* No longer pass down parent_snapshot to Agent and break point trigger moved to Pipeline._run_component
* Some cleanup since parent_snapshot is no longer passed down
* linting and typing
* Refactor chat generator break point in Agent to use triggering mechanism of Pipeline._run_component
* small changes
* Refactor so tool invoker break point uses the break_point param of Pipeline._run_component
* edits
* Further reduce duplicate code
* Further reduce duplicate code
* Add break_point as property to BreakpointException
* Fix
* Fix mypy and PR comments
* PR comments
* feat!: drop Python 3.9 support due to EOL
Remove Python 3.9 support following its end-of-life in October 2025.
Minimum required version is now Python 3.10.
BREAKING CHANGE: Python 3.10 or later is now required
Changes:
- Update pyproject.toml requires-python to >=3.10
- Remove Python 3.9 from pyproject.toml classifiers
- Update CI workflows to test Python 3.10 as minimum
- Update mypy python_version to 3.10
- Migrate TypeAlias from typing_extensions to typing stdlib
- Remove blis version pin (only needed for Python 3.9)
- Update CONTRIBUTING.md Python version requirements
- Add release note documenting breaking change
Closes#9854
* small fixes
* update relnote
---------
Co-authored-by: anakin87 <stefanofiorucci@gmail.com>
* ci: fail on malformed code blocks in release notes
* add release notes to test the workflow
* Revert "add release notes to test the workflow"
This reverts commit 8157790dd65721998b20c57654c7f97712111391.
* ci: release orchestration workflow
* offload notification preparation to external script
* swap if/needs
* slim where makes sense
* tmp test for ubuntu slim
* revet
* concurrency
* Update code snippets in docs
* Add reno note
* Revert "Add reno note"
This reverts commit 18733fa828ebedfe5b20903bcf0080abc198ad9e.
* PR feedback
* Minor fix
* No Secrets between us
* Comments format update
* Restore output format
* Script output, needs to be commented
* Update HuggingFaceLocalChatGenerator default model to Qwen/Qwen3-0.6B
* Add enable_thinking init parameter
* Pydoc wording
* Format test
* Add tests for enable_thinking flag
* Add reno note for HuggingFaceLocalChatGenerator updates
* Update haystack/components/generators/chat/hugging_face_local.py
Co-authored-by: Stefano Fiorucci <stefanofiorucci@gmail.com>
* Update release notes for HuggingFaceLocalChatGenerator
Updated the release notes to reflect changes in the HuggingFaceLocalChatGenerator, including the new default model and the addition of the enable_thinking parameter.
* Simplify test_live_run with/out enable_thinking flag
* Test shuffle
---------
Co-authored-by: Stefano Fiorucci <stefanofiorucci@gmail.com>
* refactor
* Update tests
* Add reno
* Fix types
* fix type
* Fix test
* fix unit tests
* Add asserts to make mypy happy
* Fix unit test
* Update releasenotes/notes/refactor-warm-up-components-c2777fef28a70b61.yaml
Co-authored-by: David S. Batista <dsbatista@gmail.com>
* start getting rid of asserts
* remove more asserts
* remove last assert
* Remove assert
---------
Co-authored-by: David S. Batista <dsbatista@gmail.com>
* docs: add quota note for OpenAIChatGenerator in get-started guide
* Apply suggestion from @davidsbatista
* Apply suggestions from code review
---------
Co-authored-by: David S. Batista <dsbatista@gmail.com>
