> ## 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. # List sessions > Returns sessions visible to the caller in the calling organization, most recent first, filtered by any combination of status, kind, agent_id, current agent tag_ids, and external source. kind accepts a comma-separated list, while tag_ids uses AND semantics. Capped by limit (default 100, max 1000) rather than cursor-paginated. Ordinary callers receive only unclassified public trees; callers with elevated classified-data access can receive classified rows allowed by their scope. ## OpenAPI ````yaml /managed-agents/openapi.yaml get /managed-agents/v1/sessions 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/sessions: get: tags: - Sessions summary: List sessions description: >- Returns sessions visible to the caller in the calling organization, most recent first, filtered by any combination of status, kind, agent_id, current agent tag_ids, and external source. kind accepts a comma-separated list, while tag_ids uses AND semantics. Capped by limit (default 100, max 1000) rather than cursor-paginated. Ordinary callers receive only unclassified public trees; callers with elevated classified-data access can receive classified rows allowed by their scope. operationId: managedAgentsListSessions parameters: - description: Filter by session status. in: query name: status schema: description: Filter by session status. type: string - description: >- Filter by session kind. Accepts a comma-separated list (kind=chat,api_call) to match any of several kinds, which is how a caller selects agent sessions without RL rollouts. A kind filter never widens visibility. session_analyst rows are hidden by default; naming that kind returns them only when the caller's scope permits the classified sessions. in: query name: kind schema: description: >- Filter by session kind. Accepts a comma-separated list (kind=chat,api_call) to match any of several kinds, which is how a caller selects agent sessions without RL rollouts. A kind filter never widens visibility. session_analyst rows are hidden by default; naming that kind returns them only when the caller's scope permits the classified sessions. type: string - description: Filter by agent id. in: query name: agent_id schema: description: Filter by agent id. type: string - description: >- Comma-separated current agent tag ids, with at most 32 distinct ids. A session row's agent must carry every requested tag (AND semantics). Unknown or cross-organization ids return 404. Tags are resolved at read time, not from the session snapshot. in: query name: tag_ids schema: description: >- Comma-separated current agent tag ids, with at most 32 distinct ids. A session row's agent must carry every requested tag (AND semantics). Unknown or cross-organization ids return 404. Tags are resolved at read time, not from the session snapshot. type: string - in: query name: external_source_type schema: type: string - in: query name: external_source_id schema: type: string - description: >- Exact-match filter on caller-defined session metadata as key:value, split at the first colon. Repeat the parameter to require several pairs; a session's root must carry every one (AND semantics). Children of a matching root match too, so combine with root_only to list only the roots. in: query name: metadata schema: description: >- Exact-match filter on caller-defined session metadata as key:value, split at the first colon. Repeat the parameter to require several pairs; a session's root must carry every one (AND semantics). Children of a matching root match too, so combine with root_only to list only the roots. items: type: string maxItems: 32 type: array - description: >- Require the root session to carry this caller-defined metadata key with any value. Repeatable; every listed key must be present. in: query name: metadata_key schema: description: >- Require the root session to carry this caller-defined metadata key with any value. Repeatable; every listed key must be present. items: type: string maxItems: 32 type: array - description: >- Return only root sessions. Use this for model-cost list rows so children cannot consume the bounded page before their tree root. in: query name: root_only schema: description: >- Return only root sessions. Use this for model-cost list rows so children cannot consume the bounded page before their tree root. type: boolean - description: >- Return only root sessions whose active browser handoff is awaiting a person (not already being driven or resolved). Applied before ordering and pagination. in: query name: needs_user schema: description: >- Return only root sessions whose active browser handoff is awaiting a person (not already being driven or resolved). Applied before ordering and pagination. type: boolean - description: >- Filter root sessions by their newest immutable evaluation verdict before pagination. evaluated matches any verdict; none matches sessions with no evaluation. in: query name: evaluation_result schema: description: >- Filter root sessions by their newest immutable evaluation verdict before pagination. evaluated matches any verdict; none matches sessions with no evaluation. enum: - pass - fail - not_applicable - evaluated - none type: string - description: >- Page size. When more rows match, the response carries next_page_token; pass it back as page_token with the same filters and limit to read the next page. in: query name: limit schema: default: 100 description: >- Page size. When more rows match, the response carries next_page_token; pass it back as page_token with the same filters and limit to read the next page. maximum: 1000 type: integer - description: >- Signed continuation token from a previous page's next_page_token. Bound to the organization and to the exact filters and limit it was issued for; valid for one hour. in: query name: page_token schema: description: >- Signed continuation token from a previous page's next_page_token. Bound to the organization and to the exact filters and limit it was issued for; valid for one hour. type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsSessionListResponse' description: >- Response body of GET /v1/sessions. Keyset-paginated over (updated_at, id): a page is a stable window at the moment it is read, but a session updated between two page reads moves to the front of the list, so a live list may show it twice or skip it once. Ordinary callers receive only unclassified public session trees; callers with elevated classified-data access can receive classified rows allowed by their scope. Each row is a summary without the start-time snapshots; read one session for those. Token and cost totals are not included; fetch them for a batch of ids via GET /v1/sessions/usage and GET /v1/sessions/costs. '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/ManagedAgentsApiErrorNotFound' '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: ManagedAgentsSessionListResponse: additionalProperties: false description: >- Response body of GET /v1/sessions. Keyset-paginated over (updated_at, id): a page is a stable window at the moment it is read, but a session updated between two page reads moves to the front of the list, so a live list may show it twice or skip it once. Ordinary callers receive only unclassified public session trees; callers with elevated classified-data access can receive classified rows allowed by their scope. Each row is a summary without the start-time snapshots; read one session for those. Token and cost totals are not included; fetch them for a batch of ids via GET /v1/sessions/usage and GET /v1/sessions/costs. properties: next_page_token: description: >- Present when more sessions match. Pass it as page_token with the same filters and limit to read the next page. Absent on the last page. type: string sessions: description: >- Sessions visible to the caller and matching the query filters, most recently updated first, at most limit (default 100) per page. An empty array means nothing matched. Ordinary callers receive a row only when access_policy is omitted/null on both it and its root; callers with elevated classified-data access can receive classified rows. Each row includes current evaluation eligibility and its newest immutable evaluation, when any. Rows are summaries: agent_snapshot and model_snapshot are omitted and config is an empty object; GET /v1/sessions/{session_id} returns them. items: $ref: '#/components/schemas/ManagedAgentsSessionListItem' type: array required: - sessions type: object example: next_page_token: example sessions: - access_policy: admin_only active_handoff: access_expires_at: '2026-02-18T09:30:00.000Z' deadline_at: '2026-02-18T09:30:00.000Z' handoff_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d reason: example requested_at: '2026-02-18T09:30:00.000Z' state: awaiting_user wake_cause: example agent_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d agent_snapshot: key: example agent_version_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d computer_use: true concurrency_slot_held: true config: key: example created_at: '2026-02-18T09:30:00.000Z' credential_refs: - credential_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d vault_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d credential_refs_configured: true effective_model: example environment_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d evaluation_eligibility: eligible: true reason: not_root snapshot_event_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d execution_state: provisioning external_source_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d external_source_type: example failure: at: '2026-02-18T09:30:00.000Z' category: transient code: example message: example phase: example retryable: true forked_at_event_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d kind: api_call last_activity_at: '2026-02-18T09:30:00.000Z' latest_evaluation: null metadata: key: example model_ref_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d model_snapshot: key: example organization_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d parent_session_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d root_session_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d sandbox_instance_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d sandbox_provider: example session_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d session_path: example source_refs: key: example status: active stop_reason: example tenant_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d updated_at: '2026-02-18T09:30:00.000Z' user_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d vault_ids: - example wake_at: '2026-02-18T09:30:00.000Z' 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 - atlassian_rate_limited - atlassian_unavailable - 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_disabled - 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 - launchdarkly_rate_limited - launchdarkly_unavailable - live_fleet_unconfigured - managed_agents_unavailable - merge_key_rejected - merge_link_unavailable - merge_rate_limited - merge_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. ManagedAgentsApiErrorNotFound: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - not_found 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. ManagedAgentsSessionListItem: additionalProperties: false description: >- Public session-list summary extended with current evaluation eligibility and newest verdict. properties: access_policy: description: >- Explicit access classification. Omitted/null is the ordinary behavior. admin_only requires elevated classified-data access and the current Admin organization role on public APIs. platform_internal is the service's own session over this organization's data: it is readable in-organization when addressed directly, but list and gestalt views include it only for callers with elevated classified-data access. enum: - admin_only - platform_internal type: string active_handoff: $ref: '#/components/schemas/ManagedAgentsActiveHandoff' description: >- Current browser handoff, including its exclusive driver claim and deadline. Absent when no browser handoff is active. Never contains the short-lived access URL. agent_id: description: >- Agent this session runs (UUID). Empty for imported sessions that were not started from an agent. type: string agent_snapshot: additionalProperties: {} description: >- The agent version's definition as it stood when the session started, frozen so later edits to the agent cannot change this session's behavior. type: object agent_version_id: description: >- Agent version this session runs (UUID), pinned at start so a later edit to the agent cannot change a running session. type: string computer_use: description: >- Whether this session has a computer-enabled environment and a display that passed its readiness probe. type: boolean concurrency_slot_held: description: >- Whether this root session currently occupies the agent's max_concurrent_sessions slot. True while admitted and non-terminal. False exclusively while an active queued root waits to start. Omitted for unlimited agents, child sessions, legacy rows, and terminal or deleted sessions. type: boolean config: additionalProperties: {} description: >- Resolved per-session runtime settings written at start, including the snapshotted MCP servers and tool bindings, multi-agent roster, and delegation depth limits. Read-only to callers. type: - object - 'null' created_at: description: RFC 3339 timestamp of when this record was created. Server-assigned. format: date-time type: string credential_refs: description: >- Explicit allowlist of individual credentials the session may use. Read credential_refs_configured to tell an intentionally empty allowlist from a legacy session granted whole vaults. items: $ref: '#/components/schemas/ManagedAgentsVaultCredentialRef' type: - array - 'null' credential_refs_configured: description: >- True when credential_refs is an explicit allowlist. False on legacy sessions granted every credential in their vaults, which would otherwise be indistinguishable from an empty allowlist. type: boolean effective_model: description: >- Provider-qualified model string frozen for this session, including any per-session model override. Prefer this over resolving model_ref_id or the current agent version when displaying what actually ran. type: string environment_id: description: Environment whose sandbox definition this session runs in (UUID). type: string evaluation_eligibility: $ref: '#/components/schemas/ManagedAgentsSessionEligibility' description: Current server-owned Evaluate-now decision for this session. execution_state: description: >- Where the agent loop is. Empty for sessions without a loop, such as imported rollouts. provisioning normally clears in under a minute and is bounded: a sandbox that does not become ready within the deployment's compute-ready timeout (five minutes by default) fails the session with sandbox_provision_timeout, so a session is never stuck here indefinitely. This field, read from the session itself, is the authoritative status -- a session's event stream is written on a separate path and can lag it, so an empty event list does not mean the session is still starting. When a session leaves provisioning by failing, failure carries the reason. enum: - provisioning - queued - running - idle - completed type: string external_source_id: description: >- Identifier of the session's counterpart in the external_source_type system, so a caller can find the session again from that side. Set together with external_source_type. type: string external_source_type: description: >- Kind of external system this session is correlated to, e.g. slack_thread. Set together with external_source_id and filterable when listing sessions. type: string failure: $ref: '#/components/schemas/ManagedAgentsSessionFailure' description: >- Structured terminal failure. Omitted for healthy sessions and legacy rows. forked_at_event_id: description: >- Event in the parent session (UUID) this session was forked from, so the fork's starting context is identifiable. Set only on forks. type: string kind: description: >- What produced the session: api_call, chat, rollout (an imported RL rollout), subagent (delegated by another session), benchmark, evaluation (a platform-started evaluation run over other session snapshots), reflection (a platform-started memory consolidation), or session_analyst (a platform-started read-only assistant that answers questions about another session tree). enum: - api_call - chat - rollout - subagent - benchmark - evaluation - reflection - session_analyst type: string last_activity_at: description: >- RFC 3339 timestamp of when the agent loop last made progress. Distinct from updated_at, which any metadata write touches. Absent for sessions that run no loop. format: date-time type: string latest_evaluation: anyOf: - type: 'null' - $ref: '#/components/schemas/ManagedAgentsLatestEvaluation' description: >- Newest immutable evaluation summary, or null when the session has none. metadata: additionalProperties: type: string description: >- Caller-defined string key/value pairs supplied when the session was started, e.g. ids from your own system. Immutable, present on root sessions only, and filterable with metadata=key:value or metadata_key=key on GET /v1/sessions. At most 32 entries; keys use letters, digits, '_', '.', and '-' up to 64 characters; values are 1-512 characters. type: object model_ref_id: description: >- Model reference the session's turns run on (UUID), resolved at start from the agent version or the start request. type: string model_snapshot: additionalProperties: {} description: >- The resolved model reference and inference settings as they stood when the session started, frozen for the same reason as agent_snapshot. type: object organization_id: description: >- Organization that owns this record. Resolved from the API key; never accepted from the caller. type: string parent_session_id: description: >- Session that created this one (UUID) — the delegating session for a subagent, or the source session for a fork. Empty on a root session. type: string root_session_id: description: >- Root session of the multi-agent tree this session belongs to (UUID). Equal to session_id for a root session. type: string sandbox_instance_id: description: >- Provider-assigned id of the sandbox instance serving this session. Empty before provisioning finishes; historical self_hosted sessions may also have no instance id. type: string sandbox_provider: description: >- Sandbox runtime that provisioned this session's compute, from the supported sandbox providers list. type: string session_id: description: Identifier for this session (UUID). Server-assigned. type: string session_path: description: >- Position of this session within its tree, as a slash-delimited path of session ids. "/" for a root session. type: string source_refs: additionalProperties: {} description: >- Secondary provenance ids from the originating system beyond the primary external source, e.g. an imported rollout's problem, problem-version, and run ids. type: object status: $ref: '#/components/schemas/ManagedAgentsSessionStatus' description: >- Coarse session state shared with RL rollout imports: active, awaiting_human (for a rollout, carries no score), completed, failed, or cancelled. For where a running agent loop is, read execution_state instead. stop_reason: description: >- Why the loop is not running. Set whenever execution_state is idle or completed. sleeping means the agent chose to wait and the session resumes on the next message or at wake_at; awaiting_subagents means a coordinator is waiting on delegated work. type: string tenant_id: description: >- Data-residency tenant the session's content is stored under, resolved from the request scope. A child session inherits its parent's value. type: string updated_at: description: >- RFC 3339 timestamp of the last change to this record. Server-assigned. format: date-time type: string user_id: description: >- User the session was started on behalf of, resolved from the request scope. Empty for sessions started by a service credential. type: string vault_ids: description: >- Vaults (UUIDs) the session may draw credentials from. Combine with credential_refs to narrow the grant to specific credentials. items: type: string type: array wake_at: description: >- RFC 3339 timestamp at which a sleeping session wakes itself if nobody messages it first. Absent unless the agent scheduled a timed wait. format: date-time type: string required: - root_session_id - session_path - session_id - organization_id - kind - status - computer_use - credential_refs - credential_refs_configured - config - created_at - updated_at - evaluation_eligibility - latest_evaluation type: object example: access_policy: admin_only active_handoff: access_expires_at: '2026-02-18T09:30:00.000Z' deadline_at: '2026-02-18T09:30:00.000Z' handoff_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d reason: example requested_at: '2026-02-18T09:30:00.000Z' state: awaiting_user wake_cause: example agent_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d agent_snapshot: key: example agent_version_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d computer_use: true concurrency_slot_held: true config: key: example created_at: '2026-02-18T09:30:00.000Z' credential_refs: - credential_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d vault_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d credential_refs_configured: true effective_model: example environment_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d evaluation_eligibility: eligible: true reason: not_root snapshot_event_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d execution_state: provisioning external_source_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d external_source_type: example failure: at: '2026-02-18T09:30:00.000Z' category: transient code: example message: example phase: example retryable: true forked_at_event_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d kind: api_call last_activity_at: '2026-02-18T09:30:00.000Z' latest_evaluation: null metadata: key: example model_ref_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d model_snapshot: key: example organization_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d parent_session_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d root_session_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d sandbox_instance_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d sandbox_provider: example session_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d session_path: example source_refs: key: example status: active stop_reason: example tenant_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d updated_at: '2026-02-18T09:30:00.000Z' user_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d vault_ids: - example wake_at: '2026-02-18T09:30:00.000Z' ManagedAgentsActiveHandoff: description: >- Public, credential-free state of a browser handoff that is awaiting a person, currently driven by one, or being resolved back to the agent. properties: access_expires_at: description: >- Latest time the current display access remains usable; never later than deadline_at. format: date-time type: string deadline_at: description: When the handoff automatically expires and the agent resumes. format: date-time type: string handoff_id: description: Stable identifier for this browser handoff. type: string reason: description: Why the agent asked a person to take over the shared browser. type: string requested_at: description: When the agent requested the handoff. format: date-time type: string state: description: >- Whether nobody has opened access yet, one person currently owns the display, or hand-back/deadline resolution is being delivered. enum: - awaiting_user - user_driving - resolved type: string wake_cause: description: >- Resolution cause once resolved: user_handed_back, deadline_elapsed, cancelled, or interrupted. type: string required: - handoff_id - reason - requested_at - deadline_at - state type: object example: access_expires_at: '2026-02-18T09:30:00.000Z' deadline_at: '2026-02-18T09:30:00.000Z' handoff_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d reason: example requested_at: '2026-02-18T09:30:00.000Z' state: awaiting_user wake_cause: 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 ManagedAgentsSessionEligibility: additionalProperties: false description: >- Current domain-owned Evaluate-now decision and immutable transcript snapshot boundary for one session. properties: eligible: description: Whether this session may be selected for Evaluate now. type: boolean reason: description: >- Stable reason the session is currently ineligible; omitted when eligible. enum: - not_root - non_public_access - missing_agent_attribution - unsupported_kind - no_snapshot_event type: string snapshot_event_id: description: >- Newest durable canonical UUID event boundary frozen if evaluation starts now. format: uuid type: string required: - eligible type: object example: eligible: true reason: not_root snapshot_event_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d ManagedAgentsSessionFailure: description: >- Structured, sanitized reason a session terminated abnormally. Present on a session only after a terminal failure; healthy and legacy sessions omit it. properties: at: description: Time the terminal failure was persisted. format: date-time type: string category: description: >- Who can act on this failure: transient (wait or retry), caller_error (change the request or configuration, retrying as-is will not help), or internal (report it). retryable=false with category=caller_error is a fixable mistake, not an outage. A retryable failure is never caller_error: if the platform will retry, changing the request is not the fix. enum: - transient - caller_error - internal type: string code: description: Stable machine-readable failure code. type: string message: description: >- Sanitized bounded operator-facing message; never contains raw provider response bodies or credentials. type: string phase: description: >- Lifecycle phase that failed, such as provisioning, setup, workflow, or model. type: string retryable: description: >- Whether the platform will retry, or a retry of the same request may succeed on its own. False does not mean permanently broken -- read category to tell a transient condition from a request the caller must change. type: boolean required: - phase - code - message - retryable - category - at type: object example: at: '2026-02-18T09:30:00.000Z' category: transient code: example message: example phase: example retryable: true ManagedAgentsLatestEvaluation: additionalProperties: false description: Compact newest immutable evaluation projected onto a session-list row. properties: created_at: description: UTC timestamp when the newest evaluation was recorded. format: date-time type: string evaluation_id: description: Stable identity of the newest immutable evaluation for this session. format: uuid type: string result: description: Overall pass, fail, or not-applicable verdict. enum: - pass - fail - not_applicable type: string required: - evaluation_id - result - created_at type: object example: created_at: '2026-02-18T09:30:00.000Z' evaluation_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d result: pass ManagedAgentsSessionStatus: description: Coarse session state shared by Managed Agents and imported RL rollouts. enum: - active - awaiting_human - completed - failed - cancelled type: string example: active securitySchemes: bearerAuth: type: http scheme: bearer description: A Recursion API key, created in the console under API keys. ````