--- title: "Retrieve a test run" method: GET path: "/test_framework/v2/runs/{id}/" tags: ["test_framework"] --- # Retrieve a test run `GET /test_framework/v2/runs/{id}/` ## Request - Base URL: `https://api.cekura.ai` - URL: `https://api.cekura.ai/test_framework/v2/runs/{id}/` - Auth: one of: - API key in header `X-CEKURA-API-KEY` - HTTP bearer - HTTP bearer - API key in header `X-VOCERA-SHAREABLE-LINK-TOKEN` - HTTP bearer Retrieve one run by `run_id` (the integer path parameter), including its transcript, metric evaluations and error message. Prefer this over `bulk` whenever you want a single run: `bulk` takes a comma-separated `run_ids` plus a scope parameter, so it is easy to widen by accident into every run of a result. The `call_id` field on the response is the provider's call identifier (a string) — do NOT pass it where `run_id` is expected. ## Path parameters - `id` integer, required ## Response `200` - Run - `id` integer - `provider_call_id` string: Call ID from the Assistant provider Example: `call_abc123` - `trace_id` string: OpenTelemetry trace ID (32-char hex). Set when OTel tracing is enabled. - `is_log_present` boolean: Whether provider execution logs are stored for this run. - `scenario` integer, nullable - `scenario_name` string - `scenario_type` string: Type of the run's scenario (e.g. instruction, conditional_actions), null if the scenario was deleted - `personality` integer, nullable: Personality this run belongs to - `personality_name` string: Name of the personality this run belongs to - `agent` integer: ID of the agent associated with this run - `agent_name` string: Name of the agent associated with this run - `agent_version` AgentVersionSummary - `history_id` integer, required: History record ID of the agent version - `version_id` string, nullable, required: Version label, e.g. "v12" - `version_name` string, nullable, required: Optional name given to the version - `is_current` boolean, required: Whether this is the agent's current version - `result_id` integer - `result_name` string: Name of the result this run belongs to - `expected_outcome_prompt` string - `expected_outcome` ExpectedOutcome - `score` number, double, required: Score of the expected outcome - `explanation` string[], required - `outcome_alignments` OutcomeAlignment[], required - `outcome` string, required: Outcome of the expected outcome - `prompt_part` string, required: Prompt part of the expected outcome - `aligned` boolean, required: Whether the outcome aligns with the prompt part - `evaluation` Evaluation - `metrics` CallLogListSerializerMetricsWithExplanation[], required - `id` integer, required: Metric ID - `name` string, required: Metric name - `type` string, required: Metric type - `score` number, double, required: Evaluated metric score, Present if metrictype is not enum - `enum` string, required: Metric enum, Present if type is enum - `value` string, required: Evaluated metric value, Present if metric type is enum - `explanation` string[], required - `extra` object, required: Evaluated metric extra data - `rubric` unknown - `transcript` string: 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. ``` - `transcript_object` RunListTranscriptObject[]: Transcript object - `role` string, required: Role of the message - `content` string, required: Content of the message - `timestamp` number, double, required: Timestamp of the message - `normalized_content` string, required: Backend comparison key for the full turn - `comparison_spans` unknown[], required: Raw multilingual-number spans with backend comparison keys - unknown - `duration` string: Duration of the run in MM:SS format - `voice_recording_url` string: URL to access the voice recording of this run - `email_id` string, email, nullable - `status` 'running' | 'completed' | 'failed' | 'pending' | 'in_progress' | 'evaluating' | 'in_queue' | 'timeout' | 'cancelled' | 'scaling_up': * `running` - Running * `completed` - Completed * `failed` - Failed * `pending` - Pending * `in_progress` - In Progress * `evaluating` - Evaluating * `in_queue` - In Queue * `timeout` - Timeout * `cancelled` - Cancelled * `scaling_up` - Scaling Up - `evaluation_status` 'success' | 'failure' | 'reviewed_success' | 'reviewed_failure': * `success` - Success * `failure` - Failure * `reviewed_success` - Reviewed Success * `reviewed_failure` - Reviewed Failure - `metadata` unknown - `success` boolean: Whether this run passed its quality evaluation. false means either the call failed to connect or an evaluation check did not pass. Check `error_message` for connection failures and `evaluation` for check results. - `is_reviewed` boolean: Whether the call has been reviewed. Example: `true` or `false` - `feedback` string - `timestamp` string, date-time - `executed_at` string, date-time, nullable - `outbound_number` string: Phone number used to make the outbound call for this run - `inbound_number` string: Phone number used to receive the inbound call for this run - `critical_categories` RunListCriticalCategories[]: List of critical evaluation categories and their results for this run - `category_id` integer, required: Category ID - `category` string, required: Category name - `deviation` number, double, required: Deviation - `wrongly_marked` boolean, required: Whether the category was wrongly marked - `feedback` string, required: Feedback - `priority` 'critical' | 'non-critical' | 'not_a_bug', required: Priority * `critical` - Critical * `non-critical` - Non Critical * `not_a_bug` - Not A Bug - `error_message` string - `scenario_instructions` string - `run_as_text` boolean - `test_profile_data` TestProfileData - `id` integer, required: Test Profile ID - `name` string, required: Test Profile name - `information` object, required: Information of the test profile Example: ```json { "user_name": "John Doe", "user_email": "john.doe@example.com", } ``` - `generated_mock_tool_entries` object[]: Expected mock tool calls for this run's evaluator. Each entry has shape {tool_id, tool_name, new_entry: {input, output, response?}}. - `mocked_tool_names` string[]: Tool names whose calls in this run's transcript were served by Cekura mocks. Where the provider reports the URL it resolved per tool call (ElevenLabs), a mock-enabled tool the provider served from the customer's own endpoint is excluded; otherwise this is the set that was mock-enabled. Empty if no tools were mocked. - `provider_call_details` unknown - `agent_number` string, nullable: Phone number of the agent (only for voice inbound calls) - `testing_channel_index` integer, nullable: The channel index of the testing agent in the audio recording - `waveform` object: Amplitude envelope of the recording, one array of values per audio channel, so a waveform can be drawn without downloading the audio. Null for recordings processed before peaks were stored. - `run_type` string, nullable: Run Execution Type - `outbound_dial_window_opens_at` string: ISO timestamp when the outbound dial window opened. Null until the run reaches pending/waiting-for-call. - `outbound_dial_window_seconds` string: Duration of the outbound dial window in seconds. - `outbound_dial_window_closes_at` string: ISO timestamp when the outbound dial window closes. Null until the window opens. ## Changes - **2026-11-03** `a6fb6a739212`: 1 info - endpoint added [Operation history](https://skmtc.dev/cekura/apis/cekura-api/changes/test_framework/v2/runs/:id/get.md) --- [API](https://skmtc.dev/cekura/apis/cekura-api.md) - [All operations](https://skmtc.dev/cekura/apis/cekura-api/llms.txt) - [OpenAPI document](https://skmtc.dev/cekura/apis/cekura-api/revisions/72f933bec1a6?raw)