@octavus/docs 2.16.0 → 2.17.0

package/dist/{chunk-4WYG2JYA.js → chunk-UZWGRPRR.js}

@@ -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:** `2.15.0`\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",
+    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:** `2.16.0`\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:** `2.15.0`\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',
+    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:** `2.16.0`\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
   },
@@ -81,12 +81,21 @@ var docs_default = [
     excerpt: "Debugging  Model Request Tracing Model request tracing captures the full payload sent to model providers (LLM and image) during agent execution. This helps you understand exactly what was sent \u2014...",
     order: 7
   },
+  {
+    slug: "server-sdk/computer",
+    section: "server-sdk",
+    title: "Computer",
+    description: "Adding browser, filesystem, and shell capabilities to agents with @octavus/computer.",
+    content: "\n# Computer\n\nThe `@octavus/computer` package gives agents access to a physical or virtual machine's browser, filesystem, and shell. It connects to [MCP](https://modelcontextprotocol.io) servers, discovers their tools, and provides them to the server-sdk.\n\n**Current version:** `2.16.0`\n\n## Installation\n\n```bash\nnpm install @octavus/computer\n```\n\n## Quick Start\n\n```typescript\nimport { Computer } from '@octavus/computer';\nimport { OctavusClient } from '@octavus/server-sdk';\n\nconst computer = new Computer({\n  mcpServers: {\n    browser: Computer.stdio('chrome-devtools-mcp', [\n      '--browser-url=http://127.0.0.1:9222',\n    ]),\n    filesystem: Computer.stdio(\n      '@modelcontextprotocol/server-filesystem',\n      ['/path/to/workspace'],\n    ),\n    shell: Computer.shell({ cwd: '/path/to/workspace', mode: 'unrestricted' }),\n  },\n});\n\nawait computer.start();\n\nconst client = new OctavusClient({\n  baseUrl: 'https://octavus.ai',\n  apiKey: 'your-api-key',\n});\n\nconst session = client.agentSessions.attach(sessionId, {\n  tools: { 'set-chat-title': titleHandler },\n  computer,\n});\n```\n\nThe `computer` is passed to `attach()` \u2014 the server-sdk handles the rest. Tool schemas are sent to the platform, and tool calls flow back through the existing execution loop.\n\n## How It Works\n\n1. You configure MCP servers with namespaces (e.g., `browser`, `filesystem`, `shell`)\n2. `computer.start()` connects to all servers in parallel and discovers their tools\n3. Each tool is namespaced with `__` (e.g., `browser__navigate_page`, `filesystem__read_file`)\n4. The server-sdk sends tool schemas to the platform and handles tool call execution\n\nThe agent's protocol must declare matching `mcpServers` with `source: device` \u2014 see [MCP Servers](/docs/protocol/mcp-servers).\n\n## Entry Types\n\nThe `Computer` class supports three types of MCP entries:\n\n### Stdio (MCP Subprocess)\n\nSpawns an MCP server as a child process, communicating via stdin/stdout:\n\n```typescript\nComputer.stdio(command: string, args?: string[], options?: {\n  env?: Record<string, string>;\n  cwd?: string;\n})\n```\n\nUse this for local MCP servers installed as npm packages or standalone executables:\n\n```typescript\nconst computer = new Computer({\n  mcpServers: {\n    browser: Computer.stdio('chrome-devtools-mcp', [\n      '--browser-url=http://127.0.0.1:9222',\n      '--no-usage-statistics',\n    ]),\n    filesystem: Computer.stdio(\n      '@modelcontextprotocol/server-filesystem',\n      ['/Users/me/projects/my-app'],\n    ),\n  },\n});\n```\n\n### HTTP (Remote MCP Endpoint)\n\nConnects to an MCP server over Streamable HTTP:\n\n```typescript\nComputer.http(url: string, options?: {\n  headers?: Record<string, string>;\n})\n```\n\nUse this for MCP servers running as HTTP services:\n\n```typescript\nconst computer = new Computer({\n  mcpServers: {\n    docs: Computer.http('http://localhost:3001/mcp', {\n      headers: { 'Authorization': 'Bearer token' },\n    }),\n  },\n});\n```\n\n### Shell (Built-in)\n\nProvides shell command execution without spawning an MCP subprocess:\n\n```typescript\nComputer.shell(options: {\n  cwd?: string;\n  mode: ShellMode;\n  timeout?: number;  // Default: 300,000ms (5 minutes)\n})\n```\n\nThis exposes a `run_command` tool (namespaced as `shell__run_command` when the key is `shell`). Commands execute in a login shell with the user's full environment.\n\n```typescript\nconst computer = new Computer({\n  mcpServers: {\n    shell: Computer.shell({\n      cwd: '/Users/me/projects/my-app',\n      mode: 'unrestricted',\n      timeout: 300_000,\n    }),\n  },\n});\n```\n\n#### Shell Safety Modes\n\n| Mode                                       | Description                                  |\n| ------------------------------------------ | -------------------------------------------- |\n| `'unrestricted'`                           | All commands allowed (for dedicated machines) |\n| `{ allowedPatterns, blockedPatterns }`      | Pattern-based command filtering               |\n\nPattern-based filtering:\n\n```typescript\nComputer.shell({\n  cwd: workspaceDir,\n  mode: {\n    blockedPatterns: [/rm\\s+-rf/, /sudo/],\n    allowedPatterns: [/^git\\s/, /^npm\\s/, /^ls\\s/],\n  },\n})\n```\n\nWhen `allowedPatterns` is set, only matching commands are permitted. When `blockedPatterns` is set, matching commands are rejected. Blocked patterns are checked first.\n\n## Lifecycle\n\n### Starting\n\n`computer.start()` connects to all configured MCP servers in parallel. If some servers fail to connect, the computer still starts with the remaining servers \u2014 only if *all* connections fail does it throw an error.\n\n```typescript\nconst { errors } = await computer.start();\n\nif (errors.length > 0) {\n  console.warn('Some MCP servers failed to connect:', errors);\n}\n```\n\n### Stopping\n\n`computer.stop()` closes all MCP connections and kills managed processes:\n\n```typescript\nawait computer.stop();\n```\n\nAlways call `stop()` when the session ends to clean up MCP subprocesses. For managed processes (like Chrome), pass them in the config for automatic cleanup.\n\n## Chrome Launch Helper\n\nFor desktop applications that need to control a browser, `Computer.launchChrome()` launches Chrome with remote debugging enabled:\n\n```typescript\nconst browser = await Computer.launchChrome({\n  profileDir: '/Users/me/.my-app/chrome-profiles/agent-1',\n  debuggingPort: 9222, // Optional, auto-allocated if omitted\n  flags: ['--window-size=1280,800'],\n});\n\nconsole.log(`Chrome running on port ${browser.port}, PID ${browser.pid}`);\n```\n\nPass the browser to `managedProcesses` for automatic cleanup when the computer stops:\n\n```typescript\nconst computer = new Computer({\n  mcpServers: {\n    browser: Computer.stdio('chrome-devtools-mcp', [\n      `--browser-url=http://127.0.0.1:${browser.port}`,\n    ]),\n    filesystem: Computer.stdio(\n      '@modelcontextprotocol/server-filesystem',\n      [workspaceDir],\n    ),\n    shell: Computer.shell({ cwd: workspaceDir, mode: 'unrestricted' }),\n  },\n  managedProcesses: [{ process: browser.process }],\n});\n```\n\n### ChromeLaunchOptions\n\n| Field            | Required | Description                                          |\n| ---------------- | -------- | ---------------------------------------------------- |\n| `profileDir`     | Yes      | Directory for Chrome's user data (profile isolation)  |\n| `debuggingPort`  | No       | Port for remote debugging (auto-allocated if omitted) |\n| `flags`          | No       | Additional Chrome launch flags                        |\n\n## ToolProvider Interface\n\n`Computer` implements the `ToolProvider` interface from `@octavus/core`:\n\n```typescript\ninterface ToolProvider {\n  toolHandlers(): Record<string, ToolHandler>;\n  toolSchemas(): ToolSchema[];\n}\n```\n\nThe server-sdk accepts any `ToolProvider` on the `computer` option \u2014 you can implement your own if `@octavus/computer` doesn't fit your use case:\n\n```typescript\nconst customProvider: ToolProvider = {\n  toolHandlers() {\n    return {\n      'custom__my_tool': async (args) => {\n        return { result: 'done' };\n      },\n    };\n  },\n  toolSchemas() {\n    return [\n      {\n        name: 'custom__my_tool',\n        description: 'A custom tool',\n        inputSchema: {\n          type: 'object',\n          properties: {\n            input: { type: 'string', description: 'Tool input' },\n          },\n          required: ['input'],\n        },\n      },\n    ];\n  },\n};\n\nconst session = client.agentSessions.attach(sessionId, {\n  tools: { 'set-chat-title': titleHandler },\n  computer: customProvider,\n});\n```\n\n## Complete Example\n\nA desktop application with browser, filesystem, and shell capabilities:\n\n```typescript\nimport { Computer } from '@octavus/computer';\nimport { OctavusClient } from '@octavus/server-sdk';\n\nconst WORKSPACE_DIR = '/Users/me/projects/my-app';\nconst PROFILE_DIR = '/Users/me/.my-app/chrome-profiles/agent';\n\nasync function startSession(sessionId: string) {\n  // 1. Launch Chrome with remote debugging\n  const browser = await Computer.launchChrome({\n    profileDir: PROFILE_DIR,\n  });\n\n  // 2. Create computer with all capabilities\n  const computer = new Computer({\n    mcpServers: {\n      browser: Computer.stdio('chrome-devtools-mcp', [\n        `--browser-url=http://127.0.0.1:${browser.port}`,\n        '--no-usage-statistics',\n      ]),\n      filesystem: Computer.stdio(\n        '@modelcontextprotocol/server-filesystem',\n        [WORKSPACE_DIR],\n      ),\n      shell: Computer.shell({\n        cwd: WORKSPACE_DIR,\n        mode: 'unrestricted',\n      }),\n    },\n    managedProcesses: [{ process: browser.process }],\n  });\n\n  // 3. Connect to all MCP servers\n  const { errors } = await computer.start();\n  if (errors.length > 0) {\n    console.warn('Failed to connect:', errors);\n  }\n\n  // 4. Attach to session with computer\n  const client = new OctavusClient({\n    baseUrl: process.env.OCTAVUS_API_URL!,\n    apiKey: process.env.OCTAVUS_API_KEY!,\n  });\n\n  const session = client.agentSessions.attach(sessionId, {\n    tools: {\n      'set-chat-title': async (args) => {\n        console.log('Chat title:', args.title);\n        return { success: true };\n      },\n    },\n    computer,\n  });\n\n  // 5. Execute and stream\n  const events = session.execute({\n    type: 'trigger',\n    triggerName: 'user-message',\n    input: { USER_MESSAGE: 'Navigate to github.com and take a screenshot' },\n  });\n\n  for await (const event of events) {\n    // Handle stream events\n  }\n\n  // 6. Clean up\n  await computer.stop();\n}\n```\n\n## API Reference\n\n### Computer\n\n```typescript\nclass Computer implements ToolProvider {\n  constructor(config: ComputerConfig);\n\n  // Static factories for MCP entries\n  static stdio(command: string, args?: string[], options?: {\n    env?: Record<string, string>;\n    cwd?: string;\n  }): StdioConfig;\n\n  static http(url: string, options?: {\n    headers?: Record<string, string>;\n  }): HttpConfig;\n\n  static shell(options: {\n    cwd?: string;\n    mode: ShellMode;\n    timeout?: number;\n  }): ShellConfig;\n\n  // Chrome launch helper\n  static launchChrome(options: ChromeLaunchOptions): Promise<ChromeInstance>;\n\n  // Lifecycle\n  start(): Promise<{ errors: string[] }>;\n  stop(): Promise<void>;\n\n  // ToolProvider implementation\n  toolHandlers(): Record<string, ToolHandler>;\n  toolSchemas(): ToolSchema[];\n}\n```\n\n### ComputerConfig\n\n```typescript\ninterface ComputerConfig {\n  mcpServers: Record<string, McpEntry>;\n  managedProcesses?: { process: ChildProcess }[];\n}\n\ntype McpEntry = StdioConfig | HttpConfig | ShellConfig;\ntype ShellMode = 'unrestricted' | {\n  allowedPatterns?: RegExp[];\n  blockedPatterns?: RegExp[];\n};\n```\n\n### ChromeInstance\n\n```typescript\ninterface ChromeInstance {\n  port: number;\n  process: ChildProcess;\n  pid: number;\n}\n```\n",
+    excerpt: "Computer The  package gives agents access to a physical or virtual machine's browser, filesystem, and shell. It connects to MCP servers, discovers their tools, and provides them to the server-sdk....",
+    order: 8
+  },
   {
     slug: "client-sdk/overview",
     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:** `2.15.0`\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",
+    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:** `2.16.0`\n\n### Other Frameworks\n\n```bash\nnpm install @octavus/client-sdk\n```\n\n**Current version:** `2.16.0`\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
   },
@@ -588,7 +597,7 @@ See [Streaming Events](/docs/server-sdk/streaming#event-types) for the full list
     section: "protocol",
     title: "Handlers",
     description: "Defining execution handlers with blocks.",
-    content: "\n# Handlers\n\nHandlers define what happens when a trigger fires. They contain execution blocks that run in sequence.\n\n## Handler Structure\n\n```yaml\nhandlers:\n  trigger-name:\n    Block Name:\n      block: block-kind\n      # block-specific properties\n\n    Another Block:\n      block: another-kind\n      # ...\n```\n\nEach block has a human-readable name (shown in debug UI) and a `block` field that determines its behavior.\n\n## Block Kinds\n\n### next-message\n\nGenerate a response from the LLM:\n\n```yaml\nhandlers:\n  user-message:\n    Respond to user:\n      block: next-message\n      # Uses main conversation thread by default\n      # Display defaults to 'stream'\n```\n\nWith options:\n\n```yaml\nGenerate summary:\n  block: next-message\n  thread: summary # Use named thread\n  display: stream # Show streaming content\n  independent: true # Don't add to main chat\n  output: SUMMARY # Store output in variable\n  description: Generating summary # Shown in UI\n```\n\nFor structured output (typed JSON response):\n\n```yaml\nRespond with suggestions:\n  block: next-message\n  responseType: ChatResponse # Type defined in types section\n  output: RESPONSE # Stores the parsed object\n```\n\nWhen `responseType` is specified:\n\n- The LLM generates JSON matching the type schema\n- The `output` variable receives the parsed object (not plain text)\n- The client receives a `UIObjectPart` for custom rendering\n\nSee [Types](/docs/protocol/types#structured-output) for more details.\n\n### add-message\n\nAdd a message to the conversation:\n\n```yaml\nAdd user message:\n  block: add-message\n  role: user # user | assistant | system\n  prompt: user-message # Reference to prompt file\n  input: [USER_MESSAGE] # Variables to interpolate\n  display: hidden # Don't show in UI\n```\n\nFor internal directives (LLM sees it, user doesn't):\n\n```yaml\nAdd internal directive:\n  block: add-message\n  role: user\n  prompt: ticket-directive\n  input: [TICKET_DETAILS]\n  visible: false # LLM sees this, user doesn't\n```\n\nFor structured user input (object shown in UI, prompt for LLM context):\n\n```yaml\nAdd user message:\n  block: add-message\n  role: user\n  prompt: user-message # Rendered for LLM context (hidden from UI)\n  input: [USER_INPUT]\n  uiContent: USER_INPUT # Variable shown in UI (object \u2192 object part)\n  display: hidden\n```\n\nWhen `uiContent` is set:\n\n- The variable value is shown in the UI (string \u2192 text part, object \u2192 object part)\n- The prompt text is hidden from the UI but kept for LLM context\n- Useful for rich UI interactions where the visual differs from the LLM context\n\n### tool-call\n\nCall a tool deterministically:\n\n```yaml\nCreate ticket:\n  block: tool-call\n  tool: create-support-ticket\n  input:\n    summary: SUMMARY # Variable reference\n    priority: medium # Literal value\n  output: TICKET # Store result\n```\n\n### set-resource\n\nUpdate a persistent resource:\n\n```yaml\nSave summary:\n  block: set-resource\n  resource: CONVERSATION_SUMMARY\n  value: SUMMARY # Variable to save\n  display: name # Show block name\n```\n\n### start-thread\n\nCreate a named conversation thread:\n\n```yaml\nStart summary thread:\n  block: start-thread\n  thread: summary # Thread name\n  model: anthropic/claude-sonnet-4-5 # Optional: different model\n  thinking: low # Extended reasoning level\n  maxSteps: 1 # Tool call limit\n  system: escalation-summary # System prompt\n  input: [COMPANY_NAME] # Variables for prompt\n  skills: [qr-code] # Octavus skills for this thread\n  sandboxTimeout: 600000 # Skill sandbox timeout (default: 5 min, max: 1 hour)\n  imageModel: google/gemini-2.5-flash-image # Image generation model\n```\n\nThe `model` field can also reference a variable for dynamic model selection:\n\n```yaml\nStart summary thread:\n  block: start-thread\n  thread: summary\n  model: SUMMARY_MODEL # Resolved from input variable\n  system: escalation-summary\n```\n\n### serialize-thread\n\nConvert conversation to text:\n\n```yaml\nSerialize conversation:\n  block: serialize-thread\n  thread: main # Which thread (default: main)\n  format: markdown # markdown | json\n  output: CONVERSATION_TEXT # Variable to store result\n```\n\n### generate-image\n\nGenerate an image from a prompt variable:\n\n```yaml\nGenerate image:\n  block: generate-image\n  prompt: OPTIMIZED_PROMPT # Variable containing the prompt\n  imageModel: google/gemini-2.5-flash-image # Required image model\n  size: 1024x1024 # 1024x1024 | 1792x1024 | 1024x1792\n  output: GENERATED_IMAGE # Store URL in variable\n  description: Generating your image... # Shown in UI\n```\n\nEdit an existing image using reference images:\n\n```yaml\nEdit image:\n  block: generate-image\n  prompt: EDIT_INSTRUCTIONS # e.g., \"Remove the background\"\n  referenceImages: [SOURCE_IMAGE_URL] # Variable(s) containing image URLs\n  imageModel: google/gemini-2.5-flash-image\n  output: EDITED_IMAGE\n  description: Editing image...\n```\n\n| Field             | Required | Description                                                     |\n| ----------------- | -------- | --------------------------------------------------------------- |\n| `prompt`          | Yes      | Variable name containing the image prompt or edit instructions  |\n| `imageModel`      | Yes      | Image model identifier (e.g., `google/gemini-2.5-flash-image`)  |\n| `size`            | No       | Image dimensions: `1024x1024`, `1792x1024`, or `1024x1792`      |\n| `referenceImages` | No       | Variable names containing image URLs for editing/transformation |\n| `output`          | No       | Variable name to store the generated image URL                  |\n| `thread`          | No       | Thread to associate the output file with                        |\n| `description`     | No       | Description shown in the UI during generation                   |\n\nThis block is for deterministic image generation pipelines where the prompt is constructed programmatically (e.g., via prompt engineering in a separate thread). When `referenceImages` are provided, the prompt describes how to modify those images.\n\nFor agentic image generation where the LLM decides when to generate, configure `imageModel` in the [agent config](/docs/protocol/agent-config#image-generation).\n\n## Display Modes\n\nEvery block has a `display` property:\n\n| Mode          | Default For               | Behavior          |\n| ------------- | ------------------------- | ----------------- |\n| `hidden`      | add-message               | Not shown to user |\n| `name`        | set-resource              | Shows block name  |\n| `description` | tool-call, generate-image | Shows description |\n| `stream`      | next-message              | Streams content   |\n\n## Complete Example\n\n```yaml\nhandlers:\n  user-message:\n    # Add the user's message to conversation\n    Add user message:\n      block: add-message\n      role: user\n      prompt: user-message\n      input: [USER_MESSAGE]\n      display: hidden\n\n    # Generate response (LLM may call tools)\n    Respond to user:\n      block: next-message\n      # display: stream (default)\n\n  request-human:\n    # Step 1: Serialize conversation for summary\n    Serialize conversation:\n      block: serialize-thread\n      format: markdown\n      output: CONVERSATION_TEXT\n\n    # Step 2: Create separate thread for summarization\n    Start summary thread:\n      block: start-thread\n      thread: summary\n      model: anthropic/claude-sonnet-4-5\n      thinking: low\n      system: escalation-summary\n      input: [COMPANY_NAME]\n\n    # Step 3: Add request to summary thread\n    Add summarize request:\n      block: add-message\n      thread: summary\n      role: user\n      prompt: summarize-request\n      input:\n        - CONVERSATION: CONVERSATION_TEXT\n\n    # Step 4: Generate summary\n    Generate summary:\n      block: next-message\n      thread: summary\n      display: stream\n      description: Summarizing your conversation\n      independent: true\n      output: SUMMARY\n\n    # Step 5: Save to resource\n    Save summary:\n      block: set-resource\n      resource: CONVERSATION_SUMMARY\n      value: SUMMARY\n\n    # Step 6: Create support ticket\n    Create ticket:\n      block: tool-call\n      tool: create-support-ticket\n      input:\n        summary: SUMMARY\n        priority: medium\n      output: TICKET\n\n    # Step 7: Add directive for response\n    Add directive:\n      block: add-message\n      role: user\n      prompt: ticket-directive\n      input: [TICKET_DETAILS: TICKET]\n      visible: false\n\n    # Step 8: Respond to user\n    Respond:\n      block: next-message\n```\n\n## Block Input Mapping\n\nThe `input` field on blocks controls which variables are passed to the prompt. Only variables listed in `input` are available for interpolation.\n\nVariables can come from `protocol.input`, `protocol.resources`, `protocol.variables`, `trigger.input`, or outputs from prior blocks.\n\n```yaml\n# Array format (same name)\ninput: [USER_MESSAGE, COMPANY_NAME]\n\n# Array format (rename)\ninput:\n  - CONVERSATION: CONVERSATION_TEXT  # Prompt sees CONVERSATION, value comes from CONVERSATION_TEXT\n  - TICKET_DETAILS: TICKET\n\n# Object format (rename)\ninput:\n  CONVERSATION: CONVERSATION_TEXT\n  TICKET_DETAILS: TICKET\n```\n\n## Independent Blocks\n\nUse `independent: true` for content that shouldn't go to the main chat:\n\n```yaml\nGenerate summary:\n  block: next-message\n  thread: summary\n  independent: true # Output stored in variable, not main chat\n  output: SUMMARY\n```\n\nThis is useful for:\n\n- Background processing\n- Summarization in separate threads\n- Generating content for tools\n",
+    content: "\n# Handlers\n\nHandlers define what happens when a trigger fires. They contain execution blocks that run in sequence.\n\n## Handler Structure\n\n```yaml\nhandlers:\n  trigger-name:\n    Block Name:\n      block: block-kind\n      # block-specific properties\n\n    Another Block:\n      block: another-kind\n      # ...\n```\n\nEach block has a human-readable name (shown in debug UI) and a `block` field that determines its behavior.\n\n## Block Kinds\n\n### next-message\n\nGenerate a response from the LLM:\n\n```yaml\nhandlers:\n  user-message:\n    Respond to user:\n      block: next-message\n      # Uses main conversation thread by default\n      # Display defaults to 'stream'\n```\n\nWith options:\n\n```yaml\nGenerate summary:\n  block: next-message\n  thread: summary # Use named thread\n  display: stream # Show streaming content\n  independent: true # Don't add to main chat\n  output: SUMMARY # Store output in variable\n  description: Generating summary # Shown in UI\n```\n\nFor structured output (typed JSON response):\n\n```yaml\nRespond with suggestions:\n  block: next-message\n  responseType: ChatResponse # Type defined in types section\n  output: RESPONSE # Stores the parsed object\n```\n\nWhen `responseType` is specified:\n\n- The LLM generates JSON matching the type schema\n- The `output` variable receives the parsed object (not plain text)\n- The client receives a `UIObjectPart` for custom rendering\n\nSee [Types](/docs/protocol/types#structured-output) for more details.\n\n### add-message\n\nAdd a message to the conversation:\n\n```yaml\nAdd user message:\n  block: add-message\n  role: user # user | assistant | system\n  prompt: user-message # Reference to prompt file\n  input: [USER_MESSAGE] # Variables to interpolate\n  display: hidden # Don't show in UI\n```\n\nFor internal directives (LLM sees it, user doesn't):\n\n```yaml\nAdd internal directive:\n  block: add-message\n  role: user\n  prompt: ticket-directive\n  input: [TICKET_DETAILS]\n  visible: false # LLM sees this, user doesn't\n```\n\nFor structured user input (object shown in UI, prompt for LLM context):\n\n```yaml\nAdd user message:\n  block: add-message\n  role: user\n  prompt: user-message # Rendered for LLM context (hidden from UI)\n  input: [USER_INPUT]\n  uiContent: USER_INPUT # Variable shown in UI (object \u2192 object part)\n  display: hidden\n```\n\nWhen `uiContent` is set:\n\n- The variable value is shown in the UI (string \u2192 text part, object \u2192 object part)\n- The prompt text is hidden from the UI but kept for LLM context\n- Useful for rich UI interactions where the visual differs from the LLM context\n\n### tool-call\n\nCall a tool deterministically:\n\n```yaml\nCreate ticket:\n  block: tool-call\n  tool: create-support-ticket\n  input:\n    summary: SUMMARY # Variable reference\n    priority: medium # Literal value\n  output: TICKET # Store result\n```\n\n### set-resource\n\nUpdate a persistent resource:\n\n```yaml\nSave summary:\n  block: set-resource\n  resource: CONVERSATION_SUMMARY\n  value: SUMMARY # Variable to save\n  display: name # Show block name\n```\n\n### start-thread\n\nCreate a named conversation thread:\n\n```yaml\nStart summary thread:\n  block: start-thread\n  thread: summary # Thread name\n  model: anthropic/claude-sonnet-4-5 # Optional: different model\n  backupModel: openai/gpt-4o # Failover on provider errors\n  thinking: low # Extended reasoning level\n  maxSteps: 1 # Tool call limit\n  system: escalation-summary # System prompt\n  input: [COMPANY_NAME] # Variables for prompt\n  skills: [qr-code] # Octavus skills for this thread\n  sandboxTimeout: 600000 # Skill sandbox timeout (default: 5 min, max: 1 hour)\n  imageModel: google/gemini-2.5-flash-image # Image generation model\n```\n\nThe `model` field can also reference a variable for dynamic model selection. The `backupModel` field follows the same format and supports variable references.\n\n```yaml\nStart summary thread:\n  block: start-thread\n  thread: summary\n  model: SUMMARY_MODEL # Resolved from input variable\n  system: escalation-summary\n```\n\n### serialize-thread\n\nConvert conversation to text:\n\n```yaml\nSerialize conversation:\n  block: serialize-thread\n  thread: main # Which thread (default: main)\n  format: markdown # markdown | json\n  output: CONVERSATION_TEXT # Variable to store result\n```\n\n### generate-image\n\nGenerate an image from a prompt variable:\n\n```yaml\nGenerate image:\n  block: generate-image\n  prompt: OPTIMIZED_PROMPT # Variable containing the prompt\n  imageModel: google/gemini-2.5-flash-image # Required image model\n  size: 1024x1024 # 1024x1024 | 1792x1024 | 1024x1792\n  output: GENERATED_IMAGE # Store URL in variable\n  description: Generating your image... # Shown in UI\n```\n\nEdit an existing image using reference images:\n\n```yaml\nEdit image:\n  block: generate-image\n  prompt: EDIT_INSTRUCTIONS # e.g., \"Remove the background\"\n  referenceImages: [SOURCE_IMAGE_URL] # Variable(s) containing image URLs\n  imageModel: google/gemini-2.5-flash-image\n  output: EDITED_IMAGE\n  description: Editing image...\n```\n\n| Field             | Required | Description                                                     |\n| ----------------- | -------- | --------------------------------------------------------------- |\n| `prompt`          | Yes      | Variable name containing the image prompt or edit instructions  |\n| `imageModel`      | Yes      | Image model identifier (e.g., `google/gemini-2.5-flash-image`)  |\n| `size`            | No       | Image dimensions: `1024x1024`, `1792x1024`, or `1024x1792`      |\n| `referenceImages` | No       | Variable names containing image URLs for editing/transformation |\n| `output`          | No       | Variable name to store the generated image URL                  |\n| `thread`          | No       | Thread to associate the output file with                        |\n| `description`     | No       | Description shown in the UI during generation                   |\n\nThis block is for deterministic image generation pipelines where the prompt is constructed programmatically (e.g., via prompt engineering in a separate thread). When `referenceImages` are provided, the prompt describes how to modify those images.\n\nFor agentic image generation where the LLM decides when to generate, configure `imageModel` in the [agent config](/docs/protocol/agent-config#image-generation).\n\n## Display Modes\n\nEvery block has a `display` property:\n\n| Mode          | Default For               | Behavior          |\n| ------------- | ------------------------- | ----------------- |\n| `hidden`      | add-message               | Not shown to user |\n| `name`        | set-resource              | Shows block name  |\n| `description` | tool-call, generate-image | Shows description |\n| `stream`      | next-message              | Streams content   |\n\n## Complete Example\n\n```yaml\nhandlers:\n  user-message:\n    # Add the user's message to conversation\n    Add user message:\n      block: add-message\n      role: user\n      prompt: user-message\n      input: [USER_MESSAGE]\n      display: hidden\n\n    # Generate response (LLM may call tools)\n    Respond to user:\n      block: next-message\n      # display: stream (default)\n\n  request-human:\n    # Step 1: Serialize conversation for summary\n    Serialize conversation:\n      block: serialize-thread\n      format: markdown\n      output: CONVERSATION_TEXT\n\n    # Step 2: Create separate thread for summarization\n    Start summary thread:\n      block: start-thread\n      thread: summary\n      model: anthropic/claude-sonnet-4-5\n      thinking: low\n      system: escalation-summary\n      input: [COMPANY_NAME]\n\n    # Step 3: Add request to summary thread\n    Add summarize request:\n      block: add-message\n      thread: summary\n      role: user\n      prompt: summarize-request\n      input:\n        - CONVERSATION: CONVERSATION_TEXT\n\n    # Step 4: Generate summary\n    Generate summary:\n      block: next-message\n      thread: summary\n      display: stream\n      description: Summarizing your conversation\n      independent: true\n      output: SUMMARY\n\n    # Step 5: Save to resource\n    Save summary:\n      block: set-resource\n      resource: CONVERSATION_SUMMARY\n      value: SUMMARY\n\n    # Step 6: Create support ticket\n    Create ticket:\n      block: tool-call\n      tool: create-support-ticket\n      input:\n        summary: SUMMARY\n        priority: medium\n      output: TICKET\n\n    # Step 7: Add directive for response\n    Add directive:\n      block: add-message\n      role: user\n      prompt: ticket-directive\n      input: [TICKET_DETAILS: TICKET]\n      visible: false\n\n    # Step 8: Respond to user\n    Respond:\n      block: next-message\n```\n\n## Block Input Mapping\n\nThe `input` field on blocks controls which variables are passed to the prompt. Only variables listed in `input` are available for interpolation.\n\nVariables can come from `protocol.input`, `protocol.resources`, `protocol.variables`, `trigger.input`, or outputs from prior blocks.\n\n```yaml\n# Array format (same name)\ninput: [USER_MESSAGE, COMPANY_NAME]\n\n# Array format (rename)\ninput:\n  - CONVERSATION: CONVERSATION_TEXT  # Prompt sees CONVERSATION, value comes from CONVERSATION_TEXT\n  - TICKET_DETAILS: TICKET\n\n# Object format (rename)\ninput:\n  CONVERSATION: CONVERSATION_TEXT\n  TICKET_DETAILS: TICKET\n```\n\n## Independent Blocks\n\nUse `independent: true` for content that shouldn't go to the main chat:\n\n```yaml\nGenerate summary:\n  block: next-message\n  thread: summary\n  independent: true # Output stored in variable, not main chat\n  output: SUMMARY\n```\n\nThis is useful for:\n\n- Background processing\n- Summarization in separate threads\n- Generating content for tools\n",
     excerpt: "Handlers Handlers define what happens when a trigger fires. They contain execution blocks that run in sequence.  Handler Structure Each block has a human-readable name (shown in debug UI) and a ...",
     order: 6
   },
@@ -597,7 +606,7 @@ See [Streaming Events](/docs/server-sdk/streaming#event-types) for the full list
     section: "protocol",
     title: "Agent Config",
     description: "Configuring the agent model and behavior.",
-    content: "\n# Agent Config\n\nThe `agent` section configures the LLM model, system prompt, tools, and behavior.\n\n## Basic Configuration\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system # References prompts/system.md\n  tools: [get-user-account] # Available tools\n  skills: [qr-code] # Available skills\n  references: [api-guidelines] # On-demand context documents\n```\n\n## Configuration Options\n\n| Field            | Required | Description                                               |\n| ---------------- | -------- | --------------------------------------------------------- |\n| `model`          | Yes      | Model identifier or variable reference                    |\n| `system`         | Yes      | System prompt filename (without .md)                      |\n| `input`          | No       | Variables to pass to the system prompt                    |\n| `tools`          | No       | List of tools the LLM can call                            |\n| `skills`         | No       | List of Octavus skills the LLM can use                    |\n| `references`     | No       | List of references the LLM can fetch on demand            |\n| `sandboxTimeout` | No       | Skill sandbox timeout in ms (default: 5 min, max: 1 hour) |\n| `imageModel`     | No       | Image generation model (enables agentic image generation) |\n| `webSearch`      | No       | Enable built-in web search tool (provider-agnostic)       |\n| `agentic`        | No       | Allow multiple tool call cycles                           |\n| `maxSteps`       | No       | Maximum agentic steps (default: 10)                       |\n| `temperature`    | No       | Model temperature (0-2)                                   |\n| `thinking`       | No       | Extended reasoning level                                  |\n| `anthropic`      | No       | Anthropic-specific options (tools, skills)                |\n\n## Models\n\nSpecify models in `provider/model-id` format. Any model supported by the provider's SDK will work.\n\n### Supported Providers\n\n| Provider  | Format                 | Examples                                                             |\n| --------- | ---------------------- | -------------------------------------------------------------------- |\n| Anthropic | `anthropic/{model-id}` | `claude-opus-4-5`, `claude-sonnet-4-5`, `claude-haiku-4-5`           |\n| Google    | `google/{model-id}`    | `gemini-3-pro-preview`, `gemini-3-flash-preview`, `gemini-2.5-flash` |\n| OpenAI    | `openai/{model-id}`    | `gpt-5`, `gpt-4o`, `o4-mini`, `o3`, `o3-mini`, `o1`                  |\n\n### Examples\n\n```yaml\n# Anthropic Claude 4.5\nagent:\n  model: anthropic/claude-sonnet-4-5\n\n# Google Gemini 3\nagent:\n  model: google/gemini-3-flash-preview\n\n# OpenAI GPT-5\nagent:\n  model: openai/gpt-5\n\n# OpenAI reasoning models\nagent:\n  model: openai/o3-mini\n```\n\n> **Note**: Model IDs are passed directly to the provider SDK. Check the provider's documentation for the latest available models.\n\n### Dynamic Model Selection\n\nThe model field can also reference an input variable, allowing consumers to choose the model when creating a session:\n\n```yaml\ninput:\n  MODEL:\n    type: string\n    description: The LLM model to use\n\nagent:\n  model: MODEL # Resolved from session input\n  system: system\n```\n\nWhen creating a session, pass the model:\n\n```typescript\nconst sessionId = await client.agentSessions.create('my-agent', {\n  MODEL: 'anthropic/claude-sonnet-4-5',\n});\n```\n\nThis enables:\n\n- **Multi-provider support** \u2014 Same agent works with different providers\n- **A/B testing** \u2014 Test different models without protocol changes\n- **User preferences** \u2014 Let users choose their preferred model\n\nThe model value is validated at runtime to ensure it's in the correct `provider/model-id` format.\n\n> **Note**: When using dynamic models, provider-specific options (like `anthropic:`) may not apply if the model resolves to a different provider.\n\n## System Prompt\n\nThe system prompt sets the agent's persona and instructions. The `input` field controls which variables are available to the prompt \u2014 only variables listed in `input` are interpolated.\n\n```yaml\nagent:\n  system: system # Uses prompts/system.md\n  input:\n    - COMPANY_NAME\n    - PRODUCT_NAME\n```\n\nVariables in `input` can come from `protocol.input`, `protocol.resources`, or `protocol.variables`.\n\n### Input Mapping Formats\n\n```yaml\n# Array format (same name)\ninput:\n  - COMPANY_NAME\n  - PRODUCT_NAME\n\n# Array format (rename)\ninput:\n  - CONTEXT: CONVERSATION_SUMMARY  # Prompt sees CONTEXT, value comes from CONVERSATION_SUMMARY\n\n# Object format (rename)\ninput:\n  CONTEXT: CONVERSATION_SUMMARY\n```\n\nThe left side (label) is what the prompt sees. The right side (source) is where the value comes from.\n\n### Example\n\n`prompts/system.md`:\n\n```markdown\nYou are a friendly support agent for {{COMPANY_NAME}}.\n\n## Your Role\n\nHelp users with questions about {{PRODUCT_NAME}}.\n\n## Guidelines\n\n- Be helpful and professional\n- If you can't help, offer to escalate\n- Never share internal information\n```\n\n## Agentic Mode\n\nEnable multi-step tool calling:\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  tools: [get-user-account, search-docs, create-ticket]\n  agentic: true # LLM can call multiple tools\n  maxSteps: 10 # Limit cycles to prevent runaway\n```\n\n**How it works:**\n\n1. LLM receives user message\n2. LLM decides to call a tool\n3. Tool executes, result returned to LLM\n4. LLM decides if more tools needed\n5. Repeat until LLM responds or maxSteps reached\n\n## Extended Thinking\n\nEnable extended reasoning for complex tasks:\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  thinking: medium # low | medium | high\n```\n\n| Level    | Token Budget | Use Case            |\n| -------- | ------------ | ------------------- |\n| `low`    | ~5,000       | Simple reasoning    |\n| `medium` | ~10,000      | Moderate complexity |\n| `high`   | ~20,000      | Complex analysis    |\n\nThinking content streams to the UI and can be displayed to users.\n\n## Skills\n\nEnable Octavus skills for code execution and file generation:\n\n```yaml\nskills:\n  qr-code:\n    display: description\n    description: Generating QR codes\n\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  skills: [qr-code] # Enable skills\n  agentic: true\n```\n\nSkills provide provider-agnostic code execution in isolated sandboxes. When enabled, the LLM can execute Python/Bash code, run skill scripts, and generate files.\n\nSee [Skills](/docs/protocol/skills) for full documentation.\n\n## References\n\nEnable on-demand context loading via reference documents:\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  references: [api-guidelines, error-codes]\n  agentic: true\n```\n\nReferences are markdown files stored in the agent's `references/` directory. When enabled, the LLM can list available references and read their content using `octavus_reference_list` and `octavus_reference_read` tools.\n\nSee [References](/docs/protocol/references) for full documentation.\n\n## Image Generation\n\nEnable the LLM to generate images autonomously:\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  imageModel: google/gemini-2.5-flash-image\n  agentic: true\n```\n\nWhen `imageModel` is configured, the `octavus_generate_image` tool becomes available. The LLM can decide when to generate images based on user requests. The tool supports both text-to-image generation and image editing/transformation using reference images.\n\n### Supported Image Providers\n\n| Provider | Model Types                             | Examples                                                  |\n| -------- | --------------------------------------- | --------------------------------------------------------- |\n| OpenAI   | Dedicated image models                  | `gpt-image-1`                                             |\n| Google   | Gemini native (contains \"image\")        | `gemini-2.5-flash-image`, `gemini-3-flash-image-generate` |\n| Google   | Imagen dedicated (starts with \"imagen\") | `imagen-4.0-generate-001`                                 |\n\n> **Note**: Google has two image generation approaches. Gemini \"native\" models (containing \"image\" in the ID) generate images using the language model API with `responseModalities`. Imagen models (starting with \"imagen\") use a dedicated image generation API.\n\n### Image Sizes\n\nThe tool supports three image sizes:\n\n- `1024x1024` (default) \u2014 Square\n- `1792x1024` \u2014 Landscape (16:9)\n- `1024x1792` \u2014 Portrait (9:16)\n\n### Image Editing with Reference Images\n\nBoth the agentic tool and the `generate-image` block support reference images for editing and transformation. When reference images are provided, the prompt describes how to modify or use those images.\n\n| Provider | Models                           | Reference Image Support |\n| -------- | -------------------------------- | ----------------------- |\n| OpenAI   | `gpt-image-1`                    | Yes                     |\n| Google   | Gemini native (`gemini-*-image`) | Yes                     |\n| Google   | Imagen (`imagen-*`)              | No                      |\n\n### Agentic vs Deterministic\n\nUse `imageModel` in agent config when:\n\n- The LLM should decide when to generate or edit images\n- Users ask for images in natural language\n\nUse `generate-image` block (see [Handlers](/docs/protocol/handlers#generate-image)) when:\n\n- You want explicit control over image generation or editing\n- Building prompt engineering pipelines\n- Images are generated at specific handler steps\n\n## Web Search\n\nEnable the LLM to search the web for current information:\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  webSearch: true\n  agentic: true\n```\n\nWhen `webSearch` is enabled, the `octavus_web_search` tool becomes available. The LLM can decide when to search the web based on the conversation. Search results include source URLs that are emitted as citations in the UI.\n\nThis is a **provider-agnostic** built-in tool \u2014 it works with any LLM provider (Anthropic, Google, OpenAI, etc.). For Anthropic's own web search implementation, see [Provider Options](/docs/protocol/provider-options).\n\nUse cases:\n\n- Current events and real-time data\n- Fact verification and documentation lookups\n- Any information that may have changed since the model's training\n\n## Temperature\n\nControl response randomness:\n\n```yaml\nagent:\n  model: openai/gpt-4o\n  temperature: 0.7 # 0 = deterministic, 2 = creative\n```\n\n**Guidelines:**\n\n- `0 - 0.3`: Factual, consistent responses\n- `0.4 - 0.7`: Balanced (good default)\n- `0.8 - 1.2`: Creative, varied responses\n- `> 1.2`: Very creative (may be inconsistent)\n\n## Provider Options\n\nEnable provider-specific features like Anthropic's built-in tools and skills:\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  anthropic:\n    tools:\n      web-search:\n        display: description\n        description: Searching the web\n    skills:\n      pdf:\n        type: anthropic\n        description: Processing PDF\n```\n\nProvider options are validated against the model\u2014using `anthropic:` with a non-Anthropic model will fail validation.\n\nSee [Provider Options](/docs/protocol/provider-options) for full documentation.\n\n## Thread-Specific Config\n\nOverride config for named threads:\n\n```yaml\nhandlers:\n  request-human:\n    Start summary thread:\n      block: start-thread\n      thread: summary\n      model: anthropic/claude-sonnet-4-5 # Different model\n      thinking: low # Different thinking\n      maxSteps: 1 # Limit tool calls\n      system: escalation-summary # Different prompt\n      skills: [data-analysis] # Thread-specific skills\n      references: [escalation-policy] # Thread-specific references\n      imageModel: google/gemini-2.5-flash-image # Thread-specific image model\n      webSearch: true # Thread-specific web search\n```\n\nEach thread can have its own skills, references, image model, and web search setting. Skills must be defined in the protocol's `skills:` section. References must exist in the agent's `references/` directory. Workers use this same pattern since they don't have a global `agent:` section.\n\n## Full Example\n\n```yaml\ninput:\n  COMPANY_NAME: { type: string }\n  PRODUCT_NAME: { type: string }\n  USER_ID: { type: string, optional: true }\n\nresources:\n  CONVERSATION_SUMMARY:\n    type: string\n    default: ''\n\ntools:\n  get-user-account:\n    description: Look up user account\n    parameters:\n      userId: { type: string }\n\n  search-docs:\n    description: Search help documentation\n    parameters:\n      query: { type: string }\n\n  create-support-ticket:\n    description: Create a support ticket\n    parameters:\n      summary: { type: string }\n      priority: { type: string } # low, medium, high\n\nskills:\n  qr-code:\n    display: description\n    description: Generating QR codes\n\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  input:\n    - COMPANY_NAME\n    - PRODUCT_NAME\n  tools:\n    - get-user-account\n    - search-docs\n    - create-support-ticket\n  skills: [qr-code] # Octavus skills\n  references: [support-policies] # On-demand context\n  webSearch: true # Built-in web search\n  agentic: true\n  maxSteps: 10\n  thinking: medium\n  # Anthropic-specific options\n  anthropic:\n    tools:\n      web-search:\n        display: description\n        description: Searching the web\n    skills:\n      pdf:\n        type: anthropic\n        description: Processing PDF\n\ntriggers:\n  user-message:\n    input:\n      USER_MESSAGE: { type: string }\n\nhandlers:\n  user-message:\n    Add message:\n      block: add-message\n      role: user\n      prompt: user-message\n      input: [USER_MESSAGE]\n      display: hidden\n\n    Respond:\n      block: next-message\n```\n",
+    content: "\n# Agent Config\n\nThe `agent` section configures the LLM model, system prompt, tools, and behavior.\n\n## Basic Configuration\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system # References prompts/system.md\n  tools: [get-user-account] # Available tools\n  skills: [qr-code] # Available skills\n  references: [api-guidelines] # On-demand context documents\n```\n\n## Configuration Options\n\n| Field            | Required | Description                                               |\n| ---------------- | -------- | --------------------------------------------------------- |\n| `model`          | Yes      | Model identifier or variable reference                    |\n| `backupModel`    | No       | Backup model for automatic failover on provider errors    |\n| `system`         | Yes      | System prompt filename (without .md)                      |\n| `input`          | No       | Variables to pass to the system prompt                    |\n| `tools`          | No       | List of tools the LLM can call                            |\n| `skills`         | No       | List of Octavus skills the LLM can use                    |\n| `references`     | No       | List of references the LLM can fetch on demand            |\n| `sandboxTimeout` | No       | Skill sandbox timeout in ms (default: 5 min, max: 1 hour) |\n| `imageModel`     | No       | Image generation model (enables agentic image generation) |\n| `webSearch`      | No       | Enable built-in web search tool (provider-agnostic)       |\n| `agentic`        | No       | Allow multiple tool call cycles                           |\n| `maxSteps`       | No       | Maximum agentic steps (default: 10)                       |\n| `temperature`    | No       | Model temperature (0-2)                                   |\n| `thinking`       | No       | Extended reasoning level                                  |\n| `anthropic`      | No       | Anthropic-specific options (tools, skills)                |\n\n## Models\n\nSpecify models in `provider/model-id` format. Any model supported by the provider's SDK will work.\n\n### Supported Providers\n\n| Provider  | Format                 | Examples                                                             |\n| --------- | ---------------------- | -------------------------------------------------------------------- |\n| Anthropic | `anthropic/{model-id}` | `claude-opus-4-5`, `claude-sonnet-4-5`, `claude-haiku-4-5`           |\n| Google    | `google/{model-id}`    | `gemini-3-pro-preview`, `gemini-3-flash-preview`, `gemini-2.5-flash` |\n| OpenAI    | `openai/{model-id}`    | `gpt-5`, `gpt-4o`, `o4-mini`, `o3`, `o3-mini`, `o1`                  |\n\n### Examples\n\n```yaml\n# Anthropic Claude 4.5\nagent:\n  model: anthropic/claude-sonnet-4-5\n\n# Google Gemini 3\nagent:\n  model: google/gemini-3-flash-preview\n\n# OpenAI GPT-5\nagent:\n  model: openai/gpt-5\n\n# OpenAI reasoning models\nagent:\n  model: openai/o3-mini\n```\n\n> **Note**: Model IDs are passed directly to the provider SDK. Check the provider's documentation for the latest available models.\n\n### Dynamic Model Selection\n\nThe model field can also reference an input variable, allowing consumers to choose the model when creating a session:\n\n```yaml\ninput:\n  MODEL:\n    type: string\n    description: The LLM model to use\n\nagent:\n  model: MODEL # Resolved from session input\n  system: system\n```\n\nWhen creating a session, pass the model:\n\n```typescript\nconst sessionId = await client.agentSessions.create('my-agent', {\n  MODEL: 'anthropic/claude-sonnet-4-5',\n});\n```\n\nThis enables:\n\n- **Multi-provider support** \u2014 Same agent works with different providers\n- **A/B testing** \u2014 Test different models without protocol changes\n- **User preferences** \u2014 Let users choose their preferred model\n\nThe model value is validated at runtime to ensure it's in the correct `provider/model-id` format.\n\n> **Note**: When using dynamic models, provider-specific options (like `anthropic:`) may not apply if the model resolves to a different provider.\n\n## Backup Model\n\nConfigure a fallback model that activates automatically when the primary model encounters a transient provider error (rate limits, outages, timeouts):\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  backupModel: openai/gpt-4o\n  system: system\n```\n\nWhen a provider error occurs, the system retries once with the backup model. If the backup also fails, the original error is returned.\n\n**Key behaviors:**\n\n- Only transient provider errors trigger fallback \u2014 authentication and validation errors are not retried\n- Provider-specific options (like `anthropic:`) are only forwarded to the backup model if it uses the same provider\n- For streaming responses, fallback only occurs if no content has been sent to the client yet\n\nLike `model`, `backupModel` supports variable references:\n\n```yaml\ninput:\n  BACKUP_MODEL:\n    type: string\n    description: Fallback model for provider errors\n\nagent:\n  model: anthropic/claude-sonnet-4-5\n  backupModel: BACKUP_MODEL\n  system: system\n```\n\n> **Tip**: Use a different provider for your backup model (e.g., primary on Anthropic, backup on OpenAI) to maximize resilience against single-provider outages.\n\n## System Prompt\n\nThe system prompt sets the agent's persona and instructions. The `input` field controls which variables are available to the prompt \u2014 only variables listed in `input` are interpolated.\n\n```yaml\nagent:\n  system: system # Uses prompts/system.md\n  input:\n    - COMPANY_NAME\n    - PRODUCT_NAME\n```\n\nVariables in `input` can come from `protocol.input`, `protocol.resources`, or `protocol.variables`.\n\n### Input Mapping Formats\n\n```yaml\n# Array format (same name)\ninput:\n  - COMPANY_NAME\n  - PRODUCT_NAME\n\n# Array format (rename)\ninput:\n  - CONTEXT: CONVERSATION_SUMMARY  # Prompt sees CONTEXT, value comes from CONVERSATION_SUMMARY\n\n# Object format (rename)\ninput:\n  CONTEXT: CONVERSATION_SUMMARY\n```\n\nThe left side (label) is what the prompt sees. The right side (source) is where the value comes from.\n\n### Example\n\n`prompts/system.md`:\n\n```markdown\nYou are a friendly support agent for {{COMPANY_NAME}}.\n\n## Your Role\n\nHelp users with questions about {{PRODUCT_NAME}}.\n\n## Guidelines\n\n- Be helpful and professional\n- If you can't help, offer to escalate\n- Never share internal information\n```\n\n## Agentic Mode\n\nEnable multi-step tool calling:\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  tools: [get-user-account, search-docs, create-ticket]\n  agentic: true # LLM can call multiple tools\n  maxSteps: 10 # Limit cycles to prevent runaway\n```\n\n**How it works:**\n\n1. LLM receives user message\n2. LLM decides to call a tool\n3. Tool executes, result returned to LLM\n4. LLM decides if more tools needed\n5. Repeat until LLM responds or maxSteps reached\n\n## Extended Thinking\n\nEnable extended reasoning for complex tasks:\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  thinking: medium # low | medium | high\n```\n\n| Level    | Token Budget | Use Case            |\n| -------- | ------------ | ------------------- |\n| `low`    | ~5,000       | Simple reasoning    |\n| `medium` | ~10,000      | Moderate complexity |\n| `high`   | ~20,000      | Complex analysis    |\n\nThinking content streams to the UI and can be displayed to users.\n\n## Skills\n\nEnable Octavus skills for code execution and file generation:\n\n```yaml\nskills:\n  qr-code:\n    display: description\n    description: Generating QR codes\n\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  skills: [qr-code] # Enable skills\n  agentic: true\n```\n\nSkills provide provider-agnostic code execution in isolated sandboxes. When enabled, the LLM can execute Python/Bash code, run skill scripts, and generate files.\n\nSee [Skills](/docs/protocol/skills) for full documentation.\n\n## References\n\nEnable on-demand context loading via reference documents:\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  references: [api-guidelines, error-codes]\n  agentic: true\n```\n\nReferences are markdown files stored in the agent's `references/` directory. When enabled, the LLM can list available references and read their content using `octavus_reference_list` and `octavus_reference_read` tools.\n\nSee [References](/docs/protocol/references) for full documentation.\n\n## Image Generation\n\nEnable the LLM to generate images autonomously:\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  imageModel: google/gemini-2.5-flash-image\n  agentic: true\n```\n\nWhen `imageModel` is configured, the `octavus_generate_image` tool becomes available. The LLM can decide when to generate images based on user requests. The tool supports both text-to-image generation and image editing/transformation using reference images.\n\n### Supported Image Providers\n\n| Provider | Model Types                             | Examples                                                  |\n| -------- | --------------------------------------- | --------------------------------------------------------- |\n| OpenAI   | Dedicated image models                  | `gpt-image-1`                                             |\n| Google   | Gemini native (contains \"image\")        | `gemini-2.5-flash-image`, `gemini-3-flash-image-generate` |\n| Google   | Imagen dedicated (starts with \"imagen\") | `imagen-4.0-generate-001`                                 |\n\n> **Note**: Google has two image generation approaches. Gemini \"native\" models (containing \"image\" in the ID) generate images using the language model API with `responseModalities`. Imagen models (starting with \"imagen\") use a dedicated image generation API.\n\n### Image Sizes\n\nThe tool supports three image sizes:\n\n- `1024x1024` (default) \u2014 Square\n- `1792x1024` \u2014 Landscape (16:9)\n- `1024x1792` \u2014 Portrait (9:16)\n\n### Image Editing with Reference Images\n\nBoth the agentic tool and the `generate-image` block support reference images for editing and transformation. When reference images are provided, the prompt describes how to modify or use those images.\n\n| Provider | Models                           | Reference Image Support |\n| -------- | -------------------------------- | ----------------------- |\n| OpenAI   | `gpt-image-1`                    | Yes                     |\n| Google   | Gemini native (`gemini-*-image`) | Yes                     |\n| Google   | Imagen (`imagen-*`)              | No                      |\n\n### Agentic vs Deterministic\n\nUse `imageModel` in agent config when:\n\n- The LLM should decide when to generate or edit images\n- Users ask for images in natural language\n\nUse `generate-image` block (see [Handlers](/docs/protocol/handlers#generate-image)) when:\n\n- You want explicit control over image generation or editing\n- Building prompt engineering pipelines\n- Images are generated at specific handler steps\n\n## Web Search\n\nEnable the LLM to search the web for current information:\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  webSearch: true\n  agentic: true\n```\n\nWhen `webSearch` is enabled, the `octavus_web_search` tool becomes available. The LLM can decide when to search the web based on the conversation. Search results include source URLs that are emitted as citations in the UI.\n\nThis is a **provider-agnostic** built-in tool \u2014 it works with any LLM provider (Anthropic, Google, OpenAI, etc.). For Anthropic's own web search implementation, see [Provider Options](/docs/protocol/provider-options).\n\nUse cases:\n\n- Current events and real-time data\n- Fact verification and documentation lookups\n- Any information that may have changed since the model's training\n\n## Temperature\n\nControl response randomness:\n\n```yaml\nagent:\n  model: openai/gpt-4o\n  temperature: 0.7 # 0 = deterministic, 2 = creative\n```\n\n**Guidelines:**\n\n- `0 - 0.3`: Factual, consistent responses\n- `0.4 - 0.7`: Balanced (good default)\n- `0.8 - 1.2`: Creative, varied responses\n- `> 1.2`: Very creative (may be inconsistent)\n\n## Provider Options\n\nEnable provider-specific features like Anthropic's built-in tools and skills:\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  anthropic:\n    tools:\n      web-search:\n        display: description\n        description: Searching the web\n    skills:\n      pdf:\n        type: anthropic\n        description: Processing PDF\n```\n\nProvider options are validated against the model\u2014using `anthropic:` with a non-Anthropic model will fail validation.\n\nSee [Provider Options](/docs/protocol/provider-options) for full documentation.\n\n## Thread-Specific Config\n\nOverride config for named threads:\n\n```yaml\nhandlers:\n  request-human:\n    Start summary thread:\n      block: start-thread\n      thread: summary\n      model: anthropic/claude-sonnet-4-5 # Different model\n      backupModel: openai/gpt-4o # Failover model\n      thinking: low # Different thinking\n      maxSteps: 1 # Limit tool calls\n      system: escalation-summary # Different prompt\n      skills: [data-analysis] # Thread-specific skills\n      references: [escalation-policy] # Thread-specific references\n      imageModel: google/gemini-2.5-flash-image # Thread-specific image model\n      webSearch: true # Thread-specific web search\n```\n\nEach thread can have its own model, backup model, skills, references, image model, and web search setting. Skills must be defined in the protocol's `skills:` section. References must exist in the agent's `references/` directory. Workers use this same pattern since they don't have a global `agent:` section.\n\n## Full Example\n\n```yaml\ninput:\n  COMPANY_NAME: { type: string }\n  PRODUCT_NAME: { type: string }\n  USER_ID: { type: string, optional: true }\n\nresources:\n  CONVERSATION_SUMMARY:\n    type: string\n    default: ''\n\ntools:\n  get-user-account:\n    description: Look up user account\n    parameters:\n      userId: { type: string }\n\n  search-docs:\n    description: Search help documentation\n    parameters:\n      query: { type: string }\n\n  create-support-ticket:\n    description: Create a support ticket\n    parameters:\n      summary: { type: string }\n      priority: { type: string } # low, medium, high\n\nskills:\n  qr-code:\n    display: description\n    description: Generating QR codes\n\nagent:\n  model: anthropic/claude-sonnet-4-5\n  backupModel: openai/gpt-4o\n  system: system\n  input:\n    - COMPANY_NAME\n    - PRODUCT_NAME\n  tools:\n    - get-user-account\n    - search-docs\n    - create-support-ticket\n  skills: [qr-code] # Octavus skills\n  references: [support-policies] # On-demand context\n  webSearch: true # Built-in web search\n  agentic: true\n  maxSteps: 10\n  thinking: medium\n  # Anthropic-specific options\n  anthropic:\n    tools:\n      web-search:\n        display: description\n        description: Searching the web\n    skills:\n      pdf:\n        type: anthropic\n        description: Processing PDF\n\ntriggers:\n  user-message:\n    input:\n      USER_MESSAGE: { type: string }\n\nhandlers:\n  user-message:\n    Add message:\n      block: add-message\n      role: user\n      prompt: user-message\n      input: [USER_MESSAGE]\n      display: hidden\n\n    Respond:\n      block: next-message\n```\n",
     excerpt: "Agent Config The  section configures the LLM model, system prompt, tools, and behavior.  Basic Configuration  Configuration Options | Field            | Required | Description                        ...",
     order: 7
   },
@@ -646,6 +655,15 @@ See [Streaming Events](/docs/server-sdk/streaming#event-types) for the full list
     excerpt: "References References are markdown documents that agents can fetch on demand. Instead of loading everything into the system prompt upfront, references let the agent decide what context it needs and...",
     order: 12
   },
+  {
+    slug: "protocol/mcp-servers",
+    section: "protocol",
+    title: "MCP Servers",
+    description: "Connecting agents to external tools via Model Context Protocol (MCP).",
+    content: "\n# MCP Servers\n\nMCP servers extend your agent with tools from external services. Define them in your protocol, and agents automatically discover and use their tools at runtime.\n\nThere are two types of MCP servers:\n\n| Source   | Description                                                          | Example                         |\n| -------- | -------------------------------------------------------------------- | ------------------------------- |\n| `remote` | HTTP-based MCP servers, managed by the platform                      | Figma, Sentry, GitHub           |\n| `device` | Local MCP servers running on the consumer's machine via server-sdk   | Browser automation, filesystem  |\n\n## Defining MCP Servers\n\nMCP servers are defined in the `mcpServers:` section. The key becomes the **namespace** for all tools from that server.\n\n```yaml\nmcpServers:\n  figma:\n    description: Figma design tool integration\n    source: remote\n    display: description\n\n  browser:\n    description: Chrome DevTools browser automation\n    source: device\n    display: name\n```\n\n### Fields\n\n| Field         | Required | Description                                                  |\n| ------------- | -------- | ------------------------------------------------------------ |\n| `description` | Yes      | What the MCP server provides                                 |\n| `source`      | Yes      | `remote` (platform-managed) or `device` (consumer-provided)  |\n| `display`     | No       | How tool calls appear in UI: `hidden`, `name`, `description` |\n\n### Display Modes\n\nDisplay modes control visibility of all tool calls from the MCP server, using the same modes as [regular tools](/docs/protocol/tools#display-modes):\n\n| Mode          | Behavior                                     |\n| ------------- | -------------------------------------------- |\n| `hidden`      | Tool calls run silently                      |\n| `name`        | Shows tool name while executing              |\n| `description` | Shows tool description while executing       |\n\n## Making MCP Servers Available\n\nLike tools, MCP servers defined in `mcpServers:` must be referenced in `agent.mcpServers` to be available:\n\n```yaml\nmcpServers:\n  figma:\n    description: Figma design tool integration\n    source: remote\n    display: description\n\n  sentry:\n    description: Error tracking and debugging\n    source: remote\n    display: name\n\n  browser:\n    description: Chrome DevTools browser automation\n    source: device\n    display: name\n\n  filesystem:\n    description: Filesystem access for reading and writing files\n    source: device\n    display: hidden\n\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  mcpServers: [figma, sentry, browser, filesystem]\n  tools: [set-chat-title]\n  agentic: true\n  maxSteps: 100\n```\n\n## Tool Namespacing\n\nAll MCP tools are automatically namespaced using `__` (double underscore) as a separator. The namespace comes from the `mcpServers` key.\n\nFor example, a server defined as `browser:` that exposes `navigate_page` and `click` produces:\n\n- `browser__navigate_page`\n- `browser__click`\n\nA server defined as `figma:` that exposes `get_design_context` produces:\n\n- `figma__get_design_context`\n\nThe namespace is stripped before calling the MCP server \u2014 the server receives the original tool name. This convention matches Anthropic's MCP integration in Claude Desktop and ensures tool names stay unique across servers.\n\n### What the LLM Sees\n\nWhen an agent has both regular tools and MCP servers configured, the LLM sees all tools combined:\n\n```\nProtocol tools:\n  set-chat-title\n\nRemote MCP tools (auto-discovered):\n  figma__get_design_context\n  figma__get_screenshot\n  sentry__get_issues\n  sentry__get_issue_details\n\nDevice MCP tools (auto-discovered):\n  browser__navigate_page\n  browser__click\n  browser__take_snapshot\n  filesystem__read_file\n  filesystem__write_file\n  filesystem__list_directory\n```\n\nYou don't define individual MCP tool schemas in the protocol \u2014 they're auto-discovered from each MCP server at runtime.\n\n## Remote MCP Servers\n\nRemote MCP servers (`source: remote`) connect to HTTP-based MCP endpoints. The platform manages the connection, authentication, and tool discovery.\n\nConfiguration happens in the Octavus platform UI:\n\n1. Add an MCP server to your project (URL + authentication)\n2. The server's slug must match the namespace in your protocol\n3. The platform connects, discovers tools, and makes them available to the agent\n\n### Authentication\n\nRemote MCP servers support multiple authentication methods:\n\n| Auth Type   | Description                          |\n| ----------- | ------------------------------------ |\n| MCP OAuth   | Standard MCP OAuth flow              |\n| API Key     | Static API key sent as a header      |\n| Bearer      | Bearer token authentication          |\n| None        | No authentication required           |\n\nAuthentication is configured per-project \u2014 different projects can connect to the same MCP server with different credentials.\n\n## Device MCP Servers\n\nDevice MCP servers (`source: device`) run on the consumer's machine. The consumer provides the MCP tools via the `@octavus/computer` package (or any `ToolProvider` implementation) through the server-sdk.\n\nWhen an agent has device MCP servers:\n\n1. The consumer creates a `Computer` with matching namespaces\n2. `@octavus/computer` discovers tools from each MCP server\n3. Tool schemas are sent to the platform via the server-sdk\n4. Tool calls flow back to the consumer for execution\n\nSee [`@octavus/computer`](/docs/server-sdk/computer) for the full integration guide.\n\n### Namespace Matching\n\nThe `mcpServers` keys in the protocol must match the keys in the consumer's `Computer` configuration:\n\n```yaml\n# protocol.yaml\nmcpServers:\n  browser:        # \u2190 must match\n    source: device\n  filesystem:     # \u2190 must match\n    source: device\n```\n\n```typescript\nconst computer = new Computer({\n  mcpServers: {\n    browser: Computer.stdio('chrome-devtools-mcp', ['--browser-url=...']),\n    filesystem: Computer.stdio('@modelcontextprotocol/server-filesystem', [dir]),\n  },\n});\n```\n\nIf the consumer provides a namespace not declared in the protocol, the platform rejects it.\n\n## Thread-Level Scoping\n\nThreads can scope which MCP servers are available, the same way they scope [tools](/docs/protocol/handlers#start-thread):\n\n```yaml\nhandlers:\n  user-message:\n    Start research:\n      block: start-thread\n      thread: research\n      mcpServers: [figma, browser]\n      tools: [set-chat-title]\n      system: research-prompt\n```\n\nThis thread can use Figma and browser tools, but not sentry or filesystem \u2014 even if those are available on the main agent.\n\n## Full Example\n\n```yaml\nmcpServers:\n  figma:\n    description: Figma design tool integration\n    source: remote\n    display: description\n  sentry:\n    description: Error tracking and debugging\n    source: remote\n    display: name\n  browser:\n    description: Chrome DevTools browser automation\n    source: device\n    display: name\n  filesystem:\n    description: Filesystem access for reading and writing files\n    source: device\n    display: hidden\n  shell:\n    description: Shell command execution\n    source: device\n    display: name\n\ntools:\n  set-chat-title:\n    description: Set the title of the current chat.\n    parameters:\n      title: { type: string, description: The title to set }\n\nagent:\n  model: anthropic/claude-opus-4-6\n  system: system\n  mcpServers: [figma, sentry, browser, filesystem, shell]\n  tools: [set-chat-title]\n  thinking: medium\n  maxSteps: 300\n  agentic: true\n\ntriggers:\n  user-message:\n    input:\n      USER_MESSAGE: { type: string }\n\nhandlers:\n  user-message:\n    Add message:\n      block: add-message\n      role: user\n      prompt: user-message\n      input: [USER_MESSAGE]\n      display: hidden\n\n    Respond:\n      block: next-message\n```\n\n### Cloud-Only Agent\n\nAgents that only use remote MCP servers don't need `@octavus/computer`:\n\n```yaml\nmcpServers:\n  figma:\n    description: Figma design tool integration\n    source: remote\n    display: description\n  sentry:\n    description: Error tracking and debugging\n    source: remote\n    display: name\n\ntools:\n  submit-code:\n    description: Submit code to the user.\n    parameters:\n      code: { type: string }\n\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  mcpServers: [figma, sentry]\n  tools: [submit-code]\n  agentic: true\n```\n",
+    excerpt: "MCP Servers MCP servers extend your agent with tools from external services. Define them in your protocol, and agents automatically discover and use their tools at runtime. There are two types of MCP...",
+    order: 13
+  },
   {
     slug: "api-reference/overview",
     section: "api-reference",
@@ -750,7 +768,7 @@ 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:** `2.15.0`\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",
+        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:** `2.16.0`\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
       },
@@ -786,7 +804,7 @@ 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:** `2.15.0`\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',
+        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:** `2.16.0`\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
       },
@@ -807,6 +825,15 @@ var sections_default = [
         content: "\n# Debugging\n\n## Model Request Tracing\n\nModel request tracing captures the full payload sent to model providers (LLM and image) during agent execution. This helps you understand exactly what was sent \u2014 system prompts, messages, tool definitions, and provider options \u2014 making it easier to debug agent behavior.\n\n### Enabling Tracing\n\nEnable tracing by setting `traceModelRequests: true` in the client config:\n\n```typescript\nimport { OctavusClient } from '@octavus/server-sdk';\n\nconst client = new OctavusClient({\n  baseUrl: process.env.OCTAVUS_API_URL!,\n  apiKey: process.env.OCTAVUS_API_KEY!,\n  traceModelRequests: true,\n});\n```\n\nWhen enabled, the SDK sends an `X-Octavus-Trace: true` header with every request. The platform captures the full model request payload before each provider call and stores it in the execution logs.\n\nYou can also drive this from an environment variable for per-environment control:\n\n```typescript\nconst client = new OctavusClient({\n  baseUrl: process.env.OCTAVUS_API_URL!,\n  apiKey: process.env.OCTAVUS_API_KEY!,\n  traceModelRequests: process.env.TRACE_MODEL_REQUESTS === 'true',\n});\n```\n\n### What Gets Captured\n\n**LLM requests** include:\n\n- Full system prompt\n- All messages in AI SDK format (post-conversion)\n- Tool names, descriptions, and JSON schemas\n- Provider-specific options (thinking budgets, etc.)\n- Temperature, max steps, and thinking configuration\n\n**Image generation requests** include:\n\n- Image generation prompt\n- Requested size\n- Whether reference images were provided\n\n### Where Traces Appear\n\nTraces appear as **Model Request** entries in the execution log timeline, alongside existing entries like triggers, tool calls, and responses. Each trace is linked to the block that made the model call.\n\nIn the Octavus dashboard:\n\n- **Session debug view** \u2014 Full execution log with expandable model request entries\n- **Agent preview** \u2014 Activity panel shows model requests in the execution steps\n\nEach entry shows the raw JSON payload with a copy button for easy inspection.\n\n### Storage\n\nTraces are stored in Redis alongside other execution log entries with a 24-hour TTL. They are not permanently stored. A typical LLM trace with 10 messages and 5 tools is 10\u201350KB. Image traces are smaller (just prompt and metadata).\n\n### Recommendations\n\n| Environment | Recommendation                                             |\n| ----------- | ---------------------------------------------------------- |\n| Development | Enable \u2014 helps debug agent behavior during development     |\n| Staging     | Enable \u2014 useful for pre-production testing                 |\n| Production  | Disable (default) \u2014 saves storage for high-volume sessions |\n\n### Preview Sessions\n\nModel request tracing is always enabled for preview sessions in the Octavus dashboard. No configuration needed \u2014 the platform automatically traces all model requests when using the agent preview.\n",
         excerpt: "Debugging  Model Request Tracing Model request tracing captures the full payload sent to model providers (LLM and image) during agent execution. This helps you understand exactly what was sent \u2014...",
         order: 7
+      },
+      {
+        slug: "server-sdk/computer",
+        section: "server-sdk",
+        title: "Computer",
+        description: "Adding browser, filesystem, and shell capabilities to agents with @octavus/computer.",
+        content: "\n# Computer\n\nThe `@octavus/computer` package gives agents access to a physical or virtual machine's browser, filesystem, and shell. It connects to [MCP](https://modelcontextprotocol.io) servers, discovers their tools, and provides them to the server-sdk.\n\n**Current version:** `2.16.0`\n\n## Installation\n\n```bash\nnpm install @octavus/computer\n```\n\n## Quick Start\n\n```typescript\nimport { Computer } from '@octavus/computer';\nimport { OctavusClient } from '@octavus/server-sdk';\n\nconst computer = new Computer({\n  mcpServers: {\n    browser: Computer.stdio('chrome-devtools-mcp', [\n      '--browser-url=http://127.0.0.1:9222',\n    ]),\n    filesystem: Computer.stdio(\n      '@modelcontextprotocol/server-filesystem',\n      ['/path/to/workspace'],\n    ),\n    shell: Computer.shell({ cwd: '/path/to/workspace', mode: 'unrestricted' }),\n  },\n});\n\nawait computer.start();\n\nconst client = new OctavusClient({\n  baseUrl: 'https://octavus.ai',\n  apiKey: 'your-api-key',\n});\n\nconst session = client.agentSessions.attach(sessionId, {\n  tools: { 'set-chat-title': titleHandler },\n  computer,\n});\n```\n\nThe `computer` is passed to `attach()` \u2014 the server-sdk handles the rest. Tool schemas are sent to the platform, and tool calls flow back through the existing execution loop.\n\n## How It Works\n\n1. You configure MCP servers with namespaces (e.g., `browser`, `filesystem`, `shell`)\n2. `computer.start()` connects to all servers in parallel and discovers their tools\n3. Each tool is namespaced with `__` (e.g., `browser__navigate_page`, `filesystem__read_file`)\n4. The server-sdk sends tool schemas to the platform and handles tool call execution\n\nThe agent's protocol must declare matching `mcpServers` with `source: device` \u2014 see [MCP Servers](/docs/protocol/mcp-servers).\n\n## Entry Types\n\nThe `Computer` class supports three types of MCP entries:\n\n### Stdio (MCP Subprocess)\n\nSpawns an MCP server as a child process, communicating via stdin/stdout:\n\n```typescript\nComputer.stdio(command: string, args?: string[], options?: {\n  env?: Record<string, string>;\n  cwd?: string;\n})\n```\n\nUse this for local MCP servers installed as npm packages or standalone executables:\n\n```typescript\nconst computer = new Computer({\n  mcpServers: {\n    browser: Computer.stdio('chrome-devtools-mcp', [\n      '--browser-url=http://127.0.0.1:9222',\n      '--no-usage-statistics',\n    ]),\n    filesystem: Computer.stdio(\n      '@modelcontextprotocol/server-filesystem',\n      ['/Users/me/projects/my-app'],\n    ),\n  },\n});\n```\n\n### HTTP (Remote MCP Endpoint)\n\nConnects to an MCP server over Streamable HTTP:\n\n```typescript\nComputer.http(url: string, options?: {\n  headers?: Record<string, string>;\n})\n```\n\nUse this for MCP servers running as HTTP services:\n\n```typescript\nconst computer = new Computer({\n  mcpServers: {\n    docs: Computer.http('http://localhost:3001/mcp', {\n      headers: { 'Authorization': 'Bearer token' },\n    }),\n  },\n});\n```\n\n### Shell (Built-in)\n\nProvides shell command execution without spawning an MCP subprocess:\n\n```typescript\nComputer.shell(options: {\n  cwd?: string;\n  mode: ShellMode;\n  timeout?: number;  // Default: 300,000ms (5 minutes)\n})\n```\n\nThis exposes a `run_command` tool (namespaced as `shell__run_command` when the key is `shell`). Commands execute in a login shell with the user's full environment.\n\n```typescript\nconst computer = new Computer({\n  mcpServers: {\n    shell: Computer.shell({\n      cwd: '/Users/me/projects/my-app',\n      mode: 'unrestricted',\n      timeout: 300_000,\n    }),\n  },\n});\n```\n\n#### Shell Safety Modes\n\n| Mode                                       | Description                                  |\n| ------------------------------------------ | -------------------------------------------- |\n| `'unrestricted'`                           | All commands allowed (for dedicated machines) |\n| `{ allowedPatterns, blockedPatterns }`      | Pattern-based command filtering               |\n\nPattern-based filtering:\n\n```typescript\nComputer.shell({\n  cwd: workspaceDir,\n  mode: {\n    blockedPatterns: [/rm\\s+-rf/, /sudo/],\n    allowedPatterns: [/^git\\s/, /^npm\\s/, /^ls\\s/],\n  },\n})\n```\n\nWhen `allowedPatterns` is set, only matching commands are permitted. When `blockedPatterns` is set, matching commands are rejected. Blocked patterns are checked first.\n\n## Lifecycle\n\n### Starting\n\n`computer.start()` connects to all configured MCP servers in parallel. If some servers fail to connect, the computer still starts with the remaining servers \u2014 only if *all* connections fail does it throw an error.\n\n```typescript\nconst { errors } = await computer.start();\n\nif (errors.length > 0) {\n  console.warn('Some MCP servers failed to connect:', errors);\n}\n```\n\n### Stopping\n\n`computer.stop()` closes all MCP connections and kills managed processes:\n\n```typescript\nawait computer.stop();\n```\n\nAlways call `stop()` when the session ends to clean up MCP subprocesses. For managed processes (like Chrome), pass them in the config for automatic cleanup.\n\n## Chrome Launch Helper\n\nFor desktop applications that need to control a browser, `Computer.launchChrome()` launches Chrome with remote debugging enabled:\n\n```typescript\nconst browser = await Computer.launchChrome({\n  profileDir: '/Users/me/.my-app/chrome-profiles/agent-1',\n  debuggingPort: 9222, // Optional, auto-allocated if omitted\n  flags: ['--window-size=1280,800'],\n});\n\nconsole.log(`Chrome running on port ${browser.port}, PID ${browser.pid}`);\n```\n\nPass the browser to `managedProcesses` for automatic cleanup when the computer stops:\n\n```typescript\nconst computer = new Computer({\n  mcpServers: {\n    browser: Computer.stdio('chrome-devtools-mcp', [\n      `--browser-url=http://127.0.0.1:${browser.port}`,\n    ]),\n    filesystem: Computer.stdio(\n      '@modelcontextprotocol/server-filesystem',\n      [workspaceDir],\n    ),\n    shell: Computer.shell({ cwd: workspaceDir, mode: 'unrestricted' }),\n  },\n  managedProcesses: [{ process: browser.process }],\n});\n```\n\n### ChromeLaunchOptions\n\n| Field            | Required | Description                                          |\n| ---------------- | -------- | ---------------------------------------------------- |\n| `profileDir`     | Yes      | Directory for Chrome's user data (profile isolation)  |\n| `debuggingPort`  | No       | Port for remote debugging (auto-allocated if omitted) |\n| `flags`          | No       | Additional Chrome launch flags                        |\n\n## ToolProvider Interface\n\n`Computer` implements the `ToolProvider` interface from `@octavus/core`:\n\n```typescript\ninterface ToolProvider {\n  toolHandlers(): Record<string, ToolHandler>;\n  toolSchemas(): ToolSchema[];\n}\n```\n\nThe server-sdk accepts any `ToolProvider` on the `computer` option \u2014 you can implement your own if `@octavus/computer` doesn't fit your use case:\n\n```typescript\nconst customProvider: ToolProvider = {\n  toolHandlers() {\n    return {\n      'custom__my_tool': async (args) => {\n        return { result: 'done' };\n      },\n    };\n  },\n  toolSchemas() {\n    return [\n      {\n        name: 'custom__my_tool',\n        description: 'A custom tool',\n        inputSchema: {\n          type: 'object',\n          properties: {\n            input: { type: 'string', description: 'Tool input' },\n          },\n          required: ['input'],\n        },\n      },\n    ];\n  },\n};\n\nconst session = client.agentSessions.attach(sessionId, {\n  tools: { 'set-chat-title': titleHandler },\n  computer: customProvider,\n});\n```\n\n## Complete Example\n\nA desktop application with browser, filesystem, and shell capabilities:\n\n```typescript\nimport { Computer } from '@octavus/computer';\nimport { OctavusClient } from '@octavus/server-sdk';\n\nconst WORKSPACE_DIR = '/Users/me/projects/my-app';\nconst PROFILE_DIR = '/Users/me/.my-app/chrome-profiles/agent';\n\nasync function startSession(sessionId: string) {\n  // 1. Launch Chrome with remote debugging\n  const browser = await Computer.launchChrome({\n    profileDir: PROFILE_DIR,\n  });\n\n  // 2. Create computer with all capabilities\n  const computer = new Computer({\n    mcpServers: {\n      browser: Computer.stdio('chrome-devtools-mcp', [\n        `--browser-url=http://127.0.0.1:${browser.port}`,\n        '--no-usage-statistics',\n      ]),\n      filesystem: Computer.stdio(\n        '@modelcontextprotocol/server-filesystem',\n        [WORKSPACE_DIR],\n      ),\n      shell: Computer.shell({\n        cwd: WORKSPACE_DIR,\n        mode: 'unrestricted',\n      }),\n    },\n    managedProcesses: [{ process: browser.process }],\n  });\n\n  // 3. Connect to all MCP servers\n  const { errors } = await computer.start();\n  if (errors.length > 0) {\n    console.warn('Failed to connect:', errors);\n  }\n\n  // 4. Attach to session with computer\n  const client = new OctavusClient({\n    baseUrl: process.env.OCTAVUS_API_URL!,\n    apiKey: process.env.OCTAVUS_API_KEY!,\n  });\n\n  const session = client.agentSessions.attach(sessionId, {\n    tools: {\n      'set-chat-title': async (args) => {\n        console.log('Chat title:', args.title);\n        return { success: true };\n      },\n    },\n    computer,\n  });\n\n  // 5. Execute and stream\n  const events = session.execute({\n    type: 'trigger',\n    triggerName: 'user-message',\n    input: { USER_MESSAGE: 'Navigate to github.com and take a screenshot' },\n  });\n\n  for await (const event of events) {\n    // Handle stream events\n  }\n\n  // 6. Clean up\n  await computer.stop();\n}\n```\n\n## API Reference\n\n### Computer\n\n```typescript\nclass Computer implements ToolProvider {\n  constructor(config: ComputerConfig);\n\n  // Static factories for MCP entries\n  static stdio(command: string, args?: string[], options?: {\n    env?: Record<string, string>;\n    cwd?: string;\n  }): StdioConfig;\n\n  static http(url: string, options?: {\n    headers?: Record<string, string>;\n  }): HttpConfig;\n\n  static shell(options: {\n    cwd?: string;\n    mode: ShellMode;\n    timeout?: number;\n  }): ShellConfig;\n\n  // Chrome launch helper\n  static launchChrome(options: ChromeLaunchOptions): Promise<ChromeInstance>;\n\n  // Lifecycle\n  start(): Promise<{ errors: string[] }>;\n  stop(): Promise<void>;\n\n  // ToolProvider implementation\n  toolHandlers(): Record<string, ToolHandler>;\n  toolSchemas(): ToolSchema[];\n}\n```\n\n### ComputerConfig\n\n```typescript\ninterface ComputerConfig {\n  mcpServers: Record<string, McpEntry>;\n  managedProcesses?: { process: ChildProcess }[];\n}\n\ntype McpEntry = StdioConfig | HttpConfig | ShellConfig;\ntype ShellMode = 'unrestricted' | {\n  allowedPatterns?: RegExp[];\n  blockedPatterns?: RegExp[];\n};\n```\n\n### ChromeInstance\n\n```typescript\ninterface ChromeInstance {\n  port: number;\n  process: ChildProcess;\n  pid: number;\n}\n```\n",
+        excerpt: "Computer The  package gives agents access to a physical or virtual machine's browser, filesystem, and shell. It connects to MCP servers, discovers their tools, and provides them to the server-sdk....",
+        order: 8
       }
     ]
   },
@@ -821,7 +848,7 @@ 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:** `2.15.0`\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",
+        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:** `2.16.0`\n\n### Other Frameworks\n\n```bash\nnpm install @octavus/client-sdk\n```\n\n**Current version:** `2.16.0`\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
       },
@@ -1331,7 +1358,7 @@ See [Streaming Events](/docs/server-sdk/streaming#event-types) for the full list
         section: "protocol",
         title: "Handlers",
         description: "Defining execution handlers with blocks.",
-        content: "\n# Handlers\n\nHandlers define what happens when a trigger fires. They contain execution blocks that run in sequence.\n\n## Handler Structure\n\n```yaml\nhandlers:\n  trigger-name:\n    Block Name:\n      block: block-kind\n      # block-specific properties\n\n    Another Block:\n      block: another-kind\n      # ...\n```\n\nEach block has a human-readable name (shown in debug UI) and a `block` field that determines its behavior.\n\n## Block Kinds\n\n### next-message\n\nGenerate a response from the LLM:\n\n```yaml\nhandlers:\n  user-message:\n    Respond to user:\n      block: next-message\n      # Uses main conversation thread by default\n      # Display defaults to 'stream'\n```\n\nWith options:\n\n```yaml\nGenerate summary:\n  block: next-message\n  thread: summary # Use named thread\n  display: stream # Show streaming content\n  independent: true # Don't add to main chat\n  output: SUMMARY # Store output in variable\n  description: Generating summary # Shown in UI\n```\n\nFor structured output (typed JSON response):\n\n```yaml\nRespond with suggestions:\n  block: next-message\n  responseType: ChatResponse # Type defined in types section\n  output: RESPONSE # Stores the parsed object\n```\n\nWhen `responseType` is specified:\n\n- The LLM generates JSON matching the type schema\n- The `output` variable receives the parsed object (not plain text)\n- The client receives a `UIObjectPart` for custom rendering\n\nSee [Types](/docs/protocol/types#structured-output) for more details.\n\n### add-message\n\nAdd a message to the conversation:\n\n```yaml\nAdd user message:\n  block: add-message\n  role: user # user | assistant | system\n  prompt: user-message # Reference to prompt file\n  input: [USER_MESSAGE] # Variables to interpolate\n  display: hidden # Don't show in UI\n```\n\nFor internal directives (LLM sees it, user doesn't):\n\n```yaml\nAdd internal directive:\n  block: add-message\n  role: user\n  prompt: ticket-directive\n  input: [TICKET_DETAILS]\n  visible: false # LLM sees this, user doesn't\n```\n\nFor structured user input (object shown in UI, prompt for LLM context):\n\n```yaml\nAdd user message:\n  block: add-message\n  role: user\n  prompt: user-message # Rendered for LLM context (hidden from UI)\n  input: [USER_INPUT]\n  uiContent: USER_INPUT # Variable shown in UI (object \u2192 object part)\n  display: hidden\n```\n\nWhen `uiContent` is set:\n\n- The variable value is shown in the UI (string \u2192 text part, object \u2192 object part)\n- The prompt text is hidden from the UI but kept for LLM context\n- Useful for rich UI interactions where the visual differs from the LLM context\n\n### tool-call\n\nCall a tool deterministically:\n\n```yaml\nCreate ticket:\n  block: tool-call\n  tool: create-support-ticket\n  input:\n    summary: SUMMARY # Variable reference\n    priority: medium # Literal value\n  output: TICKET # Store result\n```\n\n### set-resource\n\nUpdate a persistent resource:\n\n```yaml\nSave summary:\n  block: set-resource\n  resource: CONVERSATION_SUMMARY\n  value: SUMMARY # Variable to save\n  display: name # Show block name\n```\n\n### start-thread\n\nCreate a named conversation thread:\n\n```yaml\nStart summary thread:\n  block: start-thread\n  thread: summary # Thread name\n  model: anthropic/claude-sonnet-4-5 # Optional: different model\n  thinking: low # Extended reasoning level\n  maxSteps: 1 # Tool call limit\n  system: escalation-summary # System prompt\n  input: [COMPANY_NAME] # Variables for prompt\n  skills: [qr-code] # Octavus skills for this thread\n  sandboxTimeout: 600000 # Skill sandbox timeout (default: 5 min, max: 1 hour)\n  imageModel: google/gemini-2.5-flash-image # Image generation model\n```\n\nThe `model` field can also reference a variable for dynamic model selection:\n\n```yaml\nStart summary thread:\n  block: start-thread\n  thread: summary\n  model: SUMMARY_MODEL # Resolved from input variable\n  system: escalation-summary\n```\n\n### serialize-thread\n\nConvert conversation to text:\n\n```yaml\nSerialize conversation:\n  block: serialize-thread\n  thread: main # Which thread (default: main)\n  format: markdown # markdown | json\n  output: CONVERSATION_TEXT # Variable to store result\n```\n\n### generate-image\n\nGenerate an image from a prompt variable:\n\n```yaml\nGenerate image:\n  block: generate-image\n  prompt: OPTIMIZED_PROMPT # Variable containing the prompt\n  imageModel: google/gemini-2.5-flash-image # Required image model\n  size: 1024x1024 # 1024x1024 | 1792x1024 | 1024x1792\n  output: GENERATED_IMAGE # Store URL in variable\n  description: Generating your image... # Shown in UI\n```\n\nEdit an existing image using reference images:\n\n```yaml\nEdit image:\n  block: generate-image\n  prompt: EDIT_INSTRUCTIONS # e.g., \"Remove the background\"\n  referenceImages: [SOURCE_IMAGE_URL] # Variable(s) containing image URLs\n  imageModel: google/gemini-2.5-flash-image\n  output: EDITED_IMAGE\n  description: Editing image...\n```\n\n| Field             | Required | Description                                                     |\n| ----------------- | -------- | --------------------------------------------------------------- |\n| `prompt`          | Yes      | Variable name containing the image prompt or edit instructions  |\n| `imageModel`      | Yes      | Image model identifier (e.g., `google/gemini-2.5-flash-image`)  |\n| `size`            | No       | Image dimensions: `1024x1024`, `1792x1024`, or `1024x1792`      |\n| `referenceImages` | No       | Variable names containing image URLs for editing/transformation |\n| `output`          | No       | Variable name to store the generated image URL                  |\n| `thread`          | No       | Thread to associate the output file with                        |\n| `description`     | No       | Description shown in the UI during generation                   |\n\nThis block is for deterministic image generation pipelines where the prompt is constructed programmatically (e.g., via prompt engineering in a separate thread). When `referenceImages` are provided, the prompt describes how to modify those images.\n\nFor agentic image generation where the LLM decides when to generate, configure `imageModel` in the [agent config](/docs/protocol/agent-config#image-generation).\n\n## Display Modes\n\nEvery block has a `display` property:\n\n| Mode          | Default For               | Behavior          |\n| ------------- | ------------------------- | ----------------- |\n| `hidden`      | add-message               | Not shown to user |\n| `name`        | set-resource              | Shows block name  |\n| `description` | tool-call, generate-image | Shows description |\n| `stream`      | next-message              | Streams content   |\n\n## Complete Example\n\n```yaml\nhandlers:\n  user-message:\n    # Add the user's message to conversation\n    Add user message:\n      block: add-message\n      role: user\n      prompt: user-message\n      input: [USER_MESSAGE]\n      display: hidden\n\n    # Generate response (LLM may call tools)\n    Respond to user:\n      block: next-message\n      # display: stream (default)\n\n  request-human:\n    # Step 1: Serialize conversation for summary\n    Serialize conversation:\n      block: serialize-thread\n      format: markdown\n      output: CONVERSATION_TEXT\n\n    # Step 2: Create separate thread for summarization\n    Start summary thread:\n      block: start-thread\n      thread: summary\n      model: anthropic/claude-sonnet-4-5\n      thinking: low\n      system: escalation-summary\n      input: [COMPANY_NAME]\n\n    # Step 3: Add request to summary thread\n    Add summarize request:\n      block: add-message\n      thread: summary\n      role: user\n      prompt: summarize-request\n      input:\n        - CONVERSATION: CONVERSATION_TEXT\n\n    # Step 4: Generate summary\n    Generate summary:\n      block: next-message\n      thread: summary\n      display: stream\n      description: Summarizing your conversation\n      independent: true\n      output: SUMMARY\n\n    # Step 5: Save to resource\n    Save summary:\n      block: set-resource\n      resource: CONVERSATION_SUMMARY\n      value: SUMMARY\n\n    # Step 6: Create support ticket\n    Create ticket:\n      block: tool-call\n      tool: create-support-ticket\n      input:\n        summary: SUMMARY\n        priority: medium\n      output: TICKET\n\n    # Step 7: Add directive for response\n    Add directive:\n      block: add-message\n      role: user\n      prompt: ticket-directive\n      input: [TICKET_DETAILS: TICKET]\n      visible: false\n\n    # Step 8: Respond to user\n    Respond:\n      block: next-message\n```\n\n## Block Input Mapping\n\nThe `input` field on blocks controls which variables are passed to the prompt. Only variables listed in `input` are available for interpolation.\n\nVariables can come from `protocol.input`, `protocol.resources`, `protocol.variables`, `trigger.input`, or outputs from prior blocks.\n\n```yaml\n# Array format (same name)\ninput: [USER_MESSAGE, COMPANY_NAME]\n\n# Array format (rename)\ninput:\n  - CONVERSATION: CONVERSATION_TEXT  # Prompt sees CONVERSATION, value comes from CONVERSATION_TEXT\n  - TICKET_DETAILS: TICKET\n\n# Object format (rename)\ninput:\n  CONVERSATION: CONVERSATION_TEXT\n  TICKET_DETAILS: TICKET\n```\n\n## Independent Blocks\n\nUse `independent: true` for content that shouldn't go to the main chat:\n\n```yaml\nGenerate summary:\n  block: next-message\n  thread: summary\n  independent: true # Output stored in variable, not main chat\n  output: SUMMARY\n```\n\nThis is useful for:\n\n- Background processing\n- Summarization in separate threads\n- Generating content for tools\n",
+        content: "\n# Handlers\n\nHandlers define what happens when a trigger fires. They contain execution blocks that run in sequence.\n\n## Handler Structure\n\n```yaml\nhandlers:\n  trigger-name:\n    Block Name:\n      block: block-kind\n      # block-specific properties\n\n    Another Block:\n      block: another-kind\n      # ...\n```\n\nEach block has a human-readable name (shown in debug UI) and a `block` field that determines its behavior.\n\n## Block Kinds\n\n### next-message\n\nGenerate a response from the LLM:\n\n```yaml\nhandlers:\n  user-message:\n    Respond to user:\n      block: next-message\n      # Uses main conversation thread by default\n      # Display defaults to 'stream'\n```\n\nWith options:\n\n```yaml\nGenerate summary:\n  block: next-message\n  thread: summary # Use named thread\n  display: stream # Show streaming content\n  independent: true # Don't add to main chat\n  output: SUMMARY # Store output in variable\n  description: Generating summary # Shown in UI\n```\n\nFor structured output (typed JSON response):\n\n```yaml\nRespond with suggestions:\n  block: next-message\n  responseType: ChatResponse # Type defined in types section\n  output: RESPONSE # Stores the parsed object\n```\n\nWhen `responseType` is specified:\n\n- The LLM generates JSON matching the type schema\n- The `output` variable receives the parsed object (not plain text)\n- The client receives a `UIObjectPart` for custom rendering\n\nSee [Types](/docs/protocol/types#structured-output) for more details.\n\n### add-message\n\nAdd a message to the conversation:\n\n```yaml\nAdd user message:\n  block: add-message\n  role: user # user | assistant | system\n  prompt: user-message # Reference to prompt file\n  input: [USER_MESSAGE] # Variables to interpolate\n  display: hidden # Don't show in UI\n```\n\nFor internal directives (LLM sees it, user doesn't):\n\n```yaml\nAdd internal directive:\n  block: add-message\n  role: user\n  prompt: ticket-directive\n  input: [TICKET_DETAILS]\n  visible: false # LLM sees this, user doesn't\n```\n\nFor structured user input (object shown in UI, prompt for LLM context):\n\n```yaml\nAdd user message:\n  block: add-message\n  role: user\n  prompt: user-message # Rendered for LLM context (hidden from UI)\n  input: [USER_INPUT]\n  uiContent: USER_INPUT # Variable shown in UI (object \u2192 object part)\n  display: hidden\n```\n\nWhen `uiContent` is set:\n\n- The variable value is shown in the UI (string \u2192 text part, object \u2192 object part)\n- The prompt text is hidden from the UI but kept for LLM context\n- Useful for rich UI interactions where the visual differs from the LLM context\n\n### tool-call\n\nCall a tool deterministically:\n\n```yaml\nCreate ticket:\n  block: tool-call\n  tool: create-support-ticket\n  input:\n    summary: SUMMARY # Variable reference\n    priority: medium # Literal value\n  output: TICKET # Store result\n```\n\n### set-resource\n\nUpdate a persistent resource:\n\n```yaml\nSave summary:\n  block: set-resource\n  resource: CONVERSATION_SUMMARY\n  value: SUMMARY # Variable to save\n  display: name # Show block name\n```\n\n### start-thread\n\nCreate a named conversation thread:\n\n```yaml\nStart summary thread:\n  block: start-thread\n  thread: summary # Thread name\n  model: anthropic/claude-sonnet-4-5 # Optional: different model\n  backupModel: openai/gpt-4o # Failover on provider errors\n  thinking: low # Extended reasoning level\n  maxSteps: 1 # Tool call limit\n  system: escalation-summary # System prompt\n  input: [COMPANY_NAME] # Variables for prompt\n  skills: [qr-code] # Octavus skills for this thread\n  sandboxTimeout: 600000 # Skill sandbox timeout (default: 5 min, max: 1 hour)\n  imageModel: google/gemini-2.5-flash-image # Image generation model\n```\n\nThe `model` field can also reference a variable for dynamic model selection. The `backupModel` field follows the same format and supports variable references.\n\n```yaml\nStart summary thread:\n  block: start-thread\n  thread: summary\n  model: SUMMARY_MODEL # Resolved from input variable\n  system: escalation-summary\n```\n\n### serialize-thread\n\nConvert conversation to text:\n\n```yaml\nSerialize conversation:\n  block: serialize-thread\n  thread: main # Which thread (default: main)\n  format: markdown # markdown | json\n  output: CONVERSATION_TEXT # Variable to store result\n```\n\n### generate-image\n\nGenerate an image from a prompt variable:\n\n```yaml\nGenerate image:\n  block: generate-image\n  prompt: OPTIMIZED_PROMPT # Variable containing the prompt\n  imageModel: google/gemini-2.5-flash-image # Required image model\n  size: 1024x1024 # 1024x1024 | 1792x1024 | 1024x1792\n  output: GENERATED_IMAGE # Store URL in variable\n  description: Generating your image... # Shown in UI\n```\n\nEdit an existing image using reference images:\n\n```yaml\nEdit image:\n  block: generate-image\n  prompt: EDIT_INSTRUCTIONS # e.g., \"Remove the background\"\n  referenceImages: [SOURCE_IMAGE_URL] # Variable(s) containing image URLs\n  imageModel: google/gemini-2.5-flash-image\n  output: EDITED_IMAGE\n  description: Editing image...\n```\n\n| Field             | Required | Description                                                     |\n| ----------------- | -------- | --------------------------------------------------------------- |\n| `prompt`          | Yes      | Variable name containing the image prompt or edit instructions  |\n| `imageModel`      | Yes      | Image model identifier (e.g., `google/gemini-2.5-flash-image`)  |\n| `size`            | No       | Image dimensions: `1024x1024`, `1792x1024`, or `1024x1792`      |\n| `referenceImages` | No       | Variable names containing image URLs for editing/transformation |\n| `output`          | No       | Variable name to store the generated image URL                  |\n| `thread`          | No       | Thread to associate the output file with                        |\n| `description`     | No       | Description shown in the UI during generation                   |\n\nThis block is for deterministic image generation pipelines where the prompt is constructed programmatically (e.g., via prompt engineering in a separate thread). When `referenceImages` are provided, the prompt describes how to modify those images.\n\nFor agentic image generation where the LLM decides when to generate, configure `imageModel` in the [agent config](/docs/protocol/agent-config#image-generation).\n\n## Display Modes\n\nEvery block has a `display` property:\n\n| Mode          | Default For               | Behavior          |\n| ------------- | ------------------------- | ----------------- |\n| `hidden`      | add-message               | Not shown to user |\n| `name`        | set-resource              | Shows block name  |\n| `description` | tool-call, generate-image | Shows description |\n| `stream`      | next-message              | Streams content   |\n\n## Complete Example\n\n```yaml\nhandlers:\n  user-message:\n    # Add the user's message to conversation\n    Add user message:\n      block: add-message\n      role: user\n      prompt: user-message\n      input: [USER_MESSAGE]\n      display: hidden\n\n    # Generate response (LLM may call tools)\n    Respond to user:\n      block: next-message\n      # display: stream (default)\n\n  request-human:\n    # Step 1: Serialize conversation for summary\n    Serialize conversation:\n      block: serialize-thread\n      format: markdown\n      output: CONVERSATION_TEXT\n\n    # Step 2: Create separate thread for summarization\n    Start summary thread:\n      block: start-thread\n      thread: summary\n      model: anthropic/claude-sonnet-4-5\n      thinking: low\n      system: escalation-summary\n      input: [COMPANY_NAME]\n\n    # Step 3: Add request to summary thread\n    Add summarize request:\n      block: add-message\n      thread: summary\n      role: user\n      prompt: summarize-request\n      input:\n        - CONVERSATION: CONVERSATION_TEXT\n\n    # Step 4: Generate summary\n    Generate summary:\n      block: next-message\n      thread: summary\n      display: stream\n      description: Summarizing your conversation\n      independent: true\n      output: SUMMARY\n\n    # Step 5: Save to resource\n    Save summary:\n      block: set-resource\n      resource: CONVERSATION_SUMMARY\n      value: SUMMARY\n\n    # Step 6: Create support ticket\n    Create ticket:\n      block: tool-call\n      tool: create-support-ticket\n      input:\n        summary: SUMMARY\n        priority: medium\n      output: TICKET\n\n    # Step 7: Add directive for response\n    Add directive:\n      block: add-message\n      role: user\n      prompt: ticket-directive\n      input: [TICKET_DETAILS: TICKET]\n      visible: false\n\n    # Step 8: Respond to user\n    Respond:\n      block: next-message\n```\n\n## Block Input Mapping\n\nThe `input` field on blocks controls which variables are passed to the prompt. Only variables listed in `input` are available for interpolation.\n\nVariables can come from `protocol.input`, `protocol.resources`, `protocol.variables`, `trigger.input`, or outputs from prior blocks.\n\n```yaml\n# Array format (same name)\ninput: [USER_MESSAGE, COMPANY_NAME]\n\n# Array format (rename)\ninput:\n  - CONVERSATION: CONVERSATION_TEXT  # Prompt sees CONVERSATION, value comes from CONVERSATION_TEXT\n  - TICKET_DETAILS: TICKET\n\n# Object format (rename)\ninput:\n  CONVERSATION: CONVERSATION_TEXT\n  TICKET_DETAILS: TICKET\n```\n\n## Independent Blocks\n\nUse `independent: true` for content that shouldn't go to the main chat:\n\n```yaml\nGenerate summary:\n  block: next-message\n  thread: summary\n  independent: true # Output stored in variable, not main chat\n  output: SUMMARY\n```\n\nThis is useful for:\n\n- Background processing\n- Summarization in separate threads\n- Generating content for tools\n",
         excerpt: "Handlers Handlers define what happens when a trigger fires. They contain execution blocks that run in sequence.  Handler Structure Each block has a human-readable name (shown in debug UI) and a ...",
         order: 6
       },
@@ -1340,7 +1367,7 @@ See [Streaming Events](/docs/server-sdk/streaming#event-types) for the full list
         section: "protocol",
         title: "Agent Config",
         description: "Configuring the agent model and behavior.",
-        content: "\n# Agent Config\n\nThe `agent` section configures the LLM model, system prompt, tools, and behavior.\n\n## Basic Configuration\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system # References prompts/system.md\n  tools: [get-user-account] # Available tools\n  skills: [qr-code] # Available skills\n  references: [api-guidelines] # On-demand context documents\n```\n\n## Configuration Options\n\n| Field            | Required | Description                                               |\n| ---------------- | -------- | --------------------------------------------------------- |\n| `model`          | Yes      | Model identifier or variable reference                    |\n| `system`         | Yes      | System prompt filename (without .md)                      |\n| `input`          | No       | Variables to pass to the system prompt                    |\n| `tools`          | No       | List of tools the LLM can call                            |\n| `skills`         | No       | List of Octavus skills the LLM can use                    |\n| `references`     | No       | List of references the LLM can fetch on demand            |\n| `sandboxTimeout` | No       | Skill sandbox timeout in ms (default: 5 min, max: 1 hour) |\n| `imageModel`     | No       | Image generation model (enables agentic image generation) |\n| `webSearch`      | No       | Enable built-in web search tool (provider-agnostic)       |\n| `agentic`        | No       | Allow multiple tool call cycles                           |\n| `maxSteps`       | No       | Maximum agentic steps (default: 10)                       |\n| `temperature`    | No       | Model temperature (0-2)                                   |\n| `thinking`       | No       | Extended reasoning level                                  |\n| `anthropic`      | No       | Anthropic-specific options (tools, skills)                |\n\n## Models\n\nSpecify models in `provider/model-id` format. Any model supported by the provider's SDK will work.\n\n### Supported Providers\n\n| Provider  | Format                 | Examples                                                             |\n| --------- | ---------------------- | -------------------------------------------------------------------- |\n| Anthropic | `anthropic/{model-id}` | `claude-opus-4-5`, `claude-sonnet-4-5`, `claude-haiku-4-5`           |\n| Google    | `google/{model-id}`    | `gemini-3-pro-preview`, `gemini-3-flash-preview`, `gemini-2.5-flash` |\n| OpenAI    | `openai/{model-id}`    | `gpt-5`, `gpt-4o`, `o4-mini`, `o3`, `o3-mini`, `o1`                  |\n\n### Examples\n\n```yaml\n# Anthropic Claude 4.5\nagent:\n  model: anthropic/claude-sonnet-4-5\n\n# Google Gemini 3\nagent:\n  model: google/gemini-3-flash-preview\n\n# OpenAI GPT-5\nagent:\n  model: openai/gpt-5\n\n# OpenAI reasoning models\nagent:\n  model: openai/o3-mini\n```\n\n> **Note**: Model IDs are passed directly to the provider SDK. Check the provider's documentation for the latest available models.\n\n### Dynamic Model Selection\n\nThe model field can also reference an input variable, allowing consumers to choose the model when creating a session:\n\n```yaml\ninput:\n  MODEL:\n    type: string\n    description: The LLM model to use\n\nagent:\n  model: MODEL # Resolved from session input\n  system: system\n```\n\nWhen creating a session, pass the model:\n\n```typescript\nconst sessionId = await client.agentSessions.create('my-agent', {\n  MODEL: 'anthropic/claude-sonnet-4-5',\n});\n```\n\nThis enables:\n\n- **Multi-provider support** \u2014 Same agent works with different providers\n- **A/B testing** \u2014 Test different models without protocol changes\n- **User preferences** \u2014 Let users choose their preferred model\n\nThe model value is validated at runtime to ensure it's in the correct `provider/model-id` format.\n\n> **Note**: When using dynamic models, provider-specific options (like `anthropic:`) may not apply if the model resolves to a different provider.\n\n## System Prompt\n\nThe system prompt sets the agent's persona and instructions. The `input` field controls which variables are available to the prompt \u2014 only variables listed in `input` are interpolated.\n\n```yaml\nagent:\n  system: system # Uses prompts/system.md\n  input:\n    - COMPANY_NAME\n    - PRODUCT_NAME\n```\n\nVariables in `input` can come from `protocol.input`, `protocol.resources`, or `protocol.variables`.\n\n### Input Mapping Formats\n\n```yaml\n# Array format (same name)\ninput:\n  - COMPANY_NAME\n  - PRODUCT_NAME\n\n# Array format (rename)\ninput:\n  - CONTEXT: CONVERSATION_SUMMARY  # Prompt sees CONTEXT, value comes from CONVERSATION_SUMMARY\n\n# Object format (rename)\ninput:\n  CONTEXT: CONVERSATION_SUMMARY\n```\n\nThe left side (label) is what the prompt sees. The right side (source) is where the value comes from.\n\n### Example\n\n`prompts/system.md`:\n\n```markdown\nYou are a friendly support agent for {{COMPANY_NAME}}.\n\n## Your Role\n\nHelp users with questions about {{PRODUCT_NAME}}.\n\n## Guidelines\n\n- Be helpful and professional\n- If you can't help, offer to escalate\n- Never share internal information\n```\n\n## Agentic Mode\n\nEnable multi-step tool calling:\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  tools: [get-user-account, search-docs, create-ticket]\n  agentic: true # LLM can call multiple tools\n  maxSteps: 10 # Limit cycles to prevent runaway\n```\n\n**How it works:**\n\n1. LLM receives user message\n2. LLM decides to call a tool\n3. Tool executes, result returned to LLM\n4. LLM decides if more tools needed\n5. Repeat until LLM responds or maxSteps reached\n\n## Extended Thinking\n\nEnable extended reasoning for complex tasks:\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  thinking: medium # low | medium | high\n```\n\n| Level    | Token Budget | Use Case            |\n| -------- | ------------ | ------------------- |\n| `low`    | ~5,000       | Simple reasoning    |\n| `medium` | ~10,000      | Moderate complexity |\n| `high`   | ~20,000      | Complex analysis    |\n\nThinking content streams to the UI and can be displayed to users.\n\n## Skills\n\nEnable Octavus skills for code execution and file generation:\n\n```yaml\nskills:\n  qr-code:\n    display: description\n    description: Generating QR codes\n\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  skills: [qr-code] # Enable skills\n  agentic: true\n```\n\nSkills provide provider-agnostic code execution in isolated sandboxes. When enabled, the LLM can execute Python/Bash code, run skill scripts, and generate files.\n\nSee [Skills](/docs/protocol/skills) for full documentation.\n\n## References\n\nEnable on-demand context loading via reference documents:\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  references: [api-guidelines, error-codes]\n  agentic: true\n```\n\nReferences are markdown files stored in the agent's `references/` directory. When enabled, the LLM can list available references and read their content using `octavus_reference_list` and `octavus_reference_read` tools.\n\nSee [References](/docs/protocol/references) for full documentation.\n\n## Image Generation\n\nEnable the LLM to generate images autonomously:\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  imageModel: google/gemini-2.5-flash-image\n  agentic: true\n```\n\nWhen `imageModel` is configured, the `octavus_generate_image` tool becomes available. The LLM can decide when to generate images based on user requests. The tool supports both text-to-image generation and image editing/transformation using reference images.\n\n### Supported Image Providers\n\n| Provider | Model Types                             | Examples                                                  |\n| -------- | --------------------------------------- | --------------------------------------------------------- |\n| OpenAI   | Dedicated image models                  | `gpt-image-1`                                             |\n| Google   | Gemini native (contains \"image\")        | `gemini-2.5-flash-image`, `gemini-3-flash-image-generate` |\n| Google   | Imagen dedicated (starts with \"imagen\") | `imagen-4.0-generate-001`                                 |\n\n> **Note**: Google has two image generation approaches. Gemini \"native\" models (containing \"image\" in the ID) generate images using the language model API with `responseModalities`. Imagen models (starting with \"imagen\") use a dedicated image generation API.\n\n### Image Sizes\n\nThe tool supports three image sizes:\n\n- `1024x1024` (default) \u2014 Square\n- `1792x1024` \u2014 Landscape (16:9)\n- `1024x1792` \u2014 Portrait (9:16)\n\n### Image Editing with Reference Images\n\nBoth the agentic tool and the `generate-image` block support reference images for editing and transformation. When reference images are provided, the prompt describes how to modify or use those images.\n\n| Provider | Models                           | Reference Image Support |\n| -------- | -------------------------------- | ----------------------- |\n| OpenAI   | `gpt-image-1`                    | Yes                     |\n| Google   | Gemini native (`gemini-*-image`) | Yes                     |\n| Google   | Imagen (`imagen-*`)              | No                      |\n\n### Agentic vs Deterministic\n\nUse `imageModel` in agent config when:\n\n- The LLM should decide when to generate or edit images\n- Users ask for images in natural language\n\nUse `generate-image` block (see [Handlers](/docs/protocol/handlers#generate-image)) when:\n\n- You want explicit control over image generation or editing\n- Building prompt engineering pipelines\n- Images are generated at specific handler steps\n\n## Web Search\n\nEnable the LLM to search the web for current information:\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  webSearch: true\n  agentic: true\n```\n\nWhen `webSearch` is enabled, the `octavus_web_search` tool becomes available. The LLM can decide when to search the web based on the conversation. Search results include source URLs that are emitted as citations in the UI.\n\nThis is a **provider-agnostic** built-in tool \u2014 it works with any LLM provider (Anthropic, Google, OpenAI, etc.). For Anthropic's own web search implementation, see [Provider Options](/docs/protocol/provider-options).\n\nUse cases:\n\n- Current events and real-time data\n- Fact verification and documentation lookups\n- Any information that may have changed since the model's training\n\n## Temperature\n\nControl response randomness:\n\n```yaml\nagent:\n  model: openai/gpt-4o\n  temperature: 0.7 # 0 = deterministic, 2 = creative\n```\n\n**Guidelines:**\n\n- `0 - 0.3`: Factual, consistent responses\n- `0.4 - 0.7`: Balanced (good default)\n- `0.8 - 1.2`: Creative, varied responses\n- `> 1.2`: Very creative (may be inconsistent)\n\n## Provider Options\n\nEnable provider-specific features like Anthropic's built-in tools and skills:\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  anthropic:\n    tools:\n      web-search:\n        display: description\n        description: Searching the web\n    skills:\n      pdf:\n        type: anthropic\n        description: Processing PDF\n```\n\nProvider options are validated against the model\u2014using `anthropic:` with a non-Anthropic model will fail validation.\n\nSee [Provider Options](/docs/protocol/provider-options) for full documentation.\n\n## Thread-Specific Config\n\nOverride config for named threads:\n\n```yaml\nhandlers:\n  request-human:\n    Start summary thread:\n      block: start-thread\n      thread: summary\n      model: anthropic/claude-sonnet-4-5 # Different model\n      thinking: low # Different thinking\n      maxSteps: 1 # Limit tool calls\n      system: escalation-summary # Different prompt\n      skills: [data-analysis] # Thread-specific skills\n      references: [escalation-policy] # Thread-specific references\n      imageModel: google/gemini-2.5-flash-image # Thread-specific image model\n      webSearch: true # Thread-specific web search\n```\n\nEach thread can have its own skills, references, image model, and web search setting. Skills must be defined in the protocol's `skills:` section. References must exist in the agent's `references/` directory. Workers use this same pattern since they don't have a global `agent:` section.\n\n## Full Example\n\n```yaml\ninput:\n  COMPANY_NAME: { type: string }\n  PRODUCT_NAME: { type: string }\n  USER_ID: { type: string, optional: true }\n\nresources:\n  CONVERSATION_SUMMARY:\n    type: string\n    default: ''\n\ntools:\n  get-user-account:\n    description: Look up user account\n    parameters:\n      userId: { type: string }\n\n  search-docs:\n    description: Search help documentation\n    parameters:\n      query: { type: string }\n\n  create-support-ticket:\n    description: Create a support ticket\n    parameters:\n      summary: { type: string }\n      priority: { type: string } # low, medium, high\n\nskills:\n  qr-code:\n    display: description\n    description: Generating QR codes\n\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  input:\n    - COMPANY_NAME\n    - PRODUCT_NAME\n  tools:\n    - get-user-account\n    - search-docs\n    - create-support-ticket\n  skills: [qr-code] # Octavus skills\n  references: [support-policies] # On-demand context\n  webSearch: true # Built-in web search\n  agentic: true\n  maxSteps: 10\n  thinking: medium\n  # Anthropic-specific options\n  anthropic:\n    tools:\n      web-search:\n        display: description\n        description: Searching the web\n    skills:\n      pdf:\n        type: anthropic\n        description: Processing PDF\n\ntriggers:\n  user-message:\n    input:\n      USER_MESSAGE: { type: string }\n\nhandlers:\n  user-message:\n    Add message:\n      block: add-message\n      role: user\n      prompt: user-message\n      input: [USER_MESSAGE]\n      display: hidden\n\n    Respond:\n      block: next-message\n```\n",
+        content: "\n# Agent Config\n\nThe `agent` section configures the LLM model, system prompt, tools, and behavior.\n\n## Basic Configuration\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system # References prompts/system.md\n  tools: [get-user-account] # Available tools\n  skills: [qr-code] # Available skills\n  references: [api-guidelines] # On-demand context documents\n```\n\n## Configuration Options\n\n| Field            | Required | Description                                               |\n| ---------------- | -------- | --------------------------------------------------------- |\n| `model`          | Yes      | Model identifier or variable reference                    |\n| `backupModel`    | No       | Backup model for automatic failover on provider errors    |\n| `system`         | Yes      | System prompt filename (without .md)                      |\n| `input`          | No       | Variables to pass to the system prompt                    |\n| `tools`          | No       | List of tools the LLM can call                            |\n| `skills`         | No       | List of Octavus skills the LLM can use                    |\n| `references`     | No       | List of references the LLM can fetch on demand            |\n| `sandboxTimeout` | No       | Skill sandbox timeout in ms (default: 5 min, max: 1 hour) |\n| `imageModel`     | No       | Image generation model (enables agentic image generation) |\n| `webSearch`      | No       | Enable built-in web search tool (provider-agnostic)       |\n| `agentic`        | No       | Allow multiple tool call cycles                           |\n| `maxSteps`       | No       | Maximum agentic steps (default: 10)                       |\n| `temperature`    | No       | Model temperature (0-2)                                   |\n| `thinking`       | No       | Extended reasoning level                                  |\n| `anthropic`      | No       | Anthropic-specific options (tools, skills)                |\n\n## Models\n\nSpecify models in `provider/model-id` format. Any model supported by the provider's SDK will work.\n\n### Supported Providers\n\n| Provider  | Format                 | Examples                                                             |\n| --------- | ---------------------- | -------------------------------------------------------------------- |\n| Anthropic | `anthropic/{model-id}` | `claude-opus-4-5`, `claude-sonnet-4-5`, `claude-haiku-4-5`           |\n| Google    | `google/{model-id}`    | `gemini-3-pro-preview`, `gemini-3-flash-preview`, `gemini-2.5-flash` |\n| OpenAI    | `openai/{model-id}`    | `gpt-5`, `gpt-4o`, `o4-mini`, `o3`, `o3-mini`, `o1`                  |\n\n### Examples\n\n```yaml\n# Anthropic Claude 4.5\nagent:\n  model: anthropic/claude-sonnet-4-5\n\n# Google Gemini 3\nagent:\n  model: google/gemini-3-flash-preview\n\n# OpenAI GPT-5\nagent:\n  model: openai/gpt-5\n\n# OpenAI reasoning models\nagent:\n  model: openai/o3-mini\n```\n\n> **Note**: Model IDs are passed directly to the provider SDK. Check the provider's documentation for the latest available models.\n\n### Dynamic Model Selection\n\nThe model field can also reference an input variable, allowing consumers to choose the model when creating a session:\n\n```yaml\ninput:\n  MODEL:\n    type: string\n    description: The LLM model to use\n\nagent:\n  model: MODEL # Resolved from session input\n  system: system\n```\n\nWhen creating a session, pass the model:\n\n```typescript\nconst sessionId = await client.agentSessions.create('my-agent', {\n  MODEL: 'anthropic/claude-sonnet-4-5',\n});\n```\n\nThis enables:\n\n- **Multi-provider support** \u2014 Same agent works with different providers\n- **A/B testing** \u2014 Test different models without protocol changes\n- **User preferences** \u2014 Let users choose their preferred model\n\nThe model value is validated at runtime to ensure it's in the correct `provider/model-id` format.\n\n> **Note**: When using dynamic models, provider-specific options (like `anthropic:`) may not apply if the model resolves to a different provider.\n\n## Backup Model\n\nConfigure a fallback model that activates automatically when the primary model encounters a transient provider error (rate limits, outages, timeouts):\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  backupModel: openai/gpt-4o\n  system: system\n```\n\nWhen a provider error occurs, the system retries once with the backup model. If the backup also fails, the original error is returned.\n\n**Key behaviors:**\n\n- Only transient provider errors trigger fallback \u2014 authentication and validation errors are not retried\n- Provider-specific options (like `anthropic:`) are only forwarded to the backup model if it uses the same provider\n- For streaming responses, fallback only occurs if no content has been sent to the client yet\n\nLike `model`, `backupModel` supports variable references:\n\n```yaml\ninput:\n  BACKUP_MODEL:\n    type: string\n    description: Fallback model for provider errors\n\nagent:\n  model: anthropic/claude-sonnet-4-5\n  backupModel: BACKUP_MODEL\n  system: system\n```\n\n> **Tip**: Use a different provider for your backup model (e.g., primary on Anthropic, backup on OpenAI) to maximize resilience against single-provider outages.\n\n## System Prompt\n\nThe system prompt sets the agent's persona and instructions. The `input` field controls which variables are available to the prompt \u2014 only variables listed in `input` are interpolated.\n\n```yaml\nagent:\n  system: system # Uses prompts/system.md\n  input:\n    - COMPANY_NAME\n    - PRODUCT_NAME\n```\n\nVariables in `input` can come from `protocol.input`, `protocol.resources`, or `protocol.variables`.\n\n### Input Mapping Formats\n\n```yaml\n# Array format (same name)\ninput:\n  - COMPANY_NAME\n  - PRODUCT_NAME\n\n# Array format (rename)\ninput:\n  - CONTEXT: CONVERSATION_SUMMARY  # Prompt sees CONTEXT, value comes from CONVERSATION_SUMMARY\n\n# Object format (rename)\ninput:\n  CONTEXT: CONVERSATION_SUMMARY\n```\n\nThe left side (label) is what the prompt sees. The right side (source) is where the value comes from.\n\n### Example\n\n`prompts/system.md`:\n\n```markdown\nYou are a friendly support agent for {{COMPANY_NAME}}.\n\n## Your Role\n\nHelp users with questions about {{PRODUCT_NAME}}.\n\n## Guidelines\n\n- Be helpful and professional\n- If you can't help, offer to escalate\n- Never share internal information\n```\n\n## Agentic Mode\n\nEnable multi-step tool calling:\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  tools: [get-user-account, search-docs, create-ticket]\n  agentic: true # LLM can call multiple tools\n  maxSteps: 10 # Limit cycles to prevent runaway\n```\n\n**How it works:**\n\n1. LLM receives user message\n2. LLM decides to call a tool\n3. Tool executes, result returned to LLM\n4. LLM decides if more tools needed\n5. Repeat until LLM responds or maxSteps reached\n\n## Extended Thinking\n\nEnable extended reasoning for complex tasks:\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  thinking: medium # low | medium | high\n```\n\n| Level    | Token Budget | Use Case            |\n| -------- | ------------ | ------------------- |\n| `low`    | ~5,000       | Simple reasoning    |\n| `medium` | ~10,000      | Moderate complexity |\n| `high`   | ~20,000      | Complex analysis    |\n\nThinking content streams to the UI and can be displayed to users.\n\n## Skills\n\nEnable Octavus skills for code execution and file generation:\n\n```yaml\nskills:\n  qr-code:\n    display: description\n    description: Generating QR codes\n\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  skills: [qr-code] # Enable skills\n  agentic: true\n```\n\nSkills provide provider-agnostic code execution in isolated sandboxes. When enabled, the LLM can execute Python/Bash code, run skill scripts, and generate files.\n\nSee [Skills](/docs/protocol/skills) for full documentation.\n\n## References\n\nEnable on-demand context loading via reference documents:\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  references: [api-guidelines, error-codes]\n  agentic: true\n```\n\nReferences are markdown files stored in the agent's `references/` directory. When enabled, the LLM can list available references and read their content using `octavus_reference_list` and `octavus_reference_read` tools.\n\nSee [References](/docs/protocol/references) for full documentation.\n\n## Image Generation\n\nEnable the LLM to generate images autonomously:\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  imageModel: google/gemini-2.5-flash-image\n  agentic: true\n```\n\nWhen `imageModel` is configured, the `octavus_generate_image` tool becomes available. The LLM can decide when to generate images based on user requests. The tool supports both text-to-image generation and image editing/transformation using reference images.\n\n### Supported Image Providers\n\n| Provider | Model Types                             | Examples                                                  |\n| -------- | --------------------------------------- | --------------------------------------------------------- |\n| OpenAI   | Dedicated image models                  | `gpt-image-1`                                             |\n| Google   | Gemini native (contains \"image\")        | `gemini-2.5-flash-image`, `gemini-3-flash-image-generate` |\n| Google   | Imagen dedicated (starts with \"imagen\") | `imagen-4.0-generate-001`                                 |\n\n> **Note**: Google has two image generation approaches. Gemini \"native\" models (containing \"image\" in the ID) generate images using the language model API with `responseModalities`. Imagen models (starting with \"imagen\") use a dedicated image generation API.\n\n### Image Sizes\n\nThe tool supports three image sizes:\n\n- `1024x1024` (default) \u2014 Square\n- `1792x1024` \u2014 Landscape (16:9)\n- `1024x1792` \u2014 Portrait (9:16)\n\n### Image Editing with Reference Images\n\nBoth the agentic tool and the `generate-image` block support reference images for editing and transformation. When reference images are provided, the prompt describes how to modify or use those images.\n\n| Provider | Models                           | Reference Image Support |\n| -------- | -------------------------------- | ----------------------- |\n| OpenAI   | `gpt-image-1`                    | Yes                     |\n| Google   | Gemini native (`gemini-*-image`) | Yes                     |\n| Google   | Imagen (`imagen-*`)              | No                      |\n\n### Agentic vs Deterministic\n\nUse `imageModel` in agent config when:\n\n- The LLM should decide when to generate or edit images\n- Users ask for images in natural language\n\nUse `generate-image` block (see [Handlers](/docs/protocol/handlers#generate-image)) when:\n\n- You want explicit control over image generation or editing\n- Building prompt engineering pipelines\n- Images are generated at specific handler steps\n\n## Web Search\n\nEnable the LLM to search the web for current information:\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  webSearch: true\n  agentic: true\n```\n\nWhen `webSearch` is enabled, the `octavus_web_search` tool becomes available. The LLM can decide when to search the web based on the conversation. Search results include source URLs that are emitted as citations in the UI.\n\nThis is a **provider-agnostic** built-in tool \u2014 it works with any LLM provider (Anthropic, Google, OpenAI, etc.). For Anthropic's own web search implementation, see [Provider Options](/docs/protocol/provider-options).\n\nUse cases:\n\n- Current events and real-time data\n- Fact verification and documentation lookups\n- Any information that may have changed since the model's training\n\n## Temperature\n\nControl response randomness:\n\n```yaml\nagent:\n  model: openai/gpt-4o\n  temperature: 0.7 # 0 = deterministic, 2 = creative\n```\n\n**Guidelines:**\n\n- `0 - 0.3`: Factual, consistent responses\n- `0.4 - 0.7`: Balanced (good default)\n- `0.8 - 1.2`: Creative, varied responses\n- `> 1.2`: Very creative (may be inconsistent)\n\n## Provider Options\n\nEnable provider-specific features like Anthropic's built-in tools and skills:\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  anthropic:\n    tools:\n      web-search:\n        display: description\n        description: Searching the web\n    skills:\n      pdf:\n        type: anthropic\n        description: Processing PDF\n```\n\nProvider options are validated against the model\u2014using `anthropic:` with a non-Anthropic model will fail validation.\n\nSee [Provider Options](/docs/protocol/provider-options) for full documentation.\n\n## Thread-Specific Config\n\nOverride config for named threads:\n\n```yaml\nhandlers:\n  request-human:\n    Start summary thread:\n      block: start-thread\n      thread: summary\n      model: anthropic/claude-sonnet-4-5 # Different model\n      backupModel: openai/gpt-4o # Failover model\n      thinking: low # Different thinking\n      maxSteps: 1 # Limit tool calls\n      system: escalation-summary # Different prompt\n      skills: [data-analysis] # Thread-specific skills\n      references: [escalation-policy] # Thread-specific references\n      imageModel: google/gemini-2.5-flash-image # Thread-specific image model\n      webSearch: true # Thread-specific web search\n```\n\nEach thread can have its own model, backup model, skills, references, image model, and web search setting. Skills must be defined in the protocol's `skills:` section. References must exist in the agent's `references/` directory. Workers use this same pattern since they don't have a global `agent:` section.\n\n## Full Example\n\n```yaml\ninput:\n  COMPANY_NAME: { type: string }\n  PRODUCT_NAME: { type: string }\n  USER_ID: { type: string, optional: true }\n\nresources:\n  CONVERSATION_SUMMARY:\n    type: string\n    default: ''\n\ntools:\n  get-user-account:\n    description: Look up user account\n    parameters:\n      userId: { type: string }\n\n  search-docs:\n    description: Search help documentation\n    parameters:\n      query: { type: string }\n\n  create-support-ticket:\n    description: Create a support ticket\n    parameters:\n      summary: { type: string }\n      priority: { type: string } # low, medium, high\n\nskills:\n  qr-code:\n    display: description\n    description: Generating QR codes\n\nagent:\n  model: anthropic/claude-sonnet-4-5\n  backupModel: openai/gpt-4o\n  system: system\n  input:\n    - COMPANY_NAME\n    - PRODUCT_NAME\n  tools:\n    - get-user-account\n    - search-docs\n    - create-support-ticket\n  skills: [qr-code] # Octavus skills\n  references: [support-policies] # On-demand context\n  webSearch: true # Built-in web search\n  agentic: true\n  maxSteps: 10\n  thinking: medium\n  # Anthropic-specific options\n  anthropic:\n    tools:\n      web-search:\n        display: description\n        description: Searching the web\n    skills:\n      pdf:\n        type: anthropic\n        description: Processing PDF\n\ntriggers:\n  user-message:\n    input:\n      USER_MESSAGE: { type: string }\n\nhandlers:\n  user-message:\n    Add message:\n      block: add-message\n      role: user\n      prompt: user-message\n      input: [USER_MESSAGE]\n      display: hidden\n\n    Respond:\n      block: next-message\n```\n",
         excerpt: "Agent Config The  section configures the LLM model, system prompt, tools, and behavior.  Basic Configuration  Configuration Options | Field            | Required | Description                        ...",
         order: 7
       },
@@ -1388,6 +1415,15 @@ See [Streaming Events](/docs/server-sdk/streaming#event-types) for the full list
         content: "\n# References\n\nReferences are markdown documents that agents can fetch on demand. Instead of loading everything into the system prompt upfront, references let the agent decide what context it needs and load it when relevant.\n\n## Overview\n\nReferences are useful for:\n\n- **Large context** \u2014 Documents too long to include in every system prompt\n- **Selective loading** \u2014 Let the agent decide which context is relevant\n- **Shared knowledge** \u2014 Reusable documents across threads\n\n### How References Work\n\n1. **Definition**: Reference files live in the `references/` directory alongside your agent\n2. **Configuration**: List available references in `agent.references` or `start-thread.references`\n3. **Discovery**: The agent sees reference names and descriptions in its system prompt\n4. **Fetching**: The agent calls reference tools to read the full content when needed\n\n## Creating References\n\nEach reference is a markdown file with YAML frontmatter in the `references/` directory:\n\n```\nmy-agent/\n\u251C\u2500\u2500 settings.json\n\u251C\u2500\u2500 protocol.yaml\n\u251C\u2500\u2500 prompts/\n\u2502   \u2514\u2500\u2500 system.md\n\u2514\u2500\u2500 references/\n    \u251C\u2500\u2500 api-guidelines.md\n    \u2514\u2500\u2500 error-codes.md\n```\n\n### Reference Format\n\n```markdown\n---\ndescription: >\n  API design guidelines including naming conventions,\n  error handling patterns, and pagination standards.\n---\n\n# API Guidelines\n\n## Naming Conventions\n\nUse lowercase with dashes for URL paths...\n\n## Error Handling\n\nAll errors return a standard error envelope...\n```\n\nThe `description` field is required. It tells the agent what the reference contains so it can decide when to fetch it.\n\n### Naming Convention\n\nReference filenames use `lowercase-with-dashes`:\n\n- `api-guidelines.md`\n- `error-codes.md`\n- `coding-standards.md`\n\nThe filename (without `.md`) becomes the reference name used in the protocol.\n\n## Enabling References\n\nAfter creating reference files, specify which references are available in the protocol.\n\n### Interactive Agents\n\nList references in `agent.references`:\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  references: [api-guidelines, error-codes]\n  agentic: true\n```\n\n### Workers and Named Threads\n\nList references per-thread in `start-thread.references`:\n\n```yaml\nsteps:\n  Start thread:\n    block: start-thread\n    thread: worker\n    model: anthropic/claude-sonnet-4-5\n    system: system\n    references: [api-guidelines]\n    maxSteps: 10\n```\n\nDifferent threads can have different references.\n\n## Reference Tools\n\nWhen references are enabled, the agent has access to two tools:\n\n| Tool                     | Purpose                                         |\n| ------------------------ | ----------------------------------------------- |\n| `octavus_reference_list` | List all available references with descriptions |\n| `octavus_reference_read` | Read the full content of a specific reference   |\n\nThe agent also sees reference names and descriptions in its system prompt, so it knows what's available without calling `octavus_reference_list`.\n\n## Example\n\n```yaml\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  tools: [review-pull-request]\n  references: [coding-standards, api-guidelines]\n  agentic: true\n\nhandlers:\n  user-message:\n    Add message:\n      block: add-message\n      role: user\n      prompt: user-message\n      input: [USER_MESSAGE]\n\n    Respond:\n      block: next-message\n```\n\nWith `references/coding-standards.md`:\n\n```markdown\n---\ndescription: >\n  Team coding standards including naming conventions,\n  code organization, and review checklist.\n---\n\n# Coding Standards\n\n## Naming Conventions\n\n- Files: kebab-case\n- Variables: camelCase\n- Constants: UPPER_SNAKE_CASE\n  ...\n```\n\nWhen a user asks the agent to review code, the agent will:\n\n1. See \"coding-standards\" and \"api-guidelines\" in its system prompt\n2. Decide which references are relevant to the review\n3. Call `octavus_reference_read` to load the relevant reference\n4. Use the loaded context to provide an informed review\n\n## Validation\n\nThe CLI and platform validate references during sync and deployment:\n\n- **Undefined references** \u2014 Referencing a name that doesn't have a matching file in `references/`\n- **Unused references** \u2014 A reference file exists but isn't listed in any `agent.references` or `start-thread.references`\n- **Invalid names** \u2014 Names that don't follow the `lowercase-with-dashes` convention\n- **Missing description** \u2014 Reference files without the required `description` in frontmatter\n\n## References vs Skills\n\n| Aspect        | References                    | Skills                          |\n| ------------- | ----------------------------- | ------------------------------- |\n| **Purpose**   | On-demand context documents   | Code execution and file output  |\n| **Content**   | Markdown text                 | Documentation + scripts         |\n| **Execution** | Synchronous text retrieval    | Sandboxed code execution (E2B)  |\n| **Scope**     | Per-agent (stored with agent) | Per-organization (shared)       |\n| **Tools**     | List and read (2 tools)       | Read, list, run, code (6 tools) |\n\nUse **references** when the agent needs access to text-based knowledge. Use **skills** when the agent needs to execute code or generate files.\n\n## Next Steps\n\n- [Agent Config](/docs/protocol/agent-config) \u2014 Configuring references in agent settings\n- [Skills](/docs/protocol/skills) \u2014 Code execution and knowledge packages\n- [Workers](/docs/protocol/workers) \u2014 Using references in worker agents\n",
         excerpt: "References References are markdown documents that agents can fetch on demand. Instead of loading everything into the system prompt upfront, references let the agent decide what context it needs and...",
         order: 12
+      },
+      {
+        slug: "protocol/mcp-servers",
+        section: "protocol",
+        title: "MCP Servers",
+        description: "Connecting agents to external tools via Model Context Protocol (MCP).",
+        content: "\n# MCP Servers\n\nMCP servers extend your agent with tools from external services. Define them in your protocol, and agents automatically discover and use their tools at runtime.\n\nThere are two types of MCP servers:\n\n| Source   | Description                                                          | Example                         |\n| -------- | -------------------------------------------------------------------- | ------------------------------- |\n| `remote` | HTTP-based MCP servers, managed by the platform                      | Figma, Sentry, GitHub           |\n| `device` | Local MCP servers running on the consumer's machine via server-sdk   | Browser automation, filesystem  |\n\n## Defining MCP Servers\n\nMCP servers are defined in the `mcpServers:` section. The key becomes the **namespace** for all tools from that server.\n\n```yaml\nmcpServers:\n  figma:\n    description: Figma design tool integration\n    source: remote\n    display: description\n\n  browser:\n    description: Chrome DevTools browser automation\n    source: device\n    display: name\n```\n\n### Fields\n\n| Field         | Required | Description                                                  |\n| ------------- | -------- | ------------------------------------------------------------ |\n| `description` | Yes      | What the MCP server provides                                 |\n| `source`      | Yes      | `remote` (platform-managed) or `device` (consumer-provided)  |\n| `display`     | No       | How tool calls appear in UI: `hidden`, `name`, `description` |\n\n### Display Modes\n\nDisplay modes control visibility of all tool calls from the MCP server, using the same modes as [regular tools](/docs/protocol/tools#display-modes):\n\n| Mode          | Behavior                                     |\n| ------------- | -------------------------------------------- |\n| `hidden`      | Tool calls run silently                      |\n| `name`        | Shows tool name while executing              |\n| `description` | Shows tool description while executing       |\n\n## Making MCP Servers Available\n\nLike tools, MCP servers defined in `mcpServers:` must be referenced in `agent.mcpServers` to be available:\n\n```yaml\nmcpServers:\n  figma:\n    description: Figma design tool integration\n    source: remote\n    display: description\n\n  sentry:\n    description: Error tracking and debugging\n    source: remote\n    display: name\n\n  browser:\n    description: Chrome DevTools browser automation\n    source: device\n    display: name\n\n  filesystem:\n    description: Filesystem access for reading and writing files\n    source: device\n    display: hidden\n\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  mcpServers: [figma, sentry, browser, filesystem]\n  tools: [set-chat-title]\n  agentic: true\n  maxSteps: 100\n```\n\n## Tool Namespacing\n\nAll MCP tools are automatically namespaced using `__` (double underscore) as a separator. The namespace comes from the `mcpServers` key.\n\nFor example, a server defined as `browser:` that exposes `navigate_page` and `click` produces:\n\n- `browser__navigate_page`\n- `browser__click`\n\nA server defined as `figma:` that exposes `get_design_context` produces:\n\n- `figma__get_design_context`\n\nThe namespace is stripped before calling the MCP server \u2014 the server receives the original tool name. This convention matches Anthropic's MCP integration in Claude Desktop and ensures tool names stay unique across servers.\n\n### What the LLM Sees\n\nWhen an agent has both regular tools and MCP servers configured, the LLM sees all tools combined:\n\n```\nProtocol tools:\n  set-chat-title\n\nRemote MCP tools (auto-discovered):\n  figma__get_design_context\n  figma__get_screenshot\n  sentry__get_issues\n  sentry__get_issue_details\n\nDevice MCP tools (auto-discovered):\n  browser__navigate_page\n  browser__click\n  browser__take_snapshot\n  filesystem__read_file\n  filesystem__write_file\n  filesystem__list_directory\n```\n\nYou don't define individual MCP tool schemas in the protocol \u2014 they're auto-discovered from each MCP server at runtime.\n\n## Remote MCP Servers\n\nRemote MCP servers (`source: remote`) connect to HTTP-based MCP endpoints. The platform manages the connection, authentication, and tool discovery.\n\nConfiguration happens in the Octavus platform UI:\n\n1. Add an MCP server to your project (URL + authentication)\n2. The server's slug must match the namespace in your protocol\n3. The platform connects, discovers tools, and makes them available to the agent\n\n### Authentication\n\nRemote MCP servers support multiple authentication methods:\n\n| Auth Type   | Description                          |\n| ----------- | ------------------------------------ |\n| MCP OAuth   | Standard MCP OAuth flow              |\n| API Key     | Static API key sent as a header      |\n| Bearer      | Bearer token authentication          |\n| None        | No authentication required           |\n\nAuthentication is configured per-project \u2014 different projects can connect to the same MCP server with different credentials.\n\n## Device MCP Servers\n\nDevice MCP servers (`source: device`) run on the consumer's machine. The consumer provides the MCP tools via the `@octavus/computer` package (or any `ToolProvider` implementation) through the server-sdk.\n\nWhen an agent has device MCP servers:\n\n1. The consumer creates a `Computer` with matching namespaces\n2. `@octavus/computer` discovers tools from each MCP server\n3. Tool schemas are sent to the platform via the server-sdk\n4. Tool calls flow back to the consumer for execution\n\nSee [`@octavus/computer`](/docs/server-sdk/computer) for the full integration guide.\n\n### Namespace Matching\n\nThe `mcpServers` keys in the protocol must match the keys in the consumer's `Computer` configuration:\n\n```yaml\n# protocol.yaml\nmcpServers:\n  browser:        # \u2190 must match\n    source: device\n  filesystem:     # \u2190 must match\n    source: device\n```\n\n```typescript\nconst computer = new Computer({\n  mcpServers: {\n    browser: Computer.stdio('chrome-devtools-mcp', ['--browser-url=...']),\n    filesystem: Computer.stdio('@modelcontextprotocol/server-filesystem', [dir]),\n  },\n});\n```\n\nIf the consumer provides a namespace not declared in the protocol, the platform rejects it.\n\n## Thread-Level Scoping\n\nThreads can scope which MCP servers are available, the same way they scope [tools](/docs/protocol/handlers#start-thread):\n\n```yaml\nhandlers:\n  user-message:\n    Start research:\n      block: start-thread\n      thread: research\n      mcpServers: [figma, browser]\n      tools: [set-chat-title]\n      system: research-prompt\n```\n\nThis thread can use Figma and browser tools, but not sentry or filesystem \u2014 even if those are available on the main agent.\n\n## Full Example\n\n```yaml\nmcpServers:\n  figma:\n    description: Figma design tool integration\n    source: remote\n    display: description\n  sentry:\n    description: Error tracking and debugging\n    source: remote\n    display: name\n  browser:\n    description: Chrome DevTools browser automation\n    source: device\n    display: name\n  filesystem:\n    description: Filesystem access for reading and writing files\n    source: device\n    display: hidden\n  shell:\n    description: Shell command execution\n    source: device\n    display: name\n\ntools:\n  set-chat-title:\n    description: Set the title of the current chat.\n    parameters:\n      title: { type: string, description: The title to set }\n\nagent:\n  model: anthropic/claude-opus-4-6\n  system: system\n  mcpServers: [figma, sentry, browser, filesystem, shell]\n  tools: [set-chat-title]\n  thinking: medium\n  maxSteps: 300\n  agentic: true\n\ntriggers:\n  user-message:\n    input:\n      USER_MESSAGE: { type: string }\n\nhandlers:\n  user-message:\n    Add message:\n      block: add-message\n      role: user\n      prompt: user-message\n      input: [USER_MESSAGE]\n      display: hidden\n\n    Respond:\n      block: next-message\n```\n\n### Cloud-Only Agent\n\nAgents that only use remote MCP servers don't need `@octavus/computer`:\n\n```yaml\nmcpServers:\n  figma:\n    description: Figma design tool integration\n    source: remote\n    display: description\n  sentry:\n    description: Error tracking and debugging\n    source: remote\n    display: name\n\ntools:\n  submit-code:\n    description: Submit code to the user.\n    parameters:\n      code: { type: string }\n\nagent:\n  model: anthropic/claude-sonnet-4-5\n  system: system\n  mcpServers: [figma, sentry]\n  tools: [submit-code]\n  agentic: true\n```\n",
+        excerpt: "MCP Servers MCP servers extend your agent with tools from external services. Define them in your protocol, and agents automatically discover and use their tools at runtime. There are two types of MCP...",
+        order: 13
       }
     ]
   },
@@ -1510,4 +1546,4 @@ export {
   getDocSlugs,
   getSectionBySlug
 };
-//# sourceMappingURL=chunk-4WYG2JYA.js.map
+//# sourceMappingURL=chunk-UZWGRPRR.js.map