> ## Documentation Index > Fetch the complete documentation index at: https://docs.labelbox.com/llms.txt > Use this file to discover all available pages before exploring further. # Create a new immutable agent version > Creates a new immutable agent version from a full definition and moves the agent's latest pointer to it, in one atomic operation. base_agent_version_id must be the agent's current latest_agent_version_id or the request is rejected with 409 revision_conflict, so the caller can re-read and retry rather than silently racing another writer. Every field is full content, there is no partial-update or omit-to-inherit semantics, so an omitted field is cleared rather than carried over from the base version. Tags are changed only through the dedicated agent tag routes. Invalid model_config and unsupported reasoning_effort values return 400, including when the model catalog lists no exact options for the selected model; a model catalog that cannot be read to verify them returns 503. Of the response, only latest_agent_version_id is guaranteed to name the version this call minted: the other fields come from a read taken after the commit, so a concurrent writer's content can appear beneath that id. Read the version back with getAgentVersion when the exact published content matters. ## OpenAPI ````yaml /managed-agents/openapi.yaml post /managed-agents/v1/agents/{agent_id}/versions openapi: 3.1.0 info: title: Managed Agents API version: 0.13.0 description: >- The Recursion Managed Agents REST API. Authenticate with a Recursion API key as a bearer token. An organization-scoped key acts in its own organization and needs nothing else; a tenant-scoped key must also send `x-organization-id` with an organization id or `default`. Field names follow each operation's published schema. servers: - url: https://api.recursion.labelbox.com security: - bearerAuth: [] paths: /managed-agents/v1/agents/{agent_id}/versions: post: tags: - Agents summary: Create a new immutable agent version description: >- Creates a new immutable agent version from a full definition and moves the agent's latest pointer to it, in one atomic operation. base_agent_version_id must be the agent's current latest_agent_version_id or the request is rejected with 409 revision_conflict, so the caller can re-read and retry rather than silently racing another writer. Every field is full content, there is no partial-update or omit-to-inherit semantics, so an omitted field is cleared rather than carried over from the base version. Tags are changed only through the dedicated agent tag routes. Invalid model_config and unsupported reasoning_effort values return 400, including when the model catalog lists no exact options for the selected model; a model catalog that cannot be read to verify them returns 503. Of the response, only latest_agent_version_id is guaranteed to name the version this call minted: the other fields come from a read taken after the commit, so a concurrent writer's content can appear beneath that id. Read the version back with getAgentVersion when the exact published content matters. operationId: managedAgentsCreateAgentVersion parameters: - description: Agent id (UUID) as returned by createAgent or listAgents. in: path name: agent_id required: true schema: description: Agent id (UUID) as returned by createAgent or listAgents. format: uuid type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsCreateAgentVersionRequest' required: true responses: '201': content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsAgent' description: >- A configured agent: its versioned execution definition plus current mutable classification tags. Publishing the execution definition mints a new immutable AgentVersion; applying tags does not. A session records the version it ran and never snapshots tags. '400': description: The request was rejected by schema or semantic validation. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiError' '401': description: The caller is unauthenticated. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiError' '403': description: The caller lacks a required permission or capability. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiErrorForbidden' '404': description: No such resource is reachable for this caller. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiError' '409': description: >- The request conflicts with the resource state, or with an in-flight idempotent replay. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiError' '413': description: The request exceeds a size or transaction budget. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiError' '415': description: The request body uses a media type this operation does not accept. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiErrorUnsupportedMediaType' '429': headers: Retry-After: description: Seconds the caller should wait before retrying. schema: type: string style: simple description: A rate limit is exhausted. Honor `Retry-After`. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiError' '500': description: An unexpected server-side failure. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiError' '502': description: The service returned an invalid response. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiErrorBadGateway' '503': headers: Retry-After: description: Seconds the caller should wait before retrying. schema: type: string style: simple description: A dependency is unavailable. Retryable. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiError' '504': headers: Retry-After: description: When to retry, as delay seconds or an HTTP date. schema: type: string description: The service did not respond before the timeout. Retryable. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiErrorGatewayTimeout' components: schemas: ManagedAgentsCreateAgentVersionRequest: description: >- Request body for creating a new immutable agent version. Every field means what it means on createAgent -- full content is always required, there is no partial update -- except disabled_integration_mcp_providers, whose omission means none here rather than the new-agent default. base_agent_version_id must be the agent's current version or the request is rejected with revision_conflict so the caller can re-read and retry. properties: base_agent_version_id: description: >- The agent's current latest_agent_version_id, as returned by getAgent. Rejected with 409 revision_conflict if the agent has moved past this version. format: uuid type: string built_in_integrations: description: >- Built-in integrations this agent may use, each naming an active organization connection an admin added on the Integrations page. Sessions receive short-lived access restricted to exactly those apps and each connection's tool allow-list; nothing is granted through a vault. Omit or send [] for none. Carried in full on every version write. items: $ref: '#/components/schemas/ManagedAgentsBuiltInIntegrationRequest' maxItems: 25 type: array default_credential_refs: description: >- Individual default items within default_vault_ids. The list is a whitelist across every default vault, not a filter within one, so it must name every item the agent should receive. Omit to select every current item; [] alongside a non-empty default_vault_ids is rejected because it would select none. items: $ref: '#/components/schemas/ManagedAgentsVaultCredentialRefRequest' type: array default_rubric: description: >- Markdown rubric that sessions started from this agent are graded against when their create request omits an outcome. Must contain at least one gradeable criterion, written as markdown list items. A session that supplies its own outcome ignores this entirely. type: - 'null' - string default_vault_ids: description: >- Vaults granted by default when a session create request omits vault_ids. default_credential_refs may narrow their items. items: type: string type: array description: description: >- Optional free-text note about what the agent is for. Not sent to the model. type: string disabled_integration_mcp_providers: description: >- Native integration providers whose MCP tools sessions of this agent do not receive even though the grant is present. The grant still authenticates the provider's sandbox tools where it has any (git and gh for GitHub); the agent's own mcp_servers are never affected. Omission differs by operation: on createAgent it defaults to ["github"] (new agents use gh and git in the sandbox); on createAgentVersion it means none, as for every other field there; send [] to receive every provider's MCP tools. items: type: string type: array max_concurrent_sessions: description: >- Maximum number of this agent's root sessions that may run or wait on compute at once. Omit for unlimited. Sessions beyond the cap are accepted with execution_state=queued and wait until a slot frees. maximum: 10000 minimum: 1 type: - 'null' - integer mcp_servers: description: >- Remote MCP servers whose tools are added to the agent's tool surface. Each entry is an object with name and url, e.g. {"name": "docs", "url": "https://example.com/mcp"}. Credentials come from the vaults granted to the session, and the discovered tool list is snapshotted at session start, so a later edit here does not change a running session. items: additionalProperties: {} type: object type: array metadata: additionalProperties: {} description: >- Free-form caller-owned JSON stored with the agent and returned on reads. Not interpreted by the service and never sent to the model. type: object model: description: >- Model id, copied verbatim from the models catalog, GET /v1/models (e.g. anthropic/claude-sonnet-4-5). Reads return the stored form, which adds a provider prefix before that id. An id the catalog does not list is rejected with the list of ids that it does. type: string model_config: $ref: '#/components/schemas/ManagedAgentsInferenceConfigRequest' description: >- Default inference config applied to sessions started from this agent. Omit model_config or send {} to use provider defaults; null is invalid. reasoning_effort is normalized and validated for direct providers, and must exactly match the selected catalog model's supportedReasoningEfforts. An unsupported value, including any value for a catalog model that lists no exact options, returns 400; a model catalog that cannot be read to verify it returns 503. multiagent: additionalProperties: {} description: >- Multiagent roster: the delegation targets this agent may hand work to, an optional advisor entry, and the interventionist posture. Snapshotted at session start; a child roster may tighten the recursion depth ceiling, never widen it. type: object name: description: Human-readable label for the agent. Required. type: string nativeIntegrations: description: >- Native connections this agent may use, with provider-enforced permission and resource restrictions. Omit or send [] for none. Stored in full on each agent version; secrets remain on the connection. items: $ref: '#/components/schemas/ManagedAgentsNativeIntegrationRequest' maxItems: 25 type: array skills: description: >- Skill declarations made available to the agent, passed through as given and snapshotted into the session at start. Capped at the 100 skills a session can carry. items: additionalProperties: {} type: object maxItems: 100 type: array system: description: System prompt for the agent. type: string tools: deprecated: true description: >- Deprecated alias for toolsets; accepts only the bare evaluation marker. items: additionalProperties: false properties: type: description: The evaluation marker is the only supported toolset type. enum: - evaluation type: string required: - type type: object maxItems: 1 type: array toolsets: description: >- Only the bare {type: evaluation} marker is supported, for evaluator agents. Omit or send [] for ordinary agents; built-in sandbox tools, MCP servers, and skills do not require a toolset. The tools field is a deprecated alias. items: additionalProperties: false properties: type: description: The evaluation marker is the only supported toolset type. enum: - evaluation type: string required: - type type: object maxItems: 1 type: array web_search_enabled: default: true description: >- Whether sessions started from this agent may use the native web_search tool. Omit to enable it. The setting is snapshotted when a session starts. type: boolean required: - name - model - system - base_agent_version_id type: object example: base_agent_version_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d built_in_integrations: - connection_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d tools: - example default_credential_refs: - credential_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d vault_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d default_rubric: example default_vault_ids: - example description: example disabled_integration_mcp_providers: - example max_concurrent_sessions: 1 mcp_servers: - key: example metadata: key: example model: example model_config: max_tokens: 1 provider_params: key: example reasoning_effort: example temperature: 1.5 top_p: 1.5 multiagent: key: example name: example-name nativeIntegrations: - connectionId: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d permission: example resources: - example skills: - key: example system: example toolsets: - type: evaluation web_search_enabled: true ManagedAgentsAgent: description: >- A configured agent: its versioned execution definition plus current mutable classification tags. Publishing the execution definition mints a new immutable AgentVersion; applying tags does not. A session records the version it ran and never snapshots tags. properties: agent_id: description: >- Server-assigned id of the agent, used in the agent, agent-version, and session routes. type: string built_in_integrations: description: >- Built-in integrations this agent may use, each naming an active organization connection an admin added on the Integrations page. Sessions receive short-lived access restricted to exactly those apps and each connection's tool allow-list. Not a vault grant: nothing about these appears under credential access. A version write carries the list in full: omitting it publishes a version with none. items: $ref: '#/components/schemas/ManagedAgentsBuiltInIntegration' type: array created_at: description: Server-assigned RFC 3339 timestamp of when the agent was created. format: date-time type: string default_credential_refs: description: >- Narrows the default vaults to individual credentials. Every credential is selected when a vault is first added, and may then be unchecked. items: $ref: '#/components/schemas/ManagedAgentsVaultCredentialRef' type: - array - 'null' default_rubric: description: >- Markdown rubric that sessions started from this agent are graded against when their create request omits an outcome. A session that supplies its own outcome ignores this entirely. Carried in full on every version write: omitting it publishes a version with no rubric. type: string default_vault_ids: description: >- Vaults whose credentials are copied into a new session when its create request omits vault_ids. Sending an explicit empty list on the session still overrides these. items: type: string type: - array - 'null' description: description: Free-text note about what this agent is for. type: string disabled_integration_mcp_providers: description: >- Native integration providers whose MCP tools new sessions of this agent do not receive, even though the grant is present. The grant still authenticates the provider's sandbox tools where it has any (git and gh for GitHub). Suppresses integration-derived servers only, never the agent's own mcp_servers. New agents decline github by default when the field is omitted on create (JSON null counts as omitted); send an explicit [] on create to receive every provider's MCP tools. A version write carries the list in full: omitting it publishes a version with none. items: type: string type: - array - 'null' latest_agent_version_id: description: >- Server-maintained id of the newest version of this agent; sessions started without an explicit version use it. type: string max_concurrent_sessions: description: >- Maximum number of this agent's root sessions that may run or wait on compute at once. Omit for unlimited. Sessions beyond the cap are accepted with execution_state=queued and wait until a slot frees; child/subagent sessions do not count. Carried in full on every version write: omitting it publishes a version with no cap. maximum: 10000 minimum: 1 type: integer mcp_servers: description: >- Remote MCP servers to attach. Each entry is an object with name (the label the server's tools are grouped under) and url (its http/https endpoint); any further keys are passed to the runtime unchanged. Credentials come from the vaults granted to the session, not from this entry. Tools are discovered and snapshotted at session start. items: additionalProperties: {} type: object type: - array - 'null' metadata: additionalProperties: {} description: >- Caller-owned key/value data stored with the agent and returned unchanged. type: object model: description: >- Model the agent runs on. Pass a model id exactly as the models catalog (GET /v1/models) lists it, e.g. anthropic/claude-sonnet-4-5; reads return the stored form, which adds a provider prefix before that id. An explicitly provider-qualified string such as anthropic:claude-sonnet-4-5 selects that provider directly and is left as written. An id the catalog does not list is rejected here, not at the session's first turn. type: string model_config: $ref: '#/components/schemas/ManagedAgentsInferenceConfig' description: >- Default inference settings applied to every turn unless a session overrides them. multiagent: additionalProperties: {} description: >- Multi-agent orchestration settings, such as subagent definitions and delegation limits. type: object name: description: >- Human-readable label shown wherever agents are listed. Not required to be unique. type: string nativeIntegrations: description: >- Native connections this agent may use, with provider-enforced permission and resource restrictions. Omit or send [] for none. Stored in full on each agent version; secrets remain on the connection. items: $ref: '#/components/schemas/ManagedAgentsNativeIntegration' maxItems: 25 type: array organization_id: description: >- Organization that owns the agent. Server-assigned from the caller's credentials; a value sent in a request body is ignored. type: string skills: description: >- Skill packages loaded into the agent's runtime, each an entry with the skill reference and its metadata. items: additionalProperties: {} type: object type: - array - 'null' system: description: System prompt prepended to every conversation this agent runs. type: string tags: description: >- Current organization-scoped classification tags applied to this agent. Always an array. Tags are mutable catalog metadata and are deliberately absent from AgentVersion and session runtime snapshots. items: $ref: '#/components/schemas/ManagedAgentsTag' type: array toolsets: description: >- The bare evaluation marker, when this is an evaluator agent. Historical stored agents may contain ignored declarations, omitted from current API responses. Built-in sandbox tools need no marker. items: additionalProperties: false properties: type: description: The evaluation marker is the only supported toolset type. enum: - evaluation type: string required: - type type: object maxItems: 1 type: - array - 'null' updated_at: description: >- Server-assigned RFC 3339 timestamp of the most recent update to the agent. format: date-time type: string web_search_enabled: default: true description: >- Whether new sessions may use the native web_search tool. Omitted on legacy agents and interpreted as enabled. type: boolean required: - organization_id - agent_id - name - model - model_config - system - toolsets - mcp_servers - default_vault_ids - default_credential_refs - disabled_integration_mcp_providers - skills - tags - created_at - updated_at type: object example: agent_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d built_in_integrations: - connection_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d tools: - example created_at: '2026-02-18T09:30:00.000Z' default_credential_refs: - credential_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d vault_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d default_rubric: example default_vault_ids: - example description: example disabled_integration_mcp_providers: - example latest_agent_version_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d max_concurrent_sessions: 1 mcp_servers: - key: example metadata: key: example model: example model_config: max_tokens: 1 provider_params: key: example reasoning_effort: example temperature: 1.5 top_p: 1.5 multiagent: key: example name: example-name nativeIntegrations: - connectionId: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d permission: example resources: - example organization_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d skills: - key: example system: example tags: - color: '#14b8a6' created_at: '2026-02-18T09:30:00.000Z' description: example label: example organization_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d tag_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d updated_at: '2026-02-18T09:30:00.000Z' toolsets: - type: evaluation updated_at: '2026-02-18T09:30:00.000Z' web_search_enabled: true ManagedAgentsApiError: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - analytics - analytics_not_ready - artifact_fetch_unavailable - artifact_generation_mismatch - artifact_hash_mismatch - artifact_invalid_events - artifact_invalid_json - artifact_not_allowlisted - artifact_size_mismatch - atomic_ingest_timeout - auth_unavailable - automation_event_source_invalid - automation_memory_unavailable - automation_reference_invalid - automation_runs_unconfigured - automations_unconfigured - bad_gateway - built_in_catalog_unavailable - built_in_integrations_unconfigured - compute_offerings_unavailable - conflict - content_store_request_canceled - content_store_unavailable - content_store_upload_timeout - credential_encryption_unconfigured - delegate_preparation_failed - entity_family_not_permitted - environment_not_verified - evaluation_cancellation_pending - evaluation_deletion_pending - event_admission_unavailable - event_ingress_unavailable - event_source_verification_credential_invalid - event_sources_unconfigured - execution_unconfigured - file_quota_exceeded - file_storage_unconfigured - forbidden - gateway_timeout - gestalt_unconfigured - github_rate_limited - github_unavailable - handoff_access_invalid - handoff_access_unavailable - handoff_access_unsupported - handoff_capture_unavailable - handoff_requires_retest - handoff_revoke_unavailable - handoff_signal_unavailable - idempotency_conflict - idempotency_in_progress - idempotency_unavailable - ingest_policy_changed - ingest_policy_not_found - ingest_policy_revoked - integrations_unconfigured - internal_error - invalid_json - invalid_pull_request_review_result - invalid_request - invalid_scope - invariant_violation - live_fleet_unconfigured - managed_agents_unavailable - missing_dependency - model_gateway_metadata_missing - model_gateway_unconfigured - model_gateway_unreachable - mutation_transaction_budget_exceeded - not_found - page_token_expired - payload_too_large - persistence_busy - precondition_failed - precondition_required - provider_registration_unsupported - provider_selection_unsupported - rate_limit_exceeded - rate_limited - repository_automation_unconfigured - request_too_large - reserved_source_type - revision_conflict - run_log_store_unavailable - runner_image_resolution_failed - sandbox_provider_disabled - service_unavailable - session_analyst_busy - session_analyst_model_unavailable - session_analyst_unconfigured - session_start_admission_unavailable - session_start_not_admitted - setup_fallback_environment_unsafe - setup_run_finished - setup_run_in_progress - setup_run_limit - setup_run_not_started - setup_runs_unavailable - skill_storage_unconfigured - slack_channels_rejected - slack_channels_unavailable - slack_channels_unconfigured - slack_connection_malformed - slack_event_intake_unavailable - slack_installation_mismatch - slack_missing_scope - slack_rate_limited - slack_reapproval_required - source_ownership_mismatch - source_revision_conflict - spanner_unavailable - streaming_unsupported - submission_transaction_budget_exceeded - task_version_number_conflict - team_board_unconfigured - too_many_streams - unauthorized - unsupported_media_type - vault_creation_retired - version_content_conflict - webhook_delivery_too_large - workspace_boundary_denied message: type: string minLength: 1 description: Human-readable error message. details: description: Optional structured error details. type: object propertyNames: type: string additionalProperties: {} required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsApiErrorForbidden: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - forbidden message: type: string minLength: 1 description: Human-readable error message. details: description: Optional structured error details. type: object propertyNames: type: string additionalProperties: {} required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsApiErrorUnsupportedMediaType: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - unsupported_media_type message: type: string minLength: 1 description: Human-readable error message. details: description: Optional structured error details. type: object propertyNames: type: string additionalProperties: {} required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsApiErrorBadGateway: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - bad_gateway message: type: string minLength: 1 description: Human-readable error message. details: description: Optional structured error details. type: object propertyNames: type: string additionalProperties: {} required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsApiErrorGatewayTimeout: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - gateway_timeout message: type: string minLength: 1 description: Human-readable error message. details: description: Optional structured error details. type: object propertyNames: type: string additionalProperties: {} required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsBuiltInIntegrationRequest: description: >- One built-in integration an agent may use, named by its organization connection. The connection carries the app and the tools its agents may call; the agent inherits both. properties: connection_id: description: >- Organization integration connection (UUID) the agent may use. Must belong to the caller's organization, be a built-in integration connection, and be active. type: string tools: description: >- Reserved for per-agent narrowing below the connection's admin allow-list. Must be omitted or empty today; the agent inherits the connection's full allow-list. items: type: string type: array type: object example: connection_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d tools: - example ManagedAgentsVaultCredentialRefRequest: description: >- A pointer to one credential inside one vault. Used to grant a session specific credentials rather than every credential in a vault. properties: credential_id: description: Credential to select inside vault_id. type: string vault_id: description: >- Vault holding the credential. Required, because credential ids are unique only within a vault. type: string type: object example: credential_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d vault_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d ManagedAgentsInferenceConfigRequest: description: >- Sampling and generation settings for a model call, mirroring the provider's own request parameters. Set it on an agent or a session to govern every turn, and read it back on a model event to see what the call actually used. properties: max_tokens: description: >- Upper bound on tokens the model may generate for one assistant turn (the provider's max_tokens). Omit or 0 to use the model reference's default. format: int64 type: integer provider_params: additionalProperties: {} description: >- Extra provider request parameters merged into the inference call for options this schema does not model. Keys are provider-specific and are passed through unvalidated. type: object reasoning_effort: description: >- Provider-native reasoning depth value. For a model from the models catalog, use one of its supportedReasoningEfforts; omit it to follow the provider's current default. type: string temperature: description: >- Sampling temperature passed through to the provider, typically 0.0-2.0. Lower values are more deterministic. Omit to use the provider default. type: - 'null' - number top_p: description: >- Nucleus-sampling probability mass (0.0-1.0) passed through to the provider. Prefer setting either this or temperature, not both. Omit to use the provider default. type: - 'null' - number type: object example: max_tokens: 1 provider_params: key: example reasoning_effort: example temperature: 1.5 top_p: 1.5 ManagedAgentsNativeIntegrationRequest: description: >- A native connection and its agent-owned runtime permission and resource policy. properties: connectionId: description: Active native connection in this organization. format: uuid type: string permission: description: >- Provider permission preset, bounded by the connection's authorization. type: string resources: description: >- Optional resource subset. Omit to inherit all resources available through the connection. An explicit empty list is rejected. items: type: string maxItems: 500 type: array type: object example: connectionId: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d permission: example resources: - example ManagedAgentsBuiltInIntegration: description: >- One built-in integration an agent may use, named by its organization connection. The connection carries the app and the tools its agents may call; the agent inherits both. properties: connection_id: description: >- Organization integration connection (UUID) the agent may use. Must belong to the caller's organization, be a built-in integration connection, and be active. type: string tools: description: >- Reserved for per-agent narrowing below the connection's admin allow-list. Must be omitted or empty today; the agent inherits the connection's full allow-list. items: type: string type: array required: - connection_id type: object example: connection_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d tools: - example ManagedAgentsVaultCredentialRef: description: >- A pointer to one credential inside one vault. Used to grant a session specific credentials rather than every credential in a vault. properties: credential_id: description: Credential to select inside vault_id. type: string vault_id: description: >- Vault holding the credential. Required, because credential ids are unique only within a vault. type: string required: - vault_id - credential_id type: object example: credential_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d vault_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d ManagedAgentsInferenceConfig: description: >- Sampling and generation settings for a model call, mirroring the provider's own request parameters. Set it on an agent or a session to govern every turn, and read it back on a model event to see what the call actually used. properties: max_tokens: description: >- Upper bound on tokens the model may generate for one assistant turn (the provider's max_tokens). Omit or 0 to use the model reference's default. format: int64 type: integer provider_params: additionalProperties: {} description: >- Extra provider request parameters merged into the inference call for options this schema does not model. Keys are provider-specific and are passed through unvalidated. type: object reasoning_effort: description: >- Provider-native reasoning depth value. For a model from the models catalog, use one of its supportedReasoningEfforts; omit it to follow the provider's current default. type: string temperature: description: >- Sampling temperature passed through to the provider, typically 0.0-2.0. Lower values are more deterministic. Omit to use the provider default. type: number top_p: description: >- Nucleus-sampling probability mass (0.0-1.0) passed through to the provider. Prefer setting either this or temperature, not both. Omit to use the provider default. type: number type: object example: max_tokens: 1 provider_params: key: example reasoning_effort: example temperature: 1.5 top_p: 1.5 ManagedAgentsNativeIntegration: description: >- A native connection and its agent-owned runtime permission and resource policy. properties: connectionId: description: Active native connection in this organization. format: uuid type: string permission: description: >- Provider permission preset, bounded by the connection's authorization. type: string resources: description: >- Optional resource subset. Omit to inherit all resources available through the connection. An explicit empty list is rejected. items: type: string maxItems: 500 type: array required: - connectionId - permission type: object example: connectionId: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d permission: example resources: - example ManagedAgentsTag: description: >- An organization-scoped classification definition. Applying or removing it changes only catalog membership: it does not update the agent, mint an AgentVersion, or affect running sessions. properties: color: description: 'Display color in #RRGGBB form.' examples: - '#14b8a6' maxLength: 7 minLength: 7 pattern: ^#[0-9A-Fa-f]{6}$ type: string created_at: description: Server-assigned RFC 3339 timestamp of when the tag was created. format: date-time type: string description: description: >- Optional operator-facing explanation of the classification, up to 280 characters. maxLength: 280 type: string label: description: >- Display label, trimmed by the service. Unique case-insensitively among live tags in this organization. maxLength: 32 minLength: 1 type: string organization_id: description: >- Organization that owns the tag. Server-assigned from the authenticated principal and never accepted as authority from the request body. type: string tag_id: description: Server-assigned tag id (UUID). format: uuid type: string updated_at: description: >- Server-assigned RFC 3339 timestamp of the most recent definition update. format: date-time type: string required: - organization_id - tag_id - label - color - created_at - updated_at type: object example: color: '#14b8a6' created_at: '2026-02-18T09:30:00.000Z' description: example label: example organization_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d tag_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d updated_at: '2026-02-18T09:30:00.000Z' securitySchemes: bearerAuth: type: http scheme: bearer description: A Recursion API key, created in the console under API keys. ````