agent/agent-framework
2
0
Fork 0
mirror of https://github.com/microsoft/agent-framework.git synced 2026-06-16 21:04:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

.NET: Python: Merge main into feature-durabletask-python branch (#3160)

Browse Source 
* 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>
This commit is contained in:
Laveesh Rohra
2026-01-09 15:58:49 -08:00
committed by GitHub
Unverified
parent e3eff65a6b
commit 1e36ba33c4
184 changed files with 17907 additions and 3316 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/packages/core/agent_framework/_clients.py
+11 -5
View File
@@ -101,7 +101,7 @@ class ChatClientProtocol(Protocol):
stop: str | Sequence[str] | None = None,
store: bool | None = None,
temperature: float | None = None,
tool_choice: ToolMode | Literal["auto", "required", "none"] | dict[str, Any] | None = "auto",
tool_choice: ToolMode | Literal["auto", "required", "none"] | dict[str, Any] | None = None,
tools: ToolProtocol
| Callable[..., Any]
| MutableMapping[str, Any]
@@ -160,7 +160,7 @@ class ChatClientProtocol(Protocol):
stop: str | Sequence[str] | None = None,
store: bool | None = None,
temperature: float | None = None,
tool_choice: ToolMode | Literal["auto", "required", "none"] | dict[str, Any] | None = "auto",
tool_choice: ToolMode | Literal["auto", "required", "none"] | dict[str, Any] | None = None,
tools: ToolProtocol
| Callable[..., Any]
| MutableMapping[str, Any]
@@ -501,7 +501,7 @@ class BaseChatClient(SerializationMixin, ABC):
stop: str | Sequence[str] | None = None,
store: bool | None = None,
temperature: float | None = None,
tool_choice: ToolMode | Literal["auto", "required", "none"] | dict[str, Any] | None = "auto",
tool_choice: ToolMode | Literal["auto", "required", "none"] | dict[str, Any] | None = None,
tools: ToolProtocol
| Callable[..., Any]
| MutableMapping[str, Any]
@@ -596,7 +596,7 @@ class BaseChatClient(SerializationMixin, ABC):
stop: str | Sequence[str] | None = None,
store: bool | None = None,
temperature: float | None = None,
tool_choice: ToolMode | Literal["auto", "required", "none"] | dict[str, Any] | None = "auto",
tool_choice: ToolMode | Literal["auto", "required", "none"] | dict[str, Any] | None = None,
tools: ToolProtocol
| Callable[..., Any]
| MutableMapping[str, Any]
@@ -688,12 +688,18 @@ class BaseChatClient(SerializationMixin, ABC):
chat_options: The chat options to prepare.
"""
chat_tool_mode = chat_options.tool_choice
if chat_tool_mode is None or chat_tool_mode == ToolMode.NONE or chat_tool_mode == "none":
# Explicitly disabled: clear tools and set to NONE
if chat_tool_mode == ToolMode.NONE or chat_tool_mode == "none":
chat_options.tools = None
chat_options.tool_choice = ToolMode.NONE
return
# No tools available: set to NONE regardless of requested mode
if not chat_options.tools:
chat_options.tool_choice = ToolMode.NONE
# Tools available but no explicit mode: default to AUTO
elif chat_tool_mode is None:
chat_options.tool_choice = ToolMode.AUTO
# Tools available with explicit mode: preserve the mode
else:
chat_options.tool_choice = chat_tool_mode
python/packages/core/agent_framework/_tools.py
+43 -6
View File
@@ -16,6 +16,7 @@ from typing import (
Generic,
Literal,
Protocol,
TypedDict,
TypeVar,
cast,
get_args,
@@ -73,6 +74,7 @@ __all__ = [
"FunctionInvocationConfiguration",
"HostedCodeInterpreterTool",
"HostedFileSearchTool",
"HostedImageGenerationTool",
"HostedMCPSpecificApproval",
"HostedMCPTool",
"HostedWebSearchTool",
@@ -324,6 +326,41 @@ class HostedWebSearchTool(BaseTool):
super().__init__(**args)
class HostedImageGenerationToolOptions(TypedDict, total=False):
"""Options for HostedImageGenerationTool."""
count: int
image_size: str
media_type: str
model_id: str
response_format: Literal["uri", "data", "hosted"]
streaming_count: int
class HostedImageGenerationTool(BaseTool):
"""Represents a hosted tool that can be specified to an AI service to enable it to perform image generation."""
def __init__(
self,
*,
options: HostedImageGenerationToolOptions | None = None,
description: str | None = None,
additional_properties: dict[str, Any] | None = None,
**kwargs: Any,
):
"""Initialize a HostedImageGenerationTool."""
if "name" in kwargs:
raise ValueError("The 'name' argument is reserved for the HostedImageGenerationTool and cannot be set.")
self.options = options
super().__init__(
name="image_generation",
description=description or "",
additional_properties=additional_properties,
**kwargs,
)
class HostedMCPSpecificApproval(TypedDict, total=False):
"""Represents the specific mode for a hosted tool.
@@ -1419,14 +1456,11 @@ async def _auto_invoke_function(
Raises:
KeyError: If the requested function is not found in the tool map.
"""
from ._types import (
FunctionResultContent,
)
# Note: The scenarios for approval_mode="always_require", declaration_only, and
# terminate_on_unknown_calls are all handled in _try_execute_function_calls before
# this function is called. This function only handles the actual execution of approved,
# non-declaration-only functions.
from ._types import FunctionCallContent, FunctionResultContent
tool: AIFunction[BaseModel, Any] | None = None
if function_call_content.type == "function_call":
@@ -1444,11 +1478,14 @@ async def _auto_invoke_function(
else:
# Note: Unapproved tools (approved=False) are handled in _replace_approval_contents_with_results
# and never reach this function, so we only handle approved=True cases here.
tool = tool_map.get(function_call_content.function_call.name)
inner_call = function_call_content.function_call
if not isinstance(inner_call, FunctionCallContent):
return function_call_content
tool = tool_map.get(inner_call.name)
if tool is None:
# we assume it is a hosted tool
return function_call_content
function_call_content = function_call_content.function_call
function_call_content = inner_call
parsed_args: dict[str, Any] = dict(function_call_content.parse_arguments() or {})
python/packages/core/agent_framework/_types.py
+272 -2
View File
@@ -40,6 +40,8 @@ __all__ = [
"ChatResponse",
"ChatResponseUpdate",
"CitationAnnotation",
"CodeInterpreterToolCallContent",
"CodeInterpreterToolResultContent",
"Contents",
"DataContent",
"ErrorContent",
@@ -50,6 +52,10 @@ __all__ = [
"FunctionResultContent",
"HostedFileContent",
"HostedVectorStoreContent",
"ImageGenerationToolCallContent",
"ImageGenerationToolResultContent",
"MCPServerToolCallContent",
"MCPServerToolResultContent",
"Role",
"TextContent",
"TextReasoningContent",
@@ -121,6 +127,18 @@ def _parse_content(content_data: MutableMapping[str, Any]) -> "Contents":
return HostedFileContent.from_dict(content_data)
case "hosted_vector_store":
return HostedVectorStoreContent.from_dict(content_data)
case "code_interpreter_tool_call":
return CodeInterpreterToolCallContent.from_dict(content_data)
case "code_interpreter_tool_result":
return CodeInterpreterToolResultContent.from_dict(content_data)
case "image_generation_tool_call":
return ImageGenerationToolCallContent.from_dict(content_data)
case "image_generation_tool_result":
return ImageGenerationToolResultContent.from_dict(content_data)
case "mcp_server_tool_call":
return MCPServerToolCallContent.from_dict(content_data)
case "mcp_server_tool_result":
return MCPServerToolResultContent.from_dict(content_data)
case "function_approval_request":
return FunctionApprovalRequestContent.from_dict(content_data)
case "function_approval_response":
@@ -1607,6 +1625,8 @@ class HostedFileContent(BaseContent):
self,
file_id: str,
*,
media_type: str | None = None,
name: str | None = None,
additional_properties: dict[str, Any] | None = None,
raw_representation: Any | None = None,
**kwargs: Any,
@@ -1615,6 +1635,8 @@ class HostedFileContent(BaseContent):
Args:
file_id: The identifier of the hosted file.
media_type: Optional media type of the hosted file.
name: Optional display name of the hosted file.
Keyword Args:
additional_properties: Optional additional properties associated with the content.
@@ -1627,8 +1649,14 @@ class HostedFileContent(BaseContent):
**kwargs,
)
self.file_id = file_id
self.media_type = media_type
self.name = name
self.type: Literal["hosted_file"] = "hosted_file"
def has_top_level_media_type(self, top_level_media_type: Literal["application", "audio", "image", "text"]) -> bool:
"""Returns a boolean indicating if the media type has the specified top-level media type."""
return _has_top_level_media_type(self.media_type, top_level_media_type)
class HostedVectorStoreContent(BaseContent):
"""Represents a hosted vector store content.
@@ -1676,6 +1704,234 @@ class HostedVectorStoreContent(BaseContent):
self.type: Literal["hosted_vector_store"] = "hosted_vector_store"
class CodeInterpreterToolCallContent(BaseContent):
"""Represents a code interpreter tool call invocation by a hosted service."""
def __init__(
self,
*,
call_id: str | None = None,
inputs: Sequence["Contents | MutableMapping[str, Any]"] | None = None,
annotations: Sequence[Annotations | MutableMapping[str, Any]] | None = None,
additional_properties: dict[str, Any] | None = None,
raw_representation: Any | None = None,
**kwargs: Any,
) -> None:
super().__init__(
annotations=annotations,
additional_properties=additional_properties,
raw_representation=raw_representation,
**kwargs,
)
self.call_id = call_id
self.inputs: list["Contents"] | None = None
if inputs:
normalized_inputs: Sequence["Contents | MutableMapping[str, Any]"] = (
inputs
if isinstance(inputs, Sequence) and not isinstance(inputs, (str, bytes, MutableMapping))
else [inputs]
)
self.inputs = _parse_content_list(list(normalized_inputs))
self.type: Literal["code_interpreter_tool_call"] = "code_interpreter_tool_call"
class CodeInterpreterToolResultContent(BaseContent):
"""Represents the result of a code interpreter tool invocation by a hosted service."""
def __init__(
self,
*,
call_id: str | None = None,
outputs: Sequence["Contents | MutableMapping[str, Any]"] | None = None,
annotations: Sequence[Annotations | MutableMapping[str, Any]] | None = None,
additional_properties: dict[str, Any] | None = None,
raw_representation: Any | None = None,
**kwargs: Any,
) -> None:
super().__init__(
annotations=annotations,
additional_properties=additional_properties,
raw_representation=raw_representation,
**kwargs,
)
self.call_id = call_id
self.outputs: list["Contents"] | None = None
if outputs:
normalized_outputs: Sequence["Contents | MutableMapping[str, Any]"] = (
outputs
if isinstance(outputs, Sequence) and not isinstance(outputs, (str, bytes, MutableMapping))
else [outputs]
)
self.outputs = _parse_content_list(list(normalized_outputs))
self.type: Literal["code_interpreter_tool_result"] = "code_interpreter_tool_result"
class ImageGenerationToolCallContent(BaseContent):
"""Represents the invocation of an image generation tool call by a hosted service."""
def __init__(
self,
*,
image_id: str | None = None,
annotations: Sequence[Annotations | MutableMapping[str, Any]] | None = None,
additional_properties: dict[str, Any] | None = None,
raw_representation: Any | None = None,
**kwargs: Any,
) -> None:
"""Initializes an ImageGenerationToolCallContent instance.
Keyword Args:
image_id: The identifier of the image to be generated.
annotations: Optional annotations associated with the content.
additional_properties: Optional additional properties associated with the content.
raw_representation: Optional raw representation of the content.
**kwargs: Any additional keyword arguments.
"""
super().__init__(
annotations=annotations,
additional_properties=additional_properties,
raw_representation=raw_representation,
**kwargs,
)
self.image_id = image_id
self.type: Literal["image_generation_tool_call"] = "image_generation_tool_call"
class ImageGenerationToolResultContent(BaseContent):
"""Represents the result of an image generation tool call invocation by a hosted service."""
def __init__(
self,
*,
image_id: str | None = None,
outputs: DataContent | UriContent | None = None,
annotations: Sequence[Annotations | MutableMapping[str, Any]] | None = None,
additional_properties: dict[str, Any] | None = None,
raw_representation: Any | None = None,
**kwargs: Any,
) -> None:
"""Initializes an ImageGenerationToolResultContent instance.
Keyword Args:
image_id: The identifier of the generated image.
outputs: The outputs of the image generation tool call.
annotations: Optional annotations associated with the content.
additional_properties: Optional additional properties associated with the content.
raw_representation: Optional raw representation of the content.
**kwargs: Any additional keyword arguments.
"""
super().__init__(
annotations=annotations,
additional_properties=additional_properties,
raw_representation=raw_representation,
**kwargs,
)
self.image_id = image_id
self.outputs: DataContent | UriContent | None = outputs
self.type: Literal["image_generation_tool_result"] = "image_generation_tool_result"
class MCPServerToolCallContent(BaseContent):
"""Represents a tool call request to a MCP server."""
def __init__(
self,
call_id: str,
tool_name: str,
server_name: str | None = None,
*,
arguments: str | Mapping[str, Any] | None = None,
annotations: Sequence[Annotations | MutableMapping[str, Any]] | None = None,
additional_properties: dict[str, Any] | None = None,
raw_representation: Any | None = None,
**kwargs: Any,
) -> None:
"""Initializes a MCPServerToolCallContent instance.
Args:
call_id: The tool call identifier.
tool_name: The name of the tool requested.
server_name: The name of the MCP server where the tool is hosted.
Keyword Args:
arguments: The arguments requested to be provided to the tool,
can be a string to allow gradual completion of the args.
annotations: Optional annotations associated with the content.
additional_properties: Optional additional properties associated with the content.
raw_representation: Optional raw representation of the content.
**kwargs: Any additional keyword arguments.
"""
if not call_id:
raise ValueError("call_id must be a non-empty string.")
if not tool_name:
raise ValueError("tool_name must be a non-empty string.")
super().__init__(
annotations=annotations,
additional_properties=additional_properties,
raw_representation=raw_representation,
**kwargs,
)
self.call_id = call_id
self.tool_name = tool_name
self.name = tool_name
self.server_name = server_name
self.arguments = arguments
self.type: Literal["mcp_server_tool_call"] = "mcp_server_tool_call"
def parse_arguments(self) -> dict[str, Any] | None:
"""Returns the parsed arguments for the MCP server tool call, if any."""
if isinstance(self.arguments, str):
# If arguments are a string, try to parse it as JSON
try:
loaded = json.loads(self.arguments)
if isinstance(loaded, dict):
return loaded # type:ignore
return {"raw": loaded}
except (json.JSONDecodeError, TypeError):
return {"raw": self.arguments}
return cast(dict[str, Any] | None, self.arguments)
class MCPServerToolResultContent(BaseContent):
"""Represents the result of a MCP server tool call."""
def __init__(
self,
call_id: str,
*,
output: Any | None = None,
annotations: Sequence[Annotations | MutableMapping[str, Any]] | None = None,
additional_properties: dict[str, Any] | None = None,
raw_representation: Any | None = None,
**kwargs: Any,
) -> None:
"""Initializes a MCPServerToolResultContent instance.
Args:
call_id: The identifier of the tool call for which this is the result.
Keyword Args:
output: The output of the MCP server tool call.
annotations: Optional annotations associated with the content.
additional_properties: Optional additional properties associated with the content.
raw_representation: Optional raw representation of the content.
**kwargs: Any additional keyword arguments.
"""
if not call_id:
raise ValueError("call_id must be a non-empty string.")
super().__init__(
annotations=annotations,
additional_properties=additional_properties,
raw_representation=raw_representation,
**kwargs,
)
self.call_id = call_id
self.output: Any | None = output
self.type: Literal["mcp_server_tool_result"] = "mcp_server_tool_result"
class BaseUserInputRequest(BaseContent):
"""Base class for all user requests."""
@@ -1736,7 +1992,7 @@ class FunctionApprovalResponseContent(BaseContent):
approved: bool,
*,
id: str,
function_call: FunctionCallContent | MutableMapping[str, Any],
function_call: FunctionCallContent | MCPServerToolCallContent | MutableMapping[str, Any],
annotations: Sequence[Annotations | MutableMapping[str, Any]] | None = None,
additional_properties: dict[str, Any] | None = None,
raw_representation: Any | None = None,
@@ -1764,8 +2020,12 @@ class FunctionApprovalResponseContent(BaseContent):
self.id = id
self.approved = approved
# Convert dict to FunctionCallContent if needed (for SerializationMixin support)
self.function_call: FunctionCallContent | MCPServerToolCallContent
if isinstance(function_call, MutableMapping):
self.function_call = FunctionCallContent.from_dict(function_call)
if function_call.get("type") == "mcp_server_tool_call":
self.function_call = MCPServerToolCallContent.from_dict(function_call)
else:
self.function_call = FunctionCallContent.from_dict(function_call)
else:
self.function_call = function_call
# Override the type for this specific subclass
@@ -1823,6 +2083,7 @@ class FunctionApprovalRequestContent(BaseContent):
**kwargs,
)
self.id = id
self.function_call: FunctionCallContent
# Convert dict to FunctionCallContent if needed (for SerializationMixin support)
if isinstance(function_call, MutableMapping):
self.function_call = FunctionCallContent.from_dict(function_call)
@@ -1854,6 +2115,12 @@ Contents = (
| UsageContent
| HostedFileContent
| HostedVectorStoreContent
| CodeInterpreterToolCallContent
| CodeInterpreterToolResultContent
| ImageGenerationToolCallContent
| ImageGenerationToolResultContent
| MCPServerToolCallContent
| MCPServerToolResultContent
| FunctionApprovalRequestContent
| FunctionApprovalResponseContent
)
@@ -1869,6 +2136,9 @@ def _prepare_function_call_results_as_dumpable(content: Contents | Any | list[Co
return content.model_dump()
if hasattr(content, "to_dict"):
return content.to_dict(exclude={"raw_representation", "additional_properties"})
# Handle objects with text attribute (e.g., MCP TextContent)
if hasattr(content, "text") and isinstance(content.text, str):
return content.text
return content
python/packages/core/agent_framework/_workflows/_agent.py
+3
View File
@@ -309,6 +309,9 @@ class WorkflowAgent(BaseAgent):
if isinstance(executor, AgentExecutor) and not executor.output_response:
return None
if update:
# Enrich with executor identity if author_name is not already set
if not update.author_name:
update.author_name = executor_id
return update
return None
python/packages/core/agent_framework/_workflows/_executor.py
+7 -3
View File
@@ -1,6 +1,7 @@
# Copyright (c) Microsoft. All rights reserved.
import contextlib
import copy
import functools
import inspect
import logging
@@ -263,8 +264,9 @@ class Executor(RequestInfoMixin, DictConvertible):
)
# Invoke the handler with the message and context
# Use deepcopy to capture original input state before handler can mutate it
with _framework_event_origin():
invoke_event = ExecutorInvokedEvent(self.id, message)
invoke_event = ExecutorInvokedEvent(self.id, copy.deepcopy(message))
await context.add_event(invoke_event)
try:
await handler(message, context)
@@ -275,9 +277,11 @@ class Executor(RequestInfoMixin, DictConvertible):
await context.add_event(failure_event)
raise
with _framework_event_origin():
# Include sent messages as the completion data
# Include sent messages and yielded outputs as the completion data
sent_messages = context.get_sent_messages()
completed_event = ExecutorCompletedEvent(self.id, sent_messages if sent_messages else None)
yielded_outputs = context.get_yielded_outputs()
completion_data = sent_messages + yielded_outputs
completed_event = ExecutorCompletedEvent(self.id, completion_data if completion_data else None)
await context.add_event(completed_event)
def _create_context_for_handler(
python/packages/core/agent_framework/_workflows/_workflow_context.py
+15
View File
@@ -1,5 +1,6 @@
# Copyright (c) Microsoft. All rights reserved.
import copy
import inspect
import logging
import uuid
@@ -290,6 +291,9 @@ class WorkflowContext(Generic[T_Out, T_W_Out]):
# Track messages sent via send_message() for ExecutorCompletedEvent
self._sent_messages: list[Any] = []
# Track outputs yielded via yield_output() for ExecutorCompletedEvent
self._yielded_outputs: list[Any] = []
# Store trace contexts and source span IDs for linking (supporting multiple sources)
self._trace_contexts = trace_contexts or []
self._source_span_ids = source_span_ids or []
@@ -336,6 +340,9 @@ class WorkflowContext(Generic[T_Out, T_W_Out]):
output: The output to yield. This must conform to the workflow output type(s)
declared on this context.
"""
# Track yielded output for ExecutorCompletedEvent (deepcopy to capture state at yield time)
self._yielded_outputs.append(copy.deepcopy(output))
with _framework_event_origin():
event = WorkflowOutputEvent(data=output, source_executor_id=self._executor_id)
await self._runner_context.add_event(event)
@@ -424,6 +431,14 @@ class WorkflowContext(Generic[T_Out, T_W_Out]):
"""
return self._sent_messages.copy()
def get_yielded_outputs(self) -> list[Any]:
"""Get all outputs yielded via yield_output() during this handler execution.
Returns:
A list of outputs that were yielded as workflow outputs.
"""
return self._yielded_outputs.copy()
@deprecated(
"Override `on_checkpoint_save()` methods instead. "
"For cross-executor state sharing, use set_shared_state() instead. "
python/packages/core/agent_framework/observability.py
+2 -2
View File
@@ -321,7 +321,7 @@ def _create_otlp_exporters(
if not actual_logs_endpoint and not actual_traces_endpoint and not actual_metrics_endpoint:
return exporters
if protocol in ("grpc", "http/protobuf"):
if protocol == "grpc":
# Import all gRPC exporters
try:
from opentelemetry.exporter.otlp.proto.grpc._log_exporter import OTLPLogExporter as GRPCLogExporter
@@ -357,7 +357,7 @@ def _create_otlp_exporters(
)
)
elif protocol == "http":
elif protocol in ("http/protobuf", "http"):
# Import all HTTP exporters
try:
from opentelemetry.exporter.otlp.proto.http._log_exporter import OTLPLogExporter as HTTPLogExporter
python/packages/core/agent_framework/openai/_assistants_client.py
+33 -4
View File
@@ -3,7 +3,7 @@
import json
import sys
from collections.abc import AsyncIterable, Awaitable, Callable, Mapping, MutableMapping, MutableSequence
from typing import Any
from typing import Any, cast
from openai import AsyncOpenAI
from openai.types.beta.threads import (
@@ -28,9 +28,11 @@ from .._types import (
ChatOptions,
ChatResponse,
ChatResponseUpdate,
CodeInterpreterToolCallContent,
Contents,
FunctionCallContent,
FunctionResultContent,
MCPServerToolCallContent,
Role,
TextContent,
ToolMode,
@@ -377,10 +379,37 @@ class OpenAIAssistantsClient(OpenAIConfigMixin, BaseChatClient):
if event_data.required_action is not None:
for tool_call in event_data.required_action.submit_tool_outputs.tool_calls:
tool_call_any = cast(Any, tool_call)
call_id = json.dumps([response_id, tool_call.id])
function_name = tool_call.function.name
function_arguments = json.loads(tool_call.function.arguments)
contents.append(FunctionCallContent(call_id=call_id, name=function_name, arguments=function_arguments))
tool_type = getattr(tool_call, "type", None)
if tool_type == "code_interpreter" and getattr(tool_call_any, "code_interpreter", None):
code_input = getattr(tool_call_any.code_interpreter, "input", None)
inputs = (
[TextContent(text=code_input, raw_representation=tool_call)] if code_input is not None else None
)
contents.append(
CodeInterpreterToolCallContent(
call_id=call_id,
inputs=inputs,
raw_representation=tool_call,
)
)
elif tool_type == "mcp":
contents.append(
MCPServerToolCallContent(
call_id=call_id,
tool_name=getattr(tool_call, "name", "") or "",
server_name=getattr(tool_call, "server_label", None),
arguments=getattr(tool_call, "args", None),
raw_representation=tool_call,
)
)
else:
function_name = tool_call.function.name
function_arguments = json.loads(tool_call.function.arguments)
contents.append(
FunctionCallContent(call_id=call_id, name=function_name, arguments=function_arguments)
)
return contents
python/packages/core/agent_framework/openai/_chat_client.py
+3 -3
View File
@@ -183,7 +183,7 @@ class OpenAIBaseChatClient(OpenAIBase, BaseChatClient):
translations = {
"model_id": "model",
"allow_multiple_tool_calls": "parallel_tool_calls",
"max_tokens": "max_output_tokens",
"max_tokens": "max_completion_tokens",
}
for old_key, new_key in translations.items():
if old_key in run_options and old_key != new_key:
@@ -205,8 +205,8 @@ class OpenAIBaseChatClient(OpenAIBase, BaseChatClient):
run_options.pop("tools", None)
run_options.pop("parallel_tool_calls", None)
run_options.pop("tool_choice", None)
# tool choice when `tool_choice` is a dict with single key `mode`, extract the mode value
if (tool_choice := run_options.get("tool_choice")) and len(tool_choice.keys()) == 1:
# tool_choice: ToolMode serializes to {"type": "tool_mode", "mode": "..."}, extract mode
if (tool_choice := run_options.get("tool_choice")) and isinstance(tool_choice, dict) and "mode" in tool_choice:
run_options["tool_choice"] = tool_choice["mode"]
# response format
python/packages/core/agent_framework/openai/_responses_client.py
+241 -94
View File
@@ -1,6 +1,14 @@
# Copyright (c) Microsoft. All rights reserved.
from collections.abc import AsyncIterable, Awaitable, Callable, Mapping, MutableMapping, MutableSequence, Sequence
from collections.abc import (
AsyncIterable,
Awaitable,
Callable,
Mapping,
MutableMapping,
MutableSequence,
Sequence,
)
from datetime import datetime, timezone
from itertools import chain
from typing import Any, TypeVar, cast
@@ -12,7 +20,9 @@ from openai.types.responses.parsed_response import (
ParsedResponse,
)
from openai.types.responses.response import Response as OpenAIResponse
from openai.types.responses.response_stream_event import ResponseStreamEvent as OpenAIResponseStreamEvent
from openai.types.responses.response_stream_event import (
ResponseStreamEvent as OpenAIResponseStreamEvent,
)
from openai.types.responses.response_usage import ResponseUsage
from openai.types.responses.tool_param import (
CodeInterpreter,
@@ -20,7 +30,9 @@ from openai.types.responses.tool_param import (
Mcp,
ToolParam,
)
from openai.types.responses.web_search_tool_param import UserLocation as WebSearchUserLocation
from openai.types.responses.web_search_tool_param import (
UserLocation as WebSearchUserLocation,
)
from openai.types.responses.web_search_tool_param import WebSearchToolParam
from pydantic import BaseModel, ValidationError
@@ -31,6 +43,7 @@ from .._tools import (
AIFunction,
HostedCodeInterpreterTool,
HostedFileSearchTool,
HostedImageGenerationTool,
HostedMCPTool,
HostedWebSearchTool,
ToolProtocol,
@@ -42,6 +55,8 @@ from .._types import (
ChatResponse,
ChatResponseUpdate,
CitationAnnotation,
CodeInterpreterToolCallContent,
CodeInterpreterToolResultContent,
Contents,
DataContent,
FunctionApprovalRequestContent,
@@ -50,6 +65,10 @@ from .._types import (
FunctionResultContent,
HostedFileContent,
HostedVectorStoreContent,
ImageGenerationToolCallContent,
ImageGenerationToolResultContent,
MCPServerToolCallContent,
MCPServerToolResultContent,
Role,
TextContent,
TextReasoningContent,
@@ -57,6 +76,7 @@ from .._types import (
UriContent,
UsageContent,
UsageDetails,
_parse_content,
prepare_function_call_results,
)
from ..exceptions import (
@@ -131,13 +151,17 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
if "text_format" not in run_options:
async for chunk in await client.responses.create(stream=True, **run_options):
yield self._parse_chunk_from_openai(
chunk, chat_options=chat_options, function_call_ids=function_call_ids
chunk,
chat_options=chat_options,
function_call_ids=function_call_ids,
)
return
async with client.responses.stream(**run_options) as response:
async for chunk in response:
yield self._parse_chunk_from_openai(
chunk, chat_options=chat_options, function_call_ids=function_call_ids
chunk,
chat_options=chat_options,
function_call_ids=function_call_ids,
)
except BadRequestError as ex:
if ex.code == "content_filter":
@@ -314,39 +338,28 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
else None,
)
)
case HostedImageGenerationTool():
mapped_tool: dict[str, Any] = {"type": "image_generation"}
if tool.options:
option_mapping = {
"image_size": "size",
"media_type": "output_format",
"model_id": "model",
"streaming_count": "partial_images",
}
# count and response_format are not supported by Responses API
for key, value in tool.options.items():
mapped_key = option_mapping.get(key, key)
mapped_tool[mapped_key] = value
if tool.additional_properties:
mapped_tool.update(tool.additional_properties)
response_tools.append(mapped_tool)
case _:
logger.debug("Unsupported tool passed (type: %s)", type(tool))
else:
# Handle raw dictionary tools
tool_dict = tool if isinstance(tool, dict) else dict(tool)
# Special handling for image_generation tools
if tool_dict.get("type") == "image_generation":
# Create a copy to avoid modifying the original
mapped_tool = tool_dict.copy()
# Map user-friendly parameter names to OpenAI API parameter names
parameter_mapping = {
"format": "output_format",
"compression": "output_compression",
}
for user_param, api_param in parameter_mapping.items():
if user_param in mapped_tool:
# Map the parameter name and remove the old one
mapped_tool[api_param] = mapped_tool.pop(user_param)
# Validate partial_images parameter for streaming image generation
# OpenAI API requires partial_images to be between 0-3 (inclusive) for image_generation tool
# Reference: https://platform.openai.com/docs/api-reference/responses/create#responses_create-tools-image_generation_tool-partial_images
if "partial_images" in mapped_tool:
partial_images = mapped_tool["partial_images"]
if not isinstance(partial_images, int) or partial_images < 0 or partial_images > 3:
raise ValueError("partial_images must be an integer between 0 and 3 (inclusive).")
response_tools.append(mapped_tool)
else:
response_tools.append(tool_dict)
response_tools.append(tool_dict)
return response_tools
@staticmethod
@@ -435,20 +448,27 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
else:
run_options.pop("parallel_tool_calls", None)
run_options.pop("tool_choice", None)
# tool choice when `tool_choice` is a dict with single key `mode`, extract the mode value
if (tool_choice := run_options.get("tool_choice")) and len(tool_choice.keys()) == 1:
# tool_choice: ToolMode serializes to {"type": "tool_mode", "mode": "..."}, extract mode
if (tool_choice := run_options.get("tool_choice")) and isinstance(tool_choice, dict) and "mode" in tool_choice:
run_options["tool_choice"] = tool_choice["mode"]
# additional properties
# additional properties (excluding response_format which is handled separately)
additional_options = {
key: value for key, value in chat_options.additional_properties.items() if value is not None
key: value
for key, value in chat_options.additional_properties.items()
if value is not None and key != "response_format"
}
if additional_options:
run_options.update(additional_options)
# response format and text config (after additional_properties so user can pass text via additional_properties)
response_format = chat_options.response_format
text_config = run_options.pop("text", None)
# Check both chat_options.response_format and additional_properties for response_format
response_format: Any = (
chat_options.response_format
if chat_options.response_format is not None
else chat_options.additional_properties.get("response_format")
)
text_config: Any = run_options.pop("text", None)
response_format, text_config = self._prepare_response_and_text_format(
response_format=response_format, text_config=text_config
)
@@ -551,7 +571,10 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
if status := props.get("status"):
ret["status"] = status
if reasoning_text := props.get("reasoning_text"):
ret["content"] = {"type": "reasoning_text", "text": reasoning_text}
ret["content"] = {
"type": "reasoning_text",
"text": reasoning_text,
}
if encrypted_content := props.get("encrypted_content"):
ret["encrypted_content"] = encrypted_content
return ret
@@ -597,9 +620,17 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
return file_obj
return {}
case FunctionCallContent():
if not content.call_id:
logger.warning(f"FunctionCallContent missing call_id for function '{content.name}'")
return {}
# Use fc_id from additional_properties if available, otherwise fallback to call_id
fc_id = call_id_to_id.get(content.call_id, content.call_id)
# OpenAI Responses API requires IDs to start with `fc_`
if not fc_id.startswith("fc_"):
fc_id = f"fc_{fc_id}"
return {
"call_id": content.call_id,
"id": call_id_to_id[content.call_id],
"id": fc_id,
"type": "function_call",
"name": content.name,
"arguments": content.arguments,
@@ -735,11 +766,17 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
)
)
case _:
logger.debug("Unparsed annotation type: %s", annotation.type)
logger.debug(
"Unparsed annotation type: %s",
annotation.type,
)
contents.append(text_content)
case "refusal":
contents.append(
TextContent(text=message_content.refusal, raw_representation=message_content)
TextContent(
text=message_content.refusal,
raw_representation=message_content,
)
)
case "reasoning": # ResponseOutputReasoning
if hasattr(item, "content") and item.content:
@@ -760,22 +797,40 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
TextReasoningContent(text=summary.text, raw_representation=summary) # type: ignore[arg-type]
)
case "code_interpreter_call": # ResponseOutputCodeInterpreterCall
if hasattr(item, "outputs") and item.outputs:
for code_output in item.outputs:
if code_output.type == "logs":
contents.append(TextContent(text=code_output.logs, raw_representation=item))
if code_output.type == "image":
contents.append(
call_id = getattr(item, "call_id", None) or getattr(item, "id", None)
outputs: list["Contents"] = []
if item_outputs := getattr(item, "outputs", None):
for code_output in item_outputs:
if getattr(code_output, "type", None) == "logs":
outputs.append(
TextContent(
text=code_output.logs,
raw_representation=code_output,
)
)
elif getattr(code_output, "type", None) == "image":
outputs.append(
UriContent(
uri=code_output.url,
raw_representation=item,
# no more specific media type then this can be inferred
raw_representation=code_output,
media_type="image",
)
)
elif hasattr(item, "code") and item.code:
# fallback if no output was returned is the code:
contents.append(TextContent(text=item.code, raw_representation=item))
if code := getattr(item, "code", None):
contents.append(
CodeInterpreterToolCallContent(
call_id=call_id,
inputs=[TextContent(text=code, raw_representation=item)],
raw_representation=item,
)
)
contents.append(
CodeInterpreterToolResultContent(
call_id=call_id,
outputs=outputs,
raw_representation=item,
)
)
case "function_call": # ResponseOutputFunctionCall
contents.append(
FunctionCallContent(
@@ -799,31 +854,49 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
),
)
)
case "image_generation_call": # ResponseOutputImageGenerationCall
if item.result:
# Handle the result as either a proper data URI or raw base64 string
uri = item.result
media_type = None
if not uri.startswith("data:"):
# Raw base64 string - convert to proper data URI format using helper
uri, media_type = DataContent.create_data_uri_from_base64(uri)
else:
# Parse media type from existing data URI
try:
# Extract media type from data URI (e.g., "data:image/png;base64,...")
if ";" in uri and uri.startswith("data:"):
media_type = uri.split(";")[0].split(":", 1)[1]
except Exception:
# Fallback if parsing fails
media_type = "image"
case "mcp_call":
call_id = item.id
contents.append(
MCPServerToolCallContent(
call_id=call_id,
tool_name=item.name,
server_name=item.server_label,
arguments=item.arguments,
raw_representation=item,
)
)
if item.output is not None:
contents.append(
DataContent(
uri=uri,
media_type=media_type,
MCPServerToolResultContent(
call_id=call_id,
output=[TextContent(text=item.output)],
raw_representation=item,
)
)
# TODO(peterychang): Add support for other content types
case "image_generation_call": # ResponseOutputImageGenerationCall
image_output: DataContent | None = None
if item.result:
base64_data = item.result
image_format = DataContent.detect_image_format_from_base64(base64_data)
image_output = DataContent(
data=base64_data,
media_type=f"image/{image_format}" if image_format else "image/png",
raw_representation=item.result,
)
image_id = item.id
contents.append(
ImageGenerationToolCallContent(
image_id=image_id,
raw_representation=item,
)
)
contents.append(
ImageGenerationToolResultContent(
image_id=image_id,
outputs=image_output,
raw_representation=item,
)
)
case _:
logger.debug("Unparsed output of type: %s: %s", item.type, item)
response_message = ChatMessage(role="assistant", contents=contents)
@@ -973,7 +1046,10 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
# McpApprovalRequest,
# ResponseCustomToolCall,
case "function_call":
function_call_ids[event.output_index] = (event_item.call_id, event_item.name)
function_call_ids[event.output_index] = (
event_item.call_id,
event_item.name,
)
case "mcp_approval_request":
contents.append(
FunctionApprovalRequestContent(
@@ -987,23 +1063,78 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
),
)
)
case "mcp_call":
call_id = getattr(event_item, "id", None) or getattr(event_item, "call_id", None) or ""
contents.append(
MCPServerToolCallContent(
call_id=call_id,
tool_name=getattr(event_item, "name", "") or "",
server_name=getattr(event_item, "server_label", None),
arguments=getattr(event_item, "arguments", None),
raw_representation=event_item,
)
)
result_output = (
getattr(event_item, "result", None)
or getattr(event_item, "output", None)
or getattr(event_item, "outputs", None)
)
parsed_output: list[Contents] | None = None
if result_output:
normalized = (
result_output
if isinstance(result_output, Sequence)
and not isinstance(result_output, (str, bytes, MutableMapping))
else [result_output]
)
parsed_output = [_parse_content(output_item) for output_item in normalized]
contents.append(
MCPServerToolResultContent(
call_id=call_id,
output=parsed_output,
raw_representation=event_item,
)
)
case "code_interpreter_call": # ResponseOutputCodeInterpreterCall
call_id = getattr(event_item, "call_id", None) or getattr(event_item, "id", None)
outputs: list[Contents] = []
if hasattr(event_item, "outputs") and event_item.outputs:
for code_output in event_item.outputs:
if code_output.type == "logs":
contents.append(TextContent(text=code_output.logs, raw_representation=event_item))
if code_output.type == "image":
contents.append(
if getattr(code_output, "type", None) == "logs":
outputs.append(
TextContent(
text=cast(Any, code_output).logs,
raw_representation=code_output,
)
)
elif getattr(code_output, "type", None) == "image":
outputs.append(
UriContent(
uri=code_output.url,
raw_representation=event_item,
# no more specific media type then this can be inferred
uri=cast(Any, code_output).url,
raw_representation=code_output,
media_type="image",
)
)
elif hasattr(event_item, "code") and event_item.code:
# fallback if no output was returned is the code:
contents.append(TextContent(text=event_item.code, raw_representation=event_item))
if hasattr(event_item, "code") and event_item.code:
contents.append(
CodeInterpreterToolCallContent(
call_id=call_id,
inputs=[
TextContent(
text=event_item.code,
raw_representation=event_item,
)
],
raw_representation=event_item,
)
)
contents.append(
CodeInterpreterToolResultContent(
call_id=call_id,
outputs=outputs,
raw_representation=event_item,
)
)
case "reasoning": # ResponseOutputReasoning
if hasattr(event_item, "content") and event_item.content:
for index, reasoning_content in enumerate(event_item.content):
@@ -1031,7 +1162,10 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
call_id=call_id,
name=name,
arguments=event.delta,
additional_properties={"output_index": event.output_index, "fc_id": event.item_id},
additional_properties={
"output_index": event.output_index,
"fc_id": event.item_id,
},
raw_representation=event,
)
)
@@ -1043,14 +1177,27 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
# Use helper function to create data URI from base64
uri, media_type = DataContent.create_data_uri_from_base64(image_base64)
image_output = DataContent(
uri=uri,
media_type=media_type,
additional_properties={
"partial_image_index": partial_index,
"is_partial_image": True,
},
raw_representation=event,
)
image_id = getattr(event, "item_id", None)
contents.append(
DataContent(
uri=uri,
media_type=media_type,
additional_properties={
"partial_image_index": partial_index,
"is_partial_image": True,
},
ImageGenerationToolCallContent(
image_id=image_id,
raw_representation=event,
)
)
contents.append(
ImageGenerationToolResultContent(
image_id=image_id,
outputs=image_output,
raw_representation=event,
)
)
python/packages/core/pyproject.toml
+1 -1
View File
@@ -4,7 +4,7 @@ description = "Microsoft Agent Framework for building AI Agents with Python. Thi
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
readme = "README.md"
requires-python = ">=3.10"
version = "1.0.0b251223"
version = "1.0.0b260107"
license-files = ["LICENSE"]
urls.homepage = "https://aka.ms/agent-framework"
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
python/packages/core/tests/azure/test_azure_responses_client.py
+9 -11
View File
@@ -552,26 +552,24 @@ async def test_azure_responses_client_agent_chat_options_agent_level() -> None:
async def test_azure_responses_client_agent_hosted_mcp_tool() -> None:
"""Integration test for HostedMCPTool with Azure Response Agent using Microsoft Learn MCP."""
mcp_tool = HostedMCPTool(
name="Microsoft Learn MCP",
url="https://learn.microsoft.com/api/mcp",
description="A Microsoft Learn MCP server for documentation questions",
approval_mode="never_require",
)
async with ChatAgent(
chat_client=AzureOpenAIResponsesClient(credential=AzureCliCredential()),
instructions="You are a helpful assistant that can help with microsoft documentation questions.",
tools=[mcp_tool],
tools=HostedMCPTool(
name="Microsoft Learn MCP",
url="https://learn.microsoft.com/api/mcp",
description="A Microsoft Learn MCP server for documentation questions",
approval_mode="never_require",
),
) as agent:
response = await agent.run(
"How to create an Azure storage account using az cli?",
max_tokens=200,
# this needs to be high enough to handle the full MCP tool response.
max_tokens=5000,
)
assert isinstance(response, AgentRunResponse)
assert response.text is not None
assert len(response.text) > 0
assert response.text
# Should contain Azure-related content since it's asking about Azure CLI
assert any(term in response.text.lower() for term in ["azure", "storage", "account", "cli"])
python/packages/core/tests/core/test_agents.py
+90
View File
@@ -632,3 +632,93 @@ async def test_agent_tool_receives_thread_in_kwargs(chat_client_base: Any) -> No
assert result.text == "done"
assert captured.get("has_thread") is True
assert captured.get("has_message_store") is True
async def test_chat_agent_tool_choice_run_level_overrides_agent_level(
chat_client_base: Any, ai_function_tool: Any
) -> None:
"""Verify that tool_choice passed to run() overrides agent-level tool_choice."""
from agent_framework import ChatOptions, ToolMode
captured_options: list[ChatOptions] = []
# Store the original inner method
original_inner = chat_client_base._inner_get_response
async def capturing_inner(
*, messages: MutableSequence[ChatMessage], chat_options: ChatOptions, **kwargs: Any
) -> ChatResponse:
captured_options.append(chat_options)
return await original_inner(messages=messages, chat_options=chat_options, **kwargs)
chat_client_base._inner_get_response = capturing_inner
# Create agent with agent-level tool_choice="auto" and a tool (tools required for tool_choice to be meaningful)
agent = ChatAgent(chat_client=chat_client_base, tool_choice="auto", tools=[ai_function_tool])
# Run with run-level tool_choice="required"
await agent.run("Hello", tool_choice="required")
# Verify the client received tool_choice="required", not "auto"
assert len(captured_options) >= 1
assert captured_options[0].tool_choice == "required"
assert captured_options[0].tool_choice == ToolMode.REQUIRED_ANY
async def test_chat_agent_tool_choice_agent_level_used_when_run_level_not_specified(
chat_client_base: Any, ai_function_tool: Any
) -> None:
"""Verify that agent-level tool_choice is used when run() doesn't specify one."""
from agent_framework import ChatOptions, ToolMode
captured_options: list[ChatOptions] = []
original_inner = chat_client_base._inner_get_response
async def capturing_inner(
*, messages: MutableSequence[ChatMessage], chat_options: ChatOptions, **kwargs: Any
) -> ChatResponse:
captured_options.append(chat_options)
return await original_inner(messages=messages, chat_options=chat_options, **kwargs)
chat_client_base._inner_get_response = capturing_inner
# Create agent with agent-level tool_choice="required" and a tool
agent = ChatAgent(chat_client=chat_client_base, tool_choice="required", tools=[ai_function_tool])
# Run without specifying tool_choice
await agent.run("Hello")
# Verify the client received tool_choice="required" from agent-level
assert len(captured_options) >= 1
assert captured_options[0].tool_choice == "required"
assert captured_options[0].tool_choice == ToolMode.REQUIRED_ANY
async def test_chat_agent_tool_choice_none_at_run_preserves_agent_level(
chat_client_base: Any, ai_function_tool: Any
) -> None:
"""Verify that tool_choice=None at run() uses agent-level default."""
from agent_framework import ChatOptions
captured_options: list[ChatOptions] = []
original_inner = chat_client_base._inner_get_response
async def capturing_inner(
*, messages: MutableSequence[ChatMessage], chat_options: ChatOptions, **kwargs: Any
) -> ChatResponse:
captured_options.append(chat_options)
return await original_inner(messages=messages, chat_options=chat_options, **kwargs)
chat_client_base._inner_get_response = capturing_inner
# Create agent with agent-level tool_choice="auto" and a tool
agent = ChatAgent(chat_client=chat_client_base, tool_choice="auto", tools=[ai_function_tool])
# Run with explicitly passing None (same as not specifying)
await agent.run("Hello", tool_choice=None)
# Verify the client received tool_choice="auto" from agent-level
assert len(captured_options) >= 1
assert captured_options[0].tool_choice == "auto"
python/packages/core/tests/core/test_tools.py
+25
View File
@@ -10,6 +10,7 @@ from pydantic import BaseModel
from agent_framework import (
AIFunction,
HostedCodeInterpreterTool,
HostedImageGenerationTool,
HostedMCPTool,
ToolProtocol,
ai_function,
@@ -818,6 +819,30 @@ def test_hosted_code_interpreter_tool_with_unknown_input():
HostedCodeInterpreterTool(inputs={"hosted_file": "file-single"})
def test_hosted_image_generation_tool_defaults():
"""HostedImageGenerationTool should default name and empty description."""
tool = HostedImageGenerationTool()
assert tool.name == "image_generation"
assert tool.description == ""
assert tool.options is None
assert str(tool) == "HostedImageGenerationTool(name=image_generation)"
def test_hosted_image_generation_tool_with_options():
"""HostedImageGenerationTool should store options."""
tool = HostedImageGenerationTool(
description="Generate images",
options={"format": "png", "size": "1024x1024"},
additional_properties={"quality": "high"},
)
assert tool.name == "image_generation"
assert tool.description == "Generate images"
assert tool.options == {"format": "png", "size": "1024x1024"}
assert tool.additional_properties == {"quality": "high"}
# region HostedMCPTool tests
python/packages/core/tests/core/test_types.py
+187
View File
@@ -18,6 +18,8 @@ from agent_framework import (
ChatResponse,
ChatResponseUpdate,
CitationAnnotation,
CodeInterpreterToolCallContent,
CodeInterpreterToolResultContent,
DataContent,
ErrorContent,
FinishReason,
@@ -27,6 +29,10 @@ from agent_framework import (
FunctionResultContent,
HostedFileContent,
HostedVectorStoreContent,
ImageGenerationToolCallContent,
ImageGenerationToolResultContent,
MCPServerToolCallContent,
MCPServerToolResultContent,
Role,
TextContent,
TextReasoningContent,
@@ -269,6 +275,78 @@ def test_hosted_file_content_minimal():
assert isinstance(content, BaseContent)
def test_hosted_file_content_optional_fields():
"""HostedFileContent should capture optional media type and name."""
content = HostedFileContent(file_id="file-789", media_type="image/png", name="plot.png")
assert content.media_type == "image/png"
assert content.name == "plot.png"
assert content.has_top_level_media_type("image")
assert content.has_top_level_media_type("application") is False
# region: CodeInterpreter content
def test_code_interpreter_tool_call_content_parses_inputs():
call = CodeInterpreterToolCallContent(
call_id="call-1",
inputs=[{"type": "text", "text": "print('hi')"}],
)
assert call.type == "code_interpreter_tool_call"
assert call.call_id == "call-1"
assert call.inputs and isinstance(call.inputs[0], TextContent)
assert call.inputs[0].text == "print('hi')"
def test_code_interpreter_tool_result_content_outputs():
result = CodeInterpreterToolResultContent(
call_id="call-2",
outputs=[
{"type": "text", "text": "log output"},
{"type": "uri", "uri": "https://example.com/file.png", "media_type": "image/png"},
],
)
assert result.type == "code_interpreter_tool_result"
assert result.call_id == "call-2"
assert result.outputs is not None
assert isinstance(result.outputs[0], TextContent)
assert isinstance(result.outputs[1], UriContent)
# region: Image generation content
def test_image_generation_tool_contents():
call = ImageGenerationToolCallContent(image_id="img-1")
outputs = [DataContent(data=b"1234", media_type="image/png")]
result = ImageGenerationToolResultContent(image_id="img-1", outputs=outputs)
assert call.type == "image_generation_tool_call"
assert call.image_id == "img-1"
assert result.type == "image_generation_tool_result"
assert result.image_id == "img-1"
assert result.outputs and isinstance(result.outputs[0], DataContent)
# region: MCP server tool content
def test_mcp_server_tool_call_and_result():
call = MCPServerToolCallContent(call_id="c-1", tool_name="tool", server_name="server", arguments={"x": 1})
assert call.type == "mcp_server_tool_call"
assert call.arguments == {"x": 1}
result = MCPServerToolResultContent(call_id="c-1", output=[{"type": "text", "text": "done"}])
assert result.type == "mcp_server_tool_result"
assert result.output
with raises(ValueError):
MCPServerToolCallContent(call_id="", tool_name="tool")
# region: HostedVectorStoreContent
@@ -469,6 +547,15 @@ def test_function_approval_serialization_roundtrip():
# The Contents union will need to be handled differently when we fully migrate
def test_function_approval_accepts_mcp_call():
"""Ensure FunctionApprovalRequestContent supports MCP server tool calls."""
mcp_call = MCPServerToolCallContent(call_id="c-mcp", tool_name="tool", server_name="srv", arguments={"x": 1})
req = FunctionApprovalRequestContent(id="req-mcp", function_call=mcp_call)
assert isinstance(req.function_call, MCPServerToolCallContent)
assert req.function_call.call_id == "c-mcp"
# region BaseContent Serialization
@@ -844,6 +931,54 @@ def test_chat_options_and(ai_function_tool, ai_tool) -> None:
assert options3.additional_properties.get("p") == 1
def test_chat_options_and_tool_choice_override() -> None:
"""Test that tool_choice from other takes precedence in ChatOptions merge."""
# Agent-level defaults to "auto"
agent_options = ChatOptions(model_id="gpt-4o", tool_choice="auto")
# Run-level specifies "required"
run_options = ChatOptions(tool_choice="required")
merged = agent_options & run_options
# Run-level should override agent-level
assert merged.tool_choice == "required"
assert merged.model_id == "gpt-4o" # Other fields preserved
def test_chat_options_and_tool_choice_none_in_other_uses_self() -> None:
"""Test that when other.tool_choice is None, self.tool_choice is used."""
agent_options = ChatOptions(tool_choice="auto")
run_options = ChatOptions(model_id="gpt-4.1") # tool_choice is None
merged = agent_options & run_options
# Should keep agent-level tool_choice since run-level is None
assert merged.tool_choice == "auto"
assert merged.model_id == "gpt-4.1"
def test_chat_options_and_tool_choice_with_tool_mode() -> None:
"""Test ChatOptions merge with ToolMode objects."""
agent_options = ChatOptions(tool_choice=ToolMode.AUTO)
run_options = ChatOptions(tool_choice=ToolMode.REQUIRED_ANY)
merged = agent_options & run_options
assert merged.tool_choice == ToolMode.REQUIRED_ANY
assert merged.tool_choice == "required" # ToolMode equality with string
def test_chat_options_and_tool_choice_required_specific_function() -> None:
"""Test ChatOptions merge with required specific function."""
agent_options = ChatOptions(tool_choice="auto")
run_options = ChatOptions(tool_choice=ToolMode.REQUIRED(function_name="get_weather"))
merged = agent_options & run_options
assert merged.tool_choice == "required"
assert merged.tool_choice.required_function_name == "get_weather"
# region Agent Response Fixtures
@@ -2085,3 +2220,55 @@ def test_prepare_function_call_results_nested_pydantic_model():
assert "Seattle" in json_result
assert "rainy" in json_result
assert "18.0" in json_result or "18" in json_result
# region prepare_function_call_results with MCP TextContent-like objects
def test_prepare_function_call_results_text_content_single():
"""Test that objects with text attribute (like MCP TextContent) are properly handled."""
from dataclasses import dataclass
@dataclass
class MockTextContent:
text: str
result = [MockTextContent("Hello from MCP tool!")]
json_result = prepare_function_call_results(result)
# Should extract text and serialize as JSON array of strings
assert isinstance(json_result, str)
assert json_result == '["Hello from MCP tool!"]'
def test_prepare_function_call_results_text_content_multiple():
"""Test that multiple TextContent-like objects are serialized correctly."""
from dataclasses import dataclass
@dataclass
class MockTextContent:
text: str
result = [MockTextContent("First result"), MockTextContent("Second result")]
json_result = prepare_function_call_results(result)
# Should extract text from each and serialize as JSON array
assert isinstance(json_result, str)
assert json_result == '["First result", "Second result"]'
def test_prepare_function_call_results_text_content_with_non_string_text():
"""Test that objects with non-string text attribute are not treated as TextContent."""
class BadTextContent:
def __init__(self):
self.text = 12345 # Not a string!
result = [BadTextContent()]
json_result = prepare_function_call_results(result)
# Should not extract text since it's not a string, will serialize the object
assert isinstance(json_result, str)
# endregion
python/packages/core/tests/openai/test_openai_chat_client.py
+30
View File
@@ -236,6 +236,36 @@ async def test_openai_chat_completion_response() -> None:
assert "scientists" in response.text
@pytest.mark.flaky
@skip_if_openai_integration_tests_disabled
async def test_openai_chat_completion_response_params() -> None:
"""Test OpenAI chat completion responses."""
openai_chat_client = OpenAIChatClient()
assert isinstance(openai_chat_client, ChatClientProtocol)
messages: list[ChatMessage] = []
messages.append(
ChatMessage(
role="user",
text="Emily and David, two passionate scientists, met during a research expedition to Antarctica. "
"Bonded by their love for the natural world and shared curiosity, they uncovered a "
"groundbreaking phenomenon in glaciology that could potentially reshape our understanding "
"of climate change.",
)
)
messages.append(ChatMessage(role="user", text="who are Emily and David?"))
# Test that the client can be used to get a response
response = await openai_chat_client.get_response(
messages=messages, chat_options=ChatOptions(max_tokens=150, temperature=0.7, top_p=0.9)
)
assert response is not None
assert isinstance(response, ChatResponse)
assert "scientists" in response.text
@pytest.mark.flaky
@skip_if_openai_integration_tests_disabled
async def test_openai_chat_completion_response_tools() -> None:
python/packages/core/tests/openai/test_openai_responses_client.py
+181 -66
View File
@@ -26,6 +26,8 @@ from agent_framework import (
ChatMessage,
ChatResponse,
ChatResponseUpdate,
CodeInterpreterToolCallContent,
CodeInterpreterToolResultContent,
DataContent,
FunctionApprovalRequestContent,
FunctionApprovalResponseContent,
@@ -34,9 +36,12 @@ from agent_framework import (
HostedCodeInterpreterTool,
HostedFileContent,
HostedFileSearchTool,
HostedImageGenerationTool,
HostedMCPTool,
HostedVectorStoreContent,
HostedWebSearchTool,
ImageGenerationToolCallContent,
ImageGenerationToolResultContent,
MCPStreamableHTTPTool,
Role,
TextContent,
@@ -612,11 +617,14 @@ def test_response_content_creation_with_code_interpreter() -> None:
response = client._parse_response_from_openai(mock_response, chat_options=ChatOptions()) # type: ignore
assert len(response.messages[0].contents) == 2
assert isinstance(response.messages[0].contents[0], TextContent)
assert response.messages[0].contents[0].text == "Code execution log"
assert isinstance(response.messages[0].contents[1], UriContent)
assert response.messages[0].contents[1].uri == "https://example.com/image.png"
assert response.messages[0].contents[1].media_type == "image"
call_content, result_content = response.messages[0].contents
assert isinstance(call_content, CodeInterpreterToolCallContent)
assert call_content.inputs is not None
assert isinstance(call_content.inputs[0], TextContent)
assert isinstance(result_content, CodeInterpreterToolResultContent)
assert result_content.outputs is not None
assert any(isinstance(out, TextContent) for out in result_content.outputs)
assert any(isinstance(out, UriContent) for out in result_content.outputs)
def test_response_content_creation_with_function_call() -> None:
@@ -761,14 +769,13 @@ def test_prepare_tools_for_openai_with_raw_image_generation() -> None:
"""Test that raw image_generation tool dict is handled correctly with parameter mapping."""
client = OpenAIResponsesClient(model_id="test-model", api_key="test-key")
# Test with raw tool dict using user-friendly parameter names
# Test with raw tool dict using OpenAI parameters directly
tool = {
"type": "image_generation",
"size": "1536x1024",
"quality": "high",
"format": "webp", # Will be mapped to output_format
"compression": 75, # Will be mapped to output_compression
"background": "transparent",
"output_format": "webp",
"output_quality": 75,
}
resp_tools = client._prepare_tools_for_openai([tool])
@@ -780,10 +787,8 @@ def test_prepare_tools_for_openai_with_raw_image_generation() -> None:
assert image_tool["type"] == "image_generation"
assert image_tool["size"] == "1536x1024"
assert image_tool["quality"] == "high"
assert image_tool["background"] == "transparent"
# Check parameter name mapping
assert image_tool["output_format"] == "webp"
assert image_tool["output_compression"] == 75
assert image_tool["output_quality"] == 75
def test_prepare_tools_for_openai_with_raw_image_generation_openai_responses_params() -> None:
@@ -797,7 +802,7 @@ def test_prepare_tools_for_openai_with_raw_image_generation_openai_responses_par
"model": "gpt-image-1",
"input_fidelity": "high",
"moderation": "strict",
"partial_images": 2, # Should be integer 0-3
"output_format": "png",
}
resp_tools = client._prepare_tools_for_openai([tool])
@@ -815,7 +820,7 @@ def test_prepare_tools_for_openai_with_raw_image_generation_openai_responses_par
assert tool_dict["model"] == "gpt-image-1"
assert tool_dict["input_fidelity"] == "high"
assert tool_dict["moderation"] == "strict"
assert tool_dict["partial_images"] == 2
assert tool_dict["output_format"] == "png"
def test_prepare_tools_for_openai_with_raw_image_generation_minimal() -> None:
@@ -836,6 +841,24 @@ def test_prepare_tools_for_openai_with_raw_image_generation_minimal() -> None:
assert len(image_tool) == 1
def test_prepare_tools_for_openai_with_hosted_image_generation() -> None:
"""Test HostedImageGenerationTool conversion."""
client = OpenAIResponsesClient(model_id="test-model", api_key="test-key")
tool = HostedImageGenerationTool(
description="Generate images",
options={"output_format": "png", "size": "512x512"},
additional_properties={"quality": "high"},
)
resp_tools = client._prepare_tools_for_openai([tool])
assert len(resp_tools) == 1
image_tool = resp_tools[0]
assert image_tool["type"] == "image_generation"
assert image_tool["output_format"] == "png"
assert image_tool["size"] == "512x512"
assert image_tool["quality"] == "high"
def test_parse_chunk_from_openai_with_mcp_approval_request() -> None:
"""Test that a streaming mcp_approval_request event is parsed into FunctionApprovalRequestContent."""
client = OpenAIResponsesClient(model_id="test-model", api_key="test-key")
@@ -1278,9 +1301,11 @@ def test_parse_chunk_from_openai_code_interpreter() -> None:
result = client._parse_chunk_from_openai(mock_event_image, chat_options, function_call_ids) # type: ignore
assert len(result.contents) == 1
assert isinstance(result.contents[0], UriContent)
assert result.contents[0].uri == "https://example.com/plot.png"
assert result.contents[0].media_type == "image"
assert isinstance(result.contents[0], CodeInterpreterToolResultContent)
assert result.contents[0].outputs
assert any(
isinstance(out, UriContent) and out.uri == "https://example.com/plot.png" for out in result.contents[0].outputs
)
def test_parse_chunk_from_openai_reasoning() -> None:
@@ -1495,12 +1520,16 @@ def test_parse_response_from_openai_image_generation_raw_base64():
with patch.object(client, "_get_metadata_from_response", return_value={}):
response = client._parse_response_from_openai(mock_response, chat_options=ChatOptions()) # type: ignore
# Verify the response contains DataContent with proper URI and media_type
assert len(response.messages[0].contents) == 1
content = response.messages[0].contents[0]
assert isinstance(content, DataContent)
assert content.uri.startswith("data:image/png;base64,")
assert content.media_type == "image/png"
# Verify the response contains call + result with DataContent output
assert len(response.messages[0].contents) == 2
call_content, result_content = response.messages[0].contents
assert isinstance(call_content, ImageGenerationToolCallContent)
assert isinstance(result_content, ImageGenerationToolResultContent)
assert result_content.outputs
data_out = result_content.outputs
assert isinstance(data_out, DataContent)
assert data_out.uri.startswith("data:image/png;base64,")
assert data_out.media_type == "image/png"
def test_parse_response_from_openai_image_generation_existing_data_uri():
@@ -1521,19 +1550,23 @@ def test_parse_response_from_openai_image_generation_existing_data_uri():
valid_webp_base64 = base64.b64encode(webp_signature + b"VP8 fake_data").decode()
mock_item = MagicMock()
mock_item.type = "image_generation_call"
mock_item.result = f"data:image/webp;base64,{valid_webp_base64}"
mock_item.result = valid_webp_base64
mock_response.output = [mock_item]
with patch.object(client, "_get_metadata_from_response", return_value={}):
response = client._parse_response_from_openai(mock_response, chat_options=ChatOptions()) # type: ignore
# Verify the response contains DataContent with proper media_type parsed from URI
assert len(response.messages[0].contents) == 1
content = response.messages[0].contents[0]
assert isinstance(content, DataContent)
assert content.uri == f"data:image/webp;base64,{valid_webp_base64}"
assert content.media_type == "image/webp"
# Verify the response contains call + result with DataContent output
assert len(response.messages[0].contents) == 2
call_content, result_content = response.messages[0].contents
assert isinstance(call_content, ImageGenerationToolCallContent)
assert isinstance(result_content, ImageGenerationToolResultContent)
assert result_content.outputs
data_out = result_content.outputs
assert isinstance(data_out, DataContent)
assert data_out.uri == f"data:image/webp;base64,{valid_webp_base64}"
assert data_out.media_type == "image/webp"
def test_parse_response_from_openai_image_generation_format_detection():
@@ -1559,10 +1592,12 @@ def test_parse_response_from_openai_image_generation_format_detection():
with patch.object(client, "_get_metadata_from_response", return_value={}):
response_jpeg = client._parse_response_from_openai(mock_response_jpeg, chat_options=ChatOptions()) # type: ignore
content_jpeg = response_jpeg.messages[0].contents[0]
assert isinstance(content_jpeg, DataContent)
assert content_jpeg.media_type == "image/jpeg"
assert "data:image/jpeg;base64," in content_jpeg.uri
result_contents = response_jpeg.messages[0].contents
assert isinstance(result_contents[1], ImageGenerationToolResultContent)
outputs = result_contents[1].outputs
assert outputs and isinstance(outputs, DataContent)
assert outputs.media_type == "image/jpeg"
assert "data:image/jpeg;base64," in outputs.uri
# Test WEBP detection
webp_signature = b"RIFF" + b"\x00\x00\x00\x00" + b"WEBP"
@@ -1583,10 +1618,10 @@ def test_parse_response_from_openai_image_generation_format_detection():
with patch.object(client, "_get_metadata_from_response", return_value={}):
response_webp = client._parse_response_from_openai(mock_response_webp, chat_options=ChatOptions()) # type: ignore
content_webp = response_webp.messages[0].contents[0]
assert isinstance(content_webp, DataContent)
assert content_webp.media_type == "image/webp"
assert "data:image/webp;base64," in content_webp.uri
outputs_webp = response_webp.messages[0].contents[1].outputs
assert outputs_webp and isinstance(outputs_webp, DataContent)
assert outputs_webp.media_type == "image/webp"
assert "data:image/webp;base64," in outputs_webp.uri
def test_parse_response_from_openai_image_generation_fallback():
@@ -1615,9 +1650,11 @@ def test_parse_response_from_openai_image_generation_fallback():
response = client._parse_response_from_openai(mock_response, chat_options=ChatOptions()) # type: ignore
# Verify it falls back to PNG format for unrecognized binary data
assert len(response.messages[0].contents) == 1
content = response.messages[0].contents[0]
assert isinstance(content, DataContent)
assert len(response.messages[0].contents) == 2
result_content = response.messages[0].contents[1]
assert isinstance(result_content, ImageGenerationToolResultContent)
assert result_content.outputs
content = result_content.outputs
assert content.media_type == "image/png"
assert f"data:image/png;base64,{unrecognized_base64}" == content.uri
@@ -2153,38 +2190,30 @@ async def test_openai_responses_client_agent_hosted_code_interpreter_tool():
@pytest.mark.flaky
@skip_if_openai_integration_tests_disabled
async def test_openai_responses_client_agent_raw_image_generation_tool():
async def test_openai_responses_client_agent_image_generation_tool():
"""Test OpenAI Responses Client agent with raw image_generation tool through OpenAIResponsesClient."""
async with ChatAgent(
chat_client=OpenAIResponsesClient(),
instructions="You are a helpful assistant that can generate images.",
tools=[{"type": "image_generation", "size": "1024x1024", "quality": "low", "format": "png"}],
tools=HostedImageGenerationTool(options={"image_size": "1024x1024", "media_type": "png"}),
) as agent:
# Test image generation functionality
response = await agent.run("Generate an image of a cute red panda sitting on a tree branch in a forest.")
assert isinstance(response, AgentRunResponse)
assert response.messages
# For image generation, we expect to get some response content
# This could be DataContent with image data, UriContent
assert response.messages is not None and len(response.messages) > 0
# Check that we have some kind of content in the response
total_contents = sum(len(message.contents) for message in response.messages)
assert total_contents > 0, f"Expected some content in response messages, got {total_contents} contents"
# Verify we got image content - look for DataContent with URI starting with "data:image"
# Verify we got image content - look for ImageGenerationToolResultContent
image_content_found = False
for message in response.messages:
for content in message.contents:
uri = getattr(content, "uri", None)
if uri and uri.startswith("data:image"):
if content.type == "image_generation_tool_result" and content.outputs:
image_content_found = True
break
if image_content_found:
break
# The test passes if we got image content (which we did based on the visible base64 output)
# The test passes if we got image content
assert image_content_found, "Expected to find image content in response"
@@ -2306,26 +2335,24 @@ async def test_openai_responses_client_agent_chat_options_agent_level() -> None:
async def test_openai_responses_client_agent_hosted_mcp_tool() -> None:
"""Integration test for HostedMCPTool with OpenAI Response Agent using Microsoft Learn MCP."""
mcp_tool = HostedMCPTool(
name="Microsoft Learn MCP",
url="https://learn.microsoft.com/api/mcp",
description="A Microsoft Learn MCP server for documentation questions",
approval_mode="never_require",
)
async with ChatAgent(
chat_client=OpenAIResponsesClient(),
instructions="You are a helpful assistant that can help with microsoft documentation questions.",
tools=[mcp_tool],
tools=HostedMCPTool(
name="Microsoft Learn MCP",
url="https://learn.microsoft.com/api/mcp",
description="A Microsoft Learn MCP server for documentation questions",
approval_mode="never_require",
),
) as agent:
response = await agent.run(
"How to create an Azure storage account using az cli?",
max_tokens=200,
# this needs to be high enough to handle the full MCP tool response.
max_tokens=5000,
)
assert isinstance(response, AgentRunResponse)
assert response.text is not None
assert len(response.text) > 0
assert response.text
# Should contain Azure-related content since it's asking about Azure CLI
assert any(term in response.text.lower() for term in ["azure", "storage", "account", "cli"])
@@ -2355,3 +2382,91 @@ async def test_openai_responses_client_agent_local_mcp_tool() -> None:
assert len(response.text) > 0
# Should contain Azure-related content since it's asking about Azure CLI
assert any(term in response.text.lower() for term in ["azure", "storage", "account", "cli"])
class ReleaseBrief(BaseModel):
"""Structured output model for release brief testing."""
title: str
summary: str
highlights: list[str]
model_config = {"extra": "forbid"}
@pytest.mark.flaky
@skip_if_openai_integration_tests_disabled
async def test_openai_responses_client_agent_with_response_format_pydantic() -> None:
"""Integration test for response_format with Pydantic model using OpenAI Responses Client."""
async with ChatAgent(
chat_client=OpenAIResponsesClient(),
instructions="You are a helpful assistant that returns structured JSON responses.",
) as agent:
response = await agent.run(
"Summarize the following release notes into a ReleaseBrief:\n\n"
"Version 2.0 Release Notes:\n"
"- Added new streaming API for real-time responses\n"
"- Improved error handling with detailed messages\n"
"- Performance boost of 50% in batch processing\n"
"- Fixed memory leak in connection pooling",
response_format=ReleaseBrief,
)
# Validate response
assert isinstance(response, AgentRunResponse)
assert response.value is not None
assert isinstance(response.value, ReleaseBrief)
# Validate structured output fields
brief = response.value
assert len(brief.title) > 0
assert len(brief.summary) > 0
assert len(brief.highlights) > 0
@pytest.mark.flaky
@skip_if_openai_integration_tests_disabled
async def test_openai_responses_client_agent_with_runtime_json_schema() -> None:
"""Integration test for response_format with runtime JSON schema using OpenAI Responses Client."""
runtime_schema = {
"title": "WeatherDigest",
"type": "object",
"properties": {
"location": {"type": "string"},
"conditions": {"type": "string"},
"temperature_c": {"type": "number"},
"advisory": {"type": "string"},
},
"required": ["location", "conditions", "temperature_c", "advisory"],
"additionalProperties": False,
}
async with ChatAgent(
chat_client=OpenAIResponsesClient(),
instructions="Return only JSON that matches the provided schema. Do not add commentary.",
) as agent:
response = await agent.run(
"Give a brief weather digest for Seattle.",
additional_chat_options={
"response_format": {
"type": "json_schema",
"json_schema": {
"name": runtime_schema["title"],
"strict": True,
"schema": runtime_schema,
},
},
},
)
# Validate response
assert isinstance(response, AgentRunResponse)
assert response.text is not None
# Parse JSON and validate structure
import json
parsed = json.loads(response.text)
assert "location" in parsed
assert "conditions" in parsed
assert "temperature_c" in parsed
assert "advisory" in parsed
python/packages/core/tests/workflow/test_executor.py
+39 -4
View File
@@ -3,12 +3,14 @@
import pytest
from agent_framework import (
ChatMessage,
Executor,
ExecutorCompletedEvent,
ExecutorInvokedEvent,
Message,
WorkflowBuilder,
WorkflowContext,
executor,
handler,
)
@@ -182,8 +184,8 @@ async def test_executor_completed_event_contains_sent_messages():
assert collector_completed.data is None
async def test_executor_completed_event_none_when_no_messages_sent():
"""Test that ExecutorCompletedEvent.data is None when no messages are sent."""
async def test_executor_completed_event_includes_yielded_outputs():
"""Test that ExecutorCompletedEvent.data includes yielded outputs."""
from typing_extensions import Never
from agent_framework import WorkflowOutputEvent
@@ -201,9 +203,10 @@ async def test_executor_completed_event_none_when_no_messages_sent():
assert len(completed_events) == 1
assert completed_events[0].executor_id == "yielder"
assert completed_events[0].data is None
# Yielded outputs are now included in ExecutorCompletedEvent.data
assert completed_events[0].data == ["TEST"]
# Verify the output was still yielded correctly
# Verify the output was also yielded as WorkflowOutputEvent
output_events = [e for e in events if isinstance(e, WorkflowOutputEvent)]
assert len(output_events) == 1
assert output_events[0].data == "TEST"
@@ -261,3 +264,35 @@ async def test_executor_events_with_complex_message_types():
collector_invoked = next(e for e in invoked_events if e.executor_id == "collector")
assert isinstance(collector_invoked.data, Response)
assert collector_invoked.data.results == ["HELLO", "HELLO", "HELLO"]
async def test_executor_invoked_event_data_not_mutated_by_handler():
"""Test that ExecutorInvokedEvent.data captures original input, not mutated input."""
@executor(id="Mutator")
async def mutator(messages: list[ChatMessage], ctx: WorkflowContext[list[ChatMessage]]) -> None:
# The handler mutates the input list by appending new messages
original_len = len(messages)
messages.append(ChatMessage(role="assistant", text="Added by executor"))
await ctx.send_message(messages)
# Verify mutation happened
assert len(messages) == original_len + 1
workflow = WorkflowBuilder().set_start_executor(mutator).build()
# Run with a single user message
input_messages = [ChatMessage(role="user", text="hello")]
events = await workflow.run(input_messages)
# Find the invoked event for the Mutator executor
invoked_events = [e for e in events if isinstance(e, ExecutorInvokedEvent)]
assert len(invoked_events) == 1
mutator_invoked = invoked_events[0]
# The event data should contain ONLY the original input (1 user message)
assert mutator_invoked.executor_id == "Mutator"
assert len(mutator_invoked.data) == 1, (
f"Expected 1 message (original input), got {len(mutator_invoked.data)}: "
f"{[m.text for m in mutator_invoked.data]}"
)
assert mutator_invoked.data[0].text == "hello"
python/packages/core/tests/workflow/test_workflow_agent.py
+78
View File
@@ -702,6 +702,84 @@ class TestWorkflowAgent:
assert unique_text_count == 1, f"Response should appear exactly once, but appeared {unique_text_count} times"
class TestWorkflowAgentAuthorName:
"""Test cases for author_name enrichment in WorkflowAgent (GitHub issue #1331)."""
async def test_agent_run_update_event_gets_executor_id_as_author_name(self):
"""Test that AgentRunUpdateEvent gets executor_id as author_name when not already set.
This validates the fix for GitHub issue #1331: agent responses should include
identification of which agent produced them in multi-agent workflows.
"""
# Create workflow with executor that emits AgentRunUpdateEvent without author_name
executor1 = SimpleExecutor(id="my_executor_id", response_text="Response", emit_streaming=False)
workflow = WorkflowBuilder().set_start_executor(executor1).build()
agent = WorkflowAgent(workflow=workflow, name="Test Agent")
# Collect streaming updates
updates: list[AgentRunResponseUpdate] = []
async for update in agent.run_stream("Hello"):
updates.append(update)
# Verify at least one update was received
assert len(updates) >= 1
# Verify author_name is set to executor_id
assert updates[0].author_name == "my_executor_id"
async def test_agent_run_update_event_preserves_existing_author_name(self):
"""Test that existing author_name is preserved and not overwritten."""
class AuthorNameExecutor(Executor):
"""Executor that sets author_name explicitly."""
@handler
async def handle_message(self, message: list[ChatMessage], ctx: WorkflowContext[list[ChatMessage]]) -> None:
# Emit update with explicit author_name
update = AgentRunResponseUpdate(
contents=[TextContent(text="Response with author")],
role=Role.ASSISTANT,
author_name="custom_author_name", # Explicitly set
message_id=str(uuid.uuid4()),
)
await ctx.add_event(AgentRunUpdateEvent(executor_id=self.id, data=update))
executor = AuthorNameExecutor(id="executor_id")
workflow = WorkflowBuilder().set_start_executor(executor).build()
agent = WorkflowAgent(workflow=workflow, name="Test Agent")
# Collect streaming updates
updates: list[AgentRunResponseUpdate] = []
async for update in agent.run_stream("Hello"):
updates.append(update)
# Verify author_name is preserved (not overwritten with executor_id)
assert len(updates) >= 1
assert updates[0].author_name == "custom_author_name"
async def test_multiple_executors_have_distinct_author_names(self):
"""Test that multiple executors in a workflow have their own author_name."""
# Create workflow with two executors
executor1 = SimpleExecutor(id="first_executor", response_text="First", emit_streaming=False)
executor2 = SimpleExecutor(id="second_executor", response_text="Second", emit_streaming=False)
workflow = WorkflowBuilder().set_start_executor(executor1).add_edge(executor1, executor2).build()
agent = WorkflowAgent(workflow=workflow, name="Multi-Executor Agent")
# Collect streaming updates
updates: list[AgentRunResponseUpdate] = []
async for update in agent.run_stream("Hello"):
updates.append(update)
# Should have updates from both executors
assert len(updates) >= 2
# Verify each update has the correct author_name matching its executor
author_names = [u.author_name for u in updates]
assert "first_executor" in author_names
assert "second_executor" in author_names
class TestWorkflowAgentMergeUpdates:
"""Test cases specifically for the WorkflowAgent.merge_updates static method."""