* Further observability cleanup and update telemetry samples
* Add VS Code Extension config
* Fix unit tests
* Fix unit tests
* Add more comments
* Remove live metric
* removed intercepts_request and simplified how interception is handled
* parameterize SubWorkflowRequestInfo
* revert back the field rename of RequestResponse
* remove duplicate tests
* ignore type error
* remove SubWorkflowResponse
* Remove SubWorkflowRequestInfo and update RequestInfoMessage with source_executor_id for correlation
* Improve type utils
* Add sample
* Add Union
* Add more test cases
* Add more test cases
* Fix RequestResponse typing to only coerce mapping original_request
---------
Co-authored-by: Evan Mattson <evan.mattson@microsoft.com>
* Setting up
* Readme
* Add redis tests path to all-tests
* First pass integration
* Keep provider convention
* First pass integration
* add redis integration tests
* update README.md
* Add basic sample for redis integration
* Add partitioning, add partition-aware tests, improve sample script
* Fix code quality check
* Try to resolve pytest check
* Try to identify if pytest is the cause of failed checks
* Re-enable tests
* Rename redis test file
* Removing some tests to narrow down issue
* Revert, no difference
* Delete temp files
* Starting refactor of RedisProvider
* Build dynamic schema builder, still need to do dynamic embedding model config
* Add scope control
* Complete first pass functionality with OpenAI + HF vectors -> Tests, Samples, Demo to follow
* Fix code quality
* attempt to identify rootcause of failed test
* attempt to identify rootcause of failed test
* Attempt to resolve code quality fail
* Update pyproject.toml for foundry to pin azure-ai-projects == 1.1.0b3,azure-ai-agents == 1.2.0b3
* Add tests for redisprovider
* Remove invalid tests
* Add API key handling for openai vectorizer
* Update uv.locl
* Use master uv.lock
* Begin sample file, add lazy index creation, fix faulty override
* Index drop and reinit depends on drop_redis_index not overwrite
* Add samples, threading included, escaped queries, verify threading works, sample README.md
* Refactor filters
* Opinionated vars
* Allow filter expression combination
* Try inline stubs for mypy
* Address mypy errors
* Better docstrings, tweaks for feedback
* Tweak example 3 in redis_threads.py sample
* adjust confusing name
* Enrich docstrings
* Add descriptions and comments to samples, externalize vectorizer choice, remove nltk and sentencetransformers dependnecy
* Add descriptions and comments to samples, externalize vectorizer choice, remove nltk and sentencetransformers dependnecy
* Incorporate initial feedback from dmytrostruk
* Fix uv.lock
* Attempt to resolve conflict
* Use remote .tomls
* Sanity check
* fix tests
* Remove hardcoded API key from samples
* Fix incorrect env var
* Make add and redis_search private
* Fix tests relying on private funcs
* Expand tests
* Explainer comments to each test
* Add a 'get_conversation_history' function to RedisProvider - This just returns messages in sequential order. Added 'created_at_*' timestamps to facilitate sequential recovery. function has to be manually invoked by user
* Add agent-framework-redis to python/pyproject.toml
* Remove get_conversation_history
* improve redis context provider with pydantic techniques and safe index handling patterns
* add RedisChatMessageStore
* remove integration test :(
* fix mypy error
* Remove unused params
* Redo schema validation to be order-invariant, handle attrs (previously throwing errors due to strict ==)
* Expand explanation
* Add ChatMessageStore example
* Fix comments in redis_conversation.py
* Resolving uv.lock conflict, update to match main
* Fix test in redis provider
* Apply suggestion from @ekzhu
* Update python/packages/main/pyproject.toml
---------
Co-authored-by: Tyler Hutcherson <tyler.hutcherson@redis.com>
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* Initial middleware implementation
* Small fixes
* Small updates
* Small updates in samples
* Moved middleware functionality to decorator
* Removed obsolete file
* Renamed AgentInvocationContext to AzureRunContext
* Added unit tests
* Small settings update for test discovery in VS Code
* Added unit tests
* Reverted changes in environment settings
* Added context result override
* Renaming and updates to logic
* Added more samples
* Updated DEV_SETUP.md
* Addressed PR feedback
* Addressed PR feedback
* Removed unused parameter
* Small fix
* Small fix in telemetry logic
* Revert "Small fix in telemetry logic"
This reverts commit 6f82660d2d.
* Small fix
---------
Co-authored-by: Chris <66376200+crickman@users.noreply.github.com>
* Adds Azure Monitor Entra ID authentication support
Enables token-based authentication for Application Insights by adding an optional credential parameter to telemetry setup functions.
* Fix linting errors
* Documentation: Add Entra ID authentication details to README for Application Insights
* Documentation: Add Entra ID authentication details to README for Application Insights
* Update python/packages/main/agent_framework/telemetry.py
Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com>
* Update python/samples/getting_started/telemetry/README.md
Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com>
* Update python/packages/main/agent_framework/telemetry.py
Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com>
* Rename application_insights_credential to credential
---------
Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com>
* Move workflow to main package
* Remove workflow specific unit test config
* Remove workflow-specific version info
* Revert unintended telemetry changes
* Removed the obsolete packages/workflow/tests target
* Rename dir workflow to _workflow
* Fix test imports
* Add support for the Sequential Builder. Add samples. Add tests
* AgentExecutor: always compute full convo during response
* Upgrade azure-ai-agents ToolOutput to FunctionToolOutput
* Explicit notes around allows types for custom agent executors
* Small fix in dotnet conformance tests
* Added CopilotStudioAgent implementation
* Added examples
* Updated package README
* Small fixes
* Small improvements
* Fixed dotnet tests
* Add unit tests
* Updated tests
* Small updates
* Small test fixes
* Revert "Small test fixes"
This reverts commit 983ac44a70.
* Small fixes in documentation
* Updated test configuration
* Revert "Updated test configuration"
This reverts commit 2a16fea815.
* Small fix
* Reverted TODO item
* Small suppressions
* More fixes
* Small fixes
* Fixed tests
* Removed disallow_any_unimported rule in all packages
* Fixes
* feat: add OpenAI reasoning events support with comprehensive test coverage
- Implement reasoning event handling in OpenAI Responses client
* Add support for ResponseReasoningTextDeltaEvent
* Add support for ResponseReasoningTextDoneEvent
* Add support for ResponseReasoningSummaryTextDeltaEvent
* Add support for ResponseReasoningSummaryTextDoneEvent
* Map all reasoning events to TextReasoningContent objects
* Preserve metadata across reasoning events
- Add comprehensive test coverage (5 focused test functions)
* test_streaming_reasoning_text_delta_event
* test_streaming_reasoning_text_done_event
* test_streaming_reasoning_summary_text_delta_event
* test_streaming_reasoning_summary_text_done_event
* test_streaming_reasoning_events_preserve_metadata
- Add sample demonstrating reasoning functionality
* Shows how to enable reasoning in chat options
* Demonstrates accessing reasoning content from responses
- Code quality improvements
* Follow existing code patterns and style guidelines
* Organize imports properly
* Maintain backwards compatibility
* All tests pass and quality checks succeed
* fix: resolve type errors and cleanup unused imports after rebase
- Add proper hasattr checks for optional attributes in union types
- Remove unused OpenAI event type imports
- Fix line length formatting issues
- Ensure type safety when accessing content attributes
* Added context provider abstractions
* Added mem0 implementation
* Example and small fixes
* Added unit tests for agent
* Added unit tests for mem0 provider
* Updated README
* Small doc updates
* Update python/packages/mem0/agent_framework_mem0/_provider.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Small fixes in tests
* Renaming based on PR feedback
* Small fixes
* Added tests for AggregateContextProvider
* Small improvements
* More improvements based on PR feedback
* Small constant update
* Added more examples
* Added README for Mem0 examples
* Small updates to API
* Updated initialization logic
* Updates for context manager
* Updated Context class
* Dependency update
* Revert changes
* Fixed tests
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Chris <66376200+crickman@users.noreply.github.com>
* test with stack and simplified names
* quick demo of agent decorator
* moved builder to protocol to enhance functionality
* undid chatclientAgent -> agent rename
* one more
* reverted AIAgent rename
* final reverts
* fixed foundry import
* revert changes
* streamlined otel and fcc decorators
* cleanup of telemetry
* further refinement
* lots of updates
* fixed typing
* fix for mypy
* added input and output atttributes
* fix import
* initial work on baking in otel
* major update to telemetry
* final fixes after rename
* fix
* fix test
* updated tests
* fix for tests
* fixes for tests
* updated based on comments
* removed agent decorator
* fix for Python: ServiceResponseException when using multiple tools
Fixes#649
* addressed comments
* fix tests
* fix tests
* fix tools tests
* fix for conversation_id in assistants client
* fix responses test
* fix tests and mypy
* updated test
* foundry fix
---------
Co-authored-by: Chris <66376200+crickman@users.noreply.github.com>
* initial work on User Approval (and hosted mcp to validate)
* small update to the comments in the sample
* enable local MCP tools in chatClient get methods
* working streaming and improved setup
* fix for pyright
* updated create_approval -> create_response method
* added tests
* updated HostedMcpTool and addressed feedback
* update type name
* naming updates
* small docstring update
* mypy fix
* fixes and updates
* fixes for responses
* fix int tests
* removed broken tests
* updated test running
* removed specific content check on websearch
* increased timeout
* split slow foundry test
* don't parallel run samples
* add dist load to unit tests
---------
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* Update getting started with workflows sample structure and README
* Small updates
* Adjust getting started samples. Fix agent executor bug. Add workflow tests to unit test file.
* Fix resource links
* start a new implementation based on .net
* add response handling
* update init files
* remove handling of WorkflowCompletedEvent
* clean up implemenation
* fix bug
* update tests for merge_updates
* WorkflowAgent validation
* add a sample and fix bug
* revert pre-commit config
* revert pre-commit
* add human in the loop sample
* add comment
* fix type issue in Executor
* fix type errors and rename Executor.type to Executor.type_ with field alias
* fix test
---------
Co-authored-by: Chris <66376200+crickman@users.noreply.github.com>
* workflow tracing design doc
* add tracing implementation for workflow
* fix bug caused by double wrapping of sub workflow request
* add unit tests for tracing
* add documentation for workflow tracing
* remove unnecessary file
* update aspire command
* fix tests
* proper serialization of subworkflows and add workflow.definition
* add serialization test
* fix subworkflow serialization
* workflow_id --> id
* update workflow sample to address comments
* update naming; use costant
* use NoOpTracer instead of nullcontext
* use span event instead of attribtutes for status
* fix typing
* add workflow.build span
* rename methods for clarity
* ensure all source trace contexts are propagated in fan in
* 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>
* 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
Tao ChenandGitHub
Eduard van ValkenburgandGitHub
Eric ZhuandGitHub
Christian GlessnerandGitHub
peterychangandGitHub