Commit Graph

2155 Commits

  • Python: Context providers abstraction and Mem0 implementation (#631)
    * 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>
  • .NET: Workflow getting started samples in .Net (Second batch) (#650)
    * Add loop and agents in workflows samples
    
    * Add foundry agent and workflow as agent samples
    
    * Checkpoint sample WIP
    
    * Checkpoint sample 1 Done
    
    * Add HIL samples
    
    * Fix formatting
    
    * Force folder name change step 1
    
    * Force folder name change step 2
    
    * Fix formatting
    
    * Fix formatting
    
    * Add checkpoint and rehydrate sample
    
    * _Foundational
    
    * Fix formatting
  • .NET: Adding Image Multi Modality Sample (#688)
    * Adding Multi Modal Sample
    
    * Address typos
    
    * Update sample to Azure OpenAI
    
    * Update readme
    
    * Update readme
    
    * Update readme
    
    * Use thread
  • .NET Workflows - Add declarative action events (#679)
    * Updated
    
    * Typos
    
    * Update sample
    
    * Typo
    
    * Add parent and prior action ids to event
  • Python: Improved telemetry setup (#421)
    * 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>
  • Python: Introducing UserInputRequest and Response types and HostedMcpTool (#405)
    * 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>
  • Python: added user agents to foundry and azure openai (#658)
    * added user agents to foundry and azure openai
    
    * improvement
    
    * improvement for disabled setup
  • .NET: fix: MessageMerger crashes when there are no dangling messages (#660)
    * fix: MessageMerger crashes when there are no dangling messages
    
    * refactor: Better logic for AgentId in Workflow-as-Agent
    
    If the parent "agent" instance received an Id or Name when being instantiated, we should avoid stomping over it with the subagents' ids. But if there is no parent identifier, and only a single subagent yielded identified messages, pull that in.
  • .NET: Add getting started samples that show how to call MCP tools (#635)
    * Add getting started samples that show how to call MCP tools
    
    * Add getting started samples that show how to call MCP tools
    
    * Update dotnet/samples/GettingStarted/ModelContextProtocol/Agent_MCP_Server_Auth/README.md
    
    Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
    
    * Fix README
    
    * Address code review feedback
    
    ---------
    
    Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
  • Python: add base_url parameter for openai chat client (#661)
    * added base_url option for openai chat client
    
    * fix test url
  • .NET: Add an A2A client server sample (#633)
    * Add an A2A client server sample
    
    * Address code review feedback
    
    * Start to fix code review feedback
    
    * Start to fix code review feedback
    
    * Start to fix code review feedback
  • .NET: Remove AgentThread.GetMessagesAsync (#668)
    * Remove AgentThread.GetMessagesAsync
    
    * Remove unecessary using
  • .NET: Multiple fixes in Microsoft.Agents.Orchestration to make handoffs work end-to-end (#568)
    * Multiple fixes in Microsoft.Agents.Orchestration:
    - Enable multi-turn (via RunAsync) interactions for all orchestrating agents
    - Fix tool calling in HandoffOrchestration (multiple issues)
    - Fixes for chat history serialization involving tool calls
    
    * GHCP PR feedback
    
    * Fix issue with returning old responses
    
    ---------
    
    Co-authored-by: Chris <66376200+crickman@users.noreply.github.com>
  • .NET: Add Ollama and custom agent samples, plus ONNX improvements (#639)
    * Add ollama and custom agent samples, plus onnx improvements
    
    * Update dotnet/samples/GettingStarted/AgentProviders/Agent_With_CustomImplementation/Program.cs
    
    Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
    
    * Address PR comments.
    
    * Address pr comments.
    
    ---------
    
    Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
  • Bump actions/labeler from 5 to 6 (#630)
    Bumps [actions/labeler](https://github.com/actions/labeler) from 5 to 6.
    - [Release notes](https://github.com/actions/labeler/releases)
    - [Commits](https://github.com/actions/labeler/compare/v5...v6)
    
    ---
    updated-dependencies:
    - dependency-name: actions/labeler
      dependency-version: '6'
      dependency-type: direct:production
      update-type: version-update:semver-major
    ...
    
    Signed-off-by: dependabot[bot] <support@github.com>
    Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
  • Python: Update getting started with workflows sample structure and README (#653)
    * 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
  • Python: Samples Integration Tests (#615)
    * Samples Tests
    
    * small fixes
    
    * job fix
    
    * telemetry dependency fix
    
    * job error fix
    
    * sorting provider specific tests
    
    * telemetry fixes
    
    * openai file search fix
    
    ---------
    
    Co-authored-by: Giles Odigwe <gilesodigwe@microsoft.com>
  • .NET Workflows - Update structure of samples (#645)
    * Updated
    
    * Typos
    
    * Update readme fwiw
  • Update README (#644)
    * Update README with clearer setup instructions and direct links to getting started guides
    
    * Update README.md
    
    Co-authored-by: Tao Chen <taochen@microsoft.com>
    
    ---------
    
    Co-authored-by: Tao Chen <taochen@microsoft.com>
  • fix: Fix Checkpoint Restore when Rehydrating Run (#642)
    When checkpointing we did not persist the set of instantiated executors. This means, in turn, when we restore from a checkpoint when using Resume(Stream) rather than restoring a checkpoint in the context of an already existing (Streaming)Run, the executors never got reinstantiated and there were no executors to notify that a state should be loaded.
    
    The fix is to ensure we persist the list and reinstantiate the executors on rehydration.
    
    * Also adds a rehydration restore test
  • Adding workflows label to PRs when appropriate. (#643)
    * Adding workflows label to issues when appropriate.
    
    * Adding declarative workflows path.
  • .NET: Improve DevEx for simple Executors (#626)
    * feat: Improve DevEx for simple Executors
    
    * Add abstract types for executors that will only handle one type of message
    * Add FunctionExecutor and configuration capability on delegates
    * Add support for late-instantiated Executors
    
    * refactor: Remove open-typed extension method
    
    * refactor: Switch to TaskFactory pattern for async--from-sync
    
    * docs: Update XML docs for publics and fix formatting
    
    * refactor: Better naming for ExecutorIsh configuration methods
    
    * docs: Fix typo in ExecutorIshConfigurationExtensions.ConfigureFactory
  • Python: Improve the workflow getting started samples (#570)
    * Wip: samples
    
    * wip - samples
    
    * Updates to workflow getting started samples
    
    * Checkpointing enhancements
    
    * Cleanup
    
    * PR feedback
    
    * Updates
    
    * Sample updates
    
    * Updates
    
    * Revamp samples, improve doc strings and code comments
    
    * Cleanup unused comment
    
    * Formatting cleanup
    
    * wip
    
    * Further work on samples. Allow agent to be specified as edge.
    
    * Cleanup
    
    * Typing cleanup
    
    * Sample updates
    
    ---------
    
    Co-authored-by: Chris <66376200+crickman@users.noreply.github.com>
    Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
  • .NET: Workflow getting started samples in .Net (First batch) (#554)
    * First batch of workflow getting started samples in .Net
    
    * Add Switch Case Edge group
    
    * Add multi selection group
    
    * Add comments
    
    * Add readme
    
    * Fix formatting
    
    * clean project file
    
    * WIP: Revise sample structures
    
    * Update readme
    
    * Update readme
    
    * Fix file encoding
    
    * Update sample format
    
    * Address comments
    
    * Fix formatting
    
    * Remove unwanted file
    
    * Fix unit tests
    
    * Remove unwanted file
  • Add PrPr welcome message and important notes to README (#614)
    * Add PrPr welcome message and important notes to README
    
    Enhanced the README with a comprehensive welcome message for the private preview, highlighting the multi-language framework capabilities and key features. Added important notes about package availability and the need to sync forks regularly for this active project.
    
    * Update README to use 'clone' instead of 'fork and clone'
    
    * Update README.md
    
    Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
    
    ---------
    
    Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
  • .NET: AI agent as an MCP tool (#612)
    * add sample demostrating how to expose ai-agent as an mcp tool
    
    * Update dotnet/samples/GettingStarted/Agents/Agent_Step10_AsMcpTool/Program.cs
    
    Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
    
    * Update dotnet/samples/GettingStarted/Agents/README.md
    
    Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
    
    * remove threadId parameter
    
    ---------
    
    Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
  • Python: name changes executed (#607)
    * name changes executed
    
    * updated adr to accepted
    
    * renamed openai base config
    
    * renamed openai config to mixin
    
    * added renames in user docs
    
    * reverted mcperror
    
    * fix tests
    
    * remove sse from tests
  • Python: Added documentation how to run examples (#605)
    * Added documentation how to run examples
    
    * Small fix
    
    * Update user-documentation-python/getting-started/running_examples.md
    
    Co-authored-by: Tao Chen <taochen@microsoft.com>
    
    * Small fix
    
    ---------
    
    Co-authored-by: Tao Chen <taochen@microsoft.com>
  • Python: Add edge group traces (#597)
    * add edge group traces
    
    * add edge group attributes
    
    * update unit tests
    
    * add span links
  • Python: WorkflowViz to support sub workflows (#571)
    * add visualization for sub workflows
    
    * add visualization to subworkflow samples
    
    * Update python/packages/workflow/agent_framework_workflow/_viz.py
    
    Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
    
    * Update python/packages/workflow/agent_framework_workflow/_viz.py
    
    Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
    
    * update
    
    * remove changes to samples
    
    ---------
    
    Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
    Co-authored-by: Chris <66376200+crickman@users.noreply.github.com>
    Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com>
  • .NET: Getting started samples which use OpenAI exchange types (#598)
    * Getting started samples which use OpenAI exchange types
    
    * Update dotnet/src/Microsoft.Extensions.AI.Agents.OpenAI/Extensions/AgentRunResponseUpdateExtensions.cs
    
    Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
    
    * Update dotnet/src/Microsoft.Extensions.AI.Agents.OpenAI/Extensions/AgentRunResponseUpdateExtensions.cs
    
    Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
    
    * Update dotnet/src/Microsoft.Extensions.AI.Agents.OpenAI/ChatCompletion/StreamingUpdatePipelineResponse.cs
    
    Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
    
    * Update dotnet/samples/GettingStarted/AgentWithOpenAI/README.md
    
    Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
    
    * Fix pipeline response
    
    * Update dotnet/samples/GettingStarted/AgentWithOpenAI/README.md
    
    Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com>
    
    * Update comment to reflect OpenAI backend usage
    
    ---------
    
    Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
    Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com>
  • .NET: Add Declarative Workflow Interpreter (#401)
    * test: Add Reflection/Invocation tests
    
    * fix: Terminate on Completion event
    
    * refactor: Update public API surface
    
    * feat: Add support for external requests
    
    * feat: Support hosting AIAgent instances in Workflows
    
    * fix: Fix routing to go through Executor.ExecuteAsync
    
    * test: Update samples for "must SendMessage" semantics
    
    * Add invoking samples to unit tests to avoid future breaks
    
    * fix: ExternalRequest should block Workflow completion
    
    * feat: Normalize API surface against Python
    
    * Also adds xmldoc to all public APIs
    
    * refactor: Normalize UnitTest and Sample namespaces
    
    * fix: Formatting
    
    * refactor: Normalize project/folder names
    
    * feat: Remove DynamicCodeExecution from ValueTaskTypeErasure
    
    * fix: Fix ILTrim warnings
    
    * docs: Add missing docs and fix typos
    
    * feat: Hosted Agents should report Run events
    
    * fix: Fix type propagation for ILTrim changes
    
    * refactor: Simplify DynamicallyAccessedMembers annotations
    
    * sample: Use static-Type construction of InputPort
    
    * feat: Support non-Streaming Run Mode
    
    * test: Add test for non-streaming execution
    
    * Conversion checkpoint
    
    * Fix namespace error
    
    * Restructure
    
    * Completion
    
    * Executor checkpoint
    
    * Conditional checkpoint
    
    * Cleanup
    
    * Exception cleanup
    
    * Sample cleanup
    
    * Updates
    
    * feat: Define Workflow and Executor APIs
    
    * feat: Define IExecutionContext and Events
    
    * feat: Simple Workflow Demos
    
    * refactor: Move Workflows classes to separate assembly
    
    * feat: Move FanOut/In to LowLevel API with new semantics
    
    * feat: Implement Local Execution
    
    * refactor: Assembly name .Workflow => .Workflows
    
    * feat: Enable Default Message Handling
    
    * also lifts Bind in MessageHandlerInfo to better be able to direclty invoke handlers (for AOT, later)
    
    * feat: Implement StreamingHandle APIs
    
    This allows the user to respond to WorkflowEvents with external messages, enabling HIL.
    
    * feat: Add checks for duplicate edges and chain cycles
    
    * feat: Add built-in WorkflowEvents
    
    * refactor: Pull classes into own files
    
    * refactor: Simplify Disposal pattern in Executor
    
    * refactor: Break EdgeRunner file into per-type files
    
    * refactor: Use Throw.IfNull()
    
    * refactor: Remove AddLoop()
    
    Per https://github.com/microsoft/agent-framework/pull/272#discussion_r2241739079 we decided this was not very useful.
    
    * refactor: Normalize use of ValueTask
    
    * fix: Build Break from removing .AddLoop
    
    * refactor: Explicit routing and RouteBuilder
    
    Split out reflection from MessageRouter implemention into build phase, enabling AOT compilation to drive RouteBuilding without reflection.
    
    * test: Add Reflection/Invocation tests
    
    * fix: Terminate on Completion event
    
    * refactor: Update public API surface
    
    * feat: Add support for external requests
    
    * feat: Support hosting AIAgent instances in Workflows
    
    * fix: Fix routing to go through Executor.ExecuteAsync
    
    * test: Update samples for "must SendMessage" semantics
    
    * Add invoking samples to unit tests to avoid future breaks
    
    * fix: ExternalRequest should block Workflow completion
    
    * feat: Normalize API surface against Python
    
    * Also adds xmldoc to all public APIs
    
    * refactor: Normalize UnitTest and Sample namespaces
    
    * fix: Formatting
    
    * refactor: Normalize project/folder names
    
    * feat: Remove DynamicCodeExecution from ValueTaskTypeErasure
    
    * fix: Fix ILTrim warnings
    
    * docs: Add missing docs and fix typos
    
    * feat: Hosted Agents should report Run events
    
    * fix: Fix type propagation for ILTrim changes
    
    * refactor: Simplify DynamicallyAccessedMembers annotations
    
    * sample: Use static-Type construction of InputPort
    
    * feat: Support non-Streaming Run Mode
    
    * test: Add test for non-streaming execution
    
    * refactor: Remove unused types
    
    * refactor: Simplify Event and EdgeData type hierarchies
    
    * feat: Add Switch (=Conditional Edge Group) control flow
    
    * Fix unit-tests
    
    * Add sample
    
    * Comment cleanup
    
    * Fix debug output
    
    * Formating helpers
    
    * feat: Define Workflow and Executor APIs
    
    * feat: Define IExecutionContext and Events
    
    * feat: Simple Workflow Demos
    
    * refactor: Move Workflows classes to separate assembly
    
    * feat: Move FanOut/In to LowLevel API with new semantics
    
    * feat: Implement Local Execution
    
    * refactor: Assembly name .Workflow => .Workflows
    
    * feat: Enable Default Message Handling
    
    * also lifts Bind in MessageHandlerInfo to better be able to direclty invoke handlers (for AOT, later)
    
    * feat: Implement StreamingHandle APIs
    
    This allows the user to respond to WorkflowEvents with external messages, enabling HIL.
    
    * feat: Add checks for duplicate edges and chain cycles
    
    * feat: Add built-in WorkflowEvents
    
    * refactor: Pull classes into own files
    
    * refactor: Simplify Disposal pattern in Executor
    
    * refactor: Break EdgeRunner file into per-type files
    
    * refactor: Use Throw.IfNull()
    
    * refactor: Remove AddLoop()
    
    Per https://github.com/microsoft/agent-framework/pull/272#discussion_r2241739079 we decided this was not very useful.
    
    * refactor: Normalize use of ValueTask
    
    * fix: Build Break from removing .AddLoop
    
    * refactor: Explicit routing and RouteBuilder
    
    Split out reflection from MessageRouter implemention into build phase, enabling AOT compilation to drive RouteBuilding without reflection.
    
    * test: Add Reflection/Invocation tests
    
    * fix: Terminate on Completion event
    
    * refactor: Update public API surface
    
    * feat: Add support for external requests
    
    * feat: Support hosting AIAgent instances in Workflows
    
    * fix: Fix routing to go through Executor.ExecuteAsync
    
    * test: Update samples for "must SendMessage" semantics
    
    * Add invoking samples to unit tests to avoid future breaks
    
    * fix: ExternalRequest should block Workflow completion
    
    * feat: Normalize API surface against Python
    
    * Also adds xmldoc to all public APIs
    
    * refactor: Normalize UnitTest and Sample namespaces
    
    * fix: Formatting
    
    * refactor: Normalize project/folder names
    
    * feat: Remove DynamicCodeExecution from ValueTaskTypeErasure
    
    * fix: Fix ILTrim warnings
    
    * docs: Add missing docs and fix typos
    
    * feat: Hosted Agents should report Run events
    
    * fix: Fix type propagation for ILTrim changes
    
    * refactor: Simplify DynamicallyAccessedMembers annotations
    
    * sample: Use static-Type construction of InputPort
    
    * feat: Support non-Streaming Run Mode
    
    * test: Add test for non-streaming execution
    
    * refactor: Remove unused types
    
    * refactor: Simplify Event and EdgeData type hierarchies
    
    * feat: Add Switch (=Conditional Edge Group) control flow
    
    * feat: Make .NET AutoSend the MessageHandler result
    
    * feat: Implement State APIs
    
    * Add tests
    
    * Fix merge from main
    
    * Test coverage
    
    * Message event
    
    * Comments and clean-up
    
    * Format
    
    * Cleanup
    
    * Test checkpoint
    
    * Clean-up - comments / test
    
    * Test baseline - 100%
    
    * More clean-up
    
    * Comments
    
    * Streaming...sort've...
    
    * Fix build / test
    
    * Stable
    
    * Checkpoint
    
    * Checkpoint
    
    * Stable
    
    * Update sample after merge
    
    * Add "Question" workflow
    
    * State clean-up checkpoint
    
    * State clean-up
    
    * Sample updated
    
    * Expression bug fix
    
    * Sample formatting
    
    * Add unit test
    
    * Comments
    
    * Scope cleanup
    
    * Refine cleanup
    
    * Fill gaps
    
    * fcs
    
    * Finalize data-types
    
    * Add unit-test
    
    * Debug cleanup
    
    * Bug fixes
    
    * Demo progress
    
    * Sample clean-up
    
    * Update samples
    
    * Sample updates
    
    * Sync demo workflows
    
    * Sample formatting
    
    * Sample formatting
    
    * Demo complete
    
    * Workflow formatting
    
    * Demo formatting #2
    
    * Readme + Sample clean-up
    
    * Scope update
    
    * Update diagnostics
    
    * Variable initiaization
    
    * Rollback
    
    * Tune research summary
    
    * State management
    
    * Fix merge
    
    * Fix merge - demo
    
    * Add readme
    
    * Overload for workflow builder
    
    * Fault tolerance - scope equivalency
    
    * Fix feed
    
    * Update sample
    
    * Add default for "Bot"
    
    * Nuget.config patchwork
    
    * Scope assignment check
    
    * Rollback nuget.config haxx
    
    * Sample format
    
    * Namespace
    
    * Namespace
    
    * Agent-Provider
    
    * Clean-up extra files
    
    * Renaming
    
    * Update sample
    
    * Prune junk files
    
    * Clean-up
    
    * Use transform
    
    * agent provider fix
    
    * Typo
    
    * Null check fix
    
    * Fix merge
    
    * Checkpoint
    
    * Cleanup
    
    * Exception cleanup
    
    * Exception message
    
    * Clean-up
    
    * Sample config update
    
    * Update handling of "Env" scope
    
    * Sample agent templates
    
    * Add readme
    
    * Event cleanup
    
    * Rename event
    
    * Update workflows/README.md
    
    Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
    
    ---------
    
    Co-authored-by: Jacob Alber <jaalber@microsoft.com>
    Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
  • ADR: python naming changes (#599)
    * python naming changes
    
    * small updates
    
    ---------
    
    Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
  • .NET: Add info on how to deploy Azure OpenAI models with Azure AI Foundry (#588)
    * Include details on required role
    
    * Update dotnet/samples/GettingStarted/Agents/README.md
    
    Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
    
    * Update dotnet/samples/GettingStarted/Agents/README.md
    
    Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
    
    * Add info on how to deploy Azure OpenAI models with Azure AI Foundry
    
    * Update dotnet/samples/GettingStarted/Agents/README.md
    
    Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
    
    ---------
    
    Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
  • Python: Add FunctionExecutor and @executor decorator (#589)
    * Add FunctionExecutor and @executor decorator
    
    * refactor
    
    * add single argument function
    
    * fix test
    
    * update example code
    
    * add support for sync funciton
  • Python: Add Python agent runtime project infrastructure (#563)
    * Add Python agent runtime project infrastructure.
    
    * lint.
    
    * Rename agent_runtime dir to agent_framework_runtime.
    
    * fix uv.lock
    
    * Update pyproject for rename.
    
    * Update python/packages/runtime/agent_framework_runtime/agent_actor.py
    
    Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
    
    * Add runtime package to workspace and optional dependencies.
    
    ---------
    
    Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>