Compare commits

...
Author SHA1 Message Date
Dmytro StrukandGitHub f5786b2c5b Updated package versions (#2643) 2025-12-04 22:08:47 +00:00
Tao ChenandGitHub d858c23bab Fix observability module mypy error (#2641) 2025-12-04 19:11:05 +00:00
Giles OdigweandGitHub 365e438981 Python: AzureAI Local MCP Sample (#2616)
* added azure ai local mcp sample

* small fix

* handling for local mcp

* remove redundant local mcp handling
2025-12-04 19:10:00 +00:00
01a04a3114 seal options and context classes (#2633)
Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com>
2025-12-04 13:16:14 +00:00
Roger BarretoandGitHub ee340bef1d Address vulnerability (#2631) 2025-12-04 11:42:35 +00:00
Evan MattsonandGitHub 19ac6e57c0 Python [BREAKING]: support magentic agent tool call approvals and plan stalling HITL behavior (#2569)
* Provide way for HITL with magentic

* support tool call approvals and hitl stall replan

* human plan intervention sample

* Clean up

* Improve loging

* updates
2025-12-04 05:13:27 +00:00
CopilotGitHubmoonbox3copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>Evan Mattson
292a2078fa Python: Fix: AgentRunResponse.created_at returns local datetime labeled as UTC (#2590)
* Initial plan

* Fix created_at to use UTC datetime and add unit tests

Co-authored-by: moonbox3 <35585003+moonbox3@users.noreply.github.com>

* Address code review feedback: move datetime imports to top of test files

Co-authored-by: moonbox3 <35585003+moonbox3@users.noreply.github.com>

* Add UTC timestamp test for OpenAIResponsesClient._create_response_content

Co-authored-by: moonbox3 <35585003+moonbox3@users.noreply.github.com>

* Fix lint issue

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: moonbox3 <35585003+moonbox3@users.noreply.github.com>
Co-authored-by: Evan Mattson <evan.mattson@microsoft.com>
2025-12-04 05:09:52 +00:00
CopilotGitHubcopilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>eavanvalkenburgEvan Mattson
ae06c9e4bb Add support for Pydantic BaseModel as function call result (#2606)
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com>
Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com>
2025-12-04 01:41:47 +00:00
Evan MattsonandGitHub f7a9005235 Python: Add executor I/O data to ExecutorInvokedEvent and ExecutorCompletedEvent (#2591)
* Add executor I/O data to ExecutorInvokedEvent and ExecutorCompletedEvent

* Sample cleanup
2025-12-04 01:41:40 +00:00
b86c130411 Python: Fixed empty text content pydantic validation failure (#2539)
* Fixed empty text content pydantic validation failure

* simplify syntax. renamed test

---------

Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com>
2025-12-04 01:41:27 +00:00
d774b64df0 Python: added inline yaml sample (#2582)
* added inline yaml sample

* fixed some typos and added intro comment

* added description params and pass through to client

* add azure assistants

* fix tests

* observabiltiy mypy fix

* for some reason mypy doesn't accept a subclass

---------

Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com>
2025-12-04 01:30:56 +00:00
Victor DibiaandGitHub 42ffe59592 Python: Document ChatKit frontend requirements and air-gapped limitations (#2587)
- Add "Requirements and Limitations" section to chatkit package README
- Add "Network Requirements" and "Limitations" sections to chatkit-integration sample README
- Add explanatory comments in frontend code for CDN dependency and domain key configuration

Fixes #2347
2025-12-04 01:19:14 +00:00
Evan MattsonandGitHub a683c0e865 Python: Use executor_id and edge_group_id as span names for meaningful observability traces (#2538)
* Use executor_id and edge_group_id as span names for meaningful observability traces

* Update tests

* Adjust naming
2025-12-04 01:03:12 +00:00
Evan MattsonandGitHub a597a925cb Python: Add type annotations for AgentRunEvent and AgentRunUpdateEvent data attributes (#2589)
* Add type annotations for AgentRunEvent and AgentRunUpdateEvent data attributes

* Fix unnecessary cast after typing improvement

* Mcp pkg update introduced type change. Fix it.

* update opentelemetry deps to 1.39.0 and use LogRecordExporter for type compatibility
2025-12-04 00:40:49 +00:00
9c2e800189 Remove unnecessary PackageReferences after .NET 10 update (#2394)
Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com>
2025-12-04 00:09:51 +00:00
Peter IbekweandGitHub a26e9d6274 .NET: Add Unit test for declarative object model AddConversationMessageExecutor (#2613)
* Added unit test for RetrieveConversationMessagesExecutor

* Unit test for declarative object model AddConversationMessageExecutor

* Remove unnecessary test.

* Fix test.
2025-12-03 23:25:27 +00:00
Victor DibiaandGitHub 411ee7a60f Python: DevUI fixes : Add multimodal input support for workflows and refactor chat input (#2593)
* show app version in devui .NET: Python: Improved Versioning for DevUI
Fixes #2059

* feat: Add multimodal input support for workflows and refactor chat input

This PR adds support for multimodal content (images, files) in workflow
inputs and refactors the chat input into a reusable component.

## Multimodal Workflow Support
- Add `isChatMessageSchema()` to detect ChatMessage input schemas
- Update `RunWorkflowButton` to use `ChatMessageInput` for ChatMessage workflows
- Wrap multimodal content in OpenAI message format for backend processing
- Add `_is_openai_multimodal_format()` to detect OpenAI ResponseInputParam
- Update `_parse_workflow_input()` to route multimodal input through
  existing `_convert_input_to_chat_message()` converter

## Reusable ChatMessageInput Component
- Extract chat input logic from agent-view into `ChatMessageInput` component
- Support file upload, drag & drop, paste handling, and attachments
- Add `useDragDrop` hook for parent-level drag handling with full-area
  drop zones
- Refactor agent-view to use the new shared component

## Other Improvements
- Add `isStreaming` prop to executor nodes for animation control
- Clean up unused imports and state variables in agent-view
- Add tests for multimodal workflow input handling

Fixes workflow input not receiving images when using AgentExecutor nodes.

* add self loop edge, fix #2470

* fix test
2025-12-03 20:15:51 +00:00
CopilotGitHubrogerbarretocopilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
6835161f2d .NET: Fix flaky vector store integration tests - race condition on indexing (#2586)
* Initial plan

* Add vector store indexing wait helpers to fix flaky tests

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

* Use proper VectorStoreStatus struct comparison in Azure tests

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

* Remove unused System.ClientModel import

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

* Remove excessive comments and unnecessary status variable per code review

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

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com>
2025-12-03 20:06:21 +00:00
3cfd34836f Python: Update _provider.py (#2548)
* Update _provider.py

* Update test_mem0_context_provider.py

* Update test_mem0_context_provider.py

Ruff linting fixes

* Update test_mem0_context_provider.py

---------

Co-authored-by: Dmytro Struk <13853051+dmytrostruk@users.noreply.github.com>
2025-12-03 19:54:05 +00:00
Eduard van ValkenburgandGitHub a81279d960 Python: Pin meta core (#2597)
* pin core dependency in the meta package

* fix for mcp latest

* fix mypy

* test fix

* test fix

* fix tests for content parsing
2025-12-03 18:19:17 +00:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>Chris
931197ba95 Bump Aspire.Hosting.AppHost from 13.0.0 to 13.0.1 (#2493)
---
updated-dependencies:
- dependency-name: Aspire.Hosting.AppHost
  dependency-version: 13.0.1
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Chris <66376200+crickman@users.noreply.github.com>
2025-12-03 16:55:04 +00:00
Roger BarretoandGitHub d57303cf53 Bump Persistent V1 package with bugfixes (#2602) 2025-12-03 16:01:37 +00:00
b5595f6f70 Python: Enable Agentic Mode to Use Existing Knowledge Bases Without index_name (#2464)
* refactor KB for index creation logic

* add user agent header for tracking

* fix mypy issues

---------

Co-authored-by: farzad528 <farzad528@users.noreply.github.com>
2025-12-03 16:00:59 +00:00
6232dd8305 .NET [Breaking] Simplify and Refactor ChatclientAgentOptions Ctor + Instructions (#1517)
* Point AgentOptions.Instructions to ChatOptions

* Update tests and checks

* Update xml docs

* Removal of agentOptions.Instructions in favor of chatOptions.Instructions

* Instructions and tool check consistency

* Instructions and tool check consistency

* Address comment

* Update .github/upgrades/prompts/SemanticKernelToAgentFramework.md

Co-authored-by: westey <164392973+westey-m@users.noreply.github.com>

* Address PR Comment

* Update latest changes to comply with the PR proposal

* Address feedback

* Update dotnet/tests/Microsoft.Agents.AI.UnitTests/ChatClient/ChatClientAgentTests.cs

Co-authored-by: westey <164392973+westey-m@users.noreply.github.com>

* Address instructions

* Update declarative to use promptAgent.Instrucitons with chatOptions.Instructions

---------

Co-authored-by: westey <164392973+westey-m@users.noreply.github.com>
Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com>
2025-12-03 13:39:47 +00:00
David WuandGitHub e9ab514696 Python: Replace Eval SDK with AI Projects SDK in evaluation sample (#2540)
* Replace Eval SDK with AI Projects SDK

* Update per PR review suggestions
2025-12-02 20:28:52 +00:00
Javier Calvarro NelsonandGitHub b69f994840 .NET: Fix AG-UI forwardedProps JSON property name (#2543)
* Fix AG-UI forwardedProps JSON property name

The RunAgentInput.ForwardedProperties property was using the wrong JSON property
name 'forwardedProperties' instead of 'forwardedProps' per the AG-UI protocol
specification.

This fix:
- Changes JsonPropertyName from 'forwardedProperties' to 'forwardedProps'
- Adds comprehensive integration tests for forwarded properties

Fixes #2468

* Fix formatting
2025-12-02 17:00:40 +00:00
ceaea46765 .NET: Change Anthropic Azure sample to use Athropic.Foundry package + cachi… (#2578)
* Change Anthropic Azure sample to use Athropic.Foundry package + caching token

* Fix apikey null

* Update dotnet/samples/GettingStarted/AgentProviders/Agent_With_Anthropic/Program.cs

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

* Address copilot feedback

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-12-02 16:50:14 +00:00
1edd28b264 feat: pass agent run kwargs through to context providers (#1681)
`_prepare_thread_and_messages` and `_notify_thread_of_new_messages` now are passing through the agent's `run` kwargs, sothat they can provide the context_provider with said kwargs

#1679

Co-authored-by: David Jadczyk <david.jadczyk@lht.dlh.de>
Co-authored-by: Chris <66376200+crickman@users.noreply.github.com>
Co-authored-by: Dmytro Struk <13853051+dmytrostruk@users.noreply.github.com>
2025-12-02 14:35:32 +00:00
SergeyMenshykhandGitHub 5c70e143a0 .NET: Fix samples for hosted agents (#2550)
* update .net sdk and runtime images and update nuget packages to the latests versions

* align version of roslyn analyzers

* unlock roslyn analyzer packages
2025-12-02 11:12:46 +00:00
Evan MattsonandGitHub c2d285e614 Fix MangenticAgentExecutor producing repr str for tool call content (#2566) 2025-12-02 08:40:11 +00:00
CopilotGitHublarohracopilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>Laveesh Rohra
cb343dd707 Python: Add orchestration ID to durable agent entity state and code refactor (#2484)
* Initial plan

* Add orchestration ID to durable agent entity state for Python

Co-authored-by: larohra <41490930+larohra@users.noreply.github.com>

* Fix type safety checks

* Fix tests

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: larohra <41490930+larohra@users.noreply.github.com>
Co-authored-by: Laveesh Rohra <larohra@microsoft.com>
2025-12-02 01:34:18 +00:00
Evan MattsonandGitHub 0d5d10d24a Python: Emit ExecutorFailedEvent before WorkflowFailedEvent when executor throws exception (#2537)
* Emit ExecutorFailedEvent before WorkflowFailedEvent when executor throws exception

* Cleanup
2025-12-02 01:21:28 +00:00
Evan MattsonandGitHub e3b700ad9f Python: Add sample to show handoff as agent with HITL (#2534)
* Add sample to show handoff as agent with HITL

* Update uv.lock with latest pkg versions. Fix lint error.

* Upgrade grpcio to 1.76.0

* Handle grpcio versions

* Case insensitive compare for declarative
2025-12-02 00:50:13 +00:00
Roger BarretoandGitHub 8ae33d3c2b Address gap IServiceProvider options (#2551) 2025-12-01 20:01:13 +00:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
bf326e7f78 Bump actions/setup-dotnet from 5.0.0 to 5.0.1 (#2530)
Bumps [actions/setup-dotnet](https://github.com/actions/setup-dotnet) from 5.0.0 to 5.0.1.
- [Release notes](https://github.com/actions/setup-dotnet/releases)
- [Commits](https://github.com/actions/setup-dotnet/compare/v5.0.0...v5.0.1)

---
updated-dependencies:
- dependency-name: actions/setup-dotnet
  dependency-version: 5.0.1
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2025-12-01 19:12:06 +00:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
b457d3cdbe Bump Aspire.Hosting.Azure.CognitiveServices from 13.0.0 to 13.0.1 (#2528)
---
updated-dependencies:
- dependency-name: Aspire.Hosting.Azure.CognitiveServices
  dependency-version: 13.0.1
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2025-12-01 19:12:02 +00:00
Roger BarretoandGitHub 139c292807 .NET: Add Google ChatClientAgent provider sample using with Gemini model (#2554)
* Add Gemini model sample

* Update Readme

* Address Comments

* Address format
2025-12-01 18:51:15 +00:00
Mark WallaceandGitHub b26108975d .NET: Declarative Agents (#2476)
* Update the declarative agent samples

* Add the Microsoft.Agents.AI.Declarative project

* Make the package non packable

* Use the RecalcEngine when creating the ChatOptions

* Ignore VSTHRD200

* Add geting started samples

* Address code review feedback
2025-12-01 15:15:18 +00:00
a3909b8b5b Change sample to use official Anthropic C# package (#2471)
Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com>
2025-11-28 19:10:54 +00:00
67de7bcd93 .NET: Prevent streamed updates loss when resuming streaming (#2516)
* prevent stremed updates loss when resuming streaming with non-agent managed store or/and context provider

* Update dotnet/src/Microsoft.Agents.AI/ChatClient/ChatClientAgent.cs

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

* throw not supported exception instead invalid operation

* Update dotnet/src/Microsoft.Agents.AI/ChatClient/ChatClientAgent.cs

Co-authored-by: westey <164392973+westey-m@users.noreply.github.com>

* Update dotnet/src/Microsoft.Agents.AI/ChatClient/ChatClientAgent.cs

Co-authored-by: westey <164392973+westey-m@users.noreply.github.com>

* use conversation id to check if chat history is managed by agent service or not

* extract background responses tests into a separate file

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: westey <164392973+westey-m@users.noreply.github.com>
2025-11-28 16:11:30 +00:00
SergeyMenshykhandGitHub e769256976 .NET: Require thread for background responses (#2498)
* require thread for backgraund responses

* address pr review feedback
2025-11-27 16:26:52 +00:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
257e717608 Bump Anthropic from 10.2.1 to 10.4.0 (#2492)
---
updated-dependencies:
- dependency-name: Anthropic
  dependency-version: 10.4.0
  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>
2025-11-27 16:00:25 +00:00
Stephen ToubandGitHub 66a399ee2d Update Azure.AI.OpenAI to latest release (#2501) 2025-11-27 15:28:43 +00:00
Evan MattsonandGitHub 8cf8b0f995 Python: Refactor ag-ui to clean up some patterns (#2363)
* Refactor ag-ui to clean up some patterns

* Mypy fixes

* Fix imports, typing, tests, logging.

* Fix test import error

* Fix imports again

* Fix thread handling
2025-11-27 02:13:03 +00:00
6c624319db Python: docs: Update Python orchestration documentation (#2087)
* docs: Update Python orchestration documentation

Remove outdated 'coming soon' statements for GroupChat, Sequential,
and Concurrent orchestrations in core package README and transparency FAQ.

Add links to existing samples in python/samples/getting_started/workflows/orchestration/.

Note: python/README.md was already updated in PR #1914 (2499262f).

Fixes documentation inconsistency found in Issue #1899.

* Address review feedback: make TRANSPARENCY_FAQ language-neutral

Remove Python-specific sample links from TRANSPARENCY_FAQ.md as it should
pertain to all MAF languages (Python and .NET), not strictly Python.

The python/packages/core/README.md retains the specific sample links as
that is Python-specific documentation.

* Update Learn documentation link in README

---------

Co-authored-by: kishikawa-hayato <84244732+HerBest-max@users.noreply.github.com>
Co-authored-by: Victor Dibia <chuvidi2003@gmail.com>
2025-11-27 00:13:15 +00:00
Laveesh RohraandGitHub 306c81aef8 Python: [Breaking] Python: Respond with AgentRunResponse with serialized structured output (#2285)
* Respond with AgentRunResponse

* Fix response_Format type

* Address comments

* Fix tests

* Fix log

* Addressed comments

* Code cleanup

* Use AgentTask vs Generator

* Address comments

* use lazy logging

* fix mypy errors
2025-11-26 18:44:28 +00:00
westeyandGitHub 0f2c5e6cb8 Add office hours call to action to readme.me (#2480) 2025-11-26 18:21:02 +00:00
Phillip HoffandGitHub 17b4dfab14 .NET: Add orchestration ID to durable agent entity state (#2137)
* Propagate orchestration ID (if any).

* Add integration test for orchestration ID in entity state.

* Update schema.

* Fixup formatting issues.

* Fix more formatting issues.
2025-11-26 16:32:32 +00:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>Chris
486b78126d Bump danielpalme/ReportGenerator-GitHub-Action from 5.4.18 to 5.5.0 (#2256)
Bumps [danielpalme/ReportGenerator-GitHub-Action](https://github.com/danielpalme/reportgenerator-github-action) from 5.4.18 to 5.5.0.
- [Release notes](https://github.com/danielpalme/reportgenerator-github-action/releases)
- [Commits](https://github.com/danielpalme/reportgenerator-github-action/compare/5.4.18...5.5.0)

---
updated-dependencies:
- dependency-name: danielpalme/ReportGenerator-GitHub-Action
  dependency-version: 5.5.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Chris <66376200+crickman@users.noreply.github.com>
2025-11-26 14:41:49 +00:00
0723f1d183 .NET: Foundry V2 - Update Sample and Docs for clear distinction between Classic/New Foundry Agents. (#2459)
* Address potential confusion around agent version vs API version

* Address potential confusion around agent version vs API version

* Add extra documentation for clarity

* Remove V2 remainers

* Apply suggestions from code review

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: westey <164392973+westey-m@users.noreply.github.com>

* 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>
Co-authored-by: westey <164392973+westey-m@users.noreply.github.com>
2025-11-26 14:37:03 +00:00
Theo van KraayandGitHub a57b37d5fa .NET: Add Cosmos DB implementations for ChatMessageStore and CheckpointStore. (#1838)
* draft commit

* Added Cosmos agent thread and tests

* revert unnecessary changes and fix tests

* add multi-tenant support with hierarchical partition keys (and tests).

* enhance transactional batch

* address review comments

* Address PR review comments from @westey-m

* Merge upstream/main - resolve slnx conflicts

* use param validation helpers

* Replace useManagedIdentity boolean with TokenCredential parameter

* Remove redundant suppressions and fix tests

* Rename project from Microsoft.Agents.AI.Abstractions.CosmosNoSql to Microsoft.Agents.AI.CosmosNoSql

* Refactor constructors to use chaining pattern

* Reorder deserialization constructor parameters for consistency

* Remove database/container IDs from serialized state

* Remove auto-generation of MessageId

* Optimize AddMessagesAsync to avoid enumeration when possible

* Add MaxMessagesToRetrieve to limit context window

* Make Role nullable instead of defaulting

* Fix net472 build without rebasing 19 commits

* Add Cosmos DB emulator to CI workflow

* Fix Cosmos DB emulator tests: use Skip.If instead of Assert.Fail and start emulator before unit tests

* Replace Skip.If() with conditional return to fix compilation

* Use env var to skip Cosmos tests on non-Windows CI

* Add Xunit.SkippableFact package to properly skip Cosmos tests on Linux

* Change [Fact] to [SkippableFact] for proper test skipping behavior

* Remove stale Microsoft.Agents.AI.Abstractions.CosmosNoSql directory

* Fix code formatting: add braces, this. qualifications, and final newlines

* Fix file encoding to UTF-8 with BOM, fix import ordering, and remove unnecessary using directives

* Convert backing fields to auto-properties and remove Azure.Identity using directive

* Fix CosmosChatMessageStore.cs encoding back to UTF-8 with BOM

* Fix test file formatting: indentation, encoding, imports, this. qualifications, naming conventions, and simplify new expressions

* Fix const field naming violations: Remove s_ prefix from const fields and add this. qualification to Dispose call

* Add local .editorconfig for Cosmos DB tests to suppress IDE0005 false positives from multi-targeting

* Fix IDE1006 naming violations: Rename TestDatabaseId to s_testDatabaseId and add final newlines

* Address PR review comments

Address Wesley's review comments:

- Remove Cosmos DB package references from core projects

- Delete duplicate test files from old package structure

- Remove redundant parameter validation from extension methods

Address Kiran's review comments:

- Remove redundant 429 retry logic (SDK handles automatically)

- Add explicit RequestEntityTooLarge error handling

- Remove dead code in GetMessageCountAsync

- Add defensive partition key validation comments

* Fix IDE0001 formatting error in AgentProviderExtensions.cs. Use type alias to resolve namespace conflict between Azure.AI.Agents.Persistent.RunStatus and Microsoft.Agents.AI.Workflows.RunStatus. This eliminates the need for global:: qualifier which triggered the formatter warning.

* Update package versions for Aspire 13.0.0 compatibility

* Fix TargetFrameworks in Cosmos DB projects

- Replace  with  which is defined in Directory.Build.props
- Fix package reference from System.Linq.Async to System.Linq.AsyncEnumerable to match Directory.Packages.props

* Remove redundant counter, add partition key validation, use factory pattern for deserialization
2025-11-26 12:36:27 +00:00
Evan MattsonandGitHub 907d79ab3c [BREAKING] Python: Standardize orchestration outputs as list of ChatMessage. Allow agent as group chat manager. (#2291)
* Standardize orchestration outputs as list of chatmessage. Add chat options to group chat prompt manager

* refactor group chat

* Improve group chat manager

* README Update

* Cleanup

* Add comment

* More cleanup

* Standardize termination condition for group chat

* Improvements on termination logic

* Fix tests

* Fix new line

* PR feedback

* Update ChatKit based on OpenAI type change

* Raise error if response format is not expected type

* Only one starting executor required. Add tests.

* Add magentic start executor test
2025-11-26 07:51:04 +00:00
Dmytro StrukandGitHub ed53ba158b Temporarily suppress CS8002 error (#2462) 2025-11-25 17:24:46 -08:00
5d8be5836c Python: Added support for application endpoints in Azure AI client (#2460)
* Added support for application endpoints in Azure AI client

* Fixed tests

* Update python/samples/getting_started/agents/azure_ai/azure_ai_with_application_endpoint.py

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

* Addressed comments

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-11-25 19:32:55 +00:00
Dmytro StrukandGitHub 0c1d12feca Suppressed CS8002 for Anthropic package (#2461) 2025-11-25 19:11:49 +00:00
b1c210c9d8 Python: Added MCP tool support for azure functions package. (#2385)
* Python: Add Scaffolding for Durable AzureFunctions package to Agent Framework (#1823)

* Add scafolding

* update readme

* add code owners and label

* update owners

* .NET: Durable extension: initial src and unit tests (#1900)

* Python: Add Durable Agent Wrapper code (#1913)

* add initial changes

* Move code and add single sample

* Update logger

* Remove unused code

* address PR comments

* cleanup code and address comments

---------

Co-authored-by: Dmytro Struk <13853051+dmytrostruk@users.noreply.github.com>

* Azure Functions .NET samples (#1939)

* Python: Add Unit tests for Azurefunctions package (#1976)

* Add Unit tests for Azurefunctions

* remove duplicate import

* .NET: [Feature Branch] Migrate state schema updates and support for agents as MCP tools (#1979)

* Python: Add more samples for Azure Functions (#1980)

* Move all samples

* fix comments

* remove dead lines

* Make samples simpler

* Agents as MCP tools

* Removed unused files and updated sample

* .NET: [Feature Branch] Durable Task extension integration tests (#2017)

* .NET: [Feature Branch] Update OpenAI config for integration tests (#2063)

* Python: Add Integration tests for AzureFunctions  (#2020)

* Add Integration tests

* Remove DTS extension

* Apply suggestions from code review

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

* Apply suggestions from code review

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

* Add pyi file for type safety

* Add samples in readme

* Updated all readme instructions

* Address comments

* Update readmes

* Fix requirements

* Address comments

---------

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

* Addressed copilot feedback

* Minor refactoring and added tests

* Updated mcp sample

* Fixed broken link in readme

* Addressed copilot comments

* Addressed feedback

* Updated property to enable_mcp_tool_trigger

---------

Co-authored-by: Laveesh Rohra <larohra@microsoft.com>
Co-authored-by: Dmytro Struk <13853051+dmytrostruk@users.noreply.github.com>
Co-authored-by: Chris Gillum <cgillum@microsoft.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-11-25 18:50:02 +00:00
Dmytro StrukandGitHub b8260ae24c Python: [BREAKING] Removed default "store" value (#2443)
* Removed default store value

* Small fix
2025-11-25 17:53:08 +00:00
Dmytro StrukandGitHub d302bffc63 Updated package versions (#2455) 2025-11-25 17:16:00 +00:00
Stephen ToubandGitHub 7a4f6877c3 Use Random.GetString in hosting IdGenerator (#2427) 2025-11-25 12:01:28 +00:00
westeyandGitHub b6c3b8d3f2 [BREAKING] Remove NotifyThreadOfNewMessagesAsync AIAgent helper (#2450)
* Remove NotifyThreadOfNewMessagesAsync helper from AIAgent

* Fix bug

* Update comment
2025-11-25 11:59:26 +00:00
1dde57981e .NET: Add Anthropic Agent Package (#2359)
* WIP

* WIP

* Simple call working

* Update Thinking sample

* Non-Streaming Function calling working

* Update Anthropic Impl

* Public Preps

* UT + IT working

* Update documentation + samples

* Update variable

* Revert nuget.config

* Add IT for BetaService implementation

* Remove polyfill + enable IT to run for netstandard 2.0

* Skipping Anthropic IT's for manual execution and avoid pipeline execution

* Fix compilation error

* Address error in UT

* Apply suggestions from code review

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

* Fix warning

* Net 10 update

* Update for NET 10, remove Anthropic.Foundry due to vulnerability

* Final missing adjustments for NET 10

* Address PR comments

* Remove unused code

* Address feedback

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-11-25 11:53:18 +00:00
112410ecd6 .NET: [BREAKING] Add GetNewThread overload for taking a ChatMessageStore at thread creation time (#2429)
* Add GetNewThread overload for taking a ChatMessageStore at thread creation time and move message store creation to thread creation time.

* Fix formatting.

* Apply suggestions from code review

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

* Apply suggestion from @rogerbarreto

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

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com>
2025-11-25 10:49:01 +00:00
SergeyMenshykhandGitHub a89c15d6e6 .NET: Change type of props representing continuation token (#2430)
* change type of props representing continuation token

* use explict cast instead of the as operator
2025-11-25 09:59:43 +00:00
27b3a517eb [BREAKING] Python: Adjust magentic event types raised. No need for custom events. (#2215)
* Adjust magentic event types raised. No need for custom events.

* Cleanup

* Fix test

* Update python/packages/core/agent_framework/_workflows/_magentic.py

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

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-11-25 08:24:08 +00:00
Eduard van ValkenburgandGitHub 1b4103dce3 Python: fix for logging setup (#2371)
* fix for logging setup

* typo fixes

* fix text
2025-11-25 08:19:34 +00:00
Evan MattsonandGitHub 2a4802eac3 Python: Fix runtime response format for responses client (#2440)
* Fix runtime response format for responses client

* Handle run time schema for Azure AI Client.
2025-11-25 07:50:20 +00:00
Giles OdigweandGitHub e303cc963d Python: AzureAI OpenAPI + Memory Search Samples (#2390)
* openapi + memory search samples

* readme update

* memory store name fix
2025-11-25 01:17:14 +00:00
Tomek SłomaandGitHub c78edda64f fix: always include output in function call result message (#2414)
This follows the official OpenAI API schema
2025-11-25 00:44:43 +00:00
a610a4769c .NET: Add support for background responses to A2A agent (#2381)
* add support for baackground responses to a2a agent

* fix line endings

* address pr review comments

* address pr review comments

* update sample to net10.0

* Update dotnet/samples/GettingStarted/A2A/A2AAgent_PollingForTaskCompletion/README.md

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

* Update dotnet/src/Microsoft.Agents.AI.A2A/Extensions/A2AAgentTaskExtensions.cs

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

* Update dotnet/samples/GettingStarted/A2A/A2AAgent_PollingForTaskCompletion/Program.cs

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

* address pr review feedback

* add clarification regarding background responses

---------

Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com>
2025-11-24 19:41:06 +00:00
Giles OdigweandGitHub bcbf1b33e8 Python: Preserve MCP array items schema in Pydantic field generation (#2382)
* mcp tool parameter fix

* small fixes
2025-11-24 17:16:30 +00:00
Eduard van ValkenburgandGitHub 9f43108ef1 Python: renamed ai search and cleanup of samples and unified import logic (#2369)
* renamed ai search and cleanup of samples and unified import logic

* fixed error messages

* fixed folder name

* remove old samples from readme
2025-11-24 17:06:22 +00:00
westeyandGitHub db424d56f3 Update to latest dotnet devcontainer and add docker in docker. (#2426) 2025-11-24 15:42:53 +00:00
431 changed files with 25282 additions and 7130 deletions
+3 -2
View File
@@ -1,10 +1,11 @@
{
"name": "C# (.NET)",
"image": "mcr.microsoft.com/devcontainers/dotnet:9.0",
"image": "mcr.microsoft.com/devcontainers/dotnet:10.0",
"features": {
"ghcr.io/devcontainers/features/dotnet:2.4.0": {},
"ghcr.io/devcontainers/features/powershell:1.5.1": {},
"ghcr.io/devcontainers/features/azure-cli:1.2.8": {}
"ghcr.io/devcontainers/features/azure-cli:1.2.8": {},
"ghcr.io/devcontainers/features/docker-in-docker:2.12.4": {}
},
"workspaceFolder": "/workspaces/agent-framework/dotnet/",
"customizations": {
@@ -1636,4 +1636,4 @@ The property mapping guide from a `AutoFunctionInvocationContext` to a `Function
| Result | Use `return` from the delegate |
| Terminate | Terminate |
| CancellationToken | provided via argument to middleware delegate |
| Arguments | Arguments |
| Arguments | Arguments |
+19 -2
View File
@@ -79,7 +79,7 @@ jobs:
workflow-samples
- name: Setup dotnet
uses: actions/setup-dotnet@v5.0.0
uses: actions/setup-dotnet@v5.0.1
with:
global-json-file: ${{ github.workspace }}/dotnet/global.json
- name: Build dotnet solutions
@@ -124,6 +124,16 @@ jobs:
popd
rm -rf "$TEMP_DIR"
# Start Cosmos DB Emulator for Cosmos-based unit tests (only on Windows)
- name: Start Azure Cosmos DB Emulator
if: runner.os == 'Windows'
shell: pwsh
run: |
Write-Host "Launching Azure Cosmos DB Emulator"
Import-Module "$env:ProgramFiles\Azure Cosmos DB Emulator\PSModules\Microsoft.Azure.CosmosDB.Emulator"
Start-CosmosDbEmulator -NoUI -Key "C2y6yDjf5/R+ob0N8A7Cgv30VRDJIWEHLM+4QDU5DE2nQ9nDuVTqobD4b8mGGyPMbIZnqyMsEcaGQy67XIw/Jw=="
echo "COSMOS_EMULATOR_AVAILABLE=true" >> $env:GITHUB_ENV
- name: Run Unit Tests
shell: bash
run: |
@@ -143,6 +153,10 @@ jobs:
echo "Skipping $project - does not support target framework ${{ matrix.targetFramework }} (supports: $target_frameworks)"
fi
done
env:
# Cosmos DB Emulator connection settings
COSMOSDB_ENDPOINT: https://localhost:8081
COSMOSDB_KEY: C2y6yDjf5/R+ob0N8A7Cgv30VRDJIWEHLM+4QDU5DE2nQ9nDuVTqobD4b8mGGyPMbIZnqyMsEcaGQy67XIw/Jw==
- name: Log event name and matrix integration-tests
shell: bash
@@ -181,6 +195,9 @@ jobs:
fi
done
env:
# Cosmos DB Emulator connection settings
COSMOSDB_ENDPOINT: https://localhost:8081
COSMOSDB_KEY: C2y6yDjf5/R+ob0N8A7Cgv30VRDJIWEHLM+4QDU5DE2nQ9nDuVTqobD4b8mGGyPMbIZnqyMsEcaGQy67XIw/Jw==
# OpenAI Models
OpenAI__ApiKey: ${{ secrets.OPENAI__APIKEY }}
OpenAI__ChatModelId: ${{ vars.OPENAI__CHATMODELID }}
@@ -200,7 +217,7 @@ jobs:
# Generate test reports and check coverage
- name: Generate test reports
if: matrix.targetFramework == env.COVERAGE_FRAMEWORK
uses: danielpalme/ReportGenerator-GitHub-Action@5.4.18
uses: danielpalme/ReportGenerator-GitHub-Action@5.5.0
with:
reports: "./TestResults/Coverage/**/coverage.cobertura.xml"
targetdir: "./TestResults/Reports"
+2
View File
@@ -48,6 +48,8 @@ dotnet add package Microsoft.Agents.AI
- **[Migration from Semantic Kernel](https://learn.microsoft.com/en-us/agent-framework/migration-guide/from-semantic-kernel)** - Guide to migrate from Semantic Kernel
- **[Migration from AutoGen](https://learn.microsoft.com/en-us/agent-framework/migration-guide/from-autogen)** - Guide to migrate from AutoGen
Still have questions? Join our [weekly office hours](./COMMUNITY.md#public-community-office-hours) or ask questions in our [Discord channel](https://discord.gg/b5zjErwbQM) to get help from the team and other users.
### ✨ **Highlights**
- **Graph-based Workflows**: Connect agents and deterministic functions using data flows with streaming, checkpointing, human-in-the-loop, and time-travel capabilities
+1 -1
View File
@@ -44,7 +44,7 @@ Microsoft Agent Framework relies on existing LLMs. Using the framework retains c
- **Platform Requirements**: Python 3.10+ required, specific .NET versions (.NET 8.0, 9.0, 10.0, netstandard2.0, net472)
- **API Dependencies**: Requires proper configuration of LLM provider keys and endpoints
- **Orchestration Features**: Advanced orchestration patterns like GroupChat, Sequential, and Concurrent orchestrations are "coming soon" for Python implementation
- **Orchestration Features**: Advanced orchestration patterns including GroupChat, Sequential, and Concurrent workflows are now available in both Python and .NET implementations. See the respective language documentation for examples.
- **Privacy and Data Protection**: The framework allows for human participation in conversations between agents. It is important to ensure that user data and conversations are protected and that developers use appropriate measures to safeguard privacy.
- **Accountability and Transparency**: The framework involves multiple agents conversing and collaborating, it is important to establish clear accountability and transparency mechanisms. Users should be able to understand and trace the decision-making process of the agents involved in order to ensure accountability and address any potential issues or biases.
- **Security & unintended consequences**: The use of multi-agent conversations and automation in complex tasks may have unintended consequences. Especially, allowing agents to make changes in external environments through tool calls or function execution could pose significant risks. Developers should carefully consider the potential risks and ensure that appropriate safeguards are in place to prevent harm or negative outcomes, including keeping a human in the loop for decision making.
@@ -1,9 +1,9 @@
kind: Prompt
name: Assistant
description: Helpful assistant
instructions: You are a helpful assistant. You answer questions is the language specified by the user. You return your answers in a JSON format. You must include Assistants as the type in your response.
instructions: You are a helpful assistant. You answer questions in the language specified by the user. You return your answers in a JSON format. You must include Assistants as the type in your response.
model:
id: =Env.AZURE_OPENAI_DEPLOYMENT_NAME
id: gpt-4o-mini
provider: AzureOpenAI
apiType: Assistants
options:
@@ -12,14 +12,14 @@ model:
outputSchema:
properties:
language:
kind: string
type: string
required: true
description: The language of the answer.
answer:
kind: string
type: string
required: true
description: The answer text.
type:
kind: string
type: string
required: true
description: The type of the response.
+25
View File
@@ -0,0 +1,25 @@
kind: Prompt
name: Assistant
description: Helpful assistant
instructions: You are a helpful assistant. You answer questions in the language specified by the user. You return your answers in a JSON format. You must include Chat as the type in your response.
model:
id: gpt-4o-mini
provider: AzureOpenAI
apiType: Chat
options:
temperature: 0.9
topP: 0.95
outputSchema:
properties:
language:
type: string
required: true
description: The language of the answer.
answer:
type: string
required: true
description: The answer text.
type:
type: string
required: true
description: The type of the response.
+7 -10
View File
@@ -1,28 +1,25 @@
kind: Prompt
name: Assistant
description: Helpful assistant
instructions: You are a helpful assistant. You answer questions is the language specified by the user. You return your answers in a JSON format. You must include Responses as the type in your response.
instructions: You are a helpful assistant. You answer questions in the language specified by the user. You return your answers in a JSON format. You must include Responses as the type in your response.
model:
id: =Env.AZURE_OPENAI_DEPLOYMENT_NAME
id: gpt-4o-mini
provider: AzureOpenAI
apiType: Responses
options:
text:
verbosity: medium
connection:
kind: remote
endpoint: =Env.AZURE_OPENAI_ENDPOINT
temperature: 0.9
topP: 0.95
outputSchema:
properties:
language:
kind: string
type: string
required: true
description: The language of the answer.
answer:
kind: string
type: string
required: true
description: The answer text.
type:
kind: string
type: string
required: true
description: The type of the response.
+3 -3
View File
@@ -1,7 +1,7 @@
kind: Prompt
name: Assistant
description: Helpful assistant
instructions: You are a helpful assistant. You answer questions is the language specified by the user. You return your answers in a JSON format.
instructions: You are a helpful assistant. You answer questions in the language specified by the user. You return your answers in a JSON format.
model:
options:
temperature: 0.9
@@ -9,10 +9,10 @@ model:
outputSchema:
properties:
language:
kind: string
type: string
required: true
description: The language of the answer.
answer:
kind: string
type: string
required: true
description: The answer text.
+2
View File
@@ -4,6 +4,8 @@ description: Helpful assistant
instructions: You are a helpful assistant. You answer questions using the tools provided.
model:
options:
temperature: 0.9
topP: 0.95
allowMultipleToolCalls: true
chatToolMode: auto
tools:
+22
View File
@@ -0,0 +1,22 @@
kind: Prompt
name: Assistant
description: Helpful assistant
instructions: You are a helpful assistant. You answer questions in the language specified by the user. You return your answers in a JSON format.
model:
id: gpt-4.1-mini
options:
temperature: 0.9
topP: 0.95
connection:
kind: Remote
endpoint: =Env.AZURE_FOUNDRY_PROJECT_ENDPOINT
outputSchema:
properties:
language:
type: string
required: true
description: The language of the answer.
answer:
type: string
required: true
description: The answer text.
+6 -8
View File
@@ -1,30 +1,28 @@
kind: Prompt
name: Assistant
description: Helpful assistant
instructions: You are a helpful assistant. You answer questions is the language specified by the user. You return your answers in a JSON format. You must include Assistants as the type in your response.
instructions: You are a helpful assistant. You answer questions in the language specified by the user. You return your answers in a JSON format. You must include Assistants as the type in your response.
model:
id: =Env.OPENAI_MODEL
id: gpt-4.1-mini
provider: OpenAI
apiType: Assistants
options:
temperature: 0.9
topP: 0.95
connection:
kind: key
kind: ApiKey
key: =Env.OPENAI_APIKEY
outputSchema:
name: AssistantResponse
description: The response from the assistant.
properties:
language:
kind: string
type: string
required: true
description: The language of the answer.
answer:
kind: string
type: string
required: true
description: The answer text.
type:
kind: string
type: string
required: true
description: The type of the response.
+28
View File
@@ -0,0 +1,28 @@
kind: Prompt
name: Assistant
description: Helpful assistant
instructions: You are a helpful assistant. You answer questions in the language specified by the user. You return your answers in a JSON format. You must include Chat as the type in your response.
model:
id: gpt-4.1-mini
provider: OpenAI
apiType: Chat
options:
temperature: 0.9
topP: 0.95
connection:
kind: ApiKey
key: =Env.OPENAI_APIKEY
outputSchema:
properties:
language:
type: string
required: true
description: The language of the answer.
answer:
type: string
required: true
description: The answer text.
type:
type: string
required: true
description: The type of the response.
+8 -8
View File
@@ -1,28 +1,28 @@
kind: Prompt
name: Assistant
description: Helpful assistant
instructions: You are a helpful assistant. You answer questions is the language specified by the user. You return your answers in a JSON format. You must include Responses as the type in your response.
instructions: You are a helpful assistant. You answer questions in the language specified by the user. You return your answers in a JSON format. You must include Responses as the type in your response.
model:
id: =Env.OPENAI_MODEL
id: gpt-4.1-mini
provider: OpenAI
apiType: Responses
options:
text:
verbosity: medium
temperature: 0.9
topP: 0.95
connection:
kind: key
kind: ApiKey
key: =Env.OPENAI_APIKEY
outputSchema:
properties:
language:
kind: string
type: string
required: true
description: The language of the answer.
answer:
kind: string
type: string
required: true
description: The answer text.
type:
kind: string
type: string
required: true
description: The type of the response.
+1 -1
View File
@@ -8,7 +8,7 @@
<GenerateDocumentationFile>true</GenerateDocumentationFile>
<LangVersion>latest</LangVersion>
<Nullable>enable</Nullable>
<NoWarn>$(NoWarn);NU5128</NoWarn>
<NoWarn>$(NoWarn);NU5128;CS8002</NoWarn>
<TreatWarningsAsErrors>true</TreatWarningsAsErrors>
<TargetFrameworksCore>net10.0;net9.0;net8.0</TargetFrameworksCore>
<TargetFrameworks>$(TargetFrameworksCore);netstandard2.0;net472</TargetFrameworks>
+18 -8
View File
@@ -7,10 +7,12 @@
</PropertyGroup>
<PropertyGroup>
<!-- Aspire -->
<AspireAppHostSdkVersion>13.0.0</AspireAppHostSdkVersion>
<AspireAppHostSdkVersion>13.0.1</AspireAppHostSdkVersion>
</PropertyGroup>
<ItemGroup>
<!-- Aspire.* -->
<PackageVersion Include="Anthropic" Version="11.0.0" />
<PackageVersion Include="Anthropic.Foundry" Version="0.1.0" />
<PackageVersion Include="Aspire.Azure.AI.OpenAI" Version="13.0.0-preview.1.25560.3" />
<PackageVersion Include="Aspire.Hosting.AppHost" Version="$(AspireAppHostSdkVersion)" />
<PackageVersion Include="Aspire.Hosting.Azure.CognitiveServices" Version="$(AspireAppHostSdkVersion)" />
@@ -19,10 +21,17 @@
<!-- Azure.* -->
<PackageVersion Include="Azure.AI.Projects" Version="1.2.0-beta.3" />
<PackageVersion Include="Azure.AI.Projects.OpenAI" Version="1.0.0-beta.4" />
<PackageVersion Include="Azure.AI.Agents.Persistent" Version="1.2.0-beta.7" />
<PackageVersion Include="Azure.AI.OpenAI" Version="2.5.0-beta.1" />
<PackageVersion Include="Azure.AI.Agents.Persistent" Version="1.2.0-beta.8" />
<PackageVersion Include="Azure.AI.OpenAI" Version="2.7.0-beta.1" />
<PackageVersion Include="Azure.Identity" Version="1.17.0" />
<PackageVersion Include="Azure.Monitor.OpenTelemetry.Exporter" Version="1.4.0" />
<!-- Google Gemini -->
<PackageVersion Include="Google.GenAI" Version="0.6.0" />
<PackageVersion Include="Mscc.GenerativeAI.Microsoft" Version="2.9.3" />
<!-- Microsoft.Azure.* -->
<PackageVersion Include="Microsoft.Azure.Cosmos" Version="3.54.0" />
<!-- Newtonsoft.Json -->
<PackageVersion Include="Newtonsoft.Json" Version="13.0.4" />
<!-- System.* -->
<PackageVersion Include="Microsoft.Bcl.AsyncInterfaces" Version="10.0.0" />
<PackageVersion Include="Microsoft.Bcl.HashCode" Version="6.0.0" />
@@ -37,6 +46,7 @@
<PackageVersion Include="System.Text.Json" Version="10.0.0" />
<PackageVersion Include="System.Threading.Channels" Version="10.0.0" />
<PackageVersion Include="System.Threading.Tasks.Extensions" Version="4.6.3" />
<PackageVersion Include="System.Net.Security" Version="4.3.2" />
<!-- OpenTelemetry -->
<PackageVersion Include="OpenTelemetry" Version="1.13.1" />
<PackageVersion Include="OpenTelemetry.Api" Version="1.13.1" />
@@ -91,7 +101,6 @@
<!-- MCP -->
<PackageVersion Include="ModelContextProtocol" Version="0.4.0-preview.3" />
<!-- Inference SDKs -->
<PackageVersion Include="Anthropic.SDK" Version="5.8.0" />
<PackageVersion Include="AWSSDK.Extensions.Bedrock.MEAI" Version="4.0.4.6" />
<PackageVersion Include="Microsoft.ML.OnnxRuntimeGenAI" Version="0.10.0" />
<PackageVersion Include="OllamaSharp" Version="5.4.8" />
@@ -127,6 +136,7 @@
<PackageVersion Include="xunit" Version="2.9.3" />
<PackageVersion Include="xunit.abstractions" Version="2.0.3" />
<PackageVersion Include="xunit.runner.visualstudio" Version="3.1.3" />
<PackageVersion Include="Xunit.SkippableFact" Version="1.5.23" />
<PackageVersion Include="xretry" Version="1.9.0" />
<PackageVersion Include="coverlet.collector" Version="6.0.4" />
<!-- Symbols -->
@@ -153,20 +163,20 @@
<PrivateAssets>all</PrivateAssets>
<IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
</PackageReference>
<PackageVersion Include="Roslynator.Analyzers" Version="[4.14.1]" />
<PackageVersion Include="Roslynator.Analyzers" Version="4.14.1" />
<PackageReference Include="Roslynator.Analyzers">
<PrivateAssets>all</PrivateAssets>
<IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
</PackageReference>
<PackageVersion Include="Roslynator.CodeAnalysis.Analyzers" Version="[4.14.0]" />
<PackageVersion Include="Roslynator.CodeAnalysis.Analyzers" Version="4.14.1" />
<PackageReference Include="Roslynator.CodeAnalysis.Analyzers">
<PrivateAssets>all</PrivateAssets>
<IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
</PackageReference>
<PackageVersion Include="Roslynator.Formatting.Analyzers" Version="[4.14.0]" />
<PackageVersion Include="Roslynator.Formatting.Analyzers" Version="4.14.1" />
<PackageReference Include="Roslynator.Formatting.Analyzers">
<PrivateAssets>all</PrivateAssets>
<IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
</PackageReference>
</ItemGroup>
</Project>
</Project>
+22 -1
View File
@@ -40,16 +40,19 @@
<Folder Name="/Samples/GettingStarted/A2A/">
<File Path="samples/GettingStarted/A2A/README.md" />
<Project Path="samples/GettingStarted/A2A/A2AAgent_AsFunctionTools/A2AAgent_AsFunctionTools.csproj" />
<Project Path="samples/GettingStarted/A2A/A2AAgent_PollingForTaskCompletion/A2AAgent_PollingForTaskCompletion.csproj" />
</Folder>
<Folder Name="/Samples/GettingStarted/AgentProviders/">
<File Path="samples/GettingStarted/AgentProviders/README.md" />
<Project Path="samples/GettingStarted/AgentProviders/Agent_With_A2A/Agent_With_A2A.csproj" />
<Project Path="samples/GettingStarted/AgentProviders/Agent_With_Anthropic/Agent_With_Anthropic.csproj" />
<Project Path="samples/GettingStarted/AgentProviders/Agent_With_AzureAIAgentsPersistent/Agent_With_AzureAIAgentsPersistent.csproj" />
<Project Path="samples/GettingStarted/AgentProviders/Agent_With_AzureAIProject/Agent_With_AzureAIProject.csproj" />
<Project Path="samples/GettingStarted/AgentProviders/Agent_With_AzureFoundryModel/Agent_With_AzureFoundryModel.csproj" />
<Project Path="samples/GettingStarted/AgentProviders/Agent_With_AzureOpenAIChatCompletion/Agent_With_AzureOpenAIChatCompletion.csproj" />
<Project Path="samples/GettingStarted/AgentProviders/Agent_With_AzureOpenAIResponses/Agent_With_AzureOpenAIResponses.csproj" />
<Project Path="samples/GettingStarted/AgentProviders/Agent_With_CustomImplementation/Agent_With_CustomImplementation.csproj" />
<Project Path="samples/GettingStarted/AgentProviders/Agent_With_GoogleGemini/Agent_With_GoogleGemini.csproj" />
<Project Path="samples/GettingStarted/AgentProviders/Agent_With_Ollama/Agent_With_Ollama.csproj" />
<Project Path="samples/GettingStarted/AgentProviders/Agent_With_ONNX/Agent_With_ONNX.csproj" />
<Project Path="samples/GettingStarted/AgentProviders/Agent_With_OpenAIAssistants/Agent_With_OpenAIAssistants.csproj" />
@@ -76,11 +79,21 @@
<Project Path="samples/GettingStarted/Agents/Agent_Step16_ChatReduction/Agent_Step16_ChatReduction.csproj" />
<Project Path="samples/GettingStarted/Agents/Agent_Step17_BackgroundResponses/Agent_Step17_BackgroundResponses.csproj" />
<Project Path="samples/GettingStarted/Agents/Agent_Step18_DeepResearch/Agent_Step18_DeepResearch.csproj" />
<Project Path="samples/GettingStarted/Agents/Agent_Step19_Declarative/Agent_Step19_Declarative.csproj" />
</Folder>
<Folder Name="/Samples/GettingStarted/DeclarativeAgents/">
<Project Path="samples/GettingStarted/DeclarativeAgents/ChatClient/DeclarativeChatClientAgents.csproj" />
</Folder>
<Folder Name="/Samples/GettingStarted/DevUI/">
<File Path="samples/GettingStarted/DevUI/README.md" />
<Project Path="samples/GettingStarted/DevUI/DevUI_Step01_BasicUsage/DevUI_Step01_BasicUsage.csproj" />
</Folder>
<Folder Name="/Samples/GettingStarted/AgentWithAnthropic/">
<File Path="samples/GettingStarted/AgentWithAnthropic/README.md" />
<Project Path="samples/GettingStarted/AgentWithAnthropic/Agent_Anthropic_Step01_Running/Agent_Anthropic_Step01_Running.csproj" />
<Project Path="samples/GettingStarted/AgentWithAnthropic/Agent_Anthropic_Step02_Reasoning/Agent_Anthropic_Step02_Reasoning.csproj" />
<Project Path="samples/GettingStarted/AgentWithAnthropic/Agent_Anthropic_Step03_UsingFunctionTools/Agent_Anthropic_Step03_UsingFunctionTools.csproj" />
</Folder>
<Folder Name="/Samples/GettingStarted/AgentWithMemory/">
<File Path="samples/GettingStarted/AgentWithMemory/README.md" />
<Project Path="samples/GettingStarted/AgentWithMemory/AgentWithMemory_Step01_ChatHistoryMemory/AgentWithMemory_Step01_ChatHistoryMemory.csproj" />
@@ -311,6 +324,7 @@
<File Path="src/Shared/Demos/SampleEnvironment.cs" />
</Folder>
<Folder Name="/Solution Items/src/Shared/IntegrationTests/">
<File Path="src/Shared/IntegrationTests/AnthropicConfiguration.cs" />
<File Path="src/Shared/IntegrationTests/AzureAIConfiguration.cs" />
<File Path="src/Shared/IntegrationTests/Mem0Configuration.cs" />
<File Path="src/Shared/IntegrationTests/OpenAIConfiguration.cs" />
@@ -335,9 +349,12 @@
<Project Path="src/Microsoft.Agents.AI.A2A/Microsoft.Agents.AI.A2A.csproj" />
<Project Path="src/Microsoft.Agents.AI.Abstractions/Microsoft.Agents.AI.Abstractions.csproj" />
<Project Path="src/Microsoft.Agents.AI.AGUI/Microsoft.Agents.AI.AGUI.csproj" />
<Project Path="src/Microsoft.Agents.AI.Anthropic/Microsoft.Agents.AI.Anthropic.csproj" />
<Project Path="src/Microsoft.Agents.AI.AzureAI.Persistent/Microsoft.Agents.AI.AzureAI.Persistent.csproj" />
<Project Path="src/Microsoft.Agents.AI.AzureAI/Microsoft.Agents.AI.AzureAI.csproj" />
<Project Path="src/Microsoft.Agents.AI.CopilotStudio/Microsoft.Agents.AI.CopilotStudio.csproj" />
<Project Path="src/Microsoft.Agents.AI.CosmosNoSql/Microsoft.Agents.AI.CosmosNoSql.csproj" />
<Project Path="src/Microsoft.Agents.AI.Declarative/Microsoft.Agents.AI.Declarative.csproj" />
<Project Path="src/Microsoft.Agents.AI.DevUI/Microsoft.Agents.AI.DevUI.csproj" />
<Project Path="src/Microsoft.Agents.AI.DurableTask/Microsoft.Agents.AI.DurableTask.csproj" />
<Project Path="src/Microsoft.Agents.AI.Hosting.A2A.AspNetCore/Microsoft.Agents.AI.Hosting.A2A.AspNetCore.csproj" />
@@ -357,6 +374,7 @@
<Folder Name="/Tests/" />
<Folder Name="/Tests/IntegrationTests/">
<Project Path="tests/AgentConformance.IntegrationTests/AgentConformance.IntegrationTests.csproj" />
<Project Path="tests/AnthropicChatCompletion.IntegrationTests/AnthropicChatCompletion.IntegrationTests.csproj" />
<Project Path="tests/AzureAI.IntegrationTests/AzureAI.IntegrationTests.csproj" />
<Project Path="tests/AzureAIAgentsPersistent.IntegrationTests/AzureAIAgentsPersistent.IntegrationTests.csproj" />
<Project Path="tests/CopilotStudio.IntegrationTests/CopilotStudio.IntegrationTests.csproj" />
@@ -373,8 +391,11 @@
<Project Path="tests/Microsoft.Agents.AI.A2A.UnitTests/Microsoft.Agents.AI.A2A.UnitTests.csproj" />
<Project Path="tests/Microsoft.Agents.AI.Abstractions.UnitTests/Microsoft.Agents.AI.Abstractions.UnitTests.csproj" />
<Project Path="tests/Microsoft.Agents.AI.AGUI.UnitTests/Microsoft.Agents.AI.AGUI.UnitTests.csproj" />
<Project Path="tests/Microsoft.Agents.AI.Anthropic.UnitTests/Microsoft.Agents.AI.Anthropic.UnitTests.csproj" />
<Project Path="tests/Microsoft.Agents.AI.AzureAI.Persistent.UnitTests/Microsoft.Agents.AI.AzureAI.Persistent.UnitTests.csproj" />
<Project Path="tests/Microsoft.Agents.AI.AzureAI.UnitTests/Microsoft.Agents.AI.AzureAI.UnitTests.csproj" />
<Project Path="tests/Microsoft.Agents.AI.CosmosNoSql.UnitTests/Microsoft.Agents.AI.CosmosNoSql.UnitTests.csproj" />
<Project Path="tests/Microsoft.Agents.AI.Declarative.UnitTests/Microsoft.Agents.AI.Declarative.UnitTests.csproj" />
<Project Path="tests/Microsoft.Agents.AI.DevUI.UnitTests/Microsoft.Agents.AI.DevUI.UnitTests.csproj" />
<Project Path="tests/Microsoft.Agents.AI.DurableTask.UnitTests/Microsoft.Agents.AI.DurableTask.UnitTests.csproj" />
<Project Path="tests/Microsoft.Agents.AI.Hosting.A2A.UnitTests/Microsoft.Agents.AI.Hosting.A2A.UnitTests.csproj" />
@@ -389,4 +410,4 @@
<Project Path="tests/Microsoft.Agents.AI.Workflows.Declarative.UnitTests/Microsoft.Agents.AI.Workflows.Declarative.UnitTests.csproj" />
<Project Path="tests/Microsoft.Agents.AI.Workflows.UnitTests/Microsoft.Agents.AI.Workflows.UnitTests.csproj" />
</Folder>
</Solution>
</Solution>
+3 -3
View File
@@ -2,9 +2,9 @@
<PropertyGroup>
<!-- Central version prefix - applies to all nuget packages. -->
<VersionPrefix>1.0.0</VersionPrefix>
<PackageVersion Condition="'$(VersionSuffix)' != ''">$(VersionPrefix)-$(VersionSuffix).251114.1</PackageVersion>
<PackageVersion Condition="'$(VersionSuffix)' == ''">$(VersionPrefix)-preview.251114.1</PackageVersion>
<GitTag>1.0.0-preview.251114.1</GitTag>
<PackageVersion Condition="'$(VersionSuffix)' != ''">$(VersionPrefix)-$(VersionSuffix).251125.1</PackageVersion>
<PackageVersion Condition="'$(VersionSuffix)' == ''">$(VersionPrefix)-preview.251125.1</PackageVersion>
<GitTag>1.0.0-preview.251125.1</GitTag>
<Configurations>Debug;Release;Publish</Configurations>
<IsPackable>true</IsPackable>
@@ -14,11 +14,6 @@
<PackageReference Include="Microsoft.Extensions.Hosting" />
</ItemGroup>
<ItemGroup Condition="!$([MSBuild]::IsTargetFrameworkCompatible($(TargetFramework), 'net10.0'))">
<PackageReference Include="System.Net.ServerSentEvents" />
<PackageReference Include="Microsoft.Bcl.AsyncInterfaces" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\src\Microsoft.Agents.AI.A2A\Microsoft.Agents.AI.A2A.csproj" />
<ProjectReference Include="..\..\..\src\Microsoft.Agents.AI.Abstractions\Microsoft.Agents.AI.Abstractions.csproj" />
@@ -15,11 +15,6 @@
<PackageReference Include="Microsoft.Extensions.Hosting" />
</ItemGroup>
<ItemGroup Condition="!$([MSBuild]::IsTargetFrameworkCompatible($(TargetFramework), 'net10.0'))">
<PackageReference Include="System.Net.ServerSentEvents" />
<PackageReference Include="Microsoft.Bcl.AsyncInterfaces" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.A2A\Microsoft.Agents.AI.A2A.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
@@ -0,0 +1,25 @@
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
<TargetFramework>net10.0</TargetFramework>
<Nullable>enable</Nullable>
<ImplicitUsings>enable</ImplicitUsings>
</PropertyGroup>
<ItemGroup>
<PackageReference Include="A2A" />
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.Hosting" />
<PackageReference Include="System.Net.ServerSentEvents" />
<PackageReference Include="Microsoft.Bcl.AsyncInterfaces" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.A2A\Microsoft.Agents.AI.A2A.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
</ItemGroup>
</Project>
@@ -0,0 +1,35 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample demonstrates how to poll for long-running task completion using continuation tokens with an A2A AI agent.
using A2A;
using Microsoft.Agents.AI;
var a2aAgentHost = Environment.GetEnvironmentVariable("A2A_AGENT_HOST") ?? throw new InvalidOperationException("A2A_AGENT_HOST is not set.");
// Initialize an A2ACardResolver to get an A2A agent card.
A2ACardResolver agentCardResolver = new(new Uri(a2aAgentHost));
// Get the agent card
AgentCard agentCard = await agentCardResolver.GetAgentCardAsync();
// Create an instance of the AIAgent for an existing A2A agent specified by the agent card.
AIAgent agent = agentCard.GetAIAgent();
AgentThread thread = agent.GetNewThread();
// Start the initial run with a long-running task.
AgentRunResponse response = await agent.RunAsync("Conduct a comprehensive analysis of quantum computing applications in cryptography, including recent breakthroughs, implementation challenges, and future roadmap. Please include diagrams and visual representations to illustrate complex concepts.", thread);
// Poll until the response is complete.
while (response.ContinuationToken is { } token)
{
// Wait before polling again.
await Task.Delay(TimeSpan.FromSeconds(2));
// Continue with the token.
response = await agent.RunAsync(thread, options: new AgentRunOptions { ContinuationToken = token });
}
// Display the result
Console.WriteLine(response);
@@ -0,0 +1,25 @@
# Polling for A2A Agent Task Completion
This sample demonstrates how to poll for long-running task completion using continuation tokens with an A2A AI agent, following the background responses pattern.
The sample:
- Connects to an A2A agent server specified in the `A2A_AGENT_HOST` environment variable
- Sends a request to the agent that may take time to complete
- Polls the agent at regular intervals using continuation tokens until a final response is received
- Displays the final result
This pattern is useful when an AI model cannot complete a complex task in a single response and needs multiple rounds of processing.
# Prerequisites
Before you begin, ensure you have the following prerequisites:
- .NET 10.0 SDK or later
- An A2A agent server running and accessible via HTTP
Set the following environment variable:
```powershell
$env:A2A_AGENT_HOST="http://localhost:5000" # Replace with your A2A agent server host
```
@@ -14,6 +14,7 @@ See the README.md for each sample for the prerequisites for that sample.
|Sample|Description|
|---|---|
|[A2A Agent As Function Tools](./A2AAgent_AsFunctionTools/)|This sample demonstrates how to represent an A2A agent as a set of function tools, where each function tool corresponds to a skill of the A2A agent, and register these function tools with another AI agent so it can leverage the A2A agent's skills.|
|[A2A Agent Polling For Task Completion](./A2AAgent_PollingForTaskCompletion/)|This sample demonstrates how to poll for long-running task completion using continuation tokens with an A2A agent.|
## Running the samples from the console
@@ -0,0 +1,21 @@
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
<TargetFrameworks>net10.0</TargetFrameworks>
<Nullable>enable</Nullable>
<ImplicitUsings>enable</ImplicitUsings>
<NoWarn>$(NoWarn);IDE0059</NoWarn>
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Anthropic.Foundry" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Anthropic\Microsoft.Agents.AI.Anthropic.csproj" />
</ItemGroup>
</Project>
@@ -0,0 +1,74 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample shows how to create and use an AI agent with Anthropic as the backend.
using System.Net.Http.Headers;
using Anthropic;
using Anthropic.Foundry;
using Azure.Core;
using Azure.Identity;
using Microsoft.Agents.AI;
using Sample;
var deploymentName = Environment.GetEnvironmentVariable("ANTHROPIC_DEPLOYMENT_NAME") ?? "claude-haiku-4-5";
// The resource is the subdomain name / first name coming before '.services.ai.azure.com' in the endpoint Uri
// ie: https://(resource name).services.ai.azure.com/anthropic/v1/chat/completions
string? resource = Environment.GetEnvironmentVariable("ANTHROPIC_RESOURCE");
string? apiKey = Environment.GetEnvironmentVariable("ANTHROPIC_API_KEY");
const string JokerInstructions = "You are good at telling jokes.";
const string JokerName = "JokerAgent";
AnthropicClient? client = (resource is null)
? new AnthropicClient() { APIKey = apiKey ?? throw new InvalidOperationException("ANTHROPIC_API_KEY is required when no ANTHROPIC_RESOURCE is provided") } // If no resource is provided, use Anthropic public API
: (apiKey is not null)
? new AnthropicFoundryClient(new AnthropicFoundryApiKeyCredentials(apiKey, resource)) // If an apiKey is provided, use Foundry with ApiKey authentication
: new AnthropicFoundryClient(new AnthropicAzureTokenCredential(new AzureCliCredential(), resource)); // Otherwise, use Foundry with Azure Client authentication
AIAgent agent = client.CreateAIAgent(model: deploymentName, instructions: JokerInstructions, name: JokerName);
// Invoke the agent and output the text result.
Console.WriteLine(await agent.RunAsync("Tell me a joke about a pirate."));
namespace Sample
{
/// <summary>
/// Provides methods for invoking the Azure hosted Anthropic models using <see cref="TokenCredential"/> types.
/// </summary>
public sealed class AnthropicAzureTokenCredential : IAnthropicFoundryCredentials
{
private readonly TokenCredential _tokenCredential;
private readonly Lock _lock = new();
private AccessToken? _cachedAccessToken;
/// <inheritdoc/>
public string ResourceName { get; }
/// <summary>
/// Creates a new instance of the <see cref="AnthropicAzureTokenCredential"/>.
/// </summary>
/// <param name="tokenCredential">The credential provider. Use any specialization of <see cref="TokenCredential"/> to get your access token in supported environments.</param>
/// <param name="resourceName">The service resource subdomain name to use in the anthropic azure endpoint</param>
internal AnthropicAzureTokenCredential(TokenCredential tokenCredential, string resourceName)
{
this.ResourceName = resourceName ?? throw new ArgumentNullException(nameof(resourceName));
this._tokenCredential = tokenCredential ?? throw new ArgumentNullException(nameof(tokenCredential));
}
/// <inheritdoc/>
public void Apply(HttpRequestMessage requestMessage)
{
lock (this._lock)
{
// Add a 5-minute buffer to avoid using tokens that are about to expire
if (this._cachedAccessToken is null || this._cachedAccessToken.Value.ExpiresOn <= DateTimeOffset.Now.AddMinutes(5))
{
this._cachedAccessToken = this._tokenCredential.GetToken(new TokenRequestContext(scopes: ["https://ai.azure.com/.default"]), CancellationToken.None);
}
}
requestMessage.Headers.Authorization = new AuthenticationHeaderValue("bearer", this._cachedAccessToken.Value.Token);
}
}
}
@@ -0,0 +1,53 @@
# Creating an AIAgent with Anthropic
This sample demonstrates how to create an AIAgent using Anthropic Claude models as the underlying inference service.
The sample supports three deployment scenarios:
1. **Anthropic Public API** - Direct connection to Anthropic's public API
2. **Azure Foundry with API Key** - Anthropic models deployed through Azure Foundry using API key authentication
3. **Azure Foundry with Azure CLI** - Anthropic models deployed through Azure Foundry using Azure CLI credentials
## Prerequisites
Before you begin, ensure you have the following prerequisites:
- .NET 8.0 SDK or later
### For Anthropic Public API
- Anthropic API key
Set the following environment variables:
```powershell
$env:ANTHROPIC_API_KEY="your-anthropic-api-key" # Replace with your Anthropic API key
$env:ANTHROPIC_DEPLOYMENT_NAME="claude-haiku-4-5" # Optional, defaults to claude-haiku-4-5
```
### For Azure Foundry with API Key
- Azure Foundry service endpoint and deployment configured
- Anthropic API key
Set the following environment variables:
```powershell
$env:ANTHROPIC_RESOURCE="your-foundry-resource-name" # Replace with your Azure Foundry resource name (subdomain before .services.ai.azure.com)
$env:ANTHROPIC_API_KEY="your-anthropic-api-key" # Replace with your Anthropic API key
$env:ANTHROPIC_DEPLOYMENT_NAME="claude-haiku-4-5" # Optional, defaults to claude-haiku-4-5
```
### For Azure Foundry with Azure CLI
- Azure Foundry service endpoint and deployment configured
- Azure CLI installed and authenticated (for Azure credential authentication)
Set the following environment variables:
```powershell
$env:ANTHROPIC_RESOURCE="your-foundry-resource-name" # Replace with your Azure Foundry resource name (subdomain before .services.ai.azure.com)
$env:ANTHROPIC_DEPLOYMENT_NAME="claude-haiku-4-5" # Optional, defaults to claude-haiku-4-5
```
**Note**: When using Azure Foundry with Azure CLI, make sure you're logged in with `az login` and have access to the Azure Foundry resource. For more information, see the [Azure CLI documentation](https://learn.microsoft.com/cli/azure/authenticate-azure-cli-interactively).
@@ -1,3 +1,13 @@
# Classic Foundry Agents
This sample demonstrates how to create an agent using the classic Foundry Agents experience.
# Classic vs New Foundry Agents
Below is a comparison between the classic and new Foundry Agents approaches:
[Migration Guide](https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/migrate?view=foundry)
# Prerequisites
Before you begin, ensure you have the following prerequisites:
@@ -10,35 +10,34 @@ using Microsoft.Agents.AI;
var endpoint = Environment.GetEnvironmentVariable("AZURE_FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("AZURE_FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_FOUNDRY_PROJECT_DEPLOYMENT_NAME") ?? "gpt-4o-mini";
const string JokerInstructions = "You are good at telling jokes.";
const string JokerName = "JokerAgent";
// Get a client to create/retrieve/delete server side agents with Azure Foundry Agents.
var aiProjectClient = new AIProjectClient(new Uri(endpoint), new AzureCliCredential());
// Define the agent you want to create. (Prompt Agent in this case)
var agentVersionCreationOptions = new AgentVersionCreationOptions(new PromptAgentDefinition(model: deploymentName) { Instructions = JokerInstructions });
var agentVersionCreationOptions = new AgentVersionCreationOptions(new PromptAgentDefinition(model: deploymentName) { Instructions = "You are good at telling jokes." });
// Azure.AI.Agents SDK creates and manages agent by name and versions.
// You can create a server side agent version with the Azure.AI.Agents SDK client below.
var agentVersion = aiProjectClient.Agents.CreateAgentVersion(agentName: JokerName, options: agentVersionCreationOptions);
var createdAgentVersion = aiProjectClient.Agents.CreateAgentVersion(agentName: JokerName, options: agentVersionCreationOptions);
// Note:
// agentVersion.Id = "<agentName>:<versionNumber>",
// agentVersion.Version = <versionNumber>,
// agentVersion.Name = <agentName>
// You can retrieve an AIAgent for a already created server side agent version.
AIAgent jokerAgentV1 = aiProjectClient.GetAIAgent(agentVersion);
// You can retrieve an AIAgent for an already created server side agent version.
AIAgent existingJokerAgent = aiProjectClient.GetAIAgent(createdAgentVersion);
// You can also create another AIAgent version (V2) by providing the same name with a different definition.
AIAgent jokerAgentV2 = aiProjectClient.CreateAIAgent(name: JokerName, model: deploymentName, instructions: JokerInstructions + "V2");
// You can also create another AIAgent version by providing the same name with a different definition.
AIAgent newJokerAgent = aiProjectClient.CreateAIAgent(name: JokerName, model: deploymentName, instructions: "You are extremely hilarious at telling jokes.");
// You can also get the AIAgent latest version just providing its name.
AIAgent jokerAgentLatest = aiProjectClient.GetAIAgent(name: JokerName);
var latestVersion = jokerAgentLatest.GetService<AgentVersion>()!;
var latestAgentVersion = jokerAgentLatest.GetService<AgentVersion>()!;
// The AIAgent version can be accessed via the GetService method.
Console.WriteLine($"Latest agent version id: {latestVersion.Id}");
Console.WriteLine($"Latest agent version id: {latestAgentVersion.Id}");
// Once you have the AIAgent, you can invoke it like any other AIAgent.
AgentThread thread = jokerAgentLatest.GetNewThread();
@@ -47,5 +46,5 @@ Console.WriteLine(await jokerAgentLatest.RunAsync("Tell me a joke about a pirate
// This will use the same thread to continue the conversation.
Console.WriteLine(await jokerAgentLatest.RunAsync("Now tell me a joke about a cat and a dog using last joke as the anchor.", thread));
// Cleanup by agent name removes both agent versions created (jokerAgentV1 + jokerAgentV2).
aiProjectClient.Agents.DeleteAgent(jokerAgentV1.Name);
// Cleanup by agent name removes both agent versions created.
aiProjectClient.Agents.DeleteAgent(existingJokerAgent.Name);
@@ -1,3 +1,13 @@
# New Foundry Agents
This sample demonstrates how to create an agent using the new Foundry Agents experience.
# Classic vs New Foundry Agents
Below is a comparison between the classic and new Foundry Agents approaches:
[Migration Guide](https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/migrate?view=foundry)
# Prerequisites
Before you begin, ensure you have the following prerequisites:
@@ -39,11 +39,16 @@ namespace SampleApp
// Create a thread if the user didn't supply one.
thread ??= this.GetNewThread();
if (thread is not CustomAgentThread typedThread)
{
throw new ArgumentException($"The provided thread is not of type {nameof(CustomAgentThread)}.", nameof(thread));
}
// Clone the input messages and turn them into response messages with upper case text.
List<ChatMessage> responseMessages = CloneAndToUpperCase(messages, this.DisplayName).ToList();
// Notify the thread of the input and output messages.
await NotifyThreadOfNewMessagesAsync(thread, messages.Concat(responseMessages), cancellationToken);
await typedThread.MessageStore.AddMessagesAsync(messages.Concat(responseMessages), cancellationToken);
return new AgentRunResponse
{
@@ -58,11 +63,16 @@ namespace SampleApp
// Create a thread if the user didn't supply one.
thread ??= this.GetNewThread();
if (thread is not CustomAgentThread typedThread)
{
throw new ArgumentException($"The provided thread is not of type {nameof(CustomAgentThread)}.", nameof(thread));
}
// Clone the input messages and turn them into response messages with upper case text.
List<ChatMessage> responseMessages = CloneAndToUpperCase(messages, this.DisplayName).ToList();
// Notify the thread of the input and output messages.
await NotifyThreadOfNewMessagesAsync(thread, messages.Concat(responseMessages), cancellationToken);
await typedThread.MessageStore.AddMessagesAsync(messages.Concat(responseMessages), cancellationToken);
foreach (var message in responseMessages)
{
@@ -0,0 +1,25 @@
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
<TargetFrameworks>net8.0;net9.0;net10.0</TargetFrameworks>
<Nullable>enable</Nullable>
<ImplicitUsings>enable</ImplicitUsings>
<NoWarn>$(NoWarn);IDE0059;NU1510</NoWarn>
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Google.GenAI" />
<PackageReference Include="Mscc.GenerativeAI.Microsoft" />
</ItemGroup>
<ItemGroup Condition="'$(TargetFramework)' == 'net8.0' or '$(TargetFramework)' == 'net9.0'">
<PackageReference Include="System.Net.Security" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI\Microsoft.Agents.AI.csproj" />
</ItemGroup>
</Project>
@@ -0,0 +1,558 @@
// Copyright (c) Microsoft. All rights reserved.
using System.Runtime.CompilerServices;
using Google.Apis.Util;
using Google.GenAI;
using Google.GenAI.Types;
namespace Microsoft.Extensions.AI;
/// <summary>Provides an <see cref="IChatClient"/> implementation based on <see cref="Client"/>.</summary>
internal sealed class GoogleGenAIChatClient : IChatClient
{
/// <summary>The wrapped <see cref="Client"/> instance (optional).</summary>
private readonly Client? _client;
/// <summary>The wrapped <see cref="Models"/> instance.</summary>
private readonly Models _models;
/// <summary>The default model that should be used when no override is specified.</summary>
private readonly string? _defaultModelId;
/// <summary>Lazily-initialized metadata describing the implementation.</summary>
private ChatClientMetadata? _metadata;
/// <summary>Initializes a new <see cref="GoogleGenAIChatClient"/> instance.</summary>
public GoogleGenAIChatClient(Client client, string? defaultModelId)
{
this._client = client;
this._models = client.Models;
this._defaultModelId = defaultModelId;
}
/// <summary>Initializes a new <see cref="GoogleGenAIChatClient"/> instance.</summary>
public GoogleGenAIChatClient(Models client, string? defaultModelId)
{
this._models = client;
this._defaultModelId = defaultModelId;
}
/// <inheritdoc />
public async Task<ChatResponse> GetResponseAsync(IEnumerable<ChatMessage> messages, ChatOptions? options = null, CancellationToken cancellationToken = default)
{
Utilities.ThrowIfNull(messages, nameof(messages));
// Create the request.
(string? modelId, List<Content> contents, GenerateContentConfig config) = this.CreateRequest(messages, options);
// Send it.
GenerateContentResponse generateResult = await this._models.GenerateContentAsync(modelId!, contents, config).ConfigureAwait(false);
// Create the response.
ChatResponse chatResponse = new(new ChatMessage(ChatRole.Assistant, new List<AIContent>()))
{
CreatedAt = generateResult.CreateTime is { } dt ? new DateTimeOffset(dt) : null,
ModelId = !string.IsNullOrWhiteSpace(generateResult.ModelVersion) ? generateResult.ModelVersion : modelId,
RawRepresentation = generateResult,
ResponseId = generateResult.ResponseId,
};
// Populate the response messages.
chatResponse.FinishReason = PopulateResponseContents(generateResult, chatResponse.Messages[0].Contents);
// Populate usage information if there is any.
if (generateResult.UsageMetadata is { } usageMetadata)
{
chatResponse.Usage = ExtractUsageDetails(usageMetadata);
}
// Return the response.
return chatResponse;
}
/// <inheritdoc />
public async IAsyncEnumerable<ChatResponseUpdate> GetStreamingResponseAsync(IEnumerable<ChatMessage> messages, ChatOptions? options = null, [EnumeratorCancellation] CancellationToken cancellationToken = default)
{
Utilities.ThrowIfNull(messages, nameof(messages));
// Create the request.
(string? modelId, List<Content> contents, GenerateContentConfig config) = this.CreateRequest(messages, options);
// Send it, and process the results.
await foreach (GenerateContentResponse generateResult in this._models.GenerateContentStreamAsync(modelId!, contents, config).WithCancellation(cancellationToken).ConfigureAwait(false))
{
// Create a response update for each result in the stream.
ChatResponseUpdate responseUpdate = new(ChatRole.Assistant, new List<AIContent>())
{
CreatedAt = generateResult.CreateTime is { } dt ? new DateTimeOffset(dt) : null,
ModelId = !string.IsNullOrWhiteSpace(generateResult.ModelVersion) ? generateResult.ModelVersion : modelId,
RawRepresentation = generateResult,
ResponseId = generateResult.ResponseId,
};
// Populate the response update contents.
responseUpdate.FinishReason = PopulateResponseContents(generateResult, responseUpdate.Contents);
// Populate usage information if there is any.
if (generateResult.UsageMetadata is { } usageMetadata)
{
responseUpdate.Contents.Add(new UsageContent(ExtractUsageDetails(usageMetadata)));
}
// Yield the update.
yield return responseUpdate;
}
}
/// <inheritdoc />
public object? GetService(System.Type serviceType, object? serviceKey = null)
{
Utilities.ThrowIfNull(serviceType, nameof(serviceType));
if (serviceKey is null)
{
// If there's a request for metadata, lazily-initialize it and return it. We don't need to worry about race conditions,
// as there's no requirement that the same instance be returned each time, and creation is idempotent.
if (serviceType == typeof(ChatClientMetadata))
{
return this._metadata ??= new("gcp.gen_ai", new("https://generativelanguage.googleapis.com/"), defaultModelId: this._defaultModelId);
}
// Allow a consumer to "break glass" and access the underlying client if they need it.
if (serviceType.IsInstanceOfType(this._models))
{
return this._models;
}
if (this._client is not null && serviceType.IsInstanceOfType(this._client))
{
return this._client;
}
if (serviceType.IsInstanceOfType(this))
{
return this;
}
}
return null;
}
/// <inheritdoc />
void IDisposable.Dispose() { /* nop */ }
/// <summary>Creates the message parameters for <see cref="Models.GenerateContentAsync(string, List{Content}, GenerateContentConfig?)"/> from <paramref name="messages"/> and <paramref name="options"/>.</summary>
private (string? ModelId, List<Content> Contents, GenerateContentConfig Config) CreateRequest(IEnumerable<ChatMessage> messages, ChatOptions? options)
{
// Create the GenerateContentConfig object. If the options contains a RawRepresentationFactory, try to use it to
// create the request instance, allowing the caller to populate it with GenAI-specific options. Otherwise, create
// a new instance directly.
string? model = this._defaultModelId;
List<Content> contents = new();
GenerateContentConfig config = options?.RawRepresentationFactory?.Invoke(this) as GenerateContentConfig ?? new();
if (options is not null)
{
if (options.FrequencyPenalty is { } frequencyPenalty)
{
config.FrequencyPenalty ??= frequencyPenalty;
}
if (options.Instructions is { } instructions)
{
((config.SystemInstruction ??= new()).Parts ??= new()).Add(new() { Text = instructions });
}
if (options.MaxOutputTokens is { } maxOutputTokens)
{
config.MaxOutputTokens ??= maxOutputTokens;
}
if (!string.IsNullOrWhiteSpace(options.ModelId))
{
model = options.ModelId;
}
if (options.PresencePenalty is { } presencePenalty)
{
config.PresencePenalty ??= presencePenalty;
}
if (options.Seed is { } seed)
{
config.Seed ??= (int)seed;
}
if (options.StopSequences is { } stopSequences)
{
(config.StopSequences ??= new()).AddRange(stopSequences);
}
if (options.Temperature is { } temperature)
{
config.Temperature ??= temperature;
}
if (options.TopP is { } topP)
{
config.TopP ??= topP;
}
if (options.TopK is { } topK)
{
config.TopK ??= topK;
}
// Populate tools. Each kind of tool is added on its own, except for function declarations,
// which are grouped into a single FunctionDeclaration.
List<FunctionDeclaration>? functionDeclarations = null;
if (options.Tools is { } tools)
{
foreach (var tool in tools)
{
switch (tool)
{
case AIFunctionDeclaration af:
functionDeclarations ??= new();
functionDeclarations.Add(new()
{
Name = af.Name,
Description = af.Description ?? "",
ParametersJsonSchema = af.JsonSchema,
});
break;
case HostedCodeInterpreterTool:
(config.Tools ??= new()).Add(new() { CodeExecution = new() });
break;
case HostedFileSearchTool:
(config.Tools ??= new()).Add(new() { Retrieval = new() });
break;
case HostedWebSearchTool:
(config.Tools ??= new()).Add(new() { GoogleSearch = new() });
break;
}
}
}
if (functionDeclarations is { Count: > 0 })
{
Tool functionTools = new();
(functionTools.FunctionDeclarations ??= new()).AddRange(functionDeclarations);
(config.Tools ??= new()).Add(functionTools);
}
// Transfer over the tool mode if there are any tools.
if (options.ToolMode is { } toolMode && config.Tools?.Count > 0)
{
switch (toolMode)
{
case NoneChatToolMode:
config.ToolConfig = new() { FunctionCallingConfig = new() { Mode = FunctionCallingConfigMode.NONE } };
break;
case AutoChatToolMode:
config.ToolConfig = new() { FunctionCallingConfig = new() { Mode = FunctionCallingConfigMode.AUTO } };
break;
case RequiredChatToolMode required:
config.ToolConfig = new() { FunctionCallingConfig = new() { Mode = FunctionCallingConfigMode.ANY } };
if (required.RequiredFunctionName is not null)
{
((config.ToolConfig.FunctionCallingConfig ??= new()).AllowedFunctionNames ??= new()).Add(required.RequiredFunctionName);
}
break;
}
}
// Set the response format if specified.
if (options.ResponseFormat is ChatResponseFormatJson responseFormat)
{
config.ResponseMimeType = "application/json";
if (responseFormat.Schema is { } schema)
{
config.ResponseJsonSchema = schema;
}
}
}
// Transfer messages to request, handling system messages specially
Dictionary<string, string>? callIdToFunctionNames = null;
foreach (var message in messages)
{
if (message.Role == ChatRole.System)
{
string instruction = message.Text;
if (!string.IsNullOrWhiteSpace(instruction))
{
((config.SystemInstruction ??= new()).Parts ??= new()).Add(new() { Text = instruction });
}
continue;
}
Content content = new() { Role = message.Role == ChatRole.Assistant ? "model" : "user" };
content.Parts ??= new();
AddPartsForAIContents(ref callIdToFunctionNames, message.Contents, content.Parts);
contents.Add(content);
}
// Make sure the request contains at least one content part (the request would always fail if empty).
if (!contents.SelectMany(c => c.Parts ?? Enumerable.Empty<Part>()).Any())
{
contents.Add(new() { Role = "user", Parts = new() { { new() { Text = "" } } } });
}
return (model, contents, config);
}
/// <summary>Creates <see cref="Part"/>s for <paramref name="contents"/> and adds them to <paramref name="parts"/>.</summary>
private static void AddPartsForAIContents(ref Dictionary<string, string>? callIdToFunctionNames, IList<AIContent> contents, List<Part> parts)
{
for (int i = 0; i < contents.Count; i++)
{
var content = contents[i];
byte[]? thoughtSignature = null;
if (content is not TextReasoningContent { ProtectedData: not null } &&
i + 1 < contents.Count &&
contents[i + 1] is TextReasoningContent nextReasoning &&
string.IsNullOrWhiteSpace(nextReasoning.Text) &&
nextReasoning.ProtectedData is { } protectedData)
{
i++;
thoughtSignature = Convert.FromBase64String(protectedData);
}
Part? part = null;
switch (content)
{
case TextContent textContent:
part = new() { Text = textContent.Text };
break;
case TextReasoningContent reasoningContent:
part = new()
{
Thought = true,
Text = !string.IsNullOrWhiteSpace(reasoningContent.Text) ? reasoningContent.Text : null,
ThoughtSignature = reasoningContent.ProtectedData is not null ? Convert.FromBase64String(reasoningContent.ProtectedData) : null,
};
break;
case DataContent dataContent:
part = new()
{
InlineData = new()
{
MimeType = dataContent.MediaType,
Data = dataContent.Data.ToArray(),
DisplayName = dataContent.Name,
}
};
break;
case UriContent uriContent:
part = new()
{
FileData = new()
{
FileUri = uriContent.Uri.AbsoluteUri,
MimeType = uriContent.MediaType,
}
};
break;
case FunctionCallContent functionCallContent:
(callIdToFunctionNames ??= new())[functionCallContent.CallId] = functionCallContent.Name;
callIdToFunctionNames[""] = functionCallContent.Name; // track last function name in case calls don't have IDs
part = new()
{
FunctionCall = new()
{
Id = functionCallContent.CallId,
Name = functionCallContent.Name,
Args = functionCallContent.Arguments is null ? null : functionCallContent.Arguments as Dictionary<string, object> ?? new(functionCallContent.Arguments!),
}
};
break;
case FunctionResultContent functionResultContent:
part = new()
{
FunctionResponse = new()
{
Id = functionResultContent.CallId,
Name = callIdToFunctionNames?.TryGetValue(functionResultContent.CallId, out string? functionName) is true || callIdToFunctionNames?.TryGetValue("", out functionName) is true ?
functionName :
null,
Response = functionResultContent.Result is null ? null : new() { ["result"] = functionResultContent.Result },
}
};
break;
}
if (part is not null)
{
part.ThoughtSignature ??= thoughtSignature;
parts.Add(part);
}
}
}
/// <summary>Creates <see cref="AIContent"/>s for <paramref name="parts"/> and adds them to <paramref name="contents"/>.</summary>
private static void AddAIContentsForParts(List<Part> parts, IList<AIContent> contents)
{
foreach (var part in parts)
{
AIContent? content = null;
if (!string.IsNullOrEmpty(part.Text))
{
content = part.Thought is true ?
new TextReasoningContent(part.Text) :
new TextContent(part.Text);
}
else if (part.InlineData is { } inlineData)
{
content = new DataContent(inlineData.Data, inlineData.MimeType ?? "application/octet-stream")
{
Name = inlineData.DisplayName,
};
}
else if (part.FileData is { FileUri: not null } fileData)
{
content = new UriContent(new Uri(fileData.FileUri), fileData.MimeType ?? "application/octet-stream");
}
else if (part.FunctionCall is { Name: not null } functionCall)
{
content = new FunctionCallContent(functionCall.Id ?? "", functionCall.Name, functionCall.Args!);
}
else if (part.FunctionResponse is { } functionResponse)
{
content = new FunctionResultContent(
functionResponse.Id ?? "",
functionResponse.Response?.TryGetValue("output", out var output) is true ? output :
functionResponse.Response?.TryGetValue("error", out var error) is true ? error :
null);
}
if (content is not null)
{
content.RawRepresentation = part;
contents.Add(content);
if (part.ThoughtSignature is { } thoughtSignature)
{
contents.Add(new TextReasoningContent(null)
{
ProtectedData = Convert.ToBase64String(thoughtSignature),
});
}
}
}
}
private static ChatFinishReason? PopulateResponseContents(GenerateContentResponse generateResult, IList<AIContent> responseContents)
{
ChatFinishReason? finishReason = null;
// Populate the response messages. There should only be at most one candidate, but if there are more, ignore all but the first.
if (generateResult.Candidates is { Count: > 0 } &&
generateResult.Candidates[0] is { Content: { } candidateContent } candidate)
{
// Grab the finish reason if one exists.
finishReason = ConvertFinishReason(candidate.FinishReason);
// Add all of the response content parts as AIContents.
if (candidateContent.Parts is { } parts)
{
AddAIContentsForParts(parts, responseContents);
}
// Add any citation metadata.
if (candidate.CitationMetadata is { Citations: { Count: > 0 } citations } &&
responseContents.OfType<TextContent>().FirstOrDefault() is TextContent textContent)
{
foreach (var citation in citations)
{
textContent.Annotations = new List<AIAnnotation>()
{
new CitationAnnotation()
{
Title = citation.Title,
Url = Uri.TryCreate(citation.Uri, UriKind.Absolute, out Uri? uri) ? uri : null,
AnnotatedRegions = new List<AnnotatedRegion>()
{
new TextSpanAnnotatedRegion()
{
StartIndex = citation.StartIndex,
EndIndex = citation.EndIndex,
}
},
}
};
}
}
}
// Populate error information if there is any.
if (generateResult.PromptFeedback is { } promptFeedback)
{
responseContents.Add(new ErrorContent(promptFeedback.BlockReasonMessage));
}
return finishReason;
}
/// <summary>Creates an M.E.AI <see cref="ChatFinishReason"/> from a Google <see cref="FinishReason"/>.</summary>
private static ChatFinishReason? ConvertFinishReason(FinishReason? finishReason)
{
return finishReason switch
{
null => null,
FinishReason.MAX_TOKENS =>
ChatFinishReason.Length,
FinishReason.MALFORMED_FUNCTION_CALL or
FinishReason.UNEXPECTED_TOOL_CALL =>
ChatFinishReason.ToolCalls,
FinishReason.FINISH_REASON_UNSPECIFIED or
FinishReason.STOP =>
ChatFinishReason.Stop,
_ => ChatFinishReason.ContentFilter,
};
}
/// <summary>Creates a <see cref="UsageDetails"/> populated from the supplied <paramref name="usageMetadata"/>.</summary>
private static UsageDetails ExtractUsageDetails(GenerateContentResponseUsageMetadata usageMetadata)
{
UsageDetails details = new()
{
InputTokenCount = usageMetadata.PromptTokenCount,
OutputTokenCount = usageMetadata.CandidatesTokenCount,
TotalTokenCount = usageMetadata.TotalTokenCount,
};
AddIfPresent(nameof(usageMetadata.CachedContentTokenCount), usageMetadata.CachedContentTokenCount);
AddIfPresent(nameof(usageMetadata.ThoughtsTokenCount), usageMetadata.ThoughtsTokenCount);
AddIfPresent(nameof(usageMetadata.ToolUsePromptTokenCount), usageMetadata.ToolUsePromptTokenCount);
return details;
void AddIfPresent(string key, int? value)
{
if (value is int i)
{
(details.AdditionalCounts ??= new())[key] = i;
}
}
}
}
@@ -0,0 +1,36 @@
// Copyright (c) Microsoft. All rights reserved.
using Google.Apis.Util;
using Google.GenAI;
namespace Microsoft.Extensions.AI;
/// <summary>Provides implementations of Microsoft.Extensions.AI abstractions based on <see cref="Client"/>.</summary>
public static class GoogleGenAIExtensions
{
/// <summary>
/// Creates an <see cref="IChatClient"/> wrapper around the specified <see cref="Client"/>.
/// </summary>
/// <param name="client">The <see cref="Client"/> to wrap.</param>
/// <param name="defaultModelId">The default model ID to use for chat requests if not specified in <see cref="ChatOptions.ModelId"/>.</param>
/// <returns>An <see cref="IChatClient"/> that wraps the specified client.</returns>
/// <exception cref="ArgumentNullException"><paramref name="client"/> is <see langword="null"/>.</exception>
public static IChatClient AsIChatClient(this Client client, string? defaultModelId = null)
{
Utilities.ThrowIfNull(client, nameof(client));
return new GoogleGenAIChatClient(client, defaultModelId);
}
/// <summary>
/// Creates an <see cref="IChatClient"/> wrapper around the specified <see cref="Models"/>.
/// </summary>
/// <param name="models">The <see cref="Models"/> client to wrap.</param>
/// <param name="defaultModelId">The default model ID to use for chat requests if not specified in <see cref="ChatOptions.ModelId"/>.</param>
/// <returns>An <see cref="IChatClient"/> that wraps the specified <see cref="Models"/> client.</returns>
/// <exception cref="ArgumentNullException"><paramref name="models"/> is <see langword="null"/>.</exception>
public static IChatClient AsIChatClient(this Models models, string? defaultModelId = null)
{
Utilities.ThrowIfNull(models, nameof(models));
return new GoogleGenAIChatClient(models, defaultModelId);
}
}
@@ -0,0 +1,36 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample shows how to create and use an AI agent with Google Gemini
using Google.GenAI;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
using Mscc.GenerativeAI.Microsoft;
const string JokerInstructions = "You are good at telling jokes.";
const string JokerName = "JokerAgent";
string apiKey = Environment.GetEnvironmentVariable("GOOGLE_GENAI_API_KEY") ?? throw new InvalidOperationException("Please set the GOOGLE_GENAI_API_KEY environment variable.");
string model = Environment.GetEnvironmentVariable("GOOGLE_GENAI_MODEL") ?? "gemini-2.5-fast";
// Using a Google GenAI IChatClient implementation
// Until the PR https://github.com/googleapis/dotnet-genai/pull/81 is not merged this option
// requires usage of also both GeminiChatClient.cs and GoogleGenAIExtensions.cs polyfills to work.
ChatClientAgent agentGenAI = new(
new Client(vertexAI: false, apiKey: apiKey).AsIChatClient(model),
name: JokerName,
instructions: JokerInstructions);
AgentRunResponse response = await agentGenAI.RunAsync("Tell me a joke about a pirate.");
Console.WriteLine($"Google GenAI client based agent response:\n{response}");
// Using a community driven Mscc.GenerativeAI.Microsoft package
ChatClientAgent agentCommunity = new(
new GeminiChatClient(apiKey, model),
name: JokerName,
instructions: JokerInstructions);
response = await agentCommunity.RunAsync("Tell me a joke about a pirate.");
Console.WriteLine($"Community client based agent response:\n{response}");
@@ -0,0 +1,37 @@
# Creating an AIAgent with Google Gemini
This sample demonstrates how to create an AIAgent using Google Gemini models as the underlying inference service.
The sample showcases two different `IChatClient` implementations:
1. **Google GenAI** - Using the official [Google.GenAI](https://www.nuget.org/packages/Google.GenAI) package
2. **Mscc.GenerativeAI.Microsoft** - Using the community-driven [Mscc.GenerativeAI.Microsoft](https://www.nuget.org/packages/Mscc.GenerativeAI.Microsoft) package
## Prerequisites
Before you begin, ensure you have the following prerequisites:
- .NET 10.0 SDK or later
- Google AI Studio API key (get one at [Google AI Studio](https://aistudio.google.com/apikey))
Set the following environment variables:
```powershell
$env:GOOGLE_GENAI_API_KEY="your-google-api-key" # Replace with your Google AI Studio API key
$env:GOOGLE_GENAI_MODEL="gemini-2.5-fast" # Optional, defaults to gemini-2.5-fast
```
## Package Options
### Google GenAI (Official)
The official Google GenAI package provides direct access to Google's Generative AI models. This sample uses an extension method to convert the Google client to an `IChatClient`.
> [!NOTE]
> Until PR [googleapis/dotnet-genai#81](https://github.com/googleapis/dotnet-genai/pull/81) is merged, this option requires the additional `GeminiChatClient.cs` and `GoogleGenAIExtensions.cs` files included in this sample.
>
> We appreciate any community push by liking and commenting in the above PR to get it merged and release as part of official Google GenAI package.
### Mscc.GenerativeAI.Microsoft (Community)
The community-driven Mscc.GenerativeAI.Microsoft package provides a ready-to-use `IChatClient` implementation for Google Gemini models through the `GeminiChatClient` class.
@@ -2,7 +2,7 @@
<PropertyGroup>
<OutputType>Exe</OutputType>
<TargetFrameworks>net10.0</TargetFrameworks>
<TargetFramework>net10.0</TargetFramework>
<Nullable>enable</Nullable>
<ImplicitUsings>enable</ImplicitUsings>
@@ -3,6 +3,7 @@
// This sample shows how to create and use a simple AI agent with OpenAI Chat Completion as the backend.
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
using OpenAI;
var apiKey = Environment.GetEnvironmentVariable("OPENAI_APIKEY") ?? throw new InvalidOperationException("OPENAI_APIKEY is not set.");
@@ -15,6 +15,7 @@ See the README.md for each sample for the prerequisites for that sample.
|Sample|Description|
|---|---|
|[Creating an AIAgent with A2A](./Agent_With_A2A/)|This sample demonstrates how to create AIAgent for an existing A2A agent.|
|[Creating an AIAgent with Anthropic](./Agent_With_Anthropic/)|This sample demonstrates how to create an AIAgent using Anthropic Claude models as the underlying inference service|
|[Creating an AIAgent with Foundry Agents using Azure.AI.Agents.Persistent](./Agent_With_AzureAIAgentsPersistent/)|This sample demonstrates how to create a Foundry Persistent agent and expose it as an AIAgent using the Azure.AI.Agents.Persistent SDK|
|[Creating an AIAgent with Foundry Agents using Azure.AI.Project](./Agent_With_AzureAIProject/)|This sample demonstrates how to create an Foundry Project agent and expose it as an AIAgent using the Azure.AI.Project SDK|
|[Creating an AIAgent with AzureFoundry Model](./Agent_With_AzureFoundryModel/)|This sample demonstrates how to use any model deployed to Azure Foundry to create an AIAgent|
@@ -0,0 +1,15 @@
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
<TargetFramework>net10.0</TargetFramework>
<Nullable>enable</Nullable>
<ImplicitUsings>enable</ImplicitUsings>
</PropertyGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Anthropic\Microsoft.Agents.AI.Anthropic.csproj" />
</ItemGroup>
</Project>
@@ -0,0 +1,24 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample shows how to create and use a simple AI agent with Anthropic as the backend.
using Anthropic;
using Anthropic.Core;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
var apiKey = Environment.GetEnvironmentVariable("ANTHROPIC_API_KEY") ?? throw new InvalidOperationException("ANTHROPIC_API_KEY is not set.");
var model = Environment.GetEnvironmentVariable("ANTHROPIC_MODEL") ?? "claude-haiku-4-5";
AIAgent agent = new AnthropicClient(new ClientOptions { APIKey = apiKey })
.CreateAIAgent(model: model, instructions: "You are good at telling jokes.", name: "Joker");
// Invoke the agent and output the text result.
var response = await agent.RunAsync("Tell me a joke about a pirate.");
Console.WriteLine(response);
// Invoke the agent with streaming support.
await foreach (var update in agent.RunStreamingAsync("Tell me a joke about a pirate."))
{
Console.WriteLine(update);
}
@@ -0,0 +1,43 @@
# Running a simple agent with Anthropic
This sample demonstrates how to create and run a basic agent with Anthropic Claude models.
## What this sample demonstrates
- Creating an AI agent with Anthropic Claude
- Running a simple agent with instructions
- Managing agent lifecycle
## Prerequisites
Before you begin, ensure you have the following prerequisites:
- .NET 8.0 SDK or later
- Anthropic API key configured
**Note**: This sample uses Anthropic Claude models. For more information, see [Anthropic documentation](https://docs.anthropic.com/).
Set the following environment variables:
```powershell
$env:ANTHROPIC_API_KEY="your-anthropic-api-key" # Replace with your Anthropic API key
$env:ANTHROPIC_MODEL="your-anthropic-model" # Replace with your Anthropic model
```
## Run the sample
Navigate to the AgentWithAnthropic sample directory and run:
```powershell
cd dotnet\samples\GettingStarted\AgentWithAnthropic
dotnet run --project .\Agent_Anthropic_Step01_Running
```
## Expected behavior
The sample will:
1. Create an agent with Anthropic Claude
2. Run the agent with a simple prompt
3. Display the agent's response
@@ -0,0 +1,15 @@
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
<TargetFramework>net10.0</TargetFramework>
<Nullable>enable</Nullable>
<ImplicitUsings>enable</ImplicitUsings>
</PropertyGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Anthropic\Microsoft.Agents.AI.Anthropic.csproj" />
</ItemGroup>
</Project>
@@ -0,0 +1,59 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample shows how to create and use an AI agent with reasoning capabilities.
using Anthropic;
using Anthropic.Core;
using Anthropic.Models.Messages;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
var apiKey = Environment.GetEnvironmentVariable("ANTHROPIC_API_KEY") ?? throw new InvalidOperationException("ANTHROPIC_API_KEY is not set.");
var model = Environment.GetEnvironmentVariable("ANTHROPIC_MODEL") ?? "claude-haiku-4-5";
var maxTokens = 4096;
var thinkingTokens = 2048;
var agent = new AnthropicClient(new ClientOptions { APIKey = apiKey })
.CreateAIAgent(
model: model,
clientFactory: (chatClient) => chatClient
.AsBuilder()
.ConfigureOptions(
options => options.RawRepresentationFactory = (_) => new MessageCreateParams()
{
Model = options.ModelId ?? model,
MaxTokens = options.MaxOutputTokens ?? maxTokens,
Messages = [],
Thinking = new ThinkingConfigParam(new ThinkingConfigEnabled(budgetTokens: thinkingTokens))
})
.Build());
Console.WriteLine("1. Non-streaming:");
var response = await agent.RunAsync("Solve this problem step by step: If a train travels 60 miles per hour and needs to cover 180 miles, how long will the journey take? Show your reasoning.");
Console.WriteLine("#### Start Thinking ####");
Console.WriteLine($"\e[92m{string.Join("\n", response.Messages.SelectMany(m => m.Contents.OfType<TextReasoningContent>().Select(c => c.Text)))}\e[0m");
Console.WriteLine("#### End Thinking ####");
Console.WriteLine("\n#### Final Answer ####");
Console.WriteLine(response.Text);
Console.WriteLine("Token usage:");
Console.WriteLine($"Input: {response.Usage?.InputTokenCount}, Output: {response.Usage?.OutputTokenCount}, {string.Join(", ", response.Usage?.AdditionalCounts ?? [])}");
Console.WriteLine();
Console.WriteLine("2. Streaming");
await foreach (var update in agent.RunStreamingAsync("Explain the theory of relativity in simple terms."))
{
foreach (var item in update.Contents)
{
if (item is TextReasoningContent reasoningContent)
{
Console.WriteLine($"\e[92m{reasoningContent.Text}\e[0m");
}
else if (item is TextContent textContent)
{
Console.WriteLine(textContent.Text);
}
}
}
@@ -0,0 +1,46 @@
# Using reasoning with Anthropic agents
This sample demonstrates how to use extended thinking/reasoning capabilities with Anthropic Claude agents.
## What this sample demonstrates
- Creating an AI agent with Anthropic Claude extended thinking
- Using reasoning capabilities for complex problem solving
- Extracting thinking and response content from agent output
- Managing agent lifecycle
## Prerequisites
Before you begin, ensure you have the following prerequisites:
- .NET 8.0 SDK or later
- Anthropic API key configured
- Access to Anthropic Claude models with extended thinking support
**Note**: This sample uses Anthropic Claude models with extended thinking. For more information, see [Anthropic documentation](https://docs.anthropic.com/).
Set the following environment variables:
```powershell
$env:ANTHROPIC_API_KEY="your-anthropic-api-key" # Replace with your Anthropic API key
$env:ANTHROPIC_MODEL="your-anthropic-model" # Replace with your Anthropic model
```
## Run the sample
Navigate to the AgentWithAnthropic sample directory and run:
```powershell
cd dotnet\samples\GettingStarted\AgentWithAnthropic
dotnet run --project .\Agent_Anthropic_Step02_Reasoning
```
## Expected behavior
The sample will:
1. Create an agent with Anthropic Claude extended thinking enabled
2. Run the agent with a complex reasoning prompt
3. Display the agent's thinking process
4. Display the agent's final response
@@ -0,0 +1,15 @@
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
<TargetFramework>net10.0</TargetFramework>
<Nullable>enable</Nullable>
<ImplicitUsings>enable</ImplicitUsings>
</PropertyGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Anthropic\Microsoft.Agents.AI.Anthropic.csproj" />
</ItemGroup>
</Project>
@@ -0,0 +1,37 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample demonstrates how to use an agent with function tools.
// It shows both non-streaming and streaming agent interactions using weather-related tools.
using System.ComponentModel;
using Anthropic;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
var apiKey = Environment.GetEnvironmentVariable("ANTHROPIC_API_KEY") ?? throw new InvalidOperationException("ANTHROPIC_API_KEY is not set.");
var model = Environment.GetEnvironmentVariable("ANTHROPIC_MODEL") ?? "claude-haiku-4-5";
[Description("Get the weather for a given location.")]
static string GetWeather([Description("The location to get the weather for.")] string location)
=> $"The weather in {location} is cloudy with a high of 15°C.";
const string AssistantInstructions = "You are a helpful assistant that can get weather information.";
const string AssistantName = "WeatherAssistant";
// Define the agent with function tools.
AITool tool = AIFunctionFactory.Create(GetWeather);
// Get anthropic client to create agents.
AIAgent agent = new AnthropicClient { APIKey = apiKey }
.CreateAIAgent(model: model, instructions: AssistantInstructions, name: AssistantName, tools: [tool]);
// Non-streaming agent interaction with function tools.
AgentThread thread = agent.GetNewThread();
Console.WriteLine(await agent.RunAsync("What is the weather like in Amsterdam?", thread));
// Streaming agent interaction with function tools.
thread = agent.GetNewThread();
await foreach (AgentRunResponseUpdate update in agent.RunStreamingAsync("What is the weather like in Amsterdam?", thread))
{
Console.WriteLine(update);
}
@@ -0,0 +1,47 @@
# Using Function Tools with Anthropic agents
This sample demonstrates how to use function tools with Anthropic Claude agents, allowing agents to call custom functions to retrieve information.
## What this sample demonstrates
- Creating function tools using AIFunctionFactory
- Passing function tools to an Anthropic Claude agent
- Running agents with function tools (text output)
- Running agents with function tools (streaming output)
- Managing agent lifecycle
## Prerequisites
Before you begin, ensure you have the following prerequisites:
- .NET 8.0 SDK or later
- Anthropic API key configured
**Note**: This sample uses Anthropic Claude models. For more information, see [Anthropic documentation](https://docs.anthropic.com/).
Set the following environment variables:
```powershell
$env:ANTHROPIC_API_KEY="your-anthropic-api-key" # Replace with your Anthropic API key
$env:ANTHROPIC_MODEL="your-anthropic-model" # Replace with your Anthropic model
```
## Run the sample
Navigate to the AgentWithAnthropic sample directory and run:
```powershell
cd dotnet\samples\GettingStarted\AgentWithAnthropic
dotnet run --project .\Agent_Anthropic_Step03_UsingFunctionTools
```
## Expected behavior
The sample will:
1. Create an agent named "WeatherAssistant" with a GetWeather function tool
2. Run the agent with a text prompt asking about weather
3. The agent will invoke the GetWeather function tool to retrieve weather information
4. Run the agent again with streaming to display the response as it's generated
5. Clean up resources by deleting the agent
@@ -0,0 +1,72 @@
# Getting started with agents using Anthropic
The getting started with agents using Anthropic samples demonstrate the fundamental concepts and functionalities
of single agents using Anthropic as the AI provider.
These samples use Anthropic Claude models as the AI provider and use ChatCompletion as the type of service.
For other samples that demonstrate how to create and configure each type of agent that come with the agent framework,
see the [How to create an agent for each provider](../AgentProviders/README.md) samples.
## Getting started with agents using Anthropic prerequisites
Before you begin, ensure you have the following prerequisites:
- .NET 8.0 SDK or later
- Anthropic API key configured
- User has access to Anthropic Claude models
**Note**: These samples use Anthropic Claude models. For more information, see [Anthropic documentation](https://docs.anthropic.com/).
## Using Anthropic with Azure Foundry
To use Anthropic with Azure Foundry, you can check the sample [AgentProviders/Agent_With_Anthropic](../AgentProviders/Agent_With_Anthropic/README.md) for more details.
## Samples
|Sample|Description|
|---|---|
|[Running a simple agent](./Agent_Anthropic_Step01_Running/)|This sample demonstrates how to create and run a basic agent with Anthropic Claude|
|[Using reasoning with an agent](./Agent_Anthropic_Step02_Reasoning/)|This sample demonstrates how to use extended thinking/reasoning capabilities with Anthropic Claude agents|
|[Using function tools with an agent](./Agent_Anthropic_Step03_UsingFunctionTools/)|This sample demonstrates how to use function tools with an Anthropic Claude agent|
## Running the samples from the console
To run the samples, navigate to the desired sample directory, e.g.
```powershell
cd Agent_Anthropic_Step01_Running
```
Set the following environment variables:
```powershell
$env:ANTHROPIC_API_KEY="your-anthropic-api-key" # Replace with your Anthropic API key
```
If the variables are not set, you will be prompted for the values when running the samples.
Execute the following command to build the sample:
```powershell
dotnet build
```
Execute the following command to run the sample:
```powershell
dotnet run --no-build
```
Or just build and run in one step:
```powershell
dotnet run
```
## Running the samples from Visual Studio
Open the solution in Visual Studio and set the desired sample project as the startup project. Then, run the project using the built-in debugger or by pressing `F5`.
You will be prompted for any required environment variables if they are not already set.
@@ -32,7 +32,7 @@ AIAgent agent = new AzureOpenAIClient(
.GetChatClient(deploymentName)
.CreateAIAgent(new ChatClientAgentOptions
{
Instructions = "You are good at telling jokes.",
ChatOptions = new() { Instructions = "You are good at telling jokes." },
Name = "Joker",
AIContextProviderFactory = (ctx) => new ChatHistoryMemoryProvider(
vectorStore,
@@ -30,7 +30,7 @@ AIAgent agent = new AzureOpenAIClient(
.GetChatClient(deploymentName)
.CreateAIAgent(new ChatClientAgentOptions()
{
Instructions = "You are a friendly travel assistant. Use known memories about the user when responding, and do not invent details.",
ChatOptions = new() { Instructions = "You are a friendly travel assistant. Use known memories about the user when responding, and do not invent details." },
AIContextProviderFactory = ctx => ctx.SerializedState.ValueKind is not JsonValueKind.Null and not JsonValueKind.Undefined
// If each thread should have its own Mem0 scope, you can create a new id per thread here:
// ? new Mem0Provider(mem0HttpClient, new Mem0ProviderScope() { ThreadId = Guid.NewGuid().ToString() })
@@ -33,7 +33,7 @@ ChatClient chatClient = new AzureOpenAIClient(
// and its storage to that user id.
AIAgent agent = chatClient.CreateAIAgent(new ChatClientAgentOptions()
{
Instructions = "You are a friendly assistant. Always address the user by their name.",
ChatOptions = new() { Instructions = "You are a friendly assistant. Always address the user by their name." },
AIContextProviderFactory = ctx => new UserInfoMemory(chatClient.AsIChatClient(), ctx.SerializedState, ctx.JsonSerializerOptions)
});
@@ -62,7 +62,7 @@ AIAgent agent = azureOpenAIClient
.GetChatClient(deploymentName)
.CreateAIAgent(new ChatClientAgentOptions
{
Instructions = "You are a helpful support specialist for Contoso Outdoors. Answer questions using the provided context and cite the source document when available.",
ChatOptions = new() { Instructions = "You are a helpful support specialist for Contoso Outdoors. Answer questions using the provided context and cite the source document when available." },
AIContextProviderFactory = ctx => new TextSearchProvider(SearchAdapter, ctx.SerializedState, ctx.JsonSerializerOptions, textSearchOptions)
});
@@ -71,7 +71,7 @@ AIAgent agent = azureOpenAIClient
.GetChatClient(deploymentName)
.CreateAIAgent(new ChatClientAgentOptions
{
Instructions = "You are a helpful support specialist for the Microsoft Agent Framework. Answer questions using the provided context and cite the source document when available. Keep responses brief.",
ChatOptions = new() { Instructions = "You are a helpful support specialist for the Microsoft Agent Framework. Answer questions using the provided context and cite the source document when available. Keep responses brief." },
AIContextProviderFactory = ctx => new TextSearchProvider(SearchAdapter, ctx.SerializedState, ctx.JsonSerializerOptions, textSearchOptions)
});
@@ -29,7 +29,7 @@ AIAgent agent = new AzureOpenAIClient(
.GetChatClient(deploymentName)
.CreateAIAgent(new ChatClientAgentOptions
{
Instructions = "You are a helpful support specialist for Contoso Outdoors. Answer questions using the provided context and cite the source document when available.",
ChatOptions = new() { Instructions = "You are a helpful support specialist for Contoso Outdoors. Answer questions using the provided context and cite the source document when available." },
AIContextProviderFactory = ctx => new TextSearchProvider(MockSearchAsync, ctx.SerializedState, ctx.JsonSerializerOptions, textSearchOptions)
});
@@ -22,7 +22,7 @@ ChatClient chatClient = new AzureOpenAIClient(
.GetChatClient(deploymentName);
// Create the ChatClientAgent with the specified name and instructions.
ChatClientAgent agent = chatClient.CreateAIAgent(new ChatClientAgentOptions(name: "HelpfulAssistant", instructions: "You are a helpful assistant."));
ChatClientAgent agent = chatClient.CreateAIAgent(name: "HelpfulAssistant", instructions: "You are a helpful assistant.");
// Set PersonInfo as the type parameter of RunAsync method to specify the expected structured output from the agent and invoke the agent with some unstructured input.
AgentRunResponse<PersonInfo> response = await agent.RunAsync<PersonInfo>("Please provide information about John Smith, who is a 35-year-old software engineer.");
@@ -34,12 +34,10 @@ Console.WriteLine($"Age: {response.Result.Age}");
Console.WriteLine($"Occupation: {response.Result.Occupation}");
// Create the ChatClientAgent with the specified name, instructions, and expected structured output the agent should produce.
ChatClientAgent agentWithPersonInfo = chatClient.CreateAIAgent(new ChatClientAgentOptions(name: "HelpfulAssistant", instructions: "You are a helpful assistant.")
ChatClientAgent agentWithPersonInfo = chatClient.CreateAIAgent(new ChatClientAgentOptions()
{
ChatOptions = new()
{
ResponseFormat = Microsoft.Extensions.AI.ChatResponseFormat.ForJsonSchema<PersonInfo>()
}
Name = "HelpfulAssistant",
ChatOptions = new() { Instructions = "You are a helpful assistant.", ResponseFormat = Microsoft.Extensions.AI.ChatResponseFormat.ForJsonSchema<PersonInfo>() }
});
// Invoke the agent with some unstructured input while streaming, to extract the structured information from.
@@ -28,7 +28,7 @@ AIAgent agent = new AzureOpenAIClient(
.GetChatClient(deploymentName)
.CreateAIAgent(new ChatClientAgentOptions
{
Instructions = "You are good at telling jokes.",
ChatOptions = new() { Instructions = "You are good at telling jokes." },
Name = "Joker",
ChatMessageStoreFactory = ctx =>
{
@@ -18,8 +18,7 @@ var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT
HostApplicationBuilder builder = Host.CreateApplicationBuilder(args);
// Add agent options to the service collection.
builder.Services.AddSingleton(
new ChatClientAgentOptions(instructions: "You are good at telling jokes.", name: "Joker"));
builder.Services.AddSingleton(new ChatClientAgentOptions() { Name = "Joker", ChatOptions = new() { Instructions = "You are good at telling jokes." } });
// Add a chat client to the service collection.
builder.Services.AddKeyedChatClient("AzureOpenAI", (sp) => new AzureOpenAIClient(
@@ -16,10 +16,6 @@
<PackageReference Include="ModelContextProtocol" />
</ItemGroup>
<ItemGroup Condition="!$([MSBuild]::IsTargetFrameworkCompatible($(TargetFramework), 'net10.0'))">
<PackageReference Include="System.Net.ServerSentEvents" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.AzureAI.Persistent\Microsoft.Agents.AI.AzureAI.Persistent.csproj" />
</ItemGroup>
@@ -44,7 +44,7 @@ while (response.ContinuationToken is not null)
await Task.Delay(TimeSpan.FromSeconds(10));
RestoreAgentState(agent, out thread, out object? continuationToken);
RestoreAgentState(agent, out thread, out ResponseContinuationToken? continuationToken);
options.ContinuationToken = continuationToken;
response = await agent.RunAsync(thread, options);
@@ -52,19 +52,19 @@ while (response.ContinuationToken is not null)
Console.WriteLine(response.Text);
void PersistAgentState(AgentThread thread, object? continuationToken)
void PersistAgentState(AgentThread thread, ResponseContinuationToken? continuationToken)
{
stateStore["thread"] = thread.Serialize();
stateStore["continuationToken"] = JsonSerializer.SerializeToElement(continuationToken, AgentAbstractionsJsonUtilities.DefaultOptions.GetTypeInfo(typeof(ResponseContinuationToken)));
}
void RestoreAgentState(AIAgent agent, out AgentThread thread, out object? continuationToken)
void RestoreAgentState(AIAgent agent, out AgentThread thread, out ResponseContinuationToken? continuationToken)
{
JsonElement serializedThread = stateStore["thread"] ?? throw new InvalidOperationException("No serialized thread found in state store.");
JsonElement? serializedToken = stateStore["continuationToken"];
thread = agent.DeserializeThread(serializedThread);
continuationToken = serializedToken?.Deserialize(AgentAbstractionsJsonUtilities.DefaultOptions.GetTypeInfo(typeof(ResponseContinuationToken)));
continuationToken = (ResponseContinuationToken?)serializedToken?.Deserialize(AgentAbstractionsJsonUtilities.DefaultOptions.GetTypeInfo(typeof(ResponseContinuationToken)));
}
[Description("Researches relevant space facts and scientific information for writing a science fiction novel")]
@@ -21,7 +21,7 @@ AIAgent agent = new AzureOpenAIClient(
.GetChatClient(deploymentName)
.CreateAIAgent(new ChatClientAgentOptions
{
Instructions = "You are good at telling jokes.",
ChatOptions = new() { Instructions = "You are good at telling jokes." },
Name = "Joker",
ChatMessageStoreFactory = ctx => new InMemoryChatMessageStore(new MessageCountingChatReducer(2), ctx.SerializedState, ctx.JsonSerializerOptions)
});
@@ -0,0 +1,25 @@
<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" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
<PackageReference Include="Microsoft.Bot.ObjectModel" />
<PackageReference Include="Microsoft.Bot.ObjectModel.Json" />
<PackageReference Include="Microsoft.Bot.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>
</Project>
@@ -0,0 +1,54 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample shows how to create an agent from a YAML based declarative representation.
using Azure.AI.OpenAI;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
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";
// Create the chat client
IChatClient chatClient = new AzureOpenAIClient(
new Uri(endpoint),
new AzureCliCredential())
.GetChatClient(deploymentName)
.AsIChatClient();
// Define the agent using a YAML definition.
var text =
"""
kind: Prompt
name: Assistant
description: Helpful assistant
instructions: You are a helpful assistant. You answer questions in the language specified by the user. You return your answers in a JSON format.
model:
options:
temperature: 0.9
topP: 0.95
outputSchema:
properties:
language:
type: string
required: true
description: The language of the answer.
answer:
type: string
required: true
description: The answer text.
""";
// Create the agent from the YAML definition.
var agentFactory = new ChatClientPromptAgentFactory(chatClient);
var agent = await agentFactory.CreateFromYamlAsync(text);
// Invoke the agent and output the text result.
Console.WriteLine(await agent!.RunAsync("Tell me a joke about a pirate in English."));
// Invoke the agent with streaming support.
await foreach (var update in agent!.RunStreamingAsync("Tell me a joke about a pirate in French."))
{
Console.WriteLine(update);
}
@@ -45,6 +45,7 @@ Before you begin, ensure you have the following prerequisites:
|[Reducing chat history size](./Agent_Step16_ChatReduction/)|This sample demonstrates how to reduce the chat history to constrain its size, where chat history is maintained locally|
|[Background responses](./Agent_Step17_BackgroundResponses/)|This sample demonstrates how to use background responses for long-running operations with polling and resumption support|
|[Deep research with an agent](./Agent_Step18_DeepResearch/)|This sample demonstrates how to use the Deep Research Tool to perform comprehensive research on complex topics|
|[Declarative agent](./Agent_Step19_Declarative/)|This sample demonstrates how to declaratively define an agent.|
## Running the samples from the console
@@ -0,0 +1,25 @@
<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" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
<PackageReference Include="Microsoft.Bot.ObjectModel" />
<PackageReference Include="Microsoft.Bot.ObjectModel.Json" />
<PackageReference Include="Microsoft.Bot.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>
</Project>
@@ -0,0 +1,55 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample shows how to load an AI agent from a YAML file and process a prompt using Azure OpenAI as the backend.
using System.ComponentModel;
using Azure.AI.OpenAI;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
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";
// Create the chat client
IChatClient chatClient = new AzureOpenAIClient(
new Uri(endpoint),
new AzureCliCredential())
.GetChatClient(deploymentName)
.AsIChatClient();
// Read command-line arguments
if (args.Length < 2)
{
Console.WriteLine("Usage: DeclarativeAgents <yaml-file-path> <prompt>");
Console.WriteLine(" <yaml-file-path>: The path to the YAML file containing the agent definition");
Console.WriteLine(" <prompt>: The prompt to send to the agent");
return;
}
var yamlFilePath = args[0];
var prompt = args[1];
// Verify the YAML file exists
if (!File.Exists(yamlFilePath))
{
Console.WriteLine($"Error: File not found: {yamlFilePath}");
return;
}
// Read the YAML content from the file
var text = await File.ReadAllTextAsync(yamlFilePath);
// Example function tool that can be used by the agent.
[Description("Get the weather for a given location.")]
static string GetWeather(
[Description("The city and state, e.g. San Francisco, CA")] string location,
[Description("The unit of temperature. Possible values are 'celsius' and 'fahrenheit'.")] string unit)
=> $"The weather in {location} is cloudy with a high of {(unit.Equals("celsius", StringComparison.Ordinal) ? "15°C" : "59°F")}.";
// Create the agent from the YAML definition.
var agentFactory = new ChatClientPromptAgentFactory(chatClient, [AIFunctionFactory.Create(GetWeather, "GetWeather")]);
var agent = await agentFactory.CreateFromYamlAsync(text);
// Invoke the agent and output the text result.
Console.WriteLine(await agent!.RunAsync(prompt));
@@ -0,0 +1,12 @@
{
"profiles": {
"GetWeather": {
"commandName": "Project",
"commandLineArgs": "..\\..\\..\\..\\..\\..\\..\\..\\agent-samples\\chatclient\\GetWeather.yaml \"What is the weather in Cambridge, MA in °C?\""
},
"Assistant": {
"commandName": "Project",
"commandLineArgs": "..\\..\\..\\..\\..\\..\\..\\..\\agent-samples\\chatclient\\Assistant.yaml \"Tell me a joke about a pirate in Italian.\""
}
}
}
@@ -11,19 +11,17 @@ using Microsoft.Extensions.AI;
string endpoint = Environment.GetEnvironmentVariable("AZURE_FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("AZURE_FOUNDRY_PROJECT_ENDPOINT is not set.");
string deploymentName = Environment.GetEnvironmentVariable("AZURE_FOUNDRY_PROJECT_DEPLOYMENT_NAME") ?? "gpt-4o-mini";
const string JokerInstructionsV1 = "You are good at telling jokes.";
const string JokerInstructionsV2 = "You are extremely hilarious at telling jokes.";
const string JokerName = "JokerAgent";
// Get a client to create/retrieve/delete server side agents with Azure Foundry Agents.
AIProjectClient aiProjectClient = new(new Uri(endpoint), new AzureCliCredential());
// Define the agent you want to create. (Prompt Agent in this case)
AgentVersionCreationOptions options = new(new PromptAgentDefinition(model: deploymentName) { Instructions = JokerInstructionsV1 });
AgentVersionCreationOptions options = new(new PromptAgentDefinition(model: deploymentName) { Instructions = "You are good at telling jokes." });
// Azure.AI.Agents SDK creates and manages agent by name and versions.
// You can create a server side agent version with the Azure.AI.Agents SDK client below.
AgentVersion agentVersion = aiProjectClient.Agents.CreateAgentVersion(agentName: JokerName, options);
AgentVersion createdAgentVersion = aiProjectClient.Agents.CreateAgentVersion(agentName: JokerName, options);
// Note:
// agentVersion.Id = "<agentName>:<versionNumber>",
@@ -31,20 +29,20 @@ AgentVersion agentVersion = aiProjectClient.Agents.CreateAgentVersion(agentName:
// agentVersion.Name = <agentName>
// You can retrieve an AIAgent for an already created server side agent version.
AIAgent jokerAgentV1 = aiProjectClient.GetAIAgent(agentVersion);
AIAgent existingJokerAgent = aiProjectClient.GetAIAgent(createdAgentVersion);
// You can also create another AIAgent version (V2) by providing the same name with a different definition/instruction.
AIAgent jokerAgentV2 = aiProjectClient.CreateAIAgent(name: JokerName, model: deploymentName, instructions: JokerInstructionsV2);
// You can also create another AIAgent version by providing the same name with a different definition/instruction.
AIAgent newJokerAgent = aiProjectClient.CreateAIAgent(name: JokerName, model: deploymentName, instructions: "You are extremely hilarious at telling jokes.");
// You can also get the AIAgent latest version by just providing its name.
AIAgent jokerAgentLatest = aiProjectClient.GetAIAgent(name: JokerName);
AgentVersion latestVersion = jokerAgentLatest.GetService<AgentVersion>()!;
AgentVersion latestAgentVersion = jokerAgentLatest.GetService<AgentVersion>()!;
// The AIAgent version can be accessed via the GetService method.
Console.WriteLine($"Latest agent version id: {latestVersion.Id}");
Console.WriteLine($"Latest agent version id: {latestAgentVersion.Id}");
// Once you have the AIAgent, you can invoke it like any other AIAgent.
Console.WriteLine(await jokerAgentLatest.RunAsync("Tell me a joke about a pirate."));
// Cleanup by agent name removes both agent versions created (jokerAgentV1 + jokerAgentV2).
await aiProjectClient.Agents.DeleteAgentAsync(jokerAgentV1.Name);
// Cleanup by agent name removes both agent versions created.
await aiProjectClient.Agents.DeleteAgentAsync(existingJokerAgent.Name);
@@ -24,10 +24,12 @@ AIProjectClient aiProjectClient = new(new Uri(endpoint), new AzureCliCredential(
// Create ChatClientAgent directly
ChatClientAgent agent = await aiProjectClient.CreateAIAgentAsync(
model: deploymentName,
new ChatClientAgentOptions(name: AssistantName, instructions: AssistantInstructions)
new ChatClientAgentOptions()
{
Name = AssistantName,
ChatOptions = new()
{
Instructions = AssistantInstructions,
ResponseFormat = Microsoft.Extensions.AI.ChatResponseFormat.ForJsonSchema<PersonInfo>()
}
});
@@ -44,10 +46,12 @@ Console.WriteLine($"Occupation: {response.Result.Occupation}");
// Create the ChatClientAgent with the specified name, instructions, and expected structured output the agent should produce.
ChatClientAgent agentWithPersonInfo = aiProjectClient.CreateAIAgent(
model: deploymentName,
new ChatClientAgentOptions(name: AssistantName, instructions: AssistantInstructions)
new ChatClientAgentOptions()
{
Name = AssistantName,
ChatOptions = new()
{
Instructions = AssistantInstructions,
ResponseFormat = Microsoft.Extensions.AI.ChatResponseFormat.ForJsonSchema<PersonInfo>()
}
});
@@ -6,6 +6,15 @@ of Azure Foundry Agents and can be used with Azure Foundry as the AI provider.
These samples showcase how to work with agents managed through Azure Foundry, including agent creation,
versioning, multi-turn conversations, and advanced features like code interpretation and computer use.
## Classic vs New Foundry Agents
> [!NOTE]
> Recently, Azure Foundry introduced a new and improved experience for creating and managing AI agents, which is the target of these samples.
For more information about the previous classic agents and for what's new in Foundry Agents, see the [Foundry Agents migration documentation](https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/migrate?view=foundry).
For a sample demonstrating how to use classic Foundry Agents, see the following: [Agent with Azure AI Persistent](../AgentProviders/Agent_With_AzureAIAgentsPersistent/README.md).
## Getting started with Foundry Agents prerequisites
Before you begin, ensure you have the following prerequisites:
@@ -17,10 +17,6 @@
<PackageReference Include="ModelContextProtocol" />
</ItemGroup>
<ItemGroup Condition="!$([MSBuild]::IsTargetFrameworkCompatible($(TargetFramework), 'net10.0'))">
<PackageReference Include="System.Net.ServerSentEvents" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
</ItemGroup>
@@ -34,9 +34,9 @@ AIAgent agent = await persistentAgentsClient.CreateAIAgentAsync(
options: new()
{
Name = "MicrosoftLearnAgent",
Instructions = "You answer questions by searching the Microsoft Learn content only.",
ChatOptions = new()
{
Instructions = "You answer questions by searching the Microsoft Learn content only.",
Tools = [mcpTool]
},
});
@@ -67,9 +67,9 @@ AIAgent agentWithRequiredApproval = await persistentAgentsClient.CreateAIAgentAs
options: new()
{
Name = "MicrosoftLearnAgentWithApproval",
Instructions = "You answer questions by searching the Microsoft Learn content only.",
ChatOptions = new()
{
Instructions = "You answer questions by searching the Microsoft Learn content only.",
Tools = [mcpToolWithApproval]
},
});
+1
View File
@@ -15,5 +15,6 @@ of the agent framework.
|[A2A](./A2A/README.md)|Getting started with A2A (Agent-to-Agent) specific features|
|[Agent Open Telemetry](./AgentOpenTelemetry/README.md)|Getting started with OpenTelemetry for agents|
|[Agent With OpenAI exchange types](./AgentWithOpenAI/README.md)|Using OpenAI exchange types with agents|
|[Agent With Anthropic](./AgentWithAnthropic/README.md)|Getting started with agents using Anthropic Claude|
|[Workflow](./Workflows/README.md)|Getting started with Workflow|
|[Model Context Protocol](./ModelContextProtocol/README.md)|Getting started with Model Context Protocol|
@@ -118,10 +118,11 @@ internal sealed class SloganWriterExecutor : Executor
/// <param name="chatClient">The chat client to use for the AI agent.</param>
public SloganWriterExecutor(string id, IChatClient chatClient) : base(id)
{
ChatClientAgentOptions agentOptions = new(instructions: "You are a professional slogan writer. You will be given a task to create a slogan.")
ChatClientAgentOptions agentOptions = new()
{
ChatOptions = new()
{
Instructions = "You are a professional slogan writer. You will be given a task to create a slogan.",
ResponseFormat = ChatResponseFormat.ForJsonSchema<SloganResult>()
}
};
@@ -193,10 +194,11 @@ internal sealed class FeedbackExecutor : Executor<SloganResult>
/// <param name="chatClient">The chat client to use for the AI agent.</param>
public FeedbackExecutor(string id, IChatClient chatClient) : base(id)
{
ChatClientAgentOptions agentOptions = new(instructions: "You are a professional editor. You will be given a slogan and the task it is meant to accomplish.")
ChatClientAgentOptions agentOptions = new()
{
ChatOptions = new()
{
Instructions = "You are a professional editor. You will be given a slogan and the task it is meant to accomplish.",
ResponseFormat = ChatResponseFormat.ForJsonSchema<FeedbackResult>()
}
};
@@ -85,10 +85,11 @@ public static class Program
/// </summary>
/// <returns>A ChatClientAgent configured for spam detection</returns>
private static ChatClientAgent GetSpamDetectionAgent(IChatClient chatClient) =>
new(chatClient, new ChatClientAgentOptions(instructions: "You are a spam detection assistant that identifies spam emails.")
new(chatClient, new ChatClientAgentOptions()
{
ChatOptions = new()
{
Instructions = "You are a spam detection assistant that identifies spam emails.",
ResponseFormat = ChatResponseFormat.ForJsonSchema<DetectionResult>()
}
});
@@ -98,10 +99,11 @@ public static class Program
/// </summary>
/// <returns>A ChatClientAgent configured for email assistance</returns>
private static ChatClientAgent GetEmailAssistantAgent(IChatClient chatClient) =>
new(chatClient, new ChatClientAgentOptions(instructions: "You are an email assistant that helps users draft responses to emails with professionalism.")
new(chatClient, new ChatClientAgentOptions()
{
ChatOptions = new()
{
Instructions = "You are an email assistant that helps users draft responses to emails with professionalism.",
ResponseFormat = ChatResponseFormat.ForJsonSchema<EmailResponse>()
}
});
@@ -100,10 +100,11 @@ public static class Program
/// </summary>
/// <returns>A ChatClientAgent configured for spam detection</returns>
private static ChatClientAgent GetSpamDetectionAgent(IChatClient chatClient) =>
new(chatClient, new ChatClientAgentOptions(instructions: "You are a spam detection assistant that identifies spam emails. Be less confident in your assessments.")
new(chatClient, new ChatClientAgentOptions()
{
ChatOptions = new()
{
Instructions = "You are a spam detection assistant that identifies spam emails. Be less confident in your assessments.",
ResponseFormat = ChatResponseFormat.ForJsonSchema<DetectionResult>()
}
});
@@ -113,10 +114,11 @@ public static class Program
/// </summary>
/// <returns>A ChatClientAgent configured for email assistance</returns>
private static ChatClientAgent GetEmailAssistantAgent(IChatClient chatClient) =>
new(chatClient, new ChatClientAgentOptions(instructions: "You are an email assistant that helps users draft responses to emails with professionalism.")
new(chatClient, new ChatClientAgentOptions()
{
ChatOptions = new()
{
Instructions = "You are an email assistant that helps users draft responses to emails with professionalism.",
ResponseFormat = ChatResponseFormat.ForJsonSchema<EmailResponse>()
}
});
@@ -140,10 +140,11 @@ public static class Program
/// </summary>
/// <returns>A ChatClientAgent configured for email analysis</returns>
private static ChatClientAgent GetEmailAnalysisAgent(IChatClient chatClient) =>
new(chatClient, new ChatClientAgentOptions(instructions: "You are a spam detection assistant that identifies spam emails.")
new(chatClient, new ChatClientAgentOptions()
{
ChatOptions = new()
{
Instructions = "You are a spam detection assistant that identifies spam emails.",
ResponseFormat = ChatResponseFormat.ForJsonSchema<AnalysisResult>()
}
});
@@ -153,10 +154,11 @@ public static class Program
/// </summary>
/// <returns>A ChatClientAgent configured for email assistance</returns>
private static ChatClientAgent GetEmailAssistantAgent(IChatClient chatClient) =>
new(chatClient, new ChatClientAgentOptions(instructions: "You are an email assistant that helps users draft responses to emails with professionalism.")
new(chatClient, new ChatClientAgentOptions()
{
ChatOptions = new()
{
Instructions = "You are an email assistant that helps users draft responses to emails with professionalism.",
ResponseFormat = ChatResponseFormat.ForJsonSchema<EmailResponse>()
}
});
@@ -166,10 +168,11 @@ public static class Program
/// </summary>
/// <returns>A ChatClientAgent configured for email summarization</returns>
private static ChatClientAgent GetEmailSummaryAgent(IChatClient chatClient) =>
new(chatClient, new ChatClientAgentOptions(instructions: "You are an assistant that helps users summarize emails.")
new(chatClient, new ChatClientAgentOptions()
{
ChatOptions = new()
{
Instructions = "You are an assistant that helps users summarize emails.",
ResponseFormat = ChatResponseFormat.ForJsonSchema<EmailSummary>()
}
});
@@ -9,7 +9,7 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Anthropic.SDK" />
<PackageReference Include="Anthropic" />
<PackageReference Include="AWSSDK.Extensions.Bedrock.MEAI" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
</ItemGroup>
@@ -12,19 +12,16 @@ const string Topic = "Goldendoodles make the best pets.";
IChatClient aws = new AmazonBedrockRuntimeClient(
Environment.GetEnvironmentVariable("BEDROCK_ACCESSKEY"!),
Environment.GetEnvironmentVariable("BEDROCK_SECRETACCESSKEY")!,
Amazon.RegionEndpoint.USEast1).AsIChatClient("amazon.nova-pro-v1:0");
Amazon.RegionEndpoint.USEast1)
.AsIChatClient("amazon.nova-pro-v1:0");
IChatClient anthropic = new Anthropic.SDK.AnthropicClient(
Environment.GetEnvironmentVariable("ANTHROPIC_APIKEY")!).Messages.AsBuilder()
.ConfigureOptions(o =>
{
o.ModelId ??= "claude-sonnet-4-20250514";
o.MaxOutputTokens ??= 10 * 1024;
})
.Build();
IChatClient anthropic = new Anthropic.AnthropicClient(
new() { APIKey = Environment.GetEnvironmentVariable("ANTHROPIC_APIKEY") })
.AsIChatClient("claude-sonnet-4-20250514");
IChatClient openai = new OpenAI.OpenAIClient(
Environment.GetEnvironmentVariable("OPENAI_APIKEY")!).GetChatClient("gpt-4o-mini").AsIChatClient();
Environment.GetEnvironmentVariable("OPENAI_APIKEY")!).GetChatClient("gpt-4o-mini")
.AsIChatClient();
// Define our agents.
AIAgent researcher = new ChatClientAgent(aws,
@@ -285,19 +285,19 @@ internal sealed class CriticExecutor : Executor<ChatMessage, CriticDecision>
this._agent = new ChatClientAgent(chatClient, new ChatClientAgentOptions
{
Name = "Critic",
Instructions = """
You are a constructive critic. Review the content and provide specific feedback.
Always try to provide actionable suggestions for improvement and strive to identify improvement points.
Only approve if the content is high quality, clear, and meets the original requirements and you see no improvement points.
Provide your decision as structured output with:
- approved: true if content is good, false if revisions needed
- feedback: specific improvements needed (empty if approved)
Be concise but specific in your feedback.
""",
ChatOptions = new()
{
Instructions = """
You are a constructive critic. Review the content and provide specific feedback.
Always try to provide actionable suggestions for improvement and strive to identify improvement points.
Only approve if the content is high quality, clear, and meets the original requirements and you see no improvement points.
Provide your decision as structured output with:
- approved: true if content is good, false if revisions needed
- feedback: specific improvements needed (empty if approved)
Be concise but specific in your feedback.
""",
ResponseFormat = ChatResponseFormat.ForJsonSchema<CriticDecision>()
}
});
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -37,15 +37,15 @@
<ItemGroup>
<PackageReference Include="Azure.AI.AgentServer.AgentFramework" Version="1.0.0-beta.4" />
<PackageReference Include="Azure.AI.OpenAI" Version="2.5.0-beta.1" />
<PackageReference Include="Azure.AI.OpenAI" Version="2.7.0-beta.1" />
<PackageReference Include="Azure.Identity" Version="1.17.0" />
<PackageReference Include="Microsoft.Agents.AI.OpenAI" Version="1.0.0-preview.251110.2" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" Version="9.10.2-preview.1.25552.1" />
<PackageReference Include="Microsoft.Agents.AI.OpenAI" Version="1.0.0-preview.251125.1" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" Version="10.0.1-preview.1.25571.5" />
</ItemGroup>
<!-- Add analyzers with compatible versions -->
<ItemGroup>
<PackageReference Include="Microsoft.CodeAnalysis.NetAnalyzers" Version="9.0.0">
<PackageReference Include="Microsoft.CodeAnalysis.NetAnalyzers" Version="10.0.100">
<PrivateAssets>all</PrivateAssets>
<IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
</PackageReference>
@@ -53,15 +53,15 @@
<PrivateAssets>all</PrivateAssets>
<IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
</PackageReference>
<PackageReference Include="Roslynator.Analyzers" Version="4.12.9">
<PackageReference Include="Roslynator.Analyzers" Version="4.14.1">
<PrivateAssets>all</PrivateAssets>
<IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
</PackageReference>
<PackageReference Include="Roslynator.CodeAnalysis.Analyzers" Version="4.12.9">
<PackageReference Include="Roslynator.CodeAnalysis.Analyzers" Version="4.14.1">
<PrivateAssets>all</PrivateAssets>
<IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
</PackageReference>
<PackageReference Include="Roslynator.Formatting.Analyzers" Version="4.12.9">
<PackageReference Include="Roslynator.Formatting.Analyzers" Version="4.14.1">
<PrivateAssets>all</PrivateAssets>
<IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
</PackageReference>
@@ -1,5 +1,5 @@
# Build the application
FROM mcr.microsoft.com/dotnet/sdk:9.0-alpine AS build
FROM mcr.microsoft.com/dotnet/sdk:10.0-alpine AS build
WORKDIR /src
# Copy files from the current directory on the host to the working directory in the container
@@ -7,10 +7,10 @@ COPY . .
RUN dotnet restore
RUN dotnet build -c Release --no-restore
RUN dotnet publish -c Release --no-build -o /app
RUN dotnet publish -c Release --no-build -o /app -f net10.0
# Run the application
FROM mcr.microsoft.com/dotnet/aspnet:9.0-alpine AS final
FROM mcr.microsoft.com/dotnet/aspnet:10.0-alpine AS final
WORKDIR /app
# Copy everything needed to run the app from the "build" stage.
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -36,15 +36,15 @@
<ItemGroup>
<PackageReference Include="Azure.AI.AgentServer.AgentFramework" Version="1.0.0-beta.4" />
<PackageReference Include="Azure.AI.OpenAI" Version="2.5.0-beta.1" />
<PackageReference Include="Azure.AI.OpenAI" Version="2.7.0-beta.1" />
<PackageReference Include="Azure.Identity" Version="1.17.0" />
<PackageReference Include="Microsoft.Agents.AI.OpenAI" Version="1.0.0-preview.251110.2" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" Version="9.10.2-preview.1.25552.1" />
<PackageReference Include="Microsoft.Agents.AI.OpenAI" Version="1.0.0-preview.251125.1" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" Version="10.0.1-preview.1.25571.5" />
</ItemGroup>
<!-- Add analyzers with compatible versions -->
<ItemGroup>
<PackageReference Include="Microsoft.CodeAnalysis.NetAnalyzers" Version="9.0.0">
<PackageReference Include="Microsoft.CodeAnalysis.NetAnalyzers" Version="10.0.100">
<PrivateAssets>all</PrivateAssets>
<IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
</PackageReference>
@@ -52,15 +52,15 @@
<PrivateAssets>all</PrivateAssets>
<IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
</PackageReference>
<PackageReference Include="Roslynator.Analyzers" Version="4.12.9">
<PackageReference Include="Roslynator.Analyzers" Version="4.14.1">
<PrivateAssets>all</PrivateAssets>
<IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
</PackageReference>
<PackageReference Include="Roslynator.CodeAnalysis.Analyzers" Version="4.12.9">
<PackageReference Include="Roslynator.CodeAnalysis.Analyzers" Version="4.14.1">
<PrivateAssets>all</PrivateAssets>
<IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
</PackageReference>
<PackageReference Include="Roslynator.Formatting.Analyzers" Version="4.12.9">
<PackageReference Include="Roslynator.Formatting.Analyzers" Version="4.14.1">
<PrivateAssets>all</PrivateAssets>
<IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
</PackageReference>
@@ -1,5 +1,5 @@
# Build the application
FROM mcr.microsoft.com/dotnet/sdk:9.0-alpine AS build
FROM mcr.microsoft.com/dotnet/sdk:10.0-alpine AS build
WORKDIR /src
# Copy files from the current directory on the host to the working directory in the container
@@ -7,10 +7,10 @@ COPY . .
RUN dotnet restore
RUN dotnet build -c Release --no-restore
RUN dotnet publish -c Release --no-build -o /app
RUN dotnet publish -c Release --no-build -o /app -f net10.0
# Run the application
FROM mcr.microsoft.com/dotnet/aspnet:9.0-alpine AS final
FROM mcr.microsoft.com/dotnet/aspnet:10.0-alpine AS final
WORKDIR /app
# Copy everything needed to run the app from the "build" stage.
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -36,15 +36,15 @@
<ItemGroup>
<PackageReference Include="Azure.AI.AgentServer.AgentFramework" Version="1.0.0-beta.4" />
<PackageReference Include="Azure.AI.OpenAI" Version="2.5.0-beta.1" />
<PackageReference Include="Azure.AI.OpenAI" Version="2.7.0-beta.1" />
<PackageReference Include="Azure.Identity" Version="1.17.0" />
<PackageReference Include="Microsoft.Agents.AI.Workflows" Version="1.0.0-preview.251110.2" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" Version="9.10.2-preview.1.25552.1" />
<PackageReference Include="Microsoft.Agents.AI.Workflows" Version="1.0.0-preview.251125.1" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" Version="10.0.1-preview.1.25571.5" />
</ItemGroup>
<!-- Add analyzers with compatible versions -->
<ItemGroup>
<PackageReference Include="Microsoft.CodeAnalysis.NetAnalyzers" Version="9.0.0">
<PackageReference Include="Microsoft.CodeAnalysis.NetAnalyzers" Version="10.0.100">
<PrivateAssets>all</PrivateAssets>
<IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
</PackageReference>
@@ -52,15 +52,15 @@
<PrivateAssets>all</PrivateAssets>
<IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
</PackageReference>
<PackageReference Include="Roslynator.Analyzers" Version="4.12.9">
<PackageReference Include="Roslynator.Analyzers" Version="4.14.1">
<PrivateAssets>all</PrivateAssets>
<IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
</PackageReference>
<PackageReference Include="Roslynator.CodeAnalysis.Analyzers" Version="4.12.9">
<PackageReference Include="Roslynator.CodeAnalysis.Analyzers" Version="4.14.1">
<PrivateAssets>all</PrivateAssets>
<IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
</PackageReference>
<PackageReference Include="Roslynator.Formatting.Analyzers" Version="4.12.9">
<PackageReference Include="Roslynator.Formatting.Analyzers" Version="4.14.1">
<PrivateAssets>all</PrivateAssets>
<IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
</PackageReference>
@@ -1,5 +1,5 @@
# Build the application
FROM mcr.microsoft.com/dotnet/sdk:9.0-alpine AS build
FROM mcr.microsoft.com/dotnet/sdk:10.0-alpine AS build
WORKDIR /src
# Copy files from the current directory on the host to the working directory in the container
@@ -7,10 +7,10 @@ COPY . .
RUN dotnet restore
RUN dotnet build -c Release --no-restore
RUN dotnet publish -c Release --no-build -o /app
RUN dotnet publish -c Release --no-build -o /app -f net10.0
# Run the application
FROM mcr.microsoft.com/dotnet/aspnet:9.0-alpine AS final
FROM mcr.microsoft.com/dotnet/aspnet:10.0-alpine AS final
WORKDIR /app
# Copy everything needed to run the app from the "build" stage.
@@ -33,9 +33,9 @@ public class WeatherForecastAgent : DelegatingAIAgent
new ChatClientAgentOptions()
{
Name = AgentName,
Instructions = AgentInstructions,
ChatOptions = new ChatOptions()
{
Instructions = AgentInstructions,
Tools = [new ApprovalRequiredAIFunction(AIFunctionFactory.Create(GetWeather))],
// We want the agent to return structured output in a known format
// so that we can easily create adaptive cards from the response.
+183 -43
View File
@@ -3,6 +3,7 @@
using System;
using System.Collections.Generic;
using System.Linq;
using System.Net.ServerSentEvents;
using System.Runtime.CompilerServices;
using System.Text.Json;
using System.Threading;
@@ -74,26 +75,28 @@ internal sealed class A2AAgent : AIAgent
{
_ = Throw.IfNull(messages);
var a2aMessage = messages.ToA2AMessage();
thread ??= this.GetNewThread();
if (thread is not A2AAgentThread typedThread)
{
throw new InvalidOperationException("The provided thread is not compatible with the agent. Only threads created by the agent can be used.");
}
// Linking the message to the existing conversation, if any.
a2aMessage.ContextId = typedThread.ContextId;
A2AAgentThread typedThread = this.GetA2AThread(thread, options);
this._logger.LogA2AAgentInvokingAgent(nameof(RunAsync), this.Id, this.Name);
var a2aResponse = await this._a2aClient.SendMessageAsync(new MessageSendParams { Message = a2aMessage }, cancellationToken).ConfigureAwait(false);
A2AResponse? a2aResponse = null;
if (GetContinuationToken(messages, options) is { } token)
{
a2aResponse = await this._a2aClient.GetTaskAsync(token.TaskId, cancellationToken).ConfigureAwait(false);
}
else
{
var a2aMessage = CreateA2AMessage(typedThread, messages);
a2aResponse = await this._a2aClient.SendMessageAsync(new MessageSendParams { Message = a2aMessage }, cancellationToken).ConfigureAwait(false);
}
this._logger.LogAgentChatClientInvokedAgent(nameof(RunAsync), this.Id, this.Name);
if (a2aResponse is AgentMessage message)
{
UpdateThreadConversationId(typedThread, message.ContextId);
UpdateThread(typedThread, message.ContextId);
return new AgentRunResponse
{
@@ -101,21 +104,30 @@ internal sealed class A2AAgent : AIAgent
ResponseId = message.MessageId,
RawRepresentation = message,
Messages = [message.ToChatMessage()],
AdditionalProperties = message.Metadata.ToAdditionalProperties(),
AdditionalProperties = message.Metadata?.ToAdditionalProperties(),
};
}
if (a2aResponse is AgentTask agentTask)
{
UpdateThreadConversationId(typedThread, agentTask.ContextId);
UpdateThread(typedThread, agentTask.ContextId, agentTask.Id);
return new AgentRunResponse
var response = new AgentRunResponse
{
AgentId = this.Id,
ResponseId = agentTask.Id,
RawRepresentation = agentTask,
Messages = agentTask.ToChatMessages(),
AdditionalProperties = agentTask.Metadata.ToAdditionalProperties(),
Messages = agentTask.ToChatMessages() ?? [],
ContinuationToken = CreateContinuationToken(agentTask.Id, agentTask.Status.State),
AdditionalProperties = agentTask.Metadata?.ToAdditionalProperties(),
};
if (agentTask.ToChatMessages() is { Count: > 0 } taskMessages)
{
response.Messages = taskMessages;
}
return response;
}
throw new NotSupportedException($"Only Message and AgentTask responses are supported from A2A agents. Received: {a2aResponse.GetType().FullName ?? "null"}");
@@ -126,43 +138,63 @@ internal sealed class A2AAgent : AIAgent
{
_ = Throw.IfNull(messages);
var a2aMessage = messages.ToA2AMessage();
thread ??= this.GetNewThread();
if (thread is not A2AAgentThread typedThread)
{
throw new InvalidOperationException("The provided thread is not compatible with the agent. Only threads created by the agent can be used.");
}
// Linking the message to the existing conversation, if any.
a2aMessage.ContextId = typedThread.ContextId;
A2AAgentThread typedThread = this.GetA2AThread(thread, options);
this._logger.LogA2AAgentInvokingAgent(nameof(RunStreamingAsync), this.Id, this.Name);
var a2aSseEvents = this._a2aClient.SendMessageStreamingAsync(new MessageSendParams { Message = a2aMessage }, cancellationToken).ConfigureAwait(false);
ConfiguredCancelableAsyncEnumerable<SseItem<A2AEvent>> a2aSseEvents;
if (options?.ContinuationToken is not null)
{
// Task stream resumption is not well defined in the A2A v2.* specification, leaving it to the agent implementations.
// The v3.0 specification improves this by defining task stream reconnection that allows obtaining the same stream
// from the beginning, but it does not define stream resumption from a specific point in the stream.
// Therefore, the code should be updated once the A2A .NET library supports the A2A v3.0 specification,
// and AF has the necessary model to allow consumers to know whether they need to resume the stream and add new updates to
// the existing ones or reconnect the stream and obtain all updates again.
// For more details, see the following issue: https://github.com/microsoft/agent-framework/issues/1764
throw new InvalidOperationException("Reconnecting to task streams using continuation tokens is not supported yet.");
// a2aSseEvents = this._a2aClient.SubscribeToTaskAsync(token.TaskId, cancellationToken).ConfigureAwait(false);
}
var a2aMessage = CreateA2AMessage(typedThread, messages);
a2aSseEvents = this._a2aClient.SendMessageStreamingAsync(new MessageSendParams { Message = a2aMessage }, cancellationToken).ConfigureAwait(false);
this._logger.LogAgentChatClientInvokedAgent(nameof(RunStreamingAsync), this.Id, this.Name);
string? contextId = null;
string? taskId = null;
await foreach (var sseEvent in a2aSseEvents)
{
if (sseEvent.Data is not AgentMessage message)
if (sseEvent.Data is AgentMessage message)
{
throw new NotSupportedException($"Only message responses are supported from A2A agents. Received: {sseEvent.Data?.GetType().FullName ?? "null"}");
contextId = message.ContextId;
yield return this.ConvertToAgentResponseUpdate(message);
}
UpdateThreadConversationId(typedThread, message.ContextId);
yield return new AgentRunResponseUpdate
else if (sseEvent.Data is AgentTask task)
{
AgentId = this.Id,
ResponseId = message.MessageId,
RawRepresentation = message,
Role = ChatRole.Assistant,
MessageId = message.MessageId,
Contents = [.. message.Parts.Select(part => part.ToAIContent()).OfType<AIContent>()],
AdditionalProperties = message.Metadata.ToAdditionalProperties(),
};
contextId = task.ContextId;
taskId = task.Id;
yield return this.ConvertToAgentResponseUpdate(task);
}
else if (sseEvent.Data is TaskUpdateEvent taskUpdateEvent)
{
contextId = taskUpdateEvent.ContextId;
taskId = taskUpdateEvent.TaskId;
yield return this.ConvertToAgentResponseUpdate(taskUpdateEvent);
}
else
{
throw new NotSupportedException($"Only message, task, task update events are supported from A2A agents. Received: {sseEvent.Data.GetType().FullName ?? "null"}");
}
}
UpdateThread(typedThread, contextId, taskId);
}
/// <inheritdoc/>
@@ -177,7 +209,27 @@ internal sealed class A2AAgent : AIAgent
/// <inheritdoc/>
public override string? Description => this._description ?? base.Description;
private static void UpdateThreadConversationId(A2AAgentThread? thread, string? contextId)
private A2AAgentThread GetA2AThread(AgentThread? thread, AgentRunOptions? options)
{
// Aligning with other agent implementations that support background responses, where
// a thread is required for background responses to prevent inconsistent experience
// for callers if they forget to provide the thread for initial or follow-up runs.
if (options?.AllowBackgroundResponses is true && thread is null)
{
throw new InvalidOperationException("A thread must be provided when AllowBackgroundResponses is enabled.");
}
thread ??= this.GetNewThread();
if (thread is not A2AAgentThread typedThread)
{
throw new InvalidOperationException($"The provided thread type {thread.GetType()} is not compatible with the agent. Only A2A agent created threads are supported.");
}
return typedThread;
}
private static void UpdateThread(A2AAgentThread? thread, string? contextId, string? taskId = null)
{
if (thread is null)
{
@@ -194,5 +246,93 @@ internal sealed class A2AAgent : AIAgent
// Assign a server-generated context Id to the thread if it's not already set.
thread.ContextId ??= contextId;
thread.TaskId = taskId;
}
private static AgentMessage CreateA2AMessage(A2AAgentThread typedThread, IEnumerable<ChatMessage> messages)
{
var a2aMessage = messages.ToA2AMessage();
// Linking the message to the existing conversation, if any.
// See: https://github.com/a2aproject/A2A/blob/main/docs/topics/life-of-a-task.md#group-related-interactions
a2aMessage.ContextId = typedThread.ContextId;
// Link the message as a follow-up to an existing task, if any.
// See: https://github.com/a2aproject/A2A/blob/main/docs/topics/life-of-a-task.md#task-refinements
a2aMessage.ReferenceTaskIds = typedThread.TaskId is null ? null : [typedThread.TaskId];
return a2aMessage;
}
private static A2AContinuationToken? GetContinuationToken(IEnumerable<ChatMessage> messages, AgentRunOptions? options = null)
{
if (options?.ContinuationToken is ResponseContinuationToken token)
{
if (messages.Any())
{
throw new InvalidOperationException("Messages are not allowed when continuing a background response using a continuation token.");
}
return A2AContinuationToken.FromToken(token);
}
return null;
}
private static A2AContinuationToken? CreateContinuationToken(string taskId, TaskState state)
{
if (state == TaskState.Submitted || state == TaskState.Working)
{
return new A2AContinuationToken(taskId);
}
return null;
}
private AgentRunResponseUpdate ConvertToAgentResponseUpdate(AgentMessage message)
{
return new AgentRunResponseUpdate
{
AgentId = this.Id,
ResponseId = message.MessageId,
RawRepresentation = message,
Role = ChatRole.Assistant,
MessageId = message.MessageId,
Contents = message.Parts.ConvertAll(part => part.ToAIContent()),
AdditionalProperties = message.Metadata?.ToAdditionalProperties(),
};
}
private AgentRunResponseUpdate ConvertToAgentResponseUpdate(AgentTask task)
{
return new AgentRunResponseUpdate
{
AgentId = this.Id,
ResponseId = task.Id,
RawRepresentation = task,
Role = ChatRole.Assistant,
Contents = task.ToAIContents(),
AdditionalProperties = task.Metadata?.ToAdditionalProperties(),
};
}
private AgentRunResponseUpdate ConvertToAgentResponseUpdate(TaskUpdateEvent taskUpdateEvent)
{
AgentRunResponseUpdate responseUpdate = new()
{
AgentId = this.Id,
ResponseId = taskUpdateEvent.TaskId,
RawRepresentation = taskUpdateEvent,
Role = ChatRole.Assistant,
AdditionalProperties = taskUpdateEvent.Metadata?.ToAdditionalProperties() ?? [],
};
if (taskUpdateEvent is TaskArtifactUpdateEvent artifactUpdateEvent)
{
responseUpdate.Contents = artifactUpdateEvent.Artifact.ToAIContents();
responseUpdate.RawRepresentation = artifactUpdateEvent;
}
return responseUpdate;
}
}
@@ -1,5 +1,6 @@
// Copyright (c) Microsoft. All rights reserved.
using System;
using System.Text.Json;
namespace Microsoft.Agents.AI.A2A;
@@ -7,22 +8,59 @@ namespace Microsoft.Agents.AI.A2A;
/// <summary>
/// Thread for A2A based agents.
/// </summary>
public sealed class A2AAgentThread : ServiceIdAgentThread
public sealed class A2AAgentThread : AgentThread
{
internal A2AAgentThread()
{
}
internal A2AAgentThread(JsonElement serializedThreadState, JsonSerializerOptions? jsonSerializerOptions = null) : base(serializedThreadState, jsonSerializerOptions)
internal A2AAgentThread(JsonElement serializedThreadState, JsonSerializerOptions? jsonSerializerOptions = null)
{
if (serializedThreadState.ValueKind != JsonValueKind.Object)
{
throw new ArgumentException("The serialized thread state must be a JSON object.", nameof(serializedThreadState));
}
var state = serializedThreadState.Deserialize(
A2AJsonUtilities.DefaultOptions.GetTypeInfo(typeof(A2AAgentThreadState))) as A2AAgentThreadState;
if (state?.ContextId is string contextId)
{
this.ContextId = contextId;
}
if (state?.TaskId is string taskId)
{
this.TaskId = taskId;
}
}
/// <summary>
/// Gets the ID for the current conversation with the A2A agent.
/// </summary>
public string? ContextId
public string? ContextId { get; internal set; }
/// <summary>
/// Gets the ID for the task the agent is currently working on.
/// </summary>
public string? TaskId { get; internal set; }
/// <inheritdoc/>
public override JsonElement Serialize(JsonSerializerOptions? jsonSerializerOptions = null)
{
get { return this.ServiceThreadId; }
internal set { this.ServiceThreadId = value; }
var state = new A2AAgentThreadState
{
ContextId = this.ContextId,
TaskId = this.TaskId
};
return JsonSerializer.SerializeToElement(state, A2AJsonUtilities.DefaultOptions.GetTypeInfo(typeof(A2AAgentThreadState)));
}
internal sealed class A2AAgentThreadState
{
public string? ContextId { get; set; }
public string? TaskId { get; set; }
}
}
@@ -0,0 +1,81 @@
// Copyright (c) Microsoft. All rights reserved.
using System;
using System.IO;
using System.Text.Json;
using Microsoft.Extensions.AI;
using Microsoft.Shared.Diagnostics;
namespace Microsoft.Agents.AI.A2A;
#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.
internal class A2AContinuationToken : ResponseContinuationToken
{
internal A2AContinuationToken(string taskId)
{
_ = Throw.IfNullOrEmpty(taskId);
this.TaskId = taskId;
}
internal string TaskId { get; }
internal static A2AContinuationToken FromToken(ResponseContinuationToken token)
{
if (token is A2AContinuationToken longRunContinuationToken)
{
return longRunContinuationToken;
}
ReadOnlyMemory<byte> data = token.ToBytes();
if (data.Length == 0)
{
Throw.ArgumentException(nameof(token), "Failed to create A2AContinuationToken from provided token because it does not contain any data.");
}
Utf8JsonReader reader = new(data.Span);
string taskId = null!;
reader.Read();
while (reader.Read())
{
if (reader.TokenType == JsonTokenType.EndObject)
{
break;
}
string propertyName = reader.GetString() ?? throw new JsonException("Failed to read property name from continuation token.");
switch (propertyName)
{
case "taskId":
reader.Read();
taskId = reader.GetString()!;
break;
default:
throw new JsonException($"Unrecognized property '{propertyName}'.");
}
}
return new(taskId);
}
public override ReadOnlyMemory<byte> ToBytes()
{
using MemoryStream stream = new();
using Utf8JsonWriter writer = new(stream);
writer.WriteStartObject();
writer.WriteString("taskId", this.TaskId);
writer.WriteEndObject();
writer.Flush();
stream.Position = 0;
return stream.ToArray();
}
}
@@ -0,0 +1,80 @@
// Copyright (c) Microsoft. All rights reserved.
using System.Diagnostics.CodeAnalysis;
using System.Text.Encodings.Web;
using System.Text.Json;
using System.Text.Json.Serialization;
using Microsoft.Agents.AI.A2A;
namespace Microsoft.Agents.AI;
/// <summary>
/// Provides utility methods and configurations for JSON serialization operations for A2A agent types.
/// </summary>
public static partial class A2AJsonUtilities
{
/// <summary>
/// Gets the default <see cref="JsonSerializerOptions"/> instance used for JSON serialization operations of A2A agent types.
/// </summary>
/// <remarks>
/// <para>
/// For Native AOT or applications disabling <see cref="JsonSerializer.IsReflectionEnabledByDefault"/>, this instance
/// includes source generated contracts for A2A agent types.
/// </para>
/// <para>
/// It additionally turns on the following settings:
/// <list type="number">
/// <item><description>Enables <see cref="JsonSerializerDefaults.Web"/> defaults.</description></item>
/// <item><description>Enables <see cref="JsonIgnoreCondition.WhenWritingNull"/> as the default ignore condition for properties.</description></item>
/// <item><description>Enables <see cref="JsonNumberHandling.AllowReadingFromString"/> as the default number handling for number types.</description></item>
/// <item><description>
/// Enables <see cref="JavaScriptEncoder.UnsafeRelaxedJsonEscaping"/> when escaping JSON strings.
/// Consuming applications must ensure that JSON outputs are adequately escaped before embedding in other document formats, such as HTML and XML.
/// </description></item>
/// </list>
/// </para>
/// </remarks>
public static JsonSerializerOptions DefaultOptions { get; } = CreateDefaultOptions();
/// <summary>
/// Creates and configures the default JSON serialization options for agent abstraction types.
/// </summary>
/// <returns>The configured options.</returns>
[UnconditionalSuppressMessage("ReflectionAnalysis", "IL3050:RequiresDynamicCode", Justification = "Converter is guarded by IsReflectionEnabledByDefault check.")]
[UnconditionalSuppressMessage("Trimming", "IL2026:Members annotated with 'RequiresUnreferencedCodeAttribute' require dynamic access", Justification = "Converter is guarded by IsReflectionEnabledByDefault check.")]
private static JsonSerializerOptions CreateDefaultOptions()
{
// Copy the configuration from the source generated context.
JsonSerializerOptions options = new(JsonContext.Default.Options)
{
Encoder = JavaScriptEncoder.UnsafeRelaxedJsonEscaping, // same as AIJsonUtilities
};
// Chain in the resolvers from both AIJsonUtilities and our source generated context.
// We want AIJsonUtilities first to ensure any M.E.AI types are handled via its resolver.
options.TypeInfoResolverChain.Clear();
options.TypeInfoResolverChain.Add(AgentAbstractionsJsonUtilities.DefaultOptions.TypeInfoResolver!);
// If reflection-based serialization is enabled by default, this includes
// the default type info resolver that utilizes reflection, but we need to manually
// apply the same converter AIJsonUtilities adds for string-based enum serialization,
// as that's not propagated as part of the resolver.
if (JsonSerializer.IsReflectionEnabledByDefault)
{
options.Converters.Add(new JsonStringEnumConverter());
}
options.MakeReadOnly();
return options;
}
[JsonSourceGenerationOptions(JsonSerializerDefaults.Web,
UseStringEnumConverter = true,
DefaultIgnoreCondition = JsonIgnoreCondition.WhenWritingNull,
NumberHandling = JsonNumberHandling.AllowReadingFromString)]
// A2A agent types
[JsonSerializable(typeof(A2AAgentThread.A2AAgentThreadState))]
[ExcludeFromCodeCoverage]
private sealed partial class JsonContext : JsonSerializerContext;
}
@@ -11,20 +11,37 @@ namespace A2A;
/// </summary>
internal static class A2AAgentTaskExtensions
{
internal static IList<ChatMessage> ToChatMessages(this AgentTask agentTask)
internal static IList<ChatMessage>? ToChatMessages(this AgentTask agentTask)
{
_ = Throw.IfNull(agentTask);
List<ChatMessage> messages = [];
List<ChatMessage>? messages = null;
if (agentTask.Artifacts is not null)
if (agentTask?.Artifacts is { Count: > 0 })
{
foreach (var artifact in agentTask.Artifacts)
{
messages.Add(artifact.ToChatMessage());
(messages ??= []).Add(artifact.ToChatMessage());
}
}
return messages;
}
internal static IList<AIContent>? ToAIContents(this AgentTask agentTask)
{
_ = Throw.IfNull(agentTask);
List<AIContent>? aiContents = null;
if (agentTask.Artifacts is not null)
{
foreach (var artifact in agentTask.Artifacts)
{
(aiContents ??= []).AddRange(artifact.ToAIContents());
}
}
return aiContents;
}
}
@@ -12,21 +12,15 @@ internal static class A2AArtifactExtensions
{
internal static ChatMessage ToChatMessage(this Artifact artifact)
{
List<AIContent>? aiContents = null;
foreach (var part in artifact.Parts)
{
var content = part.ToAIContent();
if (content is not null)
{
(aiContents ??= []).Add(content);
}
}
return new ChatMessage(ChatRole.Assistant, aiContents)
return new ChatMessage(ChatRole.Assistant, artifact.ToAIContents())
{
AdditionalProperties = artifact.Metadata.ToAdditionalProperties(),
RawRepresentation = artifact,
};
}
internal static List<AIContent> ToAIContents(this Artifact artifact)
{
return artifact.Parts.ConvertAll(part => part.ToAIContent());
}
}
@@ -2,18 +2,18 @@
<PropertyGroup>
<VersionSuffix>preview</VersionSuffix>
<NoWarn>$(NoWarn);MEAI001</NoWarn>
</PropertyGroup>
<Import Project="$(RepoRoot)/dotnet/nuget/nuget-package.props" />
<PropertyGroup>
<InjectSharedThrow>true</InjectSharedThrow>
<InjectTrimAttributesOnLegacy>true</InjectTrimAttributesOnLegacy>
</PropertyGroup>
<ItemGroup>
<PackageReference Include="A2A" />
<PackageReference Include="System.Net.ServerSentEvents" />
<PackageReference Include="Microsoft.Bcl.AsyncInterfaces" />
</ItemGroup>
<PropertyGroup>
@@ -23,7 +23,6 @@
<ItemGroup>
<PackageReference Include="Microsoft.Extensions.AI" />
<PackageReference Include="System.Net.ServerSentEvents" />
<PackageReference Include="Microsoft.Bcl.AsyncInterfaces" />
<PackageReference Include="System.Net.Http.Json" />
<PackageReference Include="System.Threading.Channels" />
</ItemGroup>
@@ -32,7 +32,7 @@ internal sealed class RunAgentInput
[JsonPropertyName("context")]
public AGUIContextItem[] Context { get; set; } = [];
[JsonPropertyName("forwardedProperties")]
[JsonPropertyName("forwardedProps")]
[JsonIgnore(Condition = JsonIgnoreCondition.WhenWritingDefault)]
public JsonElement ForwardedProperties { get; set; }
}
@@ -328,28 +328,4 @@ public abstract class AIAgent
AgentThread? thread = null,
AgentRunOptions? options = null,
CancellationToken cancellationToken = default);
/// <summary>
/// Notifies the specified thread about new messages that have been added to the conversation.
/// </summary>
/// <param name="thread">The conversation thread to notify about the new messages.</param>
/// <param name="messages">The collection of new messages to report to the thread.</param>
/// <param name="cancellationToken">The <see cref="CancellationToken"/> to monitor for cancellation requests. The default is <see cref="CancellationToken.None"/>.</param>
/// <returns>A task that represents the asynchronous notification operation.</returns>
/// <exception cref="ArgumentNullException"><paramref name="thread"/> or <paramref name="messages"/> is <see langword="null"/>.</exception>
/// <remarks>
/// <para>
/// This method ensures that conversation threads are kept informed about message additions, which
/// is important for threads that manage their own state, memory components, or derived context.
/// While all agent implementations should notify their threads, the specific actions taken by
/// each thread type may vary.
/// </para>
/// </remarks>
protected static async Task NotifyThreadOfNewMessagesAsync(AgentThread thread, IEnumerable<ChatMessage> messages, CancellationToken cancellationToken)
{
_ = Throw.IfNull(thread);
_ = Throw.IfNull(messages);
await thread.MessagesReceivedAsync(messages, cancellationToken).ConfigureAwait(false);
}
}
@@ -124,7 +124,7 @@ public abstract class AIContextProvider
/// that will be used. Context providers can use this information to determine what additional context
/// should be provided for the invocation.
/// </remarks>
public class InvokingContext
public sealed class InvokingContext
{
/// <summary>
/// Initializes a new instance of the <see cref="InvokingContext"/> class with the specified request messages.
@@ -153,7 +153,7 @@ public abstract class AIContextProvider
/// request messages that were used and the response messages that were generated. It also indicates
/// whether the invocation succeeded or failed.
/// </remarks>
public class InvokedContext
public sealed class InvokedContext
{
/// <summary>
/// Initializes a new instance of the <see cref="InvokedContext"/> class with the specified request messages.
@@ -49,7 +49,7 @@ public class AgentRunOptions
/// can be polled for completion by obtaining the token from the <see cref="AgentRunResponse.ContinuationToken"/> property
/// and passing it via this property on subsequent calls to <see cref="AIAgent.RunAsync(AgentThread?, AgentRunOptions?, System.Threading.CancellationToken)"/>.
/// </remarks>
public object? ContinuationToken { get; set; }
public ResponseContinuationToken? ContinuationToken { get; set; }
/// <summary>
/// Gets or sets a value indicating whether the background responses are allowed.
@@ -175,7 +175,7 @@ public class AgentRunResponse
/// to poll for completion.
/// </para>
/// </remarks>
public object? ContinuationToken { get; set; }
public ResponseContinuationToken? ContinuationToken { get; set; }
/// <summary>
/// Gets or sets the timestamp indicating when this response was created.

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