Files
agent-framework/dotnet/src/Microsoft.Agents.AI.AzureAI/AzureAIProjectChatClientExtensions.cs
T
f45fc7d402 .NET: [Breaking] Update Foundry Agents for Responses API (#4502)
* Stage

* Add FoundryAgentClient, model param, chatClientFactory, and RAPI samples

- Add model parameter to FoundryAgentClient simple constructor
- Add chatClientFactory parameter to both constructors
- Switch to OpenAI.GetProjectResponsesClientForModel for direct Responses API usage
- Add FoundryAgents-RAPI samples (Step01 Basics, Step02 Multiturn, Step03 FunctionTools)
- Add solution folder entry for FoundryAgents-RAPI samples

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

* Add auto-discovery constructor and simplify RAPI samples

- Add FoundryAgentClient constructor that reads AZURE_AI_PROJECT_ENDPOINT and
  AZURE_AI_MODEL_DEPLOYMENT_NAME from environment variables with DefaultAzureCredential
- Simplify RAPI samples to use auto-discovery (no env var or credential code)
- Remove Azure.Identity direct references from sample csproj files
- Update READMEs to document environment variable requirements

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

* Add remaining RAPI samples (Step04-Step12)

- Step04: Function tools with human-in-the-loop approvals
- Step05: Structured output with typed responses
- Step06: Persisted conversations with session serialization
- Step07: Observability with OpenTelemetry
- Step08: Dependency injection with hosted service
- Step10: Image multi-modality
- Step11: Agent as function tool (agent composition)
- Step12: Middleware (PII, guardrails, function logging, HITL approval)
- Update solution file and folder README with all new samples

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

* Add all RAPI samples (Step09-Step23) and switch to AzureCliCredential

- Step09: MCP client as tools (GitHub server via stdio)
- Step13: Plugins with dependency injection
- Step14: Code Interpreter tool
- Step15: Computer Use tool with screenshot simulation
- Step16: File Search with vector stores
- Step17: OpenAPI tools (REST Countries API)
- Step18: Bing Custom Search
- Step19: SharePoint grounding
- Step20: Microsoft Fabric
- Step21: Web Search with citations
- Step22: Memory Search with multi-turn conversations
- Step23: Local MCP via HTTP (Microsoft Learn)
- Switch all samples (Step04-Step12) to use AzureCliCredential with env vars
- Update solution file and README with all 23 samples
- All 23 samples build successfully, tested Step05/06/11/13/21

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

* Switch Step01-03 samples to AzureCliCredential for consistency

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

* Clarify connection ID format in SharePoint and Fabric READMEs

Document that SHAREPOINT_PROJECT_CONNECTION_ID and FABRIC_PROJECT_CONNECTION_ID
should use the connection name (e.g., 'SharepointTestTool'), not the full ARM
resource URI.

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

* Normalize env vars, fix structured output, update READMEs with connection ID formats

- Normalize AZURE_FOUNDRY_PROJECT_* env vars to AZURE_AI_PROJECT_ENDPOINT / AZURE_AI_MODEL_DEPLOYMENT_NAME across all samples (Steps 18-22 READMEs + Steps 19-20 Program.cs)
- Fix RAPI Step05 StructuredOutput to use full constructor with ResponseFormat for streaming JSON
- Update Deep Research sample to use AzureCliCredential
- Enrich Bing Grounding README with full ARM resource URI format
- Fix Bing Custom Search README env var mismatch (BING_CUSTOM_SEARCH_* -> AZURE_AI_CUSTOM_SEARCH_*)
- Add finding instructions for connection ID and instance name in Bing Custom Search READMEs

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

* Refactor memory samples and switch to DefaultAzureCredential

- Refactor RAPI Step22 MemorySearch: extract store setup to EnsureMemoryStoreAsync local function
- Refactor non-RAPI Step22 MemorySearch: same pattern with explicit memory lifecycle
- Set UpdateDelay=0 on MemoryUpdateOptions and MemorySearchPreviewTool for faster ingestion
- Use WaitForMemoriesUpdateAsync with 500ms polling interval
- Switch Step19 SharePoint, Step20 Fabric, Step22 MemorySearch (both) to DefaultAzureCredential
- Remove SearchOptions from MemorySearchPreviewTool (causes unknown parameter error)

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

* Switch all RAPI samples to DefaultAzureCredential and format

- Replace AzureCliCredential with DefaultAzureCredential across all 20 RAPI samples
- Run dotnet format on all RAPI and non-RAPI Foundry samples
- AzureAI unit tests: 341 passed (net10.0 + net472)

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

* Rename to Microsoft Foundry, add metadata, rename RAPI folder

- Replace 'Azure AI Foundry' / 'Azure Foundry' with 'Microsoft Foundry' in all docs, comments, and XML docs
- Update FoundryAgentClient metadata provider name to 'microsoft.foundry'
- Rename FoundryAgents-RAPI folder to FoundryResponseAgents
- Rewrite FoundryResponseAgents README with comparison table vs Foundry Agents
- Update slnx and parent README with new folder references

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

* Address PR review: simplify sample comments and fix DeepResearch credential

- Remove 'no server-side agent' and 'Responses API directly' phrasing from comments
- Simplify to 'Create a FoundryAgentClient' per review feedback
- Switch Agent_Step15_DeepResearch to DefaultAzureCredential

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

* Restore full DefaultAzureCredential warning comment in DeepResearch sample

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

* Add ADR 0020: Foundry agent type naming convention

Proposes naming options for a new MAF type wrapping versioned
Foundry agents (Prompt, ContainerApp, Hosted, Workflow) to
distinguish from the existing FoundryResponsesAgent (RAPI path).

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

* Simplify FoundryResponsesAgent samples with env-var constructors and rename folders

- Add env-var constructors to FoundryResponsesAgent (simple + options-based)
- Fix Constructor 1 model optionality (no longer throws on missing AZURE_AI_MODEL_DEPLOYMENT_NAME)
- Add ApplyModelDeploymentFallback helper for options-based constructor
- Update all 23 FoundryResponseAgents samples to remove Environment.GetEnvironmentVariable boilerplate
- Condense 6 simple samples to one-liner constructor calls
- Add XML doc remarks about auto-resolved parameters on all constructors
- Rename FoundryAgents -> FoundryVersionedAgents (server-side, versioned)
- Rename FoundryResponseAgents -> FoundryAgents (now the default path forward)
- Update .slnx and README cross-references for new folder names

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

* Add FoundryAITool factory, rename RAPI folders, and clean up references

- Create FoundryAITool static factory class with 17 methods wrapping AgentTool.Create* and ResponseTool.Create* into AITool returns
- Rename 23 FoundryAgentsRAPI_* subfolders to FoundryAgents_* (drop RAPI prefix)
- Rename .csproj files and update .slnx references accordingly
- Update 12 samples (6 FoundryAgents + 6 FoundryVersionedAgents) to use FoundryAITool
- Replace all FoundryResponsesAgent references with FoundryAgent in comments and READMEs
- Update sample READMEs to reference FoundryAITool methods

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

* Rename FoundryVersionedAgents subfolders from FoundryAgents_* to FoundryVersionedAgents_*

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

* Add FoundryVersionedAgent class and refactor extension method internals

- Create FoundryVersionedAgent with private ctor and async static factory methods
  (CreateAIAgentAsync/GetAIAgentAsync) with env-var and explicit endpoint tiers
- Extract shared internal helpers from AzureAIProjectChatClientExtensions:
  CreateChatClientAgent, CreateAgentVersionFromOptionsAsync,
  CreateAgentVersionWithProtocolAsync (tools overload),
  CreateChatClientAgentOptions, GetAgentRecordByNameAsync, ThrowIfInvalidAgentName
- Extension methods now delegate to shared internal helpers
- All 49 existing samples continue to build successfully

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

* Add CreateConversationSessionAsync, DeleteAIAgentAsync, auto-resolve model, simplify samples

- Add CreateConversationSessionAsync to FoundryAgent and FoundryVersionedAgent
  (returns ChatClientAgentSession, creates server-side conversation + session in one call)
- Add DeleteAIAgentAsync static method to FoundryVersionedAgent
- Make model parameter optional in env-var factory overloads (auto-resolves from
  AZURE_AI_MODEL_DEPLOYMENT_NAME)
- Update all FoundryVersionedAgents samples to use DeleteAIAgentAsync
- Remove deploymentName env var from samples where only used for model parameter
- Use CreateConversationSessionAsync in Step02_MultiturnConversation
- Use explicit types instead of var for agent/session variables
- All 49 samples build successfully

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

* Remove manual AIProjectClient construction from FoundryVersionedAgents samples

- Replace manual AIProjectClient construction with GetService<AIProjectClient>()
  from the FoundryVersionedAgent in all dual-option and tool-specific samples
- Remove AZURE_AI_PROJECT_ENDPOINT env var reads from updated samples
- Remove Azure.Identity usings where no longer needed
- Only Step01.1, Step01.2, Eval_Step01 retain manual construction (pedagogical samples)
- All 49 samples build successfully

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

* Replace aiProjectClient extension calls with FoundryVersionedAgent factories in all samples

- Replace aiProjectClient.CreateAIAgentAsync with FoundryVersionedAgent.CreateAIAgentAsync
  in Option 2 (Native SDK) paths across Steps 14-21
- Replace aiProjectClient.Agents.DeleteAgentAsync with FoundryVersionedAgent.DeleteAIAgentAsync
- Remove unused AIProjectClient variables and using directives
- Only Step01.1, Step01.2, Eval_Step01 retain direct AIProjectClient usage (pedagogical)
- Step16, Step22 use GetService<AIProjectClient>() for file/memory operations

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

* Remove unused using directives from Step01.2, Step09, Eval_Step02

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

* Update ADR 0020 with accepted decision: Option 6

- Add Option 6 detailing FoundryAgent, FoundryVersionedAgent, FoundryAITool,
  env-var auto-discovery, and self-contained factory patterns
- Mark decision as accepted with rationale
- Update current state and metadata sections

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

* Update Step01 basics samples to use FoundryVersionedAgent factories

- Step01.1: Replace manual AIProjectClient/AsAIAgent with FoundryVersionedAgent.CreateAIAgentAsync/GetAIAgentAsync/DeleteAIAgentAsync
- Step01.2: Replace manual AIProjectClient with FoundryVersionedAgent.CreateAIAgentAsync/DeleteAIAgentAsync
- Remove env var boilerplate and Azure.Identity dependency

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

* Add DeleteAIAgentVersionAsync to FoundryVersionedAgent

- DeleteAIAgentAsync: deletes the agent and all its versions (existing)
- DeleteAIAgentVersionAsync: deletes only the specific version associated with the agent instance
- Internally delegates to Agents.DeleteAgentAsync vs Agents.DeleteAgentVersionAsync

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

* Fix cleanup comments: DeleteAIAgentAsync deletes the agent and all its versions

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

* Update all FoundryVersionedAgents READMEs for FoundryVersionedAgent and auto-discovery

- Rewrite main README with FoundryVersionedAgent usage, auto-discovery table, code example
- Fix sample table links from FoundryAgents_Step* to FoundryVersionedAgents_Step*
- Add FoundryAITool references in tool-specific sample descriptions
- Update individual READMEs: fix stale paths, add auto-discovery note after env var blocks
- Update tool references: AgentTool/ResponseTool -> FoundryAITool
- Update parent 02-agents/README.md with FoundryVersionedAgent description

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

* Revert unrelated AGUI and Hosting.OpenAI formatting changes to main

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

* Remove env-var auto-discovery, add AsAIAgent, mark extensions Obsolete

- Remove 2 env-var constructors from FoundryAgent (keep explicit endpoint ctors)
- Remove 5 env-var factory methods from FoundryVersionedAgent (keep explicit ones)
- Add 3 AsAIAgent static methods to FoundryVersionedAgent (AgentVersion/AgentRecord/AgentReference)
- Mark all 8 AIProjectClient extension methods as [Obsolete] pointing to FoundryVersionedAgent
- Remove ApplyModelDeploymentFallback, env var constants, Azure.Identity usings from source

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

* Update all samples to use explicit endpoint, credential, and model parameters

- Add explicit Environment.GetEnvironmentVariable reads for AZURE_AI_PROJECT_ENDPOINT
  and AZURE_AI_MODEL_DEPLOYMENT_NAME to all 48 sample files
- Pass new Uri(endpoint), new DefaultAzureCredential(), deploymentName to
  FoundryAgent constructors and FoundryVersionedAgent factory methods
- Add using Azure.Identity where missing
- Matches repo-wide pattern used by other non-Foundry samples
- All 49 samples build successfully

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

* Migrate remaining samples and source from obsoleted extension methods

- Migrate AgentProviders, AgentWithRAG, AgentWithMemory, HostedWorkflow samples to FoundryVersionedAgent
- Migrate AzureAgentProvider.cs to FoundryVersionedAgent.AsAIAgent
- Migrate AzureAIProjectChatClientTests.cs to FoundryVersionedAgent.GetAIAgentAsync
- Remove pragma suppressions from migrated files

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

* Add unit tests for FoundryAgent and FoundryVersionedAgent

- FoundryAgentTests.cs: 14 tests covering constructors, validation,
  properties, metadata, GetService, chat client factory, user-agent header
- FoundryVersionedAgentTests.cs: 31 tests covering CreateAIAgentAsync,
  GetAIAgentAsync, AsAIAgent (3 overloads), DeleteAIAgentAsync,
  DeleteAIAgentVersionAsync, validation, invalid names, metadata, GetService

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

* Finalize Foundry agent migration

Align FoundryAgent and FoundryVersionedAgent samples, docs, and tests with the explicit configuration model, clean up stale README guidance, and fix AzureAI unit test validation/build issues.

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

* Apply formatter cleanup after validation

Capture the dotnet format follow-up changes produced during branch validation so the committed state matches the successfully built and tested branch.

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

* Add integration tests for FoundryAgent and FoundryVersionedAgent

Mark old AIProjectClient extension-method integration tests as obsolete and add new integration test suites for both FoundryAgent (Responses API) and FoundryVersionedAgent (versioned agents). All 71 non-skipped tests pass against the live Foundry service.

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

* Update ADR 0020 with test coverage details

Add integration test coverage note to the Current State section of ADR 0020.

* Simplify Foundry agents and validate moved samples

* Rename FoundryAgent integration tests to ResponsesAgent

The test classes exercise the non-versioned Responses path via
AIProjectClient.AsAIAgent(), not the removed FoundryAgent wrapper type.
Rename files and class names to reflect the actual test surface.

* Update documentation for ChatClientAgent usage

Added example usage of ChatClientAgent with JokerAgent.

* Refactor ChatClientAgent instantiation for clarity

* Revise agent type naming and usage examples

Updated documentation to reflect changes in agent creation methods and added examples for using `ChatClientAgent`.

* Fix Azure SDK namespace migration after rebase

Update Azure.AI.Projects.OpenAI references to Azure.AI.Projects.Agents
and Azure.AI.Extensions.OpenAI to match Azure.AI.Projects 2.0.0-beta.2.

- Replace deprecated namespace across samples, tests, and src
- Fix renamed types: OpenAPIFunctionDefinition -> OpenApiFunctionDefinition,
  BingCustomSearchToolParameters -> BingCustomSearchToolOptions,
  BrowserAutomationToolParameters -> BrowserAutomationToolOptions
- Fix API changes: AgentRecord.Versions -> GetLatestVersion(),
  ResponsesClient constructor, FunctionApprovalRequestContent ->
  ToolApprovalRequestContent
- Apply dotnet format

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

* Address merge markers

* Replace obsolete GetAIAgentAsync with AsAIAgent in samples

Switch Agent_Step07_AsMcpTool and A2AServer to use the non-obsolete
PersistentAgentsClient.AsAIAgent(PersistentAgent) extension instead
of the deprecated GetAIAgentAsync, fixing CS0618 build errors.

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

* Fix broken markdown links in Responses sample READMEs

Replace stale ChatClientAgents_Step* folder references with the
correct Agent_Step* names across all Responses sample READMEs.

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

* Fix format errors and address PR review comments

- Fix charset and remove unused using in AzureAIProjectResponsesChatClient
- Fix doc comment tags (code -> c) in FoundryAITool
- Fix stray period in LocalMCP sample comment
- Fix grammar in FoundryMemoryProvider xmldoc
- Fix AIProjectClientAgentRunStreamingConversationTests base class

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

* Apply dotnet format fixes to PR-changed files

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

* Fix build errors from format pass and apply naming conventions

- Fix static call to CreateSessionAsync in Step02 samples and extension tests
- Use expression-bodied lambda in FoundryMemoryProvider (RCS1021)
- Apply PascalCase naming to const fields in ResponsesAgentExtensionCreateTests (IDE1006)

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

* Introduce FoundryAgent sealed type and update AsAIAgent extensions

- Add FoundryAgent sealed class wrapping ChatClientAgent with:
  - Public ctors: (projectEndpoint, credential, model, instructions) and (agentEndpoint, credential)
  - Internal ctor: (AIProjectClient, ChatClientAgent) for extension use
  - CreateConversationSessionAsync() for server-side conversations
  - GetService<ChatClientAgent>() and GetService<AIProjectClient>()
  - MEAI user-agent policy on internally-created AIProjectClient
- Change all AsAIAgent extension return types from ChatClientAgent to FoundryAgent
- Update all samples and tests to use FoundryAgent type
- Add 16 FoundryAgentTests covering ctors, GetService, UserAgent, RunAsync
- Fix pre-existing Agent_Step12_Plugins build error

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

* Collapse sample folders and add FoundryAgent_Step01 sample

- Move all Responses/* samples up to AgentsWithFoundry/ (flat structure)
- Remove entire Versioned/ folder (26 samples)
- Add FoundryAgent_Step01 sample showing direct FoundryAgent ctor usage
- Update slnx to reflect flat folder structure
- Fix csproj ProjectReference paths for new depth

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

* Update READMEs for flat AgentsWithFoundry structure

- Rewrite AgentsWithFoundry/README.md with FoundryAgent quick start
- Fix cd commands and paths in 11 sample READMEs
- Update 02-agents/README.md to single Foundry link
- Update AGENTS.md tree to flat structure
- Fix AgentWithMemory cross-reference

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

* Fix FoundryAgent_Step01 sample with full create/run/delete lifecycle

Show the complete server-side agent lifecycle: create version with
native SDK, wrap as FoundryAgent via AsAIAgent, run, then delete.

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

* Revert RAPI samples to use AIAgent instead of FoundryAgent

RAPI samples should not reference FoundryAgent directly. Restored
original sample code with only ChatClientAgent -> AIAgent type change
to accommodate the AsAIAgent return type.

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

* Convert versioned-pattern samples to pure RAPI

Step09, Step13, Step17, Step22 were using CreateAgentVersionAsync +
PromptAgentDefinition which is the versioned pattern. Converted to
use AsAIAgent(model, instructions, tools) which is the RAPI path.

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

* Fix format issues from Docker CI check

- FoundryAgent_Step01: CRLF -> LF
- Agent_Step09: missing final newline
- Agent_Step11_Middleware: add internal modifier, final newline
- Agent_Step02: remove redundant cast (IDE0004)
- Agent_Step08: simplify name (IDE0001)
- FoundryAgentTests: s_ prefix, Async suffix naming conventions

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

* Switch Step09 MCP sample to Microsoft Learn HTTP endpoint

Replace npx stdio GitHub MCP server with the public Microsoft Learn
MCP endpoint (https://learn.microsoft.com/api/mcp) using HTTP transport.
No external tooling required to run.

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

* Fix missing final newline in Step09 MCP sample

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

* Address PR review: use DelegatingAIAgent, clean up Step01 sample

- FoundryAgent now inherits DelegatingAIAgent instead of AIAgent,
  removing manual delegation boilerplate (westey-m feedback)
- Simplified Agent_Step01_Basics to single agent creation path,
  moved composable IChatClient approach to README (westey-m feedback)
- Fixed FoundryAgentTests param name assertion

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

* Update sample using Project specialized type instead

* Address PR review feedback: DefaultAzureCredential warnings, sample simplifications, format fixes

- Add DefaultAzureCredential production warning comments to ~25 samples
- Simplify Anthropic and OpenAI Step01 samples to single agent
- Convert Step11 Middleware regex patterns to [GeneratedRegex]
- Remove unnecessary cleanup comment from Step06
- Fix Step09 README MCP transport description
- Enhance FoundryAgent xmldoc with non-persistent agent comparison

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

* Split Step02, simplify RAG Step04, sharpen Step23 differentiation

- Split Step02 into 02.1 (simple multi-turn via sessions) and 02.2 (server-side conversations via CreateConversationSessionAsync)
- RAG Step04: replace HostedFileSearchTool + MEAI wrapping with native OpenAI FileSearchTool
- Step23: clarify DelegatingAIFunction wrapping pattern vs Step09 basic MCP

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

* Fix Hosted MCP sample: use ResponseTool.CreateMcpTool and move tool to PromptAgentDefinition

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

* Fix broken README link after Step02 split

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

* Address Sergey round 3 feedback: branding, README nav, sample rename

- Replace 'Azure AI Foundry' with 'Microsoft Foundry' in ADR 0020
- Fix 3 READMEs: 'ChatClientAgents' → 'AgentsWithFoundry' sample directory
- Rename FoundryAgent_Step01 → Agent_Step00_FoundryAgentLifecycle for naming consistency

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

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-30 12:09:02 +00:00

936 lines
50 KiB
C#

// Copyright (c) Microsoft. All rights reserved.
using System.ClientModel;
using System.ClientModel.Primitives;
using System.Diagnostics.CodeAnalysis;
using System.Runtime.CompilerServices;
using System.Text;
using System.Text.Json;
using System.Text.Json.Nodes;
using System.Text.Json.Serialization;
using System.Text.RegularExpressions;
using Azure.AI.Extensions.OpenAI;
using Azure.AI.Projects.Agents;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.AzureAI;
using Microsoft.Extensions.AI;
using Microsoft.Extensions.Logging;
using Microsoft.Shared.DiagnosticIds;
using Microsoft.Shared.Diagnostics;
using OpenAI;
using OpenAI.Responses;
namespace Azure.AI.Projects;
/// <summary>
/// Provides extension methods for <see cref="AIProjectClient"/>.
/// </summary>
[Experimental(DiagnosticIds.Experiments.AIOpenAIResponses)]
public static partial class AzureAIProjectChatClientExtensions
{
/// <summary>
/// Uses an existing server side agent, wrapped as a <see cref="ChatClientAgent"/> using the provided <see cref="AIProjectClient"/> and <see cref="AgentReference"/>.
/// </summary>
/// <param name="aiProjectClient">The <see cref="AIProjectClient"/> to create the <see cref="ChatClientAgent"/> with. Cannot be <see langword="null"/>.</param>
/// <param name="agentReference">The <see cref="AgentReference"/> representing the name and version of the server side agent to create a <see cref="ChatClientAgent"/> for. Cannot be <see langword="null"/>.</param>
/// <param name="tools">The tools to use when interacting with the agent. This is required when using prompt agent definitions with tools.</param>
/// <param name="clientFactory">Provides a way to customize the creation of the underlying <see cref="IChatClient"/> used by the agent.</param>
/// <param name="services">An optional <see cref="IServiceProvider"/> to use for resolving services required by the <see cref="AIFunction"/> instances being invoked.</param>
/// <returns>A <see cref="ChatClientAgent"/> instance that can be used to perform operations based on the latest version of the named Azure AI Agent.</returns>
/// <exception cref="ArgumentNullException">Thrown when <paramref name="aiProjectClient"/> or <paramref name="agentReference"/> is <see langword="null"/>.</exception>
/// <exception cref="InvalidOperationException">The agent with the specified name was not found.</exception>
/// <remarks>
/// When instantiating a <see cref="ChatClientAgent"/> by using an <see cref="AgentReference"/>, minimal information will be available about the agent in the instance level, and any logic that relies
/// on <see cref="AIAgent.GetService{TService}(object?)"/> to retrieve information about the agent like <see cref="AgentVersion" /> will receive <see langword="null"/> as the result.
/// </remarks>
public static FoundryAgent AsAIAgent(
this AIProjectClient aiProjectClient,
AgentReference agentReference,
IList<AITool>? tools = null,
Func<IChatClient, IChatClient>? clientFactory = null,
IServiceProvider? services = null)
{
Throw.IfNull(aiProjectClient);
Throw.IfNull(agentReference);
ThrowIfInvalidAgentName(agentReference.Name);
var innerAgent = AsChatClientAgent(
aiProjectClient,
agentReference,
new ChatClientAgentOptions()
{
Id = $"{agentReference.Name}:{agentReference.Version}",
Name = agentReference.Name,
ChatOptions = new() { Tools = tools },
},
clientFactory,
services);
return new FoundryAgent(aiProjectClient, innerAgent);
}
/// <summary>
/// Asynchronously retrieves an existing server side agent, wrapped as a <see cref="ChatClientAgent"/> using the provided <see cref="AIProjectClient"/>.
/// </summary>
/// <param name="aiProjectClient">The <see cref="AIProjectClient"/> to create the <see cref="ChatClientAgent"/> with. Cannot be <see langword="null"/>.</param>
/// <param name="name">The name of the server side agent to create a <see cref="ChatClientAgent"/> for. Cannot be <see langword="null"/> or whitespace.</param>
/// <param name="tools">The tools to use when interacting with the agent. This is required when using prompt agent definitions with tools.</param>
/// <param name="clientFactory">Provides a way to customize the creation of the underlying <see cref="IChatClient"/> used by the agent.</param>
/// <param name="services">An optional <see cref="IServiceProvider"/> to use for resolving services required by the <see cref="AIFunction"/> instances being invoked.</param>
/// <param name="cancellationToken">The <see cref="CancellationToken"/> to monitor for cancellation requests. The default is <see cref="CancellationToken.None"/>.</param>
/// <returns>A <see cref="ChatClientAgent"/> instance that can be used to perform operations based on the latest version of the named Azure AI Agent.</returns>
/// <exception cref="ArgumentNullException">Thrown when <paramref name="aiProjectClient"/> or <paramref name="name"/> is <see langword="null"/>.</exception>
/// <exception cref="ArgumentException">Thrown when <paramref name="name"/> is empty or whitespace, or when the agent with the specified name was not found.</exception>
/// <exception cref="InvalidOperationException">The agent with the specified name was not found.</exception>
[Obsolete("Use native AIProjectClient agent APIs and AsAIAgent(AgentRecord/AgentVersion) instead.")]
public static async Task<FoundryAgent> GetAIAgentAsync(
this AIProjectClient aiProjectClient,
string name,
IList<AITool>? tools = null,
Func<IChatClient, IChatClient>? clientFactory = null,
IServiceProvider? services = null,
CancellationToken cancellationToken = default)
{
Throw.IfNull(aiProjectClient);
ThrowIfInvalidAgentName(name);
AgentRecord agentRecord = await GetAgentRecordByNameAsync(aiProjectClient, name, cancellationToken).ConfigureAwait(false);
return AsAIAgent(
aiProjectClient,
agentRecord,
tools,
clientFactory,
services);
}
/// <summary>
/// Uses an existing server side agent, wrapped as a <see cref="ChatClientAgent"/> using the provided <see cref="AIProjectClient"/> and <see cref="AgentRecord"/>.
/// </summary>
/// <param name="aiProjectClient">The client used to interact with Azure AI Agents. Cannot be <see langword="null"/>.</param>
/// <param name="agentRecord">The agent record to be converted. The latest version will be used. Cannot be <see langword="null"/>.</param>
/// <param name="tools">The tools to use when interacting with the agent. This is required when using prompt agent definitions with tools.</param>
/// <param name="clientFactory">Provides a way to customize the creation of the underlying <see cref="IChatClient"/> used by the agent.</param>
/// <param name="services">An optional <see cref="IServiceProvider"/> to use for resolving services required by the <see cref="AIFunction"/> instances being invoked.</param>
/// <returns>A <see cref="ChatClientAgent"/> instance that can be used to perform operations based on the latest version of the Azure AI Agent.</returns>
/// <exception cref="ArgumentNullException">Thrown when <paramref name="aiProjectClient"/> or <paramref name="agentRecord"/> is <see langword="null"/>.</exception>
public static FoundryAgent AsAIAgent(
this AIProjectClient aiProjectClient,
AgentRecord agentRecord,
IList<AITool>? tools = null,
Func<IChatClient, IChatClient>? clientFactory = null,
IServiceProvider? services = null)
{
Throw.IfNull(aiProjectClient);
Throw.IfNull(agentRecord);
var allowDeclarativeMode = tools is not { Count: > 0 };
var innerAgent = AsChatClientAgent(
aiProjectClient,
agentRecord,
tools,
clientFactory,
!allowDeclarativeMode,
services);
return new FoundryAgent(aiProjectClient, innerAgent);
}
/// <summary>
/// Uses an existing server side agent, wrapped as a <see cref="ChatClientAgent"/> using the provided <see cref="AIProjectClient"/> and <see cref="AgentVersion"/>.
/// </summary>
/// <param name="aiProjectClient">The client used to interact with Azure AI Agents. Cannot be <see langword="null"/>.</param>
/// <param name="agentVersion">The agent version to be converted. Cannot be <see langword="null"/>.</param>
/// <param name="tools">In-process invocable tools to be provided. If no tools are provided manual handling will be necessary to invoke in-process tools.</param>
/// <param name="clientFactory">Provides a way to customize the creation of the underlying <see cref="IChatClient"/> used by the agent.</param>
/// <param name="services">An optional <see cref="IServiceProvider"/> to use for resolving services required by the <see cref="AIFunction"/> instances being invoked.</param>
/// <returns>A <see cref="ChatClientAgent"/> instance that can be used to perform operations based on the provided version of the Azure AI Agent.</returns>
/// <exception cref="ArgumentNullException">Thrown when <paramref name="aiProjectClient"/> or <paramref name="agentVersion"/> is <see langword="null"/>.</exception>
public static FoundryAgent AsAIAgent(
this AIProjectClient aiProjectClient,
AgentVersion agentVersion,
IList<AITool>? tools = null,
Func<IChatClient, IChatClient>? clientFactory = null,
IServiceProvider? services = null)
{
Throw.IfNull(aiProjectClient);
Throw.IfNull(agentVersion);
var allowDeclarativeMode = tools is not { Count: > 0 };
var innerAgent = AsChatClientAgent(
aiProjectClient,
agentVersion,
tools,
clientFactory,
!allowDeclarativeMode,
services);
return new FoundryAgent(aiProjectClient, innerAgent);
}
/// <summary>
/// Asynchronously retrieves an existing server side agent, wrapped as a <see cref="ChatClientAgent"/> using the provided <see cref="AIProjectClient"/>.
/// </summary>
/// <param name="aiProjectClient">The client used to manage and interact with AI agents. Cannot be <see langword="null"/>.</param>
/// <param name="options">The options for creating the agent. Cannot be <see langword="null"/>.</param>
/// <param name="clientFactory">A factory function to customize the creation of the chat client used by the agent.</param>
/// <param name="services">An optional <see cref="IServiceProvider"/> to use for resolving services required by the <see cref="AIFunction"/> instances being invoked.</param>
/// <param name="cancellationToken">A <see cref="CancellationToken"/> to cancel the operation if needed.</param>
/// <returns>A <see cref="ChatClientAgent"/> instance that can be used to perform operations on the newly created agent.</returns>
/// <exception cref="ArgumentNullException">Thrown when <paramref name="aiProjectClient"/> or <paramref name="options"/> is <see langword="null"/>.</exception>
[Obsolete("Use native AIProjectClient agent APIs and AsAIAgent(AgentRecord/AgentVersion) instead.")]
public static async Task<FoundryAgent> GetAIAgentAsync(
this AIProjectClient aiProjectClient,
ChatClientAgentOptions options,
Func<IChatClient, IChatClient>? clientFactory = null,
IServiceProvider? services = null,
CancellationToken cancellationToken = default)
{
Throw.IfNull(aiProjectClient);
Throw.IfNull(options);
if (string.IsNullOrWhiteSpace(options.Name))
{
throw new ArgumentException("Agent name must be provided in the options.Name property", nameof(options));
}
ThrowIfInvalidAgentName(options.Name);
AgentRecord agentRecord = await GetAgentRecordByNameAsync(aiProjectClient, options.Name, cancellationToken).ConfigureAwait(false);
var agentVersion = agentRecord.GetLatestVersion();
var agentOptions = CreateChatClientAgentOptions(agentVersion, options, requireInvocableTools: !options.UseProvidedChatClientAsIs);
return new FoundryAgent(
aiProjectClient,
AsChatClientAgent(aiProjectClient, agentVersion, agentOptions, clientFactory, services));
}
/// <summary>
/// Creates a new Prompt AI agent in the Foundry service using the specified configuration parameters, and exposes it as a <see cref="ChatClientAgent"/>.
/// </summary>
/// <param name="aiProjectClient">The client used to manage and interact with AI agents. Cannot be <see langword="null"/>.</param>
/// <param name="name">The name for the agent.</param>
/// <param name="model">The name of the model to use for the agent. Cannot be <see langword="null"/> or whitespace.</param>
/// <param name="instructions">The instructions that guide the agent's behavior. Cannot be <see langword="null"/> or whitespace.</param>
/// <param name="description">The description for the agent.</param>
/// <param name="tools">The tools to use when interacting with the agent, this is required when using prompt agent definitions with tools.</param>
/// <param name="clientFactory">A factory function to customize the creation of the chat client used by the agent.</param>
/// <param name="services">An optional <see cref="IServiceProvider"/> to use for resolving services required by the <see cref="AIFunction"/> instances being invoked.</param>
/// <param name="cancellationToken">A token to monitor for cancellation requests.</param>
/// <returns>A <see cref="ChatClientAgent"/> instance that can be used to perform operations on the newly created agent.</returns>
/// <exception cref="ArgumentNullException">Thrown when <paramref name="aiProjectClient"/>, <paramref name="model"/>, or <paramref name="instructions"/> is <see langword="null"/>.</exception>
/// <exception cref="ArgumentException">Thrown when <paramref name="model"/> or <paramref name="instructions"/> is empty or whitespace.</exception>
/// <remarks>When using prompt agent definitions with tools the parameter <paramref name="tools"/> needs to be provided.</remarks>
[Obsolete("Use native AIProjectClient.Agents APIs instead.")]
public static Task<FoundryAgent> CreateAIAgentAsync(
this AIProjectClient aiProjectClient,
string name,
string model,
string instructions,
string? description = null,
IList<AITool>? tools = null,
Func<IChatClient, IChatClient>? clientFactory = null,
IServiceProvider? services = null,
CancellationToken cancellationToken = default)
{
Throw.IfNull(aiProjectClient);
ThrowIfInvalidAgentName(name);
Throw.IfNullOrWhitespace(model);
Throw.IfNullOrWhitespace(instructions);
return CreateAIAgentAsync(
aiProjectClient,
name,
tools,
new AgentVersionCreationOptions(new PromptAgentDefinition(model) { Instructions = instructions }) { Description = description },
clientFactory,
services,
cancellationToken);
}
/// <summary>
/// Creates a new Prompt AI agent in the Foundry service using the specified configuration parameters, and exposes it as a <see cref="ChatClientAgent"/>.
/// </summary>
/// <param name="aiProjectClient">The client used to manage and interact with AI agents. Cannot be <see langword="null"/>.</param>
/// <param name="model">The name of the model to use for the agent. Cannot be <see langword="null"/> or whitespace.</param>
/// <param name="options">The options for creating the agent. Cannot be <see langword="null"/>.</param>
/// <param name="clientFactory">A factory function to customize the creation of the chat client used by the agent.</param>
/// <param name="services">An optional <see cref="IServiceProvider"/> to use for resolving services required by the <see cref="AIFunction"/> instances being invoked.</param>
/// <param name="cancellationToken">A <see cref="CancellationToken"/> to cancel the operation if needed.</param>
/// <returns>A <see cref="ChatClientAgent"/> instance that can be used to perform operations on the newly created agent.</returns>
/// <exception cref="ArgumentNullException">Thrown when <paramref name="aiProjectClient"/> or <paramref name="options"/> is <see langword="null"/>.</exception>
/// <exception cref="ArgumentException">Thrown when <paramref name="model"/> is empty or whitespace, or when the agent name is not provided in the options.</exception>
[Obsolete("Use native AIProjectClient.Agents APIs instead.")]
public static async Task<FoundryAgent> CreateAIAgentAsync(
this AIProjectClient aiProjectClient,
string model,
ChatClientAgentOptions options,
Func<IChatClient, IChatClient>? clientFactory = null,
IServiceProvider? services = null,
CancellationToken cancellationToken = default)
{
Throw.IfNull(aiProjectClient);
Throw.IfNull(options);
Throw.IfNullOrWhitespace(model);
if (string.IsNullOrWhiteSpace(options.Name))
{
throw new ArgumentException("Agent name must be provided in the options.Name property", nameof(options));
}
ThrowIfInvalidAgentName(options.Name);
AgentVersion agentVersion = await CreateAgentVersionFromOptionsAsync(aiProjectClient, model, options, cancellationToken).ConfigureAwait(false);
var agentOptions = CreateChatClientAgentOptions(agentVersion, options, requireInvocableTools: true);
return new FoundryAgent(
aiProjectClient,
AsChatClientAgent(aiProjectClient, agentVersion, agentOptions, clientFactory, services));
}
/// <summary>
/// Creates a new Prompt AI agent in the Foundry service using the specified configuration parameters, and exposes it as a <see cref="ChatClientAgent"/>.
/// parameters.
/// </summary>
/// <param name="aiProjectClient">The client used to manage and interact with AI agents. Cannot be <see langword="null"/>.</param>
/// <param name="name">The name for the agent.</param>
/// <param name="creationOptions">Settings that control the creation of the agent.</param>
/// <param name="clientFactory">A factory function to customize the creation of the chat client used by the agent.</param>
/// <param name="cancellationToken">A token to monitor for cancellation requests.</param>
/// <returns>A <see cref="ChatClientAgent"/> instance that can be used to perform operations on the newly created agent.</returns>
/// <exception cref="ArgumentNullException">Thrown when <paramref name="aiProjectClient"/> or <paramref name="creationOptions"/> is <see langword="null"/>.</exception>
/// <remarks>
/// When using this extension method with a <see cref="PromptAgentDefinition"/> the tools are only declarative and not invocable.
/// Invocation of any in-process tools will need to be handled manually.
/// </remarks>
[Obsolete("Use native AIProjectClient.Agents APIs instead.")]
public static Task<FoundryAgent> CreateAIAgentAsync(
this AIProjectClient aiProjectClient,
string name,
AgentVersionCreationOptions creationOptions,
Func<IChatClient, IChatClient>? clientFactory = null,
CancellationToken cancellationToken = default)
{
Throw.IfNull(aiProjectClient);
ThrowIfInvalidAgentName(name);
Throw.IfNull(creationOptions);
return CreateAIAgentAsync(
aiProjectClient,
name,
tools: null,
creationOptions,
clientFactory,
services: null,
cancellationToken);
}
/// <summary>
/// Creates a non-versioned <see cref="ChatClientAgent"/> backed by the project's Responses API using the specified model and instructions.
/// </summary>
/// <param name="aiProjectClient">The <see cref="AIProjectClient"/> to use for Responses API calls. Cannot be <see langword="null"/>.</param>
/// <param name="model">The model deployment name to use for the agent. Cannot be <see langword="null"/> or whitespace.</param>
/// <param name="instructions">The instructions that guide the agent's behavior. Cannot be <see langword="null"/> or whitespace.</param>
/// <param name="name">Optional name for the agent.</param>
/// <param name="description">Optional human-readable description for the agent.</param>
/// <param name="tools">Optional collection of tools that the agent can invoke during conversations.</param>
/// <param name="clientFactory">Provides a way to customize the creation of the underlying <see cref="IChatClient"/> used by the agent.</param>
/// <param name="loggerFactory">Optional logger factory for creating loggers used by the agent.</param>
/// <param name="services">An optional <see cref="IServiceProvider"/> to use for resolving services required by the <see cref="AIFunction"/> instances being invoked.</param>
/// <returns>A <see cref="ChatClientAgent"/> backed by the project's Responses API.</returns>
/// <exception cref="ArgumentNullException">Thrown when <paramref name="aiProjectClient"/> is <see langword="null"/>.</exception>
/// <exception cref="ArgumentException">Thrown when <paramref name="model"/> or <paramref name="instructions"/> is empty or whitespace.</exception>
public static FoundryAgent AsAIAgent(
this AIProjectClient aiProjectClient,
string model,
string instructions,
string? name = null,
string? description = null,
IList<AITool>? tools = null,
Func<IChatClient, IChatClient>? clientFactory = null,
ILoggerFactory? loggerFactory = null,
IServiceProvider? services = null)
{
Throw.IfNull(aiProjectClient);
Throw.IfNullOrWhitespace(model);
Throw.IfNullOrWhitespace(instructions);
ChatClientAgentOptions options = new()
{
Name = name,
Description = description,
ChatOptions = new ChatOptions
{
ModelId = model,
Instructions = instructions,
Tools = tools,
},
};
return new FoundryAgent(aiProjectClient, CreateResponsesChatClientAgent(aiProjectClient, options, clientFactory, loggerFactory, services));
}
/// <summary>
/// Creates a non-versioned <see cref="ChatClientAgent"/> backed by the project's Responses API using the specified options.
/// </summary>
/// <param name="aiProjectClient">The <see cref="AIProjectClient"/> to use for Responses API calls. Cannot be <see langword="null"/>.</param>
/// <param name="options">Configuration options that control the agent's behavior. <see cref="ChatOptions.ModelId"/> is required.</param>
/// <param name="clientFactory">Provides a way to customize the creation of the underlying <see cref="IChatClient"/> used by the agent.</param>
/// <param name="loggerFactory">Optional logger factory for creating loggers used by the agent.</param>
/// <param name="services">An optional <see cref="IServiceProvider"/> to use for resolving services required by the <see cref="AIFunction"/> instances being invoked.</param>
/// <returns>A <see cref="ChatClientAgent"/> backed by the project's Responses API.</returns>
/// <exception cref="ArgumentNullException">Thrown when <paramref name="aiProjectClient"/> or <paramref name="options"/> is <see langword="null"/>.</exception>
/// <exception cref="ArgumentException">Thrown when <paramref name="options"/> does not specify <see cref="ChatOptions.ModelId"/>.</exception>
public static FoundryAgent AsAIAgent(
this AIProjectClient aiProjectClient,
ChatClientAgentOptions options,
Func<IChatClient, IChatClient>? clientFactory = null,
ILoggerFactory? loggerFactory = null,
IServiceProvider? services = null)
{
Throw.IfNull(aiProjectClient);
Throw.IfNull(options);
return new FoundryAgent(aiProjectClient, CreateResponsesChatClientAgent(aiProjectClient, options, clientFactory, loggerFactory, services));
}
#region Private
private static readonly ModelReaderWriterOptions s_modelWriterOptionsWire = new("W");
/// <summary>
/// Asynchronously retrieves an agent record by name using the protocol method to inject user-agent headers.
/// </summary>
internal static async Task<AgentRecord> GetAgentRecordByNameAsync(AIProjectClient aiProjectClient, string agentName, CancellationToken cancellationToken)
{
ClientResult protocolResponse = await aiProjectClient.Agents.GetAgentAsync(agentName, cancellationToken.ToRequestOptions(false)).ConfigureAwait(false);
var rawResponse = protocolResponse.GetRawResponse();
AgentRecord? result = ModelReaderWriter.Read<AgentRecord>(rawResponse.Content, s_modelWriterOptionsWire, AzureAIProjectsAgentsContext.Default);
return result ?? throw new InvalidOperationException($"Agent with name '{agentName}' not found.");
}
/// <summary>
/// Asynchronously creates an agent version using the protocol method to inject user-agent headers.
/// </summary>
internal static async Task<AgentVersion> CreateAgentVersionWithProtocolAsync(AIProjectClient aiProjectClient, string agentName, AgentVersionCreationOptions creationOptions, CancellationToken cancellationToken)
{
BinaryData serializedOptions = ModelReaderWriter.Write(creationOptions, s_modelWriterOptionsWire, AzureAIProjectsAgentsContext.Default);
BinaryContent content = BinaryContent.Create(serializedOptions);
ClientResult protocolResponse = await aiProjectClient.Agents.CreateAgentVersionAsync(agentName, content, foundryFeatures: null, cancellationToken.ToRequestOptions(false)).ConfigureAwait(false);
var rawResponse = protocolResponse.GetRawResponse();
AgentVersion? result = ModelReaderWriter.Read<AgentVersion>(rawResponse.Content, s_modelWriterOptionsWire, AzureAIProjectsAgentsContext.Default);
return result ?? throw new InvalidOperationException($"Failed to create agent version for agent '{agentName}'.");
}
private static async Task<FoundryAgent> CreateAIAgentAsync(
this AIProjectClient aiProjectClient,
string name,
IList<AITool>? tools,
AgentVersionCreationOptions creationOptions,
Func<IChatClient, IChatClient>? clientFactory,
IServiceProvider? services,
CancellationToken cancellationToken)
{
var allowDeclarativeMode = tools is not { Count: > 0 };
if (!allowDeclarativeMode)
{
ApplyToolsToAgentDefinition(creationOptions.Definition, tools);
}
AgentVersion agentVersion = await CreateAgentVersionWithProtocolAsync(aiProjectClient, name, creationOptions, cancellationToken).ConfigureAwait(false);
return new FoundryAgent(aiProjectClient, AsChatClientAgent(aiProjectClient, agentVersion, tools, clientFactory, !allowDeclarativeMode, services));
}
/// <summary>
/// Creates an agent version with optional tool application, using the protocol method to inject user-agent headers.
/// </summary>
internal static async Task<AgentVersion> CreateAgentVersionWithProtocolAsync(AIProjectClient aiProjectClient, string agentName, AgentVersionCreationOptions creationOptions, IList<AITool>? tools, CancellationToken cancellationToken)
{
if (tools is { Count: > 0 })
{
ApplyToolsToAgentDefinition(creationOptions.Definition, tools);
}
return await CreateAgentVersionWithProtocolAsync(aiProjectClient, agentName, creationOptions, cancellationToken).ConfigureAwait(false);
}
/// <summary>
/// Creates an agent version from <see cref="ChatClientAgentOptions"/>, mapping options to a <see cref="PromptAgentDefinition"/>.
/// </summary>
internal static async Task<AgentVersion> CreateAgentVersionFromOptionsAsync(
AIProjectClient aiProjectClient,
string model,
ChatClientAgentOptions options,
CancellationToken cancellationToken)
{
PromptAgentDefinition agentDefinition = new(model)
{
Instructions = options.ChatOptions?.Instructions,
Temperature = options.ChatOptions?.Temperature,
TopP = options.ChatOptions?.TopP,
TextOptions = new() { TextFormat = ToOpenAIResponseTextFormat(options.ChatOptions?.ResponseFormat, options.ChatOptions) }
};
if (options.ChatOptions?.Reasoning is { } reasoning)
{
agentDefinition.ReasoningOptions = ToResponseReasoningOptions(reasoning);
}
else if (options.ChatOptions?.RawRepresentationFactory?.Invoke(new NoOpChatClient()) is CreateResponseOptions respCreationOptions)
{
agentDefinition.ReasoningOptions = respCreationOptions.ReasoningOptions;
}
ApplyToolsToAgentDefinition(agentDefinition, options.ChatOptions?.Tools);
AgentVersionCreationOptions creationOptions = new(agentDefinition);
if (!string.IsNullOrWhiteSpace(options.Description))
{
creationOptions.Description = options.Description;
}
return await CreateAgentVersionWithProtocolAsync(aiProjectClient, options.Name!, creationOptions, cancellationToken).ConfigureAwait(false);
}
/// <summary>Creates a <see cref="ChatClientAgent"/> with the specified options.</summary>
internal static ChatClientAgent CreateChatClientAgent(
AIProjectClient aiProjectClient,
AgentVersion agentVersion,
ChatClientAgentOptions agentOptions,
Func<IChatClient, IChatClient>? clientFactory,
IServiceProvider? services)
{
IChatClient chatClient = new AzureAIProjectChatClient(aiProjectClient, agentVersion, agentOptions.ChatOptions);
if (clientFactory is not null)
{
chatClient = clientFactory(chatClient);
}
return new ChatClientAgent(chatClient, agentOptions, services: services);
}
internal static ChatClientAgent CreateResponsesChatClientAgent(
AIProjectClient aiProjectClient,
ChatClientAgentOptions agentOptions,
Func<IChatClient, IChatClient>? clientFactory,
ILoggerFactory? loggerFactory,
IServiceProvider? services)
{
Throw.IfNull(aiProjectClient);
Throw.IfNull(agentOptions);
Throw.IfNull(agentOptions.ChatOptions);
Throw.IfNullOrWhitespace(agentOptions.ChatOptions.ModelId);
IChatClient chatClient = new AzureAIProjectResponsesChatClient(aiProjectClient, agentOptions.ChatOptions.ModelId);
if (clientFactory is not null)
{
chatClient = clientFactory(chatClient);
}
return new ChatClientAgent(chatClient, agentOptions, loggerFactory, services);
}
/// <summary>This method creates an <see cref="ChatClientAgent"/> with the specified ChatClientAgentOptions.</summary>
private static ChatClientAgent AsChatClientAgent(
AIProjectClient aiProjectClient,
AgentVersion agentVersion,
ChatClientAgentOptions agentOptions,
Func<IChatClient, IChatClient>? clientFactory,
IServiceProvider? services)
=> CreateChatClientAgent(aiProjectClient, agentVersion, agentOptions, clientFactory, services);
/// <summary>This method creates an <see cref="ChatClientAgent"/> with the specified ChatClientAgentOptions.</summary>
private static ChatClientAgent AsChatClientAgent(
AIProjectClient aiProjectClient,
AgentRecord agentRecord,
ChatClientAgentOptions agentOptions,
Func<IChatClient, IChatClient>? clientFactory,
IServiceProvider? services)
{
IChatClient chatClient = new AzureAIProjectChatClient(aiProjectClient, agentRecord, agentOptions.ChatOptions);
if (clientFactory is not null)
{
chatClient = clientFactory(chatClient);
}
return new ChatClientAgent(chatClient, agentOptions, services: services);
}
/// <summary>This method creates an <see cref="ChatClientAgent"/> with the specified ChatClientAgentOptions.</summary>
private static ChatClientAgent AsChatClientAgent(
AIProjectClient aiProjectClient,
AgentReference agentReference,
ChatClientAgentOptions agentOptions,
Func<IChatClient, IChatClient>? clientFactory,
IServiceProvider? services)
{
IChatClient chatClient = new AzureAIProjectChatClient(aiProjectClient, agentReference, defaultModelId: null, agentOptions.ChatOptions);
if (clientFactory is not null)
{
chatClient = clientFactory(chatClient);
}
return new ChatClientAgent(chatClient, agentOptions, services: services);
}
/// <summary>This method creates an <see cref="ChatClientAgent"/> with a auto-generated ChatClientAgentOptions from the specified configuration parameters.</summary>
private static ChatClientAgent AsChatClientAgent(
AIProjectClient AIProjectClient,
AgentVersion agentVersion,
IList<AITool>? tools,
Func<IChatClient, IChatClient>? clientFactory,
bool requireInvocableTools,
IServiceProvider? services)
=> AsChatClientAgent(
AIProjectClient,
agentVersion,
CreateChatClientAgentOptions(agentVersion, new ChatOptions() { Tools = tools }, requireInvocableTools),
clientFactory,
services);
/// <summary>This method creates an <see cref="ChatClientAgent"/> with a auto-generated ChatClientAgentOptions from the specified configuration parameters.</summary>
private static ChatClientAgent AsChatClientAgent(
AIProjectClient AIProjectClient,
AgentRecord agentRecord,
IList<AITool>? tools,
Func<IChatClient, IChatClient>? clientFactory,
bool requireInvocableTools,
IServiceProvider? services)
=> AsChatClientAgent(
AIProjectClient,
agentRecord,
CreateChatClientAgentOptions(agentRecord.GetLatestVersion(), new ChatOptions() { Tools = tools }, requireInvocableTools),
clientFactory,
services);
/// <summary>
/// This method creates <see cref="ChatClientAgentOptions"/> for the specified <see cref="AgentVersion"/> and the provided tools.
/// </summary>
/// <param name="agentVersion">The agent version.</param>
/// <param name="chatOptions">The <see cref="ChatOptions"/> to use when interacting with the agent.</param>
/// <param name="requireInvocableTools">Indicates whether to enforce the presence of invocable tools when the AIAgent is created with an agent definition that uses them.</param>
/// <returns>The created <see cref="ChatClientAgentOptions"/>.</returns>
/// <exception cref="InvalidOperationException">Thrown when the agent definition requires in-process tools but none were provided.</exception>
/// <exception cref="InvalidOperationException">Thrown when the agent definition required tools were not provided.</exception>
/// <remarks>
/// This method rebuilds the agent options from the agent definition returned by the version and combine with the in-proc tools when provided
/// this ensures that all required tools are provided and the definition of the agent options are consistent with the agent definition coming from the server.
/// </remarks>
internal static ChatClientAgentOptions CreateChatClientAgentOptions(AgentVersion agentVersion, ChatOptions? chatOptions, bool requireInvocableTools)
{
var agentDefinition = agentVersion.Definition;
List<AITool>? agentTools = null;
if (agentDefinition is PromptAgentDefinition { Tools: { Count: > 0 } definitionTools })
{
// Check if no tools were provided while the agent definition requires in-proc tools.
if (requireInvocableTools && chatOptions?.Tools is not { Count: > 0 } && definitionTools.Any(t => t is FunctionTool))
{
throw new ArgumentException("The agent definition in-process tools must be provided in the extension method tools parameter.");
}
// Agregate all missing tools for a single error message.
List<string>? missingTools = null;
// Check function tools
foreach (ResponseTool responseTool in definitionTools)
{
if (responseTool is FunctionTool functionTool)
{
// Check if a tool with the same type and name exists in the provided tools.
// Always prefer matching AIFunction when available, regardless of requireInvocableTools.
var matchingTool = chatOptions?.Tools?.FirstOrDefault(t => t is AIFunction tf && functionTool.FunctionName == tf.Name);
if (matchingTool is not null)
{
(agentTools ??= []).Add(matchingTool!);
continue;
}
if (requireInvocableTools)
{
(missingTools ??= []).Add($"Function tool: {functionTool.FunctionName}");
continue;
}
}
(agentTools ??= []).Add(responseTool.AsAITool());
}
if (requireInvocableTools && missingTools is { Count: > 0 })
{
throw new InvalidOperationException($"The following prompt agent definition required tools were not provided: {string.Join(", ", missingTools)}");
}
}
// Use the agent version's ID if available, otherwise generate one from name and version.
// This handles cases where hosted agents (like MCP agents) may not have an ID assigned.
var version = string.IsNullOrWhiteSpace(agentVersion.Version) ? "latest" : agentVersion.Version;
var agentId = string.IsNullOrWhiteSpace(agentVersion.Id)
? $"{agentVersion.Name}:{version}"
: agentVersion.Id;
var agentOptions = new ChatClientAgentOptions()
{
Id = agentId,
Name = agentVersion.Name,
Description = agentVersion.Description,
};
if (agentDefinition is PromptAgentDefinition promptAgentDefinition)
{
agentOptions.ChatOptions ??= chatOptions?.Clone() ?? new();
agentOptions.ChatOptions.Instructions = promptAgentDefinition.Instructions;
agentOptions.ChatOptions.Temperature = promptAgentDefinition.Temperature;
agentOptions.ChatOptions.TopP = promptAgentDefinition.TopP;
}
if (agentTools is { Count: > 0 })
{
agentOptions.ChatOptions ??= chatOptions?.Clone() ?? new();
agentOptions.ChatOptions.Tools = agentTools;
}
return agentOptions;
}
/// <summary>
/// Creates a new instance of <see cref="ChatClientAgentOptions"/> configured for the specified agent version and
/// optional base options.
/// </summary>
/// <param name="agentVersion">The agent version to use when configuring the chat client agent options.</param>
/// <param name="options">An optional <see cref="ChatClientAgentOptions"/> instance whose relevant properties will be copied to the
/// returned options. If <see langword="null"/>, only default values are used.</param>
/// <param name="requireInvocableTools">Specifies whether the returned options must include invocable tools. Set to <see langword="true"/> to require
/// invocable tools; otherwise, <see langword="false"/>.</param>
/// <returns>A <see cref="ChatClientAgentOptions"/> instance configured according to the specified parameters.</returns>
internal static ChatClientAgentOptions CreateChatClientAgentOptions(AgentVersion agentVersion, ChatClientAgentOptions? options, bool requireInvocableTools)
{
var agentOptions = CreateChatClientAgentOptions(agentVersion, options?.ChatOptions, requireInvocableTools);
if (options is not null)
{
agentOptions.AIContextProviders = options.AIContextProviders;
agentOptions.ChatHistoryProvider = options.ChatHistoryProvider;
agentOptions.UseProvidedChatClientAsIs = options.UseProvidedChatClientAsIs;
}
return agentOptions;
}
/// <summary>
/// Adds the specified AI tools to a prompt agent definition, while also ensuring that all invocable tools are provided.
/// </summary>
/// <param name="agentDefinition">The agent definition to which the tools will be applied. Must be a PromptAgentDefinition to support tools.</param>
/// <param name="tools">A list of AI tools to add to the agent definition. If null or empty, no tools are added.</param>
/// <exception cref="ArgumentException">Thrown if tools were provided but <paramref name="agentDefinition"/> is not a <see cref="PromptAgentDefinition"/>.</exception>
/// <exception cref="InvalidOperationException">When providing functions, they need to be invokable AIFunctions.</exception>
private static void ApplyToolsToAgentDefinition(AgentDefinition agentDefinition, IList<AITool>? tools)
{
if (tools is { Count: > 0 })
{
if (agentDefinition is not PromptAgentDefinition promptAgentDefinition)
{
throw new ArgumentException("Only prompt agent definitions support tools.", nameof(agentDefinition));
}
// When tools are provided, those should represent the complete set of tools for the agent definition.
// This is particularly important for existing agents so no duplication happens for what was already defined.
promptAgentDefinition.Tools.Clear();
foreach (var tool in tools)
{
// Ensure that any AIFunctions provided are In-Proc, not just the declarations.
if (tool is not AIFunction && (
tool.GetService<FunctionTool>() is not null // Declarative FunctionTool converted as AsAITool()
|| tool is AIFunctionDeclaration)) // AIFunctionDeclaration type
{
throw new InvalidOperationException("When providing functions, they need to be invokable AIFunctions. AIFunctions can be created correctly using AIFunctionFactory.Create");
}
promptAgentDefinition.Tools.Add(
// If this is a converted ResponseTool as AITool, we can directly retrieve the ResponseTool instance from GetService.
tool.GetService<ResponseTool>()
// Otherwise we should be able to convert existing MEAI Tool abstractions into OpenAI ResponseTools
?? tool.AsOpenAIResponseTool()
?? throw new InvalidOperationException("The provided AITool could not be converted to a ResponseTool, ensure that the AITool was created using responseTool.AsAITool() extension."));
}
}
}
private static ResponseTextFormat? ToOpenAIResponseTextFormat(ChatResponseFormat? format, ChatOptions? options = null) =>
format switch
{
ChatResponseFormatText => ResponseTextFormat.CreateTextFormat(),
ChatResponseFormatJson jsonFormat when StrictSchemaTransformCache.GetOrCreateTransformedSchema(jsonFormat) is { } jsonSchema =>
ResponseTextFormat.CreateJsonSchemaFormat(
jsonFormat.SchemaName ?? "json_schema",
BinaryData.FromBytes(JsonSerializer.SerializeToUtf8Bytes(jsonSchema, AgentClientJsonContext.Default.JsonElement)),
jsonFormat.SchemaDescription,
HasStrict(options?.AdditionalProperties)),
ChatResponseFormatJson => ResponseTextFormat.CreateJsonObjectFormat(),
_ => null,
};
/// <summary>Key into AdditionalProperties used to store a strict option.</summary>
private const string StrictKey = "strictJsonSchema";
/// <summary>Gets whether the properties specify that strict schema handling is desired.</summary>
private static bool? HasStrict(IReadOnlyDictionary<string, object?>? additionalProperties) =>
additionalProperties?.TryGetValue(StrictKey, out object? strictObj) is true &&
strictObj is bool strictValue ?
strictValue : null;
/// <summary>
/// Gets the JSON schema transformer cache conforming to OpenAI <b>strict</b> / structured output restrictions per
/// https://platform.openai.com/docs/guides/structured-outputs?api-mode=responses#supported-schemas.
/// </summary>
private static AIJsonSchemaTransformCache StrictSchemaTransformCache { get; } = new(new()
{
DisallowAdditionalProperties = true,
ConvertBooleanSchemas = true,
MoveDefaultKeywordToDescription = true,
RequireAllProperties = true,
TransformSchemaNode = (ctx, node) =>
{
// Move content from common but unsupported properties to description. In particular, we focus on properties that
// the AIJsonUtilities schema generator might produce and/or that are explicitly mentioned in the OpenAI documentation.
if (node is JsonObject schemaObj)
{
StringBuilder? additionalDescription = null;
ReadOnlySpan<string> unsupportedProperties =
[
// Produced by AIJsonUtilities but not in allow list at https://platform.openai.com/docs/guides/structured-outputs#supported-properties:
"contentEncoding", "contentMediaType", "not",
// Explicitly mentioned at https://platform.openai.com/docs/guides/structured-outputs?api-mode=responses#key-ordering as being unsupported with some models:
"minLength", "maxLength", "pattern", "format",
"minimum", "maximum", "multipleOf",
"patternProperties",
"minItems", "maxItems",
// Explicitly mentioned at https://learn.microsoft.com/azure/ai-services/openai/how-to/structured-outputs?pivots=programming-language-csharp&tabs=python-secure%2Cdotnet-entra-id#unsupported-type-specific-keywords
// as being unsupported with Azure OpenAI:
"unevaluatedProperties", "propertyNames", "minProperties", "maxProperties",
"unevaluatedItems", "contains", "minContains", "maxContains", "uniqueItems",
];
foreach (string propName in unsupportedProperties)
{
if (schemaObj[propName] is { } propNode)
{
_ = schemaObj.Remove(propName);
AppendLine(ref additionalDescription, propName, propNode);
}
}
if (additionalDescription is not null)
{
schemaObj["description"] = schemaObj["description"] is { } descriptionNode && descriptionNode.GetValueKind() == JsonValueKind.String ?
$"{descriptionNode.GetValue<string>()}{Environment.NewLine}{additionalDescription}" :
additionalDescription.ToString();
}
return node;
static void AppendLine(ref StringBuilder? sb, string propName, JsonNode propNode)
{
sb ??= new();
if (sb.Length > 0)
{
_ = sb.AppendLine();
}
_ = sb.Append(propName).Append(": ").Append(propNode);
}
}
return node;
},
});
/// <summary>
/// This class is a no-op implementation of <see cref="IChatClient"/> to be used to honor the argument passed
/// while triggering <see cref="ChatOptions.RawRepresentationFactory"/> avoiding any unexpected exception on the caller implementation.
/// </summary>
private sealed class NoOpChatClient : IChatClient
{
public void Dispose() { }
public Task<ChatResponse> GetResponseAsync(IEnumerable<ChatMessage> messages, ChatOptions? options = null, CancellationToken cancellationToken = default)
=> Task.FromResult(new ChatResponse());
public object? GetService(Type serviceType, object? serviceKey = null) => null;
public async IAsyncEnumerable<ChatResponseUpdate> GetStreamingResponseAsync(IEnumerable<ChatMessage> messages, ChatOptions? options = null, [EnumeratorCancellation] CancellationToken cancellationToken = default)
{
yield return new ChatResponseUpdate();
}
}
#endregion
#if NET
[GeneratedRegex("^[a-zA-Z0-9]([a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?$")]
private static partial Regex AgentNameValidationRegex();
#else
private static Regex AgentNameValidationRegex() => new("^[a-zA-Z0-9]([a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?$");
#endif
internal static string ThrowIfInvalidAgentName(string? name)
{
Throw.IfNullOrWhitespace(name);
if (!AgentNameValidationRegex().IsMatch(name))
{
throw new ArgumentException("Agent name must be 1-63 characters long, start and end with an alphanumeric character, and can only contain alphanumeric characters or hyphens.", nameof(name));
}
return name;
}
private static ResponseReasoningOptions? ToResponseReasoningOptions(ReasoningOptions reasoning)
{
ResponseReasoningEffortLevel? effortLevel = reasoning.Effort switch
{
ReasoningEffort.Low => ResponseReasoningEffortLevel.Low,
ReasoningEffort.Medium => ResponseReasoningEffortLevel.Medium,
ReasoningEffort.High => ResponseReasoningEffortLevel.High,
ReasoningEffort.ExtraHigh => ResponseReasoningEffortLevel.High,
_ => null,
};
ResponseReasoningSummaryVerbosity? summary = reasoning.Output switch
{
ReasoningOutput.Summary => ResponseReasoningSummaryVerbosity.Concise,
ReasoningOutput.Full => ResponseReasoningSummaryVerbosity.Detailed,
_ => null,
};
if (effortLevel is null && summary is null)
{
return null;
}
return new ResponseReasoningOptions
{
ReasoningEffortLevel = effortLevel,
ReasoningSummaryVerbosity = summary,
};
}
}
[JsonSerializable(typeof(JsonElement))]
internal sealed partial class AgentClientJsonContext : JsonSerializerContext;