* Add ADR for different run response options
* Add another option to the list.
* Update agno non-streaming with further clarification
* Add another option
* Adding optional includeUpdates option
* Adding Pros/Cons for each option
* Make pros/cons a list
* Add some thoughts on structured outputs and custom AIContent types
* Update design doc to clarify primary and secondary better and split out custom response types with it's own options
* Add structured outputs competitive comparison and suggestion
* Address PR comments.
* Remove AgentRunFinishReason until we can find a good use case for it.
* Add finish reason to list of excluded properties.
* Add custom agent run response types.
Usage to follow.
* Update Agent run response types
* Add additional code coverage
* Remove onIntermediateMessage since it is unecessary with the new response approach.
* Add AgentId to response.
* Rename ParseAsStructuredOutput to Deserialize
* Update decision doc.
* Fix formatting.
* Update CopilotStudio to return new response types
* Address PR comment
Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com>
---------
Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com>
* Added ADR templates and README
* First version
* Added remaining sections and commonalities across different providers
* Small formatting update
* Small formatting fix
* Updates for code interpreter tool
* Small update
---------
Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com>
* 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>
* initial draft of python package design
* typo
* revision
* further updates
* refinement
* refinement
* refinment
* added open q
* small edits
* type checking update
* refinement
* extended the logging section
* updates based on review
* added note on Otel
* restructured for even less verbosity
* initial draft
* fixes
* fixes
* incorporate reviewer feedback
* Remove attachment of context providers to threads. A separate issue now tracks this design question.
Eric ZhuandGitHub
Eduard van ValkenburgandGitHub
Ricky LoyndandGitHub
