# Overview

Resolves openai#745

This PR introduces **Sessions**, a new core feature that automatically
maintains conversation history across multiple agent runs, eliminating
the need to manually handle `.to_input_list()` between turns.

## Key Features

### 🧠 Automatic Memory Management
- **Zero-effort conversation continuity**: Agents automatically remember
previous context without manual state management
- **Session-based organization**: Each conversation is isolated by
unique session IDs
- **Seamless integration**: Works with existing `Runner.run()`,
`Runner.run_sync()`, and `Runner.run_streamed()` methods

### 🔌 Extensible Session Protocol
- **Library-agnostic design**: Clean protocol interface allows any
storage backend
- **Drop-in implementations**: Easy integration with Redis, PostgreSQL,
MongoDB, or any custom storage
- **Production-ready interface**: Async-first design with proper error
handling and type safety
- **Vendor flexibility**: Library authors can provide their own Session
implementations

### 💾 Built-in SQLite Implementation
- **In-memory SQLite**: Perfect for temporary conversations during
development
- **Persistent SQLite**: File-based storage for conversations that
survive application restarts
- **Thread-safe operations**: Production-ready with connection pooling
and proper concurrency handling

### 🔧 Simple API
```python
# Before: Manual conversation management
result1 = await Runner.run(agent, "What's the weather?")
new_input = result1.to_input_list() + [{"role": "user", "content": "How about tomorrow?"}]
result2 = await Runner.run(agent, new_input)

# After: Automatic with Sessions
session = SQLiteSession("user_123")

result1 = await Runner.run(agent, "What's the weather?", session=session)
result2 = await Runner.run(agent, "How about tomorrow?", session=session)  # Remembers context automatically
```

## What's Included

### Core Session Protocol
- **`Session` Protocol**: Clean, async interface that any storage
backend can implement
- **Type-safe design**: Full type hints and runtime validation
- **Standard operations**: `get_items()`, `add_items()`, `pop_item()`,
`clear_session()`
- **Extensibility-first**: Designed for third-party implementations

### Reference Implementation
- **`SQLiteSession` Class**: Production-ready SQLite implementation
- **Automatic schema management**: Creates tables and indexes
automatically
- **Connection pooling**: Thread-safe operations with proper resource
management
- **Flexible storage**: In-memory or persistent file-based databases

### Runner Integration
- **New `session` parameter**: Drop-in addition to existing `Runner`
methods
- **Backward compatibility**: Zero breaking changes to existing code
- **Automatic history management**: Prepends conversation history before
each run

## Session Protocol for Library Authors

The Session protocol provides a clean interface for implementing custom
storage backends:

```python
from agents.memory import Session
from typing import List

class MyCustomSession:
    """Custom session implementation following the Session protocol."""

    def __init__(self, session_id: str):
        self.session_id = session_id
        # Your initialization here

    async def get_items(self, limit: int | None = None) -> List[dict]:
        """Retrieve conversation history for this session."""
        # Your implementation here
        pass

    async def add_items(self, items: List[dict]) -> None:
        """Store new items for this session."""
        # Your implementation here
        pass

    async def pop_item(self) -> dict | None:
        """Remove and return the most recent item from this session."""
        # Your implementation here
        pass

    async def clear_session(self) -> None:
        """Clear all items for this session."""
        # Your implementation here
        pass

# Works seamlessly with any custom implementation
result = await Runner.run(agent, "Hello", session=MyCustomSession("session_123"))
```

### Example Third-Party Implementations

```python
# Redis-based session (hypothetical library implementation)
from redis_sessions import RedisSession
session = RedisSession("user_123", redis_url="redis://localhost:6379")

# PostgreSQL-based session (hypothetical library implementation) 
from postgres_sessions import PostgreSQLSession
session = PostgreSQLSession("user_123", connection_string="postgresql://...")

# Cloud-based session (hypothetical library implementation)
from cloud_sessions import CloudSession
session = CloudSession("user_123", api_key="...", region="us-east-1")

# All work identically with the Runner
result = await Runner.run(agent, "Hello", session=session)
```

## Benefits

### For Application Developers
- **Reduces boilerplate**: No more manual `.to_input_list()` management
- **Prevents memory leaks**: Automatic cleanup and organized storage
- **Easier debugging**: Clear conversation history tracking
- **Flexible storage**: Choose the right backend for your needs

### For Library Authors
- **Clean integration**: Simple protocol to implement for any storage
backend
- **Type safety**: Full type hints and runtime validation
- **Async-first**: Modern async/await design throughout
- **Documentation**: Comprehensive examples and API reference

### For Applications
- **Better user experience**: Seamless conversation continuity
- **Scalable architecture**: Support for multiple concurrent
conversations
- **Flexible deployment**: In-memory for development, production storage
for scale
- **Multi-agent support**: Same conversation history can be shared
across different agents

## Usage Examples

### Basic Usage with SQLiteSession
```python
from agents import Agent, Runner, SQLiteSession

agent = Agent(name="Assistant", instructions="Reply concisely.")
session = SQLiteSession("conversation_123")

# Conversation flows naturally
await Runner.run(agent, "Hi, I'm planning a trip to Japan", session=session)
await Runner.run(agent, "What's the best time to visit?", session=session)
await Runner.run(agent, "How about cherry blossom season?", session=session)
```

### Multiple Sessions with Isolation
```python
# Different users get separate conversation histories
session_alice = SQLiteSession("user_alice")
session_bob = SQLiteSession("user_bob")

# Completely isolated conversations
await Runner.run(agent, "I like pizza", session=session_alice)
await Runner.run(agent, "I like sushi", session=session_bob)
```

### Persistent vs In-Memory Storage
```python
# In-memory database (lost when process ends)
session = SQLiteSession("user_123")

# Persistent file-based database
session = SQLiteSession("user_123", "conversations.db")
```

### Session Management Operations
```python
session = SQLiteSession("user_123")

# Get all items in a session
items = await session.get_items()

# Add new items to a session
new_items = [
    {"role": "user", "content": "Hello"},
    {"role": "assistant", "content": "Hi there!"}
]
await session.add_items(new_items)

# Remove and return the most recent item (useful for corrections)
last_item = await session.pop_item()

# Clear all items from a session
await session.clear_session()
```

### Message Correction Pattern
```python
# User wants to correct their last question
user_message = await session.pop_item()  # Remove user's question
assistant_message = await session.pop_item()  # Remove agent's response

# Ask a corrected question
result = await Runner.run(
    agent,
    "What's 2 + 3?",  # Corrected question
    session=session
)
```

## Technical Details

### Session Protocol Design
- **Async-first**: All operations are async for non-blocking I/O
- **Type-safe**: Full type hints with runtime validation
- **Error handling**: Graceful degradation and detailed error messages
- **Resource management**: Proper cleanup and connection handling

### SQLiteSession Implementation
- **Thread-safe operations** with connection pooling
- **Automatic schema management** with proper indexing
- **JSON serialization** for message storage
- **Memory-efficient** conversation retrieval and storage
- **Cross-platform compatibility**

## Breaking Changes

None. This is a purely additive feature that doesn't affect existing
functionality.

## Documentation

- Updated core concepts in `docs/index.md` to highlight Sessions as a
key primitive
- New comprehensive guide at `docs/sessions.md` with protocol
implementation examples
- Enhanced `docs/running_agents.md` with automatic vs manual
conversation management
- Full API reference integration via `docs/ref/memory.md`
- Implementation guide for library authors

Sessions represent a significant architectural improvement for building
conversational AI applications with the Agents SDK. The extensible
Session protocol enables the ecosystem to provide specialized storage
backends while maintaining a consistent, simple API for application
developers.

---------

Co-authored-by: Rohan Mehta <[email protected]>

Updated the evaluator agent’s instructions in llm_as_a_judge.py to
prevent infinite evaluation loops. The agent is now instructed to
provide a final evaluation after 5 attempts, allowing approval if the
story outline is good enough, even if it is not perfect.

This allows base agent stuff to be shared with the realtime agent

Similar to the TS version. 



---
[//]: # (BEGIN SAPLING FOOTER)
* __->__ openai#1069
* openai#1068

Similar to the TS version.
- Config is the things you can set on the session
- Items are similar to responses items. I'm using an abstraction instead
of reusing the ones in the openai SDK, to reduce the amount of work for
other providers



---
[//]: # (BEGIN SAPLING FOOTER)
* openai#1074
* openai#1073
* openai#1072
* openai#1071
* __->__ openai#1070
* openai#1069
* openai#1068

Transport interface for actually connecting to the backend and managing
realtime conversations. The transport emits events.






---
[//]: # (BEGIN SAPLING FOOTER)
* openai#1074
* openai#1073
* openai#1072
* __->__ openai#1071

Uses the openai realtime impl over websockets. Unlike the TS version,
only supports websockets - no in browser stuff.






---
[//]: # (BEGIN SAPLING FOOTER)
* openai#1074
* openai#1073
* __->__ openai#1072
* openai#1071

RealtimeSession is like Runner, except for Realtime. It's also stateful
and manages the conversation for you.







---
[//]: # (BEGIN SAPLING FOOTER)
* openai#1076
* openai#1074
* __->__ openai#1073
* openai#1072
* openai#1071

Mostly working demo. Plays audio, shows event log.








---
[//]: # (BEGIN SAPLING FOOTER)
* openai#1076
* __->__ openai#1074

openai#1067)

Corrected the capitalization of "after" to "After" in the evaluator
instructions string to ensure grammatical consistency and proper
formatting.

Key changes:
1. Transport -> model.
2. Extract any model settings into `RealtimeSessionModelSettings`.
3. RealtimeRunConfig, similar to the RunConfig in `run.py`.
4. RealtimeRunner now exists, similar to Runner. Returns a
RealtimeSession when you call run().
5. RealtimeSession now uses streaming events instead of listener.






---
[//]: # (BEGIN SAPLING FOOTER)
* openai#1080
* openai#1079
* __->__ openai#1076

---
[//]: # (BEGIN SAPLING FOOTER)
* openai#1080
* __->__ openai#1079
* openai#1076

This pull request resolves openai#968

Guadrails with debouncing support. Output only.

---
[//]: # (BEGIN SAPLING FOOTER)
* openai#1084
* __->__ openai#1082

Just sends tracing info to the server.

---
[//]: # (BEGIN SAPLING FOOTER)
* __->__ openai#1084
* openai#1082