> ## Documentation Index > Fetch the complete documentation index at: https://hanabiaiinc-chore-update-openapi-schema.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Get Test Run > Fetch one test run with its transcript, verdicts and tool calls. ## OpenAPI ````yaml get /v1/agent/test-runs/{run_id} openapi: 3.1.0 info: title: FishAudio OpenAPI version: '1' servers: - description: Fish Audio API url: https://api.fish.audio security: [] tags: [] paths: /v1/agent/test-runs/{run_id}: get: tags: - Agent Tests summary: Get Test Run description: |- Fetch one test run. Runs start `queued` and end `passed`, `failed` or `error`. A simulation run takes minutes, so poll until it finishes. parameters: - in: path name: run_id description: '' required: true schema: title: Run Id type: string deprecated: false responses: '200': description: Request fulfilled, document follows headers: {} content: application/json: schema: properties: run_id: title: Run Id type: string test_id: title: Test Id type: string agent_id: title: Agent Id type: string batch_id: anyOf: - type: string - type: 'null' default: null title: Batch Id test_type: enum: - next_reply - tool - simulation title: Test Type type: string repeat_index: default: 0 description: Which repeat of the test in its batch this run is. title: Repeat Index type: integer status: enum: - queued - running - passed - failed - error title: Status type: string needs_review: default: false description: >- The judge could not decide, or a tool call had no mock answer. title: Needs Review type: boolean error: default: '' title: Error type: string usage: $ref: '#/components/schemas/PublicAgentTestRunUsage' created_at: format: date-time title: Created At type: string started_at: anyOf: - format: date-time type: string - type: 'null' default: null title: Started At finished_at: anyOf: - format: date-time type: string - type: 'null' default: null title: Finished At agent_reply: default: '' description: The reply a scripted test judged. title: Agent Reply type: string judge_reasoning: default: '' title: Judge Reasoning type: string config_hash: default: '' description: The agent draft's config hash the run tested. title: Config Hash type: string latency_ms: default: 0 title: Latency Ms type: integer simulation_result: anyOf: - $ref: '#/components/schemas/AgentTestSimulationResult' - type: 'null' default: null channel: anyOf: - enum: - web_voice - phone_inbound - phone_outbound type: string - type: 'null' default: null title: Channel turns_used: default: 0 title: Turns Used type: integer ended_by: anyOf: - enum: - agent - user - transfer - max_turns - timeout - error type: string - type: 'null' default: null title: Ended By mock_gaps: items: $ref: '#/components/schemas/AgentTestMockGap' title: Mock Gaps type: array required: - run_id - test_id - agent_id - test_type - status - created_at type: object '401': description: No permission -- see authorization schemes headers: {} content: application/json: schema: properties: status: title: Status type: integer message: title: Message type: string reason: anyOf: - type: string - type: 'null' default: null title: Reason required: - status - message type: object '404': description: Nothing matches the given URI headers: {} content: application/json: schema: properties: status: title: Status type: integer message: title: Message type: string reason: anyOf: - type: string - type: 'null' default: null title: Reason required: - status - message type: object '503': description: The server cannot process the request due to a high load headers: {} content: application/json: schema: properties: status: title: Status type: integer message: title: Message type: string reason: anyOf: - type: string - type: 'null' default: null title: Reason required: - status - message type: object security: - BearerAuth: [] components: schemas: PublicAgentTestRunUsage: properties: agent_replies: default: 0 title: Agent Replies type: integer cost_usd: anyOf: - type: string - type: 'null' default: null description: LLM cost of the run in USD, null while any part is unpriced. title: Cost Usd title: PublicAgentTestRunUsage type: object AgentTestSimulationResult: description: |- The simulation run's result: what was said, what the agent called, the deterministic assertions and the judge's per-condition verdicts. properties: transcript: items: $ref: '#/components/schemas/AgentTestTranscriptMessage' title: Transcript type: array tool_calls: items: $ref: '#/components/schemas/AgentTestToolCallRecord' title: Tool Calls type: array assertions: items: $ref: '#/components/schemas/AgentTestAssertionResult' title: Assertions type: array conditions: items: $ref: '#/components/schemas/AgentTestConditionResult' title: Conditions type: array summary: default: '' title: Summary type: string passed: default: false title: Passed type: boolean title: AgentTestSimulationResult type: object AgentTestMockGap: description: |- Calls of one tool the test prepared no answer for. A run with a gap never passes cleanly: it fails with needs_review. properties: tool_name: title: Tool Name type: string tool_id: anyOf: - type: string - type: 'null' default: null title: Tool Id tool_type: anyOf: - enum: - webhook - client - integration type: string - type: 'null' default: null title: Tool Type source: enum: - missing - unmatched title: Source type: string calls: default: 0 title: Calls type: integer required: - tool_name - source title: AgentTestMockGap type: object AgentTestTranscriptMessage: properties: role: enum: - user - agent title: Role type: string text: default: '' title: Text type: string turn_id: anyOf: - type: integer - type: 'null' default: null title: Turn Id node_id: anyOf: - type: string - type: 'null' default: null title: Node Id created_at: anyOf: - type: string - type: 'null' default: null title: Created At seq: anyOf: - type: integer - type: 'null' default: null title: Seq required: - role title: AgentTestTranscriptMessage type: object AgentTestToolCallRecord: description: >- One tool the agent invoked during the simulation, as the runtime ledger recorded it. properties: id: default: '' title: Id type: string tool_name: default: '' title: Tool Name type: string tool_source: default: '' title: Tool Source type: string input: additionalProperties: $ref: '#/components/schemas/JsonValue' title: Input type: object status: default: '' title: Status type: string output: anyOf: - type: string - type: 'null' default: null title: Output error: anyOf: - type: string - type: 'null' default: null title: Error mocked: default: false title: Mocked type: boolean mock_source: anyOf: - enum: - test - tool - missing - unmatched - real type: string - type: 'null' default: null title: Mock Source node_id: default: '' title: Node Id type: string turn_id: anyOf: - type: integer - type: 'null' default: null title: Turn Id created_at: anyOf: - type: string - type: 'null' default: null title: Created At seq: anyOf: - type: integer - type: 'null' default: null title: Seq title: AgentTestToolCallRecord type: object AgentTestAssertionResult: properties: kind: enum: - tool_call - forbidden_tool - ended_by title: Kind type: string target: title: Target type: string tool_id: anyOf: - type: string - type: 'null' default: null title: Tool Id tool_type: anyOf: - enum: - webhook - client - integration type: string - type: 'null' default: null title: Tool Type passed: title: Passed type: boolean detail: default: '' title: Detail type: string required: - kind - target - passed title: AgentTestAssertionResult type: object AgentTestConditionResult: properties: name: title: Name type: string result: enum: - success - failure - unknown title: Result type: string rationale: default: '' title: Rationale type: string required: - name - result title: AgentTestConditionResult type: object JsonValue: {} securitySchemes: BearerAuth: type: http scheme: bearer ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.