> ## Documentation Index > Fetch the complete documentation index at: https://docs.cekura.ai/llms.txt > Use this file to discover all available pages before exploring further. # Reevaluate Calls > Re-run metric evaluation on a call log ## OpenAPI ````yaml post /observability/v1/call-logs/rerun_evaluation/ openapi: 3.1.0 info: title: Cekura API version: v1 description: >- Complete API documentation for the Cekura platform. This API provides endpoints for testing, observing, and evaluating AI voice agents — including managing agents, running evaluators, defining metrics, and analyzing call quality. servers: - url: https://api.cekura.ai security: [] paths: /observability/v1/call-logs/rerun_evaluation/: post: tags: - observability summary: Re-run metric evaluation on call logs description: >- Trigger metric re-evaluation on one or more existing call logs. Provide either `agent_id` or `assistant_id` (not both) to identify the agent, then specify which call logs to re-evaluate. **`call_logs` accepts:** - A list of call log IDs: `[1, 2, 3]` - The string `"all"` to re-evaluate every call log for the agent **Side effect:** for non-reviewed call logs, `success` is reset to `null` before re-evaluation begins. Reviewed call logs retain their human-approved outcome. **Rate limited.** If the limit is exceeded you will receive a 429 response — wait for the `Retry-After` duration before retrying. operationId: call-logs-rerun-evaluation-create requestBody: content: application/json: schema: $ref: '#/components/schemas/RerunEvaluation' examples: Re-evaluate-specific-call-logs: value: agent_id: 2142 call_logs: - 101 - 102 - 103 summary: re-evaluate-specific-call-logs Re-evaluate-all-call-logs: value: agent_id: 2142 call_logs: all summary: re-evaluate-all-call-logs Re-evaluate-using-assistant-id: value: assistant_id: 2143 call_logs: - 101 - 102 summary: re-evaluate-using-assistant-id application/x-www-form-urlencoded: schema: $ref: '#/components/schemas/RerunEvaluation' multipart/form-data: schema: $ref: '#/components/schemas/RerunEvaluation' required: true responses: '200': content: application/json: schema: type: array items: $ref: '#/components/schemas/CallLogDetail' description: '' '400': content: application/json: schema: type: object properties: field_name: type: array items: type: string description: '' security: - api_key: [] components: schemas: RerunEvaluation: type: object properties: agent_id: type: integer description: >- Cekura agent ID. Provide this or `assistant_id`, not both. Example: `2142` assistant_id: type: integer description: >- External assistant identifier. Provide this or `agent_id`, not both. Example: `2143` call_logs: type: array items: type: integer description: >- List of call log IDs to re-evaluate, or the string `"all"` for all call logs. Example: `[1, 2, 3]` required: - agent_id - assistant_id - call_logs CallLogDetail: type: object description: '' properties: id: type: integer readOnly: true duration: type: string readOnly: true description: |- Call duration in minutes in MM:SS format. Example: `01:10` voice_recording_url: type: string readOnly: true description: >- URL to access the voice recording. Example: `"https://storage.example.com/recordings/call_123_20240315.mp3"` critical_categories: type: array items: $ref: '#/components/schemas/CallLogCriticalCategories' readOnly: true description: Critical categories from call evaluation transcript_object: type: array items: $ref: '#/components/schemas/CallLogTranscriptObject' readOnly: true description: |- Structured transcript data with timestamps. Example: ```json [ { "role": "Testing Agent", "content": "Hello", "start_time": 1.2, "end_time": 1.8 }, { "role": "Main Agent", "content": "Hello, how can I help you today?", "start_time": 1.8, "end_time": 2.5 } ]` status: enum: - success - failure - reviewed_success - reviewed_failure type: string description: |- * `success` - Success * `failure` - Failure * `reviewed_success` - Reviewed Success * `reviewed_failure` - Reviewed Failure x-spec-enum-id: a5dfbbcee6f2a6ce agent_id: type: string description: |- Agent ID. Example: `2142` agent_name: type: string readOnly: true description: Agent name evaluation: allOf: - $ref: '#/components/schemas/Evaluation' readOnly: true description: |- Evaluation results for the call. Example: ```json { "metrics": [ { "id": 35, "name": "Instruction Follow", "type": "binary_workflow_adherence", "score": 0, "explanation": ["Agent failed to follow the opening script", "Missed key product information"], "vocera_defined_metric_code": "5dedc41b", "function_name": "check_critical_deviations", "extra": { "categories": [ { "category_id": 5, "category": "Script Adherence Issue", "deviation": "Agent deviated from required script", "priority": "critical" } ] } }, { "id": 18, "name": "Customer Satisfaction", "type": "binary_qualitative", "score": 5, "explanation": ["Customer expressed satisfaction with service"] } ] } ``` metadata: type: object additionalProperties: {} readOnly: true description: |- Additional call metadata. Example: ```json { "ended_reason": "customer-ended-call", "ringing_duration": 3.941, "call_type": "inbound" } ``` dynamic_variables: type: object additionalProperties: {} readOnly: true description: |- Dynamic Variables used in the call. Example: ```json { "customer_name": "John Doe", "order_id": "ORD-12345", "product_type": "premium" } ``` testing_channel_index: type: - integer - 'null' readOnly: true description: The channel index of the testing agent in the audio recording timestamp: type: string format: date-time description: |- When the call occurred. Example: `2024-03-15T10:15:45Z` success: type: - boolean - 'null' description: |- Whether the call was successful. Example: `true` or `false` is_reviewed: type: boolean description: |- Whether the call has been reviewed. Example: `true` or `false` feedback: type: string description: |- Feedback about the call. Example: `"Great Call"` rubric: oneOf: - {} - type: 'null' description: | Detailed rubric evaluation data Example: ```json [ { "metric_id": 100, "metric_name": "Call Quality", "value": 5, "explanation": ["The response was accurate"], "passed": true, "conditions": "score gte 5", "expected_conditions": {"operator": "and", "conditions": [{"field": "score", "op": "gte", "value": 5}]} } ] ``` transcript: type: string description: > Full text transcript of the call. Example: ```text [00:01] Testing Agent: Hello. [00:02] Main Agent: Hello, how can I help you today? [00:03] Testing Agent: Well, I mean, sure. What time exactly are we talking about here [00:04] Main Agent: 6 PM. [00:05] Testing Agent: Great. I'll book that for you. Just a sec. [00:06] Main Agent: Okay. ``` call_ended_reason: type: string description: | Reason why the call ended. Example: - `"customer-ended-call"` - `"agent-ended-call"` maxLength: 100 dropoff_point: type: string description: |- Point in conversation where user disengaged. Example: `"end of conversation as no queries remaining"` maxLength: 1000 topic: type: string description: | Topic of the call. Example: - `"product_inquiry"` - `"technical_support"` maxLength: 1000 customer_number: type: string description: | Customer's phone number or identifier. Example: - `"+1234567890"` - `"customer_abc123"` maxLength: 100 user_generated_transcript: oneOf: - {} - type: 'null' description: |- Manually created or corrected transcript data. Example: ```json [ { "role": "Testing Agent", "content": "I need help with my order", "timestamp": "00:15" } ]` error_message: type: - string - 'null' created_at: type: string format: date-time readOnly: true description: |- When this record was created. Example: `2024-03-15T10:30:45Z` updated_at: type: string format: date-time readOnly: true description: |- When this record was last updated. Example: `2024-03-15T10:35:11Z` call_id: type: string description: |- Unique identifier for the call. Example: - `"call_abc123xyz"` - `"stereo_audio_session_456"` maxLength: 100 trace_id: type: string description: >- OpenTelemetry trace ID (32-char hex). Set when OTel tracing is enabled. maxLength: 32 agent: type: - integer - 'null' description: Agent ID project: type: - integer - 'null' description: Project ID (denormalized from agent for query performance) required: - call_id CallLogCriticalCategories: type: object properties: category_id: type: integer description: Category ID category: type: string description: Category name deviation: type: number format: double description: Deviation wrongly_marked: type: boolean description: Whether the category was wrongly marked feedback: type: string description: Feedback priority: enum: - critical - non-critical - not_a_bug type: string x-spec-enum-id: 6b5f38576e0a1903 description: |- Priority * `critical` - Critical * `non-critical` - Non Critical * `not_a_bug` - Not A Bug required: - category - category_id - deviation - feedback - priority - wrongly_marked CallLogTranscriptObject: type: object properties: role: type: string description: Role of the message content: type: string description: Content of the message timestamp: type: number format: double description: Timestamp of the message required: - content - role - timestamp Evaluation: type: object properties: metrics: type: array items: $ref: '#/components/schemas/CallLogListSerializerMetricsWithExplanation' required: - metrics CallLogListSerializerMetricsWithExplanation: type: object properties: id: type: integer description: Metric ID name: type: string description: Metric name type: type: string description: Metric type score: type: number format: double description: Evaluated metric score, Present if metrictype is not enum enum: type: string description: Metric enum, Present if type is enum value: type: string description: Evaluated metric value, Present if metric type is enum explanation: type: array items: type: string description: Explanation of the metric extra: type: object additionalProperties: {} description: Evaluated metric extra data required: - enum - explanation - extra - id - name - score - type - value securitySchemes: api_key: type: apiKey name: X-CEKURA-API-KEY in: header description: >- API Key Authentication. It should be included in the header of each request. ````