mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
Roger Barreto
aad20c2b33
* .NET: Bump Azure.AI.Projects to 2.1.0-beta.2 and add agent-endpoint AsAIAgent path
Bumps Azure.AI.Projects to 2.1.0-beta.2 with the matching transitive pins (Azure.Core 1.55.0, System.ClientModel 1.11.0).
Foundry agent endpoint plumbing:
* FoundryAgent now routes the agent-endpoint constructor through the new GetProjectResponsesClientForAgentEndpoint helper.
* Adds an internal FoundryAgent ctor that takes an existing AIProjectClient plus a parsed agent endpoint so the public extension does not need to construct a second project client.
* Adds public AIProjectClient.AsAIAgent(Uri agentEndpoint, ...) extension. This is the path consumer samples are expected to use for hosted agents because version selection happens server-side.
* Trims the dangling "If you want to construct a FoundryAgent against a project endpoint..." sentence from ParseAgentEndpoint.
Unit tests:
* Four new tests in AzureAIProjectChatClientExtensionsTests cover the AIProjectClient.AsAIAgent(Uri agentEndpoint, ...) overload. 263/263 pass.
Consumer samples (Using-Samples):
* SimpleAgent and SessionFilesClient now read AZURE_AI_PROJECT_ENDPOINT and AZURE_AI_AGENT_NAME (both required, throw on missing), derive the agent endpoint with new Uri($"{projectEndpoint}/agents/{agentName}/endpoint/protocols/openai"), then call aiProjectClient.AsAIAgent(agentEndpoint, ...).
* SessionFilesClient README updated.
Contributor samples (responses/*):
* New HostedContributorRouteExtensions.MapDevTemporaryLocalAgentEndpoint() wildcard route extension so localhost contributor servers accept the per-agent OpenAI endpoint shape the production Hosted runtime exposes.
* All 11 contributor Program.cs files call MapDevTemporaryLocalAgentEndpoint() with a contributor-only warning comment.
* Hosted-Files and Hosted-AzureSearchRag were importing Hosted_Shared_Contributor_Setup but never calling AddDevTemporaryLocalContributorSetup(). Both now call it so HostedSessionIsolationKeyProvider resolves correctly in dev.
* Hosted-AzureSearchRag, Hosted-Files, Hosted-MemoryAgent csprojs drop stale VersionOverride="2.1.0-beta.1" pins.
* Hosted-AzureSearchRag and Hosted-Files csprojs add ProjectReference to Hosted_Shared_Contributor_Setup.
* Hosted-Observability/.dockerignore removed the out/ exclusion that was blocking COPY out/ . in Dockerfile.contributor.
Verified:
* Full solution-scoped build of changed projects: green.
* Scoped CI-parity dotnet format via WSL2 + Docker (mcr.microsoft.com/dotnet/sdk:10.0) over every changed csproj: clean.
* Foundry unit tests: 263/263.
* Contributor docker smoke for 8 hosted samples (publish + docker build + docker run + curl POST to the wildcard route): HTTP 200 / 500 with route matched.
* End-to-end smoke against the real Azure Foundry project with a fresh bearer token: Hosted-Files contributor container served HTTP 200, the agent invoked ListBundledFiles, and returned the expected file name.
* Address PR review: forward pipeline settings; add UTs
- CreateProjectClientOptions also carries RetryPolicy, NetworkTimeout, ClientLoggingOptions, MessageLoggingPolicy (was Transport+UserAgentApplicationId only).
- Make CreateProjectClientOptions internal so tests can verify the copy directly.
- Add AsAIAgent(Uri) UTs covering tools forwarding to inner ChatOptions and null tools handling.
- Add CreateProjectClientOptions UTs covering null caller and full pipeline-settings copy.
aad20c2b33
·
2026-05-18 20:20:56 +00:00
History
Hosted-McpTools
A hosted agent demonstrating two layers of MCP (Model Context Protocol) tool integration:
-
Client-side MCP (Microsoft Learn) — The agent connects directly to the Microsoft Learn MCP server via
McpClient, discovers tools, and handles tool invocations locally within the agent process. -
Server-side MCP (Microsoft Learn) — The agent declares a
HostedMcpServerToolwhich delegates tool discovery and invocation to the LLM provider (Azure OpenAI Responses API). The provider calls the MCP server on behalf of the agent with no local connection needed.
How the two MCP patterns differ
| Client-side MCP | Server-side MCP | |
|---|---|---|
| Connection | Agent connects to MCP server directly | LLM provider connects to MCP server |
| Tool invocation | Handled by the agent process | Handled by the Responses API |
| Auth | Agent manages credentials | Provider manages credentials |
| Use case | Custom/private MCP servers, fine-grained control | Public MCP servers, simpler setup |
| Example | Microsoft Learn (McpClient + HttpClientTransport) |
Microsoft Learn (HostedMcpServerTool) |
Prerequisites
- .NET 10 SDK
- An Azure AI Foundry project with a deployed model (e.g.,
gpt-4o) - Azure CLI logged in (
az login)
Configuration
Copy the template and fill in your values:
cp .env.example .env
Edit .env:
AZURE_AI_PROJECT_ENDPOINT=https://<your-account>.services.ai.azure.com/api/projects/<your-project>
AZURE_AI_MODEL_DEPLOYMENT_NAME=gpt-4o
Running directly (contributors)
cd dotnet/samples/04-hosting/FoundryHostedAgents/responses/Hosted-McpTools
dotnet run
Test it
Using the Azure Developer CLI:
# Uses GitHub MCP (client-side)
azd ai agent invoke --local "Search for the agent-framework repository on GitHub"
# Uses Microsoft Learn MCP (server-side)
azd ai agent invoke --local "How do I create an Azure storage account using az cli?"
Running with Docker
1. Publish for the container runtime
dotnet publish -c Debug -f net10.0 -r linux-musl-x64 --self-contained false -o out
2. Build and run
docker build -f Dockerfile.contributor -t hosted-mcp-tools .
export AZURE_BEARER_TOKEN=$(az account get-access-token --resource https://ai.azure.com --query accessToken -o tsv)
docker run --rm -p 8088:8088 \
-e AGENT_NAME=mcp-tools \
-e AZURE_BEARER_TOKEN=$AZURE_BEARER_TOKEN \
--env-file .env \
hosted-mcp-tools
NuGet package users
Use the standard Dockerfile instead of Dockerfile.contributor. See the commented section in HostedMcpTools.csproj for the PackageReference alternative.