[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69AMCJ3AEDTWHYCBQRC9NHA":3,"skill-same:01M69AMCJ3AEDTWHYCBQRC9NHA":78},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":45,"linkOnly":46,"markdownContent":47,"markdownBody":48,"frontMatter":49,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":59,"ownerHtmlUrl":60,"ownerBlogUrl":61,"ownerDescription":62,"updatedAt":63,"install":64,"resources":77},"01M69AMCJ3AEDTWHYCBQRC9NHA","azure-ai-agents-persistent-dotnet",null,"Azure AI Agents Persistent SDK for .NET. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools. Use for agent CRUD, conversation threads, streaming responses, function calling, file search, and code interpreter. Triggers: \"PersistentAgentsClient\", \"persistent agents\", \"agent threads\", \"agent runs\", \"streaming agents\", \"function calling agents .NET\".","microsoft\u002Fskills","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M69AJYYW4E1RMSYCQDJ4FJSH",3199,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-sdk-dotnet\u002Fskills\u002Fazure-ai-agents-persistent-dotnet\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,9,44],"dotnet","azure ai","azure","azure ai agents persistent dotnet","ai agents","Tools","for","threads","interpreter","triggers","file search","calling","conversation","use","function calling","crud","messages","streaming","search","code","sdk","2026-11-10 10:12:30",false,"---\nname: azure-ai-agents-persistent-dotnet\ndescription: |\n  Azure AI Agents Persistent SDK for .NET. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools. Use for agent CRUD, conversation threads, streaming responses, function calling, file search, and code interpreter. Triggers: \"PersistentAgentsClient\", \"persistent agents\", \"agent threads\", \"agent runs\", \"streaming agents\", \"function calling agents .NET\".\nlicense: MIT\nmetadata:\n  author: Microsoft\n  version: \"1.0.0\"\n  package: Azure.AI.Agents.Persistent\n---\n\n# Azure.AI.Agents.Persistent (.NET)\n\nLow-level SDK for creating and managing persistent AI agents with threads, messages, runs, and tools.\n\n## Installation\n\n```bash\ndotnet add package Azure.AI.Agents.Persistent --prerelease\ndotnet add package Azure.Identity\n```\n\n**Current Versions**: Stable v1.1.0, Preview v1.2.0-beta.8\n\n## Environment Variables\n\n```bash\nPROJECT_ENDPOINT=https:\u002F\u002F\u003Cresource>.services.ai.azure.com\u002Fapi\u002Fprojects\u002F\u003Cproject>  # Required: Azure AI project endpoint\nMODEL_DEPLOYMENT_NAME=gpt-4o-mini  # Required: model deployment name\nAZURE_BING_CONNECTION_ID=\u003Cbing-connection-resource-id>  # Required: Bing connection resource ID\nAZURE_AI_SEARCH_CONNECTION_ID=\u003Csearch-connection-resource-id>  # Required: Azure AI Search connection resource ID\nAZURE_TOKEN_CREDENTIALS=prod  # Required only if DefaultAzureCredential is used in production\n```\n\n## Authentication\n\n```csharp\nusing Azure.AI.Agents.Persistent;\nusing Azure.Identity;\n\nvar projectEndpoint = Environment.GetEnvironmentVariable(\"PROJECT_ENDPOINT\");\n\u002F\u002F Local dev: DefaultAzureCredential. Production: set AZURE_TOKEN_CREDENTIALS=prod or AZURE_TOKEN_CREDENTIALS=\u003Cspecific_credential>\nvar credential = new DefaultAzureCredential(\n    DefaultAzureCredential.DefaultEnvironmentVariableName\n);\n\u002F\u002F Or use a specific credential directly in production:\n\u002F\u002F See https:\u002F\u002Flearn.microsoft.com\u002Fdotnet\u002Fapi\u002Foverview\u002Fazure\u002Fidentity-readme?view=azure-dotnet#credential-classes\n\u002F\u002F var credential = new ManagedIdentityCredential();\nPersistentAgentsClient client = new(projectEndpoint, credential);\n```\n\n## Client Hierarchy\n\n```\nPersistentAgentsClient\n├── Administration  → Agent CRUD operations\n├── Threads         → Thread management\n├── Messages        → Message operations\n├── Runs            → Run execution and streaming\n├── Files           → File upload\u002Fdownload\n└── VectorStores    → Vector store management\n```\n\n## Core Workflow\n\n### 1. Create Agent\n\n```csharp\nvar modelDeploymentName = Environment.GetEnvironmentVariable(\"MODEL_DEPLOYMENT_NAME\");\n\nPersistentAgent agent = await client.Administration.CreateAgentAsync(\n    model: modelDeploymentName,\n    name: \"Math Tutor\",\n    instructions: \"You are a personal math tutor. Write and run code to answer math questions.\",\n    tools: [new CodeInterpreterToolDefinition()]\n);\n```\n\n### 2. Create Thread and Message\n\n```csharp\n\u002F\u002F Create thread\nPersistentAgentThread thread = await client.Threads.CreateThreadAsync();\n\n\u002F\u002F Create message\nawait client.Messages.CreateMessageAsync(\n    thread.Id,\n    MessageRole.User,\n    \"I need to solve the equation `3x + 11 = 14`. Can you help me?\"\n);\n```\n\n### 3. Run Agent (Polling)\n\n```csharp\n\u002F\u002F Create run\nThreadRun run = await client.Runs.CreateRunAsync(\n    thread.Id,\n    agent.Id,\n    additionalInstructions: \"Please address the user as Jane Doe.\"\n);\n\n\u002F\u002F Poll for completion\ndo\n{\n    await Task.Delay(TimeSpan.FromMilliseconds(500));\n    run = await client.Runs.GetRunAsync(thread.Id, run.Id);\n}\nwhile (run.Status == RunStatus.Queued || run.Status == RunStatus.InProgress);\n\n\u002F\u002F Retrieve messages\nawait foreach (PersistentThreadMessage message in client.Messages.GetMessagesAsync(\n    threadId: thread.Id, \n    order: ListSortOrder.Ascending))\n{\n    Console.Write($\"{message.Role}: \");\n    foreach (MessageContent content in message.ContentItems)\n    {\n        if (content is MessageTextContent textContent)\n            Console.WriteLine(textContent.Text);\n    }\n}\n```\n\n### 4. Streaming Response\n\n```csharp\nAsyncCollectionResult\u003CStreamingUpdate> stream = client.Runs.CreateRunStreamingAsync(\n    thread.Id, \n    agent.Id\n);\n\nawait foreach (StreamingUpdate update in stream)\n{\n    if (update.UpdateKind == StreamingUpdateReason.RunCreated)\n    {\n        Console.WriteLine(\"--- Run started! ---\");\n    }\n    else if (update is MessageContentUpdate contentUpdate)\n    {\n        Console.Write(contentUpdate.Text);\n    }\n    else if (update.UpdateKind == StreamingUpdateReason.RunCompleted)\n    {\n        Console.WriteLine(\"\\n--- Run completed! ---\");\n    }\n}\n```\n\n### 5. Function Calling\n\n```csharp\n\u002F\u002F Define function tool\nFunctionToolDefinition weatherTool = new(\n    name: \"getCurrentWeather\",\n    description: \"Gets the current weather at a location.\",\n    parameters: BinaryData.FromObjectAsJson(new\n    {\n        Type = \"object\",\n        Properties = new\n        {\n            Location = new { Type = \"string\", Description = \"City and state, e.g. San Francisco, CA\" },\n            Unit = new { Type = \"string\", Enum = new[] { \"c\", \"f\" } }\n        },\n        Required = new[] { \"location\" }\n    }, new JsonSerializerOptions { PropertyNamingPolicy = JsonNamingPolicy.CamelCase })\n);\n\n\u002F\u002F Create agent with function\nPersistentAgent agent = await client.Administration.CreateAgentAsync(\n    model: modelDeploymentName,\n    name: \"Weather Bot\",\n    instructions: \"You are a weather bot.\",\n    tools: [weatherTool]\n);\n\n\u002F\u002F Handle function calls during polling\ndo\n{\n    await Task.Delay(500);\n    run = await client.Runs.GetRunAsync(thread.Id, run.Id);\n\n    if (run.Status == RunStatus.RequiresAction \n        && run.RequiredAction is SubmitToolOutputsAction submitAction)\n    {\n        List\u003CToolOutput> outputs = [];\n        foreach (RequiredToolCall toolCall in submitAction.ToolCalls)\n        {\n            if (toolCall is RequiredFunctionToolCall funcCall)\n            {\n                \u002F\u002F Execute function and get result\n                string result = ExecuteFunction(funcCall.Name, funcCall.Arguments);\n                outputs.Add(new ToolOutput(toolCall, result));\n            }\n        }\n        run = await client.Runs.SubmitToolOutputsToRunAsync(run, outputs, toolApprovals: null);\n    }\n}\nwhile (run.Status == RunStatus.Queued || run.Status == RunStatus.InProgress);\n```\n\n### 6. File Search with Vector Store\n\n```csharp\n\u002F\u002F Upload file\nPersistentAgentFileInfo file = await client.Files.UploadFileAsync(\n    filePath: \"document.txt\",\n    purpose: PersistentAgentFilePurpose.Agents\n);\n\n\u002F\u002F Create vector store\nPersistentAgentsVectorStore vectorStore = await client.VectorStores.CreateVectorStoreAsync(\n    fileIds: [file.Id],\n    name: \"my_vector_store\"\n);\n\n\u002F\u002F Create file search resource\nFileSearchToolResource fileSearchResource = new();\nfileSearchResource.VectorStoreIds.Add(vectorStore.Id);\n\n\u002F\u002F Create agent with file search\nPersistentAgent agent = await client.Administration.CreateAgentAsync(\n    model: modelDeploymentName,\n    name: \"Document Assistant\",\n    instructions: \"You help users find information in documents.\",\n    tools: [new FileSearchToolDefinition()],\n    toolResources: new ToolResources { FileSearch = fileSearchResource }\n);\n```\n\n### 7. Bing Grounding\n\n```csharp\nvar bingConnectionId = Environment.GetEnvironmentVariable(\"AZURE_BING_CONNECTION_ID\");\n\nBingGroundingToolDefinition bingTool = new(\n    new BingGroundingSearchToolParameters(\n        [new BingGroundingSearchConfiguration(bingConnectionId)]\n    )\n);\n\nPersistentAgent agent = await client.Administration.CreateAgentAsync(\n    model: modelDeploymentName,\n    name: \"Search Agent\",\n    instructions: \"Use Bing to answer questions about current events.\",\n    tools: [bingTool]\n);\n```\n\n### 8. Azure AI Search\n\n```csharp\nAzureAISearchToolResource searchResource = new(\n    connectionId: searchConnectionId,\n    indexName: \"my_index\",\n    topK: 5,\n    filter: \"category eq 'documentation'\",\n    queryType: AzureAISearchQueryType.Simple\n);\n\nPersistentAgent agent = await client.Administration.CreateAgentAsync(\n    model: modelDeploymentName,\n    name: \"Search Agent\",\n    instructions: \"Search the documentation index to answer questions.\",\n    tools: [new AzureAISearchToolDefinition()],\n    toolResources: new ToolResources { AzureAISearch = searchResource }\n);\n```\n\n### 9. Cleanup\n\n```csharp\nawait client.Threads.DeleteThreadAsync(thread.Id);\nawait client.Administration.DeleteAgentAsync(agent.Id);\nawait client.VectorStores.DeleteVectorStoreAsync(vectorStore.Id);\nawait client.Files.DeleteFileAsync(file.Id);\n```\n\n## Available Tools\n\n| Tool | Class | Purpose |\n|------|-------|---------|\n| Code Interpreter | `CodeInterpreterToolDefinition` | Execute Python code, generate visualizations |\n| File Search | `FileSearchToolDefinition` | Search uploaded files via vector stores |\n| Function Calling | `FunctionToolDefinition` | Call custom functions |\n| Bing Grounding | `BingGroundingToolDefinition` | Web search via Bing |\n| Azure AI Search | `AzureAISearchToolDefinition` | Search Azure AI Search indexes |\n| OpenAPI | `OpenApiToolDefinition` | Call external APIs via OpenAPI spec |\n| Azure Functions | `AzureFunctionToolDefinition` | Invoke Azure Functions |\n| MCP | `MCPToolDefinition` | Model Context Protocol tools |\n| SharePoint | `SharepointToolDefinition` | Access SharePoint content |\n| Microsoft Fabric | `MicrosoftFabricToolDefinition` | Access Fabric data |\n\n## Streaming Update Types\n\n| Update Type | Description |\n|-------------|-------------|\n| `StreamingUpdateReason.RunCreated` | Run started |\n| `StreamingUpdateReason.RunInProgress` | Run processing |\n| `StreamingUpdateReason.RunCompleted` | Run finished |\n| `StreamingUpdateReason.RunFailed` | Run errored |\n| `MessageContentUpdate` | Text content chunk |\n| `RunStepUpdate` | Step status change |\n\n## Key Types Reference\n\n| Type | Purpose |\n|------|---------|\n| `PersistentAgentsClient` | Main entry point |\n| `PersistentAgent` | Agent with model, instructions, tools |\n| `PersistentAgentThread` | Conversation thread |\n| `PersistentThreadMessage` | Message in thread |\n| `ThreadRun` | Execution of agent against thread |\n| `RunStatus` | Queued, InProgress, RequiresAction, Completed, Failed |\n| `ToolResources` | Combined tool resources |\n| `ToolOutput` | Function call response |\n\n## Best Practices\n\n1. **Always dispose clients** — Use `using` statements or explicit disposal\n2. **Poll with appropriate delays** — 500ms recommended between status checks\n3. **Clean up resources** — Delete threads and agents when done\n4. **Handle all run statuses** — Check for `RequiresAction`, `Failed`, `Cancelled`\n5. **Use streaming for real-time UX** — Better user experience than polling\n6. **Store IDs not objects** — Reference agents\u002Fthreads by ID\n7. **Use async methods** — All operations should be async\n\n## Error Handling\n\n```csharp\nusing Azure;\n\ntry\n{\n    var agent = await client.Administration.CreateAgentAsync(...);\n}\ncatch (RequestFailedException ex) when (ex.Status == 404)\n{\n    Console.WriteLine(\"Resource not found\");\n}\ncatch (RequestFailedException ex)\n{\n    Console.WriteLine($\"Error: {ex.Status} - {ex.ErrorCode}: {ex.Message}\");\n}\n```\n\n## Related SDKs\n\n| SDK | Purpose | Install |\n|-----|---------|---------|\n| `Azure.AI.Agents.Persistent` | Low-level agents (this SDK) | `dotnet add package Azure.AI.Agents.Persistent` |\n| `Azure.AI.Projects` | High-level project client | `dotnet add package Azure.AI.Projects` |\n\n## Reference Links\n\n| Resource | URL |\n|----------|-----|\n| NuGet Package | https:\u002F\u002Fwww.nuget.org\u002Fpackages\u002FAzure.AI.Agents.Persistent |\n| API Reference | https:\u002F\u002Flearn.microsoft.com\u002Fdotnet\u002Fapi\u002Fazure.ai.agents.persistent |\n| GitHub Source | https:\u002F\u002Fgithub.com\u002FAzure\u002Fazure-sdk-for-net\u002Ftree\u002Fmain\u002Fsdk\u002Fai\u002FAzure.AI.Agents.Persistent |\n| Samples | https:\u002F\u002Fgithub.com\u002FAzure\u002Fazure-sdk-for-net\u002Ftree\u002Fmain\u002Fsdk\u002Fai\u002FAzure.AI.Agents.Persistent\u002Fsamples |\n","# Azure.AI.Agents.Persistent (.NET)\n\nLow-level SDK for creating and managing persistent AI agents with threads, messages, runs, and tools.\n\n## Installation\n\n```bash\ndotnet add package Azure.AI.Agents.Persistent --prerelease\ndotnet add package Azure.Identity\n```\n\n**Current Versions**: Stable v1.1.0, Preview v1.2.0-beta.8\n\n## Environment Variables\n\n```bash\nPROJECT_ENDPOINT=https:\u002F\u002F\u003Cresource>.services.ai.azure.com\u002Fapi\u002Fprojects\u002F\u003Cproject>  # Required: Azure AI project endpoint\nMODEL_DEPLOYMENT_NAME=gpt-4o-mini  # Required: model deployment name\nAZURE_BING_CONNECTION_ID=\u003Cbing-connection-resource-id>  # Required: Bing connection resource ID\nAZURE_AI_SEARCH_CONNECTION_ID=\u003Csearch-connection-resource-id>  # Required: Azure AI Search connection resource ID\nAZURE_TOKEN_CREDENTIALS=prod  # Required only if DefaultAzureCredential is used in production\n```\n\n## Authentication\n\n```csharp\nusing Azure.AI.Agents.Persistent;\nusing Azure.Identity;\n\nvar projectEndpoint = Environment.GetEnvironmentVariable(\"PROJECT_ENDPOINT\");\n\u002F\u002F Local dev: DefaultAzureCredential. Production: set AZURE_TOKEN_CREDENTIALS=prod or AZURE_TOKEN_CREDENTIALS=\u003Cspecific_credential>\nvar credential = new DefaultAzureCredential(\n    DefaultAzureCredential.DefaultEnvironmentVariableName\n);\n\u002F\u002F Or use a specific credential directly in production:\n\u002F\u002F See https:\u002F\u002Flearn.microsoft.com\u002Fdotnet\u002Fapi\u002Foverview\u002Fazure\u002Fidentity-readme?view=azure-dotnet#credential-classes\n\u002F\u002F var credential = new ManagedIdentityCredential();\nPersistentAgentsClient client = new(projectEndpoint, credential);\n```\n\n## Client Hierarchy\n\n```\nPersistentAgentsClient\n├── Administration  → Agent CRUD operations\n├── Threads         → Thread management\n├── Messages        → Message operations\n├── Runs            → Run execution and streaming\n├── Files           → File upload\u002Fdownload\n└── VectorStores    → Vector store management\n```\n\n## Core Workflow\n\n### 1. Create Agent\n\n```csharp\nvar modelDeploymentName = Environment.GetEnvironmentVariable(\"MODEL_DEPLOYMENT_NAME\");\n\nPersistentAgent agent = await client.Administration.CreateAgentAsync(\n    model: modelDeploymentName,\n    name: \"Math Tutor\",\n    instructions: \"You are a personal math tutor. Write and run code to answer math questions.\",\n    tools: [new CodeInterpreterToolDefinition()]\n);\n```\n\n### 2. Create Thread and Message\n\n```csharp\n\u002F\u002F Create thread\nPersistentAgentThread thread = await client.Threads.CreateThreadAsync();\n\n\u002F\u002F Create message\nawait client.Messages.CreateMessageAsync(\n    thread.Id,\n    MessageRole.User,\n    \"I need to solve the equation `3x + 11 = 14`. Can you help me?\"\n);\n```\n\n### 3. Run Agent (Polling)\n\n```csharp\n\u002F\u002F Create run\nThreadRun run = await client.Runs.CreateRunAsync(\n    thread.Id,\n    agent.Id,\n    additionalInstructions: \"Please address the user as Jane Doe.\"\n);\n\n\u002F\u002F Poll for completion\ndo\n{\n    await Task.Delay(TimeSpan.FromMilliseconds(500));\n    run = await client.Runs.GetRunAsync(thread.Id, run.Id);\n}\nwhile (run.Status == RunStatus.Queued || run.Status == RunStatus.InProgress);\n\n\u002F\u002F Retrieve messages\nawait foreach (PersistentThreadMessage message in client.Messages.GetMessagesAsync(\n    threadId: thread.Id, \n    order: ListSortOrder.Ascending))\n{\n    Console.Write($\"{message.Role}: \");\n    foreach (MessageContent content in message.ContentItems)\n    {\n        if (content is MessageTextContent textContent)\n            Console.WriteLine(textContent.Text);\n    }\n}\n```\n\n### 4. Streaming Response\n\n```csharp\nAsyncCollectionResult\u003CStreamingUpdate> stream = client.Runs.CreateRunStreamingAsync(\n    thread.Id, \n    agent.Id\n);\n\nawait foreach (StreamingUpdate update in stream)\n{\n    if (update.UpdateKind == StreamingUpdateReason.RunCreated)\n    {\n        Console.WriteLine(\"--- Run started! ---\");\n    }\n    else if (update is MessageContentUpdate contentUpdate)\n    {\n        Console.Write(contentUpdate.Text);\n    }\n    else if (update.UpdateKind == StreamingUpdateReason.RunCompleted)\n    {\n        Console.WriteLine(\"\\n--- Run completed! ---\");\n    }\n}\n```\n\n### 5. Function Calling\n\n```csharp\n\u002F\u002F Define function tool\nFunctionToolDefinition weatherTool = new(\n    name: \"getCurrentWeather\",\n    description: \"Gets the current weather at a location.\",\n    parameters: BinaryData.FromObjectAsJson(new\n    {\n        Type = \"object\",\n        Properties = new\n        {\n            Location = new { Type = \"string\", Description = \"City and state, e.g. San Francisco, CA\" },\n            Unit = new { Type = \"string\", Enum = new[] { \"c\", \"f\" } }\n        },\n        Required = new[] { \"location\" }\n    }, new JsonSerializerOptions { PropertyNamingPolicy = JsonNamingPolicy.CamelCase })\n);\n\n\u002F\u002F Create agent with function\nPersistentAgent agent = await client.Administration.CreateAgentAsync(\n    model: modelDeploymentName,\n    name: \"Weather Bot\",\n    instructions: \"You are a weather bot.\",\n    tools: [weatherTool]\n);\n\n\u002F\u002F Handle function calls during polling\ndo\n{\n    await Task.Delay(500);\n    run = await client.Runs.GetRunAsync(thread.Id, run.Id);\n\n    if (run.Status == RunStatus.RequiresAction \n        && run.RequiredAction is SubmitToolOutputsAction submitAction)\n    {\n        List\u003CToolOutput> outputs = [];\n        foreach (RequiredToolCall toolCall in submitAction.ToolCalls)\n        {\n            if (toolCall is RequiredFunctionToolCall funcCall)\n            {\n                \u002F\u002F Execute function and get result\n                string result = ExecuteFunction(funcCall.Name, funcCall.Arguments);\n                outputs.Add(new ToolOutput(toolCall, result));\n            }\n        }\n        run = await client.Runs.SubmitToolOutputsToRunAsync(run, outputs, toolApprovals: null);\n    }\n}\nwhile (run.Status == RunStatus.Queued || run.Status == RunStatus.InProgress);\n```\n\n### 6. File Search with Vector Store\n\n```csharp\n\u002F\u002F Upload file\nPersistentAgentFileInfo file = await client.Files.UploadFileAsync(\n    filePath: \"document.txt\",\n    purpose: PersistentAgentFilePurpose.Agents\n);\n\n\u002F\u002F Create vector store\nPersistentAgentsVectorStore vectorStore = await client.VectorStores.CreateVectorStoreAsync(\n    fileIds: [file.Id],\n    name: \"my_vector_store\"\n);\n\n\u002F\u002F Create file search resource\nFileSearchToolResource fileSearchResource = new();\nfileSearchResource.VectorStoreIds.Add(vectorStore.Id);\n\n\u002F\u002F Create agent with file search\nPersistentAgent agent = await client.Administration.CreateAgentAsync(\n    model: modelDeploymentName,\n    name: \"Document Assistant\",\n    instructions: \"You help users find information in documents.\",\n    tools: [new FileSearchToolDefinition()],\n    toolResources: new ToolResources { FileSearch = fileSearchResource }\n);\n```\n\n### 7. Bing Grounding\n\n```csharp\nvar bingConnectionId = Environment.GetEnvironmentVariable(\"AZURE_BING_CONNECTION_ID\");\n\nBingGroundingToolDefinition bingTool = new(\n    new BingGroundingSearchToolParameters(\n        [new BingGroundingSearchConfiguration(bingConnectionId)]\n    )\n);\n\nPersistentAgent agent = await client.Administration.CreateAgentAsync(\n    model: modelDeploymentName,\n    name: \"Search Agent\",\n    instructions: \"Use Bing to answer questions about current events.\",\n    tools: [bingTool]\n);\n```\n\n### 8. Azure AI Search\n\n```csharp\nAzureAISearchToolResource searchResource = new(\n    connectionId: searchConnectionId,\n    indexName: \"my_index\",\n    topK: 5,\n    filter: \"category eq 'documentation'\",\n    queryType: AzureAISearchQueryType.Simple\n);\n\nPersistentAgent agent = await client.Administration.CreateAgentAsync(\n    model: modelDeploymentName,\n    name: \"Search Agent\",\n    instructions: \"Search the documentation index to answer questions.\",\n    tools: [new AzureAISearchToolDefinition()],\n    toolResources: new ToolResources { AzureAISearch = searchResource }\n);\n```\n\n### 9. Cleanup\n\n```csharp\nawait client.Threads.DeleteThreadAsync(thread.Id);\nawait client.Administration.DeleteAgentAsync(agent.Id);\nawait client.VectorStores.DeleteVectorStoreAsync(vectorStore.Id);\nawait client.Files.DeleteFileAsync(file.Id);\n```\n\n## Available Tools\n\n| Tool | Class | Purpose |\n|------|-------|---------|\n| Code Interpreter | `CodeInterpreterToolDefinition` | Execute Python code, generate visualizations |\n| File Search | `FileSearchToolDefinition` | Search uploaded files via vector stores |\n| Function Calling | `FunctionToolDefinition` | Call custom functions |\n| Bing Grounding | `BingGroundingToolDefinition` | Web search via Bing |\n| Azure AI Search | `AzureAISearchToolDefinition` | Search Azure AI Search indexes |\n| OpenAPI | `OpenApiToolDefinition` | Call external APIs via OpenAPI spec |\n| Azure Functions | `AzureFunctionToolDefinition` | Invoke Azure Functions |\n| MCP | `MCPToolDefinition` | Model Context Protocol tools |\n| SharePoint | `SharepointToolDefinition` | Access SharePoint content |\n| Microsoft Fabric | `MicrosoftFabricToolDefinition` | Access Fabric data |\n\n## Streaming Update Types\n\n| Update Type | Description |\n|-------------|-------------|\n| `StreamingUpdateReason.RunCreated` | Run started |\n| `StreamingUpdateReason.RunInProgress` | Run processing |\n| `StreamingUpdateReason.RunCompleted` | Run finished |\n| `StreamingUpdateReason.RunFailed` | Run errored |\n| `MessageContentUpdate` | Text content chunk |\n| `RunStepUpdate` | Step status change |\n\n## Key Types Reference\n\n| Type | Purpose |\n|------|---------|\n| `PersistentAgentsClient` | Main entry point |\n| `PersistentAgent` | Agent with model, instructions, tools |\n| `PersistentAgentThread` | Conversation thread |\n| `PersistentThreadMessage` | Message in thread |\n| `ThreadRun` | Execution of agent against thread |\n| `RunStatus` | Queued, InProgress, RequiresAction, Completed, Failed |\n| `ToolResources` | Combined tool resources |\n| `ToolOutput` | Function call response |\n\n## Best Practices\n\n1. **Always dispose clients** — Use `using` statements or explicit disposal\n2. **Poll with appropriate delays** — 500ms recommended between status checks\n3. **Clean up resources** — Delete threads and agents when done\n4. **Handle all run statuses** — Check for `RequiresAction`, `Failed`, `Cancelled`\n5. **Use streaming for real-time UX** — Better user experience than polling\n6. **Store IDs not objects** — Reference agents\u002Fthreads by ID\n7. **Use async methods** — All operations should be async\n\n## Error Handling\n\n```csharp\nusing Azure;\n\ntry\n{\n    var agent = await client.Administration.CreateAgentAsync(...);\n}\ncatch (RequestFailedException ex) when (ex.Status == 404)\n{\n    Console.WriteLine(\"Resource not found\");\n}\ncatch (RequestFailedException ex)\n{\n    Console.WriteLine($\"Error: {ex.Status} - {ex.ErrorCode}: {ex.Message}\");\n}\n```\n\n## Related SDKs\n\n| SDK | Purpose | Install |\n|-----|---------|---------|\n| `Azure.AI.Agents.Persistent` | Low-level agents (this SDK) | `dotnet add package Azure.AI.Agents.Persistent` |\n| `Azure.AI.Projects` | High-level project client | `dotnet add package Azure.AI.Projects` |\n\n## Reference Links\n\n| Resource | URL |\n|----------|-----|\n| NuGet Package | https:\u002F\u002Fwww.nuget.org\u002Fpackages\u002FAzure.AI.Agents.Persistent |\n| API Reference | https:\u002F\u002Flearn.microsoft.com\u002Fdotnet\u002Fapi\u002Fazure.ai.agents.persistent |\n| GitHub Source | https:\u002F\u002Fgithub.com\u002FAzure\u002Fazure-sdk-for-net\u002Ftree\u002Fmain\u002Fsdk\u002Fai\u002FAzure.AI.Agents.Persistent |\n| Samples | https:\u002F\u002Fgithub.com\u002FAzure\u002Fazure-sdk-for-net\u002Ftree\u002Fmain\u002Fsdk\u002Fai\u002FAzure.AI.Agents.Persistent\u002Fsamples |\n",{"name":5,"license":15,"metadata":50,"description":53},{"author":12,"package":51,"version":52},"Azure.AI.Agents.Persistent","1.0.0","Azure AI Agents Persistent SDK for .NET. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools. Use for agent CRUD, conversation threads, streaming responses, function calling, file search, and code interpreter. Triggers: \"PersistentAgentsClient\", \"persistent agents\", \"agent threads\", \"agent runs\", \"streaming agents\", \"function calling agents .NET\".\n","main","3f5b461b2314e01c400564051e92469114c5b68f",".github\u002Fplugins\u002Fazure-sdk-dotnet\u002Fskills\u002Fazure-ai-agents-persistent-dotnet",366,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills","https:\u002F\u002Fmicrosoft.github.io\u002Fskills\u002F","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-13 02:10:26",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add microsoft\u002Fskills --skill azure-ai-agents-persistent-dotnet",{"tool":70,"command":71},"bunx","bunx skills add microsoft\u002Fskills --skill azure-ai-agents-persistent-dotnet",{"tool":73,"command":74},"pnpm","pnpm dlx skills add microsoft\u002Fskills --skill azure-ai-agents-persistent-dotnet","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-sdk-dotnet\u002Fskills\u002Fazure-ai-agents-persistent-dotnet\u002FSKILL.md",true,[],[79,102,139,166,185,223],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":86,"publishedAt":45},"01M69B4JCRQV5SPXAFCKXQRV0H","skill-creator","Guide for creating effective skills for AI coding agents working with Azure SDKs and Microsoft Foundry services. Use when creating new skills or updating existing skills.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fskill-creator\u002FSKILL.md",[85],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[87,88,89,9,90,91,92,26,93,94,95,37,96,97,98,30,99,100,101],"skill creator","creator","coding agents","foundry","microsoft foundry","ai coding agents","services","coding","guide","ai coding","with","sdks","Existing","when","new",{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":118,"publishedAt":45},"01M69B4FD57V1MYKRWAJJECTZ7","podcast-generation","Generate AI-powered podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model via WebSocket. Use when building text-to-speech features, audio narrative generation, podcast creation from content, or integrating with Azure OpenAI Realtime API for real audio output. Covers full-stack implementation from React frontend to Python FastAPI backend with WebSocket streaming.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fpodcast-generation\u002FSKILL.md",[108,111,114,117],{"categoryNo":109,"categoryName":110,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":112,"categoryName":113,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":115,"categoryName":116,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[119,120,121,122,123,124,125,26,126,127,41,128,129,130,131,132,133,134,135,136,137,100,138],"podcast generation","podcast","generation","frontend","python","react","realtime","azure openai","generate","api","Audio","stack","text","model","fastapi","creation","python fastapi","narrative","features","fastapi backend",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":146,"publishedAt":45},"01M69B4CYPM5SESY5ZWEFDXEQZ","microsoft-docs","Understand Microsoft technologies by querying official documentation. Use whenever the user asks how something works, wants tutorials, needs configuration options, limits, quotas, or best practices for any Microsoft technology (Azure, .NET, M365, Windows, Power Platform, etc.)—even if they don't mention \"docs.\" If the question is about understanding a concept rather than writing code, this is the right skill.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fmicrosoft-docs\u002FSKILL.md",[145],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[147,9,148,149,150,151,152,153,154,155,156,26,157,158,159,37,160,67,161,162,163,164,165,30],"docs","microsoft docs","MCP","writing","cli","mcp server","windows","power platform","official","documentation","learn","best practices","question","power","back","technology","platform","learn mcp","concept",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":173,"publishedAt":45},"01M69B49C3YPD1ZJ3NC0HPCY58","mcp-builder","Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP), Node\u002FTypeScript (MCP SDK), or C#\u002F.NET (Microsoft MCP SDK).","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fmcp-builder\u002FSKILL.md",[172],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[149,174,175,176,123,177,44,178,9,179,29,132,180,181,95,37,182,183,184,97,30,100],"mcp builder","builder","typescript","llms","model context protocol","fastmcp","node","context","integrate","mcp sdk","building mcp servers",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":203,"publishedAt":45},"01M69B467A7CDMFQ0T6Q0ZA12Q","kql","KQL language expertise for writing correct, efficient Kusto Query Language queries. Covers syntax gotchas, join patterns, dynamic types, datetime pitfalls, regex patterns, serialization, memory management, result-size discipline, and advanced functions (geo, vector, graph). USE THIS SKILL whenever writing, debugging, or reviewing KQL queries — even simple ones — because the gotchas section prevents the most common errors that waste tool calls and cause expensive retry cascades. Trigger on: KQL, Kusto, ADX, Azure Data Explorer, Fabric Real-Time Intelligence, EventHouse, Log Analytics, log analysis, data exploration, time series, anomaly detection, summarize, where clause, join, extend, project, let statement, parse operator, extract function, any mention of pipe-forward query syntax.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fkql\u002FSKILL.md",[191,194,195,200],{"categoryNo":192,"categoryName":193,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":196,"categoryName":197,"taxonomyType":198,"taxonomyTypeDesc":199},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",{"categoryNo":201,"categoryName":202,"taxonomyType":198,"taxonomyTypeDesc":199},"01JBSEEDCAT000000000000036","内容创作者",[187,150,204,205,206,26,207,208,209,210,211,212,213,214,215,216,217,218,219,30,220,221,222],"summarize","memory","analytics","vector","time series","tool","discipline","log","geo","exploration","pipe","time","project","regex","join","datetime","section","anomaly","parse",{"skillNo":224,"name":225,"nameZh":6,"description":226,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":227,"categories":228,"keywords":229,"publishedAt":45},"01M69B44HJQ7897EZ7NE7DWQX3","github-issue-creator","Convert raw notes, error logs, voice dictation, or screenshots into crisp GitHub-flavored markdown issue reports. Use when the user pastes bug info, error messages, or informal descriptions and wants a structured GitHub issue. Supports images\u002FGIFs for visual evidence.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fgithub-issue-creator\u002FSKILL.md",[],[230,231,232,233,88,234,235,236,237,238,40,239,37,240,241,242,243,244,245,30,100],"github","github issue creator","github issue","issue","issue creator","screenshots","notes","logs","error messages","convert","evidence","reports","images","info","visual","error"]