* Adding design documents and data flow descriptions for sub-workflows
* Updating docs.
* Sub-workflow implementation #1. Stuck because of singleton RequestInfoExecutor, going to make a change to remove that restrivtion.
* Removed the singleton restriction on RequestInfoExecutor so enable sub-workflows.
* Scenarios seem to be working.
* Sample improved.
* going to have intern add generic response wrappers.
* Wrapped responses working.
* Non-hardcoded routing is working.
* Sample showing external approved and not approved.
* Cleaning up.
* Updating some samples and user guide.
* Removing old design doc.
* Cleaning up.
* Adding python-package-setup.md back.
* Update python/packages/workflow/agent_framework_workflow/_executor.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Update python/packages/workflow/agent_framework_workflow/_validation.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Removing prints.
* Fixing lint and type issues.
* Fixing lint and type issues.
* Update python/packages/workflow/agent_framework_workflow/_executor.py
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* Adding type hints to intercepts decorator.
* Removing unused files.
* Fixing issue with sample 5 groupchat with hil.
* Removing redundent samples.
* Updates to ensure no conflicting request interceptors and to support a subflow with multiple requests in a single super step.
* Fixing pypi errors.
* clean up samples
* update samples to make it more clear
* warning for unhandled request info from sub workflow
* add logger info
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* Refactor workflow to introduce EdgeRunner for edge execution.
* Fix edge cases
* Convert Workflow, Edge, EdgeGroup, and Executor into AFBaseModel to support object model serialization
* format
* remove accidental file
* fix typing
* Add type information to EdgeGroup and Executor subclasses
* fix format
* Add condition_name field to Edge
* Add new fields
* remove Optional
* Update
* Use generic for WorkflowContext and use its type parameters to indicate executor's output types
* Update
* Fix type errors and add in-line comments
* fix test
* type
* Fix executor type issues
* Introducing edge groups
* Add conditional and partitioning edge groups; next add samples and tests
* Add unit tests
* Add samples
* Address comments 1
* Address comments 2
* Update conditional edge group to take in cases and default
* Minor updates to sample
* Collapsing Paritioning Edge group and Conditional Edge group to source edge group
* Improve sample clarity
* Name consolidation
---------
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* Updates for message store support
* Added unit tests
* Added suspend-resume example
* Added example with custom chat message store
* Small fix
* Addressed PR feedback
* Renaming and documentation
* More renaming
* Addressed more PR feedback
* Small fixes in Foundry chat client and examples
* Small update
* Addressed PR feedback
* Increased timeout for Azure tests
* 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
* Azure Responses client
* Fix a change made in the wrong place
* allow api_version and token_endpoint to use env vars
* Add getting started sample
* add responses deployment name env var
* update azure clients to use defaults for api_version and token_endpoint
* make tests more reliable
---------
Co-authored-by: Chris <66376200+crickman@users.noreply.github.com>
* small fixes in foundry
* other samples updated
* make it optional
* added instructions and response format to create agent
* mypy fix
* shortened main readme and improved python readme
* Initial version of assistant client
* More updates to assistant client
* Finished assistant chat client implementation
* Small fixes and basic example
* Added code interpreter example
* More examples
* Added chat client example
* Small fixes
* Added tests
* Enabled telemetry
* Small fix
* Removed files temporarily
* Revert "Removed files temporarily"
This reverts commit 5cdfa0d299.
* Small fixes
* Addressed PR feedback
* Fixed tests
* Small update
* Added basic example with small fix
* Added example with function tools
* Added example with thread management
* Small renaming
* Added example with code interpreter
* Added non-streaming and streaming examples
* Updated resource management
* Added examples with thread management
* Added function tools examples
* Small rename
* Added code interpreter example
* Updated example
* Addressed PR feedback
* Added more OpenAI and Azure chat completion examples
* File renaming
* Small fix in tests
* Small revert
* More renaming
* Small fix
* 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
* tweaks to agents and sample
* updated clients and agents
* single line run and print
* improved tool handling
* added note on setting max iterations
* fixed streaming param name
* updated tools test
* made kwargs alphabetical
* added params to run methods
* tweak to ensure right overload
* Added ChatClientAgentThread
* Initial version of ChatClientAgent
* Completed ChatClientAgent
* Small fixes and unit tests
* Fixes based on pre-commit
* Small fixes
* Small renaming
* Small improvement
* Small fixes
* Addressed PR feedback
* Small fix
* Added method for AgentRunResponse from streaming conversion
* Addressed PR feedback
* Addressed PR feedback
* Addressed PR feedback
* Small fix
* More fixes
Dmytro StrukandGitHub
peterychangandGitHub
Tao ChenandGitHub
Eduard van ValkenburgandGitHub
