* fix(foundry): reconcile toolbox hosted-tool payloads with Responses API
* docs(foundry): update create_sample_toolbox docstring to reflect all tools created
* Fix streaming response losing created_at from response.completed event (#5347)
The streaming path in _parse_chunk_from_openai did not extract created_at
from the response.completed event, unlike the non-streaming path in
_parse_responses_response. This caused durabletask persistence warnings
when created_at was None.
Extract created_at in the response.completed case and pass it to the
returned ChatResponseUpdate.
Also fix pre-existing pyright errors for optional orjson import in sample
files.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Fix orjson import suppression to use pyright instead of mypy (#5347)
Replace `# type: ignore[import-not-found]` with
`# pyright: ignore[reportMissingImports]` on optional orjson imports
in conversation sample files, matching the repo's Pyright strict
configuration.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Add Azure AI Foundry Responses hosting adapter
Implement Microsoft.Agents.AI.Hosting.AzureAIResponses to host agent-framework
AIAgents and workflows within Azure Foundry as hosted agents via the
Azure.AI.AgentServer.Responses SDK.
- AgentFrameworkResponseHandler: bridges ResponseHandler to AIAgent execution
- InputConverter: converts Responses API inputs/history to MEAI ChatMessage
- OutputConverter: converts agent response updates to SSE event stream
- ServiceCollectionExtensions: DI registration helpers
- 336 unit tests across net8.0/net9.0/net10.0 (112 per TFM)
- ResponseStreamValidator: SSE protocol validation tool for samples
- FoundryResponsesHosting sample app
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Bump System.ClientModel to 1.10.0 for Azure.Core 1.52.0 compat
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Clean up tests and sample formatting
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Update Azure.AI.AgentServer packages to 1.0.0-alpha.20260401.5
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Add hosted package version suffix (0.9.0-hosted) to distinguish from mainline
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Move Foundry Responses hosting into Microsoft.Agents.AI.Foundry package
Move source and test files from the standalone Hosting.AzureAIResponses project
into the Foundry package under a Hosting/ subfolder. This consolidates the
Foundry-specific hosting adapter into the main Foundry package.
- Source: Microsoft.Agents.AI.Foundry.Hosting namespace
- Tests: merged into Foundry.UnitTests/Hosting/
- Conditionally compiled for .NETCoreApp TFMs only (net8.0+)
- Deleted standalone Hosting.AzureAIResponses project and test project
- Updated sample and solution references
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Bump package version to 0.9.0-hosted.260402.2
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Bump OpenTelemetry packages to fix NU1109 downgrade errors
- OpenTelemetry/Api/Exporter.Console/Exporter.InMemory: 1.13.1 -> 1.15.0
- OpenTelemetry.Exporter.OpenTelemetryProtocol: already 1.15.0
- OpenTelemetry.Extensions.Hosting: already 1.14.0
- OpenTelemetry.Instrumentation.AspNetCore/Http: already 1.14.0
- OpenTelemetry.Instrumentation.Runtime: 1.13.0 -> 1.14.0
- Azure.Monitor.OpenTelemetry.Exporter: 1.4.0 -> 1.5.0
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Fix CA1873: guard LogWarning with IsEnabled check
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Fix model override bug and add client REPL sample
- InputConverter: stop propagating request.Model to ChatOptions.ModelId
Hosted agents use their own model; client-provided model values like
'hosted-agent' were being passed through and causing server errors.
- Add FoundryResponsesRepl sample: interactive CLI client that connects
to a Foundry Responses endpoint using ResponsesClient.AsAIAgent()
- Bump package version to 0.9.0-hosted.260403.1
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Catch agent errors and emit response.failed with real error message
Previously, unhandled exceptions from agent execution would bubble up
to the SDK orchestrator, which emits a generic 'An internal server
error occurred.' message — hiding the actual cause (e.g., 401 auth
failures, model not found, etc.).
Now AgentFrameworkResponseHandler catches non-cancellation exceptions
and emits a proper response.failed event containing the real error
message, making it visible to clients and in logs.
OperationCanceledException still propagates for proper cancellation
handling by the SDK.
Also bumps package version to 0.9.0-hosted.260403.2.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Renaming and merging hosting extensions. (#5091)
* Rename AddAgentFrameworkHandler to AddFoundryResponses and add MapFoundryResponses
- Rename extension methods: AddAgentFrameworkHandler -> AddFoundryResponses, MapAgentFrameworkHandler -> MapFoundryResponses
- AddFoundryResponses now calls AddResponsesServer() internally
- Add MapFoundryResponses() extension on IEndpointRouteBuilder
- Update sample and tests to use new API names
- Remove redundant AddResponsesServer() and /ready endpoint from sample
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Fixing numbering in sample.
---------
Co-authored-by: alliscode <bentho@microsoft.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Address breaking changes in 260408
* Bump hosted internal package version
* Add UserAgent middleware tests for Foundry hosting
* Hosting Samples update
* Hosting Samples update
* Hosting Samples update
* Hosting Samples update
* ChatClientAgent working
* Adding SessionStorage and SessionManagement, improving samples to align Consumption vs Hosting
* Using updates
* Update chat client agent for contributor and devs
* Foundry Agent Hosting
* Address text rag sample working
* Version bump
* Adding LocalTools + Workflow samples
* Removing extra using samples
* Add Hosted-McpTools sample with dual MCP pattern
Demonstrates two MCP integration layers in a single hosted agent:
- Client-side MCP: McpClient connects to Microsoft Learn, agent handles
tool invocations locally (docs_search, code_sample_search, docs_fetch)
- Server-side MCP: HostedMcpServerTool delegates tool discovery and
invocation to the LLM provider (Responses API), no local connection
Includes DevTemporaryTokenCredential for Docker local debugging,
Dockerfile.contributor for ProjectReference builds, and the openai/v1
route mapping for AIProjectClient compatibility in Development mode.
* .NET: Bump Azure.AI.AgentServer packages to 1.0.0-beta.1/beta.21 and fix br… (#5287)
* Bump Azure.AI.AgentServer packages to 1.0.0-beta.1/beta.21 and fix breaking API changes
- Azure.AI.AgentServer.Core: 1.0.0-beta.11 -> 1.0.0-beta.21
- Azure.AI.AgentServer.Invocations: 1.0.0-alpha.20260408.4 -> 1.0.0-beta.1
- Azure.AI.AgentServer.Responses: 1.0.0-alpha.20260408.4 -> 1.0.0-beta.1
- Azure.Identity: 1.20.0 -> 1.21.0 (transitive requirement)
- Azure.Core: 1.52.0 -> 1.53.0 (transitive requirement)
- Remove azure-sdk-for-net dev feed (packages now on nuget.org)
- Fix OutputConverter for new builder API (auto-tracked children, split EmitTextDone/EmitDone)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Fixing small issues.
---------
Co-authored-by: alliscode <bentho@microsoft.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Add Azure AI Foundry Responses hosting adapter
Implement Microsoft.Agents.AI.Hosting.AzureAIResponses to host agent-framework
AIAgents and workflows within Azure Foundry as hosted agents via the
Azure.AI.AgentServer.Responses SDK.
- AgentFrameworkResponseHandler: bridges ResponseHandler to AIAgent execution
- InputConverter: converts Responses API inputs/history to MEAI ChatMessage
- OutputConverter: converts agent response updates to SSE event stream
- ServiceCollectionExtensions: DI registration helpers
- 336 unit tests across net8.0/net9.0/net10.0 (112 per TFM)
- ResponseStreamValidator: SSE protocol validation tool for samples
- FoundryResponsesHosting sample app
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Bump System.ClientModel to 1.10.0 for Azure.Core 1.52.0 compat
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Clean up tests and sample formatting
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Update Azure.AI.AgentServer packages to 1.0.0-alpha.20260401.5
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Add hosted package version suffix (0.9.0-hosted) to distinguish from mainline
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Move Foundry Responses hosting into Microsoft.Agents.AI.Foundry package
Move source and test files from the standalone Hosting.AzureAIResponses project
into the Foundry package under a Hosting/ subfolder. This consolidates the
Foundry-specific hosting adapter into the main Foundry package.
- Source: Microsoft.Agents.AI.Foundry.Hosting namespace
- Tests: merged into Foundry.UnitTests/Hosting/
- Conditionally compiled for .NETCoreApp TFMs only (net8.0+)
- Deleted standalone Hosting.AzureAIResponses project and test project
- Updated sample and solution references
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Bump package version to 0.9.0-hosted.260402.2
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Bump OpenTelemetry packages to fix NU1109 downgrade errors
- OpenTelemetry/Api/Exporter.Console/Exporter.InMemory: 1.13.1 -> 1.15.0
- OpenTelemetry.Exporter.OpenTelemetryProtocol: already 1.15.0
- OpenTelemetry.Extensions.Hosting: already 1.14.0
- OpenTelemetry.Instrumentation.AspNetCore/Http: already 1.14.0
- OpenTelemetry.Instrumentation.Runtime: 1.13.0 -> 1.14.0
- Azure.Monitor.OpenTelemetry.Exporter: 1.4.0 -> 1.5.0
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Fix CA1873: guard LogWarning with IsEnabled check
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Fix model override bug and add client REPL sample
- InputConverter: stop propagating request.Model to ChatOptions.ModelId
Hosted agents use their own model; client-provided model values like
'hosted-agent' were being passed through and causing server errors.
- Add FoundryResponsesRepl sample: interactive CLI client that connects
to a Foundry Responses endpoint using ResponsesClient.AsAIAgent()
- Bump package version to 0.9.0-hosted.260403.1
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Catch agent errors and emit response.failed with real error message
Previously, unhandled exceptions from agent execution would bubble up
to the SDK orchestrator, which emits a generic 'An internal server
error occurred.' message — hiding the actual cause (e.g., 401 auth
failures, model not found, etc.).
Now AgentFrameworkResponseHandler catches non-cancellation exceptions
and emits a proper response.failed event containing the real error
message, making it visible to clients and in logs.
OperationCanceledException still propagates for proper cancellation
handling by the SDK.
Also bumps package version to 0.9.0-hosted.260403.2.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Renaming and merging hosting extensions. (#5091)
* Rename AddAgentFrameworkHandler to AddFoundryResponses and add MapFoundryResponses
- Rename extension methods: AddAgentFrameworkHandler -> AddFoundryResponses, MapAgentFrameworkHandler -> MapFoundryResponses
- AddFoundryResponses now calls AddResponsesServer() internally
- Add MapFoundryResponses() extension on IEndpointRouteBuilder
- Update sample and tests to use new API names
- Remove redundant AddResponsesServer() and /ready endpoint from sample
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Fixing numbering in sample.
---------
Co-authored-by: alliscode <bentho@microsoft.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Address breaking changes in 260408
* Bump hosted internal package version
* Add UserAgent middleware tests for Foundry hosting
* Hosting Samples update
* Hosting Samples update
* Hosting Samples update
* Hosting Samples update
* ChatClientAgent working
* Adding SessionStorage and SessionManagement, improving samples to align Consumption vs Hosting
* Using updates
* Update chat client agent for contributor and devs
* Foundry Agent Hosting
* Address text rag sample working
* Version bump
* Adding LocalTools + Workflow samples
* Removing extra using samples
* Add Hosted-McpTools sample with dual MCP pattern
Demonstrates two MCP integration layers in a single hosted agent:
- Client-side MCP: McpClient connects to Microsoft Learn, agent handles
tool invocations locally (docs_search, code_sample_search, docs_fetch)
- Server-side MCP: HostedMcpServerTool delegates tool discovery and
invocation to the LLM provider (Responses API), no local connection
Includes DevTemporaryTokenCredential for Docker local debugging,
Dockerfile.contributor for ProjectReference builds, and the openai/v1
route mapping for AIProjectClient compatibility in Development mode.
* Bump Azure.AI.AgentServer packages to 1.0.0-beta.1/beta.21 and fix breaking API changes
- Azure.AI.AgentServer.Core: 1.0.0-beta.11 -> 1.0.0-beta.21
- Azure.AI.AgentServer.Invocations: 1.0.0-alpha.20260408.4 -> 1.0.0-beta.1
- Azure.AI.AgentServer.Responses: 1.0.0-alpha.20260408.4 -> 1.0.0-beta.1
- Azure.Identity: 1.20.0 -> 1.21.0 (transitive requirement)
- Azure.Core: 1.52.0 -> 1.53.0 (transitive requirement)
- Remove azure-sdk-for-net dev feed (packages now on nuget.org)
- Fix OutputConverter for new builder API (auto-tracked children, split EmitTextDone/EmitDone)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Fixing small issues.
* Fix IDE0009: add 'this' qualification in DevTemporaryTokenCredential
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Fix IDE0009: add 'this' qualification in all HostedAgentsV2 samples
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Fix CHARSET: add UTF-8 BOM to Hosted-LocalTools and Hosted-Workflows
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Fix dotnet format: add Async suffix to test methods (IDE1006), fix encoding and style
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Register AgentSessionStore in test DI setups
Add InMemoryAgentSessionStore registration to all ServiceCollection
setups in AgentFrameworkResponseHandlerTests and WorkflowIntegrationTests.
This is needed after the AgentSessionStore infrastructure was introduced
in the responses-hosting feature. Tests still have NotImplementedException
stubs for CreateSessionCoreAsync which will be fixed when the session
infrastructure is fully available.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Add Invocations protocol samples (hosted echo agent + client) (#5278)
Add Hosted-Invocations-EchoAgent: a minimal echo agent hosted via the
Invocations protocol (POST /invocations) using AddInvocationsServer and
MapInvocationsServer, bridged to an Agent Framework AIAgent through a
custom InvocationHandler.
Add SimpleInvocationsAgent: a console REPL client that wraps HttpClient
calls to the /invocations endpoint in a custom InvocationsAIAgent,
demonstrating programmatic consumption of the Invocations protocol.
Both samples default to port 8088 for consistency with other hosted
agent samples.
* Restructure FoundryHostedAgents samples into invocations/ and responses/
Align dotnet hosted agent samples with the Python side (PR #5281) by
reorganizing the directory structure:
- Remove HostedAgentsV1 entirely (old API pattern)
- Split HostedAgentsV2 into invocations/ and responses/ based on protocol
- Move Using-Samples accordingly (SimpleAgent to responses, SimpleInvocationsAgent to invocations)
- Update slnx with new project paths and add previously missing invocations projects
- Update README cd paths from HostedAgentsV2 to invocations or responses
- Rename .env.local to .env.example to match Python naming convention
- Fix format violations in newly included invocations projects
* Remove launchSettings, use .env for port configuration
- Delete all launchSettings.json files (port 8088 now comes from ASPNETCORE_URLS in .env)
- Add DotNetEnv to Hosted-Invocations-EchoAgent so it loads .env like the responses samples
- Create .env.example for EchoAgent with ASPNETCORE_URLS and ASPNETCORE_ENVIRONMENT
- Add AGENT_NAME to ChatClientAgent and FoundryAgent .env.example (required by those samples)
- Add AZURE_BEARER_TOKEN=DefaultAzureCredential to all .env.example files
- Update DevTemporaryTokenCredential in all 6 samples to treat the sentinel value
as unavailable, allowing ChainedTokenCredential to fall through to DefaultAzureCredential
- Update EchoAgent README with Configuration section
* Use placeholder for AGENT_NAME in Hosted-FoundryAgent .env.example
* Move FoundryResponsesHosting to responses/Hosted-WorkflowHandoff, use GetResponsesClient
* Rename Hosted-Workflows to Hosted-Workflow-Simple, Hosted-WorkflowHandoff to Hosted-Workflow-Handoff
* Remove FoundryResponsesRepl and empty FoundryResponsesHosting directory
* Add Dockerfiles, README, agent yamls and bearer token support to Hosted-Workflow-Handoff
- Add Dockerfile and Dockerfile.contributor for Docker-based testing
- Add agent.yaml and agent.manifest.yaml with triage-workflow as primary agent
- Add README.md following sibling pattern, noting Azure OpenAI vs Foundry endpoint
- Add DevTemporaryTokenCredential and ChainedTokenCredential for Docker auth
- Register triage-workflow as non-keyed default so azd invoke works without model
- Update .env.example with AZURE_BEARER_TOKEN sentinel
- Add .gitignore to 04-hosting to suppress VS-generated launchSettings.json
- Fix docker run image name in Hosted-Workflow-Simple README
* Fix AgentFrameworkResponseHandlerTests: implement session methods in test mock agents
* .NET: Auto-instrument resolved AIAgents with OpenTelemetry for Foundry Hosted Agents (#5316)
* Auto-instrument resolved AIAgents with OpenTelemetry using Core ResponsesSourceName
* Add OTel telemetry capture tests for Foundry hosted agent handler
* Net: Prepare Foundry Preview Release (#5336)
* Prepare Foundry preview release 1.2.0-preview.*
Bump VersionPrefix to 1.2.0 and update the preview stamp date. Invert packaging opt-in so only the Foundry preview set produces NuGet packages:
- Microsoft.Agents.AI.Abstractions
- Microsoft.Agents.AI
- Microsoft.Agents.AI.Workflows
- Microsoft.Agents.AI.Workflows.Generators
- Microsoft.Agents.AI.Foundry
Flip IsReleased=false on the preview set so they pick up the -preview.YYMMDD.N suffix. Gate GeneratePackageOnBuild on IsPackable=true. Remove the global IsPackable=true from nuget-package.props so the repo-level default (false) applies to everything else.
* Lower preview VersionPrefix to 0.0.1
Retroactive preview publish: bump VersionPrefix and GitTag from 1.2.0 to 0.0.1 so the 5 Foundry preview packages emit as 0.0.1-preview.260417.1.
* Net: Publish all packages as 0.0.1-preview.260417.2 (#5341)
Revises the Foundry pre-release approach to publish ALL normally packable src projects as preview packages stamped 0.0.1-preview.260417.2, including projects previously flagged IsReleased=true or with a non-default VersionSuffix (rc/alpha).
nuget-package.props:
- Collapse the four conditional PackageVersion expressions (IsReleaseCandidate, VersionSuffix, default preview, IsReleased stable) into a single unconditional 0.0.1-preview.260417.2. On this preview-only branch every package ships with the same pre-release stamp regardless of per-project flags.
- Restore the global IsPackable=true default (offsetting the repo-wide IsPackable=false in Directory.Build.props). Projects that opt out (Mem0, Declarative) already set IsPackable=false AFTER importing this file so they remain non-packable.
- Remove the IsReleased-gated EnablePackageValidation line. Package validation does not apply to a 0.0.1 preview.
csproj reverts (Abstractions, Agents.AI, Workflows, Workflows.Generators, Foundry):
- Revert the IsPackable=true opt-in block introduced in #5336 (now redundant since the props default is true again).
- Restore IsReleased=true to its pre-PR value. The setting is now a no-op because the props no longer branches on it.
* Bump preview version to 260420.1 and fix AgentServer package deps (#5367)
- Bump PackageVersion to 0.0.1-preview.260420.1
- Bump Azure.AI.AgentServer.Core beta.21 -> beta.22 (required by
Azure.AI.AgentServer.Responses beta.3)
- Replace AgentHostTelemetry.ResponsesSourceName with local constant
(type made internal in AgentServer.Core beta.22)
Co-authored-by: alliscode <bentho@microsoft.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* .NET: Hosted agents toolbox support (#5368)
* feat: Add Foundry Toolbox (MCP) support to AgentFrameworkResponseHandler
Adds support for Foundry Toolsets MCP proxy integration in the hosted agent
response handler. Toolsets connect at startup via IHostedService, gating the
readiness probe per spec §3.1. MCP tools are injected into every request's
ChatOptions and OAuth consent errors (-32006) are intercepted and surfaced as
mcp_approval_request + incomplete SSE events.
New files:
- FoundryToolboxOptions.cs: configuration POCO for toolset names and API version
- FoundryToolboxBearerTokenHandler.cs: DelegatingHandler with Azure Bearer token
auth, Foundry-Features header injection, and 3x exponential backoff on 429/5xx
- McpConsentContext.cs: AsyncLocal-based per-request consent state shared between
the tool wrapper and the response handler
- ConsentAwareMcpClientTool.cs: AIFunction wrapper that catches -32006 errors and
signals consent via shared state and linked CancellationTokenSource
- FoundryToolboxService.cs: IHostedService that creates McpClient per toolset at
startup and exposes cached tools
Modified files:
- AgentFrameworkResponseHandler.cs: injects toolbox tools into ChatOptions, sets
up linked CTS consent interception, emits mcp_approval_request on -32006
- ServiceCollectionExtensions.cs: adds AddFoundryToolboxes(params string[]) extension
- Microsoft.Agents.AI.Foundry.csproj: adds ModelContextProtocol and Azure.Identity
dependencies under NETCoreApp condition
Sample:
- Hosted-Toolbox: minimal hosted agent sample using AddFoundryToolboxes
* Rename toolset to toolbox in user-facing API; rename ConsentAwareMcpClientTool to ConsentAwareMcpClientAIFunction
* Add HostedMcpToolboxAITool for client-selectable Foundry toolboxes
Introduces HostedMcpToolboxAITool, a marker tool subclassing HostedMcpServerTool that rides the OpenAI Responses 'mcp' wire format to let clients request a specific Foundry toolbox per request.
- New FoundryAITool.CreateHostedMcpToolbox(name, version?) factory.
- FoundryToolboxOptions.StrictMode (default true) rejects unregistered toolboxes; set to false to allow lazy-open on first use.
- FoundryToolboxService.GetToolboxToolsAsync(name, version?) resolves cached or lazy-opened MCP tools.
- AgentFrameworkResponseHandler parses request.Tools for foundry-toolbox://name[?version=v] markers and injects resolved tools per request, merging with pre-registered ones.
- Unit tests for marker parsing and strict-mode resolution.
* Bump Azure.AI.Projects to 2.1.0-alpha; add ToolboxRecord/ToolboxVersion factory overloads + tests
* Fix PR review issues: retry off-by-one, URI encoding, docs, tests, build
- Fix off-by-one in FoundryToolboxBearerTokenHandler retry loop (4 attempts → 3)
- URI-encode version parameter in HostedMcpToolboxAITool.BuildAddress
- Add XML doc clarifying version pinning is reserved for future use
- Add comment clarifying AddHostedService deduplication safety
- Fix DevTemporaryTokenCredential expiry to use DateTimeOffset.MaxValue
- Fix AgentCard ambiguity in A2AServer sample with using alias
- Add 18 new unit tests for retry handler and ReadMcpToolboxMarkers
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com>
Co-authored-by: alliscode <bentho@microsoft.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* .NET: Hosted agent adapter (#5371)
* Bump preview version to 260420.1 and fix AgentServer package deps
- Bump PackageVersion to 0.0.1-preview.260420.1
- Bump Azure.AI.AgentServer.Core beta.21 -> beta.22 (required by
Azure.AI.AgentServer.Responses beta.3)
- Replace AgentHostTelemetry.ResponsesSourceName with local constant
(type made internal in AgentServer.Core beta.22)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Fix CA1873: guard LogError with IsEnabled check in FoundryToolboxService
Wrap the LogError call with an IsEnabled(LogLevel.Error) guard to satisfy
the CA1873 analyzer rule which flags potentially expensive argument
evaluation when logging is disabled.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: alliscode <bentho@microsoft.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* .NET: Hosted agent adapter (#5374)
* Bump preview version to 260420.1 and fix AgentServer package deps
- Bump PackageVersion to 0.0.1-preview.260420.1
- Bump Azure.AI.AgentServer.Core beta.21 -> beta.22 (required by
Azure.AI.AgentServer.Responses beta.3)
- Replace AgentHostTelemetry.ResponsesSourceName with local constant
(type made internal in AgentServer.Core beta.22)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Fix CA1873: guard LogError with IsEnabled check in FoundryToolboxService
Wrap the LogError call with an IsEnabled(LogLevel.Error) guard to satisfy
the CA1873 analyzer rule which flags potentially expensive argument
evaluation when logging is disabled.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Bumping NuGet version
---------
Co-authored-by: alliscode <bentho@microsoft.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* .NET: Hosted agent adapter (#5406)
* Bump preview version to 260420.1 and fix AgentServer package deps
- Bump PackageVersion to 0.0.1-preview.260420.1
- Bump Azure.AI.AgentServer.Core beta.21 -> beta.22 (required by
Azure.AI.AgentServer.Responses beta.3)
- Replace AgentHostTelemetry.ResponsesSourceName with local constant
(type made internal in AgentServer.Core beta.22)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Fix CA1873: guard LogError with IsEnabled check in FoundryToolboxService
Wrap the LogError call with an IsEnabled(LogLevel.Error) guard to satisfy
the CA1873 analyzer rule which flags potentially expensive argument
evaluation when logging is disabled.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Bumping NuGet version
* Restore conditional versioning, remove dev feed, bump Azure.AI.Projects to beta.1
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: alliscode <bentho@microsoft.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Hosted agent adapter (#5408)
* Bump preview version to 260420.1 and fix AgentServer package deps
- Bump PackageVersion to 0.0.1-preview.260420.1
- Bump Azure.AI.AgentServer.Core beta.21 -> beta.22 (required by
Azure.AI.AgentServer.Responses beta.3)
- Replace AgentHostTelemetry.ResponsesSourceName with local constant
(type made internal in AgentServer.Core beta.22)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Fix CA1873: guard LogError with IsEnabled check in FoundryToolboxService
Wrap the LogError call with an IsEnabled(LogLevel.Error) guard to satisfy
the CA1873 analyzer rule which flags potentially expensive argument
evaluation when logging is disabled.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Bumping NuGet version
* Restore conditional versioning, remove dev feed, bump Azure.AI.Projects to beta.1
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Address PR #5312 review comments
- Add comment explaining NU1903 suppression (Microsoft.Bcl.Memory transitive vuln)
- Remove NU1903 from sample/test projects where not needed
- Fix Dockerfile ENTRYPOINT mismatch in Hosted-Workflow-Simple
- Align agent name to 'hosted-workflow-simple' in agent.yaml and README
- Fix Hosted-McpTools README: replace GitHub PAT refs with Microsoft Learn
- Fix session persistence: only persist when client provides conversation ID
- Upgrade IsNullOrEmpty to IsNullOrWhiteSpace for session ID checks
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: alliscode <bentho@microsoft.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Split Foundry into stable V1 and preview Hosting package
Extract hosted agent functionality from Microsoft.Agents.AI.Foundry into a
new Microsoft.Agents.AI.Foundry.Hosting preview package. This resolves NU5104
build errors caused by the stable Foundry package depending on prerelease
Azure SDK packages (Azure.AI.AgentServer.Responses, Azure.AI.Projects beta).
Changes:
- Create Microsoft.Agents.AI.Foundry.Hosting with VersionSuffix=preview,
targeting .NET Core only (net8.0/9.0/10.0)
- Move all Hosting/ source files to the new project
- Move ToolboxRecord/ToolboxVersion overloads to FoundryAIToolExtensions
- Revert Azure.AI.Projects to 2.0.0 in Directory.Packages.props;
Hosting uses VersionOverride for 2.1.0-beta.1
- Clean V1 Foundry csproj: remove beta deps, ASP.NET Core ref, hosting conditionals
- Update 8 hosted agent sample projects to reference Foundry.Hosting
- Split unit tests: ToolboxRecord/ToolboxVersion tests moved to Hosting/
- Add Foundry.Hosting to solution file
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Address PR review comments: experimental attrs, doc fixes, token propagation
- Add [Experimental(OPENAI001)] to all 7 public Hosting types per reviewer request
- Fix McpConsentContext XML doc: 'Thread-static' -> 'Async-local' (AsyncLocal
flows with ExecutionContext, not thread-static)
- Expand UserAgentMiddleware test regex to match prerelease versions (e.g. 1.0.0-rc.4)
- Propagate CancellationToken in AgentFrameworkResponseHandler session save
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Remove unnecessary MEAI001 suppression from stable Foundry package
MEAI001 was a leftover from when Hosting code lived in the same project.
The stable V1 Foundry package builds clean without it, and suppressing
experimental diagnostics in a released package can hide unintentional
exposure of experimental APIs to consumers.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Add Foundry.Hosting to release solution filter
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: alliscode <bentho@microsoft.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Ben Thomas <ben.thomas@microsoft.com>
* Fix OpenAIEmbeddingClient with /openai/v1 endpoint (#5068)
When base_url ends with /openai/v1/ and a credential is provided,
load_openai_service_settings was creating an AsyncAzureOpenAI client.
The Azure SDK rewrites deployment-based endpoints (including /embeddings)
by inserting /deployments/{model}/ into the URL, producing 404s on the
OpenAI-compatible /openai/v1 endpoint.
Use AsyncOpenAI instead of AsyncAzureOpenAI when the resolved base_url
targets /openai/v1, converting the Azure token provider to an async
api_key callable. The responses_mode path is unaffected because the
Responses API (/responses) is not in the SDK's rewrite list.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Python: Fix OpenAIEmbeddingClient to use AsyncOpenAI for /openai/v1 endpoints
Fixes#5068
* Address review feedback: improve test coverage and remove unrelated changes
- Revert unrelated formatting change in test_a2a_agent.py
- Fix test_init_with_openai_v1_base_url_and_api_key_uses_openai_client to
exercise the Azure settings path (via AZURE_OPENAI_BASE_URL env var)
instead of the plain OpenAI path, covering the elif api_key branch
- Add _ensure_async_token_provider unit tests for both sync and async
token providers
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Address review feedback for #5068: Python: [Bug]: `OpenAIEmbeddingClient` does not work with `/openai/v1` endpoint
---------
Co-authored-by: MAF Dashboard Bot <maf-dashboard-bot@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com>
* feat(evals): add ground_truth support for similarity evaluator
- Include expected_output as ground_truth in Foundry JSONL dataset rows
- Add ground_truth to item schema and data mapping for similarity evaluator
- Add expected_output parameter to evaluate_workflow
- Add similarity Pattern 3 to evaluate_agent and evaluate_workflow samples
- Add tests for ground_truth in dataset, schema, and evaluate_workflow
* Apply suggestions from code review
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* fix: wrap long line to satisfy ruff E501
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* refactor: remove dead code
* refactor: remove ignore YieldsMessageAttribute
- the correct one to use is YieldsOutputAttribute
- fixes a comment that mistakenly refers to `.YieldsMessage()` which does not exist.
* fix: ChatForwardingExecutor does not use correct role for string messages
- make ChatForwardingExecutor use its configured role for string messages rather than always use ChatRole.User
- add ChatForwardingExecutor tests
* fixup: remove unused attribute
* test: Add tests for failure when .AsAgent used on a non-ChatProtocol workflow
* test: Add FunctionExecutor tests
- also fixes Send and YieldOutput type registration for synchronous output-returning delegates
* test: Suppress CodeCoverage for obsolete names
* fix: Re-add Obsolete attributes
- avoid hard-breaking change
- properly notify users that these attributes get ignored
Some providers, e.g. Gemini, do not use the CallId mechanism to disambiguate simultaneous function calls. This can result in message lists containing multiple turn to fail to filter properly.
The fix is to take advantage of the expectation that Handoff Orchestration is a "single-speaker" flow, which only has a single active AIAgent per "turn" and an agent's turn is not finished until all outstanding function calls are finished.
This allows us to expect that any ambiguous-CallId FunctionCallContent are either in separate turns or will have had a response before the next issued call with the same Id.
* Add set_stop_loss tool to concurrent_builder_tool_approval sample
Add a second approval-gated tool (set_stop_loss) to the concurrent workflow
tool approval sample to demonstrate handling approval requests for different
tools in the same concurrent workflow.
Changes:
- Add set_stop_loss(symbol, stop_price) with approval_mode='always_require'
- Include new tool in both agents' tool lists
- Update agent instructions and prompt to encourage stop-loss usage
- Update docstring to reflect two approval-gated tools
- Update sample output to show mixed approval requests
Fixes#4874
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Print tool name and arguments in concurrent sample's process_event_stream (#4874)
Align process_event_stream in concurrent_builder_tool_approval.py to print
the tool name and arguments when collecting approval requests, matching the
sample output comment and the sequential_builder_tool_approval.py pattern.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Add None-guard for function_call access in tool approval sample (#4874)
Add explicit None-checks before accessing function_call.name and
function_call.arguments in concurrent_builder_tool_approval.py. The
function_call field is typed Content | None, so direct attribute access
without a guard could raise AttributeError and required type: ignore
comments. The None-guard is consistent with the pattern used in
_agent_run.py and removes the suppression comments.
Also add a regression test verifying that function_call defaults to None
and that the None-guard pattern is safe.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Apply same function_call None-guard to sibling tool-approval samples (#4874)
Apply the same fix to sequential_builder_tool_approval.py and
group_chat_builder_tool_approval.py, which had the identical pattern
of accessing function_call.name/arguments without a None-guard.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Python: Wrapper + Samples 1st (#5177)
* Experiment
* Update dependency and add non streaming
* Add more samples
* Rename samples
* Add invocations
* Comments 1
* Comments 2
* Comments 3
* Improve README
* Add local shell sample
* WIP: Add eval and memory samples
* Update user agent prefix
* Update user agent prefix doc
* Update dependency (#5215)
* Add tests and more content types (#5235)
* Add tests
* fix tests and sample
* Fix formatting
* Remove function approval contents
* Python: Refine samples and upgrade packages (#5261)
* Refine samples and upgrade pacakges
* Upgrade to a new package that fixes a bug
* Update model env var
* Move samples (#5281)
* Python: Upgrade agentserver packages (#5284)
* Upgrade agentserver packages
* Fix new types
* Python: Add special handling for workflows (#5298)
* Add special handling for workflows
* Address comments
* Improve samples (#5372)
* Python: Add more types (#5378)
* Add more type supports
* Upgrade packages
* Remove TODOs in README
* Fix README
* Comments and mypy
* User agent scoped
* Fix README
* Fix pre commit
* Fix pre commit 2
* Fix pre commit 3
* Fix pre commit 4
* Fix pre commit 5
* Fix pre commit 6
* Add azure-monitor-opentelemetry to dev deps
Fixes Samples & Markdown CI failure. The PR's new transitive dep on
azure-monitor-opentelemetry-exporter (via azure-ai-agentserver-core) makes
pyright resolve the azure.monitor.opentelemetry namespace, flipping the
check_md_code_blocks diagnostic for `configure_azure_monitor` from
reportMissingImports (filtered) to reportAttributeAccessIssue (not filtered).
Installing the umbrella azure-monitor-opentelemetry package in dev makes
pyright resolve the symbol correctly, matching the install guidance the
observability README already gives users.
---------
Co-authored-by: Evan Mattson <evan.mattson@microsoft.com>
* Expose forwarded_props to agents and tools via session metadata (#5239)
Include forwarded_props from AG-UI request input_data in session.metadata
(agent runner) and function_invocation_kwargs (workflow runner) so that
agents, tools, and workflow executors can access request-level metadata
such as invocation source flags from CopilotKit.
- Add forwarded_props to base_metadata in _agent_run.py when present
- Add 'forwarded_props' to AG_UI_INTERNAL_METADATA_KEYS to filter it
from LLM-bound client metadata
- Extract forwarded_props in _workflow_run.py and pass via
function_invocation_kwargs to workflow.run()
- Accept both snake_case and camelCase keys (forwarded_props/forwardedProps)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix(ag-ui): pass stream=True as literal to satisfy pyright overload resolution (#5239)
The previous fix passed stream=True via **kwargs dict, which prevented
pyright from resolving the Workflow.run() overload to the streaming
variant. Pass stream=True as an explicit keyword argument so pyright
can correctly infer the ResponseStream return type.
Also remove unused pytest import in test file.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix: address PR review feedback for forwarded_props (#5239)
- Use key-presence checks instead of truthiness for forwarded_props so
empty dict {} is forwarded correctly
- Gate function_invocation_kwargs on workflow.run() signature inspection
to avoid TypeError for workflows without **kwargs
- Change _build_safe_metadata to drop (with warning) keys whose
serialized values exceed 512 chars instead of truncating into invalid
JSON
- Rewrite metadata tests to exercise _build_safe_metadata directly with
JSON-decodability and truncation assertions
- Add workflow tests for empty dict forwarded_props, stream=True
assertion, and signature-gated kwarg dropping
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* test: add stream=True assertions to CapturingWorkflow tests (#5239)
Guard against accidental removal of the explicit stream=True kwarg
in all forwarded_props CapturingWorkflow test cases.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Address review feedback for #5239: Python: Expose forwardedProps to agents and tools via session metadata
---------
Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Add support for the Foundry Toolbox in MAF
Introduces a Foundry Toolbox integration: FoundryChatClient gains a
get_toolbox() helper plus select_toolbox_tools(), normalize_tools in
the core package flattens tool-collection wrappers (ToolboxVersionObject
and generic iterables, while leaving Pydantic BaseModel instances
alone), and the new agent_framework.foundry namespace re-exports the
toolbox helpers. Ships with unit tests, a sample, and a design doc.
azure-ai-projects is pinned to the public >=2.0.0,<3.0 range and the
lockfile resolves from public PyPI. The toolbox test module skips when
Toolbox* types are unavailable so CI stays green until the public 2.1.0
SDK lands. OMC tooling directories (.omc/, .omx/) are gitignored.
* Update to latest azure ai projects package
* Improve sample
* Rename ADR to 0025
* Update ADR
* Apply suggestion from @alliscode
Co-authored-by: Ben Thomas <ben.thomas@microsoft.com>
* Improve samples
* Update test
---------
Co-authored-by: Ben Thomas <ben.thomas@microsoft.com>
* adds devui integration and samples
* adds unit tests for devui integration
* fix: correct formatting of copyright notice in unit test files
* fixes formatting issues
* fixes build for net8 target
* fixes formatting errors on test apphost
* adds copyright notice to multiple files and removes unnecessary using directives
* Update dotnet/aspire-integration/Aspire.Hosting.AgentFramework.DevUI/DevUIAggregatorHostedService.cs
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Update dotnet/aspire-integration/Aspire.Hosting.AgentFramework.DevUI/DevUIAggregatorHostedService.cs
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Update dotnet/tests/Aspire.Hosting.AgentFramework.DevUI.UnitTests/Aspire.Hosting.AgentFramework.DevUI.UnitTests.csproj
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Update dotnet/samples/DevUIIntegration/DevUIIntegration.AppHost/DevUIIntegration.AppHost.csproj
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Update dotnet/aspire-integration/Aspire.Hosting.AgentFramework.DevUI/DevUIAggregatorHostedService.cs
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Refactor project files to use TargetFrameworks instead of TargetFramework for multi-targeting support; add optional port property to DevUIResource class.
* Add unit tests for DevUIAggregatorHostedService; refactor project files for TargetFrameworks support
* Refactor project files to use TargetFrameworks for multi-targeting support in DevUIIntegration samples
* Remove unnecessary using directive for Aspire.Hosting in DevUIAggregatorHostedServiceTests
* merge
* fixes Conversation routing for non-first backends
* add documentation for devui integration sample
* update project references in solution file for improved integration
* fixes package versions post merge
* move Aspire.Hosting.AgentFramework.DevUI to dotnet/src
Move the project from aspire-integration/ to src/ to be consistent
with the location of all other projects in the repo.
* move DevUI sample to samples/05-end-to-end/DevUIAspireIntegration
Move the sample from samples/DevUIIntegration/ to
samples/05-end-to-end/DevUIAspireIntegration/ to match the location
of other end-to-end samples.
* remove unnecessary net472 framework condition from sample csproj files
These projects only target net10.0, so the
Condition="'$(TargetFramework)' != 'net472'" on ItemGroup is unnecessary.
* update sample model name from gpt-4.1 to gpt-5.4
Use a more up-to-date model name in the DevUI integration samples.
* Revert "remove unnecessary net472 framework condition from sample csproj files"
This reverts commit 08cf41253b.
* fix: use TargetFrameworks to override multi-targeting from Directory.Build.props
The parent Directory.Build.props sets TargetFrameworks to net10.0;net472,
which overrides the singular TargetFramework in each csproj. Use the plural
TargetFrameworks property set to net10.0 only to properly override it, and
remove the now-unnecessary net472 condition on ItemGroup.
* fixes aspire config
* fix: update Microsoft.Extensions packages to version 10.0.1
* Address Copilot review feedback on DevUI Aspire integration
- Fix request body dropping in ProxyConversationsAsync: always read the
body when ContentLength > 0 before routing, then pass it through to
all proxy calls (previously null was passed when backend was resolved
from query param or conversation map)
- Fix resource leak: dispose aggregator on startup failure in catch block
- Fix XML docs: accurately describe embedded resource serving behavior
- Remove reflection from DevUIResourceTests (InternalsVisibleTo already set)
- Make sensitive telemetry conditional on Development environment in samples
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix: update chat client version to gpt41 in both EditorAgent and WriterAgent
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Fix CopilotStudioAgent to reuse existing conversation on session (#5285)
CopilotStudioAgent unconditionally called _start_new_conversation() in both
_run_impl and _run_stream_impl, ignoring any existing service_session_id on
the session. Add a guard to only start a new conversation when there is no
existing service_session_id, matching the pattern used by other agents.
Also fix pre-existing pyright reportMissingImports errors for orjson in
file_history_provider samples.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Revert out-of-scope sample file changes
Remove unrelated orjson type-ignore comment changes from sample files
that were outside the scope of the conversation-ID reuse fix.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix: Add session support for Handoff-hosted Agents
In order to better support using `Workflows` hosted as `AIAgents` inside of Handoff workflows, we need to make proper use of AgentSession. This causes potential issues around checkpointing and making sure that we properly compute only the new incoming messages for each agent invocation.
* fix: AgentSession checkpointing using AIAgent's Serialize/Deserialize methods
We cannot rely on implicit serialization through `HandoffHostState` because we are missing type information.
* fix: Thread safety issue in `MultiPartyConversation.AllMessages`
* fix: Enable unwrapping of FunctionResultContent when ExternalRequest was wrapped into FunctionCallContent
* fix: Foundry Agents without description in Handoff
Foundry Agents without a description set will return an empty string (rather than null) for the description. This was breaking the fallback logic for `handoffReason`.
* test: Add unit tests
* Foundry Evals integration for .NET
- Core evaluation framework: EvalItem, LocalEvaluator, FunctionEvaluator, EvalChecks
- IAgentEvaluator interface with MeaiEvaluatorAdapter bridge
- AgentEvaluationExtensions for agent.EvaluateAsync() overloads
- FoundryEvals wrapping MEAI quality/safety evaluators
- ConversationSplitters (LastTurn, Full) and IConversationSplitter
- EvalItem.PerTurnItems() for multi-turn decomposition
- HasImageContent for multimodal content detection
- WorkflowEvaluationExtensions for per-agent workflow evaluation
- 7 eval samples mirroring Python parity:
02-agents/Evaluation: SimpleEval, ExpectedOutputs, Multimodal
03-workflows/Evaluation: WorkflowEval
05-end-to-end/Evaluation: FoundryQuality, MixedProviders, ConversationSplits
- Comprehensive unit tests (1958 passing)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Rewrite FoundryEvals to use real Foundry Evals API
Replace MEAI evaluator shim with actual OpenAI EvaluationClient protocol
methods. FoundryEvals now creates eval definitions, submits runs, polls
for completion, and fetches per-item results server-side.
- New constructor: FoundryEvals(AIProjectClient, model, evaluators)
- Add FoundryEvalConverter for MEAI ChatMessage -> Foundry JSON format
- Add EvalId, RunId, ReportUrl to AgentEvaluationResults
- All 20 built-in evaluator constants now work (agent, tool, quality, safety)
- Remove Microsoft.Extensions.AI.Evaluation.Quality/Safety dependencies
- Update all samples for new constructor (no more ChatConfiguration)
- Replace BuildEvaluators tests with ResolveEvaluator tests
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Add response output to CustomEvals and ExpectedOutputs samples
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Address review: pagination, validation, error handling, tests
FoundryEvals fixes:
- Add pagination for output items (has_more/after cursor)
- Add guard clauses for pollIntervalSeconds/timeoutSeconds <= 0
- Fix double TryGetProperty for passed field parsing
- Throw on all-tool-evaluators with no tool definitions
- Fix XML doc (default 300s, not 180s)
New tests (30 added, 1989 total):
- EvalChecks: NonEmpty, ContainsExpected (pass/fail/skip/case),
HasImageContent, ToolCallsPresent
- FoundryEvalConverter: ConvertMessage (text, image, function call,
function results fan-out, empty fallback, mixed content),
ConvertEvalItem, BuildTestingCriteria (quality/agent/tool/groundedness
data mappings), BuildItemSchema
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Fix review: null-refs, Data.ToString() bug, ContainsExpected, add tests
- Fix NullReferenceException in sample Response display (pattern matching)
- Fix WorkflowEvaluationExtensions Data?.ToString() producing type names
instead of message text (pattern-match ChatMessage/AgentResponse/list)
- Change EvalChecks.ContainsExpected to return Passed=false when no
ExpectedOutput (was silently passing, masking misconfiguration)
- Add EvalItem constructor tests with LastTurn/Full/null splitters
- Add FoundryEvalConverter.ConvertMessage DataContent (base64 image) test
- Add ExtractAgentData tests with ChatMessage, list, and AgentResponse data
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Fix review: conversation fidelity, eval caching, fallback tests
- WorkflowEvaluationExtensions: preserve full response messages (tool calls,
intermediate) instead of synthetic 2-message conversation. Cast completed
Data to AgentResponse and use Messages when available, fallback to text.
- FoundryEvals: cache evalId per schema shape (hasContext, hasTools) so
subsequent EvaluateAsync calls create runs under the same eval definition.
- MeaiEvaluatorAdapter: code already correctly passes queryMessages (not full
conversation) to IEvaluator — no change needed, verified by inspection.
- Add tests: AgentResponse full messages preservation, unknown object
ToString() fallback for ExtractAgentData.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Rename AzureAI→Foundry: move eval files, update references
- Move FoundryEvals.cs and FoundryEvalConverter.cs from
Microsoft.Agents.AI.AzureAI to Microsoft.Agents.AI.Foundry
- Update namespace from AzureAI to Foundry in both files
- Add explicit usings required by Foundry project (no implicit usings)
- Move FoundryEvalConverter tests to Foundry.UnitTests project
(avoids ReplacingRedactor type conflict from dual project refs)
- Update all sample csproj references and using statements
- Remove Foundry project reference from AI UnitTests
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* PR review round 4: wire up tool extraction, remove eval cache, fix null safety
- BuildEvalItem: extract tools from agent via GetService<ChatOptions>() into EvalItem.Tools (Python parity)
- FoundryEvals: remove eval ID cache - each call creates fresh definition (matches Python behavior)
- FoundryEvals: replace null-forgiving operators with descriptive InvalidOperationException
- MixedProviders sample: remove unnecessary explicit PackageReferences (transitively provided)
- FoundryEvalConverter: document that tool results take precedence over text content
- Add LocalEvaluator zero-checks test documenting 0 metrics = failed behavior
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Python-dotnet parity: 9 feature gaps filled
New checks:
- ToolCallArgsMatch() — verify tool call names + argument subset match
- ToolCalledCheck(ToolCalledMode.Any, ...) — match any of the specified tools
- ToolCalledMode enum (All/Any)
FoundryEvals enhancements:
- Default evaluators now [Relevance, Coherence, TaskAdherence] (was Relevance, Coherence)
- Auto-add ToolCallAccuracy when items have tool definitions
- EvaluateTracesAsync — evaluate by response_ids, trace_ids, or agent_id
- EvaluateFoundryTargetAsync — evaluate deployed Foundry targets
Result type enrichment:
- AgentEvaluationResults: added Status, Error, PerEvaluator, DetailedItems
- New EvalItemResult/EvalScoreResult/PerEvaluatorResult types
- FoundryEvals populates all new fields from API responses
Workflow fix:
- Skip internal executors (_*, input-conversation, end-conversation, end)
Tests: 8 new tests covering ToolCallArgsMatch, ToolCalledMode.Any, internal executor filtering
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Add MeaiEvaluatorAdapter and PerTurnItems edge case tests
- 3 tests for MeaiEvaluatorAdapter: query message forwarding, synthetic
response fallback, multiple items aggregation
- 3 tests for EvalItem.PerTurnItems: empty conversation, no user messages,
system+assistant only
- StubEvaluator and StubChatClient test helpers
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Blocking link check for outdated package in DevUI.
* Replace Dictionary<string, object> payloads with typed wire models
Introduce internal FoundryEvalWireModels.cs with compile-time-safe types
for the OpenAI Evals API wire format. The OpenAI .NET SDK (2.9.1) only
provides protocol-level methods with BinaryContent/ClientResult — no
typed request models. These internal models replace scattered dictionary
literals with [JsonPropertyName]-annotated classes, giving:
- Compile-time safety (typos become build errors)
- Single point of change when the API evolves
- IntelliSense discoverability
- Cleaner serialization via JsonPolymorphic for content items
Models: WireContentItem hierarchy (text, image, tool_call, tool_result),
WireMessage, WireEvalItemPayload, WireTestingCriterion, WireItemSchema,
WireCreateEvalRequest, WireCreateRunRequest, and data source variants.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Skip metric when Foundry returns neither score nor passed
When an evaluator returns no score and no passed value, the previous
code created BooleanMetric(name, false), which falsely failed items
via ItemPassed. Now we skip the MEAI metric entirely for indeterminate
results — the raw data remains available in DetailedItems for diagnostics.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Address PR #4914 review comments: fix tool evaluator bug and add tests
- Fix duplicate ToolCallAccuracy: resolve evaluator names before checking
against ToolEvaluators set (Comment 2)
- Make FilterToolEvaluators internal for testability; add tests for the
ArgumentException edge case when all evaluators are tool-type (Comment 3)
- Add CancellationToken test for LocalEvaluator (Comment 4)
- Add EvaluateAsync integration test on Run with sequential workflow and
per-agent SubResults verification (Comment 5)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Address Peter's review comments on PR #4914
- Add trailing newline to Evaluation_FoundryQuality.csproj (Comment 6)
- Make evaluator name lookups case-insensitive: switch BuiltinEvaluators,
ToolEvaluators, AgentEvaluators, and ResolveEvaluator's StartsWith check
from Ordinal to OrdinalIgnoreCase (Comment 7)
- Add Trace.TraceWarning when Foundry returns fewer results than submitted
items, indicating expected vs actual count before padding (Comment 8)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Add Microsoft.Extensions.AI.Evaluation packages to Directory.Packages.props
These were removed in #5269 as unused, but are needed by the Foundry
and core evaluation integration added in this PR.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: alliscode <bentho@microsoft.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* feat: add finish_reason support to AgentResponse and AgentResponseUpdate
Add finish_reason field to AgentResponse and AgentResponseUpdate classes,
propagate it through _process_update() and map_chat_to_agent_update(),
and add comprehensive unit tests.
Fixes#4622
* feat: add finish_reason to AgentResponse and AgentResponseUpdate
* style: add copyright header to test_finish_reason.py
* docs: add finish_reason to AgentResponse and AgentResponseUpdate docstrings
* refactor: move finish_reason tests into test_types.py per review feedback
Move all finish_reason test cases from the separate test_finish_reason.py
file into test_types.py as requested by eavanvalkenburg. Tests are placed
in a new '# region finish_reason' section at the end of the file.
* fix: use model instead of model_id in _process_update
Address PR review feedback from @eavanvalkenburg — ChatResponse and
ChatResponseUpdate both use 'model', not 'model_id'.
* fix: resolve SIM102 lint error in _process_update
Combine nested if statements for AgentResponse finish_reason check
to satisfy ruff SIM102 rule, with line wrapping to stay under 120 chars.
* fix: resolve pyright reportArgumentType in map_chat_to_agent_update
Add type: ignore[arg-type] for FinishReason NewType widening when
passing ChatResponseUpdate.finish_reason to AgentResponseUpdate.
Matches existing patterns in the codebase (40+ similar ignores).
* Fix url_citation annotations dropped in streaming (#5029)
Add url_citation branch to the streaming annotation handler in
_parse_chunk_from_openai, mirroring the existing non-streaming path.
The handler creates an Annotation with type='citation', title, url,
and annotated_regions (TextSpanRegion), wrapped in Content.from_text.
Update test_streaming_annotation_added_with_unknown_type to use a
truly unknown type, and add new tests for url_citation (with and
without url).
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Address review feedback for #5029: Python: [Bug]: url_citation annotations silently dropped in Foundry streaming (SharePoint grounding citations lost)
---------
Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com>
- Update Anthropic from 12.11.0 to 12.13.0
- Update Anthropic.Foundry from 0.4.2 to 0.5.0
- Change Anthropic project from release candidate to preview
- Add new IBetaService members (Agents, Environments, Sessions, Vaults) to test mock
Fixes#5246
When a custom @executor transforms agent output and sends a plain str,
the downstream AgentExecutor.from_str handler loses the full conversation
context. This adds a with_text() helper that creates a new
AgentExecutorResponse with replaced text while preserving the prior
conversation chain, so AgentExecutor.from_response is invoked instead.
- Add with_text(text) method to AgentExecutorResponse dataclass
- Add 3 regression tests in test_full_conversation.py
Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com>
* Improve workflow unit tests
* Update test name prefix for clarity.
* Update tests to surface any errors.
* fix check-point restore-time race in off-thread workflow event stream
* Fixes an intermittent checkpoint-restore race in in-process workflow runs.
The local MCP server can't be used for hosted tools tests because
Anthropic's backend needs to reach the MCP URL from their infrastructure
(not localhost on the CI runner). Revert to learn.microsoft.com/api/mcp
but catch BadRequestError, InternalServerError, APIConnectionError, and
APITimeoutError and pytest.skip so upstream outages don't block the
merge queue.
* Python: use local MCP server for hosted tools test and broaden image assertion
The hosted tools integration test was hitting rate limits on the external
learn.microsoft.com MCP server, causing persistent failures that retries
couldn't recover from. Switch to the local MCP server already spun up in
CI via LOCAL_MCP_URL, skipping when the env var isn't set.
Also broaden the image description assertion to accept common synonyms
(cottage, mansion, villa, etc.) instead of just "house", since the model
legitimately uses varied vocabulary for the same image.
* Address review feedback: validate LOCAL_MCP_URL scheme and use word boundaries
- Skip hosted tools test when LOCAL_MCP_URL lacks http/https scheme,
matching the pattern used in test_mcp.py.
- Use regex word boundaries for image assertion to avoid false matches
like "villain" matching "villa".
The misc-integration job (Anthropic, Ollama, MCP) frequently fails on merge to main when the upstream MCP server (e.g. learn.microsoft.com/api/mcp) returns a transient rate-limit error. The previous 5s retry delay is too short to ride out the upstream backoff window, so all retries fail and the merge queue is blocked. Bumping to 30s gives the upstream a chance to recover before pytest-retry re-runs the test.
* Add agent-framework-gemini package
* Add AGENTS.md documentation
* Add LICENSE file
* Add README.md for agent-framework-gemini package
* Add Google Gemini API keys to .env.example
* Add Google Gemini chat client implementation
* Add tests for GeminiChatClient
* Add Google Gemini agent examples
* Fix client inheritence order
* Update Gemini agent examples
* Update documentation
* Update AGENTS.md
* Add tests for JSON string handling in GeminiChatClient
* Add final response assembly test in GeminiChatClient
* Add tests for handling empty candidates in GeminiChatClient
* Improve Pydantic response handling in GeminiChatClient
* Add tests for function result resolution and callable tool normalization
* Add test for function result resolution when call_id is generated
* Refactor GeminiChatClient to correct inheritance order
Also updates constructor parameter order for environment file handling
* Enhance documentation and clarify Gemini-specific fields
* Update ThinkingConfig with new attributes and type
* Add tests for GoogleSearch and GoogleMaps configs
* Suppress valid-type mypy error on GeminiChatOptionsT
* Move service_url method near overrides
* Order _prepare_config kwargs by base then Gemini-specific
* Use FunctionCallingConfigMode for clarity and type safety
* Fix code_execution doc
* Add agent-framework-gemini to project dependencies
* Remove package from core dependencies
Initial release will be done without agent-framework-gemini in
core[all].
* Move integration tests into one file
* Remove __init__.py file from gemini tests directory
* Introduce RawGeminiChatClient as lightweight chat client
Updated GeminiChatClient to inherit from RawGeminiChatClient, maintaining full functionality with added features.
* Updated variable names from `model_id` to `model`
Across the codebase, including environment variables and client initialization. Adjusted related tests and sample scripts to reflect this change, ensuring consistency in the usage of the Gemini model identifier.
* Update AGENTS.md
* Update Gemini package to alpha status
* Fix docstrings in Gemini tests
* Change 'model_id' to 'model' in response handling
* Fix model property change in response handling
* Add built-in tool factory methods to Gemini client
Replaces boolean tool options (code_execution, google_search_grounding,
google_maps_grounding) with static factory methods that return types.Tool
objects: get_code_interpreter_tool, get_web_search_tool, get_mcp_tool,
get_file_search_tool, and get_maps_grounding_tool.
Simplifies _prepare_tools to a single translation boundary between
FunctionTool (framework) and FunctionDeclaration (Gemini API), with
types.Tool objects passed through unchanged.
* Surface code execution parts
_parse_parts now maps executable_code and code_execution_result
parts to text Content objects so callers can see the code run
and its output. Unknown part types log at debug level rather than
being silently dropped.
* Update Gemini client documentation
* Unify Gemini model name
Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com>
* Update Agent Framework core version
Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com>
* Add Python 3.14 in classifiers
* Replace kwargs with parameters in tool factories
* Refactor chat options handling in Gemini client
* Add tests for handling unknown and consumed keys
* Update Gemini documentation
Now reflects new options and built-in tool factory methods
* Change build system to flit
Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com>
* Fix build system in pyproject.toml
* Fix type checking for generate_content_stream
---------
Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com>
* Python: Skip get_final_response in OTel _finalize_stream when stream errored
When a streaming error occurs, _finalize_stream (a cleanup hook registered by
AgentTelemetryLayer) was unconditionally calling get_final_response(), which
triggers all registered result hooks including after_run context providers.
This caused providers to fire incorrectly on error paths.
Guard against this by checking result_stream._consumed: True only after
StopAsyncIteration (normal completion), False when an exception was raised.
The fix applies to both the chat client and agent telemetry layers.
Closes#5231
* Python: Expose consumed/stream_error on ResponseStream and capture error in OTel span
Address Copilot review feedback on #5232:
- Add `_stream_error: Exception | None` to ResponseStream, set in __anext__'s
except branch so cleanup hooks can inspect the failure.
- Expose public `consumed` and `stream_error` properties to avoid coupling
observability.py to private stream internals.
- Update both _finalize_stream closures (chat and agent layers) to use the
public properties and call capture_exception() with the stream error before
returning early, ensuring the OTel span records the failure rather than
closing silently.
* Python: Address Copilot review feedback on stream error handling
- Use stream_error is not None as the guard in _finalize_stream instead of
not consumed, so the early-return path is keyed precisely to actual errors
rather than any non-normal completion state.
- Clear _stream_error after _run_cleanup_hooks() completes to avoid retaining
the exception traceback (and any large object graphs it references) on the
stream instance beyond the cleanup phase.
* Python: Remove consumed/stream_error properties, use private attrs directly
Per review feedback: since observability.py and _types.py are in the same
package, accessing _stream_error directly is fine and the public properties
are unnecessary.
* Python: Fix Pyright reportPrivateUsage via inline ignore comments
Keep _stream_error private (consistent with rest of ResponseStream), and
suppress reportPrivateUsage at the call sites in observability.py with
inline pyright: ignore comments — access is intentional within the package.
Evan Mattson ·
S3rj ·
Roger Barreto ·
chetantoshniwal ·
Jacob Alber ·
Peter Ibekwe ·
Tao Chen ·
Eduard van Valkenburg ·
Tommaso Stocchi ·
Giles Odigwe ·
Copilot ·
Ben Thomas ·
L. Elaine Dazzio ·
Kartik Madan ·
westey ·
Chinedum Echeta ·
Björn Holtvogt ·
Dineshsuriya D ·