }, + { url = "https://files.pythonhosted.org/packages/e2/c8/b649ed972433c3f0d827d7f0cf9ea47162f4ef8f4fe98c5f3641a0bc63ff/propcache-0.3.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:a75801768bbe65499495660b777e018cbe90c7980f07f8aa57d6be79ea6f71da", size = 45934 }, + { url = "https://files.pythonhosted.org/packages/59/f9/4c0a5cf6974c2c43b1a6810c40d889769cc8f84cea676cbe1e62766a45f8/propcache-0.3.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f6f1324db48f001c2ca26a25fa25af60711e09b9aaf4b28488602776f4f9a744", size = 233633 }, + { url = "https://files.pythonhosted.org/packages/e7/64/66f2f4d1b4f0007c6e9078bd95b609b633d3957fe6dd23eac33ebde4b584/propcache-0.3.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5cdb0f3e1eb6dfc9965d19734d8f9c481b294b5274337a8cb5cb01b462dcb7e0", size = 241124 }, + { url = "https://files.pythonhosted.org/packages/aa/bf/7b8c9fd097d511638fa9b6af3d986adbdf567598a567b46338c925144c1b/propcache-0.3.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1eb34d90aac9bfbced9a58b266f8946cb5935869ff01b164573a7634d39fbcb5", size = 240283 }, + { url = "https://files.pythonhosted.org/packages/fa/c9/e85aeeeaae83358e2a1ef32d6ff50a483a5d5248bc38510d030a6f4e2816/propcache-0.3.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f35c7070eeec2cdaac6fd3fe245226ed2a6292d3ee8c938e5bb645b434c5f256", size = 232498 }, + { url = "https://files.pythonhosted.org/packages/8e/66/acb88e1f30ef5536d785c283af2e62931cb934a56a3ecf39105887aa8905/propcache-0.3.1-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b23c11c2c9e6d4e7300c92e022046ad09b91fd00e36e83c44483df4afa990073", size = 221486 }, + { url = "https://files.pythonhosted.org/packages/f5/f9/233ddb05ffdcaee4448508ee1d70aa7deff21bb41469ccdfcc339f871427/propcache-0.3.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:3e19ea4ea0bf46179f8a3652ac1426e6dcbaf577ce4b4f65be581e237340420d", size = 222675 }, + { url = "https://files.pythonhosted.org/packages/98/b8/eb977e28138f9e22a5a789daf608d36e05ed93093ef12a12441030da800a/propcache-0.3.1-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:bd39c92e4c8f6cbf5f08257d6360123af72af9f4da75a690bef50da77362d25f", size = 215727 }, + { url = "https://files.pythonhosted.org/packages/89/2d/5f52d9c579f67b8ee1edd9ec073c91b23cc5b7ff7951a1e449e04ed8fdf3/propcache-0.3.1-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:b0313e8b923b3814d1c4a524c93dfecea5f39fa95601f6a9b1ac96cd66f89ea0", size = 217878 }, + { url = "https://files.pythonhosted.org/packages/7a/fd/5283e5ed8a82b00c7a989b99bb6ea173db1ad750bf0bf8dff08d3f4a4e28/propcache-0.3.1-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:e861ad82892408487be144906a368ddbe2dc6297074ade2d892341b35c59844a", size = 230558 }, + { url = "https://files.pythonhosted.org/packages/90/38/ab17d75938ef7ac87332c588857422ae126b1c76253f0f5b1242032923ca/propcache-0.3.1-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:61014615c1274df8da5991a1e5da85a3ccb00c2d4701ac6f3383afd3ca47ab0a", size = 233754 }, + { url = "https://files.pythonhosted.org/packages/06/5d/3b921b9c60659ae464137508d3b4c2b3f52f592ceb1964aa2533b32fcf0b/propcache-0.3.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:71ebe3fe42656a2328ab08933d420df5f3ab121772eef78f2dc63624157f0ed9", size = 226088 }, + { url = "https://files.pythonhosted.org/packages/54/6e/30a11f4417d9266b5a464ac5a8c5164ddc9dd153dfa77bf57918165eb4ae/propcache-0.3.1-cp311-cp311-win32.whl", hash = "sha256:58aa11f4ca8b60113d4b8e32d37e7e78bd8af4d1a5b5cb4979ed856a45e62005", size = 40859 }, + { url = "https://files.pythonhosted.org/packages/1d/3a/8a68dd867da9ca2ee9dfd361093e9cb08cb0f37e5ddb2276f1b5177d7731/propcache-0.3.1-cp311-cp311-win_amd64.whl", hash = "sha256:9532ea0b26a401264b1365146c440a6d78269ed41f83f23818d4b79497aeabe7", size = 45153 }, + { url = "https://files.pythonhosted.org/packages/41/aa/ca78d9be314d1e15ff517b992bebbed3bdfef5b8919e85bf4940e57b6137/propcache-0.3.1-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:f78eb8422acc93d7b69964012ad7048764bb45a54ba7a39bb9e146c72ea29723", size = 80430 }, + { url = "https://files.pythonhosted.org/packages/1a/d8/f0c17c44d1cda0ad1979af2e593ea290defdde9eaeb89b08abbe02a5e8e1/propcache-0.3.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:89498dd49c2f9a026ee057965cdf8192e5ae070ce7d7a7bd4b66a8e257d0c976", size = 46637 }, + { url = "https://files.pythonhosted.org/packages/ae/bd/c1e37265910752e6e5e8a4c1605d0129e5b7933c3dc3cf1b9b48ed83b364/propcache-0.3.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:09400e98545c998d57d10035ff623266927cb784d13dd2b31fd33b8a5316b85b", size = 46123 }, + { url = "https://files.pythonhosted.org/packages/d4/b0/911eda0865f90c0c7e9f0415d40a5bf681204da5fd7ca089361a64c16b28/propcache-0.3.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:aa8efd8c5adc5a2c9d3b952815ff8f7710cefdcaf5f2c36d26aff51aeca2f12f", size = 243031 }, + { url = "https://files.pythonhosted.org/packages/0a/06/0da53397c76a74271621807265b6eb61fb011451b1ddebf43213df763669/propcache-0.3.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c2fe5c910f6007e716a06d269608d307b4f36e7babee5f36533722660e8c4a70", size = 249100 }, + { url = "https://files.pythonhosted.org/packages/f1/eb/13090e05bf6b963fc1653cdc922133ced467cb4b8dab53158db5a37aa21e/propcache-0.3.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a0ab8cf8cdd2194f8ff979a43ab43049b1df0b37aa64ab7eca04ac14429baeb7", size = 250170 }, + { url = "https://files.pythonhosted.org/packages/3b/4c/f72c9e1022b3b043ec7dc475a0f405d4c3e10b9b1d378a7330fecf0652da/propcache-0.3.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:563f9d8c03ad645597b8d010ef4e9eab359faeb11a0a2ac9f7b4bc8c28ebef25", size = 245000 }, + { url = "https://files.pythonhosted.org/packages/e8/fd/970ca0e22acc829f1adf5de3724085e778c1ad8a75bec010049502cb3a86/propcache-0.3.1-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:fb6e0faf8cb6b4beea5d6ed7b5a578254c6d7df54c36ccd3d8b3eb00d6770277", size = 230262 }, + { url = "https://files.pythonhosted.org/packages/c4/42/817289120c6b9194a44f6c3e6b2c3277c5b70bbad39e7df648f177cc3634/propcache-0.3.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:1c5c7ab7f2bb3f573d1cb921993006ba2d39e8621019dffb1c5bc94cdbae81e8", size = 236772 }, + { url = "https://files.pythonhosted.org/packages/7c/9c/3b3942b302badd589ad6b672da3ca7b660a6c2f505cafd058133ddc73918/propcache-0.3.1-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:050b571b2e96ec942898f8eb46ea4bfbb19bd5502424747e83badc2d4a99a44e", size = 231133 }, + { url = "https://files.pythonhosted.org/packages/98/a1/75f6355f9ad039108ff000dfc2e19962c8dea0430da9a1428e7975cf24b2/propcache-0.3.1-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:e1c4d24b804b3a87e9350f79e2371a705a188d292fd310e663483af6ee6718ee", size = 230741 }, + { url = "https://files.pythonhosted.org/packages/67/0c/3e82563af77d1f8731132166da69fdfd95e71210e31f18edce08a1eb11ea/propcache-0.3.1-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:e4fe2a6d5ce975c117a6bb1e8ccda772d1e7029c1cca1acd209f91d30fa72815", size = 244047 }, + { url = "https://files.pythonhosted.org/packages/f7/50/9fb7cca01532a08c4d5186d7bb2da6c4c587825c0ae134b89b47c7d62628/propcache-0.3.1-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:feccd282de1f6322f56f6845bf1207a537227812f0a9bf5571df52bb418d79d5", size = 246467 }, + { url = "https://files.pythonhosted.org/packages/a9/02/ccbcf3e1c604c16cc525309161d57412c23cf2351523aedbb280eb7c9094/propcache-0.3.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:ec314cde7314d2dd0510c6787326bbffcbdc317ecee6b7401ce218b3099075a7", size = 241022 }, + { url = "https://files.pythonhosted.org/packages/db/19/e777227545e09ca1e77a6e21274ae9ec45de0f589f0ce3eca2a41f366220/propcache-0.3.1-cp312-cp312-win32.whl", hash = "sha256:7d2d5a0028d920738372630870e7d9644ce437142197f8c827194fca404bf03b", size = 40647 }, + { url = "https://files.pythonhosted.org/packages/24/bb/3b1b01da5dd04c77a204c84e538ff11f624e31431cfde7201d9110b092b1/propcache-0.3.1-cp312-cp312-win_amd64.whl", hash = "sha256:88c423efef9d7a59dae0614eaed718449c09a5ac79a5f224a8b9664d603f04a3", size = 44784 }, + { url = "https://files.pythonhosted.org/packages/58/60/f645cc8b570f99be3cf46714170c2de4b4c9d6b827b912811eff1eb8a412/propcache-0.3.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:f1528ec4374617a7a753f90f20e2f551121bb558fcb35926f99e3c42367164b8", size = 77865 }, + { url = "https://files.pythonhosted.org/packages/6f/d4/c1adbf3901537582e65cf90fd9c26fde1298fde5a2c593f987112c0d0798/propcache-0.3.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:dc1915ec523b3b494933b5424980831b636fe483d7d543f7afb7b3bf00f0c10f", size = 45452 }, + { url = "https://files.pythonhosted.org/packages/d1/b5/fe752b2e63f49f727c6c1c224175d21b7d1727ce1d4873ef1c24c9216830/propcache-0.3.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:a110205022d077da24e60b3df8bcee73971be9575dec5573dd17ae5d81751111", size = 44800 }, + { url = "https://files.pythonhosted.org/packages/62/37/fc357e345bc1971e21f76597028b059c3d795c5ca7690d7a8d9a03c9708a/propcache-0.3.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d249609e547c04d190e820d0d4c8ca03ed4582bcf8e4e160a6969ddfb57b62e5", size = 225804 }, + { url = "https://files.pythonhosted.org/packages/0d/f1/16e12c33e3dbe7f8b737809bad05719cff1dccb8df4dafbcff5575002c0e/propcache-0.3.1-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5ced33d827625d0a589e831126ccb4f5c29dfdf6766cac441d23995a65825dcb", size = 230650 }, + { url = "https://files.pythonhosted.org/packages/3e/a2/018b9f2ed876bf5091e60153f727e8f9073d97573f790ff7cdf6bc1d1fb8/propcache-0.3.1-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:4114c4ada8f3181af20808bedb250da6bae56660e4b8dfd9cd95d4549c0962f7", size = 234235 }, + { url = "https://files.pythonhosted.org/packages/45/5f/3faee66fc930dfb5da509e34c6ac7128870631c0e3582987fad161fcb4b1/propcache-0.3.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:975af16f406ce48f1333ec5e912fe11064605d5c5b3f6746969077cc3adeb120", size = 228249 }, + { url = "https://files.pythonhosted.org/packages/62/1e/a0d5ebda5da7ff34d2f5259a3e171a94be83c41eb1e7cd21a2105a84a02e/propcache-0.3.1-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a34aa3a1abc50740be6ac0ab9d594e274f59960d3ad253cd318af76b996dd654", size = 214964 }, + { url = "https://files.pythonhosted.org/packages/db/a0/d72da3f61ceab126e9be1f3bc7844b4e98c6e61c985097474668e7e52152/propcache-0.3.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:9cec3239c85ed15bfaded997773fdad9fb5662b0a7cbc854a43f291eb183179e", size = 222501 }, + { url = "https://files.pythonhosted.org/packages/18/6d/a008e07ad7b905011253adbbd97e5b5375c33f0b961355ca0a30377504ac/propcache-0.3.1-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:05543250deac8e61084234d5fc54f8ebd254e8f2b39a16b1dce48904f45b744b", size = 217917 }, + { url = "https://files.pythonhosted.org/packages/98/37/02c9343ffe59e590e0e56dc5c97d0da2b8b19fa747ebacf158310f97a79a/propcache-0.3.1-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:5cb5918253912e088edbf023788de539219718d3b10aef334476b62d2b53de53", size = 217089 }, + { url = "https://files.pythonhosted.org/packages/53/1b/d3406629a2c8a5666d4674c50f757a77be119b113eedd47b0375afdf1b42/propcache-0.3.1-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:f3bbecd2f34d0e6d3c543fdb3b15d6b60dd69970c2b4c822379e5ec8f6f621d5", size = 228102 }, + { url = "https://files.pythonhosted.org/packages/cd/a7/3664756cf50ce739e5f3abd48febc0be1a713b1f389a502ca819791a6b69/propcache-0.3.1-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:aca63103895c7d960a5b9b044a83f544b233c95e0dcff114389d64d762017af7", size = 230122 }, + { url = "https://files.pythonhosted.org/packages/35/36/0bbabaacdcc26dac4f8139625e930f4311864251276033a52fd52ff2a274/propcache-0.3.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:5a0a9898fdb99bf11786265468571e628ba60af80dc3f6eb89a3545540c6b0ef", size = 226818 }, + { url = "https://files.pythonhosted.org/packages/cc/27/4e0ef21084b53bd35d4dae1634b6d0bad35e9c58ed4f032511acca9d4d26/propcache-0.3.1-cp313-cp313-win32.whl", hash = "sha256:3a02a28095b5e63128bcae98eb59025924f121f048a62393db682f049bf4ac24", size = 40112 }, + { url = "https://files.pythonhosted.org/packages/a6/2c/a54614d61895ba6dd7ac8f107e2b2a0347259ab29cbf2ecc7b94fa38c4dc/propcache-0.3.1-cp313-cp313-win_amd64.whl", hash = "sha256:813fbb8b6aea2fc9659815e585e548fe706d6f663fa73dff59a1677d4595a037", size = 44034 }, + { url = "https://files.pythonhosted.org/packages/5a/a8/0a4fd2f664fc6acc66438370905124ce62e84e2e860f2557015ee4a61c7e/propcache-0.3.1-cp313-cp313t-macosx_10_13_universal2.whl", hash = "sha256:a444192f20f5ce8a5e52761a031b90f5ea6288b1eef42ad4c7e64fef33540b8f", size = 82613 }, + { url = "https://files.pythonhosted.org/packages/4d/e5/5ef30eb2cd81576256d7b6caaa0ce33cd1d2c2c92c8903cccb1af1a4ff2f/propcache-0.3.1-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:0fbe94666e62ebe36cd652f5fc012abfbc2342de99b523f8267a678e4dfdee3c", size = 47763 }, + { url = "https://files.pythonhosted.org/packages/87/9a/87091ceb048efeba4d28e903c0b15bcc84b7c0bf27dc0261e62335d9b7b8/propcache-0.3.1-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:f011f104db880f4e2166bcdcf7f58250f7a465bc6b068dc84c824a3d4a5c94dc", size = 47175 }, + { url = "https://files.pythonhosted.org/packages/3e/2f/854e653c96ad1161f96194c6678a41bbb38c7947d17768e8811a77635a08/propcache-0.3.1-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3e584b6d388aeb0001d6d5c2bd86b26304adde6d9bb9bfa9c4889805021b96de", size = 292265 }, + { url = "https://files.pythonhosted.org/packages/40/8d/090955e13ed06bc3496ba4a9fb26c62e209ac41973cb0d6222de20c6868f/propcache-0.3.1-cp313-cp313t-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8a17583515a04358b034e241f952f1715243482fc2c2945fd99a1b03a0bd77d6", size = 294412 }, + { url = "https://files.pythonhosted.org/packages/39/e6/d51601342e53cc7582449e6a3c14a0479fab2f0750c1f4d22302e34219c6/propcache-0.3.1-cp313-cp313t-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5aed8d8308215089c0734a2af4f2e95eeb360660184ad3912686c181e500b2e7", size = 294290 }, + { url = "https://files.pythonhosted.org/packages/3b/4d/be5f1a90abc1881884aa5878989a1acdafd379a91d9c7e5e12cef37ec0d7/propcache-0.3.1-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6d8e309ff9a0503ef70dc9a0ebd3e69cf7b3894c9ae2ae81fc10943c37762458", size = 282926 }, + { url = "https://files.pythonhosted.org/packages/57/2b/8f61b998c7ea93a2b7eca79e53f3e903db1787fca9373af9e2cf8dc22f9d/propcache-0.3.1-cp313-cp313t-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b655032b202028a582d27aeedc2e813299f82cb232f969f87a4fde491a233f11", size = 267808 }, + { url = "https://files.pythonhosted.org/packages/11/1c/311326c3dfce59c58a6098388ba984b0e5fb0381ef2279ec458ef99bd547/propcache-0.3.1-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:9f64d91b751df77931336b5ff7bafbe8845c5770b06630e27acd5dbb71e1931c", size = 290916 }, + { url = "https://files.pythonhosted.org/packages/4b/74/91939924b0385e54dc48eb2e4edd1e4903ffd053cf1916ebc5347ac227f7/propcache-0.3.1-cp313-cp313t-musllinux_1_2_armv7l.whl", hash = "sha256:19a06db789a4bd896ee91ebc50d059e23b3639c25d58eb35be3ca1cbe967c3bf", size = 262661 }, + { url = "https://files.pythonhosted.org/packages/c2/d7/e6079af45136ad325c5337f5dd9ef97ab5dc349e0ff362fe5c5db95e2454/propcache-0.3.1-cp313-cp313t-musllinux_1_2_i686.whl", hash = "sha256:bef100c88d8692864651b5f98e871fb090bd65c8a41a1cb0ff2322db39c96c27", size = 264384 }, + { url = "https://files.pythonhosted.org/packages/b7/d5/ba91702207ac61ae6f1c2da81c5d0d6bf6ce89e08a2b4d44e411c0bbe867/propcache-0.3.1-cp313-cp313t-musllinux_1_2_ppc64le.whl", hash = "sha256:87380fb1f3089d2a0b8b00f006ed12bd41bd858fabfa7330c954c70f50ed8757", size = 291420 }, + { url = "https://files.pythonhosted.org/packages/58/70/2117780ed7edcd7ba6b8134cb7802aada90b894a9810ec56b7bb6018bee7/propcache-0.3.1-cp313-cp313t-musllinux_1_2_s390x.whl", hash = "sha256:e474fc718e73ba5ec5180358aa07f6aded0ff5f2abe700e3115c37d75c947e18", size = 290880 }, + { url = "https://files.pythonhosted.org/packages/4a/1f/ecd9ce27710021ae623631c0146719280a929d895a095f6d85efb6a0be2e/propcache-0.3.1-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:17d1c688a443355234f3c031349da69444be052613483f3e4158eef751abcd8a", size = 287407 }, + { url = "https://files.pythonhosted.org/packages/3e/66/2e90547d6b60180fb29e23dc87bd8c116517d4255240ec6d3f7dc23d1926/propcache-0.3.1-cp313-cp313t-win32.whl", hash = "sha256:359e81a949a7619802eb601d66d37072b79b79c2505e6d3fd8b945538411400d", size = 42573 }, + { url = "https://files.pythonhosted.org/packages/cb/8f/50ad8599399d1861b4d2b6b45271f0ef6af1b09b0a2386a46dbaf19c9535/propcache-0.3.1-cp313-cp313t-win_amd64.whl", hash = "sha256:e7fb9a84c9abbf2b2683fa3e7b0d7da4d8ecf139a1c635732a8bda29c5214b0e", size = 46757 }, + { url = "https://files.pythonhosted.org/packages/aa/e1/4a782cdc7ebc42dfb44224dabf93b481395a0b6cbc9f0149785edbbab19c/propcache-0.3.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:ed5f6d2edbf349bd8d630e81f474d33d6ae5d07760c44d33cd808e2f5c8f4ae6", size = 81368 }, + { url = "https://files.pythonhosted.org/packages/18/c6/9a39b2646a71321815d8d616e890851af9fb327af7d1b9fdce7d2d8377ca/propcache-0.3.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:668ddddc9f3075af019f784456267eb504cb77c2c4bd46cc8402d723b4d200bf", size = 47037 }, + { url = "https://files.pythonhosted.org/packages/f3/e2/88ad1c4c42861dd09b45924e468c42a1beb2c5267cb960b7a9f6af67dd04/propcache-0.3.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:0c86e7ceea56376216eba345aa1fc6a8a6b27ac236181f840d1d7e6a1ea9ba5c", size = 46462 }, + { url = "https://files.pythonhosted.org/packages/ae/7e/3e3b36854e96be2e881bc6e87293d59c74dd734dd038dd4981474be44e26/propcache-0.3.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:83be47aa4e35b87c106fc0c84c0fc069d3f9b9b06d3c494cd404ec6747544894", size = 209214 }, + { url = "https://files.pythonhosted.org/packages/11/1a/ac0f757cc0babdc8217056fca85150066cf43bf11db9651e6b7d8e0646d6/propcache-0.3.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:27c6ac6aa9fc7bc662f594ef380707494cb42c22786a558d95fcdedb9aa5d035", size = 224702 }, + { url = "https://files.pythonhosted.org/packages/92/0a/0cf77d0e984b7058019ffa5385b3efd6962cbd5340a8f278ae103032863a/propcache-0.3.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:64a956dff37080b352c1c40b2966b09defb014347043e740d420ca1eb7c9b908", size = 223085 }, + { url = "https://files.pythonhosted.org/packages/05/fc/cb52a0caf803caff9b95b0a99e7c9c87f15b7e34ba0feebfd2572b49013d/propcache-0.3.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:82de5da8c8893056603ac2d6a89eb8b4df49abf1a7c19d536984c8dd63f481d5", size = 209613 }, + { url = "https://files.pythonhosted.org/packages/e5/fc/b1d1fdffbe1e0278ab535f8d21fc6b030889417714a545755bdd5ebe9bb0/propcache-0.3.1-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0c3c3a203c375b08fd06a20da3cf7aac293b834b6f4f4db71190e8422750cca5", size = 199931 }, + { url = "https://files.pythonhosted.org/packages/23/a9/2a2f8d93d8f526c35dd8dbbc4a1ac22a106712cd821e15e2a6530aea8931/propcache-0.3.1-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:b303b194c2e6f171cfddf8b8ba30baefccf03d36a4d9cab7fd0bb68ba476a3d7", size = 208937 }, + { url = "https://files.pythonhosted.org/packages/ef/71/5247a264b95e8d4ba86757cf9ad6a523d764bd4579a2d80007a2d4d2b0ad/propcache-0.3.1-cp39-cp39-musllinux_1_2_armv7l.whl", hash = "sha256:916cd229b0150129d645ec51614d38129ee74c03293a9f3f17537be0029a9641", size = 202577 }, + { url = "https://files.pythonhosted.org/packages/6f/4e/c8ec771731f1b1e7d07bd8875f1d13c1564b5d60f7483624d021eaef5687/propcache-0.3.1-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:a461959ead5b38e2581998700b26346b78cd98540b5524796c175722f18b0294", size = 204669 }, + { url = "https://files.pythonhosted.org/packages/c5/b8/bdfcb1170a7b8504226064d7c0b4deb61acbcc6bb2e754ee25fb36c1b72a/propcache-0.3.1-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:069e7212890b0bcf9b2be0a03afb0c2d5161d91e1bf51569a64f629acc7defbf", size = 214334 }, + { url = "https://files.pythonhosted.org/packages/72/c6/fdb9e8ba161a4e12c75a7415cb99314cad195d3b8ae9d770783cec54001e/propcache-0.3.1-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:ef2e4e91fb3945769e14ce82ed53007195e616a63aa43b40fb7ebaaf907c8d4c", size = 218052 }, + { url = "https://files.pythonhosted.org/packages/67/3f/0dd87220f61598b61b590a8b3562142ae475a9c0f694ee32bf97e4e41d44/propcache-0.3.1-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:8638f99dca15b9dff328fb6273e09f03d1c50d9b6512f3b65a4154588a7595fe", size = 210852 }, + { url = "https://files.pythonhosted.org/packages/7b/4e/e332164372af66992c07b470448beb7e36ce7dba6a06c6c2b6131f112e74/propcache-0.3.1-cp39-cp39-win32.whl", hash = "sha256:6f173bbfe976105aaa890b712d1759de339d8a7cef2fc0a1714cc1a1e1c47f64", size = 41481 }, + { url = "https://files.pythonhosted.org/packages/61/73/d64abb7bb5d18880ecfac152247c0f1a5807256ea21e4737ce3019afffeb/propcache-0.3.1-cp39-cp39-win_amd64.whl", hash = "sha256:603f1fe4144420374f1a69b907494c3acbc867a581c2d49d4175b0de7cc64566", size = 45720 }, + { url = "https://files.pythonhosted.org/packages/b8/d3/c3cb8f1d6ae3b37f83e1de806713a9b3642c5895f0215a62e1a4bd6e5e34/propcache-0.3.1-py3-none-any.whl", hash = "sha256:9a8ecf38de50a7f518c21568c80f985e776397b902f1ce0b01f799aba1608b40", size = 12376 }, +] + [[package]] name = "pycparser" version = "2.22" @@ -1239,113 +1750,126 @@ wheels = [ [[package]] name = "pydantic" -version = "2.10.6" +version = "2.11.3" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "annotated-types" }, { name = "pydantic-core" }, { name = "typing-extensions" }, + { name = "typing-inspection" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/b7/ae/d5220c5c52b158b1de7ca89fc5edb72f304a70a4c540c84c8844bf4008de/pydantic-2.10.6.tar.gz", hash = "sha256:ca5daa827cce33de7a42be142548b0096bf05a7e7b365aebfa5f8eeec7128236", size = 761681 } +sdist = { url = "https://files.pythonhosted.org/packages/10/2e/ca897f093ee6c5f3b0bee123ee4465c50e75431c3d5b6a3b44a47134e891/pydantic-2.11.3.tar.gz", hash = "sha256:7471657138c16adad9322fe3070c0116dd6c3ad8d649300e3cbdfe91f4db4ec3", size = 785513 } wheels = [ - { url = "https://files.pythonhosted.org/packages/f4/3c/8cc1cc84deffa6e25d2d0c688ebb80635dfdbf1dbea3e30c541c8cf4d860/pydantic-2.10.6-py3-none-any.whl", hash = "sha256:427d664bf0b8a2b34ff5dd0f5a18df00591adcee7198fbd71981054cef37b584", size = 431696 }, + { url = "https://files.pythonhosted.org/packages/b0/1d/407b29780a289868ed696d1616f4aad49d6388e5a77f567dcd2629dcd7b8/pydantic-2.11.3-py3-none-any.whl", hash = "sha256:a082753436a07f9ba1289c6ffa01cd93db3548776088aa917cc43b63f68fa60f", size = 443591 }, ] [[package]] name = "pydantic-core" -version = "2.27.2" +version = "2.33.1" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "typing-extensions" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/fc/01/f3e5ac5e7c25833db5eb555f7b7ab24cd6f8c322d3a3ad2d67a952dc0abc/pydantic_core-2.27.2.tar.gz", hash = "sha256:eb026e5a4c1fee05726072337ff51d1efb6f59090b7da90d30ea58625b1ffb39", size = 413443 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/3a/bc/fed5f74b5d802cf9a03e83f60f18864e90e3aed7223adaca5ffb7a8d8d64/pydantic_core-2.27.2-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:2d367ca20b2f14095a8f4fa1210f5a7b78b8a20009ecced6b12818f455b1e9fa", size = 1895938 }, - { url = "https://files.pythonhosted.org/packages/71/2a/185aff24ce844e39abb8dd680f4e959f0006944f4a8a0ea372d9f9ae2e53/pydantic_core-2.27.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:491a2b73db93fab69731eaee494f320faa4e093dbed776be1a829c2eb222c34c", size = 1815684 }, - { url = "https://files.pythonhosted.org/packages/c3/43/fafabd3d94d159d4f1ed62e383e264f146a17dd4d48453319fd782e7979e/pydantic_core-2.27.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7969e133a6f183be60e9f6f56bfae753585680f3b7307a8e555a948d443cc05a", size = 1829169 }, - { url = "https://files.pythonhosted.org/packages/a2/d1/f2dfe1a2a637ce6800b799aa086d079998959f6f1215eb4497966efd2274/pydantic_core-2.27.2-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:3de9961f2a346257caf0aa508a4da705467f53778e9ef6fe744c038119737ef5", size = 1867227 }, - { url = "https://files.pythonhosted.org/packages/7d/39/e06fcbcc1c785daa3160ccf6c1c38fea31f5754b756e34b65f74e99780b5/pydantic_core-2.27.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e2bb4d3e5873c37bb3dd58714d4cd0b0e6238cebc4177ac8fe878f8b3aa8e74c", size = 2037695 }, - { url = "https://files.pythonhosted.org/packages/7a/67/61291ee98e07f0650eb756d44998214231f50751ba7e13f4f325d95249ab/pydantic_core-2.27.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:280d219beebb0752699480fe8f1dc61ab6615c2046d76b7ab7ee38858de0a4e7", size = 2741662 }, - { url = "https://files.pythonhosted.org/packages/32/90/3b15e31b88ca39e9e626630b4c4a1f5a0dfd09076366f4219429e6786076/pydantic_core-2.27.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:47956ae78b6422cbd46f772f1746799cbb862de838fd8d1fbd34a82e05b0983a", size = 1993370 }, - { url = "https://files.pythonhosted.org/packages/ff/83/c06d333ee3a67e2e13e07794995c1535565132940715931c1c43bfc85b11/pydantic_core-2.27.2-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:14d4a5c49d2f009d62a2a7140d3064f686d17a5d1a268bc641954ba181880236", size = 1996813 }, - { url = "https://files.pythonhosted.org/packages/7c/f7/89be1c8deb6e22618a74f0ca0d933fdcb8baa254753b26b25ad3acff8f74/pydantic_core-2.27.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:337b443af21d488716f8d0b6164de833e788aa6bd7e3a39c005febc1284f4962", size = 2005287 }, - { url = "https://files.pythonhosted.org/packages/b7/7d/8eb3e23206c00ef7feee17b83a4ffa0a623eb1a9d382e56e4aa46fd15ff2/pydantic_core-2.27.2-cp310-cp310-musllinux_1_1_armv7l.whl", hash = "sha256:03d0f86ea3184a12f41a2d23f7ccb79cdb5a18e06993f8a45baa8dfec746f0e9", size = 2128414 }, - { url = "https://files.pythonhosted.org/packages/4e/99/fe80f3ff8dd71a3ea15763878d464476e6cb0a2db95ff1c5c554133b6b83/pydantic_core-2.27.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:7041c36f5680c6e0f08d922aed302e98b3745d97fe1589db0a3eebf6624523af", size = 2155301 }, - { url = "https://files.pythonhosted.org/packages/2b/a3/e50460b9a5789ca1451b70d4f52546fa9e2b420ba3bfa6100105c0559238/pydantic_core-2.27.2-cp310-cp310-win32.whl", hash = "sha256:50a68f3e3819077be2c98110c1f9dcb3817e93f267ba80a2c05bb4f8799e2ff4", size = 1816685 }, - { url = "https://files.pythonhosted.org/packages/57/4c/a8838731cb0f2c2a39d3535376466de6049034d7b239c0202a64aaa05533/pydantic_core-2.27.2-cp310-cp310-win_amd64.whl", hash = "sha256:e0fd26b16394ead34a424eecf8a31a1f5137094cabe84a1bcb10fa6ba39d3d31", size = 1982876 }, - { url = "https://files.pythonhosted.org/packages/c2/89/f3450af9d09d44eea1f2c369f49e8f181d742f28220f88cc4dfaae91ea6e/pydantic_core-2.27.2-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:8e10c99ef58cfdf2a66fc15d66b16c4a04f62bca39db589ae8cba08bc55331bc", size = 1893421 }, - { url = "https://files.pythonhosted.org/packages/9e/e3/71fe85af2021f3f386da42d291412e5baf6ce7716bd7101ea49c810eda90/pydantic_core-2.27.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:26f32e0adf166a84d0cb63be85c562ca8a6fa8de28e5f0d92250c6b7e9e2aff7", size = 1814998 }, - { url = "https://files.pythonhosted.org/packages/a6/3c/724039e0d848fd69dbf5806894e26479577316c6f0f112bacaf67aa889ac/pydantic_core-2.27.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8c19d1ea0673cd13cc2f872f6c9ab42acc4e4f492a7ca9d3795ce2b112dd7e15", size = 1826167 }, - { url = "https://files.pythonhosted.org/packages/2b/5b/1b29e8c1fb5f3199a9a57c1452004ff39f494bbe9bdbe9a81e18172e40d3/pydantic_core-2.27.2-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:5e68c4446fe0810e959cdff46ab0a41ce2f2c86d227d96dc3847af0ba7def306", size = 1865071 }, - { url = "https://files.pythonhosted.org/packages/89/6c/3985203863d76bb7d7266e36970d7e3b6385148c18a68cc8915fd8c84d57/pydantic_core-2.27.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d9640b0059ff4f14d1f37321b94061c6db164fbe49b334b31643e0528d100d99", size = 2036244 }, - { url = "https://files.pythonhosted.org/packages/0e/41/f15316858a246b5d723f7d7f599f79e37493b2e84bfc789e58d88c209f8a/pydantic_core-2.27.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:40d02e7d45c9f8af700f3452f329ead92da4c5f4317ca9b896de7ce7199ea459", size = 2737470 }, - { url = "https://files.pythonhosted.org/packages/a8/7c/b860618c25678bbd6d1d99dbdfdf0510ccb50790099b963ff78a124b754f/pydantic_core-2.27.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1c1fd185014191700554795c99b347d64f2bb637966c4cfc16998a0ca700d048", size = 1992291 }, - { url = "https://files.pythonhosted.org/packages/bf/73/42c3742a391eccbeab39f15213ecda3104ae8682ba3c0c28069fbcb8c10d/pydantic_core-2.27.2-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:d81d2068e1c1228a565af076598f9e7451712700b673de8f502f0334f281387d", size = 1994613 }, - { url = "https://files.pythonhosted.org/packages/94/7a/941e89096d1175d56f59340f3a8ebaf20762fef222c298ea96d36a6328c5/pydantic_core-2.27.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:1a4207639fb02ec2dbb76227d7c751a20b1a6b4bc52850568e52260cae64ca3b", size = 2002355 }, - { url = "https://files.pythonhosted.org/packages/6e/95/2359937a73d49e336a5a19848713555605d4d8d6940c3ec6c6c0ca4dcf25/pydantic_core-2.27.2-cp311-cp311-musllinux_1_1_armv7l.whl", hash = "sha256:3de3ce3c9ddc8bbd88f6e0e304dea0e66d843ec9de1b0042b0911c1663ffd474", size = 2126661 }, - { url = "https://files.pythonhosted.org/packages/2b/4c/ca02b7bdb6012a1adef21a50625b14f43ed4d11f1fc237f9d7490aa5078c/pydantic_core-2.27.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:30c5f68ded0c36466acede341551106821043e9afaad516adfb6e8fa80a4e6a6", size = 2153261 }, - { url = "https://files.pythonhosted.org/packages/72/9d/a241db83f973049a1092a079272ffe2e3e82e98561ef6214ab53fe53b1c7/pydantic_core-2.27.2-cp311-cp311-win32.whl", hash = "sha256:c70c26d2c99f78b125a3459f8afe1aed4d9687c24fd677c6a4436bc042e50d6c", size = 1812361 }, - { url = "https://files.pythonhosted.org/packages/e8/ef/013f07248041b74abd48a385e2110aa3a9bbfef0fbd97d4e6d07d2f5b89a/pydantic_core-2.27.2-cp311-cp311-win_amd64.whl", hash = "sha256:08e125dbdc505fa69ca7d9c499639ab6407cfa909214d500897d02afb816e7cc", size = 1982484 }, - { url = "https://files.pythonhosted.org/packages/10/1c/16b3a3e3398fd29dca77cea0a1d998d6bde3902fa2706985191e2313cc76/pydantic_core-2.27.2-cp311-cp311-win_arm64.whl", hash = "sha256:26f0d68d4b235a2bae0c3fc585c585b4ecc51382db0e3ba402a22cbc440915e4", size = 1867102 }, - { url = "https://files.pythonhosted.org/packages/d6/74/51c8a5482ca447871c93e142d9d4a92ead74de6c8dc5e66733e22c9bba89/pydantic_core-2.27.2-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:9e0c8cfefa0ef83b4da9588448b6d8d2a2bf1a53c3f1ae5fca39eb3061e2f0b0", size = 1893127 }, - { url = "https://files.pythonhosted.org/packages/d3/f3/c97e80721735868313c58b89d2de85fa80fe8dfeeed84dc51598b92a135e/pydantic_core-2.27.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:83097677b8e3bd7eaa6775720ec8e0405f1575015a463285a92bfdfe254529ef", size = 1811340 }, - { url = "https://files.pythonhosted.org/packages/9e/91/840ec1375e686dbae1bd80a9e46c26a1e0083e1186abc610efa3d9a36180/pydantic_core-2.27.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:172fce187655fece0c90d90a678424b013f8fbb0ca8b036ac266749c09438cb7", size = 1822900 }, - { url = "https://files.pythonhosted.org/packages/f6/31/4240bc96025035500c18adc149aa6ffdf1a0062a4b525c932065ceb4d868/pydantic_core-2.27.2-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:519f29f5213271eeeeb3093f662ba2fd512b91c5f188f3bb7b27bc5973816934", size = 1869177 }, - { url = "https://files.pythonhosted.org/packages/fa/20/02fbaadb7808be578317015c462655c317a77a7c8f0ef274bc016a784c54/pydantic_core-2.27.2-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:05e3a55d124407fffba0dd6b0c0cd056d10e983ceb4e5dbd10dda135c31071d6", size = 2038046 }, - { url = "https://files.pythonhosted.org/packages/06/86/7f306b904e6c9eccf0668248b3f272090e49c275bc488a7b88b0823444a4/pydantic_core-2.27.2-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9c3ed807c7b91de05e63930188f19e921d1fe90de6b4f5cd43ee7fcc3525cb8c", size = 2685386 }, - { url = "https://files.pythonhosted.org/packages/8d/f0/49129b27c43396581a635d8710dae54a791b17dfc50c70164866bbf865e3/pydantic_core-2.27.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6fb4aadc0b9a0c063206846d603b92030eb6f03069151a625667f982887153e2", size = 1997060 }, - { url = "https://files.pythonhosted.org/packages/0d/0f/943b4af7cd416c477fd40b187036c4f89b416a33d3cc0ab7b82708a667aa/pydantic_core-2.27.2-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:28ccb213807e037460326424ceb8b5245acb88f32f3d2777427476e1b32c48c4", size = 2004870 }, - { url = "https://files.pythonhosted.org/packages/35/40/aea70b5b1a63911c53a4c8117c0a828d6790483f858041f47bab0b779f44/pydantic_core-2.27.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:de3cd1899e2c279b140adde9357c4495ed9d47131b4a4eaff9052f23398076b3", size = 1999822 }, - { url = "https://files.pythonhosted.org/packages/f2/b3/807b94fd337d58effc5498fd1a7a4d9d59af4133e83e32ae39a96fddec9d/pydantic_core-2.27.2-cp312-cp312-musllinux_1_1_armv7l.whl", hash = "sha256:220f892729375e2d736b97d0e51466252ad84c51857d4d15f5e9692f9ef12be4", size = 2130364 }, - { url = "https://files.pythonhosted.org/packages/fc/df/791c827cd4ee6efd59248dca9369fb35e80a9484462c33c6649a8d02b565/pydantic_core-2.27.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:a0fcd29cd6b4e74fe8ddd2c90330fd8edf2e30cb52acda47f06dd615ae72da57", size = 2158303 }, - { url = "https://files.pythonhosted.org/packages/9b/67/4e197c300976af185b7cef4c02203e175fb127e414125916bf1128b639a9/pydantic_core-2.27.2-cp312-cp312-win32.whl", hash = "sha256:1e2cb691ed9834cd6a8be61228471d0a503731abfb42f82458ff27be7b2186fc", size = 1834064 }, - { url = "https://files.pythonhosted.org/packages/1f/ea/cd7209a889163b8dcca139fe32b9687dd05249161a3edda62860430457a5/pydantic_core-2.27.2-cp312-cp312-win_amd64.whl", hash = "sha256:cc3f1a99a4f4f9dd1de4fe0312c114e740b5ddead65bb4102884b384c15d8bc9", size = 1989046 }, - { url = "https://files.pythonhosted.org/packages/bc/49/c54baab2f4658c26ac633d798dab66b4c3a9bbf47cff5284e9c182f4137a/pydantic_core-2.27.2-cp312-cp312-win_arm64.whl", hash = "sha256:3911ac9284cd8a1792d3cb26a2da18f3ca26c6908cc434a18f730dc0db7bfa3b", size = 1885092 }, - { url = "https://files.pythonhosted.org/packages/41/b1/9bc383f48f8002f99104e3acff6cba1231b29ef76cfa45d1506a5cad1f84/pydantic_core-2.27.2-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:7d14bd329640e63852364c306f4d23eb744e0f8193148d4044dd3dacdaacbd8b", size = 1892709 }, - { url = "https://files.pythonhosted.org/packages/10/6c/e62b8657b834f3eb2961b49ec8e301eb99946245e70bf42c8817350cbefc/pydantic_core-2.27.2-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:82f91663004eb8ed30ff478d77c4d1179b3563df6cdb15c0817cd1cdaf34d154", size = 1811273 }, - { url = "https://files.pythonhosted.org/packages/ba/15/52cfe49c8c986e081b863b102d6b859d9defc63446b642ccbbb3742bf371/pydantic_core-2.27.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:71b24c7d61131bb83df10cc7e687433609963a944ccf45190cfc21e0887b08c9", size = 1823027 }, - { url = "https://files.pythonhosted.org/packages/b1/1c/b6f402cfc18ec0024120602bdbcebc7bdd5b856528c013bd4d13865ca473/pydantic_core-2.27.2-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:fa8e459d4954f608fa26116118bb67f56b93b209c39b008277ace29937453dc9", size = 1868888 }, - { url = "https://files.pythonhosted.org/packages/bd/7b/8cb75b66ac37bc2975a3b7de99f3c6f355fcc4d89820b61dffa8f1e81677/pydantic_core-2.27.2-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ce8918cbebc8da707ba805b7fd0b382816858728ae7fe19a942080c24e5b7cd1", size = 2037738 }, - { url = "https://files.pythonhosted.org/packages/c8/f1/786d8fe78970a06f61df22cba58e365ce304bf9b9f46cc71c8c424e0c334/pydantic_core-2.27.2-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:eda3f5c2a021bbc5d976107bb302e0131351c2ba54343f8a496dc8783d3d3a6a", size = 2685138 }, - { url = "https://files.pythonhosted.org/packages/a6/74/d12b2cd841d8724dc8ffb13fc5cef86566a53ed358103150209ecd5d1999/pydantic_core-2.27.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bd8086fa684c4775c27f03f062cbb9eaa6e17f064307e86b21b9e0abc9c0f02e", size = 1997025 }, - { url = "https://files.pythonhosted.org/packages/a0/6e/940bcd631bc4d9a06c9539b51f070b66e8f370ed0933f392db6ff350d873/pydantic_core-2.27.2-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:8d9b3388db186ba0c099a6d20f0604a44eabdeef1777ddd94786cdae158729e4", size = 2004633 }, - { url = "https://files.pythonhosted.org/packages/50/cc/a46b34f1708d82498c227d5d80ce615b2dd502ddcfd8376fc14a36655af1/pydantic_core-2.27.2-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:7a66efda2387de898c8f38c0cf7f14fca0b51a8ef0b24bfea5849f1b3c95af27", size = 1999404 }, - { url = "https://files.pythonhosted.org/packages/ca/2d/c365cfa930ed23bc58c41463bae347d1005537dc8db79e998af8ba28d35e/pydantic_core-2.27.2-cp313-cp313-musllinux_1_1_armv7l.whl", hash = "sha256:18a101c168e4e092ab40dbc2503bdc0f62010e95d292b27827871dc85450d7ee", size = 2130130 }, - { url = "https://files.pythonhosted.org/packages/f4/d7/eb64d015c350b7cdb371145b54d96c919d4db516817f31cd1c650cae3b21/pydantic_core-2.27.2-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:ba5dd002f88b78a4215ed2f8ddbdf85e8513382820ba15ad5ad8955ce0ca19a1", size = 2157946 }, - { url = "https://files.pythonhosted.org/packages/a4/99/bddde3ddde76c03b65dfd5a66ab436c4e58ffc42927d4ff1198ffbf96f5f/pydantic_core-2.27.2-cp313-cp313-win32.whl", hash = "sha256:1ebaf1d0481914d004a573394f4be3a7616334be70261007e47c2a6fe7e50130", size = 1834387 }, - { url = "https://files.pythonhosted.org/packages/71/47/82b5e846e01b26ac6f1893d3c5f9f3a2eb6ba79be26eef0b759b4fe72946/pydantic_core-2.27.2-cp313-cp313-win_amd64.whl", hash = "sha256:953101387ecf2f5652883208769a79e48db18c6df442568a0b5ccd8c2723abee", size = 1990453 }, - { url = "https://files.pythonhosted.org/packages/51/b2/b2b50d5ecf21acf870190ae5d093602d95f66c9c31f9d5de6062eb329ad1/pydantic_core-2.27.2-cp313-cp313-win_arm64.whl", hash = "sha256:ac4dbfd1691affb8f48c2c13241a2e3b60ff23247cbcf981759c768b6633cf8b", size = 1885186 }, - { url = "https://files.pythonhosted.org/packages/27/97/3aef1ddb65c5ccd6eda9050036c956ff6ecbfe66cb7eb40f280f121a5bb0/pydantic_core-2.27.2-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:c10eb4f1659290b523af58fa7cffb452a61ad6ae5613404519aee4bfbf1df993", size = 1896475 }, - { url = "https://files.pythonhosted.org/packages/ad/d3/5668da70e373c9904ed2f372cb52c0b996426f302e0dee2e65634c92007d/pydantic_core-2.27.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:ef592d4bad47296fb11f96cd7dc898b92e795032b4894dfb4076cfccd43a9308", size = 1772279 }, - { url = "https://files.pythonhosted.org/packages/8a/9e/e44b8cb0edf04a2f0a1f6425a65ee089c1d6f9c4c2dcab0209127b6fdfc2/pydantic_core-2.27.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c61709a844acc6bf0b7dce7daae75195a10aac96a596ea1b776996414791ede4", size = 1829112 }, - { url = "https://files.pythonhosted.org/packages/1c/90/1160d7ac700102effe11616e8119e268770f2a2aa5afb935f3ee6832987d/pydantic_core-2.27.2-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:42c5f762659e47fdb7b16956c71598292f60a03aa92f8b6351504359dbdba6cf", size = 1866780 }, - { url = "https://files.pythonhosted.org/packages/ee/33/13983426df09a36d22c15980008f8d9c77674fc319351813b5a2739b70f3/pydantic_core-2.27.2-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4c9775e339e42e79ec99c441d9730fccf07414af63eac2f0e48e08fd38a64d76", size = 2037943 }, - { url = "https://files.pythonhosted.org/packages/01/d7/ced164e376f6747e9158c89988c293cd524ab8d215ae4e185e9929655d5c/pydantic_core-2.27.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:57762139821c31847cfb2df63c12f725788bd9f04bc2fb392790959b8f70f118", size = 2740492 }, - { url = "https://files.pythonhosted.org/packages/8b/1f/3dc6e769d5b7461040778816aab2b00422427bcaa4b56cc89e9c653b2605/pydantic_core-2.27.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0d1e85068e818c73e048fe28cfc769040bb1f475524f4745a5dc621f75ac7630", size = 1995714 }, - { url = "https://files.pythonhosted.org/packages/07/d7/a0bd09bc39283530b3f7c27033a814ef254ba3bd0b5cfd040b7abf1fe5da/pydantic_core-2.27.2-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:097830ed52fd9e427942ff3b9bc17fab52913b2f50f2880dc4a5611446606a54", size = 1997163 }, - { url = "https://files.pythonhosted.org/packages/2d/bb/2db4ad1762e1c5699d9b857eeb41959191980de6feb054e70f93085e1bcd/pydantic_core-2.27.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:044a50963a614ecfae59bb1eaf7ea7efc4bc62f49ed594e18fa1e5d953c40e9f", size = 2005217 }, - { url = "https://files.pythonhosted.org/packages/53/5f/23a5a3e7b8403f8dd8fc8a6f8b49f6b55c7d715b77dcf1f8ae919eeb5628/pydantic_core-2.27.2-cp39-cp39-musllinux_1_1_armv7l.whl", hash = "sha256:4e0b4220ba5b40d727c7f879eac379b822eee5d8fff418e9d3381ee45b3b0362", size = 2127899 }, - { url = "https://files.pythonhosted.org/packages/c2/ae/aa38bb8dd3d89c2f1d8362dd890ee8f3b967330821d03bbe08fa01ce3766/pydantic_core-2.27.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:5e4f4bb20d75e9325cc9696c6802657b58bc1dbbe3022f32cc2b2b632c3fbb96", size = 2155726 }, - { url = "https://files.pythonhosted.org/packages/98/61/4f784608cc9e98f70839187117ce840480f768fed5d386f924074bf6213c/pydantic_core-2.27.2-cp39-cp39-win32.whl", hash = "sha256:cca63613e90d001b9f2f9a9ceb276c308bfa2a43fafb75c8031c4f66039e8c6e", size = 1817219 }, - { url = "https://files.pythonhosted.org/packages/57/82/bb16a68e4a1a858bb3768c2c8f1ff8d8978014e16598f001ea29a25bf1d1/pydantic_core-2.27.2-cp39-cp39-win_amd64.whl", hash = "sha256:77d1bca19b0f7021b3a982e6f903dcd5b2b06076def36a652e3907f596e29f67", size = 1985382 }, - { url = "https://files.pythonhosted.org/packages/46/72/af70981a341500419e67d5cb45abe552a7c74b66326ac8877588488da1ac/pydantic_core-2.27.2-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:2bf14caea37e91198329b828eae1618c068dfb8ef17bb33287a7ad4b61ac314e", size = 1891159 }, - { url = "https://files.pythonhosted.org/packages/ad/3d/c5913cccdef93e0a6a95c2d057d2c2cba347815c845cda79ddd3c0f5e17d/pydantic_core-2.27.2-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:b0cb791f5b45307caae8810c2023a184c74605ec3bcbb67d13846c28ff731ff8", size = 1768331 }, - { url = "https://files.pythonhosted.org/packages/f6/f0/a3ae8fbee269e4934f14e2e0e00928f9346c5943174f2811193113e58252/pydantic_core-2.27.2-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:688d3fd9fcb71f41c4c015c023d12a79d1c4c0732ec9eb35d96e3388a120dcf3", size = 1822467 }, - { url = "https://files.pythonhosted.org/packages/d7/7a/7bbf241a04e9f9ea24cd5874354a83526d639b02674648af3f350554276c/pydantic_core-2.27.2-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3d591580c34f4d731592f0e9fe40f9cc1b430d297eecc70b962e93c5c668f15f", size = 1979797 }, - { url = "https://files.pythonhosted.org/packages/4f/5f/4784c6107731f89e0005a92ecb8a2efeafdb55eb992b8e9d0a2be5199335/pydantic_core-2.27.2-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:82f986faf4e644ffc189a7f1aafc86e46ef70372bb153e7001e8afccc6e54133", size = 1987839 }, - { url = "https://files.pythonhosted.org/packages/6d/a7/61246562b651dff00de86a5f01b6e4befb518df314c54dec187a78d81c84/pydantic_core-2.27.2-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:bec317a27290e2537f922639cafd54990551725fc844249e64c523301d0822fc", size = 1998861 }, - { url = "https://files.pythonhosted.org/packages/86/aa/837821ecf0c022bbb74ca132e117c358321e72e7f9702d1b6a03758545e2/pydantic_core-2.27.2-pp310-pypy310_pp73-musllinux_1_1_armv7l.whl", hash = "sha256:0296abcb83a797db256b773f45773da397da75a08f5fcaef41f2044adec05f50", size = 2116582 }, - { url = "https://files.pythonhosted.org/packages/81/b0/5e74656e95623cbaa0a6278d16cf15e10a51f6002e3ec126541e95c29ea3/pydantic_core-2.27.2-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:0d75070718e369e452075a6017fbf187f788e17ed67a3abd47fa934d001863d9", size = 2151985 }, - { url = "https://files.pythonhosted.org/packages/63/37/3e32eeb2a451fddaa3898e2163746b0cffbbdbb4740d38372db0490d67f3/pydantic_core-2.27.2-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:7e17b560be3c98a8e3aa66ce828bdebb9e9ac6ad5466fba92eb74c4c95cb1151", size = 2004715 }, - { url = "https://files.pythonhosted.org/packages/29/0e/dcaea00c9dbd0348b723cae82b0e0c122e0fa2b43fa933e1622fd237a3ee/pydantic_core-2.27.2-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:c33939a82924da9ed65dab5a65d427205a73181d8098e79b6b426bdf8ad4e656", size = 1891733 }, - { url = "https://files.pythonhosted.org/packages/86/d3/e797bba8860ce650272bda6383a9d8cad1d1c9a75a640c9d0e848076f85e/pydantic_core-2.27.2-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:00bad2484fa6bda1e216e7345a798bd37c68fb2d97558edd584942aa41b7d278", size = 1768375 }, - { url = "https://files.pythonhosted.org/packages/41/f7/f847b15fb14978ca2b30262548f5fc4872b2724e90f116393eb69008299d/pydantic_core-2.27.2-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c817e2b40aba42bac6f457498dacabc568c3b7a986fc9ba7c8d9d260b71485fb", size = 1822307 }, - { url = "https://files.pythonhosted.org/packages/9c/63/ed80ec8255b587b2f108e514dc03eed1546cd00f0af281e699797f373f38/pydantic_core-2.27.2-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:251136cdad0cb722e93732cb45ca5299fb56e1344a833640bf93b2803f8d1bfd", size = 1979971 }, - { url = "https://files.pythonhosted.org/packages/a9/6d/6d18308a45454a0de0e975d70171cadaf454bc7a0bf86b9c7688e313f0bb/pydantic_core-2.27.2-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:d2088237af596f0a524d3afc39ab3b036e8adb054ee57cbb1dcf8e09da5b29cc", size = 1987616 }, - { url = "https://files.pythonhosted.org/packages/82/8a/05f8780f2c1081b800a7ca54c1971e291c2d07d1a50fb23c7e4aef4ed403/pydantic_core-2.27.2-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:d4041c0b966a84b4ae7a09832eb691a35aec90910cd2dbe7a208de59be77965b", size = 1998943 }, - { url = "https://files.pythonhosted.org/packages/5e/3e/fe5b6613d9e4c0038434396b46c5303f5ade871166900b357ada4766c5b7/pydantic_core-2.27.2-pp39-pypy39_pp73-musllinux_1_1_armv7l.whl", hash = "sha256:8083d4e875ebe0b864ffef72a4304827015cff328a1be6e22cc850753bfb122b", size = 2116654 }, - { url = "https://files.pythonhosted.org/packages/db/ad/28869f58938fad8cc84739c4e592989730bfb69b7c90a8fff138dff18e1e/pydantic_core-2.27.2-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:f141ee28a0ad2123b6611b6ceff018039df17f32ada8b534e6aa039545a3efb2", size = 2152292 }, - { url = "https://files.pythonhosted.org/packages/a1/0c/c5c5cd3689c32ed1fe8c5d234b079c12c281c051759770c05b8bed6412b5/pydantic_core-2.27.2-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:7d0c8399fcc1848491f00e0314bd59fb34a9c008761bcb422a057670c3f65e35", size = 2004961 }, +sdist = { url = "https://files.pythonhosted.org/packages/17/19/ed6a078a5287aea7922de6841ef4c06157931622c89c2a47940837b5eecd/pydantic_core-2.33.1.tar.gz", hash = "sha256:bcc9c6fdb0ced789245b02b7d6603e17d1563064ddcfc36f046b61c0c05dd9df", size = 434395 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/38/ea/5f572806ab4d4223d11551af814d243b0e3e02cc6913def4d1fe4a5ca41c/pydantic_core-2.33.1-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:3077cfdb6125cc8dab61b155fdd714663e401f0e6883f9632118ec12cf42df26", size = 2044021 }, + { url = "https://files.pythonhosted.org/packages/8c/d1/f86cc96d2aa80e3881140d16d12ef2b491223f90b28b9a911346c04ac359/pydantic_core-2.33.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:8ffab8b2908d152e74862d276cf5017c81a2f3719f14e8e3e8d6b83fda863927", size = 1861742 }, + { url = "https://files.pythonhosted.org/packages/37/08/fbd2cd1e9fc735a0df0142fac41c114ad9602d1c004aea340169ae90973b/pydantic_core-2.33.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5183e4f6a2d468787243ebcd70cf4098c247e60d73fb7d68d5bc1e1beaa0c4db", size = 1910414 }, + { url = "https://files.pythonhosted.org/packages/7f/73/3ac217751decbf8d6cb9443cec9b9eb0130eeada6ae56403e11b486e277e/pydantic_core-2.33.1-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:398a38d323f37714023be1e0285765f0a27243a8b1506b7b7de87b647b517e48", size = 1996848 }, + { url = "https://files.pythonhosted.org/packages/9a/f5/5c26b265cdcff2661e2520d2d1e9db72d117ea00eb41e00a76efe68cb009/pydantic_core-2.33.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:87d3776f0001b43acebfa86f8c64019c043b55cc5a6a2e313d728b5c95b46969", size = 2141055 }, + { url = "https://files.pythonhosted.org/packages/5d/14/a9c3cee817ef2f8347c5ce0713e91867a0dceceefcb2973942855c917379/pydantic_core-2.33.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c566dd9c5f63d22226409553531f89de0cac55397f2ab8d97d6f06cfce6d947e", size = 2753806 }, + { url = "https://files.pythonhosted.org/packages/f2/68/866ce83a51dd37e7c604ce0050ff6ad26de65a7799df89f4db87dd93d1d6/pydantic_core-2.33.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a0d5f3acc81452c56895e90643a625302bd6be351e7010664151cc55b7b97f89", size = 2007777 }, + { url = "https://files.pythonhosted.org/packages/b6/a8/36771f4404bb3e49bd6d4344da4dede0bf89cc1e01f3b723c47248a3761c/pydantic_core-2.33.1-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:d3a07fadec2a13274a8d861d3d37c61e97a816beae717efccaa4b36dfcaadcde", size = 2122803 }, + { url = "https://files.pythonhosted.org/packages/18/9c/730a09b2694aa89360d20756369822d98dc2f31b717c21df33b64ffd1f50/pydantic_core-2.33.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:f99aeda58dce827f76963ee87a0ebe75e648c72ff9ba1174a253f6744f518f65", size = 2086755 }, + { url = "https://files.pythonhosted.org/packages/54/8e/2dccd89602b5ec31d1c58138d02340ecb2ebb8c2cac3cc66b65ce3edb6ce/pydantic_core-2.33.1-cp310-cp310-musllinux_1_1_armv7l.whl", hash = "sha256:902dbc832141aa0ec374f4310f1e4e7febeebc3256f00dc359a9ac3f264a45dc", size = 2257358 }, + { url = "https://files.pythonhosted.org/packages/d1/9c/126e4ac1bfad8a95a9837acdd0963695d69264179ba4ede8b8c40d741702/pydantic_core-2.33.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:fe44d56aa0b00d66640aa84a3cbe80b7a3ccdc6f0b1ca71090696a6d4777c091", size = 2257916 }, + { url = "https://files.pythonhosted.org/packages/7d/ba/91eea2047e681a6853c81c20aeca9dcdaa5402ccb7404a2097c2adf9d038/pydantic_core-2.33.1-cp310-cp310-win32.whl", hash = "sha256:ed3eb16d51257c763539bde21e011092f127a2202692afaeaccb50db55a31383", size = 1923823 }, + { url = "https://files.pythonhosted.org/packages/94/c0/fcdf739bf60d836a38811476f6ecd50374880b01e3014318b6e809ddfd52/pydantic_core-2.33.1-cp310-cp310-win_amd64.whl", hash = "sha256:694ad99a7f6718c1a498dc170ca430687a39894a60327f548e02a9c7ee4b6504", size = 1952494 }, + { url = "https://files.pythonhosted.org/packages/d6/7f/c6298830cb780c46b4f46bb24298d01019ffa4d21769f39b908cd14bbd50/pydantic_core-2.33.1-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:6e966fc3caaf9f1d96b349b0341c70c8d6573bf1bac7261f7b0ba88f96c56c24", size = 2044224 }, + { url = "https://files.pythonhosted.org/packages/a8/65/6ab3a536776cad5343f625245bd38165d6663256ad43f3a200e5936afd6c/pydantic_core-2.33.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:bfd0adeee563d59c598ceabddf2c92eec77abcb3f4a391b19aa7366170bd9e30", size = 1858845 }, + { url = "https://files.pythonhosted.org/packages/e9/15/9a22fd26ba5ee8c669d4b8c9c244238e940cd5d818649603ca81d1c69861/pydantic_core-2.33.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:91815221101ad3c6b507804178a7bb5cb7b2ead9ecd600041669c8d805ebd595", size = 1910029 }, + { url = "https://files.pythonhosted.org/packages/d5/33/8cb1a62818974045086f55f604044bf35b9342900318f9a2a029a1bec460/pydantic_core-2.33.1-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:9fea9c1869bb4742d174a57b4700c6dadea951df8b06de40c2fedb4f02931c2e", size = 1997784 }, + { url = "https://files.pythonhosted.org/packages/c0/ca/49958e4df7715c71773e1ea5be1c74544923d10319173264e6db122543f9/pydantic_core-2.33.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1d20eb4861329bb2484c021b9d9a977566ab16d84000a57e28061151c62b349a", size = 2141075 }, + { url = "https://files.pythonhosted.org/packages/7b/a6/0b3a167a9773c79ba834b959b4e18c3ae9216b8319bd8422792abc8a41b1/pydantic_core-2.33.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:0fb935c5591573ae3201640579f30128ccc10739b45663f93c06796854405505", size = 2745849 }, + { url = "https://files.pythonhosted.org/packages/0b/60/516484135173aa9e5861d7a0663dce82e4746d2e7f803627d8c25dfa5578/pydantic_core-2.33.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c964fd24e6166420d18fb53996d8c9fd6eac9bf5ae3ec3d03015be4414ce497f", size = 2005794 }, + { url = "https://files.pythonhosted.org/packages/86/70/05b1eb77459ad47de00cf78ee003016da0cedf8b9170260488d7c21e9181/pydantic_core-2.33.1-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:681d65e9011f7392db5aa002b7423cc442d6a673c635668c227c6c8d0e5a4f77", size = 2123237 }, + { url = "https://files.pythonhosted.org/packages/c7/57/12667a1409c04ae7dc95d3b43158948eb0368e9c790be8b095cb60611459/pydantic_core-2.33.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:e100c52f7355a48413e2999bfb4e139d2977a904495441b374f3d4fb4a170961", size = 2086351 }, + { url = "https://files.pythonhosted.org/packages/57/61/cc6d1d1c1664b58fdd6ecc64c84366c34ec9b606aeb66cafab6f4088974c/pydantic_core-2.33.1-cp311-cp311-musllinux_1_1_armv7l.whl", hash = "sha256:048831bd363490be79acdd3232f74a0e9951b11b2b4cc058aeb72b22fdc3abe1", size = 2258914 }, + { url = "https://files.pythonhosted.org/packages/d1/0a/edb137176a1f5419b2ddee8bde6a0a548cfa3c74f657f63e56232df8de88/pydantic_core-2.33.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:bdc84017d28459c00db6f918a7272a5190bec3090058334e43a76afb279eac7c", size = 2257385 }, + { url = "https://files.pythonhosted.org/packages/26/3c/48ca982d50e4b0e1d9954919c887bdc1c2b462801bf408613ccc641b3daa/pydantic_core-2.33.1-cp311-cp311-win32.whl", hash = "sha256:32cd11c5914d1179df70406427097c7dcde19fddf1418c787540f4b730289896", size = 1923765 }, + { url = "https://files.pythonhosted.org/packages/33/cd/7ab70b99e5e21559f5de38a0928ea84e6f23fdef2b0d16a6feaf942b003c/pydantic_core-2.33.1-cp311-cp311-win_amd64.whl", hash = "sha256:2ea62419ba8c397e7da28a9170a16219d310d2cf4970dbc65c32faf20d828c83", size = 1950688 }, + { url = "https://files.pythonhosted.org/packages/4b/ae/db1fc237b82e2cacd379f63e3335748ab88b5adde98bf7544a1b1bd10a84/pydantic_core-2.33.1-cp311-cp311-win_arm64.whl", hash = "sha256:fc903512177361e868bc1f5b80ac8c8a6e05fcdd574a5fb5ffeac5a9982b9e89", size = 1908185 }, + { url = "https://files.pythonhosted.org/packages/c8/ce/3cb22b07c29938f97ff5f5bb27521f95e2ebec399b882392deb68d6c440e/pydantic_core-2.33.1-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:1293d7febb995e9d3ec3ea09caf1a26214eec45b0f29f6074abb004723fc1de8", size = 2026640 }, + { url = "https://files.pythonhosted.org/packages/19/78/f381d643b12378fee782a72126ec5d793081ef03791c28a0fd542a5bee64/pydantic_core-2.33.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:99b56acd433386c8f20be5c4000786d1e7ca0523c8eefc995d14d79c7a081498", size = 1852649 }, + { url = "https://files.pythonhosted.org/packages/9d/2b/98a37b80b15aac9eb2c6cfc6dbd35e5058a352891c5cce3a8472d77665a6/pydantic_core-2.33.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:35a5ec3fa8c2fe6c53e1b2ccc2454398f95d5393ab398478f53e1afbbeb4d939", size = 1892472 }, + { url = "https://files.pythonhosted.org/packages/4e/d4/3c59514e0f55a161004792b9ff3039da52448f43f5834f905abef9db6e4a/pydantic_core-2.33.1-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:b172f7b9d2f3abc0efd12e3386f7e48b576ef309544ac3a63e5e9cdd2e24585d", size = 1977509 }, + { url = "https://files.pythonhosted.org/packages/a9/b6/c2c7946ef70576f79a25db59a576bce088bdc5952d1b93c9789b091df716/pydantic_core-2.33.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9097b9f17f91eea659b9ec58148c0747ec354a42f7389b9d50701610d86f812e", size = 2128702 }, + { url = "https://files.pythonhosted.org/packages/88/fe/65a880f81e3f2a974312b61f82a03d85528f89a010ce21ad92f109d94deb/pydantic_core-2.33.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:cc77ec5b7e2118b152b0d886c7514a4653bcb58c6b1d760134a9fab915f777b3", size = 2679428 }, + { url = "https://files.pythonhosted.org/packages/6f/ff/4459e4146afd0462fb483bb98aa2436d69c484737feaceba1341615fb0ac/pydantic_core-2.33.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d5e3d15245b08fa4a84cefc6c9222e6f37c98111c8679fbd94aa145f9a0ae23d", size = 2008753 }, + { url = "https://files.pythonhosted.org/packages/7c/76/1c42e384e8d78452ededac8b583fe2550c84abfef83a0552e0e7478ccbc3/pydantic_core-2.33.1-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:ef99779001d7ac2e2461d8ab55d3373fe7315caefdbecd8ced75304ae5a6fc6b", size = 2114849 }, + { url = "https://files.pythonhosted.org/packages/00/72/7d0cf05095c15f7ffe0eb78914b166d591c0eed72f294da68378da205101/pydantic_core-2.33.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:fc6bf8869e193855e8d91d91f6bf59699a5cdfaa47a404e278e776dd7f168b39", size = 2069541 }, + { url = "https://files.pythonhosted.org/packages/b3/69/94a514066bb7d8be499aa764926937409d2389c09be0b5107a970286ef81/pydantic_core-2.33.1-cp312-cp312-musllinux_1_1_armv7l.whl", hash = "sha256:b1caa0bc2741b043db7823843e1bde8aaa58a55a58fda06083b0569f8b45693a", size = 2239225 }, + { url = "https://files.pythonhosted.org/packages/84/b0/e390071eadb44b41f4f54c3cef64d8bf5f9612c92686c9299eaa09e267e2/pydantic_core-2.33.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:ec259f62538e8bf364903a7d0d0239447059f9434b284f5536e8402b7dd198db", size = 2248373 }, + { url = "https://files.pythonhosted.org/packages/d6/b2/288b3579ffc07e92af66e2f1a11be3b056fe1214aab314748461f21a31c3/pydantic_core-2.33.1-cp312-cp312-win32.whl", hash = "sha256:e14f369c98a7c15772b9da98987f58e2b509a93235582838bd0d1d8c08b68fda", size = 1907034 }, + { url = "https://files.pythonhosted.org/packages/02/28/58442ad1c22b5b6742b992ba9518420235adced665513868f99a1c2638a5/pydantic_core-2.33.1-cp312-cp312-win_amd64.whl", hash = "sha256:1c607801d85e2e123357b3893f82c97a42856192997b95b4d8325deb1cd0c5f4", size = 1956848 }, + { url = "https://files.pythonhosted.org/packages/a1/eb/f54809b51c7e2a1d9f439f158b8dd94359321abcc98767e16fc48ae5a77e/pydantic_core-2.33.1-cp312-cp312-win_arm64.whl", hash = "sha256:8d13f0276806ee722e70a1c93da19748594f19ac4299c7e41237fc791d1861ea", size = 1903986 }, + { url = "https://files.pythonhosted.org/packages/7a/24/eed3466a4308d79155f1cdd5c7432c80ddcc4530ba8623b79d5ced021641/pydantic_core-2.33.1-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:70af6a21237b53d1fe7b9325b20e65cbf2f0a848cf77bed492b029139701e66a", size = 2033551 }, + { url = "https://files.pythonhosted.org/packages/ab/14/df54b1a0bc9b6ded9b758b73139d2c11b4e8eb43e8ab9c5847c0a2913ada/pydantic_core-2.33.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:282b3fe1bbbe5ae35224a0dbd05aed9ccabccd241e8e6b60370484234b456266", size = 1852785 }, + { url = "https://files.pythonhosted.org/packages/fa/96/e275f15ff3d34bb04b0125d9bc8848bf69f25d784d92a63676112451bfb9/pydantic_core-2.33.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4b315e596282bbb5822d0c7ee9d255595bd7506d1cb20c2911a4da0b970187d3", size = 1897758 }, + { url = "https://files.pythonhosted.org/packages/b7/d8/96bc536e975b69e3a924b507d2a19aedbf50b24e08c80fb00e35f9baaed8/pydantic_core-2.33.1-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:1dfae24cf9921875ca0ca6a8ecb4bb2f13c855794ed0d468d6abbec6e6dcd44a", size = 1986109 }, + { url = "https://files.pythonhosted.org/packages/90/72/ab58e43ce7e900b88cb571ed057b2fcd0e95b708a2e0bed475b10130393e/pydantic_core-2.33.1-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:6dd8ecfde08d8bfadaea669e83c63939af76f4cf5538a72597016edfa3fad516", size = 2129159 }, + { url = "https://files.pythonhosted.org/packages/dc/3f/52d85781406886c6870ac995ec0ba7ccc028b530b0798c9080531b409fdb/pydantic_core-2.33.1-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2f593494876eae852dc98c43c6f260f45abdbfeec9e4324e31a481d948214764", size = 2680222 }, + { url = "https://files.pythonhosted.org/packages/f4/56/6e2ef42f363a0eec0fd92f74a91e0ac48cd2e49b695aac1509ad81eee86a/pydantic_core-2.33.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:948b73114f47fd7016088e5186d13faf5e1b2fe83f5e320e371f035557fd264d", size = 2006980 }, + { url = "https://files.pythonhosted.org/packages/4c/c0/604536c4379cc78359f9ee0aa319f4aedf6b652ec2854953f5a14fc38c5a/pydantic_core-2.33.1-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:e11f3864eb516af21b01e25fac915a82e9ddad3bb0fb9e95a246067398b435a4", size = 2120840 }, + { url = "https://files.pythonhosted.org/packages/1f/46/9eb764814f508f0edfb291a0f75d10854d78113fa13900ce13729aaec3ae/pydantic_core-2.33.1-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:549150be302428b56fdad0c23c2741dcdb5572413776826c965619a25d9c6bde", size = 2072518 }, + { url = "https://files.pythonhosted.org/packages/42/e3/fb6b2a732b82d1666fa6bf53e3627867ea3131c5f39f98ce92141e3e3dc1/pydantic_core-2.33.1-cp313-cp313-musllinux_1_1_armv7l.whl", hash = "sha256:495bc156026efafd9ef2d82372bd38afce78ddd82bf28ef5276c469e57c0c83e", size = 2248025 }, + { url = "https://files.pythonhosted.org/packages/5c/9d/fbe8fe9d1aa4dac88723f10a921bc7418bd3378a567cb5e21193a3c48b43/pydantic_core-2.33.1-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:ec79de2a8680b1a67a07490bddf9636d5c2fab609ba8c57597e855fa5fa4dacd", size = 2254991 }, + { url = "https://files.pythonhosted.org/packages/aa/99/07e2237b8a66438d9b26482332cda99a9acccb58d284af7bc7c946a42fd3/pydantic_core-2.33.1-cp313-cp313-win32.whl", hash = "sha256:ee12a7be1742f81b8a65b36c6921022301d466b82d80315d215c4c691724986f", size = 1915262 }, + { url = "https://files.pythonhosted.org/packages/8a/f4/e457a7849beeed1e5defbcf5051c6f7b3c91a0624dd31543a64fc9adcf52/pydantic_core-2.33.1-cp313-cp313-win_amd64.whl", hash = "sha256:ede9b407e39949d2afc46385ce6bd6e11588660c26f80576c11c958e6647bc40", size = 1956626 }, + { url = "https://files.pythonhosted.org/packages/20/d0/e8d567a7cff7b04e017ae164d98011f1e1894269fe8e90ea187a3cbfb562/pydantic_core-2.33.1-cp313-cp313-win_arm64.whl", hash = "sha256:aa687a23d4b7871a00e03ca96a09cad0f28f443690d300500603bd0adba4b523", size = 1909590 }, + { url = "https://files.pythonhosted.org/packages/ef/fd/24ea4302d7a527d672c5be06e17df16aabfb4e9fdc6e0b345c21580f3d2a/pydantic_core-2.33.1-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:401d7b76e1000d0dd5538e6381d28febdcacb097c8d340dde7d7fc6e13e9f95d", size = 1812963 }, + { url = "https://files.pythonhosted.org/packages/5f/95/4fbc2ecdeb5c1c53f1175a32d870250194eb2fdf6291b795ab08c8646d5d/pydantic_core-2.33.1-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7aeb055a42d734c0255c9e489ac67e75397d59c6fbe60d155851e9782f276a9c", size = 1986896 }, + { url = "https://files.pythonhosted.org/packages/71/ae/fe31e7f4a62431222d8f65a3bd02e3fa7e6026d154a00818e6d30520ea77/pydantic_core-2.33.1-cp313-cp313t-win_amd64.whl", hash = "sha256:338ea9b73e6e109f15ab439e62cb3b78aa752c7fd9536794112e14bee02c8d18", size = 1931810 }, + { url = "https://files.pythonhosted.org/packages/49/78/b86bad645cc3e8dfa6858c70ec38939bf350e54004837c48de09474b2b9e/pydantic_core-2.33.1-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:5ab77f45d33d264de66e1884fca158bc920cb5e27fd0764a72f72f5756ae8bdb", size = 2044282 }, + { url = "https://files.pythonhosted.org/packages/3b/00/a02531331773b2bf08743d84c6b776bd6a449d23b3ae6b0e3229d568bac4/pydantic_core-2.33.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:e7aaba1b4b03aaea7bb59e1b5856d734be011d3e6d98f5bcaa98cb30f375f2ad", size = 1877598 }, + { url = "https://files.pythonhosted.org/packages/a1/fa/32cc152b84a1f420f8a7d80161373e8d87d4ffa077e67d6c8aab3ce1a6ab/pydantic_core-2.33.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7fb66263e9ba8fea2aa85e1e5578980d127fb37d7f2e292773e7bc3a38fb0c7b", size = 1911021 }, + { url = "https://files.pythonhosted.org/packages/5e/87/ea553e0d98bce6c4876f8c50f65cb45597eff6e0aaa8b15813e9972bb19d/pydantic_core-2.33.1-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:3f2648b9262607a7fb41d782cc263b48032ff7a03a835581abbf7a3bec62bcf5", size = 1997276 }, + { url = "https://files.pythonhosted.org/packages/f7/9b/60cb9f4b52158b3adac0066492bbadd0b8473f4f8da5bcc73972655b76ef/pydantic_core-2.33.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:723c5630c4259400818b4ad096735a829074601805d07f8cafc366d95786d331", size = 2141348 }, + { url = "https://files.pythonhosted.org/packages/9b/38/374d254e270d4de0add68a8239f4ed0f444fdd7b766ea69244fb9491dccb/pydantic_core-2.33.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d100e3ae783d2167782391e0c1c7a20a31f55f8015f3293647544df3f9c67824", size = 2753708 }, + { url = "https://files.pythonhosted.org/packages/05/a8/fd79111eb5ab9bc4ef98d8fb0b3a2ffdc80107b2c59859a741ab379c96f8/pydantic_core-2.33.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:177d50460bc976a0369920b6c744d927b0ecb8606fb56858ff542560251b19e5", size = 2008699 }, + { url = "https://files.pythonhosted.org/packages/35/31/2e06619868eb4c18642c5601db420599c1cf9cf50fe868c9ac09cd298e24/pydantic_core-2.33.1-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:a3edde68d1a1f9af1273b2fe798997b33f90308fb6d44d8550c89fc6a3647cf6", size = 2123426 }, + { url = "https://files.pythonhosted.org/packages/4a/d0/3531e8783a311802e3db7ee5a1a5ed79e5706e930b1b4e3109ce15eeb681/pydantic_core-2.33.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:a62c3c3ef6a7e2c45f7853b10b5bc4ddefd6ee3cd31024754a1a5842da7d598d", size = 2087330 }, + { url = "https://files.pythonhosted.org/packages/ac/32/5ff252ed73bacd7677a706ab17723e261a76793f98b305aa20cfc10bbd56/pydantic_core-2.33.1-cp39-cp39-musllinux_1_1_armv7l.whl", hash = "sha256:c91dbb0ab683fa0cd64a6e81907c8ff41d6497c346890e26b23de7ee55353f96", size = 2258171 }, + { url = "https://files.pythonhosted.org/packages/c9/f9/e96e00f92b8f5b3e2cddc80c5ee6cf038f8a0f238c44b67b01759943a7b4/pydantic_core-2.33.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:9f466e8bf0a62dc43e068c12166281c2eca72121dd2adc1040f3aa1e21ef8599", size = 2258745 }, + { url = "https://files.pythonhosted.org/packages/54/1e/51c86688e809d94797fdf0efc41514f001caec982a05f62d90c180a9639d/pydantic_core-2.33.1-cp39-cp39-win32.whl", hash = "sha256:ab0277cedb698749caada82e5d099dc9fed3f906a30d4c382d1a21725777a1e5", size = 1923626 }, + { url = "https://files.pythonhosted.org/packages/57/18/c2da959fd8d019b70cadafdda2bf845378ada47973e0bad6cc84f56dbe6e/pydantic_core-2.33.1-cp39-cp39-win_amd64.whl", hash = "sha256:5773da0ee2d17136b1f1c6fbde543398d452a6ad2a7b54ea1033e2daa739b8d2", size = 1953703 }, + { url = "https://files.pythonhosted.org/packages/9c/c7/8b311d5adb0fe00a93ee9b4e92a02b0ec08510e9838885ef781ccbb20604/pydantic_core-2.33.1-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:5c834f54f8f4640fd7e4b193f80eb25a0602bba9e19b3cd2fc7ffe8199f5ae02", size = 2041659 }, + { url = "https://files.pythonhosted.org/packages/8a/d6/4f58d32066a9e26530daaf9adc6664b01875ae0691570094968aaa7b8fcc/pydantic_core-2.33.1-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:049e0de24cf23766f12cc5cc71d8abc07d4a9deb9061b334b62093dedc7cb068", size = 1873294 }, + { url = "https://files.pythonhosted.org/packages/f7/3f/53cc9c45d9229da427909c751f8ed2bf422414f7664ea4dde2d004f596ba/pydantic_core-2.33.1-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1a28239037b3d6f16916a4c831a5a0eadf856bdd6d2e92c10a0da3a59eadcf3e", size = 1903771 }, + { url = "https://files.pythonhosted.org/packages/f0/49/bf0783279ce674eb9903fb9ae43f6c614cb2f1c4951370258823f795368b/pydantic_core-2.33.1-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9d3da303ab5f378a268fa7d45f37d7d85c3ec19769f28d2cc0c61826a8de21fe", size = 2083558 }, + { url = "https://files.pythonhosted.org/packages/9c/5b/0d998367687f986c7d8484a2c476d30f07bf5b8b1477649a6092bd4c540e/pydantic_core-2.33.1-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:25626fb37b3c543818c14821afe0fd3830bc327a43953bc88db924b68c5723f1", size = 2118038 }, + { url = "https://files.pythonhosted.org/packages/b3/33/039287d410230ee125daee57373ac01940d3030d18dba1c29cd3089dc3ca/pydantic_core-2.33.1-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:3ab2d36e20fbfcce8f02d73c33a8a7362980cff717926bbae030b93ae46b56c7", size = 2079315 }, + { url = "https://files.pythonhosted.org/packages/1f/85/6d8b2646d99c062d7da2d0ab2faeb0d6ca9cca4c02da6076376042a20da3/pydantic_core-2.33.1-pp310-pypy310_pp73-musllinux_1_1_armv7l.whl", hash = "sha256:2f9284e11c751b003fd4215ad92d325d92c9cb19ee6729ebd87e3250072cdcde", size = 2249063 }, + { url = "https://files.pythonhosted.org/packages/17/d7/c37d208d5738f7b9ad8f22ae8a727d88ebf9c16c04ed2475122cc3f7224a/pydantic_core-2.33.1-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:048c01eee07d37cbd066fc512b9d8b5ea88ceeb4e629ab94b3e56965ad655add", size = 2254631 }, + { url = "https://files.pythonhosted.org/packages/13/e0/bafa46476d328e4553b85ab9b2f7409e7aaef0ce4c937c894821c542d347/pydantic_core-2.33.1-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:5ccd429694cf26af7997595d627dd2637e7932214486f55b8a357edaac9dae8c", size = 2080877 }, + { url = "https://files.pythonhosted.org/packages/0b/76/1794e440c1801ed35415238d2c728f26cd12695df9057154ad768b7b991c/pydantic_core-2.33.1-pp311-pypy311_pp73-macosx_10_12_x86_64.whl", hash = "sha256:3a371dc00282c4b84246509a5ddc808e61b9864aa1eae9ecc92bb1268b82db4a", size = 2042858 }, + { url = "https://files.pythonhosted.org/packages/73/b4/9cd7b081fb0b1b4f8150507cd59d27b275c3e22ad60b35cb19ea0977d9b9/pydantic_core-2.33.1-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:f59295ecc75a1788af8ba92f2e8c6eeaa5a94c22fc4d151e8d9638814f85c8fc", size = 1873745 }, + { url = "https://files.pythonhosted.org/packages/e1/d7/9ddb7575d4321e40d0363903c2576c8c0c3280ebea137777e5ab58d723e3/pydantic_core-2.33.1-pp311-pypy311_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:08530b8ac922003033f399128505f513e30ca770527cc8bbacf75a84fcc2c74b", size = 1904188 }, + { url = "https://files.pythonhosted.org/packages/d1/a8/3194ccfe461bb08da19377ebec8cb4f13c9bd82e13baebc53c5c7c39a029/pydantic_core-2.33.1-pp311-pypy311_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bae370459da6a5466978c0eacf90690cb57ec9d533f8e63e564ef3822bfa04fe", size = 2083479 }, + { url = "https://files.pythonhosted.org/packages/42/c7/84cb569555d7179ca0b3f838cef08f66f7089b54432f5b8599aac6e9533e/pydantic_core-2.33.1-pp311-pypy311_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:e3de2777e3b9f4d603112f78006f4ae0acb936e95f06da6cb1a45fbad6bdb4b5", size = 2118415 }, + { url = "https://files.pythonhosted.org/packages/3b/67/72abb8c73e0837716afbb58a59cc9e3ae43d1aa8677f3b4bc72c16142716/pydantic_core-2.33.1-pp311-pypy311_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:3a64e81e8cba118e108d7126362ea30e021291b7805d47e4896e52c791be2761", size = 2079623 }, + { url = "https://files.pythonhosted.org/packages/0b/cd/c59707e35a47ba4cbbf153c3f7c56420c58653b5801b055dc52cccc8e2dc/pydantic_core-2.33.1-pp311-pypy311_pp73-musllinux_1_1_armv7l.whl", hash = "sha256:52928d8c1b6bda03cc6d811e8923dffc87a2d3c8b3bfd2ce16471c7147a24850", size = 2250175 }, + { url = "https://files.pythonhosted.org/packages/84/32/e4325a6676b0bed32d5b084566ec86ed7fd1e9bcbfc49c578b1755bde920/pydantic_core-2.33.1-pp311-pypy311_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:1b30d92c9412beb5ac6b10a3eb7ef92ccb14e3f2a8d7732e2d739f58b3aa7544", size = 2254674 }, + { url = "https://files.pythonhosted.org/packages/12/6f/5596dc418f2e292ffc661d21931ab34591952e2843e7168ea5a52591f6ff/pydantic_core-2.33.1-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:f995719707e0e29f0f41a8aa3bcea6e761a36c9136104d3189eafb83f5cec5e5", size = 2080951 }, + { url = "https://files.pythonhosted.org/packages/2d/a8/c2c8f29bd18f7ef52de32a6deb9e3ee87ba18b7b2122636aa9f4438cf627/pydantic_core-2.33.1-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:7edbc454a29fc6aeae1e1eecba4f07b63b8d76e76a748532233c4c167b4cb9ea", size = 2041791 }, + { url = "https://files.pythonhosted.org/packages/08/ad/328081b1c82543ae49d0650048305058583c51f1a9a56a0d6e87bb3a2443/pydantic_core-2.33.1-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:ad05b683963f69a1d5d2c2bdab1274a31221ca737dbbceaa32bcb67359453cdd", size = 1873579 }, + { url = "https://files.pythonhosted.org/packages/6e/8a/bc65dbf7e501e88367cdab06a2c1340457c785f0c72288cae737fd80c0fa/pydantic_core-2.33.1-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:df6a94bf9452c6da9b5d76ed229a5683d0306ccb91cca8e1eea883189780d568", size = 1904189 }, + { url = "https://files.pythonhosted.org/packages/9a/db/30ca6aefda211fb01ef185ca73cb7a0c6e7fe952c524025c8782b5acd771/pydantic_core-2.33.1-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7965c13b3967909a09ecc91f21d09cfc4576bf78140b988904e94f130f188396", size = 2084446 }, + { url = "https://files.pythonhosted.org/packages/f2/89/a12b55286e30c9f476eab7c53c9249ec76faf70430596496ab0309f28629/pydantic_core-2.33.1-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:3f1fdb790440a34f6ecf7679e1863b825cb5ffde858a9197f851168ed08371e5", size = 2118215 }, + { url = "https://files.pythonhosted.org/packages/8e/55/12721c4a8d7951584ad3d9848b44442559cf1876e0bb424148d1060636b3/pydantic_core-2.33.1-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:5277aec8d879f8d05168fdd17ae811dd313b8ff894aeeaf7cd34ad28b4d77e33", size = 2079963 }, + { url = "https://files.pythonhosted.org/packages/bd/0c/3391bd5d6ff62ea998db94732528d9bc32c560b0ed861c39119759461946/pydantic_core-2.33.1-pp39-pypy39_pp73-musllinux_1_1_armv7l.whl", hash = "sha256:8ab581d3530611897d863d1a649fb0644b860286b4718db919bfd51ece41f10b", size = 2249388 }, + { url = "https://files.pythonhosted.org/packages/d3/5f/3e4feb042998d7886a9b523b372d83955cbc192a07013dcd24276db078ee/pydantic_core-2.33.1-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:0483847fa9ad5e3412265c1bd72aad35235512d9ce9d27d81a56d935ef489672", size = 2255226 }, + { url = "https://files.pythonhosted.org/packages/25/f2/1647933efaaad61846109a27619f3704929e758a09e6431b8f932a053d40/pydantic_core-2.33.1-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:de9e06abe3cc5ec6a2d5f75bc99b0bdca4f5c719a5b34026f8c57efbdecd2ee3", size = 2081073 }, ] [[package]] @@ -1518,14 +2042,15 @@ wheels = [ [[package]] name = "pytest-asyncio" -version = "0.25.3" +version = "0.26.0" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "pytest" }, + { name = "typing-extensions", marker = "python_full_version < '3.10'" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/f2/a8/ecbc8ede70921dd2f544ab1cadd3ff3bf842af27f87bbdea774c7baa1d38/pytest_asyncio-0.25.3.tar.gz", hash = "sha256:fc1da2cf9f125ada7e710b4ddad05518d4cee187ae9412e9ac9271003497f07a", size = 54239 } +sdist = { url = "https://files.pythonhosted.org/packages/8e/c4/453c52c659521066969523e87d85d54139bbd17b78f09532fb8eb8cdb58e/pytest_asyncio-0.26.0.tar.gz", hash = "sha256:c4df2a697648241ff39e7f0e4a73050b03f123f760673956cf0d72a4990e312f", size = 54156 } wheels = [ - { url = "https://files.pythonhosted.org/packages/67/17/3493c5624e48fd97156ebaec380dcaafee9506d7e2c46218ceebbb57d7de/pytest_asyncio-0.25.3-py3-none-any.whl", hash = "sha256:9e89518e0f9bd08928f97a3482fdc4e244df17529460bc038291ccaf8f85c7c3", size = 19467 }, + { url = "https://files.pythonhosted.org/packages/20/7f/338843f449ace853647ace35870874f69a764d251872ed1b4de9f234822c/pytest_asyncio-0.26.0-py3-none-any.whl", hash = "sha256:7b51ed894f4fbea1340262bdae5135797ebbe21d8638978e35d31c6d19f72fb0", size = 19694 }, ] [[package]] @@ -1554,11 +2079,20 @@ wheels = [ [[package]] name = "python-dotenv" -version = "1.0.1" +version = "1.1.0" source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/bc/57/e84d88dfe0aec03b7a2d4327012c1627ab5f03652216c63d49846d7a6c58/python-dotenv-1.0.1.tar.gz", hash = "sha256:e324ee90a023d808f1959c46bcbc04446a10ced277783dc6ee09987c37ec10ca", size = 39115 } +sdist = { url = "https://files.pythonhosted.org/packages/88/2c/7bb1416c5620485aa793f2de31d3df393d3686aa8a8506d11e10e13c5baf/python_dotenv-1.1.0.tar.gz", hash = "sha256:41f90bc6f5f177fb41f53e87666db362025010eb28f60a01c9143bfa33a2b2d5", size = 39920 } wheels = [ - { url = "https://files.pythonhosted.org/packages/6a/3e/b68c118422ec867fa7ab88444e1274aa40681c606d59ac27de5a5588f082/python_dotenv-1.0.1-py3-none-any.whl", hash = "sha256:f7b63ef50f1b690dddf550d03497b66d609393b40b564ed0d674909a68ebf16a", size = 19863 }, + { url = "https://files.pythonhosted.org/packages/1e/18/98a99ad95133c6a6e2005fe89faedf294a748bd5dc803008059409ac9b1e/python_dotenv-1.1.0-py3-none-any.whl", hash = "sha256:d7c01d9e2293916c18baf562d95698754b0dbbb5e74d457c45d4f6561fb9d55d", size = 20256 }, +] + +[[package]] +name = "python-multipart" +version = "0.0.20" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/f3/87/f44d7c9f274c7ee665a29b885ec97089ec5dc034c7f3fafa03da9e39a09e/python_multipart-0.0.20.tar.gz", hash = "sha256:8dd0cab45b8e23064ae09147625994d090fa46f5b0d1e13af944c331a7fa9d13", size = 37158 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/45/58/38b5afbc1a800eeea951b9285d3912613f2603bdf897a4ab0f4bd7f405fc/python_multipart-0.0.20-py3-none-any.whl", hash = "sha256:8a62d3a8335e06589fe01f2a3e178cdcc632f3fbe0d492ad9ee0ec35aab1f104", size = 24546 }, ] [[package]] @@ -1638,6 +2172,105 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/5a/66/bbb1dd374f5c870f59c5bb1db0e18cbe7fa739415a24cbd95b2d1f5ae0c4/pyyaml_env_tag-0.1-py3-none-any.whl", hash = "sha256:af31106dec8a4d68c60207c1886031cbf839b68aa7abccdb19868200532c2069", size = 3911 }, ] +[[package]] +name = "referencing" +version = "0.36.2" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "attrs" }, + { name = "rpds-py" }, + { name = "typing-extensions", marker = "python_full_version < '3.13'" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/2f/db/98b5c277be99dd18bfd91dd04e1b759cad18d1a338188c936e92f921c7e2/referencing-0.36.2.tar.gz", hash = "sha256:df2e89862cd09deabbdba16944cc3f10feb6b3e6f18e902f7cc25609a34775aa", size = 74744 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/c1/b1/3baf80dc6d2b7bc27a95a67752d0208e410351e3feb4eb78de5f77454d8d/referencing-0.36.2-py3-none-any.whl", hash = "sha256:e8699adbbf8b5c7de96d8ffa0eb5c158b3beafce084968e2ea8bb08c6794dcd0", size = 26775 }, +] + +[[package]] +name = "regex" +version = "2024.11.6" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/8e/5f/bd69653fbfb76cf8604468d3b4ec4c403197144c7bfe0e6a5fc9e02a07cb/regex-2024.11.6.tar.gz", hash = "sha256:7ab159b063c52a0333c884e4679f8d7a85112ee3078fe3d9004b2dd875585519", size = 399494 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/95/3c/4651f6b130c6842a8f3df82461a8950f923925db8b6961063e82744bddcc/regex-2024.11.6-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:ff590880083d60acc0433f9c3f713c51f7ac6ebb9adf889c79a261ecf541aa91", size = 482674 }, + { url = "https://files.pythonhosted.org/packages/15/51/9f35d12da8434b489c7b7bffc205c474a0a9432a889457026e9bc06a297a/regex-2024.11.6-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:658f90550f38270639e83ce492f27d2c8d2cd63805c65a13a14d36ca126753f0", size = 287684 }, + { url = "https://files.pythonhosted.org/packages/bd/18/b731f5510d1b8fb63c6b6d3484bfa9a59b84cc578ac8b5172970e05ae07c/regex-2024.11.6-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:164d8b7b3b4bcb2068b97428060b2a53be050085ef94eca7f240e7947f1b080e", size = 284589 }, + { url = "https://files.pythonhosted.org/packages/78/a2/6dd36e16341ab95e4c6073426561b9bfdeb1a9c9b63ab1b579c2e96cb105/regex-2024.11.6-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d3660c82f209655a06b587d55e723f0b813d3a7db2e32e5e7dc64ac2a9e86fde", size = 782511 }, + { url = "https://files.pythonhosted.org/packages/1b/2b/323e72d5d2fd8de0d9baa443e1ed70363ed7e7b2fb526f5950c5cb99c364/regex-2024.11.6-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d22326fcdef5e08c154280b71163ced384b428343ae16a5ab2b3354aed12436e", size = 821149 }, + { url = "https://files.pythonhosted.org/packages/90/30/63373b9ea468fbef8a907fd273e5c329b8c9535fee36fc8dba5fecac475d/regex-2024.11.6-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f1ac758ef6aebfc8943560194e9fd0fa18bcb34d89fd8bd2af18183afd8da3a2", size = 809707 }, + { url = "https://files.pythonhosted.org/packages/f2/98/26d3830875b53071f1f0ae6d547f1d98e964dd29ad35cbf94439120bb67a/regex-2024.11.6-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:997d6a487ff00807ba810e0f8332c18b4eb8d29463cfb7c820dc4b6e7562d0cf", size = 781702 }, + { url = "https://files.pythonhosted.org/packages/87/55/eb2a068334274db86208ab9d5599ffa63631b9f0f67ed70ea7c82a69bbc8/regex-2024.11.6-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:02a02d2bb04fec86ad61f3ea7f49c015a0681bf76abb9857f945d26159d2968c", size = 771976 }, + { url = "https://files.pythonhosted.org/packages/74/c0/be707bcfe98254d8f9d2cff55d216e946f4ea48ad2fd8cf1428f8c5332ba/regex-2024.11.6-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:f02f93b92358ee3f78660e43b4b0091229260c5d5c408d17d60bf26b6c900e86", size = 697397 }, + { url = "https://files.pythonhosted.org/packages/49/dc/bb45572ceb49e0f6509f7596e4ba7031f6819ecb26bc7610979af5a77f45/regex-2024.11.6-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:06eb1be98df10e81ebaded73fcd51989dcf534e3c753466e4b60c4697a003b67", size = 768726 }, + { url = "https://files.pythonhosted.org/packages/5a/db/f43fd75dc4c0c2d96d0881967897926942e935d700863666f3c844a72ce6/regex-2024.11.6-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:040df6fe1a5504eb0f04f048e6d09cd7c7110fef851d7c567a6b6e09942feb7d", size = 775098 }, + { url = "https://files.pythonhosted.org/packages/99/d7/f94154db29ab5a89d69ff893159b19ada89e76b915c1293e98603d39838c/regex-2024.11.6-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:fdabbfc59f2c6edba2a6622c647b716e34e8e3867e0ab975412c5c2f79b82da2", size = 839325 }, + { url = "https://files.pythonhosted.org/packages/f7/17/3cbfab1f23356fbbf07708220ab438a7efa1e0f34195bf857433f79f1788/regex-2024.11.6-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:8447d2d39b5abe381419319f942de20b7ecd60ce86f16a23b0698f22e1b70008", size = 843277 }, + { url = "https://files.pythonhosted.org/packages/7e/f2/48b393b51900456155de3ad001900f94298965e1cad1c772b87f9cfea011/regex-2024.11.6-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:da8f5fc57d1933de22a9e23eec290a0d8a5927a5370d24bda9a6abe50683fe62", size = 773197 }, + { url = "https://files.pythonhosted.org/packages/45/3f/ef9589aba93e084cd3f8471fded352826dcae8489b650d0b9b27bc5bba8a/regex-2024.11.6-cp310-cp310-win32.whl", hash = "sha256:b489578720afb782f6ccf2840920f3a32e31ba28a4b162e13900c3e6bd3f930e", size = 261714 }, + { url = "https://files.pythonhosted.org/packages/42/7e/5f1b92c8468290c465fd50c5318da64319133231415a8aa6ea5ab995a815/regex-2024.11.6-cp310-cp310-win_amd64.whl", hash = "sha256:5071b2093e793357c9d8b2929dfc13ac5f0a6c650559503bb81189d0a3814519", size = 274042 }, + { url = "https://files.pythonhosted.org/packages/58/58/7e4d9493a66c88a7da6d205768119f51af0f684fe7be7bac8328e217a52c/regex-2024.11.6-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:5478c6962ad548b54a591778e93cd7c456a7a29f8eca9c49e4f9a806dcc5d638", size = 482669 }, + { url = "https://files.pythonhosted.org/packages/34/4c/8f8e631fcdc2ff978609eaeef1d6994bf2f028b59d9ac67640ed051f1218/regex-2024.11.6-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:2c89a8cc122b25ce6945f0423dc1352cb9593c68abd19223eebbd4e56612c5b7", size = 287684 }, + { url = "https://files.pythonhosted.org/packages/c5/1b/f0e4d13e6adf866ce9b069e191f303a30ab1277e037037a365c3aad5cc9c/regex-2024.11.6-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:94d87b689cdd831934fa3ce16cc15cd65748e6d689f5d2b8f4f4df2065c9fa20", size = 284589 }, + { url = "https://files.pythonhosted.org/packages/25/4d/ab21047f446693887f25510887e6820b93f791992994f6498b0318904d4a/regex-2024.11.6-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1062b39a0a2b75a9c694f7a08e7183a80c63c0d62b301418ffd9c35f55aaa114", size = 792121 }, + { url = "https://files.pythonhosted.org/packages/45/ee/c867e15cd894985cb32b731d89576c41a4642a57850c162490ea34b78c3b/regex-2024.11.6-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:167ed4852351d8a750da48712c3930b031f6efdaa0f22fa1933716bfcd6bf4a3", size = 831275 }, + { url = "https://files.pythonhosted.org/packages/b3/12/b0f480726cf1c60f6536fa5e1c95275a77624f3ac8fdccf79e6727499e28/regex-2024.11.6-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2d548dafee61f06ebdb584080621f3e0c23fff312f0de1afc776e2a2ba99a74f", size = 818257 }, + { url = "https://files.pythonhosted.org/packages/bf/ce/0d0e61429f603bac433910d99ef1a02ce45a8967ffbe3cbee48599e62d88/regex-2024.11.6-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f2a19f302cd1ce5dd01a9099aaa19cae6173306d1302a43b627f62e21cf18ac0", size = 792727 }, + { url = "https://files.pythonhosted.org/packages/e4/c1/243c83c53d4a419c1556f43777ccb552bccdf79d08fda3980e4e77dd9137/regex-2024.11.6-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:bec9931dfb61ddd8ef2ebc05646293812cb6b16b60cf7c9511a832b6f1854b55", size = 780667 }, + { url = "https://files.pythonhosted.org/packages/c5/f4/75eb0dd4ce4b37f04928987f1d22547ddaf6c4bae697623c1b05da67a8aa/regex-2024.11.6-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:9714398225f299aa85267fd222f7142fcb5c769e73d7733344efc46f2ef5cf89", size = 776963 }, + { url = "https://files.pythonhosted.org/packages/16/5d/95c568574e630e141a69ff8a254c2f188b4398e813c40d49228c9bbd9875/regex-2024.11.6-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:202eb32e89f60fc147a41e55cb086db2a3f8cb82f9a9a88440dcfc5d37faae8d", size = 784700 }, + { url = "https://files.pythonhosted.org/packages/8e/b5/f8495c7917f15cc6fee1e7f395e324ec3e00ab3c665a7dc9d27562fd5290/regex-2024.11.6-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:4181b814e56078e9b00427ca358ec44333765f5ca1b45597ec7446d3a1ef6e34", size = 848592 }, + { url = "https://files.pythonhosted.org/packages/1c/80/6dd7118e8cb212c3c60b191b932dc57db93fb2e36fb9e0e92f72a5909af9/regex-2024.11.6-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:068376da5a7e4da51968ce4c122a7cd31afaaec4fccc7856c92f63876e57b51d", size = 852929 }, + { url = "https://files.pythonhosted.org/packages/11/9b/5a05d2040297d2d254baf95eeeb6df83554e5e1df03bc1a6687fc4ba1f66/regex-2024.11.6-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:ac10f2c4184420d881a3475fb2c6f4d95d53a8d50209a2500723d831036f7c45", size = 781213 }, + { url = "https://files.pythonhosted.org/packages/26/b7/b14e2440156ab39e0177506c08c18accaf2b8932e39fb092074de733d868/regex-2024.11.6-cp311-cp311-win32.whl", hash = "sha256:c36f9b6f5f8649bb251a5f3f66564438977b7ef8386a52460ae77e6070d309d9", size = 261734 }, + { url = "https://files.pythonhosted.org/packages/80/32/763a6cc01d21fb3819227a1cc3f60fd251c13c37c27a73b8ff4315433a8e/regex-2024.11.6-cp311-cp311-win_amd64.whl", hash = "sha256:02e28184be537f0e75c1f9b2f8847dc51e08e6e171c6bde130b2687e0c33cf60", size = 274052 }, + { url = "https://files.pythonhosted.org/packages/ba/30/9a87ce8336b172cc232a0db89a3af97929d06c11ceaa19d97d84fa90a8f8/regex-2024.11.6-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:52fb28f528778f184f870b7cf8f225f5eef0a8f6e3778529bdd40c7b3920796a", size = 483781 }, + { url = "https://files.pythonhosted.org/packages/01/e8/00008ad4ff4be8b1844786ba6636035f7ef926db5686e4c0f98093612add/regex-2024.11.6-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:fdd6028445d2460f33136c55eeb1f601ab06d74cb3347132e1c24250187500d9", size = 288455 }, + { url = "https://files.pythonhosted.org/packages/60/85/cebcc0aff603ea0a201667b203f13ba75d9fc8668fab917ac5b2de3967bc/regex-2024.11.6-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:805e6b60c54bf766b251e94526ebad60b7de0c70f70a4e6210ee2891acb70bf2", size = 284759 }, + { url = "https://files.pythonhosted.org/packages/94/2b/701a4b0585cb05472a4da28ee28fdfe155f3638f5e1ec92306d924e5faf0/regex-2024.11.6-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b85c2530be953a890eaffde05485238f07029600e8f098cdf1848d414a8b45e4", size = 794976 }, + { url = "https://files.pythonhosted.org/packages/4b/bf/fa87e563bf5fee75db8915f7352e1887b1249126a1be4813837f5dbec965/regex-2024.11.6-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:bb26437975da7dc36b7efad18aa9dd4ea569d2357ae6b783bf1118dabd9ea577", size = 833077 }, + { url = "https://files.pythonhosted.org/packages/a1/56/7295e6bad94b047f4d0834e4779491b81216583c00c288252ef625c01d23/regex-2024.11.6-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:abfa5080c374a76a251ba60683242bc17eeb2c9818d0d30117b4486be10c59d3", size = 823160 }, + { url = "https://files.pythonhosted.org/packages/fb/13/e3b075031a738c9598c51cfbc4c7879e26729c53aa9cca59211c44235314/regex-2024.11.6-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:70b7fa6606c2881c1db9479b0eaa11ed5dfa11c8d60a474ff0e095099f39d98e", size = 796896 }, + { url = "https://files.pythonhosted.org/packages/24/56/0b3f1b66d592be6efec23a795b37732682520b47c53da5a32c33ed7d84e3/regex-2024.11.6-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0c32f75920cf99fe6b6c539c399a4a128452eaf1af27f39bce8909c9a3fd8cbe", size = 783997 }, + { url = "https://files.pythonhosted.org/packages/f9/a1/eb378dada8b91c0e4c5f08ffb56f25fcae47bf52ad18f9b2f33b83e6d498/regex-2024.11.6-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:982e6d21414e78e1f51cf595d7f321dcd14de1f2881c5dc6a6e23bbbbd68435e", size = 781725 }, + { url = "https://files.pythonhosted.org/packages/83/f2/033e7dec0cfd6dda93390089864732a3409246ffe8b042e9554afa9bff4e/regex-2024.11.6-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:a7c2155f790e2fb448faed6dd241386719802296ec588a8b9051c1f5c481bc29", size = 789481 }, + { url = "https://files.pythonhosted.org/packages/83/23/15d4552ea28990a74e7696780c438aadd73a20318c47e527b47a4a5a596d/regex-2024.11.6-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:149f5008d286636e48cd0b1dd65018548944e495b0265b45e1bffecce1ef7f39", size = 852896 }, + { url = "https://files.pythonhosted.org/packages/e3/39/ed4416bc90deedbfdada2568b2cb0bc1fdb98efe11f5378d9892b2a88f8f/regex-2024.11.6-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:e5364a4502efca094731680e80009632ad6624084aff9a23ce8c8c6820de3e51", size = 860138 }, + { url = "https://files.pythonhosted.org/packages/93/2d/dd56bb76bd8e95bbce684326302f287455b56242a4f9c61f1bc76e28360e/regex-2024.11.6-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:0a86e7eeca091c09e021db8eb72d54751e527fa47b8d5787caf96d9831bd02ad", size = 787692 }, + { url = "https://files.pythonhosted.org/packages/0b/55/31877a249ab7a5156758246b9c59539abbeba22461b7d8adc9e8475ff73e/regex-2024.11.6-cp312-cp312-win32.whl", hash = "sha256:32f9a4c643baad4efa81d549c2aadefaeba12249b2adc5af541759237eee1c54", size = 262135 }, + { url = "https://files.pythonhosted.org/packages/38/ec/ad2d7de49a600cdb8dd78434a1aeffe28b9d6fc42eb36afab4a27ad23384/regex-2024.11.6-cp312-cp312-win_amd64.whl", hash = "sha256:a93c194e2df18f7d264092dc8539b8ffb86b45b899ab976aa15d48214138e81b", size = 273567 }, + { url = "https://files.pythonhosted.org/packages/90/73/bcb0e36614601016552fa9344544a3a2ae1809dc1401b100eab02e772e1f/regex-2024.11.6-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:a6ba92c0bcdf96cbf43a12c717eae4bc98325ca3730f6b130ffa2e3c3c723d84", size = 483525 }, + { url = "https://files.pythonhosted.org/packages/0f/3f/f1a082a46b31e25291d830b369b6b0c5576a6f7fb89d3053a354c24b8a83/regex-2024.11.6-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:525eab0b789891ac3be914d36893bdf972d483fe66551f79d3e27146191a37d4", size = 288324 }, + { url = "https://files.pythonhosted.org/packages/09/c9/4e68181a4a652fb3ef5099e077faf4fd2a694ea6e0f806a7737aff9e758a/regex-2024.11.6-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:086a27a0b4ca227941700e0b31425e7a28ef1ae8e5e05a33826e17e47fbfdba0", size = 284617 }, + { url = "https://files.pythonhosted.org/packages/fc/fd/37868b75eaf63843165f1d2122ca6cb94bfc0271e4428cf58c0616786dce/regex-2024.11.6-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bde01f35767c4a7899b7eb6e823b125a64de314a8ee9791367c9a34d56af18d0", size = 795023 }, + { url = "https://files.pythonhosted.org/packages/c4/7c/d4cd9c528502a3dedb5c13c146e7a7a539a3853dc20209c8e75d9ba9d1b2/regex-2024.11.6-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b583904576650166b3d920d2bcce13971f6f9e9a396c673187f49811b2769dc7", size = 833072 }, + { url = "https://files.pythonhosted.org/packages/4f/db/46f563a08f969159c5a0f0e722260568425363bea43bb7ae370becb66a67/regex-2024.11.6-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1c4de13f06a0d54fa0d5ab1b7138bfa0d883220965a29616e3ea61b35d5f5fc7", size = 823130 }, + { url = "https://files.pythonhosted.org/packages/db/60/1eeca2074f5b87df394fccaa432ae3fc06c9c9bfa97c5051aed70e6e00c2/regex-2024.11.6-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3cde6e9f2580eb1665965ce9bf17ff4952f34f5b126beb509fee8f4e994f143c", size = 796857 }, + { url = "https://files.pythonhosted.org/packages/10/db/ac718a08fcee981554d2f7bb8402f1faa7e868c1345c16ab1ebec54b0d7b/regex-2024.11.6-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0d7f453dca13f40a02b79636a339c5b62b670141e63efd511d3f8f73fba162b3", size = 784006 }, + { url = "https://files.pythonhosted.org/packages/c2/41/7da3fe70216cea93144bf12da2b87367590bcf07db97604edeea55dac9ad/regex-2024.11.6-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:59dfe1ed21aea057a65c6b586afd2a945de04fc7db3de0a6e3ed5397ad491b07", size = 781650 }, + { url = "https://files.pythonhosted.org/packages/a7/d5/880921ee4eec393a4752e6ab9f0fe28009435417c3102fc413f3fe81c4e5/regex-2024.11.6-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:b97c1e0bd37c5cd7902e65f410779d39eeda155800b65fc4d04cc432efa9bc6e", size = 789545 }, + { url = "https://files.pythonhosted.org/packages/dc/96/53770115e507081122beca8899ab7f5ae28ae790bfcc82b5e38976df6a77/regex-2024.11.6-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:f9d1e379028e0fc2ae3654bac3cbbef81bf3fd571272a42d56c24007979bafb6", size = 853045 }, + { url = "https://files.pythonhosted.org/packages/31/d3/1372add5251cc2d44b451bd94f43b2ec78e15a6e82bff6a290ef9fd8f00a/regex-2024.11.6-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:13291b39131e2d002a7940fb176e120bec5145f3aeb7621be6534e46251912c4", size = 860182 }, + { url = "https://files.pythonhosted.org/packages/ed/e3/c446a64984ea9f69982ba1a69d4658d5014bc7a0ea468a07e1a1265db6e2/regex-2024.11.6-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:4f51f88c126370dcec4908576c5a627220da6c09d0bff31cfa89f2523843316d", size = 787733 }, + { url = "https://files.pythonhosted.org/packages/2b/f1/e40c8373e3480e4f29f2692bd21b3e05f296d3afebc7e5dcf21b9756ca1c/regex-2024.11.6-cp313-cp313-win32.whl", hash = "sha256:63b13cfd72e9601125027202cad74995ab26921d8cd935c25f09c630436348ff", size = 262122 }, + { url = "https://files.pythonhosted.org/packages/45/94/bc295babb3062a731f52621cdc992d123111282e291abaf23faa413443ea/regex-2024.11.6-cp313-cp313-win_amd64.whl", hash = "sha256:2b3361af3198667e99927da8b84c1b010752fa4b1115ee30beaa332cabc3ef1a", size = 273545 }, + { url = "https://files.pythonhosted.org/packages/89/23/c4a86df398e57e26f93b13ae63acce58771e04bdde86092502496fa57f9c/regex-2024.11.6-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:5704e174f8ccab2026bd2f1ab6c510345ae8eac818b613d7d73e785f1310f839", size = 482682 }, + { url = "https://files.pythonhosted.org/packages/3c/8b/45c24ab7a51a1658441b961b86209c43e6bb9d39caf1e63f46ce6ea03bc7/regex-2024.11.6-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:220902c3c5cc6af55d4fe19ead504de80eb91f786dc102fbd74894b1551f095e", size = 287679 }, + { url = "https://files.pythonhosted.org/packages/7a/d1/598de10b17fdafc452d11f7dada11c3be4e379a8671393e4e3da3c4070df/regex-2024.11.6-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:5e7e351589da0850c125f1600a4c4ba3c722efefe16b297de54300f08d734fbf", size = 284578 }, + { url = "https://files.pythonhosted.org/packages/49/70/c7eaa219efa67a215846766fde18d92d54cb590b6a04ffe43cef30057622/regex-2024.11.6-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5056b185ca113c88e18223183aa1a50e66507769c9640a6ff75859619d73957b", size = 782012 }, + { url = "https://files.pythonhosted.org/packages/89/e5/ef52c7eb117dd20ff1697968219971d052138965a4d3d9b95e92e549f505/regex-2024.11.6-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2e34b51b650b23ed3354b5a07aab37034d9f923db2a40519139af34f485f77d0", size = 820580 }, + { url = "https://files.pythonhosted.org/packages/5f/3f/9f5da81aff1d4167ac52711acf789df13e789fe6ac9545552e49138e3282/regex-2024.11.6-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5670bce7b200273eee1840ef307bfa07cda90b38ae56e9a6ebcc9f50da9c469b", size = 809110 }, + { url = "https://files.pythonhosted.org/packages/86/44/2101cc0890c3621b90365c9ee8d7291a597c0722ad66eccd6ffa7f1bcc09/regex-2024.11.6-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:08986dce1339bc932923e7d1232ce9881499a0e02925f7402fb7c982515419ef", size = 780919 }, + { url = "https://files.pythonhosted.org/packages/ce/2e/3e0668d8d1c7c3c0d397bf54d92fc182575b3a26939aed5000d3cc78760f/regex-2024.11.6-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:93c0b12d3d3bc25af4ebbf38f9ee780a487e8bf6954c115b9f015822d3bb8e48", size = 771515 }, + { url = "https://files.pythonhosted.org/packages/a6/49/1bc4584254355e3dba930a3a2fd7ad26ccba3ebbab7d9100db0aff2eedb0/regex-2024.11.6-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:764e71f22ab3b305e7f4c21f1a97e1526a25ebdd22513e251cf376760213da13", size = 696957 }, + { url = "https://files.pythonhosted.org/packages/c8/dd/42879c1fc8a37a887cd08e358af3d3ba9e23038cd77c7fe044a86d9450ba/regex-2024.11.6-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:f056bf21105c2515c32372bbc057f43eb02aae2fda61052e2f7622c801f0b4e2", size = 768088 }, + { url = "https://files.pythonhosted.org/packages/89/96/c05a0fe173cd2acd29d5e13c1adad8b706bcaa71b169e1ee57dcf2e74584/regex-2024.11.6-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:69ab78f848845569401469da20df3e081e6b5a11cb086de3eed1d48f5ed57c95", size = 774752 }, + { url = "https://files.pythonhosted.org/packages/b5/f3/a757748066255f97f14506483436c5f6aded7af9e37bca04ec30c90ca683/regex-2024.11.6-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:86fddba590aad9208e2fa8b43b4c098bb0ec74f15718bb6a704e3c63e2cef3e9", size = 838862 }, + { url = "https://files.pythonhosted.org/packages/5c/93/c6d2092fd479dcaeea40fc8fa673822829181ded77d294a7f950f1dda6e2/regex-2024.11.6-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:684d7a212682996d21ca12ef3c17353c021fe9de6049e19ac8481ec35574a70f", size = 842622 }, + { url = "https://files.pythonhosted.org/packages/ff/9c/daa99532c72f25051a90ef90e1413a8d54413a9e64614d9095b0c1c154d0/regex-2024.11.6-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:a03e02f48cd1abbd9f3b7e3586d97c8f7a9721c436f51a5245b3b9483044480b", size = 772713 }, + { url = "https://files.pythonhosted.org/packages/13/5d/61a533ccb8c231b474ac8e3a7d70155b00dfc61af6cafdccd1947df6d735/regex-2024.11.6-cp39-cp39-win32.whl", hash = "sha256:41758407fc32d5c3c5de163888068cfee69cb4c2be844e7ac517a52770f9af57", size = 261756 }, + { url = "https://files.pythonhosted.org/packages/dc/7b/e59b7f7c91ae110d154370c24133f947262525b5d6406df65f23422acc17/regex-2024.11.6-cp39-cp39-win_amd64.whl", hash = "sha256:b2837718570f95dd41675328e111345f9b7095d821bac435aac173ac80b19983", size = 274110 }, +] + [[package]] name = "requests" version = "2.32.3" @@ -1667,6 +2300,127 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/19/71/39c7c0d87f8d4e6c020a393182060eaefeeae6c01dab6a84ec346f2567df/rich-13.9.4-py3-none-any.whl", hash = "sha256:6049d5e6ec054bf2779ab3358186963bac2ea89175919d699e378b99738c2a90", size = 242424 }, ] +[[package]] +name = "rpds-py" +version = "0.24.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/0b/b3/52b213298a0ba7097c7ea96bee95e1947aa84cc816d48cebb539770cdf41/rpds_py-0.24.0.tar.gz", hash = "sha256:772cc1b2cd963e7e17e6cc55fe0371fb9c704d63e44cacec7b9b7f523b78919e", size = 26863 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/6a/21/cbc43b220c9deb536b07fbd598c97d463bbb7afb788851891252fc920742/rpds_py-0.24.0-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:006f4342fe729a368c6df36578d7a348c7c716be1da0a1a0f86e3021f8e98724", size = 377531 }, + { url = "https://files.pythonhosted.org/packages/42/15/cc4b09ef160483e49c3aab3b56f3d375eadf19c87c48718fb0147e86a446/rpds_py-0.24.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:2d53747da70a4e4b17f559569d5f9506420966083a31c5fbd84e764461c4444b", size = 362273 }, + { url = "https://files.pythonhosted.org/packages/8c/a2/67718a188a88dbd5138d959bed6efe1cc7413a4caa8283bd46477ed0d1ad/rpds_py-0.24.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e8acd55bd5b071156bae57b555f5d33697998752673b9de554dd82f5b5352727", size = 388111 }, + { url = "https://files.pythonhosted.org/packages/e5/e6/cbf1d3163405ad5f4a1a6d23f80245f2204d0c743b18525f34982dec7f4d/rpds_py-0.24.0-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:7e80d375134ddb04231a53800503752093dbb65dad8dabacce2c84cccc78e964", size = 394447 }, + { url = "https://files.pythonhosted.org/packages/21/bb/4fe220ccc8a549b38b9e9cec66212dc3385a82a5ee9e37b54411cce4c898/rpds_py-0.24.0-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:60748789e028d2a46fc1c70750454f83c6bdd0d05db50f5ae83e2db500b34da5", size = 448028 }, + { url = "https://files.pythonhosted.org/packages/a5/41/d2d6e0fd774818c4cadb94185d30cf3768de1c2a9e0143fc8bc6ce59389e/rpds_py-0.24.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:6e1daf5bf6c2be39654beae83ee6b9a12347cb5aced9a29eecf12a2d25fff664", size = 447410 }, + { url = "https://files.pythonhosted.org/packages/a7/a7/6d04d438f53d8bb2356bb000bea9cf5c96a9315e405b577117e344cc7404/rpds_py-0.24.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1b221c2457d92a1fb3c97bee9095c874144d196f47c038462ae6e4a14436f7bc", size = 389531 }, + { url = "https://files.pythonhosted.org/packages/23/be/72e6df39bd7ca5a66799762bf54d8e702483fdad246585af96723109d486/rpds_py-0.24.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:66420986c9afff67ef0c5d1e4cdc2d0e5262f53ad11e4f90e5e22448df485bf0", size = 420099 }, + { url = "https://files.pythonhosted.org/packages/8c/c9/ca100cd4688ee0aa266197a5cb9f685231676dd7d573041ca53787b23f4e/rpds_py-0.24.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:43dba99f00f1d37b2a0265a259592d05fcc8e7c19d140fe51c6e6f16faabeb1f", size = 564950 }, + { url = "https://files.pythonhosted.org/packages/05/98/908cd95686d33b3ac8ac2e582d7ae38e2c3aa2c0377bf1f5663bafd1ffb2/rpds_py-0.24.0-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:a88c0d17d039333a41d9bf4616bd062f0bd7aa0edeb6cafe00a2fc2a804e944f", size = 591778 }, + { url = "https://files.pythonhosted.org/packages/7b/ac/e143726f1dd3215efcb974b50b03bd08a8a1556b404a0a7872af6d197e57/rpds_py-0.24.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:cc31e13ce212e14a539d430428cd365e74f8b2d534f8bc22dd4c9c55b277b875", size = 560421 }, + { url = "https://files.pythonhosted.org/packages/60/28/add1c1d2fcd5aa354f7225d036d4492261759a22d449cff14841ef36a514/rpds_py-0.24.0-cp310-cp310-win32.whl", hash = "sha256:fc2c1e1b00f88317d9de6b2c2b39b012ebbfe35fe5e7bef980fd2a91f6100a07", size = 222089 }, + { url = "https://files.pythonhosted.org/packages/b0/ac/81f8066c6de44c507caca488ba336ae30d35d57f61fe10578824d1a70196/rpds_py-0.24.0-cp310-cp310-win_amd64.whl", hash = "sha256:c0145295ca415668420ad142ee42189f78d27af806fcf1f32a18e51d47dd2052", size = 234622 }, + { url = "https://files.pythonhosted.org/packages/80/e6/c1458bbfb257448fdb2528071f1f4e19e26798ed5ef6d47d7aab0cb69661/rpds_py-0.24.0-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:2d3ee4615df36ab8eb16c2507b11e764dcc11fd350bbf4da16d09cda11fcedef", size = 377679 }, + { url = "https://files.pythonhosted.org/packages/dd/26/ea4181ef78f58b2c167548c6a833d7dc22408e5b3b181bda9dda440bb92d/rpds_py-0.24.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:e13ae74a8a3a0c2f22f450f773e35f893484fcfacb00bb4344a7e0f4f48e1f97", size = 362571 }, + { url = "https://files.pythonhosted.org/packages/56/fa/1ec54dd492c64c280a2249a047fc3369e2789dc474eac20445ebfc72934b/rpds_py-0.24.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cf86f72d705fc2ef776bb7dd9e5fbba79d7e1f3e258bf9377f8204ad0fc1c51e", size = 388012 }, + { url = "https://files.pythonhosted.org/packages/3a/be/bad8b0e0f7e58ef4973bb75e91c472a7d51da1977ed43b09989264bf065c/rpds_py-0.24.0-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:c43583ea8517ed2e780a345dd9960896afc1327e8cf3ac8239c167530397440d", size = 394730 }, + { url = "https://files.pythonhosted.org/packages/35/56/ab417fc90c21826df048fc16e55316ac40876e4b790104ececcbce813d8f/rpds_py-0.24.0-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4cd031e63bc5f05bdcda120646a0d32f6d729486d0067f09d79c8db5368f4586", size = 448264 }, + { url = "https://files.pythonhosted.org/packages/b6/75/4c63862d5c05408589196c8440a35a14ea4ae337fa70ded1f03638373f06/rpds_py-0.24.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:34d90ad8c045df9a4259c47d2e16a3f21fdb396665c94520dbfe8766e62187a4", size = 446813 }, + { url = "https://files.pythonhosted.org/packages/e7/0c/91cf17dffa9a38835869797a9f041056091ebba6a53963d3641207e3d467/rpds_py-0.24.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e838bf2bb0b91ee67bf2b889a1a841e5ecac06dd7a2b1ef4e6151e2ce155c7ae", size = 389438 }, + { url = "https://files.pythonhosted.org/packages/1b/b0/60e6c72727c978276e02851819f3986bc40668f115be72c1bc4d922c950f/rpds_py-0.24.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:04ecf5c1ff4d589987b4d9882872f80ba13da7d42427234fce8f22efb43133bc", size = 420416 }, + { url = "https://files.pythonhosted.org/packages/a1/d7/f46f85b9f863fb59fd3c534b5c874c48bee86b19e93423b9da8784605415/rpds_py-0.24.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:630d3d8ea77eabd6cbcd2ea712e1c5cecb5b558d39547ac988351195db433f6c", size = 565236 }, + { url = "https://files.pythonhosted.org/packages/2a/d1/1467620ded6dd70afc45ec822cdf8dfe7139537780d1f3905de143deb6fd/rpds_py-0.24.0-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:ebcb786b9ff30b994d5969213a8430cbb984cdd7ea9fd6df06663194bd3c450c", size = 592016 }, + { url = "https://files.pythonhosted.org/packages/5d/13/fb1ded2e6adfaa0c0833106c42feb290973f665300f4facd5bf5d7891d9c/rpds_py-0.24.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:174e46569968ddbbeb8a806d9922f17cd2b524aa753b468f35b97ff9c19cb718", size = 560123 }, + { url = "https://files.pythonhosted.org/packages/1e/df/09fc1857ac7cc2eb16465a7199c314cbce7edde53c8ef21d615410d7335b/rpds_py-0.24.0-cp311-cp311-win32.whl", hash = "sha256:5ef877fa3bbfb40b388a5ae1cb00636a624690dcb9a29a65267054c9ea86d88a", size = 222256 }, + { url = "https://files.pythonhosted.org/packages/ff/25/939b40bc4d54bf910e5ee60fb5af99262c92458f4948239e8c06b0b750e7/rpds_py-0.24.0-cp311-cp311-win_amd64.whl", hash = "sha256:e274f62cbd274359eff63e5c7e7274c913e8e09620f6a57aae66744b3df046d6", size = 234718 }, + { url = "https://files.pythonhosted.org/packages/1a/e0/1c55f4a3be5f1ca1a4fd1f3ff1504a1478c1ed48d84de24574c4fa87e921/rpds_py-0.24.0-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:d8551e733626afec514b5d15befabea0dd70a343a9f23322860c4f16a9430205", size = 366945 }, + { url = "https://files.pythonhosted.org/packages/39/1b/a3501574fbf29118164314dbc800d568b8c1c7b3258b505360e8abb3902c/rpds_py-0.24.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:0e374c0ce0ca82e5b67cd61fb964077d40ec177dd2c4eda67dba130de09085c7", size = 351935 }, + { url = "https://files.pythonhosted.org/packages/dc/47/77d3d71c55f6a374edde29f1aca0b2e547325ed00a9da820cabbc9497d2b/rpds_py-0.24.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d69d003296df4840bd445a5d15fa5b6ff6ac40496f956a221c4d1f6f7b4bc4d9", size = 390817 }, + { url = "https://files.pythonhosted.org/packages/4e/ec/1e336ee27484379e19c7f9cc170f4217c608aee406d3ae3a2e45336bff36/rpds_py-0.24.0-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:8212ff58ac6dfde49946bea57474a386cca3f7706fc72c25b772b9ca4af6b79e", size = 401983 }, + { url = "https://files.pythonhosted.org/packages/07/f8/39b65cbc272c635eaea6d393c2ad1ccc81c39eca2db6723a0ca4b2108fce/rpds_py-0.24.0-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:528927e63a70b4d5f3f5ccc1fa988a35456eb5d15f804d276709c33fc2f19bda", size = 451719 }, + { url = "https://files.pythonhosted.org/packages/32/05/05c2b27dd9c30432f31738afed0300659cb9415db0ff7429b05dfb09bbde/rpds_py-0.24.0-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a824d2c7a703ba6daaca848f9c3d5cb93af0505be505de70e7e66829affd676e", size = 442546 }, + { url = "https://files.pythonhosted.org/packages/7d/e0/19383c8b5d509bd741532a47821c3e96acf4543d0832beba41b4434bcc49/rpds_py-0.24.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:44d51febb7a114293ffd56c6cf4736cb31cd68c0fddd6aa303ed09ea5a48e029", size = 393695 }, + { url = "https://files.pythonhosted.org/packages/9d/15/39f14e96d94981d0275715ae8ea564772237f3fa89bc3c21e24de934f2c7/rpds_py-0.24.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:3fab5f4a2c64a8fb64fc13b3d139848817a64d467dd6ed60dcdd6b479e7febc9", size = 427218 }, + { url = "https://files.pythonhosted.org/packages/22/b9/12da7124905a680f690da7a9de6f11de770b5e359f5649972f7181c8bf51/rpds_py-0.24.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:9be4f99bee42ac107870c61dfdb294d912bf81c3c6d45538aad7aecab468b6b7", size = 568062 }, + { url = "https://files.pythonhosted.org/packages/88/17/75229017a2143d915f6f803721a6d721eca24f2659c5718a538afa276b4f/rpds_py-0.24.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:564c96b6076a98215af52f55efa90d8419cc2ef45d99e314fddefe816bc24f91", size = 596262 }, + { url = "https://files.pythonhosted.org/packages/aa/64/8e8a1d8bd1b6b638d6acb6d41ab2cec7f2067a5b8b4c9175703875159a7c/rpds_py-0.24.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:75a810b7664c17f24bf2ffd7f92416c00ec84b49bb68e6a0d93e542406336b56", size = 564306 }, + { url = "https://files.pythonhosted.org/packages/68/1c/a7eac8d8ed8cb234a9b1064647824c387753343c3fab6ed7c83481ed0be7/rpds_py-0.24.0-cp312-cp312-win32.whl", hash = "sha256:f6016bd950be4dcd047b7475fdf55fb1e1f59fc7403f387be0e8123e4a576d30", size = 224281 }, + { url = "https://files.pythonhosted.org/packages/bb/46/b8b5424d1d21f2f2f3f2d468660085318d4f74a8df8289e3dd6ad224d488/rpds_py-0.24.0-cp312-cp312-win_amd64.whl", hash = "sha256:998c01b8e71cf051c28f5d6f1187abbdf5cf45fc0efce5da6c06447cba997034", size = 239719 }, + { url = "https://files.pythonhosted.org/packages/9d/c3/3607abc770395bc6d5a00cb66385a5479fb8cd7416ddef90393b17ef4340/rpds_py-0.24.0-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:3d2d8e4508e15fc05b31285c4b00ddf2e0eb94259c2dc896771966a163122a0c", size = 367072 }, + { url = "https://files.pythonhosted.org/packages/d8/35/8c7ee0fe465793e3af3298dc5a9f3013bd63e7a69df04ccfded8293a4982/rpds_py-0.24.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:0f00c16e089282ad68a3820fd0c831c35d3194b7cdc31d6e469511d9bffc535c", size = 351919 }, + { url = "https://files.pythonhosted.org/packages/91/d3/7e1b972501eb5466b9aca46a9c31bcbbdc3ea5a076e9ab33f4438c1d069d/rpds_py-0.24.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:951cc481c0c395c4a08639a469d53b7d4afa252529a085418b82a6b43c45c240", size = 390360 }, + { url = "https://files.pythonhosted.org/packages/a2/a8/ccabb50d3c91c26ad01f9b09a6a3b03e4502ce51a33867c38446df9f896b/rpds_py-0.24.0-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:c9ca89938dff18828a328af41ffdf3902405a19f4131c88e22e776a8e228c5a8", size = 400704 }, + { url = "https://files.pythonhosted.org/packages/53/ae/5fa5bf0f3bc6ce21b5ea88fc0ecd3a439e7cb09dd5f9ffb3dbe1b6894fc5/rpds_py-0.24.0-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ed0ef550042a8dbcd657dfb284a8ee00f0ba269d3f2286b0493b15a5694f9fe8", size = 450839 }, + { url = "https://files.pythonhosted.org/packages/e3/ac/c4e18b36d9938247e2b54f6a03746f3183ca20e1edd7d3654796867f5100/rpds_py-0.24.0-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2b2356688e5d958c4d5cb964af865bea84db29971d3e563fb78e46e20fe1848b", size = 441494 }, + { url = "https://files.pythonhosted.org/packages/bf/08/b543969c12a8f44db6c0f08ced009abf8f519191ca6985509e7c44102e3c/rpds_py-0.24.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:78884d155fd15d9f64f5d6124b486f3d3f7fd7cd71a78e9670a0f6f6ca06fb2d", size = 393185 }, + { url = "https://files.pythonhosted.org/packages/da/7e/f6eb6a7042ce708f9dfc781832a86063cea8a125bbe451d663697b51944f/rpds_py-0.24.0-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:6a4a535013aeeef13c5532f802708cecae8d66c282babb5cd916379b72110cf7", size = 426168 }, + { url = "https://files.pythonhosted.org/packages/38/b0/6cd2bb0509ac0b51af4bb138e145b7c4c902bb4b724d6fd143689d6e0383/rpds_py-0.24.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:84e0566f15cf4d769dade9b366b7b87c959be472c92dffb70462dd0844d7cbad", size = 567622 }, + { url = "https://files.pythonhosted.org/packages/64/b0/c401f4f077547d98e8b4c2ec6526a80e7cb04f519d416430ec1421ee9e0b/rpds_py-0.24.0-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:823e74ab6fbaa028ec89615ff6acb409e90ff45580c45920d4dfdddb069f2120", size = 595435 }, + { url = "https://files.pythonhosted.org/packages/9f/ec/7993b6e803294c87b61c85bd63e11142ccfb2373cf88a61ec602abcbf9d6/rpds_py-0.24.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:c61a2cb0085c8783906b2f8b1f16a7e65777823c7f4d0a6aaffe26dc0d358dd9", size = 563762 }, + { url = "https://files.pythonhosted.org/packages/1f/29/4508003204cb2f461dc2b83dd85f8aa2b915bc98fe6046b9d50d4aa05401/rpds_py-0.24.0-cp313-cp313-win32.whl", hash = "sha256:60d9b630c8025b9458a9d114e3af579a2c54bd32df601c4581bd054e85258143", size = 223510 }, + { url = "https://files.pythonhosted.org/packages/f9/12/09e048d1814195e01f354155fb772fb0854bd3450b5f5a82224b3a319f0e/rpds_py-0.24.0-cp313-cp313-win_amd64.whl", hash = "sha256:6eea559077d29486c68218178ea946263b87f1c41ae7f996b1f30a983c476a5a", size = 239075 }, + { url = "https://files.pythonhosted.org/packages/d2/03/5027cde39bb2408d61e4dd0cf81f815949bb629932a6c8df1701d0257fc4/rpds_py-0.24.0-cp313-cp313t-macosx_10_12_x86_64.whl", hash = "sha256:d09dc82af2d3c17e7dd17120b202a79b578d79f2b5424bda209d9966efeed114", size = 362974 }, + { url = "https://files.pythonhosted.org/packages/bf/10/24d374a2131b1ffafb783e436e770e42dfdb74b69a2cd25eba8c8b29d861/rpds_py-0.24.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:5fc13b44de6419d1e7a7e592a4885b323fbc2f46e1f22151e3a8ed3b8b920405", size = 348730 }, + { url = "https://files.pythonhosted.org/packages/7a/d1/1ef88d0516d46cd8df12e5916966dbf716d5ec79b265eda56ba1b173398c/rpds_py-0.24.0-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c347a20d79cedc0a7bd51c4d4b7dbc613ca4e65a756b5c3e57ec84bd43505b47", size = 387627 }, + { url = "https://files.pythonhosted.org/packages/4e/35/07339051b8b901ecefd449ebf8e5522e92bcb95e1078818cbfd9db8e573c/rpds_py-0.24.0-cp313-cp313t-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:20f2712bd1cc26a3cc16c5a1bfee9ed1abc33d4cdf1aabd297fe0eb724df4272", size = 394094 }, + { url = "https://files.pythonhosted.org/packages/dc/62/ee89ece19e0ba322b08734e95441952062391065c157bbd4f8802316b4f1/rpds_py-0.24.0-cp313-cp313t-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:aad911555286884be1e427ef0dc0ba3929e6821cbeca2194b13dc415a462c7fd", size = 449639 }, + { url = "https://files.pythonhosted.org/packages/15/24/b30e9f9e71baa0b9dada3a4ab43d567c6b04a36d1cb531045f7a8a0a7439/rpds_py-0.24.0-cp313-cp313t-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:0aeb3329c1721c43c58cae274d7d2ca85c1690d89485d9c63a006cb79a85771a", size = 438584 }, + { url = "https://files.pythonhosted.org/packages/28/d9/49f7b8f3b4147db13961e19d5e30077cd0854ccc08487026d2cb2142aa4a/rpds_py-0.24.0-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2a0f156e9509cee987283abd2296ec816225145a13ed0391df8f71bf1d789e2d", size = 391047 }, + { url = "https://files.pythonhosted.org/packages/49/b0/e66918d0972c33a259ba3cd7b7ff10ed8bd91dbcfcbec6367b21f026db75/rpds_py-0.24.0-cp313-cp313t-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:aa6800adc8204ce898c8a424303969b7aa6a5e4ad2789c13f8648739830323b7", size = 418085 }, + { url = "https://files.pythonhosted.org/packages/e1/6b/99ed7ea0a94c7ae5520a21be77a82306aac9e4e715d4435076ead07d05c6/rpds_py-0.24.0-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:a18fc371e900a21d7392517c6f60fe859e802547309e94313cd8181ad9db004d", size = 564498 }, + { url = "https://files.pythonhosted.org/packages/28/26/1cacfee6b800e6fb5f91acecc2e52f17dbf8b0796a7c984b4568b6d70e38/rpds_py-0.24.0-cp313-cp313t-musllinux_1_2_i686.whl", hash = "sha256:9168764133fd919f8dcca2ead66de0105f4ef5659cbb4fa044f7014bed9a1797", size = 590202 }, + { url = "https://files.pythonhosted.org/packages/a9/9e/57bd2f9fba04a37cef673f9a66b11ca8c43ccdd50d386c455cd4380fe461/rpds_py-0.24.0-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:5f6e3cec44ba05ee5cbdebe92d052f69b63ae792e7d05f1020ac5e964394080c", size = 561771 }, + { url = "https://files.pythonhosted.org/packages/9f/cf/b719120f375ab970d1c297dbf8de1e3c9edd26fe92c0ed7178dd94b45992/rpds_py-0.24.0-cp313-cp313t-win32.whl", hash = "sha256:8ebc7e65ca4b111d928b669713865f021b7773350eeac4a31d3e70144297baba", size = 221195 }, + { url = "https://files.pythonhosted.org/packages/2d/e5/22865285789f3412ad0c3d7ec4dc0a3e86483b794be8a5d9ed5a19390900/rpds_py-0.24.0-cp313-cp313t-win_amd64.whl", hash = "sha256:675269d407a257b8c00a6b58205b72eec8231656506c56fd429d924ca00bb350", size = 237354 }, + { url = "https://files.pythonhosted.org/packages/22/ef/a194eaef0d0f2cd3f4c893c5b809a7458aaa7c0a64e60a45a72a04835ed4/rpds_py-0.24.0-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:a36b452abbf29f68527cf52e181fced56685731c86b52e852053e38d8b60bc8d", size = 378126 }, + { url = "https://files.pythonhosted.org/packages/c3/8d/9a07f69933204c098760c884f03835ab8fb66e28d2d5f3dd6741720cf29c/rpds_py-0.24.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:8b3b397eefecec8e8e39fa65c630ef70a24b09141a6f9fc17b3c3a50bed6b50e", size = 362887 }, + { url = "https://files.pythonhosted.org/packages/29/74/315f42060f2e3cedd77d382a98484a68ef727bd3b5fd7b91825b859a3e85/rpds_py-0.24.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cdabcd3beb2a6dca7027007473d8ef1c3b053347c76f685f5f060a00327b8b65", size = 388661 }, + { url = "https://files.pythonhosted.org/packages/29/22/7ee7bb2b25ecdfcf1265d5a51472814fe60b580f9e1e2746eed9c476310a/rpds_py-0.24.0-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:5db385bacd0c43f24be92b60c857cf760b7f10d8234f4bd4be67b5b20a7c0b6b", size = 394993 }, + { url = "https://files.pythonhosted.org/packages/46/7b/5f40e278d81cd23eea6b88bbac62bacc27ed19412051a1fc4229e8f9367a/rpds_py-0.24.0-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8097b3422d020ff1c44effc40ae58e67d93e60d540a65649d2cdaf9466030791", size = 448706 }, + { url = "https://files.pythonhosted.org/packages/5a/7a/06aada7ecdb0d02fbc041daee998ae841882fcc8ed3c0f84e72d6832fef1/rpds_py-0.24.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:493fe54318bed7d124ce272fc36adbf59d46729659b2c792e87c3b95649cdee9", size = 447369 }, + { url = "https://files.pythonhosted.org/packages/c6/f3/428a9367077268f852db9b3b68b6eda6ee4594ab7dc2d603a2c370619cc0/rpds_py-0.24.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8aa362811ccdc1f8dadcc916c6d47e554169ab79559319ae9fae7d7752d0d60c", size = 390012 }, + { url = "https://files.pythonhosted.org/packages/55/66/24b61f14cd54e525583404afe6e3c221b309d1abd4b0b597a566dd8ee42d/rpds_py-0.24.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:d8f9a6e7fd5434817526815f09ea27f2746c4a51ee11bb3439065f5fc754db58", size = 421576 }, + { url = "https://files.pythonhosted.org/packages/22/56/18b81a4f0550e0d4be700cdcf1415ebf250fd21f9a5a775843dd3588dbf6/rpds_py-0.24.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:8205ee14463248d3349131bb8099efe15cd3ce83b8ef3ace63c7e976998e7124", size = 565562 }, + { url = "https://files.pythonhosted.org/packages/42/80/82a935d78f74974f82d38e83fb02430f8e8cc09ad35e06d9a5d2e9b907a7/rpds_py-0.24.0-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:921ae54f9ecba3b6325df425cf72c074cd469dea843fb5743a26ca7fb2ccb149", size = 592924 }, + { url = "https://files.pythonhosted.org/packages/0d/49/b717e7b93c2ca881d2dac8b23b3a87a4c30f7c762bfd3df0b3953e655f13/rpds_py-0.24.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:32bab0a56eac685828e00cc2f5d1200c548f8bc11f2e44abf311d6b548ce2e45", size = 560847 }, + { url = "https://files.pythonhosted.org/packages/1e/26/ba630a291238e7f42d25bc5569d152623f18c21e9183e506585b23325c48/rpds_py-0.24.0-cp39-cp39-win32.whl", hash = "sha256:f5c0ed12926dec1dfe7d645333ea59cf93f4d07750986a586f511c0bc61fe103", size = 222570 }, + { url = "https://files.pythonhosted.org/packages/2d/84/01126e25e21f2ed6e63ec4030f78793dfee1a21aff1842136353c9caaed9/rpds_py-0.24.0-cp39-cp39-win_amd64.whl", hash = "sha256:afc6e35f344490faa8276b5f2f7cbf71f88bc2cda4328e00553bd451728c571f", size = 234931 }, + { url = "https://files.pythonhosted.org/packages/99/48/11dae46d0c7f7e156ca0971a83f89c510af0316cd5d42c771b7cef945f0c/rpds_py-0.24.0-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:619ca56a5468f933d940e1bf431c6f4e13bef8e688698b067ae68eb4f9b30e3a", size = 378224 }, + { url = "https://files.pythonhosted.org/packages/33/18/e8398d255369e35d312942f3bb8ecaff013c44968904891be2ab63b3aa94/rpds_py-0.24.0-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:4b28e5122829181de1898c2c97f81c0b3246d49f585f22743a1246420bb8d399", size = 363252 }, + { url = "https://files.pythonhosted.org/packages/17/39/dd73ba691f4df3e6834bf982de214086ac3359ab3ac035adfb30041570e3/rpds_py-0.24.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e8e5ab32cf9eb3647450bc74eb201b27c185d3857276162c101c0f8c6374e098", size = 388871 }, + { url = "https://files.pythonhosted.org/packages/2f/2e/da0530b25cabd0feca2a759b899d2df325069a94281eeea8ac44c6cfeff7/rpds_py-0.24.0-pp310-pypy310_pp73-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:208b3a70a98cf3710e97cabdc308a51cd4f28aa6e7bb11de3d56cd8b74bab98d", size = 394766 }, + { url = "https://files.pythonhosted.org/packages/4c/ee/dd1c5040a431beb40fad4a5d7868acf343444b0bc43e627c71df2506538b/rpds_py-0.24.0-pp310-pypy310_pp73-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:bbc4362e06f950c62cad3d4abf1191021b2ffaf0b31ac230fbf0526453eee75e", size = 448712 }, + { url = "https://files.pythonhosted.org/packages/f5/ec/6b93ffbb686be948e4d91ec76f4e6757f8551034b2a8176dd848103a1e34/rpds_py-0.24.0-pp310-pypy310_pp73-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ebea2821cdb5f9fef44933617be76185b80150632736f3d76e54829ab4a3b4d1", size = 447150 }, + { url = "https://files.pythonhosted.org/packages/55/d5/a1c23760adad85b432df074ced6f910dd28f222b8c60aeace5aeb9a6654e/rpds_py-0.24.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b9a4df06c35465ef4d81799999bba810c68d29972bf1c31db61bfdb81dd9d5bb", size = 390662 }, + { url = "https://files.pythonhosted.org/packages/a5/f3/419cb1f9bfbd3a48c256528c156e00f3349e3edce5ad50cbc141e71f66a5/rpds_py-0.24.0-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:d3aa13bdf38630da298f2e0d77aca967b200b8cc1473ea05248f6c5e9c9bdb44", size = 421351 }, + { url = "https://files.pythonhosted.org/packages/98/8e/62d1a55078e5ede0b3b09f35e751fa35924a34a0d44d7c760743383cd54a/rpds_py-0.24.0-pp310-pypy310_pp73-musllinux_1_2_aarch64.whl", hash = "sha256:041f00419e1da7a03c46042453598479f45be3d787eb837af382bfc169c0db33", size = 566074 }, + { url = "https://files.pythonhosted.org/packages/fc/69/b7d1003166d78685da032b3c4ff1599fa536a3cfe6e5ce2da87c9c431906/rpds_py-0.24.0-pp310-pypy310_pp73-musllinux_1_2_i686.whl", hash = "sha256:d8754d872a5dfc3c5bf9c0e059e8107451364a30d9fd50f1f1a85c4fb9481164", size = 592398 }, + { url = "https://files.pythonhosted.org/packages/ea/a8/1c98bc99338c37faadd28dd667d336df7409d77b4da999506a0b6b1c0aa2/rpds_py-0.24.0-pp310-pypy310_pp73-musllinux_1_2_x86_64.whl", hash = "sha256:896c41007931217a343eff197c34513c154267636c8056fb409eafd494c3dcdc", size = 561114 }, + { url = "https://files.pythonhosted.org/packages/2b/41/65c91443685a4c7b5f1dd271beadc4a3e063d57c3269221548dd9416e15c/rpds_py-0.24.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:92558d37d872e808944c3c96d0423b8604879a3d1c86fdad508d7ed91ea547d5", size = 235548 }, + { url = "https://files.pythonhosted.org/packages/65/53/40bcc246a8354530d51a26d2b5b9afd1deacfb0d79e67295cc74df362f52/rpds_py-0.24.0-pp311-pypy311_pp73-macosx_10_12_x86_64.whl", hash = "sha256:f9e0057a509e096e47c87f753136c9b10d7a91842d8042c2ee6866899a717c0d", size = 378386 }, + { url = "https://files.pythonhosted.org/packages/80/b0/5ea97dd2f53e3618560aa1f9674e896e63dff95a9b796879a201bc4c1f00/rpds_py-0.24.0-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:d6e109a454412ab82979c5b1b3aee0604eca4bbf9a02693bb9df027af2bfa91a", size = 363440 }, + { url = "https://files.pythonhosted.org/packages/57/9d/259b6eada6f747cdd60c9a5eb3efab15f6704c182547149926c38e5bd0d5/rpds_py-0.24.0-pp311-pypy311_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fc1c892b1ec1f8cbd5da8de287577b455e388d9c328ad592eabbdcb6fc93bee5", size = 388816 }, + { url = "https://files.pythonhosted.org/packages/94/c1/faafc7183712f89f4b7620c3c15979ada13df137d35ef3011ae83e93b005/rpds_py-0.24.0-pp311-pypy311_pp73-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:9c39438c55983d48f4bb3487734d040e22dad200dab22c41e331cee145e7a50d", size = 395058 }, + { url = "https://files.pythonhosted.org/packages/6c/96/d7fa9d2a7b7604a61da201cc0306a355006254942093779d7121c64700ce/rpds_py-0.24.0-pp311-pypy311_pp73-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9d7e8ce990ae17dda686f7e82fd41a055c668e13ddcf058e7fb5e9da20b57793", size = 448692 }, + { url = "https://files.pythonhosted.org/packages/96/37/a3146c6eebc65d6d8c96cc5ffdcdb6af2987412c789004213227fbe52467/rpds_py-0.24.0-pp311-pypy311_pp73-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9ea7f4174d2e4194289cb0c4e172d83e79a6404297ff95f2875cf9ac9bced8ba", size = 446462 }, + { url = "https://files.pythonhosted.org/packages/1f/13/6481dfd9ac7de43acdaaa416e3a7da40bc4bb8f5c6ca85e794100aa54596/rpds_py-0.24.0-pp311-pypy311_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bb2954155bb8f63bb19d56d80e5e5320b61d71084617ed89efedb861a684baea", size = 390460 }, + { url = "https://files.pythonhosted.org/packages/61/e1/37e36bce65e109543cc4ff8d23206908649023549604fa2e7fbeba5342f7/rpds_py-0.24.0-pp311-pypy311_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:04f2b712a2206e13800a8136b07aaedc23af3facab84918e7aa89e4be0260032", size = 421609 }, + { url = "https://files.pythonhosted.org/packages/20/dd/1f1a923d6cd798b8582176aca8a0784676f1a0449fb6f07fce6ac1cdbfb6/rpds_py-0.24.0-pp311-pypy311_pp73-musllinux_1_2_aarch64.whl", hash = "sha256:eda5c1e2a715a4cbbca2d6d304988460942551e4e5e3b7457b50943cd741626d", size = 565818 }, + { url = "https://files.pythonhosted.org/packages/56/ec/d8da6df6a1eb3a418944a17b1cb38dd430b9e5a2e972eafd2b06f10c7c46/rpds_py-0.24.0-pp311-pypy311_pp73-musllinux_1_2_i686.whl", hash = "sha256:9abc80fe8c1f87218db116016de575a7998ab1629078c90840e8d11ab423ee25", size = 592627 }, + { url = "https://files.pythonhosted.org/packages/b3/14/c492b9c7d5dd133e13f211ddea6bb9870f99e4f73932f11aa00bc09a9be9/rpds_py-0.24.0-pp311-pypy311_pp73-musllinux_1_2_x86_64.whl", hash = "sha256:6a727fd083009bc83eb83d6950f0c32b3c94c8b80a9b667c87f4bd1274ca30ba", size = 560885 }, + { url = "https://files.pythonhosted.org/packages/ef/e2/16cbbd7aaa4deaaeef5c90fee8b485c8b3312094cdad31e8006f5a3e5e08/rpds_py-0.24.0-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:e0f3ef95795efcd3b2ec3fe0a5bcfb5dadf5e3996ea2117427e524d4fbf309c6", size = 378245 }, + { url = "https://files.pythonhosted.org/packages/d4/8c/5024dd105bf0a515576b7df8aeeba6556ffdbe2d636dee172c1a30497dd1/rpds_py-0.24.0-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:2c13777ecdbbba2077670285dd1fe50828c8742f6a4119dbef6f83ea13ad10fb", size = 363461 }, + { url = "https://files.pythonhosted.org/packages/a4/6f/3a4efcfa2f4391b69f5d0ed3e6be5d2c5468c24fd2d15b712d2dbefc1749/rpds_py-0.24.0-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:79e8d804c2ccd618417e96720ad5cd076a86fa3f8cb310ea386a3e6229bae7d1", size = 388839 }, + { url = "https://files.pythonhosted.org/packages/6c/d2/b8e5f0a0e97d295a0ebceb5265ef2e44c3d55e0d0f938d64a5ecfffa715e/rpds_py-0.24.0-pp39-pypy39_pp73-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:fd822f019ccccd75c832deb7aa040bb02d70a92eb15a2f16c7987b7ad4ee8d83", size = 394860 }, + { url = "https://files.pythonhosted.org/packages/90/e9/9f1f297bdbc5b871826ad790b6641fc40532d97917916e6bd9f87fdd128d/rpds_py-0.24.0-pp39-pypy39_pp73-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:0047638c3aa0dbcd0ab99ed1e549bbf0e142c9ecc173b6492868432d8989a046", size = 449314 }, + { url = "https://files.pythonhosted.org/packages/06/ad/62ddbbaead31a1a22f0332958d0ea7c7aeed1b2536c6a51dd66dfae321a2/rpds_py-0.24.0-pp39-pypy39_pp73-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a5b66d1b201cc71bc3081bc2f1fc36b0c1f268b773e03bbc39066651b9e18391", size = 446376 }, + { url = "https://files.pythonhosted.org/packages/82/a7/05b660d2f3789506e98be69aaf2ccde94e0fc49cd26cd78d7069bc5ba1b8/rpds_py-0.24.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dbcbb6db5582ea33ce46a5d20a5793134b5365110d84df4e30b9d37c6fd40ad3", size = 390560 }, + { url = "https://files.pythonhosted.org/packages/66/1b/79fa0abffb802ff817821a148ce752eaaab87ba3a6a5e6b9f244c00c73d0/rpds_py-0.24.0-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:63981feca3f110ed132fd217bf7768ee8ed738a55549883628ee3da75bb9cb78", size = 421225 }, + { url = "https://files.pythonhosted.org/packages/6e/9b/368893ad2f7b2ece42cad87c7ec71309b5d93188db28b307eadb48cd28e5/rpds_py-0.24.0-pp39-pypy39_pp73-musllinux_1_2_aarch64.whl", hash = "sha256:3a55fc10fdcbf1a4bd3c018eea422c52cf08700cf99c28b5cb10fe97ab77a0d3", size = 566071 }, + { url = "https://files.pythonhosted.org/packages/41/75/1cd0a654d300449411e6fd0821f83c1cfc7223da2e8109f586b4d9b89054/rpds_py-0.24.0-pp39-pypy39_pp73-musllinux_1_2_i686.whl", hash = "sha256:c30ff468163a48535ee7e9bf21bd14c7a81147c0e58a36c1078289a8ca7af0bd", size = 592334 }, + { url = "https://files.pythonhosted.org/packages/31/33/5905e2a2e7612218e25307a9255fc8671b977449d40d62fe317775fe4939/rpds_py-0.24.0-pp39-pypy39_pp73-musllinux_1_2_x86_64.whl", hash = "sha256:369d9c6d4c714e36d4a03957b4783217a3ccd1e222cdd67d464a3a479fc17796", size = 561111 }, + { url = "https://files.pythonhosted.org/packages/64/bd/f4cc34ac2261a7cb8a48bc90ce1e36dc05f1ec5ac3b4537def20be5df555/rpds_py-0.24.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:24795c099453e3721fda5d8ddd45f5dfcc8e5a547ce7b8e9da06fecc3832e26f", size = 235168 }, +] + [[package]] name = "ruff" version = "0.9.2" @@ -1740,19 +2494,20 @@ wheels = [ [[package]] name = "starlette" -version = "0.46.1" +version = "0.46.2" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "anyio", marker = "python_full_version >= '3.10'" }, + { name = "anyio" }, + { name = "typing-extensions", marker = "python_full_version < '3.10'" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/04/1b/52b27f2e13ceedc79a908e29eac426a63465a1a01248e5f24aa36a62aeb3/starlette-0.46.1.tar.gz", hash = "sha256:3c88d58ee4bd1bb807c0d1acb381838afc7752f9ddaec81bbe4383611d833230", size = 2580102 } +sdist = { url = "https://files.pythonhosted.org/packages/ce/20/08dfcd9c983f6a6f4a1000d934b9e6d626cff8d2eeb77a89a68eef20a2b7/starlette-0.46.2.tar.gz", hash = "sha256:7f7361f34eed179294600af672f565727419830b54b7b084efe44bb82d2fccd5", size = 2580846 } wheels = [ - { url = "https://files.pythonhosted.org/packages/a0/4b/528ccf7a982216885a1ff4908e886b8fb5f19862d1962f56a3fce2435a70/starlette-0.46.1-py3-none-any.whl", hash = "sha256:77c74ed9d2720138b25875133f3a2dae6d854af2ec37dceb56aef370c1d8a227", size = 71995 }, + { url = "https://files.pythonhosted.org/packages/8b/0c/9d30a4ebeb6db2b25a841afbb80f6ef9a854fc3b41be131d249a977b4959/starlette-0.46.2-py3-none-any.whl", hash = "sha256:595633ce89f8ffa71a015caed34a5b2dc1c0cdb3f0f1fbd1e69339cf2abeec35", size = 72037 }, ] [[package]] name = "textual" -version = "2.1.2" +version = "3.1.0" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "markdown-it-py", extra = ["linkify", "plugins"] }, @@ -1760,9 +2515,76 @@ dependencies = [ { name = "rich" }, { name = "typing-extensions" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/41/62/4af4689dd971ed4fb3215467624016d53550bff1df9ca02e7625eec07f8b/textual-2.1.2.tar.gz", hash = "sha256:aae3f9fde00c7440be00e3c3ac189e02d014f5298afdc32132f93480f9e09146", size = 1596600 } +sdist = { url = "https://files.pythonhosted.org/packages/dc/1f/df371f1455524a3d0079871e49e3850c82767904e9f4e2bdea6d30a866a7/textual-3.1.0.tar.gz", hash = "sha256:6bcab6581e9753d2a2043caf49f43c5818feb35f8049ed185bd38982bfb310ca", size = 1591879 } wheels = [ - { url = "https://files.pythonhosted.org/packages/07/81/9df1988c908cbba77f10fecb8587496b3dff2838d4510457877a521d87fd/textual-2.1.2-py3-none-any.whl", hash = "sha256:95f37f49e930838e721bba8612f62114d410a3019665b6142adabc14c2fb9611", size = 680148 }, + { url = "https://files.pythonhosted.org/packages/32/6b/d6d37a5fd93c344a27c53cdc4910d8d52cedd3ae63eae3d645fb108bd591/textual-3.1.0-py3-none-any.whl", hash = "sha256:940a765b6fcd562cd88603780343dc98a4e66c1d8d42f09b6a16a474a89aca0c", size = 683799 }, +] + +[[package]] +name = "tiktoken" +version = "0.9.0" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "regex" }, + { name = "requests" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/ea/cf/756fedf6981e82897f2d570dd25fa597eb3f4459068ae0572d7e888cfd6f/tiktoken-0.9.0.tar.gz", hash = "sha256:d02a5ca6a938e0490e1ff957bc48c8b078c88cb83977be1625b1fd8aac792c5d", size = 35991 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/64/f3/50ec5709fad61641e4411eb1b9ac55b99801d71f1993c29853f256c726c9/tiktoken-0.9.0-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:586c16358138b96ea804c034b8acf3f5d3f0258bd2bc3b0227af4af5d622e382", size = 1065770 }, + { url = "https://files.pythonhosted.org/packages/d6/f8/5a9560a422cf1755b6e0a9a436e14090eeb878d8ec0f80e0cd3d45b78bf4/tiktoken-0.9.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:d9c59ccc528c6c5dd51820b3474402f69d9a9e1d656226848ad68a8d5b2e5108", size = 1009314 }, + { url = "https://files.pythonhosted.org/packages/bc/20/3ed4cfff8f809cb902900ae686069e029db74567ee10d017cb254df1d598/tiktoken-0.9.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f0968d5beeafbca2a72c595e8385a1a1f8af58feaebb02b227229b69ca5357fd", size = 1143140 }, + { url = "https://files.pythonhosted.org/packages/f1/95/cc2c6d79df8f113bdc6c99cdec985a878768120d87d839a34da4bd3ff90a/tiktoken-0.9.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:92a5fb085a6a3b7350b8fc838baf493317ca0e17bd95e8642f95fc69ecfed1de", size = 1197860 }, + { url = "https://files.pythonhosted.org/packages/c7/6c/9c1a4cc51573e8867c9381db1814223c09ebb4716779c7f845d48688b9c8/tiktoken-0.9.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:15a2752dea63d93b0332fb0ddb05dd909371ededa145fe6a3242f46724fa7990", size = 1259661 }, + { url = "https://files.pythonhosted.org/packages/cd/4c/22eb8e9856a2b1808d0a002d171e534eac03f96dbe1161978d7389a59498/tiktoken-0.9.0-cp310-cp310-win_amd64.whl", hash = "sha256:26113fec3bd7a352e4b33dbaf1bd8948de2507e30bd95a44e2b1156647bc01b4", size = 894026 }, + { url = "https://files.pythonhosted.org/packages/4d/ae/4613a59a2a48e761c5161237fc850eb470b4bb93696db89da51b79a871f1/tiktoken-0.9.0-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:f32cc56168eac4851109e9b5d327637f15fd662aa30dd79f964b7c39fbadd26e", size = 1065987 }, + { url = "https://files.pythonhosted.org/packages/3f/86/55d9d1f5b5a7e1164d0f1538a85529b5fcba2b105f92db3622e5d7de6522/tiktoken-0.9.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:45556bc41241e5294063508caf901bf92ba52d8ef9222023f83d2483a3055348", size = 1009155 }, + { url = "https://files.pythonhosted.org/packages/03/58/01fb6240df083b7c1916d1dcb024e2b761213c95d576e9f780dfb5625a76/tiktoken-0.9.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:03935988a91d6d3216e2ec7c645afbb3d870b37bcb67ada1943ec48678e7ee33", size = 1142898 }, + { url = "https://files.pythonhosted.org/packages/b1/73/41591c525680cd460a6becf56c9b17468d3711b1df242c53d2c7b2183d16/tiktoken-0.9.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8b3d80aad8d2c6b9238fc1a5524542087c52b860b10cbf952429ffb714bc1136", size = 1197535 }, + { url = "https://files.pythonhosted.org/packages/7d/7c/1069f25521c8f01a1a182f362e5c8e0337907fae91b368b7da9c3e39b810/tiktoken-0.9.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:b2a21133be05dc116b1d0372af051cd2c6aa1d2188250c9b553f9fa49301b336", size = 1259548 }, + { url = "https://files.pythonhosted.org/packages/6f/07/c67ad1724b8e14e2b4c8cca04b15da158733ac60136879131db05dda7c30/tiktoken-0.9.0-cp311-cp311-win_amd64.whl", hash = "sha256:11a20e67fdf58b0e2dea7b8654a288e481bb4fc0289d3ad21291f8d0849915fb", size = 893895 }, + { url = "https://files.pythonhosted.org/packages/cf/e5/21ff33ecfa2101c1bb0f9b6df750553bd873b7fb532ce2cb276ff40b197f/tiktoken-0.9.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:e88f121c1c22b726649ce67c089b90ddda8b9662545a8aeb03cfef15967ddd03", size = 1065073 }, + { url = "https://files.pythonhosted.org/packages/8e/03/a95e7b4863ee9ceec1c55983e4cc9558bcfd8f4f80e19c4f8a99642f697d/tiktoken-0.9.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:a6600660f2f72369acb13a57fb3e212434ed38b045fd8cc6cdd74947b4b5d210", size = 1008075 }, + { url = "https://files.pythonhosted.org/packages/40/10/1305bb02a561595088235a513ec73e50b32e74364fef4de519da69bc8010/tiktoken-0.9.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:95e811743b5dfa74f4b227927ed86cbc57cad4df859cb3b643be797914e41794", size = 1140754 }, + { url = "https://files.pythonhosted.org/packages/1b/40/da42522018ca496432ffd02793c3a72a739ac04c3794a4914570c9bb2925/tiktoken-0.9.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:99376e1370d59bcf6935c933cb9ba64adc29033b7e73f5f7569f3aad86552b22", size = 1196678 }, + { url = "https://files.pythonhosted.org/packages/5c/41/1e59dddaae270ba20187ceb8aa52c75b24ffc09f547233991d5fd822838b/tiktoken-0.9.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:badb947c32739fb6ddde173e14885fb3de4d32ab9d8c591cbd013c22b4c31dd2", size = 1259283 }, + { url = "https://files.pythonhosted.org/packages/5b/64/b16003419a1d7728d0d8c0d56a4c24325e7b10a21a9dd1fc0f7115c02f0a/tiktoken-0.9.0-cp312-cp312-win_amd64.whl", hash = "sha256:5a62d7a25225bafed786a524c1b9f0910a1128f4232615bf3f8257a73aaa3b16", size = 894897 }, + { url = "https://files.pythonhosted.org/packages/7a/11/09d936d37f49f4f494ffe660af44acd2d99eb2429d60a57c71318af214e0/tiktoken-0.9.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:2b0e8e05a26eda1249e824156d537015480af7ae222ccb798e5234ae0285dbdb", size = 1064919 }, + { url = "https://files.pythonhosted.org/packages/80/0e/f38ba35713edb8d4197ae602e80837d574244ced7fb1b6070b31c29816e0/tiktoken-0.9.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:27d457f096f87685195eea0165a1807fae87b97b2161fe8c9b1df5bd74ca6f63", size = 1007877 }, + { url = "https://files.pythonhosted.org/packages/fe/82/9197f77421e2a01373e27a79dd36efdd99e6b4115746ecc553318ecafbf0/tiktoken-0.9.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2cf8ded49cddf825390e36dd1ad35cd49589e8161fdcb52aa25f0583e90a3e01", size = 1140095 }, + { url = "https://files.pythonhosted.org/packages/f2/bb/4513da71cac187383541facd0291c4572b03ec23c561de5811781bbd988f/tiktoken-0.9.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cc156cb314119a8bb9748257a2eaebd5cc0753b6cb491d26694ed42fc7cb3139", size = 1195649 }, + { url = "https://files.pythonhosted.org/packages/fa/5c/74e4c137530dd8504e97e3a41729b1103a4ac29036cbfd3250b11fd29451/tiktoken-0.9.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:cd69372e8c9dd761f0ab873112aba55a0e3e506332dd9f7522ca466e817b1b7a", size = 1258465 }, + { url = "https://files.pythonhosted.org/packages/de/a8/8f499c179ec900783ffe133e9aab10044481679bb9aad78436d239eee716/tiktoken-0.9.0-cp313-cp313-win_amd64.whl", hash = "sha256:5ea0edb6f83dc56d794723286215918c1cde03712cbbafa0348b33448faf5b95", size = 894669 }, + { url = "https://files.pythonhosted.org/packages/c4/92/4d681b5c066d417b98f22a0176358d9e606e183c6b61c337d61fb54accb4/tiktoken-0.9.0-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:c6386ca815e7d96ef5b4ac61e0048cd32ca5a92d5781255e13b31381d28667dc", size = 1066217 }, + { url = "https://files.pythonhosted.org/packages/12/dd/af27bbe186df481666de48cf0f2f4e0643ba9c78b472e7bf70144c663b22/tiktoken-0.9.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:75f6d5db5bc2c6274b674ceab1615c1778e6416b14705827d19b40e6355f03e0", size = 1009441 }, + { url = "https://files.pythonhosted.org/packages/33/35/2792b7dcb8b150d2767322637513c73a3e80833c19212efea80b31087894/tiktoken-0.9.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e15b16f61e6f4625a57a36496d28dd182a8a60ec20a534c5343ba3cafa156ac7", size = 1144423 }, + { url = "https://files.pythonhosted.org/packages/65/ae/4d1682510172ce3500bbed3b206ebc4efefe280f0bf1179cfb043f88cc16/tiktoken-0.9.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3ebcec91babf21297022882344c3f7d9eed855931466c3311b1ad6b64befb3df", size = 1199002 }, + { url = "https://files.pythonhosted.org/packages/1c/2e/df2dc31dd161190f315829775a9652ea01d60f307af8f98e35bdd14a6a93/tiktoken-0.9.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:e5fd49e7799579240f03913447c0cdfa1129625ebd5ac440787afc4345990427", size = 1260610 }, + { url = "https://files.pythonhosted.org/packages/70/22/e8fc1bf9cdecc439b7ddc28a45b976a8c699a38874c070749d855696368a/tiktoken-0.9.0-cp39-cp39-win_amd64.whl", hash = "sha256:26242ca9dc8b58e875ff4ca078b9a94d2f0813e6a535dcd2205df5d49d927cc7", size = 894215 }, +] + +[[package]] +name = "tokenizers" +version = "0.21.1" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "huggingface-hub" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/92/76/5ac0c97f1117b91b7eb7323dcd61af80d72f790b4df71249a7850c195f30/tokenizers-0.21.1.tar.gz", hash = "sha256:a1bb04dc5b448985f86ecd4b05407f5a8d97cb2c0532199b2a302a604a0165ab", size = 343256 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/a5/1f/328aee25f9115bf04262e8b4e5a2050b7b7cf44b59c74e982db7270c7f30/tokenizers-0.21.1-cp39-abi3-macosx_10_12_x86_64.whl", hash = "sha256:e78e413e9e668ad790a29456e677d9d3aa50a9ad311a40905d6861ba7692cf41", size = 2780767 }, + { url = "https://files.pythonhosted.org/packages/ae/1a/4526797f3719b0287853f12c5ad563a9be09d446c44ac784cdd7c50f76ab/tokenizers-0.21.1-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:cd51cd0a91ecc801633829fcd1fda9cf8682ed3477c6243b9a095539de4aecf3", size = 2650555 }, + { url = "https://files.pythonhosted.org/packages/4d/7a/a209b29f971a9fdc1da86f917fe4524564924db50d13f0724feed37b2a4d/tokenizers-0.21.1-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:28da6b72d4fb14ee200a1bd386ff74ade8992d7f725f2bde2c495a9a98cf4d9f", size = 2937541 }, + { url = "https://files.pythonhosted.org/packages/3c/1e/b788b50ffc6191e0b1fc2b0d49df8cff16fe415302e5ceb89f619d12c5bc/tokenizers-0.21.1-cp39-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:34d8cfde551c9916cb92014e040806122295a6800914bab5865deb85623931cf", size = 2819058 }, + { url = "https://files.pythonhosted.org/packages/36/aa/3626dfa09a0ecc5b57a8c58eeaeb7dd7ca9a37ad9dd681edab5acd55764c/tokenizers-0.21.1-cp39-abi3-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:aaa852d23e125b73d283c98f007e06d4595732104b65402f46e8ef24b588d9f8", size = 3133278 }, + { url = "https://files.pythonhosted.org/packages/a4/4d/8fbc203838b3d26269f944a89459d94c858f5b3f9a9b6ee9728cdcf69161/tokenizers-0.21.1-cp39-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a21a15d5c8e603331b8a59548bbe113564136dc0f5ad8306dd5033459a226da0", size = 3144253 }, + { url = "https://files.pythonhosted.org/packages/d8/1b/2bd062adeb7c7511b847b32e356024980c0ffcf35f28947792c2d8ad2288/tokenizers-0.21.1-cp39-abi3-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2fdbd4c067c60a0ac7eca14b6bd18a5bebace54eb757c706b47ea93204f7a37c", size = 3398225 }, + { url = "https://files.pythonhosted.org/packages/8a/63/38be071b0c8e06840bc6046991636bcb30c27f6bb1e670f4f4bc87cf49cc/tokenizers-0.21.1-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2dd9a0061e403546f7377df940e866c3e678d7d4e9643d0461ea442b4f89e61a", size = 3038874 }, + { url = "https://files.pythonhosted.org/packages/ec/83/afa94193c09246417c23a3c75a8a0a96bf44ab5630a3015538d0c316dd4b/tokenizers-0.21.1-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:db9484aeb2e200c43b915a1a0150ea885e35f357a5a8fabf7373af333dcc8dbf", size = 9014448 }, + { url = "https://files.pythonhosted.org/packages/ae/b3/0e1a37d4f84c0f014d43701c11eb8072704f6efe8d8fc2dcdb79c47d76de/tokenizers-0.21.1-cp39-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:ed248ab5279e601a30a4d67bdb897ecbe955a50f1e7bb62bd99f07dd11c2f5b6", size = 8937877 }, + { url = "https://files.pythonhosted.org/packages/ac/33/ff08f50e6d615eb180a4a328c65907feb6ded0b8f990ec923969759dc379/tokenizers-0.21.1-cp39-abi3-musllinux_1_2_i686.whl", hash = "sha256:9ac78b12e541d4ce67b4dfd970e44c060a2147b9b2a21f509566d556a509c67d", size = 9186645 }, + { url = "https://files.pythonhosted.org/packages/5f/aa/8ae85f69a9f6012c6f8011c6f4aa1c96154c816e9eea2e1b758601157833/tokenizers-0.21.1-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:e5a69c1a4496b81a5ee5d2c1f3f7fbdf95e90a0196101b0ee89ed9956b8a168f", size = 9384380 }, + { url = "https://files.pythonhosted.org/packages/e8/5b/a5d98c89f747455e8b7a9504910c865d5e51da55e825a7ae641fb5ff0a58/tokenizers-0.21.1-cp39-abi3-win32.whl", hash = "sha256:1039a3a5734944e09de1d48761ade94e00d0fa760c0e0551151d4dd851ba63e3", size = 2239506 }, + { url = "https://files.pythonhosted.org/packages/e6/b6/072a8e053ae600dcc2ac0da81a23548e3b523301a442a6ca900e92ac35be/tokenizers-0.21.1-cp39-abi3-win_amd64.whl", hash = "sha256:0f0dcbcc9f6e13e675a66d7a5f2f225a736745ce484c1a4e07476a89ccdad382", size = 2435481 }, ] [[package]] @@ -1827,23 +2649,35 @@ wheels = [ [[package]] name = "types-requests" -version = "2.32.0.20250306" +version = "2.32.0.20250328" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "urllib3" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/09/1a/beaeff79ef9efd186566ba5f0d95b44ae21f6d31e9413bcfbef3489b6ae3/types_requests-2.32.0.20250306.tar.gz", hash = "sha256:0962352694ec5b2f95fda877ee60a159abdf84a0fc6fdace599f20acb41a03d1", size = 23012 } +sdist = { url = "https://files.pythonhosted.org/packages/00/7d/eb174f74e3f5634eaacb38031bbe467dfe2e545bc255e5c90096ec46bc46/types_requests-2.32.0.20250328.tar.gz", hash = "sha256:c9e67228ea103bd811c96984fac36ed2ae8da87a36a633964a21f199d60baf32", size = 22995 } wheels = [ - { url = "https://files.pythonhosted.org/packages/99/26/645d89f56004aa0ba3b96fec27793e3c7e62b40982ee069e52568922b6db/types_requests-2.32.0.20250306-py3-none-any.whl", hash = "sha256:25f2cbb5c8710b2022f8bbee7b2b66f319ef14aeea2f35d80f18c9dbf3b60a0b", size = 20673 }, + { url = "https://files.pythonhosted.org/packages/cc/15/3700282a9d4ea3b37044264d3e4d1b1f0095a4ebf860a99914fd544e3be3/types_requests-2.32.0.20250328-py3-none-any.whl", hash = "sha256:72ff80f84b15eb3aa7a8e2625fffb6a93f2ad5a0c20215fc1dcfa61117bcb2a2", size = 20663 }, ] [[package]] name = "typing-extensions" -version = "4.12.2" +version = "4.13.2" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/f6/37/23083fcd6e35492953e8d2aaaa68b860eb422b34627b13f2ce3eb6106061/typing_extensions-4.13.2.tar.gz", hash = "sha256:e6c81219bd689f51865d9e372991c540bda33a0379d5573cddb9a3a23f7caaef", size = 106967 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/8b/54/b1ae86c0973cc6f0210b53d508ca3641fb6d0c56823f288d108bc7ab3cc8/typing_extensions-4.13.2-py3-none-any.whl", hash = "sha256:a439e7c04b49fec3e5d3e2beaa21755cadbbdc391694e28ccdd36ca4a1408f8c", size = 45806 }, +] + +[[package]] +name = "typing-inspection" +version = "0.4.0" source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/df/db/f35a00659bc03fec321ba8bce9420de607a1d37f8342eee1863174c69557/typing_extensions-4.12.2.tar.gz", hash = "sha256:1a7ead55c7e559dd4dee8856e3a88b41225abfe1ce8df57b7c13915fe121ffb8", size = 85321 } +dependencies = [ + { name = "typing-extensions" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/82/5c/e6082df02e215b846b4b8c0b887a64d7d08ffaba30605502639d44c06b82/typing_inspection-0.4.0.tar.gz", hash = "sha256:9765c87de36671694a67904bf2c96e395be9c6439bb6c87b5142569dcdd65122", size = 76222 } wheels = [ - { url = "https://files.pythonhosted.org/packages/26/9f/ad63fc0248c5379346306f8668cda6e2e2e9c95e01216d2b8ffd9ff037d0/typing_extensions-4.12.2-py3-none-any.whl", hash = "sha256:04e5ca0351e0f3f85c6853954072df659d0d13fac324d0072316b67d7794700d", size = 37438 }, + { url = "https://files.pythonhosted.org/packages/31/08/aa4fdfb71f7de5176385bd9e90852eaf6b5d622735020ad600f2bab54385/typing_inspection-0.4.0-py3-none-any.whl", hash = "sha256:50e72559fcd2a6367a19f7a7e610e6afcb9fac940c650290eed893d61386832f", size = 14125 }, ] [[package]] @@ -1857,25 +2691,25 @@ wheels = [ [[package]] name = "urllib3" -version = "2.3.0" +version = "2.4.0" source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/aa/63/e53da845320b757bf29ef6a9062f5c669fe997973f966045cb019c3f4b66/urllib3-2.3.0.tar.gz", hash = "sha256:f8c5449b3cf0861679ce7e0503c7b44b5ec981bec0d1d3795a07f1ba96f0204d", size = 307268 } +sdist = { url = "https://files.pythonhosted.org/packages/8a/78/16493d9c386d8e60e442a35feac5e00f0913c0f4b7c217c11e8ec2ff53e0/urllib3-2.4.0.tar.gz", hash = "sha256:414bc6535b787febd7567804cc015fee39daab8ad86268f1310a9250697de466", size = 390672 } wheels = [ - { url = "https://files.pythonhosted.org/packages/c8/19/4ec628951a74043532ca2cf5d97b7b14863931476d117c471e8e2b1eb39f/urllib3-2.3.0-py3-none-any.whl", hash = "sha256:1cee9ad369867bfdbbb48b7dd50374c0967a0bb7710050facf0dd6911440e3df", size = 128369 }, + { url = "https://files.pythonhosted.org/packages/6b/11/cc635220681e93a0183390e26485430ca2c7b5f9d33b15c74c2861cb8091/urllib3-2.4.0-py3-none-any.whl", hash = "sha256:4e16665048960a0900c702d4a66415956a584919c03361cac9f1df5c5dd7e813", size = 128680 }, ] [[package]] name = "uvicorn" -version = "0.34.0" +version = "0.34.1" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "click", marker = "python_full_version >= '3.10'" }, { name = "h11", marker = "python_full_version >= '3.10'" }, { name = "typing-extensions", marker = "python_full_version == '3.10.*'" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/4b/4d/938bd85e5bf2edeec766267a5015ad969730bb91e31b44021dfe8b22df6c/uvicorn-0.34.0.tar.gz", hash = "sha256:404051050cd7e905de2c9a7e61790943440b3416f49cb409f965d9dcd0fa73e9", size = 76568 } +sdist = { url = "https://files.pythonhosted.org/packages/86/37/dd92f1f9cedb5eaf74d9999044306e06abe65344ff197864175dbbd91871/uvicorn-0.34.1.tar.gz", hash = "sha256:af981725fc4b7ffc5cb3b0e9eda6258a90c4b52cb2a83ce567ae0a7ae1757afc", size = 76755 } wheels = [ - { url = "https://files.pythonhosted.org/packages/61/14/33a3a1352cfa71812a3a21e8c9bfb83f60b0011f5e36f2b1399d51928209/uvicorn-0.34.0-py3-none-any.whl", hash = "sha256:023dc038422502fa28a09c7a30bf2b6991512da7dcdb8fd35fe57cfc154126f4", size = 62315 }, + { url = "https://files.pythonhosted.org/packages/5f/38/a5801450940a858c102a7ad9e6150146a25406a119851c993148d56ab041/uvicorn-0.34.1-py3-none-any.whl", hash = "sha256:984c3a8c7ca18ebaad15995ee7401179212c59521e67bfc390c07fa2b8d2e065", size = 62404 }, ] [[package]] @@ -1991,6 +2825,105 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/fa/a8/5b41e0da817d64113292ab1f8247140aac61cbf6cfd085d6a0fa77f4984f/websockets-15.0.1-py3-none-any.whl", hash = "sha256:f7a866fbc1e97b5c617ee4116daaa09b722101d4a3c170c787450ba409f9736f", size = 169743 }, ] +[[package]] +name = "yarl" +version = "1.19.0" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "idna" }, + { name = "multidict" }, + { name = "propcache" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/fc/4d/8a8f57caccce49573e567744926f88c6ab3ca0b47a257806d1cf88584c5f/yarl-1.19.0.tar.gz", hash = "sha256:01e02bb80ae0dbed44273c304095295106e1d9470460e773268a27d11e594892", size = 184396 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/96/0f/e5bd0d7d98bb194a30740dea2c4324f85dfc2f8daba9d7bc7e47b45d1034/yarl-1.19.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:0bae32f8ebd35c04d6528cedb4a26b8bf25339d3616b04613b97347f919b76d3", size = 144954 }, + { url = "https://files.pythonhosted.org/packages/07/bf/2acc4b643dbdfc823d0d2058768197198a3d93b41fffb41b83359c520a4d/yarl-1.19.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:8015a076daf77823e7ebdcba474156587391dab4e70c732822960368c01251e6", size = 96613 }, + { url = "https://files.pythonhosted.org/packages/ca/38/c60ccca9aad0bb939e665b63a4e1550fecc922971f1f246dd7ad709a1a72/yarl-1.19.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:9973ac95327f5d699eb620286c39365990b240031672b5c436a4cd00539596c5", size = 94408 }, + { url = "https://files.pythonhosted.org/packages/9a/43/2d5b49b4784743d88054e612a97aee2a9d2d463983c6a8e2fa4c872b294a/yarl-1.19.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fd4b5fbd7b9dde785cfeb486b8cca211a0b138d4f3a7da27db89a25b3c482e5c", size = 330774 }, + { url = "https://files.pythonhosted.org/packages/3b/48/7decce219b6eedce321345f61461ee140ee6b3faf4875efe518f0e7b5817/yarl-1.19.0-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:75460740005de5a912b19f657848aef419387426a40f581b1dc9fac0eb9addb5", size = 323399 }, + { url = "https://files.pythonhosted.org/packages/67/2f/d6253528e49ce1c6f5119ec5269314752b06dd670f5a81721648d98b1dc7/yarl-1.19.0-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:57abd66ca913f2cfbb51eb3dbbbac3648f1f6983f614a4446e0802e241441d2a", size = 343329 }, + { url = "https://files.pythonhosted.org/packages/fc/6b/efeb1a088e8addbf5841a84b74dad2a06346b0e4a712eb269a0cd9ada8b7/yarl-1.19.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:46ade37911b7c99ce28a959147cb28bffbd14cea9e7dd91021e06a8d2359a5aa", size = 338275 }, + { url = "https://files.pythonhosted.org/packages/a6/b6/31acc2efcaf6999fd256d11f26ccc95ea773bc790ad1973331d7294b25db/yarl-1.19.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8346ec72ada749a6b5d82bff7be72578eab056ad7ec38c04f668a685abde6af0", size = 334014 }, + { url = "https://files.pythonhosted.org/packages/79/16/1deb54324842479e4d8b34841a383653587dfcc403c132f88b493f0c513e/yarl-1.19.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7e4cb14a6ee5b6649ccf1c6d648b4da9220e8277d4d4380593c03cc08d8fe937", size = 322007 }, + { url = "https://files.pythonhosted.org/packages/80/77/4a073cec4f40ce84897510ee9d347bc10128f715be59b36e5c037463523b/yarl-1.19.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:66fc1c2926a73a2fb46e4b92e3a6c03904d9bc3a0b65e01cb7d2b84146a8bd3b", size = 336569 }, + { url = "https://files.pythonhosted.org/packages/73/e1/2f0455379bbee5f4ece8bc0968106386ec4e74237e8d68ced00bbff0a1fc/yarl-1.19.0-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:5a70201dd1e0a4304849b6445a9891d7210604c27e67da59091d5412bc19e51c", size = 336384 }, + { url = "https://files.pythonhosted.org/packages/74/e0/307aa8ae96bc0e72644855c76e8960019fc24c511a5dda73f05214da46f0/yarl-1.19.0-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:e4807aab1bdeab6ae6f296be46337a260ae4b1f3a8c2fcd373e236b4b2b46efd", size = 340454 }, + { url = "https://files.pythonhosted.org/packages/af/19/2dcdb1e5eef26751c9e79369d1f80d6a1162dababb5070f62bc5b1a8f81e/yarl-1.19.0-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:ae584afe81a1de4c1bb06672481050f0d001cad13163e3c019477409f638f9b7", size = 355804 }, + { url = "https://files.pythonhosted.org/packages/c1/af/8c1e102c6d61713ed31022ab8f8866d263b87cb8f466c37f20a99019d169/yarl-1.19.0-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:30eaf4459df6e91f21b2999d1ee18f891bcd51e3cbe1de301b4858c84385895b", size = 359877 }, + { url = "https://files.pythonhosted.org/packages/1a/cf/c3c4bd85ecc7f189e14d21c3bea67ce389511d9178a302d97281868477aa/yarl-1.19.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:0e617d45d03c8dec0dfce6f51f3e1b8a31aa81aaf4a4d1442fdb232bcf0c6d8c", size = 351282 }, + { url = "https://files.pythonhosted.org/packages/c6/85/0994f1c607b0520ef007717ff74f3317df3f7b7f32756ba2bf26c0c58ddf/yarl-1.19.0-cp310-cp310-win32.whl", hash = "sha256:32ba32d0fa23893fd8ea8d05bdb05de6eb19d7f2106787024fd969f4ba5466cb", size = 86529 }, + { url = "https://files.pythonhosted.org/packages/59/00/39bc8da1f67614633a099a44a5f69d056bb4d65a8e52a4003460e3fa4cc7/yarl-1.19.0-cp310-cp310-win_amd64.whl", hash = "sha256:545575ecfcd465891b51546c2bcafdde0acd2c62c2097d8d71902050b20e4922", size = 92707 }, + { url = "https://files.pythonhosted.org/packages/9b/df/5fa7cd75e46306e0f9baf38a7c8969ff6730ea503b86232e85cb740304cf/yarl-1.19.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:163ff326680de5f6d4966954cf9e3fe1bf980f5fee2255e46e89b8cf0f3418b5", size = 145126 }, + { url = "https://files.pythonhosted.org/packages/2a/be/c1b52129cd2166ab7337f08e701a61baa7c260c7b03b534098cc8297aecc/yarl-1.19.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:a626c4d9cca298d1be8625cff4b17004a9066330ac82d132bbda64a4c17c18d3", size = 96691 }, + { url = "https://files.pythonhosted.org/packages/8d/39/ad62139b45515f9bf129c805aeaaedf86fd93ae57ffe911f4caeabef3e74/yarl-1.19.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:961c3e401ea7f13d02b8bb7cb0c709152a632a6e14cdc8119e9c6ee5596cd45d", size = 94505 }, + { url = "https://files.pythonhosted.org/packages/be/be/04e3202cdc9bb5f81761e327af7095cffb0d81e32421a6b87f926052d2ae/yarl-1.19.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a39d7b807ab58e633ed760f80195cbd145b58ba265436af35f9080f1810dfe64", size = 355485 }, + { url = "https://files.pythonhosted.org/packages/00/7d/1463203663ca1ae62af8fb9ebc9601dd07f04dbced7edb1df3141a2cb2fe/yarl-1.19.0-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:c4228978fb59c6b10f60124ba8e311c26151e176df364e996f3f8ff8b93971b5", size = 344569 }, + { url = "https://files.pythonhosted.org/packages/b0/1b/5263203017348669e637bb73856fb9632110538e92d5e9f8214fcc764da9/yarl-1.19.0-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9ba536b17ecf3c74a94239ec1137a3ad3caea8c0e4deb8c8d2ffe847d870a8c5", size = 371426 }, + { url = "https://files.pythonhosted.org/packages/78/59/90ca5f16d56b7741e5383951acc2e065fce41920eb5d8fda3065b5e288dc/yarl-1.19.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a251e00e445d2e9df7b827c9843c0b87f58a3254aaa3f162fb610747491fe00f", size = 368102 }, + { url = "https://files.pythonhosted.org/packages/84/f2/5e33aa0251ffd2c2a9041bf887e163eeefdc1dca238fdabac444d9463c3f/yarl-1.19.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f9b92431d8b4d4ca5ccbfdbac95b05a3a6cd70cd73aa62f32f9627acfde7549c", size = 358740 }, + { url = "https://files.pythonhosted.org/packages/22/9e/ba92d234c81cf94495fc01eaa0b6000175733f76bd63e60ff748bce22c81/yarl-1.19.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ec2f56edaf476f70b5831bbd59700b53d9dd011b1f77cd4846b5ab5c5eafdb3f", size = 346965 }, + { url = "https://files.pythonhosted.org/packages/8d/0b/d4f53136ef12ddad540855a886d7503a6cc17cfabb9a03ce0c179f3b9e51/yarl-1.19.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:acf9b92c4245ac8b59bc7ec66a38d3dcb8d1f97fac934672529562bb824ecadb", size = 368547 }, + { url = "https://files.pythonhosted.org/packages/31/4b/35ec8622908a728f378a8511f0ab2d47878b2c0b8cbe035f2d907914a5fc/yarl-1.19.0-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:57711f1465c06fee8825b95c0b83e82991e6d9425f9a042c3c19070a70ac92bf", size = 357610 }, + { url = "https://files.pythonhosted.org/packages/c1/71/1f39f7c55b0684834d945a2bcfdfe59e6e02ca2483a3d33c2f77a0c3b177/yarl-1.19.0-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:528e86f5b1de0ad8dd758ddef4e0ed24f5d946d4a1cef80ffb2d4fca4e10f122", size = 365331 }, + { url = "https://files.pythonhosted.org/packages/2e/13/57675964de5c8ccf6427df93ac97f9bb7328f3f8f7ebc31a5f5a286ab1c0/yarl-1.19.0-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:3b77173663e075d9e5a57e09d711e9da2f3266be729ecca0b8ae78190990d260", size = 378624 }, + { url = "https://files.pythonhosted.org/packages/d4/c6/5868e40f8da041ed0c3b5fd8c08cece849d9f609e970e6043308767fbb60/yarl-1.19.0-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:d8717924cf0a825b62b1a96fc7d28aab7f55a81bf5338b8ef41d7a76ab9223e9", size = 383981 }, + { url = "https://files.pythonhosted.org/packages/f4/3f/e40124c986d96741d3d341ffac35be42b6df82ef8c18b5984ca2e7d838dd/yarl-1.19.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:0df9f0221a78d858793f40cbea3915c29f969c11366646a92ca47e080a14f881", size = 378868 }, + { url = "https://files.pythonhosted.org/packages/01/eb/caf2774c770288bd87a818b11f3a56ada6a855f1987d93421aae01a175bf/yarl-1.19.0-cp311-cp311-win32.whl", hash = "sha256:8b3ade62678ee2c7c10dcd6be19045135e9badad53108f7d2ed14896ee396045", size = 86446 }, + { url = "https://files.pythonhosted.org/packages/4a/97/d4fe6168c1bb789507ffeb58c2e8c675a7e71de732dc02e12bda904c1362/yarl-1.19.0-cp311-cp311-win_amd64.whl", hash = "sha256:0626ee31edb23ac36bdffe607231de2cca055ad3a5e2dc5da587ef8bc6a321bc", size = 93121 }, + { url = "https://files.pythonhosted.org/packages/b8/70/44ef8f69d61cb5123167a4dda87f6c739a833fbdb2ed52960b4e8409d65c/yarl-1.19.0-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:7b687c334da3ff8eab848c9620c47a253d005e78335e9ce0d6868ed7e8fd170b", size = 146855 }, + { url = "https://files.pythonhosted.org/packages/c3/94/38c14d6c8217cc818647689f2dd647b976ced8fea08d0ac84e3c8168252b/yarl-1.19.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:b0fe766febcf523a2930b819c87bb92407ae1368662c1bc267234e79b20ff894", size = 97523 }, + { url = "https://files.pythonhosted.org/packages/35/a5/43a613586a6255105c4655a911c307ef3420e49e540d6ae2c5829863fb25/yarl-1.19.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:742ceffd3c7beeb2b20d47cdb92c513eef83c9ef88c46829f88d5b06be6734ee", size = 95540 }, + { url = "https://files.pythonhosted.org/packages/d4/60/ed26049f4a8b06ebfa6d5f3cb6a51b152fd57081aa818b6497474f65a631/yarl-1.19.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2af682a1e97437382ee0791eacbf540318bd487a942e068e7e0a6c571fadbbd3", size = 344386 }, + { url = "https://files.pythonhosted.org/packages/49/a6/b84899cab411f49af5986cfb44b514040788d81c8084f5811e6a7c0f1ce6/yarl-1.19.0-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:63702f1a098d0eaaea755e9c9d63172be1acb9e2d4aeb28b187092bcc9ca2d17", size = 338889 }, + { url = "https://files.pythonhosted.org/packages/cc/ce/0704f7166a781b1f81bdd45c4f49eadbae0230ebd35b9ec7cd7769d3a6ff/yarl-1.19.0-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3560dcba3c71ae7382975dc1e912ee76e50b4cd7c34b454ed620d55464f11876", size = 353107 }, + { url = "https://files.pythonhosted.org/packages/75/e5/0ecd6f2a9cc4264c16d8dfb0d3d71ba8d03cb58f3bcd42b1df4358331189/yarl-1.19.0-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:68972df6a0cc47c8abaf77525a76ee5c5f6ea9bbdb79b9565b3234ded3c5e675", size = 353128 }, + { url = "https://files.pythonhosted.org/packages/ad/c7/cd0fd1de581f1c2e8f996e704c9fd979e00106f18eebd91b0173cf1a13c6/yarl-1.19.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5684e7ff93ea74e47542232bd132f608df4d449f8968fde6b05aaf9e08a140f9", size = 349107 }, + { url = "https://files.pythonhosted.org/packages/e6/34/ba3e5a20bd1d6a09034fc7985aaf1309976f2a7a5aefd093c9e56f6e1e0c/yarl-1.19.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8182ad422bfacdebd4759ce3adc6055c0c79d4740aea1104e05652a81cd868c6", size = 335144 }, + { url = "https://files.pythonhosted.org/packages/1e/98/d9b7beb932fade015906efe0980aa7d522b8f93cf5ebf1082e74faa314b7/yarl-1.19.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:aee5b90a5a9b71ac57400a7bdd0feaa27c51e8f961decc8d412e720a004a1791", size = 360795 }, + { url = "https://files.pythonhosted.org/packages/9a/11/70b8770039cc54af5948970591517a1e1d093df3f04f328c655c9a0fefb7/yarl-1.19.0-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:8c0b2371858d5a814b08542d5d548adb03ff2d7ab32f23160e54e92250961a72", size = 360140 }, + { url = "https://files.pythonhosted.org/packages/d4/67/708e3e36fafc4d9d96b4eecc6c8b9f37c8ad50df8a16c7a1d5ba9df53050/yarl-1.19.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:cd430c2b7df4ae92498da09e9b12cad5bdbb140d22d138f9e507de1aa3edfea3", size = 364431 }, + { url = "https://files.pythonhosted.org/packages/c3/8b/937fbbcc895553a7e16fcd86ae4e0724c6ac9468237ad8e7c29cc3b1c9d9/yarl-1.19.0-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:a93208282c0ccdf73065fd76c6c129bd428dba5ff65d338ae7d2ab27169861a0", size = 373832 }, + { url = "https://files.pythonhosted.org/packages/f8/ca/288ddc2230c9b6647fe907504f1119adb41252ac533eb564d3fc73511215/yarl-1.19.0-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:b8179280cdeb4c36eb18d6534a328f9d40da60d2b96ac4a295c5f93e2799e9d9", size = 378122 }, + { url = "https://files.pythonhosted.org/packages/4f/5a/79e1ef31d14968fbfc0ecec70a6683b574890d9c7550c376dd6d40de7754/yarl-1.19.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:eda3c2b42dc0c389b7cfda2c4df81c12eeb552019e0de28bde8f913fc3d1fcf3", size = 375178 }, + { url = "https://files.pythonhosted.org/packages/95/38/9b0e56bf14026c3f550ad6425679f6d1a2f4821d70767f39d6f4c56a0820/yarl-1.19.0-cp312-cp312-win32.whl", hash = "sha256:57f3fed859af367b9ca316ecc05ce79ce327d6466342734305aa5cc380e4d8be", size = 86172 }, + { url = "https://files.pythonhosted.org/packages/b3/96/5c2f3987c4bb4e5cdebea3caf99a45946b13a9516f849c02222203d99860/yarl-1.19.0-cp312-cp312-win_amd64.whl", hash = "sha256:5507c1f7dd3d41251b67eecba331c8b2157cfd324849879bebf74676ce76aff7", size = 92617 }, + { url = "https://files.pythonhosted.org/packages/cd/a7/222144efa2f4a47363a5fee27d8a1d24851283b5a7f628890805fe7f7a66/yarl-1.19.0-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:59281b9ed27bc410e0793833bcbe7fc149739d56ffa071d1e0fe70536a4f7b61", size = 144789 }, + { url = "https://files.pythonhosted.org/packages/72/4f/3ee8de3f94baa33c0716260b0048b1fd5306f104b3efc6e1713693e7063e/yarl-1.19.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:d27a6482ad5e05e8bafd47bf42866f8a1c0c3345abcb48d4511b3c29ecc197dc", size = 96685 }, + { url = "https://files.pythonhosted.org/packages/3e/7c/fbeebf875c1ededd872d6fefabd8a8526ef8aba6e9e8bcdf230d895d487b/yarl-1.19.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:7a8e19fd5a6fdf19a91f2409665c7a089ffe7b9b5394ab33c0eec04cbecdd01f", size = 94307 }, + { url = "https://files.pythonhosted.org/packages/f3/ff/b7a9c1d7df37e594b43b7a8030e228ccd4ce361eeff24a92b17fe210e57d/yarl-1.19.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cda34ab19099c3a1685ad48fe45172536610c312b993310b5f1ca3eb83453b36", size = 342811 }, + { url = "https://files.pythonhosted.org/packages/79/e2/9e092876b2156c1d386e4864e85eba541ccabf2b9dcc47da64624bad0cc9/yarl-1.19.0-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:7908a25d33f94852b479910f9cae6cdb9e2a509894e8d5f416c8342c0253c397", size = 336928 }, + { url = "https://files.pythonhosted.org/packages/71/24/648d99c134f2e14fc01ba790ad36ab56815e00069e60a12a4af893448b83/yarl-1.19.0-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e66c14d162bac94973e767b24de5d7e6c5153f7305a64ff4fcba701210bcd638", size = 351021 }, + { url = "https://files.pythonhosted.org/packages/0c/ee/7278d475784d407d1990a5939722e66a0fef057046fb5f1721f0a6eb156c/yarl-1.19.0-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c03607bf932aa4cfae371e2dc9ca8b76faf031f106dac6a6ff1458418140c165", size = 354454 }, + { url = "https://files.pythonhosted.org/packages/15/ae/242546114e052a7de21a75bd7d4860266439f90bbc21c5e4dd696866d91d/yarl-1.19.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9931343d1c1f4e77421687b6b94bbebd8a15a64ab8279adf6fbb047eff47e536", size = 347594 }, + { url = "https://files.pythonhosted.org/packages/46/2c/35f4347f76ea4c986e9c1f774b085f489b3a1bf1503c67a4dfc5d8e68e92/yarl-1.19.0-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:262087a8a0d73e1d169d45c2baf968126f93c97cf403e1af23a7d5455d52721f", size = 334113 }, + { url = "https://files.pythonhosted.org/packages/20/89/3086bc8ec8d7bd505531c51056452d7ae6af906d29c427374f1170ac1938/yarl-1.19.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:70f384921c24e703d249a6ccdabeb57dd6312b568b504c69e428a8dd3e8e68ca", size = 361037 }, + { url = "https://files.pythonhosted.org/packages/a1/5b/2c9765524a70d1c51922b41c91caa30c8094a416734349166e1a3d8de055/yarl-1.19.0-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:756b9ea5292a2c180d1fe782a377bc4159b3cfefaca7e41b5b0a00328ef62fa9", size = 361025 }, + { url = "https://files.pythonhosted.org/packages/ca/f8/c4a190bcc3cd98fb428d1dd31519e58004153dc7f2acd1236ecae54e3433/yarl-1.19.0-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:cbeb9c145d534c240a63b6ecc8a8dd451faeb67b3dc61d729ec197bb93e29497", size = 364397 }, + { url = "https://files.pythonhosted.org/packages/6b/fb/f65b1347be8e12ac4e3e37a9bb880e6b9b604f252aaafd88e4879b1e9348/yarl-1.19.0-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:087ae8f8319848c18e0d114d0f56131a9c017f29200ab1413b0137ad7c83e2ae", size = 374065 }, + { url = "https://files.pythonhosted.org/packages/1c/c5/102cc3b9baad1a76f9127453ad08e0f5bc9c996c18128b1e28fe03817d6c/yarl-1.19.0-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:362f5480ba527b6c26ff58cff1f229afe8b7fdd54ee5ffac2ab827c1a75fc71c", size = 381341 }, + { url = "https://files.pythonhosted.org/packages/f7/ce/f5dc0439320dfe59fadab8cdd24ac324be19cf6ae4736422c7e2a510ddf3/yarl-1.19.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:f408d4b4315e814e5c3668094e33d885f13c7809cbe831cbdc5b1bb8c7a448f4", size = 376552 }, + { url = "https://files.pythonhosted.org/packages/a9/4a/4833a134c76af987eff3ce8cb71e42932234120e6be061eb2555061e8844/yarl-1.19.0-cp313-cp313-win32.whl", hash = "sha256:24e4c367ad69988a2283dd45ea88172561ca24b2326b9781e164eb46eea68345", size = 85878 }, + { url = "https://files.pythonhosted.org/packages/32/e9/59327daab3af8f79221638a8f0d11474d20f6a8fbc41e9da80c5ef69e688/yarl-1.19.0-cp313-cp313-win_amd64.whl", hash = "sha256:0110f91c57ab43d1538dfa92d61c45e33b84df9257bd08fcfcda90cce931cbc9", size = 92448 }, + { url = "https://files.pythonhosted.org/packages/f0/77/38ee2b6ea52fa46efb3a68c17d066760a2e873c99837001922dad3c5d4e5/yarl-1.19.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:85ac908cd5a97bbd3048cca9f1bf37b932ea26c3885099444f34b0bf5d5e9fa6", size = 146440 }, + { url = "https://files.pythonhosted.org/packages/08/14/4c2f8696bf09d851d299e4af62bf005e6087f162cd34b8c88c332d8580ea/yarl-1.19.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:6ba0931b559f1345df48a78521c31cfe356585670e8be22af84a33a39f7b9221", size = 97490 }, + { url = "https://files.pythonhosted.org/packages/8d/b9/a67586d46e9c68ecae6162164539c50fdeab3f4722decda4f6ea9f7bf4fd/yarl-1.19.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:5bc503e1c1fee1b86bcb58db67c032957a52cae39fe8ddd95441f414ffbab83e", size = 95236 }, + { url = "https://files.pythonhosted.org/packages/76/01/2f3c33ef91f9292bb4bb59654fc5f6e0c24780de74cc993f583dec7c6adb/yarl-1.19.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d995122dcaf180fd4830a9aa425abddab7c0246107c21ecca2fa085611fa7ce9", size = 330624 }, + { url = "https://files.pythonhosted.org/packages/43/fd/64e414ffba8f19e5d151c06e9402a0a0054f0c8f5d5e25519612d5d583ad/yarl-1.19.0-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:217f69e60a14da4eed454a030ea8283f8fbd01a7d6d81e57efb865856822489b", size = 325798 }, + { url = "https://files.pythonhosted.org/packages/7a/84/813be2b6b8c4c5bdafa5e0c0e5b17213f45fd10efbfaaa1279a917201373/yarl-1.19.0-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:aad67c8f13a4b79990082f72ef09c078a77de2b39899aabf3960a48069704973", size = 348176 }, + { url = "https://files.pythonhosted.org/packages/4f/06/81f9a80e243e043f0dc6a043d1a89dc004b06e3f71fb7c83f9013959bb5b/yarl-1.19.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:dff065a1a8ed051d7e641369ba1ad030d5a707afac54cf4ede7069b959898835", size = 343497 }, + { url = "https://files.pythonhosted.org/packages/ec/8a/abbed688dd85b5a29e91ed9a7f4cce9efe925083d7567f341ece0b36cc7e/yarl-1.19.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ada882e26b16ee651ab6544ce956f2f4beaed38261238f67c2a96db748e17741", size = 336969 }, + { url = "https://files.pythonhosted.org/packages/33/1a/7a6316473afec0b57e1cbf2ccaa02df9f138c0e447b43e85e8b1a4e7a549/yarl-1.19.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:67a56b1acc7093451ea2de0687aa3bd4e58d6b4ef6cbeeaad137b45203deaade", size = 328910 }, + { url = "https://files.pythonhosted.org/packages/29/07/ba204b362147a04a5e172af726887156ae4e098fab826aa9d7269fbdbf89/yarl-1.19.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:e97d2f0a06b39e231e59ebab0e6eec45c7683b339e8262299ac952707bdf7688", size = 342614 }, + { url = "https://files.pythonhosted.org/packages/e1/43/555be0062c999a610ad2c7b5a78695f25a70890be8c3e9ae555386b20cd3/yarl-1.19.0-cp39-cp39-musllinux_1_2_armv7l.whl", hash = "sha256:a5288adb7c59d0f54e4ad58d86fb06d4b26e08a59ed06d00a1aac978c0e32884", size = 340438 }, + { url = "https://files.pythonhosted.org/packages/26/17/703f82dbac560b9a47cee7c83abad923ac98f062eda9430dab098c28a3c9/yarl-1.19.0-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:1efbf4d03e6eddf5da27752e0b67a8e70599053436e9344d0969532baa99df53", size = 343236 }, + { url = "https://files.pythonhosted.org/packages/e7/2c/a73354c4cc84e39a1eb83c1fabce01a75640a7fcf4183e5d3e99b1e510bd/yarl-1.19.0-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:f228f42f29cc87db67020f7d71624102b2c837686e55317b16e1d3ef2747a993", size = 358432 }, + { url = "https://files.pythonhosted.org/packages/f2/b5/5213af4695344281637d65005b781151008446bbd852a4b6a1b47b6952fa/yarl-1.19.0-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:c515f7dd60ca724e4c62b34aeaa603188964abed2eb66bb8e220f7f104d5a187", size = 359656 }, + { url = "https://files.pythonhosted.org/packages/d0/7d/00c56abbb3bec635dbe1f0ffb11f04eefc9ec2e1af24f10b34ed5d4e154d/yarl-1.19.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:4815ec6d3d68a96557fa71bd36661b45ac773fb50e5cfa31a7e843edb098f060", size = 353732 }, + { url = "https://files.pythonhosted.org/packages/84/4f/37e5c9162af1a494f9854683869c67be271c5e66f75b0c7010c78a025356/yarl-1.19.0-cp39-cp39-win32.whl", hash = "sha256:9fac2dd1c5ecb921359d9546bc23a6dcc18c6acd50c6d96f118188d68010f497", size = 87082 }, + { url = "https://files.pythonhosted.org/packages/55/7f/ef6a2a6d95671430364ec801286ed748cc9808bd747f038639158b5f308d/yarl-1.19.0-cp39-cp39-win_amd64.whl", hash = "sha256:5864f539ce86b935053bfa18205fa08ce38e9a40ea4d51b19ce923345f0ed5db", size = 93180 }, + { url = "https://files.pythonhosted.org/packages/a4/06/ae25a353e8f032322df6f30d6bb1fc329773ee48e1a80a2196ccb8d1206b/yarl-1.19.0-py3-none-any.whl", hash = "sha256:a727101eb27f66727576630d02985d8a065d09cd0b5fcbe38a5793f71b2a97ef", size = 45990 }, +] + [[package]] name = "zipp" version = "3.21.0"