> ## Documentation Index > Fetch the complete documentation index at: https://docs.mka1.com/llms.txt > Use this file to discover all available pages before exploring further. # Generate LiveKit room token > Generates a LiveKit access token for joining a real-time voice room. The token includes encrypted credentials and model configuration for the voice agent. ## OpenAPI ````yaml https://apigw.mka1.com/speakeasy.json post /api/v1/llm/speech/livekit/token openapi: 3.1.1 info: title: MKA1 API version: 1.1.0 description: >- The MKA1 API is a RESTful API that provides access to the MKA1 platform. Learn how to get started with the API and the TypeScript SDK [here](https://mka1.apidocumentation.com/guides/getting-started). license: name: Proprietary servers: - url: https://apigw.mka1.com description: MKA1 API Gateway - url: / description: Relative server URL (configurable via SDK constructor) security: [] tags: - name: Resource Authorization description: >- Manage permissions for LLM resources. Create resources, grant/revoke permissions, and delete resources. Only resource owners can grant, revoke, or delete permissions. x-displayName: Resource Authorization - name: Embeddings description: >- Text embedding API endpoints for generating vector representations of text. Create semantic embeddings for search, clustering, and similarity matching using various embedding models. x-displayName: Embeddings - name: Feedback description: >- User feedback API for rating and commenting on chat completions. Collect thumbs up/down ratings and detailed feedback to improve model responses and track user satisfaction. x-displayName: Feedback - name: Images description: >- Image generation API endpoints for creating images from text descriptions. Generate images with control over size, quality, and style. x-displayName: Images - name: MCP Vault description: >- MCP vault API for storing user-owned MCP server configurations and encrypted credentials. Agents reference vault IDs so secrets are resolved only at tool execution time. x-displayName: MCP Vault - name: Speech description: >- Speech API endpoints for audio processing. Convert text to natural-sounding speech (TTS) or transcribe speech to text (STT) in different languages. x-displayName: Speech - name: Usage description: >- Usage tracking and analytics API for monitoring token consumption, request counts, and cost analysis. View detailed statistics per user, model, and time period. x-displayName: Usage - name: Extract description: >- Structured data extraction API for extracting information from files. Define JSON schemas to extract structured data from images, PDFs, and documents. Supports reusable schema templates. x-displayName: Extract - name: Text Classification description: >- Text classification API for categorizing text into predefined labels. Use AI models to classify text content for sentiment analysis, topic categorization, and content moderation. x-displayName: Text Classification - name: Responses description: >- Agent-powered responses API for creating AI agents with autonomous tool usage. Build conversational assistants that can use web search, file operations, image generation, code execution, computer use simulation, and MCP integrations. Supports background processing, streaming, and real-time status tracking. x-displayName: Responses - name: Files description: >- File management API for uploading, storing, and managing files with automatic expiration and S3 integration. Upload files that can be used with Assistants, Vector Stores, and other features. Files are stored in S3 with metadata tracked in PostgreSQL. Supports automatic cleanup of expired files. x-displayName: Files - name: Vector Stores description: >- Vector store API for storing and searching documents using embeddings. Create vector stores, upload files with automatic chunking and embedding generation, and perform semantic search. Files are processed asynchronously using Temporal workflows for durability. Supports automatic cleanup of expired stores and LanceDB for efficient vector storage. x-displayName: Vector Stores - name: Conversations description: >- Conversation management API for storing and retrieving conversation state across Response API calls. Create conversations, add items (user messages, assistant messages, system messages), and maintain conversation history. Supports metadata tracking and multi-turn dialogue state management. x-displayName: Conversations - name: Guardrails description: >- AI safety guardrails API for configuring content moderation and security policies. Set up ban word lists, prompt injection detection, and system prompt leakage prevention. Guardrails apply to all requests from an account and can be tested before deployment. x-displayName: Guardrails - name: Models description: >- Model listing API for discovering available models. Returns model IDs, ownership, and metadata for all registered models in the gateway. x-displayName: Models - name: Skills description: >- Skills API for managing versioned bundles of instructions and files following the Agent Skills standard. Create, version, and download reusable skill packages that include SKILL.md manifests for agent environments. x-displayName: Skills - name: Chat Completions description: >- **Deprecated: Use the Responses API (`/api/v1/llm/responses`) instead.** Chat completion endpoints with support for streaming, tool calls, and multiple providers. x-deprecated: true x-displayName: Chat Completions - name: Batches x-displayName: Batches - name: Evals x-displayName: Evals - name: Fine-Tuning x-displayName: Fine-Tuning - name: Memory Stores x-displayName: Memory Stores - name: Prompts x-displayName: Prompts - name: API Key x-displayName: API Key - name: Organization x-displayName: Organization - name: Cluster Admin x-displayName: Cluster Admin - name: Sessions description: Create, inspect, access, and terminate sandbox sessions. x-displayName: Sessions - name: Browser description: >- Connect to browser sessions through the gateway port proxy. Browser sessions expose a Chrome DevTools Protocol endpoint on port 9222. x-displayName: Browser - name: Execution description: Run shell commands and code inside an existing sandbox session. x-displayName: Execution - name: Workspace description: >- Inspect the workspace manifest, transfer files or archives, and download generated artifacts. x-displayName: Workspace - name: Sandbox Usage description: >- Aggregate sandbox usage statistics across sessions, execution, and workspace operations. x-displayName: Sandbox Usage - name: Sandbox Pricing description: >- Cluster-admin management of the sandbox compute rate card used for budgeted spend. x-displayName: Sandbox Pricing - name: Agents description: Create and manage reusable agent definitions. x-displayName: Agents - name: Agent Versions description: Inspect an agent's configuration history and roll back to a prior version. x-displayName: Agent Versions - name: Agent Runs description: Execute saved agents and inspect persisted run results. x-displayName: Agent Runs - name: Agent Connectors description: >- Connect saved agents to external messaging channels such as Telegram, including text, photo, and supported document exchange. x-displayName: Agent Connectors - name: Agent Schedules description: Create and manage scheduled or recurring saved agent runs. x-displayName: Agent Schedules - name: schema-4_other x-displayName: other - name: Budgets x-displayName: Budgets - name: Settings x-displayName: Settings - name: Deployments description: Long-lived inference servers. x-displayName: Deployments - name: Fine-Tune Jobs description: Submit, monitor, and cancel fine-tune jobs. x-displayName: Fine-Tune Jobs - name: Container Images description: Custom container images for deployments and jobs. x-displayName: Container Images - name: Serving Models description: Models registered for deployment and fine-tuning. x-displayName: Serving Models - name: Volumes description: Persistent storage for weights and checkpoints. x-displayName: Volumes - name: Secrets description: Credentials injected into your workloads. x-displayName: Secrets - name: Accelerators description: Available accelerator types (GPU, NPU, TPU). x-displayName: Accelerators paths: /api/v1/llm/speech/livekit/token: post: tags: - Speech summary: Generate LiveKit room token description: >- Generates a LiveKit access token for joining a real-time voice room. The token includes encrypted credentials and model configuration for the voice agent. operationId: livekitToken parameters: - name: X-On-Behalf-Of in: header required: false schema: type: string description: Optional external end-user identifier forwarded by the API gateway. requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/LivekitTokenRequest' example: llm: model: auto responses: '200': description: OK content: application/json: schema: $ref: '#/components/schemas/LivekitTokenResponse' example: token: eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9... url: wss://apigw.mka1.com/api/v1/livekit roomName: 550e8400-e29b-41d4-a716-446655440000 security: - bearerAuth: [] x-codeSamples: - lang: python label: Python (SDK) source: |- from meetkai_mka1 import SDK with SDK( bearer_auth="", ) as sdk: res = sdk.llm.speech.livekit_token(llm={ "model": "auto", }) # Handle response print(res) - lang: typescript label: Typescript (SDK) source: |- import { SDK } from "@meetkai/mka1"; const sdk = new SDK({ bearerAuth: "", }); async function run() { const result = await sdk.llm.speech.livekitToken({ livekitTokenRequest: { llm: { model: "auto", }, }, }); console.log(result); } run(); - lang: csharp label: CSharp (SDK) source: >- using MeetKai.MKA1; using MeetKai.MKA1.Types.Components; var sdk = new SDK(bearerAuth: ""); var res = await sdk.Llm.Speech.LivekitTokenAsync(body: new MeetKai.MKA1.Types.Components.LivekitTokenRequest() { Llm = new MeetKai.MKA1.Types.Components.Llm() { Model = "auto", }, }); // handle response components: schemas: LivekitTokenRequest: type: object properties: llm: type: object properties: model: type: string description: The ID of the model to use for generating the response. instructions: type: string description: >- System or developer instructions inserted into the model's context before user input. Use this to guide the agent's behavior, set personality, define constraints, or provide domain-specific knowledge. Acts as a persistent system message for this response. conversation: anyOf: - anyOf: - type: string - $ref: '#/components/schemas/Conversation' - type: 'null' description: >- The conversation that this response belongs to. Can be a conversation ID string or a conversation object. Used to maintain context and history across multiple agent interactions. Optional - omit for one-off interactions. previous_response_id: type: string description: >- The unique ID of a previous response to continue from. Used for multi-turn conversations to maintain context and history. The agent will have access to all previous interactions in the chain. prompt: $ref: '#/components/schemas/PromptTemplate' description: >- Reference to a prompt template to use for this response, along with variables to substitute. Allows using predefined, versioned prompt templates instead of inline instructions. The template system supports variable interpolation. tools: type: array items: anyOf: - $ref: '#/components/schemas/FunctionToolDefinition' - $ref: '#/components/schemas/FileSearchToolDefinition' - $ref: '#/components/schemas/ComputerUseToolDefinition' - $ref: '#/components/schemas/WebSearchToolDefinition' - $ref: '#/components/schemas/MCPToolDefinition' - $ref: '#/components/schemas/CodeInterpreterToolDefinition' - $ref: '#/components/schemas/ImageGenerationToolDefinition' - $ref: '#/components/schemas/LocalShellToolDefinition' - $ref: '#/components/schemas/ShellToolDefinition' - $ref: '#/components/schemas/CustomToolDefinition' - $ref: '#/components/schemas/WebSearchPreviewToolDefinition' - $ref: '#/components/schemas/HostedToolDefinition' - $ref: '#/components/schemas/SleepToolDefinition' - $ref: '#/components/schemas/HistoryToolDefinition' description: >- Array of tool definitions that the agent can use during response generation. Supports built-in tools (web search, file search, code interpreter, computer use, image generation) and custom tools (functions, MCP, local shell). Each tool definition specifies its type and configuration. tool_choice: $ref: '#/components/schemas/ToolChoice' description: >- Controls how the agent selects which tools to use. Can be 'none' (no tools), 'auto' (model decides), 'required' (must use tools), or a specific tool selection object. Use this to force or prevent tool usage. parallel_tool_calls: type: boolean default: true description: >- Whether to allow the agent to execute multiple tool calls in parallel. When true, the agent can make concurrent tool calls for efficiency. When false, tools are called sequentially. Defaults to true for better performance. max_tool_calls: type: integer minimum: 1 maximum: 300 default: 64 description: >- The maximum total number of tool calls the agent can make during this response. Useful for controlling execution time and preventing infinite loops. Applies to all built-in tools like web search, file search, code interpreter, etc. Must be a positive integer between 1 and 300. Defaults to 64. reasoning: $ref: '#/components/schemas/ReasoningConfiguration' description: >- Configuration options for reasoning models. Controls reasoning effort level (minimal, low, medium, high) and summary verbosity (auto, concise, detailed). Only applicable to specific reasoning-capable models. max_output_tokens: type: integer minimum: 1 maximum: 9007199254740991 description: >- The maximum number of tokens the model can generate in its output. Sets an upper bound to control costs and response length. The actual output may be shorter if the model finishes naturally. Must be a positive integer. temperature: type: number minimum: 0 maximum: 2 description: >- Controls randomness in the model's output. Higher values (e.g., 1.5-2.0) make output more random and creative, lower values (e.g., 0.0-0.5) make it more focused and deterministic. Must be between 0 and 2. top_p: type: number minimum: 0 maximum: 1 description: >- Nucleus sampling parameter. The model considers only the tokens with top_p cumulative probability. Lower values (e.g., 0.1) make output more focused, higher values (e.g., 0.9) allow more diversity. Must be between 0 and 1. Alternative to temperature. truncation: enum: - auto - disabled type: string default: auto description: >- The truncation strategy for handling inputs that exceed the model's context window. 'auto' automatically truncates old messages to fit, 'disabled' returns an error if context is too long. Defaults to 'auto'. presence_penalty: type: number minimum: -2 maximum: 2 description: >- Penalizes new tokens based on whether they appear in the text so far. Higher values increase the model's likelihood to talk about new topics. frequency_penalty: type: number minimum: -2 maximum: 2 description: >- Penalizes new tokens based on their frequency in the text so far. Higher values decrease the model's likelihood to repeat the same line verbatim. context_management: $ref: '#/components/schemas/ContextManagement' description: >- Context management strategies to apply during response generation. Supports compaction, which summarizes older conversation history when the context exceeds a token threshold. service_tier: enum: - auto - default - flex - priority type: string default: auto description: >- Specifies the processing tier for serving the request. 'auto' lets the system choose, 'default' uses standard processing, 'flex' allows flexible scheduling for lower priority, 'priority' provides faster processing. Defaults to 'auto'. metadata: type: object propertyNames: type: string maxLength: 64 additionalProperties: type: string maxLength: 512 description: >- Custom metadata to attach to this response as key-value pairs. Keys must be strings up to 64 characters, values must be strings up to 512 characters. Maximum 16 pairs. Useful for tracking, categorization, or passing custom identifiers through your system. text: $ref: '#/components/schemas/TextConfiguration' description: >- Configuration options for text output from the model. Includes response format (text, JSON object, JSON schema) and verbosity level (low, medium, high). Use this to control output structure and detail level. required: - model description: >- LLM configuration for the voice session. Uses a subset of the responses create schema — fields like input, stream, background, webhooks, and store are excluded since the voice agent manages those. WARNING: This object is serialized into the LiveKit JWT metadata which is transmitted via HTTP headers. Keep payloads small — large tools arrays can exceed the ~8KB header size limit imposed by most servers and proxies. stt: $ref: '#/components/schemas/SttConfig' description: Optional STT (speech-to-text) VAD configuration. required: - llm description: >- Request parameters for generating a LiveKit room token with LLM configuration and optional STT settings. LivekitTokenResponse: type: object properties: token: type: string description: JWT access token for authenticating with the LiveKit room url: type: string format: uri description: >- LiveKit server WebSocket URL to connect to (e.g., wss://apigw.mka1.com/api/v1/livekit) roomName: type: string description: Auto-generated UUID room name assigned to this session required: - token - url - roomName description: >- Response containing a LiveKit access token, server URL, and the generated room name. examples: - token: eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9... url: wss://apigw.mka1.com/api/v1/livekit roomName: 550e8400-e29b-41d4-a716-446655440000 Conversation: type: object properties: id: type: string required: - id PromptTemplate: type: object properties: id: type: string variables: type: object propertyNames: type: string additionalProperties: anyOf: - type: string - {} version: type: string required: - id FunctionToolDefinition: type: object properties: type: const: function name: type: string parameters: type: object propertyNames: type: string additionalProperties: {} strict: type: boolean description: type: string defer_loading: type: boolean required: - type - name - parameters - strict title: Function tool definition description: >- Function tool definition: Defines a callable function tool. Provide a tool name and parameters schema, with optional description and deferred loading. FileSearchToolDefinition: type: object properties: type: const: file_search vector_store_ids: type: array items: type: string filters: anyOf: - $ref: '#/components/schemas/ComparisonFilter' - $ref: '#/components/schemas/CompoundFilter' max_num_results: type: integer minimum: 1 maximum: 50 ranking_options: $ref: '#/components/schemas/RankingOptions' required: - type - vector_store_ids title: File search tool definition description: >- File search tool definition: Configures semantic search over one or more vector stores, with optional filters, ranking options, and result limits. ComputerUseToolDefinition: type: object properties: type: const: computer_use_preview display_height: type: integer minimum: -9007199254740991 maximum: 9007199254740991 display_width: type: integer minimum: -9007199254740991 maximum: 9007199254740991 environment: type: string required: - type - display_height - display_width - environment title: Computer use tool definition description: >- Computer use tool definition: Configures the computer-use preview tool, including required display dimensions and runtime environment. WebSearchToolDefinition: type: object properties: type: enum: - web_search - web_search_2025_08_26 type: string filters: $ref: '#/components/schemas/WebSearchFilters' search_context_size: enum: - low - medium - high type: string default: medium user_location: $ref: '#/components/schemas/UserLocation' required: - type title: Web search tool definition description: >- Web search tool definition: Enables web search with optional domain filters, search context size, and approximate user location. MCPToolDefinition: type: object properties: type: const: mcp server_label: type: string minLength: 1 maxLength: 255 pattern: ^[A-Za-z0-9._-]+$ mcp_server_id: type: string description: >- Reference to a gateway-managed MCP server. When provided, server_url is resolved from the MCP vault. mcp_credential_id: type: string description: >- Optional reference to a gateway-managed MCP credential owned by the run caller. allowed_tools: anyOf: - type: array items: type: string - $ref: '#/components/schemas/MCPToolFilter' authorization: type: string connector_id: enum: - connector_dropbox - connector_gmail - connector_googlecalendar - connector_googledrive - connector_microsoftteams - connector_outlookcalendar - connector_outlookemail - connector_sharepoint type: string headers: type: object propertyNames: type: string minLength: 1 maxLength: 256 pattern: ^[!#$%&'*+.^_`|~0-9A-Za-z-]+$ additionalProperties: type: string minLength: 1 maxLength: 8192 pattern: ^[^\r\n]*$ require_approval: anyOf: - const: always - const: never - $ref: '#/components/schemas/MCPToolApprovalFilter' server_description: type: string server_url: type: string required: - type title: MCP tool definition description: >- MCP tool definition: Connects to an MCP server and exposes its tools, with optional vault references, auth, headers, allow-lists, connector ID, and approval policy. CodeInterpreterToolDefinition: type: object properties: type: const: code_interpreter container: anyOf: - type: string - $ref: '#/components/schemas/CodeInterpreterContainerAuto' required: - type - container title: Code interpreter tool definition description: >- Code interpreter tool definition: Enables code execution. Provide an explicit container ID or auto container configuration with optional file IDs and memory limit. ImageGenerationToolDefinition: type: object properties: type: const: image_generation background: enum: - transparent - opaque - auto type: string default: auto input_fidelity: enum: - high - low type: string default: low input_image_mask: $ref: '#/components/schemas/InputImageMask' model: type: string minLength: 1 default: auto description: >- The model to use for image generation. Defaults to 'auto' for automatic model selection. moderation: enum: - auto - low - none type: string default: auto output_compression: type: integer minimum: -9007199254740991 maximum: 9007199254740991 default: 100 output_format: enum: - png - webp - jpeg type: string default: png partial_images: type: integer minimum: 0 maximum: 3 default: 0 quality: enum: - low - medium - high - auto type: string default: auto size: enum: - 1024x1024 - 1024x1536 - 1536x1024 - auto type: string default: auto prompt_guard: type: string description: >- Adds a guardrail to prevent the model from generating content that is not allowed. required: - type title: Image generation tool definition description: >- Image generation tool definition: Enables image generation and configures output settings like model, quality, size, format, moderation, and optional masking. LocalShellToolDefinition: type: object properties: type: const: local_shell required: - type title: Local shell tool definition description: 'Local shell tool definition: Enables the local shell execution tool.' ShellToolDefinition: type: object properties: type: const: shell environment: $ref: '#/components/schemas/ShellEnvironment' description: Container environment configuration. Defaults to container_auto. required: - type title: Shell tool definition description: >- Shell tool definition: Enables shell command execution in a managed container environment. CustomToolDefinition: type: object properties: type: const: custom name: type: string description: type: string format: $ref: '#/components/schemas/CustomToolFormat' required: - type - name title: Custom tool definition description: >- Custom tool definition: Defines a custom tool by name, with optional description and optional output format constraints. WebSearchPreviewToolDefinition: type: object properties: type: enum: - web_search_preview - web_search_preview_2025_03_11 type: string search_context_size: enum: - low - medium - high type: string user_location: $ref: '#/components/schemas/UserLocation' required: - type title: Web search preview tool definition description: >- Web search preview tool definition: Enables the preview web search tool variant with optional context size and user location. HostedToolDefinition: type: object properties: type: enum: - file_search - web_search_preview - computer_use_preview - code_interpreter - image_generation type: string required: - type title: Hosted tool definition description: >- Hosted tool definition: Shorthand hosted-tool selector for built-in tool types. This is a compatibility form that overlaps with the detailed per-tool schemas. SleepToolDefinition: type: object properties: type: const: sleep required: - type title: Sleep tool definition description: >- Sleep tool definition: Allows an agent to pause the current response briefly and resume later or when woken. HistoryToolDefinition: type: object properties: type: const: history required: - type title: History tool definition description: >- History tool definition: Enables the internal conversation-history retrieval tool for semantic lookup of past interactions. ToolChoice: anyOf: - $ref: '#/components/schemas/ToolChoiceMode' - $ref: '#/components/schemas/AllowedTools' - $ref: '#/components/schemas/HostedToolChoice' - $ref: '#/components/schemas/FunctionToolChoice' - $ref: '#/components/schemas/MCPToolChoice' - $ref: '#/components/schemas/CustomToolChoice' ReasoningConfiguration: type: object properties: effort: anyOf: - enum: - none - minimal - low - medium - high - xhigh type: string - type: 'null' summary: anyOf: - enum: - auto - concise - detailed type: string - type: 'null' required: - effort - summary ContextManagement: type: array maxItems: 1 items: $ref: '#/components/schemas/CompactionContextManagement' description: >- Array of context management strategies to apply during response generation. TextConfiguration: type: object properties: format: $ref: '#/components/schemas/ResponseFormat' verbosity: enum: - low - medium - high type: string default: medium required: - format SttConfig: type: object properties: silence_timeout_ms: type: integer minimum: 100 maximum: 5000 description: >- Server-side VAD silence timeout in ms (100–5000). Controls how long to wait after silence before finalizing speech. initial_silence_timeout_ms: type: integer minimum: 1000 maximum: 30000 description: Timeout in ms before any speech is detected (1000–30000). description: Optional STT (speech-to-text) VAD configuration for the voice session. ComparisonFilter: type: object properties: type: enum: - eq - ne - gt - gte - lt - lte type: string key: type: string value: anyOf: - type: string - type: number - type: boolean required: - type - key - value CompoundFilter: type: object properties: type: enum: - and - or type: string filters: type: array items: anyOf: - $ref: '#/components/schemas/ComparisonFilter' - $ref: '#/components/schemas/CompoundFilter' required: - type - filters RankingOptions: type: object properties: ranker: type: string score_threshold: type: number WebSearchFilters: type: object properties: allowed_domains: type: array items: type: string default: [] UserLocation: type: object properties: type: const: approximate default: approximate city: type: string country: type: string region: type: string timezone: type: string MCPToolFilter: type: object properties: read_only: type: boolean tool_names: type: array items: type: string MCPToolApprovalFilter: type: object properties: always: $ref: '#/components/schemas/MCPToolFilter' never: $ref: '#/components/schemas/MCPToolFilter' CodeInterpreterContainerAuto: type: object properties: type: const: auto file_ids: anyOf: - type: array items: type: string - type: 'null' memory_limit: anyOf: - enum: - 1g - 4g - 16g - 64g type: string - type: 'null' required: - type InputImageMask: type: object properties: file_id: type: string image_url: type: string ShellEnvironment: anyOf: - $ref: '#/components/schemas/ShellEnvironmentContainerAuto' - $ref: '#/components/schemas/ShellEnvironmentContainerReference' discriminator: propertyName: type mapping: container_auto: $ref: '#/components/schemas/ShellEnvironmentContainerAuto' container_reference: $ref: '#/components/schemas/ShellEnvironmentContainerReference' CustomToolFormat: anyOf: - $ref: '#/components/schemas/TextFormat' - $ref: '#/components/schemas/GrammarFormat' ToolChoiceMode: enum: - none - auto - required type: string title: Tool choice mode description: >- Tool choice mode: Selects how the model decides tool usage. Use none, auto, or required. AllowedTools: type: object properties: type: const: allowed_tools mode: enum: - auto - required type: string tools: type: array items: type: object properties: type: type: string name: type: string server_label: type: string required: - type required: - type - mode - tools title: Allowed tools tool choice description: >- Allowed tools tool choice: Restricts tool use to a provided list and sets whether tool use is optional (auto) or mandatory (required). HostedToolChoice: type: object properties: type: enum: - file_search - web_search_preview - computer_use_preview - code_interpreter - image_generation type: string required: - type title: Hosted tool choice description: 'Hosted tool choice: Forces a specific built-in hosted tool type.' FunctionToolChoice: type: object properties: type: const: function name: type: string required: - type - name title: Function tool choice description: 'Function tool choice: Forces a specific function tool by name.' MCPToolChoice: type: object properties: type: const: mcp server_label: type: string name: type: string required: - type - server_label title: MCP tool choice description: >- MCP tool choice: Forces an MCP server, optionally narrowed to a specific MCP tool name. CustomToolChoice: type: object properties: type: const: custom name: type: string required: - type - name title: Custom tool choice description: 'Custom tool choice: Forces a specific custom tool by name.' CompactionContextManagement: type: object properties: type: const: compaction compact_threshold: type: integer minimum: 1000 maximum: 9007199254740991 description: >- The token threshold above which conversation context should be compacted. Must be at least 1000. required: - type - compact_threshold ResponseFormat: anyOf: - $ref: '#/components/schemas/TextResponseFormat' - $ref: '#/components/schemas/JSONSchemaResponseFormat' - $ref: '#/components/schemas/JSONObjectResponseFormat' ShellEnvironmentContainerAuto: type: object properties: type: const: container_auto network_policy: $ref: '#/components/schemas/ShellNetworkPolicy' description: Network policy restricting outbound access. skills: type: array items: $ref: '#/components/schemas/SkillEntry' description: Skills to inject into the container's /skills directory. memory_stores: type: array items: $ref: '#/components/schemas/MemoryStoreMount' description: Memory stores to mount into the container under /mnt/memory. required: - type ShellEnvironmentContainerReference: type: object properties: type: const: container_reference container_id: type: string description: ID of an existing container to reuse. network_policy: $ref: '#/components/schemas/ShellNetworkPolicy' description: Network policy restricting outbound access. skills: type: array items: $ref: '#/components/schemas/SkillEntry' description: Skills to inject into the container's /skills directory. memory_stores: type: array items: $ref: '#/components/schemas/MemoryStoreMount' description: Memory stores to mount into the container under /mnt/memory. required: - type - container_id TextFormat: type: object properties: type: const: text required: - type GrammarFormat: type: object properties: type: const: grammar definition: type: string syntax: enum: - lark - regex type: string required: - type - definition - syntax TextResponseFormat: type: object properties: type: const: text required: - type JSONSchemaResponseFormat: type: object properties: type: const: json_schema name: type: string maxLength: 64 pattern: ^[a-zA-Z0-9_-]+$ schema: type: object propertyNames: type: string additionalProperties: {} description: type: string strict: type: boolean default: false required: - type - name - schema JSONObjectResponseFormat: type: object properties: type: const: json_object required: - type ShellNetworkPolicy: type: object properties: type: const: allowlist allowed_domains: type: array items: type: string description: Domains permitted for outbound network access. domain_secrets: type: array items: $ref: '#/components/schemas/ShellNetworkPolicyDomainSecret' description: Secrets injected per domain. required: - type SkillEntry: anyOf: - $ref: '#/components/schemas/SkillReference' - $ref: '#/components/schemas/PreconfiguredSkillReference' discriminator: propertyName: type mapping: skill_reference: $ref: '#/components/schemas/SkillReference' preconfigured: $ref: '#/components/schemas/PreconfiguredSkillReference' MemoryStoreMount: type: object properties: store_id: type: string minLength: 1 description: ID of the memory store to mount into the container. label: type: string minLength: 1 maxLength: 64 pattern: ^(?!\.+$)[A-Za-z0-9._-]+$ description: Directory name for this store under /mnt/memory. access: enum: - read_only - read_write type: string default: read_only description: Whether the mounted memory store can be modified. description: type: string maxLength: 2000 description: Optional short description of the store for agent context. instructions: type: string maxLength: 4000 description: >- Optional instructions for how the agent should use this mounted store. required: - store_id - label ShellNetworkPolicyDomainSecret: type: object properties: domain: type: string description: The domain to associate this secret with. name: type: string description: The name/placeholder for the secret (e.g., $API_KEY). value: type: string description: The secret value to substitute. required: - domain - name - value SkillReference: type: object properties: type: const: skill_reference skill_id: type: string description: ID of the skill to inject into the container. version: anyOf: - type: string - type: integer minimum: -9007199254740991 maximum: 9007199254740991 description: >- Version number, or 'latest' for the most recent version. Defaults to the skill's default_version. required: - type - skill_id PreconfiguredSkillReference: type: object properties: type: const: preconfigured name: type: string description: Name of a preconfigured skill (e.g., 'pdf', 'docx', 'xlsx', 'pptx'). required: - type - name securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: API Key description: >- Gateway auth: send `Authorization: Bearer `. For multi-user server-side integrations, you can also send `X-On-Behalf-Of: `. ````