Python: Merge durabletask changes into main (#3420)

* Python: Add initial scaffold for `durabletask` package (#2761) * Add initial scaffold * Update design * Fix mypy and update design * add additional style considered * Address comments * Fix test * Update readmes * Python: Rebase durable task feature branch with main (#2806) * Python: Add Entity State Providers for DurableTask Package (#2981) * Add Entity State Providers * address comments * Fix tests * Fix tests * Revert unrelated changes and remove thread_id * Revert unrelated files * Python: [Durabletask] Update `feature-durabletask-python` branch with `main` (#3068) * Python: Add factory pattern to concurrent orchestration builder (#2738) * Add factory pattern to concurrent orchestration builder * Update readme * Address AI comments * Fix unit tests * Fix import * Prevent multiple calls to set participants or factories * Add comments * Mitigate warnings * Fix mypy * Address comments * Address Copilot comments * Fix tests * Python: fix: GroupChat ManagerSelectionResponse JSON Schema for OpenAI Structured Outpu… (#2750) * fix: ManagerSelectionResponse JSON Schema for OpenAI Structured Output Strict Mode * refactor: install pre-commit then commit again * Capture file IDs from code interpreter in streaming responses (#2741) * .NET: [BREAKING] Prevent nulls in AIAgent property (#2719) * prevent nulls in AIAgent property * address feedback * code ql sm04598 (#2723) Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> * .NET: Add Conversation State Sample (Step05) (#2697) * Initial plan * Add Agent_OpenAI_Step05_Conversation sample for conversation state management Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> * Update Program.cs comment to accurately describe the sample Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> * Update the code to use the ConversationClient more in line with the samples in OpenAI * Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Changing sample to use ChatClientAgent and conversationId in GetNewThread --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Bump AWSSDK.Extensions.Bedrock.MEAI from 4.0.4.7 to 4.0.4.11 (#2777) --- updated-dependencies: - dependency-name: AWSSDK.Extensions.Bedrock.MEAI dependency-version: 4.0.4.11 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump Azure.Identity from 1.17.0 to 1.17.1 (#2780) --- updated-dependencies: - dependency-name: Azure.Identity dependency-version: 1.17.1 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.Identity dependency-version: 1.17.1 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.Identity dependency-version: 1.17.1 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.Identity dependency-version: 1.17.1 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump Azure.AI.AgentServer.AgentFramework from 1.0.0-beta.4 to 1.0.0-beta.5 (#2778) --- updated-dependencies: - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Python: added more complete parsing for mcp tool arguments (#2756) * added more complete parsing for mcp tool arguments * fixed mypy * added nonlocal model counter, and some fixes * fixes in naming logic * extracted json parsing function, added parametrized test and checked coverage * Python: Updated package versions (#2784) * Updated package versions * Small fix * Bump actions/checkout from 5 to 6 (#2404) Bumps [actions/checkout](https://github.com/actions/checkout) from 5 to 6. - [Release notes](https://github.com/actions/checkout/releases) - [Changelog](https://github.com/actions/checkout/blob/main/CHANGELOG.md) - [Commits](https://github.com/actions/checkout/compare/v5...v6) --- updated-dependencies: - dependency-name: actions/checkout 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> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * .NET: adds support for labels in edges, fixes rendering of labels in dot a… (#1507) * adds support for labels in edges, fixes rendering of labels in dot and mermaid, adds rendering of labels in edges * Update dotnet/src/Microsoft.Agents.AI.Workflows/Visualization/WorkflowVisualizer.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * escaping edge labels, adding tests for labels containing strange characters that would break the diagram and enabling the previous signature so the API has backwards compatibility. * Unify label in EdgeData * Edge API adjustments, removed useless "sanitizer" * fixed test --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Jacob Alber <jaalber@microsoft.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * Python: Added custom args and thread object to ai_function kwargs (#2769) * Added an example of using kwargs in ai_function * Added thread object to ai_function kwargs * Updated docs * Small fix * Added thread parameter filtering * Fix WorkflowAgent to include thread convo history. Enable checkpointing. (#2774) * Update OpenAIResponses.yaml to match AgentSchema (#2598) 1. Update `connection` child types -- `kind: ApiKey` to `kind: key` otherwise schema will fail: https://microsoft.github.io/AgentSchema/reference/apikeyconnection/ 2. Update `outputSchema`'s `PropertySchema` to be `kind` instead of `type` otherwise schema will fail: https://microsoft.github.io/AgentSchema/reference/propertyschema/ * Python: Remove warnings from workflow builder on not using factories (#2808) * Revert concurrent * Fix comments * Python: Filter framework kwargs from MCP tool invocations (#2870) * Filter framework kwargs from MCP tool invocations * Fixes * Python: Fix WorkflowAgent to emit yield_output as agent response (#2866) * Fix WorkflowAgent to emit yield_output as agent response * use raw_representation * Raw representation handling * Python: Use agent description in HandoffBuilder auto-generated tools (#2713) (#2714) ## Summary Enhanced `HandoffBuilder._apply_auto_tools` to use the target agent's description when creating handoff tools, providing more informative tool descriptions for LLMs. ## Changes - Modified `_apply_auto_tools` to extract `description` from `AgentExecutor._agent` when available - Updated iteration to use `.items()` for more efficient dict traversal - Handoff tools now use agent descriptions instead of generic placeholders ## Example Before: "Handoff to the refund_agent agent." After: "You handle refund requests. Ask for order details and process refunds." ## Testing - All handoff tests pass (20/20) - No breaking changes to existing API Fixes #2713 Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com> * Python: [BREAKING] Observability updates (#2782) * fixes Python: Add env_file_path parameter to setup_observability() similar to AzureOpenAIChatClient Fixes #2186 * WIP on updates using configure_azure_monitor * improved setup and clarity * fixed root .env.example * revert changes * updated files * updated sample * updated zero code * test fixes and fixed links * fix devui * removed planning docs * added enable method and updated readme and samples * clarified docstring * add return annotation * updated naming * update capatilized version * updated readme and some fixes * updated decorator name inline with the rest * feedback from comments addressed * Python: Fix middleware terminate flag to exit function calling loop immediately (#2868) * Fix middleware terminate flag to exit function calling loop immediately * Eliminating duck typing * Improve function exec result handling * Fix race condition * Fix mypy issues * Python: Fix context duplication in handoff workflows when restoring from checkpoint (#2867) * Fix context duplication in handoff workflows when restoring from checkpoint * Address Copilot PR review * .NET: Update to latest Azure.AI.*, OpenAI, and M.E.AI* (#2850) * Update to latest Azure.AI.*, OpenAI, and M.E.AI* Absorb breaking changes in Responses surface area * Update dotnet/samples/AgentWebChat/AgentWebChat.AgentHost/Utilities/ChatClientExtensions.cs * Update dotnet/samples/AgentWebChat/AgentWebChat.AgentHost/Utilities/ChatClientExtensions.cs * Update dotnet/samples/AgentWebChat/AgentWebChat.AgentHost/Utilities/ChatClientExtensions.cs * Update dotnet/samples/GettingStarted/AgentWithOpenAI/Agent_OpenAI_Step04_CreateFromOpenAIResponseClient/Program.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Using patch to remove the model is necessary, updated the response client to actually use the the ForAgent --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com> * Bump actions/download-artifact from 6 to 7 (#2862) Bumps [actions/download-artifact](https://github.com/actions/download-artifact) from 6 to 7. - [Release notes](https://github.com/actions/download-artifact/releases) - [Commits](https://github.com/actions/download-artifact/compare/v6...v7) --- updated-dependencies: - dependency-name: actions/download-artifact dependency-version: '7' 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> * Bump actions/cache from 4 to 5 (#2861) Bumps [actions/cache](https://github.com/actions/cache) from 4 to 5. - [Release notes](https://github.com/actions/cache/releases) - [Changelog](https://github.com/actions/cache/blob/main/RELEASES.md) - [Commits](https://github.com/actions/cache/compare/v4...v5) --- updated-dependencies: - dependency-name: actions/cache dependency-version: '5' 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> * Bump actions/upload-artifact from 5 to 6 (#2860) Bumps [actions/upload-artifact](https://github.com/actions/upload-artifact) from 5 to 6. - [Release notes](https://github.com/actions/upload-artifact/releases) - [Commits](https://github.com/actions/upload-artifact/compare/v5...v6) --- updated-dependencies: - dependency-name: actions/upload-artifact 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 : Ollama Connector for Agent Framework (#1104) * Initial Commit for Olama Connector * Added Olama Sample * Add Sample & Fixed Open Telemetry * Fixed Spelling from Olama to Ollama * remove"opentelemetry-semantic-conventions-ai ~=0.4.13" since its handled in a different pr * Added Tool Calling * Finalizing test cases * Adjust samples to be more reliable * Update python/packages/ollama/agent_framework_ollama/_chat_client.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update python/packages/ollama/pyproject.toml Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update python/packages/ollama/tests/test_ollama_chat_client.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update python/packages/ollama/agent_framework_ollama/_chat_client.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Improved Docstrings & Sample * Update python/packages/ollama/agent_framework_ollama/_chat_client.py Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com> * Integrate PR Feedback - Divided Streaming and Non-Streaming into independent Methods - Catch Ollama Validation Error - Add OTEL Provider Name - Checked Ollama Messages - Add Usage Statistics * Revert setting, so it can be none * Validate Message formatting between AF and Ollama * Catch Ollama Error and raise a ServiceResponse Error * Fix mypy error * remove .vscode comma * Add Reasoning support & adjust to new structure * Add Ollama Multimodality and Reasoning * Add test cases for reasoning * Add Tests for Error Handling in Ollama Client * Update python/samples/getting_started/multimodal_input/ollama_chat_multimodal.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Integrated Copilot Feedback * Implement first PR Feedback * Adjust Readme files for examples * Adjust argument passing via additional chat options * Implemented PR Feedback * Removing Ollama Package from Core and moving samples * Fix Link & Adding Samples to Main Sample Readme * Fixing Links in Readme * Moved Multimodal and Chat Example * Fixed Link in ChatClient to Ollama * Fix AgentFramework Links in Ollama Project * Fix observability breaking change --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com> * Skip failing IT (#2904) * .NET: Cosmos DB UT Fast Skip (For Non-Configured Local envs) (#2906) * Cosmos DB UT Fast Skip (Non-Configured Local envs) + Long running UT skip in pipeline when no CosmosDB changes happened * Force a CosmosDB source code change to trigger the pipeline * Address possible string boolean mismatch * Add debug * Enabling emulator always when running IT * .NET: Add TTLs to durable agent sessions (#2679) * .NET: Add TTLs to durable agent sessions * Remove unnecessary async * PR feedback: clarify UTC * PR feedback: limit minimum signal delay to <= 5 minutes * PR feedback: Fix TTL disablement * Linter: use auto-property * Fix build break from OpenAI SDK change * Updated CHANGELOG.md * PR feedback * Reduce default TTL to 14 days to work around DTS bug * Python: Update Mem0Provider to use v2 search API `filters` parameter (#2766) * short fix to move id parameters to filters object * added tests * small fix * mem0 dependency update * Updated package versions (#2913) * .NET: Switch to new "Run" method name. (#2843) * Switch to new "RunAgent" method name. * Try to disable false positive naming warning. * Add comment about disabled warnings. * Rename `RunAgent` to just `Run`. * Update CHANGELOG. * Python: Switch to new "run" method name. (#2890) * Switch to `run` method. * Add support for deprecated `run_agent`. * Fix entity method name. * Fix method name and improve tests. * Update comment. * Update Python CHANGELOG. * [BREAKING] Python: Add factory pattern to handoff orchestration builder (#2844) * WIP: Factory pattern to handoff * Add factory pattern to concurrent orchestration builder; Next: tests and sample verification * Add tests and improve comments * Fix mypy * Simplify handoff_simple.py * Simplify handoff_autonoumous.py and bug fix * Update readme * Address Copilot comments * Python: Flow custom kwargs to agents via Workflow SharedState (#2894) * Flow custom kwargs to agents via SharedState * Address Copilot feedback * Improve sample typing * Fix test * Fix Pydantic error when using Literal type for tool params (#2893) * Updated Ollama package version (#2920) * Python: Azure AI Agent with Bing Grounding Citations Sample (#2892) * bing grounding sample with citations * small fix * fix * .NET: Make DelegatingAIAgent abstract (#2797) * Initial plan * Make DelegatingAIAgent abstract Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Added additional arguments for Azure AI agent (#2922) * Python: Correction of MCP image type conversion in _mcp.py (#2901) * Correction of MCP image type conversion in _mcp.py * Added a new overload to the init function of the DataContent() type of the Agent Framework, edited the test case to correctly test the usage of the data and uri fields while using DataContent() * Fixed tests related to the changes of the DataContent type, added testing for both string and byte representations * Pass kwargs into subworkflows (#2923) * Python: Move ollama samples to samples getting started dir (#2921) * Move ollama samples to samples getting started dir * Address feedback * Python: fix: correct BadRequestError when using Pydantic model in response_fo… (#1843) * fix: correct BadRequestError when using Pydantic model in response_format * Fix lint --------- Co-authored-by: Evan Mattson <evan.mattson@microsoft.com> * .NET: [Breaking] Delete display name property (#2758) * delete the AIAgent.DisplayName property * use agent name as a first value for activity display name * Update dotnet/src/Microsoft.Agents.AI.Workflows/Specialized/HandoffAgentExecutor.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Python: cleanup and refactoring of chat clients (#2937) * refactoring and unifying naming schemes of internal methods of chat clients * set tool_choice to auto * fix for mypy * added note on naming and fix #2951 * fix responses * fixes in azure ai agents client * Python: Workflow add option to visualize internal executors (#2917) * Workflow add option to visualize internal executors * Address Copilot comments * Python: Fixes Run ID and Thread ID casing to align with AG-UI Typescript SDK (#2948) * added camelCase input to run id and thread id aligning with @ag-ui/core * fixed per copilot suggestions * Python: Add workflow cancellation sample (#2732) * Add workflow cancellation sample Add sample demonstrating how to cancel a running workflow using asyncio tasks. Shows both cancellation mid-execution and normal completion paths. Useful for implementing timeouts, graceful shutdown, or A2A executors. * update docstring * .NET: Update Anthropic package to version 12.0.0 (#2914) * Initial plan * Update Anthropic package to version 12.0.0 Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com> * Python: Add Azure Managed Redis Support with Credential Provider (#2887) * azure redis support * small fixes * azure managed redis sample * fixes * Bump CommunityToolkit.Aspire.OllamaSharp from 13.0.0-beta.440 to 13.0.0 (#2856) --- updated-dependencies: - dependency-name: CommunityToolkit.Aspire.OllamaSharp dependency-version: 13.0.0 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump AWSSDK.Extensions.Bedrock.MEAI from 4.0.4.11 to 4.0.5 (#2853) --- updated-dependencies: - dependency-name: AWSSDK.Extensions.Bedrock.MEAI dependency-version: 4.0.5 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> * Bump Azure.AI.AgentServer.AgentFramework from 1.0.0-beta.4 to 1.0.0-beta.5 (#2854) --- updated-dependencies: - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * Python: Fix WorkflowAgent event handling and kwargs forwarding (#2946) * Fix kwargs propagation through workflow.as_agent() * Fix WorkflowAgent to respect AgentExecutor output_response setting * .NET: Use GrpcEntityRunner instead of TaskEntityDispatcher (#2759) * Use GrpcEntityRunner instead of TaskEntityDispatcher * Pin to Durable worker 1.11.0 * Set the invocation result * Update all Durable packages * Update changelog, rename dispatcher to encondedEntityRequest * Python: Bump Py version to 1.0.0b251218 for a release. Update CHANGELOG (#2968) * Bump Py version to 1.0.0b251218 for a release. Update CHANGELOG * update lock * Fix formatting * Fix ChatKit typing * Python: Introducing Foundry Local Chat Clients (#2915) * redo foundry local chat client * fix mypy and spelling * better docstring, updated sample * fixed tests and added tests * small sample update * Updated package versions (#2978) * Python: Added GitHub MCP sample with PAT (#2967) * added github mcp sample with PAT * addressed copilot fixes * env fix * Python: Preserve reasoning blocks with OpenRouter (#2950) * Preserve reasoning blocks with OpenRouter * Put encrypted reasoning in TextReasoningContent * Remove unneccessary change * Fix docs * Support streaming * Fix handling None in TextReasoningContent.text * Python: Added response.created and response.in_progress event process to OpenAIBaseResponseClient (#2975) * added response.created and response.in_progress to include response.id * better doc string * added tests for the new streaming event types * Python: Introducing support for Bedrock-hosted models (Anthropic, Cohere, etc.) (#2610) * Pushing the bedrock related changes to the new branch after addressing the review comments * 2524 Addressed the second round review comments * 2524 Addressed few more minor comments on the PR * resolving the merge conflict * 2524 resolved the uv.lock conflicts * 2524 addressed more comments * 2524 removed the print statement to fix the checks failure * 2524 resolved the CI failure issues * 2524 fixing the CI breaks * 2524 Addressed the review comment * 2524 resolved conflict --------- Co-authored-by: Sunil Dutta <sunil.dutta@penske.com> Co-authored-by: budgetboardingai <apurva.sharma31@gmail.com> * .NET: [Durable Agents] Reliable streaming sample (#2942) * .NET: [Durable Agents] Reliable streaming sample * Add automated validation for new sample * Address Copilot PR feedback * Fix typo in README.md about agent definitions (#2634) * Fix typo in README.md about agent definitions * Update agent-samples/README.md Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Python: latency improvements (#3014) * latency improvements * fixed mypy, added coding standards and instructions * slight logic improvement * Python: Updated package versions (#3024) * Updated package versions * Updated changelog * Python: add powerfx safe mode (#3028) * add powerfx safe mode * improved docstring and aligned env_file loading * ensured test uses reset * .NET: [Breaking] Introduce RunCoreAsync/RunCoreStreamingAsync delegation pattern in AIAgent (#2749) * Initial plan * Refactor AIAgent: Make RunAsync and RunStreamingAsync non-abstract, add RunCoreAsync and RunCoreStreamingAsync Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Fix infinite recursion in test implementations Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Make RunAsync and RunStreamingAsync non-virtual as requested Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Fix DelegatingAIAgent subclasses to use RunCoreAsync/RunCoreStreamingAsync Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Fix XML documentation references in AnonymousDelegatingAIAgent Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Restore <see cref> tags with proper qualified signatures in AnonymousDelegatingAIAgent Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Rollback unnecessary XML documentation changes in AnonymousDelegatingAIAgent Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Remove pragma and update crefs to RunCoreAsync/RunCoreStreamingAsync Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Fix EntityAgentWrapper to call base.RunCoreAsync/RunCoreStreamingAsync Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * fix compilation issues * fix compilatio issue * fix tests * fix unit tests * fix unit test --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> Co-authored-by: SergeyMenshykh <sergemenshikh@gmail.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * Remove from feature branch * Remove ollama changes --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: Tao Chen <taochen@microsoft.com> Co-authored-by: Kurt <65111699+q33566@users.noreply.github.com> Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> Co-authored-by: Korolev Dmitry <deagle.gross@gmail.com> Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com> Co-authored-by: Dmytro Struk <13853051+dmytrostruk@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> Co-authored-by: Jose Luis Latorre Millas <joslat@gmail.com> Co-authored-by: Jacob Alber <jaalber@microsoft.com> Co-authored-by: Richard Ortega <richardjortega@gmail.com> Co-authored-by: 刘邦学AI <lbbniu@gmail.com> Co-authored-by: Stephen Toub <stoub@microsoft.com> Co-authored-by: Nico Möller <nkm-moeller@mail.de> Co-authored-by: Chris Gillum <cgillum@microsoft.com> Co-authored-by: Giles Odigwe <79032838+giles17@users.noreply.github.com> Co-authored-by: Phillip Hoff <phillip.hoff@gmail.com> Co-authored-by: Ege Ozan Özyedek <36128615+egeozanozyedek@users.noreply.github.com> Co-authored-by: samueljohnsiby <66901393+samueljohnsiby@users.noreply.github.com> Co-authored-by: Evan Mattson <evan.mattson@microsoft.com> Co-authored-by: Hao Luo <338265+howlowck@users.noreply.github.com> Co-authored-by: Victor Dibia <chuvidi2003@gmail.com> Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com> Co-authored-by: Jacob Viau <javia@microsoft.com> Co-authored-by: SuperKenVery <39673849+SuperKenVery@users.noreply.github.com> Co-authored-by: Sunil Dutta <dutta.2003@gmail.com> Co-authored-by: Sunil Dutta <sunil.dutta@penske.com> Co-authored-by: budgetboardingai <apurva.sharma31@gmail.com> Co-authored-by: Syrine Chelly <62653967+SyChell@users.noreply.github.com> Co-authored-by: SergeyMenshykh <sergemenshikh@gmail.com> * Python: Complete durableagent package (#3058) * Add worker and clients * Clean code and refactor common code * Implement sample * Add sample * Update readmes * Fix tests * Fix tests * Update requirements * Fix typo * Address comments * use response.text * .NET: Python: Merge main into feature-durabletask-python branch (#3160) * Python: Add factory pattern to concurrent orchestration builder (#2738) * Add factory pattern to concurrent orchestration builder * Update readme * Address AI comments * Fix unit tests * Fix import * Prevent multiple calls to set participants or factories * Add comments * Mitigate warnings * Fix mypy * Address comments * Address Copilot comments * Fix tests * Python: fix: GroupChat ManagerSelectionResponse JSON Schema for OpenAI Structured Outpu… (#2750) * fix: ManagerSelectionResponse JSON Schema for OpenAI Structured Output Strict Mode * refactor: install pre-commit then commit again * Capture file IDs from code interpreter in streaming responses (#2741) * .NET: [BREAKING] Prevent nulls in AIAgent property (#2719) * prevent nulls in AIAgent property * address feedback * code ql sm04598 (#2723) Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> * .NET: Add Conversation State Sample (Step05) (#2697) * Initial plan * Add Agent_OpenAI_Step05_Conversation sample for conversation state management Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> * Update Program.cs comment to accurately describe the sample Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> * Update the code to use the ConversationClient more in line with the samples in OpenAI * Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Changing sample to use ChatClientAgent and conversationId in GetNewThread --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Bump AWSSDK.Extensions.Bedrock.MEAI from 4.0.4.7 to 4.0.4.11 (#2777) --- updated-dependencies: - dependency-name: AWSSDK.Extensions.Bedrock.MEAI dependency-version: 4.0.4.11 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump Azure.Identity from 1.17.0 to 1.17.1 (#2780) --- updated-dependencies: - dependency-name: Azure.Identity dependency-version: 1.17.1 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.Identity dependency-version: 1.17.1 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.Identity dependency-version: 1.17.1 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.Identity dependency-version: 1.17.1 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump Azure.AI.AgentServer.AgentFramework from 1.0.0-beta.4 to 1.0.0-beta.5 (#2778) --- updated-dependencies: - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Python: added more complete parsing for mcp tool arguments (#2756) * added more complete parsing for mcp tool arguments * fixed mypy * added nonlocal model counter, and some fixes * fixes in naming logic * extracted json parsing function, added parametrized test and checked coverage * Python: Updated package versions (#2784) * Updated package versions * Small fix * Bump actions/checkout from 5 to 6 (#2404) Bumps [actions/checkout](https://github.com/actions/checkout) from 5 to 6. - [Release notes](https://github.com/actions/checkout/releases) - [Changelog](https://github.com/actions/checkout/blob/main/CHANGELOG.md) - [Commits](https://github.com/actions/checkout/compare/v5...v6) --- updated-dependencies: - dependency-name: actions/checkout 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> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * .NET: adds support for labels in edges, fixes rendering of labels in dot a… (#1507) * adds support for labels in edges, fixes rendering of labels in dot and mermaid, adds rendering of labels in edges * Update dotnet/src/Microsoft.Agents.AI.Workflows/Visualization/WorkflowVisualizer.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * escaping edge labels, adding tests for labels containing strange characters that would break the diagram and enabling the previous signature so the API has backwards compatibility. * Unify label in EdgeData * Edge API adjustments, removed useless "sanitizer" * fixed test --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Jacob Alber <jaalber@microsoft.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * Python: Added custom args and thread object to ai_function kwargs (#2769) * Added an example of using kwargs in ai_function * Added thread object to ai_function kwargs * Updated docs * Small fix * Added thread parameter filtering * Fix WorkflowAgent to include thread convo history. Enable checkpointing. (#2774) * Update OpenAIResponses.yaml to match AgentSchema (#2598) 1. Update `connection` child types -- `kind: ApiKey` to `kind: key` otherwise schema will fail: https://microsoft.github.io/AgentSchema/reference/apikeyconnection/ 2. Update `outputSchema`'s `PropertySchema` to be `kind` instead of `type` otherwise schema will fail: https://microsoft.github.io/AgentSchema/reference/propertyschema/ * Python: Remove warnings from workflow builder on not using factories (#2808) * Revert concurrent * Fix comments * Python: Filter framework kwargs from MCP tool invocations (#2870) * Filter framework kwargs from MCP tool invocations * Fixes * Python: Fix WorkflowAgent to emit yield_output as agent response (#2866) * Fix WorkflowAgent to emit yield_output as agent response * use raw_representation * Raw representation handling * Python: Use agent description in HandoffBuilder auto-generated tools (#2713) (#2714) ## Summary Enhanced `HandoffBuilder._apply_auto_tools` to use the target agent's description when creating handoff tools, providing more informative tool descriptions for LLMs. ## Changes - Modified `_apply_auto_tools` to extract `description` from `AgentExecutor._agent` when available - Updated iteration to use `.items()` for more efficient dict traversal - Handoff tools now use agent descriptions instead of generic placeholders ## Example Before: "Handoff to the refund_agent agent." After: "You handle refund requests. Ask for order details and process refunds." ## Testing - All handoff tests pass (20/20) - No breaking changes to existing API Fixes #2713 Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com> * Python: [BREAKING] Observability updates (#2782) * fixes Python: Add env_file_path parameter to setup_observability() similar to AzureOpenAIChatClient Fixes #2186 * WIP on updates using configure_azure_monitor * improved setup and clarity * fixed root .env.example * revert changes * updated files * updated sample * updated zero code * test fixes and fixed links * fix devui * removed planning docs * added enable method and updated readme and samples * clarified docstring * add return annotation * updated naming * update capatilized version * updated readme and some fixes * updated decorator name inline with the rest * feedback from comments addressed * Python: Fix middleware terminate flag to exit function calling loop immediately (#2868) * Fix middleware terminate flag to exit function calling loop immediately * Eliminating duck typing * Improve function exec result handling * Fix race condition * Fix mypy issues * Python: Fix context duplication in handoff workflows when restoring from checkpoint (#2867) * Fix context duplication in handoff workflows when restoring from checkpoint * Address Copilot PR review * .NET: Update to latest Azure.AI.*, OpenAI, and M.E.AI* (#2850) * Update to latest Azure.AI.*, OpenAI, and M.E.AI* Absorb breaking changes in Responses surface area * Update dotnet/samples/AgentWebChat/AgentWebChat.AgentHost/Utilities/ChatClientExtensions.cs * Update dotnet/samples/AgentWebChat/AgentWebChat.AgentHost/Utilities/ChatClientExtensions.cs * Update dotnet/samples/AgentWebChat/AgentWebChat.AgentHost/Utilities/ChatClientExtensions.cs * Update dotnet/samples/GettingStarted/AgentWithOpenAI/Agent_OpenAI_Step04_CreateFromOpenAIResponseClient/Program.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Using patch to remove the model is necessary, updated the response client to actually use the the ForAgent --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com> * Bump actions/download-artifact from 6 to 7 (#2862) Bumps [actions/download-artifact](https://github.com/actions/download-artifact) from 6 to 7. - [Release notes](https://github.com/actions/download-artifact/releases) - [Commits](https://github.com/actions/download-artifact/compare/v6...v7) --- updated-dependencies: - dependency-name: actions/download-artifact dependency-version: '7' 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> * Bump actions/cache from 4 to 5 (#2861) Bumps [actions/cache](https://github.com/actions/cache) from 4 to 5. - [Release notes](https://github.com/actions/cache/releases) - [Changelog](https://github.com/actions/cache/blob/main/RELEASES.md) - [Commits](https://github.com/actions/cache/compare/v4...v5) --- updated-dependencies: - dependency-name: actions/cache dependency-version: '5' 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> * Bump actions/upload-artifact from 5 to 6 (#2860) Bumps [actions/upload-artifact](https://github.com/actions/upload-artifact) from 5 to 6. - [Release notes](https://github.com/actions/upload-artifact/releases) - [Commits](https://github.com/actions/upload-artifact/compare/v5...v6) --- updated-dependencies: - dependency-name: actions/upload-artifact 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 : Ollama Connector for Agent Framework (#1104) * Initial Commit for Olama Connector * Added Olama Sample * Add Sample & Fixed Open Telemetry * Fixed Spelling from Olama to Ollama * remove"opentelemetry-semantic-conventions-ai ~=0.4.13" since its handled in a different pr * Added Tool Calling * Finalizing test cases * Adjust samples to be more reliable * Update python/packages/ollama/agent_framework_ollama/_chat_client.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update python/packages/ollama/pyproject.toml Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update python/packages/ollama/tests/test_ollama_chat_client.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update python/packages/ollama/agent_framework_ollama/_chat_client.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Improved Docstrings & Sample * Update python/packages/ollama/agent_framework_ollama/_chat_client.py Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com> * Integrate PR Feedback - Divided Streaming and Non-Streaming into independent Methods - Catch Ollama Validation Error - Add OTEL Provider Name - Checked Ollama Messages - Add Usage Statistics * Revert setting, so it can be none * Validate Message formatting between AF and Ollama * Catch Ollama Error and raise a ServiceResponse Error * Fix mypy error * remove .vscode comma * Add Reasoning support & adjust to new structure * Add Ollama Multimodality and Reasoning * Add test cases for reasoning * Add Tests for Error Handling in Ollama Client * Update python/samples/getting_started/multimodal_input/ollama_chat_multimodal.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Integrated Copilot Feedback * Implement first PR Feedback * Adjust Readme files for examples * Adjust argument passing via additional chat options * Implemented PR Feedback * Removing Ollama Package from Core and moving samples * Fix Link & Adding Samples to Main Sample Readme * Fixing Links in Readme * Moved Multimodal and Chat Example * Fixed Link in ChatClient to Ollama * Fix AgentFramework Links in Ollama Project * Fix observability breaking change --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com> * Skip failing IT (#2904) * .NET: Cosmos DB UT Fast Skip (For Non-Configured Local envs) (#2906) * Cosmos DB UT Fast Skip (Non-Configured Local envs) + Long running UT skip in pipeline when no CosmosDB changes happened * Force a CosmosDB source code change to trigger the pipeline * Address possible string boolean mismatch * Add debug * Enabling emulator always when running IT * .NET: Add TTLs to durable agent sessions (#2679) * .NET: Add TTLs to durable agent sessions * Remove unnecessary async * PR feedback: clarify UTC * PR feedback: limit minimum signal delay to <= 5 minutes * PR feedback: Fix TTL disablement * Linter: use auto-property * Fix build break from OpenAI SDK change * Updated CHANGELOG.md * PR feedback * Reduce default TTL to 14 days to work around DTS bug * Python: Update Mem0Provider to use v2 search API `filters` parameter (#2766) * short fix to move id parameters to filters object * added tests * small fix * mem0 dependency update * Updated package versions (#2913) * .NET: Switch to new "Run" method name. (#2843) * Switch to new "RunAgent" method name. * Try to disable false positive naming warning. * Add comment about disabled warnings. * Rename `RunAgent` to just `Run`. * Update CHANGELOG. * Python: Switch to new "run" method name. (#2890) * Switch to `run` method. * Add support for deprecated `run_agent`. * Fix entity method name. * Fix method name and improve tests. * Update comment. * Update Python CHANGELOG. * [BREAKING] Python: Add factory pattern to handoff orchestration builder (#2844) * WIP: Factory pattern to handoff * Add factory pattern to concurrent orchestration builder; Next: tests and sample verification * Add tests and improve comments * Fix mypy * Simplify handoff_simple.py * Simplify handoff_autonoumous.py and bug fix * Update readme * Address Copilot comments * Python: Flow custom kwargs to agents via Workflow SharedState (#2894) * Flow custom kwargs to agents via SharedState * Address Copilot feedback * Improve sample typing * Fix test * Fix Pydantic error when using Literal type for tool params (#2893) * Updated Ollama package version (#2920) * Python: Azure AI Agent with Bing Grounding Citations Sample (#2892) * bing grounding sample with citations * small fix * fix * .NET: Make DelegatingAIAgent abstract (#2797) * Initial plan * Make DelegatingAIAgent abstract Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Added additional arguments for Azure AI agent (#2922) * Python: Correction of MCP image type conversion in _mcp.py (#2901) * Correction of MCP image type conversion in _mcp.py * Added a new overload to the init function of the DataContent() type of the Agent Framework, edited the test case to correctly test the usage of the data and uri fields while using DataContent() * Fixed tests related to the changes of the DataContent type, added testing for both string and byte representations * Pass kwargs into subworkflows (#2923) * Python: Move ollama samples to samples getting started dir (#2921) * Move ollama samples to samples getting started dir * Address feedback * Python: fix: correct BadRequestError when using Pydantic model in response_fo… (#1843) * fix: correct BadRequestError when using Pydantic model in response_format * Fix lint --------- Co-authored-by: Evan Mattson <evan.mattson@microsoft.com> * .NET: [Breaking] Delete display name property (#2758) * delete the AIAgent.DisplayName property * use agent name as a first value for activity display name * Update dotnet/src/Microsoft.Agents.AI.Workflows/Specialized/HandoffAgentExecutor.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Python: cleanup and refactoring of chat clients (#2937) * refactoring and unifying naming schemes of internal methods of chat clients * set tool_choice to auto * fix for mypy * added note on naming and fix #2951 * fix responses * fixes in azure ai agents client * Python: Workflow add option to visualize internal executors (#2917) * Workflow add option to visualize internal executors * Address Copilot comments * Python: Fixes Run ID and Thread ID casing to align with AG-UI Typescript SDK (#2948) * added camelCase input to run id and thread id aligning with @ag-ui/core * fixed per copilot suggestions * Python: Add workflow cancellation sample (#2732) * Add workflow cancellation sample Add sample demonstrating how to cancel a running workflow using asyncio tasks. Shows both cancellation mid-execution and normal completion paths. Useful for implementing timeouts, graceful shutdown, or A2A executors. * update docstring * .NET: Update Anthropic package to version 12.0.0 (#2914) * Initial plan * Update Anthropic package to version 12.0.0 Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com> * Python: Add Azure Managed Redis Support with Credential Provider (#2887) * azure redis support * small fixes * azure managed redis sample * fixes * Bump CommunityToolkit.Aspire.OllamaSharp from 13.0.0-beta.440 to 13.0.0 (#2856) --- updated-dependencies: - dependency-name: CommunityToolkit.Aspire.OllamaSharp dependency-version: 13.0.0 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump AWSSDK.Extensions.Bedrock.MEAI from 4.0.4.11 to 4.0.5 (#2853) --- updated-dependencies: - dependency-name: AWSSDK.Extensions.Bedrock.MEAI dependency-version: 4.0.5 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> * Bump Azure.AI.AgentServer.AgentFramework from 1.0.0-beta.4 to 1.0.0-beta.5 (#2854) --- updated-dependencies: - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * Python: Fix WorkflowAgent event handling and kwargs forwarding (#2946) * Fix kwargs propagation through workflow.as_agent() * Fix WorkflowAgent to respect AgentExecutor output_response setting * .NET: Use GrpcEntityRunner instead of TaskEntityDispatcher (#2759) * Use GrpcEntityRunner instead of TaskEntityDispatcher * Pin to Durable worker 1.11.0 * Set the invocation result * Update all Durable packages * Update changelog, rename dispatcher to encondedEntityRequest * Python: Bump Py version to 1.0.0b251218 for a release. Update CHANGELOG (#2968) * Bump Py version to 1.0.0b251218 for a release. Update CHANGELOG * update lock * Fix formatting * Fix ChatKit typing * Python: Introducing Foundry Local Chat Clients (#2915) * redo foundry local chat client * fix mypy and spelling * better docstring, updated sample * fixed tests and added tests * small sample update * Updated package versions (#2978) * Python: Added GitHub MCP sample with PAT (#2967) * added github mcp sample with PAT * addressed copilot fixes * env fix * Python: Preserve reasoning blocks with OpenRouter (#2950) * Preserve reasoning blocks with OpenRouter * Put encrypted reasoning in TextReasoningContent * Remove unneccessary change * Fix docs * Support streaming * Fix handling None in TextReasoningContent.text * Python: Added response.created and response.in_progress event process to OpenAIBaseResponseClient (#2975) * added response.created and response.in_progress to include response.id * better doc string * added tests for the new streaming event types * Python: Introducing support for Bedrock-hosted models (Anthropic, Cohere, etc.) (#2610) * Pushing the bedrock related changes to the new branch after addressing the review comments * 2524 Addressed the second round review comments * 2524 Addressed few more minor comments on the PR * resolving the merge conflict * 2524 resolved the uv.lock conflicts * 2524 addressed more comments * 2524 removed the print statement to fix the checks failure * 2524 resolved the CI failure issues * 2524 fixing the CI breaks * 2524 Addressed the review comment * 2524 resolved conflict --------- Co-authored-by: Sunil Dutta <sunil.dutta@penske.com> Co-authored-by: budgetboardingai <apurva.sharma31@gmail.com> * .NET: [Durable Agents] Reliable streaming sample (#2942) * .NET: [Durable Agents] Reliable streaming sample * Add automated validation for new sample * Address Copilot PR feedback * Fix typo in README.md about agent definitions (#2634) * Fix typo in README.md about agent definitions * Update agent-samples/README.md Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Python: latency improvements (#3014) * latency improvements * fixed mypy, added coding standards and instructions * slight logic improvement * Python: Updated package versions (#3024) * Updated package versions * Updated changelog * Python: add powerfx safe mode (#3028) * add powerfx safe mode * improved docstring and aligned env_file loading * ensured test uses reset * .NET: [Breaking] Introduce RunCoreAsync/RunCoreStreamingAsync delegation pattern in AIAgent (#2749) * Initial plan * Refactor AIAgent: Make RunAsync and RunStreamingAsync non-abstract, add RunCoreAsync and RunCoreStreamingAsync Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Fix infinite recursion in test implementations Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Make RunAsync and RunStreamingAsync non-virtual as requested Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Fix DelegatingAIAgent subclasses to use RunCoreAsync/RunCoreStreamingAsync Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Fix XML documentation references in AnonymousDelegatingAIAgent Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Restore <see cref> tags with proper qualified signatures in AnonymousDelegatingAIAgent Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Rollback unnecessary XML documentation changes in AnonymousDelegatingAIAgent Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Remove pragma and update crefs to RunCoreAsync/RunCoreStreamingAsync Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Fix EntityAgentWrapper to call base.RunCoreAsync/RunCoreStreamingAsync Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * fix compilation issues * fix compilatio issue * fix tests * fix unit tests * fix unit test --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> Co-authored-by: SergeyMenshykh <sergemenshikh@gmail.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * add issue template and additional labeling (#3006) * fix and extra int test (#3037) * .NET: [BREAKING] Refactor ChatMessageStore methods to be similar to AIContextProvider and add filtering support (#2604) * Refactor ChatMessageStore methods to be similar to AIContextProvider * Fix file encoding * Ensure that AIContextProvider messages area also persisted. * Update formatting and seal context classes * Improve formatting * Remove optional messages from constructor and add unit test * Add ChatMessageStore filtering via a decorator * Update sample and cosmos message store to store AIContextProvider messages in right order. Fix unit tests. * Update Workflowmessage store to use aicontext provider messages. * Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Apply suggestions from code review Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Improve xml docs messaging * Address code review comments. * Also notify message store on failure --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * [BREAKING] Remove unused AgentThreadMetadata (#3067) * Remove unused AgentThreadMetadata * Update DurableTask Changelog * Python: Fix AzureAIClient failure when conversation history contains assistant messages (#3076) * Fix AzureAIClient failure when conversation history contains assistant messages * Address PR review feedback: improve docstring and test assertions * Remove redundant cast * Fix: Update OTLP exporter protocol conditions (#3070) * Python: Fix ExecutorInvokedEvent and ExecutorCompletedEvent observability data (#3090) * Fix ExecutorInvokedEvent.data mutation bug * Fix bug related to not yielding output type * .NET: Seal ChatClientAgentThread (#2842) * Initial plan * Seal ChatClientAgentThread class Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Fix broken strands urls. (#3102) * Fix broken strands urls. * Fix typos * .NET: Fix message ordering inconsistency when using AIContextProvider (#2659) * Initial plan * Fix message ordering inconsistency when using AIContextProvider Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> * Revert to original message ordering: Input, AIContextProvider, Response Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> * Reorder messages to ChatClient to match MessageStore order: Existing, Input, AIContextProvider Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> * Remove redundant test methods as existing tests already verify the behavior Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * fix: tool_choice parameter not being honored when passed to agent.run() (#3095) * sharepoint sample fix (#3108) * Bump versions to 1.0.0b260106 for a release. Update CHANGELOG.md (#3109) * Bump Bedrock version to latest (#3110) * Python: Fix MCP tool result serialization for list[TextContent] (#2523) * Fix MCP tool result serialization for list[TextContent] When MCP tools return results containing list[TextContent], they were incorrectly serialized to object repr strings like: '[<agent_framework._types.TextContent object at 0x...>]' This fix properly extracts text content from list items by: 1. Checking if items have a 'text' attribute (TextContent) 2. Using model_dump() for items that support it 3. Falling back to str() for other types 4. Joining single items as plain text, multiple items as JSON array Fixes #2509 * Address PR review feedback for MCP tool result serialization - Extract serialize_content_result() to shared _utils.py - Fix logic: use texts[0] instead of join for single item - Add type annotation: texts: list[str] = [] - Return empty string for empty list instead of '[]' - Move import json to file top level - Add comprehensive unit tests for serialization * Address PR review feedback: fix type checking and double serialization - Add isinstance(item.text, str) check to ensure text attribute is a string - Fix double-serialization issue by keeping model_dump results as dicts until final json.dumps (removes escaped JSON strings in arrays) - Improve docstring with detailed return value documentation - Add test for non-string text attribute handling - Add tests for list type tool results in _events.py path * Simplify PR: minimal changes to fix MCP tool result serialization Addresses reviewer feedback about excessive refactoring: - Reset _events.py to original structure - Only add import and use serialize_content_result in one location - All review comments addressed in serialize_content_result(): - Added isinstance(item.text, str) check - Use model_dump(mode="json") to avoid double-serialization - Improved docstring with explicit return value documentation - Empty list returns "" instead of "[]" * Refactor: Move MCP TextContent serialization to core prepare_function_call_results Per reviewer feedback, moved the TextContent serialization logic from ag-ui's serialize_content_result to the core package's prepare_function_call_results function. Changes: - Added handling for objects with 'text' attribute (like MCP TextContent) in _prepare_function_call_results_as_dumpable - Removed serialize_content_result from ag-ui/_utils.py - Updated _events.py and _message_adapters.py to use prepare_function_call_results from core package - Updated tests to match the core function's behavior * Fix failing tests for prepare_function_call_results behavior - test_tool_result_with_none: Update expected value to 'null' (JSON serialization of None) - test_tool_result_with_model_dump_objects: Use Pydantic BaseModel instead of plain class * Fix B903 linter error: Convert MockTextContent to dataclass The ruff linter was reporting B903 (class could be dataclass or namedtuple) for the MockTextContent test helper classes. This commit converts them to dataclasses to satisfy the linter check. * Python: Improve DevUI, add Context Inspector view as new tab under traces (#2742) * Improve DevUI, add Context Inspector view as new tab under traces * fix mypy errors * fix: Handle stale MCP connections in DevUI executor MCP tools can become stale when HTTP streaming responses end - the underlying stdio streams close but `is_connected` remains True. This causes subsequent requests to fail with `ClosedResourceError`. Add `_ensure_mcp_connections()` to detect and reconnect stale MCP tools before agent execution. This is a workaround for an upstream Agent Framework issue where connection state isn't properly tracked. Fixes MCP tools failing on second HTTP request in DevUI. fixes #1476 #1515 #2865 * fix #1572 report import dependency errors more clearly * Ensure there is streaming toggle where users can select streaming vs non streaming mode in devui . Fixes .NET: [Python] DevUI tool call rendering in non-streaming mode? * remove unused dead code * improve ux - workflows with agents show a chat component in execution timelien, also ensure magentic final output shows correctly * update ui build * update devui to use instrumentation instead of tracing, other instrumentation and type/instance check fixes * .NET: Seal factory contexts and add non JSO deserialize overloads (#3066) * Seal factory contexts and add non JSO deserialize overloads * Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Enable blank issues in issue template configuration Need to re-enable creating blank issues * updated templates (#3106) * updated templates * enabled blank and fixed triage * made language optional and moved to the bottom for features * Python: Streaming sample for azurefunctions (#3057) * Streaming sample for azurefunctions * Fixed links and sample name * Addressed feedback * Addressed feedback * Fixed integration tests * Updated test * Python: fix(azure-ai): Fix response_format handling for structured outputs (#3114) * fix(azure-ai): read response_format from chat_options instead of run_options * refactor: use explicit None checks for response_format * Fix mypy error * Mypy fix * Python: Bump python version to 1.0.0b260107 for a release (#3128) * Bump python version to 1.0.0b260107 for a release * Update changelog * Make A2AAgent public, so that it's concrete implementation methods can be used. (#3119) * .NET: Map additional props <-> A2A metadata (#3137) * map additional props from agent run options to a2a request metadata * small touches * add unit tests for new extension methods * Sort using * add unit test * add additiona unit tests * special case json element to avoid unnecessary serialization * Python: Fix Anthropic streaming response bugs (#3141) * test commit identity * fix(anthropic): fix raw_representation and finish_reason in streaming * lint fix * Bump AWSSDK.Extensions.Bedrock.MEAI from 4.0.5 to 4.0.5.1 (#2994) --- updated-dependencies: - dependency-name: AWSSDK.Extensions.Bedrock.MEAI dependency-version: 4.0.5.1 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * Bump Anthropic from 12.0.0 to 12.0.1 (#2993) --- updated-dependencies: - dependency-name: Anthropic dependency-version: 12.0.1 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * .NET: [Breaking] Prevent loss of input messages & streamed updates when resuming streaming (#2748) * save input messages and stream updates to the continuation token to be able to use them in the last successful stream resumption call. * Update dotnet/src/Microsoft.Agents.AI/ChatClient/ChatClientAgentContinuationToken.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update dotnet/src/Microsoft.Agents.AI/ChatClient/ChatClientAgentContinuationToken.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update dotnet/tests/Microsoft.Agents.AI.UnitTests/ChatClient/ChatClientAgent_BackgroundResponsesTests.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update dotnet/src/Microsoft.Agents.AI/ChatClient/ChatClientAgentContinuationToken.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update dotnet/src/Microsoft.Agents.AI/ChatClient/ChatClientAgentContinuationToken.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * fix typo * init continuation token from chat response * remove unnecessary types for source generation * remove check for continuation token passed at initial run * remove check for continuation token pass at initial run * centralize continuation token parsing * update xml comments * use readonly collection instead of enumerable --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * .NET: fix: Expose WorkflowErrorEvent as ErrorContent (#2762) * fix: Expose WorkflowErrorEvent as ErrorContent When hosted using .AsAgent(), Workflows were not exposing inner errors coming as Exceptions (through the WorkflowErrorEvent) The fix is to convert their message to an ErrorContent on the way out, rather than rely on the default "empty update" to collect the raw event. * feat: Add a way to show/suppress exception information * Bump Microsoft.Agents.AI.Workflows from 1.0.0-preview.251125.1 to 1.0.0-preview.251219.1 (#2997) --- updated-dependencies: - dependency-name: Microsoft.Agents.AI.Workflows dependency-version: 1.0.0-preview.251219.1 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * .NET: Add Run overloads to expose ChatClientAgentRunOptions in IntelliSense (#3115) * Initial plan * Add ChatClientAgentExtensions for improved discoverability of ChatClientAgentRunOptions Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> * Address code review feedback - use collection expression syntax Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> * Apply suggestion from @westey-m * Fix issues with Copilot implementation * Add additional tests for structured output overloads. --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> * Python: Add tool call/result content types and update connectors and samples (#2971) * Add new AI content types and image tool support Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Add Python content types for tool calls/results and image generation tool support Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Address review feedback for tool content and samples Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Tighten image generation typing and sample tools list Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Align image generation output typing Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Handle MCP naming, image options mapping, and connector tool content Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Allow MCP call in function approval request Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Remove raw image_generation tool remapping Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Restore Anthropic tool_use to function calls unless code execution Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Fix lint issues for hosted file docstring and MCP parsing Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Import ChatResponse types in Anthropic client Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Fix Anthropics citation type imports and MCP typing for handoff/tools Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Skip lightning tests without agentlightning and fix function call import Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * fix lint on lab package * rebuilt anthropic parsing * redid anthropic parsing * typo * updated parsing and added missing docstrings * fix tests * mypy fixes * second mypy fix * add new class to other samples --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> Co-authored-by: eavanvalkenburg <github@vanvalkenburg.eu> * Bump Google.GenAI from 0.6.0 to 0.9.0 (#2995) --- updated-dependencies: - dependency-name: Google.GenAI dependency-version: 0.9.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * Bump js-yaml from 4.1.0 to 4.1.1 in /python/packages/devui/frontend (#3123) Bumps [js-yaml](https://github.com/nodeca/js-yaml) from 4.1.0 to 4.1.1. - [Changelog](https://github.com/nodeca/js-yaml/blob/master/CHANGELOG.md) - [Commits](https://github.com/nodeca/js-yaml/compare/4.1.0...4.1.1) --- updated-dependencies: - dependency-name: js-yaml dependency-version: 4.1.1 dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Updated package versions (#3144) * .NET: Bump Microsoft.Agents.AI.OpenAI and Microsoft.Extensions.AI.OpenAI (#2996) * Bump Microsoft.Agents.AI.OpenAI and Microsoft.Extensions.AI.OpenAI Bumps Microsoft.Agents.AI.OpenAI from 1.0.0-preview.251125.1 to 1.0.0-preview.251219.1 Bumps Microsoft.Extensions.AI.OpenAI from 10.1.0-preview.1.25608.1 to 10.1.1-preview.1.25612.2 --- updated-dependencies: - dependency-name: Microsoft.Agents.AI.OpenAI dependency-version: 1.0.0-preview.251219.1 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Microsoft.Extensions.AI.OpenAI dependency-version: 10.1.1-preview.1.25612.2 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Microsoft.Agents.AI.OpenAI dependency-version: 1.0.0-preview.251219.1 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Microsoft.Extensions.AI.OpenAI dependency-version: 10.1.1-preview.1.25612.2 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * Fixed samples --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> Co-authored-by: Dmytro Struk <13853051+dmytrostruk@users.noreply.github.com> * Python: fix(ag-ui): Execute tools with approval_mode, fix shared state, code cleanup (#3079) * fix(ag-ui): execute tools after approval in human-in-the-loop flow * Fix shared state bug * Bug fix finalized * Refactoring to clean up code * Code cleanup * More fixes * More code cleanup * Add version detection in __init__.py to ruff ignore list * Track agent name with updates for workflow agent (#3146) * Python: Fix AzureAIClient tool call bug for AG-UI use (#3148) * Fiz AzureAIClient tool call bug * Address copilot feedback * Revert to match main * revert file to main --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: Tao Chen <taochen@microsoft.com> Co-authored-by: Kurt <65111699+q33566@users.noreply.github.com> Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> Co-authored-by: Korolev Dmitry <deagle.gross@gmail.com> Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com> Co-authored-by: Dmytro Struk <13853051+dmytrostruk@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> Co-authored-by: Jose Luis Latorre Millas <joslat@gmail.com> Co-authored-by: Jacob Alber <jaalber@microsoft.com> Co-authored-by: Richard Ortega <richardjortega@gmail.com> Co-authored-by: 刘邦学AI <lbbniu@gmail.com> Co-authored-by: Stephen Toub <stoub@microsoft.com> Co-authored-by: Nico Möller <nkm-moeller@mail.de> Co-authored-by: Chris Gillum <cgillum@microsoft.com> Co-authored-by: Giles Odigwe <79032838+giles17@users.noreply.github.com> Co-authored-by: Phillip Hoff <phillip.hoff@gmail.com> Co-authored-by: Ege Ozan Özyedek <36128615+egeozanozyedek@users.noreply.github.com> Co-authored-by: samueljohnsiby <66901393+samueljohnsiby@users.noreply.github.com> Co-authored-by: Evan Mattson <evan.mattson@microsoft.com> Co-authored-by: Hao Luo <338265+howlowck@users.noreply.github.com> Co-authored-by: Victor Dibia <chuvidi2003@gmail.com> Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com> Co-authored-by: Jacob Viau <javia@microsoft.com> Co-authored-by: SuperKenVery <39673849+SuperKenVery@users.noreply.github.com> Co-authored-by: Sunil Dutta <dutta.2003@gmail.com> Co-authored-by: Sunil Dutta <sunil.dutta@penske.com> Co-authored-by: budgetboardingai <apurva.sharma31@gmail.com> Co-authored-by: Syrine Chelly <62653967+SyChell@users.noreply.github.com> Co-authored-by: SergeyMenshykh <sergemenshikh@gmail.com> Co-authored-by: westey <164392973+westey-m@users.noreply.github.com> Co-authored-by: takanori-terai <123897708+takanori-terai@users.noreply.github.com> Co-authored-by: claude89757 <138977524+claude89757@users.noreply.github.com> Co-authored-by: Gavin Aguiar <80794152+gavin-aguiar@users.noreply.github.com> Co-authored-by: Sukeesh <vsukeeshbabu@gmail.com> Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> Co-authored-by: eavanvalkenburg <github@vanvalkenburg.eu> * Python: Add Durabletask samples and minor fixes (#3157) * Add samples and minor fixes * Add redis sample and wait-for-completion * Add wait-for-completion support * ADd missing docs * Python: Merge `main` into `feature-durabletask-python` branch (#3261) * Python: Add factory pattern to concurrent orchestration builder (#2738) * Add factory pattern to concurrent orchestration builder * Update readme * Address AI comments * Fix unit tests * Fix import * Prevent multiple calls to set participants or factories * Add comments * Mitigate warnings * Fix mypy * Address comments * Address Copilot comments * Fix tests * Python: fix: GroupChat ManagerSelectionResponse JSON Schema for OpenAI Structured Outpu… (#2750) * fix: ManagerSelectionResponse JSON Schema for OpenAI Structured Output Strict Mode * refactor: install pre-commit then commit again * Capture file IDs from code interpreter in streaming responses (#2741) * .NET: [BREAKING] Prevent nulls in AIAgent property (#2719) * prevent nulls in AIAgent property * address feedback * code ql sm04598 (#2723) Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> * .NET: Add Conversation State Sample (Step05) (#2697) * Initial plan * Add Agent_OpenAI_Step05_Conversation sample for conversation state management Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> * Update Program.cs comment to accurately describe the sample Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> * Update the code to use the ConversationClient more in line with the samples in OpenAI * Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Changing sample to use ChatClientAgent and conversationId in GetNewThread --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Bump AWSSDK.Extensions.Bedrock.MEAI from 4.0.4.7 to 4.0.4.11 (#2777) --- updated-dependencies: - dependency-name: AWSSDK.Extensions.Bedrock.MEAI dependency-version: 4.0.4.11 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump Azure.Identity from 1.17.0 to 1.17.1 (#2780) --- updated-dependencies: - dependency-name: Azure.Identity dependency-version: 1.17.1 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.Identity dependency-version: 1.17.1 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.Identity dependency-version: 1.17.1 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.Identity dependency-version: 1.17.1 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump Azure.AI.AgentServer.AgentFramework from 1.0.0-beta.4 to 1.0.0-beta.5 (#2778) --- updated-dependencies: - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Python: added more complete parsing for mcp tool arguments (#2756) * added more complete parsing for mcp tool arguments * fixed mypy * added nonlocal model counter, and some fixes * fixes in naming logic * extracted json parsing function, added parametrized test and checked coverage * Python: Updated package versions (#2784) * Updated package versions * Small fix * Bump actions/checkout from 5 to 6 (#2404) Bumps [actions/checkout](https://github.com/actions/checkout) from 5 to 6. - [Release notes](https://github.com/actions/checkout/releases) - [Changelog](https://github.com/actions/checkout/blob/main/CHANGELOG.md) - [Commits](https://github.com/actions/checkout/compare/v5...v6) --- updated-dependencies: - dependency-name: actions/checkout 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> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * .NET: adds support for labels in edges, fixes rendering of labels in dot a… (#1507) * adds support for labels in edges, fixes rendering of labels in dot and mermaid, adds rendering of labels in edges * Update dotnet/src/Microsoft.Agents.AI.Workflows/Visualization/WorkflowVisualizer.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * escaping edge labels, adding tests for labels containing strange characters that would break the diagram and enabling the previous signature so the API has backwards compatibility. * Unify label in EdgeData * Edge API adjustments, removed useless "sanitizer" * fixed test --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Jacob Alber <jaalber@microsoft.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * Python: Added custom args and thread object to ai_function kwargs (#2769) * Added an example of using kwargs in ai_function * Added thread object to ai_function kwargs * Updated docs * Small fix * Added thread parameter filtering * Fix WorkflowAgent to include thread convo history. Enable checkpointing. (#2774) * Update OpenAIResponses.yaml to match AgentSchema (#2598) 1. Update `connection` child types -- `kind: ApiKey` to `kind: key` otherwise schema will fail: https://microsoft.github.io/AgentSchema/reference/apikeyconnection/ 2. Update `outputSchema`'s `PropertySchema` to be `kind` instead of `type` otherwise schema will fail: https://microsoft.github.io/AgentSchema/reference/propertyschema/ * Python: Remove warnings from workflow builder on not using factories (#2808) * Revert concurrent * Fix comments * Python: Filter framework kwargs from MCP tool invocations (#2870) * Filter framework kwargs from MCP tool invocations * Fixes * Python: Fix WorkflowAgent to emit yield_output as agent response (#2866) * Fix WorkflowAgent to emit yield_output as agent response * use raw_representation * Raw representation handling * Python: Use agent description in HandoffBuilder auto-generated tools (#2713) (#2714) ## Summary Enhanced `HandoffBuilder._apply_auto_tools` to use the target agent's description when creating handoff tools, providing more informative tool descriptions for LLMs. ## Changes - Modified `_apply_auto_tools` to extract `description` from `AgentExecutor._agent` when available - Updated iteration to use `.items()` for more efficient dict traversal - Handoff tools now use agent descriptions instead of generic placeholders ## Example Before: "Handoff to the refund_agent agent." After: "You handle refund requests. Ask for order details and process refunds." ## Testing - All handoff tests pass (20/20) - No breaking changes to existing API Fixes #2713 Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com> * Python: [BREAKING] Observability updates (#2782) * fixes Python: Add env_file_path parameter to setup_observability() similar to AzureOpenAIChatClient Fixes #2186 * WIP on updates using configure_azure_monitor * improved setup and clarity * fixed root .env.example * revert changes * updated files * updated sample * updated zero code * test fixes and fixed links * fix devui * removed planning docs * added enable method and updated readme and samples * clarified docstring * add return annotation * updated naming * update capatilized version * updated readme and some fixes * updated decorator name inline with the rest * feedback from comments addressed * Python: Fix middleware terminate flag to exit function calling loop immediately (#2868) * Fix middleware terminate flag to exit function calling loop immediately * Eliminating duck typing * Improve function exec result handling * Fix race condition * Fix mypy issues * Python: Fix context duplication in handoff workflows when restoring from checkpoint (#2867) * Fix context duplication in handoff workflows when restoring from checkpoint * Address Copilot PR review * .NET: Update to latest Azure.AI.*, OpenAI, and M.E.AI* (#2850) * Update to latest Azure.AI.*, OpenAI, and M.E.AI* Absorb breaking changes in Responses surface area * Update dotnet/samples/AgentWebChat/AgentWebChat.AgentHost/Utilities/ChatClientExtensions.cs * Update dotnet/samples/AgentWebChat/AgentWebChat.AgentHost/Utilities/ChatClientExtensions.cs * Update dotnet/samples/AgentWebChat/AgentWebChat.AgentHost/Utilities/ChatClientExtensions.cs * Update dotnet/samples/GettingStarted/AgentWithOpenAI/Agent_OpenAI_Step04_CreateFromOpenAIResponseClient/Program.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Using patch to remove the model is necessary, updated the response client to actually use the the ForAgent --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com> * Bump actions/download-artifact from 6 to 7 (#2862) Bumps [actions/download-artifact](https://github.com/actions/download-artifact) from 6 to 7. - [Release notes](https://github.com/actions/download-artifact/releases) - [Commits](https://github.com/actions/download-artifact/compare/v6...v7) --- updated-dependencies: - dependency-name: actions/download-artifact dependency-version: '7' 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> * Bump actions/cache from 4 to 5 (#2861) Bumps [actions/cache](https://github.com/actions/cache) from 4 to 5. - [Release notes](https://github.com/actions/cache/releases) - [Changelog](https://github.com/actions/cache/blob/main/RELEASES.md) - [Commits](https://github.com/actions/cache/compare/v4...v5) --- updated-dependencies: - dependency-name: actions/cache dependency-version: '5' 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> * Bump actions/upload-artifact from 5 to 6 (#2860) Bumps [actions/upload-artifact](https://github.com/actions/upload-artifact) from 5 to 6. - [Release notes](https://github.com/actions/upload-artifact/releases) - [Commits](https://github.com/actions/upload-artifact/compare/v5...v6) --- updated-dependencies: - dependency-name: actions/upload-artifact 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 : Ollama Connector for Agent Framework (#1104) * Initial Commit for Olama Connector * Added Olama Sample * Add Sample & Fixed Open Telemetry * Fixed Spelling from Olama to Ollama * remove"opentelemetry-semantic-conventions-ai ~=0.4.13" since its handled in a different pr * Added Tool Calling * Finalizing test cases * Adjust samples to be more reliable * Update python/packages/ollama/agent_framework_ollama/_chat_client.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update python/packages/ollama/pyproject.toml Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update python/packages/ollama/tests/test_ollama_chat_client.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update python/packages/ollama/agent_framework_ollama/_chat_client.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Improved Docstrings & Sample * Update python/packages/ollama/agent_framework_ollama/_chat_client.py Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com> * Integrate PR Feedback - Divided Streaming and Non-Streaming into independent Methods - Catch Ollama Validation Error - Add OTEL Provider Name - Checked Ollama Messages - Add Usage Statistics * Revert setting, so it can be none * Validate Message formatting between AF and Ollama * Catch Ollama Error and raise a ServiceResponse Error * Fix mypy error * remove .vscode comma * Add Reasoning support & adjust to new structure * Add Ollama Multimodality and Reasoning * Add test cases for reasoning * Add Tests for Error Handling in Ollama Client * Update python/samples/getting_started/multimodal_input/ollama_chat_multimodal.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Integrated Copilot Feedback * Implement first PR Feedback * Adjust Readme files for examples * Adjust argument passing via additional chat options * Implemented PR Feedback * Removing Ollama Package from Core and moving samples * Fix Link & Adding Samples to Main Sample Readme * Fixing Links in Readme * Moved Multimodal and Chat Example * Fixed Link in ChatClient to Ollama * Fix AgentFramework Links in Ollama Project * Fix observability breaking change --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com> * Skip failing IT (#2904) * .NET: Cosmos DB UT Fast Skip (For Non-Configured Local envs) (#2906) * Cosmos DB UT Fast Skip (Non-Configured Local envs) + Long running UT skip in pipeline when no CosmosDB changes happened * Force a CosmosDB source code change to trigger the pipeline * Address possible string boolean mismatch * Add debug * Enabling emulator always when running IT * .NET: Add TTLs to durable agent sessions (#2679) * .NET: Add TTLs to durable agent sessions * Remove unnecessary async * PR feedback: clarify UTC * PR feedback: limit minimum signal delay to <= 5 minutes * PR feedback: Fix TTL disablement * Linter: use auto-property * Fix build break from OpenAI SDK change * Updated CHANGELOG.md * PR feedback * Reduce default TTL to 14 days to work around DTS bug * Python: Update Mem0Provider to use v2 search API `filters` parameter (#2766) * short fix to move id parameters to filters object * added tests * small fix * mem0 dependency update * Updated package versions (#2913) * .NET: Switch to new "Run" method name. (#2843) * Switch to new "RunAgent" method name. * Try to disable false positive naming warning. * Add comment about disabled warnings. * Rename `RunAgent` to just `Run`. * Update CHANGELOG. * Python: Switch to new "run" method name. (#2890) * Switch to `run` method. * Add support for deprecated `run_agent`. * Fix entity method name. * Fix method name and improve tests. * Update comment. * Update Python CHANGELOG. * [BREAKING] Python: Add factory pattern to handoff orchestration builder (#2844) * WIP: Factory pattern to handoff * Add factory pattern to concurrent orchestration builder; Next: tests and sample verification * Add tests and improve comments * Fix mypy * Simplify handoff_simple.py * Simplify handoff_autonoumous.py and bug fix * Update readme * Address Copilot comments * Python: Flow custom kwargs to agents via Workflow SharedState (#2894) * Flow custom kwargs to agents via SharedState * Address Copilot feedback * Improve sample typing * Fix test * Fix Pydantic error when using Literal type for tool params (#2893) * Updated Ollama package version (#2920) * Python: Azure AI Agent with Bing Grounding Citations Sample (#2892) * bing grounding sample with citations * small fix * fix * .NET: Make DelegatingAIAgent abstract (#2797) * Initial plan * Make DelegatingAIAgent abstract Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Added additional arguments for Azure AI agent (#2922) * Python: Correction of MCP image type conversion in _mcp.py (#2901) * Correction of MCP image type conversion in _mcp.py * Added a new overload to the init function of the DataContent() type of the Agent Framework, edited the test case to correctly test the usage of the data and uri fields while using DataContent() * Fixed tests related to the changes of the DataContent type, added testing for both string and byte representations * Pass kwargs into subworkflows (#2923) * Python: Move ollama samples to samples getting started dir (#2921) * Move ollama samples to samples getting started dir * Address feedback * Python: fix: correct BadRequestError when using Pydantic model in response_fo… (#1843) * fix: correct BadRequestError when using Pydantic model in response_format * Fix lint --------- Co-authored-by: Evan Mattson <evan.mattson@microsoft.com> * .NET: [Breaking] Delete display name property (#2758) * delete the AIAgent.DisplayName property * use agent name as a first value for activity display name * Update dotnet/src/Microsoft.Agents.AI.Workflows/Specialized/HandoffAgentExecutor.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Python: cleanup and refactoring of chat clients (#2937) * refactoring and unifying naming schemes of internal methods of chat clients * set tool_choice to auto * fix for mypy * added note on naming and fix #2951 * fix responses * fixes in azure ai agents client * Python: Workflow add option to visualize internal executors (#2917) * Workflow add option to visualize internal executors * Address Copilot comments * Python: Fixes Run ID and Thread ID casing to align with AG-UI Typescript SDK (#2948) * added camelCase input to run id and thread id aligning with @ag-ui/core * fixed per copilot suggestions * Python: Add workflow cancellation sample (#2732) * Add workflow cancellation sample Add sample demonstrating how to cancel a running workflow using asyncio tasks. Shows both cancellation mid-execution and normal completion paths. Useful for implementing timeouts, graceful shutdown, or A2A executors. * update docstring * .NET: Update Anthropic package to version 12.0.0 (#2914) * Initial plan * Update Anthropic package to version 12.0.0 Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com> * Python: Add Azure Managed Redis Support with Credential Provider (#2887) * azure redis support * small fixes * azure managed redis sample * fixes * Bump CommunityToolkit.Aspire.OllamaSharp from 13.0.0-beta.440 to 13.0.0 (#2856) --- updated-dependencies: - dependency-name: CommunityToolkit.Aspire.OllamaSharp dependency-version: 13.0.0 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump AWSSDK.Extensions.Bedrock.MEAI from 4.0.4.11 to 4.0.5 (#2853) --- updated-dependencies: - dependency-name: AWSSDK.Extensions.Bedrock.MEAI dependency-version: 4.0.5 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> * Bump Azure.AI.AgentServer.AgentFramework from 1.0.0-beta.4 to 1.0.0-beta.5 (#2854) --- updated-dependencies: - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * Python: Fix WorkflowAgent event handling and kwargs forwarding (#2946) * Fix kwargs propagation through workflow.as_agent() * Fix WorkflowAgent to respect AgentExecutor output_response setting * .NET: Use GrpcEntityRunner instead of TaskEntityDispatcher (#2759) * Use GrpcEntityRunner instead of TaskEntityDispatcher * Pin to Durable worker 1.11.0 * Set the invocation result * Update all Durable packages * Update changelog, rename dispatcher to encondedEntityRequest * Python: Bump Py version to 1.0.0b251218 for a release. Update CHANGELOG (#2968) * Bump Py version to 1.0.0b251218 for a release. Update CHANGELOG * update lock * Fix formatting * Fix ChatKit typing * Python: Introducing Foundry Local Chat Clients (#2915) * redo foundry local chat client * fix mypy and spelling * better docstring, updated sample * fixed tests and added tests * small sample update * Updated package versions (#2978) * Python: Added GitHub MCP sample with PAT (#2967) * added github mcp sample with PAT * addressed copilot fixes * env fix * Python: Preserve reasoning blocks with OpenRouter (#2950) * Preserve reasoning blocks with OpenRouter * Put encrypted reasoning in TextReasoningContent * Remove unneccessary change * Fix docs * Support streaming * Fix handling None in TextReasoningContent.text * Python: Added response.created and response.in_progress event process to OpenAIBaseResponseClient (#2975) * added response.created and response.in_progress to include response.id * better doc string * added tests for the new streaming event types * Python: Introducing support for Bedrock-hosted models (Anthropic, Cohere, etc.) (#2610) * Pushing the bedrock related changes to the new branch after addressing the review comments * 2524 Addressed the second round review comments * 2524 Addressed few more minor comments on the PR * resolving the merge conflict * 2524 resolved the uv.lock conflicts * 2524 addressed more comments * 2524 removed the print statement to fix the checks failure * 2524 resolved the CI failure issues * 2524 fixing the CI breaks * 2524 Addressed the review comment * 2524 resolved conflict --------- Co-authored-by: Sunil Dutta <sunil.dutta@penske.com> Co-authored-by: budgetboardingai <apurva.sharma31@gmail.com> * .NET: [Durable Agents] Reliable streaming sample (#2942) * .NET: [Durable Agents] Reliable streaming sample * Add automated validation for new sample * Address Copilot PR feedback * Fix typo in README.md about agent definitions (#2634) * Fix typo in README.md about agent definitions * Update agent-samples/README.md Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Python: latency improvements (#3014) * latency improvements * fixed mypy, added coding standards and instructions * slight logic improvement * Python: Updated package versions (#3024) * Updated package versions * Updated changelog * Python: add powerfx safe mode (#3028) * add powerfx safe mode * improved docstring and aligned env_file loading * ensured test uses reset * .NET: [Breaking] Introduce RunCoreAsync/RunCoreStreamingAsync delegation pattern in AIAgent (#2749) * Initial plan * Refactor AIAgent: Make RunAsync and RunStreamingAsync non-abstract, add RunCoreAsync and RunCoreStreamingAsync Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Fix infinite recursion in test implementations Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Make RunAsync and RunStreamingAsync non-virtual as requested Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Fix DelegatingAIAgent subclasses to use RunCoreAsync/RunCoreStreamingAsync Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Fix XML documentation references in AnonymousDelegatingAIAgent Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Restore <see cref> tags with proper qualified signatures in AnonymousDelegatingAIAgent Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Rollback unnecessary XML documentation changes in AnonymousDelegatingAIAgent Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Remove pragma and update crefs to RunCoreAsync/RunCoreStreamingAsync Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Fix EntityAgentWrapper to call base.RunCoreAsync/RunCoreStreamingAsync Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * fix compilation issues * fix compilatio issue * fix tests * fix unit tests * fix unit test --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> Co-authored-by: SergeyMenshykh <sergemenshikh@gmail.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * add issue template and additional labeling (#3006) * fix and extra int test (#3037) * .NET: [BREAKING] Refactor ChatMessageStore methods to be similar to AIContextProvider and add filtering support (#2604) * Refactor ChatMessageStore methods to be similar to AIContextProvider * Fix file encoding * Ensure that AIContextProvider messages area also persisted. * Update formatting and seal context classes * Improve formatting * Remove optional messages from constructor and add unit test * Add ChatMessageStore filtering via a decorator * Update sample and cosmos message store to store AIContextProvider messages in right order. Fix unit tests. * Update Workflowmessage store to use aicontext provider messages. * Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Apply suggestions from code review Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Improve xml docs messaging * Address code review comments. * Also notify message store on failure --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * [BREAKING] Remove unused AgentThreadMetadata (#3067) * Remove unused AgentThreadMetadata * Update DurableTask Changelog * Python: Fix AzureAIClient failure when conversation history contains assistant messages (#3076) * Fix AzureAIClient failure when conversation history contains assistant messages * Address PR review feedback: improve docstring and test assertions * Remove redundant cast * Fix: Update OTLP exporter protocol conditions (#3070) * Python: Fix ExecutorInvokedEvent and ExecutorCompletedEvent observability data (#3090) * Fix ExecutorInvokedEvent.data mutation bug * Fix bug related to not yielding output type * .NET: Seal ChatClientAgentThread (#2842) * Initial plan * Seal ChatClientAgentThread class Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Fix broken strands urls. (#3102) * Fix broken strands urls. * Fix typos * .NET: Fix message ordering inconsistency when using AIContextProvider (#2659) * Initial plan * Fix message ordering inconsistency when using AIContextProvider Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> * Revert to original message ordering: Input, AIContextProvider, Response Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> * Reorder messages to ChatClient to match MessageStore order: Existing, Input, AIContextProvider Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> * Remove redundant test methods as existing tests already verify the behavior Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * fix: tool_choice parameter not being honored when passed to agent.run() (#3095) * sharepoint sample fix (#3108) * Bump versions to 1.0.0b260106 for a release. Update CHANGELOG.md (#3109) * Bump Bedrock version to latest (#3110) * Python: Fix MCP tool result serialization for list[TextContent] (#2523) * Fix MCP tool result serialization for list[TextContent] When MCP tools return results containing list[TextContent], they were incorrectly serialized to object repr strings like: '[<agent_framework._types.TextContent object at 0x...>]' This fix properly extracts text content from list items by: 1. Checking if items have a 'text' attribute (TextContent) 2. Using model_dump() for items that support it 3. Falling back to str() for other types 4. Joining single items as plain text, multiple items as JSON array Fixes #2509 * Address PR review feedback for MCP tool result serialization - Extract serialize_content_result() to shared _utils.py - Fix logic: use texts[0] instead of join for single item - Add type annotation: texts: list[str] = [] - Return empty string for empty list instead of '[]' - Move import json to file top level - Add comprehensive unit tests for serialization * Address PR review feedback: fix type checking and double serialization - Add isinstance(item.text, str) check to ensure text attribute is a string - Fix double-serialization issue by keeping model_dump results as dicts until final json.dumps (removes escaped JSON strings in arrays) - Improve docstring with detailed return value documentation - Add test for non-string text attribute handling - Add tests for list type tool results in _events.py path * Simplify PR: minimal changes to fix MCP tool result serialization Addresses reviewer feedback about excessive refactoring: - Reset _events.py to original structure - Only add import and use serialize_content_result in one location - All review comments addressed in serialize_content_result(): - Added isinstance(item.text, str) check - Use model_dump(mode="json") to avoid double-serialization - Improved docstring with explicit return value documentation - Empty list returns "" instead of "[]" * Refactor: Move MCP TextContent serialization to core prepare_function_call_results Per reviewer feedback, moved the TextContent serialization logic from ag-ui's serialize_content_result to the core package's prepare_function_call_results function. Changes: - Added handling for objects with 'text' attribute (like MCP TextContent) in _prepare_function_call_results_as_dumpable - Removed serialize_content_result from ag-ui/_utils.py - Updated _events.py and _message_adapters.py to use prepare_function_call_results from core package - Updated tests to match the core function's behavior * Fix failing tests for prepare_function_call_results behavior - test_tool_result_with_none: Update expected value to 'null' (JSON serialization of None) - test_tool_result_with_model_dump_objects: Use Pydantic BaseModel instead of plain class * Fix B903 linter error: Convert MockTextContent to dataclass The ruff linter was reporting B903 (class could be dataclass or namedtuple) for the MockTextContent test helper classes. This commit converts them to dataclasses to satisfy the linter check. * Python: Improve DevUI, add Context Inspector view as new tab under traces (#2742) * Improve DevUI, add Context Inspector view as new tab under traces * fix mypy errors * fix: Handle stale MCP connections in DevUI executor MCP tools can become stale when HTTP streaming responses end - the underlying stdio streams close but `is_connected` remains True. This causes subsequent requests to fail with `ClosedResourceError`. Add `_ensure_mcp_connections()` to detect and reconnect stale MCP tools before agent execution. This is a workaround for an upstream Agent Framework issue where connection state isn't properly tracked. Fixes MCP tools failing on second HTTP request in DevUI. fixes #1476 #1515 #2865 * fix #1572 report import dependency errors more clearly * Ensure there is streaming toggle where users can select streaming vs non streaming mode in devui . Fixes .NET: [Python] DevUI tool call rendering in non-streaming mode? * remove unused dead code * improve ux - workflows with agents show a chat component in execution timelien, also ensure magentic final output shows correctly * update ui build * update devui to use instrumentation instead of tracing, other instrumentation and type/instance check fixes * .NET: Seal factory contexts and add non JSO deserialize overloads (#3066) * Seal factory contexts and add non JSO deserialize overloads * Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Enable blank issues in issue template configuration Need to re-enable creating blank issues * updated templates (#3106) * updated templates * enabled blank and fixed triage * made language optional and moved to the bottom for features * Python: Streaming sample for azurefunctions (#3057) * Streaming sample for azurefunctions * Fixed links and sample name * Addressed feedback * Addressed feedback * Fixed integration tests * Updated test * Python: fix(azure-ai): Fix response_format handling for structured outputs (#3114) * fix(azure-ai): read response_format from chat_options instead of run_options * refactor: use explicit None checks for response_format * Fix mypy error * Mypy fix * Python: Bump python version to 1.0.0b260107 for a release (#3128) * Bump python version to 1.0.0b260107 for a release * Update changelog * Make A2AAgent public, so that it's concrete implementation methods can be used. (#3119) * .NET: Map additional props <-> A2A metadata (#3137) * map additional props from agent run options to a2a request metadata * small touches * add unit tests for new extension methods * Sort using * add unit test * add additiona unit tests * special case json element to avoid unnecessary serialization * Python: Fix Anthropic streaming response bugs (#3141) * test commit identity * fix(anthropic): fix raw_representation and finish_reason in streaming * lint fix * Bump AWSSDK.Extensions.Bedrock.MEAI from 4.0.5 to 4.0.5.1 (#2994) --- updated-dependencies: - dependency-name: AWSSDK.Extensions.Bedrock.MEAI dependency-version: 4.0.5.1 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * Bump Anthropic from 12.0.0 to 12.0.1 (#2993) --- updated-dependencies: - dependency-name: Anthropic dependency-version: 12.0.1 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * .NET: [Breaking] Prevent loss of input messages & streamed updates when resuming streaming (#2748) * save input messages and stream updates to the continuation token to be able to use them in the last successful stream resumption call. * Update dotnet/src/Microsoft.Agents.AI/ChatClient/ChatClientAgentContinuationToken.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update dotnet/src/Microsoft.Agents.AI/ChatClient/ChatClientAgentContinuationToken.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update dotnet/tests/Microsoft.Agents.AI.UnitTests/ChatClient/ChatClientAgent_BackgroundResponsesTests.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update dotnet/src/Microsoft.Agents.AI/ChatClient/ChatClientAgentContinuationToken.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update dotnet/src/Microsoft.Agents.AI/ChatClient/ChatClientAgentContinuationToken.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * fix typo * init continuation token from chat response * remove unnecessary types for source generation * remove check for continuation token passed at initial run * remove check for continuation token pass at initial run * centralize continuation token parsing * update xml comments * use readonly collection instead of enumerable --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * .NET: fix: Expose WorkflowErrorEvent as ErrorContent (#2762) * fix: Expose WorkflowErrorEvent as ErrorContent When hosted using .AsAgent(), Workflows were not exposing inner errors coming as Exceptions (through the WorkflowErrorEvent) The fix is to convert their message to an ErrorContent on the way out, rather than rely on the default "empty update" to collect the raw event. * feat: Add a way to show/suppress exception information * Bump Microsoft.Agents.AI.Workflows from 1.0.0-preview.251125.1 to 1.0.0-preview.251219.1 (#2997) --- updated-dependencies: - dependency-name: Microsoft.Agents.AI.Workflows dependency-version: 1.0.0-preview.251219.1 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * .NET: Add Run overloads to expose ChatClientAgentRunOptions in IntelliSense (#3115) * Initial plan * Add ChatClientAgentExtensions for improved discoverability of ChatClientAgentRunOptions Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> * Address code review feedback - use collection expression syntax Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> * Apply suggestion from @westey-m * Fix issues with Copilot implementation * Add additional tests for structured output overloads. --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> * Python: Add tool call/result content types and update connectors and samples (#2971) * Add new AI content types and image tool support Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Add Python content types for tool calls/results and image generation tool support Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Address review feedback for tool content and samples Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Tighten image generation typing and sample tools list Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Align image generation output typing Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Handle MCP naming, image options mapping, and connector tool content Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Allow MCP call in function approval request Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Remove raw image_generation tool remapping Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Restore Anthropic tool_use to function calls unless code execution Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Fix lint issues for hosted file docstring and MCP parsing Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Import ChatResponse types in Anthropic client Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Fix Anthropics citation type imports and MCP typing for handoff/tools Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Skip lightning tests without agentlightning and fix function call import Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * fix lint on lab package * rebuilt anthropic parsing * redid anthropic parsing * typo * updated parsing and added missing docstrings * fix tests * mypy fixes * second mypy fix * add new class to other samples --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> Co-authored-by: eavanvalkenburg <github@vanvalkenburg.eu> * Bump Google.GenAI from 0.6.0 to 0.9.0 (#2995) --- updated-dependencies: - dependency-name: Google.GenAI dependency-version: 0.9.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * Bump js-yaml from 4.1.0 to 4.1.1 in /python/packages/devui/frontend (#3123) Bumps [js-yaml](https://github.com/nodeca/js-yaml) from 4.1.0 to 4.1.1. - [Changelog](https://github.com/nodeca/js-yaml/blob/master/CHANGELOG.md) - [Commits](https://github.com/nodeca/js-yaml/compare/4.1.0...4.1.1) --- updated-dependencies: - dependency-name: js-yaml dependency-version: 4.1.1 dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Updated package versions (#3144) * .NET: Bump Microsoft.Agents.AI.OpenAI and Microsoft.Extensions.AI.OpenAI (#2996) * Bump Microsoft.Agents.AI.OpenAI and Microsoft.Extensions.AI.OpenAI Bumps Microsoft.Agents.AI.OpenAI from 1.0.0-preview.251125.1 to 1.0.0-preview.251219.1 Bumps Microsoft.Extensions.AI.OpenAI from 10.1.0-preview.1.25608.1 to 10.1.1-preview.1.25612.2 --- updated-dependencies: - dependency-name: Microsoft.Agents.AI.OpenAI dependency-version: 1.0.0-preview.251219.1 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Microsoft.Extensions.AI.OpenAI dependency-version: 10.1.1-preview.1.25612.2 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Microsoft.Agents.AI.OpenAI dependency-version: 1.0.0-preview.251219.1 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Microsoft.Extensions.AI.OpenAI dependency-version: 10.1.1-preview.1.25612.2 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * Fixed samples --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> Co-authored-by: Dmytro Struk <13853051+dmytrostruk@users.noreply.github.com> * Python: fix(ag-ui): Execute tools with approval_mode, fix shared state, code cleanup (#3079) * fix(ag-ui): execute tools after approval in human-in-the-loop flow * Fix shared state bug * Bug fix finalized * Refactoring to clean up code * Code cleanup * More fixes * More code cleanup * Add version detection in __init__.py to ruff ignore list * Track agent name with updates for workflow agent (#3146) * Python: Fix AzureAIClient tool call bug for AG-UI use (#3148) * Fiz AzureAIClient tool call bug * Address copilot feedback * Python: multiple bug fixes (#3150) * fix Python: kwargs are not passed to _prepare_thread_and_messages in ChatAgent.run Fixes #3118 * fix Python: [Bug]: model_id versus model_deployment_name is confusing in Azure AI Agents Fixes #3147 * add types * fixed type and docstring * fix(anthropic): fix duplicate ToolCallStartEvent in streaming tool calls (#3051) When processing `input_json_delta` events, the Anthropic client was passing the tool name from the previous `tool_use` event. This caused ag-ui's `_handle_function_call_content` to emit a `ToolCallStartEvent` for every streaming chunk (since it triggers on `if content.name:`). This fix changes the behavior to pass an empty string for `name` in `input_json_delta` events, matching OpenAI's behavior where streaming argument chunks have `name=""`. The initial `tool_use` event still provides the tool name, so only one `ToolCallStartEvent` is emitted. Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com> * .NET: [BREAKING] Change GetNewThread and DeserializeThread to async (#3152) * Change GetNewThread and DeserializeThread plus ChatMessageStore and AIContextProvider Factories to async * Merge fixes * Fix Ollama model env var in documentation (#3156) Signed-off-by: Dina Suehiro Jones <dina.s.jones@intel.com> * Python: Add Pydantic request model and OpenAPI tags support to AG-UI FastAPI endpoint (#2522) * feat(ag-ui): Add Pydantic request model and OpenAPI tags support - Add AGUIRequest Pydantic model in _types.py with field descriptions - Update add_agent_framework_fastapi_endpoint() to accept tags parameter - Use AGUIRequest model for automatic validation and OpenAPI schema generation - Export AGUIRequest and DEFAULT_TAGS in __init__.py - Update test_endpoint.py to expect 422 for invalid requests - Add tests for OpenAPI schema, default tags, custom tags, and validation Benefits: - Better API documentation with complete request schema in Swagger UI - Automatic request validation with Pydantic - Organized endpoints under 'AG-UI' tag instead of 'default' - Improved developer experience and type safety Fixes #<issue-number> * test(ag-ui): Add test for internal error handling to achieve 100% coverage - Add test_endpoint_internal_error_handling() to cover exception handling code - Mock copy.deepcopy to simulate internal error during default_state processing - Add type: ignore for FastAPI tags parameter (known pyright compatibility issue) - Achieves 100% test coverage for _endpoint.py (previously missing lines 103-105) * .NET: Improve resolving `AITool` from DI (#3175) * remove localagenttoolregistry * also give the factory method API * Python: Fix MCPStreamableHTTPTool to use new streamable_http_client API (#3088) * Fix MCPStreamableHTTPTool to use new streamable_http_client API with proper httpx client cleanup Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Update docstring to reflect new streamable_http_client API usage Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Refactor MCPStreamableHTTPTool to accept optional http_client parameter and delegate client creation to streamable_http_client Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Update mcp package minimum version to 1.24.0 for streamable_http_client API support Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Fix critical bugs: apply headers/timeout/sse_read_timeout when creating httpx client, add version constraint <2, and properly manage client lifecycle Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Simplify implementation: remove headers/timeout/sse_read_timeout params, remove kwargs, remove close() override per feedback Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Add back **kwargs parameter for backward compatibility (accepted but not used) Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Remove unused httpx import from test file Note: The uv.lock file needs to be updated with 'uv sync' to reflect the mcp version constraint change (>=1.24.0,<2) Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * cicd fixes * udpated samples with headers examples --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> Co-authored-by: eavanvalkenburg <github@vanvalkenburg.eu> * azureai direct a2a endpoint support (#3127) * Python: [BREAKING]: removed display_name, renamed context_providers, middleware and AggregateContextProvider (#3139) * removed display_name, renamed context_providers, middleware and AggregateContextProvider * fixes * fixed test * testfix * removed mistakenly put back test * updated new test * rename middlewares to middleware * middleware fixes * Python: MCP Improvements: improved connection loss behavior, pagination for loading and a param to control representation (#3154) * pagination support (#2848) added a parse_tool_result param and connection loss (#2884) * fix #3153 * improved connection handling * improved logic * Python: Add declarative workflow runtime (#2815) * Further support for declarative python workflows * Add tests. Clean up for typing and formatting * Improvements and cleanup * Typing cleanup. Improve docstrings * Proper code in docstrings * Fix malformed code-block directive in docstring * Remove dead links * PR feedback * Address PR feedback * Address PR feedback * Remove sl * Update devui frontend * More cleanup * Fix uv lock * Skip Py 3.14 tests as powerfx doesn't support it * Fix mypy error * Fix for tool calls * Removed stale docstring * Fix lint * Standardize on .NET namespaces. Revert DevUI changes (bring in later) * Implement remaining items for Python declarative support to match dotnet * point URL to agent, not to agentcard (#3176) * Python: [BREAKING]: Introducing Options as TypedDict and Generic (#3140) * WIP typeddict for options * updated all clients and ChatAgents * updated everything * added ADR * fix mypy * proper typevar imports * fixed import * fixed other imports * slight update in the sample * updated from feedback * fixes * fixed missing covariants and test fixes * fixed typing * updated anthropic thinking config * ruff fixes * fixed int tests * fix tests and mypy * updated integration tests * updated docstring and test fix * improved options handling in obser * mypy fix * updated a host of integration tests * fix tests * bedrock fix * [BREAKING] Python: Refactor orchestrations (#3023) * Group chat refactoring Part 1; Next: HIL and handoff * Add agent approval flow; next samples * WIP: samples * WIP: HIL samples * Group chat HIL working; next: handoff * Fix group chat tool approval sample * WIP: refactor handoff; next handoff handling * Handoff done; next handoff samples and concurrent and sequential * Handoff samples, concurrent, and sequential done; next Magentic * WIP: magentic; next test with samples + HIL * Magentic Working; next fix all samples and tests * Fix handoff samples; next tests * WIP: fixing tests; some orchestration as agent samples are failing * Group chat unit tests done * Handoff unit tests done * Remove old orchestration_request_info and fix related tests * Magentic unit tests done * Fix samples * Fix test * Fix test 2 * mypy * Address comments * Update readme * Address comments * Address comments 2 * Replace display name * Python: ADR for create/get agent API (#2618) * ADR for create/get agent API * Updated ADR with implementation options * Small updates * Updated decision outcome section * Updated broken links * Small updates * Fixed merge conflicts * Small fix * Updated decision outcome section * Small fixes * Updated provider naming based on client SDK * Add ignored parameter for CodeQL in workflow (#3204) * Implement IReadOnlyList on InMemoryChatMessageStore (#3205) * .NET: Make ChatMessageStore and AIContextProvider context props settable (#3196) * Make ChatMessageStore and AIContextProvider context props setable * Add validation to preserve non-null requirement of certain properties. * Fix broken tests. * Python: Add dependencies param to ag-ui FastAPI endpoint (#3191) * Add dependencies param to ag-ui FastAPI endpoint * Address Copilot feedback * renamed all (#3207) * Python: ADR for simplified get response (#3098) * ADR for simplified get response * updated some language, added agent option and code comparison * small update in sample * added workflows and expanded some points * changed decision and number * updated with stream=False default * .NET: [Breaking] Rename`AgentRunResponse` and `AgentRunResponseUpdate` classes (#3197) * rename AgentRunResponse and AgentRunResponseUpdate classes - part1 * rename varialbles, parameters, methods and tests * rollback unnecessary changes * .NET: [Breaking] Rename AgentRunResponseEvent and AgentRunUpdateEvent classes (#3214) * rename AgentRunResponseEvent and AgentRunUpdateEvent classes * rollback unnecessary changes * Python: Create/Get Agent API for Azure V2 (#3059) * Added get_agent method to Azure AI V2 * Small fixes * Small fix * Removed AzureAIAgentProvider * Added create_agent method * Small fixes * Fixed code interpreter tool mapping * Added agent provider for V2 client * Updated response format handling * Added provider example * Fixed errors * Update python/samples/getting_started/agents/azure_ai/README.md Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Small fix * Updates from merge * Resolved comments * Resolved comments --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Python: Add more specific exceptions to Workflow (#3188) * Add more specifc workflow exceptions * Fix tests * AI comments * Misc * Python: Added AzureAI sample for downloading code interpreter generated files (#3189) * added azure ai code interpreter file download sample * copilot fix suggestions * function name fixes + readme update * small fix * update package versions (#3223) Co-authored-by: Dmytro Struk <13853051+dmytrostruk@users.noreply.github.com> * Python: fix(core): correct FunctionResultContent ordering in WorkflowAgent.merge_updates (#3168) * fix(core): simplify FunctionResultContent ordering in WorkflowAgent.merge_updates * improve comment * Fix name * fix(workflows): rename WorkflowOutputEvent.source_executor_id to executor_id for API consistency (#3166) * Python: fix(ag-ui): add MCP tool support for AG-UI approval flows (#3212) * add MCP tool support for AG-UI approval flows * use attribute in place of property * Python: Properly configure structured outputs based on new options dict (#3213) * Properly configure structured outputs based on new options dict * Fix mypy * .NET: Merge AgentRunOptions.AdditionalProperties into ChatOptions.AdditionalProperties (#3184) * Merge AgentRunOptions.AdditionalProperties into ChatOptions.AdditionalProperties * Fix namespace and typo. * .NET: Update Google.GenAI to 0.11.0 and remove polyfill implementations (#3232) * Initial plan * Update Google.GenAI to 0.11.0 and remove polyfill files Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> * .NET: [BREAKING] Renamed CreateAIAgent/GetAIAgent to AsAIAgent (#3222) * Renamed chat client extension method * Additional renaming * Updated documentation * Fixed tests * Small fix * Small fix * Updated DurableAIAgent and fixed integration tests (#3241) * Python: Create/Get Agent API for Azure V1 (#3192) * Added provider implementation for Azure AI V1 * Small fixes * Fixed OpenAPI example * Fixed local MCP example * Fixed hosted MCP example * Fixed file search sample * Small fixes * Resolved comments * Doc updates * Bump azure-core from 1.37.0 to 1.38.0 in /python (#3209) Bumps [azure-core](https://github.com/Azure/azure-sdk-for-python) from 1.37.0 to 1.38.0. - [Release notes](https://github.com/Azure/azure-sdk-for-python/releases) - [Commits](https://github.com/Azure/azure-sdk-for-python/compare/azure-core_1.37.0...azure-core_1.38.0) --- updated-dependencies: - dependency-name: azure-core dependency-version: 1.38.0 dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Python: Create/Get Agent API for OpenAI Assistants (#3208) * Added provider implementation * Added example with response format * Small improvements * Python: (AG-UI) Support service-managed thread on AG-UI (#3136) * added service thread support * set service_thread_id to only supplied_thread_id * uses raw_representation to extract the conversation_id * removed accidental edit * updated test to use raw_representation * resolves copilot review feedback * revert back StubAgent, since not used * removed relative module import * removed hasattr check per PR feedback * Create/Get Agent API - fixes and example improvements (#3246) * Fix merge conflicts --------- Signed-off-by: dependabot[bot] <support@github.com> Signed-off-by: Dina Suehiro Jones <dina.s.jones@intel.com> Co-authored-by: Tao Chen <taochen@microsoft.com> Co-authored-by: Kurt <65111699+q33566@users.noreply.github.com> Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> Co-authored-by: Korolev Dmitry <deagle.gross@gmail.com> Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com> Co-authored-by: Dmytro Struk <13853051+dmytrostruk@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> Co-authored-by: Jose Luis Latorre Millas <joslat@gmail.com> Co-authored-by: Jacob Alber <jaalber@microsoft.com> Co-authored-by: Richard Ortega <richardjortega@gmail.com> Co-authored-by: 刘邦学AI <lbbniu@gmail.com> Co-authored-by: Stephen Toub <stoub@microsoft.com> Co-authored-by: Nico Möller <nkm-moeller@mail.de> Co-authored-by: Chris Gillum <cgillum@microsoft.com> Co-authored-by: Giles Odigwe <79032838+giles17@users.noreply.github.com> Co-authored-by: Phillip Hoff <phillip.hoff@gmail.com> Co-authored-by: Ege Ozan Özyedek <36128615+egeozanozyedek@users.noreply.github.com> Co-authored-by: samueljohnsiby <66901393+samueljohnsiby@users.noreply.github.com> Co-authored-by: Evan Mattson <evan.mattson@microsoft.com> Co-authored-by: Hao Luo <338265+howlowck@users.noreply.github.com> Co-authored-by: Victor Dibia <chuvidi2003@gmail.com> Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com> Co-authored-by: Jacob Viau <javia@microsoft.com> Co-authored-by: SuperKenVery <39673849+SuperKenVery@users.noreply.github.com> Co-authored-by: Sunil Dutta <dutta.2003@gmail.com> Co-authored-by: Sunil Dutta <sunil.dutta@penske.com> Co-authored-by: budgetboardingai <apurva.sharma31@gmail.com> Co-authored-by: Syrine Chelly <62653967+SyChell@users.noreply.github.com> Co-authored-by: SergeyMenshykh <sergemenshikh@gmail.com> Co-authored-by: westey <164392973+westey-m@users.noreply.github.com> Co-authored-by: takanori-terai <123897708+takanori-terai@users.noreply.github.com> Co-authored-by: claude89757 <138977524+claude89757@users.noreply.github.com> Co-authored-by: Gavin Aguiar <80794152+gavin-aguiar@users.noreply.github.com> Co-authored-by: Sukeesh <vsukeeshbabu@gmail.com> Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> Co-authored-by: eavanvalkenburg <github@vanvalkenburg.eu> Co-authored-by: Ao Chen <chenao3220@gmail.com> Co-authored-by: Dina Suehiro Jones <dina.s.jones@intel.com> * Python: Add integration tests for durabletask package (#3317) * Add integration tests * Fix flaky test * Fix env viz * Fix tests and address feedback * Fix imports for durabletask (#3345) * .NET: Python: Merge `main` into `feature-durabletask` branch (#3385) * Python: Add factory pattern to concurrent orchestration builder (#2738) * Add factory pattern to concurrent orchestration builder * Update readme * Address AI comments * Fix unit tests * Fix import * Prevent multiple calls to set participants or factories * Add comments * Mitigate warnings * Fix mypy * Address comments * Address Copilot comments * Fix tests * Python: fix: GroupChat ManagerSelectionResponse JSON Schema for OpenAI Structured Outpu… (#2750) * fix: ManagerSelectionResponse JSON Schema for OpenAI Structured Output Strict Mode * refactor: install pre-commit then commit again * Capture file IDs from code interpreter in streaming responses (#2741) * .NET: [BREAKING] Prevent nulls in AIAgent property (#2719) * prevent nulls in AIAgent property * address feedback * code ql sm04598 (#2723) Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> * .NET: Add Conversation State Sample (Step05) (#2697) * Initial plan * Add Agent_OpenAI_Step05_Conversation sample for conversation state management Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> * Update Program.cs comment to accurately describe the sample Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> * Update the code to use the ConversationClient more in line with the samples in OpenAI * Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Changing sample to use ChatClientAgent and conversationId in GetNewThread --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Bump AWSSDK.Extensions.Bedrock.MEAI from 4.0.4.7 to 4.0.4.11 (#2777) --- updated-dependencies: - dependency-name: AWSSDK.Extensions.Bedrock.MEAI dependency-version: 4.0.4.11 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump Azure.Identity from 1.17.0 to 1.17.1 (#2780) --- updated-dependencies: - dependency-name: Azure.Identity dependency-version: 1.17.1 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.Identity dependency-version: 1.17.1 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.Identity dependency-version: 1.17.1 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.Identity dependency-version: 1.17.1 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump Azure.AI.AgentServer.AgentFramework from 1.0.0-beta.4 to 1.0.0-beta.5 (#2778) --- updated-dependencies: - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Python: added more complete parsing for mcp tool arguments (#2756) * added more complete parsing for mcp tool arguments * fixed mypy * added nonlocal model counter, and some fixes * fixes in naming logic * extracted json parsing function, added parametrized test and checked coverage * Python: Updated package versions (#2784) * Updated package versions * Small fix * Bump actions/checkout from 5 to 6 (#2404) Bumps [actions/checkout](https://github.com/actions/checkout) from 5 to 6. - [Release notes](https://github.com/actions/checkout/releases) - [Changelog](https://github.com/actions/checkout/blob/main/CHANGELOG.md) - [Commits](https://github.com/actions/checkout/compare/v5...v6) --- updated-dependencies: - dependency-name: actions/checkout 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> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * .NET: adds support for labels in edges, fixes rendering of labels in dot a… (#1507) * adds support for labels in edges, fixes rendering of labels in dot and mermaid, adds rendering of labels in edges * Update dotnet/src/Microsoft.Agents.AI.Workflows/Visualization/WorkflowVisualizer.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * escaping edge labels, adding tests for labels containing strange characters that would break the diagram and enabling the previous signature so the API has backwards compatibility. * Unify label in EdgeData * Edge API adjustments, removed useless "sanitizer" * fixed test --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Jacob Alber <jaalber@microsoft.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * Python: Added custom args and thread object to ai_function kwargs (#2769) * Added an example of using kwargs in ai_function * Added thread object to ai_function kwargs * Updated docs * Small fix * Added thread parameter filtering * Fix WorkflowAgent to include thread convo history. Enable checkpointing. (#2774) * Update OpenAIResponses.yaml to match AgentSchema (#2598) 1. Update `connection` child types -- `kind: ApiKey` to `kind: key` otherwise schema will fail: https://microsoft.github.io/AgentSchema/reference/apikeyconnection/ 2. Update `outputSchema`'s `PropertySchema` to be `kind` instead of `type` otherwise schema will fail: https://microsoft.github.io/AgentSchema/reference/propertyschema/ * Python: Remove warnings from workflow builder on not using factories (#2808) * Revert concurrent * Fix comments * Python: Filter framework kwargs from MCP tool invocations (#2870) * Filter framework kwargs from MCP tool invocations * Fixes * Python: Fix WorkflowAgent to emit yield_output as agent response (#2866) * Fix WorkflowAgent to emit yield_output as agent response * use raw_representation * Raw representation handling * Python: Use agent description in HandoffBuilder auto-generated tools (#2713) (#2714) ## Summary Enhanced `HandoffBuilder._apply_auto_tools` to use the target agent's description when creating handoff tools, providing more informative tool descriptions for LLMs. ## Changes - Modified `_apply_auto_tools` to extract `description` from `AgentExecutor._agent` when available - Updated iteration to use `.items()` for more efficient dict traversal - Handoff tools now use agent descriptions instead of generic placeholders ## Example Before: "Handoff to the refund_agent agent." After: "You handle refund requests. Ask for order details and process refunds." ## Testing - All handoff tests pass (20/20) - No breaking changes to existing API Fixes #2713 Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com> * Python: [BREAKING] Observability updates (#2782) * fixes Python: Add env_file_path parameter to setup_observability() similar to AzureOpenAIChatClient Fixes #2186 * WIP on updates using configure_azure_monitor * improved setup and clarity * fixed root .env.example * revert changes * updated files * updated sample * updated zero code * test fixes and fixed links * fix devui * removed planning docs * added enable method and updated readme and samples * clarified docstring * add return annotation * updated naming * update capatilized version * updated readme and some fixes * updated decorator name inline with the rest * feedback from comments addressed * Python: Fix middleware terminate flag to exit function calling loop immediately (#2868) * Fix middleware terminate flag to exit function calling loop immediately * Eliminating duck typing * Improve function exec result handling * Fix race condition * Fix mypy issues * Python: Fix context duplication in handoff workflows when restoring from checkpoint (#2867) * Fix context duplication in handoff workflows when restoring from checkpoint * Address Copilot PR review * .NET: Update to latest Azure.AI.*, OpenAI, and M.E.AI* (#2850) * Update to latest Azure.AI.*, OpenAI, and M.E.AI* Absorb breaking changes in Responses surface area * Update dotnet/samples/AgentWebChat/AgentWebChat.AgentHost/Utilities/ChatClientExtensions.cs * Update dotnet/samples/AgentWebChat/AgentWebChat.AgentHost/Utilities/ChatClientExtensions.cs * Update dotnet/samples/AgentWebChat/AgentWebChat.AgentHost/Utilities/ChatClientExtensions.cs * Update dotnet/samples/GettingStarted/AgentWithOpenAI/Agent_OpenAI_Step04_CreateFromOpenAIResponseClient/Program.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Using patch to remove the model is necessary, updated the response client to actually use the the ForAgent --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com> * Bump actions/download-artifact from 6 to 7 (#2862) Bumps [actions/download-artifact](https://github.com/actions/download-artifact) from 6 to 7. - [Release notes](https://github.com/actions/download-artifact/releases) - [Commits](https://github.com/actions/download-artifact/compare/v6...v7) --- updated-dependencies: - dependency-name: actions/download-artifact dependency-version: '7' 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> * Bump actions/cache from 4 to 5 (#2861) Bumps [actions/cache](https://github.com/actions/cache) from 4 to 5. - [Release notes](https://github.com/actions/cache/releases) - [Changelog](https://github.com/actions/cache/blob/main/RELEASES.md) - [Commits](https://github.com/actions/cache/compare/v4...v5) --- updated-dependencies: - dependency-name: actions/cache dependency-version: '5' 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> * Bump actions/upload-artifact from 5 to 6 (#2860) Bumps [actions/upload-artifact](https://github.com/actions/upload-artifact) from 5 to 6. - [Release notes](https://github.com/actions/upload-artifact/releases) - [Commits](https://github.com/actions/upload-artifact/compare/v5...v6) --- updated-dependencies: - dependency-name: actions/upload-artifact 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 : Ollama Connector for Agent Framework (#1104) * Initial Commit for Olama Connector * Added Olama Sample * Add Sample & Fixed Open Telemetry * Fixed Spelling from Olama to Ollama * remove"opentelemetry-semantic-conventions-ai ~=0.4.13" since its handled in a different pr * Added Tool Calling * Finalizing test cases * Adjust samples to be more reliable * Update python/packages/ollama/agent_framework_ollama/_chat_client.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update python/packages/ollama/pyproject.toml Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update python/packages/ollama/tests/test_ollama_chat_client.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update python/packages/ollama/agent_framework_ollama/_chat_client.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Improved Docstrings & Sample * Update python/packages/ollama/agent_framework_ollama/_chat_client.py Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com> * Integrate PR Feedback - Divided Streaming and Non-Streaming into independent Methods - Catch Ollama Validation Error - Add OTEL Provider Name - Checked Ollama Messages - Add Usage Statistics * Revert setting, so it can be none * Validate Message formatting between AF and Ollama * Catch Ollama Error and raise a ServiceResponse Error * Fix mypy error * remove .vscode comma * Add Reasoning support & adjust to new structure * Add Ollama Multimodality and Reasoning * Add test cases for reasoning * Add Tests for Error Handling in Ollama Client * Update python/samples/getting_started/multimodal_input/ollama_chat_multimodal.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Integrated Copilot Feedback * Implement first PR Feedback * Adjust Readme files for examples * Adjust argument passing via additional chat options * Implemented PR Feedback * Removing Ollama Package from Core and moving samples * Fix Link & Adding Samples to Main Sample Readme * Fixing Links in Readme * Moved Multimodal and Chat Example * Fixed Link in ChatClient to Ollama * Fix AgentFramework Links in Ollama Project * Fix observability breaking change --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com> * Skip failing IT (#2904) * .NET: Cosmos DB UT Fast Skip (For Non-Configured Local envs) (#2906) * Cosmos DB UT Fast Skip (Non-Configured Local envs) + Long running UT skip in pipeline when no CosmosDB changes happened * Force a CosmosDB source code change to trigger the pipeline * Address possible string boolean mismatch * Add debug * Enabling emulator always when running IT * .NET: Add TTLs to durable agent sessions (#2679) * .NET: Add TTLs to durable agent sessions * Remove unnecessary async * PR feedback: clarify UTC * PR feedback: limit minimum signal delay to <= 5 minutes * PR feedback: Fix TTL disablement * Linter: use auto-property * Fix build break from OpenAI SDK change * Updated CHANGELOG.md * PR feedback * Reduce default TTL to 14 days to work around DTS bug * Python: Update Mem0Provider to use v2 search API `filters` parameter (#2766) * short fix to move id parameters to filters object * added tests * small fix * mem0 dependency update * Updated package versions (#2913) * .NET: Switch to new "Run" method name. (#2843) * Switch to new "RunAgent" method name. * Try to disable false positive naming warning. * Add comment about disabled warnings. * Rename `RunAgent` to just `Run`. * Update CHANGELOG. * Python: Switch to new "run" method name. (#2890) * Switch to `run` method. * Add support for deprecated `run_agent`. * Fix entity method name. * Fix method name and improve tests. * Update comment. * Update Python CHANGELOG. * [BREAKING] Python: Add factory pattern to handoff orchestration builder (#2844) * WIP: Factory pattern to handoff * Add factory pattern to concurrent orchestration builder; Next: tests and sample verification * Add tests and improve comments * Fix mypy * Simplify handoff_simple.py * Simplify handoff_autonoumous.py and bug fix * Update readme * Address Copilot comments * Python: Flow custom kwargs to agents via Workflow SharedState (#2894) * Flow custom kwargs to agents via SharedState * Address Copilot feedback * Improve sample typing * Fix test * Fix Pydantic error when using Literal type for tool params (#2893) * Updated Ollama package version (#2920) * Python: Azure AI Agent with Bing Grounding Citations Sample (#2892) * bing grounding sample with citations * small fix * fix * .NET: Make DelegatingAIAgent abstract (#2797) * Initial plan * Make DelegatingAIAgent abstract Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Added additional arguments for Azure AI agent (#2922) * Python: Correction of MCP image type conversion in _mcp.py (#2901) * Correction of MCP image type conversion in _mcp.py * Added a new overload to the init function of the DataContent() type of the Agent Framework, edited the test case to correctly test the usage of the data and uri fields while using DataContent() * Fixed tests related to the changes of the DataContent type, added testing for both string and byte representations * Pass kwargs into subworkflows (#2923) * Python: Move ollama samples to samples getting started dir (#2921) * Move ollama samples to samples getting started dir * Address feedback * Python: fix: correct BadRequestError when using Pydantic model in response_fo… (#1843) * fix: correct BadRequestError when using Pydantic model in response_format * Fix lint --------- Co-authored-by: Evan Mattson <evan.mattson@microsoft.com> * .NET: [Breaking] Delete display name property (#2758) * delete the AIAgent.DisplayName property * use agent name as a first value for activity display name * Update dotnet/src/Microsoft.Agents.AI.Workflows/Specialized/HandoffAgentExecutor.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Python: cleanup and refactoring of chat clients (#2937) * refactoring and unifying naming schemes of internal methods of chat clients * set tool_choice to auto * fix for mypy * added note on naming and fix #2951 * fix responses * fixes in azure ai agents client * Python: Workflow add option to visualize internal executors (#2917) * Workflow add option to visualize internal executors * Address Copilot comments * Python: Fixes Run ID and Thread ID casing to align with AG-UI Typescript SDK (#2948) * added camelCase input to run id and thread id aligning with @ag-ui/core * fixed per copilot suggestions * Python: Add workflow cancellation sample (#2732) * Add workflow cancellation sample Add sample demonstrating how to cancel a running workflow using asyncio tasks. Shows both cancellation mid-execution and normal completion paths. Useful for implementing timeouts, graceful shutdown, or A2A executors. * update docstring * .NET: Update Anthropic package to version 12.0.0 (#2914) * Initial plan * Update Anthropic package to version 12.0.0 Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com> * Python: Add Azure Managed Redis Support with Credential Provider (#2887) * azure redis support * small fixes * azure managed redis sample * fixes * Bump CommunityToolkit.Aspire.OllamaSharp from 13.0.0-beta.440 to 13.0.0 (#2856) --- updated-dependencies: - dependency-name: CommunityToolkit.Aspire.OllamaSharp dependency-version: 13.0.0 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump AWSSDK.Extensions.Bedrock.MEAI from 4.0.4.11 to 4.0.5 (#2853) --- updated-dependencies: - dependency-name: AWSSDK.Extensions.Bedrock.MEAI dependency-version: 4.0.5 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> * Bump Azure.AI.AgentServer.AgentFramework from 1.0.0-beta.4 to 1.0.0-beta.5 (#2854) --- updated-dependencies: - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * Python: Fix WorkflowAgent event handling and kwargs forwarding (#2946) * Fix kwargs propagation through workflow.as_agent() * Fix WorkflowAgent to respect AgentExecutor output_response setting * .NET: Use GrpcEntityRunner instead of TaskEntityDispatcher (#2759) * Use GrpcEntityRunner instead of TaskEntityDispatcher * Pin to Durable worker 1.11.0 * Set the invocation result * Update all Durable packages * Update changelog, rename dispatcher to encondedEntityRequest * Python: Bump Py version to 1.0.0b251218 for a release. Update CHANGELOG (#2968) * Bump Py version to 1.0.0b251218 for a release. Update CHANGELOG * update lock * Fix formatting * Fix ChatKit typing * Python: Introducing Foundry Local Chat Clients (#2915) * redo foundry local chat client * fix mypy and spelling * better docstring, updated sample * fixed tests and added tests * small sample update * Updated package versions (#2978) * Python: Added GitHub MCP sample with PAT (#2967) * added github mcp sample with PAT * addressed copilot fixes * env fix * Python: Preserve reasoning blocks with OpenRouter (#2950) * Preserve reasoning blocks with OpenRouter * Put encrypted reasoning in TextReasoningContent * Remove unneccessary change * Fix docs * Support streaming * Fix handling None in TextReasoningContent.text * Python: Added response.created and response.in_progress event process to OpenAIBaseResponseClient (#2975) * added response.created and response.in_progress to include response.id * better doc string * added tests for the new streaming event types * Python: Introducing support for Bedrock-hosted models (Anthropic, Cohere, etc.) (#2610) * Pushing the bedrock related changes to the new branch after addressing the review comments * 2524 Addressed the second round review comments * 2524 Addressed few more minor comments on the PR * resolving the merge conflict * 2524 resolved the uv.lock conflicts * 2524 addressed more comments * 2524 removed the print statement to fix the checks failure * 2524 resolved the CI failure issues * 2524 fixing the CI breaks * 2524 Addressed the review comment * 2524 resolved conflict --------- Co-authored-by: Sunil Dutta <sunil.dutta@penske.com> Co-authored-by: budgetboardingai <apurva.sharma31@gmail.com> * .NET: [Durable Agents] Reliable streaming sample (#2942) * .NET: [Durable Agents] Reliable streaming sample * Add automated validation for new sample * Address Copilot PR feedback * Fix typo in README.md about agent definitions (#2634) * Fix typo in README.md about agent definitions * Update agent-samples/README.md Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Python: latency improvements (#3014) * latency improvements * fixed mypy, added coding standards and instructions * slight logic improvement * Python: Updated package versions (#3024) * Updated package versions * Updated changelog * Python: add powerfx safe mode (#3028) * add powerfx safe mode * improved docstring and aligned env_file loading * ensured test uses reset * .NET: [Breaking] Introduce RunCoreAsync/RunCoreStreamingAsync delegation pattern in AIAgent (#2749) * Initial plan * Refactor AIAgent: Make RunAsync and RunStreamingAsync non-abstract, add RunCoreAsync and RunCoreStreamingAsync Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Fix infinite recursion in test implementations Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Make RunAsync and RunStreamingAsync non-virtual as requested Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Fix DelegatingAIAgent subclasses to use RunCoreAsync/RunCoreStreamingAsync Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Fix XML documentation references in AnonymousDelegatingAIAgent Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Restore <see cref> tags with proper qualified signatures in AnonymousDelegatingAIAgent Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Rollback unnecessary XML documentation changes in AnonymousDelegatingAIAgent Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Remove pragma and update crefs to RunCoreAsync/RunCoreStreamingAsync Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Fix EntityAgentWrapper to call base.RunCoreAsync/RunCoreStreamingAsync Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * fix compilation issues * fix compilatio issue * fix tests * fix unit tests * fix unit test --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> Co-authored-by: SergeyMenshykh <sergemenshikh@gmail.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * add issue template and additional labeling (#3006) * fix and extra int test (#3037) * .NET: [BREAKING] Refactor ChatMessageStore methods to be similar to AIContextProvider and add filtering support (#2604) * Refactor ChatMessageStore methods to be similar to AIContextProvider * Fix file encoding * Ensure that AIContextProvider messages area also persisted. * Update formatting and seal context classes * Improve formatting * Remove optional messages from constructor and add unit test * Add ChatMessageStore filtering via a decorator * Update sample and cosmos message store to store AIContextProvider messages in right order. Fix unit tests. * Update Workflowmessage store to use aicontext provider messages. * Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Apply suggestions from code review Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Improve xml docs messaging * Address code review comments. * Also notify message store on failure --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * [BREAKING] Remove unused AgentThreadMetadata (#3067) * Remove unused AgentThreadMetadata * Update DurableTask Changelog * Python: Fix AzureAIClient failure when conversation history contains assistant messages (#3076) * Fix AzureAIClient failure when conversation history contains assistant messages * Address PR review feedback: improve docstring and test assertions * Remove redundant cast * Fix: Update OTLP exporter protocol conditions (#3070) * Python: Fix ExecutorInvokedEvent and ExecutorCompletedEvent observability data (#3090) * Fix ExecutorInvokedEvent.data mutation bug * Fix bug related to not yielding output type * .NET: Seal ChatClientAgentThread (#2842) * Initial plan * Seal ChatClientAgentThread class Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Fix broken strands urls. (#3102) * Fix broken strands urls. * Fix typos * .NET: Fix message ordering inconsistency when using AIContextProvider (#2659) * Initial plan * Fix message ordering inconsistency when using AIContextProvider Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> * Revert to original message ordering: Input, AIContextProvider, Response Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> * Reorder messages to ChatClient to match MessageStore order: Existing, Input, AIContextProvider Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> * Remove redundant test methods as existing tests already verify the behavior Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * fix: tool_choice parameter not being honored when passed to agent.run() (#3095) * sharepoint sample fix (#3108) * Bump versions to 1.0.0b260106 for a release. Update CHANGELOG.md (#3109) * Bump Bedrock version to latest (#3110) * Python: Fix MCP tool result serialization for list[TextContent] (#2523) * Fix MCP tool result serialization for list[TextContent] When MCP tools return results containing list[TextContent], they were incorrectly serialized to object repr strings like: '[<agent_framework._types.TextContent object at 0x...>]' This fix properly extracts text content from list items by: 1. Checking if items have a 'text' attribute (TextContent) 2. Using model_dump() for items that support it 3. Falling back to str() for other types 4. Joining single items as plain text, multiple items as JSON array Fixes #2509 * Address PR review feedback for MCP tool result serialization - Extract serialize_content_result() to shared _utils.py - Fix logic: use texts[0] instead of join for single item - Add type annotation: texts: list[str] = [] - Return empty string for empty list instead of '[]' - Move import json to file top level - Add comprehensive unit tests for serialization * Address PR review feedback: fix type checking and double serialization - Add isinstance(item.text, str) check to ensure text attribute is a string - Fix double-serialization issue by keeping model_dump results as dicts until final json.dumps (removes escaped JSON strings in arrays) - Improve docstring with detailed return value documentation - Add test for non-string text attribute handling - Add tests for list type tool results in _events.py path * Simplify PR: minimal changes to fix MCP tool result serialization Addresses reviewer feedback about excessive refactoring: - Reset _events.py to original structure - Only add import and use serialize_content_result in one location - All review comments addressed in serialize_content_result(): - Added isinstance(item.text, str) check - Use model_dump(mode="json") to avoid double-serialization - Improved docstring with explicit return value documentation - Empty list returns "" instead of "[]" * Refactor: Move MCP TextContent serialization to core prepare_function_call_results Per reviewer feedback, moved the TextContent serialization logic from ag-ui's serialize_content_result to the core package's prepare_function_call_results function. Changes: - Added handling for objects with 'text' attribute (like MCP TextContent) in _prepare_function_call_results_as_dumpable - Removed serialize_content_result from ag-ui/_utils.py - Updated _events.py and _message_adapters.py to use prepare_function_call_results from core package - Updated tests to match the core function's behavior * Fix failing tests for prepare_function_call_results behavior - test_tool_result_with_none: Update expected value to 'null' (JSON serialization of None) - test_tool_result_with_model_dump_objects: Use Pydantic BaseModel instead of plain class * Fix B903 linter error: Convert MockTextContent to dataclass The ruff linter was reporting B903 (class could be dataclass or namedtuple) for the MockTextContent test helper classes. This commit converts them to dataclasses to satisfy the linter check. * Python: Improve DevUI, add Context Inspector view as new tab under traces (#2742) * Improve DevUI, add Context Inspector view as new tab under traces * fix mypy errors * fix: Handle stale MCP connections in DevUI executor MCP tools can become stale when HTTP streaming responses end - the underlying stdio streams close but `is_connected` remains True. This causes subsequent requests to fail with `ClosedResourceError`. Add `_ensure_mcp_connections()` to detect and reconnect stale MCP tools before agent execution. This is a workaround for an upstream Agent Framework issue where connection state isn't properly tracked. Fixes MCP tools failing on second HTTP request in DevUI. fixes #1476 #1515 #2865 * fix #1572 report import dependency errors more clearly * Ensure there is streaming toggle where users can select streaming vs non streaming mode in devui . Fixes .NET: [Python] DevUI tool call rendering in non-streaming mode? * remove unused dead code * improve ux - workflows with agents show a chat component in execution timelien, also ensure magentic final output shows correctly * update ui build * update devui to use instrumentation instead of tracing, other instrumentation and type/instance check fixes * .NET: Seal factory contexts and add non JSO deserialize overloads (#3066) * Seal factory contexts and add non JSO deserialize overloads * Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Enable blank issues in issue template configuration Need to re-enable creating blank issues * updated templates (#3106) * updated templates * enabled blank and fixed triage * made language optional and moved to the bottom for features * Python: Streaming sample for azurefunctions (#3057) * Streaming sample for azurefunctions * Fixed links and sample name * Addressed feedback * Addressed feedback * Fixed integration tests * Updated test * Python: fix(azure-ai): Fix response_format handling for structured outputs (#3114) * fix(azure-ai): read response_format from chat_options instead of run_options * refactor: use explicit None checks for response_format * Fix mypy error * Mypy fix * Python: Bump python version to 1.0.0b260107 for a release (#3128) * Bump python version to 1.0.0b260107 for a release * Update changelog * Make A2AAgent public, so that it's concrete implementation methods can be used. (#3119) * .NET: Map additional props <-> A2A metadata (#3137) * map additional props from agent run options to a2a request metadata * small touches * add unit tests for new extension methods * Sort using * add unit test * add additiona unit tests * special case json element to avoid unnecessary serialization * Python: Fix Anthropic streaming response bugs (#3141) * test commit identity * fix(anthropic): fix raw_representation and finish_reason in streaming * lint fix * Bump AWSSDK.Extensions.Bedrock.MEAI from 4.0.5 to 4.0.5.1 (#2994) --- updated-dependencies: - dependency-name: AWSSDK.Extensions.Bedrock.MEAI dependency-version: 4.0.5.1 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * Bump Anthropic from 12.0.0 to 12.0.1 (#2993) --- updated-dependencies: - dependency-name: Anthropic dependency-version: 12.0.1 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * .NET: [Breaking] Prevent loss of input messages & streamed updates when resuming streaming (#2748) * save input messages and stream updates to the continuation token to be able to use them in the last successful stream resumption call. * Update dotnet/src/Microsoft.Agents.AI/ChatClient/ChatClientAgentContinuationToken.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update dotnet/src/Microsoft.Agents.AI/ChatClient/ChatClientAgentContinuationToken.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update dotnet/tests/Microsoft.Agents.AI.UnitTests/ChatClient/ChatClientAgent_BackgroundResponsesTests.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update dotnet/src/Microsoft.Agents.AI/ChatClient/ChatClientAgentContinuationToken.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update dotnet/src/Microsoft.Agents.AI/ChatClient/ChatClientAgentContinuationToken.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * fix typo * init continuation token from chat response * remove unnecessary types for source generation * remove check for continuation token passed at initial run * remove check for continuation token pass at initial run * centralize continuation token parsing * update xml comments * use readonly collection instead of enumerable --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * .NET: fix: Expose WorkflowErrorEvent as ErrorContent (#2762) * fix: Expose WorkflowErrorEvent as ErrorContent When hosted using .AsAgent(), Workflows were not exposing inner errors coming as Exceptions (through the WorkflowErrorEvent) The fix is to convert their message to an ErrorContent on the way out, rather than rely on the default "empty update" to collect the raw event. * feat: Add a way to show/suppress exception information * Bump Microsoft.Agents.AI.Workflows from 1.0.0-preview.251125.1 to 1.0.0-preview.251219.1 (#2997) --- updated-dependencies: - dependency-name: Microsoft.Agents.AI.Workflows dependency-version: 1.0.0-preview.251219.1 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * .NET: Add Run overloads to expose ChatClientAgentRunOptions in IntelliSense (#3115) * Initial plan * Add ChatClientAgentExtensions for improved discoverability of ChatClientAgentRunOptions Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> * Address code review feedback - use collection expression syntax Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> * Apply suggestion from @westey-m * Fix issues with Copilot implementation * Add additional tests for structured output overloads. --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> * Python: Add tool call/result content types and update connectors and samples (#2971) * Add new AI content types and image tool support Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Add Python content types for tool calls/results and image generation tool support Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Address review feedback for tool content and samples Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Tighten image generation typing and sample tools list Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Align image generation output typing Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Handle MCP naming, image options mapping, and connector tool content Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Allow MCP call in function approval request Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Remove raw image_generation tool remapping Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Restore Anthropic tool_use to function calls unless code execution Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Fix lint issues for hosted file docstring and MCP parsing Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Import ChatResponse types in Anthropic client Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Fix Anthropics citation type imports and MCP typing for handoff/tools Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Skip lightning tests without agentlightning and fix function call import Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * fix lint on lab package * rebuilt anthropic parsing * redid anthropic parsing * typo * updated parsing and added missing docstrings * fix tests * mypy fixes * second mypy fix * add new class to other samples --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> Co-authored-by: eavanvalkenburg <github@vanvalkenburg.eu> * Bump Google.GenAI from 0.6.0 to 0.9.0 (#2995) --- updated-dependencies: - dependency-name: Google.GenAI dependency-version: 0.9.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * Bump js-yaml from 4.1.0 to 4.1.1 in /python/packages/devui/frontend (#3123) Bumps [js-yaml](https://github.com/nodeca/js-yaml) from 4.1.0 to 4.1.1. - [Changelog](https://github.com/nodeca/js-yaml/blob/master/CHANGELOG.md) - [Commits](https://github.com/nodeca/js-yaml/compare/4.1.0...4.1.1) --- updated-dependencies: - dependency-name: js-yaml dependency-version: 4.1.1 dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Updated package versions (#3144) * .NET: Bump Microsoft.Agents.AI.OpenAI and Microsoft.Extensions.AI.OpenAI (#2996) * Bump Microsoft.Agents.AI.OpenAI and Microsoft.Extensions.AI.OpenAI Bumps Microsoft.Agents.AI.OpenAI from 1.0.0-preview.251125.1 to 1.0.0-preview.251219.1 Bumps Microsoft.Extensions.AI.OpenAI from 10.1.0-preview.1.25608.1 to 10.1.1-preview.1.25612.2 --- updated-dependencies: - dependency-name: Microsoft.Agents.AI.OpenAI dependency-version: 1.0.0-preview.251219.1 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Microsoft.Extensions.AI.OpenAI dependency-version: 10.1.1-preview.1.25612.2 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Microsoft.Agents.AI.OpenAI dependency-version: 1.0.0-preview.251219.1 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Microsoft.Extensions.AI.OpenAI dependency-version: 10.1.1-preview.1.25612.2 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * Fixed samples --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> Co-authored-by: Dmytro Struk <13853051+dmytrostruk@users.noreply.github.com> * Python: fix(ag-ui): Execute tools with approval_mode, fix shared state, code cleanup (#3079) * fix(ag-ui): execute tools after approval in human-in-the-loop flow * Fix shared state bug * Bug fix finalized * Refactoring to clean up code * Code cleanup * More fixes * More code cleanup * Add version detection in __init__.py to ruff ignore list * Track agent name with updates for workflow agent (#3146) * Python: Fix AzureAIClient tool call bug for AG-UI use (#3148) * Fiz AzureAIClient tool call bug * Address copilot feedback * Python: multiple bug fixes (#3150) * fix Python: kwargs are not passed to _prepare_thread_and_messages in ChatAgent.run Fixes #3118 * fix Python: [Bug]: model_id versus model_deployment_name is confusing in Azure AI Agents Fixes #3147 * add types * fixed type and docstring * fix(anthropic): fix duplicate ToolCallStartEvent in streaming tool calls (#3051) When processing `input_json_delta` events, the Anthropic client was passing the tool name from the previous `tool_use` event. This caused ag-ui's `_handle_function_call_content` to emit a `ToolCallStartEvent` for every streaming chunk (since it triggers on `if content.name:`). This fix changes the behavior to pass an empty string for `name` in `input_json_delta` events, matching OpenAI's behavior where streaming argument chunks have `name=""`. The initial `tool_use` event still provides the tool name, so only one `ToolCallStartEvent` is emitted. Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com> * .NET: [BREAKING] Change GetNewThread and DeserializeThread to async (#3152) * Change GetNewThread and DeserializeThread plus ChatMessageStore and AIContextProvider Factories to async * Merge fixes * Fix Ollama model env var in documentation (#3156) Signed-off-by: Dina Suehiro Jones <dina.s.jones@intel.com> * Python: Add Pydantic request model and OpenAPI tags support to AG-UI FastAPI endpoint (#2522) * feat(ag-ui): Add Pydantic request model and OpenAPI tags support - Add AGUIRequest Pydantic model in _types.py with field descriptions - Update add_agent_framework_fastapi_endpoint() to accept tags parameter - Use AGUIRequest model for automatic validation and OpenAPI schema generation - Export AGUIRequest and DEFAULT_TAGS in __init__.py - Update test_endpoint.py to expect 422 for invalid requests - Add tests for OpenAPI schema, default tags, custom tags, and validation Benefits: - Better API documentation with complete request schema in Swagger UI - Automatic request validation with Pydantic - Organized endpoints under 'AG-UI' tag instead of 'default' - Improved developer experience and type safety Fixes #<issue-number> * test(ag-ui): Add test for internal error handling to achieve 100% coverage - Add test_endpoint_internal_error_handling() to cover exception handling code - Mock copy.deepcopy to simulate internal error during default_state processing - Add type: ignore for FastAPI tags parameter (known pyright compatibility issue) - Achieves 100% test coverage for _endpoint.py (previously missing lines 103-105) * .NET: Improve resolving `AITool` from DI (#3175) * remove localagenttoolregistry * also give the factory method API * Python: Fix MCPStreamableHTTPTool to use new streamable_http_client API (#3088) * Fix MCPStreamableHTTPTool to use new streamable_http_client API with proper httpx client cleanup Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Update docstring to reflect new streamable_http_client API usage Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Refactor MCPStreamableHTTPTool to accept optional http_client parameter and delegate client creation to streamable_http_client Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Update mcp package minimum version to 1.24.0 for streamable_http_client API support Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Fix critical bugs: apply headers/timeout/sse_read_timeout when creating httpx client, add version constraint <2, and properly manage client lifecycle Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Simplify implementation: remove headers/timeout/sse_read_timeout params, remove kwargs, remove close() override per feedback Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Add back **kwargs parameter for backward compatibility (accepted but not used) Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Remove unused httpx import from test file Note: The uv.lock file needs to be updated with 'uv sync' to reflect the mcp version constraint change (>=1.24.0,<2) Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * cicd fixes * udpated samples with headers examples --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> Co-authored-by: eavanvalkenburg <github@vanvalkenburg.eu> * azureai direct a2a endpoint support (#3127) * Python: [BREAKING]: removed display_name, renamed context_providers, middleware and AggregateContextProvider (#3139) * removed display_name, renamed context_providers, middleware and AggregateContextProvider * fixes * fixed test * testfix * removed mistakenly put back test * updated new test * rename middlewares to middleware * middleware fixes * Python: MCP Improvements: improved connection loss behavior, pagination for loading and a param to control representation (#3154) * pagination support (#2848) added a parse_tool_result param and connection loss (#2884) * fix #3153 * improved connection handling * improved logic * Python: Add declarative workflow runtime (#2815) * Further support for declarative python workflows * Add tests. Clean up for typing and formatting * Improvements and cleanup * Typing cleanup. Improve docstrings * Proper code in docstrings * Fix malformed code-block directive in docstring * Remove dead links * PR feedback * Address PR feedback * Address PR feedback * Remove sl * Update devui frontend * More cleanup * Fix uv lock * Skip Py 3.14 tests as powerfx doesn't support it * Fix mypy error * Fix for tool calls * Removed stale docstring * Fix lint * Standardize on .NET namespaces. Revert DevUI changes (bring in later) * Implement remaining items for Python declarative support to match dotnet * point URL to agent, not to agentcard (#3176) * Python: [BREAKING]: Introducing Options as TypedDict and Generic (#3140) * WIP typeddict for options * updated all clients and ChatAgents * updated everything * added ADR * fix mypy * proper typevar imports * fixed import * fixed other imports * slight update in the sample * updated from feedback * fixes * fixed missing covariants and test fixes * fixed typing * updated anthropic thinking config * ruff fixes * fixed int tests * fix tests and mypy * updated integration tests * updated docstring and test fix * improved options handling in obser * mypy fix * updated a host of integration tests * fix tests * bedrock fix * [BREAKING] Python: Refactor orchestrations (#3023) * Group chat refactoring Part 1; Next: HIL and handoff * Add agent approval flow; next samples * WIP: samples * WIP: HIL samples * Group chat HIL working; next: handoff * Fix group chat tool approval sample * WIP: refactor handoff; next handoff handling * Handoff done; next handoff samples and concurrent and sequential * Handoff samples, concurrent, and sequential done; next Magentic * WIP: magentic; next test with samples + HIL * Magentic Working; next fix all samples and tests * Fix handoff samples; next tests * WIP: fixing tests; some orchestration as agent samples are failing * Group chat unit tests done * Handoff unit tests done * Remove old orchestration_request_info and fix related tests * Magentic unit tests done * Fix samples * Fix test * Fix test 2 * mypy * Address comments * Update readme * Address comments * Address comments 2 * Replace display name * Python: ADR for create/get agent API (#2618) * ADR for create/get agent API * Updated ADR with implementation options * Small updates * Updated decision outcome section * Updated broken links * Small updates * Fixed merge conflicts * Small fix * Updated decision outcome section * Small fixes * Updated provider naming based on client SDK * Add ignored parameter for CodeQL in workflow (#3204) * Implement IReadOnlyList on InMemoryChatMessageStore (#3205) * .NET: Make ChatMessageStore and AIContextProvider context props settable (#3196) * Make ChatMessageStore and AIContextProvider context props setable * Add validation to preserve non-null requirement of certain properties. * Fix broken tests. * Python: Add dependencies param to ag-ui FastAPI endpoint (#3191) * Add dependencies param to ag-ui FastAPI endpoint * Address Copilot feedback * renamed all (#3207) * Python: ADR for simplified get response (#3098) * ADR for simplified get response * updated some language, added agent option and code comparison * small update in sample * added workflows and expanded some points * changed decision and number * updated with stream=False default * .NET: [Breaking] Rename`AgentRunResponse` and `AgentRunResponseUpdate` classes (#3197) * rename AgentRunResponse and AgentRunResponseUpdate classes - part1 * rename varialbles, parameters, methods and tests * rollback unnecessary changes * .NET: [Breaking] Rename AgentRunResponseEvent and AgentRunUpdateEvent classes (#3214) * rename AgentRunResponseEvent and AgentRunUpdateEvent classes * rollback unnecessary changes * Python: Create/Get Agent API for Azure V2 (#3059) * Added get_agent method to Azure AI V2 * Small fixes * Small fix * Removed AzureAIAgentProvider * Added create_agent method * Small fixes * Fixed code interpreter tool mapping * Added agent provider for V2 client * Updated response format handling * Added provider example * Fixed errors * Update python/samples/getting_started/agents/azure_ai/README.md Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Small fix * Updates from merge * Resolved comments * Resolved comments --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Python: Add more specific exceptions to Workflow (#3188) * Add more specifc workflow exceptions * Fix tests * AI comments * Misc * Python: Added AzureAI sample for downloading code interpreter generated files (#3189) * added azure ai code interpreter file download sample * copilot fix suggestions * function name fixes + readme update * small fix * update package versions (#3223) Co-authored-by: Dmytro Struk <13853051+dmytrostruk@users.noreply.github.com> * Python: fix(core): correct FunctionResultContent ordering in WorkflowAgent.merge_updates (#3168) * fix(core): simplify FunctionResultContent ordering in WorkflowAgent.merge_updates * improve comment * Fix name * fix(workflows): rename WorkflowOutputEvent.source_executor_id to executor_id for API consistency (#3166) * Python: fix(ag-ui): add MCP tool support for AG-UI approval flows (#3212) * add MCP tool support for AG-UI approval flows * use attribute in place of property * Python: Properly configure structured outputs based on new options dict (#3213) * Properly configure structured outputs based on new options dict * Fix mypy * .NET: Merge AgentRunOptions.AdditionalProperties into ChatOptions.AdditionalProperties (#3184) * Merge AgentRunOptions.AdditionalProperties into ChatOptions.AdditionalProperties * Fix namespace and typo. * .NET: Update Google.GenAI to 0.11.0 and remove polyfill implementations (#3232) * Initial plan * Update Google.GenAI to 0.11.0 and remove polyfill files Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> * .NET: [BREAKING] Renamed CreateAIAgent/GetAIAgent to AsAIAgent (#3222) * Renamed chat client extension method * Additional renaming * Updated documentation * Fixed tests * Small fix * Small fix * Updated DurableAIAgent and fixed integration tests (#3241) * Python: Create/Get Agent API for Azure V1 (#3192) * Added provider implementation for Azure AI V1 * Small fixes * Fixed OpenAPI example * Fixed local MCP example * Fixed hosted MCP example * Fixed file search sample * Small fixes * Resolved comments * Doc updates * Bump azure-core from 1.37.0 to 1.38.0 in /python (#3209) Bumps [azure-core](https://github.com/Azure/azure-sdk-for-python) from 1.37.0 to 1.38.0. - [Release notes](https://github.com/Azure/azure-sdk-for-python/releases) - [Commits](https://github.com/Azure/azure-sdk-for-python/compare/azure-core_1.37.0...azure-core_1.38.0) --- updated-dependencies: - dependency-name: azure-core dependency-version: 1.38.0 dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Python: Create/Get Agent API for OpenAI Assistants (#3208) * Added provider implementation * Added example with response format * Small improvements * Python: (AG-UI) Support service-managed thread on AG-UI (#3136) * added service thread support * set service_thread_id to only supplied_thread_id * uses raw_representation to extract the conversation_id * removed accidental edit * updated test to use raw_representation * resolves copilot review feedback * revert back StubAgent, since not used * removed relative module import * removed hasattr check per PR feedback * Create/Get Agent API - fixes and example improvements (#3246) * .NET Purview Middleware: Improve Background Job Runner Injection (#3256) * Clean up background job dependency injection * Fix xml documentation grammar * Python: [BREAKING] Renamed create_agent to as_agent (#3249) * Renamed create_agent to as_agent * Override for as_agent * Added override * Python: Update package version (#3258) * package version 260116 * removed name tags * Python: Fixed Azure chat client for asynchronous filtering (#3260) * Fixed Azure chat client for asynchronous filtering * Updated test * Python: Fixed use_agent_middleware calling private _normalize_messages (#3264) * Fix use_agent_middleware calling private _normalize_messages * Fixed A2A and Copilot Studio agent * Python: Added rai_config to Azure AI agent creation (#3265) * Add kwargs to create_agent method * Added test for kwargs * Addressed comment * Added doc string * Python: Filter conversation_id when passing kwargs to agent as tool (#3266) * Filter conversation_id when passing kwargs to agent as tool * Small fix * Update python/samples/getting_started/agents/azure_ai/README.md Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update python/samples/getting_started/agents/openai/openai_responses_client_with_agent_as_tool.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update python/samples/getting_started/agents/azure_ai/azure_ai_with_agent_as_tool.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Bump actions/setup-dotnet from 5.0.1 to 5.1.0 (#3273) Bumps [actions/setup-dotnet](https://github.com/actions/setup-dotnet) from 5.0.1 to 5.1.0. - [Release notes](https://github.com/actions/setup-dotnet/releases) - [Commits](https://github.com/actions/setup-dotnet/compare/v5.0.1...v5.1.0) --- updated-dependencies: - dependency-name: actions/setup-dotnet dependency-version: 5.1.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Update ignored checks in merge-gatekeeper workflow * Python: [BREAKING] Make response_format validation errors visible to users (#3274) * Make response_format validation errors visible to users * Small fix * Addressed comments * Python: fix(declarative): Fix MCP tool connection not passed from YAML to Azure AI agent creation API (#3248) * fix(declarative): Fix MCP tool connection not passed from YAML * Add samples to README * Fix mypy * Fix mypy again * Address PR comments * fix #3171, ensure proper form rendering for int (#3201) * Bump uv from 0.9.25 to 0.9.26 in /python (#3288) Bumps [uv](https://github.com/astral-sh/uv) from 0.9.25 to 0.9.26. - [Release notes](https://github.com/astral-sh/uv/releases) - [Changelog](https://github.com/astral-sh/uv/blob/main/CHANGELOG.md) - [Commits](https://github.com/astral-sh/uv/compare/0.9.25...0.9.26) --- updated-dependencies: - dependency-name: uv dependency-version: 0.9.26 dependency-type: direct:development update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump ruff from 0.14.11 to 0.14.13 in /python (#3287) Bumps [ruff](https://github.com/astral-sh/ruff) from 0.14.11 to 0.14.13. - [Release notes](https://github.com/astral-sh/ruff/releases) - [Changelog](https://github.com/astral-sh/ruff/blob/main/CHANGELOG.md) - [Commits](https://github.com/astral-sh/ruff/compare/0.14.11...0.14.13) --- updated-dependencies: - dependency-name: ruff dependency-version: 0.14.13 dependency-type: direct:development update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump tar from 7.4.3 to 7.5.3 in /python/packages/devui/frontend (#3267) Bumps [tar](https://github.com/isaacs/node-tar) from 7.4.3 to 7.5.3. - [Release notes](https://github.com/isaacs/node-tar/releases) - [Changelog](https://github.com/isaacs/node-tar/blob/main/CHANGELOG.md) - [Commits](https://github.com/isaacs/node-tar/compare/v7.4.3...v7.5.3) --- updated-dependencies: - dependency-name: tar dependency-version: 7.5.3 dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * .NET: Delete sync extension methods for agent (#3291) * Delete sync extension methods for agent * Fix comments and obsolete attribute * Remove more sync methods. * Fix naming and comments. * Fix unit tests * Python: Fix: Add system_instructions to ChatClient LLM span tracing (#3164) * Fix: Add system_instructions to ChatClient LLM span tracing - Add system_instructions parameter to _capture_messages() calls in _trace_get_response() and _trace_get_streaming_response() - Extract instructions from chat_options in kwargs - Add unit tests to verify system_instructions are captured correctly When using ChatClient with ChatOptions.instructions, the OpenTelemetry LLM span was missing system messages in gen_ai.input.messages and the gen_ai.system_instructions attribute was not being set. This fix aligns the ChatClient-level tracing with the Agent-level tracing which already correctly passes system_instructions. Fixes #3163 Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * Add edge case tests for system_instructions - Add test for empty string instructions (should not set attribute) - Add test for list-type instructions (verify multiple items captured) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * Simplify: use options.get('instructions') directly instead of kwargs.get('chat_options') Addresses reviewer feedback: - Removed unnecessary chat_options variable from kwargs - Directly access instructions from the options parameter - Updated tests to use dict syntax for options (TypedDict convention) --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com> * Improve PR number handling in workflow (#3302) * Improve PR number handling in workflow Refine PR number extraction and validation method. * Update .github/workflows/python-test-coverage-report.yml Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Fix error message for invalid PR number --------- Co-authored-by: Copilot <175728472+Copilot@… * Modify failures * Fix mypy errors * Address comments * Update durabletask version * Remove event loops * Add comment * Fix typing for apps --------- Signed-off-by: dependabot[bot] <support@github.com> Signed-off-by: Dina Suehiro Jones <dina.s.jones@intel.com> Co-authored-by: Tao Chen <taochen@microsoft.com> Co-authored-by: Kurt <65111699+q33566@users.noreply.github.com> Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> Co-authored-by: Korolev Dmitry <deagle.gross@gmail.com> Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com> Co-authored-by: Dmytro Struk <13853051+dmytrostruk@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> Co-authored-by: Jose Luis Latorre Millas <joslat@gmail.com> Co-authored-by: Jacob Alber <jaalber@microsoft.com> Co-authored-by: Richard Ortega <richardjortega@gmail.com> Co-authored-by: 刘邦学AI <lbbniu@gmail.com> Co-authored-by: Stephen Toub <stoub@microsoft.com> Co-authored-by: Nico Möller <nkm-moeller@mail.de> Co-authored-by: Chris Gillum <cgillum@microsoft.com> Co-authored-by: Giles Odigwe <79032838+giles17@users.noreply.github.com> Co-authored-by: Phillip Hoff <phillip.hoff@gmail.com> Co-authored-by: Ege Ozan Özyedek <36128615+egeozanozyedek@users.noreply.github.com> Co-authored-by: samueljohnsiby <66901393+samueljohnsiby@users.noreply.github.com> Co-authored-by: Evan Mattson <evan.mattson@microsoft.com> Co-authored-by: Hao Luo <338265+howlowck@users.noreply.github.com> Co-authored-by: Victor Dibia <chuvidi2003@gmail.com> Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com> Co-authored-by: Jacob Viau <javia@microsoft.com> Co-authored-by: SuperKenVery <39673849+SuperKenVery@users.noreply.github.com> Co-authored-by: Sunil Dutta <dutta.2003@gmail.com> Co-authored-by: Sunil Dutta <sunil.dutta@penske.com> Co-authored-by: budgetboardingai <apurva.sharma31@gmail.com> Co-authored-by: Syrine Chelly <62653967+SyChell@users.noreply.github.com> Co-authored-by: SergeyMenshykh <sergemenshikh@gmail.com> Co-authored-by: westey <164392973+westey-m@users.noreply.github.com> Co-authored-by: takanori-terai <123897708+takanori-terai@users.noreply.github.com> Co-authored-by: claude89757 <138977524+claude89757@users.noreply.github.com> Co-authored-by: Gavin Aguiar <80794152+gavin-aguiar@users.noreply.github.com> Co-authored-by: Sukeesh <vsukeeshbabu@gmail.com> Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> Co-authored-by: eavanvalkenburg <github@vanvalkenburg.eu> Co-authored-by: Ao Chen <chenao3220@gmail.com> Co-authored-by: Dina Suehiro Jones <dina.s.jones@intel.com> Co-authored-by: eoindoherty1 <eoindoherty@microsoft.com> Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com> Co-authored-by: Darren Cohen <39422044+dargilco@users.noreply.github.com> Co-authored-by: Ben Thomas <ben.thomas@microsoft.com> Co-authored-by: alliscode <bentho@microsoft.com> Co-authored-by: TaoChenOSU <12570346+TaoChenOSU@users.noreply.github.com> Co-authored-by: Shyju Krishnankutty <connectshyju@gmail.com>
2026-06-16 21:04:09 +08:00 · 2026-01-27 13:08:05 -08:00
parent c860385a8c
commit 787becfc9f
96 changed files with 11536 additions and 3032 deletions
@@ -3,8 +3,6 @@
 import importlib.metadata

 from ._app import AgentFunctionApp
-from ._callbacks import AgentCallbackContext, AgentResponseCallbackProtocol
-from ._orchestration import DurableAIAgent

 try:
    __version__ = importlib.metadata.version(__name__)
@@ -12,9 +10,6 @@ except importlib.metadata.PackageNotFoundError:
    __version__ = "0.0.0"  # Fallback for development mode

 __all__ = [
-    "AgentCallbackContext",
    "AgentFunctionApp",
-    "AgentResponseCallbackProtocol",
-    "DurableAIAgent",
    "__version__",
 ]
@@ -8,16 +8,16 @@ with Azure Durable Entities, enabling stateful and durable AI agent execution.

 import json
 import re
+import uuid
 from collections.abc import Callable, Mapping
 from dataclasses import dataclass
+from datetime import datetime, timezone
 from typing import TYPE_CHECKING, Any, TypeVar, cast

 import azure.durable_functions as df
 import azure.functions as func
 from agent_framework import AgentProtocol, get_logger
-
-from ._callbacks import AgentResponseCallbackProtocol
-from ._constants import (
+from agent_framework_durabletask import (
    DEFAULT_MAX_POLL_RETRIES,
    DEFAULT_POLL_INTERVAL_SECONDS,
    MIMETYPE_APPLICATION_JSON,
@@ -28,12 +28,17 @@ from ._constants import (
    THREAD_ID_HEADER,
    WAIT_FOR_RESPONSE_FIELD,
    WAIT_FOR_RESPONSE_HEADER,
+    AgentResponseCallbackProtocol,
+    AgentSessionId,
+    ApiResponseFields,
+    DurableAgentState,
+    DurableAIAgent,
+    RunRequest,
 )
-from ._durable_agent_state import DurableAgentState
+
 from ._entities import create_agent_entity
 from ._errors import IncomingRequestError
-from ._models import AgentSessionId, RunRequest
-from ._orchestration import AgentOrchestrationContextType, DurableAIAgent
+from ._orchestration import AgentOrchestrationContextType, AgentTask, AzureFunctionsAgentExecutor

 logger = get_logger("agent_framework.azurefunctions")

@@ -294,7 +299,7 @@ class AgentFunctionApp(DFAppBase):
        self,
        context: AgentOrchestrationContextType,
        agent_name: str,
-    ) -> DurableAIAgent:
+    ) -> DurableAIAgent[AgentTask]:
        """Return a DurableAIAgent proxy for a registered agent.

        Args:
@@ -305,14 +310,15 @@ class AgentFunctionApp(DFAppBase):
            ValueError: If the requested agent has not been registered.

        Returns:
-            DurableAIAgent wrapper bound to the orchestration context.
+            DurableAIAgent[AgentTask] wrapper bound to the orchestration context.
        """
        normalized_name = str(agent_name)

        if normalized_name not in self._agent_metadata:
            raise ValueError(f"Agent '{normalized_name}' is not registered with this app.")

-        return DurableAIAgent(context, normalized_name)
+        executor = AzureFunctionsAgentExecutor(context)
+        return DurableAIAgent(executor, normalized_name)

    def _setup_agent_functions(
        self,
@@ -375,8 +381,6 @@ class AgentFunctionApp(DFAppBase):
                "enable_tool_calls": true|false (optional, default: true)
            }
            """
-            logger.debug(f"[HTTP Trigger] Received request on route: /api/agents/{agent_name}/run")
-
            request_response_format: str = REQUEST_RESPONSE_FORMAT_JSON
            thread_id: str | None = None

@@ -385,9 +389,9 @@ class AgentFunctionApp(DFAppBase):
                thread_id = self._resolve_thread_id(req=req, req_body=req_body)
                wait_for_response = self._should_wait_for_response(req=req, req_body=req_body)

-                logger.debug(f"[HTTP Trigger] Message: {message}")
-                logger.debug(f"[HTTP Trigger] Thread ID: {thread_id}")
-                logger.debug(f"[HTTP Trigger] wait_for_response: {wait_for_response}")
+                logger.debug(
+                    f"[HTTP Trigger] Message: {message}, Thread ID: {thread_id}, wait_for_response: {wait_for_response}"
+                )

                if not message:
                    logger.warning("[HTTP Trigger] Request rejected: Missing message")
@@ -401,15 +405,18 @@ class AgentFunctionApp(DFAppBase):
                session_id = self._create_session_id(agent_name, thread_id)
                correlation_id = self._generate_unique_id()

-                logger.debug(f"[HTTP Trigger] Using session ID: {session_id}")
-                logger.debug(f"[HTTP Trigger] Generated correlation ID: {correlation_id}")
-                logger.debug("[HTTP Trigger] Calling entity to run agent...")
+                logger.debug(
+                    f"[HTTP Trigger] Calling entity to run agent using session ID: {session_id} "
+                    f"and correlation ID: {correlation_id}"
+                )

-                entity_instance_id = session_id.to_entity_id()
+                entity_instance_id = df.EntityId(
+                    name=session_id.entity_name,
+                    key=session_id.key,
+                )
                run_request = self._build_request_data(
                    req_body,
                    message,
-                    thread_id,
                    correlation_id,
                    request_response_format,
                )
@@ -622,14 +629,16 @@ class AgentFunctionApp(DFAppBase):
            session_id = AgentSessionId.with_random_key(agent_name)

        # Build entity instance ID
-        entity_instance_id = session_id.to_entity_id()
+        entity_instance_id = df.EntityId(
+            name=session_id.entity_name,
+            key=session_id.key,
+        )

        # Create run request
        correlation_id = self._generate_unique_id()
        run_request = self._build_request_data(
            req_body={"message": query, "role": "user"},
            message=query,
-            thread_id=str(session_id),
            correlation_id=correlation_id,
            request_response_format=REQUEST_RESPONSE_FORMAT_TEXT,
        )
@@ -781,7 +790,7 @@ class AgentFunctionApp(DFAppBase):
            agent_response = state.try_get_agent_response(correlation_id)
            if agent_response:
                result = self._build_success_result(
-                    response_data=agent_response,
+                    response_message=agent_response.text,
                    message=message,
                    thread_id=thread_id,
                    correlation_id=correlation_id,
@@ -827,23 +836,22 @@ class AgentFunctionApp(DFAppBase):
        )

    def _build_success_result(
-        self, response_data: dict[str, Any], message: str, thread_id: str, correlation_id: str, state: DurableAgentState
+        self, response_message: str, message: str, thread_id: str, correlation_id: str, state: DurableAgentState
    ) -> dict[str, Any]:
        """Build the success result returned to the HTTP caller."""
        return self._build_response_payload(
-            response=response_data.get("content"),
+            response=response_message,
            message=message,
            thread_id=thread_id,
            status="success",
            correlation_id=correlation_id,
-            extra_fields={"message_count": response_data.get("message_count", state.message_count)},
+            extra_fields={ApiResponseFields.MESSAGE_COUNT: state.message_count},
        )

    def _build_request_data(
        self,
        req_body: dict[str, Any],
        message: str,
-        thread_id: str,
        correlation_id: str,
        request_response_format: str,
    ) -> dict[str, Any]:
@@ -857,8 +865,8 @@ class AgentFunctionApp(DFAppBase):
            request_response_format=request_response_format,
            response_format=req_body.get("response_format"),
            enable_tool_calls=enable_tool_calls,
-            thread_id=thread_id,
            correlation_id=correlation_id,
+            created_at=datetime.now(timezone.utc),
        ).to_dict()

    def _build_accepted_response(self, message: str, thread_id: str, correlation_id: str) -> dict[str, Any]:
@@ -910,15 +918,13 @@ class AgentFunctionApp(DFAppBase):

    def _generate_unique_id(self) -> str:
        """Generate a new unique identifier."""
-        import uuid
-
        return uuid.uuid4().hex

-    def _create_session_id(self, func_name: str, thread_id: str | None) -> AgentSessionId:
+    def _create_session_id(self, agent_name: str, thread_id: str | None) -> AgentSessionId:
        """Create a session identifier using the provided thread id or a random value."""
        if thread_id:
-            return AgentSessionId(name=func_name, key=thread_id)
-        return AgentSessionId.with_random_key(name=func_name)
+            return AgentSessionId(name=agent_name, key=thread_id)
+        return AgentSessionId.with_random_key(name=agent_name)

    def _resolve_thread_id(self, req: func.HttpRequest, req_body: dict[str, Any]) -> str:
        """Retrieve the thread identifier from request body or query parameters."""
@@ -1,40 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-
-"""Callback interfaces for Durable Agent executions.
-
-This module enables callers of AgentFunctionApp to supply streaming and final-response callbacks that are
-invoked during durable entity execution.
-"""
-
-from dataclasses import dataclass
-from typing import Protocol
-
-from agent_framework import AgentResponse, AgentResponseUpdate
-
-
-@dataclass(frozen=True)
-class AgentCallbackContext:
-    """Context supplied to callback invocations."""
-
-    agent_name: str
-    correlation_id: str
-    thread_id: str | None = None
-    request_message: str | None = None
-
-
-class AgentResponseCallbackProtocol(Protocol):
-    """Protocol describing the callbacks invoked during agent execution."""
-
-    async def on_streaming_response_update(
-        self,
-        update: AgentResponseUpdate,
-        context: AgentCallbackContext,
-    ) -> None:
-        """Handle a streaming response update emitted by the agent."""
-
-    async def on_agent_response(
-        self,
-        response: AgentResponse,
-        context: AgentCallbackContext,
-    ) -> None:
-        """Handle the final agent response."""
@@ -1,130 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-
-"""Constants for Azure Functions Agent Framework integration.
-
-This module contains:
- Runtime configuration constants (polling, MIME types, headers)
- JSON field name mappings for camelCase (JSON) ↔ snake_case (Python) serialization
-
-For serialization constants, use the DurableStateFields, ContentTypes, and EntryTypes classes
-to ensure consistent field naming between to_dict() and from_dict() methods.
-"""
-
-from typing import Final
-
-# Supported request/response formats and MIME types
-REQUEST_RESPONSE_FORMAT_JSON: str = "json"
-REQUEST_RESPONSE_FORMAT_TEXT: str = "text"
-MIMETYPE_APPLICATION_JSON: str = "application/json"
-MIMETYPE_TEXT_PLAIN: str = "text/plain"
-
-# Field and header names
-THREAD_ID_FIELD: str = "thread_id"
-THREAD_ID_HEADER: str = "x-ms-thread-id"
-WAIT_FOR_RESPONSE_FIELD: str = "wait_for_response"
-WAIT_FOR_RESPONSE_HEADER: str = "x-ms-wait-for-response"
-
-# Polling configuration
-DEFAULT_MAX_POLL_RETRIES: int = 30
-DEFAULT_POLL_INTERVAL_SECONDS: float = 1.0
-
-
-# =============================================================================
-# JSON Field Name Constants for Durable Agent State Serialization
-# =============================================================================
-# These constants ensure consistent camelCase field names in JSON serialization.
-# Use these in both to_dict() and from_dict() methods to prevent mismatches.
-
-# NOTE: Changing these constants is a breaking change and might require a schema version bump.
-
-
-class DurableStateFields:
-    """JSON field name constants for durable agent state serialization.
-
-    All field names are in camelCase to match the JSON schema.
-    Use these constants in both to_dict() and from_dict() methods.
-    """
-
-    # Schema-level fields
-    SCHEMA_VERSION: Final[str] = "schemaVersion"
-    DATA: Final[str] = "data"
-
-    # Entry discriminator
-    TYPE_DISCRIMINATOR: Final[str] = "$type"
-
-    # Internal field names
-    JSON_TYPE: Final[str] = "json_type"
-    TYPE_INTERNAL: Final[str] = "type"
-
-    # Common entry fields
-    CORRELATION_ID: Final[str] = "correlationId"
-    CREATED_AT: Final[str] = "createdAt"
-    MESSAGES: Final[str] = "messages"
-    EXTENSION_DATA: Final[str] = "extensionData"
-
-    # Request-specific fields
-    RESPONSE_TYPE: Final[str] = "responseType"
-    RESPONSE_SCHEMA: Final[str] = "responseSchema"
-    ORCHESTRATION_ID: Final[str] = "orchestrationId"
-
-    # Response-specific fields
-    USAGE: Final[str] = "usage"
-
-    # Message fields
-    ROLE: Final[str] = "role"
-    CONTENTS: Final[str] = "contents"
-    AUTHOR_NAME: Final[str] = "authorName"
-
-    # Content fields
-    TEXT: Final[str] = "text"
-    URI: Final[str] = "uri"
-    MEDIA_TYPE: Final[str] = "mediaType"
-    MESSAGE: Final[str] = "message"
-    ERROR_CODE: Final[str] = "errorCode"
-    DETAILS: Final[str] = "details"
-    CALL_ID: Final[str] = "callId"
-    NAME: Final[str] = "name"
-    ARGUMENTS: Final[str] = "arguments"
-    RESULT: Final[str] = "result"
-    FILE_ID: Final[str] = "fileId"
-    VECTOR_STORE_ID: Final[str] = "vectorStoreId"
-    CONTENT: Final[str] = "content"
-
-    # Usage fields (noqa: S105 - these are JSON field names, not passwords)
-    INPUT_TOKEN_COUNT: Final[str] = "inputTokenCount"  # noqa: S105
-    OUTPUT_TOKEN_COUNT: Final[str] = "outputTokenCount"  # noqa: S105
-    TOTAL_TOKEN_COUNT: Final[str] = "totalTokenCount"  # noqa: S105
-
-    # History field
-    CONVERSATION_HISTORY: Final[str] = "conversationHistory"
-
-
-class ContentTypes:
-    """Content type discriminator values for the $type field.
-
-    These values are used in the JSON $type field to identify content types.
-    """
-
-    TEXT: Final[str] = "text"
-    DATA: Final[str] = "data"
-    ERROR: Final[str] = "error"
-    FUNCTION_CALL: Final[str] = "functionCall"
-    FUNCTION_RESULT: Final[str] = "functionResult"
-    HOSTED_FILE: Final[str] = "hostedFile"
-    HOSTED_VECTOR_STORE: Final[str] = "hostedVectorStore"
-    REASONING: Final[str] = "reasoning"
-    URI: Final[str] = "uri"
-    USAGE: Final[str] = "usage"
-    UNKNOWN: Final[str] = "unknown"
-
-
-class ApiResponseFields:
-    """Field names for HTTP API responses (not part of persisted schema).
-
-    These are used in try_get_agent_response() for backward compatibility
-    with the HTTP API response format.
-    """
-
-    CONTENT: Final[str] = "content"
-    MESSAGE_COUNT: Final[str] = "message_count"
-    CORRELATION_ID: Final[str] = "correlationId"
@@ -8,346 +8,41 @@ allows for long-running agent conversations.
 """

 import asyncio
-import inspect
-from collections.abc import AsyncIterable, Callable
+from collections.abc import Callable
 from typing import Any, cast

 import azure.durable_functions as df
-from agent_framework import (
-    AgentProtocol,
-    AgentResponse,
-    AgentResponseUpdate,
-    ChatMessage,
-    Content,
-    Role,
-    get_logger,
+from agent_framework import AgentProtocol, get_logger
+from agent_framework_durabletask import (
+    AgentEntity,
+    AgentEntityStateProviderMixin,
+    AgentResponseCallbackProtocol,
 )

-from ._callbacks import AgentCallbackContext, AgentResponseCallbackProtocol
-from ._durable_agent_state import (
-    DurableAgentState,
-    DurableAgentStateData,
-    DurableAgentStateEntry,
-    DurableAgentStateRequest,
-    DurableAgentStateResponse,
-)
-from ._models import RunRequest
-
 logger = get_logger("agent_framework.azurefunctions.entities")


-class AgentEntity:
-    """Durable entity that manages agent execution and conversation state.
+class AzureFunctionEntityStateProvider(AgentEntityStateProviderMixin):
+    """Azure Functions Durable Entity state provider for AgentEntity.

-    This entity:
-    - Maintains conversation history
-    - Executes agent with messages
-    - Stores agent responses
-    - Handles tool execution
-
-    Operations:
-    - run: Execute the agent with a message
-    - run_agent: (Deprecated) Execute the agent with a message
-    - reset: Clear conversation history
-
-    Attributes:
-        agent: The AgentProtocol instance
-        state: The DurableAgentState managing conversation history
+    This class utilizes the Durable Entity context from `azure-functions-durable` package
+    to get and set the state of the agent entity.
    """

-    agent: AgentProtocol
-    state: DurableAgentState
+    def __init__(self, context: df.DurableEntityContext) -> None:
+        self._context = context

-    def __init__(
-        self,
-        agent: AgentProtocol,
-        callback: AgentResponseCallbackProtocol | None = None,
-    ):
-        """Initialize the agent entity.
+    def _get_state_dict(self) -> dict[str, Any]:
+        raw_state = self._context.get_state(lambda: {})
+        if not isinstance(raw_state, dict):
+            return {}
+        return cast(dict[str, Any], raw_state)

-        Args:
-            agent: The Microsoft Agent Framework agent instance (must implement AgentProtocol)
-            callback: Optional callback invoked during streaming updates and final responses
-        """
-        self.agent = agent
-        self.state = DurableAgentState()
-        self.callback = callback
+    def _set_state_dict(self, state: dict[str, Any]) -> None:
+        self._context.set_state(state)

-        logger.debug(f"[AgentEntity] Initialized with agent type: {type(agent).__name__}")
-
-    def _is_error_response(self, entry: DurableAgentStateEntry) -> bool:
-        """Check if a conversation history entry is an error response.
-
-        Error responses should be kept in history for tracking but not sent to the agent
-        since Azure OpenAI doesn't support 'error' content type.
-
-        Args:
-            entry: A conversation history entry (DurableAgentStateEntry or dict)
-
-        Returns:
-            True if the entry is a response containing error content, False otherwise
-        """
-        if isinstance(entry, DurableAgentStateResponse):
-            return entry.is_error
-        return False
-
-    async def run_agent(
-        self,
-        context: df.DurableEntityContext,
-        request: RunRequest | dict[str, Any] | str,
-    ) -> AgentResponse:
-        """(Deprecated) Execute the agent with a message directly in the entity.
-
-        Args:
-            context: Entity context
-            request: RunRequest object, dict, or string message (for backward compatibility)
-
-        Returns:
-            AgentResponse enriched with execution metadata.
-        """
-        return await self.run(context, request)
-
-    async def run(
-        self,
-        context: df.DurableEntityContext,
-        request: RunRequest | dict[str, Any] | str,
-    ) -> AgentResponse:
-        """Execute the agent with a message directly in the entity.
-
-        Args:
-            context: Entity context
-            request: RunRequest object, dict, or string message (for backward compatibility)
-
-        Returns:
-            AgentResponse enriched with execution metadata.
-        """
-        if isinstance(request, str):
-            run_request = RunRequest(message=request, role=Role.USER)
-        elif isinstance(request, dict):
-            run_request = RunRequest.from_dict(request)
-        else:
-            run_request = request
-
-        message = run_request.message
-        thread_id = run_request.thread_id
-        correlation_id = run_request.correlation_id
-        if not thread_id:
-            raise ValueError("RunRequest must include a thread_id")
-        if not correlation_id:
-            raise ValueError("RunRequest must include a correlation_id")
-        response_format = run_request.response_format
-        enable_tool_calls = run_request.enable_tool_calls
-
-        state_request = DurableAgentStateRequest.from_run_request(run_request)
-        self.state.data.conversation_history.append(state_request)
-
-        logger.debug(f"[AgentEntity.run] Received Message: {state_request}")
-
-        try:
-            # Build messages from conversation history, excluding error responses
-            # Error responses are kept in history for tracking but not sent to the agent
-            chat_messages: list[ChatMessage] = [
-                m.to_chat_message()
-                for entry in self.state.data.conversation_history
-                if not self._is_error_response(entry)
-                for m in entry.messages
-            ]
-
-            run_kwargs: dict[str, Any] = {"messages": chat_messages, "options": {}}
-            if not enable_tool_calls:
-                run_kwargs["options"]["tools"] = None
-            if response_format:
-                run_kwargs["options"]["response_format"] = response_format
-
-            agent_response: AgentResponse = await self._invoke_agent(
-                run_kwargs=run_kwargs,
-                correlation_id=correlation_id,
-                thread_id=thread_id,
-                request_message=message,
-            )
-
-            logger.debug(
-                "[AgentEntity.run] Agent invocation completed - response type: %s",
-                type(agent_response).__name__,
-            )
-
-            try:
-                response_text = agent_response.text if agent_response.text else "No response"
-                logger.debug(f"Response: {response_text[:100]}...")
-            except Exception as extraction_error:
-                logger.error(
-                    "Error extracting response text: %s",
-                    extraction_error,
-                    exc_info=True,
-                )
-
-            state_response = DurableAgentStateResponse.from_run_response(correlation_id, agent_response)
-            self.state.data.conversation_history.append(state_response)
-
-            logger.debug("[AgentEntity.run] AgentResponse stored in conversation history")
-
-            return agent_response
-
-        except Exception as exc:
-            logger.exception("[AgentEntity.run] Agent execution failed.")
-
-            # Create error message
-            error_message = ChatMessage(
-                role=Role.ASSISTANT, contents=[Content.from_error(message=str(exc), error_code=type(exc).__name__)]
-            )
-
-            error_response = AgentResponse(messages=[error_message])
-
-            # Create and store error response in conversation history
-            error_state_response = DurableAgentStateResponse.from_run_response(correlation_id, error_response)
-            error_state_response.is_error = True
-            self.state.data.conversation_history.append(error_state_response)
-
-            return error_response
-
-    async def _invoke_agent(
-        self,
-        run_kwargs: dict[str, Any],
-        correlation_id: str,
-        thread_id: str,
-        request_message: str,
-    ) -> AgentResponse:
-        """Execute the agent, preferring streaming when available."""
-        callback_context: AgentCallbackContext | None = None
-        if self.callback is not None:
-            callback_context = self._build_callback_context(
-                correlation_id=correlation_id,
-                thread_id=thread_id,
-                request_message=request_message,
-            )
-
-        run_stream_callable = getattr(self.agent, "run_stream", None)
-        if callable(run_stream_callable):
-            try:
-                stream_candidate = run_stream_callable(**run_kwargs)
-                if inspect.isawaitable(stream_candidate):
-                    stream_candidate = await stream_candidate
-
-                return await self._consume_stream(
-                    stream=cast(AsyncIterable[AgentResponseUpdate], stream_candidate),
-                    callback_context=callback_context,
-                )
-            except TypeError as type_error:
-                if "__aiter__" not in str(type_error):
-                    raise
-                logger.debug(
-                    "run_stream returned a non-async result; falling back to run(): %s",
-                    type_error,
-                )
-            except Exception as stream_error:
-                logger.warning(
-                    "run_stream failed; falling back to run(): %s",
-                    stream_error,
-                    exc_info=True,
-                )
-        else:
-            logger.debug("Agent does not expose run_stream; falling back to run().")
-
-        agent_response = await self._invoke_non_stream(run_kwargs)
-        await self._notify_final_response(agent_response, callback_context)
-        return agent_response
-
-    async def _consume_stream(
-        self,
-        stream: AsyncIterable[AgentResponseUpdate],
-        callback_context: AgentCallbackContext | None = None,
-    ) -> AgentResponse:
-        """Consume streaming responses and build the final AgentResponse."""
-        updates: list[AgentResponseUpdate] = []
-
-        async for update in stream:
-            updates.append(update)
-            await self._notify_stream_update(update, callback_context)
-
-        if updates:
-            response = AgentResponse.from_agent_run_response_updates(updates)
-        else:
-            logger.debug("[AgentEntity] No streaming updates received; creating empty response")
-            response = AgentResponse(messages=[])
-
-        await self._notify_final_response(response, callback_context)
-        return response
-
-    async def _invoke_non_stream(self, run_kwargs: dict[str, Any]) -> AgentResponse:
-        """Invoke the agent without streaming support."""
-        run_callable = getattr(self.agent, "run", None)
-        if run_callable is None or not callable(run_callable):
-            raise AttributeError("Agent does not implement run() method")
-
-        result = run_callable(**run_kwargs)
-        if inspect.isawaitable(result):
-            result = await result
-
-        if not isinstance(result, AgentResponse):
-            raise TypeError(f"Agent run() must return an AgentResponse instance; received {type(result).__name__}")
-
-        return result
-
-    async def _notify_stream_update(
-        self,
-        update: AgentResponseUpdate,
-        context: AgentCallbackContext | None,
-    ) -> None:
-        """Invoke the streaming callback if one is registered."""
-        if self.callback is None or context is None:
-            return
-
-        try:
-            callback_result = self.callback.on_streaming_response_update(update, context)
-            if inspect.isawaitable(callback_result):
-                await callback_result
-        except Exception as exc:
-            logger.warning(
-                "[AgentEntity] Streaming callback raised an exception: %s",
-                exc,
-                exc_info=True,
-            )
-
-    async def _notify_final_response(
-        self,
-        response: AgentResponse,
-        context: AgentCallbackContext | None,
-    ) -> None:
-        """Invoke the final response callback if one is registered."""
-        if self.callback is None or context is None:
-            return
-
-        try:
-            callback_result = self.callback.on_agent_response(response, context)
-            if inspect.isawaitable(callback_result):
-                await callback_result
-        except Exception as exc:
-            logger.warning(
-                "[AgentEntity] Response callback raised an exception: %s",
-                exc,
-                exc_info=True,
-            )
-
-    def _build_callback_context(
-        self,
-        correlation_id: str,
-        thread_id: str,
-        request_message: str,
-    ) -> AgentCallbackContext:
-        """Create the callback context provided to consumers."""
-        agent_name = getattr(self.agent, "name", None) or type(self.agent).__name__
-        return AgentCallbackContext(
-            agent_name=agent_name,
-            correlation_id=correlation_id,
-            thread_id=thread_id,
-            request_message=request_message,
-        )
-
-    def reset(self, context: df.DurableEntityContext) -> None:
-        """Reset the entity state (clear conversation history)."""
-        logger.debug("[AgentEntity.reset] Resetting entity state")
-        self.state.data = DurableAgentStateData(conversation_history=[])
-        logger.debug("[AgentEntity.reset] State reset complete")
+    def _get_thread_id_from_entity(self) -> str:
+        return str(self._context.entity_key)


 def create_agent_entity(
@@ -368,19 +63,10 @@ def create_agent_entity(
        """Async handler that executes the entity operations."""
        try:
            logger.debug("[entity_function] Entity triggered")
-            logger.debug(f"[entity_function] Operation: {context.operation_name}")
+            logger.debug("[entity_function] Operation: %s", context.operation_name)

-            current_state = context.get_state(lambda: None)
-            logger.debug("Retrieved state: %s", str(current_state)[:100])
-            entity = AgentEntity(agent, callback)
-
-            if current_state is not None:
-                entity.state = DurableAgentState.from_dict(current_state)
-                logger.debug(
-                    "[entity_function] Restored entity from state (message_count: %s)", entity.state.message_count
-                )
-            else:
-                logger.debug("[entity_function] Created new entity instance")
+            state_provider = AzureFunctionEntityStateProvider(context)
+            entity = AgentEntity(agent, callback, state_provider=state_provider)

            operation = context.operation_name

@@ -394,21 +80,18 @@ def create_agent_entity(
                    # Fall back to treating input as message string
                    request = "" if input_data is None else str(cast(object, input_data))

-                result = await entity.run(context, request)
+                result = await entity.run(request)
                context.set_result(result.to_dict())

            elif operation == "reset":
-                entity.reset(context)
+                entity.reset()
                context.set_result({"status": "reset"})

            else:
                logger.error("[entity_function] Unknown operation: %s", operation)
                context.set_result({"error": f"Unknown operation: {operation}"})

-            serialized_state = entity.state.to_dict()
-            logger.debug("State dict: %s", serialized_state)
-            context.set_state(serialized_state)
-            logger.info(f"[entity_function] Operation {operation} completed successfully")
+            logger.info("[entity_function] Operation %s completed successfully", operation)

        except Exception as exc:
            logger.exception("[entity_function] Error executing entity operation %s", exc)
@@ -1,379 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-
-"""Data models for Durable Agent Framework.
-
-This module defines the request and response models used by the framework.
-"""
-
-from __future__ import annotations
-
-import inspect
-import uuid
-from collections.abc import MutableMapping
-from dataclasses import dataclass
-from importlib import import_module
-from typing import TYPE_CHECKING, Any, cast
-
-import azure.durable_functions as df
-from agent_framework import AgentThread, Role
-
-from ._constants import REQUEST_RESPONSE_FORMAT_TEXT
-
-if TYPE_CHECKING:  # pragma: no cover - type checking imports only
-    from pydantic import BaseModel
-
-_PydanticBaseModel: type[BaseModel] | None
-
-try:
-    from pydantic import BaseModel as _RuntimeBaseModel
-except ImportError:  # pragma: no cover - optional dependency
-    _PydanticBaseModel = None
-else:
-    _PydanticBaseModel = _RuntimeBaseModel
-
-
-@dataclass
-class AgentSessionId:
-    """Represents an agent session ID, which is used to identify a long-running agent session.
-
-    Attributes:
-        name: The name of the agent that owns the session (case-insensitive)
-        key: The unique key of the agent session (case-sensitive)
-    """
-
-    name: str
-    key: str
-
-    ENTITY_NAME_PREFIX: str = "dafx-"
-
-    @staticmethod
-    def to_entity_name(name: str) -> str:
-        """Converts an agent name to an entity name by adding the DAFx prefix.
-
-        Args:
-            name: The agent name
-
-        Returns:
-            The entity name with the dafx- prefix
-        """
-        return f"{AgentSessionId.ENTITY_NAME_PREFIX}{name}"
-
-    @staticmethod
-    def with_random_key(name: str) -> AgentSessionId:
-        """Creates a new AgentSessionId with the specified name and a randomly generated key.
-
-        Args:
-            name: The name of the agent that owns the session
-
-        Returns:
-            A new AgentSessionId with the specified name and a random GUID key
-        """
-        return AgentSessionId(name=name, key=uuid.uuid4().hex)
-
-    def to_entity_id(self) -> df.EntityId:
-        """Converts this AgentSessionId to a Durable Functions EntityId.
-
-        Returns:
-            EntityId for use with Durable Functions APIs
-        """
-        return df.EntityId(self.to_entity_name(self.name), self.key)
-
-    @staticmethod
-    def from_entity_id(entity_id: df.EntityId) -> AgentSessionId:
-        """Creates an AgentSessionId from a Durable Functions EntityId.
-
-        Args:
-            entity_id: The EntityId to convert
-
-        Returns:
-            AgentSessionId instance
-
-        Raises:
-            ValueError: If the entity ID does not have the expected prefix
-        """
-        if not entity_id.name.startswith(AgentSessionId.ENTITY_NAME_PREFIX):
-            raise ValueError(
-                f"'{entity_id}' is not a valid agent session ID. "
-                f"Expected entity name to start with '{AgentSessionId.ENTITY_NAME_PREFIX}'"
-            )
-
-        agent_name = entity_id.name[len(AgentSessionId.ENTITY_NAME_PREFIX) :]
-        return AgentSessionId(name=agent_name, key=entity_id.key)
-
-    def __str__(self) -> str:
-        """Returns a string representation in the form @name@key."""
-        return f"@{self.name}@{self.key}"
-
-    def __repr__(self) -> str:
-        """Returns a detailed string representation."""
-        return f"AgentSessionId(name='{self.name}', key='{self.key}')"
-
-    @staticmethod
-    def parse(session_id_string: str, agent_name: str | None = None) -> AgentSessionId:
-        """Parses a string representation of an agent session ID.
-
-        Args:
-            session_id_string: A string in the form @name@key, or a plain key string
-                when agent_name is provided.
-            agent_name: Optional agent name to use instead of parsing from the string.
-                If provided, only the key portion is extracted from session_id_string
-                (for @name@key format) or the entire string is used as the key
-                (for plain strings).
-
-        Returns:
-            AgentSessionId instance
-
-        Raises:
-            ValueError: If the string format is invalid and agent_name is not provided
-        """
-        # Check if string is in @name@key format
-        if session_id_string.startswith("@") and "@" in session_id_string[1:]:
-            parts = session_id_string[1:].split("@", 1)
-            name = agent_name if agent_name is not None else parts[0]
-            return AgentSessionId(name=name, key=parts[1])
-
-        # Plain string format - only valid when agent_name is provided
-        if agent_name is not None:
-            return AgentSessionId(name=agent_name, key=session_id_string)
-
-        raise ValueError(f"Invalid agent session ID format: {session_id_string}")
-
-
-class DurableAgentThread(AgentThread):
-    """Durable agent thread that tracks the owning :class:`AgentSessionId`."""
-
-    _SERIALIZED_SESSION_ID_KEY = "durable_session_id"
-
-    def __init__(
-        self,
-        *,
-        session_id: AgentSessionId | None = None,
-        service_thread_id: str | None = None,
-        message_store: Any = None,
-        context_provider: Any = None,
-    ) -> None:
-        super().__init__(
-            service_thread_id=service_thread_id,
-            message_store=message_store,
-            context_provider=context_provider,
-        )
-        self._session_id: AgentSessionId | None = session_id
-
-    @property
-    def session_id(self) -> AgentSessionId | None:
-        """Returns the durable agent session identifier for this thread."""
-        return self._session_id
-
-    def attach_session(self, session_id: AgentSessionId) -> None:
-        """Associates the thread with the provided :class:`AgentSessionId`."""
-        self._session_id = session_id
-
-    @classmethod
-    def from_session_id(
-        cls,
-        session_id: AgentSessionId,
-        *,
-        service_thread_id: str | None = None,
-        message_store: Any = None,
-        context_provider: Any = None,
-    ) -> DurableAgentThread:
-        """Creates a durable thread pre-associated with the supplied session ID."""
-        return cls(
-            session_id=session_id,
-            service_thread_id=service_thread_id,
-            message_store=message_store,
-            context_provider=context_provider,
-        )
-
-    async def serialize(self, **kwargs: Any) -> dict[str, Any]:
-        """Serializes thread state including the durable session identifier."""
-        state = await super().serialize(**kwargs)
-        if self._session_id is not None:
-            state[self._SERIALIZED_SESSION_ID_KEY] = str(self._session_id)
-        return state
-
-    @classmethod
-    async def deserialize(
-        cls,
-        serialized_thread_state: MutableMapping[str, Any],
-        *,
-        message_store: Any = None,
-        **kwargs: Any,
-    ) -> DurableAgentThread:
-        """Restores a durable thread, rehydrating the stored session identifier."""
-        state_payload = dict(serialized_thread_state)
-        session_id_value = state_payload.pop(cls._SERIALIZED_SESSION_ID_KEY, None)
-        thread = await super().deserialize(
-            state_payload,
-            message_store=message_store,
-            **kwargs,
-        )
-        if not isinstance(thread, DurableAgentThread):
-            raise TypeError("Deserialized thread is not a DurableAgentThread instance")
-
-        if session_id_value is None:
-            return thread
-
-        if not isinstance(session_id_value, str):
-            raise ValueError("durable_session_id must be a string when present in serialized state")
-
-        thread.attach_session(AgentSessionId.parse(session_id_value))
-        return thread
-
-
-def serialize_response_format(response_format: type[BaseModel] | None) -> Any:
-    """Serialize response format for transport across durable function boundaries."""
-    if response_format is None:
-        return None
-
-    if _PydanticBaseModel is None:
-        raise RuntimeError("pydantic is required to use structured response formats")
-
-    if not inspect.isclass(response_format) or not issubclass(response_format, _PydanticBaseModel):
-        raise TypeError("response_format must be a Pydantic BaseModel type")
-
-    return {
-        "__response_schema_type__": "pydantic_model",
-        "module": response_format.__module__,
-        "qualname": response_format.__qualname__,
-    }
-
-
-def _deserialize_response_format(response_format: Any) -> type[BaseModel] | None:
-    """Deserialize response format back into actionable type if possible."""
-    if response_format is None:
-        return None
-
-    if (
-        _PydanticBaseModel is not None
-        and inspect.isclass(response_format)
-        and issubclass(response_format, _PydanticBaseModel)
-    ):
-        return response_format
-
-    if not isinstance(response_format, dict):
-        return None
-
-    response_dict = cast(dict[str, Any], response_format)
-
-    if response_dict.get("__response_schema_type__") != "pydantic_model":
-        return None
-
-    module_name = response_dict.get("module")
-    qualname = response_dict.get("qualname")
-    if not module_name or not qualname:
-        return None
-
-    try:
-        module = import_module(module_name)
-    except ImportError:  # pragma: no cover - user provided module missing
-        return None
-
-    attr: Any = module
-    for part in qualname.split("."):
-        try:
-            attr = getattr(attr, part)
-        except AttributeError:  # pragma: no cover - invalid qualname
-            return None
-
-    if _PydanticBaseModel is not None and inspect.isclass(attr) and issubclass(attr, _PydanticBaseModel):
-        return attr
-
-    return None
-
-
-@dataclass
-class RunRequest:
-    """Represents a request to run an agent with a specific message and configuration.
-
-    Attributes:
-        message: The message to send to the agent
-        request_response_format: The desired response format (e.g., "text" or "json")
-        role: The role of the message sender (user, system, or assistant)
-        response_format: Optional Pydantic BaseModel type describing the structured response format
-        enable_tool_calls: Whether to enable tool calls for this request
-        thread_id: Optional thread ID for tracking
-        correlation_id: Optional correlation ID for tracking the response to this specific request
-        created_at: Optional timestamp when the request was created
-        orchestration_id: Optional ID of the orchestration that initiated this request
-    """
-
-    message: str
-    request_response_format: str
-    role: Role = Role.USER
-    response_format: type[BaseModel] | None = None
-    enable_tool_calls: bool = True
-    thread_id: str | None = None
-    correlation_id: str | None = None
-    created_at: str | None = None
-    orchestration_id: str | None = None
-
-    def __init__(
-        self,
-        message: str,
-        request_response_format: str = REQUEST_RESPONSE_FORMAT_TEXT,
-        role: Role | str | None = Role.USER,
-        response_format: type[BaseModel] | None = None,
-        enable_tool_calls: bool = True,
-        thread_id: str | None = None,
-        correlation_id: str | None = None,
-        created_at: str | None = None,
-        orchestration_id: str | None = None,
-    ) -> None:
-        self.message = message
-        self.role = self.coerce_role(role)
-        self.response_format = response_format
-        self.request_response_format = request_response_format
-        self.enable_tool_calls = enable_tool_calls
-        self.thread_id = thread_id
-        self.correlation_id = correlation_id
-        self.created_at = created_at
-        self.orchestration_id = orchestration_id
-
-    @staticmethod
-    def coerce_role(value: Role | str | None) -> Role:
-        """Normalize various role representations into a Role instance."""
-        if isinstance(value, Role):
-            return value
-        if isinstance(value, str):
-            normalized = value.strip()
-            if not normalized:
-                return Role.USER
-            return Role(value=normalized.lower())
-        return Role.USER
-
-    def to_dict(self) -> dict[str, Any]:
-        """Convert to dictionary for JSON serialization."""
-        result = {
-            "message": self.message,
-            "enable_tool_calls": self.enable_tool_calls,
-            "role": self.role.value,
-            "request_response_format": self.request_response_format,
-        }
-        if self.response_format:
-            result["response_format"] = serialize_response_format(self.response_format)
-        if self.thread_id:
-            result["thread_id"] = self.thread_id
-        if self.correlation_id:
-            result["correlationId"] = self.correlation_id
-        if self.created_at:
-            result["created_at"] = self.created_at
-        if self.orchestration_id:
-            result["orchestrationId"] = self.orchestration_id
-
-        return result
-
-    @classmethod
-    def from_dict(cls, data: dict[str, Any]) -> RunRequest:
-        """Create RunRequest from dictionary."""
-        return cls(
-            message=data.get("message", ""),
-            request_response_format=data.get("request_response_format", REQUEST_RESPONSE_FORMAT_TEXT),
-            role=cls.coerce_role(data.get("role")),
-            response_format=_deserialize_response_format(data.get("response_format")),
-            enable_tool_calls=data.get("enable_tool_calls", True),
-            thread_id=data.get("thread_id"),
-            correlation_id=data.get("correlationId"),
-            created_at=data.get("created_at"),
-            orchestration_id=data.get("orchestrationId"),
-        )
@@ -5,24 +5,22 @@
 This module provides support for using agents inside Durable Function orchestrations.
 """

-import uuid
-from collections.abc import AsyncIterator, Callable, Sequence
-from typing import TYPE_CHECKING, Any, TypeAlias, cast
+from collections.abc import Callable
+from typing import TYPE_CHECKING, Any, TypeAlias

-from agent_framework import (
-    AgentProtocol,
-    AgentResponse,
-    AgentResponseUpdate,
-    AgentThread,
-    ChatMessage,
-    get_logger,
+import azure.durable_functions as df
+from agent_framework import AgentThread, get_logger
+from agent_framework_durabletask import (
+    DurableAgentExecutor,
+    RunRequest,
+    ensure_response_format,
+    load_agent_response,
 )
 from azure.durable_functions.models import TaskBase
+from azure.durable_functions.models.actions.NoOpAction import NoOpAction
 from azure.durable_functions.models.Task import CompoundTask, TaskState
 from pydantic import BaseModel

-from ._models import AgentSessionId, DurableAgentThread, RunRequest
-
 logger = get_logger("agent_framework.azurefunctions.orchestration")

 CompoundActionConstructor: TypeAlias = Callable[[list[Any]], Any] | None
@@ -45,6 +43,25 @@ else:
    _TypedCompoundTask = CompoundTask


+class PreCompletedTask(TaskBase):  # type: ignore[misc]
+    """A simple task that is already completed with a result.
+
+    Used for fire-and-forget mode where we want to return immediately
+    with an acceptance response without waiting for entity processing.
+    """
+
+    def __init__(self, result: Any):
+        """Initialize with a completed result.
+
+        Args:
+            result: The result value for this completed task
+        """
+        # Initialize with a NoOp action since we don't need actual orchestration actions
+        super().__init__(-1, NoOpAction())
+        # Immediately mark as completed with the result
+        self.set_value(is_error=False, value=result)
+
+
 class AgentTask(_TypedCompoundTask):
    """A custom Task that wraps entity calls and provides typed AgentResponse results.

@@ -65,10 +82,13 @@ class AgentTask(_TypedCompoundTask):
            response_format: Optional Pydantic model for response parsing
            correlation_id: Correlation ID for logging
        """
-        super().__init__([entity_task])
+        # Set instance variables BEFORE calling super().__init__
+        # because super().__init__ may trigger try_set_value for pre-completed tasks
        self._response_format = response_format
        self._correlation_id = correlation_id

+        super().__init__([entity_task])
+
        # Override action_repr to expose the inner task's action directly
        # This ensures compatibility with ReplaySchema V3 which expects Action objects.
        self.action_repr = entity_task.action_repr
@@ -95,10 +115,10 @@ class AgentTask(_TypedCompoundTask):
                )

                try:
-                    response = self._load_agent_response(raw_result)
+                    response = load_agent_response(raw_result)

                    if self._response_format is not None:
-                        self._ensure_response_format(
+                        ensure_response_format(
                            self._response_format,
                            self._correlation_id,
                            response,
@@ -118,230 +138,84 @@ class AgentTask(_TypedCompoundTask):
                self._first_error = child.result
                self.set_value(is_error=True, value=self._first_error)

-    def _load_agent_response(self, agent_response: AgentResponse | dict[str, Any] | None) -> AgentResponse:
-        """Convert raw payloads into AgentResponse instance."""
-        if agent_response is None:
-            raise ValueError("agent_response cannot be None")

-        logger.debug("[load_agent_response] Loading agent response of type: %s", type(agent_response))
+class AzureFunctionsAgentExecutor(DurableAgentExecutor[AgentTask]):
+    """Executor that executes durable agents inside Azure Functions orchestrations."""

-        if isinstance(agent_response, AgentResponse):
-            return agent_response
-        if isinstance(agent_response, dict):
-            logger.debug("[load_agent_response] Converting dict payload using AgentResponse.from_dict")
-            return AgentResponse.from_dict(agent_response)
-
-        raise TypeError(f"Unsupported type for agent_response: {type(agent_response)}")
-
-    def _ensure_response_format(
-        self,
-        response_format: type[BaseModel] | None,
-        correlation_id: str,
-        response: AgentResponse,
-    ) -> None:
-        """Ensure the AgentResponse value is parsed into the expected response_format."""
-        if response_format is not None and not isinstance(response.value, response_format):
-            response.try_parse_value(response_format)
-
-            logger.debug(
-                "[DurableAIAgent] Loaded AgentResponse.value for correlation_id %s with type: %s",
-                correlation_id,
-                type(response.value).__name__,
-            )
-
-
-class DurableAIAgent(AgentProtocol):
-    """A durable agent implementation that uses entity methods to interact with agent entities.
-
-    This class implements AgentProtocol and provides methods to work with Azure Durable Functions
-    orchestrations, which use generators and yield instead of async/await.
-
-    Key methods:
-    - get_new_thread(): Create a new conversation thread
-    - run(): Execute the agent and return a Task for yielding in orchestrations
-
-    Note: The run() method is NOT async. It returns a Task directly that must be
-    yielded in orchestrations to wait for the entity call to complete.
-
-    Example usage in orchestration:
-        writer = app.get_agent(context, "WriterAgent")
-        thread = writer.get_new_thread()  # NOT yielded - returns immediately
-
-        response = yield writer.run(  # Yielded - waits for entity call
-            message="Write a haiku about coding",
-            thread=thread
-        )
-    """
-
-    def __init__(self, context: AgentOrchestrationContextType, agent_name: str):
-        """Initialize the DurableAIAgent.
-
-        Args:
-            context: The orchestration context
-            agent_name: Name of the agent (used to construct entity ID)
-        """
+    def __init__(self, context: AgentOrchestrationContextType):
        self.context = context
-        self.agent_name = agent_name
-        self.id = str(uuid.uuid4())
-        self.name = agent_name
-        self.description = f"Durable agent proxy for {agent_name}"
-        logger.debug("[DurableAIAgent] Initialized for agent: %s", agent_name)

-    # We return an AgentTask here which is a TaskBase subclass.
-    # This is an intentional deviation from AgentProtocol which defines run() as async.
-    # The AgentTask can be yielded in Durable Functions orchestrations and will provide
-    # a typed AgentResponse result.
-    def run(  # type: ignore[override]
+    def generate_unique_id(self) -> str:
+        return str(self.context.new_uuid())
+
+    def get_run_request(
        self,
-        messages: str | ChatMessage | Sequence[str | ChatMessage] | None = None,
+        message: str,
        *,
-        thread: AgentThread | None = None,
        options: dict[str, Any] | None = None,
-        **kwargs: Any,
-    ) -> AgentTask:
-        """Execute the agent with messages and return an AgentTask for orchestrations.
-
-        This method implements AgentProtocol and returns an AgentTask (subclass of TaskBase)
-        that can be yielded in Durable Functions orchestrations. The task's result will be
-        a typed AgentResponse.
+    ) -> RunRequest:
+        """Get the current run request from the orchestration context.

        Args:
-            messages: The message(s) to send to the agent
-            thread: Optional agent thread for conversation context
-            options: Optional dict containing chat options like response_format, tools, etc.
-            **kwargs: Additional arguments (enable_tool_calls)
+            message: The message to send to the agent
+            options: Optional options dictionary. Supported keys include
+                ``response_format``, ``enable_tool_calls``, and ``wait_for_response``.
+                Additional keys are forwarded to the agent execution.

        Returns:
-            An AgentTask that resolves to an AgentResponse when yielded
+            RunRequest: The current run request

-        Example:
-            @app.orchestration_trigger(context_name="context")
-            def my_orchestration(context):
-                agent = app.get_agent(context, "MyAgent")
-                thread = agent.get_new_thread()
-                response = yield agent.run("Hello", thread=thread, options={"response_format": MyModel})
-                # response is typed as AgentResponse
+        Raises:
+            ValueError: If wait_for_response=False (not supported in orchestrations)
        """
-        message_str = self._normalize_messages(messages)
+        # Create a copy to avoid modifying the caller's dict

-        # Extract options from the options dict (aligned with ChatAgent pattern)
-        opts = options or {}
-        response_format: type[BaseModel] | None = opts.get("response_format")
-        enable_tool_calls = opts.get("enable_tool_calls", kwargs.get("enable_tool_calls", True))
+        request = super().get_run_request(message, options=options)
+        request.orchestration_id = self.context.instance_id
+        return request

-        # Get the session ID for the entity
-        if isinstance(thread, DurableAgentThread) and thread.session_id is not None:
-            session_id = thread.session_id
-        else:
-            # Create a unique session ID for each call when no thread is provided
-            # This ensures each call gets its own conversation context
-            session_key = str(self.context.new_uuid())
-            session_id = AgentSessionId(name=self.agent_name, key=session_key)
-            logger.debug("[DurableAIAgent] No thread provided, created unique session_id: %s", session_id)
+    def run_durable_agent(
+        self,
+        agent_name: str,
+        run_request: RunRequest,
+        thread: AgentThread | None = None,
+    ) -> AgentTask:

-        # Create entity ID from session ID
-        entity_id = session_id.to_entity_id()
+        # Resolve session
+        session_id = self._create_session_id(agent_name, thread)
+
+        entity_id = df.EntityId(
+            name=session_id.entity_name,
+            key=session_id.key,
+        )

-        # Generate a deterministic correlation ID for this call
-        # This is required by the entity and must be unique per call
-        correlation_id = str(self.context.new_uuid())
        logger.debug(
-            "[DurableAIAgent] Using correlation_id: %s for entity_id: %s for session_id: %s",
-            correlation_id,
+            "[AzureFunctionsAgentProvider] correlation_id: %s entity_id: %s session_id: %s",
+            run_request.correlation_id,
            entity_id,
            session_id,
        )

-        # Prepare the request using RunRequest model
-        # Include the orchestration's instance_id so it can be stored in the agent's entity state
-        run_request = RunRequest(
-            message=message_str,
-            enable_tool_calls=enable_tool_calls,
-            correlation_id=correlation_id,
-            thread_id=session_id.key,
-            response_format=response_format,
-            orchestration_id=self.context.instance_id,
-        )
+        # Branch based on wait_for_response
+        if not run_request.wait_for_response:
+            # Fire-and-forget mode: signal entity and return pre-completed task
+            logger.debug(
+                "[AzureFunctionsAgentExecutor] Fire-and-forget mode: signaling entity (correlation: %s)",
+                run_request.correlation_id,
+            )
+            self.context.signal_entity(entity_id, "run", run_request.to_dict())

-        logger.debug("[DurableAIAgent] Calling entity %s with message: %s", entity_id, message_str[:100])
+            # Create acceptance response using base class helper
+            acceptance_response = self._create_acceptance_response(run_request.correlation_id)

-        # Call the entity to get the underlying task
-        entity_task = self.context.call_entity(entity_id, "run", run_request.to_dict())
+            # Create a pre-completed task with the acceptance response
+            entity_task = PreCompletedTask(acceptance_response)
+        else:
+            # Blocking mode: call entity and wait for response
+            entity_task = self.context.call_entity(entity_id, "run", run_request.to_dict())

-        # Wrap it in an AgentTask that will convert the result to AgentResponse
-        agent_task = AgentTask(
+        return AgentTask(
            entity_task=entity_task,
-            response_format=response_format,
-            correlation_id=correlation_id,
+            response_format=run_request.response_format,
+            correlation_id=run_request.correlation_id,
        )
-
-        logger.debug(
-            "[DurableAIAgent] Created AgentTask for correlation_id %s",
-            correlation_id,
-        )
-
-        return agent_task
-
-    def run_stream(
-        self,
-        messages: str | ChatMessage | Sequence[str | ChatMessage] | None = None,
-        *,
-        thread: AgentThread | None = None,
-        **kwargs: Any,
-    ) -> AsyncIterator[AgentResponseUpdate]:
-        """Run the agent with streaming (not supported for durable agents).
-
-        Raises:
-            NotImplementedError: Streaming is not supported for durable agents.
-        """
-        raise NotImplementedError("Streaming is not supported for durable agents in orchestrations.")
-
-    def get_new_thread(self, **kwargs: Any) -> AgentThread:
-        """Create a new agent thread for this orchestration instance.
-
-        Each call creates a unique thread with its own conversation context.
-        The session ID is deterministic (uses context.new_uuid()) to ensure
-        orchestration replay works correctly.
-
-        Returns:
-            A new AgentThread instance with a unique session ID
-        """
-        # Generate a deterministic unique key for this thread
-        # Using context.new_uuid() ensures the same GUID is generated during replay
-        session_key = str(self.context.new_uuid())
-
-        # Create AgentSessionId with agent name and session key
-        session_id = AgentSessionId(name=self.agent_name, key=session_key)
-
-        thread = DurableAgentThread.from_session_id(session_id, **kwargs)
-
-        logger.debug("[DurableAIAgent] Created new thread with session_id: %s", session_id)
-        return thread
-
-    def _messages_to_string(self, messages: list[ChatMessage]) -> str:
-        """Convert a list of ChatMessage objects to a single string.
-
-        Args:
-            messages: List of ChatMessage objects
-
-        Returns:
-            Concatenated string of message contents
-        """
-        return "\n".join([msg.text or "" for msg in messages])
-
-    def _normalize_messages(self, messages: str | ChatMessage | Sequence[str | ChatMessage] | None) -> str:
-        """Convert supported message inputs to a single string."""
-        if messages is None:
-            return ""
-        if isinstance(messages, str):
-            return messages
-        if isinstance(messages, ChatMessage):
-            return messages.text or ""
-        if isinstance(messages, list):
-            if not messages:
-                return ""
-            first_item = messages[0]
-            if isinstance(first_item, str):
-                return "\n".join(cast(list[str], messages))
-            return self._messages_to_string(cast(list[ChatMessage], messages))
-        return str(messages)
@@ -23,6 +23,7 @@ classifiers = [
 ]
 dependencies = [
    "agent-framework-core",
+    "agent-framework-durabletask",
    "azure-functions",
    "azure-functions-durable",
 ]
@@ -15,10 +15,9 @@ Usage:
 """

 import pytest
+from agent_framework_durabletask import THREAD_ID_HEADER
 from testutils import SampleTestHelper, skip_if_azure_functions_integration_tests_disabled

-from agent_framework_azurefunctions._constants import THREAD_ID_HEADER
-
 # Module-level markers - applied to all tests in this file
 pytestmark = [
    pytest.mark.sample("01_single_agent"),
@@ -2,6 +2,8 @@

 """Unit tests for AgentFunctionApp."""

+# pyright: reportPrivateUsage=false
+
 import json
 from collections.abc import Awaitable, Callable
 from typing import Any, TypeVar
@@ -11,20 +13,42 @@ import azure.durable_functions as df
 import azure.functions as func
 import pytest
 from agent_framework import AgentResponse, ChatMessage
-
-from agent_framework_azurefunctions import AgentFunctionApp
-from agent_framework_azurefunctions._app import WAIT_FOR_RESPONSE_FIELD, WAIT_FOR_RESPONSE_HEADER
-from agent_framework_azurefunctions._constants import (
+from agent_framework_durabletask import (
    MIMETYPE_APPLICATION_JSON,
    MIMETYPE_TEXT_PLAIN,
    THREAD_ID_HEADER,
+    WAIT_FOR_RESPONSE_FIELD,
+    WAIT_FOR_RESPONSE_HEADER,
+    AgentEntity,
+    AgentEntityStateProviderMixin,
+    DurableAgentState,
 )
-from agent_framework_azurefunctions._durable_agent_state import DurableAgentState
-from agent_framework_azurefunctions._entities import AgentEntity, create_agent_entity
+
+from agent_framework_azurefunctions import AgentFunctionApp
+from agent_framework_azurefunctions._entities import create_agent_entity

 TFunc = TypeVar("TFunc", bound=Callable[..., Any])


+def _identity_decorator(func: TFunc) -> TFunc:
+    return func
+
+
+class _InMemoryStateProvider(AgentEntityStateProviderMixin):
+    def __init__(self, *, thread_id: str = "test-thread", initial_state: dict[str, Any] | None = None) -> None:
+        self._thread_id = thread_id
+        self._state_dict: dict[str, Any] = initial_state or {}
+
+    def _get_state_dict(self) -> dict[str, Any]:
+        return self._state_dict
+
+    def _set_state_dict(self, state: dict[str, Any]) -> None:
+        self._state_dict = state
+
+    def _get_thread_id_from_entity(self) -> str:
+        return self._thread_id
+
+
 class TestAgentFunctionAppInit:
    """Test suite for AgentFunctionApp initialization."""

@@ -88,7 +112,7 @@ class TestAgentFunctionAppInit:
            app.add_agent(mock_agent, callback=specific_callback)

        setup_mock.assert_called_once()
-        _, _, passed_callback, enable_http_endpoint, enable_mcp_tool_trigger = setup_mock.call_args[0]
+        _, _, passed_callback, enable_http_endpoint, _enable_mcp_tool_trigger = setup_mock.call_args[0]
        assert passed_callback is specific_callback
        assert enable_http_endpoint is True

@@ -104,7 +128,7 @@ class TestAgentFunctionAppInit:
            app.add_agent(mock_agent)

        setup_mock.assert_called_once()
-        _, _, passed_callback, enable_http_endpoint, enable_mcp_tool_trigger = setup_mock.call_args[0]
+        _, _, passed_callback, enable_http_endpoint, _enable_mcp_tool_trigger = setup_mock.call_args[0]
        assert passed_callback is default_callback
        assert enable_http_endpoint is True

@@ -119,7 +143,7 @@ class TestAgentFunctionAppInit:
            AgentFunctionApp(agents=[mock_agent], default_callback=default_callback)

        setup_mock.assert_called_once()
-        _, _, passed_callback, enable_http_endpoint, enable_mcp_tool_trigger = setup_mock.call_args[0]
+        _, _, passed_callback, enable_http_endpoint, _enable_mcp_tool_trigger = setup_mock.call_args[0]
        assert passed_callback is default_callback
        assert enable_http_endpoint is True

@@ -335,13 +359,12 @@ class TestAgentEntityOperations:
            return_value=AgentResponse(messages=[ChatMessage(role="assistant", text="Test response")])
        )

-        entity = AgentEntity(mock_agent)
-        mock_context = Mock()
+        entity = AgentEntity(mock_agent, state_provider=_InMemoryStateProvider(thread_id="test-conv-123"))

-        result = await entity.run(
-            mock_context,
-            {"message": "Test message", "thread_id": "test-conv-123", "correlationId": "corr-app-entity-1"},
-        )
+        result = await entity.run({
+            "message": "Test message",
+            "correlationId": "corr-app-entity-1",
+        })

        assert isinstance(result, AgentResponse)
        assert result.text == "Test response"
@@ -354,22 +377,17 @@ class TestAgentEntityOperations:
            return_value=AgentResponse(messages=[ChatMessage(role="assistant", text="Response 1")])
        )

-        entity = AgentEntity(mock_agent)
-        mock_context = Mock()
+        entity = AgentEntity(mock_agent, state_provider=_InMemoryStateProvider(thread_id="conv-1"))

        # Send first message
-        await entity.run(
-            mock_context, {"message": "Message 1", "thread_id": "conv-1", "correlationId": "corr-app-entity-2"}
-        )
+        await entity.run({"message": "Message 1", "correlationId": "corr-app-entity-2"})

        # Each conversation turn creates 2 entries: request and response
        history = entity.state.data.conversation_history[0].messages  # Request entry
        assert len(history) == 1  # Just the user message

        # Send second message
-        await entity.run(
-            mock_context, {"message": "Message 2", "thread_id": "conv-2", "correlationId": "corr-app-entity-2b"}
-        )
+        await entity.run({"message": "Message 2", "correlationId": "corr-app-entity-2b"})

        # Now we have 4 entries total (2 requests + 2 responses)
        # Access the first request entry
@@ -393,32 +411,26 @@ class TestAgentEntityOperations:
            return_value=AgentResponse(messages=[ChatMessage(role="assistant", text="Response")])
        )

-        entity = AgentEntity(mock_agent)
-        mock_context = Mock()
+        entity = AgentEntity(mock_agent, state_provider=_InMemoryStateProvider(thread_id="conv-1"))

        assert len(entity.state.data.conversation_history) == 0

-        await entity.run(
-            mock_context, {"message": "Message 1", "thread_id": "conv-1", "correlationId": "corr-app-entity-3a"}
-        )
+        await entity.run({"message": "Message 1", "correlationId": "corr-app-entity-3a"})
        assert len(entity.state.data.conversation_history) == 2

-        await entity.run(
-            mock_context, {"message": "Message 2", "thread_id": "conv-1", "correlationId": "corr-app-entity-3b"}
-        )
+        await entity.run({"message": "Message 2", "correlationId": "corr-app-entity-3b"})
        assert len(entity.state.data.conversation_history) == 4

    def test_entity_reset(self) -> None:
        """Test that entity reset clears state."""
        mock_agent = Mock()
-        entity = AgentEntity(mock_agent)
+        entity = AgentEntity(mock_agent, state_provider=_InMemoryStateProvider())

        # Set some state
        entity.state = DurableAgentState()

        # Reset
-        mock_context = Mock()
-        entity.reset(mock_context)
+        entity.reset()

        assert len(entity.state.data.conversation_history) == 0

@@ -447,7 +459,6 @@ class TestAgentEntityFactory:
        mock_context.operation_name = "run"
        mock_context.get_input.return_value = {
            "message": "Test message",
-            "thread_id": "conv-123",
            "correlationId": "corr-app-factory-1",
        }
        mock_context.get_state.return_value = None
@@ -475,7 +486,6 @@ class TestAgentEntityFactory:
        mock_context.operation_name = "run_agent"
        mock_context.get_input.return_value = {
            "message": "Test message",
-            "thread_id": "conv-123",
            "correlationId": "corr-app-factory-1",
        }
        mock_context.get_state.return_value = None
@@ -595,7 +605,11 @@ class TestAgentEntityFactory:
        }

        mock_context = Mock()
-        mock_context.operation_name = "reset"
+        mock_context.operation_name = "run"
+        mock_context.get_input.return_value = {
+            "message": "Test message",
+            "correlationId": "corr-restore-1",
+        }
        mock_context.get_state.return_value = existing_state

        with patch.object(DurableAgentState, "from_dict", wraps=DurableAgentState.from_dict) as from_dict_mock:
@@ -612,12 +626,12 @@ class TestErrorHandling:
        mock_agent = Mock()
        mock_agent.run = AsyncMock(side_effect=Exception("Agent error"))

-        entity = AgentEntity(mock_agent)
-        mock_context = Mock()
+        entity = AgentEntity(mock_agent, state_provider=_InMemoryStateProvider(thread_id="conv-1"))

-        result = await entity.run(
-            mock_context, {"message": "Test message", "thread_id": "conv-1", "correlationId": "corr-app-error-1"}
-        )
+        result = await entity.run({
+            "message": "Test message",
+            "correlationId": "corr-app-error-1",
+        })

        assert isinstance(result, AgentResponse)
        assert len(result.messages) == 1
@@ -710,7 +724,7 @@ class TestIncomingRequestParsing:

        request = Mock()
        request.params = {"thread_id": "query-thread"}
-        req_body = {}
+        req_body: dict[str, Any] = {}

        thread_id = app._resolve_thread_id(request, req_body)

@@ -777,7 +791,7 @@ class TestHttpRunRoute:

        assert run_request["message"] == "Plain text via HTTP"
        assert run_request["role"] == "user"
-        assert "thread_id" in run_request
+        assert "thread_id" not in run_request

    async def test_http_run_accept_header_returns_json(self) -> None:
        """Test that Accept header requesting JSON results in JSON response."""
@@ -913,9 +927,9 @@ class TestMCPToolEndpoint:
            patch.object(app, "durable_client_input") as client_mock,
        ):
            # Setup mock decorator chain
-            func_name_mock.return_value = lambda f: f
-            mcp_trigger_mock.return_value = lambda f: f
-            client_mock.return_value = lambda f: f
+            func_name_mock.return_value = _identity_decorator
+            mcp_trigger_mock.return_value = _identity_decorator
+            client_mock.return_value = _identity_decorator

            app._setup_mcp_tool_trigger(mock_agent.name, mock_agent.description)

@@ -938,11 +952,11 @@ class TestMCPToolEndpoint:
        app = AgentFunctionApp()

        with (
-            patch.object(app, "function_name", return_value=lambda f: f),
+            patch.object(app, "function_name", return_value=_identity_decorator),
            patch.object(app, "mcp_tool_trigger") as mcp_trigger_mock,
-            patch.object(app, "durable_client_input", return_value=lambda f: f),
+            patch.object(app, "durable_client_input", return_value=_identity_decorator),
        ):
-            mcp_trigger_mock.return_value = lambda f: f
+            mcp_trigger_mock.return_value = _identity_decorator

            app._setup_mcp_tool_trigger(mock_agent.name, None)

@@ -1128,10 +1142,10 @@ class TestMCPToolEndpoint:
        app = AgentFunctionApp(agents=[mock_agent], enable_mcp_tool_trigger=True)

        # Capture the health check handler function
-        captured_handler = None
+        captured_handler: Callable[[func.HttpRequest], func.HttpResponse] | None = None

-        def capture_decorator(*args, **kwargs):
-            def decorator(func):
+        def capture_decorator(*args: Any, **kwargs: Any) -> Callable[[TFunc], TFunc]:
+            def decorator(func: TFunc) -> TFunc:
                nonlocal captured_handler
                captured_handler = func
                return func
@@ -1,423 +1,32 @@
 # Copyright (c) Microsoft. All rights reserved.

-"""Unit tests for AgentEntity and entity operations.
+"""Unit tests for create_agent_entity factory function.

 Run with: pytest tests/test_entities.py -v
 """

-import asyncio
-from collections.abc import AsyncIterator, Callable
-from datetime import datetime
+from collections.abc import Callable
 from typing import Any, TypeVar
-from unittest.mock import AsyncMock, Mock, patch
+from unittest.mock import AsyncMock, Mock

 import pytest
-from agent_framework import AgentResponse, AgentResponseUpdate, ChatMessage, Role
-from pydantic import BaseModel
+from agent_framework import AgentResponse, ChatMessage, Role

-from agent_framework_azurefunctions._durable_agent_state import (
-    DurableAgentState,
-    DurableAgentStateData,
-    DurableAgentStateMessage,
-    DurableAgentStateRequest,
-    DurableAgentStateTextContent,
-)
-from agent_framework_azurefunctions._entities import AgentEntity, create_agent_entity
-from agent_framework_azurefunctions._models import RunRequest
+from agent_framework_azurefunctions._entities import create_agent_entity

 TFunc = TypeVar("TFunc", bound=Callable[..., Any])


-def _role_value(chat_message: DurableAgentStateMessage) -> str:
-    """Helper to extract the string role from a ChatMessage."""
-    role = getattr(chat_message, "role", None)
-    role_value = getattr(role, "value", role)
-    if role_value is None:
-        return ""
-    return str(role_value)
-
-
 def _agent_response(text: str | None) -> AgentResponse:
    """Create an AgentResponse with a single assistant message."""
    message = (
-        ChatMessage(role="assistant", text=text) if text is not None else ChatMessage(role="assistant", contents=[])
+        ChatMessage(role=Role.ASSISTANT, text=text)
+        if text is not None
+        else ChatMessage(role=Role.ASSISTANT, contents=[])
    )
    return AgentResponse(messages=[message])


-class RecordingCallback:
-    """Callback implementation capturing streaming and final responses for assertions."""
-
-    def __init__(self):
-        self.stream_mock = AsyncMock()
-        self.response_mock = AsyncMock()
-
-    async def on_streaming_response_update(
-        self,
-        update: AgentResponseUpdate,
-        context: Any,
-    ) -> None:
-        await self.stream_mock(update, context)
-
-    async def on_agent_response(self, response: AgentResponse, context: Any) -> None:
-        await self.response_mock(response, context)
-
-
-class EntityStructuredResponse(BaseModel):
-    answer: float
-
-
-class TestAgentEntityInit:
-    """Test suite for AgentEntity initialization."""
-
-    def test_init_creates_entity(self) -> None:
-        """Test that AgentEntity initializes correctly."""
-        mock_agent = Mock()
-
-        entity = AgentEntity(mock_agent)
-
-        assert entity.agent == mock_agent
-        assert len(entity.state.data.conversation_history) == 0
-        assert entity.state.data.extension_data is None
-        assert entity.state.schema_version == DurableAgentState.SCHEMA_VERSION
-
-    def test_init_stores_agent_reference(self) -> None:
-        """Test that the agent reference is stored correctly."""
-        mock_agent = Mock()
-        mock_agent.name = "TestAgent"
-
-        entity = AgentEntity(mock_agent)
-
-        assert entity.agent.name == "TestAgent"
-
-    def test_init_with_different_agent_types(self) -> None:
-        """Test initialization with different agent types."""
-        agent1 = Mock()
-        agent1.__class__.__name__ = "AzureOpenAIAgent"
-
-        agent2 = Mock()
-        agent2.__class__.__name__ = "CustomAgent"
-
-        entity1 = AgentEntity(agent1)
-        entity2 = AgentEntity(agent2)
-
-        assert entity1.agent.__class__.__name__ == "AzureOpenAIAgent"
-        assert entity2.agent.__class__.__name__ == "CustomAgent"
-
-
-class TestAgentEntityRunAgent:
-    """Test suite for the run_agent operation."""
-
-    async def test_run_executes_agent(self) -> None:
-        """Test that run executes the agent."""
-        mock_agent = Mock()
-        mock_response = _agent_response("Test response")
-        mock_agent.run = AsyncMock(return_value=mock_response)
-
-        entity = AgentEntity(mock_agent)
-        mock_context = Mock()
-
-        result = await entity.run(
-            mock_context, {"message": "Test message", "thread_id": "conv-123", "correlationId": "corr-entity-1"}
-        )
-
-        # Verify agent.run was called
-        mock_agent.run.assert_called_once()
-        _, kwargs = mock_agent.run.call_args
-        sent_messages: list[Any] = kwargs.get("messages")
-        assert len(sent_messages) == 1
-        sent_message = sent_messages[0]
-        assert isinstance(sent_message, ChatMessage)
-        assert getattr(sent_message, "text", None) == "Test message"
-        assert getattr(sent_message.role, "value", sent_message.role) == "user"
-
-        # Verify result
-        assert isinstance(result, AgentResponse)
-        assert result.text == "Test response"
-
-    async def test_run_agent_executes_agent(self) -> None:
-        """Test that run_agent executes the agent."""
-        mock_agent = Mock()
-        mock_response = _agent_response("Test response")
-        mock_agent.run = AsyncMock(return_value=mock_response)
-
-        entity = AgentEntity(mock_agent)
-        mock_context = Mock()
-
-        result = await entity.run_agent(
-            mock_context, {"message": "Test message", "thread_id": "conv-123", "correlationId": "corr-entity-1"}
-        )
-
-        # Verify agent.run was called
-        mock_agent.run.assert_called_once()
-        _, kwargs = mock_agent.run.call_args
-        sent_messages: list[Any] = kwargs.get("messages")
-        assert len(sent_messages) == 1
-        sent_message = sent_messages[0]
-        assert isinstance(sent_message, ChatMessage)
-        assert getattr(sent_message, "text", None) == "Test message"
-        assert getattr(sent_message.role, "value", sent_message.role) == "user"
-
-        # Verify result
-        assert isinstance(result, AgentResponse)
-        assert result.text == "Test response"
-
-    async def test_run_agent_streaming_callbacks_invoked(self) -> None:
-        """Ensure streaming updates trigger callbacks and run() is not used."""
-
-        updates = [
-            AgentResponseUpdate(text="Hello"),
-            AgentResponseUpdate(text=" world"),
-        ]
-
-        async def update_generator() -> AsyncIterator[AgentResponseUpdate]:
-            for update in updates:
-                yield update
-
-        mock_agent = Mock()
-        mock_agent.name = "StreamingAgent"
-        mock_agent.run_stream = Mock(return_value=update_generator())
-        mock_agent.run = AsyncMock(side_effect=AssertionError("run() should not be called when streaming succeeds"))
-
-        callback = RecordingCallback()
-        entity = AgentEntity(mock_agent, callback=callback)
-        mock_context = Mock()
-
-        result = await entity.run(
-            mock_context,
-            {
-                "message": "Tell me something",
-                "thread_id": "session-1",
-                "correlationId": "corr-stream-1",
-            },
-        )
-
-        assert isinstance(result, AgentResponse)
-        assert "Hello" in result.text
-        assert callback.stream_mock.await_count == len(updates)
-        assert callback.response_mock.await_count == 1
-        mock_agent.run.assert_not_called()
-
-        # Validate callback arguments
-        stream_calls = callback.stream_mock.await_args_list
-        for expected_update, recorded_call in zip(updates, stream_calls, strict=True):
-            assert recorded_call.args[0] is expected_update
-            context = recorded_call.args[1]
-            assert context.agent_name == "StreamingAgent"
-            assert context.correlation_id == "corr-stream-1"
-            assert context.thread_id == "session-1"
-            assert context.request_message == "Tell me something"
-
-        final_call = callback.response_mock.await_args
-        assert final_call is not None
-        final_response, final_context = final_call.args
-        assert final_context.agent_name == "StreamingAgent"
-        assert final_context.correlation_id == "corr-stream-1"
-        assert final_context.thread_id == "session-1"
-        assert final_context.request_message == "Tell me something"
-        assert getattr(final_response, "text", "").strip()
-
-    async def test_run_agent_final_callback_without_streaming(self) -> None:
-        """Ensure the final callback fires even when streaming is unavailable."""
-
-        mock_agent = Mock()
-        mock_agent.name = "NonStreamingAgent"
-        mock_agent.run_stream = None
-        agent_response = _agent_response("Final response")
-        mock_agent.run = AsyncMock(return_value=agent_response)
-
-        callback = RecordingCallback()
-        entity = AgentEntity(mock_agent, callback=callback)
-        mock_context = Mock()
-
-        result = await entity.run(
-            mock_context,
-            {
-                "message": "Hi",
-                "thread_id": "session-2",
-                "correlationId": "corr-final-1",
-            },
-        )
-
-        assert isinstance(result, AgentResponse)
-        assert result.text == "Final response"
-        assert callback.stream_mock.await_count == 0
-        assert callback.response_mock.await_count == 1
-
-        final_call = callback.response_mock.await_args
-        assert final_call is not None
-        assert final_call.args[0] is agent_response
-        final_context = final_call.args[1]
-        assert final_context.agent_name == "NonStreamingAgent"
-        assert final_context.correlation_id == "corr-final-1"
-        assert final_context.thread_id == "session-2"
-        assert final_context.request_message == "Hi"
-
-    async def test_run_agent_updates_conversation_history(self) -> None:
-        """Test that run_agent updates the conversation history."""
-        mock_agent = Mock()
-        mock_response = _agent_response("Agent response")
-        mock_agent.run = AsyncMock(return_value=mock_response)
-
-        entity = AgentEntity(mock_agent)
-        mock_context = Mock()
-
-        await entity.run(
-            mock_context, {"message": "User message", "thread_id": "conv-1", "correlationId": "corr-entity-2"}
-        )
-
-        # Should have 1 entry: user message + assistant response
-        user_history = entity.state.data.conversation_history[0].messages
-        assistant_history = entity.state.data.conversation_history[1].messages
-
-        assert len(user_history) == 1
-
-        user_msg = user_history[0]
-        assert _role_value(user_msg) == "user"
-        assert user_msg.text == "User message"
-
-        assistant_msg = assistant_history[0]
-        assert _role_value(assistant_msg) == "assistant"
-        assert assistant_msg.text == "Agent response"
-
-    async def test_run_agent_increments_message_count(self) -> None:
-        """Test that run_agent increments the message count."""
-        mock_agent = Mock()
-        mock_agent.run = AsyncMock(return_value=_agent_response("Response"))
-
-        entity = AgentEntity(mock_agent)
-        mock_context = Mock()
-
-        assert len(entity.state.data.conversation_history) == 0
-
-        await entity.run(
-            mock_context, {"message": "Message 1", "thread_id": "conv-1", "correlationId": "corr-entity-3a"}
-        )
-        assert len(entity.state.data.conversation_history) == 2
-
-        await entity.run(
-            mock_context, {"message": "Message 2", "thread_id": "conv-1", "correlationId": "corr-entity-3b"}
-        )
-        assert len(entity.state.data.conversation_history) == 4
-
-        await entity.run(
-            mock_context, {"message": "Message 3", "thread_id": "conv-1", "correlationId": "corr-entity-3c"}
-        )
-        assert len(entity.state.data.conversation_history) == 6
-
-    async def test_run_agent_with_none_thread_id(self) -> None:
-        """Test run_agent with a None thread identifier."""
-        mock_agent = Mock()
-        mock_agent.run = AsyncMock(return_value=_agent_response("Response"))
-
-        entity = AgentEntity(mock_agent)
-        mock_context = Mock()
-
-        with pytest.raises(ValueError, match="thread_id"):
-            await entity.run(mock_context, {"message": "Message", "thread_id": None, "correlationId": "corr-entity-5"})
-
-    async def test_run_agent_multiple_conversations(self) -> None:
-        """Test that run_agent maintains history across multiple messages."""
-        mock_agent = Mock()
-        mock_agent.run = AsyncMock(return_value=_agent_response("Response"))
-
-        entity = AgentEntity(mock_agent)
-        mock_context = Mock()
-
-        # Send multiple messages
-        await entity.run(
-            mock_context, {"message": "Message 1", "thread_id": "conv-1", "correlationId": "corr-entity-8a"}
-        )
-        await entity.run(
-            mock_context, {"message": "Message 2", "thread_id": "conv-1", "correlationId": "corr-entity-8b"}
-        )
-        await entity.run(
-            mock_context, {"message": "Message 3", "thread_id": "conv-1", "correlationId": "corr-entity-8c"}
-        )
-
-        history = entity.state.data.conversation_history
-        assert len(history) == 6
-        assert entity.state.message_count == 6
-
-
-class TestAgentEntityReset:
-    """Test suite for the reset operation."""
-
-    def test_reset_clears_conversation_history(self) -> None:
-        """Test that reset clears the conversation history."""
-        mock_agent = Mock()
-        entity = AgentEntity(mock_agent)
-
-        # Add some history with proper DurableAgentStateEntry objects
-        entity.state.data.conversation_history = [
-            DurableAgentStateRequest(
-                correlation_id="test-1",
-                created_at=datetime.now(),
-                messages=[
-                    DurableAgentStateMessage(
-                        role="user",
-                        contents=[DurableAgentStateTextContent(text="msg1")],
-                    )
-                ],
-            ),
-        ]
-
-        mock_context = Mock()
-        entity.reset(mock_context)
-
-        assert entity.state.data.conversation_history == []
-
-    def test_reset_with_extension_data(self) -> None:
-        """Test that reset works when entity has extension data."""
-        mock_agent = Mock()
-        entity = AgentEntity(mock_agent)
-
-        # Set up some initial state with conversation history
-        entity.state.data = DurableAgentStateData(conversation_history=[], extension_data={"some_key": "some_value"})
-
-        mock_context = Mock()
-        entity.reset(mock_context)
-
-        assert len(entity.state.data.conversation_history) == 0
-
-    def test_reset_clears_message_count(self) -> None:
-        """Test that reset clears the message count."""
-        mock_agent = Mock()
-        entity = AgentEntity(mock_agent)
-
-        mock_context = Mock()
-        entity.reset(mock_context)
-
-        assert len(entity.state.data.conversation_history) == 0
-
-    async def test_reset_after_conversation(self) -> None:
-        """Test reset after a full conversation."""
-        mock_agent = Mock()
-        mock_agent.run = AsyncMock(return_value=_agent_response("Response"))
-
-        entity = AgentEntity(mock_agent)
-        mock_context = Mock()
-
-        # Have a conversation
-        await entity.run(
-            mock_context, {"message": "Message 1", "thread_id": "conv-1", "correlationId": "corr-entity-10a"}
-        )
-        await entity.run(
-            mock_context, {"message": "Message 2", "thread_id": "conv-1", "correlationId": "corr-entity-10b"}
-        )
-
-        # Verify state before reset
-        assert entity.state.message_count == 4
-        assert len(entity.state.data.conversation_history) == 4
-
-        # Reset
-        entity.reset(mock_context)
-
-        # Verify state after reset
-        assert entity.state.message_count == 0
-        assert len(entity.state.data.conversation_history) == 0
-
-
 class TestCreateAgentEntity:
    """Test suite for the create_agent_entity factory function."""

@@ -439,9 +48,9 @@ class TestCreateAgentEntity:
        # Mock context
        mock_context = Mock()
        mock_context.operation_name = "run"
+        mock_context.entity_key = "conv-123"
        mock_context.get_input.return_value = {
            "message": "Test message",
-            "thread_id": "conv-123",
            "correlationId": "corr-entity-factory",
        }
        mock_context.get_state.return_value = None
@@ -535,7 +144,7 @@ class TestCreateAgentEntity:
        assert state["data"] == {"conversationHistory": []}

    def test_entity_function_restores_existing_state(self) -> None:
-        """Test that the entity function restores existing state."""
+        """Test that the entity function can operate when existing state is present."""
        mock_agent = Mock()

        entity_function = create_agent_entity(mock_agent)
@@ -584,482 +193,14 @@ class TestCreateAgentEntity:
        mock_context.operation_name = "reset"
        mock_context.get_state.return_value = existing_state

-        with patch.object(DurableAgentState, "from_dict", wraps=DurableAgentState.from_dict) as from_dict_mock:
-            entity_function(mock_context)
-
-        from_dict_mock.assert_called_once_with(existing_state)
-
-
-class TestErrorHandling:
-    """Test suite for error handling in entities."""
-
-    async def test_run_agent_handles_agent_exception(self) -> None:
-        """Test that run_agent handles agent exceptions."""
-        mock_agent = Mock()
-        mock_agent.run = AsyncMock(side_effect=Exception("Agent failed"))
-
-        entity = AgentEntity(mock_agent)
-        mock_context = Mock()
-
-        result = await entity.run(
-            mock_context, {"message": "Message", "thread_id": "conv-1", "correlationId": "corr-entity-error-1"}
-        )
-
-        assert isinstance(result, AgentResponse)
-        assert len(result.messages) == 1
-        content = result.messages[0].contents[0]
-        assert content.type == "error"
-        assert "Agent failed" in (content.message or "")
-        assert content.error_code == "Exception"
-
-    async def test_run_agent_handles_value_error(self) -> None:
-        """Test that run_agent handles ValueError instances."""
-        mock_agent = Mock()
-        mock_agent.run = AsyncMock(side_effect=ValueError("Invalid input"))
-
-        entity = AgentEntity(mock_agent)
-        mock_context = Mock()
-
-        result = await entity.run(
-            mock_context, {"message": "Message", "thread_id": "conv-1", "correlationId": "corr-entity-error-2"}
-        )
-
-        assert isinstance(result, AgentResponse)
-        assert len(result.messages) == 1
-        content = result.messages[0].contents[0]
-        assert content.type == "error"
-        assert content.error_code == "ValueError"
-        assert "Invalid input" in str(content.message)
-
-    async def test_run_agent_handles_timeout_error(self) -> None:
-        """Test that run_agent handles TimeoutError instances."""
-        mock_agent = Mock()
-        mock_agent.run = AsyncMock(side_effect=TimeoutError("Request timeout"))
-
-        entity = AgentEntity(mock_agent)
-        mock_context = Mock()
-
-        result = await entity.run(
-            mock_context, {"message": "Message", "thread_id": "conv-1", "correlationId": "corr-entity-error-3"}
-        )
-
-        assert isinstance(result, AgentResponse)
-        assert len(result.messages) == 1
-        content = result.messages[0].contents[0]
-        assert content.type == "error"
-        assert content.error_code == "TimeoutError"
-
-    def test_entity_function_handles_exception_in_operation(self) -> None:
-        """Test that the entity function handles exceptions gracefully."""
-        mock_agent = Mock()
-
-        entity_function = create_agent_entity(mock_agent)
-
-        mock_context = Mock()
-        mock_context.operation_name = "run"
-        mock_context.get_input.side_effect = Exception("Input error")
-        mock_context.get_state.return_value = None
-
-        # Execute - should not raise
        entity_function(mock_context)

-        # Verify error was set
        assert mock_context.set_result.called
-        result = mock_context.set_result.call_args[0][0]
-        assert "error" in result

-    async def test_run_agent_preserves_message_on_error(self) -> None:
-        """Test that run_agent preserves message information on error."""
-        mock_agent = Mock()
-        mock_agent.run = AsyncMock(side_effect=Exception("Error"))
-
-        entity = AgentEntity(mock_agent)
-        mock_context = Mock()
-
-        result = await entity.run(
-            mock_context,
-            {"message": "Test message", "thread_id": "conv-123", "correlationId": "corr-entity-error-4"},
-        )
-
-        # Even on error, message info should be preserved
-        assert isinstance(result, AgentResponse)
-        assert len(result.messages) == 1
-        content = result.messages[0].contents[0]
-        assert content.type == "error"
-
-
-class TestConversationHistory:
-    """Test suite for conversation history tracking."""
-
-    async def test_conversation_history_has_timestamps(self) -> None:
-        """Test that conversation history entries include timestamps."""
-        mock_agent = Mock()
-        mock_agent.run = AsyncMock(return_value=_agent_response("Response"))
-
-        entity = AgentEntity(mock_agent)
-        mock_context = Mock()
-
-        await entity.run(
-            mock_context, {"message": "Message", "thread_id": "conv-1", "correlationId": "corr-entity-history-1"}
-        )
-
-        # Check both user and assistant messages have timestamps
-        for entry in entity.state.data.conversation_history:
-            timestamp = entry.created_at
-            assert timestamp is not None
-            # Verify timestamp is in ISO format
-            datetime.fromisoformat(str(timestamp))
-
-    async def test_conversation_history_ordering(self) -> None:
-        """Test that conversation history maintains the correct order."""
-        mock_agent = Mock()
-
-        entity = AgentEntity(mock_agent)
-        mock_context = Mock()
-
-        # Send multiple messages with different responses
-        mock_agent.run = AsyncMock(return_value=_agent_response("Response 1"))
-        await entity.run(
-            mock_context,
-            {"message": "Message 1", "thread_id": "conv-1", "correlationId": "corr-entity-history-2a"},
-        )
-
-        mock_agent.run = AsyncMock(return_value=_agent_response("Response 2"))
-        await entity.run(
-            mock_context,
-            {"message": "Message 2", "thread_id": "conv-1", "correlationId": "corr-entity-history-2b"},
-        )
-
-        mock_agent.run = AsyncMock(return_value=_agent_response("Response 3"))
-        await entity.run(
-            mock_context,
-            {"message": "Message 3", "thread_id": "conv-1", "correlationId": "corr-entity-history-2c"},
-        )
-
-        # Verify order
-        history = entity.state.data.conversation_history
-        # Each conversation turn creates 2 entries: request and response
-        assert history[0].messages[0].text == "Message 1"  # Request 1
-        assert history[1].messages[0].text == "Response 1"  # Response 1
-        assert history[2].messages[0].text == "Message 2"  # Request 2
-        assert history[3].messages[0].text == "Response 2"  # Response 2
-        assert history[4].messages[0].text == "Message 3"  # Request 3
-        assert history[5].messages[0].text == "Response 3"  # Response 3
-
-    async def test_conversation_history_role_alternation(self) -> None:
-        """Test that conversation history alternates between user and assistant roles."""
-        mock_agent = Mock()
-        mock_agent.run = AsyncMock(return_value=_agent_response("Response"))
-
-        entity = AgentEntity(mock_agent)
-        mock_context = Mock()
-
-        await entity.run(
-            mock_context,
-            {"message": "Message 1", "thread_id": "conv-1", "correlationId": "corr-entity-history-3a"},
-        )
-        await entity.run(
-            mock_context,
-            {"message": "Message 2", "thread_id": "conv-1", "correlationId": "corr-entity-history-3b"},
-        )
-
-        # Check role alternation
-        history = entity.state.data.conversation_history
-        # Each conversation turn creates 2 entries: request and response
-        assert history[0].messages[0].role == "user"  # Request 1
-        assert history[1].messages[0].role == "assistant"  # Response 1
-        assert history[2].messages[0].role == "user"  # Request 2
-        assert history[3].messages[0].role == "assistant"  # Response 2
-
-
-class TestRunRequestSupport:
-    """Test suite for RunRequest support in entities."""
-
-    async def test_run_agent_with_run_request_object(self) -> None:
-        """Test run_agent with a RunRequest object."""
-        mock_agent = Mock()
-        mock_agent.run = AsyncMock(return_value=_agent_response("Response"))
-
-        entity = AgentEntity(mock_agent)
-        mock_context = Mock()
-
-        request = RunRequest(
-            message="Test message",
-            thread_id="conv-123",
-            role=Role.USER,
-            enable_tool_calls=True,
-            correlation_id="corr-runreq-1",
-        )
-
-        result = await entity.run(mock_context, request)
-
-        assert isinstance(result, AgentResponse)
-        assert result.text == "Response"
-
-    async def test_run_agent_with_dict_request(self) -> None:
-        """Test run_agent with a dictionary request."""
-        mock_agent = Mock()
-        mock_agent.run = AsyncMock(return_value=_agent_response("Response"))
-
-        entity = AgentEntity(mock_agent)
-        mock_context = Mock()
-
-        request_dict = {
-            "message": "Test message",
-            "thread_id": "conv-456",
-            "role": "system",
-            "enable_tool_calls": False,
-            "correlationId": "corr-runreq-2",
-        }
-
-        result = await entity.run(mock_context, request_dict)
-
-        assert isinstance(result, AgentResponse)
-        assert result.text == "Response"
-
-    async def test_run_agent_with_string_raises_without_correlation(self) -> None:
-        """Test that run_agent rejects legacy string input without correlation ID."""
-        mock_agent = Mock()
-        mock_agent.run = AsyncMock(return_value=_agent_response("Response"))
-
-        entity = AgentEntity(mock_agent)
-        mock_context = Mock()
-
-        with pytest.raises(ValueError):
-            await entity.run(mock_context, "Simple message")
-
-    async def test_run_agent_stores_role_in_history(self) -> None:
-        """Test that run_agent stores the role in conversation history."""
-        mock_agent = Mock()
-        mock_agent.run = AsyncMock(return_value=_agent_response("Response"))
-
-        entity = AgentEntity(mock_agent)
-        mock_context = Mock()
-
-        # Send as system role
-        request = RunRequest(
-            message="System message",
-            thread_id="conv-runreq-3",
-            role=Role.SYSTEM,
-            correlation_id="corr-runreq-3",
-        )
-
-        await entity.run(mock_context, request)
-
-        # Check that system role was stored
-        history = entity.state.data.conversation_history
-        assert history[0].messages[0].role == "system"
-        assert history[0].messages[0].text == "System message"
-
-    async def test_run_agent_with_response_format(self) -> None:
-        """Test run_agent with a JSON response format."""
-        mock_agent = Mock()
-        # Return JSON response
-        mock_agent.run = AsyncMock(return_value=_agent_response('{"answer": 42}'))
-
-        entity = AgentEntity(mock_agent)
-        mock_context = Mock()
-
-        request = RunRequest(
-            message="What is the answer?",
-            thread_id="conv-runreq-4",
-            response_format=EntityStructuredResponse,
-            correlation_id="corr-runreq-4",
-        )
-
-        result = await entity.run(mock_context, request)
-
-        assert isinstance(result, AgentResponse)
-        assert result.text == '{"answer": 42}'
-        assert result.value is None
-
-    async def test_run_agent_disable_tool_calls(self) -> None:
-        """Test run_agent with tool calls disabled."""
-        mock_agent = Mock()
-        mock_agent.run = AsyncMock(return_value=_agent_response("Response"))
-
-        entity = AgentEntity(mock_agent)
-        mock_context = Mock()
-
-        request = RunRequest(
-            message="Test", thread_id="conv-runreq-5", enable_tool_calls=False, correlation_id="corr-runreq-5"
-        )
-
-        result = await entity.run(mock_context, request)
-
-        assert isinstance(result, AgentResponse)
-        # Agent should have been called (tool disabling is framework-dependent)
-        mock_agent.run.assert_called_once()
-
-    async def test_entity_function_with_run_request_dict(self) -> None:
-        """Test that the entity function handles the RunRequest dict format."""
-        mock_agent = Mock()
-        mock_agent.run = AsyncMock(return_value=_agent_response("Response"))
-
-        entity_function = create_agent_entity(mock_agent)
-
-        mock_context = Mock()
-        mock_context.operation_name = "run"
-        mock_context.get_input.return_value = {
-            "message": "Test message",
-            "thread_id": "conv-789",
-            "role": "user",
-            "enable_tool_calls": True,
-            "correlationId": "corr-runreq-6",
-        }
-        mock_context.get_state.return_value = None
-
-        await asyncio.to_thread(entity_function, mock_context)
-
-        # Verify result was set
-        assert mock_context.set_result.called
-        result = mock_context.set_result.call_args[0][0]
-        assert isinstance(result, dict)
-
-        # Check if messages are present
-        assert "messages" in result
-        assert len(result["messages"]) > 0
-        message = result["messages"][0]
-
-        # Check for text in various possible locations
-        text_found = False
-        if "text" in message and message["text"] == "Response":
-            text_found = True
-        elif "contents" in message:
-            for content in message["contents"]:
-                if isinstance(content, dict) and content.get("text") == "Response":
-                    text_found = True
-                    break
-
-        assert text_found, f"Response text not found in message: {message}"
-
-
-class TestDurableAgentStateRequestOrchestrationId:
-    """Test suite for DurableAgentStateRequest orchestration_id field."""
-
-    def test_request_with_orchestration_id(self) -> None:
-        """Test creating a request with an orchestration_id."""
-        request = DurableAgentStateRequest(
-            correlation_id="corr-123",
-            created_at=datetime.now(),
-            messages=[
-                DurableAgentStateMessage(
-                    role="user",
-                    contents=[DurableAgentStateTextContent(text="test")],
-                )
-            ],
-            orchestration_id="orch-456",
-        )
-
-        assert request.orchestration_id == "orch-456"
-
-    def test_request_to_dict_includes_orchestration_id(self) -> None:
-        """Test that to_dict includes orchestrationId when set."""
-        request = DurableAgentStateRequest(
-            correlation_id="corr-123",
-            created_at=datetime.now(),
-            messages=[
-                DurableAgentStateMessage(
-                    role="user",
-                    contents=[DurableAgentStateTextContent(text="test")],
-                )
-            ],
-            orchestration_id="orch-789",
-        )
-
-        data = request.to_dict()
-
-        assert "orchestrationId" in data
-        assert data["orchestrationId"] == "orch-789"
-
-    def test_request_to_dict_excludes_orchestration_id_when_none(self) -> None:
-        """Test that to_dict excludes orchestrationId when not set."""
-        request = DurableAgentStateRequest(
-            correlation_id="corr-123",
-            created_at=datetime.now(),
-            messages=[
-                DurableAgentStateMessage(
-                    role="user",
-                    contents=[DurableAgentStateTextContent(text="test")],
-                )
-            ],
-        )
-
-        data = request.to_dict()
-
-        assert "orchestrationId" not in data
-
-    def test_request_from_dict_with_orchestration_id(self) -> None:
-        """Test from_dict correctly parses orchestrationId."""
-        data = {
-            "$type": "request",
-            "correlationId": "corr-123",
-            "createdAt": "2024-01-01T00:00:00Z",
-            "messages": [{"role": "user", "contents": [{"$type": "text", "text": "test"}]}],
-            "orchestrationId": "orch-from-dict",
-        }
-
-        request = DurableAgentStateRequest.from_dict(data)
-
-        assert request.orchestration_id == "orch-from-dict"
-
-    def test_request_from_run_request_with_orchestration_id(self) -> None:
-        """Test from_run_request correctly transfers orchestration_id."""
-        run_request = RunRequest(
-            message="test message",
-            correlation_id="corr-run",
-            orchestration_id="orch-from-run-request",
-        )
-
-        durable_request = DurableAgentStateRequest.from_run_request(run_request)
-
-        assert durable_request.orchestration_id == "orch-from-run-request"
-
-    def test_request_from_run_request_without_orchestration_id(self) -> None:
-        """Test from_run_request correctly handles missing orchestration_id."""
-        run_request = RunRequest(
-            message="test message",
-            correlation_id="corr-run",
-        )
-
-        durable_request = DurableAgentStateRequest.from_run_request(run_request)
-
-        assert durable_request.orchestration_id is None
-
-
-class TestDurableAgentStateMessageCreatedAt:
-    """Test suite for DurableAgentStateMessage created_at field handling."""
-
-    def test_message_from_run_request_without_created_at_preserves_none(self) -> None:
-        """Test from_run_request preserves None created_at instead of defaulting to current time.
-
-        When a RunRequest has no created_at value, the resulting DurableAgentStateMessage
-        should also have None for created_at, not default to current UTC time.
-        """
-        run_request = RunRequest(
-            message="test message",
-            correlation_id="corr-run",
-            created_at=None,  # Explicitly None
-        )
-
-        durable_message = DurableAgentStateMessage.from_run_request(run_request)
-
-        assert durable_message.created_at is None
-
-    def test_message_from_run_request_with_created_at_parses_correctly(self) -> None:
-        """Test from_run_request correctly parses a valid created_at timestamp."""
-        run_request = RunRequest(
-            message="test message",
-            correlation_id="corr-run",
-            created_at="2024-01-15T10:30:00Z",
-        )
-
-        durable_message = DurableAgentStateMessage.from_run_request(run_request)
-
-        assert durable_message.created_at is not None
-        assert durable_message.created_at.year == 2024
-        assert durable_message.created_at.month == 1
-        assert durable_message.created_at.day == 15
+        # Reset should clear history and persist via set_state
+        assert mock_context.set_state.called
+        persisted_state = mock_context.set_state.call_args[0][0]
+        assert persisted_state["data"]["conversationHistory"] == []


 if __name__ == "__main__":
@@ -1,447 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-
-"""Unit tests for data models (AgentSessionId, RunRequest, AgentResponse)."""
-
-import azure.durable_functions as df
-import pytest
-from agent_framework import Role
-from pydantic import BaseModel
-
-from agent_framework_azurefunctions._models import AgentSessionId, RunRequest
-
-
-class ModuleStructuredResponse(BaseModel):
-    value: int
-
-
-class TestAgentSessionId:
-    """Test suite for AgentSessionId."""
-
-    def test_init_creates_session_id(self) -> None:
-        """Test that AgentSessionId initializes correctly."""
-        session_id = AgentSessionId(name="AgentEntity", key="test-key-123")
-
-        assert session_id.name == "AgentEntity"
-        assert session_id.key == "test-key-123"
-
-    def test_with_random_key_generates_guid(self) -> None:
-        """Test that with_random_key generates a GUID."""
-        session_id = AgentSessionId.with_random_key(name="AgentEntity")
-
-        assert session_id.name == "AgentEntity"
-        assert len(session_id.key) == 32  # UUID hex is 32 chars
-        # Verify it's a valid hex string
-        int(session_id.key, 16)
-
-    def test_with_random_key_unique_keys(self) -> None:
-        """Test that with_random_key generates unique keys."""
-        session_id1 = AgentSessionId.with_random_key(name="AgentEntity")
-        session_id2 = AgentSessionId.with_random_key(name="AgentEntity")
-
-        assert session_id1.key != session_id2.key
-
-    def test_to_entity_id_conversion(self) -> None:
-        """Test conversion to EntityId."""
-        session_id = AgentSessionId(name="AgentEntity", key="test-key")
-        entity_id = session_id.to_entity_id()
-
-        assert isinstance(entity_id, df.EntityId)
-        assert entity_id.name == "dafx-AgentEntity"
-        assert entity_id.key == "test-key"
-
-    def test_from_entity_id_conversion(self) -> None:
-        """Test creation from EntityId."""
-        entity_id = df.EntityId(name="dafx-AgentEntity", key="test-key")
-        session_id = AgentSessionId.from_entity_id(entity_id)
-
-        assert isinstance(session_id, AgentSessionId)
-        assert session_id.name == "AgentEntity"
-        assert session_id.key == "test-key"
-
-    def test_round_trip_entity_id_conversion(self) -> None:
-        """Test round-trip conversion to and from EntityId."""
-        original = AgentSessionId(name="AgentEntity", key="test-key")
-        entity_id = original.to_entity_id()
-        restored = AgentSessionId.from_entity_id(entity_id)
-
-        assert restored.name == original.name
-        assert restored.key == original.key
-
-    def test_str_representation(self) -> None:
-        """Test string representation."""
-        session_id = AgentSessionId(name="AgentEntity", key="test-key-123")
-        str_repr = str(session_id)
-
-        assert str_repr == "@AgentEntity@test-key-123"
-
-    def test_repr_representation(self) -> None:
-        """Test repr representation."""
-        session_id = AgentSessionId(name="AgentEntity", key="test-key")
-        repr_str = repr(session_id)
-
-        assert "AgentSessionId" in repr_str
-        assert "AgentEntity" in repr_str
-        assert "test-key" in repr_str
-
-    def test_parse_valid_session_id(self) -> None:
-        """Test parsing valid session ID string."""
-        session_id = AgentSessionId.parse("@AgentEntity@test-key-123")
-
-        assert session_id.name == "AgentEntity"
-        assert session_id.key == "test-key-123"
-
-    def test_parse_invalid_format_no_prefix(self) -> None:
-        """Test parsing invalid format without @ prefix."""
-        with pytest.raises(ValueError) as exc_info:
-            AgentSessionId.parse("AgentEntity@test-key")
-
-        assert "Invalid agent session ID format" in str(exc_info.value)
-
-    def test_parse_invalid_format_single_part(self) -> None:
-        """Test parsing invalid format with single part."""
-        with pytest.raises(ValueError) as exc_info:
-            AgentSessionId.parse("@AgentEntity")
-
-        assert "Invalid agent session ID format" in str(exc_info.value)
-
-    def test_parse_with_multiple_at_signs_in_key(self) -> None:
-        """Test parsing with @ signs in the key."""
-        session_id = AgentSessionId.parse("@AgentEntity@key-with@symbols")
-
-        assert session_id.name == "AgentEntity"
-        assert session_id.key == "key-with@symbols"
-
-    def test_parse_round_trip(self) -> None:
-        """Test round-trip parse and string conversion."""
-        original = AgentSessionId(name="AgentEntity", key="test-key")
-        str_repr = str(original)
-        parsed = AgentSessionId.parse(str_repr)
-
-        assert parsed.name == original.name
-        assert parsed.key == original.key
-
-    def test_parse_with_agent_name_override(self) -> None:
-        """Test parsing @name@key format with agent_name parameter overrides the name."""
-        session_id = AgentSessionId.parse("@OriginalAgent@test-key-123", agent_name="OverriddenAgent")
-
-        assert session_id.name == "OverriddenAgent"
-        assert session_id.key == "test-key-123"
-
-    def test_parse_without_agent_name_uses_parsed_name(self) -> None:
-        """Test parsing @name@key format without agent_name uses name from string."""
-        session_id = AgentSessionId.parse("@ParsedAgent@test-key-123")
-
-        assert session_id.name == "ParsedAgent"
-        assert session_id.key == "test-key-123"
-
-    def test_parse_plain_string_with_agent_name(self) -> None:
-        """Test parsing plain string with agent_name uses entire string as key."""
-        session_id = AgentSessionId.parse("simple-thread-123", agent_name="TestAgent")
-
-        assert session_id.name == "TestAgent"
-        assert session_id.key == "simple-thread-123"
-
-    def test_parse_plain_string_without_agent_name_raises(self) -> None:
-        """Test parsing plain string without agent_name raises ValueError."""
-        with pytest.raises(ValueError) as exc_info:
-            AgentSessionId.parse("simple-thread-123")
-
-        assert "Invalid agent session ID format" in str(exc_info.value)
-
-    def test_to_entity_name_adds_prefix(self) -> None:
-        """Test that to_entity_name adds the dafx- prefix."""
-        entity_name = AgentSessionId.to_entity_name("TestAgent")
-        assert entity_name == "dafx-TestAgent"
-
-    def test_from_entity_id_strips_prefix(self) -> None:
-        """Test that from_entity_id strips the dafx- prefix."""
-        entity_id = df.EntityId(name="dafx-TestAgent", key="key123")
-        session_id = AgentSessionId.from_entity_id(entity_id)
-
-        assert session_id.name == "TestAgent"
-        assert session_id.key == "key123"
-
-    def test_from_entity_id_raises_without_prefix(self) -> None:
-        """Test that from_entity_id raises ValueError when entity name lacks the prefix."""
-        entity_id = df.EntityId(name="TestAgent", key="key123")
-
-        with pytest.raises(ValueError) as exc_info:
-            AgentSessionId.from_entity_id(entity_id)
-
-        assert "not a valid agent session ID" in str(exc_info.value)
-        assert "dafx-" in str(exc_info.value)
-
-
-class TestRunRequest:
-    """Test suite for RunRequest."""
-
-    def test_init_with_defaults(self) -> None:
-        """Test RunRequest initialization with defaults."""
-        request = RunRequest(message="Hello", thread_id="thread-default")
-
-        assert request.message == "Hello"
-        assert request.role == Role.USER
-        assert request.response_format is None
-        assert request.enable_tool_calls is True
-        assert request.thread_id == "thread-default"
-
-    def test_init_with_all_fields(self) -> None:
-        """Test RunRequest initialization with all fields."""
-        schema = ModuleStructuredResponse
-        request = RunRequest(
-            message="Hello",
-            thread_id="thread-123",
-            role=Role.SYSTEM,
-            response_format=schema,
-            enable_tool_calls=False,
-        )
-
-        assert request.message == "Hello"
-        assert request.role == Role.SYSTEM
-        assert request.response_format is schema
-        assert request.enable_tool_calls is False
-        assert request.thread_id == "thread-123"
-
-    def test_init_coerces_string_role(self) -> None:
-        """Ensure string role values are coerced into Role instances."""
-        request = RunRequest(message="Hello", thread_id="thread-str-role", role="system")  # type: ignore[arg-type]
-
-        assert request.role == Role.SYSTEM
-
-    def test_to_dict_with_defaults(self) -> None:
-        """Test to_dict with default values."""
-        request = RunRequest(message="Test message", thread_id="thread-to-dict")
-        data = request.to_dict()
-
-        assert data["message"] == "Test message"
-        assert data["enable_tool_calls"] is True
-        assert data["role"] == "user"
-        assert "response_format" not in data or data["response_format"] is None
-        assert data["thread_id"] == "thread-to-dict"
-
-    def test_to_dict_with_all_fields(self) -> None:
-        """Test to_dict with all fields."""
-        schema = ModuleStructuredResponse
-        request = RunRequest(
-            message="Hello",
-            thread_id="thread-456",
-            role=Role.ASSISTANT,
-            response_format=schema,
-            enable_tool_calls=False,
-        )
-        data = request.to_dict()
-
-        assert data["message"] == "Hello"
-        assert data["role"] == "assistant"
-        assert data["response_format"]["__response_schema_type__"] == "pydantic_model"
-        assert data["response_format"]["module"] == schema.__module__
-        assert data["response_format"]["qualname"] == schema.__qualname__
-        assert data["enable_tool_calls"] is False
-        assert data["thread_id"] == "thread-456"
-
-    def test_from_dict_with_defaults(self) -> None:
-        """Test from_dict with minimal data."""
-        data = {"message": "Hello", "thread_id": "thread-from-dict"}
-        request = RunRequest.from_dict(data)
-
-        assert request.message == "Hello"
-        assert request.role == Role.USER
-        assert request.enable_tool_calls is True
-        assert request.thread_id == "thread-from-dict"
-
-    def test_from_dict_with_all_fields(self) -> None:
-        """Test from_dict with all fields."""
-        data = {
-            "message": "Test",
-            "role": "system",
-            "response_format": {
-                "__response_schema_type__": "pydantic_model",
-                "module": ModuleStructuredResponse.__module__,
-                "qualname": ModuleStructuredResponse.__qualname__,
-            },
-            "enable_tool_calls": False,
-            "thread_id": "thread-789",
-        }
-        request = RunRequest.from_dict(data)
-
-        assert request.message == "Test"
-        assert request.role == Role.SYSTEM
-        assert request.response_format is ModuleStructuredResponse
-        assert request.enable_tool_calls is False
-        assert request.thread_id == "thread-789"
-
-    def test_from_dict_with_unknown_role_preserves_value(self) -> None:
-        """Test from_dict keeps custom roles intact."""
-        data = {"message": "Test", "role": "reviewer", "thread_id": "thread-with-custom-role"}
-        request = RunRequest.from_dict(data)
-
-        assert request.role.value == "reviewer"
-        assert request.role != Role.USER
-
-    def test_from_dict_empty_message(self) -> None:
-        """Test from_dict with empty message."""
-        data = {"thread_id": "thread-empty"}
-        request = RunRequest.from_dict(data)
-
-        assert request.message == ""
-        assert request.role == Role.USER
-        assert request.thread_id == "thread-empty"
-
-    def test_round_trip_dict_conversion(self) -> None:
-        """Test round-trip to_dict and from_dict."""
-        original = RunRequest(
-            message="Test message",
-            thread_id="thread-123",
-            role=Role.SYSTEM,
-            response_format=ModuleStructuredResponse,
-            enable_tool_calls=False,
-        )
-
-        data = original.to_dict()
-        restored = RunRequest.from_dict(data)
-
-        assert restored.message == original.message
-        assert restored.role == original.role
-        assert restored.response_format is ModuleStructuredResponse
-        assert restored.enable_tool_calls == original.enable_tool_calls
-        assert restored.thread_id == original.thread_id
-
-    def test_round_trip_with_pydantic_response_format(self) -> None:
-        """Ensure Pydantic response formats serialize and deserialize properly."""
-        original = RunRequest(
-            message="Structured",
-            thread_id="thread-pydantic",
-            response_format=ModuleStructuredResponse,
-        )
-
-        data = original.to_dict()
-
-        assert data["response_format"]["__response_schema_type__"] == "pydantic_model"
-        assert data["response_format"]["module"] == ModuleStructuredResponse.__module__
-        assert data["response_format"]["qualname"] == ModuleStructuredResponse.__qualname__
-
-        restored = RunRequest.from_dict(data)
-        assert restored.response_format is ModuleStructuredResponse
-
-    def test_init_with_correlationId(self) -> None:
-        """Test RunRequest initialization with correlationId."""
-        request = RunRequest(message="Test message", thread_id="thread-corr-init", correlation_id="corr-123")
-
-        assert request.message == "Test message"
-        assert request.correlation_id == "corr-123"
-
-    def test_to_dict_with_correlationId(self) -> None:
-        """Test to_dict includes correlationId."""
-        request = RunRequest(message="Test", thread_id="thread-corr-to-dict", correlation_id="corr-456")
-        data = request.to_dict()
-
-        assert data["message"] == "Test"
-        assert data["correlationId"] == "corr-456"
-
-    def test_from_dict_with_correlationId(self) -> None:
-        """Test from_dict with correlationId."""
-        data = {"message": "Test", "correlationId": "corr-789", "thread_id": "thread-corr-from-dict"}
-        request = RunRequest.from_dict(data)
-
-        assert request.message == "Test"
-        assert request.correlation_id == "corr-789"
-        assert request.thread_id == "thread-corr-from-dict"
-
-    def test_round_trip_with_correlationId(self) -> None:
-        """Test round-trip to_dict and from_dict with correlationId."""
-        original = RunRequest(
-            message="Test message",
-            thread_id="thread-123",
-            role=Role.SYSTEM,
-            correlation_id="corr-123",
-        )
-
-        data = original.to_dict()
-        restored = RunRequest.from_dict(data)
-
-        assert restored.message == original.message
-        assert restored.role == original.role
-        assert restored.correlation_id == original.correlation_id
-        assert restored.thread_id == original.thread_id
-
-    def test_init_with_orchestration_id(self) -> None:
-        """Test RunRequest initialization with orchestration_id."""
-        request = RunRequest(
-            message="Test message",
-            thread_id="thread-orch-init",
-            orchestration_id="orch-123",
-        )
-
-        assert request.message == "Test message"
-        assert request.orchestration_id == "orch-123"
-
-    def test_to_dict_with_orchestration_id(self) -> None:
-        """Test to_dict includes orchestrationId."""
-        request = RunRequest(
-            message="Test",
-            thread_id="thread-orch-to-dict",
-            orchestration_id="orch-456",
-        )
-        data = request.to_dict()
-
-        assert data["message"] == "Test"
-        assert data["orchestrationId"] == "orch-456"
-
-    def test_to_dict_excludes_orchestration_id_when_none(self) -> None:
-        """Test to_dict excludes orchestrationId when not set."""
-        request = RunRequest(
-            message="Test",
-            thread_id="thread-orch-none",
-        )
-        data = request.to_dict()
-
-        assert "orchestrationId" not in data
-
-    def test_from_dict_with_orchestration_id(self) -> None:
-        """Test from_dict with orchestrationId."""
-        data = {
-            "message": "Test",
-            "orchestrationId": "orch-789",
-            "thread_id": "thread-orch-from-dict",
-        }
-        request = RunRequest.from_dict(data)
-
-        assert request.message == "Test"
-        assert request.orchestration_id == "orch-789"
-        assert request.thread_id == "thread-orch-from-dict"
-
-    def test_round_trip_with_orchestration_id(self) -> None:
-        """Test round-trip to_dict and from_dict with orchestration_id."""
-        original = RunRequest(
-            message="Test message",
-            thread_id="thread-123",
-            role=Role.SYSTEM,
-            correlation_id="corr-123",
-            orchestration_id="orch-123",
-        )
-
-        data = original.to_dict()
-        restored = RunRequest.from_dict(data)
-
-        assert restored.message == original.message
-        assert restored.role == original.role
-        assert restored.correlation_id == original.correlation_id
-        assert restored.orchestration_id == original.orchestration_id
-        assert restored.thread_id == original.thread_id
-
-
-class TestModelIntegration:
-    """Test suite for integration between models."""
-
-    def test_run_request_with_session_id(self) -> None:
-        """Test using RunRequest with AgentSessionId."""
-        session_id = AgentSessionId.with_random_key("AgentEntity")
-        request = RunRequest(message="Test message", thread_id=str(session_id))
-
-        assert request.thread_id is not None
-        assert request.thread_id == str(session_id)
-        assert request.thread_id.startswith("@AgentEntity@")
-
-
-if __name__ == "__main__":
-    pytest.main([__file__, "-v", "--tb=short"])
@@ -6,11 +6,11 @@ from typing import Any
 from unittest.mock import Mock

 import pytest
-from agent_framework import AgentResponse, AgentThread, ChatMessage
+from agent_framework import AgentResponse, ChatMessage, Role
+from agent_framework_durabletask import DurableAIAgent
 from azure.durable_functions.models.Task import TaskBase, TaskState

-from agent_framework_azurefunctions import AgentFunctionApp, DurableAIAgent
-from agent_framework_azurefunctions._models import AgentSessionId, DurableAgentThread
+from agent_framework_azurefunctions import AgentFunctionApp
 from agent_framework_azurefunctions._orchestration import AgentTask


@@ -38,46 +38,96 @@ def _create_entity_task(task_id: int = 1) -> TaskBase:
    return _FakeTask(task_id)


+@pytest.fixture
+def mock_context():
+    """Create a mock orchestration context with UUID support."""
+    context = Mock()
+    context.instance_id = "test-instance"
+    context.current_utc_datetime = Mock()
+    return context
+
+
+@pytest.fixture
+def mock_context_with_uuid() -> tuple[Mock, str]:
+    """Create a mock context with a single UUID."""
+    from uuid import UUID
+
+    context = Mock()
+    context.instance_id = "test-instance"
+    context.current_utc_datetime = Mock()
+    test_uuid = UUID("aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa")
+    context.new_uuid = Mock(return_value=test_uuid)
+    return context, test_uuid.hex
+
+
+@pytest.fixture
+def mock_context_with_multiple_uuids() -> tuple[Mock, list[str]]:
+    """Create a mock context with multiple UUIDs via side_effect."""
+    from uuid import UUID
+
+    context = Mock()
+    context.instance_id = "test-instance"
+    context.current_utc_datetime = Mock()
+    uuids = [
+        UUID("aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa"),
+        UUID("bbbbbbbb-bbbb-bbbb-bbbb-bbbbbbbbbbbb"),
+        UUID("cccccccc-cccc-cccc-cccc-cccccccccccc"),
+    ]
+    context.new_uuid = Mock(side_effect=uuids)
+    # Return the hex versions for assertion checking
+    hex_uuids = [uuid.hex for uuid in uuids]
+    return context, hex_uuids
+
+
+@pytest.fixture
+def executor_with_uuid() -> tuple[Any, Mock, str]:
+    """Create an executor with a mocked generate_unique_id method."""
+    from agent_framework_azurefunctions._orchestration import AzureFunctionsAgentExecutor
+
+    context = Mock()
+    context.instance_id = "test-instance"
+    context.current_utc_datetime = Mock()
+
+    executor = AzureFunctionsAgentExecutor(context)
+    test_uuid_hex = "aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa"
+    executor.generate_unique_id = Mock(return_value=test_uuid_hex)
+
+    return executor, context, test_uuid_hex
+
+
+@pytest.fixture
+def executor_with_multiple_uuids() -> tuple[Any, Mock, list[str]]:
+    """Create an executor with multiple mocked UUIDs."""
+    from agent_framework_azurefunctions._orchestration import AzureFunctionsAgentExecutor
+
+    context = Mock()
+    context.instance_id = "test-instance"
+    context.current_utc_datetime = Mock()
+
+    executor = AzureFunctionsAgentExecutor(context)
+    uuid_hexes = [
+        "aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa",
+        "bbbbbbbb-bbbb-bbbb-bbbb-bbbbbbbbbbbb",
+        "cccccccc-cccc-cccc-cccc-cccccccccccc",
+        "dddddddd-dddd-dddd-dddd-dddddddddddd",
+        "eeeeeeee-eeee-eeee-eeee-eeeeeeeeeeee",
+    ]
+    executor.generate_unique_id = Mock(side_effect=uuid_hexes)
+
+    return executor, context, uuid_hexes
+
+
+@pytest.fixture
+def executor_with_context(mock_context_with_uuid: tuple[Mock, str]) -> tuple[Any, Mock]:
+    """Create an executor with a mocked context."""
+    from agent_framework_azurefunctions._orchestration import AzureFunctionsAgentExecutor
+
+    context, _ = mock_context_with_uuid
+    return AzureFunctionsAgentExecutor(context), context
+
+
 class TestAgentResponseHelpers:
-    """Tests for helper utilities that prepare AgentResponse values."""
-
-    @staticmethod
-    def _create_agent_task() -> AgentTask:
-        entity_task = _create_entity_task()
-        return AgentTask(entity_task, None, "correlation-id")
-
-    def test_load_agent_response_from_instance(self) -> None:
-        task = self._create_agent_task()
-        response = AgentResponse(messages=[ChatMessage(role="assistant", text='{"foo": "bar"}')])
-
-        loaded = task._load_agent_response(response)
-
-        assert loaded is response
-        assert loaded.value is None
-
-    def test_load_agent_response_from_serialized(self) -> None:
-        task = self._create_agent_task()
-        serialized = AgentResponse(messages=[ChatMessage(role="assistant", text="structured")]).to_dict()
-        serialized["value"] = {"answer": 42}
-
-        loaded = task._load_agent_response(serialized)
-
-        assert loaded is not None
-        assert loaded.value == {"answer": 42}
-        loaded_dict = loaded.to_dict()
-        assert loaded_dict["type"] == "agent_response"
-
-    def test_load_agent_response_rejects_none(self) -> None:
-        task = self._create_agent_task()
-
-        with pytest.raises(ValueError):
-            task._load_agent_response(None)
-
-    def test_load_agent_response_rejects_unsupported_type(self) -> None:
-        task = self._create_agent_task()
-
-        with pytest.raises(TypeError, match="Unsupported type"):
-            task._load_agent_response(["invalid", "list"])  # type: ignore[arg-type]
+    """Tests for response handling through public AgentTask API."""

    def test_try_set_value_success(self) -> None:
        """Test try_set_value correctly processes successful task completion."""
@@ -142,334 +192,10 @@ class TestAgentResponseHelpers:
        assert isinstance(task.result.value, TestSchema)
        assert task.result.value.answer == "42"

-    def test_ensure_response_format_parses_value(self) -> None:
-        """Test _ensure_response_format correctly parses response value."""
-        from pydantic import BaseModel
-
-        class SampleSchema(BaseModel):
-            name: str
-
-        task = self._create_agent_task()
-        response = AgentResponse(messages=[ChatMessage(role="assistant", text='{"name": "test"}')])
-
-        # Value should be None initially
-        assert response.value is None
-
-        # Parse the value
-        task._ensure_response_format(SampleSchema, "test-correlation", response)
-
-        # Value should now be parsed
-        assert isinstance(response.value, SampleSchema)
-        assert response.value.name == "test"
-
-    def test_ensure_response_format_skips_if_already_parsed(self) -> None:
-        """Test _ensure_response_format does not re-parse if value already matches format."""
-        from pydantic import BaseModel
-
-        class SampleSchema(BaseModel):
-            name: str
-
-        task = self._create_agent_task()
-        existing_value = SampleSchema(name="existing")
-        response = AgentResponse(
-            messages=[ChatMessage(role="assistant", text='{"name": "new"}')],
-            value=existing_value,
-        )
-
-        # Call _ensure_response_format
-        task._ensure_response_format(SampleSchema, "test-correlation", response)
-
-        # Value should remain unchanged (not re-parsed)
-        assert response.value is existing_value
-        assert response.value.name == "existing"
-
-
-class TestDurableAIAgent:
-    """Test suite for DurableAIAgent wrapper."""
-
-    def test_init(self) -> None:
-        """Test DurableAIAgent initialization."""
-        mock_context = Mock()
-        mock_context.instance_id = "test-instance-123"
-
-        agent = DurableAIAgent(mock_context, "TestAgent")
-
-        assert agent.context == mock_context
-        assert agent.agent_name == "TestAgent"
-
-    def test_implements_agent_protocol(self) -> None:
-        """Test that DurableAIAgent implements AgentProtocol."""
-        from agent_framework import AgentProtocol
-
-        mock_context = Mock()
-        agent = DurableAIAgent(mock_context, "TestAgent")
-
-        # Check that agent satisfies AgentProtocol
-        assert isinstance(agent, AgentProtocol)
-
-    def test_has_agent_protocol_properties(self) -> None:
-        """Test that DurableAIAgent has AgentProtocol properties."""
-        mock_context = Mock()
-        agent = DurableAIAgent(mock_context, "TestAgent")
-
-        # AgentProtocol properties
-        assert hasattr(agent, "id")
-        assert hasattr(agent, "name")
-        assert hasattr(agent, "description")
-
-        # Verify values
-        assert agent.name == "TestAgent"
-        assert agent.description == "Durable agent proxy for TestAgent"
-        assert agent.id is not None  # Auto-generated UUID
-
-    def test_get_new_thread(self) -> None:
-        """Test creating a new agent thread."""
-        mock_context = Mock()
-        mock_context.instance_id = "test-instance-456"
-        mock_context.new_uuid = Mock(return_value="test-guid-456")
-
-        agent = DurableAIAgent(mock_context, "WriterAgent")
-        thread = agent.get_new_thread()
-
-        assert isinstance(thread, DurableAgentThread)
-        assert thread.session_id is not None
-        session_id = thread.session_id
-        assert isinstance(session_id, AgentSessionId)
-        assert session_id.name == "WriterAgent"
-        assert session_id.key == "test-guid-456"
-        mock_context.new_uuid.assert_called_once()
-
-    def test_get_new_thread_deterministic(self) -> None:
-        """Test that get_new_thread creates deterministic session IDs."""
-
-        mock_context = Mock()
-        mock_context.instance_id = "test-instance-789"
-        mock_context.new_uuid = Mock(side_effect=["session-guid-1", "session-guid-2"])
-
-        agent = DurableAIAgent(mock_context, "EditorAgent")
-
-        # Create multiple threads - they should have unique session IDs
-        thread1 = agent.get_new_thread()
-        thread2 = agent.get_new_thread()
-
-        assert isinstance(thread1, DurableAgentThread)
-        assert isinstance(thread2, DurableAgentThread)
-
-        session_id1 = thread1.session_id
-        session_id2 = thread2.session_id
-        assert session_id1 is not None and session_id2 is not None
-        assert isinstance(session_id1, AgentSessionId)
-        assert isinstance(session_id2, AgentSessionId)
-        assert session_id1.name == "EditorAgent"
-        assert session_id2.name == "EditorAgent"
-        assert session_id1.key == "session-guid-1"
-        assert session_id2.key == "session-guid-2"
-        assert mock_context.new_uuid.call_count == 2
-
-    def test_run_creates_entity_call(self) -> None:
-        """Test that run() creates proper entity call and returns a Task."""
-        mock_context = Mock()
-        mock_context.instance_id = "test-instance-001"
-        mock_context.new_uuid = Mock(side_effect=["thread-guid", "correlation-guid"])
-
-        entity_task = _create_entity_task()
-        mock_context.call_entity = Mock(return_value=entity_task)
-
-        agent = DurableAIAgent(mock_context, "TestAgent")
-
-        # Create thread
-        thread = agent.get_new_thread()
-
-        # Call run() - returns AgentTask directly
-        task = agent.run(messages="Test message", thread=thread, enable_tool_calls=True)
-
-        assert isinstance(task, AgentTask)
-        assert task.children[0] == entity_task
-
-        # Verify call_entity was called with correct parameters
-        assert mock_context.call_entity.called
-        call_args = mock_context.call_entity.call_args
-        entity_id, operation, request = call_args[0]
-
-        assert operation == "run"
-        assert request["message"] == "Test message"
-        assert request["enable_tool_calls"] is True
-        assert "correlationId" in request
-        assert request["correlationId"] == "correlation-guid"
-        assert "thread_id" in request
-        assert request["thread_id"] == "thread-guid"
-        # Verify orchestration ID is set from context.instance_id
-        assert "orchestrationId" in request
-        assert request["orchestrationId"] == "test-instance-001"
-
-    def test_run_sets_orchestration_id(self) -> None:
-        """Test that run() sets the orchestration_id from context.instance_id."""
-        mock_context = Mock()
-        mock_context.instance_id = "my-orchestration-123"
-        mock_context.new_uuid = Mock(side_effect=["thread-guid", "correlation-guid"])
-
-        entity_task = _create_entity_task()
-        mock_context.call_entity = Mock(return_value=entity_task)
-
-        agent = DurableAIAgent(mock_context, "TestAgent")
-        thread = agent.get_new_thread()
-
-        agent.run(messages="Test", thread=thread)
-
-        call_args = mock_context.call_entity.call_args
-        request = call_args[0][2]
-
-        assert request["orchestrationId"] == "my-orchestration-123"
-
-    def test_run_without_thread(self) -> None:
-        """Test that run() works without explicit thread (creates unique session key)."""
-        mock_context = Mock()
-        mock_context.instance_id = "test-instance-002"
-        mock_context.new_uuid = Mock(side_effect=["auto-generated-guid", "correlation-guid"])
-
-        entity_task = _create_entity_task()
-        mock_context.call_entity = Mock(return_value=entity_task)
-
-        agent = DurableAIAgent(mock_context, "TestAgent")
-
-        # Call without thread
-        task = agent.run(messages="Test message")
-
-        assert isinstance(task, AgentTask)
-        assert task.children[0] == entity_task
-
-        # Verify the entity ID uses the auto-generated GUID with dafx- prefix
-        call_args = mock_context.call_entity.call_args
-        entity_id = call_args[0][0]
-        assert entity_id.name == "dafx-TestAgent"
-        assert entity_id.key == "auto-generated-guid"
-        # Should be called twice: once for session_key, once for correlationId
-        assert mock_context.new_uuid.call_count == 2
-
-    def test_run_with_response_format(self) -> None:
-        """Test that run() passes response format correctly."""
-        mock_context = Mock()
-        mock_context.instance_id = "test-instance-003"
-
-        entity_task = _create_entity_task()
-        mock_context.call_entity = Mock(return_value=entity_task)
-
-        agent = DurableAIAgent(mock_context, "TestAgent")
-
-        from pydantic import BaseModel
-
-        class SampleSchema(BaseModel):
-            key: str
-
-        # Create thread and call
-        thread = agent.get_new_thread()
-
-        task = agent.run(messages="Test message", thread=thread, options={"response_format": SampleSchema})
-
-        assert isinstance(task, AgentTask)
-        assert task.children[0] == entity_task
-
-        # Verify schema was passed in the call_entity arguments
-        call_args = mock_context.call_entity.call_args
-        input_data = call_args[0][2]  # Third argument is input_data
-        assert "response_format" in input_data
-        assert input_data["response_format"]["__response_schema_type__"] == "pydantic_model"
-        assert input_data["response_format"]["module"] == SampleSchema.__module__
-        assert input_data["response_format"]["qualname"] == SampleSchema.__qualname__
-
-    def test_messages_to_string(self) -> None:
-        """Test converting ChatMessage list to string."""
-        from agent_framework import ChatMessage
-
-        mock_context = Mock()
-        agent = DurableAIAgent(mock_context, "TestAgent")
-
-        messages = [
-            ChatMessage(role="user", text="Hello"),
-            ChatMessage(role="assistant", text="Hi there"),
-            ChatMessage(role="user", text="How are you?"),
-        ]
-
-        result = agent._messages_to_string(messages)
-
-        assert result == "Hello\nHi there\nHow are you?"
-
-    def test_run_with_chat_message(self) -> None:
-        """Test that run() handles ChatMessage input."""
-        from agent_framework import ChatMessage
-
-        mock_context = Mock()
-        mock_context.new_uuid = Mock(side_effect=["thread-guid", "correlation-guid"])
-        entity_task = _create_entity_task()
-        mock_context.call_entity = Mock(return_value=entity_task)
-
-        agent = DurableAIAgent(mock_context, "TestAgent")
-        thread = agent.get_new_thread()
-
-        # Call with ChatMessage
-        msg = ChatMessage(role="user", text="Hello")
-        task = agent.run(messages=msg, thread=thread)
-
-        assert isinstance(task, AgentTask)
-        assert task.children[0] == entity_task
-
-        # Verify message was converted to string
-        call_args = mock_context.call_entity.call_args
-        request = call_args[0][2]
-        assert request["message"] == "Hello"
-
-    def test_run_stream_raises_not_implemented(self) -> None:
-        """Test that run_stream() method raises NotImplementedError."""
-        mock_context = Mock()
-        agent = DurableAIAgent(mock_context, "TestAgent")
-
-        with pytest.raises(NotImplementedError) as exc_info:
-            agent.run_stream("Test message")
-
-        error_msg = str(exc_info.value)
-        assert "Streaming is not supported" in error_msg
-
-    def test_entity_id_format(self) -> None:
-        """Test that EntityId is created with correct format (name, key)."""
-        from azure.durable_functions import EntityId
-
-        mock_context = Mock()
-        mock_context.new_uuid = Mock(return_value="test-guid-789")
-        mock_context.call_entity = Mock(return_value=_create_entity_task())
-
-        agent = DurableAIAgent(mock_context, "WriterAgent")
-        thread = agent.get_new_thread()
-
-        # Call run() to trigger entity ID creation
-        agent.run("Test", thread=thread)
-
-        # Verify call_entity was called with correct EntityId
-        call_args = mock_context.call_entity.call_args
-        entity_id = call_args[0][0]
-
-        # EntityId should be EntityId(name="dafx-WriterAgent", key="test-guid-789")
-        # Which formats as "@dafx-writeragent@test-guid-789"
-        assert isinstance(entity_id, EntityId)
-        assert entity_id.name == "dafx-WriterAgent"
-        assert entity_id.key == "test-guid-789"
-        assert str(entity_id) == "@dafx-writeragent@test-guid-789"
-

 class TestAgentFunctionAppGetAgent:
    """Test suite for AgentFunctionApp.get_agent."""

-    def test_get_agent_method(self) -> None:
-        """Test get_agent method creates DurableAIAgent for registered agent."""
-        app = _app_with_registered_agents("MyAgent")
-        mock_context = Mock()
-        mock_context.instance_id = "test-instance-100"
-
-        agent = app.get_agent(mock_context, "MyAgent")
-
-        assert isinstance(agent, DurableAIAgent)
-        assert agent.agent_name == "MyAgent"
-        assert agent.context == mock_context
-
    def test_get_agent_raises_for_unregistered_agent(self) -> None:
        """Test get_agent raises ValueError when agent is not registered."""
        app = _app_with_registered_agents("KnownAgent")
@@ -478,18 +204,87 @@ class TestAgentFunctionAppGetAgent:
            app.get_agent(Mock(), "MissingAgent")


+class TestAzureFunctionsFireAndForget:
+    """Test fire-and-forget mode for AzureFunctionsAgentExecutor."""
+
+    def test_fire_and_forget_calls_signal_entity(self, executor_with_uuid: tuple[Any, Mock, str]) -> None:
+        """Verify wait_for_response=False calls signal_entity instead of call_entity."""
+        executor, context, _ = executor_with_uuid
+        context.signal_entity = Mock()
+        context.call_entity = Mock(return_value=_create_entity_task())
+
+        agent = DurableAIAgent(executor, "TestAgent")
+        thread = agent.get_new_thread()
+
+        # Run with wait_for_response=False
+        result = agent.run("Test message", thread=thread, options={"wait_for_response": False})
+
+        # Verify signal_entity was called and call_entity was not
+        assert context.signal_entity.call_count == 1
+        assert context.call_entity.call_count == 0
+
+        # Should still return an AgentTask
+        assert isinstance(result, AgentTask)
+
+    def test_fire_and_forget_returns_completed_task(self, executor_with_uuid: tuple[Any, Mock, str]) -> None:
+        """Verify wait_for_response=False returns pre-completed AgentTask."""
+        executor, context, _ = executor_with_uuid
+        context.signal_entity = Mock()
+
+        agent = DurableAIAgent(executor, "TestAgent")
+        thread = agent.get_new_thread()
+
+        result = agent.run("Test message", thread=thread, options={"wait_for_response": False})
+
+        # Task should be immediately complete
+        assert isinstance(result, AgentTask)
+        assert result.is_completed
+
+    def test_fire_and_forget_returns_acceptance_response(self, executor_with_uuid: tuple[Any, Mock, str]) -> None:
+        """Verify wait_for_response=False returns acceptance response."""
+        executor, context, _ = executor_with_uuid
+        context.signal_entity = Mock()
+
+        agent = DurableAIAgent(executor, "TestAgent")
+        thread = agent.get_new_thread()
+
+        result = agent.run("Test message", thread=thread, options={"wait_for_response": False})
+
+        # Get the result
+        response = result.result
+        assert isinstance(response, AgentResponse)
+        assert len(response.messages) == 1
+        assert response.messages[0].role == Role.SYSTEM
+        # Check message contains key information
+        message_text = response.messages[0].text
+        assert "accepted" in message_text.lower()
+        assert "background" in message_text.lower()
+
+    def test_blocking_mode_still_works(self, executor_with_uuid: tuple[Any, Mock, str]) -> None:
+        """Verify wait_for_response=True uses call_entity as before."""
+        executor, context, _ = executor_with_uuid
+        context.signal_entity = Mock()
+        context.call_entity = Mock(return_value=_create_entity_task())
+
+        agent = DurableAIAgent(executor, "TestAgent")
+        thread = agent.get_new_thread()
+
+        result = agent.run("Test message", thread=thread, options={"wait_for_response": True})
+
+        # Verify call_entity was called and signal_entity was not
+        assert context.call_entity.call_count == 1
+        assert context.signal_entity.call_count == 0
+
+        # Should return an AgentTask
+        assert isinstance(result, AgentTask)
+
+
 class TestOrchestrationIntegration:
    """Integration tests for orchestration scenarios."""

-    def test_sequential_agent_calls_simulation(self) -> None:
+    def test_sequential_agent_calls_simulation(self, executor_with_multiple_uuids: tuple[Any, Mock, list[str]]) -> None:
        """Simulate sequential agent calls in an orchestration."""
-        mock_context = Mock()
-        mock_context.instance_id = "test-orchestration-001"
-        # new_uuid will be called 3 times:
-        # 1. thread creation
-        # 2. correlationId for first call
-        # 3. correlationId for second call
-        mock_context.new_uuid = Mock(side_effect=["deterministic-guid-001", "corr-1", "corr-2"])
+        executor, context, uuid_hexes = executor_with_multiple_uuids

        # Track entity calls
        entity_calls: list[dict[str, Any]] = []
@@ -498,10 +293,10 @@ class TestOrchestrationIntegration:
            entity_calls.append({"entity_id": str(entity_id), "operation": operation, "input": input_data})
            return _create_entity_task()

-        mock_context.call_entity = Mock(side_effect=mock_call_entity_side_effect)
+        context.call_entity = Mock(side_effect=mock_call_entity_side_effect)

-        app = _app_with_registered_agents("WriterAgent")
-        agent = app.get_agent(mock_context, "WriterAgent")
+        # Create agent directly with executor (not via app.get_agent)
+        agent = DurableAIAgent(executor, "WriterAgent")

        # Create thread
        thread = agent.get_new_thread()
@@ -517,18 +312,15 @@ class TestOrchestrationIntegration:
        # Verify both calls used the same entity (same session key)
        assert len(entity_calls) == 2
        assert entity_calls[0]["entity_id"] == entity_calls[1]["entity_id"]
-        # EntityId format is @dafx-writeragent@deterministic-guid-001
-        assert entity_calls[0]["entity_id"] == "@dafx-writeragent@deterministic-guid-001"
-        # new_uuid called 3 times: thread + 2 correlation IDs
-        assert mock_context.new_uuid.call_count == 3
+        # EntityId format is @dafx-writeragent@<uuid_hex>
+        expected_entity_id = f"@dafx-writeragent@{uuid_hexes[0]}"
+        assert entity_calls[0]["entity_id"] == expected_entity_id
+        # generate_unique_id called 3 times: thread + 2 correlation IDs
+        assert executor.generate_unique_id.call_count == 3

-    def test_multiple_agents_in_orchestration(self) -> None:
+    def test_multiple_agents_in_orchestration(self, executor_with_multiple_uuids: tuple[Any, Mock, list[str]]) -> None:
        """Test using multiple different agents in one orchestration."""
-        mock_context = Mock()
-        mock_context.instance_id = "test-orchestration-002"
-        # Mock new_uuid to return different GUIDs for each call
-        # Order: writer thread, editor thread, writer correlation, editor correlation
-        mock_context.new_uuid = Mock(side_effect=["writer-guid-001", "editor-guid-002", "writer-corr", "editor-corr"])
+        executor, context, uuid_hexes = executor_with_multiple_uuids

        entity_calls: list[str] = []

@@ -536,11 +328,11 @@ class TestOrchestrationIntegration:
            entity_calls.append(str(entity_id))
            return _create_entity_task()

-        mock_context.call_entity = Mock(side_effect=mock_call_entity_side_effect)
+        context.call_entity = Mock(side_effect=mock_call_entity_side_effect)

-        app = _app_with_registered_agents("WriterAgent", "EditorAgent")
-        writer = app.get_agent(mock_context, "WriterAgent")
-        editor = app.get_agent(mock_context, "EditorAgent")
+        # Create agents directly with executor (not via app.get_agent)
+        writer = DurableAIAgent(executor, "WriterAgent")
+        editor = DurableAIAgent(executor, "EditorAgent")

        writer_thread = writer.get_new_thread()
        editor_thread = editor.get_new_thread()
@@ -554,62 +346,11 @@ class TestOrchestrationIntegration:

        # Verify different entity IDs were used
        assert len(entity_calls) == 2
-        # EntityId format is @dafx-agentname@guid (lowercased agent name with dafx- prefix)
-        assert entity_calls[0] == "@dafx-writeragent@writer-guid-001"
-        assert entity_calls[1] == "@dafx-editoragent@editor-guid-002"
-
-
-class TestAgentThreadSerialization:
-    """Test that AgentThread can be serialized for orchestration state."""
-
-    async def test_agent_thread_serialize(self) -> None:
-        """Test that AgentThread can be serialized."""
-        thread = AgentThread()
-
-        # Serialize
-        serialized = await thread.serialize()
-
-        assert isinstance(serialized, dict)
-        assert "service_thread_id" in serialized
-
-    async def test_agent_thread_deserialize(self) -> None:
-        """Test that AgentThread can be deserialized."""
-        thread = AgentThread()
-        serialized = await thread.serialize()
-
-        # Deserialize
-        restored = await AgentThread.deserialize(serialized)
-
-        assert isinstance(restored, AgentThread)
-        assert restored.service_thread_id == thread.service_thread_id
-
-    async def test_durable_agent_thread_serialization(self) -> None:
-        """Test that DurableAgentThread persists session metadata during serialization."""
-        mock_context = Mock()
-        mock_context.instance_id = "test-instance-999"
-        mock_context.new_uuid = Mock(return_value="test-guid-999")
-
-        agent = DurableAIAgent(mock_context, "TestAgent")
-        thread = agent.get_new_thread()
-
-        assert isinstance(thread, DurableAgentThread)
-        # Verify custom attribute and property exist
-        assert thread.session_id is not None
-        session_id = thread.session_id
-        assert isinstance(session_id, AgentSessionId)
-        assert session_id.name == "TestAgent"
-        assert session_id.key == "test-guid-999"
-
-        # Standard serialization should still work
-        serialized = await thread.serialize()
-        assert isinstance(serialized, dict)
-        assert serialized.get("durable_session_id") == str(session_id)
-
-        # After deserialization, we'd need to restore the custom attribute
-        # This would be handled by the orchestration framework
-        restored = await DurableAgentThread.deserialize(serialized)
-        assert isinstance(restored, DurableAgentThread)
-        assert restored.session_id == session_id
+        # EntityId format is @dafx-agentname@uuid_hex (lowercased agent name with dafx- prefix)
+        expected_writer_id = f"@dafx-writeragent@{uuid_hexes[0]}"
+        expected_editor_id = f"@dafx-editoragent@{uuid_hexes[1]}"
+        assert entity_calls[0] == expected_writer_id
+        assert entity_calls[1] == expected_editor_id


 if __name__ == "__main__":