openapi: 3.1.0 info: title: Bluejay Agents Retrieve Simulation Result API description: Bluejay API version: 0.1.0 servers: - url: https://api.getbluejay.ai description: Production server security: - apiKeyAuth: [] tags: - name: Retrieve Simulation Result paths: /v1/retrieve-simulation-result/{test_result_id}: get: summary: Retrieve Simulation Result description: "Retrieve a single test result and its associated custom metrics.\n\nArgs:\n test_result_id: the ID of the test result to retrieve.\n\nReturns:\n the test result along with its custom metric results." operationId: retrieve_simulation_result_v1_retrieve_simulation_result__test_result_id__get security: - HTTPBearer: [] parameters: - name: test_result_id in: path required: true schema: type: string title: Test Result Id - name: X-API-Key in: header required: true schema: type: string description: API key required to authenticate requests. responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/SingleSimulationResultResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' tags: - Retrieve Simulation Result components: schemas: src__models__api_custom_metric__CustomMetric: properties: name: type: string title: Name description: The name of the custom metric description: type: string title: Description description: The description of the custom metric response_type: type: string title: Response Type description: The response type of the custom metric response_value: type: string title: Response Value description: The response value of the custom metric reasoning: anyOf: - type: string - type: 'null' title: Reasoning description: The reasoning of the custom metric min_value: anyOf: - type: number - type: 'null' title: Min Value description: The minimum value of the custom metric max_value: anyOf: - type: number - type: 'null' title: Max Value description: The maximum value of the custom metric category: anyOf: - type: string - type: 'null' title: Category description: The category of the custom metric tags: anyOf: - items: type: string type: array - type: 'null' title: Tags description: The tags of the custom metric scoring_guidance: anyOf: - type: string - type: 'null' title: Scoring Guidance description: The scoring guidance of the custom metric enum_options: anyOf: - items: type: string type: array - type: 'null' title: Enum Options description: The enum options of the custom metric type: object required: - name - description - response_type - response_value title: Custom Metric ToolCallComparisonGroup: properties: name: type: string title: Name description: Tool name expected: items: $ref: '#/components/schemas/ExpectedToolCallDetail' type: array title: Expected description: Expected invocations of this tool actual: items: $ref: '#/components/schemas/ActualToolCallDetail' type: array title: Actual description: Actual invocations of this tool during the simulation type: object required: - name title: ToolCallComparisonGroup SimulationResultResponse: properties: id: type: integer title: Id description: ID of the simulation result digital_human_id: type: integer title: Digital Human Id description: ID of the digital human associated with the simulation result result: anyOf: - additionalProperties: true type: object - type: 'null' title: Result description: Result of the simulation run duration: anyOf: - type: integer - type: 'null' title: Duration description: Duration of the simulation run in milliseconds start_time: anyOf: - type: string format: date-time - type: 'null' title: Start Time description: Start time of the simulation run end_time: anyOf: - type: string format: date-time - type: 'null' title: End Time description: End time of the simulation run custom_metrics: anyOf: - additionalProperties: true type: object - items: {} type: array - type: 'null' title: Custom Metrics description: Custom metrics associated with the simulation result status: anyOf: - type: string - type: 'null' title: Status description: Current status of the simulation result latency: anyOf: - additionalProperties: true type: object - items: {} type: array - type: 'null' title: Latency description: Average latency of the simulation run events: anyOf: - items: $ref: '#/components/schemas/Event' type: array - type: 'null' title: Events description: Events of the simulation run transcript_url: anyOf: - type: string - type: 'null' title: Transcript Url description: URL to the transcript file of the simulation run audio_url: anyOf: - type: string - type: 'null' title: Audio Url description: URL to the audio file of the simulation run evaluations: anyOf: - items: $ref: '#/components/schemas/Evaluation' type: array - type: 'null' title: Evaluations description: Evaluations of the simulation result tool_calls: anyOf: - items: $ref: '#/components/schemas/ToolCallComparisonGroup' type: array - type: 'null' title: Tool Calls description: Expected vs actual tool calls grouped by tool name type: object required: - id - digital_human_id title: SimulationResultResponse ActualToolCallDetail: properties: parameters: anyOf: - additionalProperties: true type: object - type: 'null' title: Parameters description: Parameters passed to the tool output: anyOf: - {} - type: 'null' title: Output description: Output returned by the tool start_offset_ms: anyOf: - type: integer - type: 'null' title: Start Offset Ms description: When the tool was called relative to conversation start, in milliseconds type: object title: ActualToolCallDetail ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type type: object required: - loc - msg - type title: ValidationError FillerIgnoredLatency: properties: avg_filler_ignored_latency: anyOf: - type: number - type: 'null' title: Avg Filler Ignored Latency description: Average filler ignored latency default: 0 p50_filler_ignored_latency: anyOf: - type: number - type: 'null' title: P50 Filler Ignored Latency description: 50th percentile filler ignored latency default: 0 p90_filler_ignored_latency: anyOf: - type: number - type: 'null' title: P90 Filler Ignored Latency description: 90th percentile filler ignored latency default: 0 p95_filler_ignored_latency: anyOf: - type: number - type: 'null' title: P95 Filler Ignored Latency description: 95th percentile filler ignored latency default: 0 p99_filler_ignored_latency: anyOf: - type: number - type: 'null' title: P99 Filler Ignored Latency description: 99th percentile filler ignored latency default: 0 type: object title: FillerIgnoredLatency Evaluation: properties: id: type: string title: Id description: Unique identifier for the evaluation result created_at: type: string format: date-time title: Created At description: When this evaluation result was created (defaults to now in UTC) hallucination: anyOf: - type: boolean - type: 'null' title: Hallucination description: Whether the agent exhibited hallucination during the call hallucination_reasoning: anyOf: - type: string - type: 'null' title: Hallucination Reasoning description: Reasoning behind the hallucination, if applicable redundancy: anyOf: - type: boolean - type: 'null' title: Redundancy description: Whether the agent exhibited redundancy during the call redundancy_reasoning: anyOf: - type: string - type: 'null' title: Redundancy Reasoning description: Reasoning behind the redundancy, if applicable agent_speak_percentage: anyOf: - type: number - type: 'null' title: Agent Speak Percentage description: Percentage of the call where the agent was speaking avg_agent_latency: anyOf: - type: number - type: 'null' title: Avg Agent Latency description: Average latency of the agent's responses during the call latency: anyOf: - $ref: '#/components/schemas/Latency' - type: 'null' description: Latency metrics for the agent's responses filler_ignored_latency: anyOf: - $ref: '#/components/schemas/FillerIgnoredLatency' - type: 'null' description: Filler ignored latency metrics num_turns: anyOf: - type: integer - type: 'null' title: Num Turns description: Total number of turns taken by the agent during the call call_summary: anyOf: - type: string - type: 'null' title: Call Summary description: Summary of the call, if applicable custom_evals: anyOf: - items: {} type: array - additionalProperties: true type: object - type: 'null' title: Custom Evals description: List of custom evaluations performed during the call custom_evals_success_rate: anyOf: - type: number - type: 'null' title: Custom Evals Success Rate description: Success rate of the custom evaluations performed during the call goal_success: anyOf: - type: boolean - type: 'null' title: Goal Success description: Whether the goal was successfully achieved during the call goal_reasoning: anyOf: - type: string - type: 'null' title: Goal Reasoning description: Reasoning behind the goal success, if applicable pronunciation_score: anyOf: - type: number - type: 'null' title: Pronunciation Score description: Pronunciation score of the agent during the call pronunciation_reasoning: anyOf: - type: string - type: 'null' title: Pronunciation Reasoning description: Reasoning behind the pronunciation score, if applicable custom_metrics: anyOf: - items: $ref: '#/components/schemas/src__models__api_custom_metric__CustomMetric' type: array - type: 'null' title: Custom Metrics description: Custom metrics associated with the evaluation type: object required: - agent_speak_percentage - avg_agent_latency title: Evaluation description: Pydantic model for evaluation result ExpectedToolCallDetail: properties: parameters: anyOf: - additionalProperties: true type: object - type: 'null' title: Parameters description: Expected parameters output: anyOf: - {} - type: 'null' title: Output description: Expected output type: object title: ExpectedToolCallDetail Latency: properties: avg_agent_latency: anyOf: - type: number - type: 'null' title: Avg Agent Latency description: Average latency default: 0 max_agent_latency: anyOf: - type: number - type: 'null' title: Max Agent Latency description: Maximum latency default: 0 p50_agent_latency: anyOf: - type: number - type: 'null' title: P50 Agent Latency description: 50th percentile latency default: 0 p90_agent_latency: anyOf: - type: number - type: 'null' title: P90 Agent Latency description: 90th percentile latency default: 0 p95_agent_latency: anyOf: - type: number - type: 'null' title: P95 Agent Latency description: 95th percentile latency default: 0 p99_agent_latency: anyOf: - type: number - type: 'null' title: P99 Agent Latency description: 99th percentile latency default: 0 type: object title: Latency SingleSimulationResultResponse: properties: simulation_result: $ref: '#/components/schemas/SimulationResultResponse' description: The requested simulation result status: type: string title: Status description: Status of the response default: '200' type: object required: - simulation_result title: SingleSimulationResultResponse Event: properties: title: type: string title: Title description: Title of the event start_offset_ms: type: integer title: Start Offset Ms description: Start offset of the event in milliseconds description: anyOf: - type: string - type: 'null' title: Description description: Description of the event end_offset_ms: anyOf: - type: integer - type: 'null' title: End Offset Ms description: End offset of the event in milliseconds tags: anyOf: - items: type: string type: array - type: 'null' title: Tags description: List of tags associated with the event metadata: anyOf: - additionalProperties: true type: object - type: 'null' title: Metadata description: Additional metadata associated with the event type: object required: - title - start_offset_ms title: Event description: Pydantic model for event data HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError securitySchemes: apiKeyAuth: type: apiKey in: header name: X-API-Key description: API key required to authenticate requests.