> ## Documentation Index > Fetch the complete documentation index at: https://docs.streamkap.com/llms.txt > Use this file to discover all available pages before exploring further. # Get Observability Session Transcript > Full transcript timeline for one session. Reads ``streamkap_agent_transcript`` (the Flink-runtime transcript stream). A row is one chat call, tool call, or final output emission; they share an ``iteration_id`` when they belong to the same input record's processing chain. Rows are returned oldest-first. Tenant + service scoping enforced at the query layer — a session id that belongs to another tenant or sibling service simply returns an empty ``rows`` list, identical to "session not found / expired". No existence leak across tenants. ## OpenAPI ````yaml /openapi/openapi.json get /agentic/observability/sessions/{session_id}/transcript openapi: 3.1.0 info: title: Streamkap REST API description: >- The Streamkap REST API allows you to programmatically manage your CDC pipelines, sources, destinations, transforms, and more. Authenticate using a bearer token obtained from the [Access Token](/api-reference/auth/access-token) endpoint with your API client credentials. contact: name: Streamkap Support url: https://streamkap.com/ email: support@streamkap.com license: name: Proprietary version: 2.0.0 servers: - url: https://api.streamkap.com description: Production security: [] tags: - name: Agents description: Create, deploy, and manage Flink-based AI agents. - name: Agents Observability description: >- Read-only views over the MCP audit log: agent rollup, sessions, spans, histograms, external-agent verify. - name: Alerts description: Manage alert subscribers, preferences, and notification credentials. - name: Authentication description: Obtain and refresh access tokens, manage client credentials and roles. - name: Billing description: Retrieve usage metrics, summaries, and export billing data. - name: Consumer Groups description: List, inspect, and reset Kafka consumer group offsets. - name: Dashboard description: Retrieve organisation-level statistics and overview data. - name: Destinations description: Create, configure, and manage data destinations and their lifecycle. - name: Kafka Access description: Manage Kafka users and their access permissions. - name: Logs description: Query and summarise system logs. - name: Pipelines description: Create, configure, and manage CDC pipelines and their lifecycle. - name: Project Keys description: Manage project keys that bundle API credentials and optional Kafka access. - name: Schema Registry description: Browse schema subjects, versions, and retrieve schema definitions. - name: Services description: View and switch service metadata. - name: Sources description: >- Create, configure, and manage data sources, snapshots, and their lifecycle. - name: Tags description: Create, update, and manage resource tags for organisation. - name: Topics description: Browse topic details, statistics, configurations, metrics, and messages. - name: Transforms description: >- Create, deploy, and manage data transforms, unit tests, and implementation details. paths: /agentic/observability/sessions/{session_id}/transcript: get: tags: - Agents Observability summary: Get Observability Session Transcript description: |- Full transcript timeline for one session. Reads ``streamkap_agent_transcript`` (the Flink-runtime transcript stream). A row is one chat call, tool call, or final output emission; they share an ``iteration_id`` when they belong to the same input record's processing chain. Rows are returned oldest-first. Tenant + service scoping enforced at the query layer — a session id that belongs to another tenant or sibling service simply returns an empty ``rows`` list, identical to "session not found / expired". No existence leak across tenants. operationId: getAgenticObservabilitySessionTranscript parameters: - name: session_id in: path required: true schema: type: string title: Session Id responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ObservabilityTranscriptResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - FronteggHTTPAuthentication: [] components: schemas: ObservabilityTranscriptResponse: properties: session_id: type: string title: Session Id rows: items: $ref: '#/components/schemas/ObservabilityTranscriptRow' type: array title: Rows truncated: type: boolean title: Truncated default: false additionalProperties: false type: object required: - session_id - rows title: ObservabilityTranscriptResponse description: |- `/agentic/observability/sessions/{session_id}/transcript` envelope. Rows are returned oldest-first so the FE can render the timeline in natural reading order without an additional sort. ``truncated`` is ``True`` when the BE applied a defensive row cap on the underlying ClickHouse read (rare; happens when a runaway agent produced an unusually long session). The FE should surface a "showing first N rows" notice; full transcript is not paginatable at this endpoint (sessions are conceptually one timeline). HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError ObservabilityTranscriptRow: properties: event_timestamp: type: string format: date-time title: Event Timestamp agent_id: type: string title: Agent Id iteration_id: type: string title: Iteration Id session_id: anyOf: - type: string - type: 'null' title: Session Id operation: type: string enum: - chat - tool_call - output title: Operation provider: anyOf: - type: string - type: 'null' title: Provider model: anyOf: - type: string - type: 'null' title: Model input_tokens: type: integer title: Input Tokens default: 0 output_tokens: type: integer title: Output Tokens default: 0 tool_name: anyOf: - type: string - type: 'null' title: Tool Name tool_call_id: anyOf: - type: string - type: 'null' title: Tool Call Id duration_ms: type: integer title: Duration Ms default: 0 status: type: string title: Status error_code: anyOf: - type: string - type: 'null' title: Error Code error_message: anyOf: - type: string - type: 'null' title: Error Message payload_truncated: type: boolean title: Payload Truncated default: false payload_text: anyOf: - type: string - type: 'null' title: Payload Text additionalProperties: false type: object required: - event_timestamp - agent_id - iteration_id - operation - status title: ObservabilityTranscriptRow description: |- One row inside a session's transcript timeline. A row is the runtime's record of a single chat call, tool call, or final output emission. ``iteration_id`` correlates rows that belong to the same input-record processing chain (a ``chat`` followed by one or more ``tool_call`` rows followed by another ``chat`` followed by an ``output`` row all share an iteration id). ``payload_text`` is capped at 32 KB UTF-8 by the runtime emitter (matches the MCP cap). When the cap fires, ``payload_truncated`` is ``True`` and the visible text ends with the `` ... (truncated)`` marker. 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 securitySchemes: FronteggHTTPAuthentication: type: http scheme: bearer ````