…ents#515)

Co-authored-by: jer <[email protected]>

…rands-agents#513)

These were necessary when we had conditional running but we switched to needing to approve all workflows for non-maintainers, so we no longer need these.

Co-authored-by: Mackenzie Zastrow <[email protected]>

…ectory (strands-agents#517)

- Add new section showcasing Agent(load_tools_from_directory=True) functionality
- Document automatic tool loading and reloading from ./tools/ directory
- Include practical code example for developers
- Improve discoverability of this development feature

…strands-agents#510)

Fixes issue strands-agents#50

Customers naturally want to pass nested collections of tools - the above issue has gathered enough data points proving that.

…ts#524)

* feat(a2a): support mounts for containerized deployments

* feat(a2a): escape hatch for load balancers which strip paths

* feat(a2a): formatting

---------

Co-authored-by: jer <[email protected]>

…#526)

…agents#176)

…trands-agents#553)

* Update bedrock.py

* Update anthropic.py

…ds-agents#528)

Co-authored-by: ketan-clairyon <[email protected]>
Co-authored-by: Dean Schmigelski <[email protected]>

…-agents#581)

Co-authored-by: Jeremiah <[email protected]>

…agents#586)

strands-agents#576)

* fix(event_loop): raise dedicated exception when encountering max tokens stop reason

* fix: update integ tests

* fix: rename exception message, add to exception, move earlier in cycle

* Update tests_integ/test_max_tokens_reached.py

Co-authored-by: Nick Clegg <[email protected]>

* Update tests_integ/test_max_tokens_reached.py

Co-authored-by: Nick Clegg <[email protected]>

* linting

---------

Co-authored-by: Nick Clegg <[email protected]>

…#569)

)

Using a string causes the Anthropic API call to fail:
```
anthropic.BadRequestError: Error code: 400 - {'type': 'error', 'error': {'type': 'invalid_request_error', 'message': 'max_tokens: Input should be a valid integer'}}
```

… are ready to be worked on (strands-agents#595)

Co-authored-by: jer <[email protected]>

Co-authored-by: jer <[email protected]>

…okens to prevent unrecoverable state (strands-agents#607)

…t is passed (strands-agents#628)

…trands-agents#657)

Co-authored-by: Harry Wilton <[email protected]>

…rands-agents#643)

Previously (strands-agents#642) bedrock would hang during message conversion because the exception was not being caught and thus the queue was always empty. Now all exceptions during conversion are caught

Co-authored-by: Mackenzie Zastrow <[email protected]>

…ek (strands-agents#652)

* Fix: strip reasoningContent from messages before sending to Bedrock to avoid ValidationException

* Using Message class instead of dict in _strip_reasoning_content_from_message().

* fix(models): filter reasoningContent blocks on Bedrock requests using DeepSeek

* fix: formatting and linting

* fix: formatting and linting

* remove unrelated registry formatting

* linting

* add log

---------

Co-authored-by: Dean Schmigelski <[email protected]>

…gents#820)

)

Implement the ability for all built-in providers to emit a warning when unknown configuration properties are included.

Co-authored-by: Mackenzie Zastrow <[email protected]>

)

…ands-agents#817)

* feat: improve structured output tool circular reference handling and optional field detection

- Move circular reference detection earlier in schema flattening process
- Simplify optional field detection using field.is_required() instead of Union type inspection
- Add comprehensive test coverage for circular reference scenarios
- Fix handling of fields with default values that make them optional

…om file path (strands-agents#742)

- Collect all DecoratedFunctionTool objects when loading a .py file and return list when multiple exist
- Normalize loader results and register each AgentTool separately in registry
- Add normalize_loaded_tools helper and test for multiple decorated tools

---------

Co-authored-by: ratish <[email protected]>
Co-authored-by: Mackenzie Zastrow <[email protected]>

…as client_args (strands-agents#808)

* fix(models): patch litellm bug to honor passing in use_litellm_proxy as client_args

---------

Co-authored-by: Patrick Gray <[email protected]>

- Set DEFAULT_READ_TIMEOUT constant to 120 seconds
- Configure BotocoreConfig with read_timeout when no custom config provided
- Add test coverage for default read timeout behavior

…ut (strands-agents#720)

For structured output so that some providers can force tool calls

---------

Co-authored-by: Mackenzie Zastrow <[email protected]>
Co-authored-by: Shang Liu <[email protected]>

…executors (strands-agents#816)

* feat(multiagent): allow callers of swarm and graph to pass kwargs to executors

---------

Co-authored-by: Nick Clegg <[email protected]>
Co-authored-by: Aditya Bhushan Sharma <[email protected]>

These changes introduce region-aware default model ID functionality for Bedrock, formatting based on region prefixes, warnings for unsupported regions, and preservation of custom model IDs. Comprehensive test coverage was added, and existing tests were updated. We also maintain compatibility for two key use cases: preserving customer-overridden model IDs and maintaining compatibility with existing DEFAULT_BEDROCK_MODEL_ID usage patterns.

…strands-agents#838)

…nds-agents#825)

Adds cacheReadInputTokens and cacheWriteInputTokens to span attributes
in both end_model_invoke_span and end_agent_span methods to enable
monitoring of cache token usage for cost calculation.

Closes strands-agents#776

Co-authored-by: Vamil Gandhi <[email protected]>

…ent` class. [for better VS Code hover] (strands-agents#846)

Bumps [actions/setup-python](https://github.com/actions/setup-python) from 5 to 6.
- [Release notes](https://github.com/actions/setup-python/releases)
- [Commits](actions/setup-python@v5...v6)

---
updated-dependencies:
- dependency-name: actions/setup-python
  dependency-version: '6'
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

Bumps [actions/github-script](https://github.com/actions/github-script) from 7 to 8.
- [Release notes](https://github.com/actions/github-script/releases)
- [Commits](actions/github-script@v7...v8)

---
updated-dependencies:
- dependency-name: actions/github-script
  dependency-version: '8'
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

…gents#795)

Bumps [aws-actions/configure-aws-credentials](https://github.com/aws-actions/configure-aws-credentials) from 4 to 5.
- [Release notes](https://github.com/aws-actions/configure-aws-credentials/releases)
- [Changelog](https://github.com/aws-actions/configure-aws-credentials/blob/main/CHANGELOG.md)
- [Commits](aws-actions/configure-aws-credentials@v4...v5)

---
updated-dependencies:
- dependency-name: aws-actions/configure-aws-credentials
  dependency-version: '5'
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

…strands-agents#840)

Updates the requirements on [ruff](https://github.com/astral-sh/ruff) to permit the latest version.
- [Release notes](https://github.com/astral-sh/ruff/releases)
- [Changelog](https://github.com/astral-sh/ruff/blob/main/CHANGELOG.md)
- [Commits](astral-sh/ruff@0.12.0...0.13.0)

---
updated-dependencies:
- dependency-name: ruff
  dependency-version: 0.13.0
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

Updates the requirements on [openai](https://github.com/openai/openai-python) to permit the latest version.
- [Release notes](https://github.com/openai/openai-python/releases)
- [Changelog](https://github.com/openai/openai-python/blob/main/CHANGELOG.md)
- [Commits](openai/openai-python@v1.68.0...v1.107.0)

---
updated-dependencies:
- dependency-name: openai
  dependency-version: 1.107.0
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

…trands-agents#832)

* feat: add GitHub workflow for auto-closing stale issues with dry-run support

- Daily workflow checks issues with configurable labels after X days
- Removes label if unauthorized users comment, closes if only authorized users
- Supports team-based or write-access authorization modes
- Includes comprehensive input validation and error handling
- Adds manual trigger with dry-run mode for safe testing

* fix: Replace deprecated GitHub Search API with Issues API

- Replace github.rest.search.issuesAndPullRequests with github.rest.issues.listForRepo
- Add pagination support to handle repositories with many labeled issues

* feat: remove label immediately on unauthorized comments

- Check for unauthorized comments before time validation
- Remove the label instantly when non-authorized users respond

* feat: add optional replacement label when removing auto-close label

- Add REPLACEMENT_LABEL environment variable for optional label substitution
- Apply replacement label when unauthorized users comment and auto-close label is removed

* feat: Consolidate auto-close workflows into a single matrix-based action

- Merge auto-close-3-days.yml and auto-close-7-days.yml into auto-close.yml
- Use a matrix strategy to handle both 3-day and 7-day label processing

The documentation provided for the tool decorator has been updated to work with the version 1.8.0