> ## Documentation Index > Fetch the complete documentation index at: https://docs.openhands.dev/llms.txt > Use this file to discover all available pages before exploring further. # Get Org > Get organization details by ID through the deprecated detail route. ## OpenAPI ````yaml /openapi/openhands-cloud.json get /api/organizations/{org_id} openapi: 3.1.0 info: title: OpenHands description: 'OpenHands: Code Less, Make More' version: 0.0.1 servers: [] security: [] paths: /api/organizations/{org_id}: get: tags: - Orgs summary: Get Org description: Get organization details by ID through the deprecated detail route. operationId: get_org_api_organizations__org_id__get parameters: - name: org_id in: path required: true schema: anyOf: - type: string format: uuid - type: 'null' title: Org Id - name: X-Org-Id in: header required: false schema: anyOf: - type: string - type: 'null' title: X-Org-Id responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/OrgResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' deprecated: true security: - APIKeyHeader: [] components: schemas: OrgResponse: properties: id: type: string title: Id name: type: string title: Name contact_name: type: string title: Contact Name contact_email: type: string title: Contact Email conversation_expiration: anyOf: - type: integer - type: 'null' title: Conversation Expiration remote_runtime_resource_factor: anyOf: - type: integer - type: 'null' title: Remote Runtime Resource Factor billing_margin: anyOf: - type: number - type: 'null' title: Billing Margin enable_proactive_conversation_starters: type: boolean title: Enable Proactive Conversation Starters default: true sandbox_base_container_image: anyOf: - type: string - type: 'null' title: Sandbox Base Container Image sandbox_runtime_container_image: anyOf: - type: string - type: 'null' title: Sandbox Runtime Container Image org_version: type: integer title: Org Version default: 0 agent_settings: oneOf: - $ref: '#/components/schemas/OpenHandsAgentSettings' - $ref: '#/components/schemas/LLMAgentSettings' - $ref: '#/components/schemas/ACPAgentSettings' title: Agent Settings conversation_settings: $ref: '#/components/schemas/ConversationSettings' search_api_key: anyOf: - type: string - type: 'null' title: Search Api Key sandbox_api_key: anyOf: - type: string - type: 'null' title: Sandbox Api Key max_budget_per_task: anyOf: - type: number - type: 'null' title: Max Budget Per Task v1_enabled: anyOf: - type: boolean - type: 'null' title: V1 Enabled credits: anyOf: - type: number - type: 'null' title: Credits is_personal: type: boolean title: Is Personal default: false type: object required: - id - name - contact_name - contact_email title: OrgResponse description: Response model for organization. HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError OpenHandsAgentSettings: properties: schema_version: type: integer minimum: 1 title: Schema Version default: 5 agent_kind: type: string const: openhands title: Agent Kind description: >- Discriminator for the ``AgentSettings`` union. ``'openhands'`` selects the standard built-in OpenHands agent. default: openhands agent: type: string title: Agent description: Agent class to use. default: CodeActAgent openhands_settings: depends_on: [] label: Agent prominence: major variant: openhands llm: $ref: '#/components/schemas/LLM-Output' description: LLM settings for the agent. openhands_settings_section: key: llm label: LLM variant: openhands tools: anyOf: - items: $ref: '#/components/schemas/openhands__sdk__tool__spec__Tool' type: array - type: 'null' title: Tools description: >- Tools available to the agent. None (the default) resolves to the standard exec set (see openhands.sdk.tool.defaults), plus the sub-agent tool set when enable_sub_agents is set; [] is an explicitly bare agent; a non-empty list is used exactly as given. Environment-dependent tools (browser) are injected by the serving layer, not the default. openhands_settings: depends_on: [] label: Tools prominence: major variant: openhands enable_sub_agents: type: boolean title: Enable Sub Agents description: Enable sub-agent delegation via TaskToolSet. default: false openhands_settings: depends_on: [] label: Enable sub-agents prominence: major variant: openhands enable_switch_llm_tool: type: boolean title: Enable Switch Llm Tool description: >- Enable the built-in switch_llm tool for switching between saved LLM profiles. default: true openhands_settings: depends_on: [] label: Enable LLM switching tool prominence: minor variant: openhands tool_concurrency_limit: type: integer minimum: 1 title: Tool Concurrency Limit description: >- Maximum number of tool calls to execute concurrently per agent step. 1 = sequential (default). Values > 1 enable parallel tool calls; concurrent tools share the conversation object, filesystem, and working directory, so mutations to shared state may race. default: 1 openhands_settings: depends_on: [] label: Parallel tool calls prominence: major variant: openhands mcp_config: additionalProperties: $ref: '#/components/schemas/MCPServer-Output' type: object title: Mcp Config description: MCP servers available to the agent. openhands_settings: depends_on: [] label: MCP servers prominence: minor variant: openhands agent_context: $ref: '#/components/schemas/AgentContext-Output' description: Context for the agent (skills, secrets, message suffixes). openhands_settings_section: key: agent_context label: Memory variant: openhands condenser: oneOf: - $ref: '#/components/schemas/LLMSummarizingCondenserSettings' - $ref: '#/components/schemas/NoOpCondenserSettings' title: Condenser description: Condenser settings for the agent. openhands_settings_section: key: condenser label: Condenser variant: openhands verification: $ref: '#/components/schemas/VerificationSettings' description: Verification settings for the agent critic. openhands_settings_section: key: verification label: Verification variant: openhands type: object title: OpenHandsAgentSettings description: |- Settings for a standard LLM-backed :class:`Agent`. This is the long-standing ``AgentSettings`` shape; fields here build the default ``Agent`` (LLM + tools + MCP + condenser + critic). LLMAgentSettings: properties: schema_version: type: integer minimum: 1 title: Schema Version default: 5 agent_kind: type: string const: llm title: Agent Kind description: >- Discriminator for the ``AgentSettings`` union. ``'llm'`` selects the standard LLM-backed agent. Deprecated; use ``'openhands'``. default: llm agent: type: string title: Agent description: Agent class to use. default: CodeActAgent openhands_settings: depends_on: [] label: Agent prominence: major variant: openhands llm: $ref: '#/components/schemas/LLM-Output' description: LLM settings for the agent. openhands_settings_section: key: llm label: LLM variant: openhands tools: anyOf: - items: $ref: '#/components/schemas/openhands__sdk__tool__spec__Tool' type: array - type: 'null' title: Tools description: >- Tools available to the agent. None (the default) resolves to the standard exec set (see openhands.sdk.tool.defaults), plus the sub-agent tool set when enable_sub_agents is set; [] is an explicitly bare agent; a non-empty list is used exactly as given. Environment-dependent tools (browser) are injected by the serving layer, not the default. openhands_settings: depends_on: [] label: Tools prominence: major variant: openhands enable_sub_agents: type: boolean title: Enable Sub Agents description: Enable sub-agent delegation via TaskToolSet. default: false openhands_settings: depends_on: [] label: Enable sub-agents prominence: major variant: openhands enable_switch_llm_tool: type: boolean title: Enable Switch Llm Tool description: >- Enable the built-in switch_llm tool for switching between saved LLM profiles. default: true openhands_settings: depends_on: [] label: Enable LLM switching tool prominence: minor variant: openhands tool_concurrency_limit: type: integer minimum: 1 title: Tool Concurrency Limit description: >- Maximum number of tool calls to execute concurrently per agent step. 1 = sequential (default). Values > 1 enable parallel tool calls; concurrent tools share the conversation object, filesystem, and working directory, so mutations to shared state may race. default: 1 openhands_settings: depends_on: [] label: Parallel tool calls prominence: major variant: openhands mcp_config: additionalProperties: $ref: '#/components/schemas/MCPServer-Output' type: object title: Mcp Config description: MCP servers available to the agent. openhands_settings: depends_on: [] label: MCP servers prominence: minor variant: openhands agent_context: $ref: '#/components/schemas/AgentContext-Output' description: Context for the agent (skills, secrets, message suffixes). openhands_settings_section: key: agent_context label: Memory variant: openhands condenser: oneOf: - $ref: '#/components/schemas/LLMSummarizingCondenserSettings' - $ref: '#/components/schemas/NoOpCondenserSettings' title: Condenser description: Condenser settings for the agent. openhands_settings_section: key: condenser label: Condenser variant: openhands verification: $ref: '#/components/schemas/VerificationSettings' description: Verification settings for the agent critic. openhands_settings_section: key: verification label: Verification variant: openhands type: object title: LLMAgentSettings description: >- Legacy ``agent_kind='llm'`` variant of :class:`OpenHandsAgentSettings`. ``LLMAgentSettings`` was the public class name before the v1.19.0 rename. The public import aliases (``from openhands.sdk import LLMAgentSettings`` and ``from openhands.sdk.settings import LLMAgentSettings``) were removed in v1.24.0 — use :class:`OpenHandsAgentSettings` for all new code. The class itself is retained (reachable at ``openhands.sdk.settings.model.LLMAgentSettings``) because it remains a member of the settings discriminated union: it keeps ``agent_kind='llm'`` so persisted legacy payloads still deserialize and the API-breakage checker sees no field-value change versus the published release. ACPAgentSettings: properties: schema_version: type: integer minimum: 1 title: Schema Version default: 5 agent_kind: type: string const: acp title: Agent Kind description: >- Discriminator for the ``AgentSettings`` union. ``'acp'`` selects an ACP-delegating agent. default: acp acp_server: type: string enum: - claude-code - codex - gemini-cli - custom title: Acp Server description: >- Which ACP-compatible backend to launch. Each choice maps to a default subprocess command (see ``acp_command`` to override). default: claude-code openhands_settings: depends_on: [] label: ACP server prominence: critical openhands_settings_section: key: acp label: ACP (Agent Client Protocol) variant: acp acp_command: items: type: string type: array title: Acp Command description: >- Optional explicit command to launch the ACP subprocess. Leave empty to use the default for :attr:`acp_server` (e.g. ``npx -y @agentclientprotocol/claude-agent-acp`` for ``claude-code``). Must be set when :attr:`acp_server` is ``'custom'``. openhands_settings: depends_on: [] label: ACP command (custom override) prominence: minor openhands_settings_section: key: acp label: ACP (Agent Client Protocol) variant: acp acp_args: items: type: string type: array title: Acp Args description: Additional arguments appended to the ACP server command. openhands_settings: depends_on: [] label: ACP extra args prominence: minor openhands_settings_section: key: acp label: ACP (Agent Client Protocol) variant: acp acp_model: anyOf: - type: string - type: 'null' title: Acp Model description: >- Model identifier for the ACP server to use (e.g. ``'sonnet'`` or ``'gpt-5.5'``). Applied via the protocol — set_config_option(model) for configOptions-based servers (codex, claude), else set_session_model. Leave blank to let the server pick its default. openhands_settings: depends_on: [] label: ACP model prominence: critical openhands_settings_section: key: acp label: ACP (Agent Client Protocol) variant: acp acp_session_mode: anyOf: - type: string - type: 'null' title: Acp Session Mode description: >- Session mode ID (e.g. ``bypassPermissions``). Leave blank to auto-detect from the ACP server type. openhands_settings: depends_on: [] label: ACP session mode prominence: minor openhands_settings_section: key: acp label: ACP (Agent Client Protocol) variant: acp acp_prompt_timeout: type: number exclusiveMinimum: 0 title: Acp Prompt Timeout description: >- Inactivity timeout (seconds) for a single ACP prompt() round-trip. The deadline resets on every update from the ACP server, so a steadily-progressing agent keeps running; the prompt is only aborted after this many seconds with no activity at all. default: 1800 openhands_settings: depends_on: [] label: ACP prompt inactivity timeout (seconds) prominence: minor openhands_settings_section: key: acp label: ACP (Agent Client Protocol) variant: acp acp_startup_timeout: type: number exclusiveMinimum: 0 title: Acp Startup Timeout description: >- Timeout (seconds) for ACP server startup: spawning the subprocess, the initialize/authenticate handshake, and new_session()/load_session(). A hard deadline, unlike acp_prompt_timeout, since startup has no intermediate progress signal to reset it against. default: 90 openhands_settings: depends_on: [] label: ACP startup timeout (seconds) prominence: minor openhands_settings_section: key: acp label: ACP (Agent Client Protocol) variant: acp mcp_config: additionalProperties: $ref: '#/components/schemas/MCPServer-Output' type: object title: Mcp Config description: >- MCP servers to make available to the ACP subprocess. Unlike the OpenHands agent — where these become in-process MCP tools — the servers are forwarded to the ACP server at session creation and it owns the connection. Remote (http/sse) servers are only forwarded when the ACP server advertises support for that transport; stdio servers (which run inside the runtime) are always forwarded. openhands_settings: depends_on: [] label: MCP servers prominence: minor variant: acp acp_isolate_data_dir: type: boolean title: Acp Isolate Data Dir description: >- Give the ACP subprocess a per-conversation CLI data/config root instead of the shared user HOME. Forwarded to :attr:`~openhands.sdk.agent.ACPAgent.acp_isolate_data_dir`; off by default. Enable from the deploying application when several conversations share one sandbox (see #1019). default: false acp_file_secrets: items: $ref: '#/components/schemas/ACPFileSecretSpec' type: array title: Acp File Secrets description: >- Reserved 'file-content' credential secrets the SDK materialises to disk before launching the ACP subprocess (e.g. Codex auth.json, Gemini Vertex SA JSON). Defaults to the built-in supported providers; override to support other ACP servers with different file-auth schemes. llm: $ref: '#/components/schemas/LLM-Output' description: >- DEPRECATED (removed in 1.33.0): LLM identity used for cost/token attribution. The ACP subprocess makes its own model calls; ``acp_model`` is the model identity. Credentials set here (``api_key`` / ``base_url``) are ignored — route provider credentials through the conversation secrets channel (agent_context.secrets / StartConversationRequest.secrets, which route through state.secret_registry), keyed by the provider's env var name. openhands_settings_section: key: llm label: LLM (for metrics) variant: acp agent_context: anyOf: - $ref: '#/components/schemas/AgentContext-Output' - type: 'null' description: >- Prompt-only context for the ACP server. ``secrets`` here are advertised to the agent (names/descriptions) and reach the subprocess env through ``state.secret_registry``: ``LocalConversation`` seeds ``agent_context.secrets`` into the registry at conversation init (below ``request.secrets``), so callers that build the request outside Python (e.g. canvas-local) are covered too, not just the ``create_request`` path. Provider credentials belong here (or in ``request.secrets``) keyed by the provider's env var name. type: object title: ACPAgentSettings description: >- Settings for an ACP (Agent Client Protocol) agent. ``create_agent()`` returns an :class:`ACPAgent` that delegates to a subprocess ACP server. The ACP server manages its own system prompt, tools, MCP, and (primary) LLM calls; those fields from :class:`OpenHandsAgentSettings` do not apply here. ``ACPAgent`` uses the :attr:`llm` field purely for cost/token attribution, never for LLM requests; :attr:`acp_model` is the model identity. Any credentials set on it (``llm.api_key`` / ``llm.base_url``) are ignored — provider credentials ride the conversation secrets channel (``request.secrets`` / ``agent_context.secrets`` → ``state.secret_registry``) keyed by the provider's env var name (:attr:`api_key_env_var`). ConversationSettings: properties: schema_version: type: integer minimum: 1 title: Schema Version default: 1 max_iterations: type: integer minimum: 1 title: Max Iterations description: >- Maximum number of iterations the conversation will run before stopping. default: 500 openhands_settings: depends_on: [] label: Max iterations prominence: major confirmation_mode: type: boolean title: Confirmation Mode description: Require user confirmation before executing risky actions. default: false openhands_settings: depends_on: [] label: Confirmation mode prominence: critical openhands_settings_section: key: verification label: Verification security_analyzer: anyOf: - type: string enum: - llm - none - type: 'null' title: Security Analyzer description: Security analyzer that evaluates actions before execution. default: llm openhands_settings: depends_on: - confirmation_mode label: Security analyzer prominence: major openhands_settings_section: key: verification label: Verification type: object title: ConversationSettings ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError LLM-Output: properties: model: type: string title: Model description: Model name. default: gpt-5.5 openhands_settings: depends_on: [] prominence: critical api_key: anyOf: - type: string - type: string format: password writeOnly: true - type: 'null' title: Api Key description: API key. openhands_settings: depends_on: [] label: API Key prominence: critical auth_type: type: string enum: - api_key - subscription title: Auth Type description: Authentication mode for the LLM. default: api_key openhands_settings: depends_on: [] label: Authentication prominence: critical subscription_vendor: anyOf: - type: string const: openai - type: 'null' title: Subscription Vendor description: Subscription provider for subscription-backed LLM access. openhands_settings: depends_on: - auth_type label: Subscription provider prominence: critical base_url: anyOf: - type: string - type: 'null' title: Base Url description: Custom base URL. openhands_settings: depends_on: [] prominence: major api_version: anyOf: - type: string - type: 'null' title: Api Version description: API version (e.g., Azure). openhands_settings: depends_on: [] prominence: minor aws_access_key_id: anyOf: - type: string - type: string format: password writeOnly: true - type: 'null' title: Aws Access Key Id openhands_settings: depends_on: [] prominence: minor aws_secret_access_key: anyOf: - type: string - type: string format: password writeOnly: true - type: 'null' title: Aws Secret Access Key openhands_settings: depends_on: [] prominence: minor aws_session_token: anyOf: - type: string - type: string format: password writeOnly: true - type: 'null' title: Aws Session Token openhands_settings: depends_on: [] prominence: minor aws_region_name: anyOf: - type: string - type: 'null' title: Aws Region Name openhands_settings: depends_on: [] prominence: minor aws_profile_name: anyOf: - type: string - type: 'null' title: Aws Profile Name openhands_settings: depends_on: [] prominence: minor aws_role_name: anyOf: - type: string - type: 'null' title: Aws Role Name openhands_settings: depends_on: [] prominence: minor aws_session_name: anyOf: - type: string - type: 'null' title: Aws Session Name openhands_settings: depends_on: [] prominence: minor aws_bedrock_runtime_endpoint: anyOf: - type: string - type: 'null' title: Aws Bedrock Runtime Endpoint openhands_settings: depends_on: [] prominence: minor openrouter_site_url: type: string title: Openrouter Site Url default: https://docs.all-hands.dev/ openhands_settings: depends_on: [] prominence: minor openrouter_app_name: type: string title: Openrouter App Name default: OpenHands openhands_settings: depends_on: [] prominence: minor num_retries: type: integer minimum: 0 title: Num Retries default: 5 openhands_settings: depends_on: [] prominence: minor retry_multiplier: type: number minimum: 0 title: Retry Multiplier default: 8 openhands_settings: depends_on: [] prominence: minor retry_min_wait: type: integer minimum: 0 title: Retry Min Wait default: 8 openhands_settings: depends_on: [] prominence: minor retry_max_wait: type: integer minimum: 0 title: Retry Max Wait default: 64 openhands_settings: depends_on: [] prominence: minor timeout: anyOf: - type: integer minimum: 0 - type: 'null' title: Timeout description: >- HTTP timeout in seconds. Default is 300s (5 minutes). Set to None to disable timeout (not recommended for production). default: 300 openhands_settings: depends_on: [] prominence: minor max_message_chars: type: integer minimum: 1 title: Max Message Chars description: Approx max chars in each event/content sent to the LLM. default: 30000 openhands_settings: depends_on: [] prominence: minor temperature: anyOf: - type: number minimum: 0 - type: 'null' title: Temperature description: >- Sampling temperature for response generation. Defaults to None (uses provider default temperature). Set to 0.0 for deterministic outputs, or higher values (0.7-1.0) for more creative responses. openhands_settings: depends_on: [] prominence: minor top_p: anyOf: - type: number maximum: 1 minimum: 0 - type: 'null' title: Top P description: >- Nucleus sampling parameter. Defaults to None (uses provider default). Set to a value between 0 and 1 to control diversity of outputs. openhands_settings: depends_on: [] prominence: minor top_k: anyOf: - type: number minimum: 0 - type: 'null' title: Top K openhands_settings: depends_on: [] prominence: minor max_input_tokens: anyOf: - type: integer minimum: 1 - type: 'null' title: Max Input Tokens description: >- The maximum number of input tokens. Note that this is currently unused, and the value at runtime is actually the total tokens in OpenAI (e.g. 128,000 tokens for GPT-4). openhands_settings: depends_on: [] prominence: minor max_output_tokens: anyOf: - type: integer minimum: 1 - type: 'null' title: Max Output Tokens description: The maximum number of output tokens. This is sent to the LLM. openhands_settings: depends_on: [] prominence: minor model_canonical_name: anyOf: - type: string - type: 'null' title: Model Canonical Name description: >- Optional canonical model name for feature registry lookups. The OpenHands SDK maintains a model feature registry that maps model names to capabilities (e.g., vision support, prompt caching, responses API support). When using proxied or aliased model identifiers, set this field to the canonical model name (e.g., 'openai/gpt-4o') to ensure correct capability detection. If not provided, the 'model' field will be used for capability lookups. openhands_settings: depends_on: [] prominence: minor api_mode: type: string enum: - auto - chat - responses title: Api Mode description: >- LLM API endpoint mode. 'auto' resolves from model metadata and SDK fallbacks; use 'chat' or 'responses' to override endpoint selection for proxy aliases and newly released models. default: auto openhands_settings: depends_on: [] prominence: minor capability_overrides: additionalProperties: anyOf: - type: boolean - type: string type: object title: Capability Overrides description: >- Explicit model capability overrides. Supported keys include supports_reasoning_effort, thinking_mode (adaptive, manual, none, or unknown), supports_sampling_params, supports_prompt_cache, supports_stop_words, supports_responses_api, supports_vision, and supports_prompt_cache_retention. Overrides take precedence over LiteLLM metadata and SDK fallbacks. openhands_settings: depends_on: [] prominence: minor extra_headers: anyOf: - additionalProperties: type: string type: object - type: 'null' title: Extra Headers description: Optional HTTP headers to forward to LiteLLM requests. openhands_settings: depends_on: [] prominence: minor input_cost_per_token: anyOf: - type: number minimum: 0 - type: 'null' title: Input Cost Per Token description: The cost per input token. This will available in logs for user. openhands_settings: depends_on: [] prominence: minor output_cost_per_token: anyOf: - type: number minimum: 0 - type: 'null' title: Output Cost Per Token description: The cost per output token. This will available in logs for user. openhands_settings: depends_on: [] prominence: minor ollama_base_url: anyOf: - type: string - type: 'null' title: Ollama Base Url openhands_settings: depends_on: [] prominence: minor stream: type: boolean title: Stream description: >- Enable streaming responses from the LLM. When enabled, the provided `on_token` callback in .completions and .responses will be invoked for each chunk of tokens. default: false openhands_settings: depends_on: [] prominence: minor drop_params: type: boolean title: Drop Params default: true openhands_settings: depends_on: [] prominence: minor modify_params: type: boolean title: Modify Params description: >- Modify params allows litellm to do transformations like adding a default message, when a message is empty. default: true openhands_settings: depends_on: [] prominence: minor disable_vision: anyOf: - type: boolean - type: 'null' title: Disable Vision description: >- If model is vision capable, this option allows to disable image processing (useful for cost reduction). openhands_settings: depends_on: [] prominence: minor disable_stop_word: anyOf: - type: boolean - type: 'null' title: Disable Stop Word description: Disable using of stop word. default: false openhands_settings: depends_on: [] prominence: minor caching_prompt: type: boolean title: Caching Prompt description: Enable caching of prompts. default: true openhands_settings: depends_on: [] prominence: minor log_completions: type: boolean title: Log Completions description: Enable logging of completions. default: false openhands_settings: depends_on: [] prominence: minor log_completions_folder: type: string title: Log Completions Folder description: >- The folder to log LLM completions to. Required if log_completions is True. default: logs/completions openhands_settings: depends_on: [] prominence: minor custom_tokenizer: anyOf: - type: string - type: 'null' title: Custom Tokenizer description: A custom tokenizer to use for token counting. openhands_settings: depends_on: [] prominence: minor native_tool_calling: type: boolean title: Native Tool Calling description: Whether to use native tool calling. default: true openhands_settings: depends_on: [] prominence: minor force_string_serializer: anyOf: - type: boolean - type: 'null' title: Force String Serializer description: >- Force using string content serializer when sending to LLM API. If None (default), auto-detect based on model. Useful for providers that do not support list content, like HuggingFace and Groq. openhands_settings: depends_on: [] prominence: minor inline_image_urls: anyOf: - type: boolean - type: 'null' title: Inline Image Urls description: >- If True, fetch any http(s) image URL in outgoing messages and inline it as a base64 ``data:`` URL before sending. If None (default), auto-detect based on model (some APIs such as Moonshot's public Kimi endpoint reject URL-formatted images and require base64). Set this explicitly when the model is reached through a proxy alias that hides the underlying provider (e.g. ``litellm_proxy/``). Note: inlining only runs when ``vision_is_active()`` is True, so the alias must still be recognised as vision-capable by the SDK feature registry or proxy model metadata. openhands_settings: depends_on: [] prominence: minor reasoning_effort: anyOf: - type: string enum: - low - medium - high - xhigh - none - type: 'null' title: Reasoning Effort description: >- Provider-neutral reasoning effort. Common values include 'none', 'minimal', 'low', 'medium', 'high', 'xhigh', and 'max'. The SDK accepts future provider values and lets LiteLLM translate them. default: high openhands_settings: depends_on: [] prominence: minor reasoning_summary: anyOf: - type: string enum: - auto - concise - detailed - type: 'null' title: Reasoning Summary description: >- The level of detail for reasoning summaries. This is a string that can be one of 'auto', 'concise', or 'detailed'. Requires verified OpenAI organization. Only sent when explicitly set. openhands_settings: depends_on: [] prominence: minor enable_encrypted_reasoning: type: boolean title: Enable Encrypted Reasoning description: >- If True, ask for ['reasoning.encrypted_content'] in Responses API include. default: true openhands_settings: depends_on: [] prominence: minor prompt_cache_retention: anyOf: - type: string - type: 'null' title: Prompt Cache Retention description: >- Retention policy for prompt cache. Only sent for supported models (GPT-5+ and GPT-4.1, excluding Azure deployments); explicitly stripped for all others. default: 24h openhands_settings: depends_on: [] prominence: minor extended_thinking_budget: anyOf: - type: integer - type: 'null' title: Extended Thinking Budget description: >- Legacy token budget for models confirmed to use manual Anthropic extended thinking. Ignored for adaptive-thinking models. Prefer reasoning_effort for new integrations. default: 200000 openhands_settings: depends_on: [] prominence: minor seed: anyOf: - type: integer - type: 'null' title: Seed description: The seed to use for random number generation. openhands_settings: depends_on: [] prominence: minor usage_id: type: string title: Usage Id description: >- Unique usage identifier for the LLM. Used for registry lookups, telemetry, and spend tracking. default: default openhands_settings: depends_on: [] prominence: minor litellm_extra_body: additionalProperties: true type: object title: Litellm Extra Body description: >- Additional key-value pairs to pass to litellm's extra_body parameter. This is useful for custom inference endpoints that need additional parameters for configuration, routing, or advanced features. NOTE: Not all LLM providers support extra_body parameters. Some providers (e.g., OpenAI) may reject requests with unrecognized options. This is commonly supported by: - LiteLLM proxy servers (routing metadata, tracing) - vLLM endpoints (return_token_ids, etc.) - Custom inference clusters Examples: - Proxy routing: {'trace_version': '1.0.0', 'tags': ['agent:my-agent']} - vLLM features: {'return_token_ids': True} openhands_settings: depends_on: [] prominence: minor is_subscription: type: boolean title: Is Subscription description: >- Whether this LLM uses subscription-based authentication. Serialized so that subscription-specific request handling survives transport to a remote agent-server. readOnly: true type: object required: - is_subscription title: LLM description: >- Language model interface for OpenHands agents. The LLM class provides a unified interface for interacting with various language models through the litellm library. It handles model configuration, API authentication, retry logic, and tool calling capabilities. Attributes: model: Model name (e.g., "gpt-5.5"). api_key: API key for authentication. base_url: Custom API base URL. num_retries: Number of retry attempts for failed requests. timeout: Request timeout in seconds. Example: ```python from openhands.sdk import LLM from pydantic import SecretStr llm = LLM( model="gpt-5.5", api_key=SecretStr("your-api-key"), usage_id="my-agent" ) # Use with agent or conversation ``` openhands__sdk__tool__spec__Tool: properties: name: type: string title: Name description: >- Name of the tool class, e.g., 'TerminalTool'. Import it from an `openhands.tools.` subpackage. examples: - TerminalTool - FileEditorTool - TaskTrackerTool params: additionalProperties: true type: object title: Params description: >- Parameters for the tool's .create() method, e.g., {'working_dir': '/app'} examples: - working_dir: /workspace type: object required: - name title: Tool description: |- Defines a tool to be initialized for the agent. This is only used in agent-sdk for type schema for server use. MCPServer-Output: properties: url: anyOf: - type: string minLength: 1 - type: 'null' title: Url transport: anyOf: - type: string enum: - stdio - http - sse - streamable-http - type: 'null' title: Transport command: anyOf: - type: string minLength: 1 - type: 'null' title: Command args: anyOf: - items: type: string type: array - type: 'null' title: Args env: anyOf: - additionalProperties: anyOf: - type: string - type: 'null' type: object - type: 'null' title: Env cwd: anyOf: - type: string - type: 'null' title: Cwd description: anyOf: - type: string - type: 'null' title: Description icon: anyOf: - type: string - type: 'null' title: Icon timeout: anyOf: - type: number - type: 'null' title: Timeout sse_read_timeout: anyOf: - type: number - type: 'null' title: Sse Read Timeout keep_alive: anyOf: - type: boolean - type: 'null' title: Keep Alive headers: anyOf: - additionalProperties: anyOf: - type: string - type: 'null' type: object - type: 'null' title: Headers auth: anyOf: - oneOf: - $ref: '#/components/schemas/MCPNoneAuthCredential' - $ref: '#/components/schemas/MCPApiKeyAuthCredential-Output' - $ref: '#/components/schemas/MCPBearerAuthCredential-Output' - $ref: '#/components/schemas/MCPBasicAuthCredential-Output' - $ref: '#/components/schemas/MCPHeaderAuthCredential-Output' - $ref: '#/components/schemas/MCPOAuthAuthCredential-Output' discriminator: propertyName: strategy mapping: api_key: $ref: '#/components/schemas/MCPApiKeyAuthCredential-Output' basic: $ref: '#/components/schemas/MCPBasicAuthCredential-Output' bearer: $ref: '#/components/schemas/MCPBearerAuthCredential-Output' header: $ref: '#/components/schemas/MCPHeaderAuthCredential-Output' none: $ref: '#/components/schemas/MCPNoneAuthCredential' oauth2: $ref: '#/components/schemas/MCPOAuthAuthCredential-Output' - type: 'null' title: Auth enabled: type: boolean title: Enabled description: >- Whether this server is exposed to the agent. A disabled server stays fully configured -- including its secrets -- but is skipped when MCP tools are created and when servers are forwarded to an ACP subprocess. default: true additionalProperties: false type: object title: MCPServer description: One MCP server in the settings DataModel. AgentContext-Output: properties: skills: items: $ref: '#/components/schemas/Skill-Output' type: array title: Skills description: List of available skills that can extend the user's input. acp_compatible: true system_message_suffix: anyOf: - type: string - type: 'null' title: System Message Suffix description: Optional suffix to append to the system prompt. acp_compatible: true user_message_suffix: anyOf: - type: string - type: 'null' title: User Message Suffix description: Optional suffix to append to the user's message. acp_compatible: true load_user_skills: type: boolean title: Load User Skills description: >- Whether to automatically load user skills from ~/.openhands/skills/ and ~/.openhands/microagents/ (for backward compatibility). default: false acp_compatible: true load_public_skills: type: boolean title: Load Public Skills description: >- Whether to automatically load skills from the public OpenHands skills repository at https://github.com/OpenHands/extensions. This allows you to get the latest skills without SDK updates. default: false acp_compatible: true marketplace_path: anyOf: - type: string - type: 'null' title: Marketplace Path description: >- Relative marketplace JSON path within the public skills repository. Set to None to load all public skills without marketplace filtering. default: marketplaces/default.json acp_compatible: true registered_marketplaces: items: $ref: >- #/components/schemas/openhands__sdk__marketplace__registration__MarketplaceRegistration type: array title: Registered Marketplaces description: >- Marketplace registrations for plugin resolution. Registrations with auto_load=True or a list of plugin names are resolved by LocalConversation at startup. acp_compatible: true load_project_skills: type: boolean title: Load Project Skills description: >- Whether to automatically load project skills from the conversation workspace (e.g. .openhands/skills/, AGENTS.md). Unlike load_user_skills / load_public_skills, this flag is not resolved by AgentContext itself (the workspace path is unknown at validation time); LocalConversation resolves it lazily on the first send_message() / run(), when the workspace is known. Also unlike load_user_skills / load_public_skills (which yield to explicit skills on a name conflict), resolved project skills are authoritative: a project skill overrides a same-named skill already present in `skills`. default: false acp_compatible: true load_memory: type: boolean title: Load Memory description: >- Whether to load persistent agent memory (MEMORY.md indexes under ~/.openhands/memory/ and /.openhands/memory/) into the system prompt. Like load_project_skills, this flag is not resolved by AgentContext itself (the workspace path is unknown at validation time); LocalConversation resolves it lazily on the first send_message() / run() and stores the result in memory_context. default: false acp_compatible: true openhands_settings: depends_on: [] label: Persistent memory prominence: major disabled_skills: items: type: string type: array title: Disabled Skills description: >- Names of skills to EXCLUDE from this context — a deny-list applied after every skill source is loaded (auto-loaded user/public, explicit, and lazily-loaded project skills). A listed name absent from the loaded set is a harmless no-op. [] (the default) keeps every skill. This is the single, drift-tolerant skill-selection mechanism (agent profiles set it from their own deny-list; #4017). acp_compatible: true secrets: anyOf: - additionalProperties: true type: object - type: 'null' title: Secrets description: >- Dictionary mapping secret keys to values or secret sources. Secrets are used for authentication and sensitive data handling. Values can be either strings or SecretSource instances (str | SecretSource). acp_compatible: true current_datetime: anyOf: - type: string format: date-time - type: string - type: 'null' title: Current Datetime description: >- Current date and time information to provide to the agent. Can be a datetime object (which will be formatted as ISO 8601) or a pre-formatted string. When provided, this information is included in the system prompt to give the agent awareness of the current time context. Defaults to the current (timezone-aware) datetime. acp_compatible: true type: object title: AgentContext description: >- Central structure for managing prompt extension. AgentContext unifies all the contextual inputs that shape how the system extends and interprets user prompts. It combines both static environment details and dynamic, user-activated extensions from skills. Specifically, it provides: - **Repository context / Repo Skills**: Information about the active codebase, branches, and repo-specific instructions contributed by repo skills. - **Runtime context**: Current execution environment (hosts, working directory, secrets, date, etc.). - **Conversation instructions**: Optional task- or channel-specific rules that constrain or guide the agent’s behavior across the session. - **Knowledge Skills**: Extensible components that can be triggered by user input to inject knowledge or domain-specific guidance. Together, these elements make AgentContext the primary container responsible for assembling, formatting, and injecting all prompt-relevant context into LLM interactions. LLMSummarizingCondenserSettings: properties: enabled: type: boolean title: Enabled description: Enable conversation memory condensation. default: true openhands_settings: depends_on: [] label: Enable memory condensation prominence: critical max_size: type: integer minimum: 20 title: Max Size description: >- Maximum number of events kept before the condenser runs. Kept on the base settings class for compatibility; concrete condenser-settings variants may opt out when this does not apply. default: 240 openhands_settings: depends_on: - enabled label: Max size prominence: minor condenser_kind: type: string const: llm_summarizing title: Condenser Kind description: >- Discriminator for the condenser settings union. ``'llm_summarizing'`` selects the default LLM summarizing condenser. default: llm_summarizing openhands_settings: depends_on: [] prominence: minor max_tokens: anyOf: - type: integer exclusiveMinimum: 0 - type: 'null' title: Max Tokens description: >- Maximum number of tokens allowed before the condenser runs. When unset, condensation is only based on event count. openhands_settings: depends_on: - enabled label: Max tokens prominence: minor keep_first: type: integer minimum: 0 title: Keep First description: Minimum number of initial events to preserve before condensation. default: 2 openhands_settings: depends_on: - enabled label: Keep first prominence: minor minimum_progress: type: number exclusiveMaximum: 1 exclusiveMinimum: 0 title: Minimum Progress description: >- Minimum fraction of events that must be condensed for condensation to be considered successful. default: 0.1 openhands_settings: depends_on: - enabled label: Minimum progress prominence: minor hard_context_reset_max_retries: type: integer exclusiveMinimum: 0 title: Hard Context Reset Max Retries description: Number of hard context reset attempts before raising an error. default: 5 openhands_settings: depends_on: - enabled label: Hard reset retries prominence: minor hard_context_reset_context_scaling: type: number exclusiveMaximum: 1 exclusiveMinimum: 0 title: Hard Context Reset Context Scaling description: >- Factor used to reduce event string size after a hard context reset summarization failure. default: 0.8 openhands_settings: depends_on: - enabled label: Hard reset scaling prominence: minor type: object title: LLMSummarizingCondenserSettings description: Settings for the default LLM summarizing condenser. NoOpCondenserSettings: properties: enabled: type: boolean title: Enabled description: Enable conversation memory condensation. default: true openhands_settings: depends_on: [] label: Enable memory condensation prominence: critical condenser_kind: type: string const: no_op title: Condenser Kind description: >- Discriminator for the condenser settings union. ``'no_op'`` selects a condenser that leaves conversation views unchanged. default: no_op openhands_settings: depends_on: [] prominence: minor type: object title: NoOpCondenserSettings description: Settings for a condenser that leaves conversation views unchanged. VerificationSettings: properties: critic_enabled: type: boolean title: Critic Enabled description: Enable critic evaluation for the agent. default: false openhands_settings: depends_on: [] label: Enable critic prominence: critical critic_mode: type: string enum: - finish_and_message - all_actions title: Critic Mode description: When critic evaluation should run. default: finish_and_message openhands_settings: depends_on: - critic_enabled label: Critic mode prominence: minor enable_iterative_refinement: type: boolean title: Enable Iterative Refinement description: >- Automatically retry tasks when critic scores fall below the threshold. default: false openhands_settings: depends_on: - critic_enabled label: Enable iterative refinement prominence: critical critic_threshold: type: number maximum: 1 minimum: 0 title: Critic Threshold description: Critic success threshold used for iterative refinement. default: 0.6 openhands_settings: depends_on: - critic_enabled - enable_iterative_refinement label: Critic threshold prominence: minor max_refinement_iterations: type: integer minimum: 1 title: Max Refinement Iterations description: Maximum number of refinement attempts after critic feedback. default: 3 openhands_settings: depends_on: - critic_enabled - enable_iterative_refinement label: Max refinement iterations prominence: minor critic_server_url: anyOf: - type: string - type: 'null' title: Critic Server Url description: >- Override the critic service URL. When None, the APIBasedCritic default is used. openhands_settings: depends_on: - critic_enabled label: Critic server URL prominence: minor critic_model_name: anyOf: - type: string - type: 'null' title: Critic Model Name description: >- Override the critic model name. When None, the APIBasedCritic default is used. openhands_settings: depends_on: - critic_enabled label: Critic model name prominence: minor critic_api_key: title: Critic Api Key description: >- API key used to authenticate with the critic service. When None, the LLM's ``api_key`` is reused, which preserves the auto-configuration path for the All-Hands LLM proxy. openhands_settings: depends_on: - critic_enabled label: Critic API Key prominence: critical type: object title: VerificationSettings description: Critic and iterative-refinement settings for the agent. ACPFileSecretSpec: properties: secret_name: type: string minLength: 1 title: Secret Name filename: type: string minLength: 1 title: Filename env_var: type: string minLength: 1 title: Env Var subdir: type: string minLength: 1 title: Subdir env_points_to: type: string enum: - dir - file title: Env Points To default: file warn_if_unset: items: type: string type: array title: Warn If Unset default: [] type: object required: - secret_name - filename - env_var - subdir title: ACPFileSecretSpec description: >- Declarative mapping from a reserved "file-content" secret to a credential file the ACP subprocess authenticates from. Some providers read their credential from a *file on disk* rather than an env var: Codex reads ``$CODEX_HOME/auth.json``; Gemini (Vertex AI) reads a service-account JSON pointed at by ``GOOGLE_APPLICATION_CREDENTIALS``. The user supplies that credential as a pasted blob — a reserved secret named :attr:`secret_name` — and :class:`~openhands.sdk.agent.ACPAgent` materialises it to :attr:`filename` under the conversation's durable per-conversation root (seed-if-absent), then sets :attr:`env_var` so the CLI can find it. Materialisation is keyed off :attr:`secret_name` (not the launch command), so a custom or aliased ``acp_command`` still works as long as the reserved secret is supplied. The SDK owns the *mechanism* (writing the file in the runtime pod, setting the env var, seed-if-absent, permissions); the *policy* — which secrets map to which files for which CLIs — lives in these specs. Built-in defaults cover the supported providers, but downstream applications can override :attr:`~openhands.sdk.agent.ACPAgent.acp_file_secrets` to support other ACP servers with different file-auth schemes without an SDK change. MCPNoneAuthCredential: properties: strategy: type: string const: none title: Strategy type: object required: - strategy title: MCPNoneAuthCredential MCPApiKeyAuthCredential-Output: properties: strategy: type: string const: api_key title: Strategy value: anyOf: - type: string - type: 'null' title: Value header_name: anyOf: - type: string - type: 'null' title: Header Name type: object required: - strategy title: MCPApiKeyAuthCredential MCPBearerAuthCredential-Output: properties: strategy: type: string const: bearer title: Strategy value: anyOf: - type: string - type: 'null' title: Value type: object required: - strategy title: MCPBearerAuthCredential MCPBasicAuthCredential-Output: properties: strategy: type: string const: basic title: Strategy username: type: string title: Username password: anyOf: - type: string - type: 'null' title: Password type: object required: - strategy - username title: MCPBasicAuthCredential MCPHeaderAuthCredential-Output: properties: strategy: type: string const: header title: Strategy headers: additionalProperties: anyOf: - type: string - type: 'null' type: object title: Headers type: object required: - strategy title: MCPHeaderAuthCredential MCPOAuthAuthCredential-Output: properties: strategy: type: string const: oauth2 title: Strategy authentication: anyOf: - $ref: '#/components/schemas/MCPOAuthAuthentication-Output' - type: 'null' state: anyOf: - $ref: '#/components/schemas/MCPOAuthState-Output' - type: 'null' type: object required: - strategy title: MCPOAuthAuthCredential Skill-Output: properties: name: type: string title: Name content: type: string title: Content trigger: anyOf: - oneOf: - $ref: '#/components/schemas/KeywordTrigger' - $ref: '#/components/schemas/TaskTrigger' - $ref: '#/components/schemas/PathTrigger' discriminator: propertyName: type mapping: keyword: $ref: '#/components/schemas/KeywordTrigger' path: $ref: '#/components/schemas/PathTrigger' task: $ref: '#/components/schemas/TaskTrigger' - type: 'null' title: Trigger description: >- Trigger determines when skill content is auto-injected. None = no auto-injection (for AgentSkills: agent reads on demand; for legacy: full content always in system prompt). KeywordTrigger = auto-inject when keywords appear in user messages. TaskTrigger = auto-inject for specific tasks, may require user input. source: anyOf: - type: string - type: 'null' title: Source description: >- The source path or identifier of the skill. When it is None, it is treated as a programmatically defined skill. mcp_tools: anyOf: - additionalProperties: additionalProperties: true type: object type: object - type: 'null' title: Mcp Tools description: MCP servers for the skill (repo skills only). inputs: items: $ref: '#/components/schemas/InputMetadata' type: array title: Inputs description: Input metadata for the skill (task skills only) is_agentskills_format: type: boolean title: Is Agentskills Format description: >- Whether this skill was loaded from a SKILL.md file following the AgentSkills standard. AgentSkills-format skills use progressive disclosure: always listed in with name, description, and location. If the skill also has triggers, content is auto-injected when triggered AND agent can read file anytime. default: false version: type: string title: Version description: Skill version (AgentSkills standard field). default: 1.0.0 description: anyOf: - type: string - type: 'null' title: Description description: >- A brief description of what the skill does and when to use it. Descriptions exceeding MAX_DESCRIPTION_LENGTH are truncated with a notice pointing to the skill's source path. license: anyOf: - type: string - type: 'null' title: License description: >- The license under which the skill is distributed. AgentSkills standard field (e.g., 'Apache-2.0', 'MIT'). compatibility: anyOf: - type: string - type: 'null' title: Compatibility description: >- Environment requirements or compatibility notes for the skill. AgentSkills standard field (e.g., 'Requires git and docker'). metadata: anyOf: - additionalProperties: type: string type: object - type: 'null' title: Metadata description: >- Arbitrary key-value metadata for the skill. AgentSkills standard field for extensibility. allowed_tools: anyOf: - items: type: string type: array - type: 'null' title: Allowed Tools description: >- List of pre-approved tools for this skill. AgentSkills standard field (parsed from space-delimited string). disable_model_invocation: type: boolean title: Disable Model Invocation description: >- Whether this skill can only be activated by trigger matching and should not be advertised to the model for direct invocation. default: false resources: anyOf: - $ref: '#/components/schemas/SkillResources' - type: 'null' description: >- Resource directories for the skill (scripts/, references/, assets/). AgentSkills standard field. Only populated for SKILL.md directory format. type: object required: - name - content title: Skill description: >- A skill provides specialized knowledge or functionality. Skill behavior depends on format (is_agentskills_format) and trigger: AgentSkills format (SKILL.md files): - Always listed in with name, description, location - Agent reads full content on demand (progressive disclosure) - If has triggers: content is ALSO auto-injected when triggered Legacy OpenHands format: - With triggers: Listed in , content injected on trigger - Without triggers (None): Full content in , always active This model supports both OpenHands-specific fields and AgentSkills standard fields (https://agentskills.io/specification) for cross-platform compatibility. openhands__sdk__marketplace__registration__MarketplaceRegistration: properties: name: type: string title: Name description: Identifier for this marketplace registration source: type: string title: Source description: 'Marketplace source: ''github:owner/repo'', git URL, or local path' ref: anyOf: - type: string - type: 'null' title: Ref description: Optional branch, tag, or commit for git sources repo_path: anyOf: - type: string - type: 'null' title: Repo Path description: >- Subdirectory path within the git repository containing the marketplace. Only relevant for git sources. auto_load: anyOf: - type: boolean - items: type: string type: array title: Auto Load description: >- Whether to load marketplace plugins and standalone skills at conversation start. Use True for all, False or [] for none, or a list of plugin/skill names for selective loading. default: false type: object required: - name - source title: MarketplaceRegistration description: Registration for a marketplace source used for plugin resolution. MCPOAuthAuthentication-Output: properties: type: type: string const: oauth title: Type client_auth_method: anyOf: - type: string enum: - none - client_secret_post - client_secret_basic - private_key_jwt - type: 'null' title: Client Auth Method scopes: anyOf: - type: string - items: type: string type: array - type: 'null' title: Scopes client_name: anyOf: - type: string - type: 'null' title: Client Name client_metadata_url: anyOf: - type: string - type: 'null' title: Client Metadata Url client_id: anyOf: - type: string - type: 'null' title: Client Id client_secret: anyOf: - type: string - type: 'null' title: Client Secret additional_client_metadata: anyOf: - additionalProperties: true type: object - type: 'null' title: Additional Client Metadata additionalProperties: false type: object required: - type title: MCPOAuthAuthentication MCPOAuthState-Output: properties: tokens: anyOf: - $ref: '#/components/schemas/MCPOAuthTokenState-Output' - type: 'null' client_info: anyOf: - $ref: '#/components/schemas/MCPOAuthClientInfoState-Output' - type: 'null' token_expires_at: anyOf: - type: number - type: 'null' title: Token Expires At type: object title: MCPOAuthState KeywordTrigger: properties: type: type: string const: keyword title: Type default: keyword keywords: items: type: string type: array title: Keywords type: object required: - keywords title: KeywordTrigger description: >- Trigger for keyword-based skills. These skills are activated when specific keywords appear in the user's query. TaskTrigger: properties: type: type: string const: task title: Type default: task triggers: items: type: string type: array title: Triggers type: object required: - triggers title: TaskTrigger description: >- Trigger for task-specific skills. These skills are activated for specific task types and can modify prompts. PathTrigger: properties: type: type: string const: path title: Type default: path paths: items: type: string type: array title: Paths type: object required: - paths title: PathTrigger description: >- Trigger for path-scoped skills ("rules"). These skills are activated when the agent touches a file whose path matches one of the ``paths`` glob patterns (gitignore-style ``**`` semantics). InputMetadata: properties: name: type: string title: Name description: Name of the input parameter description: type: string title: Description description: Description of the input parameter type: object required: - name - description title: InputMetadata description: Metadata for task skill inputs. SkillResources: properties: skill_root: type: string title: Skill Root description: Root directory of the skill (absolute path) scripts: items: type: string type: array title: Scripts description: List of script files in scripts/ directory (relative paths) references: items: type: string type: array title: References description: List of reference files in references/ directory (relative paths) assets: items: type: string type: array title: Assets description: List of asset files in assets/ directory (relative paths) type: object required: - skill_root title: SkillResources description: |- Resource directories for a skill (AgentSkills standard). Per the AgentSkills specification, skills can include: - scripts/: Executable scripts the agent can run - references/: Reference documentation and examples - assets/: Static assets (images, data files, etc.) MCPOAuthTokenState-Output: properties: access_token: anyOf: - type: string - type: 'null' title: Access Token refresh_token: anyOf: - type: string - type: 'null' title: Refresh Token additionalProperties: true type: object title: MCPOAuthTokenState MCPOAuthClientInfoState-Output: properties: client_secret: anyOf: - type: string - type: 'null' title: Client Secret additionalProperties: true type: object title: MCPOAuthClientInfoState securitySchemes: APIKeyHeader: type: apiKey in: header name: X-Access-Token ````