* mcp parts
* mcp parts 2
* removed structured output in favor of handling in chatresponse, mcp as AITool and running samples
* updated naming
* fixed test
* openai updates
* rebuild of openai structure
* updated responses structure
* renamed sample
* added file id support to code interpreter
* added hosted file ids to code interpretor
* mypy fixes
* removed default az cred from codebase
* updated agent name setup
* added kwargs to entra methods
* and further kwargs
* extra comment
* updated all samples
* readded custom get methods for responses
* updated int tests with ad credential
* missed one
* added AIAnnotation types and extra tests
* fixed typing and such
* use copy
* fix raw representation for add
* handle annotations in add
* clarified concat
* self to first
* move all tests under tests and initial work on int tests
* added updated tests setup and merge tests
* without failing step
* fixed upload
* updated file names for coverage
* reenable surface tests
* removed package matrix
* simplified variables
* correct path
* removed mistake
* fix mistake in path
* fix path
* windows specific env set
* updated merge tests
* slight update in marker
* added run integration tests settings
* updated setup, moved foundry int tests and updated merge test
* Initial version of FoundryChatClient
* Updates to the tool call streaming wrapper
* Small fixes
* Small updates and addressed PR feedback
* Handle automatic client creation
* Small improvement
* Added credential parameter
* Small improvements
* Made FoundryChatClient disposable
* Small fixes
* Added unit tests
* Refactored samples
* Small improvements
* Small fix
* Addressed PR feedback
* Small fixes
* Small updates
* Small fix
* Addressed PR feedback
* added ChatClientBase with function calling
* streaming update
* fixed typing
* test setup
* small update
* src setup
* removed src, updated test naming
* fixed test command
* alolow args
* updated test run
* added unit test folder to azure
* added init and unit test to azure
* added other cross tests
* restructured
* reset test run
* fix name
* removed always
* updated test
* extend pytest.xml locations
* run surface always
* added decorators for FC and marked tests
* fixed mypy settings and added tests
* fix override import
* removed import
* feat: ModelClient and content types
* refactor: Pythonify ChatResponseFormat and ChatRole
* feat: Add guardrail interfaces
* refactor: Remove CancellationToken
* feat: Solidify the Usage APIs
* Adds well-known keys for additional_counts, and guidance for how to avoid collisions between providers
* Implement sum-aggregation for usage
* refactor: Move AITool out of model_client
* refactor: Copy editing
* fix: CI checks (pyupgrade, ruff, etc.)
* ci: Fix pre-commit to use pyright in uv venv
The existing pyright precommit hook inside of python-pyright is no longer being maintained by the owner (see https://github.com/RobertCraigie/pyright-python/issues/265)
The fix is to define the hook ourselves, relying on `uv run` to drive it. In order for that to work right we need to use the "system" language to break out of the sandbox.
* fix: Pyright error fixes
* docs: Update models and types design docs
* Python: Refinement of content types and model client (#112)
* refinement of structure and buildup
with ports from semantigen
* refined the data and uri contents
* refined chat response and updates
* moved things and added tests
* moved out of src folder
* fixed imports and tests
* small tweaks
* missing build system
* upgrade
* add mypy
* fixed typing for types
* fix tests
* fixed tool
* disable json checks on vscode
* remove print
---------
Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com>
Co-authored-by: eavanvalkenburg <github@vanvalkenburg.eu>
Eduard van ValkenburgandGitHub
peterychangandGitHub
Dmytro StrukandGitHub
Jack GerritsandGitHub