@octavus/docs 2.13.0 → 2.15.0

package/dist/{chunk-Z5E72EIS.js → chunk-2UFDUNPK.js}

@@ -14,7 +14,7 @@ var docs_default = [
     section: "getting-started",
     title: "Quick Start",
     description: "Get your first Octavus agent running in minutes.",
-    content: "\n# Quick Start\n\nThis guide will walk you through integrating Octavus into your application in under 10 minutes.\n\n## Prerequisites\n\n- Node.js 18+\n- An Octavus account with API key\n- A Next.js application (or any Node.js backend)\n\n## Test Your Agent First\n\nBefore integrating with SDKs, use **Agent Preview** to test your agent directly in the platform:\n\n1. Open your agent in the platform at `octavus.ai/agents/[agentId]`\n2. Click the **Preview** tab\n3. Configure session inputs and tool mock responses\n4. Start a conversation to test agent behavior\n\nAgent Preview supports all trigger types, file attachments, tool mocking, and real-time streaming. This is the fastest way to iterate on your agent logic before writing any integration code.\n\n## Installation\n\nInstall the Octavus SDKs in your project:\n\n```bash\n# Server SDK for backend\nnpm install @octavus/server-sdk\n\n# React bindings for frontend\nnpm install @octavus/react\n```\n\n## Backend Setup\n\n### 1. Initialize the Client\n\nCreate an Octavus client instance in your backend:\n\n```typescript\n// lib/octavus.ts\nimport { OctavusClient } from '@octavus/server-sdk';\n\nexport const octavus = new OctavusClient({\n  baseUrl: process.env.OCTAVUS_API_URL!,\n  apiKey: process.env.OCTAVUS_API_KEY!,\n});\n```\n\n### 2. Create a Session Endpoint\n\nCreate an API endpoint that creates sessions and returns the session ID:\n\n```typescript\n// app/api/chat/create/route.ts\nimport { NextResponse } from 'next/server';\nimport { octavus } from '@/lib/octavus';\n\n// Agent ID - get from platform or CLI (see below)\nconst SUPPORT_AGENT_ID = process.env.OCTAVUS_SUPPORT_AGENT_ID!;\n\nexport async function POST(request: Request) {\n  const { input } = await request.json();\n\n  // Create a new session using the agent ID\n  const sessionId = await octavus.agentSessions.create(SUPPORT_AGENT_ID, input);\n\n  return NextResponse.json({ sessionId });\n}\n```\n\n### Getting Your Agent ID\n\nThere are two ways to create and manage agents:\n\n**Option 1: Platform UI (Recommended for getting started)**\n\n1. Go to [octavus.ai](https://octavus.ai) and create an agent in the web editor\n2. Copy the agent ID from the URL (e.g., `octavus.ai/agents/clxyz123abc456`)\n3. Add it to your `.env.local`: `OCTAVUS_SUPPORT_AGENT_ID=clxyz123abc456`\n\n**Option 2: Local Development with CLI**\n\nFor version-controlled agent definitions, use the [Octavus CLI](/docs/server-sdk/cli):\n\n```bash\nnpm install --save-dev @octavus/cli\noctavus sync ./agents/support-chat\n# Output: Agent ID: clxyz123abc456\n```\n\nThe CLI approach is better for teams and CI/CD pipelines where you want agent definitions in your repository.\n\n### 3. Create a Trigger Endpoint\n\nCreate an endpoint that handles triggers and streams responses:\n\n```typescript\n// app/api/trigger/route.ts\nimport { toSSEStream } from '@octavus/server-sdk';\nimport { octavus } from '@/lib/octavus';\n\nexport async function POST(request: Request) {\n  const body = await request.json();\n  const { sessionId, ...payload } = body;\n\n  // Attach to session with tool handlers\n  const session = octavus.agentSessions.attach(sessionId, {\n    tools: {\n      // Define tool handlers that run on your server\n      'get-user-account': async (args) => {\n        const userId = args.userId as string;\n        // Fetch from your database\n        return {\n          name: 'Demo User',\n          email: 'demo@example.com',\n          plan: 'pro',\n        };\n      },\n      'create-support-ticket': async (args) => {\n        // Create ticket in your system\n        return {\n          ticketId: 'TICKET-123',\n          estimatedResponse: '24 hours',\n        };\n      },\n    },\n  });\n\n  // Execute the request and convert to SSE stream\n  const events = session.execute(payload, { signal: request.signal });\n\n  // Return as streaming response\n  return new Response(toSSEStream(events), {\n    headers: {\n      'Content-Type': 'text/event-stream',\n      'Cache-Control': 'no-cache',\n      Connection: 'keep-alive',\n    },\n  });\n}\n```\n\n## Frontend Setup\n\n### 1. Create a Chat Component\n\nUse the `useOctavusChat` hook with the HTTP transport:\n\n```tsx\n// components/chat.tsx\n'use client';\n\nimport { useState, useMemo } from 'react';\nimport { useOctavusChat, createHttpTransport, type UIMessage } from '@octavus/react';\n\ninterface ChatProps {\n  sessionId: string;\n}\n\nexport function Chat({ sessionId }: ChatProps) {\n  const [inputValue, setInputValue] = useState('');\n\n  // Create a stable transport instance\n  const transport = useMemo(\n    () =>\n      createHttpTransport({\n        request: (payload, options) =>\n          fetch('/api/trigger', {\n            method: 'POST',\n            headers: { 'Content-Type': 'application/json' },\n            body: JSON.stringify({ sessionId, ...payload }),\n            signal: options?.signal,\n          }),\n      }),\n    [sessionId],\n  );\n\n  const { messages, status, error, send } = useOctavusChat({ transport });\n\n  const isStreaming = status === 'streaming';\n\n  const handleSubmit = async (e: React.FormEvent) => {\n    e.preventDefault();\n    if (!inputValue.trim() || isStreaming) return;\n\n    const message = inputValue.trim();\n    setInputValue('');\n\n    // Add user message and trigger in one call\n    await send('user-message', { USER_MESSAGE: message }, { userMessage: { content: message } });\n  };\n\n  return (\n    <div className=\"flex flex-col h-full\">\n      {/* Messages */}\n      <div className=\"flex-1 overflow-y-auto p-4 space-y-4\">\n        {messages.map((msg) => (\n          <MessageBubble key={msg.id} message={msg} />\n        ))}\n      </div>\n\n      {/* Input */}\n      <form onSubmit={handleSubmit} className=\"p-4 border-t\">\n        <div className=\"flex gap-2\">\n          <input\n            type=\"text\"\n            value={inputValue}\n            onChange={(e) => setInputValue(e.target.value)}\n            placeholder=\"Type a message...\"\n            className=\"flex-1 px-4 py-2 border rounded-lg\"\n            disabled={isStreaming}\n          />\n          <button\n            type=\"submit\"\n            disabled={isStreaming}\n            className=\"px-4 py-2 bg-blue-500 text-white rounded-lg disabled:opacity-50\"\n          >\n            Send\n          </button>\n        </div>\n      </form>\n    </div>\n  );\n}\n\nfunction MessageBubble({ message }: { message: UIMessage }) {\n  const isUser = message.role === 'user';\n\n  return (\n    <div className={`flex ${isUser ? 'justify-end' : 'justify-start'}`}>\n      <div\n        className={`p-3 rounded-lg max-w-md ${isUser ? 'bg-blue-500 text-white' : 'bg-gray-100'}`}\n      >\n        {message.parts.map((part, i) => {\n          if (part.type === 'text') {\n            return <p key={i}>{part.text}</p>;\n          }\n          return null;\n        })}\n\n        {/* Streaming indicator */}\n        {message.status === 'streaming' && (\n          <span className=\"inline-block w-2 h-4 bg-gray-400 animate-pulse ml-1\" />\n        )}\n      </div>\n    </div>\n  );\n}\n```\n\n### 2. Create Session and Render Chat\n\n```tsx\n// app/chat/page.tsx\n'use client';\n\nimport { useEffect, useState } from 'react';\nimport { Chat } from '@/components/chat';\n\nexport default function ChatPage() {\n  const [sessionId, setSessionId] = useState<string | null>(null);\n\n  useEffect(() => {\n    async function createSession() {\n      const response = await fetch('/api/chat/create', {\n        method: 'POST',\n        headers: { 'Content-Type': 'application/json' },\n        body: JSON.stringify({\n          input: {\n            COMPANY_NAME: 'Acme Corp',\n            PRODUCT_NAME: 'Widget Pro',\n          },\n        }),\n      });\n      const { sessionId } = await response.json();\n      setSessionId(sessionId);\n    }\n\n    createSession();\n  }, []);\n\n  if (!sessionId) {\n    return <div>Loading...</div>;\n  }\n\n  return <Chat sessionId={sessionId} />;\n}\n```\n\n## Environment Variables\n\nAdd these to your `.env.local`:\n\n```bash\nOCTAVUS_API_URL=https://octavus.ai\nOCTAVUS_API_KEY=your-api-key-here\n```\n\n## What's Next?\n\nNow that you have a basic integration working:\n\n- [Learn about the protocol](/docs/protocol/overview) to define custom agent behavior\n- [Explore the Server SDK](/docs/server-sdk/overview) for advanced backend features\n- [Build rich UIs](/docs/client-sdk/overview) with the Client SDK\n- [Handle tools on the client](/docs/client-sdk/client-tools) for interactive UIs and browser APIs\n",
+    content: "\n# Quick Start\n\nThis guide will walk you through integrating Octavus into your application in under 10 minutes.\n\n## Prerequisites\n\n- Node.js 18+\n- An Octavus account with API key\n- A Next.js application (or any Node.js backend)\n\n## Test Your Agent First\n\nBefore integrating with SDKs, use **Agent Preview** to test your agent directly in the platform:\n\n1. Open your agent in the platform at `octavus.ai/platform/agents/[agentId]`\n2. Click the **Preview** tab\n3. Configure session inputs and tool mock responses\n4. Start a conversation to test agent behavior\n\nAgent Preview supports all trigger types, file attachments, tool mocking, and real-time streaming. This is the fastest way to iterate on your agent logic before writing any integration code.\n\n## Installation\n\nInstall the Octavus SDKs in your project:\n\n```bash\n# Server SDK for backend\nnpm install @octavus/server-sdk\n\n# React bindings for frontend\nnpm install @octavus/react\n```\n\n## Backend Setup\n\n### 1. Initialize the Client\n\nCreate an Octavus client instance in your backend:\n\n```typescript\n// lib/octavus.ts\nimport { OctavusClient } from '@octavus/server-sdk';\n\nexport const octavus = new OctavusClient({\n  baseUrl: process.env.OCTAVUS_API_URL!,\n  apiKey: process.env.OCTAVUS_API_KEY!,\n});\n```\n\n### 2. Create a Session Endpoint\n\nCreate an API endpoint that creates sessions and returns the session ID:\n\n```typescript\n// app/api/chat/create/route.ts\nimport { NextResponse } from 'next/server';\nimport { octavus } from '@/lib/octavus';\n\n// Agent ID - get from platform or CLI (see below)\nconst SUPPORT_AGENT_ID = process.env.OCTAVUS_SUPPORT_AGENT_ID!;\n\nexport async function POST(request: Request) {\n  const { input } = await request.json();\n\n  // Create a new session using the agent ID\n  const sessionId = await octavus.agentSessions.create(SUPPORT_AGENT_ID, input);\n\n  return NextResponse.json({ sessionId });\n}\n```\n\n### Getting Your Agent ID\n\nThere are two ways to create and manage agents:\n\n**Option 1: Platform UI (Recommended for getting started)**\n\n1. Go to [octavus.ai](https://octavus.ai) and create an agent in the web editor\n2. Copy the agent ID from the URL (e.g., `octavus.ai/platform/agents/clxyz123abc456`)\n3. Add it to your `.env.local`: `OCTAVUS_SUPPORT_AGENT_ID=clxyz123abc456`\n\n**Option 2: Local Development with CLI**\n\nFor version-controlled agent definitions, use the [Octavus CLI](/docs/server-sdk/cli):\n\n```bash\nnpm install --save-dev @octavus/cli\noctavus sync ./agents/support-chat\n# Output: Agent ID: clxyz123abc456\n```\n\nThe CLI approach is better for teams and CI/CD pipelines where you want agent definitions in your repository.\n\n### 3. Create a Trigger Endpoint\n\nCreate an endpoint that handles triggers and streams responses:\n\n```typescript\n// app/api/trigger/route.ts\nimport { toSSEStream } from '@octavus/server-sdk';\nimport { octavus } from '@/lib/octavus';\n\nexport async function POST(request: Request) {\n  const body = await request.json();\n  const { sessionId, ...payload } = body;\n\n  // Attach to session with tool handlers\n  const session = octavus.agentSessions.attach(sessionId, {\n    tools: {\n      // Define tool handlers that run on your server\n      'get-user-account': async (args) => {\n        const userId = args.userId as string;\n        // Fetch from your database\n        return {\n          name: 'Demo User',\n          email: 'demo@example.com',\n          plan: 'pro',\n        };\n      },\n      'create-support-ticket': async (args) => {\n        // Create ticket in your system\n        return {\n          ticketId: 'TICKET-123',\n          estimatedResponse: '24 hours',\n        };\n      },\n    },\n  });\n\n  // Execute the request and convert to SSE stream\n  const events = session.execute(payload, { signal: request.signal });\n\n  // Return as streaming response\n  return new Response(toSSEStream(events), {\n    headers: {\n      'Content-Type': 'text/event-stream',\n      'Cache-Control': 'no-cache',\n      Connection: 'keep-alive',\n    },\n  });\n}\n```\n\n## Frontend Setup\n\n### 1. Create a Chat Component\n\nUse the `useOctavusChat` hook with the HTTP transport:\n\n```tsx\n// components/chat.tsx\n'use client';\n\nimport { useState, useMemo } from 'react';\nimport { useOctavusChat, createHttpTransport, type UIMessage } from '@octavus/react';\n\ninterface ChatProps {\n  sessionId: string;\n}\n\nexport function Chat({ sessionId }: ChatProps) {\n  const [inputValue, setInputValue] = useState('');\n\n  // Create a stable transport instance\n  const transport = useMemo(\n    () =>\n      createHttpTransport({\n        request: (payload, options) =>\n          fetch('/api/trigger', {\n            method: 'POST',\n            headers: { 'Content-Type': 'application/json' },\n            body: JSON.stringify({ sessionId, ...payload }),\n            signal: options?.signal,\n          }),\n      }),\n    [sessionId],\n  );\n\n  const { messages, status, error, send } = useOctavusChat({ transport });\n\n  const isStreaming = status === 'streaming';\n\n  const handleSubmit = async (e: React.FormEvent) => {\n    e.preventDefault();\n    if (!inputValue.trim() || isStreaming) return;\n\n    const message = inputValue.trim();\n    setInputValue('');\n\n    // Add user message and trigger in one call\n    await send('user-message', { USER_MESSAGE: message }, { userMessage: { content: message } });\n  };\n\n  return (\n    <div className=\"flex flex-col h-full\">\n      {/* Messages */}\n      <div className=\"flex-1 overflow-y-auto p-4 space-y-4\">\n        {messages.map((msg) => (\n          <MessageBubble key={msg.id} message={msg} />\n        ))}\n      </div>\n\n      {/* Input */}\n      <form onSubmit={handleSubmit} className=\"p-4 border-t\">\n        <div className=\"flex gap-2\">\n          <input\n            type=\"text\"\n            value={inputValue}\n            onChange={(e) => setInputValue(e.target.value)}\n            placeholder=\"Type a message...\"\n            className=\"flex-1 px-4 py-2 border rounded-lg\"\n            disabled={isStreaming}\n          />\n          <button\n            type=\"submit\"\n            disabled={isStreaming}\n            className=\"px-4 py-2 bg-blue-500 text-white rounded-lg disabled:opacity-50\"\n          >\n            Send\n          </button>\n        </div>\n      </form>\n    </div>\n  );\n}\n\nfunction MessageBubble({ message }: { message: UIMessage }) {\n  const isUser = message.role === 'user';\n\n  return (\n    <div className={`flex ${isUser ? 'justify-end' : 'justify-start'}`}>\n      <div\n        className={`p-3 rounded-lg max-w-md ${isUser ? 'bg-blue-500 text-white' : 'bg-gray-100'}`}\n      >\n        {message.parts.map((part, i) => {\n          if (part.type === 'text') {\n            return <p key={i}>{part.text}</p>;\n          }\n          return null;\n        })}\n\n        {/* Streaming indicator */}\n        {message.status === 'streaming' && (\n          <span className=\"inline-block w-2 h-4 bg-gray-400 animate-pulse ml-1\" />\n        )}\n      </div>\n    </div>\n  );\n}\n```\n\n### 2. Create Session and Render Chat\n\n```tsx\n// app/chat/page.tsx\n'use client';\n\nimport { useEffect, useState } from 'react';\nimport { Chat } from '@/components/chat';\n\nexport default function ChatPage() {\n  const [sessionId, setSessionId] = useState<string | null>(null);\n\n  useEffect(() => {\n    async function createSession() {\n      const response = await fetch('/api/chat/create', {\n        method: 'POST',\n        headers: { 'Content-Type': 'application/json' },\n        body: JSON.stringify({\n          input: {\n            COMPANY_NAME: 'Acme Corp',\n            PRODUCT_NAME: 'Widget Pro',\n          },\n        }),\n      });\n      const { sessionId } = await response.json();\n      setSessionId(sessionId);\n    }\n\n    createSession();\n  }, []);\n\n  if (!sessionId) {\n    return <div>Loading...</div>;\n  }\n\n  return <Chat sessionId={sessionId} />;\n}\n```\n\n## Environment Variables\n\nAdd these to your `.env.local`:\n\n```bash\nOCTAVUS_API_URL=https://octavus.ai\nOCTAVUS_API_KEY=your-api-key-here\n```\n\n## What's Next?\n\nNow that you have a basic integration working:\n\n- [Learn about the protocol](/docs/protocol/overview) to define custom agent behavior\n- [Explore the Server SDK](/docs/server-sdk/overview) for advanced backend features\n- [Build rich UIs](/docs/client-sdk/overview) with the Client SDK\n- [Handle tools on the client](/docs/client-sdk/client-tools) for interactive UIs and browser APIs\n",
     excerpt: "Quick Start This guide will walk you through integrating Octavus into your application in under 10 minutes.  Prerequisites - Node.js 18+ - An Octavus account with API key - A Next.js application (or...",
     order: 2
   },
@@ -23,7 +23,7 @@ var docs_default = [
     section: "server-sdk",
     title: "Overview",
     description: "Introduction to the Octavus Server SDK for backend integration.",
-    content: "\n# Server SDK Overview\n\nThe `@octavus/server-sdk` package provides a Node.js SDK for integrating Octavus agents into your backend application. It handles session management, streaming, and the tool execution continuation loop.\n\n**Current version:** `2.12.0`\n\n## Installation\n\n```bash\nnpm install @octavus/server-sdk\n```\n\nFor agent management (sync, validate), install the CLI as a dev dependency:\n\n```bash\nnpm install --save-dev @octavus/cli\n```\n\n## Basic Usage\n\n```typescript\nimport { OctavusClient } from '@octavus/server-sdk';\n\nconst client = new OctavusClient({\n  baseUrl: 'https://octavus.ai',\n  apiKey: 'your-api-key',\n});\n```\n\n## Key Features\n\n### Agent Management\n\nAgent definitions are managed via the CLI. See the [CLI documentation](/docs/server-sdk/cli) for details.\n\n```bash\n# Sync agent from local files\noctavus sync ./agents/support-chat\n\n# Output: Created: support-chat\n#         Agent ID: clxyz123abc456\n```\n\n### Session Management\n\nCreate and manage agent sessions using the agent ID:\n\n```typescript\n// Create a new session (use agent ID from CLI sync)\nconst sessionId = await client.agentSessions.create('clxyz123abc456', {\n  COMPANY_NAME: 'Acme Corp',\n  PRODUCT_NAME: 'Widget Pro',\n});\n\n// Get UI-ready session messages (for session restore)\nconst session = await client.agentSessions.getMessages(sessionId);\n```\n\n### Tool Handlers\n\nTools run on your server with your data:\n\n```typescript\nconst session = client.agentSessions.attach(sessionId, {\n  tools: {\n    'get-user-account': async (args) => {\n      // Access your database, APIs, etc.\n      return await db.users.findById(args.userId);\n    },\n  },\n});\n```\n\n### Streaming\n\nAll responses stream in real-time:\n\n```typescript\nimport { toSSEStream } from '@octavus/server-sdk';\n\n// execute() returns an async generator of events\nconst events = session.execute({\n  type: 'trigger',\n  triggerName: 'user-message',\n  input: { USER_MESSAGE: 'Hello!' },\n});\n\n// Convert to SSE stream for HTTP responses\nreturn new Response(toSSEStream(events), {\n  headers: { 'Content-Type': 'text/event-stream' },\n});\n```\n\n### Workers\n\nExecute worker agents for task-based processing:\n\n```typescript\n// Non-streaming: get the output directly\nconst { output } = await client.workers.generate(agentId, {\n  TOPIC: 'AI safety',\n});\n\n// Streaming: observe events in real-time\nfor await (const event of client.workers.execute(agentId, input)) {\n  // Handle stream events\n}\n```\n\n## API Reference\n\n### OctavusClient\n\nThe main entry point for interacting with Octavus.\n\n```typescript\ninterface OctavusClientConfig {\n  baseUrl: string; // Octavus API URL\n  apiKey?: string; // Your API key\n  traceModelRequests?: boolean; // Enable model request tracing (default: false)\n}\n\nclass OctavusClient {\n  readonly agents: AgentsApi;\n  readonly agentSessions: AgentSessionsApi;\n  readonly workers: WorkersApi;\n  readonly files: FilesApi;\n\n  constructor(config: OctavusClientConfig);\n}\n```\n\n### AgentSessionsApi\n\nManages agent sessions.\n\n```typescript\nclass AgentSessionsApi {\n  // Create a new session\n  async create(agentId: string, input?: Record<string, unknown>): Promise<string>;\n\n  // Get full session state (for debugging/internal use)\n  async get(sessionId: string): Promise<SessionState>;\n\n  // Get UI-ready messages (for client display)\n  async getMessages(sessionId: string): Promise<UISessionState>;\n\n  // Attach to a session for triggering\n  attach(sessionId: string, options?: SessionAttachOptions): AgentSession;\n}\n\n// Full session state (internal format)\ninterface SessionState {\n  id: string;\n  agentId: string;\n  input: Record<string, unknown>;\n  variables: Record<string, unknown>;\n  resources: Record<string, unknown>;\n  messages: ChatMessage[]; // Internal message format\n  createdAt: string;\n  updatedAt: string;\n}\n\n// UI-ready session state\ninterface UISessionState {\n  sessionId: string;\n  agentId: string;\n  messages: UIMessage[]; // UI-ready messages for frontend\n}\n```\n\n### AgentSession\n\nHandles request execution and streaming for a specific session.\n\n```typescript\nclass AgentSession {\n  // Execute a request and stream parsed events\n  execute(request: SessionRequest, options?: TriggerOptions): AsyncGenerator<StreamEvent>;\n\n  // Get the session ID\n  getSessionId(): string;\n}\n\ntype SessionRequest = TriggerRequest | ContinueRequest;\n\ninterface TriggerRequest {\n  type: 'trigger';\n  triggerName: string;\n  input?: Record<string, unknown>;\n}\n\ninterface ContinueRequest {\n  type: 'continue';\n  executionId: string;\n  toolResults: ToolResult[];\n}\n\n// Helper to convert events to SSE stream\nfunction toSSEStream(events: AsyncIterable<StreamEvent>): ReadableStream<Uint8Array>;\n```\n\n### FilesApi\n\nHandles file uploads for sessions.\n\n```typescript\nclass FilesApi {\n  // Get presigned URLs for file uploads\n  async getUploadUrls(sessionId: string, files: FileUploadRequest[]): Promise<UploadUrlsResponse>;\n}\n\ninterface FileUploadRequest {\n  filename: string;\n  mediaType: string;\n  size: number;\n}\n\ninterface UploadUrlsResponse {\n  files: {\n    id: string; // File ID for references\n    uploadUrl: string; // PUT to this URL\n    downloadUrl: string; // GET URL after upload\n  }[];\n}\n```\n\nThe client uploads files directly to S3 using the presigned upload URL. See [File Uploads](/docs/client-sdk/file-uploads) for the full integration pattern.\n\n## Next Steps\n\n- [Sessions](/docs/server-sdk/sessions) \u2014 Deep dive into session management\n- [Tools](/docs/server-sdk/tools) \u2014 Implementing tool handlers\n- [Streaming](/docs/server-sdk/streaming) \u2014 Understanding stream events\n- [Workers](/docs/server-sdk/workers) \u2014 Executing worker agents\n- [Debugging](/docs/server-sdk/debugging) \u2014 Model request tracing and debugging\n",
+    content: "\n# Server SDK Overview\n\nThe `@octavus/server-sdk` package provides a Node.js SDK for integrating Octavus agents into your backend application. It handles session management, streaming, and the tool execution continuation loop.\n\n**Current version:** `2.15.0`\n\n## Installation\n\n```bash\nnpm install @octavus/server-sdk\n```\n\nFor agent management (sync, validate), install the CLI as a dev dependency:\n\n```bash\nnpm install --save-dev @octavus/cli\n```\n\n## Basic Usage\n\n```typescript\nimport { OctavusClient } from '@octavus/server-sdk';\n\nconst client = new OctavusClient({\n  baseUrl: 'https://octavus.ai',\n  apiKey: 'your-api-key',\n});\n```\n\n## Key Features\n\n### Agent Management\n\nAgent definitions are managed via the CLI. See the [CLI documentation](/docs/server-sdk/cli) for details.\n\n```bash\n# Sync agent from local files\noctavus sync ./agents/support-chat\n\n# Output: Created: support-chat\n#         Agent ID: clxyz123abc456\n```\n\n### Session Management\n\nCreate and manage agent sessions using the agent ID:\n\n```typescript\n// Create a new session (use agent ID from CLI sync)\nconst sessionId = await client.agentSessions.create('clxyz123abc456', {\n  COMPANY_NAME: 'Acme Corp',\n  PRODUCT_NAME: 'Widget Pro',\n});\n\n// Get UI-ready session messages (for session restore)\nconst session = await client.agentSessions.getMessages(sessionId);\n```\n\n### Tool Handlers\n\nTools run on your server with your data:\n\n```typescript\nconst session = client.agentSessions.attach(sessionId, {\n  tools: {\n    'get-user-account': async (args) => {\n      // Access your database, APIs, etc.\n      return await db.users.findById(args.userId);\n    },\n  },\n});\n```\n\n### Streaming\n\nAll responses stream in real-time:\n\n```typescript\nimport { toSSEStream } from '@octavus/server-sdk';\n\n// execute() returns an async generator of events\nconst events = session.execute({\n  type: 'trigger',\n  triggerName: 'user-message',\n  input: { USER_MESSAGE: 'Hello!' },\n});\n\n// Convert to SSE stream for HTTP responses\nreturn new Response(toSSEStream(events), {\n  headers: { 'Content-Type': 'text/event-stream' },\n});\n```\n\n### Workers\n\nExecute worker agents for task-based processing:\n\n```typescript\n// Non-streaming: get the output directly\nconst { output } = await client.workers.generate(agentId, {\n  TOPIC: 'AI safety',\n});\n\n// Streaming: observe events in real-time\nfor await (const event of client.workers.execute(agentId, input)) {\n  // Handle stream events\n}\n```\n\n## API Reference\n\n### OctavusClient\n\nThe main entry point for interacting with Octavus.\n\n```typescript\ninterface OctavusClientConfig {\n  baseUrl: string; // Octavus API URL\n  apiKey?: string; // Your API key\n  traceModelRequests?: boolean; // Enable model request tracing (default: false)\n}\n\nclass OctavusClient {\n  readonly agents: AgentsApi;\n  readonly agentSessions: AgentSessionsApi;\n  readonly workers: WorkersApi;\n  readonly files: FilesApi;\n\n  constructor(config: OctavusClientConfig);\n}\n```\n\n### AgentSessionsApi\n\nManages agent sessions.\n\n```typescript\nclass AgentSessionsApi {\n  // Create a new session\n  async create(agentId: string, input?: Record<string, unknown>): Promise<string>;\n\n  // Get full session state (for debugging/internal use)\n  async get(sessionId: string): Promise<SessionState>;\n\n  // Get UI-ready messages (for client display)\n  async getMessages(sessionId: string): Promise<UISessionState>;\n\n  // Attach to a session for triggering\n  attach(sessionId: string, options?: SessionAttachOptions): AgentSession;\n}\n\n// Full session state (internal format)\ninterface SessionState {\n  id: string;\n  agentId: string;\n  input: Record<string, unknown>;\n  variables: Record<string, unknown>;\n  resources: Record<string, unknown>;\n  messages: ChatMessage[]; // Internal message format\n  createdAt: string;\n  updatedAt: string;\n}\n\n// UI-ready session state\ninterface UISessionState {\n  sessionId: string;\n  agentId: string;\n  messages: UIMessage[]; // UI-ready messages for frontend\n}\n```\n\n### AgentSession\n\nHandles request execution and streaming for a specific session.\n\n```typescript\nclass AgentSession {\n  // Execute a request and stream parsed events\n  execute(request: SessionRequest, options?: TriggerOptions): AsyncGenerator<StreamEvent>;\n\n  // Get the session ID\n  getSessionId(): string;\n}\n\ntype SessionRequest = TriggerRequest | ContinueRequest;\n\ninterface TriggerRequest {\n  type: 'trigger';\n  triggerName: string;\n  input?: Record<string, unknown>;\n}\n\ninterface ContinueRequest {\n  type: 'continue';\n  executionId: string;\n  toolResults: ToolResult[];\n}\n\n// Helper to convert events to SSE stream\nfunction toSSEStream(events: AsyncIterable<StreamEvent>): ReadableStream<Uint8Array>;\n```\n\n### FilesApi\n\nHandles file uploads for sessions.\n\n```typescript\nclass FilesApi {\n  // Get presigned URLs for file uploads\n  async getUploadUrls(sessionId: string, files: FileUploadRequest[]): Promise<UploadUrlsResponse>;\n}\n\ninterface FileUploadRequest {\n  filename: string;\n  mediaType: string;\n  size: number;\n}\n\ninterface UploadUrlsResponse {\n  files: {\n    id: string; // File ID for references\n    uploadUrl: string; // PUT to this URL\n    downloadUrl: string; // GET URL after upload\n  }[];\n}\n```\n\nThe client uploads files directly to S3 using the presigned upload URL. See [File Uploads](/docs/client-sdk/file-uploads) for the full integration pattern.\n\n## Next Steps\n\n- [Sessions](/docs/server-sdk/sessions) \u2014 Deep dive into session management\n- [Tools](/docs/server-sdk/tools) \u2014 Implementing tool handlers\n- [Streaming](/docs/server-sdk/streaming) \u2014 Understanding stream events\n- [Workers](/docs/server-sdk/workers) \u2014 Executing worker agents\n- [Debugging](/docs/server-sdk/debugging) \u2014 Model request tracing and debugging\n",
     excerpt: "Server SDK Overview The  package provides a Node.js SDK for integrating Octavus agents into your backend application. It handles session management, streaming, and the tool execution continuation...",
     order: 1
   },
@@ -59,7 +59,7 @@ var docs_default = [
     section: "server-sdk",
     title: "CLI",
     description: "Command-line interface for validating and syncing agent definitions.",
-    content: '\n# Octavus CLI\n\nThe `@octavus/cli` package provides a command-line interface for validating and syncing agent definitions from your local filesystem to the Octavus platform.\n\n**Current version:** `2.12.0`\n\n## Installation\n\n```bash\nnpm install --save-dev @octavus/cli\n```\n\n## Configuration\n\nThe CLI requires an API key with the **Agents** permission.\n\n### Environment Variables\n\n| Variable              | Description                                    |\n| --------------------- | ---------------------------------------------- |\n| `OCTAVUS_CLI_API_KEY` | API key with "Agents" permission (recommended) |\n| `OCTAVUS_API_KEY`     | Fallback if `OCTAVUS_CLI_API_KEY` not set      |\n| `OCTAVUS_API_URL`     | Optional, defaults to `https://octavus.ai`     |\n\n### Two-Key Strategy (Recommended)\n\nFor production deployments, use separate API keys with minimal permissions:\n\n```bash\n# CI/CD or .env.local (not committed)\nOCTAVUS_CLI_API_KEY=oct_sk_...  # "Agents" permission only\n\n# Production .env\nOCTAVUS_API_KEY=oct_sk_...      # "Sessions" permission only\n```\n\nThis ensures production servers only have session permissions (smaller blast radius if leaked), while agent management is restricted to development/CI environments.\n\n### Multiple Environments\n\nUse separate Octavus projects for staging and production, each with their own API keys. The `--env` flag lets you load different environment files:\n\n```bash\n# Local development (default: .env)\noctavus sync ./agents/my-agent\n\n# Staging project\noctavus --env .env.staging sync ./agents/my-agent\n\n# Production project\noctavus --env .env.production sync ./agents/my-agent\n```\n\nExample environment files:\n\n```bash\n# .env.staging (syncs to your staging project)\nOCTAVUS_CLI_API_KEY=oct_sk_staging_project_key...\n\n# .env.production (syncs to your production project)\nOCTAVUS_CLI_API_KEY=oct_sk_production_project_key...\n```\n\nEach project has its own agents, so you\'ll get different agent IDs per environment.\n\n## Global Options\n\n| Option         | Description                                             |\n| -------------- | ------------------------------------------------------- |\n| `--env <file>` | Load environment from a specific file (default: `.env`) |\n| `--help`       | Show help                                               |\n| `--version`    | Show version                                            |\n\n## Commands\n\n### `octavus sync <path>`\n\nSync an agent definition to the platform. Creates the agent if it doesn\'t exist, or updates it if it does.\n\n```bash\noctavus sync ./agents/my-agent\n```\n\n**Options:**\n\n- `--json` \u2014 Output as JSON (for CI/CD parsing)\n- `--quiet` \u2014 Suppress non-essential output\n\n**Example output:**\n\n```\n\u2139 Reading agent from ./agents/my-agent...\n\u2139 Syncing support-chat...\n\u2713 Created: support-chat\n  Agent ID: clxyz123abc456\n```\n\n### `octavus validate <path>`\n\nValidate an agent definition without saving. Useful for CI/CD pipelines.\n\n```bash\noctavus validate ./agents/my-agent\n```\n\n**Exit codes:**\n\n- `0` \u2014 Validation passed\n- `1` \u2014 Validation errors\n- `2` \u2014 Configuration errors (missing API key, etc.)\n\n### `octavus list`\n\nList all agents in your project.\n\n```bash\noctavus list\n```\n\n**Example output:**\n\n```\nSLUG                  NAME                            FORMAT        ID\n\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\nsupport-chat          Support Chat Agent              interactive   clxyz123abc456\n\n1 agent(s)\n```\n\n### `octavus get <slug>`\n\nGet details about a specific agent by its slug.\n\n```bash\noctavus get support-chat\n```\n\n### `octavus archive <slug>`\n\nArchive an agent by slug (soft delete). Archived agents are removed from the active agent list and their slug is freed for reuse.\n\n```bash\noctavus archive support-chat\n```\n\n**Options:**\n\n- `--json` \u2014 Output as JSON (for CI/CD parsing)\n- `--quiet` \u2014 Suppress non-essential output\n\n**Example output:**\n\n```\n\u2139 Archiving support-chat...\n\u2713 Archived: support-chat\n  Agent ID: clxyz123abc456\n```\n\n## Agent Directory Structure\n\nThe CLI expects agent definitions in a specific directory structure:\n\n```\nmy-agent/\n\u251C\u2500\u2500 settings.json     # Required: Agent metadata\n\u251C\u2500\u2500 protocol.yaml     # Required: Agent protocol\n\u251C\u2500\u2500 prompts/          # Optional: Prompt templates\n\u2502   \u251C\u2500\u2500 system.md\n\u2502   \u2514\u2500\u2500 user-message.md\n\u2514\u2500\u2500 references/       # Optional: Reference documents\n    \u2514\u2500\u2500 api-guidelines.md\n```\n\n### references/\n\nReference files are markdown documents with YAML frontmatter containing a `description`. The agent can fetch these on demand during execution. See [References](/docs/protocol/references) for details.\n\n### settings.json\n\n```json\n{\n  "slug": "my-agent",\n  "name": "My Agent",\n  "description": "A helpful assistant",\n  "format": "interactive"\n}\n```\n\n### protocol.yaml\n\nSee the [Protocol documentation](/docs/protocol/overview) for details on protocol syntax.\n\n## CI/CD Integration\n\n### GitHub Actions\n\n```yaml\nname: Validate and Sync Agents\n\non:\n  push:\n    branches: [main]\n    paths:\n      - \'agents/**\'\n\njobs:\n  sync:\n    runs-on: ubuntu-latest\n    steps:\n      - uses: actions/checkout@v4\n\n      - uses: actions/setup-node@v4\n        with:\n          node-version: \'22\'\n\n      - run: npm install\n\n      - name: Validate agent\n        run: npx octavus validate ./agents/support-chat\n        env:\n          OCTAVUS_CLI_API_KEY: ${{ secrets.OCTAVUS_CLI_API_KEY }}\n\n      - name: Sync agent\n        run: npx octavus sync ./agents/support-chat\n        env:\n          OCTAVUS_CLI_API_KEY: ${{ secrets.OCTAVUS_CLI_API_KEY }}\n```\n\n### Package.json Scripts\n\nAdd sync scripts to your `package.json`:\n\n```json\n{\n  "scripts": {\n    "agents:validate": "octavus validate ./agents/my-agent",\n    "agents:sync": "octavus sync ./agents/my-agent"\n  },\n  "devDependencies": {\n    "@octavus/cli": "^0.1.0"\n  }\n}\n```\n\n## Workflow\n\nThe recommended workflow for managing agents:\n\n1. **Define agent locally** \u2014 Create `settings.json`, `protocol.yaml`, and prompts\n2. **Validate** \u2014 Run `octavus validate ./my-agent` to check for errors\n3. **Sync** \u2014 Run `octavus sync ./my-agent` to push to platform\n4. **Store agent ID** \u2014 Save the output ID in an environment variable\n5. **Use in app** \u2014 Read the ID from env and pass to `client.agentSessions.create()`\n\n```bash\n# After syncing: octavus sync ./agents/support-chat\n# Output: Agent ID: clxyz123abc456\n\n# Add to your .env file\nOCTAVUS_SUPPORT_AGENT_ID=clxyz123abc456\n```\n\n```typescript\nconst agentId = process.env.OCTAVUS_SUPPORT_AGENT_ID;\n\nconst sessionId = await client.agentSessions.create(agentId, {\n  COMPANY_NAME: \'Acme Corp\',\n});\n```\n',
+    content: '\n# Octavus CLI\n\nThe `@octavus/cli` package provides a command-line interface for validating and syncing agent definitions from your local filesystem to the Octavus platform.\n\n**Current version:** `2.15.0`\n\n## Installation\n\n```bash\nnpm install --save-dev @octavus/cli\n```\n\n## Configuration\n\nThe CLI requires an API key with the **Agents** permission.\n\n### Environment Variables\n\n| Variable              | Description                                    |\n| --------------------- | ---------------------------------------------- |\n| `OCTAVUS_CLI_API_KEY` | API key with "Agents" permission (recommended) |\n| `OCTAVUS_API_KEY`     | Fallback if `OCTAVUS_CLI_API_KEY` not set      |\n| `OCTAVUS_API_URL`     | Optional, defaults to `https://octavus.ai`     |\n\n### Two-Key Strategy (Recommended)\n\nFor production deployments, use separate API keys with minimal permissions:\n\n```bash\n# CI/CD or .env.local (not committed)\nOCTAVUS_CLI_API_KEY=oct_sk_...  # "Agents" permission only\n\n# Production .env\nOCTAVUS_API_KEY=oct_sk_...      # "Sessions" permission only\n```\n\nThis ensures production servers only have session permissions (smaller blast radius if leaked), while agent management is restricted to development/CI environments.\n\n### Multiple Environments\n\nUse separate Octavus projects for staging and production, each with their own API keys. The `--env` flag lets you load different environment files:\n\n```bash\n# Local development (default: .env)\noctavus sync ./agents/my-agent\n\n# Staging project\noctavus --env .env.staging sync ./agents/my-agent\n\n# Production project\noctavus --env .env.production sync ./agents/my-agent\n```\n\nExample environment files:\n\n```bash\n# .env.staging (syncs to your staging project)\nOCTAVUS_CLI_API_KEY=oct_sk_staging_project_key...\n\n# .env.production (syncs to your production project)\nOCTAVUS_CLI_API_KEY=oct_sk_production_project_key...\n```\n\nEach project has its own agents, so you\'ll get different agent IDs per environment.\n\n## Global Options\n\n| Option         | Description                                             |\n| -------------- | ------------------------------------------------------- |\n| `--env <file>` | Load environment from a specific file (default: `.env`) |\n| `--help`       | Show help                                               |\n| `--version`    | Show version                                            |\n\n## Commands\n\n### `octavus sync <path>`\n\nSync an agent definition to the platform. Creates the agent if it doesn\'t exist, or updates it if it does.\n\n```bash\noctavus sync ./agents/my-agent\n```\n\n**Options:**\n\n- `--json` \u2014 Output as JSON (for CI/CD parsing)\n- `--quiet` \u2014 Suppress non-essential output\n\n**Example output:**\n\n```\n\u2139 Reading agent from ./agents/my-agent...\n\u2139 Syncing support-chat...\n\u2713 Created: support-chat\n  Agent ID: clxyz123abc456\n```\n\n### `octavus validate <path>`\n\nValidate an agent definition without saving. Useful for CI/CD pipelines.\n\n```bash\noctavus validate ./agents/my-agent\n```\n\n**Exit codes:**\n\n- `0` \u2014 Validation passed\n- `1` \u2014 Validation errors\n- `2` \u2014 Configuration errors (missing API key, etc.)\n\n### `octavus list`\n\nList all agents in your project.\n\n```bash\noctavus list\n```\n\n**Example output:**\n\n```\nSLUG                  NAME                            FORMAT        ID\n\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\nsupport-chat          Support Chat Agent              interactive   clxyz123abc456\n\n1 agent(s)\n```\n\n### `octavus get <slug>`\n\nGet details about a specific agent by its slug.\n\n```bash\noctavus get support-chat\n```\n\n### `octavus archive <slug>`\n\nArchive an agent by slug (soft delete). Archived agents are removed from the active agent list and their slug is freed for reuse.\n\n```bash\noctavus archive support-chat\n```\n\n**Options:**\n\n- `--json` \u2014 Output as JSON (for CI/CD parsing)\n- `--quiet` \u2014 Suppress non-essential output\n\n**Example output:**\n\n```\n\u2139 Archiving support-chat...\n\u2713 Archived: support-chat\n  Agent ID: clxyz123abc456\n```\n\n## Agent Directory Structure\n\nThe CLI expects agent definitions in a specific directory structure:\n\n```\nmy-agent/\n\u251C\u2500\u2500 settings.json     # Required: Agent metadata\n\u251C\u2500\u2500 protocol.yaml     # Required: Agent protocol\n\u251C\u2500\u2500 prompts/          # Optional: Prompt templates\n\u2502   \u251C\u2500\u2500 system.md\n\u2502   \u2514\u2500\u2500 user-message.md\n\u2514\u2500\u2500 references/       # Optional: Reference documents\n    \u2514\u2500\u2500 api-guidelines.md\n```\n\n### references/\n\nReference files are markdown documents with YAML frontmatter containing a `description`. The agent can fetch these on demand during execution. See [References](/docs/protocol/references) for details.\n\n### settings.json\n\n```json\n{\n  "slug": "my-agent",\n  "name": "My Agent",\n  "description": "A helpful assistant",\n  "format": "interactive"\n}\n```\n\n### protocol.yaml\n\nSee the [Protocol documentation](/docs/protocol/overview) for details on protocol syntax.\n\n## CI/CD Integration\n\n### GitHub Actions\n\n```yaml\nname: Validate and Sync Agents\n\non:\n  push:\n    branches: [main]\n    paths:\n      - \'agents/**\'\n\njobs:\n  sync:\n    runs-on: ubuntu-latest\n    steps:\n      - uses: actions/checkout@v4\n\n      - uses: actions/setup-node@v4\n        with:\n          node-version: \'22\'\n\n      - run: npm install\n\n      - name: Validate agent\n        run: npx octavus validate ./agents/support-chat\n        env:\n          OCTAVUS_CLI_API_KEY: ${{ secrets.OCTAVUS_CLI_API_KEY }}\n\n      - name: Sync agent\n        run: npx octavus sync ./agents/support-chat\n        env:\n          OCTAVUS_CLI_API_KEY: ${{ secrets.OCTAVUS_CLI_API_KEY }}\n```\n\n### Package.json Scripts\n\nAdd sync scripts to your `package.json`:\n\n```json\n{\n  "scripts": {\n    "agents:validate": "octavus validate ./agents/my-agent",\n    "agents:sync": "octavus sync ./agents/my-agent"\n  },\n  "devDependencies": {\n    "@octavus/cli": "^0.1.0"\n  }\n}\n```\n\n## Workflow\n\nThe recommended workflow for managing agents:\n\n1. **Define agent locally** \u2014 Create `settings.json`, `protocol.yaml`, and prompts\n2. **Validate** \u2014 Run `octavus validate ./my-agent` to check for errors\n3. **Sync** \u2014 Run `octavus sync ./my-agent` to push to platform\n4. **Store agent ID** \u2014 Save the output ID in an environment variable\n5. **Use in app** \u2014 Read the ID from env and pass to `client.agentSessions.create()`\n\n```bash\n# After syncing: octavus sync ./agents/support-chat\n# Output: Agent ID: clxyz123abc456\n\n# Add to your .env file\nOCTAVUS_SUPPORT_AGENT_ID=clxyz123abc456\n```\n\n```typescript\nconst agentId = process.env.OCTAVUS_SUPPORT_AGENT_ID;\n\nconst sessionId = await client.agentSessions.create(agentId, {\n  COMPANY_NAME: \'Acme Corp\',\n});\n```\n',
     excerpt: "Octavus CLI The  package provides a command-line interface for validating and syncing agent definitions from your local filesystem to the Octavus platform. Current version:   Installation ...",
     order: 5
   },
@@ -68,7 +68,7 @@ var docs_default = [
     section: "server-sdk",
     title: "Workers",
     description: "Executing worker agents with the Server SDK.",
-    content: "\n# Workers API\n\nThe `WorkersApi` enables executing worker agents from your server. Workers are task-based agents that run steps sequentially and return an output value.\n\n## Basic Usage\n\n```typescript\nimport { OctavusClient } from '@octavus/server-sdk';\n\nconst client = new OctavusClient({\n  baseUrl: 'https://octavus.ai',\n  apiKey: 'your-api-key',\n});\n\nconst { output, sessionId } = await client.workers.generate(agentId, {\n  TOPIC: 'AI safety',\n  DEPTH: 'detailed',\n});\n\nconsole.log('Result:', output);\nconsole.log(`Debug: ${client.baseUrl}/sessions/${sessionId}`);\n```\n\n## WorkersApi Reference\n\n### generate()\n\nExecute a worker and return the output directly.\n\n```typescript\nasync generate(\n  agentId: string,\n  input: Record<string, unknown>,\n  options?: WorkerExecuteOptions\n): Promise<WorkerGenerateResult>\n```\n\nRuns the worker to completion and returns the output value. This is the simplest way to execute a worker.\n\n**Returns:**\n\n```typescript\ninterface WorkerGenerateResult {\n  /** The worker's output value */\n  output: unknown;\n  /** Session ID for debugging (usable for session URLs) */\n  sessionId: string;\n}\n```\n\n**Throws:** `WorkerError` if the worker fails or completes without producing output.\n\n### execute()\n\nExecute a worker and stream the response. Use this when you need to observe intermediate events like text deltas, tool calls, or progress tracking.\n\n```typescript\nasync *execute(\n  agentId: string,\n  input: Record<string, unknown>,\n  options?: WorkerExecuteOptions\n): AsyncGenerator<StreamEvent>\n```\n\n### continue()\n\nContinue execution after client-side tool handling.\n\n```typescript\nasync *continue(\n  agentId: string,\n  executionId: string,\n  toolResults: ToolResult[],\n  options?: WorkerExecuteOptions\n): AsyncGenerator<StreamEvent>\n```\n\nUse this when the worker has tools without server-side handlers. The execution pauses with a `client-tool-request` event, you execute the tools, then call `continue()` to resume.\n\n### Shared Options\n\nAll methods accept the same options:\n\n```typescript\ninterface WorkerExecuteOptions {\n  /** Tool handlers for server-side tool execution */\n  tools?: ToolHandlers;\n  /** Abort signal to cancel the execution */\n  signal?: AbortSignal;\n}\n```\n\n**Parameters:**\n\n| Parameter | Type                      | Description                 |\n| --------- | ------------------------- | --------------------------- |\n| `agentId` | `string`                  | The worker agent ID         |\n| `input`   | `Record<string, unknown>` | Input values for the worker |\n| `options` | `WorkerExecuteOptions`    | Optional configuration      |\n\n## Tool Handlers\n\nProvide tool handlers to execute tools server-side:\n\n```typescript\nconst { output } = await client.workers.generate(\n  agentId,\n  { TOPIC: 'AI safety' },\n  {\n    tools: {\n      'web-search': async (args) => {\n        return await searchWeb(args.query);\n      },\n      'get-user-data': async (args) => {\n        return await db.users.findById(args.userId);\n      },\n    },\n  },\n);\n```\n\nTools defined in the worker protocol but not provided as handlers become client tools \u2014 the execution pauses and emits a `client-tool-request` event.\n\n## Error Handling\n\n### WorkerError (generate)\n\n`generate()` throws a `WorkerError` on failure. The error includes an optional `sessionId` for constructing debug URLs:\n\n```typescript\nimport { OctavusClient, WorkerError } from '@octavus/server-sdk';\n\ntry {\n  const { output } = await client.workers.generate(agentId, input);\n  console.log('Result:', output);\n} catch (error) {\n  if (error instanceof WorkerError) {\n    console.error('Worker failed:', error.message);\n    if (error.sessionId) {\n      console.error(`Debug: ${client.baseUrl}/sessions/${error.sessionId}`);\n    }\n  }\n}\n```\n\n### Stream Errors (execute)\n\nWhen using `execute()`, errors appear as stream events:\n\n```typescript\nfor await (const event of client.workers.execute(agentId, input)) {\n  if (event.type === 'error') {\n    console.error(`Error: ${event.message}`);\n    console.error(`Type: ${event.errorType}`);\n    console.error(`Retryable: ${event.retryable}`);\n  }\n\n  if (event.type === 'worker-result' && event.error) {\n    console.error(`Worker failed: ${event.error}`);\n  }\n}\n```\n\n### Error Types\n\n| Type               | Description           |\n| ------------------ | --------------------- |\n| `validation_error` | Invalid input         |\n| `not_found_error`  | Worker not found      |\n| `provider_error`   | LLM provider error    |\n| `tool_error`       | Tool execution failed |\n| `execution_error`  | Worker step failed    |\n\n## Cancellation\n\nUse an abort signal to cancel execution:\n\n```typescript\nconst { output } = await client.workers.generate(agentId, input, {\n  signal: AbortSignal.timeout(30_000),\n});\n```\n\nWith `execute()` and a manual controller:\n\n```typescript\nconst controller = new AbortController();\nsetTimeout(() => controller.abort(), 30000);\n\ntry {\n  for await (const event of client.workers.execute(agentId, input, {\n    signal: controller.signal,\n  })) {\n    // Process events\n  }\n} catch (error) {\n  if (error.name === 'AbortError') {\n    console.log('Worker cancelled');\n  }\n}\n```\n\n## Streaming\n\nWhen you need real-time visibility into the worker's execution \u2014 text generation, tool calls, or progress \u2014 use `execute()` instead of `generate()`.\n\n### Basic Streaming\n\n```typescript\nconst events = client.workers.execute(agentId, {\n  TOPIC: 'AI safety',\n  DEPTH: 'detailed',\n});\n\nfor await (const event of events) {\n  if (event.type === 'worker-start') {\n    console.log(`Worker ${event.workerSlug} started`);\n  }\n  if (event.type === 'text-delta') {\n    process.stdout.write(event.delta);\n  }\n  if (event.type === 'worker-result') {\n    console.log('Output:', event.output);\n  }\n}\n```\n\n### Streaming to HTTP Response\n\nConvert worker events to an SSE stream:\n\n```typescript\nimport { toSSEStream } from '@octavus/server-sdk';\n\nexport async function POST(request: Request) {\n  const { agentId, input } = await request.json();\n\n  const events = client.workers.execute(agentId, input, {\n    tools: {\n      search: async (args) => await search(args.query),\n    },\n  });\n\n  return new Response(toSSEStream(events), {\n    headers: { 'Content-Type': 'text/event-stream' },\n  });\n}\n```\n\n### Client Tool Continuation\n\nWhen workers have tools without handlers, execution pauses:\n\n```typescript\nfor await (const event of client.workers.execute(agentId, input)) {\n  if (event.type === 'client-tool-request') {\n    const results = await executeClientTools(event.toolCalls);\n\n    for await (const ev of client.workers.continue(agentId, event.executionId, results)) {\n      // Handle remaining events\n    }\n    break;\n  }\n}\n```\n\nThe `client-tool-request` event includes:\n\n```typescript\n{\n  type: 'client-tool-request',\n  executionId: string,      // Pass to continue()\n  toolCalls: [{\n    toolCallId: string,\n    toolName: string,\n    args: Record<string, unknown>,\n  }],\n}\n```\n\n### Stream Events\n\nWorkers emit standard stream events plus worker-specific events.\n\n#### Worker Events\n\n```typescript\n// Worker started\n{\n  type: 'worker-start',\n  workerId: string,     // Unique ID (also used as session ID for debug)\n  workerSlug: string,   // The worker's slug\n  description?: string, // Display description for UI\n}\n\n// Worker completed\n{\n  type: 'worker-result',\n  workerId: string,\n  output?: unknown,  // The worker's output value\n  error?: string,    // Error message if worker failed\n}\n```\n\n#### Common Events\n\n| Event                   | Description                 |\n| ----------------------- | --------------------------- |\n| `start`                 | Execution started           |\n| `finish`                | Execution completed         |\n| `text-start`            | Text generation started     |\n| `text-delta`            | Text chunk received         |\n| `text-end`              | Text generation ended       |\n| `block-start`           | Step started                |\n| `block-end`             | Step completed              |\n| `tool-input-available`  | Tool arguments ready        |\n| `tool-output-available` | Tool result ready           |\n| `client-tool-request`   | Client tools need execution |\n| `error`                 | Error occurred              |\n\n## Full Examples\n\n### generate()\n\n```typescript\nimport { OctavusClient, WorkerError } from '@octavus/server-sdk';\n\nconst client = new OctavusClient({\n  baseUrl: 'https://octavus.ai',\n  apiKey: process.env.OCTAVUS_API_KEY!,\n});\n\ntry {\n  const { output, sessionId } = await client.workers.generate(\n    'research-assistant-id',\n    {\n      TOPIC: 'AI safety best practices',\n      DEPTH: 'detailed',\n    },\n    {\n      tools: {\n        'web-search': async ({ query }) => await performWebSearch(query),\n      },\n      signal: AbortSignal.timeout(120_000),\n    },\n  );\n\n  console.log('Result:', output);\n} catch (error) {\n  if (error instanceof WorkerError) {\n    console.error('Failed:', error.message);\n    if (error.sessionId) {\n      console.error(`Debug: ${client.baseUrl}/sessions/${error.sessionId}`);\n    }\n  }\n}\n```\n\n### execute()\n\nFor full control over streaming events and progress tracking:\n\n```typescript\nimport { OctavusClient, type StreamEvent } from '@octavus/server-sdk';\n\nconst client = new OctavusClient({\n  baseUrl: 'https://octavus.ai',\n  apiKey: process.env.OCTAVUS_API_KEY!,\n});\n\nasync function runResearchWorker(topic: string) {\n  console.log(`Researching: ${topic}\\n`);\n\n  const events = client.workers.execute(\n    'research-assistant-id',\n    {\n      TOPIC: topic,\n      DEPTH: 'detailed',\n    },\n    {\n      tools: {\n        'web-search': async ({ query }) => {\n          console.log(`Searching: ${query}`);\n          return await performWebSearch(query);\n        },\n      },\n    },\n  );\n\n  let output: unknown;\n\n  for await (const event of events) {\n    switch (event.type) {\n      case 'worker-start':\n        console.log(`Started: ${event.workerSlug}`);\n        break;\n\n      case 'block-start':\n        console.log(`Step: ${event.blockName}`);\n        break;\n\n      case 'text-delta':\n        process.stdout.write(event.delta);\n        break;\n\n      case 'worker-result':\n        if (event.error) {\n          throw new Error(event.error);\n        }\n        output = event.output;\n        break;\n\n      case 'error':\n        throw new Error(event.message);\n    }\n  }\n\n  console.log('\\n\\nResearch complete!');\n  return output;\n}\n\nconst result = await runResearchWorker('AI safety best practices');\nconsole.log('Result:', result);\n```\n\n## Next Steps\n\n- [Workers Protocol](/docs/protocol/workers) \u2014 Worker protocol reference\n- [Streaming](/docs/server-sdk/streaming) \u2014 Understanding stream events\n- [Tools](/docs/server-sdk/tools) \u2014 Tool handler patterns\n",
+    content: "\n# Workers API\n\nThe `WorkersApi` enables executing worker agents from your server. Workers are task-based agents that run steps sequentially and return an output value.\n\n## Basic Usage\n\n```typescript\nimport { OctavusClient } from '@octavus/server-sdk';\n\nconst client = new OctavusClient({\n  baseUrl: 'https://octavus.ai',\n  apiKey: 'your-api-key',\n});\n\nconst { output, sessionId } = await client.workers.generate(agentId, {\n  TOPIC: 'AI safety',\n  DEPTH: 'detailed',\n});\n\nconsole.log('Result:', output);\nconsole.log(`Debug: ${client.baseUrl}/sessions/${sessionId}`);\n```\n\n## WorkersApi Reference\n\n### generate()\n\nExecute a worker and return the output directly.\n\n```typescript\nasync generate(\n  agentId: string,\n  input: Record<string, unknown>,\n  options?: WorkerExecuteOptions\n): Promise<WorkerGenerateResult>\n```\n\nRuns the worker to completion and returns the output value. This is the simplest way to execute a worker.\n\n**Returns:**\n\n```typescript\ninterface WorkerGenerateResult {\n  /** The worker's output value */\n  output: unknown;\n  /** Session ID for debugging (usable for session URLs) */\n  sessionId: string;\n}\n```\n\n**Throws:** `WorkerError` if the worker fails or completes without producing output.\n\n### execute()\n\nExecute a worker and stream the response. Use this when you need to observe intermediate events like text deltas, tool calls, or progress tracking.\n\n```typescript\nasync *execute(\n  agentId: string,\n  input: Record<string, unknown>,\n  options?: WorkerExecuteOptions\n): AsyncGenerator<StreamEvent>\n```\n\n### continue()\n\nContinue execution after client-side tool handling.\n\n```typescript\nasync *continue(\n  agentId: string,\n  executionId: string,\n  toolResults: ToolResult[],\n  options?: WorkerExecuteOptions\n): AsyncGenerator<StreamEvent>\n```\n\nUse this when the worker has tools without server-side handlers. The execution pauses with a `client-tool-request` event, you execute the tools, then call `continue()` to resume.\n\n### Shared Options\n\nAll methods accept the same options:\n\n```typescript\ninterface WorkerExecuteOptions {\n  /** Tool handlers for server-side tool execution */\n  tools?: ToolHandlers;\n  /** Abort signal to cancel the execution */\n  signal?: AbortSignal;\n}\n```\n\n**Parameters:**\n\n| Parameter | Type                      | Description                 |\n| --------- | ------------------------- | --------------------------- |\n| `agentId` | `string`                  | The worker agent ID         |\n| `input`   | `Record<string, unknown>` | Input values for the worker |\n| `options` | `WorkerExecuteOptions`    | Optional configuration      |\n\n## Tool Handlers\n\nProvide tool handlers to execute tools server-side:\n\n```typescript\nconst { output } = await client.workers.generate(\n  agentId,\n  { TOPIC: 'AI safety' },\n  {\n    tools: {\n      'web-search': async (args) => {\n        return await searchWeb(args.query);\n      },\n      'get-user-data': async (args) => {\n        return await db.users.findById(args.userId);\n      },\n    },\n  },\n);\n```\n\nTools defined in the worker protocol but not provided as handlers become client tools \u2014 the execution pauses and emits a `client-tool-request` event.\n\n## Error Handling\n\n### WorkerError (generate)\n\n`generate()` throws a `WorkerError` on failure. The error includes an optional `sessionId` for constructing debug URLs:\n\n```typescript\nimport { OctavusClient, WorkerError } from '@octavus/server-sdk';\n\ntry {\n  const { output } = await client.workers.generate(agentId, input);\n  console.log('Result:', output);\n} catch (error) {\n  if (error instanceof WorkerError) {\n    console.error('Worker failed:', error.message);\n    if (error.sessionId) {\n      console.error(`Debug: ${client.baseUrl}/platform/sessions/${error.sessionId}`);\n    }\n  }\n}\n```\n\n### Stream Errors (execute)\n\nWhen using `execute()`, errors appear as stream events:\n\n```typescript\nfor await (const event of client.workers.execute(agentId, input)) {\n  if (event.type === 'error') {\n    console.error(`Error: ${event.message}`);\n    console.error(`Type: ${event.errorType}`);\n    console.error(`Retryable: ${event.retryable}`);\n  }\n\n  if (event.type === 'worker-result' && event.error) {\n    console.error(`Worker failed: ${event.error}`);\n  }\n}\n```\n\n### Error Types\n\n| Type               | Description           |\n| ------------------ | --------------------- |\n| `validation_error` | Invalid input         |\n| `not_found_error`  | Worker not found      |\n| `provider_error`   | LLM provider error    |\n| `tool_error`       | Tool execution failed |\n| `execution_error`  | Worker step failed    |\n\n## Cancellation\n\nUse an abort signal to cancel execution:\n\n```typescript\nconst { output } = await client.workers.generate(agentId, input, {\n  signal: AbortSignal.timeout(30_000),\n});\n```\n\nWith `execute()` and a manual controller:\n\n```typescript\nconst controller = new AbortController();\nsetTimeout(() => controller.abort(), 30000);\n\ntry {\n  for await (const event of client.workers.execute(agentId, input, {\n    signal: controller.signal,\n  })) {\n    // Process events\n  }\n} catch (error) {\n  if (error.name === 'AbortError') {\n    console.log('Worker cancelled');\n  }\n}\n```\n\n## Streaming\n\nWhen you need real-time visibility into the worker's execution \u2014 text generation, tool calls, or progress \u2014 use `execute()` instead of `generate()`.\n\n### Basic Streaming\n\n```typescript\nconst events = client.workers.execute(agentId, {\n  TOPIC: 'AI safety',\n  DEPTH: 'detailed',\n});\n\nfor await (const event of events) {\n  if (event.type === 'worker-start') {\n    console.log(`Worker ${event.workerSlug} started`);\n  }\n  if (event.type === 'text-delta') {\n    process.stdout.write(event.delta);\n  }\n  if (event.type === 'worker-result') {\n    console.log('Output:', event.output);\n  }\n}\n```\n\n### Streaming to HTTP Response\n\nConvert worker events to an SSE stream:\n\n```typescript\nimport { toSSEStream } from '@octavus/server-sdk';\n\nexport async function POST(request: Request) {\n  const { agentId, input } = await request.json();\n\n  const events = client.workers.execute(agentId, input, {\n    tools: {\n      search: async (args) => await search(args.query),\n    },\n  });\n\n  return new Response(toSSEStream(events), {\n    headers: { 'Content-Type': 'text/event-stream' },\n  });\n}\n```\n\n### Client Tool Continuation\n\nWhen workers have tools without handlers, execution pauses:\n\n```typescript\nfor await (const event of client.workers.execute(agentId, input)) {\n  if (event.type === 'client-tool-request') {\n    const results = await executeClientTools(event.toolCalls);\n\n    for await (const ev of client.workers.continue(agentId, event.executionId, results)) {\n      // Handle remaining events\n    }\n    break;\n  }\n}\n```\n\nThe `client-tool-request` event includes:\n\n```typescript\n{\n  type: 'client-tool-request',\n  executionId: string,      // Pass to continue()\n  toolCalls: [{\n    toolCallId: string,\n    toolName: string,\n    args: Record<string, unknown>,\n  }],\n}\n```\n\n### Stream Events\n\nWorkers emit standard stream events plus worker-specific events.\n\n#### Worker Events\n\n```typescript\n// Worker started\n{\n  type: 'worker-start',\n  workerId: string,     // Unique ID (also used as session ID for debug)\n  workerSlug: string,   // The worker's slug\n  description?: string, // Display description for UI\n}\n\n// Worker completed\n{\n  type: 'worker-result',\n  workerId: string,\n  output?: unknown,  // The worker's output value\n  error?: string,    // Error message if worker failed\n}\n```\n\n#### Common Events\n\n| Event                   | Description                 |\n| ----------------------- | --------------------------- |\n| `start`                 | Execution started           |\n| `finish`                | Execution completed         |\n| `text-start`            | Text generation started     |\n| `text-delta`            | Text chunk received         |\n| `text-end`              | Text generation ended       |\n| `block-start`           | Step started                |\n| `block-end`             | Step completed              |\n| `tool-input-available`  | Tool arguments ready        |\n| `tool-output-available` | Tool result ready           |\n| `client-tool-request`   | Client tools need execution |\n| `error`                 | Error occurred              |\n\n## Full Examples\n\n### generate()\n\n```typescript\nimport { OctavusClient, WorkerError } from '@octavus/server-sdk';\n\nconst client = new OctavusClient({\n  baseUrl: 'https://octavus.ai',\n  apiKey: process.env.OCTAVUS_API_KEY!,\n});\n\ntry {\n  const { output, sessionId } = await client.workers.generate(\n    'research-assistant-id',\n    {\n      TOPIC: 'AI safety best practices',\n      DEPTH: 'detailed',\n    },\n    {\n      tools: {\n        'web-search': async ({ query }) => await performWebSearch(query),\n      },\n      signal: AbortSignal.timeout(120_000),\n    },\n  );\n\n  console.log('Result:', output);\n} catch (error) {\n  if (error instanceof WorkerError) {\n    console.error('Failed:', error.message);\n    if (error.sessionId) {\n      console.error(`Debug: ${client.baseUrl}/platform/sessions/${error.sessionId}`);\n    }\n  }\n}\n```\n\n### execute()\n\nFor full control over streaming events and progress tracking:\n\n```typescript\nimport { OctavusClient, type StreamEvent } from '@octavus/server-sdk';\n\nconst client = new OctavusClient({\n  baseUrl: 'https://octavus.ai',\n  apiKey: process.env.OCTAVUS_API_KEY!,\n});\n\nasync function runResearchWorker(topic: string) {\n  console.log(`Researching: ${topic}\\n`);\n\n  const events = client.workers.execute(\n    'research-assistant-id',\n    {\n      TOPIC: topic,\n      DEPTH: 'detailed',\n    },\n    {\n      tools: {\n        'web-search': async ({ query }) => {\n          console.log(`Searching: ${query}`);\n          return await performWebSearch(query);\n        },\n      },\n    },\n  );\n\n  let output: unknown;\n\n  for await (const event of events) {\n    switch (event.type) {\n      case 'worker-start':\n        console.log(`Started: ${event.workerSlug}`);\n        break;\n\n      case 'block-start':\n        console.log(`Step: ${event.blockName}`);\n        break;\n\n      case 'text-delta':\n        process.stdout.write(event.delta);\n        break;\n\n      case 'worker-result':\n        if (event.error) {\n          throw new Error(event.error);\n        }\n        output = event.output;\n        break;\n\n      case 'error':\n        throw new Error(event.message);\n    }\n  }\n\n  console.log('\\n\\nResearch complete!');\n  return output;\n}\n\nconst result = await runResearchWorker('AI safety best practices');\nconsole.log('Result:', result);\n```\n\n## Next Steps\n\n- [Workers Protocol](/docs/protocol/workers) \u2014 Worker protocol reference\n- [Streaming](/docs/server-sdk/streaming) \u2014 Understanding stream events\n- [Tools](/docs/server-sdk/tools) \u2014 Tool handler patterns\n",
     excerpt: "Workers API The  enables executing worker agents from your server. Workers are task-based agents that run steps sequentially and return an output value.  Basic Usage  WorkersApi Reference  generate()...",
     order: 6
   },
@@ -86,7 +86,7 @@ var docs_default = [
     section: "client-sdk",
     title: "Overview",
     description: "Introduction to the Octavus Client SDKs for building chat interfaces.",
-    content: "\n# Client SDK Overview\n\nOctavus provides two packages for frontend integration:\n\n| Package               | Purpose                  | Use When                                              |\n| --------------------- | ------------------------ | ----------------------------------------------------- |\n| `@octavus/react`      | React hooks and bindings | Building React applications                           |\n| `@octavus/client-sdk` | Framework-agnostic core  | Using Vue, Svelte, vanilla JS, or custom integrations |\n\n**Most users should install `@octavus/react`** \u2014 it includes everything from `@octavus/client-sdk` plus React-specific hooks.\n\n## Installation\n\n### React Applications\n\n```bash\nnpm install @octavus/react\n```\n\n**Current version:** `2.12.0`\n\n### Other Frameworks\n\n```bash\nnpm install @octavus/client-sdk\n```\n\n**Current version:** `2.12.0`\n\n## Transport Pattern\n\nThe Client SDK uses a **transport abstraction** to handle communication with your backend. This gives you flexibility in how events are delivered:\n\n| Transport               | Use Case                                     | Docs                                                  |\n| ----------------------- | -------------------------------------------- | ----------------------------------------------------- |\n| `createHttpTransport`   | HTTP/SSE (Next.js, Express, etc.)            | [HTTP Transport](/docs/client-sdk/http-transport)     |\n| `createSocketTransport` | WebSocket, SockJS, or other socket protocols | [Socket Transport](/docs/client-sdk/socket-transport) |\n\nWhen the transport changes (e.g., when `sessionId` changes), the `useOctavusChat` hook automatically reinitializes with the new transport.\n\n> **Recommendation**: Use HTTP transport unless you specifically need WebSocket features (custom real-time events, Meteor/Phoenix, etc.).\n\n## React Usage\n\nThe `useOctavusChat` hook provides state management and streaming for React applications:\n\n```tsx\nimport { useMemo } from 'react';\nimport { useOctavusChat, createHttpTransport, type UIMessage } from '@octavus/react';\n\nfunction Chat({ sessionId }: { sessionId: string }) {\n  // Create a stable transport instance (memoized on sessionId)\n  const transport = useMemo(\n    () =>\n      createHttpTransport({\n        request: (payload, options) =>\n          fetch('/api/trigger', {\n            method: 'POST',\n            headers: { 'Content-Type': 'application/json' },\n            body: JSON.stringify({ sessionId, ...payload }),\n            signal: options?.signal,\n          }),\n      }),\n    [sessionId],\n  );\n\n  const { messages, status, send } = useOctavusChat({ transport });\n\n  const sendMessage = async (text: string) => {\n    await send('user-message', { USER_MESSAGE: text }, { userMessage: { content: text } });\n  };\n\n  return (\n    <div>\n      {messages.map((msg) => (\n        <MessageBubble key={msg.id} message={msg} />\n      ))}\n    </div>\n  );\n}\n\nfunction MessageBubble({ message }: { message: UIMessage }) {\n  return (\n    <div>\n      {message.parts.map((part, i) => {\n        if (part.type === 'text') {\n          return <p key={i}>{part.text}</p>;\n        }\n        return null;\n      })}\n    </div>\n  );\n}\n```\n\n## Framework-Agnostic Usage\n\nThe `OctavusChat` class can be used with any framework or vanilla JavaScript:\n\n```typescript\nimport { OctavusChat, createHttpTransport } from '@octavus/client-sdk';\n\nconst transport = createHttpTransport({\n  request: (payload, options) =>\n    fetch('/api/trigger', {\n      method: 'POST',\n      headers: { 'Content-Type': 'application/json' },\n      body: JSON.stringify({ sessionId, ...payload }),\n      signal: options?.signal,\n    }),\n});\n\nconst chat = new OctavusChat({ transport });\n\n// Subscribe to state changes\nconst unsubscribe = chat.subscribe(() => {\n  console.log('Messages:', chat.messages);\n  console.log('Status:', chat.status);\n  // Update your UI here\n});\n\n// Send a message\nawait chat.send('user-message', { USER_MESSAGE: 'Hello' }, { userMessage: { content: 'Hello' } });\n\n// Cleanup when done\nunsubscribe();\n```\n\n## Key Features\n\n### Unified Send Function\n\nThe `send` function handles both user message display and agent triggering in one call:\n\n```tsx\nconst { send } = useOctavusChat({ transport });\n\n// Add user message to UI and trigger agent\nawait send('user-message', { USER_MESSAGE: text }, { userMessage: { content: text } });\n\n// Trigger without adding a user message (e.g., button click)\nawait send('request-human');\n```\n\n### Message Parts\n\nMessages contain ordered `parts` for rich content:\n\n```tsx\nconst { messages } = useOctavusChat({ transport });\n\n// Each message has typed parts\nmessage.parts.map((part) => {\n  switch (part.type) {\n    case 'text': // Text content\n    case 'reasoning': // Extended reasoning/thinking\n    case 'tool-call': // Tool execution\n    case 'operation': // Internal operations (set-resource, etc.)\n  }\n});\n```\n\n### Status Tracking\n\n```tsx\nconst { status } = useOctavusChat({ transport });\n\n// status: 'idle' | 'streaming' | 'error' | 'awaiting-input'\n// 'awaiting-input' occurs when interactive client tools need user action\n```\n\n### Stop Streaming\n\n```tsx\nconst { stop } = useOctavusChat({ transport });\n\n// Stop current stream and finalize message\nstop();\n```\n\n### Retry Last Trigger\n\nRe-execute the last trigger from the same starting point. Messages are rolled back to the state before the trigger, the user message is re-added (if any), and the agent re-executes. Already-uploaded files are reused without re-uploading.\n\n```tsx\nconst { retry, canRetry } = useOctavusChat({ transport });\n\n// Retry after an error, cancellation, or unsatisfactory result\nif (canRetry) {\n  await retry();\n}\n```\n\n`canRetry` is `true` when a trigger has been sent and the chat is not currently streaming or awaiting input.\n\n## Hook Reference (React)\n\n### useOctavusChat\n\n```typescript\nfunction useOctavusChat(options: OctavusChatOptions): UseOctavusChatReturn;\n\ninterface OctavusChatOptions {\n  // Required: Transport for streaming events\n  transport: Transport;\n\n  // Optional: Function to request upload URLs for file uploads\n  requestUploadUrls?: (\n    files: { filename: string; mediaType: string; size: number }[],\n  ) => Promise<UploadUrlsResponse>;\n\n  // Optional: Client-side tool handlers\n  // - Function: executes automatically and returns result\n  // - 'interactive': appears in pendingClientTools for user input\n  clientTools?: Record<string, ClientToolHandler>;\n\n  // Optional: Pre-populate with existing messages (session restore)\n  initialMessages?: UIMessage[];\n\n  // Optional: Callbacks\n  onError?: (error: OctavusError) => void; // Structured error with type, source, retryable\n  onFinish?: () => void;\n  onStop?: () => void; // Called when user stops generation\n  onResourceUpdate?: (name: string, value: unknown) => void;\n}\n\ninterface UseOctavusChatReturn {\n  // State\n  messages: UIMessage[];\n  status: ChatStatus; // 'idle' | 'streaming' | 'error' | 'awaiting-input'\n  error: OctavusError | null; // Structured error with type, source, retryable\n\n  // Connection (socket transport only - undefined for HTTP)\n  connectionState: ConnectionState | undefined; // 'disconnected' | 'connecting' | 'connected' | 'error'\n  connectionError: Error | undefined;\n\n  // Client tools (interactive tools awaiting user input)\n  pendingClientTools: Record<string, InteractiveTool[]>; // Keyed by tool name\n\n  // Actions\n  send: (\n    triggerName: string,\n    input?: Record<string, unknown>,\n    options?: { userMessage?: UserMessageInput },\n  ) => Promise<void>;\n  stop: () => void;\n  retry: () => Promise<void>; // Retry last trigger from same starting point\n  canRetry: boolean; // Whether retry() can be called\n\n  // Connection management (socket transport only - undefined for HTTP)\n  connect: (() => Promise<void>) | undefined;\n  disconnect: (() => void) | undefined;\n\n  // File uploads (requires requestUploadUrls)\n  uploadFiles: (\n    files: FileList | File[],\n    onProgress?: (fileIndex: number, progress: number) => void,\n  ) => Promise<FileReference[]>;\n}\n\ninterface UserMessageInput {\n  content?: string;\n  files?: FileList | File[] | FileReference[];\n}\n```\n\n## Transport Reference\n\n### createHttpTransport\n\nCreates an HTTP/SSE transport using native `fetch()`:\n\n```typescript\nimport { createHttpTransport } from '@octavus/react';\n\nconst transport = createHttpTransport({\n  request: (payload, options) =>\n    fetch('/api/trigger', {\n      method: 'POST',\n      headers: { 'Content-Type': 'application/json' },\n      body: JSON.stringify({ sessionId, ...payload }),\n      signal: options?.signal,\n    }),\n});\n```\n\n### createSocketTransport\n\nCreates a WebSocket/SockJS transport for real-time connections:\n\n```typescript\nimport { createSocketTransport } from '@octavus/react';\n\nconst transport = createSocketTransport({\n  connect: () =>\n    new Promise((resolve, reject) => {\n      const ws = new WebSocket(`wss://api.example.com/stream?sessionId=${sessionId}`);\n      ws.onopen = () => resolve(ws);\n      ws.onerror = () => reject(new Error('Connection failed'));\n    }),\n});\n```\n\nSocket transport provides additional connection management:\n\n```typescript\n// Access connection state directly\ntransport.connectionState; // 'disconnected' | 'connecting' | 'connected' | 'error'\n\n// Subscribe to state changes\ntransport.onConnectionStateChange((state, error) => {\n  /* ... */\n});\n\n// Eager connection (instead of lazy on first send)\nawait transport.connect();\n\n// Manual disconnect\ntransport.disconnect();\n```\n\nFor detailed WebSocket/SockJS usage including custom events, reconnection patterns, and server-side implementation, see [Socket Transport](/docs/client-sdk/socket-transport).\n\n## Class Reference (Framework-Agnostic)\n\n### OctavusChat\n\n```typescript\nclass OctavusChat {\n  constructor(options: OctavusChatOptions);\n\n  // State (read-only)\n  readonly messages: UIMessage[];\n  readonly status: ChatStatus; // 'idle' | 'streaming' | 'error' | 'awaiting-input'\n  readonly error: OctavusError | null; // Structured error\n  readonly pendingClientTools: Record<string, InteractiveTool[]>; // Interactive tools\n\n  // Actions\n  send(\n    triggerName: string,\n    input?: Record<string, unknown>,\n    options?: { userMessage?: UserMessageInput },\n  ): Promise<void>;\n  stop(): void;\n\n  // Subscription\n  subscribe(callback: () => void): () => void; // Returns unsubscribe function\n}\n```\n\n## Next Steps\n\n- [HTTP Transport](/docs/client-sdk/http-transport) \u2014 HTTP/SSE integration (recommended)\n- [Socket Transport](/docs/client-sdk/socket-transport) \u2014 WebSocket and SockJS integration\n- [Messages](/docs/client-sdk/messages) \u2014 Working with message state\n- [Streaming](/docs/client-sdk/streaming) \u2014 Building streaming UIs\n- [Client Tools](/docs/client-sdk/client-tools) \u2014 Interactive browser-side tool handling\n- [Operations](/docs/client-sdk/execution-blocks) \u2014 Showing agent progress\n- [Error Handling](/docs/client-sdk/error-handling) \u2014 Handling errors with type guards\n- [File Uploads](/docs/client-sdk/file-uploads) \u2014 Uploading images and documents\n- [Examples](/docs/examples/overview) \u2014 Complete working examples\n",
+    content: "\n# Client SDK Overview\n\nOctavus provides two packages for frontend integration:\n\n| Package               | Purpose                  | Use When                                              |\n| --------------------- | ------------------------ | ----------------------------------------------------- |\n| `@octavus/react`      | React hooks and bindings | Building React applications                           |\n| `@octavus/client-sdk` | Framework-agnostic core  | Using Vue, Svelte, vanilla JS, or custom integrations |\n\n**Most users should install `@octavus/react`** \u2014 it includes everything from `@octavus/client-sdk` plus React-specific hooks.\n\n## Installation\n\n### React Applications\n\n```bash\nnpm install @octavus/react\n```\n\n**Current version:** `2.15.0`\n\n### Other Frameworks\n\n```bash\nnpm install @octavus/client-sdk\n```\n\n**Current version:** `2.15.0`\n\n## Transport Pattern\n\nThe Client SDK uses a **transport abstraction** to handle communication with your backend. This gives you flexibility in how events are delivered:\n\n| Transport               | Use Case                                     | Docs                                                  |\n| ----------------------- | -------------------------------------------- | ----------------------------------------------------- |\n| `createHttpTransport`   | HTTP/SSE (Next.js, Express, etc.)            | [HTTP Transport](/docs/client-sdk/http-transport)     |\n| `createSocketTransport` | WebSocket, SockJS, or other socket protocols | [Socket Transport](/docs/client-sdk/socket-transport) |\n\nWhen the transport changes (e.g., when `sessionId` changes), the `useOctavusChat` hook automatically reinitializes with the new transport.\n\n> **Recommendation**: Use HTTP transport unless you specifically need WebSocket features (custom real-time events, Meteor/Phoenix, etc.).\n\n## React Usage\n\nThe `useOctavusChat` hook provides state management and streaming for React applications:\n\n```tsx\nimport { useMemo } from 'react';\nimport { useOctavusChat, createHttpTransport, type UIMessage } from '@octavus/react';\n\nfunction Chat({ sessionId }: { sessionId: string }) {\n  // Create a stable transport instance (memoized on sessionId)\n  const transport = useMemo(\n    () =>\n      createHttpTransport({\n        request: (payload, options) =>\n          fetch('/api/trigger', {\n            method: 'POST',\n            headers: { 'Content-Type': 'application/json' },\n            body: JSON.stringify({ sessionId, ...payload }),\n            signal: options?.signal,\n          }),\n      }),\n    [sessionId],\n  );\n\n  const { messages, status, send } = useOctavusChat({ transport });\n\n  const sendMessage = async (text: string) => {\n    await send('user-message', { USER_MESSAGE: text }, { userMessage: { content: text } });\n  };\n\n  return (\n    <div>\n      {messages.map((msg) => (\n        <MessageBubble key={msg.id} message={msg} />\n      ))}\n    </div>\n  );\n}\n\nfunction MessageBubble({ message }: { message: UIMessage }) {\n  return (\n    <div>\n      {message.parts.map((part, i) => {\n        if (part.type === 'text') {\n          return <p key={i}>{part.text}</p>;\n        }\n        return null;\n      })}\n    </div>\n  );\n}\n```\n\n## Framework-Agnostic Usage\n\nThe `OctavusChat` class can be used with any framework or vanilla JavaScript:\n\n```typescript\nimport { OctavusChat, createHttpTransport } from '@octavus/client-sdk';\n\nconst transport = createHttpTransport({\n  request: (payload, options) =>\n    fetch('/api/trigger', {\n      method: 'POST',\n      headers: { 'Content-Type': 'application/json' },\n      body: JSON.stringify({ sessionId, ...payload }),\n      signal: options?.signal,\n    }),\n});\n\nconst chat = new OctavusChat({ transport });\n\n// Subscribe to state changes\nconst unsubscribe = chat.subscribe(() => {\n  console.log('Messages:', chat.messages);\n  console.log('Status:', chat.status);\n  // Update your UI here\n});\n\n// Send a message\nawait chat.send('user-message', { USER_MESSAGE: 'Hello' }, { userMessage: { content: 'Hello' } });\n\n// Cleanup when done\nunsubscribe();\n```\n\n## Key Features\n\n### Unified Send Function\n\nThe `send` function handles both user message display and agent triggering in one call:\n\n```tsx\nconst { send } = useOctavusChat({ transport });\n\n// Add user message to UI and trigger agent\nawait send('user-message', { USER_MESSAGE: text }, { userMessage: { content: text } });\n\n// Trigger without adding a user message (e.g., button click)\nawait send('request-human');\n```\n\n### Message Parts\n\nMessages contain ordered `parts` for rich content:\n\n```tsx\nconst { messages } = useOctavusChat({ transport });\n\n// Each message has typed parts\nmessage.parts.map((part) => {\n  switch (part.type) {\n    case 'text': // Text content\n    case 'reasoning': // Extended reasoning/thinking\n    case 'tool-call': // Tool execution\n    case 'operation': // Internal operations (set-resource, etc.)\n  }\n});\n```\n\n### Status Tracking\n\n```tsx\nconst { status } = useOctavusChat({ transport });\n\n// status: 'idle' | 'streaming' | 'error' | 'awaiting-input'\n// 'awaiting-input' occurs when interactive client tools need user action\n```\n\n### Stop Streaming\n\n```tsx\nconst { stop } = useOctavusChat({ transport });\n\n// Stop current stream and finalize message\nstop();\n```\n\n### Retry Last Trigger\n\nRe-execute the last trigger from the same starting point. Messages are rolled back to the state before the trigger, the user message is re-added (if any), and the agent re-executes. Already-uploaded files are reused without re-uploading.\n\n```tsx\nconst { retry, canRetry } = useOctavusChat({ transport });\n\n// Retry after an error, cancellation, or unsatisfactory result\nif (canRetry) {\n  await retry();\n}\n```\n\n`canRetry` is `true` when a trigger has been sent and the chat is not currently streaming or awaiting input.\n\n## Hook Reference (React)\n\n### useOctavusChat\n\n```typescript\nfunction useOctavusChat(options: OctavusChatOptions): UseOctavusChatReturn;\n\ninterface OctavusChatOptions {\n  // Required: Transport for streaming events\n  transport: Transport;\n\n  // Optional: Function to request upload URLs for file uploads\n  requestUploadUrls?: (\n    files: { filename: string; mediaType: string; size: number }[],\n  ) => Promise<UploadUrlsResponse>;\n\n  // Optional: Client-side tool handlers\n  // - Function: executes automatically and returns result\n  // - 'interactive': appears in pendingClientTools for user input\n  clientTools?: Record<string, ClientToolHandler>;\n\n  // Optional: Pre-populate with existing messages (session restore)\n  initialMessages?: UIMessage[];\n\n  // Optional: Callbacks\n  onError?: (error: OctavusError) => void; // Structured error with type, source, retryable\n  onFinish?: () => void;\n  onStop?: () => void; // Called when user stops generation\n  onResourceUpdate?: (name: string, value: unknown) => void;\n}\n\ninterface UseOctavusChatReturn {\n  // State\n  messages: UIMessage[];\n  status: ChatStatus; // 'idle' | 'streaming' | 'error' | 'awaiting-input'\n  error: OctavusError | null; // Structured error with type, source, retryable\n\n  // Connection (socket transport only - undefined for HTTP)\n  connectionState: ConnectionState | undefined; // 'disconnected' | 'connecting' | 'connected' | 'error'\n  connectionError: Error | undefined;\n\n  // Client tools (interactive tools awaiting user input)\n  pendingClientTools: Record<string, InteractiveTool[]>; // Keyed by tool name\n\n  // Actions\n  send: (\n    triggerName: string,\n    input?: Record<string, unknown>,\n    options?: { userMessage?: UserMessageInput },\n  ) => Promise<void>;\n  stop: () => void;\n  retry: () => Promise<void>; // Retry last trigger from same starting point\n  canRetry: boolean; // Whether retry() can be called\n\n  // Connection management (socket transport only - undefined for HTTP)\n  connect: (() => Promise<void>) | undefined;\n  disconnect: (() => void) | undefined;\n\n  // File uploads (requires requestUploadUrls)\n  uploadFiles: (\n    files: FileList | File[],\n    onProgress?: (fileIndex: number, progress: number) => void,\n  ) => Promise<FileReference[]>;\n}\n\ninterface UserMessageInput {\n  content?: string;\n  files?: FileList | File[] | FileReference[];\n}\n```\n\n## Transport Reference\n\n### createHttpTransport\n\nCreates an HTTP/SSE transport using native `fetch()`:\n\n```typescript\nimport { createHttpTransport } from '@octavus/react';\n\nconst transport = createHttpTransport({\n  request: (payload, options) =>\n    fetch('/api/trigger', {\n      method: 'POST',\n      headers: { 'Content-Type': 'application/json' },\n      body: JSON.stringify({ sessionId, ...payload }),\n      signal: options?.signal,\n    }),\n});\n```\n\n### createSocketTransport\n\nCreates a WebSocket/SockJS transport for real-time connections:\n\n```typescript\nimport { createSocketTransport } from '@octavus/react';\n\nconst transport = createSocketTransport({\n  connect: () =>\n    new Promise((resolve, reject) => {\n      const ws = new WebSocket(`wss://api.example.com/stream?sessionId=${sessionId}`);\n      ws.onopen = () => resolve(ws);\n      ws.onerror = () => reject(new Error('Connection failed'));\n    }),\n});\n```\n\nSocket transport provides additional connection management:\n\n```typescript\n// Access connection state directly\ntransport.connectionState; // 'disconnected' | 'connecting' | 'connected' | 'error'\n\n// Subscribe to state changes\ntransport.onConnectionStateChange((state, error) => {\n  /* ... */\n});\n\n// Eager connection (instead of lazy on first send)\nawait transport.connect();\n\n// Manual disconnect\ntransport.disconnect();\n```\n\nFor detailed WebSocket/SockJS usage including custom events, reconnection patterns, and server-side implementation, see [Socket Transport](/docs/client-sdk/socket-transport).\n\n## Class Reference (Framework-Agnostic)\n\n### OctavusChat\n\n```typescript\nclass OctavusChat {\n  constructor(options: OctavusChatOptions);\n\n  // State (read-only)\n  readonly messages: UIMessage[];\n  readonly status: ChatStatus; // 'idle' | 'streaming' | 'error' | 'awaiting-input'\n  readonly error: OctavusError | null; // Structured error\n  readonly pendingClientTools: Record<string, InteractiveTool[]>; // Interactive tools\n\n  // Actions\n  send(\n    triggerName: string,\n    input?: Record<string, unknown>,\n    options?: { userMessage?: UserMessageInput },\n  ): Promise<void>;\n  stop(): void;\n\n  // Subscription\n  subscribe(callback: () => void): () => void; // Returns unsubscribe function\n}\n```\n\n## Next Steps\n\n- [HTTP Transport](/docs/client-sdk/http-transport) \u2014 HTTP/SSE integration (recommended)\n- [Socket Transport](/docs/client-sdk/socket-transport) \u2014 WebSocket and SockJS integration\n- [Messages](/docs/client-sdk/messages) \u2014 Working with message state\n- [Streaming](/docs/client-sdk/streaming) \u2014 Building streaming UIs\n- [Client Tools](/docs/client-sdk/client-tools) \u2014 Interactive browser-side tool handling\n- [Operations](/docs/client-sdk/execution-blocks) \u2014 Showing agent progress\n- [Error Handling](/docs/client-sdk/error-handling) \u2014 Handling errors with type guards\n- [File Uploads](/docs/client-sdk/file-uploads) \u2014 Uploading images and documents\n- [Examples](/docs/examples/overview) \u2014 Complete working examples\n",
     excerpt: "Client SDK Overview Octavus provides two packages for frontend integration: | Package               | Purpose                  | Use When                                              | |...",
     order: 1
   },
@@ -658,7 +658,7 @@ See [Streaming Events](/docs/server-sdk/streaming#event-types) for the full list
     section: "api-reference",
     title: "Sessions",
     description: "Session management API endpoints.",
-    content: '\n# Sessions API\n\nSessions represent conversations with agents. They store conversation history, resources, and variables.\n\nAll session endpoints require an API key with the **Sessions** permission.\n\n## Create Session\n\nCreate a new agent session.\n\n```\nPOST /api/agent-sessions\n```\n\n### Request Body\n\n```json\n{\n  "agentId": "cm5xvz7k80001abcd",\n  "input": {\n    "COMPANY_NAME": "Acme Corp",\n    "PRODUCT_NAME": "Widget Pro",\n    "USER_ID": "user-123"\n  }\n}\n```\n\n| Field     | Type   | Required | Description                           |\n| --------- | ------ | -------- | ------------------------------------- |\n| `agentId` | string | Yes      | Agent ID (the `id` field, not `slug`) |\n| `input`   | object | No       | Input variables for the agent         |\n\n> **Getting the agent ID:** Copy the ID from the agent URL in the [platform](https://octavus.ai) (e.g., `octavus.ai/agents/clxyz123`), or use the [CLI](/docs/server-sdk/cli) (`octavus sync ./agents/my-agent`) for local development workflows.\n\n### Response\n\n```json\n{\n  "sessionId": "cm5xyz123abc456def"\n}\n```\n\n### Example\n\n```bash\ncurl -X POST https://octavus.ai/api/agent-sessions \\\n  -H "Authorization: Bearer YOUR_API_KEY" \\\n  -H "Content-Type: application/json" \\\n  -d \'{\n    "agentId": "cm5xvz7k80001abcd",\n    "input": {\n      "COMPANY_NAME": "Acme Corp",\n      "PRODUCT_NAME": "Widget Pro"\n    }\n  }\'\n```\n\n## Get Session\n\nRetrieve session state. Returns UI-ready messages for active sessions, or expiration info for expired sessions.\n\n```\nGET /api/agent-sessions/:sessionId\n```\n\n### Query Parameters\n\n| Parameter | Type   | Description                                          |\n| --------- | ------ | ---------------------------------------------------- |\n| `format`  | string | Optional. Use `format=ui` for UI-ready messages only |\n\n### Response (Active Session)\n\nWhen the session is active, the response includes `UIMessage` objects:\n\n```json\n{\n  "id": "cm5xyz123abc456def",\n  "agentId": "cm5xvz7k80001abcd",\n  "status": "active",\n  "input": {\n    "COMPANY_NAME": "Acme Corp",\n    "PRODUCT_NAME": "Widget Pro"\n  },\n  "variables": {},\n  "resources": {\n    "CONVERSATION_SUMMARY": ""\n  },\n  "messages": [\n    {\n      "id": "1702345800000-xyz789a",\n      "role": "user",\n      "parts": [{ "type": "text", "text": "How do I reset my password?", "status": "done" }],\n      "status": "done",\n      "createdAt": "2024-01-15T10:30:00.000Z"\n    },\n    {\n      "id": "1702345805000-def456b",\n      "role": "assistant",\n      "parts": [\n        { "type": "text", "text": "I can help you reset your password...", "status": "done" }\n      ],\n      "status": "done",\n      "createdAt": "2024-01-15T10:30:05.000Z"\n    }\n  ],\n  "createdAt": "2024-01-15T10:30:00Z",\n  "updatedAt": "2024-01-15T10:30:05Z"\n}\n```\n\n### Response (Expired Session)\n\nWhen the session has expired, the response indicates the expiration status:\n\n```json\n{\n  "status": "expired",\n  "sessionId": "cm5xyz123abc456def",\n  "agentId": "cm5xvz7k80001abcd",\n  "createdAt": "2024-01-15T10:30:00Z"\n}\n```\n\nUse the [Restore Session](#restore-session) endpoint to restore an expired session from stored messages.\n\n````\n\n### UIMessage Parts\n\nMessages contain typed `parts` that preserve content ordering:\n\n| Part Type | Description |\n|-----------|-------------|\n| `text` | Text content with `text` and `status` fields |\n| `reasoning` | Extended reasoning with `text` and `status` fields |\n| `tool-call` | Tool execution with `toolCallId`, `toolName`, `displayName`, `args`, `result`, `status` |\n| `operation` | Internal operations with `operationId`, `name`, `operationType`, `status` |\n| `file` | File attachment with `id`, `mediaType`, `url`, `filename`, `size` |\n| `source` | Source reference with `sourceType`, `id`, `url`, `title` |\n| `object` | Structured output with `id`, `typeName`, `object`, `status` |\n\n### Example\n\n```bash\ncurl https://octavus.ai/api/agent-sessions/:sessionId \\\n  -H "Authorization: Bearer YOUR_API_KEY"\n````\n\n## Restore Session\n\nRestore an expired session from stored messages. This allows you to continue a conversation after the server-side state has expired.\n\n```\nPOST /api/agent-sessions/:sessionId/restore\n```\n\n### Request Body\n\n```json\n{\n  "messages": [\n    {\n      "id": "1702345800000-xyz789a",\n      "role": "user",\n      "parts": [{ "type": "text", "text": "How do I reset my password?", "status": "done" }],\n      "status": "done",\n      "createdAt": "2024-01-15T10:30:00.000Z"\n    }\n  ],\n  "input": {\n    "COMPANY_NAME": "Acme Corp"\n  }\n}\n```\n\n| Field      | Type        | Required | Description                                                    |\n| ---------- | ----------- | -------- | -------------------------------------------------------------- |\n| `messages` | UIMessage[] | Yes      | Previously stored chat history                                 |\n| `input`    | object      | No       | Session input for system prompt interpolation (same as create) |\n\n### Response\n\n```json\n{\n  "sessionId": "cm5xyz123abc456def",\n  "restored": true\n}\n```\n\n| Field       | Type    | Description                                                             |\n| ----------- | ------- | ----------------------------------------------------------------------- |\n| `sessionId` | string  | The session ID                                                          |\n| `restored`  | boolean | `true` if restored from messages, `false` if session was already active |\n\n### Example\n\n```bash\ncurl -X POST https://octavus.ai/api/agent-sessions/:sessionId/restore \\\n  -H "Authorization: Bearer YOUR_API_KEY" \\\n  -H "Content-Type: application/json" \\\n  -d \'{\n    "messages": [...],\n    "input": { "COMPANY_NAME": "Acme Corp" }\n  }\'\n```\n\n> **Note**: Store the `UIMessage[]` array after each interaction to enable restoration. The restore endpoint reconstructs the conversation state from these messages.\n\n## Clear Session\n\nClear session state, transitioning it to `expired` status. The session can be restored afterwards with the [Restore Session](#restore-session) endpoint.\n\nThis is idempotent \u2014 clearing an already expired session succeeds without error.\n\n```\nDELETE /api/agent-sessions/:sessionId\n```\n\n### Response\n\n```json\n{\n  "sessionId": "cm5xyz123abc456def",\n  "cleared": true\n}\n```\n\n### Example\n\n```bash\ncurl -X DELETE https://octavus.ai/api/agent-sessions/:sessionId \\\n  -H "Authorization: Bearer YOUR_API_KEY"\n```\n\n## Trigger Session\n\nExecute a trigger on a session. Returns a Server-Sent Events stream.\n\n```\nPOST /api/agent-sessions/:sessionId/trigger\n```\n\n### Request Body\n\n```json\n{\n  "triggerName": "user-message",\n  "input": {\n    "USER_MESSAGE": "How do I reset my password?"\n  },\n  "toolResults": []\n}\n```\n\n| Field                     | Type           | Required | Description                                                                                           |\n| ------------------------- | -------------- | -------- | ----------------------------------------------------------------------------------------------------- |\n| `triggerName`             | string         | Yes      | Name of the trigger to execute                                                                        |\n| `input`                   | object         | No       | Input variables for the trigger                                                                       |\n| `toolResults`             | array          | No       | Tool results for continuation (handled by SDK)                                                        |\n| `rollbackAfterMessageId`  | string \\| null | No       | For retry: ID of the last message to keep. Messages after this are removed. `null` = truncate all.    |\n\n### Response\n\nReturns `text/event-stream` with SSE events:\n\n```\ndata: {"type":"start","messageId":"msg-123"}\n\ndata: {"type":"block-start","blockId":"b1","blockName":"Add user message","blockType":"add-message","display":"hidden"}\n\ndata: {"type":"block-end","blockId":"b1"}\n\ndata: {"type":"block-start","blockId":"b2","blockName":"Respond to user","blockType":"next-message","display":"stream","outputToChat":true}\n\ndata: {"type":"text-start","id":"t1"}\n\ndata: {"type":"text-delta","id":"t1","delta":"I"}\n\ndata: {"type":"text-delta","id":"t1","delta":" can"}\n\ndata: {"type":"text-delta","id":"t1","delta":" help"}\n\ndata: {"type":"text-delta","id":"t1","delta":" you"}\n\ndata: {"type":"text-delta","id":"t1","delta":" reset"}\n\ndata: {"type":"text-delta","id":"t1","delta":" your"}\n\ndata: {"type":"text-delta","id":"t1","delta":" password"}\n\ndata: {"type":"text-delta","id":"t1","delta":"!"}\n\ndata: {"type":"text-end","id":"t1"}\n\ndata: {"type":"block-end","blockId":"b2"}\n\ndata: {"type":"finish","finishReason":"stop"}\n\ndata: [DONE]\n```\n\n### Event Types\n\n| Event                   | Description                        |\n| ----------------------- | ---------------------------------- |\n| `start`                 | Stream started                     |\n| `finish`                | Execution complete                 |\n| `error`                 | Error occurred                     |\n| `block-start`           | Execution block started            |\n| `block-end`             | Execution block completed          |\n| `text-start`            | Text generation started            |\n| `text-delta`            | Incremental text content           |\n| `text-end`              | Text generation ended              |\n| `reasoning-start`       | Extended reasoning started         |\n| `reasoning-delta`       | Reasoning content                  |\n| `reasoning-end`         | Extended reasoning ended           |\n| `tool-input-start`      | Tool call initiated                |\n| `tool-input-delta`      | Tool arguments streaming           |\n| `tool-input-end`        | Tool arguments streaming ended     |\n| `tool-input-available`  | Tool input complete                |\n| `tool-output-available` | Tool completed with result         |\n| `tool-output-error`     | Tool failed                        |\n| `tool-request`          | Platform requesting tool execution |\n| `file-available`        | File ready for display/download    |\n| `resource-update`       | Resource value changed             |\n\n### Example\n\n```bash\ncurl -N -X POST https://octavus.ai/api/agent-sessions/:sessionId/trigger \\\n  -H "Authorization: Bearer YOUR_API_KEY" \\\n  -H "Content-Type: application/json" \\\n  -d \'{\n    "triggerName": "user-message",\n    "input": { "USER_MESSAGE": "How do I reset my password?" }\n  }\'\n```\n\n## Tool Continuation\n\nWhen the agent calls external tools, you\'ll receive a `tool-request` event. Execute the tools and send results back:\n\n```json\n{\n  "triggerName": "user-message",\n  "input": { "USER_MESSAGE": "..." },\n  "toolResults": [\n    {\n      "toolCallId": "tc_123",\n      "toolName": "get-user-account",\n      "result": {\n        "name": "Demo User",\n        "email": "demo@example.com"\n      }\n    }\n  ]\n}\n```\n\nThe Server SDK handles this continuation pattern automatically.\n\n## Upload URLs\n\nGet presigned URLs for file uploads. Files are uploaded directly to S3.\n\n```\nPOST /api/files/upload-urls\n```\n\n### Request Body\n\n```json\n{\n  "sessionId": "cm5xyz123abc456def",\n  "files": [\n    {\n      "filename": "photo.jpg",\n      "mediaType": "image/jpeg",\n      "size": 102400\n    }\n  ]\n}\n```\n\n| Field               | Type   | Required | Description                         |\n| ------------------- | ------ | -------- | ----------------------------------- |\n| `sessionId`         | string | Yes      | Session ID to associate files with  |\n| `files`             | array  | Yes      | Array of file metadata (1-20 files) |\n| `files[].filename`  | string | Yes      | Original filename                   |\n| `files[].mediaType` | string | Yes      | MIME type (e.g., `image/png`)       |\n| `files[].size`      | number | Yes      | File size in bytes                  |\n\n### Response\n\n```json\n{\n  "files": [\n    {\n      "id": "file-abc123",\n      "uploadUrl": "https://s3.amazonaws.com/bucket/key?...",\n      "downloadUrl": "https://s3.amazonaws.com/bucket/key?..."\n    }\n  ]\n}\n```\n\n### Upload Flow\n\n1. Request upload URLs from the platform\n2. PUT file content to `uploadUrl` with `Content-Type` header\n3. Use `downloadUrl` as the `url` in `FileReference`\n4. Include `FileReference` in trigger input\n\n### Supported Types\n\n| Category  | Media Types                                                          |\n| --------- | -------------------------------------------------------------------- |\n| Images    | `image/jpeg`, `image/png`, `image/gif`, `image/webp`                 |\n| Documents | `application/pdf`, `text/plain`, `text/markdown`, `application/json` |\n\n### Limits\n\n| Limit                 | Value      |\n| --------------------- | ---------- |\n| Max file size         | 10 MB      |\n| Max total per request | 50 MB      |\n| Max files per request | 20         |\n| Upload URL expiry     | 15 minutes |\n| Download URL expiry   | 24 hours   |\n',
+    content: '\n# Sessions API\n\nSessions represent conversations with agents. They store conversation history, resources, and variables.\n\nAll session endpoints require an API key with the **Sessions** permission.\n\n## Create Session\n\nCreate a new agent session.\n\n```\nPOST /api/agent-sessions\n```\n\n### Request Body\n\n```json\n{\n  "agentId": "cm5xvz7k80001abcd",\n  "input": {\n    "COMPANY_NAME": "Acme Corp",\n    "PRODUCT_NAME": "Widget Pro",\n    "USER_ID": "user-123"\n  }\n}\n```\n\n| Field     | Type   | Required | Description                           |\n| --------- | ------ | -------- | ------------------------------------- |\n| `agentId` | string | Yes      | Agent ID (the `id` field, not `slug`) |\n| `input`   | object | No       | Input variables for the agent         |\n\n> **Getting the agent ID:** Copy the ID from the agent URL in the [platform](https://octavus.ai) (e.g., `octavus.ai/platform/agents/clxyz123`), or use the [CLI](/docs/server-sdk/cli) (`octavus sync ./agents/my-agent`) for local development workflows.\n\n### Response\n\n```json\n{\n  "sessionId": "cm5xyz123abc456def"\n}\n```\n\n### Example\n\n```bash\ncurl -X POST https://octavus.ai/api/agent-sessions \\\n  -H "Authorization: Bearer YOUR_API_KEY" \\\n  -H "Content-Type: application/json" \\\n  -d \'{\n    "agentId": "cm5xvz7k80001abcd",\n    "input": {\n      "COMPANY_NAME": "Acme Corp",\n      "PRODUCT_NAME": "Widget Pro"\n    }\n  }\'\n```\n\n## Get Session\n\nRetrieve session state. Returns UI-ready messages for active sessions, or expiration info for expired sessions.\n\n```\nGET /api/agent-sessions/:sessionId\n```\n\n### Query Parameters\n\n| Parameter | Type   | Description                                          |\n| --------- | ------ | ---------------------------------------------------- |\n| `format`  | string | Optional. Use `format=ui` for UI-ready messages only |\n\n### Response (Active Session)\n\nWhen the session is active, the response includes `UIMessage` objects:\n\n```json\n{\n  "id": "cm5xyz123abc456def",\n  "agentId": "cm5xvz7k80001abcd",\n  "status": "active",\n  "input": {\n    "COMPANY_NAME": "Acme Corp",\n    "PRODUCT_NAME": "Widget Pro"\n  },\n  "variables": {},\n  "resources": {\n    "CONVERSATION_SUMMARY": ""\n  },\n  "messages": [\n    {\n      "id": "1702345800000-xyz789a",\n      "role": "user",\n      "parts": [{ "type": "text", "text": "How do I reset my password?", "status": "done" }],\n      "status": "done",\n      "createdAt": "2024-01-15T10:30:00.000Z"\n    },\n    {\n      "id": "1702345805000-def456b",\n      "role": "assistant",\n      "parts": [\n        { "type": "text", "text": "I can help you reset your password...", "status": "done" }\n      ],\n      "status": "done",\n      "createdAt": "2024-01-15T10:30:05.000Z"\n    }\n  ],\n  "createdAt": "2024-01-15T10:30:00Z",\n  "updatedAt": "2024-01-15T10:30:05Z"\n}\n```\n\n### Response (Expired Session)\n\nWhen the session has expired, the response indicates the expiration status:\n\n```json\n{\n  "status": "expired",\n  "sessionId": "cm5xyz123abc456def",\n  "agentId": "cm5xvz7k80001abcd",\n  "createdAt": "2024-01-15T10:30:00Z"\n}\n```\n\nUse the [Restore Session](#restore-session) endpoint to restore an expired session from stored messages.\n\n````\n\n### UIMessage Parts\n\nMessages contain typed `parts` that preserve content ordering:\n\n| Part Type | Description |\n|-----------|-------------|\n| `text` | Text content with `text` and `status` fields |\n| `reasoning` | Extended reasoning with `text` and `status` fields |\n| `tool-call` | Tool execution with `toolCallId`, `toolName`, `displayName`, `args`, `result`, `status` |\n| `operation` | Internal operations with `operationId`, `name`, `operationType`, `status` |\n| `file` | File attachment with `id`, `mediaType`, `url`, `filename`, `size` |\n| `source` | Source reference with `sourceType`, `id`, `url`, `title` |\n| `object` | Structured output with `id`, `typeName`, `object`, `status` |\n\n### Example\n\n```bash\ncurl https://octavus.ai/api/agent-sessions/:sessionId \\\n  -H "Authorization: Bearer YOUR_API_KEY"\n````\n\n## Restore Session\n\nRestore an expired session from stored messages. This allows you to continue a conversation after the server-side state has expired.\n\n```\nPOST /api/agent-sessions/:sessionId/restore\n```\n\n### Request Body\n\n```json\n{\n  "messages": [\n    {\n      "id": "1702345800000-xyz789a",\n      "role": "user",\n      "parts": [{ "type": "text", "text": "How do I reset my password?", "status": "done" }],\n      "status": "done",\n      "createdAt": "2024-01-15T10:30:00.000Z"\n    }\n  ],\n  "input": {\n    "COMPANY_NAME": "Acme Corp"\n  }\n}\n```\n\n| Field      | Type        | Required | Description                                                    |\n| ---------- | ----------- | -------- | -------------------------------------------------------------- |\n| `messages` | UIMessage[] | Yes      | Previously stored chat history                                 |\n| `input`    | object      | No       | Session input for system prompt interpolation (same as create) |\n\n### Response\n\n```json\n{\n  "sessionId": "cm5xyz123abc456def",\n  "restored": true\n}\n```\n\n| Field       | Type    | Description                                                             |\n| ----------- | ------- | ----------------------------------------------------------------------- |\n| `sessionId` | string  | The session ID                                                          |\n| `restored`  | boolean | `true` if restored from messages, `false` if session was already active |\n\n### Example\n\n```bash\ncurl -X POST https://octavus.ai/api/agent-sessions/:sessionId/restore \\\n  -H "Authorization: Bearer YOUR_API_KEY" \\\n  -H "Content-Type: application/json" \\\n  -d \'{\n    "messages": [...],\n    "input": { "COMPANY_NAME": "Acme Corp" }\n  }\'\n```\n\n> **Note**: Store the `UIMessage[]` array after each interaction to enable restoration. The restore endpoint reconstructs the conversation state from these messages.\n\n## Clear Session\n\nClear session state, transitioning it to `expired` status. The session can be restored afterwards with the [Restore Session](#restore-session) endpoint.\n\nThis is idempotent \u2014 clearing an already expired session succeeds without error.\n\n```\nDELETE /api/agent-sessions/:sessionId\n```\n\n### Response\n\n```json\n{\n  "sessionId": "cm5xyz123abc456def",\n  "cleared": true\n}\n```\n\n### Example\n\n```bash\ncurl -X DELETE https://octavus.ai/api/agent-sessions/:sessionId \\\n  -H "Authorization: Bearer YOUR_API_KEY"\n```\n\n## Trigger Session\n\nExecute a trigger on a session. Returns a Server-Sent Events stream.\n\n```\nPOST /api/agent-sessions/:sessionId/trigger\n```\n\n### Request Body\n\n```json\n{\n  "triggerName": "user-message",\n  "input": {\n    "USER_MESSAGE": "How do I reset my password?"\n  },\n  "toolResults": []\n}\n```\n\n| Field                    | Type           | Required | Description                                                                                        |\n| ------------------------ | -------------- | -------- | -------------------------------------------------------------------------------------------------- |\n| `triggerName`            | string         | Yes      | Name of the trigger to execute                                                                     |\n| `input`                  | object         | No       | Input variables for the trigger                                                                    |\n| `toolResults`            | array          | No       | Tool results for continuation (handled by SDK)                                                     |\n| `rollbackAfterMessageId` | string \\| null | No       | For retry: ID of the last message to keep. Messages after this are removed. `null` = truncate all. |\n\n### Response\n\nReturns `text/event-stream` with SSE events:\n\n```\ndata: {"type":"start","messageId":"msg-123"}\n\ndata: {"type":"block-start","blockId":"b1","blockName":"Add user message","blockType":"add-message","display":"hidden"}\n\ndata: {"type":"block-end","blockId":"b1"}\n\ndata: {"type":"block-start","blockId":"b2","blockName":"Respond to user","blockType":"next-message","display":"stream","outputToChat":true}\n\ndata: {"type":"text-start","id":"t1"}\n\ndata: {"type":"text-delta","id":"t1","delta":"I"}\n\ndata: {"type":"text-delta","id":"t1","delta":" can"}\n\ndata: {"type":"text-delta","id":"t1","delta":" help"}\n\ndata: {"type":"text-delta","id":"t1","delta":" you"}\n\ndata: {"type":"text-delta","id":"t1","delta":" reset"}\n\ndata: {"type":"text-delta","id":"t1","delta":" your"}\n\ndata: {"type":"text-delta","id":"t1","delta":" password"}\n\ndata: {"type":"text-delta","id":"t1","delta":"!"}\n\ndata: {"type":"text-end","id":"t1"}\n\ndata: {"type":"block-end","blockId":"b2"}\n\ndata: {"type":"finish","finishReason":"stop"}\n\ndata: [DONE]\n```\n\n### Event Types\n\n| Event                   | Description                        |\n| ----------------------- | ---------------------------------- |\n| `start`                 | Stream started                     |\n| `finish`                | Execution complete                 |\n| `error`                 | Error occurred                     |\n| `block-start`           | Execution block started            |\n| `block-end`             | Execution block completed          |\n| `text-start`            | Text generation started            |\n| `text-delta`            | Incremental text content           |\n| `text-end`              | Text generation ended              |\n| `reasoning-start`       | Extended reasoning started         |\n| `reasoning-delta`       | Reasoning content                  |\n| `reasoning-end`         | Extended reasoning ended           |\n| `tool-input-start`      | Tool call initiated                |\n| `tool-input-delta`      | Tool arguments streaming           |\n| `tool-input-end`        | Tool arguments streaming ended     |\n| `tool-input-available`  | Tool input complete                |\n| `tool-output-available` | Tool completed with result         |\n| `tool-output-error`     | Tool failed                        |\n| `tool-request`          | Platform requesting tool execution |\n| `file-available`        | File ready for display/download    |\n| `resource-update`       | Resource value changed             |\n\n### Example\n\n```bash\ncurl -N -X POST https://octavus.ai/api/agent-sessions/:sessionId/trigger \\\n  -H "Authorization: Bearer YOUR_API_KEY" \\\n  -H "Content-Type: application/json" \\\n  -d \'{\n    "triggerName": "user-message",\n    "input": { "USER_MESSAGE": "How do I reset my password?" }\n  }\'\n```\n\n## Tool Continuation\n\nWhen the agent calls external tools, you\'ll receive a `tool-request` event. Execute the tools and send results back:\n\n```json\n{\n  "triggerName": "user-message",\n  "input": { "USER_MESSAGE": "..." },\n  "toolResults": [\n    {\n      "toolCallId": "tc_123",\n      "toolName": "get-user-account",\n      "result": {\n        "name": "Demo User",\n        "email": "demo@example.com"\n      }\n    }\n  ]\n}\n```\n\nThe Server SDK handles this continuation pattern automatically.\n\n## Upload URLs\n\nGet presigned URLs for file uploads. Files are uploaded directly to S3.\n\n```\nPOST /api/files/upload-urls\n```\n\n### Request Body\n\n```json\n{\n  "sessionId": "cm5xyz123abc456def",\n  "files": [\n    {\n      "filename": "photo.jpg",\n      "mediaType": "image/jpeg",\n      "size": 102400\n    }\n  ]\n}\n```\n\n| Field               | Type   | Required | Description                         |\n| ------------------- | ------ | -------- | ----------------------------------- |\n| `sessionId`         | string | Yes      | Session ID to associate files with  |\n| `files`             | array  | Yes      | Array of file metadata (1-20 files) |\n| `files[].filename`  | string | Yes      | Original filename                   |\n| `files[].mediaType` | string | Yes      | MIME type (e.g., `image/png`)       |\n| `files[].size`      | number | Yes      | File size in bytes                  |\n\n### Response\n\n```json\n{\n  "files": [\n    {\n      "id": "file-abc123",\n      "uploadUrl": "https://s3.amazonaws.com/bucket/key?...",\n      "downloadUrl": "https://s3.amazonaws.com/bucket/key?..."\n    }\n  ]\n}\n```\n\n### Upload Flow\n\n1. Request upload URLs from the platform\n2. PUT file content to `uploadUrl` with `Content-Type` header\n3. Use `downloadUrl` as the `url` in `FileReference`\n4. Include `FileReference` in trigger input\n\n### Supported Types\n\n| Category  | Media Types                                                          |\n| --------- | -------------------------------------------------------------------- |\n| Images    | `image/jpeg`, `image/png`, `image/gif`, `image/webp`                 |\n| Documents | `application/pdf`, `text/plain`, `text/markdown`, `application/json` |\n\n### Limits\n\n| Limit                 | Value      |\n| --------------------- | ---------- |\n| Max file size         | 10 MB      |\n| Max total per request | 50 MB      |\n| Max files per request | 20         |\n| Upload URL expiry     | 15 minutes |\n| Download URL expiry   | 24 hours   |\n',
     excerpt: "Sessions API Sessions represent conversations with agents. They store conversation history, resources, and variables. All session endpoints require an API key with the Sessions permission.  Create...",
     order: 2
   },
@@ -731,7 +731,7 @@ var sections_default = [
         section: "getting-started",
         title: "Quick Start",
         description: "Get your first Octavus agent running in minutes.",
-        content: "\n# Quick Start\n\nThis guide will walk you through integrating Octavus into your application in under 10 minutes.\n\n## Prerequisites\n\n- Node.js 18+\n- An Octavus account with API key\n- A Next.js application (or any Node.js backend)\n\n## Test Your Agent First\n\nBefore integrating with SDKs, use **Agent Preview** to test your agent directly in the platform:\n\n1. Open your agent in the platform at `octavus.ai/agents/[agentId]`\n2. Click the **Preview** tab\n3. Configure session inputs and tool mock responses\n4. Start a conversation to test agent behavior\n\nAgent Preview supports all trigger types, file attachments, tool mocking, and real-time streaming. This is the fastest way to iterate on your agent logic before writing any integration code.\n\n## Installation\n\nInstall the Octavus SDKs in your project:\n\n```bash\n# Server SDK for backend\nnpm install @octavus/server-sdk\n\n# React bindings for frontend\nnpm install @octavus/react\n```\n\n## Backend Setup\n\n### 1. Initialize the Client\n\nCreate an Octavus client instance in your backend:\n\n```typescript\n// lib/octavus.ts\nimport { OctavusClient } from '@octavus/server-sdk';\n\nexport const octavus = new OctavusClient({\n  baseUrl: process.env.OCTAVUS_API_URL!,\n  apiKey: process.env.OCTAVUS_API_KEY!,\n});\n```\n\n### 2. Create a Session Endpoint\n\nCreate an API endpoint that creates sessions and returns the session ID:\n\n```typescript\n// app/api/chat/create/route.ts\nimport { NextResponse } from 'next/server';\nimport { octavus } from '@/lib/octavus';\n\n// Agent ID - get from platform or CLI (see below)\nconst SUPPORT_AGENT_ID = process.env.OCTAVUS_SUPPORT_AGENT_ID!;\n\nexport async function POST(request: Request) {\n  const { input } = await request.json();\n\n  // Create a new session using the agent ID\n  const sessionId = await octavus.agentSessions.create(SUPPORT_AGENT_ID, input);\n\n  return NextResponse.json({ sessionId });\n}\n```\n\n### Getting Your Agent ID\n\nThere are two ways to create and manage agents:\n\n**Option 1: Platform UI (Recommended for getting started)**\n\n1. Go to [octavus.ai](https://octavus.ai) and create an agent in the web editor\n2. Copy the agent ID from the URL (e.g., `octavus.ai/agents/clxyz123abc456`)\n3. Add it to your `.env.local`: `OCTAVUS_SUPPORT_AGENT_ID=clxyz123abc456`\n\n**Option 2: Local Development with CLI**\n\nFor version-controlled agent definitions, use the [Octavus CLI](/docs/server-sdk/cli):\n\n```bash\nnpm install --save-dev @octavus/cli\noctavus sync ./agents/support-chat\n# Output: Agent ID: clxyz123abc456\n```\n\nThe CLI approach is better for teams and CI/CD pipelines where you want agent definitions in your repository.\n\n### 3. Create a Trigger Endpoint\n\nCreate an endpoint that handles triggers and streams responses:\n\n```typescript\n// app/api/trigger/route.ts\nimport { toSSEStream } from '@octavus/server-sdk';\nimport { octavus } from '@/lib/octavus';\n\nexport async function POST(request: Request) {\n  const body = await request.json();\n  const { sessionId, ...payload } = body;\n\n  // Attach to session with tool handlers\n  const session = octavus.agentSessions.attach(sessionId, {\n    tools: {\n      // Define tool handlers that run on your server\n      'get-user-account': async (args) => {\n        const userId = args.userId as string;\n        // Fetch from your database\n        return {\n          name: 'Demo User',\n          email: 'demo@example.com',\n          plan: 'pro',\n        };\n      },\n      'create-support-ticket': async (args) => {\n        // Create ticket in your system\n        return {\n          ticketId: 'TICKET-123',\n          estimatedResponse: '24 hours',\n        };\n      },\n    },\n  });\n\n  // Execute the request and convert to SSE stream\n  const events = session.execute(payload, { signal: request.signal });\n\n  // Return as streaming response\n  return new Response(toSSEStream(events), {\n    headers: {\n      'Content-Type': 'text/event-stream',\n      'Cache-Control': 'no-cache',\n      Connection: 'keep-alive',\n    },\n  });\n}\n```\n\n## Frontend Setup\n\n### 1. Create a Chat Component\n\nUse the `useOctavusChat` hook with the HTTP transport:\n\n```tsx\n// components/chat.tsx\n'use client';\n\nimport { useState, useMemo } from 'react';\nimport { useOctavusChat, createHttpTransport, type UIMessage } from '@octavus/react';\n\ninterface ChatProps {\n  sessionId: string;\n}\n\nexport function Chat({ sessionId }: ChatProps) {\n  const [inputValue, setInputValue] = useState('');\n\n  // Create a stable transport instance\n  const transport = useMemo(\n    () =>\n      createHttpTransport({\n        request: (payload, options) =>\n          fetch('/api/trigger', {\n            method: 'POST',\n            headers: { 'Content-Type': 'application/json' },\n            body: JSON.stringify({ sessionId, ...payload }),\n            signal: options?.signal,\n          }),\n      }),\n    [sessionId],\n  );\n\n  const { messages, status, error, send } = useOctavusChat({ transport });\n\n  const isStreaming = status === 'streaming';\n\n  const handleSubmit = async (e: React.FormEvent) => {\n    e.preventDefault();\n    if (!inputValue.trim() || isStreaming) return;\n\n    const message = inputValue.trim();\n    setInputValue('');\n\n    // Add user message and trigger in one call\n    await send('user-message', { USER_MESSAGE: message }, { userMessage: { content: message } });\n  };\n\n  return (\n    <div className=\"flex flex-col h-full\">\n      {/* Messages */}\n      <div className=\"flex-1 overflow-y-auto p-4 space-y-4\">\n        {messages.map((msg) => (\n          <MessageBubble key={msg.id} message={msg} />\n        ))}\n      </div>\n\n      {/* Input */}\n      <form onSubmit={handleSubmit} className=\"p-4 border-t\">\n        <div className=\"flex gap-2\">\n          <input\n            type=\"text\"\n            value={inputValue}\n            onChange={(e) => setInputValue(e.target.value)}\n            placeholder=\"Type a message...\"\n            className=\"flex-1 px-4 py-2 border rounded-lg\"\n            disabled={isStreaming}\n          />\n          <button\n            type=\"submit\"\n            disabled={isStreaming}\n            className=\"px-4 py-2 bg-blue-500 text-white rounded-lg disabled:opacity-50\"\n          >\n            Send\n          </button>\n        </div>\n      </form>\n    </div>\n  );\n}\n\nfunction MessageBubble({ message }: { message: UIMessage }) {\n  const isUser = message.role === 'user';\n\n  return (\n    <div className={`flex ${isUser ? 'justify-end' : 'justify-start'}`}>\n      <div\n        className={`p-3 rounded-lg max-w-md ${isUser ? 'bg-blue-500 text-white' : 'bg-gray-100'}`}\n      >\n        {message.parts.map((part, i) => {\n          if (part.type === 'text') {\n            return <p key={i}>{part.text}</p>;\n          }\n          return null;\n        })}\n\n        {/* Streaming indicator */}\n        {message.status === 'streaming' && (\n          <span className=\"inline-block w-2 h-4 bg-gray-400 animate-pulse ml-1\" />\n        )}\n      </div>\n    </div>\n  );\n}\n```\n\n### 2. Create Session and Render Chat\n\n```tsx\n// app/chat/page.tsx\n'use client';\n\nimport { useEffect, useState } from 'react';\nimport { Chat } from '@/components/chat';\n\nexport default function ChatPage() {\n  const [sessionId, setSessionId] = useState<string | null>(null);\n\n  useEffect(() => {\n    async function createSession() {\n      const response = await fetch('/api/chat/create', {\n        method: 'POST',\n        headers: { 'Content-Type': 'application/json' },\n        body: JSON.stringify({\n          input: {\n            COMPANY_NAME: 'Acme Corp',\n            PRODUCT_NAME: 'Widget Pro',\n          },\n        }),\n      });\n      const { sessionId } = await response.json();\n      setSessionId(sessionId);\n    }\n\n    createSession();\n  }, []);\n\n  if (!sessionId) {\n    return <div>Loading...</div>;\n  }\n\n  return <Chat sessionId={sessionId} />;\n}\n```\n\n## Environment Variables\n\nAdd these to your `.env.local`:\n\n```bash\nOCTAVUS_API_URL=https://octavus.ai\nOCTAVUS_API_KEY=your-api-key-here\n```\n\n## What's Next?\n\nNow that you have a basic integration working:\n\n- [Learn about the protocol](/docs/protocol/overview) to define custom agent behavior\n- [Explore the Server SDK](/docs/server-sdk/overview) for advanced backend features\n- [Build rich UIs](/docs/client-sdk/overview) with the Client SDK\n- [Handle tools on the client](/docs/client-sdk/client-tools) for interactive UIs and browser APIs\n",
+        content: "\n# Quick Start\n\nThis guide will walk you through integrating Octavus into your application in under 10 minutes.\n\n## Prerequisites\n\n- Node.js 18+\n- An Octavus account with API key\n- A Next.js application (or any Node.js backend)\n\n## Test Your Agent First\n\nBefore integrating with SDKs, use **Agent Preview** to test your agent directly in the platform:\n\n1. Open your agent in the platform at `octavus.ai/platform/agents/[agentId]`\n2. Click the **Preview** tab\n3. Configure session inputs and tool mock responses\n4. Start a conversation to test agent behavior\n\nAgent Preview supports all trigger types, file attachments, tool mocking, and real-time streaming. This is the fastest way to iterate on your agent logic before writing any integration code.\n\n## Installation\n\nInstall the Octavus SDKs in your project:\n\n```bash\n# Server SDK for backend\nnpm install @octavus/server-sdk\n\n# React bindings for frontend\nnpm install @octavus/react\n```\n\n## Backend Setup\n\n### 1. Initialize the Client\n\nCreate an Octavus client instance in your backend:\n\n```typescript\n// lib/octavus.ts\nimport { OctavusClient } from '@octavus/server-sdk';\n\nexport const octavus = new OctavusClient({\n  baseUrl: process.env.OCTAVUS_API_URL!,\n  apiKey: process.env.OCTAVUS_API_KEY!,\n});\n```\n\n### 2. Create a Session Endpoint\n\nCreate an API endpoint that creates sessions and returns the session ID:\n\n```typescript\n// app/api/chat/create/route.ts\nimport { NextResponse } from 'next/server';\nimport { octavus } from '@/lib/octavus';\n\n// Agent ID - get from platform or CLI (see below)\nconst SUPPORT_AGENT_ID = process.env.OCTAVUS_SUPPORT_AGENT_ID!;\n\nexport async function POST(request: Request) {\n  const { input } = await request.json();\n\n  // Create a new session using the agent ID\n  const sessionId = await octavus.agentSessions.create(SUPPORT_AGENT_ID, input);\n\n  return NextResponse.json({ sessionId });\n}\n```\n\n### Getting Your Agent ID\n\nThere are two ways to create and manage agents:\n\n**Option 1: Platform UI (Recommended for getting started)**\n\n1. Go to [octavus.ai](https://octavus.ai) and create an agent in the web editor\n2. Copy the agent ID from the URL (e.g., `octavus.ai/platform/agents/clxyz123abc456`)\n3. Add it to your `.env.local`: `OCTAVUS_SUPPORT_AGENT_ID=clxyz123abc456`\n\n**Option 2: Local Development with CLI**\n\nFor version-controlled agent definitions, use the [Octavus CLI](/docs/server-sdk/cli):\n\n```bash\nnpm install --save-dev @octavus/cli\noctavus sync ./agents/support-chat\n# Output: Agent ID: clxyz123abc456\n```\n\nThe CLI approach is better for teams and CI/CD pipelines where you want agent definitions in your repository.\n\n### 3. Create a Trigger Endpoint\n\nCreate an endpoint that handles triggers and streams responses:\n\n```typescript\n// app/api/trigger/route.ts\nimport { toSSEStream } from '@octavus/server-sdk';\nimport { octavus } from '@/lib/octavus';\n\nexport async function POST(request: Request) {\n  const body = await request.json();\n  const { sessionId, ...payload } = body;\n\n  // Attach to session with tool handlers\n  const session = octavus.agentSessions.attach(sessionId, {\n    tools: {\n      // Define tool handlers that run on your server\n      'get-user-account': async (args) => {\n        const userId = args.userId as string;\n        // Fetch from your database\n        return {\n          name: 'Demo User',\n          email: 'demo@example.com',\n          plan: 'pro',\n        };\n      },\n      'create-support-ticket': async (args) => {\n        // Create ticket in your system\n        return {\n          ticketId: 'TICKET-123',\n          estimatedResponse: '24 hours',\n        };\n      },\n    },\n  });\n\n  // Execute the request and convert to SSE stream\n  const events = session.execute(payload, { signal: request.signal });\n\n  // Return as streaming response\n  return new Response(toSSEStream(events), {\n    headers: {\n      'Content-Type': 'text/event-stream',\n      'Cache-Control': 'no-cache',\n      Connection: 'keep-alive',\n    },\n  });\n}\n```\n\n## Frontend Setup\n\n### 1. Create a Chat Component\n\nUse the `useOctavusChat` hook with the HTTP transport:\n\n```tsx\n// components/chat.tsx\n'use client';\n\nimport { useState, useMemo } from 'react';\nimport { useOctavusChat, createHttpTransport, type UIMessage } from '@octavus/react';\n\ninterface ChatProps {\n  sessionId: string;\n}\n\nexport function Chat({ sessionId }: ChatProps) {\n  const [inputValue, setInputValue] = useState('');\n\n  // Create a stable transport instance\n  const transport = useMemo(\n    () =>\n      createHttpTransport({\n        request: (payload, options) =>\n          fetch('/api/trigger', {\n            method: 'POST',\n            headers: { 'Content-Type': 'application/json' },\n            body: JSON.stringify({ sessionId, ...payload }),\n            signal: options?.signal,\n          }),\n      }),\n    [sessionId],\n  );\n\n  const { messages, status, error, send } = useOctavusChat({ transport });\n\n  const isStreaming = status === 'streaming';\n\n  const handleSubmit = async (e: React.FormEvent) => {\n    e.preventDefault();\n    if (!inputValue.trim() || isStreaming) return;\n\n    const message = inputValue.trim();\n    setInputValue('');\n\n    // Add user message and trigger in one call\n    await send('user-message', { USER_MESSAGE: message }, { userMessage: { content: message } });\n  };\n\n  return (\n    <div className=\"flex flex-col h-full\">\n      {/* Messages */}\n      <div className=\"flex-1 overflow-y-auto p-4 space-y-4\">\n        {messages.map((msg) => (\n          <MessageBubble key={msg.id} message={msg} />\n        ))}\n      </div>\n\n      {/* Input */}\n      <form onSubmit={handleSubmit} className=\"p-4 border-t\">\n        <div className=\"flex gap-2\">\n          <input\n            type=\"text\"\n            value={inputValue}\n            onChange={(e) => setInputValue(e.target.value)}\n            placeholder=\"Type a message...\"\n            className=\"flex-1 px-4 py-2 border rounded-lg\"\n            disabled={isStreaming}\n          />\n          <button\n            type=\"submit\"\n            disabled={isStreaming}\n            className=\"px-4 py-2 bg-blue-500 text-white rounded-lg disabled:opacity-50\"\n          >\n            Send\n          </button>\n        </div>\n      </form>\n    </div>\n  );\n}\n\nfunction MessageBubble({ message }: { message: UIMessage }) {\n  const isUser = message.role === 'user';\n\n  return (\n    <div className={`flex ${isUser ? 'justify-end' : 'justify-start'}`}>\n      <div\n        className={`p-3 rounded-lg max-w-md ${isUser ? 'bg-blue-500 text-white' : 'bg-gray-100'}`}\n      >\n        {message.parts.map((part, i) => {\n          if (part.type === 'text') {\n            return <p key={i}>{part.text}</p>;\n          }\n          return null;\n        })}\n\n        {/* Streaming indicator */}\n        {message.status === 'streaming' && (\n          <span className=\"inline-block w-2 h-4 bg-gray-400 animate-pulse ml-1\" />\n        )}\n      </div>\n    </div>\n  );\n}\n```\n\n### 2. Create Session and Render Chat\n\n```tsx\n// app/chat/page.tsx\n'use client';\n\nimport { useEffect, useState } from 'react';\nimport { Chat } from '@/components/chat';\n\nexport default function ChatPage() {\n  const [sessionId, setSessionId] = useState<string | null>(null);\n\n  useEffect(() => {\n    async function createSession() {\n      const response = await fetch('/api/chat/create', {\n        method: 'POST',\n        headers: { 'Content-Type': 'application/json' },\n        body: JSON.stringify({\n          input: {\n            COMPANY_NAME: 'Acme Corp',\n            PRODUCT_NAME: 'Widget Pro',\n          },\n        }),\n      });\n      const { sessionId } = await response.json();\n      setSessionId(sessionId);\n    }\n\n    createSession();\n  }, []);\n\n  if (!sessionId) {\n    return <div>Loading...</div>;\n  }\n\n  return <Chat sessionId={sessionId} />;\n}\n```\n\n## Environment Variables\n\nAdd these to your `.env.local`:\n\n```bash\nOCTAVUS_API_URL=https://octavus.ai\nOCTAVUS_API_KEY=your-api-key-here\n```\n\n## What's Next?\n\nNow that you have a basic integration working:\n\n- [Learn about the protocol](/docs/protocol/overview) to define custom agent behavior\n- [Explore the Server SDK](/docs/server-sdk/overview) for advanced backend features\n- [Build rich UIs](/docs/client-sdk/overview) with the Client SDK\n- [Handle tools on the client](/docs/client-sdk/client-tools) for interactive UIs and browser APIs\n",
         excerpt: "Quick Start This guide will walk you through integrating Octavus into your application in under 10 minutes.  Prerequisites - Node.js 18+ - An Octavus account with API key - A Next.js application (or...",
         order: 2
       }
@@ -748,7 +748,7 @@ var sections_default = [
         section: "server-sdk",
         title: "Overview",
         description: "Introduction to the Octavus Server SDK for backend integration.",
-        content: "\n# Server SDK Overview\n\nThe `@octavus/server-sdk` package provides a Node.js SDK for integrating Octavus agents into your backend application. It handles session management, streaming, and the tool execution continuation loop.\n\n**Current version:** `2.12.0`\n\n## Installation\n\n```bash\nnpm install @octavus/server-sdk\n```\n\nFor agent management (sync, validate), install the CLI as a dev dependency:\n\n```bash\nnpm install --save-dev @octavus/cli\n```\n\n## Basic Usage\n\n```typescript\nimport { OctavusClient } from '@octavus/server-sdk';\n\nconst client = new OctavusClient({\n  baseUrl: 'https://octavus.ai',\n  apiKey: 'your-api-key',\n});\n```\n\n## Key Features\n\n### Agent Management\n\nAgent definitions are managed via the CLI. See the [CLI documentation](/docs/server-sdk/cli) for details.\n\n```bash\n# Sync agent from local files\noctavus sync ./agents/support-chat\n\n# Output: Created: support-chat\n#         Agent ID: clxyz123abc456\n```\n\n### Session Management\n\nCreate and manage agent sessions using the agent ID:\n\n```typescript\n// Create a new session (use agent ID from CLI sync)\nconst sessionId = await client.agentSessions.create('clxyz123abc456', {\n  COMPANY_NAME: 'Acme Corp',\n  PRODUCT_NAME: 'Widget Pro',\n});\n\n// Get UI-ready session messages (for session restore)\nconst session = await client.agentSessions.getMessages(sessionId);\n```\n\n### Tool Handlers\n\nTools run on your server with your data:\n\n```typescript\nconst session = client.agentSessions.attach(sessionId, {\n  tools: {\n    'get-user-account': async (args) => {\n      // Access your database, APIs, etc.\n      return await db.users.findById(args.userId);\n    },\n  },\n});\n```\n\n### Streaming\n\nAll responses stream in real-time:\n\n```typescript\nimport { toSSEStream } from '@octavus/server-sdk';\n\n// execute() returns an async generator of events\nconst events = session.execute({\n  type: 'trigger',\n  triggerName: 'user-message',\n  input: { USER_MESSAGE: 'Hello!' },\n});\n\n// Convert to SSE stream for HTTP responses\nreturn new Response(toSSEStream(events), {\n  headers: { 'Content-Type': 'text/event-stream' },\n});\n```\n\n### Workers\n\nExecute worker agents for task-based processing:\n\n```typescript\n// Non-streaming: get the output directly\nconst { output } = await client.workers.generate(agentId, {\n  TOPIC: 'AI safety',\n});\n\n// Streaming: observe events in real-time\nfor await (const event of client.workers.execute(agentId, input)) {\n  // Handle stream events\n}\n```\n\n## API Reference\n\n### OctavusClient\n\nThe main entry point for interacting with Octavus.\n\n```typescript\ninterface OctavusClientConfig {\n  baseUrl: string; // Octavus API URL\n  apiKey?: string; // Your API key\n  traceModelRequests?: boolean; // Enable model request tracing (default: false)\n}\n\nclass OctavusClient {\n  readonly agents: AgentsApi;\n  readonly agentSessions: AgentSessionsApi;\n  readonly workers: WorkersApi;\n  readonly files: FilesApi;\n\n  constructor(config: OctavusClientConfig);\n}\n```\n\n### AgentSessionsApi\n\nManages agent sessions.\n\n```typescript\nclass AgentSessionsApi {\n  // Create a new session\n  async create(agentId: string, input?: Record<string, unknown>): Promise<string>;\n\n  // Get full session state (for debugging/internal use)\n  async get(sessionId: string): Promise<SessionState>;\n\n  // Get UI-ready messages (for client display)\n  async getMessages(sessionId: string): Promise<UISessionState>;\n\n  // Attach to a session for triggering\n  attach(sessionId: string, options?: SessionAttachOptions): AgentSession;\n}\n\n// Full session state (internal format)\ninterface SessionState {\n  id: string;\n  agentId: string;\n  input: Record<string, unknown>;\n  variables: Record<string, unknown>;\n  resources: Record<string, unknown>;\n  messages: ChatMessage[]; // Internal message format\n  createdAt: string;\n  updatedAt: string;\n}\n\n// UI-ready session state\ninterface UISessionState {\n  sessionId: string;\n  agentId: string;\n  messages: UIMessage[]; // UI-ready messages for frontend\n}\n```\n\n### AgentSession\n\nHandles request execution and streaming for a specific session.\n\n```typescript\nclass AgentSession {\n  // Execute a request and stream parsed events\n  execute(request: SessionRequest, options?: TriggerOptions): AsyncGenerator<StreamEvent>;\n\n  // Get the session ID\n  getSessionId(): string;\n}\n\ntype SessionRequest = TriggerRequest | ContinueRequest;\n\ninterface TriggerRequest {\n  type: 'trigger';\n  triggerName: string;\n  input?: Record<string, unknown>;\n}\n\ninterface ContinueRequest {\n  type: 'continue';\n  executionId: string;\n  toolResults: ToolResult[];\n}\n\n// Helper to convert events to SSE stream\nfunction toSSEStream(events: AsyncIterable<StreamEvent>): ReadableStream<Uint8Array>;\n```\n\n### FilesApi\n\nHandles file uploads for sessions.\n\n```typescript\nclass FilesApi {\n  // Get presigned URLs for file uploads\n  async getUploadUrls(sessionId: string, files: FileUploadRequest[]): Promise<UploadUrlsResponse>;\n}\n\ninterface FileUploadRequest {\n  filename: string;\n  mediaType: string;\n  size: number;\n}\n\ninterface UploadUrlsResponse {\n  files: {\n    id: string; // File ID for references\n    uploadUrl: string; // PUT to this URL\n    downloadUrl: string; // GET URL after upload\n  }[];\n}\n```\n\nThe client uploads files directly to S3 using the presigned upload URL. See [File Uploads](/docs/client-sdk/file-uploads) for the full integration pattern.\n\n## Next Steps\n\n- [Sessions](/docs/server-sdk/sessions) \u2014 Deep dive into session management\n- [Tools](/docs/server-sdk/tools) \u2014 Implementing tool handlers\n- [Streaming](/docs/server-sdk/streaming) \u2014 Understanding stream events\n- [Workers](/docs/server-sdk/workers) \u2014 Executing worker agents\n- [Debugging](/docs/server-sdk/debugging) \u2014 Model request tracing and debugging\n",
+        content: "\n# Server SDK Overview\n\nThe `@octavus/server-sdk` package provides a Node.js SDK for integrating Octavus agents into your backend application. It handles session management, streaming, and the tool execution continuation loop.\n\n**Current version:** `2.15.0`\n\n## Installation\n\n```bash\nnpm install @octavus/server-sdk\n```\n\nFor agent management (sync, validate), install the CLI as a dev dependency:\n\n```bash\nnpm install --save-dev @octavus/cli\n```\n\n## Basic Usage\n\n```typescript\nimport { OctavusClient } from '@octavus/server-sdk';\n\nconst client = new OctavusClient({\n  baseUrl: 'https://octavus.ai',\n  apiKey: 'your-api-key',\n});\n```\n\n## Key Features\n\n### Agent Management\n\nAgent definitions are managed via the CLI. See the [CLI documentation](/docs/server-sdk/cli) for details.\n\n```bash\n# Sync agent from local files\noctavus sync ./agents/support-chat\n\n# Output: Created: support-chat\n#         Agent ID: clxyz123abc456\n```\n\n### Session Management\n\nCreate and manage agent sessions using the agent ID:\n\n```typescript\n// Create a new session (use agent ID from CLI sync)\nconst sessionId = await client.agentSessions.create('clxyz123abc456', {\n  COMPANY_NAME: 'Acme Corp',\n  PRODUCT_NAME: 'Widget Pro',\n});\n\n// Get UI-ready session messages (for session restore)\nconst session = await client.agentSessions.getMessages(sessionId);\n```\n\n### Tool Handlers\n\nTools run on your server with your data:\n\n```typescript\nconst session = client.agentSessions.attach(sessionId, {\n  tools: {\n    'get-user-account': async (args) => {\n      // Access your database, APIs, etc.\n      return await db.users.findById(args.userId);\n    },\n  },\n});\n```\n\n### Streaming\n\nAll responses stream in real-time:\n\n```typescript\nimport { toSSEStream } from '@octavus/server-sdk';\n\n// execute() returns an async generator of events\nconst events = session.execute({\n  type: 'trigger',\n  triggerName: 'user-message',\n  input: { USER_MESSAGE: 'Hello!' },\n});\n\n// Convert to SSE stream for HTTP responses\nreturn new Response(toSSEStream(events), {\n  headers: { 'Content-Type': 'text/event-stream' },\n});\n```\n\n### Workers\n\nExecute worker agents for task-based processing:\n\n```typescript\n// Non-streaming: get the output directly\nconst { output } = await client.workers.generate(agentId, {\n  TOPIC: 'AI safety',\n});\n\n// Streaming: observe events in real-time\nfor await (const event of client.workers.execute(agentId, input)) {\n  // Handle stream events\n}\n```\n\n## API Reference\n\n### OctavusClient\n\nThe main entry point for interacting with Octavus.\n\n```typescript\ninterface OctavusClientConfig {\n  baseUrl: string; // Octavus API URL\n  apiKey?: string; // Your API key\n  traceModelRequests?: boolean; // Enable model request tracing (default: false)\n}\n\nclass OctavusClient {\n  readonly agents: AgentsApi;\n  readonly agentSessions: AgentSessionsApi;\n  readonly workers: WorkersApi;\n  readonly files: FilesApi;\n\n  constructor(config: OctavusClientConfig);\n}\n```\n\n### AgentSessionsApi\n\nManages agent sessions.\n\n```typescript\nclass AgentSessionsApi {\n  // Create a new session\n  async create(agentId: string, input?: Record<string, unknown>): Promise<string>;\n\n  // Get full session state (for debugging/internal use)\n  async get(sessionId: string): Promise<SessionState>;\n\n  // Get UI-ready messages (for client display)\n  async getMessages(sessionId: string): Promise<UISessionState>;\n\n  // Attach to a session for triggering\n  attach(sessionId: string, options?: SessionAttachOptions): AgentSession;\n}\n\n// Full session state (internal format)\ninterface SessionState {\n  id: string;\n  agentId: string;\n  input: Record<string, unknown>;\n  variables: Record<string, unknown>;\n  resources: Record<string, unknown>;\n  messages: ChatMessage[]; // Internal message format\n  createdAt: string;\n  updatedAt: string;\n}\n\n// UI-ready session state\ninterface UISessionState {\n  sessionId: string;\n  agentId: string;\n  messages: UIMessage[]; // UI-ready messages for frontend\n}\n```\n\n### AgentSession\n\nHandles request execution and streaming for a specific session.\n\n```typescript\nclass AgentSession {\n  // Execute a request and stream parsed events\n  execute(request: SessionRequest, options?: TriggerOptions): AsyncGenerator<StreamEvent>;\n\n  // Get the session ID\n  getSessionId(): string;\n}\n\ntype SessionRequest = TriggerRequest | ContinueRequest;\n\ninterface TriggerRequest {\n  type: 'trigger';\n  triggerName: string;\n  input?: Record<string, unknown>;\n}\n\ninterface ContinueRequest {\n  type: 'continue';\n  executionId: string;\n  toolResults: ToolResult[];\n}\n\n// Helper to convert events to SSE stream\nfunction toSSEStream(events: AsyncIterable<StreamEvent>): ReadableStream<Uint8Array>;\n```\n\n### FilesApi\n\nHandles file uploads for sessions.\n\n```typescript\nclass FilesApi {\n  // Get presigned URLs for file uploads\n  async getUploadUrls(sessionId: string, files: FileUploadRequest[]): Promise<UploadUrlsResponse>;\n}\n\ninterface FileUploadRequest {\n  filename: string;\n  mediaType: string;\n  size: number;\n}\n\ninterface UploadUrlsResponse {\n  files: {\n    id: string; // File ID for references\n    uploadUrl: string; // PUT to this URL\n    downloadUrl: string; // GET URL after upload\n  }[];\n}\n```\n\nThe client uploads files directly to S3 using the presigned upload URL. See [File Uploads](/docs/client-sdk/file-uploads) for the full integration pattern.\n\n## Next Steps\n\n- [Sessions](/docs/server-sdk/sessions) \u2014 Deep dive into session management\n- [Tools](/docs/server-sdk/tools) \u2014 Implementing tool handlers\n- [Streaming](/docs/server-sdk/streaming) \u2014 Understanding stream events\n- [Workers](/docs/server-sdk/workers) \u2014 Executing worker agents\n- [Debugging](/docs/server-sdk/debugging) \u2014 Model request tracing and debugging\n",
         excerpt: "Server SDK Overview The  package provides a Node.js SDK for integrating Octavus agents into your backend application. It handles session management, streaming, and the tool execution continuation...",
         order: 1
       },
@@ -784,7 +784,7 @@ var sections_default = [
         section: "server-sdk",
         title: "CLI",
         description: "Command-line interface for validating and syncing agent definitions.",
-        content: '\n# Octavus CLI\n\nThe `@octavus/cli` package provides a command-line interface for validating and syncing agent definitions from your local filesystem to the Octavus platform.\n\n**Current version:** `2.12.0`\n\n## Installation\n\n```bash\nnpm install --save-dev @octavus/cli\n```\n\n## Configuration\n\nThe CLI requires an API key with the **Agents** permission.\n\n### Environment Variables\n\n| Variable              | Description                                    |\n| --------------------- | ---------------------------------------------- |\n| `OCTAVUS_CLI_API_KEY` | API key with "Agents" permission (recommended) |\n| `OCTAVUS_API_KEY`     | Fallback if `OCTAVUS_CLI_API_KEY` not set      |\n| `OCTAVUS_API_URL`     | Optional, defaults to `https://octavus.ai`     |\n\n### Two-Key Strategy (Recommended)\n\nFor production deployments, use separate API keys with minimal permissions:\n\n```bash\n# CI/CD or .env.local (not committed)\nOCTAVUS_CLI_API_KEY=oct_sk_...  # "Agents" permission only\n\n# Production .env\nOCTAVUS_API_KEY=oct_sk_...      # "Sessions" permission only\n```\n\nThis ensures production servers only have session permissions (smaller blast radius if leaked), while agent management is restricted to development/CI environments.\n\n### Multiple Environments\n\nUse separate Octavus projects for staging and production, each with their own API keys. The `--env` flag lets you load different environment files:\n\n```bash\n# Local development (default: .env)\noctavus sync ./agents/my-agent\n\n# Staging project\noctavus --env .env.staging sync ./agents/my-agent\n\n# Production project\noctavus --env .env.production sync ./agents/my-agent\n```\n\nExample environment files:\n\n```bash\n# .env.staging (syncs to your staging project)\nOCTAVUS_CLI_API_KEY=oct_sk_staging_project_key...\n\n# .env.production (syncs to your production project)\nOCTAVUS_CLI_API_KEY=oct_sk_production_project_key...\n```\n\nEach project has its own agents, so you\'ll get different agent IDs per environment.\n\n## Global Options\n\n| Option         | Description                                             |\n| -------------- | ------------------------------------------------------- |\n| `--env <file>` | Load environment from a specific file (default: `.env`) |\n| `--help`       | Show help                                               |\n| `--version`    | Show version                                            |\n\n## Commands\n\n### `octavus sync <path>`\n\nSync an agent definition to the platform. Creates the agent if it doesn\'t exist, or updates it if it does.\n\n```bash\noctavus sync ./agents/my-agent\n```\n\n**Options:**\n\n- `--json` \u2014 Output as JSON (for CI/CD parsing)\n- `--quiet` \u2014 Suppress non-essential output\n\n**Example output:**\n\n```\n\u2139 Reading agent from ./agents/my-agent...\n\u2139 Syncing support-chat...\n\u2713 Created: support-chat\n  Agent ID: clxyz123abc456\n```\n\n### `octavus validate <path>`\n\nValidate an agent definition without saving. Useful for CI/CD pipelines.\n\n```bash\noctavus validate ./agents/my-agent\n```\n\n**Exit codes:**\n\n- `0` \u2014 Validation passed\n- `1` \u2014 Validation errors\n- `2` \u2014 Configuration errors (missing API key, etc.)\n\n### `octavus list`\n\nList all agents in your project.\n\n```bash\noctavus list\n```\n\n**Example output:**\n\n```\nSLUG                  NAME                            FORMAT        ID\n\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\nsupport-chat          Support Chat Agent              interactive   clxyz123abc456\n\n1 agent(s)\n```\n\n### `octavus get <slug>`\n\nGet details about a specific agent by its slug.\n\n```bash\noctavus get support-chat\n```\n\n### `octavus archive <slug>`\n\nArchive an agent by slug (soft delete). Archived agents are removed from the active agent list and their slug is freed for reuse.\n\n```bash\noctavus archive support-chat\n```\n\n**Options:**\n\n- `--json` \u2014 Output as JSON (for CI/CD parsing)\n- `--quiet` \u2014 Suppress non-essential output\n\n**Example output:**\n\n```\n\u2139 Archiving support-chat...\n\u2713 Archived: support-chat\n  Agent ID: clxyz123abc456\n```\n\n## Agent Directory Structure\n\nThe CLI expects agent definitions in a specific directory structure:\n\n```\nmy-agent/\n\u251C\u2500\u2500 settings.json     # Required: Agent metadata\n\u251C\u2500\u2500 protocol.yaml     # Required: Agent protocol\n\u251C\u2500\u2500 prompts/          # Optional: Prompt templates\n\u2502   \u251C\u2500\u2500 system.md\n\u2502   \u2514\u2500\u2500 user-message.md\n\u2514\u2500\u2500 references/       # Optional: Reference documents\n    \u2514\u2500\u2500 api-guidelines.md\n```\n\n### references/\n\nReference files are markdown documents with YAML frontmatter containing a `description`. The agent can fetch these on demand during execution. See [References](/docs/protocol/references) for details.\n\n### settings.json\n\n```json\n{\n  "slug": "my-agent",\n  "name": "My Agent",\n  "description": "A helpful assistant",\n  "format": "interactive"\n}\n```\n\n### protocol.yaml\n\nSee the [Protocol documentation](/docs/protocol/overview) for details on protocol syntax.\n\n## CI/CD Integration\n\n### GitHub Actions\n\n```yaml\nname: Validate and Sync Agents\n\non:\n  push:\n    branches: [main]\n    paths:\n      - \'agents/**\'\n\njobs:\n  sync:\n    runs-on: ubuntu-latest\n    steps:\n      - uses: actions/checkout@v4\n\n      - uses: actions/setup-node@v4\n        with:\n          node-version: \'22\'\n\n      - run: npm install\n\n      - name: Validate agent\n        run: npx octavus validate ./agents/support-chat\n        env:\n          OCTAVUS_CLI_API_KEY: ${{ secrets.OCTAVUS_CLI_API_KEY }}\n\n      - name: Sync agent\n        run: npx octavus sync ./agents/support-chat\n        env:\n          OCTAVUS_CLI_API_KEY: ${{ secrets.OCTAVUS_CLI_API_KEY }}\n```\n\n### Package.json Scripts\n\nAdd sync scripts to your `package.json`:\n\n```json\n{\n  "scripts": {\n    "agents:validate": "octavus validate ./agents/my-agent",\n    "agents:sync": "octavus sync ./agents/my-agent"\n  },\n  "devDependencies": {\n    "@octavus/cli": "^0.1.0"\n  }\n}\n```\n\n## Workflow\n\nThe recommended workflow for managing agents:\n\n1. **Define agent locally** \u2014 Create `settings.json`, `protocol.yaml`, and prompts\n2. **Validate** \u2014 Run `octavus validate ./my-agent` to check for errors\n3. **Sync** \u2014 Run `octavus sync ./my-agent` to push to platform\n4. **Store agent ID** \u2014 Save the output ID in an environment variable\n5. **Use in app** \u2014 Read the ID from env and pass to `client.agentSessions.create()`\n\n```bash\n# After syncing: octavus sync ./agents/support-chat\n# Output: Agent ID: clxyz123abc456\n\n# Add to your .env file\nOCTAVUS_SUPPORT_AGENT_ID=clxyz123abc456\n```\n\n```typescript\nconst agentId = process.env.OCTAVUS_SUPPORT_AGENT_ID;\n\nconst sessionId = await client.agentSessions.create(agentId, {\n  COMPANY_NAME: \'Acme Corp\',\n});\n```\n',
+        content: '\n# Octavus CLI\n\nThe `@octavus/cli` package provides a command-line interface for validating and syncing agent definitions from your local filesystem to the Octavus platform.\n\n**Current version:** `2.15.0`\n\n## Installation\n\n```bash\nnpm install --save-dev @octavus/cli\n```\n\n## Configuration\n\nThe CLI requires an API key with the **Agents** permission.\n\n### Environment Variables\n\n| Variable              | Description                                    |\n| --------------------- | ---------------------------------------------- |\n| `OCTAVUS_CLI_API_KEY` | API key with "Agents" permission (recommended) |\n| `OCTAVUS_API_KEY`     | Fallback if `OCTAVUS_CLI_API_KEY` not set      |\n| `OCTAVUS_API_URL`     | Optional, defaults to `https://octavus.ai`     |\n\n### Two-Key Strategy (Recommended)\n\nFor production deployments, use separate API keys with minimal permissions:\n\n```bash\n# CI/CD or .env.local (not committed)\nOCTAVUS_CLI_API_KEY=oct_sk_...  # "Agents" permission only\n\n# Production .env\nOCTAVUS_API_KEY=oct_sk_...      # "Sessions" permission only\n```\n\nThis ensures production servers only have session permissions (smaller blast radius if leaked), while agent management is restricted to development/CI environments.\n\n### Multiple Environments\n\nUse separate Octavus projects for staging and production, each with their own API keys. The `--env` flag lets you load different environment files:\n\n```bash\n# Local development (default: .env)\noctavus sync ./agents/my-agent\n\n# Staging project\noctavus --env .env.staging sync ./agents/my-agent\n\n# Production project\noctavus --env .env.production sync ./agents/my-agent\n```\n\nExample environment files:\n\n```bash\n# .env.staging (syncs to your staging project)\nOCTAVUS_CLI_API_KEY=oct_sk_staging_project_key...\n\n# .env.production (syncs to your production project)\nOCTAVUS_CLI_API_KEY=oct_sk_production_project_key...\n```\n\nEach project has its own agents, so you\'ll get different agent IDs per environment.\n\n## Global Options\n\n| Option         | Description                                             |\n| -------------- | ------------------------------------------------------- |\n| `--env <file>` | Load environment from a specific file (default: `.env`) |\n| `--help`       | Show help                                               |\n| `--version`    | Show version                                            |\n\n## Commands\n\n### `octavus sync <path>`\n\nSync an agent definition to the platform. Creates the agent if it doesn\'t exist, or updates it if it does.\n\n```bash\noctavus sync ./agents/my-agent\n```\n\n**Options:**\n\n- `--json` \u2014 Output as JSON (for CI/CD parsing)\n- `--quiet` \u2014 Suppress non-essential output\n\n**Example output:**\n\n```\n\u2139 Reading agent from ./agents/my-agent...\n\u2139 Syncing support-chat...\n\u2713 Created: support-chat\n  Agent ID: clxyz123abc456\n```\n\n### `octavus validate <path>`\n\nValidate an agent definition without saving. Useful for CI/CD pipelines.\n\n```bash\noctavus validate ./agents/my-agent\n```\n\n**Exit codes:**\n\n- `0` \u2014 Validation passed\n- `1` \u2014 Validation errors\n- `2` \u2014 Configuration errors (missing API key, etc.)\n\n### `octavus list`\n\nList all agents in your project.\n\n```bash\noctavus list\n```\n\n**Example output:**\n\n```\nSLUG                  NAME                            FORMAT        ID\n\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\nsupport-chat          Support Chat Agent              interactive   clxyz123abc456\n\n1 agent(s)\n```\n\n### `octavus get <slug>`\n\nGet details about a specific agent by its slug.\n\n```bash\noctavus get support-chat\n```\n\n### `octavus archive <slug>`\n\nArchive an agent by slug (soft delete). Archived agents are removed from the active agent list and their slug is freed for reuse.\n\n```bash\noctavus archive support-chat\n```\n\n**Options:**\n\n- `--json` \u2014 Output as JSON (for CI/CD parsing)\n- `--quiet` \u2014 Suppress non-essential output\n\n**Example output:**\n\n```\n\u2139 Archiving support-chat...\n\u2713 Archived: support-chat\n  Agent ID: clxyz123abc456\n```\n\n## Agent Directory Structure\n\nThe CLI expects agent definitions in a specific directory structure:\n\n```\nmy-agent/\n\u251C\u2500\u2500 settings.json     # Required: Agent metadata\n\u251C\u2500\u2500 protocol.yaml     # Required: Agent protocol\n\u251C\u2500\u2500 prompts/          # Optional: Prompt templates\n\u2502   \u251C\u2500\u2500 system.md\n\u2502   \u2514\u2500\u2500 user-message.md\n\u2514\u2500\u2500 references/       # Optional: Reference documents\n    \u2514\u2500\u2500 api-guidelines.md\n```\n\n### references/\n\nReference files are markdown documents with YAML frontmatter containing a `description`. The agent can fetch these on demand during execution. See [References](/docs/protocol/references) for details.\n\n### settings.json\n\n```json\n{\n  "slug": "my-agent",\n  "name": "My Agent",\n  "description": "A helpful assistant",\n  "format": "interactive"\n}\n```\n\n### protocol.yaml\n\nSee the [Protocol documentation](/docs/protocol/overview) for details on protocol syntax.\n\n## CI/CD Integration\n\n### GitHub Actions\n\n```yaml\nname: Validate and Sync Agents\n\non:\n  push:\n    branches: [main]\n    paths:\n      - \'agents/**\'\n\njobs:\n  sync:\n    runs-on: ubuntu-latest\n    steps:\n      - uses: actions/checkout@v4\n\n      - uses: actions/setup-node@v4\n        with:\n          node-version: \'22\'\n\n      - run: npm install\n\n      - name: Validate agent\n        run: npx octavus validate ./agents/support-chat\n        env:\n          OCTAVUS_CLI_API_KEY: ${{ secrets.OCTAVUS_CLI_API_KEY }}\n\n      - name: Sync agent\n        run: npx octavus sync ./agents/support-chat\n        env:\n          OCTAVUS_CLI_API_KEY: ${{ secrets.OCTAVUS_CLI_API_KEY }}\n```\n\n### Package.json Scripts\n\nAdd sync scripts to your `package.json`:\n\n```json\n{\n  "scripts": {\n    "agents:validate": "octavus validate ./agents/my-agent",\n    "agents:sync": "octavus sync ./agents/my-agent"\n  },\n  "devDependencies": {\n    "@octavus/cli": "^0.1.0"\n  }\n}\n```\n\n## Workflow\n\nThe recommended workflow for managing agents:\n\n1. **Define agent locally** \u2014 Create `settings.json`, `protocol.yaml`, and prompts\n2. **Validate** \u2014 Run `octavus validate ./my-agent` to check for errors\n3. **Sync** \u2014 Run `octavus sync ./my-agent` to push to platform\n4. **Store agent ID** \u2014 Save the output ID in an environment variable\n5. **Use in app** \u2014 Read the ID from env and pass to `client.agentSessions.create()`\n\n```bash\n# After syncing: octavus sync ./agents/support-chat\n# Output: Agent ID: clxyz123abc456\n\n# Add to your .env file\nOCTAVUS_SUPPORT_AGENT_ID=clxyz123abc456\n```\n\n```typescript\nconst agentId = process.env.OCTAVUS_SUPPORT_AGENT_ID;\n\nconst sessionId = await client.agentSessions.create(agentId, {\n  COMPANY_NAME: \'Acme Corp\',\n});\n```\n',
         excerpt: "Octavus CLI The  package provides a command-line interface for validating and syncing agent definitions from your local filesystem to the Octavus platform. Current version:   Installation ...",
         order: 5
       },
@@ -793,7 +793,7 @@ var sections_default = [
         section: "server-sdk",
         title: "Workers",
         description: "Executing worker agents with the Server SDK.",
-        content: "\n# Workers API\n\nThe `WorkersApi` enables executing worker agents from your server. Workers are task-based agents that run steps sequentially and return an output value.\n\n## Basic Usage\n\n```typescript\nimport { OctavusClient } from '@octavus/server-sdk';\n\nconst client = new OctavusClient({\n  baseUrl: 'https://octavus.ai',\n  apiKey: 'your-api-key',\n});\n\nconst { output, sessionId } = await client.workers.generate(agentId, {\n  TOPIC: 'AI safety',\n  DEPTH: 'detailed',\n});\n\nconsole.log('Result:', output);\nconsole.log(`Debug: ${client.baseUrl}/sessions/${sessionId}`);\n```\n\n## WorkersApi Reference\n\n### generate()\n\nExecute a worker and return the output directly.\n\n```typescript\nasync generate(\n  agentId: string,\n  input: Record<string, unknown>,\n  options?: WorkerExecuteOptions\n): Promise<WorkerGenerateResult>\n```\n\nRuns the worker to completion and returns the output value. This is the simplest way to execute a worker.\n\n**Returns:**\n\n```typescript\ninterface WorkerGenerateResult {\n  /** The worker's output value */\n  output: unknown;\n  /** Session ID for debugging (usable for session URLs) */\n  sessionId: string;\n}\n```\n\n**Throws:** `WorkerError` if the worker fails or completes without producing output.\n\n### execute()\n\nExecute a worker and stream the response. Use this when you need to observe intermediate events like text deltas, tool calls, or progress tracking.\n\n```typescript\nasync *execute(\n  agentId: string,\n  input: Record<string, unknown>,\n  options?: WorkerExecuteOptions\n): AsyncGenerator<StreamEvent>\n```\n\n### continue()\n\nContinue execution after client-side tool handling.\n\n```typescript\nasync *continue(\n  agentId: string,\n  executionId: string,\n  toolResults: ToolResult[],\n  options?: WorkerExecuteOptions\n): AsyncGenerator<StreamEvent>\n```\n\nUse this when the worker has tools without server-side handlers. The execution pauses with a `client-tool-request` event, you execute the tools, then call `continue()` to resume.\n\n### Shared Options\n\nAll methods accept the same options:\n\n```typescript\ninterface WorkerExecuteOptions {\n  /** Tool handlers for server-side tool execution */\n  tools?: ToolHandlers;\n  /** Abort signal to cancel the execution */\n  signal?: AbortSignal;\n}\n```\n\n**Parameters:**\n\n| Parameter | Type                      | Description                 |\n| --------- | ------------------------- | --------------------------- |\n| `agentId` | `string`                  | The worker agent ID         |\n| `input`   | `Record<string, unknown>` | Input values for the worker |\n| `options` | `WorkerExecuteOptions`    | Optional configuration      |\n\n## Tool Handlers\n\nProvide tool handlers to execute tools server-side:\n\n```typescript\nconst { output } = await client.workers.generate(\n  agentId,\n  { TOPIC: 'AI safety' },\n  {\n    tools: {\n      'web-search': async (args) => {\n        return await searchWeb(args.query);\n      },\n      'get-user-data': async (args) => {\n        return await db.users.findById(args.userId);\n      },\n    },\n  },\n);\n```\n\nTools defined in the worker protocol but not provided as handlers become client tools \u2014 the execution pauses and emits a `client-tool-request` event.\n\n## Error Handling\n\n### WorkerError (generate)\n\n`generate()` throws a `WorkerError` on failure. The error includes an optional `sessionId` for constructing debug URLs:\n\n```typescript\nimport { OctavusClient, WorkerError } from '@octavus/server-sdk';\n\ntry {\n  const { output } = await client.workers.generate(agentId, input);\n  console.log('Result:', output);\n} catch (error) {\n  if (error instanceof WorkerError) {\n    console.error('Worker failed:', error.message);\n    if (error.sessionId) {\n      console.error(`Debug: ${client.baseUrl}/sessions/${error.sessionId}`);\n    }\n  }\n}\n```\n\n### Stream Errors (execute)\n\nWhen using `execute()`, errors appear as stream events:\n\n```typescript\nfor await (const event of client.workers.execute(agentId, input)) {\n  if (event.type === 'error') {\n    console.error(`Error: ${event.message}`);\n    console.error(`Type: ${event.errorType}`);\n    console.error(`Retryable: ${event.retryable}`);\n  }\n\n  if (event.type === 'worker-result' && event.error) {\n    console.error(`Worker failed: ${event.error}`);\n  }\n}\n```\n\n### Error Types\n\n| Type               | Description           |\n| ------------------ | --------------------- |\n| `validation_error` | Invalid input         |\n| `not_found_error`  | Worker not found      |\n| `provider_error`   | LLM provider error    |\n| `tool_error`       | Tool execution failed |\n| `execution_error`  | Worker step failed    |\n\n## Cancellation\n\nUse an abort signal to cancel execution:\n\n```typescript\nconst { output } = await client.workers.generate(agentId, input, {\n  signal: AbortSignal.timeout(30_000),\n});\n```\n\nWith `execute()` and a manual controller:\n\n```typescript\nconst controller = new AbortController();\nsetTimeout(() => controller.abort(), 30000);\n\ntry {\n  for await (const event of client.workers.execute(agentId, input, {\n    signal: controller.signal,\n  })) {\n    // Process events\n  }\n} catch (error) {\n  if (error.name === 'AbortError') {\n    console.log('Worker cancelled');\n  }\n}\n```\n\n## Streaming\n\nWhen you need real-time visibility into the worker's execution \u2014 text generation, tool calls, or progress \u2014 use `execute()` instead of `generate()`.\n\n### Basic Streaming\n\n```typescript\nconst events = client.workers.execute(agentId, {\n  TOPIC: 'AI safety',\n  DEPTH: 'detailed',\n});\n\nfor await (const event of events) {\n  if (event.type === 'worker-start') {\n    console.log(`Worker ${event.workerSlug} started`);\n  }\n  if (event.type === 'text-delta') {\n    process.stdout.write(event.delta);\n  }\n  if (event.type === 'worker-result') {\n    console.log('Output:', event.output);\n  }\n}\n```\n\n### Streaming to HTTP Response\n\nConvert worker events to an SSE stream:\n\n```typescript\nimport { toSSEStream } from '@octavus/server-sdk';\n\nexport async function POST(request: Request) {\n  const { agentId, input } = await request.json();\n\n  const events = client.workers.execute(agentId, input, {\n    tools: {\n      search: async (args) => await search(args.query),\n    },\n  });\n\n  return new Response(toSSEStream(events), {\n    headers: { 'Content-Type': 'text/event-stream' },\n  });\n}\n```\n\n### Client Tool Continuation\n\nWhen workers have tools without handlers, execution pauses:\n\n```typescript\nfor await (const event of client.workers.execute(agentId, input)) {\n  if (event.type === 'client-tool-request') {\n    const results = await executeClientTools(event.toolCalls);\n\n    for await (const ev of client.workers.continue(agentId, event.executionId, results)) {\n      // Handle remaining events\n    }\n    break;\n  }\n}\n```\n\nThe `client-tool-request` event includes:\n\n```typescript\n{\n  type: 'client-tool-request',\n  executionId: string,      // Pass to continue()\n  toolCalls: [{\n    toolCallId: string,\n    toolName: string,\n    args: Record<string, unknown>,\n  }],\n}\n```\n\n### Stream Events\n\nWorkers emit standard stream events plus worker-specific events.\n\n#### Worker Events\n\n```typescript\n// Worker started\n{\n  type: 'worker-start',\n  workerId: string,     // Unique ID (also used as session ID for debug)\n  workerSlug: string,   // The worker's slug\n  description?: string, // Display description for UI\n}\n\n// Worker completed\n{\n  type: 'worker-result',\n  workerId: string,\n  output?: unknown,  // The worker's output value\n  error?: string,    // Error message if worker failed\n}\n```\n\n#### Common Events\n\n| Event                   | Description                 |\n| ----------------------- | --------------------------- |\n| `start`                 | Execution started           |\n| `finish`                | Execution completed         |\n| `text-start`            | Text generation started     |\n| `text-delta`            | Text chunk received         |\n| `text-end`              | Text generation ended       |\n| `block-start`           | Step started                |\n| `block-end`             | Step completed              |\n| `tool-input-available`  | Tool arguments ready        |\n| `tool-output-available` | Tool result ready           |\n| `client-tool-request`   | Client tools need execution |\n| `error`                 | Error occurred              |\n\n## Full Examples\n\n### generate()\n\n```typescript\nimport { OctavusClient, WorkerError } from '@octavus/server-sdk';\n\nconst client = new OctavusClient({\n  baseUrl: 'https://octavus.ai',\n  apiKey: process.env.OCTAVUS_API_KEY!,\n});\n\ntry {\n  const { output, sessionId } = await client.workers.generate(\n    'research-assistant-id',\n    {\n      TOPIC: 'AI safety best practices',\n      DEPTH: 'detailed',\n    },\n    {\n      tools: {\n        'web-search': async ({ query }) => await performWebSearch(query),\n      },\n      signal: AbortSignal.timeout(120_000),\n    },\n  );\n\n  console.log('Result:', output);\n} catch (error) {\n  if (error instanceof WorkerError) {\n    console.error('Failed:', error.message);\n    if (error.sessionId) {\n      console.error(`Debug: ${client.baseUrl}/sessions/${error.sessionId}`);\n    }\n  }\n}\n```\n\n### execute()\n\nFor full control over streaming events and progress tracking:\n\n```typescript\nimport { OctavusClient, type StreamEvent } from '@octavus/server-sdk';\n\nconst client = new OctavusClient({\n  baseUrl: 'https://octavus.ai',\n  apiKey: process.env.OCTAVUS_API_KEY!,\n});\n\nasync function runResearchWorker(topic: string) {\n  console.log(`Researching: ${topic}\\n`);\n\n  const events = client.workers.execute(\n    'research-assistant-id',\n    {\n      TOPIC: topic,\n      DEPTH: 'detailed',\n    },\n    {\n      tools: {\n        'web-search': async ({ query }) => {\n          console.log(`Searching: ${query}`);\n          return await performWebSearch(query);\n        },\n      },\n    },\n  );\n\n  let output: unknown;\n\n  for await (const event of events) {\n    switch (event.type) {\n      case 'worker-start':\n        console.log(`Started: ${event.workerSlug}`);\n        break;\n\n      case 'block-start':\n        console.log(`Step: ${event.blockName}`);\n        break;\n\n      case 'text-delta':\n        process.stdout.write(event.delta);\n        break;\n\n      case 'worker-result':\n        if (event.error) {\n          throw new Error(event.error);\n        }\n        output = event.output;\n        break;\n\n      case 'error':\n        throw new Error(event.message);\n    }\n  }\n\n  console.log('\\n\\nResearch complete!');\n  return output;\n}\n\nconst result = await runResearchWorker('AI safety best practices');\nconsole.log('Result:', result);\n```\n\n## Next Steps\n\n- [Workers Protocol](/docs/protocol/workers) \u2014 Worker protocol reference\n- [Streaming](/docs/server-sdk/streaming) \u2014 Understanding stream events\n- [Tools](/docs/server-sdk/tools) \u2014 Tool handler patterns\n",
+        content: "\n# Workers API\n\nThe `WorkersApi` enables executing worker agents from your server. Workers are task-based agents that run steps sequentially and return an output value.\n\n## Basic Usage\n\n```typescript\nimport { OctavusClient } from '@octavus/server-sdk';\n\nconst client = new OctavusClient({\n  baseUrl: 'https://octavus.ai',\n  apiKey: 'your-api-key',\n});\n\nconst { output, sessionId } = await client.workers.generate(agentId, {\n  TOPIC: 'AI safety',\n  DEPTH: 'detailed',\n});\n\nconsole.log('Result:', output);\nconsole.log(`Debug: ${client.baseUrl}/sessions/${sessionId}`);\n```\n\n## WorkersApi Reference\n\n### generate()\n\nExecute a worker and return the output directly.\n\n```typescript\nasync generate(\n  agentId: string,\n  input: Record<string, unknown>,\n  options?: WorkerExecuteOptions\n): Promise<WorkerGenerateResult>\n```\n\nRuns the worker to completion and returns the output value. This is the simplest way to execute a worker.\n\n**Returns:**\n\n```typescript\ninterface WorkerGenerateResult {\n  /** The worker's output value */\n  output: unknown;\n  /** Session ID for debugging (usable for session URLs) */\n  sessionId: string;\n}\n```\n\n**Throws:** `WorkerError` if the worker fails or completes without producing output.\n\n### execute()\n\nExecute a worker and stream the response. Use this when you need to observe intermediate events like text deltas, tool calls, or progress tracking.\n\n```typescript\nasync *execute(\n  agentId: string,\n  input: Record<string, unknown>,\n  options?: WorkerExecuteOptions\n): AsyncGenerator<StreamEvent>\n```\n\n### continue()\n\nContinue execution after client-side tool handling.\n\n```typescript\nasync *continue(\n  agentId: string,\n  executionId: string,\n  toolResults: ToolResult[],\n  options?: WorkerExecuteOptions\n): AsyncGenerator<StreamEvent>\n```\n\nUse this when the worker has tools without server-side handlers. The execution pauses with a `client-tool-request` event, you execute the tools, then call `continue()` to resume.\n\n### Shared Options\n\nAll methods accept the same options:\n\n```typescript\ninterface WorkerExecuteOptions {\n  /** Tool handlers for server-side tool execution */\n  tools?: ToolHandlers;\n  /** Abort signal to cancel the execution */\n  signal?: AbortSignal;\n}\n```\n\n**Parameters:**\n\n| Parameter | Type                      | Description                 |\n| --------- | ------------------------- | --------------------------- |\n| `agentId` | `string`                  | The worker agent ID         |\n| `input`   | `Record<string, unknown>` | Input values for the worker |\n| `options` | `WorkerExecuteOptions`    | Optional configuration      |\n\n## Tool Handlers\n\nProvide tool handlers to execute tools server-side:\n\n```typescript\nconst { output } = await client.workers.generate(\n  agentId,\n  { TOPIC: 'AI safety' },\n  {\n    tools: {\n      'web-search': async (args) => {\n        return await searchWeb(args.query);\n      },\n      'get-user-data': async (args) => {\n        return await db.users.findById(args.userId);\n      },\n    },\n  },\n);\n```\n\nTools defined in the worker protocol but not provided as handlers become client tools \u2014 the execution pauses and emits a `client-tool-request` event.\n\n## Error Handling\n\n### WorkerError (generate)\n\n`generate()` throws a `WorkerError` on failure. The error includes an optional `sessionId` for constructing debug URLs:\n\n```typescript\nimport { OctavusClient, WorkerError } from '@octavus/server-sdk';\n\ntry {\n  const { output } = await client.workers.generate(agentId, input);\n  console.log('Result:', output);\n} catch (error) {\n  if (error instanceof WorkerError) {\n    console.error('Worker failed:', error.message);\n    if (error.sessionId) {\n      console.error(`Debug: ${client.baseUrl}/platform/sessions/${error.sessionId}`);\n    }\n  }\n}\n```\n\n### Stream Errors (execute)\n\nWhen using `execute()`, errors appear as stream events:\n\n```typescript\nfor await (const event of client.workers.execute(agentId, input)) {\n  if (event.type === 'error') {\n    console.error(`Error: ${event.message}`);\n    console.error(`Type: ${event.errorType}`);\n    console.error(`Retryable: ${event.retryable}`);\n  }\n\n  if (event.type === 'worker-result' && event.error) {\n    console.error(`Worker failed: ${event.error}`);\n  }\n}\n```\n\n### Error Types\n\n| Type               | Description           |\n| ------------------ | --------------------- |\n| `validation_error` | Invalid input         |\n| `not_found_error`  | Worker not found      |\n| `provider_error`   | LLM provider error    |\n| `tool_error`       | Tool execution failed |\n| `execution_error`  | Worker step failed    |\n\n## Cancellation\n\nUse an abort signal to cancel execution:\n\n```typescript\nconst { output } = await client.workers.generate(agentId, input, {\n  signal: AbortSignal.timeout(30_000),\n});\n```\n\nWith `execute()` and a manual controller:\n\n```typescript\nconst controller = new AbortController();\nsetTimeout(() => controller.abort(), 30000);\n\ntry {\n  for await (const event of client.workers.execute(agentId, input, {\n    signal: controller.signal,\n  })) {\n    // Process events\n  }\n} catch (error) {\n  if (error.name === 'AbortError') {\n    console.log('Worker cancelled');\n  }\n}\n```\n\n## Streaming\n\nWhen you need real-time visibility into the worker's execution \u2014 text generation, tool calls, or progress \u2014 use `execute()` instead of `generate()`.\n\n### Basic Streaming\n\n```typescript\nconst events = client.workers.execute(agentId, {\n  TOPIC: 'AI safety',\n  DEPTH: 'detailed',\n});\n\nfor await (const event of events) {\n  if (event.type === 'worker-start') {\n    console.log(`Worker ${event.workerSlug} started`);\n  }\n  if (event.type === 'text-delta') {\n    process.stdout.write(event.delta);\n  }\n  if (event.type === 'worker-result') {\n    console.log('Output:', event.output);\n  }\n}\n```\n\n### Streaming to HTTP Response\n\nConvert worker events to an SSE stream:\n\n```typescript\nimport { toSSEStream } from '@octavus/server-sdk';\n\nexport async function POST(request: Request) {\n  const { agentId, input } = await request.json();\n\n  const events = client.workers.execute(agentId, input, {\n    tools: {\n      search: async (args) => await search(args.query),\n    },\n  });\n\n  return new Response(toSSEStream(events), {\n    headers: { 'Content-Type': 'text/event-stream' },\n  });\n}\n```\n\n### Client Tool Continuation\n\nWhen workers have tools without handlers, execution pauses:\n\n```typescript\nfor await (const event of client.workers.execute(agentId, input)) {\n  if (event.type === 'client-tool-request') {\n    const results = await executeClientTools(event.toolCalls);\n\n    for await (const ev of client.workers.continue(agentId, event.executionId, results)) {\n      // Handle remaining events\n    }\n    break;\n  }\n}\n```\n\nThe `client-tool-request` event includes:\n\n```typescript\n{\n  type: 'client-tool-request',\n  executionId: string,      // Pass to continue()\n  toolCalls: [{\n    toolCallId: string,\n    toolName: string,\n    args: Record<string, unknown>,\n  }],\n}\n```\n\n### Stream Events\n\nWorkers emit standard stream events plus worker-specific events.\n\n#### Worker Events\n\n```typescript\n// Worker started\n{\n  type: 'worker-start',\n  workerId: string,     // Unique ID (also used as session ID for debug)\n  workerSlug: string,   // The worker's slug\n  description?: string, // Display description for UI\n}\n\n// Worker completed\n{\n  type: 'worker-result',\n  workerId: string,\n  output?: unknown,  // The worker's output value\n  error?: string,    // Error message if worker failed\n}\n```\n\n#### Common Events\n\n| Event                   | Description                 |\n| ----------------------- | --------------------------- |\n| `start`                 | Execution started           |\n| `finish`                | Execution completed         |\n| `text-start`            | Text generation started     |\n| `text-delta`            | Text chunk received         |\n| `text-end`              | Text generation ended       |\n| `block-start`           | Step started                |\n| `block-end`             | Step completed              |\n| `tool-input-available`  | Tool arguments ready        |\n| `tool-output-available` | Tool result ready           |\n| `client-tool-request`   | Client tools need execution |\n| `error`                 | Error occurred              |\n\n## Full Examples\n\n### generate()\n\n```typescript\nimport { OctavusClient, WorkerError } from '@octavus/server-sdk';\n\nconst client = new OctavusClient({\n  baseUrl: 'https://octavus.ai',\n  apiKey: process.env.OCTAVUS_API_KEY!,\n});\n\ntry {\n  const { output, sessionId } = await client.workers.generate(\n    'research-assistant-id',\n    {\n      TOPIC: 'AI safety best practices',\n      DEPTH: 'detailed',\n    },\n    {\n      tools: {\n        'web-search': async ({ query }) => await performWebSearch(query),\n      },\n      signal: AbortSignal.timeout(120_000),\n    },\n  );\n\n  console.log('Result:', output);\n} catch (error) {\n  if (error instanceof WorkerError) {\n    console.error('Failed:', error.message);\n    if (error.sessionId) {\n      console.error(`Debug: ${client.baseUrl}/platform/sessions/${error.sessionId}`);\n    }\n  }\n}\n```\n\n### execute()\n\nFor full control over streaming events and progress tracking:\n\n```typescript\nimport { OctavusClient, type StreamEvent } from '@octavus/server-sdk';\n\nconst client = new OctavusClient({\n  baseUrl: 'https://octavus.ai',\n  apiKey: process.env.OCTAVUS_API_KEY!,\n});\n\nasync function runResearchWorker(topic: string) {\n  console.log(`Researching: ${topic}\\n`);\n\n  const events = client.workers.execute(\n    'research-assistant-id',\n    {\n      TOPIC: topic,\n      DEPTH: 'detailed',\n    },\n    {\n      tools: {\n        'web-search': async ({ query }) => {\n          console.log(`Searching: ${query}`);\n          return await performWebSearch(query);\n        },\n      },\n    },\n  );\n\n  let output: unknown;\n\n  for await (const event of events) {\n    switch (event.type) {\n      case 'worker-start':\n        console.log(`Started: ${event.workerSlug}`);\n        break;\n\n      case 'block-start':\n        console.log(`Step: ${event.blockName}`);\n        break;\n\n      case 'text-delta':\n        process.stdout.write(event.delta);\n        break;\n\n      case 'worker-result':\n        if (event.error) {\n          throw new Error(event.error);\n        }\n        output = event.output;\n        break;\n\n      case 'error':\n        throw new Error(event.message);\n    }\n  }\n\n  console.log('\\n\\nResearch complete!');\n  return output;\n}\n\nconst result = await runResearchWorker('AI safety best practices');\nconsole.log('Result:', result);\n```\n\n## Next Steps\n\n- [Workers Protocol](/docs/protocol/workers) \u2014 Worker protocol reference\n- [Streaming](/docs/server-sdk/streaming) \u2014 Understanding stream events\n- [Tools](/docs/server-sdk/tools) \u2014 Tool handler patterns\n",
         excerpt: "Workers API The  enables executing worker agents from your server. Workers are task-based agents that run steps sequentially and return an output value.  Basic Usage  WorkersApi Reference  generate()...",
         order: 6
       },
@@ -819,7 +819,7 @@ var sections_default = [
         section: "client-sdk",
         title: "Overview",
         description: "Introduction to the Octavus Client SDKs for building chat interfaces.",
-        content: "\n# Client SDK Overview\n\nOctavus provides two packages for frontend integration:\n\n| Package               | Purpose                  | Use When                                              |\n| --------------------- | ------------------------ | ----------------------------------------------------- |\n| `@octavus/react`      | React hooks and bindings | Building React applications                           |\n| `@octavus/client-sdk` | Framework-agnostic core  | Using Vue, Svelte, vanilla JS, or custom integrations |\n\n**Most users should install `@octavus/react`** \u2014 it includes everything from `@octavus/client-sdk` plus React-specific hooks.\n\n## Installation\n\n### React Applications\n\n```bash\nnpm install @octavus/react\n```\n\n**Current version:** `2.12.0`\n\n### Other Frameworks\n\n```bash\nnpm install @octavus/client-sdk\n```\n\n**Current version:** `2.12.0`\n\n## Transport Pattern\n\nThe Client SDK uses a **transport abstraction** to handle communication with your backend. This gives you flexibility in how events are delivered:\n\n| Transport               | Use Case                                     | Docs                                                  |\n| ----------------------- | -------------------------------------------- | ----------------------------------------------------- |\n| `createHttpTransport`   | HTTP/SSE (Next.js, Express, etc.)            | [HTTP Transport](/docs/client-sdk/http-transport)     |\n| `createSocketTransport` | WebSocket, SockJS, or other socket protocols | [Socket Transport](/docs/client-sdk/socket-transport) |\n\nWhen the transport changes (e.g., when `sessionId` changes), the `useOctavusChat` hook automatically reinitializes with the new transport.\n\n> **Recommendation**: Use HTTP transport unless you specifically need WebSocket features (custom real-time events, Meteor/Phoenix, etc.).\n\n## React Usage\n\nThe `useOctavusChat` hook provides state management and streaming for React applications:\n\n```tsx\nimport { useMemo } from 'react';\nimport { useOctavusChat, createHttpTransport, type UIMessage } from '@octavus/react';\n\nfunction Chat({ sessionId }: { sessionId: string }) {\n  // Create a stable transport instance (memoized on sessionId)\n  const transport = useMemo(\n    () =>\n      createHttpTransport({\n        request: (payload, options) =>\n          fetch('/api/trigger', {\n            method: 'POST',\n            headers: { 'Content-Type': 'application/json' },\n            body: JSON.stringify({ sessionId, ...payload }),\n            signal: options?.signal,\n          }),\n      }),\n    [sessionId],\n  );\n\n  const { messages, status, send } = useOctavusChat({ transport });\n\n  const sendMessage = async (text: string) => {\n    await send('user-message', { USER_MESSAGE: text }, { userMessage: { content: text } });\n  };\n\n  return (\n    <div>\n      {messages.map((msg) => (\n        <MessageBubble key={msg.id} message={msg} />\n      ))}\n    </div>\n  );\n}\n\nfunction MessageBubble({ message }: { message: UIMessage }) {\n  return (\n    <div>\n      {message.parts.map((part, i) => {\n        if (part.type === 'text') {\n          return <p key={i}>{part.text}</p>;\n        }\n        return null;\n      })}\n    </div>\n  );\n}\n```\n\n## Framework-Agnostic Usage\n\nThe `OctavusChat` class can be used with any framework or vanilla JavaScript:\n\n```typescript\nimport { OctavusChat, createHttpTransport } from '@octavus/client-sdk';\n\nconst transport = createHttpTransport({\n  request: (payload, options) =>\n    fetch('/api/trigger', {\n      method: 'POST',\n      headers: { 'Content-Type': 'application/json' },\n      body: JSON.stringify({ sessionId, ...payload }),\n      signal: options?.signal,\n    }),\n});\n\nconst chat = new OctavusChat({ transport });\n\n// Subscribe to state changes\nconst unsubscribe = chat.subscribe(() => {\n  console.log('Messages:', chat.messages);\n  console.log('Status:', chat.status);\n  // Update your UI here\n});\n\n// Send a message\nawait chat.send('user-message', { USER_MESSAGE: 'Hello' }, { userMessage: { content: 'Hello' } });\n\n// Cleanup when done\nunsubscribe();\n```\n\n## Key Features\n\n### Unified Send Function\n\nThe `send` function handles both user message display and agent triggering in one call:\n\n```tsx\nconst { send } = useOctavusChat({ transport });\n\n// Add user message to UI and trigger agent\nawait send('user-message', { USER_MESSAGE: text }, { userMessage: { content: text } });\n\n// Trigger without adding a user message (e.g., button click)\nawait send('request-human');\n```\n\n### Message Parts\n\nMessages contain ordered `parts` for rich content:\n\n```tsx\nconst { messages } = useOctavusChat({ transport });\n\n// Each message has typed parts\nmessage.parts.map((part) => {\n  switch (part.type) {\n    case 'text': // Text content\n    case 'reasoning': // Extended reasoning/thinking\n    case 'tool-call': // Tool execution\n    case 'operation': // Internal operations (set-resource, etc.)\n  }\n});\n```\n\n### Status Tracking\n\n```tsx\nconst { status } = useOctavusChat({ transport });\n\n// status: 'idle' | 'streaming' | 'error' | 'awaiting-input'\n// 'awaiting-input' occurs when interactive client tools need user action\n```\n\n### Stop Streaming\n\n```tsx\nconst { stop } = useOctavusChat({ transport });\n\n// Stop current stream and finalize message\nstop();\n```\n\n### Retry Last Trigger\n\nRe-execute the last trigger from the same starting point. Messages are rolled back to the state before the trigger, the user message is re-added (if any), and the agent re-executes. Already-uploaded files are reused without re-uploading.\n\n```tsx\nconst { retry, canRetry } = useOctavusChat({ transport });\n\n// Retry after an error, cancellation, or unsatisfactory result\nif (canRetry) {\n  await retry();\n}\n```\n\n`canRetry` is `true` when a trigger has been sent and the chat is not currently streaming or awaiting input.\n\n## Hook Reference (React)\n\n### useOctavusChat\n\n```typescript\nfunction useOctavusChat(options: OctavusChatOptions): UseOctavusChatReturn;\n\ninterface OctavusChatOptions {\n  // Required: Transport for streaming events\n  transport: Transport;\n\n  // Optional: Function to request upload URLs for file uploads\n  requestUploadUrls?: (\n    files: { filename: string; mediaType: string; size: number }[],\n  ) => Promise<UploadUrlsResponse>;\n\n  // Optional: Client-side tool handlers\n  // - Function: executes automatically and returns result\n  // - 'interactive': appears in pendingClientTools for user input\n  clientTools?: Record<string, ClientToolHandler>;\n\n  // Optional: Pre-populate with existing messages (session restore)\n  initialMessages?: UIMessage[];\n\n  // Optional: Callbacks\n  onError?: (error: OctavusError) => void; // Structured error with type, source, retryable\n  onFinish?: () => void;\n  onStop?: () => void; // Called when user stops generation\n  onResourceUpdate?: (name: string, value: unknown) => void;\n}\n\ninterface UseOctavusChatReturn {\n  // State\n  messages: UIMessage[];\n  status: ChatStatus; // 'idle' | 'streaming' | 'error' | 'awaiting-input'\n  error: OctavusError | null; // Structured error with type, source, retryable\n\n  // Connection (socket transport only - undefined for HTTP)\n  connectionState: ConnectionState | undefined; // 'disconnected' | 'connecting' | 'connected' | 'error'\n  connectionError: Error | undefined;\n\n  // Client tools (interactive tools awaiting user input)\n  pendingClientTools: Record<string, InteractiveTool[]>; // Keyed by tool name\n\n  // Actions\n  send: (\n    triggerName: string,\n    input?: Record<string, unknown>,\n    options?: { userMessage?: UserMessageInput },\n  ) => Promise<void>;\n  stop: () => void;\n  retry: () => Promise<void>; // Retry last trigger from same starting point\n  canRetry: boolean; // Whether retry() can be called\n\n  // Connection management (socket transport only - undefined for HTTP)\n  connect: (() => Promise<void>) | undefined;\n  disconnect: (() => void) | undefined;\n\n  // File uploads (requires requestUploadUrls)\n  uploadFiles: (\n    files: FileList | File[],\n    onProgress?: (fileIndex: number, progress: number) => void,\n  ) => Promise<FileReference[]>;\n}\n\ninterface UserMessageInput {\n  content?: string;\n  files?: FileList | File[] | FileReference[];\n}\n```\n\n## Transport Reference\n\n### createHttpTransport\n\nCreates an HTTP/SSE transport using native `fetch()`:\n\n```typescript\nimport { createHttpTransport } from '@octavus/react';\n\nconst transport = createHttpTransport({\n  request: (payload, options) =>\n    fetch('/api/trigger', {\n      method: 'POST',\n      headers: { 'Content-Type': 'application/json' },\n      body: JSON.stringify({ sessionId, ...payload }),\n      signal: options?.signal,\n    }),\n});\n```\n\n### createSocketTransport\n\nCreates a WebSocket/SockJS transport for real-time connections:\n\n```typescript\nimport { createSocketTransport } from '@octavus/react';\n\nconst transport = createSocketTransport({\n  connect: () =>\n    new Promise((resolve, reject) => {\n      const ws = new WebSocket(`wss://api.example.com/stream?sessionId=${sessionId}`);\n      ws.onopen = () => resolve(ws);\n      ws.onerror = () => reject(new Error('Connection failed'));\n    }),\n});\n```\n\nSocket transport provides additional connection management:\n\n```typescript\n// Access connection state directly\ntransport.connectionState; // 'disconnected' | 'connecting' | 'connected' | 'error'\n\n// Subscribe to state changes\ntransport.onConnectionStateChange((state, error) => {\n  /* ... */\n});\n\n// Eager connection (instead of lazy on first send)\nawait transport.connect();\n\n// Manual disconnect\ntransport.disconnect();\n```\n\nFor detailed WebSocket/SockJS usage including custom events, reconnection patterns, and server-side implementation, see [Socket Transport](/docs/client-sdk/socket-transport).\n\n## Class Reference (Framework-Agnostic)\n\n### OctavusChat\n\n```typescript\nclass OctavusChat {\n  constructor(options: OctavusChatOptions);\n\n  // State (read-only)\n  readonly messages: UIMessage[];\n  readonly status: ChatStatus; // 'idle' | 'streaming' | 'error' | 'awaiting-input'\n  readonly error: OctavusError | null; // Structured error\n  readonly pendingClientTools: Record<string, InteractiveTool[]>; // Interactive tools\n\n  // Actions\n  send(\n    triggerName: string,\n    input?: Record<string, unknown>,\n    options?: { userMessage?: UserMessageInput },\n  ): Promise<void>;\n  stop(): void;\n\n  // Subscription\n  subscribe(callback: () => void): () => void; // Returns unsubscribe function\n}\n```\n\n## Next Steps\n\n- [HTTP Transport](/docs/client-sdk/http-transport) \u2014 HTTP/SSE integration (recommended)\n- [Socket Transport](/docs/client-sdk/socket-transport) \u2014 WebSocket and SockJS integration\n- [Messages](/docs/client-sdk/messages) \u2014 Working with message state\n- [Streaming](/docs/client-sdk/streaming) \u2014 Building streaming UIs\n- [Client Tools](/docs/client-sdk/client-tools) \u2014 Interactive browser-side tool handling\n- [Operations](/docs/client-sdk/execution-blocks) \u2014 Showing agent progress\n- [Error Handling](/docs/client-sdk/error-handling) \u2014 Handling errors with type guards\n- [File Uploads](/docs/client-sdk/file-uploads) \u2014 Uploading images and documents\n- [Examples](/docs/examples/overview) \u2014 Complete working examples\n",
+        content: "\n# Client SDK Overview\n\nOctavus provides two packages for frontend integration:\n\n| Package               | Purpose                  | Use When                                              |\n| --------------------- | ------------------------ | ----------------------------------------------------- |\n| `@octavus/react`      | React hooks and bindings | Building React applications                           |\n| `@octavus/client-sdk` | Framework-agnostic core  | Using Vue, Svelte, vanilla JS, or custom integrations |\n\n**Most users should install `@octavus/react`** \u2014 it includes everything from `@octavus/client-sdk` plus React-specific hooks.\n\n## Installation\n\n### React Applications\n\n```bash\nnpm install @octavus/react\n```\n\n**Current version:** `2.15.0`\n\n### Other Frameworks\n\n```bash\nnpm install @octavus/client-sdk\n```\n\n**Current version:** `2.15.0`\n\n## Transport Pattern\n\nThe Client SDK uses a **transport abstraction** to handle communication with your backend. This gives you flexibility in how events are delivered:\n\n| Transport               | Use Case                                     | Docs                                                  |\n| ----------------------- | -------------------------------------------- | ----------------------------------------------------- |\n| `createHttpTransport`   | HTTP/SSE (Next.js, Express, etc.)            | [HTTP Transport](/docs/client-sdk/http-transport)     |\n| `createSocketTransport` | WebSocket, SockJS, or other socket protocols | [Socket Transport](/docs/client-sdk/socket-transport) |\n\nWhen the transport changes (e.g., when `sessionId` changes), the `useOctavusChat` hook automatically reinitializes with the new transport.\n\n> **Recommendation**: Use HTTP transport unless you specifically need WebSocket features (custom real-time events, Meteor/Phoenix, etc.).\n\n## React Usage\n\nThe `useOctavusChat` hook provides state management and streaming for React applications:\n\n```tsx\nimport { useMemo } from 'react';\nimport { useOctavusChat, createHttpTransport, type UIMessage } from '@octavus/react';\n\nfunction Chat({ sessionId }: { sessionId: string }) {\n  // Create a stable transport instance (memoized on sessionId)\n  const transport = useMemo(\n    () =>\n      createHttpTransport({\n        request: (payload, options) =>\n          fetch('/api/trigger', {\n            method: 'POST',\n            headers: { 'Content-Type': 'application/json' },\n            body: JSON.stringify({ sessionId, ...payload }),\n            signal: options?.signal,\n          }),\n      }),\n    [sessionId],\n  );\n\n  const { messages, status, send } = useOctavusChat({ transport });\n\n  const sendMessage = async (text: string) => {\n    await send('user-message', { USER_MESSAGE: text }, { userMessage: { content: text } });\n  };\n\n  return (\n    <div>\n      {messages.map((msg) => (\n        <MessageBubble key={msg.id} message={msg} />\n      ))}\n    </div>\n  );\n}\n\nfunction MessageBubble({ message }: { message: UIMessage }) {\n  return (\n    <div>\n      {message.parts.map((part, i) => {\n        if (part.type === 'text') {\n          return <p key={i}>{part.text}</p>;\n        }\n        return null;\n      })}\n    </div>\n  );\n}\n```\n\n## Framework-Agnostic Usage\n\nThe `OctavusChat` class can be used with any framework or vanilla JavaScript:\n\n```typescript\nimport { OctavusChat, createHttpTransport } from '@octavus/client-sdk';\n\nconst transport = createHttpTransport({\n  request: (payload, options) =>\n    fetch('/api/trigger', {\n      method: 'POST',\n      headers: { 'Content-Type': 'application/json' },\n      body: JSON.stringify({ sessionId, ...payload }),\n      signal: options?.signal,\n    }),\n});\n\nconst chat = new OctavusChat({ transport });\n\n// Subscribe to state changes\nconst unsubscribe = chat.subscribe(() => {\n  console.log('Messages:', chat.messages);\n  console.log('Status:', chat.status);\n  // Update your UI here\n});\n\n// Send a message\nawait chat.send('user-message', { USER_MESSAGE: 'Hello' }, { userMessage: { content: 'Hello' } });\n\n// Cleanup when done\nunsubscribe();\n```\n\n## Key Features\n\n### Unified Send Function\n\nThe `send` function handles both user message display and agent triggering in one call:\n\n```tsx\nconst { send } = useOctavusChat({ transport });\n\n// Add user message to UI and trigger agent\nawait send('user-message', { USER_MESSAGE: text }, { userMessage: { content: text } });\n\n// Trigger without adding a user message (e.g., button click)\nawait send('request-human');\n```\n\n### Message Parts\n\nMessages contain ordered `parts` for rich content:\n\n```tsx\nconst { messages } = useOctavusChat({ transport });\n\n// Each message has typed parts\nmessage.parts.map((part) => {\n  switch (part.type) {\n    case 'text': // Text content\n    case 'reasoning': // Extended reasoning/thinking\n    case 'tool-call': // Tool execution\n    case 'operation': // Internal operations (set-resource, etc.)\n  }\n});\n```\n\n### Status Tracking\n\n```tsx\nconst { status } = useOctavusChat({ transport });\n\n// status: 'idle' | 'streaming' | 'error' | 'awaiting-input'\n// 'awaiting-input' occurs when interactive client tools need user action\n```\n\n### Stop Streaming\n\n```tsx\nconst { stop } = useOctavusChat({ transport });\n\n// Stop current stream and finalize message\nstop();\n```\n\n### Retry Last Trigger\n\nRe-execute the last trigger from the same starting point. Messages are rolled back to the state before the trigger, the user message is re-added (if any), and the agent re-executes. Already-uploaded files are reused without re-uploading.\n\n```tsx\nconst { retry, canRetry } = useOctavusChat({ transport });\n\n// Retry after an error, cancellation, or unsatisfactory result\nif (canRetry) {\n  await retry();\n}\n```\n\n`canRetry` is `true` when a trigger has been sent and the chat is not currently streaming or awaiting input.\n\n## Hook Reference (React)\n\n### useOctavusChat\n\n```typescript\nfunction useOctavusChat(options: OctavusChatOptions): UseOctavusChatReturn;\n\ninterface OctavusChatOptions {\n  // Required: Transport for streaming events\n  transport: Transport;\n\n  // Optional: Function to request upload URLs for file uploads\n  requestUploadUrls?: (\n    files: { filename: string; mediaType: string; size: number }[],\n  ) => Promise<UploadUrlsResponse>;\n\n  // Optional: Client-side tool handlers\n  // - Function: executes automatically and returns result\n  // - 'interactive': appears in pendingClientTools for user input\n  clientTools?: Record<string, ClientToolHandler>;\n\n  // Optional: Pre-populate with existing messages (session restore)\n  initialMessages?: UIMessage[];\n\n  // Optional: Callbacks\n  onError?: (error: OctavusError) => void; // Structured error with type, source, retryable\n  onFinish?: () => void;\n  onStop?: () => void; // Called when user stops generation\n  onResourceUpdate?: (name: string, value: unknown) => void;\n}\n\ninterface UseOctavusChatReturn {\n  // State\n  messages: UIMessage[];\n  status: ChatStatus; // 'idle' | 'streaming' | 'error' | 'awaiting-input'\n  error: OctavusError | null; // Structured error with type, source, retryable\n\n  // Connection (socket transport only - undefined for HTTP)\n  connectionState: ConnectionState | undefined; // 'disconnected' | 'connecting' | 'connected' | 'error'\n  connectionError: Error | undefined;\n\n  // Client tools (interactive tools awaiting user input)\n  pendingClientTools: Record<string, InteractiveTool[]>; // Keyed by tool name\n\n  // Actions\n  send: (\n    triggerName: string,\n    input?: Record<string, unknown>,\n    options?: { userMessage?: UserMessageInput },\n  ) => Promise<void>;\n  stop: () => void;\n  retry: () => Promise<void>; // Retry last trigger from same starting point\n  canRetry: boolean; // Whether retry() can be called\n\n  // Connection management (socket transport only - undefined for HTTP)\n  connect: (() => Promise<void>) | undefined;\n  disconnect: (() => void) | undefined;\n\n  // File uploads (requires requestUploadUrls)\n  uploadFiles: (\n    files: FileList | File[],\n    onProgress?: (fileIndex: number, progress: number) => void,\n  ) => Promise<FileReference[]>;\n}\n\ninterface UserMessageInput {\n  content?: string;\n  files?: FileList | File[] | FileReference[];\n}\n```\n\n## Transport Reference\n\n### createHttpTransport\n\nCreates an HTTP/SSE transport using native `fetch()`:\n\n```typescript\nimport { createHttpTransport } from '@octavus/react';\n\nconst transport = createHttpTransport({\n  request: (payload, options) =>\n    fetch('/api/trigger', {\n      method: 'POST',\n      headers: { 'Content-Type': 'application/json' },\n      body: JSON.stringify({ sessionId, ...payload }),\n      signal: options?.signal,\n    }),\n});\n```\n\n### createSocketTransport\n\nCreates a WebSocket/SockJS transport for real-time connections:\n\n```typescript\nimport { createSocketTransport } from '@octavus/react';\n\nconst transport = createSocketTransport({\n  connect: () =>\n    new Promise((resolve, reject) => {\n      const ws = new WebSocket(`wss://api.example.com/stream?sessionId=${sessionId}`);\n      ws.onopen = () => resolve(ws);\n      ws.onerror = () => reject(new Error('Connection failed'));\n    }),\n});\n```\n\nSocket transport provides additional connection management:\n\n```typescript\n// Access connection state directly\ntransport.connectionState; // 'disconnected' | 'connecting' | 'connected' | 'error'\n\n// Subscribe to state changes\ntransport.onConnectionStateChange((state, error) => {\n  /* ... */\n});\n\n// Eager connection (instead of lazy on first send)\nawait transport.connect();\n\n// Manual disconnect\ntransport.disconnect();\n```\n\nFor detailed WebSocket/SockJS usage including custom events, reconnection patterns, and server-side implementation, see [Socket Transport](/docs/client-sdk/socket-transport).\n\n## Class Reference (Framework-Agnostic)\n\n### OctavusChat\n\n```typescript\nclass OctavusChat {\n  constructor(options: OctavusChatOptions);\n\n  // State (read-only)\n  readonly messages: UIMessage[];\n  readonly status: ChatStatus; // 'idle' | 'streaming' | 'error' | 'awaiting-input'\n  readonly error: OctavusError | null; // Structured error\n  readonly pendingClientTools: Record<string, InteractiveTool[]>; // Interactive tools\n\n  // Actions\n  send(\n    triggerName: string,\n    input?: Record<string, unknown>,\n    options?: { userMessage?: UserMessageInput },\n  ): Promise<void>;\n  stop(): void;\n\n  // Subscription\n  subscribe(callback: () => void): () => void; // Returns unsubscribe function\n}\n```\n\n## Next Steps\n\n- [HTTP Transport](/docs/client-sdk/http-transport) \u2014 HTTP/SSE integration (recommended)\n- [Socket Transport](/docs/client-sdk/socket-transport) \u2014 WebSocket and SockJS integration\n- [Messages](/docs/client-sdk/messages) \u2014 Working with message state\n- [Streaming](/docs/client-sdk/streaming) \u2014 Building streaming UIs\n- [Client Tools](/docs/client-sdk/client-tools) \u2014 Interactive browser-side tool handling\n- [Operations](/docs/client-sdk/execution-blocks) \u2014 Showing agent progress\n- [Error Handling](/docs/client-sdk/error-handling) \u2014 Handling errors with type guards\n- [File Uploads](/docs/client-sdk/file-uploads) \u2014 Uploading images and documents\n- [Examples](/docs/examples/overview) \u2014 Complete working examples\n",
         excerpt: "Client SDK Overview Octavus provides two packages for frontend integration: | Package               | Purpose                  | Use When                                              | |...",
         order: 1
       },
@@ -1407,7 +1407,7 @@ See [Streaming Events](/docs/server-sdk/streaming#event-types) for the full list
         section: "api-reference",
         title: "Sessions",
         description: "Session management API endpoints.",
-        content: '\n# Sessions API\n\nSessions represent conversations with agents. They store conversation history, resources, and variables.\n\nAll session endpoints require an API key with the **Sessions** permission.\n\n## Create Session\n\nCreate a new agent session.\n\n```\nPOST /api/agent-sessions\n```\n\n### Request Body\n\n```json\n{\n  "agentId": "cm5xvz7k80001abcd",\n  "input": {\n    "COMPANY_NAME": "Acme Corp",\n    "PRODUCT_NAME": "Widget Pro",\n    "USER_ID": "user-123"\n  }\n}\n```\n\n| Field     | Type   | Required | Description                           |\n| --------- | ------ | -------- | ------------------------------------- |\n| `agentId` | string | Yes      | Agent ID (the `id` field, not `slug`) |\n| `input`   | object | No       | Input variables for the agent         |\n\n> **Getting the agent ID:** Copy the ID from the agent URL in the [platform](https://octavus.ai) (e.g., `octavus.ai/agents/clxyz123`), or use the [CLI](/docs/server-sdk/cli) (`octavus sync ./agents/my-agent`) for local development workflows.\n\n### Response\n\n```json\n{\n  "sessionId": "cm5xyz123abc456def"\n}\n```\n\n### Example\n\n```bash\ncurl -X POST https://octavus.ai/api/agent-sessions \\\n  -H "Authorization: Bearer YOUR_API_KEY" \\\n  -H "Content-Type: application/json" \\\n  -d \'{\n    "agentId": "cm5xvz7k80001abcd",\n    "input": {\n      "COMPANY_NAME": "Acme Corp",\n      "PRODUCT_NAME": "Widget Pro"\n    }\n  }\'\n```\n\n## Get Session\n\nRetrieve session state. Returns UI-ready messages for active sessions, or expiration info for expired sessions.\n\n```\nGET /api/agent-sessions/:sessionId\n```\n\n### Query Parameters\n\n| Parameter | Type   | Description                                          |\n| --------- | ------ | ---------------------------------------------------- |\n| `format`  | string | Optional. Use `format=ui` for UI-ready messages only |\n\n### Response (Active Session)\n\nWhen the session is active, the response includes `UIMessage` objects:\n\n```json\n{\n  "id": "cm5xyz123abc456def",\n  "agentId": "cm5xvz7k80001abcd",\n  "status": "active",\n  "input": {\n    "COMPANY_NAME": "Acme Corp",\n    "PRODUCT_NAME": "Widget Pro"\n  },\n  "variables": {},\n  "resources": {\n    "CONVERSATION_SUMMARY": ""\n  },\n  "messages": [\n    {\n      "id": "1702345800000-xyz789a",\n      "role": "user",\n      "parts": [{ "type": "text", "text": "How do I reset my password?", "status": "done" }],\n      "status": "done",\n      "createdAt": "2024-01-15T10:30:00.000Z"\n    },\n    {\n      "id": "1702345805000-def456b",\n      "role": "assistant",\n      "parts": [\n        { "type": "text", "text": "I can help you reset your password...", "status": "done" }\n      ],\n      "status": "done",\n      "createdAt": "2024-01-15T10:30:05.000Z"\n    }\n  ],\n  "createdAt": "2024-01-15T10:30:00Z",\n  "updatedAt": "2024-01-15T10:30:05Z"\n}\n```\n\n### Response (Expired Session)\n\nWhen the session has expired, the response indicates the expiration status:\n\n```json\n{\n  "status": "expired",\n  "sessionId": "cm5xyz123abc456def",\n  "agentId": "cm5xvz7k80001abcd",\n  "createdAt": "2024-01-15T10:30:00Z"\n}\n```\n\nUse the [Restore Session](#restore-session) endpoint to restore an expired session from stored messages.\n\n````\n\n### UIMessage Parts\n\nMessages contain typed `parts` that preserve content ordering:\n\n| Part Type | Description |\n|-----------|-------------|\n| `text` | Text content with `text` and `status` fields |\n| `reasoning` | Extended reasoning with `text` and `status` fields |\n| `tool-call` | Tool execution with `toolCallId`, `toolName`, `displayName`, `args`, `result`, `status` |\n| `operation` | Internal operations with `operationId`, `name`, `operationType`, `status` |\n| `file` | File attachment with `id`, `mediaType`, `url`, `filename`, `size` |\n| `source` | Source reference with `sourceType`, `id`, `url`, `title` |\n| `object` | Structured output with `id`, `typeName`, `object`, `status` |\n\n### Example\n\n```bash\ncurl https://octavus.ai/api/agent-sessions/:sessionId \\\n  -H "Authorization: Bearer YOUR_API_KEY"\n````\n\n## Restore Session\n\nRestore an expired session from stored messages. This allows you to continue a conversation after the server-side state has expired.\n\n```\nPOST /api/agent-sessions/:sessionId/restore\n```\n\n### Request Body\n\n```json\n{\n  "messages": [\n    {\n      "id": "1702345800000-xyz789a",\n      "role": "user",\n      "parts": [{ "type": "text", "text": "How do I reset my password?", "status": "done" }],\n      "status": "done",\n      "createdAt": "2024-01-15T10:30:00.000Z"\n    }\n  ],\n  "input": {\n    "COMPANY_NAME": "Acme Corp"\n  }\n}\n```\n\n| Field      | Type        | Required | Description                                                    |\n| ---------- | ----------- | -------- | -------------------------------------------------------------- |\n| `messages` | UIMessage[] | Yes      | Previously stored chat history                                 |\n| `input`    | object      | No       | Session input for system prompt interpolation (same as create) |\n\n### Response\n\n```json\n{\n  "sessionId": "cm5xyz123abc456def",\n  "restored": true\n}\n```\n\n| Field       | Type    | Description                                                             |\n| ----------- | ------- | ----------------------------------------------------------------------- |\n| `sessionId` | string  | The session ID                                                          |\n| `restored`  | boolean | `true` if restored from messages, `false` if session was already active |\n\n### Example\n\n```bash\ncurl -X POST https://octavus.ai/api/agent-sessions/:sessionId/restore \\\n  -H "Authorization: Bearer YOUR_API_KEY" \\\n  -H "Content-Type: application/json" \\\n  -d \'{\n    "messages": [...],\n    "input": { "COMPANY_NAME": "Acme Corp" }\n  }\'\n```\n\n> **Note**: Store the `UIMessage[]` array after each interaction to enable restoration. The restore endpoint reconstructs the conversation state from these messages.\n\n## Clear Session\n\nClear session state, transitioning it to `expired` status. The session can be restored afterwards with the [Restore Session](#restore-session) endpoint.\n\nThis is idempotent \u2014 clearing an already expired session succeeds without error.\n\n```\nDELETE /api/agent-sessions/:sessionId\n```\n\n### Response\n\n```json\n{\n  "sessionId": "cm5xyz123abc456def",\n  "cleared": true\n}\n```\n\n### Example\n\n```bash\ncurl -X DELETE https://octavus.ai/api/agent-sessions/:sessionId \\\n  -H "Authorization: Bearer YOUR_API_KEY"\n```\n\n## Trigger Session\n\nExecute a trigger on a session. Returns a Server-Sent Events stream.\n\n```\nPOST /api/agent-sessions/:sessionId/trigger\n```\n\n### Request Body\n\n```json\n{\n  "triggerName": "user-message",\n  "input": {\n    "USER_MESSAGE": "How do I reset my password?"\n  },\n  "toolResults": []\n}\n```\n\n| Field                     | Type           | Required | Description                                                                                           |\n| ------------------------- | -------------- | -------- | ----------------------------------------------------------------------------------------------------- |\n| `triggerName`             | string         | Yes      | Name of the trigger to execute                                                                        |\n| `input`                   | object         | No       | Input variables for the trigger                                                                       |\n| `toolResults`             | array          | No       | Tool results for continuation (handled by SDK)                                                        |\n| `rollbackAfterMessageId`  | string \\| null | No       | For retry: ID of the last message to keep. Messages after this are removed. `null` = truncate all.    |\n\n### Response\n\nReturns `text/event-stream` with SSE events:\n\n```\ndata: {"type":"start","messageId":"msg-123"}\n\ndata: {"type":"block-start","blockId":"b1","blockName":"Add user message","blockType":"add-message","display":"hidden"}\n\ndata: {"type":"block-end","blockId":"b1"}\n\ndata: {"type":"block-start","blockId":"b2","blockName":"Respond to user","blockType":"next-message","display":"stream","outputToChat":true}\n\ndata: {"type":"text-start","id":"t1"}\n\ndata: {"type":"text-delta","id":"t1","delta":"I"}\n\ndata: {"type":"text-delta","id":"t1","delta":" can"}\n\ndata: {"type":"text-delta","id":"t1","delta":" help"}\n\ndata: {"type":"text-delta","id":"t1","delta":" you"}\n\ndata: {"type":"text-delta","id":"t1","delta":" reset"}\n\ndata: {"type":"text-delta","id":"t1","delta":" your"}\n\ndata: {"type":"text-delta","id":"t1","delta":" password"}\n\ndata: {"type":"text-delta","id":"t1","delta":"!"}\n\ndata: {"type":"text-end","id":"t1"}\n\ndata: {"type":"block-end","blockId":"b2"}\n\ndata: {"type":"finish","finishReason":"stop"}\n\ndata: [DONE]\n```\n\n### Event Types\n\n| Event                   | Description                        |\n| ----------------------- | ---------------------------------- |\n| `start`                 | Stream started                     |\n| `finish`                | Execution complete                 |\n| `error`                 | Error occurred                     |\n| `block-start`           | Execution block started            |\n| `block-end`             | Execution block completed          |\n| `text-start`            | Text generation started            |\n| `text-delta`            | Incremental text content           |\n| `text-end`              | Text generation ended              |\n| `reasoning-start`       | Extended reasoning started         |\n| `reasoning-delta`       | Reasoning content                  |\n| `reasoning-end`         | Extended reasoning ended           |\n| `tool-input-start`      | Tool call initiated                |\n| `tool-input-delta`      | Tool arguments streaming           |\n| `tool-input-end`        | Tool arguments streaming ended     |\n| `tool-input-available`  | Tool input complete                |\n| `tool-output-available` | Tool completed with result         |\n| `tool-output-error`     | Tool failed                        |\n| `tool-request`          | Platform requesting tool execution |\n| `file-available`        | File ready for display/download    |\n| `resource-update`       | Resource value changed             |\n\n### Example\n\n```bash\ncurl -N -X POST https://octavus.ai/api/agent-sessions/:sessionId/trigger \\\n  -H "Authorization: Bearer YOUR_API_KEY" \\\n  -H "Content-Type: application/json" \\\n  -d \'{\n    "triggerName": "user-message",\n    "input": { "USER_MESSAGE": "How do I reset my password?" }\n  }\'\n```\n\n## Tool Continuation\n\nWhen the agent calls external tools, you\'ll receive a `tool-request` event. Execute the tools and send results back:\n\n```json\n{\n  "triggerName": "user-message",\n  "input": { "USER_MESSAGE": "..." },\n  "toolResults": [\n    {\n      "toolCallId": "tc_123",\n      "toolName": "get-user-account",\n      "result": {\n        "name": "Demo User",\n        "email": "demo@example.com"\n      }\n    }\n  ]\n}\n```\n\nThe Server SDK handles this continuation pattern automatically.\n\n## Upload URLs\n\nGet presigned URLs for file uploads. Files are uploaded directly to S3.\n\n```\nPOST /api/files/upload-urls\n```\n\n### Request Body\n\n```json\n{\n  "sessionId": "cm5xyz123abc456def",\n  "files": [\n    {\n      "filename": "photo.jpg",\n      "mediaType": "image/jpeg",\n      "size": 102400\n    }\n  ]\n}\n```\n\n| Field               | Type   | Required | Description                         |\n| ------------------- | ------ | -------- | ----------------------------------- |\n| `sessionId`         | string | Yes      | Session ID to associate files with  |\n| `files`             | array  | Yes      | Array of file metadata (1-20 files) |\n| `files[].filename`  | string | Yes      | Original filename                   |\n| `files[].mediaType` | string | Yes      | MIME type (e.g., `image/png`)       |\n| `files[].size`      | number | Yes      | File size in bytes                  |\n\n### Response\n\n```json\n{\n  "files": [\n    {\n      "id": "file-abc123",\n      "uploadUrl": "https://s3.amazonaws.com/bucket/key?...",\n      "downloadUrl": "https://s3.amazonaws.com/bucket/key?..."\n    }\n  ]\n}\n```\n\n### Upload Flow\n\n1. Request upload URLs from the platform\n2. PUT file content to `uploadUrl` with `Content-Type` header\n3. Use `downloadUrl` as the `url` in `FileReference`\n4. Include `FileReference` in trigger input\n\n### Supported Types\n\n| Category  | Media Types                                                          |\n| --------- | -------------------------------------------------------------------- |\n| Images    | `image/jpeg`, `image/png`, `image/gif`, `image/webp`                 |\n| Documents | `application/pdf`, `text/plain`, `text/markdown`, `application/json` |\n\n### Limits\n\n| Limit                 | Value      |\n| --------------------- | ---------- |\n| Max file size         | 10 MB      |\n| Max total per request | 50 MB      |\n| Max files per request | 20         |\n| Upload URL expiry     | 15 minutes |\n| Download URL expiry   | 24 hours   |\n',
+        content: '\n# Sessions API\n\nSessions represent conversations with agents. They store conversation history, resources, and variables.\n\nAll session endpoints require an API key with the **Sessions** permission.\n\n## Create Session\n\nCreate a new agent session.\n\n```\nPOST /api/agent-sessions\n```\n\n### Request Body\n\n```json\n{\n  "agentId": "cm5xvz7k80001abcd",\n  "input": {\n    "COMPANY_NAME": "Acme Corp",\n    "PRODUCT_NAME": "Widget Pro",\n    "USER_ID": "user-123"\n  }\n}\n```\n\n| Field     | Type   | Required | Description                           |\n| --------- | ------ | -------- | ------------------------------------- |\n| `agentId` | string | Yes      | Agent ID (the `id` field, not `slug`) |\n| `input`   | object | No       | Input variables for the agent         |\n\n> **Getting the agent ID:** Copy the ID from the agent URL in the [platform](https://octavus.ai) (e.g., `octavus.ai/platform/agents/clxyz123`), or use the [CLI](/docs/server-sdk/cli) (`octavus sync ./agents/my-agent`) for local development workflows.\n\n### Response\n\n```json\n{\n  "sessionId": "cm5xyz123abc456def"\n}\n```\n\n### Example\n\n```bash\ncurl -X POST https://octavus.ai/api/agent-sessions \\\n  -H "Authorization: Bearer YOUR_API_KEY" \\\n  -H "Content-Type: application/json" \\\n  -d \'{\n    "agentId": "cm5xvz7k80001abcd",\n    "input": {\n      "COMPANY_NAME": "Acme Corp",\n      "PRODUCT_NAME": "Widget Pro"\n    }\n  }\'\n```\n\n## Get Session\n\nRetrieve session state. Returns UI-ready messages for active sessions, or expiration info for expired sessions.\n\n```\nGET /api/agent-sessions/:sessionId\n```\n\n### Query Parameters\n\n| Parameter | Type   | Description                                          |\n| --------- | ------ | ---------------------------------------------------- |\n| `format`  | string | Optional. Use `format=ui` for UI-ready messages only |\n\n### Response (Active Session)\n\nWhen the session is active, the response includes `UIMessage` objects:\n\n```json\n{\n  "id": "cm5xyz123abc456def",\n  "agentId": "cm5xvz7k80001abcd",\n  "status": "active",\n  "input": {\n    "COMPANY_NAME": "Acme Corp",\n    "PRODUCT_NAME": "Widget Pro"\n  },\n  "variables": {},\n  "resources": {\n    "CONVERSATION_SUMMARY": ""\n  },\n  "messages": [\n    {\n      "id": "1702345800000-xyz789a",\n      "role": "user",\n      "parts": [{ "type": "text", "text": "How do I reset my password?", "status": "done" }],\n      "status": "done",\n      "createdAt": "2024-01-15T10:30:00.000Z"\n    },\n    {\n      "id": "1702345805000-def456b",\n      "role": "assistant",\n      "parts": [\n        { "type": "text", "text": "I can help you reset your password...", "status": "done" }\n      ],\n      "status": "done",\n      "createdAt": "2024-01-15T10:30:05.000Z"\n    }\n  ],\n  "createdAt": "2024-01-15T10:30:00Z",\n  "updatedAt": "2024-01-15T10:30:05Z"\n}\n```\n\n### Response (Expired Session)\n\nWhen the session has expired, the response indicates the expiration status:\n\n```json\n{\n  "status": "expired",\n  "sessionId": "cm5xyz123abc456def",\n  "agentId": "cm5xvz7k80001abcd",\n  "createdAt": "2024-01-15T10:30:00Z"\n}\n```\n\nUse the [Restore Session](#restore-session) endpoint to restore an expired session from stored messages.\n\n````\n\n### UIMessage Parts\n\nMessages contain typed `parts` that preserve content ordering:\n\n| Part Type | Description |\n|-----------|-------------|\n| `text` | Text content with `text` and `status` fields |\n| `reasoning` | Extended reasoning with `text` and `status` fields |\n| `tool-call` | Tool execution with `toolCallId`, `toolName`, `displayName`, `args`, `result`, `status` |\n| `operation` | Internal operations with `operationId`, `name`, `operationType`, `status` |\n| `file` | File attachment with `id`, `mediaType`, `url`, `filename`, `size` |\n| `source` | Source reference with `sourceType`, `id`, `url`, `title` |\n| `object` | Structured output with `id`, `typeName`, `object`, `status` |\n\n### Example\n\n```bash\ncurl https://octavus.ai/api/agent-sessions/:sessionId \\\n  -H "Authorization: Bearer YOUR_API_KEY"\n````\n\n## Restore Session\n\nRestore an expired session from stored messages. This allows you to continue a conversation after the server-side state has expired.\n\n```\nPOST /api/agent-sessions/:sessionId/restore\n```\n\n### Request Body\n\n```json\n{\n  "messages": [\n    {\n      "id": "1702345800000-xyz789a",\n      "role": "user",\n      "parts": [{ "type": "text", "text": "How do I reset my password?", "status": "done" }],\n      "status": "done",\n      "createdAt": "2024-01-15T10:30:00.000Z"\n    }\n  ],\n  "input": {\n    "COMPANY_NAME": "Acme Corp"\n  }\n}\n```\n\n| Field      | Type        | Required | Description                                                    |\n| ---------- | ----------- | -------- | -------------------------------------------------------------- |\n| `messages` | UIMessage[] | Yes      | Previously stored chat history                                 |\n| `input`    | object      | No       | Session input for system prompt interpolation (same as create) |\n\n### Response\n\n```json\n{\n  "sessionId": "cm5xyz123abc456def",\n  "restored": true\n}\n```\n\n| Field       | Type    | Description                                                             |\n| ----------- | ------- | ----------------------------------------------------------------------- |\n| `sessionId` | string  | The session ID                                                          |\n| `restored`  | boolean | `true` if restored from messages, `false` if session was already active |\n\n### Example\n\n```bash\ncurl -X POST https://octavus.ai/api/agent-sessions/:sessionId/restore \\\n  -H "Authorization: Bearer YOUR_API_KEY" \\\n  -H "Content-Type: application/json" \\\n  -d \'{\n    "messages": [...],\n    "input": { "COMPANY_NAME": "Acme Corp" }\n  }\'\n```\n\n> **Note**: Store the `UIMessage[]` array after each interaction to enable restoration. The restore endpoint reconstructs the conversation state from these messages.\n\n## Clear Session\n\nClear session state, transitioning it to `expired` status. The session can be restored afterwards with the [Restore Session](#restore-session) endpoint.\n\nThis is idempotent \u2014 clearing an already expired session succeeds without error.\n\n```\nDELETE /api/agent-sessions/:sessionId\n```\n\n### Response\n\n```json\n{\n  "sessionId": "cm5xyz123abc456def",\n  "cleared": true\n}\n```\n\n### Example\n\n```bash\ncurl -X DELETE https://octavus.ai/api/agent-sessions/:sessionId \\\n  -H "Authorization: Bearer YOUR_API_KEY"\n```\n\n## Trigger Session\n\nExecute a trigger on a session. Returns a Server-Sent Events stream.\n\n```\nPOST /api/agent-sessions/:sessionId/trigger\n```\n\n### Request Body\n\n```json\n{\n  "triggerName": "user-message",\n  "input": {\n    "USER_MESSAGE": "How do I reset my password?"\n  },\n  "toolResults": []\n}\n```\n\n| Field                    | Type           | Required | Description                                                                                        |\n| ------------------------ | -------------- | -------- | -------------------------------------------------------------------------------------------------- |\n| `triggerName`            | string         | Yes      | Name of the trigger to execute                                                                     |\n| `input`                  | object         | No       | Input variables for the trigger                                                                    |\n| `toolResults`            | array          | No       | Tool results for continuation (handled by SDK)                                                     |\n| `rollbackAfterMessageId` | string \\| null | No       | For retry: ID of the last message to keep. Messages after this are removed. `null` = truncate all. |\n\n### Response\n\nReturns `text/event-stream` with SSE events:\n\n```\ndata: {"type":"start","messageId":"msg-123"}\n\ndata: {"type":"block-start","blockId":"b1","blockName":"Add user message","blockType":"add-message","display":"hidden"}\n\ndata: {"type":"block-end","blockId":"b1"}\n\ndata: {"type":"block-start","blockId":"b2","blockName":"Respond to user","blockType":"next-message","display":"stream","outputToChat":true}\n\ndata: {"type":"text-start","id":"t1"}\n\ndata: {"type":"text-delta","id":"t1","delta":"I"}\n\ndata: {"type":"text-delta","id":"t1","delta":" can"}\n\ndata: {"type":"text-delta","id":"t1","delta":" help"}\n\ndata: {"type":"text-delta","id":"t1","delta":" you"}\n\ndata: {"type":"text-delta","id":"t1","delta":" reset"}\n\ndata: {"type":"text-delta","id":"t1","delta":" your"}\n\ndata: {"type":"text-delta","id":"t1","delta":" password"}\n\ndata: {"type":"text-delta","id":"t1","delta":"!"}\n\ndata: {"type":"text-end","id":"t1"}\n\ndata: {"type":"block-end","blockId":"b2"}\n\ndata: {"type":"finish","finishReason":"stop"}\n\ndata: [DONE]\n```\n\n### Event Types\n\n| Event                   | Description                        |\n| ----------------------- | ---------------------------------- |\n| `start`                 | Stream started                     |\n| `finish`                | Execution complete                 |\n| `error`                 | Error occurred                     |\n| `block-start`           | Execution block started            |\n| `block-end`             | Execution block completed          |\n| `text-start`            | Text generation started            |\n| `text-delta`            | Incremental text content           |\n| `text-end`              | Text generation ended              |\n| `reasoning-start`       | Extended reasoning started         |\n| `reasoning-delta`       | Reasoning content                  |\n| `reasoning-end`         | Extended reasoning ended           |\n| `tool-input-start`      | Tool call initiated                |\n| `tool-input-delta`      | Tool arguments streaming           |\n| `tool-input-end`        | Tool arguments streaming ended     |\n| `tool-input-available`  | Tool input complete                |\n| `tool-output-available` | Tool completed with result         |\n| `tool-output-error`     | Tool failed                        |\n| `tool-request`          | Platform requesting tool execution |\n| `file-available`        | File ready for display/download    |\n| `resource-update`       | Resource value changed             |\n\n### Example\n\n```bash\ncurl -N -X POST https://octavus.ai/api/agent-sessions/:sessionId/trigger \\\n  -H "Authorization: Bearer YOUR_API_KEY" \\\n  -H "Content-Type: application/json" \\\n  -d \'{\n    "triggerName": "user-message",\n    "input": { "USER_MESSAGE": "How do I reset my password?" }\n  }\'\n```\n\n## Tool Continuation\n\nWhen the agent calls external tools, you\'ll receive a `tool-request` event. Execute the tools and send results back:\n\n```json\n{\n  "triggerName": "user-message",\n  "input": { "USER_MESSAGE": "..." },\n  "toolResults": [\n    {\n      "toolCallId": "tc_123",\n      "toolName": "get-user-account",\n      "result": {\n        "name": "Demo User",\n        "email": "demo@example.com"\n      }\n    }\n  ]\n}\n```\n\nThe Server SDK handles this continuation pattern automatically.\n\n## Upload URLs\n\nGet presigned URLs for file uploads. Files are uploaded directly to S3.\n\n```\nPOST /api/files/upload-urls\n```\n\n### Request Body\n\n```json\n{\n  "sessionId": "cm5xyz123abc456def",\n  "files": [\n    {\n      "filename": "photo.jpg",\n      "mediaType": "image/jpeg",\n      "size": 102400\n    }\n  ]\n}\n```\n\n| Field               | Type   | Required | Description                         |\n| ------------------- | ------ | -------- | ----------------------------------- |\n| `sessionId`         | string | Yes      | Session ID to associate files with  |\n| `files`             | array  | Yes      | Array of file metadata (1-20 files) |\n| `files[].filename`  | string | Yes      | Original filename                   |\n| `files[].mediaType` | string | Yes      | MIME type (e.g., `image/png`)       |\n| `files[].size`      | number | Yes      | File size in bytes                  |\n\n### Response\n\n```json\n{\n  "files": [\n    {\n      "id": "file-abc123",\n      "uploadUrl": "https://s3.amazonaws.com/bucket/key?...",\n      "downloadUrl": "https://s3.amazonaws.com/bucket/key?..."\n    }\n  ]\n}\n```\n\n### Upload Flow\n\n1. Request upload URLs from the platform\n2. PUT file content to `uploadUrl` with `Content-Type` header\n3. Use `downloadUrl` as the `url` in `FileReference`\n4. Include `FileReference` in trigger input\n\n### Supported Types\n\n| Category  | Media Types                                                          |\n| --------- | -------------------------------------------------------------------- |\n| Images    | `image/jpeg`, `image/png`, `image/gif`, `image/webp`                 |\n| Documents | `application/pdf`, `text/plain`, `text/markdown`, `application/json` |\n\n### Limits\n\n| Limit                 | Value      |\n| --------------------- | ---------- |\n| Max file size         | 10 MB      |\n| Max total per request | 50 MB      |\n| Max files per request | 20         |\n| Upload URL expiry     | 15 minutes |\n| Download URL expiry   | 24 hours   |\n',
         excerpt: "Sessions API Sessions represent conversations with agents. They store conversation history, resources, and variables. All session endpoints require an API key with the Sessions permission.  Create...",
         order: 2
       },
@@ -1506,4 +1506,4 @@ export {
   getDocSlugs,
   getSectionBySlug
 };
-//# sourceMappingURL=chunk-Z5E72EIS.js.map
+//# sourceMappingURL=chunk-2UFDUNPK.js.map