> ## Documentation Index > Fetch the complete documentation index at: https://docs.conduit.ai/llms.txt > Use this file to discover all available pages before exploring further. # Get Agent Run > Returns a single agent run with its full trace: status, disposition, error, token usage, latency, the model's reply, its reasoning, and the ordered tool-call timeline. ## OpenAPI ````yaml GET /v1/agents/{id}/runs/{run_id} openapi: 3.0.0 info: title: Conduit API version: 1.0.0 description: Public API for Conduit. servers: - url: https://api.conduit.ai description: Production security: [] tags: - name: meta description: Discovery and API metadata endpoints. - name: agents description: >- V2 chat agent configuration, including instructions, skills, triggers, and automation behavior. - name: contacts description: >- Contact profile and contact-scoped related resources such as tickets and calls. - name: workspaces description: Workspaces accessible to the current API token. - name: escalations description: >- Chat escalations that require operator review, including message, proposed response, and disposition context when available. - name: conversations description: >- Canonical message threads. Use these endpoints to list threads, inspect conversation state, read transcripts, and send replies. - name: conversation-tags description: >- Conversation labels, root topics, and subtopics used for classification and topic analytics. - name: tickets description: >- Operational queue items tied to conversations, including ticket-scoped transcripts and replies. - name: calls description: Phone call records, transcripts, summaries, and recordings when available. - name: reservations description: >- PMS reservations synced from the workspace's integrations (Hostaway, Guesty, Airbnb, etc.), including guest identity, payment status, and stay dates. - name: appointments description: >- Scheduled appointments (bookings) backed by the Conduit booking service. Exposes allocation context and the upstream booking-service `external_id`. - name: helpdesk_tickets description: >- Helpdesk tickets mirrored from external helpdesk integrations (Zendesk, Pylon, Plain), including requester identity and upstream metadata. - name: kb description: >- Knowledge base search and node management. Nodes represent knowledge base entries (files or directories), chunks are the indexed retrieval units used by search. - name: skills description: >- Workspace agent skills that can be attached to V2 chat agents. Sidebar/global-assistant skills are intentionally excluded. - name: custom_tools description: >- Custom code tools: user-authored Python/JavaScript functions executed in a sandbox when an agent calls them. Includes a runtimes endpoint describing the entrypoint signature, return shape, and available dependencies per language. paths: /v1/agents/{id}/runs/{run_id}: get: tags: - agents summary: Get agent run description: >- Returns a single agent run with its full trace: status, disposition, error, token usage, latency, the model's reply, its reasoning, and the ordered tool-call timeline. operationId: getAgentRun parameters: - schema: type: string description: Agent id. example: ag77c0dy0mgdpzmqz6tesry8w184002s required: true name: id in: path - schema: type: string description: Run id (from the list-runs response). example: ar77c0dy0mgdpzmqz6tesry8w184002s required: true name: run_id in: path - schema: type: string description: >- Optional workspace override. If omitted, Conduit resolves the agent's workspace automatically. example: j57demo8f8x7c9v0n2q4r6t8y1u3i5o required: false name: workspace_id in: query responses: '200': description: Agent run content: application/json: schema: type: object properties: data: type: object properties: id: type: string description: Run identifier. Pass to the get-run endpoint. run_id: type: string description: >- Agent backend run id, useful for cross-referencing traces. agent_id: type: string workspace_id: type: string status: type: string enum: - accepted - running - completed - failed description: >- Lifecycle status of the run. `accepted`/`running` are in-flight; `completed`/`failed` are terminal. disposition: type: string nullable: true enum: - escalated - escalation_and_answer - resolved - unresolved - no_op - proactive description: The agent's decision for this run. contact_id: type: string nullable: true conversation_id: type: string nullable: true trigger_id: type: string nullable: true error: type: string nullable: true description: Failure message when `status` is `failed`. duration_ms: type: number nullable: true description: End-to-end run latency in milliseconds. token_usage: type: object nullable: true properties: input: type: number description: Input (prompt) tokens consumed. output: type: number description: Output (completion) tokens produced. required: - input - output description: Token usage reported by the agent backend. total_cost: type: number nullable: true description: >- Provider cost of the run in USD. Null for internal agents (billed in credits). trace_id: type: string nullable: true created_at: type: string completed_at: type: string nullable: true session_id: type: string nullable: true disposition_reason: type: string nullable: true description: Short tag explaining the disposition. trigger_event_id: type: string nullable: true response: type: string nullable: true description: The reply text the agent produced, if any. reflection: type: string nullable: true description: The agent's reasoning narrative for its decision. tool_trace: type: array nullable: true items: nullable: true description: >- Ordered timeline of tool calls the agent made (name, input, output per step). required: - id - run_id - agent_id - workspace_id - status - disposition - contact_id - conversation_id - trigger_id - error - duration_ms - token_usage - total_cost - trace_id - created_at - completed_at - session_id - disposition_reason - trigger_event_id - response - reflection - tool_trace required: - data description: Single agent run with its full tool-call trace and status. example: data: id: ar77c0dy0mgdpzmqz6tesry8w184002s run_id: run_9f3a1c7e agent_id: ag77c0dy0mgdpzmqz6tesry8w184002s workspace_id: j57demo8f8x7c9v0n2q4r6t8y1u3i5o status: completed disposition: resolved contact_id: co77c0dy0mgdpzmqz6tesry8w184002s conversation_id: cv77c0dy0mgdpzmqz6tesry8w184002s trigger_id: tr77c0dy0mgdpzmqz6tesry8w184002s error: null duration_ms: 4213 token_usage: input: 1820 output: 342 total_cost: 0.0121 trace_id: 0f9c2b1d8a7e4f36 created_at: '2026-04-03T03:14:15.000Z' completed_at: '2026-04-03T03:14:19.213Z' session_id: sess_4b21e9 disposition_reason: answered_from_knowledge trigger_event_id: te77c0dy0mgdpzmqz6tesry8w184002s response: >- You're all set, your reservation is confirmed for April 5th. Let me know if you need anything else! reflection: >- Contact asked to confirm their booking. The reservation lookup returned an active booking, so I confirmed it directly instead of escalating. tool_trace: - name: get_reservation input: reservation_id: res_123 output: status: confirmed check_in: '2026-04-05' '400': description: Invalid request content: application/json: schema: type: object properties: error: type: string required: - error description: Standard error response. example: error: Invalid workspace id '401': description: Unauthorized content: application/json: schema: type: object properties: error: type: string required: - error description: Standard error response. example: error: Invalid workspace id '403': description: Forbidden content: application/json: schema: type: object properties: error: type: string required: - error description: Standard error response. example: error: Invalid workspace id '404': description: Not found content: application/json: schema: type: object properties: error: type: string required: - error description: Standard error response. example: error: Invalid workspace id '429': description: Rate limit exceeded content: application/json: schema: type: object properties: error: type: string required: - error description: Standard error response. example: error: Invalid workspace id security: - bearerAuth: [] components: securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: API Token description: >- Conduit API token. Use `Authorization: Bearer `. Read/write endpoints require a token with write access. ````