> ## Documentation Index > Fetch the complete documentation index at: https://docs.rcintell.com/llms.txt > Use this file to discover all available pages before exploring further. # Get reasoning trace > Get the full reasoning trace for a completed agent job. The trace includes each reasoning step the agent took, tool calls made, and any security annotations added by the SENTINEL audit system. ## OpenAPI ````yaml /docs/openapi.client.json get /v1/agents/jobs/{job_id}/trace openapi: 3.1.0 info: description: >- Client API for RCIntel. Admin ingest, catalog sync, and internal audit routes are omitted. See Guides → Which API to use. summary: Multi-tenant knowledge API for healthcare revenue cycle management. title: Healthcare Knowledge Layer version: 0.1.0 servers: [] security: [] tags: - description: >- Geographic payer policy lookup (national NCD vs MAC LCD vs state). Query payer, code, state, plan_type. Each row includes geo_scope and document_version. name: policies - description: >- Payer network directory — search payers, check prior auth requirements, view filing rules, denial patterns, and appeal levels. name: payers - description: >- Resolve healthcare billing knowledge across the L1-L6 layer stack. Includes payment calculation, billing guidance, and per-layer queries. name: knowledge - description: >- CMS Fee Schedule lookups — OPPS (Addendum B / APC), DMEPOS (state-level pricing), and Clinical Lab Fee Schedule (CLFS). name: fee-schedules - description: >- NCCI (National Correct Coding Initiative) — dedicated MUE limits, PTP bundling edits, add-on code edits, and code pair validation. name: ncci - description: >- Service code intelligence — CPT/HCPCS lookup, RVU data, NCCI edits, payment calculation, implant/GUDID search, and service group classification. name: codes - description: >- Submit asynchronous AI agent jobs for code research, medical necessity, and denial resolution. Poll for results and retrieve reasoning traces. name: agents - description: >- Register and manage healthcare facilities by CCN (Medicare Provider Number). Each facility is the root entity for knowledge resolution. name: facilities - description: >- NPI Registry — live search against CMS NPPES API for provider and organization National Provider Identifiers. name: npi - description: >- OpenFDA drug product lookup by NDC. Includes product-level fields with normalized ingredient and package detail. name: drugs - description: Health checks, service metadata, and Prometheus metrics. name: system paths: /v1/agents/jobs/{job_id}/trace: get: tags: - agents summary: Get reasoning trace description: |- Get the full reasoning trace for a completed agent job. The trace includes each reasoning step the agent took, tool calls made, and any security annotations added by the SENTINEL audit system. operationId: get_job_trace_v1_agents_jobs__job_id__trace_get parameters: - description: >- Asynchronous job identifier returned by an agent submission endpoint. in: path name: job_id required: true schema: format: uuid title: Job Id type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/TraceResponse' description: Ordered reasoning steps and security annotations '422': content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' description: Validation Error security: - APIKeyHeader: [] components: schemas: TraceResponse: description: Reasoning trace for a completed agent job. properties: job_id: format: uuid title: Job Id type: string security_annotations: description: Security-related annotations from SENTINEL items: $ref: '#/components/schemas/SecurityAnnotation' title: Security Annotations type: array steps: description: Ordered reasoning steps items: $ref: '#/components/schemas/TraceStep' title: Steps type: array required: - job_id - steps title: TraceResponse type: object HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' title: Detail type: array title: HTTPValidationError type: object SecurityAnnotation: description: A security annotation from the SENTINEL audit system. properties: description: anyOf: - type: string - type: 'null' title: Description finding_type: description: 'Finding type: phi_detection, unsafe_failover, etc.' title: Finding Type type: string severity: default: info description: 'Severity: info, warning, critical' title: Severity type: string step_index: anyOf: - type: integer - type: 'null' description: Index of the traced step this annotation refers to title: Step Index required: - finding_type title: SecurityAnnotation type: object TraceStep: description: A single step in an agent's reasoning trace. properties: content: anyOf: - type: string - type: 'null' description: Step content or description title: Content duration_ms: anyOf: - type: number - type: 'null' description: Step duration in ms title: Duration Ms step_index: default: 0 description: Step order index title: Step Index type: integer step_type: default: reasoning description: 'Step type: reasoning, tool_call, observation, security' title: Step Type type: string tool_input: additionalProperties: true description: Tool call input title: Tool Input type: object tool_name: anyOf: - type: string - type: 'null' description: Tool called (if tool_call step) title: Tool Name tool_output: anyOf: - type: string - type: 'null' description: Tool call result title: Tool Output title: TraceStep type: object ValidationError: properties: ctx: title: Context type: object input: title: Input loc: items: anyOf: - type: string - type: integer title: Location type: array msg: title: Message type: string type: title: Error Type type: string required: - loc - msg - type title: ValidationError type: object securitySchemes: APIKeyHeader: in: header name: X-API-Key type: apiKey ````