Compare commits

...
Author SHA1 Message Date
copilot-swe-agent[bot]androgerbarreto b57c9f175b fix: update PyRIT repository link from Azure/PyRIT to microsoft/PyRIT
Agent-Logs-Url: https://github.com/microsoft/agent-framework/sessions/830b8ccf-a79c-49b6-90c9-3bb3e740bc06

Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com>
2026-03-28 15:43:29 +00:00
copilot-swe-agent[bot] a503a2a8a6 Initial plan 2026-03-28 15:42:25 +00:00
b1b528e4a8 Python: [BREAKING] Remove deprecated kwargs compatibility paths (#4858)
* [BREAKING] Remove deprecated kwargs compatibility paths

Remove the deprecated kwargs compatibility shims across core agents, clients, tools, middleware, and telemetry.

Keep workflow kwargs behavior intact in this branch and follow up separately in #4850.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix PR CI fallout for kwargs removal

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Address PR review feedback

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* updates

* Fix Azure AI CI fallout

Remove the stale _get_current_conversation_id override from the Azure AI client after the OpenAI base helper was deleted.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* fixed new classes

* Fix Assistants deprecated import gating

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix integration replay regressions

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Switch multi-agent hosting samples to Azure chat completions

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Simplify Azure multi-agent sample config

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-27 21:00:12 +00:00
westeyandGitHub ca6cdd142e .NET: Fixes for durable agents integration tests (#4952)
* Fixing for durable agents integration tests

* Add further fixes
2026-03-27 17:38:23 +00:00
6b47cdbf52 Python: Fix broken samples for GitHub Copilot, declarative, and Responses API (#4915)
* Python: Fix broken samples for GitHub Copilot, declarative, and Responses API

- Add missing on_permission_request handler to github_copilot_basic and
  github_copilot_with_session samples (required by copilot SDK)
- Increase timeout for remote MCP query in github_copilot_with_mcp sample
- Soften session isolation claim in github_copilot_with_session sample
- Fix inline_yaml sample: pass project_endpoint via client_kwargs instead
  of relying on YAML connection block (AzureAIClient expects
  project_endpoint, not endpoint)
- Handle raw JSON schemas in Responses client _convert_response_format
  so declarative outputSchema works with the Responses API

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Improve raw JSON schema detection heuristic and add tests

- Broaden raw schema detection to handle anyOf, oneOf, allOf, $ref, $defs
  keywords and JSON Schema primitive types, not just 'properties'
- Apply same raw schema handling to azure-ai _shared.py for consistency
- Add unit tests for both openai and azure-ai response_format conversion

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-27 16:27:19 +00:00
cc0cfaaac8 [BREAKING] Python: fix OpenAI Azure routing and provider samples (#4925)
* Python: fix OpenAI Azure routing and provider samples

Prefer OpenAI when OPENAI_API_KEY is present unless Azure is explicitly requested. Clarify constructor docs, keep deprecated Azure wrappers compatible with stricter settings validation, and refresh the provider samples and tests to use the current client patterns.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* fix bandit

* Python: align OpenAI embedding Azure routing

Extend the shared OpenAI-vs-Azure routing and credential behavior to the embedding client, add Azure embedding regression coverage, and refresh the embedding samples to use the generic client path.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Python: fix embedding client pyright check

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Python: thin OpenAI embedding wrapper

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Python: document embedding overload routing

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Python: fix callable OpenAI key routing

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Python: fix Azure credential routing tests

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Python: address OpenAI review feedback

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Python: narrow Azure routing markers

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Python: refine OpenAI model fallback order

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Python: narrow Azure deployment docs

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Python: remove embedding routing wording

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Python: run embedding Azure integration tests

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* changed variable name

* Python: expand OpenAI package README

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* clarified readme

* Python: fix Azure OpenAI integration setup

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Python: correct Azure integration env mapping

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* updated code to fix int tests

* test updates

* test fix

* fix test setup

* updates to tests and setup

* remove openai assistants int tests

* improvements in int tests

* fix env var

* fix env vars

* fix azure responses test

* trigger actions

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-27 13:33:39 +00:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
3611be82cf Bump flatted from 3.3.3 to 3.4.2 in /python/packages/devui/frontend (#4805)
Bumps [flatted](https://github.com/WebReflection/flatted) from 3.3.3 to 3.4.2.
- [Commits](https://github.com/WebReflection/flatted/compare/v3.3.3...v3.4.2)

---
updated-dependencies:
- dependency-name: flatted
  dependency-version: 3.4.2
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-03-27 03:43:25 +00:00
SergeyMenshykhandGitHub 0fcbe7e105 .NET: [Breaking] Restructure agent skills to use multi-source architecture (#4871)
* initial commit

* address comments

* address comments

* address comments

* address  comments

* rename executor to runner to align naming with python implementation

* rename runner execute method to run method

* remove poc leftovers and fix compilation issues

* make script runner optional

* remove unnecessary pragmas

* make resources and scripts props virtual

* address comments

* update comment for name validation regex

* address comments
2026-03-26 22:27:17 +00:00
Jacob AlberandGitHub 5530bc536b .NET: feat: Implement return-to-previous routing in handoff workflow (#4356)
* feat: Implement return-to-previous routing in handoff workflow

- Also obsoletes HandoffsWorkflowBuilder => HandoffWorkflowBuilder (no "s")

* refactor: Remove instance-shared current agent tracking in handoffs

Because the tracker was instance-shared between the start and end executors, it would be shared between all sessions, resulting in incorrect behaviour.

The corect way to do this is to keep the data in a shared executor scope, which is per-session.

* fix: Fix test logic for Handoff to correctly use checkpointing for multiturn
2026-03-26 20:17:57 +00:00
9bfa593ae7 Python: Move ag_ui_workflow_handoff demo from demos/ to 05-end-to-end/ (#4900)
* Move ag_ui_workflow_handoff demo to 05-end-to-end (#4895)

Move the AG-UI workflow handoff demo from python/samples/demos/ to
python/samples/05-end-to-end/ to follow the current folder structure
convention. Update README paths accordingly.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix review feedback: remove build artifacts, fix README paths (#4895)

- Add .gitignore to frontend/ to exclude *.tsbuildinfo, vite.config.js,
  and vite.config.d.ts build artifacts from version control
- Remove the 4 tracked build artifact files from the tree
- Fix step 2 cd path in README to be relative after 'cd python'

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Clarify working directory context in README Step 2 (#4895)

Step 2 uses a python/-relative path (samples/...) which assumes the
user is still in the python/ directory from Step 1. Add a brief note
making this explicit.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-26 17:52:07 +00:00
3585581c7a .NET: Fix bug with per-service-call persistence and approvals (#4933)
* Fix bug with per-service-call persistence and approvals

* 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>
2026-03-26 17:45:46 +00:00
63dee91a5f .NET: Improve observability sample (#4917)
* Improve .Net observability sample

* Update dotnet/samples/02-agents/AgentOpenTelemetry/Program.cs

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-03-26 17:33:22 +00:00
westeyandGitHub 3b8b56e6ea Samples fix (#4932) 2026-03-26 16:45:01 +00:00
9691c9c271 .NET: Fix role assignment in ChatMessage construction (#4290)
* Use actual message role when creating ChatMessage

Replace hard-coded ChatRole.User with a ChatRole constructed from the message's Role. The change ensures ToChatMessage and FunctionMessage use the original role (new ChatRole(this.Role)) for both text and contents branches, fixing incorrect role assignment when constructing ChatMessage instances.

* Update changes

* Fix formatting in ToChatMessage tests

---------

Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com>
2026-03-26 16:13:00 +00:00
d2977d63da .NET: Add integration test validating OpenAPI tools with AsAIAgent(agentVersion) (#4931)
* .NET: Add integration test for OpenAPI tools with AsAIAgent(agentVersion)

Validates end-to-end flow creating a Foundry agent with an OpenAPI tool
definition via native Azure.AI.Projects SDK types and wrapping it with
AsAIAgent(agentVersion). The test confirms the server-side OpenAPI
function is invoked correctly through RunAsync.

Addresses #4883

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Address PR review: RetryFact, PascalCase naming, stronger tool assertion

- Use RetryFact with Skip for manual testing (flaky due to external API)
- Fix agentName -> AgentName to match PascalCase convention in file
- Strengthen tool invocation assertion: require >= 3 Eurozone countries
- Add comment explaining server-side OpenAPI tools don't surface as
  FunctionCallContent in the MEAI abstraction

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-26 15:35:16 +00:00
84fe6c46ab .NET: Add AsIChatClientWithStoredOutputDisabled for ProjectResponsesClient (#4911)
* Add AsIChatClientWithStoredOutputDisabled for ProjectResponsesClient

Add extension method on ProjectResponsesClient in Microsoft.Agents.AI.AzureAI
package (Azure.AI.Extensions.OpenAI namespace) mirroring the existing extension
on ResponsesClient in the OpenAI package. This enables Azure AI consumers to
disable server-side response storage without depending on the OpenAI package.

- New ProjectResponsesClientExtensions class with AsIChatClientWithStoredOutputDisabled
- Optional deploymentName parameter (model is no longer required)
- Updated OpenAI counterpart doc to remove 'Required' wording for model param
- Added unit tests covering null guard, inner client accessibility,
  StoredOutputEnabled=false, and reasoning encrypted content inclusion/exclusion

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Preserve existing RawRepresentationFactory when disabling stored output

Address PR review feedback: wrap/chain the existing factory instead of
replacing it, so upstream configuration (e.g., deploymentName/model defaults
from AsIChatClient) is preserved.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-26 11:19:32 +00:00
SergeyMenshykhandGitHub 6626565f7a ADR to support a multi-source architecture for agent skills (#4787)
* add  adr suggesting a new design to support a multi-source architecture for agent skills

* add deciders

* move the adr to the decisions folder

* remove unnecessary section

* describe adding a custom skill source

* update

* address comments

* add constructor overloads to inline skill resource and script

* consider ai-function as an alternative for skill script and skill resource model classes

* update decision outcome section and sync adr with latest changes in the code
2026-03-26 11:19:09 +00:00
westeyandGitHub bfda595e56 Add ADR to decide consistency of Chat History Persistence (#4816)
* Add ADR to decide consitency of Chat History Persistence

* Add example

* Update ADR with review results

* Remove unecessary clarification

* Rename ADR to no 22
2026-03-26 11:10:33 +00:00
efb14cedb1 Python: Support structuredContent in MCP tool results and fix sampling options type (#4763)
* Support MCP sampling tools capability (#4625)

Forward systemPrompt, tools, and toolChoice from MCP sampling requests
to the chat client's get_response() call. Also advertise the
sampling.tools capability to MCP servers when a client is configured.

- Pass SamplingCapability with tools support to ClientSession
- Convert systemPrompt to instructions in options
- Convert MCP Tool objects to FunctionTool instances for options
- Map MCP ToolChoice.mode to tool_choice in options
- Add tests for all new behaviors and update existing sampling tests

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix #4625: Support MCP sampling tool with proper typing and structured content

- Fix mypy error by typing sampling callback options as ChatOptions[None]
  instead of dict[str, Any], and importing ChatOptions from _types
- Handle structuredContent from CallToolResult in _parse_tool_result_from_mcp,
  serializing it as JSON text Content when present
- Add tests for structuredContent parsing (with and without regular content)

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix lint: add author to TODO comment

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Address review feedback for #4625: remove default=str, add edge-case tests

- Remove default=str from json.dumps for structuredContent to fail fast
  on non-JSON-serializable values instead of silently converting
- Add test for non-JSON-serializable structuredContent (TypeError)
- Add tests for empty systemPrompt ('') and empty tools list ([]) edge
  cases in sampling callback
- Expand TODO comment noting list[Content] return type constraint for
  future result_type support

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Sanitize sampling callback error to avoid leaking internals (#4625)

Log exception details at DEBUG level instead of including them in the
ErrorData message returned to the MCP server, which may be untrusted.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Address review feedback for #4625: move params to options, restore error info

- Remove stale TODO comment about response_format (ChatOptions already has it)
- Restore {ex} in sampling callback error message for useful debugging info
- Set structuredContent as additional_property on Content for structured access
- Move temperature, max_tokens, stop into options dict (not top-level kwargs)
- Only set temperature when provided (not all models support it)
- Add tests for generation params in options and temperature omission

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix MCP sampling callback and structured content error handling (#4625)

- Guard max_tokens like temperature: only set when not None, so options
  can properly evaluate to None when all params are absent
- Wrap json.dumps of structuredContent in try/except to fall back to
  str() for non-serializable values instead of propagating TypeError
- Extract test_connect_sampling_capabilities_with_client into its own
  test function so pytest can discover it independently
- Add test for max_tokens=None omission from options
- Update structured content non-serializable test to expect fallback

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Address review feedback for #4625: review comment fixes

* Fix MCP and Azure validation regressions

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-26 07:33:19 +00:00
dd3d085539 Python: Include reasoning messages in MESSAGES_SNAPSHOT events (#4844)
* Include reasoning messages in MESSAGES_SNAPSHOT (#4843)

FlowState now tracks reasoning messages emitted during a run.
_emit_text_reasoning() persists reasoning (including encrypted_value)
into flow.reasoning_messages, and _build_messages_snapshot() appends
them to the final MESSAGES_SNAPSHOT event.

Changes:
- Add reasoning_messages field to FlowState
- Update _emit_text_reasoning() to accept optional flow parameter
- Include reasoning_messages in _build_messages_snapshot()
- Add 'reasoning' to ALLOWED_AGUI_ROLES so normalize_agui_role()
  preserves the role through snapshot round-trips
- Skip reasoning messages in agui_messages_to_agent_framework() since
  they are UI-only state and should not be forwarded to LLM providers
- Add regression tests for snapshot emission, encrypted value
  preservation, and multi-turn round-trip with reasoning

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Python: Include reasoning messages in MESSAGES_SNAPSHOT events

Fixes #4843

* Fix PR review feedback for reasoning persistence (#4843)

- Accumulate reasoning text per message_id (append deltas) instead of
  storing only the current chunk, matching flow.accumulated_text pattern
- Use camelCase encryptedValue in snapshot JSON to match AG-UI protocol
  conventions (toolCallId, encryptedValue)
- Normalize snake_case encrypted_value to encryptedValue in
  agui_messages_to_snapshot_format for input compatibility
- Update normalize_agui_role docstring to include reasoning role
- Add tests for incremental reasoning accumulation and key normalization

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Address review feedback for #4843: Python: agent-framework-ag-ui: include reasoning messages in MESSAGES_SNAPSHOT

---------

Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-26 05:56:10 +00:00
dc27740f1a Python: Fix streaming path to emit mcp_server_tool_result on output_item.done instead of output_item.added (#4821)
* Fix streaming path to deliver mcp_server_tool_result content (#4814)

Remove premature mcp_server_tool_result emission from the
response.output_item.added/mcp_call handler — at that point the MCP
server has not yet responded and output is always None.

Add a handler for response.mcp_call.completed that emits
mcp_server_tool_result with the actual tool output, matching the
non-streaming path behavior.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix streaming path to deliver mcp_server_tool_result content (#4814)

Stop eagerly emitting mcp_server_tool_result on response.output_item.added
(when output is always None). Instead, handle response.output_item.done for
mcp_call items, which carries the full McpCall with populated output.

This matches the non-streaming path which guards with 'if item.output is not
None' before emitting the result.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix test docstring to match actual implementation event name

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Address review: call_id fallback and raw_representation consistency (#4814)

- Add call_id fallback in response.output_item.done mcp_call handler to
  match the output_item.added handler pattern
- Use done_item instead of event for raw_representation to keep
  consistent with other output_item branches and non-streaming path
- Add test for call_id fallback when id attribute is missing
- Add raw_representation assertions to existing done handler tests

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Address review: call_id fallback for non-streaming path and test coverage (#4814)

- Apply defensive call_id fallback (getattr with id/call_id/empty) to
  non-streaming mcp_call path for consistency with streaming path
- Add raw_representation assertion to call_id fallback test
- Add test for empty-string fallback when neither id nor call_id exist

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-26 02:09:22 +00:00
c1435ac201 Python: Fix A2AAgent to surface message content from in-progress TaskStatusUpdateEvents (#4798)
* Fix A2AAgent dropping message content from in-progress TaskStatusUpdateEvents (#4783)

_updates_from_task() returned [] for working-state tasks when
background=False, silently discarding all intermediate message content
from task.status.message. Now extracts and yields message parts from
in-progress status updates during streaming.

Also fixed MockA2AClient.send_message to yield all queued responses
(enabling multi-event streaming tests) and added text parameter to
add_in_progress_task_response for tests that need status messages.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix: gate intermediate status updates behind emit_intermediate flag and add missing test coverage

- Add emit_intermediate parameter to _updates_from_task and _map_a2a_stream
- Thread stream flag from run() so only streaming callers see intermediate updates
- Add IN_PROGRESS_TASK_STATES guard to emit_intermediate condition
- Add role parameter to test helper add_in_progress_task_response
- Add clarifying comment on MockA2AClient.send_message batch semantics
- Add tests for user role mapping, background precedence, non-streaming behavior,
  terminal task with no artifacts, and empty parts edge case

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-26 02:08:47 +00:00
Jacob AlberandGitHub 0bdcaa5c07 fix: Re-enable the "retrieve object" check in StateManager (#1881) 2026-03-25 22:53:44 +00:00
Jacob AlberandGitHub 35f44e854e .NET: fix: HandoffAgentExecutor does not output any response when non-streaming (#4745)
* fix: HandoffAgentExecutor does not output any reponse when non-streaming

* fix: Ensure Workflow outputs persisted in chat history when hosted AsAgent

* fix: Remove duplicate history entry creation and ad test

* test: Add streaming tests for AsAgent to smoke tests

* feat: Add output configurability to Handoffs
2026-03-25 22:22:13 +00:00
Jacob AlberandGitHub 0756c45702 .NET: [BREAKING] Update type names and source generator to reduce conflicts (#4903)
* refactor: [BREAKING] Config => ExecutorConfig

Make the Config name less likely to collide with other classes by renaming to ExecutorConfig. Makes Configured and related classes internal as they do not need to be part of the public surface.

* fix: Make RouteBuilder explicit in SourceGen to avoid conflicts
2026-03-25 20:35:17 +00:00
0b2ccd6126 .NET: Fix ChatOptions mutation in AIContextProviderChatClient across calls (#4891)
* Fix UseAIContextProviders tool accumulation across calls (#4864)

Clone ChatOptions before mutating it in InvokeProvidersAsync to prevent
context provider tools from accumulating when the same ChatOptions
instance is reused across multiple API calls.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Apply suggestions from code review

Co-authored-by: chetantoshniwal <chetantoshniwal@gmail.com>

* Apply suggestion from @westey-m

---------

Co-authored-by: MAF Dashboard Bot <maf-dashboard-bot@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: westey <164392973+westey-m@users.noreply.github.com>
2026-03-25 20:02:16 +00:00
Peter IbekweandGitHub 23921c0f6e .NET: Pass through external input request and handle response conversion for workflow as agent scenario (#4361)
* Handle external input request and response conversion for workflow as agent scenario

* Remove unnecessary test comment

* Fix PR comments

* Updated to fix edge cases, and add more tests.

* Update pending requests to use typed properties instead of relying on StateBag. replying to PR feedback.

* Fixed external response de-dup and updated possible brittle test.

* Address PR comments on sending turn token for normal messages and handle contentId collision by source agent

* Remove unnecessary serialization element and address pr comment on intercepted outgoing requests

* Updated MEAI changes for UserInput request and response abstractions.
2026-03-25 19:23:44 +00:00
db16a9e74c .NET: Clarify IResettableExecutor usage comment in workflow sample (#4905)
* Clarify IResettableExecutor usage comment in workflow sample

* Update dotnet/samples/03-workflows/Agents/WorkflowAsAnAgent/WorkflowFactory.cs

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update dotnet/samples/03-workflows/Agents/WorkflowAsAnAgent/WorkflowFactory.cs

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-03-25 18:50:29 +00:00
Eduard van ValkenburgandGitHub c012aac5f2 Python: [BREAKING] Reduce core dependencies and simplify optional integrations (#4904)
* improved dependencies and some fixes

* fix for mypy

* improve mcp
2026-03-25 18:03:43 +00:00
Shyju KrishnankuttyandGitHub 49d69b3bf5 .NET: Expose workflows as MCP tools when hosting on Azure functions (#4768)
* Expose workflow as MCP Tool

* Expose workflow as MCP Tool

* Cleanup

* PR feedback fixes

* update changelog to include PR numner

* Improvements to error handling.

* Adding a sample project demonstrating how to setup Agents and Workflows together.

* Ensure duplicate agent registrations are properly handled.
2026-03-25 15:43:15 +00:00
Jacob AlberandGitHub a9db40886e fix: FS Checkpoint storage special character support (#4730)
The `sessionId`, an optional parameter when starting a new session when
running a workflow is an arbitrary string. This allows consumers to
support whatever ids are needed by other systems, but can result in
errors when an OS special or forbidden character is included.

The fix is to escape the paths, in a 1:1 manner. We rely on
EncodeDataString to do this.

* Also modifies the index file to make it easier to determine what the
  name of the file on disk is for a given `sessionId`.
2026-03-25 15:21:30 +00:00
westeyandGitHub 87962e53c5 .NET: Persist messages during function call loop (#4762)
* Persist messages during the Function Call Loop

* Revert version reset

* Fix bugs and improve sample

* Fix formatting issues

* Also updating conversation id during run

* Update based on ADR feedback
2026-03-25 11:53:45 +00:00
5e056b672e Python: [BREAKING] Python: Provider-leading client design & OpenAI package extraction (#4818)
* Python: Provider-leading client design & OpenAI package extraction

Major refactoring of the Python Agent Framework client architecture:

- Extract OpenAI clients into new `agent-framework-openai` package
- Core package no longer depends on openai, azure-identity, azure-ai-projects
- Rename clients for discoverability: OpenAIResponsesClient → OpenAIChatClient,
  OpenAIChatClient → OpenAIChatCompletionClient
- Unify `model_id`/`deployment_name`/`model_deployment_name` → `model` param
- New FoundryChatClient for Azure AI Foundry Responses API
- New FoundryAgent/FoundryAgentClient for connecting to pre-configured Foundry agents
- Remove OpenAIBase/OpenAIConfigMixin from non-deprecated client MRO
- Deprecate AzureOpenAI* clients, AzureAIClient, OpenAIAssistantsClient
- Reorganize samples: azure_openai+azure_ai+azure_ai_agent → azure/
- ADR-0020: Provider-Leading Client Design

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* fix: missing Agent imports in samples, .model_id → .model in foundry_local sample

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* fix: CI failures — mypy errors, coverage targets, sample imports

- azure-ai mypy: add type ignores for TypedDict total=, model arg, forward ref
- Coverage: replace core.azure/openai targets with openai package target
- project_provider: add type annotation for opts dict

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* fix: populate openai .pyi stub, fix broken README links, coverage targets

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* fixes

* updated observabilitty

* reset azure init.pyi

* fix errors

* updated adr number

* fix foundry local

* fixed not renamed docstrings and comments, and added deprecated markers to old classes

* fix tests and pyprojects

* fix test vars

* updated function tests

* update durable

* updated test setup for functions

* Fix Foundry auth in workflow samples

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Stabilize Python integration workflows

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Update hosting samples for Foundry

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Trigger full CI rerun

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Trigger CI rerun again

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* trigger rerun

* trigger rerun

* fix for litellm

* undo durabletask changes

* Move Foundry APIs into foundry namespace

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix Foundry pyproject formatting

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Split provider samples by Foundry surface

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Restore hosting sample requirements

Also fix the Foundry Local sample link after the provider sample move.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* updated tests

* udpated foundry integration tests

* removed dist from azurefunctions tests

* Use separate Foundry clients for concurrent agents

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* fix client setup in azfunc and durable

* disabled two tests

* updated setup for some function and durable tests

* improved azure openai setup with new clients

* ignore deprecated

* fixes

* skip 11

* remove openai assistants int tests

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-25 09:56:29 +00:00
Tao ChenandGitHub 4b533608b6 Python: Update sample validation scripts (#4870)
* Update sample validation scripts

* Adjust prompt

* Update autogen-migration samples

* Add fix suggestion

* Split jobs

* Add .env

* Create trend report

* Add timestamp

* Add more env vars

* Comments

* force node24

* force node24

* force node22
2026-03-25 01:21:32 +00:00
westeyandGitHub 2c000b032d .NET: Update AIContextProviders to use Microsoft.Extensions.Compliance.Redaction (#4854)
* Update providers to use Microsoft.Extensions.Compliance.Redaction

* Fix formatting.

* Fix readme
2026-03-24 18:12:55 +00:00
cc85bbc2dc .NET: Re-enable AzureAI.Persistent packaging and integration tests (#4769) (#4865)
Azure.AI.Agents.Persistent 1.2.0-beta.10 now targets ME.AI 10.4.0+,
resolving the compatibility issue that required disabling this package.

- Remove IsPackable=false from the csproj
- Re-enable all 6 integration test classes (IntegrationDisabled → Integration)
- Remove outdated compatibility warning from README.md

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-24 11:06:32 +00:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
01aaf2baea Bump actions/download-artifact from 7 to 8 (#4372)
Bumps [actions/download-artifact](https://github.com/actions/download-artifact) from 7 to 8.
- [Release notes](https://github.com/actions/download-artifact/releases)
- [Commits](https://github.com/actions/download-artifact/compare/v7...v8)

---
updated-dependencies:
- dependency-name: actions/download-artifact
  dependency-version: '8'
  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>
2026-03-23 21:55:19 +00:00
cb96347c95 Python: Fix PydanticSchemaGenerationError when using from __future__ import annotations with @tool (#4822)
* Fix PydanticSchemaGenerationError with PEP 563 annotations in @tool

_resolve_input_model used raw param.annotation from inspect.signature(),
which returns string annotations when 'from __future__ import annotations'
is active (PEP 563). This caused Pydantic's create_model to fail for
complex types like Optional[int] or FunctionInvocationContext.

Use typing.get_type_hints() to resolve annotations to actual types before
passing them to create_model, matching the approach already used by
_discover_injected_parameters.

Fixes #4809

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Apply pre-commit auto-fixes

* Remove reproduction report and unused test imports

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* fix(tests): strengthen PEP 563 regression tests per review feedback (#4809)

- Verify type correctness in schema assertions (not just key presence)
- Fix ctx annotation to FunctionInvocationContext | None for type consistency
- Add test for Optional[CustomType] pattern (original bug trigger)
- Add test for get_type_hints() fallback with unresolvable forward refs

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Apply pre-commit auto-fixes

* Address review feedback for #4809: Python: [Bug]: PydanticSchemaGenerationError in FunctionInvocationContext

---------

Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-23 21:47:12 +00:00
westeyandGitHub 5070c67d0e Mark constructors of InvokingContext and InvokedContext as experimental (#4851) 2026-03-23 19:06:07 +00:00
9a47620f64 .NET: Update Hosted Samples References to latest beta.11 (#4853)
* Bump HostedAgents samples to AgentFramework beta.11 and pass credential to UseFoundryTools

Update all 8 HostedAgents samples:
- Azure.AI.AgentServer.AgentFramework -> 1.0.0-beta.11
- Microsoft.Agents.AI.OpenAI -> 1.0.0-rc4
- Microsoft.Agents.AI/AzureAI/Workflows -> 1.0.0-rc4
- Azure.AI.Projects -> 2.0.0-beta.1
- Fix Workflow.AsAgent() -> AsAIAgent() in FoundryMultiAgent
- Pass credential to UseFoundryTools in AgentWithTools (resolves #56802)

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Remove AgentWithTools sample (UseFoundryTools no longer supported)

Remove the AgentWithTools hosted agent sample as the UseFoundryTools
backend is no longer supported. Updated HostedAgents README and solution
file to remove all references.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix AgentWithHostedMCP: downgrade Azure.AI.OpenAI to 2.8.0-beta.1 for rc4 compatibility

Azure.AI.OpenAI 2.9.0-beta.1 has breaking changes (GetResponsesClient no
longer accepts deployment name, ResponsesClient.Model removed) that are
incompatible with Microsoft.Agents.AI.OpenAI rc4. Pin to 2.8.0-beta.1 and
use GetResponsesClient(deploymentName).AsAIAgent() pattern.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-23 17:41:49 +00:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
e11633a2c8 Bump Azure.AI.Agents.Persistent from 1.2.0-beta.9 to 1.2.0-beta.10 (#4833)
---
updated-dependencies:
- dependency-name: Azure.AI.Agents.Persistent
  dependency-version: 1.2.0-beta.10
  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>
2026-03-23 15:26:40 +00:00
Peter IbekweandGitHub 7e6d87e7ec .NET: Fix broken workflow samples (#4800)
* Fix source generator bug that silently drops base class handler registrations for protocol-only partial executors

* Fixed xml comments and variable naming.

* Fix workflow samples broken due to routing change
2026-03-20 20:49:30 +00:00
9dfe7c40ca Add ADR-0020: Foundry Evals integration (#4731)
* Add ADR-0020: Foundry Evals integration design

Captures the design for integrating Azure AI Foundry Evaluations with
agent-framework. Key decisions:

- EvalItem with conversation (list[Message]) as single source of truth
- query/response derived from configurable conversation split strategies
- Tools as list[FunctionTool] (including auto-extracted MCP tools)
- FoundryEvals provider with auto-detection of evaluator capabilities
- LocalEvaluator with @function_evaluator decorator for local checks
- Consistent Python/C# APIs: evaluate_agent, evaluate_workflow

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Mark ADR 0020 Foundry Evals as accepted

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: alliscode <bentho@microsoft.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-20 20:20:59 +00:00
westeyandGitHub 6803058e36 .NET: Obsolete the V1 helper methods and migrate samples using it where possible (#4795)
* Obsolete the V1 helper methods and migrate samples using it where possible

* Address PR comments
2026-03-20 19:41:34 +00:00
westeyandGitHub 7645ec4e07 .NET: Improve visibility for AzureFunctions Workflows samples run tests in increase timeouts (#4820)
* Reduce timeout flakiness for AzureFunctions Workflows samples run tests

* Add more updates

* Address PR comments

* Address PR comments
2026-03-20 18:41:30 +00:00
Tao ChenandGitHub 51828abed4 [BREAKING] Python: Add context mode to AgentExecutor (#4668)
* Add context mode to AgentExecutor

* Fix unit tests

* Address comments

* Address comments

* REvise context mode and add tests

* Add chain config to sequential builder

* Add sample

* Fix pipeline

* Address comments

* Address comments
2026-03-20 18:27:02 +00:00
CopilotGitHubCopilotcopilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>stephentoubrogerbarreto
88ea9d08c7 .NET: Update to OpenAI 2.9.1, Azure.AI.OpenAI 2.9.0-beta.1, Microsoft.Extensions.AI 10.4.0, and Azure.AI.Projects 2.0.0-beta.2 (#4613)
* Initial plan

* Update code for Microsoft.Extensions.AI.Abstractions 10.4.0 breaking changes

- Rename FunctionApprovalRequestContent → ToolApprovalRequestContent
- Rename FunctionApprovalResponseContent → ToolApprovalResponseContent
- Rename UserInputRequestContent → ToolApprovalRequestContent
- Rename UserInputResponseContent → ToolApprovalResponseContent
- Update .FunctionCall property → .ToolCall with FunctionCallContent casts where needed
- Update .Id property → .RequestId on the renamed types
- Rename FunctionApprovalRequestEventGenerator → ToolApprovalRequestEventGenerator
- Rename FunctionApprovalResponseEventGenerator → ToolApprovalResponseEventGenerator

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Update OpenAI 2.9.1, ME.AI 10.4.0, fix breaking API changes

Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com>

* Fix remaining ME.AI 10.4.0 breaking changes: MCP approval types, .Output→.Outputs

Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com>

* Use pattern matching with `when` for ToolApprovalRequestContent/FunctionCallContent

Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com>

* Update Azure.AI.OpenAI to 2.9.0-beta.1

Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com>

* Fix remaining GetResponsesClient(model) build failures for Azure.AI.OpenAI 2.9.0-beta.1

Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com>

* Address review feedback: remove redundant type checks in TestRequestAgent.cs and fix error message in AIAgentHostExecutor.cs

Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com>

* Update Azure.AI.Projects to 2.0.0-beta.2 with namespace migration

- Azure.AI.Projects 2.0.0-beta.1 → 2.0.0-beta.2
- Azure.AI.Projects.OpenAI → Azure.AI.Extensions.OpenAI (transitive)
- Agent types moved to Azure.AI.Projects.Agents namespace
- AgentRecord.Versions.Latest → AgentRecord.GetLatestVersion()
- OpenAPIFunctionDefinition → OpenApiFunctionDefinition
- BingCustomSearchToolParameters → BingCustomSearchToolOptions
- MemorySearchPreviewTool.UpdateDelay → UpdateDelayInSecs
- Azure.Identity 1.17.1 → 1.19.0
- Microsoft.Identity.Client.Extensions.Msal 4.78.0 → 4.83.1

Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com>

* Fix remaining type renames for Azure.AI.Projects 2.0.0-beta.2

- BrowserAutomationToolParameters → BrowserAutomationToolOptions
- MemoryUpdateOptions.UpdateDelay stays as UpdateDelay (not renamed)
- WaitForMemoriesUpdateAsync parameter order: pollingInterval before options
- AIProjectAgentsOperations → AgentsClient

Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com>

* Fix format errors and OpenTelemetry test for ME.AI 10.4.0

- Remove unused 'using Azure.AI.Extensions.OpenAI' and fix import ordering
  in Agent_With_AzureAIProject/Program.cs
- Update OpenTelemetryAgentTests: gen_ai.tool.definitions is now always
  emitted regardless of EnableSensitiveData per ME.AI 10.4.0 change
  (dotnet/extensions#7346). Tool definitions are not considered sensitive.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix GetRepoFolder() to work in git worktrees

Use 'workflow-samples' directory as repo root marker instead of '.git',
which fails in worktrees (.git is a file) and also matches too early
when a '.github' folder exists in subdirectories.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix formatting: remove unused usings and fix import ordering

dotnet format applied across 59 impacted projects. Primarily removes
unnecessary 'using Azure.AI.Projects' where Azure.AI.Projects.Agents
provides all needed types, and fixes import ordering per editorconfig.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Disable AzureAIAgentsPersistent integration tests (#4769)

Azure.AI.Agents.Persistent 1.2.0-beta.9 references McpServerToolApprovalResponseContent
which was removed in ME.AI 10.4.0 (renamed to ToolApprovalResponseContent), causing
TypeLoadException at runtime. Mark all 6 test classes with IntegrationDisabled trait
until Persistent ships a version targeting ME.AI 10.4.0+.

Upstream fix: https://github.com/Azure/azure-sdk-for-net/pull/56929

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Add README with compatibility note for AzureAI.Persistent (#4769)

Documents that Azure.AI.Agents.Persistent 1.2.0-beta.9 is only compatible
with ME.AI ≤10.3.0 and OpenAI ≤2.8.0 due to type renames in ME.AI 10.4.0.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix file encoding: restore UTF-8 BOM on Persistent test files

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Mark AzureAI.Persistent as IsPackable=false (#4769)

Prevent shipping until Azure.AI.Agents.Persistent targets ME.AI 10.4.0+.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Moving IsPackable after import

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com>
Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com>
2026-03-20 14:29:29 +00:00
8edcb282f4 Update script to ping only on waiting-for-author label (#4812)
* update script to ping only on certain waiting for author label

* Update .github/scripts/stale_issue_pr_ping.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update .github/scripts/stale_issue_pr_ping.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Fix docstring

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-03-20 19:39:22 +09:00
81e2336d47 Python: avoid duplicate agent response telemetry (#4685)
* Python: avoid duplicate agent response telemetry

* Python: conditionally suppress duplicate agent telemetry

* Simplify telemetry ownership tracking

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Aggregate token usage from inner chat spans on invoke_agent span

The invoke_agent span now carries the aggregated input/output token
counts from all inner chat completion spans that occur during an agent
run. Previously, when inner ChatTelemetryLayer spans captured usage,
the outer AgentTelemetryLayer skipped setting usage entirely to avoid
duplication. Now a new INNER_ACCUMULATED_USAGE context variable tracks
cumulative usage across all inner completions, and the agent span
always reports the total.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-20 10:09:46 +00:00
8fc19a3437 Python: Deprecate Azure AI v1 (Persistent Agents API) helper methods (#4804)
* Deprecate Azure AI v1 (Persistent Agents API) helper methods

Add DeprecationWarning to v1 classes and functions that have been
superseded by the v2 (Projects/Responses) API:

- AzureAIAgentsProvider -> use AzureAIProjectAgentProvider
- AzureAIAgentClient -> use AzureAIClient
- AzureAIAgentOptions -> use AzureAIProjectAgentOptions
- to_azure_ai_agent_tools() -> use to_azure_ai_tools()
- from_azure_ai_agent_tools() -> use from_azure_ai_tools()
- AzureAIAgentClient static tool factory methods -> use AzureAIClient equivalents

All v1 components still function but emit warnings to guide migration.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Add deprecation warnings to AzureAIAgentsProvider methods

Mark create_agent(), get_agent(), and as_agent() as deprecated
individually, pointing to AzureAIProjectAgentProvider equivalents.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-20 08:53:36 +00:00
Evan MattsonandGitHub 26cd5cc1bf Python: Bump Python version to 1.0.0rc5 and 1.0.0b260319 for a release. (#4807)
* Bump Python version to 1.0.0rc5 and 1.0.0b260319 for a release.

* update missed pkg versions

* Update changelog
2026-03-20 10:35:47 +09:00
James SturtevantandGitHub b4c4f5094e Python: Emit tool call events in GitHubCopilotAgent streaming (#4711)
* Emit tool call events in GitHubCopilotAgent streaming

_stream_updates now yields FunctionCallContent for TOOL_EXECUTION_START
and FunctionResultContent for TOOL_EXECUTION_COMPLETE events from the
Copilot SDK session. This enables DevUI and other consumers to display
tool calls during streaming agent execution. Previously only ASSISTANT_MESSAGE_DELTA, SESSION_IDLE, and SESSION_ERROR
were handled — tool execution events were silently dropped.

Signed-off-by: James Sturtevant <jsturtevant@gmail.com>

* Add some tests

Signed-off-by: James Sturtevant <jsturtevant@gmail.com>

* Respond to feedback

Signed-off-by: James Sturtevant <jsturtevant@gmail.com>

* Fix TOOL_EXECUTION_COMPLETE to use correct SDK types

- Read result text from session_events.Result.content (not ToolResult.text_result_for_llm)
- Read failure state from event.data.success/error (not result_obj.result_type/error)
- Handle ErrorClass.message and plain string errors
- Update tests to use session_events.Result and ErrorClass
- Add tests for string errors, success-with-error, and COMPLETE missing fields

Signed-off-by: James Sturtevant <jsturtevant@gmail.com>

---------

Signed-off-by: James Sturtevant <jsturtevant@gmail.com>
2026-03-20 01:27:36 +00:00
0cd40f8354 Python: [BREAKING] Refactor middleware layering and split Anthropic raw client (#4746)
* [BREAKING] Refactor middleware layering and raw clients

Reorder chat client layers so function invocation wraps chat middleware, and chat middleware stays outside telemetry while still running for each inner model call. Add middleware pipeline caching, refresh docs and samples, and split Anthropic into raw and public clients to match the standard layering model.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Tighten typing ignores in ancillary modules

Add targeted typing ignores in workflow visualization and lab modules so pyright stays clean alongside the middleware refactor work.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix categorize_middleware to unpack tuple/Sequence and use relative MRO assertions

- Broaden isinstance check in categorize_middleware from list to Sequence
  so tuples and other Sequence types are properly unpacked instead of
  being appended as a single item.
- Replace fragile hardcoded MRO index assertions in anthropic test with
  relative ordering via mro.index().
- Add regression tests for categorize_middleware with tuple, list, and
  None inputs.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix middleware string decomposition, add middleware param to FunctionInvocationLayer, and add tests (#4710)

- Guard categorize_middleware Sequence check against str/bytes to prevent
  character-by-character decomposition of accidentally passed strings
- Add explicit middleware parameter to FunctionInvocationLayer.get_response
  and merge it into client_kwargs before categorization, fixing the
  inconsistency where only OpenAIChatClient supported this parameter
- Add assertions that RawAnthropicClient does not inherit convenience layers
- Add chat middleware cache test with non-empty base middleware
- Add tests for single unwrapped middleware item and string input

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Apply pre-commit auto-fixes

* Apply pre-commit auto-fixes

* Address review feedback for #4710: review comment fixes

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <copilot@github.com>
2026-03-20 00:43:37 +00:00
cefda44283 Python: Emit TOOL_CALL_RESULT events when resuming after tool approval (#4758)
* Emit TOOL_CALL_RESULT events on approval resume (#4589)

When a tool call is approved via the interrupt/resume flow,
_resolve_approval_responses executes the tool and injects the result
into the messages array, but no TOOL_CALL_RESULT SSE event was yielded
to the client.

Changes:
- _resolve_approval_responses now returns the list of resolved
  function_result Content objects instead of None
- run_agent_stream yields ToolCallResultEvent for each resolved
  approval result after RunStartedEvent is emitted
- Add ToolCallResultEvent to ag_ui.core imports in _agent_run.py

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Apply pre-commit auto-fixes

* fix(ag-ui): address PR review feedback for #4589

1. _resolve_approval_responses now returns only approved results (not
   rejections) so TOOL_CALL_RESULT events are emitted only for executed
   tools. Rejection results are still written into message history.

2. Emit resolved TOOL_CALL_RESULT events in the no-updates fallback
   RUN_STARTED path so approval results are never lost.

3. Rewrite tests to use real FunctionTool with func and
   approval_mode='always_require' via StubAgent default_options,
   verifying actual tool execution output in TOOL_CALL_RESULT content.
   Added test for rejection not emitting TOOL_CALL_RESULT.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix #4589: clean up approval resolution and add missing tests

- Extract duplicated TOOL_CALL_RESULT emission block into
  _make_approval_tool_result_events helper to prevent drift
- Remove dead rejection_results construction in _resolve_approval_responses;
  _replace_approval_contents_with_results already handles rejections inline
- Pass only approved_results (not all_results) to clarify the contract
- Add mixed approve/reject test validating the core splitting logic
- Add zero-updates test covering the no-updates fallback emission path
- Add direct unit test for _resolve_approval_responses return value

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Apply pre-commit auto-fixes

* Fix import sorting lint error in test_approval_result_event.py

Add blank line between first-party and third-party import groups
to satisfy ruff I001 rule.

Fixes #4589

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-20 00:41:46 +00:00
4afc088f01 Python: Emit AG-UI events for MCP tool calls, results, and text reasoning (#4760)
* Python: Emit AG-UI events for MCP tool calls, results, and text reasoning

Fixes #4213 — `_emit_content()` in the AG-UI layer only handled `text`,
`function_call`, `function_result`, `function_approval_request`, `usage`,
and `oauth_consent_request` content types. Foundry MCP content types
(`mcp_server_tool_call`, `mcp_server_tool_result`) and `text_reasoning`
fell through unhandled, producing no SSE events for AG-UI consumers.

Added three new handler functions wired into `_emit_content()`:

- `_emit_mcp_tool_call`: emits TOOL_CALL_START + TOOL_CALL_ARGS and
  tracks in FlowState for MESSAGES_SNAPSHOT inclusion
- `_emit_mcp_tool_result`: emits TOOL_CALL_END + TOOL_CALL_RESULT with
  full FlowState cleanup mirroring `_emit_tool_result`
- `_emit_text_reasoning`: emits the protocol-defined reasoning event
  sequence (ReasoningStart → MessageStart → MessageContent → MessageEnd
  → ReasoningEnd) with ReasoningEncryptedValueEvent for protected_data

* Add HTTP round-trip tests for MCP tool and reasoning SSE events

Exercises the full POST → SSE bytes → parse → validate pipeline for
mcp_server_tool_call, mcp_server_tool_result, text_reasoning, and
ReasoningEncryptedValueEvent content through FastAPI TestClient.

* Fix _emit_mcp_tool_result missing predictive_handler support (#4213)

- Add predictive_handler parameter to _emit_mcp_tool_result and mirror
  the apply_pending_updates + StateSnapshotEvent block from _emit_tool_result
- Forward predictive_handler from _emit_content to _emit_mcp_tool_result
- Add assertion for stored arguments in MCP tool call test
- Add test for predictive handler state snapshot after MCP tool result

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Apply pre-commit auto-fixes

* Refactor MCP tool emit functions and add missing tests (#4213)

- Extract _emit_tool_result_common shared helper to eliminate duplication
  between _emit_tool_result and _emit_mcp_tool_result
- Remove server_name prefix from tool_call_name in _emit_mcp_tool_call;
  display_name now equals tool_name directly
- Add test for tool_name fallback to 'mcp_tool' when tool_name is None
- Add test for output=None fallback to empty string in _emit_mcp_tool_result

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Address review feedback for #4213: review comment fixes

---------

Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-20 00:41:37 +00:00
1272ec5adf Add automated stale issue and PR follow-up ping workflow (#4776)
* Add script to ping on stale issues/PRs

* Add script to ping on stale issues/PRs

* Fix stale issue/PR ping script review comments

- Rename TEAM_NAME env var to TEAM_SLUG for clarity
- Add actionable error messages for 403/404 team lookup failures
- Add contents:read permission for actions/checkout
- Use github.event.inputs context with fallback for scheduled runs
- Pin PyGithub to 2.6.0 for reproducible builds
- Fetch comments once in should_ping() to reduce API calls
- Make ping() retry loop idempotent (track comment/label state)
- Validate DAYS_THRESHOLD with helpful error for non-numeric input
- Fix timezone bug: use astimezone() instead of replace(tzinfo=)
- Add comprehensive unit tests (29 tests)

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-20 00:41:31 +00:00
47ead84753 Python: Support detail field in OpenAI Chat API image_url payload (#4756)
* Support detail field in OpenAI image_url payload (#4616)

Include the optional 'detail' field from Content.additional_properties
when building image_url payloads for the OpenAI Chat API, matching the
existing pattern used for 'filename' in document file payloads.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Apply pre-commit auto-fixes

* Remove reproduction report

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Simplify detail extraction from additional_properties (#4616)

- Remove unnecessary hasattr check; additional_properties is always
  initialized as a dict on Content instances.
- Use 'is not None' instead of truthy check to be more precise.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Apply pre-commit auto-fixes

* Remove detail allowlist in chat client to align with responses client

Replace the strict allowlist check ('low', 'high', 'auto') with an
isinstance(detail, str) check so that any valid string detail value is
passed through to OpenAI. This aligns the chat client behavior with the
responses client, which passes detail through unconditionally.

Also add test coverage for:
- Future/unknown string detail values being passed through
- Data URI images (covering the 'data' branch of the match)

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-20 00:33:57 +00:00
4c287c2424 Python: Fix MCP tool schema normalization for zero-argument tools missing 'properties' key (#4771)
* Fix zero-argument MCP tool schema missing 'properties' key (#4540)

MCP servers for zero-argument tools (e.g. matlab-mcp-core-server's
detect_matlab_toolboxes) declare inputSchema as {"type": "object"}
without a "properties" key. OpenAI's API requires "properties" to
be present on object schemas, causing a 400 invalid_request_error.

Normalize inputSchema at MCP ingestion in load_tools() to inject an
empty "properties": {} when it is missing from object-type schemas.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Address review feedback for #4540: improve test robustness and add defensive guard

- Look up loaded functions by name instead of index to avoid brittle
  ordering assumptions
- Add negative-path test cases: non-object schema (type: string) and
  empty schema ({}) to verify guard clause skips them correctly
- Assert original inputSchema dicts are not mutated by load_tools()
- Add defensive guard for tool.inputSchema being None

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Address review feedback for #4540: Python: [Bug]: Local stdio MCP works for calculator but fails for official matlab-mcp-core-server on LM Studio /v1/responses

---------

Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-19 22:13:37 +00:00
westeyandGitHub 100086a276 Add docker-in-docker feature to dev container (#4794) 2026-03-19 19:18:46 +00:00
fc6721ca8e .NET: Trim src references and add utility to enforce (#4693)
* Trim src references and add utility to enforce

* Potential fix for pull request finding

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
2026-03-19 10:57:43 +00:00
4b21f38650 Python: Fix A2AAgent to invoke context providers before and after run (#4757)
* Fix A2AAgent to invoke context providers before and after run

A2AAgent.run() bypassed the context provider lifecycle (before_run/after_run)
that BaseAgent defines as a contract for all agents. This caused A2AAgent to
violate the semantic definition of BaseAgent, resulting in inconsistency with
other agent implementations.

The fix follows the same pattern used by WorkflowAgent:
- Create SessionContext and run before_run on all context providers before
  processing the A2A stream
- Collect response updates and run after_run on all context providers after
  the stream is fully consumed
- Auto-create a session when context providers are configured but no session
  is explicitly passed

Fixes #4754

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Apply pre-commit auto-fixes

* Remove reproduction report from repository

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Address PR review feedback for #4754

- Validate messages when no continuation_token: raise ValueError if
  normalized_messages is empty, preventing IndexError on messages[-1]
- Import BaseContextProvider/SessionContext from public agent_framework
  package instead of internal agent_framework._sessions module
- Add test for ValueError on run(None) without continuation_token

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Improve test coverage for empty-messages guard in A2AAgent.run (#4754)

- Parameterize test to cover both messages=None and messages=[] inputs
- Add test verifying run(None, continuation_token=...) does not raise

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-19 10:45:42 +00:00
bf8d9672e1 Python: Aggregate token usage across tool-call loop iterations in invoke_agent span (#4739)
* Fix invoke_agent span to aggregate token usage across LLM calls (#4062)

The FunctionInvocationLayer._get_response() loop was overwriting the
response on each iteration, so usage_details only reflected the last
chat completion call. Now tracks aggregated_usage across all iterations
using add_usage_details() and sets it on the returned response.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Apply pre-commit auto-fixes

* Remove reproduction report artifact

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Apply pre-commit auto-fixes

* Apply pre-commit auto-fixes

---------

Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-19 06:41:33 +00:00
Peter IbekweandGitHub 5374dd47c5 .NET: Fix source generator bug that silently drops base class handler registrations for protocol-only partial executors (#4751)
* Fix source generator bug that silently drops base class handler registrations for protocol-only partial executors

* Fixed xml comments and variable naming.
2026-03-19 02:19:42 +00:00
29dfcbb584 .NET: Validate SkillsInstructionPrompt contains {0} placeholder in FileAgentSkillsProvider (#4642)
* Fix FileAgentSkillsProvider accepting SkillsInstructionPrompt without {0} placeholder (#4638)

BuildSkillsInstructionPrompt validated only format-string syntax via
string.Format(template, ""), which silently accepted templates without a
{0} placeholder. The generated skills list was then dropped from the final
instructions.

Tighten validation to format with a sentinel string and verify it appears
in the output, rejecting templates that do not reference argument 0 with
an ArgumentException.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix netstandard2.0 compat and simplify prompt template validation (#4638)

- Replace string.Contains(string, StringComparison) with IndexOf for
  netstandard2.0/net472 compatibility
- Remove sentinel round-trip check; validate {0} directly on the raw
  template string using IndexOf
- Add positive test verifying custom SkillsInstructionPrompt with {0}
  is accepted and applied to output

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-19 00:18:39 +00:00
CopilotGitHubcrickmanCopilot Autofix powered by AIcopilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>Chris Rickman
c9321b9028 .NET Compaction - Allow developer to specify a custom formatter for ToolResultCompactionStrategy (#4667)
* Initial plan

* Allow developer to specify custom formatter for ToolResultCompactionStrategy

Co-authored-by: crickman <66376200+crickman@users.noreply.github.com>

* Refine shape

* Fix test expectation

* Potential fix for pull request finding

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: crickman <66376200+crickman@users.noreply.github.com>
Co-authored-by: Chris Rickman <crickman@microsoft.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
2026-03-18 19:24:43 +00:00
f48c4512d3 Python: Simplify Python Poe tasks and unify package selectors (#4722)
* updated automation tasks and commands, with alias for the time being

* Restore aggregate test exclusions

Preserve the legacy all-tests scope for test --all by excluding lab and devui from the default aggregate sweep, while still allowing explicit package selection. Also ignore hidden/generated test directories such as .mypy_cache during aggregate discovery.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* updated versions in pre-commit

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-18 18:39:11 +00:00
CopilotGitHubcrickmanCopilot Autofix powered by AIcopilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>Chris Rickman
d3d0100822 .NET Compaction - Add AsChatReducer() extension to expose CompactionStrategy as IChatReducer (#4664)
* Initial plan

* Add ChatStrategyExtensions.cs with AsChatReducer() extension method and tests

Co-authored-by: crickman <66376200+crickman@users.noreply.github.com>

* Refactor message list creation in ReduceAsync method

* Remove unnecessary blank line in AsChatReducer method

* Potential fix for pull request finding

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

* Potential fix for pull request finding

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

* Fix test

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: crickman <66376200+crickman@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Chris Rickman <crickman@microsoft.com>
2026-03-18 17:25:54 +00:00
acaf6b7054 Python: Fix ENABLE_SENSITIVE_DATA env var ignored when set after module import (#4743)
* Python: Re-read env vars in configure_otel_providers and enable_instrumentation (#4119)

Fix ENABLE_SENSITIVE_DATA and VS_CODE_EXTENSION_PORT env vars being ignored
when load_dotenv() runs after module import. The module-level
OBSERVABILITY_SETTINGS singleton cached env state at import time, and
configure_otel_providers() / enable_instrumentation() never re-read from
os.environ when parameters were None.

Both functions now construct a fresh ObservabilitySettings() to pick up
current env vars when explicit parameters are not provided, matching the
existing behavior of the env_file_path branch.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Address PR review feedback for #4119: avoid throwaway ObservabilitySettings

- Add _read_bool_env/_read_int_env helpers to read env vars without
  constructing a full ObservabilitySettings (which calls create_resource())
- Replace ObservabilitySettings() in enable_instrumentation() and
  configure_otel_providers() else-branch with direct env reads
- Add enable_console_exporters parameter to configure_otel_providers()
  for override parity with enable_sensitive_data and vs_code_extension_port
- Propagate _resource and _executed_setup in the non-env_file_path branch
- Make existing tests hermetic (clear VS_CODE_EXTENSION_PORT and
  ENABLE_CONSOLE_EXPORTERS env vars)
- Add tests: enable_console_exporters env refresh, explicit param overrides
  for both enable_instrumentation() and configure_otel_providers()

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Address remaining review feedback for #4119

- Refresh enable_console_exporters in enable_instrumentation() for
  consistency with configure_otel_providers(), so env var changes
  after import are picked up by both public API functions
- Make test_configure_otel_providers_reads_env_vs_code_port hermetic
  by clearing ENABLE_CONSOLE_EXPORTERS from the environment
- Add test_enable_instrumentation_reads_env_console_exporters to
  cover the new refresh behavior

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Remove unconditional enable_console_exporters overwrite from enable_instrumentation() (#4119)

enable_instrumentation() is documented as not configuring exporters, so
managing enable_console_exporters there was a leaky abstraction. The
unconditional _read_bool_env call silently reset the value to False when
ENABLE_CONSOLE_EXPORTERS was absent from env, clobbering any value
previously set by configure_otel_providers(enable_console_exporters=True).

- Remove the unconditional overwrite line from enable_instrumentation()
- Replace test_enable_instrumentation_reads_env_console_exporters with
  test_enable_instrumentation_does_not_touch_console_exporters
- Add regression test: enable_instrumentation() does not clobber a
  previously configured enable_console_exporters value
- Add test: explicit enable_sensitive_data param still leaves
  enable_console_exporters untouched

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-18 15:58:22 +00:00
Hui MiaoandGitHub c2fec6b51c Python: Add foundry hosted agents samples for python (#4648)
* Add two hosted agent samples using the foundry agent

* Refactor formatting and improve readability in main.py

* Add agent-framework dependency to requirements and update copyright notice in main.py files

* Refactor agent imports and update credential handling in hosted agent samples

* Update agent framework dependency in requirements for hosted agents

* chore: update Python version to 3.14 and improve Dockerfile for hosted agents

* feat: add hosted agent samples for Azure AI with local tools and multi-agent workflows

* fix: update Azure AI client import and refactor agent initialization in hotel agent sample

* feat: add hosted agent samples for Seattle hotel search and writer-reviewer workflow

* fix: correct agent name in YAML configuration for local tools agent
2026-03-18 08:39:08 +00:00
705ed47a0b Python: Fix missing methods on the Content class in durable tasks (#4738)
* Fix Content serialization in DurableAgentStateUnknownContent (#4719)

DurableAgentStateUnknownContent.from_unknown_content() stored raw Content
objects without converting them to dicts, causing json.dumps to fail in
Azure Durable Functions' entity state serialization. This affected content
types not explicitly handled (e.g., mcp_server_tool_call/result).

The fix converts Content objects to dicts via to_dict() when storing in
DurableAgentStateUnknownContent, and restores them via Content.from_dict()
in to_ai_content().

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Add to_json and from_json methods to Content class (#4719)

Add to_json() and from_json() methods to the Content class to match the
serialization interface provided by SerializationMixin on other model classes.
Also fix pre-existing pyright type errors in durabletask's
DurableAgentStateUnknownContent.to_ai_content().

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Address PR review: add type guard, remove to_json, add fallback, and tests

- Remove Content.to_json() per reviewer request (comment 3)
- Add type guard in Content.from_json() for non-dict JSON (comments 1, 4)
- Wrap json.JSONDecodeError as ValueError for consistent exception contract
- Add try/except fallback in to_ai_content() for invalid Content dicts (comment 5)
- Add test_content_to_dict_exclude_none and test_content_to_dict_exclude_fields (comment 2)
- Add test_unknown_content_to_ai_content_fallback_on_invalid_type_dict (comment 5)

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Apply pre-commit auto-fixes

* Address review feedback for #4719: review comment fixes

* Remove Content.from_json, move logic to consuming code (#4719)

Remove the from_json convenience method from Content class per review
feedback. This is the same trivial json.loads + from_dict wrapper as
to_json which was already removed. Consumers should call json.loads
and Content.from_dict directly.

Update tests to use Content.from_dict(json.loads(...)) pattern and
remove from_json-specific error handling tests (those errors are
already covered by json.loads and Content.from_dict).

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-18 08:08:44 +00:00
192a283c9a Python: Reduce Azure chat client import overhead (#4744)
* Reduce Azure chat client import overhead

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix Azure chat client type annotations and add _parse_text_from_openai tests

- Move Choice and ChunkChoice imports under TYPE_CHECKING to avoid
  runtime import cost (from __future__ annotations is already present)
- Restore proper typed signature (Choice | ChunkChoice) instead of Any
- Add direct unit tests for _parse_text_from_openai covering:
  - Choice with message content
  - ChunkChoice with delta content
  - Refusal branch for both Choice and ChunkChoice
  - No content/no refusal returning None
  - None delta (async content filtering) returning None

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <copilot@github.com>
2026-03-18 08:05:42 +00:00
Peter IbekweandGitHub c74b1b08eb .NET: Fix race condition issue in FanInEdge while processing messages. (#4662)
* Fix race condition issue in FanInEdge while processing messages.

* refactored to limit the code segment under lock.

* Remove extra materialization of the result.

* Added comment to clarify future changes if process message is made async.
2026-03-18 00:36:10 +00:00
Shyju KrishnankuttyandGitHub 7c85f98c27 .NET: Align sample build configuration with test runner in CI (#4735)
* Run azure functions integration tests in release mode.

* Use debug when in debug build.
2026-03-17 20:20:14 +00:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
1e6f8909ec Bump pyjwt from 2.11.0 to 2.12.0 in /python (#4699)
Bumps [pyjwt](https://github.com/jpadilla/pyjwt) from 2.11.0 to 2.12.0.
- [Release notes](https://github.com/jpadilla/pyjwt/releases)
- [Changelog](https://github.com/jpadilla/pyjwt/blob/master/CHANGELOG.rst)
- [Commits](https://github.com/jpadilla/pyjwt/compare/2.11.0...2.12.0)

---
updated-dependencies:
- dependency-name: pyjwt
  dependency-version: 2.12.0
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-03-17 16:06:07 +00:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
008fe23585 Bump actions/upload-artifact from 4 to 7 (#4373)
Bumps [actions/upload-artifact](https://github.com/actions/upload-artifact) from 4 to 7.
- [Release notes](https://github.com/actions/upload-artifact/releases)
- [Commits](https://github.com/actions/upload-artifact/compare/v4...v7)

---
updated-dependencies:
- dependency-name: actions/upload-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>
2026-03-17 16:05:55 +00:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
6af0511e2b Bump MishaKav/pytest-coverage-comment from 1.2.0 to 1.6.0 (#4543)
Bumps [MishaKav/pytest-coverage-comment](https://github.com/mishakav/pytest-coverage-comment) from 1.2.0 to 1.6.0.
- [Release notes](https://github.com/mishakav/pytest-coverage-comment/releases)
- [Changelog](https://github.com/MishaKav/pytest-coverage-comment/blob/main/CHANGELOG.md)
- [Commits](https://github.com/mishakav/pytest-coverage-comment/compare/v1.2.0...v1.6.0)

---
updated-dependencies:
- dependency-name: MishaKav/pytest-coverage-comment
  dependency-version: 1.6.0
  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>
2026-03-17 16:04:37 +00:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
6dbb0a5bb4 Bump danielpalme/ReportGenerator-GitHub-Action from 5.5.1 to 5.5.3 (#4542)
Bumps [danielpalme/ReportGenerator-GitHub-Action](https://github.com/danielpalme/reportgenerator-github-action) from 5.5.1 to 5.5.3.
- [Release notes](https://github.com/danielpalme/reportgenerator-github-action/releases)
- [Commits](https://github.com/danielpalme/reportgenerator-github-action/compare/5.5.1...5.5.3)

---
updated-dependencies:
- dependency-name: danielpalme/ReportGenerator-GitHub-Action
  dependency-version: 5.5.3
  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>
2026-03-17 16:04:20 +00:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
21af304c7d Bump actions/setup-dotnet from 5.1.0 to 5.2.0 (#4541)
Bumps [actions/setup-dotnet](https://github.com/actions/setup-dotnet) from 5.1.0 to 5.2.0.
- [Release notes](https://github.com/actions/setup-dotnet/releases)
- [Commits](https://github.com/actions/setup-dotnet/compare/v5.1.0...v5.2.0)

---
updated-dependencies:
- dependency-name: actions/setup-dotnet
  dependency-version: 5.2.0
  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>
2026-03-17 16:04:07 +00:00
94af83680e Python: Fix RUN_FINISHED.interrupt to accumulate all interrupts when multiple tools need approval (#4717)
* Fix flow.interrupts overwrite when multiple tools need approval (#4590)

Change flow.interrupts assignment to append so that all interrupt entries
accumulate when multiple tools require approval in a single turn.

Both _run_common.py and _agent_run.py used assignment (=) which caused
each new interrupt to overwrite the previous one. Switching to append()
ensures RUN_FINISHED.interrupt contains all pending approvals.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Add test for streaming path with multiple confirm_changes interrupts (#4590)

Add integration test exercising run_agent_stream with multiple predictive
tool calls requiring confirmation. Verifies that flow.interrupts.append()
correctly accumulates all interrupt entries and they appear in the
RUN_FINISHED event.

Also confirms FlowState already declares interrupts field with
default_factory=list, addressing the AttributeError concern from review.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Apply pre-commit auto-fixes

---------

Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-17 12:44:44 +00:00
cdb51e6a41 Python: fix thread serialization for multi-turn tool calls (#4684)
* Python: strip fc_id from loaded history

* Move fc_id replay handling into Responses client

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Remove unnecessary pytest asyncio marker

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Add Responses integration test for fc_id replay

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* removed old arg

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-17 10:00:04 +00:00
cbcdb2d29e .NET: Add durable workflow support (#4436)
* .NET: [Feature Branch] Add basic durable workflow support (#3648)

* Add basic durable workflow support.

* PR feedback fixes

* Add conditional edge sample.

* PR feedback fixes.

* Minor cleanup.

* Minor cleanup

* Minor formatting improvements.

* Improve comments/documentation on the execution flow.

* .NET: [Feature Branch] Add Azure Functions hosting support for durable workflows (#3935)

* Adding azure functions workflow support.

* - PR feedback fixes.
- Add example to demonstrate complex Object as payload.

* rename instanceId to runId.

* Use custom ITaskOrchestrator to run orchestrator function.

* .NET: [Feature Branch] Adding support for events & shared state in durable workflows (#4020)

* Adding support for events & shared state in durable workflows.

* PR feedback fixes

* PR feedback fixes.

* Add YieldOutputAsync calls to 05_WorkflowEvents sample executors

The integration test asserts that WorkflowOutputEvent is found in the
stream, but the sample executors only used AddEventAsync for custom
events and never called YieldOutputAsync. Since WorkflowOutputEvent is
only emitted via explicit YieldOutputAsync calls, the assertion would
fail. Added YieldOutputAsync to each executor to match the test
expectation and demonstrate the API in the sample.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix deserialization to use shared serializer options.

* PR feedback updates.

* Sample cleanup

* PR feedback fixes

* Addressing PR review feedback for DurableStreamingWorkflowRun

   - Use -1 instead of 0 for taskId in TaskFailedException when task ID is not relevant.
   - Add [NotNullWhen(true)] to TryParseWorkflowResult out parameter following .NET TryXXX conventions.

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* .NET: [Feature Branch]  Add nested sub-workflow support for durable workflows (#4190)

* .NET: [Feature Branch] Add nested sub-workflow support for durable workflows

* fix readme path

* Switch Orchestration output from string to DurableWorkflowResult.

* PR feedback fixes

* Minor cleanup based on PR feedback.

* .NET: [Feature Branch] Add Human In the Loop support for durable workflows (#4358)

* Add Azure Functions HITL workflow sample

Add 06_WorkflowHITL Azure Functions sample demonstrating Human-in-the-Loop
workflow support with HTTP endpoints for status checking and approval responses.

The sample includes:
- ExpenseReimbursement workflow with RequestPort for manager approval
- Custom HTTP endpoint to check workflow status and pending approvals
- Custom HTTP endpoint to send approval responses via RaiseEventAsync
- demo.http file with step-by-step interaction examples

* PR feedback fixes

* Minor comment cleanup

* Minor comment clReverted the `!context.IsReplaying` guards on `PendingEvents.Add`/`RemoveAll` and `SetCustomStatus` in `ExecuteRequestPortAsync`. The guards broke fan-out scenarios where parallel RequestPorts      need to be discoverable after replay. `SetCustomStatus` is idempotent metadata that doesn't affect replay determinism.eanup

* fix  for PR feedback

* PR feedback updates

* Improvements to samples

* Improvements to README

* Update samples to use parallel request ports.

* Unit tests

* Introduce local variables to improve readability of Workflows.Workflows access patter

* Use GitHub-style callouts and add PowerShell command variants in HITL sample README

* Add changelog entries for durable workflow support (#4436)

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Bump Microsoft.DurableTask.Worker to 1.19.1 to fix version downgrade

Microsoft.Azure.Functions.Worker.Extensions.DurableTask 1.13.1 requires
Microsoft.DurableTask.Worker >= 1.19.1 via its transitive dependency on
Microsoft.DurableTask.Worker.Grpc 1.19.1.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix broken markdown links in durable workflow sample READMEs

- Create Workflow/README.md with environment setup docs
- Fix ../README.md -> ../../README.md in ConsoleApps 01, 02, 03, 08
- Fix SubWorkflows relative path (3 levels -> 4 levels up)
- Fix dead Durable Task Scheduler URL

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix build errors from main merge: Throw conflict, ExecuteAsync rename, GetNewSessionAsync rename

- Remove InjectSharedThrow from DurableTask csproj (uses Workflows' internal Throw via InternalsVisibleTo)
- Update ExecuteAsync -> ExecuteCoreAsync with WorkflowTelemetryContext.Disabled
- Update GetNewSessionAsync -> CreateSessionAsync

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Move durable workflow samples to 04-hosting/DurableWorkflows

Aligns with main branch sample reorganization where durable samples
live under 04-hosting/ (alongside DurableAgents/).

- Move samples/Durable/Workflow/ -> samples/04-hosting/DurableWorkflows/
- Add Directory.Build.props matching DurableAgents pattern
- Update slnx project paths
- Update integration test sample paths
- Update README cd paths and cross-references

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix build errors: remove duplicate base class members, update renamed APIs

- Remove duplicate OutputLog, WriteInputAsync, CreateTestTimeoutCts, etc. from
  ConsoleAppSamplesValidation (already in SamplesValidationBase)
- Update AddFanInEdge -> AddFanInBarrierEdge in workflow samples
- Update GetNewSessionAsync -> CreateSessionAsync in workflow samples
- Update SourceId -> ExecutorId (obsolete) in workflow samples

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix dotnet format issues: add UTF-8 BOM and remove unused using

- Add UTF-8 BOM to 20 .cs files across DurableTask, AzureFunctions,
  unit tests, and workflow samples
- Remove unnecessary using directive in 07_SubWorkflows/Executors.cs

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix typo PaymentProcesser -> PaymentProcessor and garbled arrows in README

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix GetExecutorName to handle agent names with underscores

Split on last underscore instead of first, and validate that the
suffix is a 32-char hex string (sanitized GUID) before stripping it.
This prevents truncation of agent names like 'my_agent' when the
executor ID is 'my_agent_<guid>'.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Align DurableTask.Client.AzureManaged to 1.19.1

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Bump DurableTask and Azure Functions extension package versions

- DurableTask.* packages: 1.19.1 -> 1.22.0
- Functions.Worker.Extensions.DurableTask: 1.13.1 -> 1.16.0
- Functions.Worker.Extensions.DurableTask.AzureManaged: 1.0.1 -> 1.5.0 (telemetry bug fix)

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Bump DurableTask SDK packages to 1.22.0

- DurableTask.Client: 1.19.1 -> 1.22.0
- DurableTask.Client.AzureManaged: 1.19.1 -> 1.22.0
- DurableTask.Worker: 1.19.1 -> 1.22.0
- DurableTask.Worker.AzureManaged: 1.19.1 -> 1.22.0
- Azure Functions extensions kept at original versions (1.13.1/1.0.1) due to
  host-side DurableTask.Core 3.7.0 incompatibility with newer extensions

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Update Microsoft.Azure.Functions.Worker.Extensions.DurableTask to "1.16.0"

* Add the local.settings.json files to the sample which were previously ignored. This aligns with our other samples.

* Increase timeout for tests as CI has them failing transiently.

* increaset timeout value for azure functions integration tests.

* Add YieldsOutput(string) to workflow shared state sample executors

ValidateOrder and EnrichOrder call YieldOutputAsync with string messages,
but only their TOutput (OrderDetails) was in the allowed yield types.
This caused TargetInvocationException in the WorkflowSharedState sample
validation integration test.

* Downgrade the durable packages to 1.18.0

* Downgrading Worker.Extensions.DurableTask to 1.12.1

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-16 23:00:50 +00:00
0fdcfd0f4c Python: preserve A2A message context_id (#4686)
* Python: forward A2A context_id

* Avoid duplicating A2A context ids

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-16 21:41:31 +00:00
Giles OdigweandGitHub 414496dda7 fix: Azure Redis sample missing session for history persistence (#4692) 2026-03-16 21:34:21 +00:00
55011b7258 Python: Fix _deduplicate_messages catch-all branch dropping valid repeated messages (#4716)
* Fix _deduplicate_messages catch-all branch dropping valid repeated messages (#4682)

Remove the catch-all dedup branch that used (role, hash(content_str)) as a
dedup key. This incorrectly treated any two messages with the same role and
identical content as duplicates, dropping valid repeated messages (e.g., a
user saying 'yes' to confirm two separate things).

The tool-specific dedup branches (tool results by call_id, assistant tool
calls by call_id tuple) remain unchanged as they correctly identify true
protocol-level duplicates.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Address review: consecutive-duplicate detection for non-tool messages (#4682)

- Replace blanket dedup removal with consecutive-duplicate detection:
  only skip a message if the immediately preceding message has the same
  role and content, preserving protection against upstream replays while
  allowing identical messages at different conversation points.
- Strengthen test assertions to verify message identity and order, not
  just list length.
- Add tests for consecutive duplicate skipping, non-consecutive
  preservation, and messages with contents=None.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Apply pre-commit auto-fixes

* Use message_id for deduplication instead of content hashing

Deduplicate general messages by message_id when available, replacing
the consecutive-duplicate content check. Two messages with the same id
are definitively the same message (upstream replay), while identical
content with distinct ids (e.g. repeated "yes" confirmations) is
preserved. Messages without a message_id are always kept.

* Fix message_id dedup: truthy check, content-hash fallback, log safety

- Use truthy check (`if msg.message_id`) instead of `is not None` so
  empty-string IDs fall through to content-hash dedup rather than
  collapsing unrelated messages.
- Add content-hash fallback for messages without message_id, preventing
  false negatives from integrations that don't set IDs.
- Remove raw message_id from log format string (addresses log-injection
  surface with control characters).
- Add tests for empty-string message_id edge cases.
- Update existing tests to reflect content-hash dedup behavior.

Fixes #4682

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-16 17:47:33 +00:00
CopilotGitHubcrickmancopilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
bf0af178bd .NET - Fix flaky workflows test (#4700)
* Initial plan

* Fix flaky test: initialize creationTime 1 second in the past

Co-authored-by: crickman <66376200+crickman@users.noreply.github.com>

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: crickman <66376200+crickman@users.noreply.github.com>
2026-03-16 17:33:08 +00:00
1107 changed files with 53268 additions and 20740 deletions
+1
View File
@@ -3,6 +3,7 @@
"image": "mcr.microsoft.com/devcontainers/dotnet",
"features": {
"ghcr.io/devcontainers/features/azure-cli:1.2.9": {},
"ghcr.io/devcontainers/features/docker-in-docker:2": {},
"ghcr.io/devcontainers/features/github-cli:1": {
"version": "2"
},
@@ -24,7 +24,9 @@ runs:
using: "composite"
steps:
- name: Set up Node.js environment
uses: actions/setup-node@v4
uses: actions/setup-node@v6
with:
node-version: 22
- name: Install Copilot CLI
shell: bash
@@ -0,0 +1,166 @@
name: Setup Local MCP Server
description: Start and validate a local streamable HTTP MCP server for integration tests
inputs:
fallback_url:
description: Existing LOCAL_MCP_URL value to keep as a fallback if local startup fails
required: false
default: ''
host:
description: Host interface to bind the local MCP server
required: false
default: '127.0.0.1'
port:
description: Port to bind the local MCP server
required: false
default: '8011'
mount_path:
description: Mount path for the local streamable HTTP MCP endpoint
required: false
default: '/mcp'
outputs:
effective_url:
description: Local MCP URL when startup succeeds, otherwise the provided fallback URL
value: ${{ steps.start.outputs.effective_url }}
local_url:
description: URL of the local MCP server
value: ${{ steps.start.outputs.local_url }}
started:
description: Whether the local MCP server started and passed validation
value: ${{ steps.start.outputs.started }}
pid:
description: PID of the local MCP server process when startup succeeded
value: ${{ steps.start.outputs.pid }}
runs:
using: composite
steps:
- name: Start and validate local MCP server
id: start
shell: bash
run: |
set -euo pipefail
host="${{ inputs.host }}"
port="${{ inputs.port }}"
mount_path="${{ inputs.mount_path }}"
fallback_url="${{ inputs.fallback_url }}"
if [[ ! "$mount_path" =~ ^/ ]]; then
mount_path="/$mount_path"
fi
local_url="http://${host}:${port}${mount_path}"
health_url="http://${host}:${port}/healthz"
log_file="$RUNNER_TEMP/local-mcp-server.log"
pid_file="$RUNNER_TEMP/local-mcp-server.pid"
rm -f "$log_file" "$pid_file"
server_pid="$(
python3 - "$GITHUB_WORKSPACE/python" "$log_file" "$host" "$port" "$mount_path" <<'PY'
from __future__ import annotations
import subprocess
import sys
workspace, log_file, host, port, mount_path = sys.argv[1:]
with open(log_file, "w", encoding="utf-8") as log:
process = subprocess.Popen(
[
"uv",
"run",
"python",
"scripts/local_mcp_streamable_http_server.py",
"--host",
host,
"--port",
port,
"--mount-path",
mount_path,
],
cwd=workspace,
stdout=log,
stderr=subprocess.STDOUT,
start_new_session=True,
)
print(process.pid)
PY
)"
echo "$server_pid" > "$pid_file"
started=false
for _ in $(seq 1 30); do
if curl --silent --fail "$health_url" >/dev/null; then
started=true
break
fi
if ! kill -0 "$server_pid" 2>/dev/null; then
break
fi
sleep 1
done
if [[ "$started" == "true" ]]; then
if ! (
cd "$GITHUB_WORKSPACE/python"
LOCAL_MCP_URL="$local_url" uv run python - <<'PY'
from __future__ import annotations
import asyncio
import os
from agent_framework import Content, MCPStreamableHTTPTool
def result_to_text(result: str | list[Content]) -> str:
if isinstance(result, str):
return result
return "\n".join(content.text for content in result if content.type == "text" and content.text)
async def main() -> None:
tool = MCPStreamableHTTPTool(
name="local_ci_mcp",
url=os.environ["LOCAL_MCP_URL"],
approval_mode="never_require",
)
async with tool:
assert tool.functions, "Local MCP server did not expose any tools."
result = result_to_text(await tool.functions[0].invoke(query="What is Agent Framework?"))
assert result, "Local MCP server returned an empty response."
asyncio.run(main())
PY
); then
started=false
fi
fi
effective_url="$local_url"
pid="$server_pid"
if [[ "$started" != "true" ]]; then
effective_url="$fallback_url"
pid=""
if kill -0 "$server_pid" 2>/dev/null; then
kill -TERM -- "-$server_pid" 2>/dev/null || kill -TERM "$server_pid" || true
sleep 1
kill -KILL -- "-$server_pid" 2>/dev/null || kill -KILL "$server_pid" || true
fi
echo "Local MCP server was unavailable; continuing with fallback LOCAL_MCP_URL."
if [[ -f "$log_file" ]]; then
tail -n 100 "$log_file" || true
fi
else
echo "Using local MCP server at $local_url"
fi
echo "started=$started" >> "$GITHUB_OUTPUT"
echo "local_url=$local_url" >> "$GITHUB_OUTPUT"
echo "effective_url=$effective_url" >> "$GITHUB_OUTPUT"
echo "pid=$pid" >> "$GITHUB_OUTPUT"
+216
View File
@@ -0,0 +1,216 @@
# Copyright (c) Microsoft. All rights reserved.
"""Scan open issues and PRs labeled 'waiting-for-author' for stale follow-ups.
Team members manually add the 'waiting-for-author' label when they need a
response from the external author. If the author hasn't replied within
DAYS_THRESHOLD days of the last team comment, post a reminder and add the
'requested-info' label to prevent duplicate pings.
"""
from __future__ import annotations
import os
import sys
import time
from datetime import datetime, timezone
from github import Auth, Github, GithubException
from github.Issue import Issue
from github.IssueComment import IssueComment
PING_COMMENT = (
"@{author}, friendly reminder — this issue is waiting on your response. "
"Please share any updates when you get a chance. (This is an automated message.)"
)
TRIGGER_LABEL = "waiting-for-author"
PINGED_LABEL = "requested-info"
def get_team_members(g: Github, org: str, team_slug: str) -> set[str]:
"""Fetch active team member usernames."""
try:
org_obj = g.get_organization(org)
team = org_obj.get_team_by_slug(team_slug)
return {m.login for m in team.get_members()}
except GithubException as exc:
if exc.status in (403, 404):
print(
f"ERROR: Failed to fetch team members for {org}/{team_slug} "
f"(HTTP {exc.status}). Check that the token has the 'read:org' "
f"scope and that the team slug '{team_slug}' is correct."
)
else:
print(f"ERROR: Failed to fetch team members for {org}/{team_slug}: {exc}")
sys.exit(1)
except Exception as exc:
print(f"ERROR: Failed to fetch team members for {org}/{team_slug}: {exc}")
sys.exit(1)
def find_last_team_comment(
comments: list[IssueComment], team_members: set[str]
) -> IssueComment | None:
"""Return the most recent comment from a team member, or None."""
for comment in reversed(comments):
if comment.user and comment.user.login in team_members:
return comment
return None
def author_replied_after(
comments: list[IssueComment], author: str, after: datetime
) -> bool:
"""Check if the issue author commented after the given timestamp."""
for comment in comments:
if (
comment.user
and comment.user.login == author
and comment.created_at > after
):
return True
return False
def should_ping(
issue: Issue,
team_members: set[str],
days_threshold: int,
now: datetime,
) -> bool:
"""Determine whether this issue/PR should be pinged.
Only issues/PRs carrying the 'waiting-for-author' label are candidates.
"""
author = issue.user.login
# Skip if the trigger label is not present
if not any(label.name == TRIGGER_LABEL for label in issue.labels):
return False
# Skip if author is a team member
if author in team_members:
return False
# Skip if already pinged
if any(label.name == PINGED_LABEL for label in issue.labels):
return False
# Skip if no comments at all
if issue.comments == 0:
return False
# Fetch comments once for both lookups
comments = list(issue.get_comments())
# Find last team member comment
last_team_comment = find_last_team_comment(comments, team_members)
if last_team_comment is None:
return False
# Skip if author replied after the last team comment
if author_replied_after(comments, author, last_team_comment.created_at):
return False
# Check if enough days have passed
days_since = (now - last_team_comment.created_at.astimezone(timezone.utc)).days
if days_since < days_threshold:
return False
return True
def ping(issue: Issue, dry_run: bool) -> bool:
"""Post a reminder comment and add the 'requested-info' label. Returns True on success."""
author = issue.user.login
kind = "PR" if issue.pull_request else "Issue"
if dry_run:
print(f" [DRY RUN] Would ping {kind} #{issue.number} (@{author})")
return True
max_retries = 3
commented = False
labeled = False
for attempt in range(1, max_retries + 1):
try:
if not commented:
issue.create_comment(PING_COMMENT.format(author=author))
commented = True
if not labeled:
issue.add_to_labels(PINGED_LABEL)
labeled = True
print(f" Pinged {kind} #{issue.number} (@{author})")
return True
except Exception as exc:
if attempt < max_retries:
wait = 2 ** attempt # 2s, 4s
print(f" WARN: Attempt {attempt}/{max_retries} failed for {kind} #{issue.number}: {exc}. Retrying in {wait}s...")
time.sleep(wait)
else:
print(f" ERROR: Failed to ping {kind} #{issue.number} after {max_retries} attempts: {exc}")
return False
def main() -> None:
token = os.environ.get("GITHUB_TOKEN")
if not token:
print("ERROR: GITHUB_TOKEN environment variable is required")
sys.exit(1)
repository = os.environ.get("GITHUB_REPOSITORY")
if not repository:
print("ERROR: GITHUB_REPOSITORY environment variable is required")
sys.exit(1)
team_slug = os.environ.get("TEAM_SLUG")
if not team_slug:
print("ERROR: TEAM_SLUG environment variable is required")
sys.exit(1)
days_threshold_raw = os.environ.get("DAYS_THRESHOLD", "4")
try:
days_threshold = int(days_threshold_raw)
except ValueError:
print(f"ERROR: DAYS_THRESHOLD must be a numeric value, got '{days_threshold_raw}'")
sys.exit(1)
dry_run = os.environ.get("DRY_RUN", "false").lower() == "true"
org = repository.split("/")[0]
if dry_run:
print("Running in DRY RUN mode — no comments or labels will be applied.\n")
g = Github(auth=Auth.Token(token))
repo = g.get_repo(repository)
print(f"Fetching team members for {org}/{team_slug}...")
team_members = get_team_members(g, org, team_slug)
print(f"Found {len(team_members)} team members.\n")
now = datetime.now(timezone.utc)
pinged = []
failed = []
scanned = 0
print(f"Scanning open issues and PRs labeled '{TRIGGER_LABEL}' (threshold: {days_threshold} days)...\n")
for issue in repo.get_issues(state="open", labels=[TRIGGER_LABEL]):
scanned += 1
if should_ping(issue, team_members, days_threshold, now):
if ping(issue, dry_run):
pinged.append(issue.number)
else:
failed.append(issue.number)
print(f"\nDone. Scanned {scanned} items, pinged {len(pinged)}, failed {len(failed)}.")
if pinged:
print(f"Pinged: {', '.join(f'#{n}' for n in pinged)}")
if failed:
print(f"Failed: {', '.join(f'#{n}' for n in failed)}")
sys.exit(1)
if __name__ == "__main__":
main()
+297
View File
@@ -0,0 +1,297 @@
# Copyright (c) Microsoft. All rights reserved.
"""Tests for stale_issue_pr_ping.py."""
from __future__ import annotations
import os
import sys
from datetime import datetime, timezone, timedelta
from unittest.mock import MagicMock, patch
import pytest
# Ensure the script directory is importable
sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "scripts"))
from stale_issue_pr_ping import (
PINGED_LABEL,
PING_COMMENT,
TRIGGER_LABEL,
author_replied_after,
find_last_team_comment,
get_team_members,
main,
ping,
should_ping,
)
TEAM = {"alice", "bob"}
NOW = datetime(2026, 3, 15, 12, 0, 0, tzinfo=timezone.utc)
# ---------------------------------------------------------------------------
# Helpers
# ---------------------------------------------------------------------------
def _make_comment(login: str | None, created_at: datetime) -> MagicMock:
"""Create a mock IssueComment."""
c = MagicMock()
if login is None:
c.user = None
else:
c.user = MagicMock()
c.user.login = login
c.created_at = created_at
return c
def _make_label(name: str) -> MagicMock:
lbl = MagicMock()
lbl.name = name
return lbl
def _make_issue(
author: str = "external",
labels: list[str] | None = None,
comment_count: int = 1,
comments: list[MagicMock] | None = None,
pull_request: bool = False,
number: int = 42,
) -> MagicMock:
issue = MagicMock()
issue.user = MagicMock()
issue.user.login = author
issue.number = number
# Default to having the trigger label, since the API query pre-filters.
if labels is None:
labels = [TRIGGER_LABEL]
issue.labels = [_make_label(n) for n in labels]
issue.comments = comment_count
issue.pull_request = MagicMock() if pull_request else None
if comments is not None:
issue.get_comments.return_value = comments
return issue
# ---------------------------------------------------------------------------
# find_last_team_comment
# ---------------------------------------------------------------------------
class TestFindLastTeamComment:
def test_returns_last_team_comment(self):
c1 = _make_comment("alice", datetime(2026, 3, 1, tzinfo=timezone.utc))
c2 = _make_comment("external", datetime(2026, 3, 2, tzinfo=timezone.utc))
c3 = _make_comment("bob", datetime(2026, 3, 3, tzinfo=timezone.utc))
assert find_last_team_comment([c1, c2, c3], TEAM) is c3
def test_returns_none_when_no_team_comments(self):
c1 = _make_comment("external", datetime(2026, 3, 1, tzinfo=timezone.utc))
assert find_last_team_comment([c1], TEAM) is None
def test_returns_none_for_empty_list(self):
assert find_last_team_comment([], TEAM) is None
def test_skips_deleted_user(self):
c1 = _make_comment(None, datetime(2026, 3, 1, tzinfo=timezone.utc))
c2 = _make_comment("alice", datetime(2026, 3, 2, tzinfo=timezone.utc))
assert find_last_team_comment([c1, c2], TEAM) is c2
def test_only_deleted_users(self):
c1 = _make_comment(None, datetime(2026, 3, 1, tzinfo=timezone.utc))
assert find_last_team_comment([c1], TEAM) is None
# ---------------------------------------------------------------------------
# author_replied_after
# ---------------------------------------------------------------------------
class TestAuthorRepliedAfter:
def test_author_replied(self):
after = datetime(2026, 3, 1, tzinfo=timezone.utc)
c1 = _make_comment("external", datetime(2026, 3, 2, tzinfo=timezone.utc))
assert author_replied_after([c1], "external", after) is True
def test_author_not_replied(self):
after = datetime(2026, 3, 5, tzinfo=timezone.utc)
c1 = _make_comment("external", datetime(2026, 3, 2, tzinfo=timezone.utc))
assert author_replied_after([c1], "external", after) is False
def test_different_user_replied(self):
after = datetime(2026, 3, 1, tzinfo=timezone.utc)
c1 = _make_comment("someone_else", datetime(2026, 3, 2, tzinfo=timezone.utc))
assert author_replied_after([c1], "external", after) is False
def test_deleted_user_comment(self):
after = datetime(2026, 3, 1, tzinfo=timezone.utc)
c1 = _make_comment(None, datetime(2026, 3, 2, tzinfo=timezone.utc))
assert author_replied_after([c1], "external", after) is False
# ---------------------------------------------------------------------------
# should_ping
# ---------------------------------------------------------------------------
class TestShouldPing:
def test_should_ping_stale_issue(self):
team_comment = _make_comment("alice", NOW - timedelta(days=5))
issue = _make_issue(comments=[team_comment], comment_count=1)
assert should_ping(issue, TEAM, 4, NOW) is True
def test_skip_team_member_author(self):
issue = _make_issue(author="alice", labels=[TRIGGER_LABEL], comment_count=1)
assert should_ping(issue, TEAM, 4, NOW) is False
def test_skip_already_pinged(self):
issue = _make_issue(labels=[TRIGGER_LABEL, PINGED_LABEL], comment_count=1)
assert should_ping(issue, TEAM, 4, NOW) is False
def test_skip_no_comments(self):
issue = _make_issue(comment_count=0)
assert should_ping(issue, TEAM, 4, NOW) is False
def test_skip_no_team_comment(self):
c = _make_comment("external", NOW - timedelta(days=5))
issue = _make_issue(comments=[c], comment_count=1)
assert should_ping(issue, TEAM, 4, NOW) is False
def test_skip_author_replied(self):
team_c = _make_comment("alice", NOW - timedelta(days=5))
author_c = _make_comment("external", NOW - timedelta(days=3))
issue = _make_issue(comments=[team_c, author_c], comment_count=2)
assert should_ping(issue, TEAM, 4, NOW) is False
def test_skip_not_enough_days(self):
team_comment = _make_comment("alice", NOW - timedelta(days=2))
issue = _make_issue(comments=[team_comment], comment_count=1)
assert should_ping(issue, TEAM, 4, NOW) is False
def test_aware_datetime_handled(self):
"""Timezone-aware datetimes should not be mangled by astimezone."""
aware_dt = (NOW - timedelta(days=5)).replace(tzinfo=timezone.utc)
team_comment = _make_comment("alice", aware_dt)
issue = _make_issue(comments=[team_comment], comment_count=1)
assert should_ping(issue, TEAM, 4, NOW) is True
def test_naive_datetime_handled(self):
"""Naive datetimes (pre-PyGithub 2.x) should be handled by astimezone."""
naive_dt = (NOW - timedelta(days=5)).replace(tzinfo=None)
team_comment = _make_comment("alice", naive_dt)
issue = _make_issue(comments=[team_comment], comment_count=1)
# astimezone on naive datetime treats it as local time; just verify no crash
should_ping(issue, TEAM, 4, NOW)
# ---------------------------------------------------------------------------
# ping
# ---------------------------------------------------------------------------
class TestPing:
def test_dry_run(self, capsys):
issue = _make_issue()
assert ping(issue, dry_run=True) is True
issue.create_comment.assert_not_called()
assert "DRY RUN" in capsys.readouterr().out
def test_success(self, capsys):
issue = _make_issue()
assert ping(issue, dry_run=False) is True
issue.create_comment.assert_called_once()
issue.add_to_labels.assert_called_once_with(PINGED_LABEL)
@patch("stale_issue_pr_ping.time.sleep")
def test_retry_on_failure(self, mock_sleep):
issue = _make_issue()
issue.create_comment.side_effect = [Exception("net error"), None]
assert ping(issue, dry_run=False) is True
assert issue.create_comment.call_count == 2
mock_sleep.assert_called_once()
@patch("stale_issue_pr_ping.time.sleep")
def test_idempotent_retry_skips_comment_on_label_failure(self, mock_sleep):
"""If create_comment succeeds but add_to_labels fails, retry should not re-comment."""
issue = _make_issue()
issue.add_to_labels.side_effect = [Exception("label error"), None]
assert ping(issue, dry_run=False) is True
# Comment should only be created once even though there were 2 attempts
assert issue.create_comment.call_count == 1
assert issue.add_to_labels.call_count == 2
@patch("stale_issue_pr_ping.time.sleep")
def test_all_retries_fail(self, mock_sleep):
issue = _make_issue()
issue.create_comment.side_effect = Exception("permanent error")
assert ping(issue, dry_run=False) is False
assert issue.create_comment.call_count == 3
# ---------------------------------------------------------------------------
# get_team_members
# ---------------------------------------------------------------------------
class TestGetTeamMembers:
def test_success(self):
g = MagicMock()
member = MagicMock()
member.login = "alice"
g.get_organization.return_value.get_team_by_slug.return_value.get_members.return_value = [member]
assert get_team_members(g, "org", "my-team") == {"alice"}
def test_403_error_message(self, capsys):
from github import GithubException
g = MagicMock()
g.get_organization.return_value.get_team_by_slug.side_effect = GithubException(
403, {"message": "Forbidden"}, None
)
with pytest.raises(SystemExit):
get_team_members(g, "org", "my-team")
out = capsys.readouterr().out
assert "read:org" in out
assert "403" in out
def test_404_error_message(self, capsys):
from github import GithubException
g = MagicMock()
g.get_organization.return_value.get_team_by_slug.side_effect = GithubException(
404, {"message": "Not Found"}, None
)
with pytest.raises(SystemExit):
get_team_members(g, "org", "bad-slug")
out = capsys.readouterr().out
assert "read:org" in out
assert "bad-slug" in out
def test_generic_error(self, capsys):
g = MagicMock()
g.get_organization.side_effect = RuntimeError("boom")
with pytest.raises(SystemExit):
get_team_members(g, "org", "team")
# ---------------------------------------------------------------------------
# main env var validation
# ---------------------------------------------------------------------------
class TestMain:
@patch.dict(os.environ, {
"GITHUB_TOKEN": "tok",
"GITHUB_REPOSITORY": "org/repo",
"TEAM_SLUG": "my-team",
"DAYS_THRESHOLD": "abc",
}, clear=True)
def test_invalid_days_threshold(self, capsys):
with pytest.raises(SystemExit):
main()
assert "numeric" in capsys.readouterr().out
@patch.dict(os.environ, {
"GITHUB_TOKEN": "tok",
"GITHUB_REPOSITORY": "org/repo",
}, clear=True)
def test_missing_team_slug(self, capsys):
with pytest.raises(SystemExit):
main()
assert "TEAM_SLUG" in capsys.readouterr().out
+4 -4
View File
@@ -85,7 +85,7 @@ jobs:
workflow-samples
- name: Setup dotnet
uses: actions/setup-dotnet@v5.1.0
uses: actions/setup-dotnet@v5.2.0
with:
global-json-file: ${{ github.workspace }}/dotnet/global.json
- name: Build dotnet solutions
@@ -165,7 +165,7 @@ jobs:
echo "COSMOSDB_EMULATOR_AVAILABLE=true" >> $env:GITHUB_ENV
- name: Setup dotnet
uses: actions/setup-dotnet@v5.1.0
uses: actions/setup-dotnet@v5.2.0
with:
global-json-file: ${{ github.workspace }}/dotnet/global.json
@@ -281,7 +281,7 @@ jobs:
# Generate test reports and check coverage
- name: Generate test reports
if: matrix.targetFramework == env.COVERAGE_FRAMEWORK
uses: danielpalme/ReportGenerator-GitHub-Action@5.5.1
uses: danielpalme/ReportGenerator-GitHub-Action@5.5.3
with:
reports: "./TestResults/Coverage/**/*.cobertura.xml"
targetdir: "./TestResults/Reports"
@@ -289,7 +289,7 @@ jobs:
- name: Upload coverage report artifact
if: matrix.targetFramework == env.COVERAGE_FRAMEWORK
uses: actions/upload-artifact@v6
uses: actions/upload-artifact@v7
with:
name: CoverageReport-${{ matrix.os }}-${{ matrix.targetFramework }}-${{ matrix.configuration }} # Artifact name
path: ./TestResults/Reports # Directory containing files to upload
@@ -50,7 +50,7 @@ jobs:
echo "COSMOS_EMULATOR_AVAILABLE=true" >> $env:GITHUB_ENV
- name: Setup dotnet
uses: actions/setup-dotnet@v5.1.0
uses: actions/setup-dotnet@v5.2.0
with:
global-json-file: ${{ github.workspace }}/dotnet/global.json
+1 -2
View File
@@ -41,8 +41,7 @@ ENFORCED_TARGETS: set[str] = {
"packages.purview.agent_framework_purview",
"packages.anthropic.agent_framework_anthropic",
"packages.azure-ai-search.agent_framework_azure_ai_search",
"packages.core.agent_framework.azure",
"packages.core.agent_framework.openai",
"packages.openai.agent_framework_openai",
# Individual files (if you want to enforce specific files instead of whole packages)
"packages/core/agent_framework/observability.py",
# Add more targets here as coverage improves
+4 -6
View File
@@ -75,7 +75,7 @@ jobs:
os: ${{ runner.os }}
env:
UV_CACHE_DIR: /tmp/.uv-cache
- name: Run fmt, lint, pyright in parallel across packages
- name: Run syntax and pyright across packages
run: uv run poe check-packages
samples-markdown:
@@ -104,10 +104,8 @@ jobs:
os: ${{ runner.os }}
env:
UV_CACHE_DIR: /tmp/.uv-cache
- name: Run samples lint
run: uv run poe samples-lint
- name: Run samples syntax check
run: uv run poe samples-syntax
- name: Run samples checks
run: uv run poe check -S
- name: Run markdown code lint
run: uv run poe markdown-code-lint
@@ -140,4 +138,4 @@ jobs:
- name: Run Mypy
env:
GITHUB_BASE_REF: ${{ github.event.pull_request.base.ref || github.base_ref || 'main' }}
run: uv run poe ci-mypy
run: uv run python scripts/workspace_poe_tasks.py ci-mypy
@@ -38,13 +38,13 @@ jobs:
id: validate_ranges
# Keep workflow running so we can still publish diagnostics from this run.
continue-on-error: true
run: uv run poe validate-dependency-bounds-project --mode upper --project "*"
run: uv run poe validate-dependency-bounds-project --mode upper --package "*"
working-directory: ./python
- name: Upload dependency range report
# Always publish the report so failures are inspectable even when validation fails.
if: always()
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@v7
with:
name: dependency-range-results
path: python/scripts/dependencies/dependency-range-results.json
@@ -203,7 +203,7 @@ jobs:
cat > "${PR_BODY_FILE}" <<'EOF'
This PR was generated by the dependency range validation workflow.
- Ran `uv run poe validate-dependency-bounds-project --mode upper --project "*"`
- Ran `uv run poe validate-dependency-bounds-project --mode upper --package "*"`
- Updated package dependency bounds
- Refreshed `python/uv.lock` with `uv lock --upgrade`
EOF
+67 -19
View File
@@ -48,9 +48,8 @@ jobs:
os: ${{ runner.os }}
- name: Test with pytest (unit tests only)
run: >
uv run poe all-tests
uv run poe test -A
-m "not integration"
-n logical --dist worksteal
--timeout=120 --session-timeout=900 --timeout_method thread
--retries 2 --retry-delay 5
@@ -61,9 +60,10 @@ jobs:
environment: integration
timeout-minutes: 60
env:
OPENAI_CHAT_MODEL_ID: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_RESPONSES_MODEL_ID: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_EMBEDDINGS_MODEL_ID: ${{ vars.OPENAI_EMBEDDING_MODEL_ID }}
OPENAI_CHAT_MODEL: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_RESPONSES_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_EMBEDDING_MODEL: ${{ vars.OPENAI_EMBEDDING_MODEL_ID }}
OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
defaults:
run:
@@ -82,8 +82,8 @@ jobs:
- name: Test with pytest (OpenAI integration)
run: >
uv run pytest --import-mode=importlib
packages/core/tests/openai
-m integration
packages/openai/tests
-m "integration and not azure"
-n logical --dist worksteal
--timeout=120 --session-timeout=900 --timeout_method thread
--retries 2 --retry-delay 5
@@ -97,7 +97,8 @@ jobs:
env:
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__EMBEDDINGDEPLOYMENTNAME }}
AZURE_OPENAI_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME: ${{ vars.AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME }}
AZURE_OPENAI_ENDPOINT: ${{ vars.AZUREOPENAI__ENDPOINT }}
defaults:
run:
@@ -122,7 +123,11 @@ jobs:
- name: Test with pytest (Azure OpenAI integration)
run: >
uv run pytest --import-mode=importlib
packages/core/tests/azure
packages/openai/tests/openai/test_openai_chat_completion_client_azure.py
packages/openai/tests/openai/test_openai_chat_client_azure.py
packages/openai/tests/openai/test_openai_embedding_client_azure.py
packages/azure-ai/tests/azure_openai
--ignore=packages/azure-ai/tests/azure_openai/test_azure_responses_client_foundry.py
-m integration
-n logical --dist worksteal
--timeout=120 --session-timeout=900 --timeout_method thread
@@ -152,6 +157,13 @@ jobs:
with:
python-version: ${{ env.UV_PYTHON }}
os: ${{ runner.os }}
- name: Start local MCP server
id: local-mcp
uses: ./.github/actions/setup-local-mcp-server
with:
fallback_url: ${{ env.LOCAL_MCP_URL }}
- name: Prefer local MCP URL when available
run: echo "LOCAL_MCP_URL=${{ steps.local-mcp.outputs.effective_url }}" >> "$GITHUB_ENV"
- name: Test with pytest (Anthropic, Ollama, MCP integration)
run: >
uv run pytest --import-mode=importlib
@@ -162,6 +174,26 @@ jobs:
-n logical --dist worksteal
--timeout=120 --session-timeout=900 --timeout_method thread
--retries 2 --retry-delay 5
- name: Stop local MCP server
if: always()
shell: bash
run: |
set -euo pipefail
server_pid="${{ steps.local-mcp.outputs.pid }}"
if [[ -z "$server_pid" ]]; then
exit 0
fi
if ! kill -0 "$server_pid" 2>/dev/null; then
exit 0
fi
kill -TERM -- "-$server_pid" 2>/dev/null || kill -TERM "$server_pid" 2>/dev/null || true
for _ in $(seq 1 10); do
if ! kill -0 "$server_pid" 2>/dev/null; then
exit 0
fi
sleep 1
done
kill -KILL -- "-$server_pid" 2>/dev/null || kill -KILL "$server_pid" 2>/dev/null || true
# Azure Functions + Durable Task integration tests
python-tests-functions:
@@ -171,12 +203,16 @@ jobs:
timeout-minutes: 60
env:
UV_PYTHON: "3.11"
OPENAI_CHAT_MODEL_ID: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_RESPONSES_MODEL_ID: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_CHAT_MODEL: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_RESPONSES_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_EMBEDDING_MODEL: ${{ vars.OPENAI_EMBEDDING_MODEL_ID }}
OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
AZURE_OPENAI_ENDPOINT: ${{ vars.AZUREOPENAI__ENDPOINT }}
AZURE_OPENAI_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
FOUNDRY_PROJECT_ENDPOINT: ${{ vars.FOUNDRY_PROJECT_ENDPOINT }}
FOUNDRY_MODEL: ${{ vars.FOUNDRY_MODEL }}
FUNCTIONS_WORKER_RUNTIME: "python"
DURABLE_TASK_SCHEDULER_CONNECTION_STRING: "Endpoint=http://localhost:8080;TaskHub=default;Authentication=None"
AzureWebJobsStorage: "UseDevelopmentStorage=true"
@@ -210,18 +246,23 @@ jobs:
packages/durabletask/tests/integration_tests
-m integration
-n logical --dist worksteal
--timeout=120 --session-timeout=900 --timeout_method thread
-x
--timeout=360 --session-timeout=900 --timeout_method thread
--retries 2 --retry-delay 5
# Azure AI integration tests
python-tests-azure-ai:
name: Python Integration Tests - Azure AI
# Foundry integration tests
python-tests-foundry:
name: Python Integration Tests - Foundry
runs-on: ubuntu-latest
environment: integration
timeout-minutes: 60
env:
AZURE_AI_PROJECT_ENDPOINT: ${{ secrets.AZUREAI__ENDPOINT }}
AZURE_AI_MODEL_DEPLOYMENT_NAME: ${{ vars.AZUREAI__DEPLOYMENTNAME }}
FOUNDRY_PROJECT_ENDPOINT: ${{ vars.FOUNDRY_PROJECT_ENDPOINT }}
FOUNDRY_MODEL: ${{ vars.FOUNDRY_MODEL }}
FOUNDRY_AGENT_NAME: ${{ vars.FOUNDRY_AGENT_NAME }}
FOUNDRY_AGENT_VERSION: ${{ vars.FOUNDRY_AGENT_VERSION }}
LOCAL_MCP_URL: ${{ vars.LOCAL_MCP__URL }}
defaults:
run:
@@ -245,7 +286,14 @@ jobs:
subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
- name: Test with pytest
timeout-minutes: 15
run: uv run --directory packages/azure-ai poe integration-tests -n logical --dist worksteal --timeout=120 --session-timeout=900 --timeout_method thread --retries 2 --retry-delay 5
run: >
uv run pytest --import-mode=importlib
packages/azure-ai/tests/azure_openai/test_azure_responses_client_foundry.py
packages/foundry/tests
-m integration
-n logical --dist worksteal
--timeout=120 --session-timeout=900 --timeout_method thread
--retries 2 --retry-delay 5
# Azure Cosmos integration tests
python-tests-cosmos:
@@ -302,7 +350,7 @@ jobs:
python-tests-azure-openai,
python-tests-misc-integration,
python-tests-functions,
python-tests-azure-ai,
python-tests-foundry,
python-tests-cosmos
]
steps:
+81 -20
View File
@@ -47,6 +47,9 @@ jobs:
filters: |
python:
- 'python/**'
- '.github/actions/setup-local-mcp-server/**'
- '.github/workflows/python-merge-tests.yml'
- '.github/workflows/python-integration-tests.yml'
core:
- 'python/packages/core/agent_framework/_*.py'
- 'python/packages/core/agent_framework/_workflows/**'
@@ -54,20 +57,30 @@ jobs:
- 'python/packages/core/agent_framework/observability.py'
openai:
- 'python/packages/core/agent_framework/openai/**'
- 'python/packages/core/tests/openai/**'
- 'python/packages/openai/**'
- 'python/samples/**/providers/openai/**'
azure:
- 'python/packages/openai/**'
- 'python/packages/core/agent_framework/azure/**'
- 'python/packages/core/tests/azure/**'
- 'python/packages/azure-ai/agent_framework_azure_ai/_deprecated_azure_openai.py'
- 'python/packages/azure-ai/tests/azure_openai/**'
- 'python/samples/**/providers/azure/openai_chat_completion_client_azure*.py'
misc:
- 'python/packages/anthropic/**'
- 'python/packages/ollama/**'
- 'python/packages/core/agent_framework/_mcp.py'
- 'python/packages/core/tests/core/test_mcp.py'
- 'python/scripts/local_mcp_streamable_http_server.py'
- '.github/actions/setup-local-mcp-server/**'
- '.github/workflows/python-merge-tests.yml'
- '.github/workflows/python-integration-tests.yml'
functions:
- 'python/packages/azurefunctions/**'
- 'python/packages/durabletask/**'
azure-ai:
- 'python/packages/azure-ai/**'
- 'python/packages/foundry/**'
- 'python/samples/**/providers/foundry/**'
cosmos:
- 'python/packages/azure-cosmos/**'
# run only if 'python' files were changed
@@ -100,9 +113,8 @@ jobs:
os: ${{ runner.os }}
- name: Test with pytest (unit tests only)
run: >
uv run poe all-tests
uv run poe test -A
-m "not integration"
-n logical --dist worksteal
--timeout=120 --session-timeout=900 --timeout_method thread
--retries 2 --retry-delay 5
working-directory: ./python
@@ -129,9 +141,10 @@ jobs:
runs-on: ubuntu-latest
environment: integration
env:
OPENAI_CHAT_MODEL_ID: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_RESPONSES_MODEL_ID: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_EMBEDDINGS_MODEL_ID: ${{ vars.OPENAI_EMBEDDING_MODEL_ID }}
OPENAI_CHAT_MODEL: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_RESPONSES_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_EMBEDDING_MODEL: ${{ vars.OPENAI_EMBEDDING_MODEL_ID }}
OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
defaults:
run:
@@ -147,8 +160,8 @@ jobs:
- name: Test with pytest (OpenAI integration)
run: >
uv run pytest --import-mode=importlib
packages/core/tests/openai
-m integration
packages/openai/tests
-m "integration and not azure"
-n logical --dist worksteal
--timeout=120 --session-timeout=900 --timeout_method thread
--retries 2 --retry-delay 5
@@ -183,7 +196,8 @@ jobs:
env:
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__EMBEDDINGDEPLOYMENTNAME }}
AZURE_OPENAI_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME: ${{ vars.AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME }}
AZURE_OPENAI_ENDPOINT: ${{ vars.AZUREOPENAI__ENDPOINT }}
defaults:
run:
@@ -206,7 +220,11 @@ jobs:
- name: Test with pytest (Azure OpenAI integration)
run: >
uv run pytest --import-mode=importlib
packages/core/tests/azure
packages/openai/tests/openai/test_openai_chat_completion_client_azure.py
packages/openai/tests/openai/test_openai_chat_client_azure.py
packages/openai/tests/openai/test_openai_embedding_client_azure.py
packages/azure-ai/tests/azure_openai
--ignore=packages/azure-ai/tests/azure_openai/test_azure_responses_client_foundry.py
-m integration
-n logical --dist worksteal
--timeout=120 --session-timeout=900 --timeout_method thread
@@ -254,6 +272,13 @@ jobs:
with:
python-version: ${{ env.UV_PYTHON }}
os: ${{ runner.os }}
- name: Start local MCP server
id: local-mcp
uses: ./.github/actions/setup-local-mcp-server
with:
fallback_url: ${{ env.LOCAL_MCP_URL }}
- name: Prefer local MCP URL when available
run: echo "LOCAL_MCP_URL=${{ steps.local-mcp.outputs.effective_url }}" >> "$GITHUB_ENV"
- name: Test with pytest (Anthropic, Ollama, MCP integration)
run: >
uv run pytest --import-mode=importlib
@@ -265,6 +290,26 @@ jobs:
--timeout=120 --session-timeout=900 --timeout_method thread
--retries 2 --retry-delay 5
working-directory: ./python
- name: Stop local MCP server
if: always()
shell: bash
run: |
set -euo pipefail
server_pid="${{ steps.local-mcp.outputs.pid }}"
if [[ -z "$server_pid" ]]; then
exit 0
fi
if ! kill -0 "$server_pid" 2>/dev/null; then
exit 0
fi
kill -TERM -- "-$server_pid" 2>/dev/null || kill -TERM "$server_pid" 2>/dev/null || true
for _ in $(seq 1 10); do
if ! kill -0 "$server_pid" 2>/dev/null; then
exit 0
fi
sleep 1
done
kill -KILL -- "-$server_pid" 2>/dev/null || kill -KILL "$server_pid" 2>/dev/null || true
- name: Surface failing tests
if: always()
uses: pmeier/pytest-results-action@v0.7.2
@@ -289,12 +334,16 @@ jobs:
environment: integration
env:
UV_PYTHON: "3.11"
OPENAI_CHAT_MODEL_ID: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_RESPONSES_MODEL_ID: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_CHAT_MODEL: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_RESPONSES_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_EMBEDDING_MODEL: ${{ vars.OPENAI_EMBEDDING_MODEL_ID }}
OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
AZURE_OPENAI_ENDPOINT: ${{ vars.AZUREOPENAI__ENDPOINT }}
AZURE_OPENAI_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
FOUNDRY_PROJECT_ENDPOINT: ${{ vars.FOUNDRY_PROJECT_ENDPOINT }}
FOUNDRY_MODEL: ${{ vars.FOUNDRY_MODEL }}
FUNCTIONS_WORKER_RUNTIME: "python"
DURABLE_TASK_SCHEDULER_CONNECTION_STRING: "Endpoint=http://localhost:8080;TaskHub=default;Authentication=None"
AzureWebJobsStorage: "UseDevelopmentStorage=true"
@@ -326,7 +375,8 @@ jobs:
packages/durabletask/tests/integration_tests
-m integration
-n logical --dist worksteal
--timeout=120 --session-timeout=900 --timeout_method thread
-x
--timeout=360 --session-timeout=900 --timeout_method thread
--retries 2 --retry-delay 5
working-directory: ./python
- name: Surface failing tests
@@ -339,8 +389,8 @@ jobs:
fail-on-empty: false
title: Functions integration test results
python-tests-azure-ai:
name: Python Tests - Azure AI
python-tests-foundry:
name: Python Integration Tests - Foundry
needs: paths-filter
if: >
github.event_name != 'pull_request' &&
@@ -353,6 +403,10 @@ jobs:
env:
AZURE_AI_PROJECT_ENDPOINT: ${{ secrets.AZUREAI__ENDPOINT }}
AZURE_AI_MODEL_DEPLOYMENT_NAME: ${{ vars.AZUREAI__DEPLOYMENTNAME }}
FOUNDRY_PROJECT_ENDPOINT: ${{ vars.FOUNDRY_PROJECT_ENDPOINT }}
FOUNDRY_MODEL: ${{ vars.FOUNDRY_MODEL }}
FOUNDRY_AGENT_NAME: ${{ vars.FOUNDRY_AGENT_NAME }}
FOUNDRY_AGENT_VERSION: ${{ vars.FOUNDRY_AGENT_VERSION }}
LOCAL_MCP_URL: ${{ vars.LOCAL_MCP__URL }}
defaults:
run:
@@ -374,7 +428,14 @@ jobs:
subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
- name: Test with pytest
timeout-minutes: 15
run: uv run --directory packages/azure-ai poe integration-tests -n logical --dist worksteal --timeout=120 --session-timeout=900 --timeout_method thread --retries 2 --retry-delay 5
run: >
uv run pytest --import-mode=importlib
packages/azure-ai/tests/azure_openai/test_azure_responses_client_foundry.py
packages/foundry/tests
-m integration
-n logical --dist worksteal
--timeout=120 --session-timeout=900 --timeout_method thread
--retries 2 --retry-delay 5
working-directory: ./python
- name: Test Azure AI samples
timeout-minutes: 10
@@ -461,7 +522,7 @@ jobs:
python-tests-azure-openai,
python-tests-misc-integration,
python-tests-functions,
python-tests-azure-ai,
python-tests-foundry,
python-tests-cosmos,
]
steps:
+532 -17
View File
@@ -41,16 +41,23 @@ jobs:
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Create .env for samples
run: |
echo "AZURE_AI_PROJECT_ENDPOINT=$AZURE_AI_PROJECT_ENDPOINT" >> .env
echo "AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME=$AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME" >> .env
echo "AZURE_OPENAI_ENDPOINT=$AZURE_OPENAI_ENDPOINT" >> .env
echo "AZURE_OPENAI_CHAT_DEPLOYMENT_NAME=$AZURE_OPENAI_CHAT_DEPLOYMENT_NAME" >> .env
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir 01-get-started --save-report --report-name 01-get-started
- name: Upload validation report
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-01-get-started
path: python/scripts/sample_validation/reports/
path: python/samples/sample_validation/reports/
validate-02-agents:
name: Validate 02-agents
@@ -64,10 +71,14 @@ jobs:
AZURE_OPENAI_ENDPOINT: ${{ vars.AZUREOPENAI__ENDPOINT }}
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__EMBEDDINGDEPLOYMENTNAME }}
# OpenAI configuration
OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
OPENAI_CHAT_MODEL_ID: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_RESPONSES_MODEL_ID: ${{ vars.OPENAI__RESPONSESMODELID }}
# GitHub MCP
GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
# Observability
ENABLE_INSTRUMENTATION: "true"
defaults:
@@ -84,16 +95,420 @@ jobs:
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Create .env for samples
run: |
echo "AZURE_AI_PROJECT_ENDPOINT=$AZURE_AI_PROJECT_ENDPOINT" >> .env
echo "AZURE_AI_MODEL_DEPLOYMENT_NAME=$AZURE_AI_MODEL_DEPLOYMENT_NAME" >> .env
echo "AZURE_OPENAI_ENDPOINT=$AZURE_OPENAI_ENDPOINT" >> .env
echo "AZURE_OPENAI_CHAT_DEPLOYMENT_NAME=$AZURE_OPENAI_CHAT_DEPLOYMENT_NAME" >> .env
echo "AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME=$AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME" >> .env
echo "AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME=$AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME" >> .env
echo "OPENAI_API_KEY=$OPENAI_API_KEY" >> .env
echo "OPENAI_CHAT_MODEL_ID=$OPENAI_CHAT_MODEL_ID" >> .env
echo "OPENAI_RESPONSES_MODEL_ID=$OPENAI_RESPONSES_MODEL_ID" >> .env
echo "GITHUB_PAT=$GITHUB_PAT" >> .env
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir 02-agents --save-report --report-name 02-agents
cd scripts && uv run python -m sample_validation --subdir 02-agents --exclude providers --save-report --report-name 02-agents
- name: Upload validation report
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-02-agents
path: python/scripts/sample_validation/reports/
path: python/samples/sample_validation/reports/
validate-02-agents-openai:
name: Validate 02-agents/providers/openai
runs-on: ubuntu-latest
environment: integration
env:
OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
OPENAI_CHAT_MODEL_ID: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_RESPONSES_MODEL_ID: ${{ vars.OPENAI__RESPONSESMODELID }}
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Setup environment
uses: ./.github/actions/sample-validation-setup
with:
azure-client-id: ${{ secrets.AZURE_CLIENT_ID }}
azure-tenant-id: ${{ secrets.AZURE_TENANT_ID }}
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Create .env for samples
run: |
echo "OPENAI_API_KEY=$OPENAI_API_KEY" >> .env
echo "OPENAI_CHAT_MODEL_ID=$OPENAI_CHAT_MODEL_ID" >> .env
echo "OPENAI_RESPONSES_MODEL_ID=$OPENAI_RESPONSES_MODEL_ID" >> .env
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/openai --save-report --report-name 02-agents-openai
- name: Upload validation report
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-02-agents-openai
path: python/samples/sample_validation/reports/
validate-02-agents-azure-openai:
name: Validate 02-agents/providers/azure_openai
runs-on: ubuntu-latest
environment: integration
env:
AZURE_AI_PROJECT_ENDPOINT: ${{ vars.AZURE_AI_PROJECT_ENDPOINT }}
AZURE_OPENAI_ENDPOINT: ${{ vars.AZUREOPENAI__ENDPOINT }}
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Setup environment
uses: ./.github/actions/sample-validation-setup
with:
azure-client-id: ${{ secrets.AZURE_CLIENT_ID }}
azure-tenant-id: ${{ secrets.AZURE_TENANT_ID }}
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Create .env for samples
run: |
echo "AZURE_AI_PROJECT_ENDPOINT=$AZURE_AI_PROJECT_ENDPOINT" >> .env
echo "AZURE_OPENAI_ENDPOINT=$AZURE_OPENAI_ENDPOINT" >> .env
echo "AZURE_OPENAI_CHAT_DEPLOYMENT_NAME=$AZURE_OPENAI_CHAT_DEPLOYMENT_NAME" >> .env
echo "AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME=$AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME" >> .env
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/azure_openai --save-report --report-name 02-agents-azure-openai
- name: Upload validation report
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-02-agents-azure-openai
path: python/samples/sample_validation/reports/
validate-02-agents-azure-ai:
name: Validate 02-agents/providers/azure_ai
runs-on: ubuntu-latest
environment: integration
env:
AZURE_AI_PROJECT_ENDPOINT: ${{ vars.AZURE_AI_PROJECT_ENDPOINT }}
AZURE_AI_MODEL_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
AZURE_AI_CHAT_MODEL_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
AZURE_AI_EMBEDDING_MODEL_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__EMBEDDINGDEPLOYMENTNAME }}
BING_CONNECTION_ID: ${{ secrets.BING_CONNECTION_ID }}
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Setup environment
uses: ./.github/actions/sample-validation-setup
with:
azure-client-id: ${{ secrets.AZURE_CLIENT_ID }}
azure-tenant-id: ${{ secrets.AZURE_TENANT_ID }}
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Create .env for samples
run: |
echo "AZURE_AI_PROJECT_ENDPOINT=$AZURE_AI_PROJECT_ENDPOINT" >> .env
echo "AZURE_AI_MODEL_DEPLOYMENT_NAME=$AZURE_AI_MODEL_DEPLOYMENT_NAME" >> .env
echo "AZURE_AI_CHAT_MODEL_DEPLOYMENT_NAME=$AZURE_AI_CHAT_MODEL_DEPLOYMENT_NAME" >> .env
echo "AZURE_AI_EMBEDDING_MODEL_DEPLOYMENT_NAME=$AZURE_AI_EMBEDDING_MODEL_DEPLOYMENT_NAME" >> .env
echo "BING_CONNECTION_ID=$BING_CONNECTION_ID" >> .env
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/azure_ai --save-report --report-name 02-agents-azure-ai
- name: Upload validation report
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-02-agents-azure-ai
path: python/samples/sample_validation/reports/
validate-02-agents-azure-ai-agent:
name: Validate 02-agents/providers/azure_ai_agent
runs-on: ubuntu-latest
environment: integration
env:
AZURE_AI_PROJECT_ENDPOINT: ${{ vars.AZURE_AI_PROJECT_ENDPOINT }}
AZURE_AI_MODEL_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Setup environment
uses: ./.github/actions/sample-validation-setup
with:
azure-client-id: ${{ secrets.AZURE_CLIENT_ID }}
azure-tenant-id: ${{ secrets.AZURE_TENANT_ID }}
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Create .env for samples
run: |
echo "AZURE_AI_PROJECT_ENDPOINT=$AZURE_AI_PROJECT_ENDPOINT" >> .env
echo "AZURE_AI_MODEL_DEPLOYMENT_NAME=$AZURE_AI_MODEL_DEPLOYMENT_NAME" >> .env
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/azure_ai_agent --save-report --report-name 02-agents-azure-ai-agent
- name: Upload validation report
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-02-agents-azure-ai-agent
path: python/samples/sample_validation/reports/
validate-02-agents-anthropic:
name: Validate 02-agents/providers/anthropic
runs-on: ubuntu-latest
environment: integration
env:
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
ANTHROPIC_CHAT_MODEL_ID: ${{ vars.ANTHROPIC_CHAT_MODEL_ID }}
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Setup environment
uses: ./.github/actions/sample-validation-setup
with:
azure-client-id: ${{ secrets.AZURE_CLIENT_ID }}
azure-tenant-id: ${{ secrets.AZURE_TENANT_ID }}
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Create .env for samples
run: |
echo "ANTHROPIC_API_KEY=$ANTHROPIC_API_KEY" >> .env
echo "ANTHROPIC_CHAT_MODEL_ID=$ANTHROPIC_CHAT_MODEL_ID" >> .env
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/anthropic --save-report --report-name 02-agents-anthropic
- name: Upload validation report
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-02-agents-anthropic
path: python/samples/sample_validation/reports/
validate-02-agents-github-copilot:
name: Validate 02-agents/providers/github_copilot
runs-on: ubuntu-latest
environment: integration
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Setup environment
uses: ./.github/actions/sample-validation-setup
with:
azure-client-id: ${{ secrets.AZURE_CLIENT_ID }}
azure-tenant-id: ${{ secrets.AZURE_TENANT_ID }}
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/github_copilot --save-report --report-name 02-agents-github-copilot
- name: Upload validation report
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-02-agents-github-copilot
path: python/samples/sample_validation/reports/
validate-02-agents-amazon:
name: Validate 02-agents/providers/amazon
if: false # Temporarily disabled - requires AWS credentials
runs-on: ubuntu-latest
environment: integration
env:
BEDROCK_CHAT_MODEL_ID: ${{ vars.BEDROCK__CHATMODELID }}
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Setup environment
uses: ./.github/actions/sample-validation-setup
with:
azure-client-id: ${{ secrets.AZURE_CLIENT_ID }}
azure-tenant-id: ${{ secrets.AZURE_TENANT_ID }}
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/amazon --save-report --report-name 02-agents-amazon
- name: Upload validation report
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-02-agents-amazon
path: python/samples/sample_validation/reports/
validate-02-agents-ollama:
name: Validate 02-agents/providers/ollama
if: false # Temporarily disabled - requires local Ollama server
runs-on: ubuntu-latest
environment: integration
env:
OLLAMA_MODEL: ${{ vars.OLLAMA__MODEL }}
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Setup environment
uses: ./.github/actions/sample-validation-setup
with:
azure-client-id: ${{ secrets.AZURE_CLIENT_ID }}
azure-tenant-id: ${{ secrets.AZURE_TENANT_ID }}
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/ollama --save-report --report-name 02-agents-ollama
- name: Upload validation report
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-02-agents-ollama
path: python/samples/sample_validation/reports/
validate-02-agents-foundry-local:
name: Validate 02-agents/providers/foundry_local
if: false # Temporarily disabled - requires local Foundry setup
runs-on: ubuntu-latest
environment: integration
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Setup environment
uses: ./.github/actions/sample-validation-setup
with:
azure-client-id: ${{ secrets.AZURE_CLIENT_ID }}
azure-tenant-id: ${{ secrets.AZURE_TENANT_ID }}
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/foundry_local --save-report --report-name 02-agents-foundry-local
- name: Upload validation report
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-02-agents-foundry-local
path: python/samples/sample_validation/reports/
validate-02-agents-copilotstudio:
name: Validate 02-agents/providers/copilotstudio
if: false # Temporarily disabled - requires Copilot Studio setup
runs-on: ubuntu-latest
environment: integration
env:
COPILOTSTUDIOAGENT__ENVIRONMENTID: ${{ secrets.COPILOTSTUDIOAGENT__ENVIRONMENTID }}
COPILOTSTUDIOAGENT__SCHEMANAME: ${{ secrets.COPILOTSTUDIOAGENT__SCHEMANAME }}
COPILOTSTUDIOAGENT__TENANTID: ${{ secrets.COPILOTSTUDIOAGENT__TENANTID }}
COPILOTSTUDIOAGENT__AGENTAPPID: ${{ secrets.COPILOTSTUDIOAGENT__AGENTAPPID }}
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Setup environment
uses: ./.github/actions/sample-validation-setup
with:
azure-client-id: ${{ secrets.AZURE_CLIENT_ID }}
azure-tenant-id: ${{ secrets.AZURE_TENANT_ID }}
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Create .env for samples
run: |
echo "COPILOTSTUDIOAGENT__ENVIRONMENTID=$COPILOTSTUDIOAGENT__ENVIRONMENTID" >> .env
echo "COPILOTSTUDIOAGENT__SCHEMANAME=$COPILOTSTUDIOAGENT__SCHEMANAME" >> .env
echo "COPILOTSTUDIOAGENT__TENANTID=$COPILOTSTUDIOAGENT__TENANTID" >> .env
echo "COPILOTSTUDIOAGENT__AGENTAPPID=$COPILOTSTUDIOAGENT__AGENTAPPID" >> .env
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/copilotstudio --save-report --report-name 02-agents-copilotstudio
- name: Upload validation report
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-02-agents-copilotstudio
path: python/samples/sample_validation/reports/
validate-02-agents-custom:
name: Validate 02-agents/providers/custom
runs-on: ubuntu-latest
environment: integration
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Setup environment
uses: ./.github/actions/sample-validation-setup
with:
azure-client-id: ${{ secrets.AZURE_CLIENT_ID }}
azure-tenant-id: ${{ secrets.AZURE_TENANT_ID }}
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/custom --save-report --report-name 02-agents-custom
- name: Upload validation report
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-02-agents-custom
path: python/samples/sample_validation/reports/
validate-03-workflows:
name: Validate 03-workflows
@@ -121,20 +536,28 @@ jobs:
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Create .env for samples
run: |
echo "AZURE_AI_PROJECT_ENDPOINT=$AZURE_AI_PROJECT_ENDPOINT" >> .env
echo "AZURE_AI_MODEL_DEPLOYMENT_NAME=$AZURE_AI_MODEL_DEPLOYMENT_NAME" >> .env
echo "AZURE_OPENAI_ENDPOINT=$AZURE_OPENAI_ENDPOINT" >> .env
echo "AZURE_OPENAI_CHAT_DEPLOYMENT_NAME=$AZURE_OPENAI_CHAT_DEPLOYMENT_NAME" >> .env
echo "AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME=$AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME" >> .env
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir 03-workflows --save-report --report-name 03-workflows
- name: Upload validation report
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-03-workflows
path: python/scripts/sample_validation/reports/
path: python/samples/sample_validation/reports/
validate-04-hosting:
name: Validate 04-hosting
if: false # Temporarily disabled because of sample complexity
if: false # Temporarily disabled because of sample complexity
runs-on: ubuntu-latest
environment: integration
env:
@@ -165,15 +588,15 @@ jobs:
cd scripts && uv run python -m sample_validation --subdir 04-hosting --save-report --report-name 04-hosting
- name: Upload validation report
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-04-hosting
path: python/scripts/sample_validation/reports/
path: python/samples/sample_validation/reports/
validate-05-end-to-end:
name: Validate 05-end-to-end
if: false # Temporarily disabled because of sample complexity
if: false # Temporarily disabled because of sample complexity
runs-on: ubuntu-latest
environment: integration
env:
@@ -209,11 +632,11 @@ jobs:
cd scripts && uv run python -m sample_validation --subdir 05-end-to-end --save-report --report-name 05-end-to-end
- name: Upload validation report
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-05-end-to-end
path: python/scripts/sample_validation/reports/
path: python/samples/sample_validation/reports/
validate-autogen-migration:
name: Validate autogen-migration
@@ -230,6 +653,7 @@ jobs:
OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
OPENAI_CHAT_MODEL_ID: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_RESPONSES_MODEL_ID: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
defaults:
run:
working-directory: python
@@ -244,16 +668,26 @@ jobs:
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Create .env for samples
run: |
echo "AZURE_AI_PROJECT_ENDPOINT=$AZURE_AI_PROJECT_ENDPOINT" >> .env
echo "AZURE_AI_MODEL_DEPLOYMENT_NAME=$AZURE_AI_MODEL_DEPLOYMENT_NAME" >> .env
echo "AZURE_OPENAI_ENDPOINT=$AZURE_OPENAI_ENDPOINT" >> .env
echo "AZURE_OPENAI_CHAT_DEPLOYMENT_NAME=$AZURE_OPENAI_CHAT_DEPLOYMENT_NAME" >> .env
echo "OPENAI_API_KEY=$OPENAI_API_KEY" >> .env
echo "OPENAI_CHAT_MODEL_ID=$OPENAI_CHAT_MODEL_ID" >> .env
echo "OPENAI_RESPONSES_MODEL_ID=$OPENAI_RESPONSES_MODEL_ID" >> .env
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir autogen-migration --save-report --report-name autogen-migration
- name: Upload validation report
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-autogen-migration
path: python/scripts/sample_validation/reports/
path: python/samples/sample_validation/reports/
validate-semantic-kernel-migration:
name: Validate semantic-kernel-migration
@@ -271,6 +705,7 @@ jobs:
OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
OPENAI_CHAT_MODEL_ID: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_RESPONSES_MODEL_ID: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
# Copilot Studio
COPILOTSTUDIOAGENT__ENVIRONMENTID: ${{ secrets.COPILOTSTUDIOAGENT__ENVIRONMENTID }}
COPILOTSTUDIOAGENT__SCHEMANAME: ${{ secrets.COPILOTSTUDIOAGENT__SCHEMANAME }}
@@ -290,13 +725,93 @@ jobs:
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Create .env for samples
run: |
echo "AZURE_AI_PROJECT_ENDPOINT=$AZURE_AI_PROJECT_ENDPOINT" >> .env
echo "AZURE_AI_MODEL_DEPLOYMENT_NAME=$AZURE_AI_MODEL_DEPLOYMENT_NAME" >> .env
echo "AZURE_OPENAI_ENDPOINT=$AZURE_OPENAI_ENDPOINT" >> .env
echo "AZURE_OPENAI_CHAT_DEPLOYMENT_NAME=$AZURE_OPENAI_CHAT_DEPLOYMENT_NAME" >> .env
echo "AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME=$AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME" >> .env
echo "OPENAI_API_KEY=$OPENAI_API_KEY" >> .env
echo "OPENAI_CHAT_MODEL_ID=$OPENAI_CHAT_MODEL_ID" >> .env
echo "OPENAI_RESPONSES_MODEL_ID=$OPENAI_RESPONSES_MODEL_ID" >> .env
echo "COPILOTSTUDIOAGENT__ENVIRONMENTID=$COPILOTSTUDIOAGENT__ENVIRONMENTID" >> .env
echo "COPILOTSTUDIOAGENT__SCHEMANAME=$COPILOTSTUDIOAGENT__SCHEMANAME" >> .env
echo "COPILOTSTUDIOAGENT__TENANTID=$COPILOTSTUDIOAGENT__TENANTID" >> .env
echo "COPILOTSTUDIOAGENT__AGENTAPPID=$COPILOTSTUDIOAGENT__AGENTAPPID" >> .env
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir semantic-kernel-migration --save-report --report-name semantic-kernel-migration
- name: Upload validation report
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-semantic-kernel-migration
path: python/scripts/sample_validation/reports/
path: python/samples/sample_validation/reports/
aggregate-results:
name: Aggregate Results
runs-on: ubuntu-latest
if: always()
needs:
- validate-01-get-started
- validate-02-agents
- validate-02-agents-openai
- validate-02-agents-azure-openai
- validate-02-agents-azure-ai
- validate-02-agents-azure-ai-agent
- validate-02-agents-anthropic
- validate-02-agents-github-copilot
- validate-02-agents-amazon
- validate-02-agents-ollama
- validate-02-agents-foundry-local
- validate-02-agents-copilotstudio
- validate-02-agents-custom
- validate-03-workflows
- validate-04-hosting
- validate-05-end-to-end
- validate-autogen-migration
- validate-semantic-kernel-migration
steps:
- uses: actions/checkout@v6
- name: Download all validation reports
uses: actions/download-artifact@v7
with:
pattern: validation-report-*
path: reports/
merge-multiple: true
- name: Restore validation history
id: cache-restore
uses: actions/cache/restore@v4
with:
path: validation-history/
key: validation-history-${{ github.run_id }}
restore-keys: |
validation-history-
- name: Aggregate results and generate trend report
run: |
python3 python/scripts/sample_validation/aggregate.py \
reports/ \
validation-history/history.json \
trend-report.md
- name: Write trend report to job summary
run: cat trend-report.md >> "$GITHUB_STEP_SUMMARY"
- name: Save validation history
uses: actions/cache/save@v4
with:
path: validation-history/
key: validation-history-${{ github.run_id }}
- name: Upload trend report
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-trend-report
path: trend-report.md
@@ -21,7 +21,7 @@ jobs:
steps:
- uses: actions/checkout@v6
- name: Download coverage report
uses: actions/download-artifact@v7
uses: actions/download-artifact@v8
with:
github-token: ${{ secrets.GH_ACTIONS_PR_WRITE }}
run-id: ${{ github.event.workflow_run.id }}
@@ -46,7 +46,7 @@ jobs:
echo "PR_NUMBER=$PR_NUMBER" >> "$GITHUB_ENV"
- name: Pytest coverage comment
id: coverageComment
uses: MishaKav/pytest-coverage-comment@v1.2.0
uses: MishaKav/pytest-coverage-comment@v1.6.0
with:
github-token: ${{ secrets.GH_ACTIONS_PR_WRITE }}
issue-number: ${{ env.PR_NUMBER }}
+3 -3
View File
@@ -32,17 +32,17 @@ jobs:
id: python-setup
uses: ./.github/actions/python-setup
with:
python-version: ${{ matrix.python-version }}
python-version: ${{ env.UV_PYTHON }}
os: ${{ runner.os }}
env:
# Configure a constant location for the uv cache
UV_CACHE_DIR: /tmp/.uv-cache
- name: Run all tests with coverage report
run: uv run poe all-tests-cov --cov-report=xml:python-coverage.xml -q --junitxml=pytest.xml
run: uv run poe test -A -C --cov-report=xml:python-coverage.xml -q --junitxml=pytest.xml
- name: Check coverage threshold
run: python ${{ github.workspace }}/.github/workflows/python-check-coverage.py python-coverage.xml ${{ env.COVERAGE_THRESHOLD }}
- name: Upload coverage report
uses: actions/upload-artifact@v6
uses: actions/upload-artifact@v7
with:
path: |
python/python-coverage.xml
+1 -1
View File
@@ -40,7 +40,7 @@ jobs:
UV_CACHE_DIR: /tmp/.uv-cache
# Unit tests
- name: Run all tests
run: uv run poe all-tests ${{ matrix.python-version == '3.10' && '--ignore-glob=packages/github_copilot/**' || '' }}
run: uv run poe test -A
working-directory: ./python
# Surface failing tests
+49
View File
@@ -0,0 +1,49 @@
name: Stale issue and PR ping
on:
schedule:
- cron: '0 0 * * *' # Midnight UTC daily
workflow_dispatch:
inputs:
days_threshold:
description: 'Days of silence before pinging the author'
required: false
default: '4'
dry_run:
description: 'Log what would be pinged without taking action'
required: false
default: 'false'
type: choice
options:
- 'false'
- 'true'
concurrency:
group: stale-issue-pr-ping
cancel-in-progress: true
jobs:
ping_stale:
name: "Ping stale issues and PRs"
runs-on: ubuntu-latest
permissions:
contents: read
issues: write
pull-requests: write
steps:
- uses: actions/checkout@v6
- uses: actions/setup-python@v5
with:
python-version: '3.13'
- name: Install dependencies
run: pip install PyGithub==2.6.0
- name: Run stale issue/PR ping
run: python .github/scripts/stale_issue_pr_ping.py
env:
GITHUB_TOKEN: ${{ secrets.GH_ACTIONS_PR_WRITE }}
TEAM_SLUG: ${{ secrets.DEVELOPER_TEAM }}
DAYS_THRESHOLD: ${{ github.event.inputs.days_threshold || '4' }}
DRY_RUN: ${{ github.event.inputs.dry_run || 'false' }}
@@ -0,0 +1,815 @@
---
status: accepted
contact: bentho
date: 2026-02-27
deciders: bentho, markwallace-microsoft, westey-m
consulted: Pratyush Mishra, Shivam Shrivastava, Manni Arora (Centrica eval scenario)
informed: Agent Framework team, Foundry Evals team
---
# Agent Evaluation Architecture with Azure AI Foundry Integration
## Context and Problem Statement
Azure AI Foundry provides a rich evaluation service for AI agents — built-in evaluators for agent behavior (task adherence, intent resolution), tool usage (tool call accuracy, tool selection), quality (coherence, fluency, relevance), and safety (violence, self-harm, prohibited actions). Results are viewable in the Foundry portal with dashboards and comparison views.
However, using Foundry Evals with an agent-framework agent today requires significant manual effort. Developers must:
1. Transform agent-framework's `Message`/`Content` types into the OpenAI-style agent message schema that Foundry evaluators expect
2. Map tool definitions from agent-framework's `FunctionTool` format to evaluator-compatible schemas
3. Manually wire up the correct Foundry data source type (`azure_ai_traces`, `jsonl`, `azure_ai_target_completions`, etc.) depending on their scenario
4. Handle App Insights trace ID queries, response ID collection, and eval polling
Additionally, evaluation is a concern that extends beyond any single provider. Developers may want to use local evaluators (LLM-as-judge, regex, keyword matching), third-party evaluation libraries, or multiple providers in combination. The architecture must support this without creating a Foundry-specific lock-in at the API level.
### Functional Requirements for Agent Evaluation
- **Single agents and workflows.** Evaluate both individual agent responses and multi-agent workflow results, with per-agent breakdown to pinpoint underperformance.
- **One-shot and multi-turn conversations.** Capture full conversation trajectories — including tool calls and results — not just final query/response pairs.
- **Conversation factoring.** Support splitting conversations into query/response in multiple ways (last turn, full trajectory, per-turn) because different factorings measure different things.
- **Multiple providers, mix and match.** Run Foundry LLM-as-judge evaluators alongside fast local checks and custom evaluators on the same data, without restructuring code.
- **Third-party extensibility.** Any evaluation library can participate by implementing the `Evaluator` protocol (Python) or `IAgentEvaluator` interface (.NET). No predetermined list of supported libraries — the protocol is intentionally simple (`evaluate(items) → results`) so that wrappers for libraries like DeepEval, RAGAS, or Promptfoo are straightforward to write.
- **Bring your own evaluator.** Creating a custom evaluator should be as simple as writing a function.
- **Evaluate without re-running.** Evaluate existing responses from logs or previous runs without invoking the agent again.
## Decision Drivers
- **Zero-friction evaluation**: Developers should go from "I have an agent" to "I have eval results" with minimal code.
- **Provider-agnostic API**: Core evaluation capabilities must not be tied to any specific provider. Provider configuration should be separate from the evaluation call.
- **Lowest concept count**: Introduce the fewest possible new types, abstractions, and APIs for developers to learn.
- **Leverage existing knowledge**: The framework already knows which agents exist, what tools they have, and what conversations occurred. Evals should use this automatically rather than requiring the developer to re-specify it.
- **Foundry-native results**: When using Foundry, results should be viewable in the Foundry portal with dashboards and comparison views.
- **Progressive disclosure**: Simple scenarios should be near-zero code. Advanced scenarios should build on the same primitives.
- **Cross-language parity**: Design must be implementable in both Python and .NET.
## Considered Options
1. **Provider-specific functions** — Build Foundry-specific helper functions (`evaluate_agent()`, etc.) directly in the Azure package. All eval functions take Foundry connection parameters.
2. **Evaluator protocol with shared orchestration** — Define a provider-agnostic `Evaluator` protocol in the base agent library (`agent_framework` in Python, `Microsoft.Agents.AI` in .NET). Orchestration functions live alongside it. Providers implement the protocol.
3. **Full eval framework** — Build comprehensive eval infrastructure including custom evaluator definitions, scoring profiles, and reporting inside agent-framework.
## Decision Outcome
Proposed option: "Evaluator protocol with shared orchestration", because it delivers the low-friction developer experience, supports multiple providers without API changes, and keeps the concept count low.
### Usage Examples
#### Evaluate an agent
The agent is invoked once per query by default. For statistically meaningful evaluation, provide multiple diverse queries. For measuring **consistency** (does the same query produce reliable results?), use `num_repetitions` to run each query N times independently:
**Python:**
```python
evals = FoundryEvals(
project_client=client,
model_deployment="gpt-4o",
evaluators=[FoundryEvals.RELEVANCE, FoundryEvals.COHERENCE],
)
results = await evaluate_agent(
agent=my_agent,
queries=[
"What's the weather in Seattle?",
"Plan a weekend trip to Portland",
"What restaurants are near Pike Place?",
],
evaluators=evals,
)
for r in results:
r.assert_passed()
```
**C#:**
```csharp
var evals = new FoundryEvals(chatConfiguration, FoundryEvals.Relevance, FoundryEvals.Coherence);
AgentEvaluationResults results = await agent.EvaluateAsync(
new[] {
"What's the weather in Seattle?",
"Plan a weekend trip to Portland",
"What restaurants are near Pike Place?",
},
evals);
results.AssertAllPassed();
```
`evaluate_agent` returns one `EvalResults` per evaluator. Each result contains per-item scores with the evaluated response for auditing:
```
# results[0] (FoundryEvals)
EvalResults(status="completed", passed=3, failed=0, total=3)
items[0]: EvalItemResult(
query="What's the weather in Seattle?",
response="It's currently 72°F and sunny in Seattle.",
scores={"relevance": 5, "coherence": 5})
items[1]: EvalItemResult(
query="Plan a weekend trip to Portland",
response="Here's a 2-day Portland itinerary...",
scores={"relevance": 4, "coherence": 5})
items[2]: EvalItemResult(
query="What restaurants are near Pike Place?",
response="Top restaurants near Pike Place Market: ...",
scores={"relevance": 5, "coherence": 4})
```
#### Measure consistency with repetitions
Run each query multiple times to detect non-deterministic behavior:
**Python:**
```python
results = await evaluate_agent(
agent=my_agent,
queries=["What's the weather in Seattle?"],
evaluators=evals,
num_repetitions=3, # each query runs 3 times independently
)
# results contain 3 items (1 query × 3 repetitions)
```
**C#:**
```csharp
AgentEvaluationResults results = await agent.EvaluateAsync(
new[] { "What's the weather in Seattle?" },
evals,
numRepetitions: 3); // each query runs 3 times independently
// results contain 3 items (1 query × 3 repetitions)
```
#### Evaluate a response you already have
When you already have agent responses, pass them directly to skip re-running the agent. Each query is paired with its corresponding response:
**Python:**
```python
queries = ["What's the weather?", "What's the capital of France?"]
responses = [await agent.run([Message("user", [q])]) for q in queries]
results = await evaluate_agent(
responses=responses,
evaluators=evals,
)
```
**C#:**
```csharp
var queries = new[] { "What's the weather?" };
var responses = new List<AgentResponse>();
foreach (var q in queries)
responses.Add(await agent.RunAsync(new[] { new ChatMessage(ChatRole.User, q) }));
AgentEvaluationResults results = await agent.EvaluateAsync(
responses: responses,
evals);
```
Each `AgentResponse` already contains the conversation (query + response), so the evaluator extracts query/response from the conversation. When you pass `responses` without `queries`, the conversation is the source of truth.
#### Evaluate with conversation split strategies
By default, evaluators see only the last turn (final user message → final assistant response). For multi-turn conversations, you can control how the conversation is factored for evaluation:
**Python:**
```python
results = await evaluate_agent(
agent=agent,
queries=["Plan a 3-day trip to Paris"],
evaluators=evals,
conversation_split=ConversationSplit.FULL, # evaluate entire trajectory
)
# Or per-turn: each user→assistant exchange scored independently
results = await evaluate_agent(
agent=agent,
queries=["Plan a 3-day trip to Paris"],
evaluators=evals,
conversation_split=ConversationSplit.PER_TURN,
)
```
**C#:**
```csharp
// Full conversation as context
AgentEvaluationResults results = await agent.EvaluateAsync(
new[] { "Plan a 3-day trip to Paris" },
evals,
splitter: ConversationSplitters.Full);
// Per-turn splitting
var items = EvalItem.PerTurnItems(conversation); // one EvalItem per user turn
var results = await evals.EvaluateAsync(items);
```
With `PER_TURN`, a 3-turn conversation produces 3 scored items:
```
EvalResults(status="completed", passed=3, failed=0, total=3)
items[0]: query="Plan a 3-day trip to Paris" scores={"relevance": 5}
items[1]: query="What about restaurants?" scores={"relevance": 4}
items[2]: query="Make it budget-friendly" scores={"relevance": 5}
```
#### Evaluate a multi-agent workflow
**Python:**
```python
result = await workflow.run("Plan a trip to Paris")
eval_results = await evaluate_workflow(
workflow=workflow,
workflow_result=result,
evaluators=evals,
)
for r in eval_results:
print(f" overall: {r.passed}/{r.total}")
for name, sub in r.sub_results.items():
print(f" {name}: {sub.passed}/{sub.total}")
```
**C#:**
```csharp
WorkflowRunResult result = await workflow.RunAsync("Plan a trip to Paris");
IReadOnlyList<AgentEvaluationResults> evalResults = await result.EvaluateAsync(evals);
foreach (var r in evalResults)
{
Console.WriteLine($" overall: {r.Passed}/{r.Total}");
foreach (var (name, sub) in r.SubResults)
Console.WriteLine($" {name}: {sub.Passed}/{sub.Total}");
}
```
Workflows return one result per evaluator, with sub-results per agent in the workflow:
```
EvalResults(status="completed", passed=2, failed=0, total=2)
sub_results:
"planner": EvalResults(passed=1, total=1)
"researcher": EvalResults(passed=1, total=1)
```
#### Mix multiple providers
**Python:**
```python
@evaluator
def is_helpful(response: str) -> bool:
return len(response.split()) > 10
foundry = FoundryEvals(
project_client=client,
model_deployment="gpt-4o",
evaluators=[FoundryEvals.RELEVANCE, FoundryEvals.COHERENCE],
)
results = await evaluate_agent(
agent=agent,
queries=queries,
evaluators=[is_helpful, keyword_check("weather"), foundry],
)
```
**C#:**
```csharp
IReadOnlyList<AgentEvaluationResults> results = await agent.EvaluateAsync(
queries,
evaluators: new IAgentEvaluator[]
{
new LocalEvaluator(
EvalChecks.KeywordCheck("weather"),
FunctionEvaluator.Create("is_helpful", (string r) => r.Split(' ').Length > 10)),
new FoundryEvals(chatConfiguration, FoundryEvals.Relevance, FoundryEvals.Coherence),
});
```
Multiple evaluators return one result each — `results[0]` is the local evaluator, `results[1]` is Foundry.
#### Custom function evaluators
**Python:**
```python
@evaluator
def mentions_city(response: str, expected_output: str) -> bool:
return expected_output.lower() in response.lower()
@evaluator
def used_tools(conversation: list, tools: list) -> float:
# ... scoring logic
return score
local = LocalEvaluator(mentions_city, used_tools)
```
`@evaluator` uses **parameter name injection** — the function's parameter names determine what data it receives from the `EvalItem`. Supported names: `query`, `response`, `expected`, `expected_tool_calls`, `conversation`, `tools`, `context`. Any combination is valid.
**C#:**
```csharp
var local = new LocalEvaluator(
FunctionEvaluator.Create("mentions_city",
(EvalItem item) => item.ExpectedOutput != null
&& item.Response.Contains(item.ExpectedOutput, StringComparison.OrdinalIgnoreCase)),
FunctionEvaluator.Create("is_concise",
(string response) => response.Split(' ').Length < 500));
```
## What To Build
### Core: Evaluator Protocol
A runtime-checkable protocol that any evaluation provider implements:
```python
@runtime_checkable
class Evaluator(Protocol):
name: str
async def evaluate(
self, items: Sequence[EvalItem], *, eval_name: str = "Agent Framework Eval"
) -> EvalResults: ...
```
The protocol is minimal — just `name` and `evaluate()`.
### Core: EvalItem
Provider-agnostic data format for items to evaluate:
```python
@dataclass
class ExpectedToolCall:
name: str # Tool/function name
arguments: dict[str, Any] | None = None # None = don't check args
@dataclass
class EvalItem:
conversation: list[Message] # Single source of truth
tools: list[FunctionTool] | None = None # Agent's available tools
context: str | None = None
expected_output: str | None = None # Ground-truth for comparison
expected_tool_calls: list[ExpectedToolCall] | None = None
split_strategy: ConversationSplitter | None = None
query: str # property — derived from conversation split
response: str # property — derived from conversation split
```
`conversation` is the single source of truth. `query` and `response` are derived properties — splitting the conversation at the last user message (default) and extracting text from each side. Changing the `split_strategy` consistently changes all derived values.
`tools` provides typed `FunctionTool` objects — including MCP tools, which are automatically extracted after agent runs.
### Internal: AgentEvalConverter
Internal class that converts agent-framework types to `EvalItem`. Used by `evaluate_agent()` and `evaluate_workflow()` — not part of the public API:
| Agent Framework | Eval Format |
|---|---|
| `Content.function_call` | `tool_call` in OpenAI chat format |
| `Content.function_result` | `tool_result` in OpenAI chat format |
| `FunctionTool` | `{name, description, parameters}` schema |
| `Message` history | `conversation` list + `query`/`response` extraction |
### Core: EvalResults
Rich result type with convenience properties for CI integration:
```python
results.all_passed # bool: no failures or errors (recursive for workflow)
results.passed # int: passing count
results.failed # int: failure count
results.total # int: total = passed + failed + errored
results.items # list[EvalItemResult]: per-item detail with query, response, and scores
results.error # str | None: error details on failure
results.sub_results # dict: per-agent breakdown (workflow evals)
results.report_url # str | None: portal link (Foundry)
results.assert_passed() # raises AssertionError with details
```
### Core: Orchestration Functions
Provider-agnostic functions that extract data and delegate to evaluators:
| Function | What it does |
|---|---|
| `evaluate_agent()` | Runs agent against test queries (or evaluates pre-existing `responses=`), converts to `EvalItem`s, passes to evaluator. Accepts optional `expected_output=` for ground-truth comparison, `expected_tool_calls=` for tool-correctness evaluation, and `num_repetitions=` for consistency measurement |
| `evaluate_workflow()` | Extracts per-agent data from `WorkflowRunResult`, evaluates each agent and overall output. Per-agent breakdown in `sub_results`. Also accepts `num_repetitions=` |
### Core: Conversation Split Strategies
Multi-turn conversations must be split into query (input) and response (output) halves for evaluation. How you split determines *what you're evaluating*:
**Last-turn split** — split at the last user message. Everything up to and including it is the query context; the agent's subsequent actions are the response:
```
conversation: user1 → assistant1 → user2 → assistant2(tool) → tool_result → assistant3
query_messages: [user1, assistant1, user2]
response_messages: [assistant2(tool), tool_result, assistant3]
```
This evaluates: "Given all the context so far, did the agent answer the latest question well?" Best for response quality at a specific point in the conversation.
**Full-conversation split** — the first user message is the query; everything after is the response:
```
query_messages: [user1]
response_messages: [assistant1, user2, assistant2(tool), tool_result, assistant3]
```
This evaluates: "Given the original request, did the entire conversation trajectory serve the user?" Best for task completion and overall conversation quality.
**Per-turn split** — produces N eval items from an N-turn conversation. Each turn is evaluated with its cumulative context:
```
item 1: query = [user1], response = [assistant1]
item 2: query = [user1, assistant1, user2], response = [assistant2(tool), tool_result, assistant3]
```
This evaluates each response independently. Best for fine-grained analysis and pinpointing where a conversation goes wrong.
These factorings produce different scores for the same conversation. The framework ships all three as built-in strategies, defaulting to last-turn. Developers can also provide a custom splitter — a function (Python) or `IConversationSplitter` implementation (.NET) — and override the strategy at the call site or per evaluator.
### Azure AI: FoundryEvals
`Evaluator` implementation backed by Azure AI Foundry:
```python
class FoundryEvals:
def __init__(self, *, project_client=None, openai_client=None,
model_deployment: str, evaluators=None, ...)
async def evaluate(self, items, *, eval_name) -> EvalResults
```
**Smart auto-detection in `evaluate()`:**
- Default evaluators: relevance, coherence, task_adherence
- Auto-adds `tool_call_accuracy` when items have tools/`tool_definitions`
- Filters out tool evaluators for items without tools
### Azure AI: FoundryEvals Constants
```python
from agent_framework_azure_ai import FoundryEvals
evaluators = [FoundryEvals.RELEVANCE, FoundryEvals.TOOL_CALL_ACCURACY]
```
Categories: Agent behavior, Tool usage, Quality, Safety.
### Azure AI: Foundry-Specific Functions
| Function | What it does |
|---|---|
| `evaluate_traces()` | Evaluate from stored response IDs or OTel traces |
| `evaluate_foundry_target()` | Evaluate a Foundry-registered agent or deployment |
### Core: LocalEvaluator and Function Evaluators
`LocalEvaluator` implements the `Evaluator` protocol for fast, API-free evaluation. It runs check functions locally — useful for inner-loop development, CI smoke tests, and combining with cloud-based evaluators.
Built-in checks:
- `keyword_check(*keywords)` — response must contain specified keywords
- `tool_called_check(*tool_names)` — agent must have called specified tools
- `tool_calls_present` — all `expected_tool_calls` names appear in conversation (unordered, extras OK)
- `tool_call_args_match` — expected tool calls match on name + arguments (subset match on args)
Custom function evaluators use `@evaluator` to wrap plain Python functions. The function's **parameter names** determine what data it receives from the `EvalItem`:
```python
from agent_framework import evaluator, LocalEvaluator
# Tier 1: Simple check — just query + response
@evaluator
def is_concise(response: str) -> bool:
return len(response.split()) < 500
# Tier 2: Ground truth — compare against expected output
@evaluator
def mentions_city(response: str, expected_output: str) -> bool:
return expected_output.lower() in response.lower()
# Tier 3: Full context — inspect conversation and tools
@evaluator
def used_tools(conversation: list, tools: list) -> float:
# ... scoring logic
return score
local = LocalEvaluator(is_concise, mentions_city, used_tools)
```
Supported parameters: `query`, `response`, `expected`, `expected_tool_calls`, `conversation`, `tools`, `context`.
Return types: `bool`, `float` (≥0.5 = pass), `dict` with `score` or `passed` key, or `CheckResult`.
Async functions are handled automatically — `@evaluator` detects `async def` and produces the right wrapper.
### Example: GAIA Benchmark
[GAIA](https://huggingface.co/gaia-benchmark) tests real-world multi-step tasks with known expected answers. Each task has a question and a ground-truth answer, with optional file attachments. The framework accommodates GAIA's knobs (difficulty levels, file inputs, multi-step tool use) through the existing `EvalItem` fields:
```python
from datasets import load_dataset
from agent_framework import evaluate_agent, evaluator, LocalEvaluator
gaia = load_dataset("gaia-benchmark/GAIA", "2023_level1", split="test")
@evaluator
def exact_match(response: str, expected_output: str) -> bool:
return expected_output.strip().lower() in response.strip().lower()
# Simple path — evaluate_agent handles running + expected_output stamping
results = await evaluate_agent(
agent=agent,
queries=[task["Question"] for task in gaia],
expected_output=[task["Final answer"] for task in gaia],
evaluators=LocalEvaluator(exact_match),
)
```
### Package Location
- Core types and orchestration: `agent_framework._eval`, `agent_framework._local_eval` (Python), `Microsoft.Agents.AI` (.NET)
- Foundry provider: `agent_framework_azure_ai._foundry_evals` (Python), `Microsoft.Agents.AI.AzureAI` (.NET)
- Azure-AI re-exports core types for convenience (Python)
## Known Limitations
1. **Tool evaluators require query + agent**: Tool evaluators need tool definition schemas. When using these evaluators with `evaluate_agent(responses=...)`, provide `queries=` and pass an agent with tool definitions.
2. **`model_deployment` always required**: Could potentially be inferred from the Foundry project configuration.
## Open Questions
1. **Red teaming non-registered agents**: Requires Foundry API support for callback-based flows.
2. **Datasets with expected outputs**: A dataset abstraction for pre-populating `expected_output` values across eval runs is a natural next step but not yet designed.
3. **Multi-modal evaluation**: The `conversation` field on `EvalItem` already stores full `Message`/`Content` (Python) and `ChatMessage` (.NET) objects, which can represent multi-modal content (images, audio, structured data). Evaluators that accept the full `EvalItem` or `conversation` parameter can access this content today. However, the convenience shortcuts — `query`/`response` string projections and the `FunctionEvaluator` string overloads — are text-only. Multi-modal-aware evaluators should use the full-item path (`Func<EvalItem, CheckResult>` in .NET, `conversation: list` parameter in Python).
## .NET Implementation Design
### Key Difference: MEAI Ecosystem
Unlike Python, the .NET ecosystem already has `Microsoft.Extensions.AI.Evaluation` (v10.3.0) providing:
- `IEvaluator` — per-item evaluation of `(messages, chatResponse) → EvaluationResult`
- `CompositeEvaluator` — combines multiple evaluators
- Quality evaluators — `RelevanceEvaluator`, `CoherenceEvaluator`, `GroundednessEvaluator`
- Safety evaluators — `ContentHarmEvaluator`, `ProtectedMaterialEvaluator`
- Metric types — `NumericMetric`, `BooleanMetric`, `StringMetric`
The .NET integration uses MEAI's `IEvaluator` directly — no new evaluator interface. Our contribution is the **orchestration layer**: extension methods that run agents, extract data, call `IEvaluator` per item, and aggregate results.
### Architecture
```
┌──────────────────────────────────────────────────────────────┐
│ Developer Code │
│ agent.EvaluateAsync(queries, evaluator) │
│ run.EvaluateAsync(evaluator) │
└────────────────┬─────────────────────────────────────────────┘
┌────────────────▼─────────────────────────────────────────────┐
│ Orchestration Layer (Microsoft.Agents.AI) │
│ AgentEvaluationExtensions — runs agents, extracts data, │
│ calls IEvaluator per item, aggregates into │
│ AgentEvaluationResults │
└────────────────┬─────────────────────────────────────────────┘
│ IEvaluator (MEAI)
┌───────────┼────────────┐
│ │ │
┌───▼───-┐ ┌───▼────┐ ┌────▼──────────┐
│ MEAI │ │ Local │ │ Foundry │
│ Quality│ │ Checks │ │ (cloud batch) │
│ Safety │ │ Lambdas│ │ │
└────────┘ └────────┘ └───────────────┘
```
All evaluators implement MEAI's `IEvaluator`. The orchestration layer doesn't need to know which kind — it calls `EvaluateAsync(messages, chatResponse)` per item on all of them. `FoundryEvals` handles batching internally (buffers items, submits once, returns per-item results).
### .NET Core Types
**No new evaluator interface.** Use MEAI's `IEvaluator` directly.
**`AgentEvaluationResults`** — The only new type. Aggregates per-item MEAI `EvaluationResult`s across a batch of queries:
```csharp
public class AgentEvaluationResults
{
public string Provider { get; init; }
public string? ReportUrl { get; init; }
// Per-item — standard MEAI EvaluationResult, unchanged
public IReadOnlyList<EvaluationResult> Items { get; init; }
// Aggregate pass/fail derived from metric interpretations
public int Passed { get; }
public int Failed { get; }
public int Total { get; }
public bool AllPassed { get; }
// Workflow: per-agent breakdown
public IReadOnlyDictionary<string, AgentEvaluationResults>? SubResults { get; init; }
public void AssertAllPassed(string? message = null);
}
```
### .NET Evaluator Implementations
All implement MEAI's `IEvaluator`:
**`LocalEvaluator`** — Runs lambda checks locally, returns `BooleanMetric` per check:
```csharp
var local = new LocalEvaluator(
FunctionEvaluator.Create("is_concise",
(string response) => response.Split().Length < 500),
EvalChecks.KeywordCheck("weather"),
EvalChecks.ToolCalledCheck("get_weather"));
```
**MEAI evaluators** — Used directly, no adapter needed:
```csharp
var quality = new CompositeEvaluator(
new RelevanceEvaluator(),
new CoherenceEvaluator());
```
**`FoundryEvals`** — Implements `IEvaluator` but batches internally. On first call, buffers the item. On the last item (or when explicitly flushed), submits the batch to Foundry and distributes per-item results:
```csharp
var foundry = new FoundryEvals(projectClient, "gpt-4o");
```
### .NET Orchestration: Extension Methods
```csharp
public static class AgentEvaluationExtensions
{
// Evaluate an agent against test queries
public static Task<AgentEvaluationResults> EvaluateAsync(
this AIAgent agent,
IEnumerable<string> queries,
IEvaluator evaluator,
ChatConfiguration? chatConfiguration = null,
IEnumerable<string>? expectedOutput = null,
CancellationToken cancellationToken = default);
// Evaluate pre-existing responses (without re-running the agent)
public static Task<AgentEvaluationResults> EvaluateAsync(
this AIAgent agent,
AgentResponse responses,
IEvaluator evaluator,
IEnumerable<string>? queries = null,
ChatConfiguration? chatConfiguration = null,
IEnumerable<string>? expectedOutput = null,
CancellationToken cancellationToken = default);
// Evaluate with multiple evaluators (one result per evaluator)
public static Task<IReadOnlyList<AgentEvaluationResults>> EvaluateAsync(
this AIAgent agent,
IEnumerable<string> queries,
IEnumerable<IEvaluator> evaluators,
ChatConfiguration? chatConfiguration = null,
IEnumerable<string>? expectedOutput = null,
CancellationToken cancellationToken = default);
// Evaluate a workflow run with per-agent breakdown
public static Task<AgentEvaluationResults> EvaluateAsync(
this Run run,
IEvaluator evaluator,
ChatConfiguration? chatConfiguration = null,
bool includeOverall = true,
bool includePerAgent = true,
CancellationToken cancellationToken = default);
}
```
**Usage:**
```csharp
// MEAI evaluators — just works
var results = await agent.EvaluateAsync(
queries: ["What's the weather?"],
evaluator: new RelevanceEvaluator(),
chatConfiguration: new ChatConfiguration(evalClient));
// Local checks
var results = await agent.EvaluateAsync(
queries: ["What's the weather?"],
evaluator: new LocalEvaluator(
EvalChecks.KeywordCheck("weather")));
// Foundry cloud
var results = await agent.EvaluateAsync(
queries: ["What's the weather?"],
evaluator: new FoundryEvals(projectClient, "gpt-4o"));
// Evaluate existing response (without re-running the agent)
var response = await agent.RunAsync("What's the weather?");
var results = await agent.EvaluateAsync(
responses: response,
queries: ["What's the weather?"],
evaluator: new FoundryEvals(projectClient, "gpt-4o"));
// Mixed — one result per evaluator
var results = await agent.EvaluateAsync(
queries: ["What's the weather?"],
evaluators: [
new LocalEvaluator(EvalChecks.KeywordCheck("weather")),
new RelevanceEvaluator(),
new FoundryEvals(projectClient, "gpt-4o")
],
chatConfiguration: new ChatConfiguration(evalClient));
// Workflow with per-agent breakdown
Run run = await workflowRunner.RunAsync(workflow, "Plan a trip");
var results = await run.EvaluateAsync(
evaluator: new FoundryEvals(projectClient, "gpt-4o"));
```
### .NET Function Evaluators
Typed factory overloads (C# equivalent of Python's `@evaluator`):
```csharp
public static class FunctionEvaluator
{
public static EvalCheck Create(string name, Func<string, bool> check); // response only
public static EvalCheck Create(string name, Func<string, string?, bool> check); // expectedOutput
public static EvalCheck Create(string name, Func<EvalItem, bool> check); // full item
public static EvalCheck Create(string name, Func<EvalItem, CheckResult> check); // full control
public static EvalCheck Create(string name, Func<string, Task<bool>> check); // async
}
```
`EvalItem` is a lightweight record used only by `FunctionEvaluator` and `LocalEvaluator` to pass context to check functions. It is not part of the `IEvaluator` interface:
```csharp
public record ExpectedToolCall(string Name, IReadOnlyDictionary<string, object>? Arguments = null);
public sealed class EvalItem
{
public EvalItem(string query, string response, IReadOnlyList<ChatMessage> conversation);
public string Query { get; }
public string Response { get; }
public IReadOnlyList<ChatMessage> Conversation { get; }
public IReadOnlyList<AITool>? Tools { get; set; }
public string? ExpectedOutput { get; set; }
public IReadOnlyList<ExpectedToolCall>? ExpectedToolCalls { get; set; }
public string? Context { get; set; }
public IConversationSplitter? Splitter { get; set; }
}
```
### Workflow Data Extraction (.NET)
`run.EvaluateAsync()` walks `Run.OutgoingEvents` via LINQ:
1. Pair `ExecutorInvokedEvent` / `ExecutorCompletedEvent` by `ExecutorId`
2. Extract `AgentResponseEvent` for per-agent `ChatResponse`
3. Call `evaluator.EvaluateAsync()` per invocation
4. Group by `ExecutorId` for per-agent `SubResults`
5. Use final workflow output for overall eval
### .NET Package Structure
| Package | Contents |
|---------|----------|
| `Microsoft.Agents.AI` | `IAgentEvaluator`, `AgentEvaluationResults`, `LocalEvaluator`, `FunctionEvaluator`, `EvalChecks`, `EvalItem`, `ExpectedToolCall`, `AgentEvaluationExtensions` |
| `Microsoft.Agents.AI.AzureAI` | `FoundryEvals` (provider + constants) |
### Python ↔ .NET Mapping
| Python | .NET |
|--------|------|
| `Evaluator` protocol | `IAgentEvaluator` (our interface; MEAI provides `IEvaluator` for per-item scoring) |
| `EvalItem` dataclass | `EvalItem` class |
| `EvalResults` | `AgentEvaluationResults` |
| `EvalItemResult` / `EvalScoreResult` | MEAI `EvaluationResult` / `EvaluationMetric` (reused) |
| `LocalEvaluator` | `LocalEvaluator` (implements `IAgentEvaluator`) |
| `@evaluator` | `FunctionEvaluator.Create()` overloads |
| `keyword_check()` / `tool_called_check()` | `EvalChecks.KeywordCheck()` / `EvalChecks.ToolCalledCheck()` |
| `tool_calls_present` / `tool_call_args_match` | (custom `FunctionEvaluator` — same pattern) |
| `ExpectedToolCall` dataclass | `ExpectedToolCall` record |
| `FoundryEvals` | `FoundryEvals` (implements `IAgentEvaluator`, includes evaluator name constants) |
| `evaluate_agent()` | `agent.EvaluateAsync(queries, evaluator)` extension method |
| `evaluate_agent(responses=)` | `agent.EvaluateAsync(responses, evaluator)` extension method |
| `evaluate_workflow()` | `run.EvaluateAsync()` extension method |
## More Information
- [Foundry Evals documentation](https://learn.microsoft.com/azure/ai-foundry/concepts/evaluation-approach-gen-ai) — Azure AI Foundry evaluation overview
+960
View File
@@ -0,0 +1,960 @@
status: proposed
date: 2026-03-23
contact: sergeymenshykh
deciders: rbarreto, westey-m, eavanvalkenburg
---
# Agent Skills: Multi-Source Architecture
## Context and Problem Statement
The Agent Framework needs a skills system that lets agents discover and use domain-specific knowledge, reference documents, and executable scripts. Skills can originate from different sources — filesystem directories (SKILL.md files), inline C# code, or reusable class libraries — and the framework must support all three uniformly while allowing extensibility, composition, and filtering.
## Decision Drivers
- Skills must be definable from multiple sources: filesystem, inline code, reusable classes, etc
- Common abstractions are needed so the provider and builder work uniformly regardless of skill origin
- File-based scripts must support user-defined executors, enabling custom runtimes and languages; code/class-based scripts execute in-process as C# delegates
- Skills must be filterable so consumers can include or exclude specific skills based on defined criteria
- Multiple skill sources must be composable into a single provider
- It must be possible to add custom skill sources (e.g., databases, REST APIs, package registries) by implementing a common abstraction
## Architecture
### Model-Facing Tools
Skills are presented to the model as up to three tools that progressively disclose skill content. The system prompt lists available skill names and descriptions; the model then calls these tools on demand:
- **`load_skill(skillName)`** — returns the full skill body (instructions, listed resources, listed scripts)
- **`read_skill_resource(skillName, resourceName)`** — reads a supplementary resource (file-based or code-defined) associated with a skill
- **`run_skill_script(skillName, scriptName, arguments?)`** — executes a script associated with a skill; only registered when at least one skill contains scripts
Each tool delegates to the corresponding method on the resolved `AgentSkill` — calling `Resource.ReadAsync()` or `Script.RunAsync()` respectively.
If skills have no scripts defined, the `run_skill_script` tool is **not advertised** to the model and instructions related to script execution are **not included** in the default skills instructions.
### Abstract Base Types
The architecture defines four abstract base types that all skill variants implement:
```csharp
public abstract class AgentSkill
{
public abstract AgentSkillFrontmatter Frontmatter { get; }
public abstract string Content { get; }
public abstract IReadOnlyList<AgentSkillResource>? Resources { get; }
public abstract IReadOnlyList<AgentSkillScript>? Scripts { get; }
}
public abstract class AgentSkillResource
{
public string Name { get; }
public string? Description { get; }
public abstract Task<object?> ReadAsync(IServiceProvider? serviceProvider = null, CancellationToken cancellationToken = default);
}
public abstract class AgentSkillScript
{
public string Name { get; }
public string? Description { get; }
public abstract Task<object?> RunAsync(AgentSkill skill, AIFunctionArguments arguments, CancellationToken cancellationToken = default);
}
public abstract class AgentSkillsSource
{
public abstract Task<IList<AgentSkill>> GetSkillsAsync(CancellationToken cancellationToken = default);
}
```
Skill metadata is captured via `AgentSkillFrontmatter`:
```csharp
public sealed class AgentSkillFrontmatter
{
public AgentSkillFrontmatter(string name, string description) { ... }
public string Name { get; }
public string Description { get; }
public string? License { get; set; }
public string? Compatibility { get; set; }
public string? AllowedTools { get; set; }
public AdditionalPropertiesDictionary? Metadata { get; set; }
}
```
The type hierarchy at a glance:
```
AgentSkill (abstract) AgentSkillsSource (abstract)
├── AgentFileSkill ├── AgentFileSkillsSource (public)
└── [Programmatic] ├── AgentInMemorySkillsSource (public)
├── AgentInlineSkill ├── AggregatingAgentSkillsSource (public)
└── AgentClassSkill (abstract) └── DelegatingAgentSkillsSource (abstract, public)
├── FilteringAgentSkillsSource (public)
AgentSkillResource (abstract) ├── CachingAgentSkillsSource (public)
├── AgentFileSkillResource └── DeduplicatingAgentSkillsSource (public)
└── AgentInlineSkillResource
AgentSkillScript (abstract)
├── AgentFileSkillScript
└── AgentInlineSkillScript
```
There are two top-level categories of skills:
1. **File-Based Skills** — discovered from `SKILL.md` files on the filesystem. Resources and scripts are files in subdirectories.
2. **Programmatic Skills** — defined in C# code. These are further divided into:
- **Inline Skills** — built at runtime via the `AgentInlineSkill` class and its fluent API. Ideal for quick, agent-specific skill definitions.
- **Class-Based Skills** — defined as reusable C# classes that subclass `AgentClassSkill`. Ideal for packaging skills as shared libraries or NuGet packages.
Both programmatic skill types use `AgentInlineSkillResource` and `AgentInlineSkillScript` for their resources and scripts. They are typically served by `AgentInMemorySkillsSource`, which accepts any `AgentSkill` and is not limited to programmatic skills.
### File-Based Skills
File-based skills are authored as `SKILL.md` files on disk. Resources and scripts are discovered from corresponding subfolders within the skill directory.
**`AgentFileSkill`** — A filesystem-based skill discovered from a directory containing a `SKILL.md` file. Parsed from YAML frontmatter; content is the raw markdown body. Resources and scripts are discovered from files in corresponding subfolders:
```csharp
public sealed class AgentFileSkill : AgentSkill
{
internal AgentFileSkill(
AgentSkillFrontmatter frontmatter, string content, string path,
IReadOnlyList<AgentSkillResource>? resources = null,
IReadOnlyList<AgentSkillScript>? scripts = null) { ... }
}
```
**`AgentFileSkillResource`** — A file-based skill resource. Reads content from a file on disk relative to the skill directory:
```csharp
internal sealed class AgentFileSkillResource : AgentSkillResource
{
public AgentFileSkillResource(string name, string fullPath) { ... }
public string FullPath { get; }
public override Task<object?> ReadAsync(IServiceProvider? serviceProvider = null, CancellationToken cancellationToken = default)
{
return File.ReadAllTextAsync(FullPath, Encoding.UTF8, cancellationToken);
}
}
```
**`AgentFileSkillScript`** — A file-based skill script that represents a script file on disk. Delegates execution to an external `AgentFileSkillScriptRunner` callback (e.g., runs Python/shell via `Process.Start`). Throws `NotSupportedException` if no executor is configured:
```csharp
public delegate Task<object?> AgentFileSkillScriptRunner(
AgentFileSkill skill, AgentFileSkillScript script,
AIFunctionArguments arguments, CancellationToken cancellationToken);
public sealed class AgentFileSkillScript : AgentSkillScript
{
private readonly AgentFileSkillScriptRunner _executor;
internal AgentFileSkillScript(string name, string fullPath, AgentFileSkillScriptRunner executor)
: base(name) { ... }
public override async Task<object?> RunAsync(AgentSkill skill, AIFunctionArguments arguments, ...)
{
return await _executor(fileSkill, this, arguments, cancellationToken);
}
}
```
The executor can be provided at the **provider level** via `AgentSkillsProviderBuilder.UseFileScriptRunner(executor)` and optionally overridden for a **particular file skill** or for a **set of skills** at the file skill source level, giving fine-grained control over how different scripts are executed.
**`AgentFileSkillsSource`** — A skill source that discovers skills from filesystem directories containing `SKILL.md` files. Recursively scans directories (max 2 levels), validates frontmatter, and enforces path traversal and symlink security checks:
```csharp
public sealed partial class AgentFileSkillsSource : AgentSkillsSource
{
public AgentFileSkillsSource(
IEnumerable<string> skillPaths,
AgentFileSkillScriptRunner scriptRunner,
AgentFileSkillsSourceOptions? options = null,
ILoggerFactory? loggerFactory = null) { ... }
}
```
**`AgentFileSkillsSourceOptions`** — Configuration options for `AgentFileSkillsSource`. Allows customizing the allowed file extensions for resources and scripts without adding constructor parameters:
```csharp
public sealed class AgentFileSkillsSourceOptions
{
public IEnumerable<string>? AllowedResourceExtensions { get; set; }
public IEnumerable<string>? AllowedScriptExtensions { get; set; }
}
```
**Example** — A file-based skill on disk and how it is added to a source:
```
skills/
└── unit-converter/
├── SKILL.md # frontmatter + instructions
├── resources/
│ └── conversion-table.csv # discovered as a resource
└── scripts/
└── convert.py # discovered as a script
```
```csharp
var source = new AgentFileSkillsSource(skillPaths: ["./skills"], scriptRunner: SubprocessScriptRunner.RunAsync);
var provider = new AgentSkillsProvider(source);
AIAgent agent = chatClient.AsAIAgent(new ChatClientAgentOptions
{
AIContextProviders = [provider],
});
```
### Programmatic Skills
Programmatic skills are defined in C# code rather than discovered from the filesystem. There are two kinds: **inline** and **class-based**. Both use `AgentInlineSkillResource` and `AgentInlineSkillScript` for resources and scripts, and are held by a single `AgentInMemorySkillsSource`.
**`AgentInMemorySkillsSource`** — A general-purpose skill source that holds any `AgentSkill` instances in memory. Although commonly used for programmatic skills (`AgentInlineSkill` and `AgentClassSkill`), it accepts any `AgentSkill` subclass and is not restricted to code-defined skills:
```csharp
public sealed class AgentInMemorySkillsSource : AgentSkillsSource
{
public AgentInMemorySkillsSource(
IEnumerable<AgentSkill> skills,
ILoggerFactory? loggerFactory = null) { ... }
}
```
#### Inline Skills
Inline skills are built at runtime via the `AgentInlineSkill` class and its fluent API. They are ideal for quick, agent-specific skill definitions where a full class hierarchy would be overkill.
**`AgentInlineSkill`** — A skill defined entirely in code. Resources can be static values or functions; scripts are always functions. Constructed with name, description, and instructions, then extended with resources and scripts:
```csharp
public sealed class AgentInlineSkill : AgentSkill
{
public AgentInlineSkill(string name, string description, string instructions, string? license = null, string? compatibility = null, ...) { ... }
public AgentInlineSkill(AgentSkillFrontmatter frontmatter, string instructions) { ... }
public AgentInlineSkill AddResource(object value, string name, string? description = null);
public AgentInlineSkill AddResource(Delegate handler, string name, string? description = null);
public AgentInlineSkill AddScript(Delegate handler, string name, string? description = null);
}
```
**`AgentInlineSkillResource`** — A skill resource that wraps a static value:
```csharp
public sealed class AgentInlineSkillResource : AgentSkillResource
{
public AgentInlineSkillResource(object value, string name, string? description = null)
: base(name, description)
{
_value = value;
}
public override Task<object?> ReadAsync(IServiceProvider? serviceProvider = null, CancellationToken cancellationToken = default)
{
return Task.FromResult<object?>(_value);
}
}
```
**`AgentInlineSkillResource`** — A skill resource backed by a delegate. The delegate is invoked via an `AIFunction` each time `ReadAsync` is called, producing a dynamic (computed) value:
```csharp
public sealed class AgentInlineSkillResource : AgentSkillResource
{
public AgentInlineSkillResource(Delegate handler, string name, string? description = null)
: base(name, description)
{
_function = AIFunctionFactory.Create(handler, name: name);
}
public override async Task<object?> ReadAsync(IServiceProvider? serviceProvider = null, CancellationToken cancellationToken = default)
{
return await _function.InvokeAsync(new AIFunctionArguments() { Services = serviceProvider }, cancellationToken);
}
}
```
**`AgentInlineSkillScript`** — A skill script backed by a delegate via an `AIFunction`:
```csharp
public sealed class AgentInlineSkillScript : AgentSkillScript
{
private readonly AIFunction _function;
public AgentInlineSkillScript(Delegate handler, string name, string? description = null)
: base(name, description)
{
_function = AIFunctionFactory.Create(handler, name: name);
}
public JsonElement? ParametersSchema => _function.JsonSchema;
public override async Task<object?> RunAsync(AgentSkill skill, AIFunctionArguments arguments, ...)
{
return await _function.InvokeAsync(arguments, cancellationToken);
}
}
```
**Example** — Creating an inline skill with a resource and script, then adding it to a source:
```csharp
var skill = new AgentInlineSkill(
name: "unit-converter",
description: "Converts between measurement units.",
instructions: """
Use this skill to convert values between metric and imperial units.
Refer to the conversion-table resource for supported unit pairs.
Run the convert script to perform conversions.
"""
)
.AddResource("kg=2.205lb, m=3.281ft, L=0.264gal", "conversion-table", "Supported unit pairs")
.AddScript(Convert, "convert", "Converts a value between units");
var source = new AgentInMemorySkillsSource([skill]);
var provider = new AgentSkillsProvider(source);
AIAgent agent = chatClient.AsAIAgent(new ChatClientAgentOptions
{
AIContextProviders = [provider],
});
static string Convert(double value, double factor)
=> JsonSerializer.Serialize(new { result = Math.Round(value * factor, 4) });
```
#### Class-Based Skills
Class-based skills are designed for packaging skills as reusable libraries. Users subclass `AgentClassSkill` and override properties. Unlike inline skills, class-based skills are self-contained, can live in shared libraries or NuGet packages, and are well-suited for dependency injection.
**`AgentClassSkill`** — An abstract base class for defining skills as reusable C# classes that bundle all skill components (frontmatter, instructions, resources, scripts) together. Designed for packaging skills as distributable libraries:
```csharp
public abstract class AgentClassSkill : AgentSkill
{
public abstract string Instructions { get; }
// Content is auto-synthesized from Frontmatter + Instructions + Resources + Scripts
public override string Content =>
SkillContentBuilder.BuildContent(Frontmatter.Name, Frontmatter.Description,
SkillContentBuilder.BuildBody(Instructions, Resources, Scripts));
}
```
**Example** — Defining a class-based skill and adding it to a source:
```csharp
public class UnitConverterSkill : AgentClassSkill
{
public override AgentSkillFrontmatter Frontmatter { get; } =
new("unit-converter", "Converts between measurement units.");
public override string Instructions => """
Use this skill to convert values between metric and imperial units.
Refer to the conversion-table resource for supported unit pairs.
Run the convert script to perform conversions.
""";
public override IReadOnlyList<AgentSkillResource>? Resources { get; } =
[
new AgentInlineSkillResource("kg=2.205lb, m=3.281ft", "conversion-table"),
];
public override IReadOnlyList<AgentSkillScript>? Scripts { get; } =
[
new AgentInlineSkillScript(Convert, "convert"),
];
private static string Convert(double value, double factor)
=> JsonSerializer.Serialize(new { result = Math.Round(value * factor, 4) });
}
var source = new AgentInMemorySkillsSource([new UnitConverterSkill()]);
var provider = new AgentSkillsProvider(source);
AIAgent agent = chatClient.AsAIAgent(new ChatClientAgentOptions
{
AIContextProviders = [provider],
});
```
## Filtering, Caching, and Deduplication
The following subsections present alternative approaches for handling filtering, caching, and deduplication of skills across multiple sources.
### Via Composition
In this approach, the `AgentSkillsProvider` accepts a **single** `AgentSkillsSource`. Multiple sources are composed externally via an aggregate source, and cross-cutting concerns like filtering, caching, and deduplication are implemented as **source decorators** — subclasses of `DelegatingAgentSkillsSource` that intercept `GetSkillsAsync()`.
**`FilteringAgentSkillsSource`** — A decorator that applies filter logic before returning results. The decorator pattern keeps filtering orthogonal to source implementations and allows composing multiple filters:
```csharp
public sealed class FilteringAgentSkillsSource : DelegatingAgentSkillsSource
{
private readonly Func<AgentSkill, bool> _predicate;
public FilteringAgentSkillsSource(AgentSkillsSource innerSource, Func<AgentSkill, bool> predicate)
: base(innerSource)
{
_predicate = predicate;
}
public override async Task<IList<AgentSkill>> GetSkillsAsync(CancellationToken cancellationToken = default)
{
var skills = await this.InnerSource.GetSkillsAsync(cancellationToken);
return skills.Where(_predicate).ToList();
}
}
```
**`CachingAgentSkillsSource`** — A decorator that caches skills after the first load, keeping the provider stateless and giving consumers control over caching granularity per source. For example, file-based skills (expensive to discover) can be cached while code-defined skills remain uncached:
```csharp
public sealed class CachingAgentSkillsSource : DelegatingAgentSkillsSource
{
private IList<AgentSkill>? _cached;
public CachingAgentSkillsSource(AgentSkillsSource innerSource)
: base(innerSource)
{
}
public override async Task<IList<AgentSkill>> GetSkillsAsync(CancellationToken cancellationToken = default)
{
return _cached ??= await this.InnerSource.GetSkillsAsync(cancellationToken);
}
}
```
**Deduplication** is similarly implemented as a decorator (`DeduplicatingAgentSkillsSource`) that deduplicates by name (case-insensitive, first-one-wins) and logs a warning for skipped duplicates.
**Example** — Combining file-based and code-defined sources with filtering and caching:
```csharp
var fileSource = new CachingAgentSkillsSource(new AgentFileSkillsSource(["./skills"]));
var codeSource = new AgentInMemorySkillsSource([myCodeSkill]);
var compositeSource = new FilteringAgentSkillsSource(
new AggregatingAgentSkillsSource([fileSource, codeSource]),
filter: s => s.Frontmatter.Name != "internal");
var provider = new AgentSkillsProvider(compositeSource);
AIAgent agent = chatClient.AsAIAgent(new ChatClientAgentOptions
{
AIContextProviders = [provider],
});
```
**Pros:**
- Clean single-responsibility: the provider serves skills, sources provide them.
- Caching, filtering, and deduplication are composable as source decorators — each concern is a separate, testable wrapper.
**Cons:**
- DI is less flexible: multiple `AgentSkillsSource` implementations registered in the container cannot be auto-injected into the provider. The consumer must manually compose them via an aggregate source.
- Increased public API surface: requires additional public classes (aggregate source, caching decorators, filtering decorators) that consumers need to learn and use.
### Via AgentSkillsProvider
In this approach, the `AgentSkillsProvider` accepts **`IEnumerable<AgentSkillsSource>`** and handles aggregation, filtering, caching, and deduplication internally.
The provider aggregates skills from all registered sources, deduplicates by name (case-insensitive, first-one-wins), caches the result after the first load, and optionally applies filtering via a predicate on `AgentSkillsProviderOptions`. Duplicate skill names are logged as warnings.
**Example** — Registering multiple sources directly with the provider:
```csharp
// Conceptual example — in practice, use AgentSkillsProviderBuilder
var fileSource = new AgentFileSkillsSource(["./skills"]);
var codeSource = new AgentInMemorySkillsSource([myCodeSkill]);
var provider = new AgentSkillsProvider(
sources: [fileSource, codeSource],
options: new AgentSkillsProviderOptions
{
Filter = s => s.Frontmatter.Name != "internal",
});
AIAgent agent = chatClient.AsAIAgent(new ChatClientAgentOptions
{
AIContextProviders = [provider],
});
```
**Pros:**
- DI-friendly: register multiple `AgentSkillsSource` implementations in the container, and they are all auto-injected into `AgentSkillsProvider` via `IEnumerable<AgentSkillsSource>`.
- Smaller public API surface: no need for aggregate source, caching decorators, or filtering decorator classes — these concerns are handled internally by the provider.
**Cons:**
- The provider takes on multiple responsibilities — aggregation, caching, deduplication, and filtering.
- Less granular caching control: caching is all-or-nothing across sources rather than per-source as with decorators.
- Less extensible: new behaviors (e.g., ordering, TTL expiration) require modifying the provider rather than adding a decorator.
### Builder Pattern
**`AgentSkillsProviderBuilder`** provides a fluent API for composing skills from multiple sources. The builder centralizes configuration — script executors, approval callbacks, prompt templates, and filtering — so consumers don't need to know the underlying source types.
The builder internally decides how to wire up the object graph: it creates the appropriate source instances, applies caching and filtering, and returns a fully configured `AgentSkillsProvider`. This keeps the setup code concise while still allowing fine-grained control when needed.
**Example** — Using the builder to combine multiple source types with configuration:
```csharp
var provider = new AgentSkillsProviderBuilder()
.UseFileSkill("./skills") // file-based source
.UseInlineSkills(codeSkill) // code-defined source
.UseClassSkills(new ClassSkill()) // class-based source
.UseFileScriptRunner(SubprocessScriptRunner.RunAsync) // script runner
.UseScriptApproval() // optional human-in-the-loop
.UsePromptTemplate(customTemplate) // optional prompt customization
.UseFilter(s => s.Frontmatter.Name != "internal") // optional skill filtering
.Build();
AIAgent agent = chatClient.AsAIAgent(new ChatClientAgentOptions
{
AIContextProviders = [provider],
});
```
## Adding a Custom Skill Type
The skills framework is designed for extensibility. While file-based and inline skills cover common
scenarios, you can introduce entirely new skill types by subclassing the four base classes:
| Base class | Purpose |
|-----------------------|-----------------------------------------------------|
| `AgentSkillsSource` | Discovers and loads skills from a particular origin |
| `AgentSkill` | Holds metadata, content, resources, and scripts |
| `AgentSkillResource` | Provides supplementary content to a skill |
| `AgentSkillScript` | Represents an executable action within a skill |
The example below implements a **cloud-based skill type** where skills, resources, and scripts are
all stored in and executed through a remote cloud service (e.g., Azure Blob Storage + Azure Functions).
### Step 1 — Define a custom resource
A `CloudSkillResource` reads resource content from a cloud storage endpoint instead of the local
filesystem:
```csharp
/// <summary>
/// A skill resource backed by a cloud storage endpoint.
/// </summary>
public sealed class CloudSkillResource : AgentSkillResource
{
private readonly HttpClient _httpClient;
public CloudSkillResource(string name, Uri blobUri, HttpClient httpClient, string? description = null)
: base(name, description)
{
BlobUri = blobUri ?? throw new ArgumentNullException(nameof(blobUri));
_httpClient = httpClient ?? throw new ArgumentNullException(nameof(httpClient));
}
/// <summary>
/// Gets the URI of the cloud blob that holds this resource's content.
/// </summary>
public Uri BlobUri { get; }
/// <inheritdoc/>
public override async Task<object?> ReadAsync(
IServiceProvider? serviceProvider = null,
CancellationToken cancellationToken = default)
{
return await _httpClient.GetStringAsync(BlobUri, cancellationToken).ConfigureAwait(false);
}
}
```
### Step 2 — Define a custom script
A `CloudSkillScript` executes a script by calling a cloud function endpoint, passing arguments as
the request body:
```csharp
/// <summary>
/// A skill script executed via a cloud function endpoint.
/// </summary>
public sealed class CloudSkillScript : AgentSkillScript
{
private readonly HttpClient _httpClient;
public CloudSkillScript(string name, Uri functionUri, HttpClient httpClient, string? description = null)
: base(name, description)
{
FunctionUri = functionUri ?? throw new ArgumentNullException(nameof(functionUri));
_httpClient = httpClient ?? throw new ArgumentNullException(nameof(httpClient));
}
/// <summary>
/// Gets the URI of the cloud function that runs this script.
/// </summary>
public Uri FunctionUri { get; }
/// <inheritdoc/>
public override async Task<object?> RunAsync(
AgentSkill skill,
AIFunctionArguments arguments,
CancellationToken cancellationToken = default)
{
var json = JsonSerializer.Serialize(arguments);
using var content = new StringContent(json, Encoding.UTF8, "application/json");
var response = await _httpClient.PostAsync(FunctionUri, content, cancellationToken)
.ConfigureAwait(false);
response.EnsureSuccessStatusCode();
return await response.Content.ReadAsStringAsync(cancellationToken).ConfigureAwait(false);
}
}
```
### Step 3 — Define a custom skill
A `CloudSkill` bundles cloud-specific metadata (e.g., the base endpoint) with the standard skill
shape:
```csharp
/// <summary>
/// An <see cref="AgentSkill"/> whose content, resources, and scripts are stored in a cloud service.
/// </summary>
public sealed class CloudSkill : AgentSkill
{
public CloudSkill(
AgentSkillFrontmatter frontmatter,
string content,
Uri endpoint,
IReadOnlyList<AgentSkillResource>? resources = null,
IReadOnlyList<AgentSkillScript>? scripts = null)
{
Frontmatter = frontmatter ?? throw new ArgumentNullException(nameof(frontmatter));
Content = content ?? throw new ArgumentNullException(nameof(content));
Endpoint = endpoint ?? throw new ArgumentNullException(nameof(endpoint));
Resources = resources;
Scripts = scripts;
}
/// <inheritdoc/>
public override AgentSkillFrontmatter Frontmatter { get; }
/// <inheritdoc/>
public override string Content { get; }
/// <summary>
/// Gets the base cloud endpoint for this skill.
/// </summary>
public Uri Endpoint { get; }
/// <inheritdoc/>
public override IReadOnlyList<AgentSkillResource>? Resources { get; }
/// <inheritdoc/>
public override IReadOnlyList<AgentSkillScript>? Scripts { get; }
}
```
### Step 4 — Define a custom source
A `CloudSkillsSource` discovers skills from a cloud catalog API and constructs `CloudSkill`
instances with their associated resources and scripts:
```csharp
/// <summary>
/// A skill source that discovers and loads skills from a cloud catalog API.
/// </summary>
public sealed class CloudSkillsSource : AgentSkillsSource
{
private readonly Uri _catalogUri;
private readonly HttpClient _httpClient;
public CloudSkillsSource(Uri catalogUri, HttpClient httpClient)
{
_catalogUri = catalogUri ?? throw new ArgumentNullException(nameof(catalogUri));
_httpClient = httpClient ?? throw new ArgumentNullException(nameof(httpClient));
}
/// <inheritdoc/>
public override async Task<IList<AgentSkill>> GetSkillsAsync(
CancellationToken cancellationToken = default)
{
// Fetch the skill catalog from the cloud service.
var json = await _httpClient.GetStringAsync(_catalogUri, cancellationToken)
.ConfigureAwait(false);
var catalog = JsonSerializer.Deserialize<CloudSkillCatalog>(json)!;
var skills = new List<AgentSkill>();
foreach (var entry in catalog.Skills)
{
var frontmatter = new AgentSkillFrontmatter(entry.Name, entry.Description);
// Build cloud-backed resources.
var resources = entry.Resources
.Select(r => new CloudSkillResource(r.Name, r.BlobUri, _httpClient, r.Description))
.ToList<AgentSkillResource>();
// Build cloud-backed scripts.
var scripts = entry.Scripts
.Select(s => new CloudSkillScript(s.Name, s.FunctionUri, _httpClient, s.Description))
.ToList<AgentSkillScript>();
skills.Add(new CloudSkill(frontmatter, entry.Content, entry.Endpoint, resources, scripts));
}
return skills;
}
}
```
### Step 5 — Register with the builder
Use `UseSource` to wire the custom source into the provider:
```csharp
var httpClient = new HttpClient();
var provider = new AgentSkillsProviderBuilder()
.UseSource(new CloudSkillsSource(
new Uri("https://my-service.example.com/skills/catalog"),
httpClient))
// Mix with other source types if needed:
.UseFileSkill("/local/skills", scriptRunner)
.UseInlineSkills(someInlineSkill)
.Build();
```
The `AgentSkillsProvider` handles all skill types uniformly — any combination of file-based, inline,
class-based, and custom skills can coexist in the same provider. Custom skills automatically
participate in the model-facing tools (`load_skill`, `read_skill_resource`, `run_skill_script`),
filtering, deduplication, and caching — no additional integration work is required.
## Script Representation: `AgentSkillScript` vs `AIFunction`
Two approaches were considered for representing executable scripts within skills:
### Option A — Custom `AgentSkillScript` abstract base class (original design)
Scripts are modeled as a custom `AgentSkillScript` abstract class with `Name`, `Description`, and
`RunAsync(AgentSkill, AIFunctionArguments, CancellationToken)`. Concrete implementations:
`AgentInlineSkillScript` (wraps a delegate/`AIFunction`) and `AgentFileSkillScript` (wraps a file path + executor delegate).
```csharp
// Base type
public abstract class AgentSkillScript
{
public string Name { get; }
public string? Description { get; }
public abstract Task<object?> RunAsync(AgentSkill skill, AIFunctionArguments arguments, CancellationToken cancellationToken = default);
}
// AgentSkill exposes scripts as:
public abstract IReadOnlyList<AgentSkillScript>? Scripts { get; }
// Inline script wraps an AIFunction internally
var script = new AgentInlineSkillScript(ConvertUnits, "convert");
// Pre-built AIFunction must be wrapped
var script = new AgentInlineSkillScript(myAIFunction);
// Class-based skill declares scripts as:
public override IReadOnlyList<AgentSkillScript>? Scripts { get; } =
[
new AgentInlineSkillScript(ConvertUnits, "convert"),
];
// Provider executes scripts by passing the owning skill:
await script.RunAsync(skill, arguments, cancellationToken);
```
**Pros:**
- **Explicit skill context at execution time.** `RunAsync` receives the owning `AgentSkill`, so any script can access skill metadata or resources during execution without requiring construction-time wiring.
- **Self-contained abstraction.** A dedicated type communicates clearly that scripts are a skills-framework concept, separate from general-purpose AI functions.
- **Easier extensibility for custom script types.** Third-party implementations can subclass `AgentSkillScript` and access the owning skill in `RunAsync` without special setup.
**Cons:**
- **Wrapper overhead.** `AgentInlineSkillScript` is a thin pass-through around `AIFunction` — it adds a class, a constructor, and an indirection layer for no behavioral difference.
- **Parallel abstraction.** `AgentSkillScript` and `AIFunction` serve overlapping purposes (named callable with arguments), creating two parallel hierarchies for the same concept.
- **Friction for consumers.** Users who already have `AIFunction` instances must wrap them in `AgentInlineSkillScript` to use them as scripts, adding ceremony.
### Option B — Reuse `AIFunction` directly
Scripts are represented as `AIFunction` (from `Microsoft.Extensions.AI`). `AgentSkill.Scripts` returns
`IReadOnlyList<AIFunction>?`. `AgentInlineSkillScript` is eliminated entirely — callers use
`AIFunctionFactory.Create(delegate, name: ...)` or pass `AIFunction` instances directly.
`AgentFileSkillScript` becomes an `AIFunction` subclass that captures its owning `AgentFileSkill` via
an internal back-reference set during construction.
```csharp
// AgentSkill exposes scripts as AIFunction directly:
public abstract IReadOnlyList<AIFunction>? Scripts { get; }
// Inline scripts use AIFunctionFactory — no wrapper class needed
var skill = new AgentInlineSkill("my-skill", "desc", "instructions");
skill.AddScript(ConvertUnits, "convert"); // delegate
skill.AddScript(myAIFunction); // pre-built AIFunction — no wrapping
// Class-based skill declares scripts as:
public override IReadOnlyList<AIFunction>? Scripts { get; } =
[
AIFunctionFactory.Create(ConvertUnits, name: "convert"),
];
// Provider executes scripts via standard AIFunction invocation:
await script.InvokeAsync(arguments, cancellationToken);
// File-based scripts extend AIFunction and capture the owning skill internally:
public sealed class AgentFileSkillScript : AIFunction
{
internal AgentFileSkill? Skill { get; set; } // set by AgentFileSkill constructor
protected override async ValueTask<object?> InvokeCoreAsync(
AIFunctionArguments arguments, CancellationToken cancellationToken)
{
return await _executor(Skill!, this, arguments, cancellationToken);
}
}
```
**Pros:**
- **Fewer types.** Eliminates `AgentSkillScript` and `AgentInlineSkillScript`, reducing the public API surface by two classes.
- **Seamless interop.** Any `AIFunction` — whether from `AIFunctionFactory`, a custom subclass, or an external library — can be used as a skill script with zero wrapping.
- **Consistent with `Microsoft.Extensions.AI` ecosystem.** Scripts share the same type as tool functions used by `IChatClient` and `FunctionInvokingChatClient`, reducing conceptual overhead for developers already familiar with the ecosystem.
**Cons:**
- **No owning-skill context in invocation signature.** `AIFunction.InvokeAsync` does not accept an `AgentSkill` parameter, so `AgentFileSkillScript` must capture its owning skill via an internal setter during construction. This adds a construction-order dependency: the skill must set the back-reference on its scripts.
- **Custom script types lose automatic skill access.** Third-party `AIFunction` subclasses that need the owning skill must implement their own mechanism (e.g., constructor injection, closure capture) instead of receiving it as a method parameter.
- **Semantic overloading.** `AIFunction` now means both "a tool the model can call" and "a script within a skill", which could blur the distinction for framework users.
## Resource Representation: `AgentSkillResource` vs `AIFunction`
Two approaches were considered for representing skill resources (supplementary content such as references, assets, or dynamic data):
### Option A — Custom `AgentSkillResource` abstract base class (original design)
Resources are modeled as a custom `AgentSkillResource` abstract class with `Name`, `Description`, and
`ReadAsync(IServiceProvider?, CancellationToken)`. Concrete implementations:
`AgentInlineSkillResource` (static value, delegate, or `AIFunction` wrapper) and `AgentFileSkillResource` (reads file content from disk).
```csharp
// Base type
public abstract class AgentSkillResource
{
public string Name { get; }
public string? Description { get; }
public abstract Task<object?> ReadAsync(IServiceProvider? serviceProvider = null, CancellationToken cancellationToken = default);
}
// AgentSkill exposes resources as:
public abstract IReadOnlyList<AgentSkillResource>? Resources { get; }
// Static resource
var resource = new AgentInlineSkillResource("static content", "my-resource");
// Dynamic resource (delegate)
var resource = new AgentInlineSkillResource((IServiceProvider sp) => GetData(sp), "my-resource");
// Pre-built AIFunction must be wrapped
var resource = new AgentInlineSkillResource(myAIFunction);
// Class-based skill declares resources as:
public override IReadOnlyList<AgentSkillResource>? Resources { get; } =
[
new AgentInlineSkillResource("# Conversion Tables\n...", "conversion-table"),
];
// Provider reads resources via:
await resource.ReadAsync(serviceProvider, cancellationToken);
```
**Pros:**
- **Clear semantic distinction.** A dedicated `AgentSkillResource` type distinguishes resources (data providers) from scripts (executable actions), making the API self-documenting.
- **Purpose-built API.** `ReadAsync` communicates intent better than `InvokeAsync` for a data-access operation.
**Cons:**
- **Wrapper overhead.** `AgentInlineSkillResource` wraps `AIFunction` internally for delegate/function cases — adding a class and indirection for no behavioral difference.
- **Parallel abstraction.** `AgentSkillResource` and `AIFunction` serve overlapping purposes (named callable that returns data), creating two parallel hierarchies.
- **Friction for consumers.** Users who already have `AIFunction` instances must wrap them in `AgentInlineSkillResource`, adding ceremony.
### Option B — Reuse `AIFunction` directly
Resources are represented as `AIFunction`. `AgentSkill.Resources` returns `IReadOnlyList<AIFunction>?`.
`AgentInlineSkillResource` becomes an `AIFunction` subclass (retained as a convenience for the static-value
pattern: `new AgentInlineSkillResource("data", "name")`). `AgentFileSkillResource` becomes an `AIFunction`
subclass that reads file content.
```csharp
// AgentSkill exposes resources as AIFunction directly:
public abstract IReadOnlyList<AIFunction>? Resources { get; }
// Static resource — AgentInlineSkillResource is retained as a convenience AIFunction subclass
var resource = new AgentInlineSkillResource("static content", "my-resource");
// Dynamic resource — AgentInlineSkillResource wraps delegate as AIFunction
var resource = new AgentInlineSkillResource((IServiceProvider sp) => GetData(sp), "my-resource");
// Pre-built AIFunction can be used directly — no wrapping needed
skill.AddResource(myAIFunction);
// Class-based skill declares resources as:
public override IReadOnlyList<AIFunction>? Resources { get; } =
[
new AgentInlineSkillResource("# Conversion Tables\n...", "conversion-table"),
];
// Provider reads resources via standard AIFunction invocation:
await resource.InvokeAsync(arguments, cancellationToken);
// File-based resources extend AIFunction directly:
internal sealed class AgentFileSkillResource : AIFunction
{
public string FullPath { get; }
protected override async ValueTask<object?> InvokeCoreAsync(
AIFunctionArguments arguments, CancellationToken cancellationToken)
{
return await File.ReadAllTextAsync(FullPath, Encoding.UTF8, cancellationToken);
}
}
```
**Pros:**
- **Fewer base types.** Eliminates the `AgentSkillResource` abstract class, reducing the public API surface.
- **Seamless interop.** Any `AIFunction` can be used as a skill resource with zero wrapping.
**Cons:**
- **Loss of semantic distinction.** Resources and scripts are now both `AIFunction`, which could make it less obvious which list a function belongs to when reading code.
- **Static values require a wrapper.** Unlike the original `ReadAsync` which could return a stored value directly, `AIFunction.InvokeAsync` implies invocation. `AgentInlineSkillResource` is retained as a convenience subclass to handle the static-value case, so this is not eliminated — just moved to a different class.
## Decision Outcome
### 1. Keep `AgentSkillResource` and `AgentSkillScript` (Option A for both sections)
We are staying with the custom `AgentSkillResource` and `AgentSkillScript` model classes instead of reusing `AIFunction`:
- **Resources have no parameters.** If a consumer provides an `AIFunction` with parameters, those parameters will never be advertised to the LLM, and the resulting call will fail.
- **Approval breaks for `AIFunction`-based representations.** When a resource or script represented by an `AIFunction` is configured with approval, the second approval invocation will not work correctly.
- **Injecting the owning skill into an `AIFunction`-based script is problematic.** Constructor injection would introduce a circular reference between the skill and the script. An internal property setter is possible but adds coupling.
### 2. Make all agent skill classes internal
All agent-skill-related classes are made `internal` to minimize the public API surface while the feature matures. We can reconsider and promote types to `public` later based on community signal.
This leaves two public entry points:
- **`AgentSkillsProvider`** — use directly when all skills come from a single source and filtering is not needed.
- **`AgentSkillsProviderBuilder`** — use when mixing skill types or when filtering support is required.
### 3. Caching at provider level
Caching of tools and instructions is implemented inside `AgentSkillsProvider` rather than as an external decorator. Recreating tools and instructions on every provider call is wasteful, and a caching decorator sitting outside the provider would not have the information needed to cache them effectively.
@@ -0,0 +1,72 @@
---
status: accepted
contact: eavanvalkenburg
date: 2026-03-20
deciders: eavanvalkenburg, sphenry, chetantoshnival
consulted: taochenosu, moonbox3, dmytrostruk, giles17, alliscode
---
# Provider-Leading Client Design & OpenAI Package Extraction
## Context and Problem Statement
The `agent-framework-core` package currently bundles OpenAI and Azure OpenAI client implementations along with their dependencies (`openai`, `azure-identity`, `azure-ai-projects`, `packaging`). This makes core heavier than necessary for users who don't use OpenAI, and it conflates the core abstractions with a specific provider implementation. Additionally, the current class naming (`OpenAIResponsesClient`, `OpenAIChatClient`) is based on the underlying OpenAI API names rather than what users actually want to do, making discoverability harder for newcomers.
## Decision Drivers
- **Lightweight core**: Core should only contain abstractions, middleware infrastructure, and telemetry — no provider-specific code or dependencies.
- **Discoverability-first**: Import namespaces should guide users to the right client. `from agent_framework.openai import ...` should surface all OpenAI-related clients; `from agent_framework.azure import ...` should surface Foundry, Azure AI, and other Azure-specific classes.
- **Provider-leading naming**: The primary client name should reflect the provider, not the underlying API. The Responses API is now the recommended default for OpenAI, so its client should be called `OpenAIChatClient` (not `OpenAIResponsesClient`).
- **Clean separation of concerns**: Azure-specific deprecated wrappers belong in the azure-ai package, not in the OpenAI package.
## Considered Options
- **Keep OpenAI in core**: Simpler but keeps core heavy; doesn't help discoverability.
- **Extract OpenAI with Azure wrappers in the OpenAI package**: Keeps Azure OpenAI wrappers alongside OpenAI code, but pollutes the OpenAI package with Azure concerns.
- **Extract OpenAI, place Azure wrappers in azure-ai**: Clean separation; the OpenAI package has zero Azure dependencies; deprecated Azure wrappers live in a single file in azure-ai for easy future deletion.
## Decision Outcome
Chosen option: "Extract OpenAI, place Azure wrappers in azure-ai", because it achieves the lightest core, cleanest OpenAI package, and the most maintainable deprecation path.
Key changes:
1. **New `agent-framework-openai` package** with dependencies on `agent-framework-core`, `openai`, and `packaging` only.
2. **Class renames**: `OpenAIResponsesClient``OpenAIChatClient` (Responses API), `OpenAIChatClient``OpenAIChatCompletionClient` (Chat Completions API). Old names remain as deprecated aliases.
3. **Deprecated classes**: `OpenAIAssistantsClient`, all `AzureOpenAI*Client` classes, `AzureAIClient`, `AzureAIAgentClient`, and `AzureAIProjectAgentProvider` are marked deprecated.
4. **New `FoundryChatClient`** in azure-ai for Azure AI Foundry Responses API access, built on `RawFoundryChatClient(RawOpenAIChatClient)`.
5. **All deprecated `AzureOpenAI*` classes** consolidated into a single file (`_deprecated_azure_openai.py`) in the azure-ai package for clean future deletion.
6. **Core's `agent_framework.openai` and `agent_framework.azure` namespaces** become lazy-loading gateways, preserving backward-compatible import paths while removing hard dependencies.
7. **Unified `model` parameter** replaces `model_id` (OpenAI), `deployment_name` (Azure OpenAI), and `model_deployment_name` (Azure AI) across all client constructors. The term `model` is intentionally generic: it naturally maps to an OpenAI model name *and* to an Azure OpenAI deployment name, making it straightforward to use `OpenAIChatClient` with either OpenAI or Azure OpenAI backends (via `AsyncAzureOpenAI`). Environment variables are similarly unified (e.g., `OPENAI_MODEL` instead of separate `OPENAI_RESPONSES_MODEL_ID` / `OPENAI_CHAT_MODEL_ID`).
8. **`FoundryAgent`** replaces the pattern of `Agent(client=AzureAIClient(...))` for connecting to pre-configured agents in Azure AI Foundry (PromptAgents and HostedAgents). The underlying `RawFoundryAgentChatClient` is an implementation detail — most users interact only with `FoundryAgent`. `AzureAIAgentClient` is separately deprecated as it refers to the V1 Agents Service API. See below for design rationale.
### Foundry Agent Design: `FoundryAgentClient` vs `FoundryAgent`
The existing `AzureAIClient` combines two concerns: CRUD lifecycle management (creating/deleting agents on the service) and runtime communication (sending messages via the Responses API). The new design removes CRUD entirely — users connect to agents that already exist in Foundry.
**Two approaches were considered:**
**Option A — `FoundryAgentClient` only (public ChatClient):**
Users compose `Agent(client=FoundryAgentClient(...), tools=[...])`. This follows the universal `Agent(client=X)` pattern used by every other provider. However, a "client" that wraps a named remote agent (with `agent_name` as a constructor param) is semantically odd — clients typically wrap a model endpoint, not a specific agent.
**Option B — `FoundryAgent` (Agent subclass) + private `_FoundryAgentChatClient` and public `RawFoundryAgentChatClient`:**
Users write `FoundryAgent(agent_name="my-agent", ...)` for the common case. Internally, `FoundryAgent` creates a `_FoundryAgentChatClient` and passes it to the standard `Agent` base class. For advanced customization, users pass `client_type=RawFoundryAgentChatClient` (or a custom subclass) to control the client middleware layers. The `Agent(client=RawFoundryAgentChatClient(...))` composition pattern still works for users who prefer it.
**Chosen option: Option B**, because:
- The common case (`FoundryAgent(...)`) is a single object with no boilerplate.
- `client_type=` gives full control over client middleware without parameter duplication — the agent forwards connection params to the client internally.
- `RawFoundryAgent(RawAgent)` and `FoundryAgent(Agent)` mirror the established `RawAgent`/`Agent` pattern.
- Runtime validation (only `FunctionTool` allowed) lives in `RawFoundryAgentChatClient._prepare_options`, ensuring it applies regardless of how the client is used — through `FoundryAgent`, `Agent(client=...)`, or any custom composition.
**Public classes:**
- `RawFoundryAgentChatClient(RawOpenAIChatClient)` — Responses API client that injects agent reference and validates tools. Extension point for custom client middleware.
- `RawFoundryAgent(RawAgent)` — Agent without agent-level middleware/telemetry.
- `FoundryAgent(AgentTelemetryLayer, AgentMiddlewareLayer, RawFoundryAgent)` — Recommended production agent.
**Internal (private):**
- `_FoundryAgentChatClient` — Full client with function invocation, chat middleware, and telemetry layers. Created automatically by `FoundryAgent`; users customize via `client_type=RawFoundryAgentChatClient` or a custom subclass.
**Deprecated:**
- `AzureAIClient` — replaced by `FoundryAgent` (which uses `FoundryAgentClient` internally).
- `AzureAIAgentClient` — refers to V1 Agents Service API, no direct replacement.
- `AzureAIProjectAgentProvider` — replaced by `FoundryAgent`.
@@ -0,0 +1,116 @@
---
status: accepted
contact: westey-m
date: 2026-03-23
deciders: sergeymenshykh, markwallace, rbarreto, dmytrostruk, westey-m, eavanvalkenburg, stephentoub
consulted:
informed:
---
# Chat History Persistence Consistency
## Context and Problem Statement
When using `ChatClientAgent` with tools, the `FunctionInvokingChatClient` (FIC) loops multiple times — service call → tool execution → service call → … — before producing a final response. There are two points of discrepancy between how chat history is stored by the framework's `ChatHistoryProvider` and how the underlying AI service stores chat history (e.g., OpenAI Responses with `store=true`):
1. **Persistence timing**: The AI service persists messages after *each* service call within the FIC loop. The `ChatHistoryProvider` currently persists messages only once, at the *end* of the full agent run (after all FIC loop iterations complete).
2. **Trailing `FunctionResultContent` storage**: When tool calling is terminated mid-loop (e.g., via `FunctionInvokingChatClient` termination filters), the final response from the agent may contain `FunctionResultContent` that was never sent to a subsequent service call. The AI service never stores this trailing `FunctionResultContent`, but the `ChatHistoryProvider` currently stores all response content, including the trailing `FunctionResultContent`.
These discrepancies mean that a `ChatHistoryProvider`-managed conversation and a service-managed conversation can diverge in content and structure, even when processing the same interactions.
### Practical Impact: Resuming After Tool-Call Termination
Today, users of `AIAgent` get different behaviors depending on whether chat history is stored service-side or in a `ChatHistoryProvider`. This creates concrete challenges — for example, when the function call loop is terminated and the user wants to resume the conversation in a subsequent run. With service-stored history, the trailing `FunctionResultContent` is never persisted, so the last stored message is the `FunctionCallContent` from the service. With `ChatHistoryProvider`-stored history, the trailing `FunctionResultContent` *is* persisted. The user cannot know whether the last `FunctionResultContent` is in the chat history or not without inspecting the storage mechanism, making it difficult to write resumption logic that works correctly regardless of the storage backend.
### Relationship Between the Two Discrepancies
The persistence timing and `FunctionResultContent` trimming behaviors are interrelated:
- **Per-service-call persistence**: When messages are persisted after each individual service call, trailing `FunctionResultContent` trimming is unnecessary. If tool calling is terminated, the `FunctionResultContent` from the terminated call was never sent to a subsequent service call, so it is never persisted. The per-service-call approach naturally matches the service's behavior.
- **Per-run persistence**: When messages are batched and persisted at the end of the full run, trailing `FunctionResultContent` trimming becomes necessary to match the service's behavior. Without trimming, the stored history contains `FunctionResultContent` that the service would never have stored.
This means the trimming feature (introduced in [PR #4792](https://github.com/microsoft/agent-framework/pull/4792)) is primarily needed as a complement to per-run persistence. The `PersistChatHistoryAtEndOfRun` setting (introduced in [PR #4762](https://github.com/microsoft/agent-framework/pull/4762)) inverts the default so that per-service-call persistence is the standard behavior, and per-run persistence is opt-in.
## Decision Drivers
- **A. Consistency**: The default behavior of `ChatHistoryProvider` should produce stored history that closely matches what the underlying AI service would store, minimizing surprise when switching between framework-managed and service-managed chat history.
- **B. Atomicity**: A run that fails mid-way through a multi-step tool-calling loop should not leave chat history in a partially-updated state, unless the user explicitly opts into that behavior.
- **C. Recoverability**: For long-running tool-calling loops, it should be possible to recover intermediate progress if the process is interrupted, rather than losing all work from the current run.
- **D. Simplicity**: The default behavior should be easy to understand and predict for most users, without requiring knowledge of the FIC loop internals.
- **E. Flexibility**: Regardless of the chosen default, users should be able to opt into the alternative behavior.
## Considered Options
- Option 1: Default to per-run persistence with `FunctionResultContent` trimming (opt-in to per-service-call)
- Option 2: Default to per-service-call persistence (opt-in to per-run)
## Pros and Cons of the Options
### Option 1: Default to per-run persistence with `FunctionResultContent` trimming
Keep the current default behavior of persisting chat history only at the end of the full agent run. Add `FunctionResultContent` trimming as the default to improve consistency with service storage. Provide an opt-in setting for users who want per-service-call persistence.
Settings:
- `PersistChatHistoryAtEndOfRun` = `true`
- Good, because runs are atomic — chat history is only updated when the full run succeeds, satisfying driver B.
- Good, because the mental model is simple: one run = one history update, satisfying driver D.
- Good, because trimming trailing `FunctionResultContent` improves consistency with service storage, partially satisfying driver A.
- Good, because users can opt in to per-service-call persistence for checkpointing/recovery scenarios, satisfying drivers C and E.
- Bad, because the default persistence timing still differs from the service's behavior (per-run vs. per-service-call), only partially satisfying driver A.
- Bad, because if the process crashes mid-loop, all intermediate progress from the current run is lost, not satisfying driver C by default.
### Option 2: Default to per-service-call persistence
Change the default to persist chat history after each individual service call within the FIC loop, matching the AI service's behavior. Trailing `FunctionResultContent` trimming is unnecessary with this approach (it is naturally handled). Provide an opt-in setting for users who want per-run atomicity with trimming.
Settings:
- `PersistChatHistoryAtEndOfRun` = `false` (default)
- Good, because the stored history matches the service's behavior by default for both timing and content, fully satisfying driver A.
- Good, because intermediate progress is preserved if the process is interrupted, satisfying driver C.
- Good, because no separate `FunctionResultContent` trimming logic is needed, reducing complexity.
- Bad, because chat history may be left in an incomplete state if the run fails mid-loop (e.g., `FunctionCallContent` stored without corresponding `FunctionResultContent`), not satisfying driver B. A subsequent run cannot proceed without manually providing the missing `FunctionResultContent`.
- Bad, because the mental model is more complex: a single run may produce multiple history updates, partially failing driver D.
- Neutral, because users can opt out to per-run persistence if they prefer atomicity, satisfying driver E.
## Decision Outcome
Chosen option: **Option 2 — Default to per-service-call persistence**, because it fully satisfies the consistency driver (A), naturally handles `FunctionResultContent` trimming without additional logic, and provides better recoverability for long-running tool-calling loops. Per-run persistence remains available via the `PersistChatHistoryAtEndOfRun` setting for users who prefer atomic run semantics.
### Configuration Matrix
The behavior depends on the combination of `UseProvidedChatClientAsIs` and `PersistChatHistoryAtEndOfRun`:
| `UseProvidedChatClientAsIs` | `PersistChatHistoryAtEndOfRun` | Behavior |
|---|---|---|
| `false` (default) | `false` (default) | **Per-service-call persistence.** A `ChatHistoryPersistingChatClient` middleware is automatically injected into the chat client pipeline between `FunctionInvokingChatClient` and the leaf `IChatClient`. Messages are persisted after each service call. |
| `true` | `false` | **User responsibility.** No middleware is injected because the user has provided a custom chat client stack. The user is responsible for ensuring correct persistence behavior (e.g., by including their own persisting middleware). |
| `false` | `true` | **Per-run persistence with marking.** A `ChatHistoryPersistingChatClient` middleware is injected, but configured to *mark* messages with metadata rather than store them immediately. At the end of the run, marked messages are stored. Trailing `FunctionResultContent` is trimmed. |
| `true` | `true` | **Per-run persistence with warning.** The system checks whether the custom chat client stack includes a `ChatHistoryPersistingChatClient`. If not, a warning is emitted (particularly relevant for workflow handoff scenarios where trimming cannot be guaranteed). If no `ChatHistoryPersistingChatClient` is preset, all messages are stored at the end of the run, otherwise marked messages are stored. |
### Consequences
- Good, because the stored history matches the service's behavior by default for both timing and content, fully satisfying consistency (driver A).
- Good, because intermediate progress is preserved if the process is interrupted, satisfying recoverability (driver C).
- Good, because no separate `FunctionResultContent` trimming logic is needed in the default path, reducing complexity.
- Good, because marking persisted messages with metadata enables deduplication and aids debugging.
- Good, because warnings for custom chat client configurations without the persisting middleware help prevent silent failures in workflow handoff scenarios.
- Bad, because chat history may be left in an incomplete state if the run fails mid-loop (e.g., `FunctionCallContent` stored without corresponding `FunctionResultContent`), requiring manual recovery in rare cases.
- Bad, because the mental model is more complex for the default path: a single run may produce multiple history updates.
- Neutral, because users who prefer atomic run semantics can opt in to per-run persistence via `PersistChatHistoryAtEndOfRun = true`.
- Neutral, because increased write frequency from per-service-call persistence may impact performance for some storage backends; this can be mitigated with a caching decorator.
### Implementation Notes
#### Conversation ID Consistency
The `ChatHistoryPersistingChatClient` middleware must also update the session's `ConversationId` consistently for both response-based and conversation-based service interactions, ensuring the session always reflects the latest service-provided identifier.
## More Information
- [PR #4762: Persist messages during function call loop](https://github.com/microsoft/agent-framework/pull/4762) — introduces `PersistChatHistoryAfterEachServiceCall` option and `ChatHistoryPersistingChatClient` decorator
- [PR #4792: Trim final FRC to match service storage](https://github.com/microsoft/agent-framework/pull/4792) — introduces `StoreFinalFunctionResultContent` option and `FilterFinalFunctionResultContent` logic
- [Issue #2889](https://github.com/microsoft/agent-framework/issues/2889) — original issue tracking chat history persistence during function call loops
+20 -19
View File
@@ -19,11 +19,10 @@
<PackageVersion Include="Aspire.Microsoft.Azure.Cosmos" Version="$(AspireAppHostSdkVersion)" />
<PackageVersion Include="CommunityToolkit.Aspire.OllamaSharp" Version="13.0.0" />
<!-- Azure.* -->
<PackageVersion Include="Azure.AI.Projects" Version="2.0.0-beta.1" />
<PackageVersion Include="Azure.AI.Projects.OpenAI" Version="2.0.0-beta.1" />
<PackageVersion Include="Azure.AI.Agents.Persistent" Version="1.2.0-beta.8" />
<PackageVersion Include="Azure.AI.OpenAI" Version="2.8.0-beta.1" />
<PackageVersion Include="Azure.Identity" Version="1.17.1" />
<PackageVersion Include="Azure.AI.Projects" Version="2.0.0-beta.2" />
<PackageVersion Include="Azure.AI.Agents.Persistent" Version="1.2.0-beta.10" />
<PackageVersion Include="Azure.AI.OpenAI" Version="2.9.0-beta.1" />
<PackageVersion Include="Azure.Identity" Version="1.19.0" />
<PackageVersion Include="Azure.Monitor.OpenTelemetry.Exporter" Version="1.4.0" />
<!-- Google Gemini -->
<PackageVersion Include="Google.GenAI" Version="0.11.0" />
@@ -40,12 +39,12 @@
<PackageVersion Include="System.CodeDom" Version="10.0.0" />
<PackageVersion Include="System.Collections.Immutable" Version="10.0.1" />
<PackageVersion Include="System.CommandLine" Version="2.0.0-rc.2.25502.107" />
<PackageVersion Include="System.Diagnostics.DiagnosticSource" Version="10.0.3" />
<PackageVersion Include="System.Diagnostics.DiagnosticSource" Version="10.0.4" />
<PackageVersion Include="System.Linq.AsyncEnumerable" Version="10.0.4" />
<PackageVersion Include="System.Net.Http.Json" Version="10.0.0" />
<PackageVersion Include="System.Net.ServerSentEvents" Version="10.0.3" />
<PackageVersion Include="System.Text.Json" Version="10.0.3" />
<PackageVersion Include="System.Threading.Channels" Version="10.0.3" />
<PackageVersion Include="System.Net.ServerSentEvents" Version="10.0.4" />
<PackageVersion Include="System.Text.Json" Version="10.0.4" />
<PackageVersion Include="System.Threading.Channels" Version="10.0.4" />
<PackageVersion Include="System.Threading.Tasks.Extensions" Version="4.6.3" />
<PackageVersion Include="System.Net.Security" Version="4.3.2" />
<!-- OpenTelemetry -->
@@ -64,24 +63,25 @@
<PackageVersion Include="Microsoft.AspNetCore.OpenApi" Version="10.0.0" />
<PackageVersion Include="Swashbuckle.AspNetCore.SwaggerUI" Version="10.0.0" />
<!-- Microsoft.Extensions.* -->
<PackageVersion Include="Microsoft.Extensions.AI" Version="10.3.0" />
<PackageVersion Include="Microsoft.Extensions.AI.Abstractions" Version="10.3.0" />
<PackageVersion Include="Microsoft.Extensions.AI.Evaluation" Version="10.3.0" />
<PackageVersion Include="Microsoft.Extensions.AI.Evaluation.Quality" Version="10.3.0" />
<PackageVersion Include="Microsoft.Extensions.AI" Version="10.4.0" />
<PackageVersion Include="Microsoft.Extensions.AI.Abstractions" Version="10.4.0" />
<PackageVersion Include="Microsoft.Extensions.AI.Evaluation" Version="10.4.0" />
<PackageVersion Include="Microsoft.Extensions.AI.Evaluation.Quality" Version="10.4.0" />
<PackageVersion Include="Microsoft.Extensions.AI.Evaluation.Safety" Version="10.3.0-preview.1.26109.11" />
<PackageVersion Include="Microsoft.Extensions.AI.OpenAI" Version="10.3.0" />
<PackageVersion Include="Microsoft.Extensions.AI.OpenAI" Version="10.4.0" />
<PackageVersion Include="Microsoft.Extensions.Caching.Memory" Version="10.0.0" />
<PackageVersion Include="Microsoft.Extensions.Compliance.Abstractions" Version="10.4.0" />
<PackageVersion Include="Microsoft.Extensions.Configuration" Version="10.0.0" />
<PackageVersion Include="Microsoft.Extensions.Configuration.Binder" Version="10.0.0" />
<PackageVersion Include="Microsoft.Extensions.Configuration.EnvironmentVariables" Version="10.0.0" />
<PackageVersion Include="Microsoft.Extensions.Configuration.Json" Version="10.0.0" />
<PackageVersion Include="Microsoft.Extensions.Configuration.UserSecrets" Version="10.0.0" />
<PackageVersion Include="Microsoft.Extensions.DependencyInjection" Version="10.0.0" />
<PackageVersion Include="Microsoft.Extensions.DependencyInjection.Abstractions" Version="10.0.3" />
<PackageVersion Include="Microsoft.Extensions.DependencyInjection.Abstractions" Version="10.0.4" />
<PackageVersion Include="Microsoft.Extensions.Hosting" Version="10.0.0" />
<PackageVersion Include="Microsoft.Extensions.Http.Resilience" Version="10.0.0" />
<PackageVersion Include="Microsoft.Extensions.Logging" Version="10.0.0" />
<PackageVersion Include="Microsoft.Extensions.Logging.Abstractions" Version="10.0.3" />
<PackageVersion Include="Microsoft.Extensions.Logging.Abstractions" Version="10.0.4" />
<PackageVersion Include="Microsoft.Extensions.Logging.Console" Version="10.0.0" />
<PackageVersion Include="Microsoft.Extensions.ServiceDiscovery" Version="10.0.0" />
<PackageVersion Include="Microsoft.Extensions.VectorData.Abstractions" Version="9.7.0" />
@@ -111,9 +111,9 @@
<PackageVersion Include="Microsoft.ML.OnnxRuntimeGenAI" Version="0.10.0" />
<PackageVersion Include="Microsoft.ML.Tokenizers" Version="2.0.0" />
<PackageVersion Include="OllamaSharp" Version="5.4.8" />
<PackageVersion Include="OpenAI" Version="2.8.0" />
<PackageVersion Include="OpenAI" Version="2.9.1" />
<!-- Identity -->
<PackageVersion Include="Microsoft.Identity.Client.Extensions.Msal" Version="4.78.0" />
<PackageVersion Include="Microsoft.Identity.Client.Extensions.Msal" Version="4.83.1" />
<!-- Workflows -->
<PackageVersion Include="Microsoft.Agents.ObjectModel" Version="2026.2.4.1" />
<PackageVersion Include="Microsoft.Agents.ObjectModel.Json" Version="2026.2.4.1" />
@@ -127,7 +127,7 @@
<!-- Azure Functions -->
<PackageVersion Include="Microsoft.Azure.Functions.Worker" Version="2.50.0" />
<PackageVersion Include="Microsoft.Azure.Functions.Worker.ApplicationInsights" Version="2.50.0" />
<PackageVersion Include="Microsoft.Azure.Functions.Worker.Extensions.DurableTask" Version="1.11.0" />
<PackageVersion Include="Microsoft.Azure.Functions.Worker.Extensions.DurableTask" Version="1.12.1" />
<PackageVersion Include="Microsoft.Azure.Functions.Worker.Extensions.DurableTask.AzureManaged" Version="1.0.1" />
<PackageVersion Include="Microsoft.Azure.Functions.Worker.Extensions.Http" Version="3.3.0" />
<PackageVersion Include="Microsoft.Azure.Functions.Worker.Extensions.Http.AspNetCore" Version="2.1.0" />
@@ -149,6 +149,7 @@
<!-- Symbols -->
<PackageVersion Include="Microsoft.SourceLink.GitHub" Version="8.0.0" />
<!-- Toolset -->
<PackageVersion Include="ReferenceTrimmer" Version="3.4.5" />
<PackageVersion Include="Microsoft.CodeAnalysis.Analyzers" Version="3.11.0" />
<PackageVersion Include="Microsoft.CodeAnalysis.CSharp" Version="4.14.0" />
<PackageVersion Include="Microsoft.CodeAnalysis.NetAnalyzers" Version="10.0.100" />
+28 -3
View File
@@ -57,10 +57,32 @@
<Project Path="samples/02-agents/Agents/Agent_Step16_Declarative/Agent_Step16_Declarative.csproj" />
<Project Path="samples/02-agents/Agents/Agent_Step17_AdditionalAIContext/Agent_Step17_AdditionalAIContext.csproj" />
<Project Path="samples/02-agents/Agents/Agent_Step18_CompactionPipeline/Agent_Step18_CompactionPipeline.csproj" />
<Project Path="samples/02-agents/Agents/Agent_Step19_InFunctionLoopCheckpointing/Agent_Step19_InFunctionLoopCheckpointing.csproj" />
</Folder>
<Folder Name="/Samples/02-agents/DeclarativeAgents/">
<Project Path="samples/02-agents/DeclarativeAgents/ChatClient/DeclarativeChatClientAgents.csproj" />
</Folder>
<Folder Name="/Samples/04-hosting/DurableWorkflows/" />
<Folder Name="/Samples/04-hosting/DurableWorkflows/ConsoleApps/">
<Project Path="samples/04-hosting/DurableWorkflows/ConsoleApps/01_SequentialWorkflow/01_SequentialWorkflow.csproj" />
<Project Path="samples/04-hosting/DurableWorkflows/ConsoleApps/02_ConcurrentWorkflow/02_ConcurrentWorkflow.csproj" />
<Project Path="samples/04-hosting/DurableWorkflows/ConsoleApps/03_ConditionalEdges/03_ConditionalEdges.csproj" />
<Project Path="samples/04-hosting/DurableWorkflows/ConsoleApps/04_WorkflowAndAgents/04_WorkflowAndAgents.csproj" />
<Project Path="samples/04-hosting/DurableWorkflows/ConsoleApps/05_WorkflowEvents/05_WorkflowEvents.csproj" />
<Project Path="samples/04-hosting/DurableWorkflows/ConsoleApps/06_WorkflowSharedState/06_WorkflowSharedState.csproj" />
<Project Path="samples/04-hosting/DurableWorkflows/ConsoleApps/07_SubWorkflows/07_SubWorkflows.csproj" />
<Project Path="samples/04-hosting/DurableWorkflows/ConsoleApps/08_WorkflowHITL/08_WorkflowHITL.csproj" />
</Folder>
<Folder Name="/Samples/04-hosting/DurableWorkflows/AzureFunctions/">
<Project Path="samples/04-hosting/DurableWorkflows/AzureFunctions/01_SequentialWorkflow/01_SequentialWorkflow.csproj" />
<Project Path="samples/04-hosting/DurableWorkflows/AzureFunctions/02_ConcurrentWorkflow/02_ConcurrentWorkflow.csproj" />
<Project Path="samples/04-hosting/DurableWorkflows/AzureFunctions/03_WorkflowHITL/03_WorkflowHITL.csproj" />
<Project Path="samples/04-hosting/DurableWorkflows/AzureFunctions/04_WorkflowMcpTool/04_WorkflowMcpTool.csproj" />
<Project Path="samples/04-hosting/DurableWorkflows/AzureFunctions/05_WorkflowAndAgents/05_WorkflowAndAgents.csproj" />
</Folder>
<Folder Name="/Samples/GettingStarted/">
<File Path="samples/GettingStarted/README.md" />
</Folder>
<Folder Name="/Samples/02-agents/AGUI/">
<File Path="samples/02-agents/AGUI/README.md" />
</Folder>
@@ -82,7 +104,7 @@
</Folder>
<Folder Name="/Samples/02-agents/AgentSkills/">
<File Path="samples/02-agents/AgentSkills/README.md" />
<Project Path="samples/02-agents/AgentSkills/Agent_Step01_BasicSkills/Agent_Step01_BasicSkills.csproj" />
<Project Path="samples/02-agents/AgentSkills/Agent_Step01_FileBasedSkills/Agent_Step01_FileBasedSkills.csproj" />
</Folder>
<Folder Name="/Samples/02-agents/AGUI/Step05_StateManagement/">
<Project Path="samples/02-agents/AGUI/Step05_StateManagement/Client/Client.csproj" />
@@ -290,7 +312,6 @@
<Project Path="samples/05-end-to-end/HostedAgents/AgentWithHostedMCP/AgentWithHostedMCP.csproj" />
<Project Path="samples/05-end-to-end/HostedAgents/AgentWithLocalTools/AgentWithLocalTools.csproj" />
<Project Path="samples/05-end-to-end/HostedAgents/AgentWithTextSearchRag/AgentWithTextSearchRag.csproj" />
<Project Path="samples/05-end-to-end/HostedAgents/AgentWithTools/AgentWithTools.csproj" />
<Project Path="samples/05-end-to-end/HostedAgents/FoundryMultiAgent/FoundryMultiAgent.csproj" />
<Project Path="samples/05-end-to-end/HostedAgents/FoundrySingleAgent/FoundrySingleAgent.csproj" />
</Folder>
@@ -434,6 +455,10 @@
<File Path="src/Shared/Samples/TextOutputHelperExtensions.cs" />
<File Path="src/Shared/Samples/XunitLogger.cs" />
</Folder>
<Folder Name="/Solution Items/src/Shared/Redaction/">
<File Path="src/Shared/Redaction/README.md" />
<File Path="src/Shared/Redaction/ReplacingRedactor.cs" />
</Folder>
<Folder Name="/Solution Items/src/Shared/Throw/">
<File Path="src/Shared/Throw/README.md" />
<File Path="src/Shared/Throw/Throw.cs" />
@@ -520,4 +545,4 @@
<Project Path="tests/Microsoft.Agents.AI.Workflows.Generators.UnitTests/Microsoft.Agents.AI.Workflows.Generators.UnitTests.csproj" />
<Project Path="tests/Microsoft.Agents.AI.Workflows.UnitTests/Microsoft.Agents.AI.Workflows.UnitTests.csproj" />
</Folder>
</Solution>
</Solution>
+3
View File
@@ -29,4 +29,7 @@
<ItemGroup Condition="'$(InjectSharedDiagnosticIds)' == 'true'">
<Compile Include="$(MSBuildThisFileDirectory)\..\..\src\Shared\DiagnosticIds\*.cs" LinkBase="Shared\DiagnosticIds" />
</ItemGroup>
<ItemGroup Condition="'$(InjectSharedRedaction)' == 'true'">
<Compile Include="$(MSBuildThisFileDirectory)\..\..\src\Shared\Redaction\*.cs" LinkBase="Shared\Redaction" />
</ItemGroup>
</Project>
@@ -59,14 +59,14 @@ while ((input = Console.ReadLine()) != null && !input.Equals("exit", StringCompa
{
switch (content)
{
case FunctionApprovalRequestContent approvalRequest:
DisplayApprovalRequest(approvalRequest);
case ToolApprovalRequestContent approvalRequest when approvalRequest.ToolCall is FunctionCallContent fcc:
DisplayApprovalRequest(approvalRequest, fcc);
Console.Write($"\nApprove '{approvalRequest.FunctionCall.Name}'? (yes/no): ");
Console.Write($"\nApprove '{fcc.Name}'? (yes/no): ");
string? userInput = Console.ReadLine();
bool approved = userInput?.ToUpperInvariant() is "YES" or "Y";
FunctionApprovalResponseContent approvalResponse = approvalRequest.CreateResponse(approved);
ToolApprovalResponseContent approvalResponse = approvalRequest.CreateResponse(approved);
if (approvalRequest.AdditionalProperties != null)
{
@@ -128,19 +128,19 @@ while ((input = Console.ReadLine()) != null && !input.Equals("exit", StringCompa
}
#pragma warning disable MEAI001
static void DisplayApprovalRequest(FunctionApprovalRequestContent approvalRequest)
static void DisplayApprovalRequest(ToolApprovalRequestContent approvalRequest, FunctionCallContent fcc)
{
Console.ForegroundColor = ConsoleColor.Yellow;
Console.WriteLine();
Console.WriteLine("============================================================");
Console.WriteLine("APPROVAL REQUIRED");
Console.WriteLine("============================================================");
Console.WriteLine($"Function: {approvalRequest.FunctionCall.Name}");
Console.WriteLine($"Function: {fcc.Name}");
if (approvalRequest.FunctionCall.Arguments != null)
if (fcc.Arguments != null)
{
Console.WriteLine("Arguments:");
foreach (var arg in approvalRequest.FunctionCall.Arguments)
foreach (var arg in fcc.Arguments)
{
Console.WriteLine($" {arg.Key} = {arg.Value}");
}
@@ -9,7 +9,7 @@ using ServerFunctionApproval;
/// <summary>
/// A delegating agent that handles server function approval requests and responses.
/// Transforms between FunctionApprovalRequestContent/FunctionApprovalResponseContent
/// Transforms between ToolApprovalRequestContent/ToolApprovalResponseContent
/// and the server's request_approval tool call pattern.
/// </summary>
internal sealed class ServerFunctionApprovalClientAgent : DelegatingAIAgent
@@ -50,14 +50,14 @@ internal sealed class ServerFunctionApprovalClientAgent : DelegatingAIAgent
}
#pragma warning disable MEAI001 // Type is for evaluation purposes only
private static FunctionResultContent ConvertApprovalResponseToToolResult(FunctionApprovalResponseContent approvalResponse, JsonSerializerOptions jsonOptions)
private static FunctionResultContent ConvertApprovalResponseToToolResult(ToolApprovalResponseContent approvalResponse, JsonSerializerOptions jsonOptions)
{
return new FunctionResultContent(
callId: approvalResponse.Id,
callId: approvalResponse.RequestId,
result: JsonSerializer.SerializeToElement(
new ApprovalResponse
{
ApprovalId = approvalResponse.Id,
ApprovalId = approvalResponse.RequestId,
Approved = approvalResponse.Approved
},
jsonOptions));
@@ -89,7 +89,7 @@ internal sealed class ServerFunctionApprovalClientAgent : DelegatingAIAgent
{
List<ChatMessage>? result = null;
Dictionary<string, FunctionApprovalRequestContent> approvalRequests = [];
Dictionary<string, ToolApprovalRequestContent> approvalRequests = [];
for (var messageIndex = 0; messageIndex < messages.Count; messageIndex++)
{
var message = messages[messageIndex];
@@ -102,21 +102,21 @@ internal sealed class ServerFunctionApprovalClientAgent : DelegatingAIAgent
var content = message.Contents[contentIndex];
// Handle pending approval requests (transform to tool call)
if (content is FunctionApprovalRequestContent approvalRequest &&
if (content is ToolApprovalRequestContent approvalRequest &&
approvalRequest.AdditionalProperties?.TryGetValue("original_function", out var originalFunction) == true &&
originalFunction is FunctionCallContent original)
{
approvalRequests[approvalRequest.Id] = approvalRequest;
approvalRequests[approvalRequest.RequestId] = approvalRequest;
transformedContents ??= CopyContentsUpToIndex(message.Contents, contentIndex);
transformedContents.Add(original);
}
// Handle pending approval responses (transform to tool result)
else if (content is FunctionApprovalResponseContent approvalResponse &&
approvalRequests.TryGetValue(approvalResponse.Id, out var correspondingRequest))
else if (content is ToolApprovalResponseContent approvalResponse &&
approvalRequests.TryGetValue(approvalResponse.RequestId, out var correspondingRequest))
{
transformedContents ??= CopyContentsUpToIndex(message.Contents, contentIndex);
transformedContents.Add(ConvertApprovalResponseToToolResult(approvalResponse, jsonSerializerOptions));
approvalRequests.Remove(approvalResponse.Id);
approvalRequests.Remove(approvalResponse.RequestId);
correspondingRequest.AdditionalProperties?.Remove("original_function");
}
// Skip historical approval content
@@ -198,8 +198,8 @@ internal sealed class ServerFunctionApprovalClientAgent : DelegatingAIAgent
var functionCallArgs = (Dictionary<string, object?>?)approvalRequest.FunctionArguments?
.Deserialize(jsonSerializerOptions.GetTypeInfo(typeof(Dictionary<string, object?>)));
var approvalRequestContent = new FunctionApprovalRequestContent(
id: approvalRequest.ApprovalId,
var approvalRequestContent = new ToolApprovalRequestContent(
requestId: approvalRequest.ApprovalId,
new FunctionCallContent(
callId: approvalRequest.ApprovalId,
name: approvalRequest.FunctionName,
@@ -9,7 +9,7 @@ using ServerFunctionApproval;
/// <summary>
/// A delegating agent that handles function approval requests on the server side.
/// Transforms between FunctionApprovalRequestContent/FunctionApprovalResponseContent
/// Transforms between ToolApprovalRequestContent/ToolApprovalResponseContent
/// and the request_approval tool call pattern for client communication.
/// </summary>
internal sealed class ServerFunctionApprovalAgent : DelegatingAIAgent
@@ -50,7 +50,7 @@ internal sealed class ServerFunctionApprovalAgent : DelegatingAIAgent
}
#pragma warning disable MEAI001 // Type is for evaluation purposes only
private static FunctionApprovalRequestContent ConvertToolCallToApprovalRequest(FunctionCallContent toolCall, JsonSerializerOptions jsonSerializerOptions)
private static ToolApprovalRequestContent ConvertToolCallToApprovalRequest(FunctionCallContent toolCall, JsonSerializerOptions jsonSerializerOptions)
{
if (toolCall.Name != "request_approval" || toolCall.Arguments == null)
{
@@ -67,15 +67,15 @@ internal sealed class ServerFunctionApprovalAgent : DelegatingAIAgent
throw new InvalidOperationException("Failed to deserialize approval request from tool call");
}
return new FunctionApprovalRequestContent(
id: request.ApprovalId,
return new ToolApprovalRequestContent(
requestId: request.ApprovalId,
new FunctionCallContent(
callId: request.ApprovalId,
name: request.FunctionName,
arguments: request.FunctionArguments));
}
private static FunctionApprovalResponseContent ConvertToolResultToApprovalResponse(FunctionResultContent result, FunctionApprovalRequestContent approval, JsonSerializerOptions jsonSerializerOptions)
private static ToolApprovalResponseContent ConvertToolResultToApprovalResponse(FunctionResultContent result, ToolApprovalRequestContent approval, JsonSerializerOptions jsonSerializerOptions)
{
var approvalResponse = result.Result is JsonElement je ?
(ApprovalResponse?)je.Deserialize(jsonSerializerOptions.GetTypeInfo(typeof(ApprovalResponse))) :
@@ -121,7 +121,7 @@ internal sealed class ServerFunctionApprovalAgent : DelegatingAIAgent
// Track approval ID to original call ID mapping
_ = new Dictionary<string, string>();
#pragma warning disable MEAI001 // Type is for evaluation purposes only and is subject to change or removal in future updates. Suppress this diagnostic to proceed.
Dictionary<string, FunctionApprovalRequestContent> trackedRequestApprovalToolCalls = new(); // Remote approvals
Dictionary<string, ToolApprovalRequestContent> trackedRequestApprovalToolCalls = new(); // Remote approvals
for (int messageIndex = 0; messageIndex < messages.Count; messageIndex++)
{
var message = messages[messageIndex];
@@ -181,11 +181,10 @@ internal sealed class ServerFunctionApprovalAgent : DelegatingAIAgent
{
var content = update.Contents[i];
#pragma warning disable MEAI001 // Type is for evaluation purposes only
if (content is FunctionApprovalRequestContent request)
if (content is ToolApprovalRequestContent request && request.ToolCall is FunctionCallContent functionCall)
{
updatedContents ??= [.. update.Contents];
var functionCall = request.FunctionCall;
var approvalId = request.Id;
var approvalId = request.RequestId;
var approvalData = new ApprovalRequest
{
@@ -18,6 +18,7 @@ using OpenTelemetry.Trace;
#region Setup Telemetry
// Source name for this sample's custom ActivitySource and Meter; other instrumentation uses their own sources/categories.
const string SourceName = "OpenTelemetryAspire.ConsoleApp";
const string ServiceName = "AgentOpenTelemetry";
@@ -40,7 +41,6 @@ var resource = ResourceBuilder.CreateDefault()
var tracerProviderBuilder = Sdk.CreateTracerProviderBuilder()
.SetResourceBuilder(ResourceBuilder.CreateDefault().AddService(ServiceName, serviceVersion: "1.0.0"))
.AddSource(SourceName) // Our custom activity source
.AddSource("*Microsoft.Agents.AI") // Agent Framework telemetry
.AddHttpClientInstrumentation() // Capture HTTP calls to OpenAI
.AddOtlpExporter(options => options.Endpoint = new Uri(otlpEndpoint));
@@ -54,8 +54,7 @@ using var tracerProvider = tracerProviderBuilder.Build();
// Setup metrics with resource and instrument name filtering
using var meterProvider = Sdk.CreateMeterProviderBuilder()
.SetResourceBuilder(ResourceBuilder.CreateDefault().AddService(ServiceName, serviceVersion: "1.0.0"))
.AddMeter(SourceName) // Our custom meter
.AddMeter("*Microsoft.Agents.AI") // Agent Framework metrics
.AddMeter(SourceName) // Our custom meter source
.AddHttpClientInstrumentation() // HTTP client metrics
.AddRuntimeInstrumentation() // .NET runtime metrics
.AddOtlpExporter(options => options.Endpoint = new Uri(otlpEndpoint))
@@ -128,7 +127,7 @@ var agent = new ChatClientAgent(instrumentedChatClient,
instructions: "You are a helpful assistant that provides concise and informative responses.",
tools: [AIFunctionFactory.Create(GetWeatherAsync)])
.AsBuilder()
.UseOpenTelemetry(SourceName, configure: (cfg) => cfg.EnableSensitiveData = true) // enable telemetry at the agent level
.UseOpenTelemetry(sourceName: SourceName, configure: (cfg) => cfg.EnableSensitiveData = true) // enable telemetry at the agent level
.Build();
var session = await agent.CreateSessionAsync();
@@ -1,5 +1,7 @@
// Copyright (c) Microsoft. All rights reserved.
#pragma warning disable CS0618 // Type or member is obsolete - sample uses deprecated PersistentAgentsClientExtensions
// This sample shows how to create and use a simple AI agent with Azure Foundry Agents as the backend.
using Azure.AI.Agents.Persistent;
@@ -3,7 +3,7 @@
// This sample shows how to create and use a AI agents with Azure Foundry Agents as the backend.
using Azure.AI.Projects;
using Azure.AI.Projects.OpenAI;
using Azure.AI.Projects.Agents;
using Azure.Identity;
using Microsoft.Agents.AI;
@@ -17,8 +17,8 @@ var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT
AIAgent agent = new AzureOpenAIClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetResponsesClient(deploymentName)
.AsAIAgent(instructions: "You are good at telling jokes.", name: "Joker");
.GetResponsesClient()
.AsAIAgent(model: deploymentName, instructions: "You are good at telling jokes.", name: "Joker");
// Invoke the agent and output the text result.
Console.WriteLine(await agent.RunAsync("Tell me a joke about a pirate."));
@@ -29,8 +29,8 @@ Console.WriteLine(await agent.RunAsync("Tell me a joke about a pirate."));
AIAgent agentStoreFalse = new AzureOpenAIClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetResponsesClient(deploymentName)
.AsIChatClientWithStoredOutputDisabled()
.GetResponsesClient()
.AsIChatClientWithStoredOutputDisabled(model: deploymentName)
.AsAIAgent(instructions: "You are good at telling jokes.", name: "Joker");
// Invoke the agent and output the text result.
@@ -9,7 +9,7 @@
</PropertyGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI\Microsoft.Agents.AI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Abstractions\Microsoft.Agents.AI.Abstractions.csproj" />
</ItemGroup>
</Project>
@@ -11,8 +11,8 @@ var model = Environment.GetEnvironmentVariable("OPENAI_CHAT_MODEL_NAME") ?? "gpt
AIAgent agent = new OpenAIClient(
apiKey)
.GetResponsesClient(model)
.AsAIAgent(instructions: "You are good at telling jokes.", name: "Joker");
.GetResponsesClient()
.AsAIAgent(model: model, instructions: "You are good at telling jokes.", name: "Joker");
// Invoke the agent and output the text result.
Console.WriteLine(await agent.RunAsync("Tell me a joke about a pirate."));
@@ -1,49 +0,0 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample demonstrates how to use Agent Skills with a ChatClientAgent.
// Agent Skills are modular packages of instructions and resources that extend an agent's capabilities.
// Skills follow the progressive disclosure pattern: advertise -> load -> read resources.
//
// This sample includes the expense-report skill:
// - Policy-based expense filing with references and assets
using Azure.AI.OpenAI;
using Azure.Identity;
using Microsoft.Agents.AI;
using OpenAI.Responses;
// --- Configuration ---
string endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT")
?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
string deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-4o-mini";
// --- Skills Provider ---
// Discovers skills from the 'skills' directory and makes them available to the agent
var skillsProvider = new FileAgentSkillsProvider(skillPath: Path.Combine(AppContext.BaseDirectory, "skills"));
// --- Agent Setup ---
AIAgent agent = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential())
.GetResponsesClient(deploymentName)
.AsAIAgent(new ChatClientAgentOptions
{
Name = "SkillsAgent",
ChatOptions = new()
{
Instructions = "You are a helpful assistant.",
},
AIContextProviders = [skillsProvider],
});
// --- Example 1: Expense policy question (loads FAQ resource) ---
Console.WriteLine("Example 1: Checking expense policy FAQ");
Console.WriteLine("---------------------------------------");
AgentResponse response1 = await agent.RunAsync("Are tips reimbursable? I left a 25% tip on a taxi ride and want to know if that's covered.");
Console.WriteLine($"Agent: {response1.Text}\n");
// --- Example 2: Filing an expense report (multi-turn with template asset) ---
Console.WriteLine("Example 2: Filing an expense report");
Console.WriteLine("---------------------------------------");
AgentSession session = await agent.CreateSessionAsync();
AgentResponse response2 = await agent.RunAsync("I had 3 client dinners and a $1,200 flight last week. Return a draft expense report and ask about any missing details.",
session);
Console.WriteLine($"Agent: {response2.Text}\n");
@@ -1,63 +0,0 @@
# Agent Skills Sample
This sample demonstrates how to use **Agent Skills** with a `ChatClientAgent` in the Microsoft Agent Framework.
## What are Agent Skills?
Agent Skills are modular packages of instructions and resources that enable AI agents to perform specialized tasks. They follow the [Agent Skills specification](https://agentskills.io/) and implement the progressive disclosure pattern:
1. **Advertise**: Skills are advertised with name + description (~100 tokens per skill)
2. **Load**: Full instructions are loaded on-demand via `load_skill` tool
3. **Resources**: References and other files loaded via `read_skill_resource` tool
## Skills Included
### expense-report
Policy-based expense filing with spending limits, receipt requirements, and approval workflows.
- `references/POLICY_FAQ.md` — Detailed expense policy Q&A
- `assets/expense-report-template.md` — Submission template
## Project Structure
```
Agent_Step01_BasicSkills/
├── Program.cs
├── Agent_Step01_BasicSkills.csproj
└── skills/
└── expense-report/
├── SKILL.md
├── references/
│ └── POLICY_FAQ.md
└── assets/
└── expense-report-template.md
```
## Running the Sample
### Prerequisites
- .NET 10.0 SDK
- Azure OpenAI endpoint with a deployed model
### Setup
1. Set environment variables:
```bash
export AZURE_OPENAI_ENDPOINT="https://your-endpoint.openai.azure.com/"
export AZURE_OPENAI_DEPLOYMENT_NAME="gpt-4o-mini"
```
2. Run the sample:
```bash
dotnet run
```
### Examples
The sample runs two examples:
1. **Expense policy FAQ** — Asks about tip reimbursement; the agent loads the expense-report skill and reads the FAQ resource
2. **Filing an expense report** — Multi-turn conversation to draft an expense report using the template asset
## Learn More
- [Agent Skills Specification](https://agentskills.io/)
- [Microsoft Agent Framework Documentation](../../../../../docs/)
@@ -1,40 +0,0 @@
---
name: expense-report
description: File and validate employee expense reports according to Contoso company policy. Use when asked about expense submissions, reimbursement rules, receipt requirements, spending limits, or expense categories.
metadata:
author: contoso-finance
version: "2.1"
---
# Expense Report
## Categories and Limits
| Category | Limit | Receipt | Approval |
|---|---|---|---|
| Meals — solo | $50/day | >$25 | No |
| Meals — team/client | $75/person | Always | Manager if >$200 total |
| Lodging | $250/night | Always | Manager if >3 nights |
| Ground transport | $100/day | >$15 | No |
| Airfare | Economy | Always | Manager; VP if >$1,500 |
| Conference/training | $2,000/event | Always | Manager + L&D |
| Office supplies | $100 | Yes | No |
| Software/subscriptions | $50/month | Yes | Manager if >$200/year |
## Filing Process
1. Collect receipts — must show vendor, date, amount, payment method.
2. Categorize per table above.
3. Use template: [assets/expense-report-template.md](assets/expense-report-template.md).
4. For client/team meals: list attendee names and business purpose.
5. Submit — auto-approved if <$500; manager if $500$2,000; VP if >$2,000.
6. Reimbursement: 10 business days via direct deposit.
## Policy Rules
- Submit within 30 days of transaction.
- Alcohol is never reimbursable.
- Foreign currency: convert to USD at transaction-date rate; note original currency and amount.
- Mixed personal/business travel: only business portion reimbursable; provide comparison quotes.
- Lost receipts (>$25): file Lost Receipt Affidavit from Finance. Max 2 per quarter.
- For policy questions not covered above, consult the FAQ: [references/POLICY_FAQ.md](references/POLICY_FAQ.md). Answers should be based on what this document and the FAQ state.
@@ -1,5 +0,0 @@
# Expense Report Template
| Date | Category | Vendor | Description | Amount (USD) | Original Currency | Original Amount | Attendees | Business Purpose | Receipt Attached |
|------|----------|--------|-------------|--------------|-------------------|-----------------|-----------|------------------|------------------|
| | | | | | | | | | Yes or No |
@@ -1,55 +0,0 @@
# Expense Policy — Frequently Asked Questions
## Meals
**Q: Can I expense coffee or snacks during the workday?**
A: Daily coffee/snacks under $10 are not reimbursable (considered personal). Coffee purchased during a client meeting or team working session is reimbursable as a team meal.
**Q: What if a team dinner exceeds the per-person limit?**
A: The $75/person limit applies as a guideline. Overages up to 20% are accepted with a written justification (e.g., "client dinner at venue chosen by client"). Overages beyond 20% require pre-approval from your VP.
**Q: Do I need to list every attendee?**
A: Yes. For client meals, list the client's name and company. For team meals, list all employee names. For groups over 10, you may attach a separate attendee list.
## Travel
**Q: Can I book a premium economy or business class flight?**
A: Economy class is the standard. Premium economy is allowed for flights over 6 hours. Business class requires VP pre-approval and is generally reserved for flights over 10 hours or medical accommodation.
**Q: What about ride-sharing (Uber/Lyft) vs. rental cars?**
A: Use ride-sharing for trips under 30 miles round-trip. Rent a car for multi-day travel or when ride-sharing would exceed $100/day. Always choose the compact/standard category unless traveling with 3+ people.
**Q: Are tips reimbursable?**
A: Tips up to 20% are reimbursable for meals, taxi/ride-share, and hotel housekeeping. Tips above 20% require justification.
## Lodging
**Q: What if the $250/night limit isn't enough for the city I'm visiting?**
A: For high-cost cities (New York, San Francisco, London, Tokyo, Sydney), the limit is automatically increased to $350/night. No additional approval is needed. For other locations where rates are unusually high (e.g., during a major conference), request a per-trip exception from your manager before booking.
**Q: Can I stay with friends/family instead and get a per-diem?**
A: No. Contoso reimburses actual lodging costs only, not per-diems.
## Subscriptions and Software
**Q: Can I expense a personal productivity tool?**
A: Software must be directly related to your job function. Tools like IDE licenses, design software, or project management apps are reimbursable. General productivity apps (note-taking, personal calendar) are not, unless your manager confirms a business need in writing.
**Q: What about annual subscriptions?**
A: Annual subscriptions over $200 require manager approval before purchase. Submit the approval email with your expense report.
## Receipts and Documentation
**Q: My receipt is faded/damaged. What do I do?**
A: Try to obtain a duplicate from the vendor. If not possible, submit a Lost Receipt Affidavit (available from the Finance SharePoint site). You're limited to 2 affidavits per quarter.
**Q: Do I need a receipt for parking meters or tolls?**
A: For amounts under $15, no receipt is required — just note the date, location, and amount. For $15 and above, a receipt or bank/credit card statement excerpt is required.
## Approval and Reimbursement
**Q: My manager is on leave. Who approves my report?**
A: Expense reports can be approved by your skip-level manager or any manager designated as an alternate approver in the expense system.
**Q: Can I submit expenses from a previous quarter?**
A: The standard 30-day window applies. Expenses older than 30 days require a written explanation and VP approval. Expenses older than 90 days are not reimbursable except in extraordinary circumstances (extended leave, medical emergency) with CFO approval.
@@ -14,6 +14,10 @@
<PackageReference Include="Azure.Identity" />
</ItemGroup>
<ItemGroup>
<Compile Include="..\SubprocessScriptRunner.cs" Link="SubprocessScriptRunner.cs" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
</ItemGroup>
@@ -0,0 +1,48 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample demonstrates how to use file-based Agent Skills with a ChatClientAgent.
// Skills are discovered from SKILL.md files on disk and follow the progressive disclosure pattern:
// 1. Advertise — skill names and descriptions in the system prompt
// 2. Load — full instructions loaded on demand via load_skill tool
// 3. Read resources — reference files read via read_skill_resource tool
// 4. Run scripts — scripts executed via run_skill_script tool with a subprocess executor
//
// This sample uses a unit-converter skill that converts between miles, kilometers, pounds, and kilograms.
using Azure.AI.OpenAI;
using Azure.Identity;
using Microsoft.Agents.AI;
using OpenAI.Responses;
// --- Configuration ---
string endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
string deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-4o-mini";
// --- Skills Provider ---
// Discovers skills from the 'skills' directory containing SKILL.md files.
// The script runner runs file-based scripts (e.g. Python) as local subprocesses.
var skillsProvider = new AgentSkillsProvider(
Path.Combine(AppContext.BaseDirectory, "skills"),
SubprocessScriptRunner.RunAsync);
// --- Agent Setup ---
AIAgent agent = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential())
.GetResponsesClient()
.AsAIAgent(new ChatClientAgentOptions
{
Name = "UnitConverterAgent",
ChatOptions = new()
{
Instructions = "You are a helpful assistant that can convert units.",
},
AIContextProviders = [skillsProvider],
},
model: deploymentName);
// --- Example: Unit conversion ---
Console.WriteLine("Converting units with file-based skills");
Console.WriteLine(new string('-', 60));
AgentResponse response = await agent.RunAsync(
"How many kilometers is a marathon (26.2 miles)? And how many pounds is 75 kilograms?");
Console.WriteLine($"Agent: {response.Text}");
@@ -0,0 +1,51 @@
# File-Based Agent Skills Sample
This sample demonstrates how to use **file-based Agent Skills** with a `ChatClientAgent`.
## What it demonstrates
- Discovering skills from `SKILL.md` files on disk via `AgentFileSkillsSource`
- The progressive disclosure pattern: advertise → load → read resources → run scripts
- Using the `AgentSkillsProvider` constructor with a skill directory path and script executor
- Running file-based scripts (Python) via a subprocess-based executor
## Skills Included
### unit-converter
Converts between common units (miles↔km, pounds↔kg) using a multiplication factor.
- `references/conversion-table.md` — Conversion factor table
- `scripts/convert.py` — Python script that performs the conversion
## Running the Sample
### Prerequisites
- .NET 10.0 SDK
- Azure OpenAI endpoint with a deployed model
- Python 3 installed and available as `python3` on your PATH
### Setup
```bash
export AZURE_OPENAI_ENDPOINT="https://your-endpoint.openai.azure.com/"
export AZURE_OPENAI_DEPLOYMENT_NAME="gpt-4o-mini"
```
### Run
```bash
dotnet run
```
### Expected Output
```
Converting units with file-based skills
------------------------------------------------------------
Agent: Here are your conversions:
1. **26.2 miles → 42.16 km** (a marathon distance)
2. **75 kg → 165.35 lbs**
```
@@ -0,0 +1,11 @@
---
name: unit-converter
description: Convert between common units using a multiplication factor. Use when asked to convert miles, kilometers, pounds, or kilograms.
---
## Usage
When the user requests a unit conversion:
1. First, review `references/conversion-table.md` to find the correct factor
2. Run the `scripts/convert.py` script with `--value <number> --factor <factor>` (e.g. `--value 26.2 --factor 1.60934`)
3. Present the converted value clearly with both units
@@ -0,0 +1,10 @@
# Conversion Tables
Formula: **result = value × factor**
| From | To | Factor |
|-------------|-------------|----------|
| miles | kilometers | 1.60934 |
| kilometers | miles | 0.621371 |
| pounds | kilograms | 0.453592 |
| kilograms | pounds | 2.20462 |
@@ -0,0 +1,29 @@
# Unit conversion script
# Converts a value using a multiplication factor: result = value × factor
#
# Usage:
# python scripts/convert.py --value 26.2 --factor 1.60934
# python scripts/convert.py --value 75 --factor 2.20462
import argparse
import json
def main() -> None:
parser = argparse.ArgumentParser(
description="Convert a value using a multiplication factor.",
epilog="Examples:\n"
" python scripts/convert.py --value 26.2 --factor 1.60934\n"
" python scripts/convert.py --value 75 --factor 2.20462",
formatter_class=argparse.RawDescriptionHelpFormatter,
)
parser.add_argument("--value", type=float, required=True, help="The numeric value to convert.")
parser.add_argument("--factor", type=float, required=True, help="The conversion factor from the table.")
args = parser.parse_args()
result = round(args.value * args.factor, 4)
print(json.dumps({"value": args.value, "factor": args.factor, "result": result}))
if __name__ == "__main__":
main()
@@ -4,4 +4,4 @@ Samples demonstrating Agent Skills capabilities.
| Sample | Description |
|--------|-------------|
| [Agent_Step01_BasicSkills](Agent_Step01_BasicSkills/) | Using Agent Skills with a ChatClientAgent, including progressive disclosure and skill resources |
| [Agent_Step01_FileBasedSkills](Agent_Step01_FileBasedSkills/) | Define skills as `SKILL.md` files on disk with reference documents. Uses a unit-converter skill. |
@@ -0,0 +1,137 @@
// Copyright (c) Microsoft. All rights reserved.
// Sample subprocess-based skill script runner.
// Executes file-based skill scripts as local subprocesses.
// This is provided for demonstration purposes only.
using System.Diagnostics;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
/// <summary>
/// Executes file-based skill scripts as local subprocesses.
/// </summary>
/// <remarks>
/// This runner uses the script's absolute path, converts the arguments
/// to CLI flags, and returns captured output. It is intended for
/// demonstration purposes only.
/// </remarks>
internal static class SubprocessScriptRunner
{
/// <summary>
/// Runs a skill script as a local subprocess.
/// </summary>
public static async Task<object?> RunAsync(
AgentFileSkill skill,
AgentFileSkillScript script,
AIFunctionArguments arguments,
CancellationToken cancellationToken)
{
if (!File.Exists(script.FullPath))
{
return $"Error: Script file not found: {script.FullPath}";
}
string extension = Path.GetExtension(script.FullPath);
string? interpreter = extension switch
{
".py" => "python3",
".js" => "node",
".sh" => "bash",
".ps1" => "pwsh",
_ => null,
};
var startInfo = new ProcessStartInfo
{
RedirectStandardOutput = true,
RedirectStandardError = true,
UseShellExecute = false,
CreateNoWindow = true,
WorkingDirectory = Path.GetDirectoryName(script.FullPath) ?? ".",
};
if (interpreter is not null)
{
startInfo.FileName = interpreter;
startInfo.ArgumentList.Add(script.FullPath);
}
else
{
startInfo.FileName = script.FullPath;
}
if (arguments is not null)
{
foreach (var (key, value) in arguments)
{
if (value is bool boolValue)
{
if (boolValue)
{
startInfo.ArgumentList.Add(NormalizeKey(key));
}
}
else if (value is not null)
{
startInfo.ArgumentList.Add(NormalizeKey(key));
startInfo.ArgumentList.Add(value.ToString()!);
}
}
}
Process? process = null;
try
{
process = Process.Start(startInfo);
if (process is null)
{
return $"Error: Failed to start process for script '{script.Name}'.";
}
Task<string> outputTask = process.StandardOutput.ReadToEndAsync(cancellationToken);
Task<string> errorTask = process.StandardError.ReadToEndAsync(cancellationToken);
await process.WaitForExitAsync(cancellationToken).ConfigureAwait(false);
string output = await outputTask.ConfigureAwait(false);
string error = await errorTask.ConfigureAwait(false);
if (!string.IsNullOrEmpty(error))
{
output += $"\nStderr:\n{error}";
}
if (process.ExitCode != 0)
{
output += $"\nScript exited with code {process.ExitCode}";
}
return string.IsNullOrEmpty(output) ? "(no output)" : output.Trim();
}
catch (OperationCanceledException) when (cancellationToken.IsCancellationRequested)
{
// Kill the process on cancellation to avoid leaving orphaned subprocesses.
process?.Kill(entireProcessTree: true);
throw;
}
catch (OperationCanceledException)
{
throw;
}
catch (Exception ex)
{
return $"Error: Failed to execute script '{script.Name}': {ex.Message}";
}
finally
{
process?.Dispose();
}
}
/// <summary>
/// Normalizes a parameter key to a consistent --flag format.
/// Models may return keys with or without leading dashes (e.g., "value" vs "--value").
/// </summary>
private static string NormalizeKey(string key) => "--" + key.TrimStart('-');
}
@@ -10,8 +10,8 @@ var apiKey = Environment.GetEnvironmentVariable("OPENAI_API_KEY") ?? throw new I
var model = Environment.GetEnvironmentVariable("OPENAI_CHAT_MODEL_NAME") ?? "gpt-5";
var client = new OpenAIClient(apiKey)
.GetResponsesClient(model)
.AsIChatClient().AsBuilder()
.GetResponsesClient()
.AsIChatClient(model).AsBuilder()
.ConfigureOptions(o =>
{
o.Reasoning = new()
@@ -20,19 +20,21 @@ public class OpenAIResponseClientAgent : DelegatingAIAgent
/// <param name="instructions">Optional instructions for the agent.</param>
/// <param name="name">Optional name for the agent.</param>
/// <param name="description">Optional description for the agent.</param>
/// <param name="model">Optional default model ID to use for requests. Required when using a plain <see cref="ResponsesClient"/> (not via Azure OpenAI).</param>
/// <param name="loggerFactory">Optional instance of <see cref="ILoggerFactory"/></param>
public OpenAIResponseClientAgent(
ResponsesClient client,
string? instructions = null,
string? name = null,
string? description = null,
string? model = null,
ILoggerFactory? loggerFactory = null) :
this(client, new()
{
Name = name,
Description = description,
ChatOptions = new ChatOptions() { Instructions = instructions },
}, loggerFactory)
}, model, loggerFactory)
{
}
@@ -41,10 +43,11 @@ public class OpenAIResponseClientAgent : DelegatingAIAgent
/// </summary>
/// <param name="client">Instance of <see cref="ResponsesClient"/></param>
/// <param name="options">Options to create the agent.</param>
/// <param name="model">Optional default model ID to use for requests. Required when using a plain <see cref="ResponsesClient"/> (not via Azure OpenAI).</param>
/// <param name="loggerFactory">Optional instance of <see cref="ILoggerFactory"/></param>
public OpenAIResponseClientAgent(
ResponsesClient client, ChatClientAgentOptions options, ILoggerFactory? loggerFactory = null) :
base(new ChatClientAgent((client ?? throw new ArgumentNullException(nameof(client))).AsIChatClient(), options, loggerFactory))
ResponsesClient client, ChatClientAgentOptions options, string? model = null, ILoggerFactory? loggerFactory = null) :
base(new ChatClientAgent((client ?? throw new ArgumentNullException(nameof(client))).AsIChatClient(model), options, loggerFactory))
{
}
@@ -10,10 +10,10 @@ var apiKey = Environment.GetEnvironmentVariable("OPENAI_API_KEY") ?? throw new I
var model = Environment.GetEnvironmentVariable("OPENAI_CHAT_MODEL_NAME") ?? "gpt-4o-mini";
// Create a ResponsesClient directly from OpenAIClient
ResponsesClient responseClient = new OpenAIClient(apiKey).GetResponsesClient(model);
ResponsesClient responseClient = new OpenAIClient(apiKey).GetResponsesClient();
// Create an agent directly from the ResponsesClient using OpenAIResponseClientAgent
OpenAIResponseClientAgent agent = new(responseClient, instructions: "You are good at telling jokes.", name: "Joker");
OpenAIResponseClientAgent agent = new(responseClient, instructions: "You are good at telling jokes.", name: "Joker", model: model);
ResponseItem userMessage = ResponseItem.CreateUserMessageItem("Tell me a joke about a pirate.");
@@ -22,7 +22,7 @@ OpenAIClient openAIClient = new(apiKey);
ConversationClient conversationClient = openAIClient.GetConversationClient();
// Create an agent directly from the ResponsesClient using OpenAIResponseClientAgent
ChatClientAgent agent = new(openAIClient.GetResponsesClient(model).AsIChatClient(), instructions: "You are a helpful assistant.", name: "ConversationAgent");
ChatClientAgent agent = new(openAIClient.GetResponsesClient().AsIChatClient(model), instructions: "You are a helpful assistant.", name: "ConversationAgent");
ClientResult createConversationResult = await conversationClient.CreateConversationAsync(BinaryContent.Create(BinaryData.FromString("{}")));
@@ -73,16 +73,28 @@ foreach (ClientResult result in getConversationItemsResults.GetRawPages())
using JsonDocument getConversationItemsResultAsJson = JsonDocument.Parse(result.GetRawResponse().Content.ToString());
foreach (JsonElement element in getConversationItemsResultAsJson.RootElement.GetProperty("data").EnumerateArray())
{
// Skip non-message items (e.g. tool calls, reasoning) that lack a "role" property
if (!element.TryGetProperty("role"u8, out var roleElement))
{
continue;
}
string messageId = element.GetProperty("id"u8).ToString();
string messageRole = element.GetProperty("role"u8).ToString();
string messageRole = roleElement.ToString();
Console.WriteLine($" Message ID: {messageId}");
Console.WriteLine($" Message Role: {messageRole}");
foreach (var content in element.GetProperty("content").EnumerateArray())
if (element.TryGetProperty("content"u8, out var contentElement))
{
string messageContentText = content.GetProperty("text"u8).ToString();
Console.WriteLine($" Message Text: {messageContentText}");
foreach (var content in contentElement.EnumerateArray())
{
if (content.TryGetProperty("text"u8, out var textElement))
{
Console.WriteLine($" Message Text: {textElement}");
}
}
}
Console.WriteLine();
}
}
@@ -36,11 +36,11 @@ AIAgent agent = new AzureOpenAIClient(
// For simplicity, we are assuming here that only function approvals are pending.
AgentSession session = await agent.CreateSessionAsync();
AgentResponse response = await agent.RunAsync("What is the weather like in Amsterdam?", session);
List<FunctionApprovalRequestContent> approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<FunctionApprovalRequestContent>().ToList();
List<ToolApprovalRequestContent> approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<ToolApprovalRequestContent>().ToList();
// For streaming use:
// var updates = await agent.RunStreamingAsync("What is the weather like in Amsterdam?", session).ToListAsync();
// approvalRequests = updates.SelectMany(x => x.Contents).OfType<FunctionApprovalRequestContent>().ToList();
// approvalRequests = updates.SelectMany(x => x.Contents).OfType<ToolApprovalRequestContent>().ToList();
while (approvalRequests.Count > 0)
{
@@ -48,18 +48,18 @@ while (approvalRequests.Count > 0)
List<ChatMessage> userInputResponses = approvalRequests
.ConvertAll(functionApprovalRequest =>
{
Console.WriteLine($"The agent would like to invoke the following function, please reply Y to approve: Name {functionApprovalRequest.FunctionCall.Name}");
Console.WriteLine($"The agent would like to invoke the following function, please reply Y to approve: Name {((FunctionCallContent)functionApprovalRequest.ToolCall).Name}");
return new ChatMessage(ChatRole.User, [functionApprovalRequest.CreateResponse(Console.ReadLine()?.Equals("Y", StringComparison.OrdinalIgnoreCase) ?? false)]);
});
// Pass the user input responses back to the agent for further processing.
response = await agent.RunAsync(userInputResponses, session);
approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<FunctionApprovalRequestContent>().ToList();
approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<ToolApprovalRequestContent>().ToList();
// For streaming use:
// updates = await agent.RunStreamingAsync(userInputResponses, session).ToListAsync();
// approvalRequests = updates.SelectMany(x => x.Contents).OfType<FunctionApprovalRequestContent>().ToList();
// approvalRequests = updates.SelectMany(x => x.Contents).OfType<ToolApprovalRequestContent>().ToList();
}
Console.WriteLine($"\nAgent: {response}");
@@ -10,14 +10,14 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.Agents.Persistent" />
<PackageReference Include="Azure.AI.Projects" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.Hosting" />
<PackageReference Include="ModelContextProtocol" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.AzureAI.Persistent\Microsoft.Agents.AI.AzureAI.Persistent.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.AzureAI\Microsoft.Agents.AI.AzureAI.csproj" />
</ItemGroup>
</Project>
@@ -2,7 +2,7 @@
// This sample shows how to expose an AI agent as an MCP tool.
using Azure.AI.Agents.Persistent;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.DependencyInjection;
@@ -15,18 +15,15 @@ var deploymentName = Environment.GetEnvironmentVariable("AZURE_AI_MODEL_DEPLOYME
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
var persistentAgentsClient = new PersistentAgentsClient(endpoint, new DefaultAzureCredential());
var aiProjectClient = new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential());
// Create a server side persistent agent
var agentMetadata = await persistentAgentsClient.Administration.CreateAgentAsync(
// Create a server side agent and expose it as an AIAgent.
AIAgent agent = await aiProjectClient.CreateAIAgentAsync(
model: deploymentName,
instructions: "You are good at telling jokes, and you always start each joke with 'Aye aye, captain!'.",
name: "Joker",
description: "An agent that tells jokes.");
// Retrieve the server side persistent agent as an AIAgent.
AIAgent agent = await persistentAgentsClient.GetAIAgentAsync(agentMetadata.Value.Id);
// Convert the agent to an AIFunction and then to an MCP tool.
// The agent name and description will be used as the mcp tool name and description.
McpServerTool tool = McpServerTool.Create(agent.AsAIFunction());
@@ -16,5 +16,11 @@
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
</ItemGroup>
<ItemGroup>
<None Update="Assets\walkway.jpg">
<CopyToOutputDirectory>Always</CopyToOutputDirectory>
</None>
</ItemGroup>
</Project>
Binary file not shown.

After

Width:  |  Height:  |  Size: 37 KiB

@@ -22,7 +22,7 @@ var agent = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential(
ChatMessage message = new(ChatRole.User, [
new TextContent("What do you see in this image?"),
new UriContent("https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg", "image/jpeg")
await DataContent.LoadFromAsync("Assets/walkway.jpg"),
]);
var session = await agent.CreateSessionAsync();
@@ -25,8 +25,9 @@ var stateStore = new Dictionary<string, JsonElement?>();
AIAgent agent = new AzureOpenAIClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetResponsesClient(deploymentName)
.GetResponsesClient()
.AsAIAgent(
model: deploymentName,
name: "SpaceNovelWriter",
instructions: "You are a space novel writer. Always research relevant facts and generate character profiles for the main characters before writing novels." +
"Write complete chapters without asking for approval or feedback. Do not ask the user about tone, style, pace, or format preferences - just write the novel based on the request.",
@@ -246,7 +246,7 @@ async Task<AgentResponse> ConsolePromptingApprovalMiddleware(IEnumerable<ChatMes
AgentResponse response = await innerAgent.RunAsync(messages, session, options, cancellationToken);
// For simplicity, we are assuming here that only function approvals are pending.
List<FunctionApprovalRequestContent> approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<FunctionApprovalRequestContent>().ToList();
List<ToolApprovalRequestContent> approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<ToolApprovalRequestContent>().ToList();
while (approvalRequests.Count > 0)
{
@@ -255,13 +255,13 @@ async Task<AgentResponse> ConsolePromptingApprovalMiddleware(IEnumerable<ChatMes
response.Messages = approvalRequests
.ConvertAll(functionApprovalRequest =>
{
Console.WriteLine($"The agent would like to invoke the following function, please reply Y to approve: Name {functionApprovalRequest.FunctionCall.Name}");
Console.WriteLine($"The agent would like to invoke the following function, please reply Y to approve: Name {((FunctionCallContent)functionApprovalRequest.ToolCall).Name}");
return new ChatMessage(ChatRole.User, [functionApprovalRequest.CreateResponse(Console.ReadLine()?.Equals("Y", StringComparison.OrdinalIgnoreCase) ?? false)]);
});
response = await innerAgent.RunAsync(response.Messages, session, options, cancellationToken);
approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<FunctionApprovalRequestContent>().ToList();
approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<ToolApprovalRequestContent>().ToList();
}
return response;
@@ -16,8 +16,8 @@ var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT
AIAgent agent = new AzureOpenAIClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetResponsesClient(deploymentName)
.AsAIAgent();
.GetResponsesClient()
.AsAIAgent(model: deploymentName);
// Enable background responses (only supported by OpenAI Responses at this time).
AgentRunOptions options = new() { AllowBackgroundResponses = true };
@@ -1,5 +1,7 @@
// Copyright (c) Microsoft. All rights reserved.
#pragma warning disable CS0618 // Type or member is obsolete - sample uses deprecated PersistentAgentsClientExtensions
// This sample shows how to create an Azure AI Foundry Agent with the Deep Research Tool.
using Azure.AI.Agents.Persistent;
@@ -12,13 +12,9 @@
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
<PackageReference Include="Microsoft.Agents.ObjectModel" />
<PackageReference Include="Microsoft.Agents.ObjectModel.Json" />
<PackageReference Include="Microsoft.Agents.ObjectModel.PowerFx" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Declarative\Microsoft.Agents.AI.Declarative.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
</ItemGroup>
@@ -0,0 +1,20 @@
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
<TargetFrameworks>net10.0</TargetFrameworks>
<Nullable>enable</Nullable>
<ImplicitUsings>enable</ImplicitUsings>
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
</ItemGroup>
</Project>
@@ -0,0 +1,226 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample demonstrates how the ChatClientAgent persists chat history after each individual
// call to the AI service.
// When an agent uses tools, FunctionInvokingChatClient may loop multiple times
// (service call → tool execution → service call), and intermediate messages (tool calls and
// results) are persisted after each service call. This allows you to inspect or recover them
// even if the process is interrupted mid-loop, but may also result in chat history that is not
// yet finalized (e.g., tool calls without results) being persisted, which may be undesirable in some cases.
//
// To opt into end-of-run persistence instead (atomic run semantics), set
// PersistChatHistoryAtEndOfRun = true on ChatClientAgentOptions.
//
// The sample runs two multi-turn conversations: one using non-streaming (RunAsync) and one
// using streaming (RunStreamingAsync), to demonstrate correct behavior in both modes.
using System.ComponentModel;
using Azure.AI.OpenAI;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
using OpenAI.Responses;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-4o-mini";
var store = Environment.GetEnvironmentVariable("AZURE_OPENAI_RESPONSES_STORE") ?? "false";
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AzureOpenAIClient openAIClient = new(new Uri(endpoint), new DefaultAzureCredential());
// Define multiple tools so the model makes several tool calls in a single run.
[Description("Get the current weather for a city.")]
static string GetWeather([Description("The city name.")] string city) =>
city.ToUpperInvariant() switch
{
"SEATTLE" => "Seattle: 55°F, cloudy with light rain.",
"NEW YORK" => "New York: 72°F, sunny and warm.",
"LONDON" => "London: 48°F, overcast with fog.",
"DUBLIN" => "Dublin: 43°F, overcast with fog.",
_ => $"{city}: weather data not available."
};
[Description("Get the current time in a city.")]
static string GetTime([Description("The city name.")] string city) =>
city.ToUpperInvariant() switch
{
"SEATTLE" => "Seattle: 9:00 AM PST",
"NEW YORK" => "New York: 12:00 PM EST",
"LONDON" => "London: 5:00 PM GMT",
"DUBLIN" => "Dublin: 5:00 PM GMT",
_ => $"{city}: time data not available."
};
// Create the agent — per-service-call persistence is the default behavior.
// The in-memory ChatHistoryProvider is used by default when the service does not require service stored chat
// history, so for those cases, we can inspect the chat history via session.TryGetInMemoryChatHistory().
IChatClient chatClient = string.Equals(store, "TRUE", StringComparison.OrdinalIgnoreCase) ?
openAIClient.GetResponsesClient().AsIChatClient(deploymentName) :
openAIClient.GetResponsesClient().AsIChatClientWithStoredOutputDisabled(deploymentName);
AIAgent agent = chatClient.AsAIAgent(
new ChatClientAgentOptions
{
Name = "WeatherAssistant",
ChatOptions = new()
{
Instructions = "You are a helpful assistant. When asked about multiple cities, call the appropriate tool for each city.",
Tools = [AIFunctionFactory.Create(GetWeather), AIFunctionFactory.Create(GetTime)]
},
});
await RunNonStreamingAsync();
await RunStreamingAsync();
async Task RunNonStreamingAsync()
{
int lastChatHistorySize = 0;
string lastConversationId = string.Empty;
Console.ForegroundColor = ConsoleColor.Yellow;
Console.WriteLine("\n=== Non-Streaming Mode ===");
Console.ResetColor();
AgentSession session = await agent.CreateSessionAsync();
// First turn — ask about multiple cities so the model calls tools.
const string Prompt = "What's the weather and time in Seattle, New York, and London?";
PrintUserMessage(Prompt);
var response = await agent.RunAsync(Prompt, session);
PrintAgentResponse(response.Text);
PrintChatHistory(session, "After run", ref lastChatHistorySize, ref lastConversationId);
// Second turn — follow-up to verify chat history is correct.
const string FollowUp1 = "And Dublin?";
PrintUserMessage(FollowUp1);
response = await agent.RunAsync(FollowUp1, session);
PrintAgentResponse(response.Text);
PrintChatHistory(session, "After second run", ref lastChatHistorySize, ref lastConversationId);
// Third turn — follow-up to verify chat history is correct.
const string FollowUp2 = "Which city is the warmest?";
PrintUserMessage(FollowUp2);
response = await agent.RunAsync(FollowUp2, session);
PrintAgentResponse(response.Text);
PrintChatHistory(session, "After third run", ref lastChatHistorySize, ref lastConversationId);
}
async Task RunStreamingAsync()
{
int lastChatHistorySize = 0;
string lastConversationId = string.Empty;
Console.ForegroundColor = ConsoleColor.Yellow;
Console.WriteLine("\n=== Streaming Mode ===");
Console.ResetColor();
AgentSession session = await agent.CreateSessionAsync();
// First turn — ask about multiple cities so the model calls tools.
const string Prompt = "What's the weather and time in Seattle, New York, and London?";
PrintUserMessage(Prompt);
Console.ForegroundColor = ConsoleColor.Cyan;
Console.Write("\n[Agent] ");
Console.ResetColor();
await foreach (var update in agent.RunStreamingAsync(Prompt, session))
{
Console.Write(update);
// During streaming we should be able to see updates to the chat history
// before the full run completes, as each service call is made and persisted.
PrintChatHistory(session, "During run", ref lastChatHistorySize, ref lastConversationId);
}
Console.WriteLine();
PrintChatHistory(session, "After run", ref lastChatHistorySize, ref lastConversationId);
// Second turn — follow-up to verify chat history is correct.
const string FollowUp1 = "And Dublin?";
PrintUserMessage(FollowUp1);
Console.ForegroundColor = ConsoleColor.Cyan;
Console.Write("\n[Agent] ");
Console.ResetColor();
await foreach (var update in agent.RunStreamingAsync(FollowUp1, session))
{
Console.Write(update);
// During streaming we should be able to see updates to the chat history
// before the full run completes, as each service call is made and persisted.
PrintChatHistory(session, "During second run", ref lastChatHistorySize, ref lastConversationId);
}
Console.WriteLine();
PrintChatHistory(session, "After second run", ref lastChatHistorySize, ref lastConversationId);
// Third turn — follow-up to verify chat history is correct.
const string FollowUp2 = "Which city is the warmest?";
PrintUserMessage(FollowUp2);
Console.ForegroundColor = ConsoleColor.Cyan;
Console.Write("\n[Agent] ");
Console.ResetColor();
await foreach (var update in agent.RunStreamingAsync(FollowUp2, session))
{
Console.Write(update);
// During streaming we should be able to see updates to the chat history
// before the full run completes, as each service call is made and persisted.
PrintChatHistory(session, "During third run", ref lastChatHistorySize, ref lastConversationId);
}
Console.WriteLine();
PrintChatHistory(session, "After third run", ref lastChatHistorySize, ref lastConversationId);
}
void PrintUserMessage(string message)
{
Console.ForegroundColor = ConsoleColor.Cyan;
Console.Write("\n[User] ");
Console.ResetColor();
Console.WriteLine(message);
}
void PrintAgentResponse(string? text)
{
Console.ForegroundColor = ConsoleColor.Cyan;
Console.Write("\n[Agent] ");
Console.ResetColor();
Console.WriteLine(text);
}
// Helper to print the current chat history from the session.
void PrintChatHistory(AgentSession session, string label, ref int lastChatHistorySize, ref string lastConversationId)
{
if (session.TryGetInMemoryChatHistory(out var history) && history.Count != lastChatHistorySize)
{
Console.ForegroundColor = ConsoleColor.DarkGray;
Console.WriteLine($"\n [{label} — Chat history: {history.Count} message(s)]");
foreach (var msg in history)
{
var preview = msg.Text?.Length > 80 ? msg.Text[..80] + "…" : msg.Text;
var contentTypes = string.Join(", ", msg.Contents.Select(c => c.GetType().Name));
Console.WriteLine($" {msg.Role,-12} | {(string.IsNullOrWhiteSpace(preview) ? $"[{contentTypes}]" : preview)}");
}
Console.ResetColor();
lastChatHistorySize = history.Count;
}
if (session is ChatClientAgentSession ccaSession && ccaSession.ConversationId is not null && ccaSession.ConversationId != lastConversationId)
{
Console.ForegroundColor = ConsoleColor.DarkGray;
Console.WriteLine($" [{label} — Conversation ID: {ccaSession.ConversationId}]");
Console.ResetColor();
lastConversationId = ccaSession.ConversationId;
}
}
@@ -0,0 +1,63 @@
# In-Function-Loop Checkpointing
This sample demonstrates how `ChatClientAgent` persists chat history after each individual call to the AI service by default. This per-service-call persistence ensures intermediate progress is saved during the function invocation loop.
## What This Sample Shows
When an agent uses tools, the `FunctionInvokingChatClient` loops multiple times (service call → tool execution → service call → …). By default, chat history is persisted after each service call via the `ChatHistoryPersistingChatClient` decorator:
- A `ChatHistoryPersistingChatClient` decorator is automatically inserted into the chat client pipeline
- After each service call, the decorator notifies the `ChatHistoryProvider` (and any `AIContextProvider` instances) with the new messages
- Only **new** messages are sent to providers on each notification — messages that were already persisted in an earlier call within the same run are deduplicated automatically
To opt into end-of-run persistence instead (atomic run semantics), set `PersistChatHistoryAtEndOfRun = true` on `ChatClientAgentOptions`. In that mode, the decorator marks messages with metadata rather than persisting them immediately, and `ChatClientAgent` persists only the marked messages at the end of the run.
Per-service-call persistence is useful for:
- **Crash recovery** — if the process is interrupted mid-loop, the intermediate tool calls and results are already persisted
- **Observability** — you can inspect the chat history while the agent is still running (e.g., during streaming)
- **Long-running tool loops** — agents with many sequential tool calls benefit from incremental persistence
## How It Works
The sample asks the agent about the weather and time in three cities. The model calls the `GetWeather` and `GetTime` tools for each city, resulting in multiple service calls within a single `RunStreamingAsync` invocation. After the run completes, the sample prints the full chat history to show all the intermediate messages that were persisted along the way.
### Pipeline Architecture
```
ChatClientAgent
└─ FunctionInvokingChatClient (handles tool call loop)
└─ ChatHistoryPersistingChatClient (persists after each service call)
└─ Leaf IChatClient (Azure OpenAI)
```
## Prerequisites
- .NET 10 SDK or later
- Azure OpenAI service endpoint and model deployment
- Azure CLI installed and authenticated
**Note**: This sample uses `DefaultAzureCredential`. Sign in with `az login` before running. For production, prefer a specific credential such as `ManagedIdentityCredential`. For more information, see the [Azure CLI authentication documentation](https://learn.microsoft.com/cli/azure/authenticate-azure-cli-interactively).
## Environment Variables
```powershell
$env:AZURE_OPENAI_ENDPOINT="https://your-resource.openai.azure.com/" # Required
$env:AZURE_OPENAI_DEPLOYMENT_NAME="gpt-4o-mini" # Optional, defaults to gpt-4o-mini
```
## Running the Sample
```powershell
cd dotnet/samples/02-agents/Agents/Agent_Step19_InFunctionLoopCheckpointing
dotnet run
```
## Expected Behavior
The sample runs two conversation turns:
1. **First turn** — asks about weather and time in three cities. The model calls `GetWeather` and `GetTime` tools (potentially in parallel or sequentially), then provides a summary. The chat history dump after the run shows all the intermediate tool call and result messages.
2. **Second turn** — asks a follow-up question ("Which city is the warmest?") that uses the persisted conversation context. The chat history dump shows the full accumulated conversation.
The chat history printout uses `session.TryGetInMemoryChatHistory()` to inspect the in-memory storage.
@@ -45,6 +45,7 @@ Before you begin, ensure you have the following prerequisites:
|[Declarative agent](./Agent_Step16_Declarative/)|This sample demonstrates how to declaratively define an agent.|
|[Providing additional AI Context to an agent using multiple AIContextProviders](./Agent_Step17_AdditionalAIContext/)|This sample demonstrates how to inject additional AI context into a ChatClientAgent using multiple custom AIContextProvider components that are attached to the agent.|
|[Using compaction pipeline with an agent](./Agent_Step18_CompactionPipeline/)|This sample demonstrates how to use a compaction pipeline to efficiently limit the size of the conversation history for an agent.|
|[In-function-loop checkpointing](./Agent_Step19_InFunctionLoopCheckpointing/)|This sample demonstrates how to persist chat history after each service call during a tool-calling loop, enabling crash recovery and mid-run observability.|
## Running the samples from the console
@@ -3,7 +3,7 @@
// This sample shows how to create and use AI agents with Azure Foundry Agents as the backend.
using Azure.AI.Projects;
using Azure.AI.Projects.OpenAI;
using Azure.AI.Projects.Agents;
using Azure.Identity;
using Microsoft.Agents.AI;
@@ -3,7 +3,7 @@
// This sample shows how to create and use a simple AI agent with Azure Foundry Agents as the backend.
using Azure.AI.Projects;
using Azure.AI.Projects.OpenAI;
using Azure.AI.Projects.Agents;
using Azure.Identity;
using Microsoft.Agents.AI;
@@ -2,8 +2,9 @@
// This sample shows how to create and use a simple AI agent with a multi-turn conversation.
using Azure.AI.Extensions.OpenAI;
using Azure.AI.Projects;
using Azure.AI.Projects.OpenAI;
using Azure.AI.Projects.Agents;
using Azure.Identity;
using Microsoft.Agents.AI;
@@ -40,7 +40,7 @@ AgentResponse response = await agent.RunAsync("What is the weather like in Amste
// Check if there are any approval requests.
// For simplicity, we are assuming here that only function approvals are pending.
List<FunctionApprovalRequestContent> approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<FunctionApprovalRequestContent>().ToList();
List<ToolApprovalRequestContent> approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<ToolApprovalRequestContent>().ToList();
while (approvalRequests.Count > 0)
{
@@ -48,7 +48,7 @@ while (approvalRequests.Count > 0)
List<ChatMessage> userInputMessages = approvalRequests
.ConvertAll(functionApprovalRequest =>
{
Console.WriteLine($"The agent would like to invoke the following function, please reply Y to approve: Name {functionApprovalRequest.FunctionCall.Name}");
Console.WriteLine($"The agent would like to invoke the following function, please reply Y to approve: Name {((FunctionCallContent)functionApprovalRequest.ToolCall).Name}");
bool approved = Console.ReadLine()?.Equals("Y", StringComparison.OrdinalIgnoreCase) ?? false;
return new ChatMessage(ChatRole.User, [functionApprovalRequest.CreateResponse(approved)]);
});
@@ -56,7 +56,7 @@ while (approvalRequests.Count > 0)
// Pass the user input responses back to the agent for further processing.
response = await agent.RunAsync(userInputMessages, session);
approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<FunctionApprovalRequestContent>().ToList();
approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<ToolApprovalRequestContent>().ToList();
}
Console.WriteLine($"\nAgent: {response}");
@@ -24,7 +24,7 @@ AIAgent agent = await aiProjectClient.CreateAIAgentAsync(name: VisionName, model
ChatMessage message = new(ChatRole.User, [
new TextContent("What do you see in this image?"),
await DataContent.LoadFromAsync("assets/walkway.jpg"),
await DataContent.LoadFromAsync("Assets/walkway.jpg"),
]);
AgentSession session = await agent.CreateSessionAsync();
@@ -197,7 +197,7 @@ async Task<AgentResponse> ConsolePromptingApprovalMiddleware(IEnumerable<ChatMes
AgentResponse response = await innerAgent.RunAsync(messages, session, options, cancellationToken);
// For simplicity, we are assuming here that only function approvals are pending.
List<FunctionApprovalRequestContent> approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<FunctionApprovalRequestContent>().ToList();
List<ToolApprovalRequestContent> approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<ToolApprovalRequestContent>().ToList();
while (approvalRequests.Count > 0)
{
@@ -206,14 +206,14 @@ async Task<AgentResponse> ConsolePromptingApprovalMiddleware(IEnumerable<ChatMes
response.Messages = approvalRequests
.ConvertAll(functionApprovalRequest =>
{
Console.WriteLine($"The agent would like to invoke the following function, please reply Y to approve: Name {functionApprovalRequest.FunctionCall.Name}");
Console.WriteLine($"The agent would like to invoke the following function, please reply Y to approve: Name {((FunctionCallContent)functionApprovalRequest.ToolCall).Name}");
bool approved = Console.ReadLine()?.Equals("Y", StringComparison.OrdinalIgnoreCase) ?? false;
return new ChatMessage(ChatRole.User, [functionApprovalRequest.CreateResponse(approved)]);
});
response = await innerAgent.RunAsync(response.Messages, session, options, cancellationToken);
approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<FunctionApprovalRequestContent>().ToList();
approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<ToolApprovalRequestContent>().ToList();
}
return response;
@@ -4,7 +4,7 @@
using System.Text;
using Azure.AI.Projects;
using Azure.AI.Projects.OpenAI;
using Azure.AI.Projects.Agents;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
@@ -3,7 +3,7 @@
// This sample shows how to use Computer Use Tool with AI Agents.
using Azure.AI.Projects;
using Azure.AI.Projects.OpenAI;
using Azure.AI.Projects.Agents;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
@@ -3,7 +3,7 @@
// This sample shows how to use File Search Tool with AI Agents.
using Azure.AI.Projects;
using Azure.AI.Projects.OpenAI;
using Azure.AI.Projects.Agents;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
@@ -3,7 +3,7 @@
// This sample shows how to use OpenAPI Tools with AI Agents.
using Azure.AI.Projects;
using Azure.AI.Projects.OpenAI;
using Azure.AI.Projects.Agents;
using Azure.Identity;
using Microsoft.Agents.AI;
using OpenAI.Responses;
@@ -72,7 +72,7 @@ const string CountriesOpenApiSpec = """
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
// Create the OpenAPI function definition
var openApiFunction = new OpenAPIFunctionDefinition(
var openApiFunction = new OpenApiFunctionDefinition(
"get_countries",
BinaryData.FromString(CountriesOpenApiSpec),
new OpenAPIAnonymousAuthenticationDetails())
@@ -3,7 +3,7 @@
// This sample shows how to use Bing Custom Search Tool with AI Agents.
using Azure.AI.Projects;
using Azure.AI.Projects.OpenAI;
using Azure.AI.Projects.Agents;
using Azure.Identity;
using Microsoft.Agents.AI;
using OpenAI.Responses;
@@ -25,7 +25,7 @@ const string AgentInstructions = """
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
// Bing Custom Search tool parameters shared by both options
BingCustomSearchToolParameters bingCustomSearchToolParameters = new([
BingCustomSearchToolOptions bingCustomSearchToolParameters = new([
new BingCustomSearchConfiguration(connectionId, instanceName)
]);
@@ -3,7 +3,7 @@
// This sample shows how to use SharePoint Grounding Tool with AI Agents.
using Azure.AI.Projects;
using Azure.AI.Projects.OpenAI;
using Azure.AI.Projects.Agents;
using Azure.Identity;
using Microsoft.Agents.AI;
using OpenAI.Responses;
@@ -3,7 +3,7 @@
// This sample shows how to use Microsoft Fabric Tool with AI Agents.
using Azure.AI.Projects;
using Azure.AI.Projects.OpenAI;
using Azure.AI.Projects.Agents;
using Azure.Identity;
using Microsoft.Agents.AI;
using OpenAI.Responses;
@@ -3,7 +3,7 @@
// This sample shows how to use the Responses API Web Search Tool with AI Agents.
using Azure.AI.Projects;
using Azure.AI.Projects.OpenAI;
using Azure.AI.Projects.Agents;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
@@ -13,7 +13,6 @@
<PackageReference Include="Microsoft.Extensions.Logging.Console" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Azure.AI.Projects" />
<PackageReference Include="Azure.AI.Projects.OpenAI" />
</ItemGroup>
<ItemGroup>
@@ -4,8 +4,9 @@
// The Memory Search Tool enables agents to recall information from previous conversations,
// supporting user profile persistence and chat summaries across sessions.
using Azure.AI.Extensions.OpenAI;
using Azure.AI.Projects;
using Azure.AI.Projects.OpenAI;
using Azure.AI.Projects.Agents;
using Azure.Identity;
using Microsoft.Agents.AI;
using OpenAI.Responses;
@@ -36,7 +37,7 @@ AIProjectClient aiProjectClient = new(new Uri(endpoint), credential);
await EnsureMemoryStoreAsync();
// Create the Memory Search tool configuration
MemorySearchPreviewTool memorySearchTool = new(memoryStoreName, userScope) { UpdateDelay = 0 };
MemorySearchPreviewTool memorySearchTool = new(memoryStoreName, userScope) { UpdateDelayInSecs = 0 };
// Create agent using Option 1 (MEAI) or Option 2 (Native SDK)
AIAgent agent = await CreateAgentWithMEAI();
@@ -128,8 +129,8 @@ async Task EnsureMemoryStoreAsync()
MemoryUpdateResult updateResult = await aiProjectClient.MemoryStores.WaitForMemoriesUpdateAsync(
memoryStoreName: memoryStoreName,
options: memoryOptions,
pollingInterval: 500);
pollingInterval: 500,
options: memoryOptions);
if (updateResult.Status == MemoryStoreUpdateStatus.Failed)
{
@@ -9,12 +9,12 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.Agents.Persistent" />
<PackageReference Include="Azure.AI.Projects" />
<PackageReference Include="Azure.Identity" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.AzureAI.Persistent\Microsoft.Agents.AI.AzureAI.Persistent.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.AzureAI\Microsoft.Agents.AI.AzureAI.csproj" />
</ItemGroup>
</Project>
@@ -4,7 +4,7 @@
// In this case the Azure Foundry Agents service will invoke any MCP tools as required. MCP tools are not invoked by the Agent Framework.
// The sample first shows how to use MCP tools with auto approval, and then how to set up a tool that requires approval before it can be invoked and how to approve such a tool.
using Azure.AI.Agents.Persistent;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
@@ -16,7 +16,7 @@ var model = Environment.GetEnvironmentVariable("AZURE_AI_MODEL_DEPLOYMENT_NAME")
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
var persistentAgentsClient = new PersistentAgentsClient(endpoint, new DefaultAzureCredential());
var aiProjectClient = new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential());
// **** MCP Tool with Auto Approval ****
// *************************************
@@ -31,8 +31,8 @@ var mcpTool = new HostedMcpServerTool(
ApprovalMode = HostedMcpServerToolApprovalMode.NeverRequire
};
// Create a server side persistent agent with the mcp tool, and expose it as an AIAgent.
AIAgent agent = await persistentAgentsClient.CreateAIAgentAsync(
// Create a server side agent with the mcp tool, and expose it as an AIAgent.
AIAgent agent = await aiProjectClient.CreateAIAgentAsync(
model: model,
options: new()
{
@@ -49,7 +49,7 @@ AgentSession session = await agent.CreateSessionAsync();
Console.WriteLine(await agent.RunAsync("Please summarize the Azure AI Agent documentation related to MCP Tool calling?", session));
// Cleanup for sample purposes.
await persistentAgentsClient.Administration.DeleteAgentAsync(agent.Id);
aiProjectClient.Agents.DeleteAgent(agent.Name);
// **** MCP Tool with Approval Required ****
// *****************************************
@@ -64,8 +64,8 @@ var mcpToolWithApproval = new HostedMcpServerTool(
ApprovalMode = HostedMcpServerToolApprovalMode.AlwaysRequire
};
// Create an agent based on Azure OpenAI Responses as the backend.
AIAgent agentWithRequiredApproval = await persistentAgentsClient.CreateAIAgentAsync(
// Create an agent with the MCP tool that requires approval.
AIAgent agentWithRequiredApproval = await aiProjectClient.CreateAIAgentAsync(
model: model,
options: new()
{
@@ -81,7 +81,7 @@ AIAgent agentWithRequiredApproval = await persistentAgentsClient.CreateAIAgentAs
// For simplicity, we are assuming here that only mcp tool approvals are pending.
AgentSession sessionWithRequiredApproval = await agentWithRequiredApproval.CreateSessionAsync();
AgentResponse response = await agentWithRequiredApproval.RunAsync("Please summarize the Azure AI Agent documentation related to MCP Tool calling?", sessionWithRequiredApproval);
List<McpServerToolApprovalRequestContent> approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<McpServerToolApprovalRequestContent>().ToList();
List<ToolApprovalRequestContent> approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<ToolApprovalRequestContent>().ToList();
while (approvalRequests.Count > 0)
{
@@ -89,11 +89,12 @@ while (approvalRequests.Count > 0)
List<ChatMessage> userInputResponses = approvalRequests
.ConvertAll(approvalRequest =>
{
McpServerToolCallContent mcpToolCall = (McpServerToolCallContent)approvalRequest.ToolCall!;
Console.WriteLine($"""
The agent would like to invoke the following MCP Tool, please reply Y to approve.
ServerName: {approvalRequest.ToolCall.ServerName}
Name: {approvalRequest.ToolCall.ToolName}
Arguments: {string.Join(", ", approvalRequest.ToolCall.Arguments?.Select(x => $"{x.Key}: {x.Value}") ?? [])}
ServerName: {mcpToolCall.ServerName}
Name: {mcpToolCall.Name}
Arguments: {string.Join(", ", mcpToolCall.Arguments?.Select(x => $"{x.Key}: {x.Value}") ?? [])}
""");
return new ChatMessage(ChatRole.User, [approvalRequest.CreateResponse(Console.ReadLine()?.Equals("Y", StringComparison.OrdinalIgnoreCase) ?? false)]);
});
@@ -101,7 +102,7 @@ while (approvalRequests.Count > 0)
// Pass the user input responses back to the agent for further processing.
response = await agentWithRequiredApproval.RunAsync(userInputResponses, sessionWithRequiredApproval);
approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<McpServerToolApprovalRequestContent>().ToList();
approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<ToolApprovalRequestContent>().ToList();
}
Console.WriteLine($"\nAgent: {response}");
@@ -33,8 +33,9 @@ var mcpTool = new HostedMcpServerTool(
AIAgent agent = new AzureOpenAIClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetResponsesClient(deploymentName)
.GetResponsesClient()
.AsAIAgent(
model: deploymentName,
instructions: "You answer questions by searching the Microsoft Learn content only.",
name: "MicrosoftLearnAgent",
tools: [mcpTool]);
@@ -60,8 +61,9 @@ var mcpToolWithApproval = new HostedMcpServerTool(
AIAgent agentWithRequiredApproval = new AzureOpenAIClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetResponsesClient(deploymentName)
.GetResponsesClient()
.AsAIAgent(
model: deploymentName,
instructions: "You answer questions by searching the Microsoft Learn content only.",
name: "MicrosoftLearnAgentWithApproval",
tools: [mcpToolWithApproval]);
@@ -70,7 +72,7 @@ AIAgent agentWithRequiredApproval = new AzureOpenAIClient(
// For simplicity, we are assuming here that only mcp tool approvals are pending.
AgentSession sessionWithRequiredApproval = await agentWithRequiredApproval.CreateSessionAsync();
AgentResponse response = await agentWithRequiredApproval.RunAsync("Please summarize the Azure AI Agent documentation related to MCP Tool calling?", sessionWithRequiredApproval);
List<McpServerToolApprovalRequestContent> approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<McpServerToolApprovalRequestContent>().ToList();
List<ToolApprovalRequestContent> approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<ToolApprovalRequestContent>().ToList();
while (approvalRequests.Count > 0)
{
@@ -78,11 +80,12 @@ while (approvalRequests.Count > 0)
List<ChatMessage> userInputResponses = approvalRequests
.ConvertAll(approvalRequest =>
{
McpServerToolCallContent mcpToolCall = (McpServerToolCallContent)approvalRequest.ToolCall!;
Console.WriteLine($"""
The agent would like to invoke the following MCP Tool, please reply Y to approve.
ServerName: {approvalRequest.ToolCall.ServerName}
Name: {approvalRequest.ToolCall.ToolName}
Arguments: {string.Join(", ", approvalRequest.ToolCall.Arguments?.Select(x => $"{x.Key}: {x.Value}") ?? [])}
ServerName: {mcpToolCall.ServerName}
Name: {mcpToolCall.Name}
Arguments: {string.Join(", ", mcpToolCall.Arguments?.Select(x => $"{x.Key}: {x.Value}") ?? [])}
""");
return new ChatMessage(ChatRole.User, [approvalRequest.CreateResponse(Console.ReadLine()?.Equals("Y", StringComparison.OrdinalIgnoreCase) ?? false)]);
});
@@ -90,7 +93,7 @@ while (approvalRequests.Count > 0)
// Pass the user input responses back to the agent for further processing.
response = await agentWithRequiredApproval.RunAsync(userInputResponses, sessionWithRequiredApproval);
approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<McpServerToolApprovalRequestContent>().ToList();
approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<ToolApprovalRequestContent>().ToList();
}
Console.WriteLine($"\nAgent: {response}");
@@ -61,6 +61,12 @@ public static class Program
{
Console.WriteLine($"{outputEvent}");
}
if (evt is WorkflowErrorEvent errorEvent)
{
Console.WriteLine($"Workflow error: {errorEvent.Exception?.Message}");
Console.WriteLine($"Details: {errorEvent.Exception}");
}
}
}
}
@@ -175,7 +181,9 @@ internal sealed class FeedbackEvent(FeedbackResult feedbackResult) : WorkflowEve
/// <summary>
/// A custom executor that uses an AI agent to provide feedback on a slogan.
/// </summary>
internal sealed class FeedbackExecutor : Executor<SloganResult>
[SendsMessage(typeof(FeedbackResult))]
[YieldsOutput(typeof(string))]
internal sealed partial class FeedbackExecutor : Executor<SloganResult>
{
private readonly AIAgent _agent;
private AgentSession? _session;
@@ -9,13 +9,13 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.Agents.Persistent" />
<PackageReference Include="Azure.AI.Projects" />
<PackageReference Include="Azure.Identity" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Workflows\Microsoft.Agents.AI.Workflows.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.AzureAI.Persistent\Microsoft.Agents.AI.AzureAI.Persistent.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.AzureAI\Microsoft.Agents.AI.AzureAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI\Microsoft.Agents.AI.csproj" />
</ItemGroup>
@@ -1,6 +1,6 @@
// Copyright (c) Microsoft. All rights reserved.
using Azure.AI.Agents.Persistent;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.Workflows;
@@ -20,60 +20,63 @@ public static class Program
{
private static async Task Main()
{
// Set up the Azure OpenAI client
// Set up the Azure AI Project client
var endpoint = Environment.GetEnvironmentVariable("AZURE_AI_PROJECT_ENDPOINT")
?? throw new InvalidOperationException("AZURE_AI_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_AI_MODEL_DEPLOYMENT_NAME") ?? "gpt-4o-mini";
var persistentAgentsClient = new PersistentAgentsClient(endpoint, new AzureCliCredential());
var aiProjectClient = new AIProjectClient(new Uri(endpoint), new AzureCliCredential());
// Create agents
AIAgent frenchAgent = await GetTranslationAgentAsync("French", persistentAgentsClient, deploymentName);
AIAgent spanishAgent = await GetTranslationAgentAsync("Spanish", persistentAgentsClient, deploymentName);
AIAgent englishAgent = await GetTranslationAgentAsync("English", persistentAgentsClient, deploymentName);
AIAgent frenchAgent = await CreateTranslationAgentAsync("French", aiProjectClient, deploymentName);
AIAgent spanishAgent = await CreateTranslationAgentAsync("Spanish", aiProjectClient, deploymentName);
AIAgent englishAgent = await CreateTranslationAgentAsync("English", aiProjectClient, deploymentName);
// Build the workflow by adding executors and connecting them
var workflow = new WorkflowBuilder(frenchAgent)
.AddEdge(frenchAgent, spanishAgent)
.AddEdge(spanishAgent, englishAgent)
.Build();
// Execute the workflow
await using StreamingRun run = await InProcessExecution.RunStreamingAsync(workflow, new ChatMessage(ChatRole.User, "Hello World!"));
// Must send the turn token to trigger the agents.
// The agents are wrapped as executors. When they receive messages,
// they will cache the messages and only start processing when they receive a TurnToken.
await run.TrySendMessageAsync(new TurnToken(emitEvents: true));
await foreach (WorkflowEvent evt in run.WatchStreamAsync())
try
{
if (evt is AgentResponseUpdateEvent executorComplete)
// Build the workflow by adding executors and connecting them
var workflow = new WorkflowBuilder(frenchAgent)
.AddEdge(frenchAgent, spanishAgent)
.AddEdge(spanishAgent, englishAgent)
.Build();
// Execute the workflow
await using StreamingRun run = await InProcessExecution.RunStreamingAsync(workflow, new ChatMessage(ChatRole.User, "Hello World!"));
// Must send the turn token to trigger the agents.
// The agents are wrapped as executors. When they receive messages,
// they will cache the messages and only start processing when they receive a TurnToken.
await run.TrySendMessageAsync(new TurnToken(emitEvents: true));
await foreach (WorkflowEvent evt in run.WatchStreamAsync())
{
Console.WriteLine($"{executorComplete.ExecutorId}: {executorComplete.Data}");
if (evt is AgentResponseUpdateEvent executorComplete)
{
Console.WriteLine($"{executorComplete.ExecutorId}: {executorComplete.Data}");
}
}
}
// Cleanup the agents created for the sample.
await persistentAgentsClient.Administration.DeleteAgentAsync(frenchAgent.Id);
await persistentAgentsClient.Administration.DeleteAgentAsync(spanishAgent.Id);
await persistentAgentsClient.Administration.DeleteAgentAsync(englishAgent.Id);
finally
{
// Cleanup the agents created for the sample.
await aiProjectClient.Agents.DeleteAgentAsync(frenchAgent.Name);
await aiProjectClient.Agents.DeleteAgentAsync(spanishAgent.Name);
await aiProjectClient.Agents.DeleteAgentAsync(englishAgent.Name);
}
}
/// <summary>
/// Creates a translation agent for the specified target language.
/// </summary>
/// <param name="targetLanguage">The target language for translation</param>
/// <param name="persistentAgentsClient">The PersistentAgentsClient to create the agent</param>
/// <param name="aiProjectClient">The <see cref="AIProjectClient"/> to create the agent with.</param>
/// <param name="model">The model to use for the agent</param>
/// <returns>A ChatClientAgent configured for the specified language</returns>
private static async Task<ChatClientAgent> GetTranslationAgentAsync(
private static async Task<ChatClientAgent> CreateTranslationAgentAsync(
string targetLanguage,
PersistentAgentsClient persistentAgentsClient,
AIProjectClient aiProjectClient,
string model)
{
var agentMetadata = await persistentAgentsClient.Administration.CreateAgentAsync(
model: model,
return await aiProjectClient.CreateAIAgentAsync(
name: $"{targetLanguage} Translator",
model: model,
instructions: $"You are a translation assistant that translates the provided text to {targetLanguage}.");
return await persistentAgentsClient.GetAIAgentAsync(agentMetadata.Value.Id);
}
}
@@ -17,7 +17,7 @@
//
// Demonstrate:
// - Using custom GroupChatManager with agents that have approval-required tools.
// - Handling FunctionApprovalRequestContent in group chat scenarios.
// - Handling ToolApprovalRequestContent in group chat scenarios.
// - Multi-round group chat with tool approval interruption and resumption.
using System.ComponentModel;
@@ -101,16 +101,16 @@ public static class Program
{
case RequestInfoEvent e:
{
if (e.Request.TryGetDataAs(out FunctionApprovalRequestContent? approvalRequestContent))
if (e.Request.TryGetDataAs(out ToolApprovalRequestContent? approvalRequestContent))
{
Console.WriteLine();
Console.WriteLine($"[APPROVAL REQUIRED] From agent: {e.Request.PortInfo.PortId}");
Console.WriteLine($" Tool: {approvalRequestContent.FunctionCall.Name}");
Console.WriteLine($" Arguments: {JsonSerializer.Serialize(approvalRequestContent.FunctionCall.Arguments)}");
Console.WriteLine($" Tool: {((FunctionCallContent)approvalRequestContent.ToolCall).Name}");
Console.WriteLine($" Arguments: {JsonSerializer.Serialize(((FunctionCallContent)approvalRequestContent.ToolCall).Arguments)}");
Console.WriteLine();
// Approve the tool call request
Console.WriteLine($"Tool: {approvalRequestContent.FunctionCall.Name} approved");
Console.WriteLine($"Tool: {((FunctionCallContent)approvalRequestContent.ToolCall).Name} approved");
await run.SendResponseAsync(e.Request.CreateResponse(approvalRequestContent.CreateResponse(approved: true)));
}
@@ -9,7 +9,7 @@ using Microsoft.Extensions.AI;
namespace WorkflowAsAnAgentSample;
/// <summary>
/// This sample introduces the concepts workflows as agents, where a workflow can be
/// This sample introduces the concept of workflows as agents, where a workflow can be
/// treated as an <see cref="AIAgent"/>. This allows you to interact with a workflow
/// as if it were a single agent.
///
@@ -18,6 +18,14 @@ namespace WorkflowAsAnAgentSample;
///
/// You will interact with the workflow in an interactive loop, sending messages and receiving
/// streaming responses from the workflow as if it were an agent who responds in both languages.
///
/// This sample also demonstrates <see cref="IResettableExecutor"/>, which is required
/// for stateful executors that are shared across multiple workflow runs. Each iteration
/// of the interactive loop triggers a new workflow run against the same workflow instance.
/// Between runs, the framework automatically calls <see cref="IResettableExecutor.ResetAsync"/>
/// on shared executors so that accumulated state (e.g., collected messages) is cleared
/// before the next run begins. See <c>WorkflowFactory.ConcurrentAggregationExecutor</c>
/// for the implementation.
/// </summary>
/// <remarks>
/// Pre-requisites:
@@ -39,7 +47,10 @@ public static class Program
var agent = workflow.AsAIAgent("workflow-agent", "Workflow Agent");
var session = await agent.CreateSessionAsync();
// Start an interactive loop to interact with the workflow as if it were an agent
// Start an interactive loop to interact with the workflow as if it were an agent.
// Each iteration runs the workflow again on the same workflow instance. Between runs,
// the framework calls IResettableExecutor.ResetAsync() on shared stateful executors
// (like ConcurrentAggregationExecutor) to clear accumulated state from the previous run.
while (true)
{
Console.WriteLine();
@@ -10,6 +10,14 @@ internal static class WorkflowFactory
{
/// <summary>
/// Creates a workflow that uses two language agents to process input concurrently.
///
/// In this workflow, the <c>Start</c> <see cref="ChatForwardingExecutor"/> and the
/// <see cref="ConcurrentAggregationExecutor"/> are provided as shared instances, meaning
/// the same executor objects are reused across multiple workflow runs. The language agents
/// (French and English) are created via a factory and instantiated per workflow run.
/// Stateful shared executors must implement <see cref="IResettableExecutor"/> so the
/// framework can clear their state between runs. Framework-provided executors like
/// <see cref="ChatForwardingExecutor"/> already implement this interface.
/// </summary>
/// <param name="chatClient">The chat client to use for the agents</param>
/// <returns>A workflow that processes input using two language agents</returns>
@@ -40,7 +48,18 @@ internal static class WorkflowFactory
/// <summary>
/// Executor that aggregates the results from the concurrent agents.
///
/// This executor is stateful — it accumulates messages in <see cref="_messages"/>
/// as they arrive from each agent. Because it is provided as a shared instance
/// (not via a factory), the same object is reused across workflow runs. Implementing
/// <see cref="IResettableExecutor"/> allows the framework to call <see cref="ResetAsync"/>
/// between runs, clearing accumulated state so each run starts fresh.
///
/// Without <see cref="IResettableExecutor"/>, attempting to reuse a workflow containing
/// shared executor instances that do not implement this interface would throw an
/// <see cref="InvalidOperationException"/>.
/// </summary>
[YieldsOutput(typeof(string))]
private sealed class ConcurrentAggregationExecutor() :
Executor<List<ChatMessage>>("ConcurrentAggregationExecutor"), IResettableExecutor
{
@@ -64,7 +83,11 @@ internal static class WorkflowFactory
}
}
/// <inheritdoc/>
/// <summary>
/// Resets the executor state between workflow runs by clearing accumulated messages.
/// The framework calls this automatically when a workflow run completes, before the
/// workflow can be used for another run.
/// </summary>
public ValueTask ResetAsync()
{
this._messages.Clear();
@@ -41,6 +41,7 @@ internal enum NumberSignal
/// <summary>
/// Executor that makes a guess based on the current bounds.
/// </summary>
[SendsMessage(typeof(int))]
internal sealed class GuessNumberExecutor() : Executor<NumberSignal>("Guess")
{
/// <summary>
@@ -104,6 +105,8 @@ internal sealed class GuessNumberExecutor() : Executor<NumberSignal>("Guess")
/// <summary>
/// Executor that judges the guess and provides feedback.
/// </summary>
[SendsMessage(typeof(NumberSignal))]
[YieldsOutput(typeof(string))]
internal sealed class JudgeExecutor() : Executor<int>("Judge")
{
private readonly int _targetNumber;
@@ -41,6 +41,7 @@ internal enum NumberSignal
/// <summary>
/// Executor that makes a guess based on the current bounds.
/// </summary>
[SendsMessage(typeof(int))]
internal sealed class GuessNumberExecutor() : Executor<NumberSignal>("Guess")
{
/// <summary>
@@ -104,6 +105,8 @@ internal sealed class GuessNumberExecutor() : Executor<NumberSignal>("Guess")
/// <summary>
/// Executor that judges the guess and provides feedback.
/// </summary>
[SendsMessage(typeof(NumberSignal))]
[YieldsOutput(typeof(string))]
internal sealed class JudgeExecutor() : Executor<int>("Judge")
{
private readonly int _targetNumber;
@@ -53,6 +53,8 @@ internal sealed class SignalWithNumber
/// <summary>
/// Executor that judges the guess and provides feedback.
/// </summary>
[SendsMessage(typeof(SignalWithNumber))]
[YieldsOutput(typeof(string))]
internal sealed class JudgeExecutor() : Executor<int>("Judge")
{
private readonly int _targetNumber;
@@ -72,6 +72,8 @@ public static class Program
/// <summary>
/// Executor that starts the concurrent processing by sending messages to the agents.
/// </summary>
[SendsMessage(typeof(ChatMessage))]
[SendsMessage(typeof(TurnToken))]
internal sealed partial class ConcurrentStartExecutor() :
Executor("ConcurrentStartExecutor")
{
@@ -97,7 +99,8 @@ internal sealed partial class ConcurrentStartExecutor() :
/// <summary>
/// Executor that aggregates the results from the concurrent agents.
/// </summary>
internal sealed class ConcurrentAggregationExecutor() :
[YieldsOutput(typeof(string))]
internal sealed partial class ConcurrentAggregationExecutor() :
Executor<List<ChatMessage>>("ConcurrentAggregationExecutor")
{
private readonly List<ChatMessage> _messages = [];
@@ -128,6 +128,7 @@ public static class Program
/// <summary>
/// Splits data into roughly equal chunks based on the number of mapper nodes.
/// </summary>
[SendsMessage(typeof(SplitComplete))]
internal sealed class Split(string[] mapperIds, string id) :
Executor<string>(id)
{
@@ -186,6 +187,7 @@ internal sealed class Split(string[] mapperIds, string id) :
/// <summary>
/// Maps each token to a count of 1 and writes pairs to a per-mapper file.
/// </summary>
[SendsMessage(typeof(MapComplete))]
internal sealed class Mapper(string id) : Executor<SplitComplete>(id)
{
/// <summary>
@@ -212,6 +214,7 @@ internal sealed class Mapper(string id) : Executor<SplitComplete>(id)
/// <summary>
/// Groups intermediate pairs by key and partitions them across reducers.
/// </summary>
[SendsMessage(typeof(ShuffleComplete))]
internal sealed class Shuffler(string[] reducerIds, string[] mapperIds, string id) :
Executor<MapComplete>(id)
{
@@ -311,6 +314,7 @@ internal sealed class Shuffler(string[] reducerIds, string[] mapperIds, string i
/// <summary>
/// Sums grouped counts per key for its assigned partition.
/// </summary>
[SendsMessage(typeof(ReduceComplete))]
internal sealed class Reducer(string id) : Executor<ShuffleComplete>(id)
{
/// <summary>
@@ -352,6 +356,7 @@ internal sealed class Reducer(string id) : Executor<ShuffleComplete>(id)
/// <summary>
/// Joins all reducer outputs and yields the final output.
/// </summary>
[YieldsOutput(typeof(List<string>))]
internal sealed class CompletionExecutor(string id) :
Executor<List<ReduceComplete>>(id)
{
@@ -228,6 +228,7 @@ internal sealed class EmailAssistantExecutor : Executor<DetectionResult, EmailRe
/// <summary>
/// Executor that sends emails.
/// </summary>
[YieldsOutput(typeof(string))]
internal sealed class SendEmailExecutor() : Executor<EmailResponse>("SendEmailExecutor")
{
/// <summary>
@@ -240,6 +241,7 @@ internal sealed class SendEmailExecutor() : Executor<EmailResponse>("SendEmailEx
/// <summary>
/// Executor that handles spam messages.
/// </summary>
[YieldsOutput(typeof(string))]
internal sealed class HandleSpamExecutor() : Executor<DetectionResult>("HandleSpamExecutor")
{
/// <summary>
@@ -252,6 +252,7 @@ internal sealed class EmailAssistantExecutor : Executor<DetectionResult, EmailRe
/// <summary>
/// Executor that sends emails.
/// </summary>
[YieldsOutput(typeof(string))]
internal sealed class SendEmailExecutor() : Executor<EmailResponse>("SendEmailExecutor")
{
/// <summary>
@@ -264,6 +265,7 @@ internal sealed class SendEmailExecutor() : Executor<EmailResponse>("SendEmailEx
/// <summary>
/// Executor that handles spam messages.
/// </summary>
[YieldsOutput(typeof(string))]
internal sealed class HandleSpamExecutor() : Executor<DetectionResult>("HandleSpamExecutor")
{
/// <summary>
@@ -285,6 +287,7 @@ internal sealed class HandleSpamExecutor() : Executor<DetectionResult>("HandleSp
/// <summary>
/// Executor that handles uncertain emails.
/// </summary>
[YieldsOutput(typeof(string))]
internal sealed class HandleUncertainExecutor() : Executor<DetectionResult>("HandleUncertainExecutor")
{
/// <summary>
@@ -310,6 +310,7 @@ internal sealed class EmailAssistantExecutor : Executor<AnalysisResult, EmailRes
/// <summary>
/// Executor that sends emails.
/// </summary>
[YieldsOutput(typeof(string))]
internal sealed class SendEmailExecutor() : Executor<EmailResponse>("SendEmailExecutor")
{
/// <summary>
@@ -322,6 +323,7 @@ internal sealed class SendEmailExecutor() : Executor<EmailResponse>("SendEmailEx
/// <summary>
/// Executor that handles spam messages.
/// </summary>
[YieldsOutput(typeof(string))]
internal sealed class HandleSpamExecutor() : Executor<AnalysisResult>("HandleSpamExecutor")
{
/// <summary>
@@ -343,6 +345,7 @@ internal sealed class HandleSpamExecutor() : Executor<AnalysisResult>("HandleSpa
/// <summary>
/// Executor that handles uncertain messages.
/// </summary>
[YieldsOutput(typeof(string))]
internal sealed class HandleUncertainExecutor() : Executor<AnalysisResult>("HandleUncertainExecutor")
{
/// <summary>
@@ -1,7 +1,7 @@
// Copyright (c) Microsoft. All rights reserved.
using Azure.AI.Projects;
using Azure.AI.Projects.OpenAI;
using Azure.AI.Projects.Agents;
using Azure.Identity;
using Microsoft.Extensions.AI;
using Microsoft.Extensions.Configuration;
@@ -1,7 +1,7 @@
// Copyright (c) Microsoft. All rights reserved.
using Azure.AI.Projects;
using Azure.AI.Projects.OpenAI;
using Azure.AI.Projects.Agents;
using Azure.Identity;
using Microsoft.Extensions.Configuration;
using OpenAI.Responses;
@@ -275,7 +275,7 @@ internal sealed class Program
Tools =
{
AgentTool.CreateOpenApiTool(
new OpenAPIFunctionDefinition(
new OpenApiFunctionDefinition(
"weather-forecast",
BinaryData.FromString(File.ReadAllText(Path.Combine(AppContext.BaseDirectory, "wttr.json"))),
new OpenAPIAnonymousAuthenticationDetails()))

Some files were not shown because too many files have changed in this diff Show More