Properties
| Name | Type | Description |
|---|---|---|
| status | string | Always 'completed' — the report is computed on read, not queued. |
| success_rate | number | Percentage of runs that passed, across every result in the report |
| total_runs_count | integer | Runs in the report, including those still executing |
| completed_runs_count | integer | Runs that reached a terminal state (completed, failed, timeout or cancelled) |
| success_runs_count | integer | Completed runs that passed |
| failed_runs_count | integer | Completed runs that failed |
| agent | integer | ID of the agent the results belong to |
| agent_version | object | Agent version every result ran against, or `null` when the results did not all run against the same version. Example: ```json { "history_id": 812, "version_id": "v3", "version_name": "Pricing prompt f |
| overall_evaluation | object | Aggregate evaluation across all runs in the report. - `success_rate` — percentage of runs that passed - `metric_summary` — keyed by metric ID. Every entry has `id`, `name`, `type`, `score`, `errors` ( |
| metrics | object | Metrics configured on the agent. Example: ```json [ { "id": 101, "name": "Politeness", "eval_type": "binary", "simulation_enabled": true, "observability_enabled": true, "function_name": null, "vocera_ |
| critical_categories | object | Critical-issue categories found across the runs, most critical first. Categories marked as not a bug and evaluations marked as wrong are excluded. Example: ```json [ { "id": 55, "category": "Wrong pri |
| runs_by_tags | object | Keyed by scenario tag: the IDs of the runs whose scenario carries the tag and the success rate (percentage) of those runs. Example: ```json { "billing": {"runs": [90013, 90012, 90011], "success_rate": |
| latency_data | object | Response latency in milliseconds across all measured turns of all runs. Example: ```json {"mean": 800.0, "median": 800.0, "p50": 800.0, "p95": 890.0, "p99": 898.0} ``` |
| failed_reasons | object | Failure issues merged and deduplicated across the results, ranked by how many runs they affect. Example: ```json { "issues": [ { "rank": 1, "title": "Missed pricing", "description": "The agent never s |
| performance_metrics | object | Per-metric performance across the runs, rubric metrics first. `aggregate_unit` is `percent`, `value`, `score` or an empty string. `passed` and `threshold_text` come from the project rubric; `passed` i |
| runs | object | Every run in the report, keyed by run ID. Present only when `ql` selects it (e.g. `{*}`); the default `{-runs}` omits it. Example: ```json { "90012": { "id": 90012, "result_id": 5591, "result_name": " |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://artifacts.apis.io/cekura-ai/json-schema/cekura-ai-schema-combined-results-report-schema.json",
"title": "SchemaCombinedResultsReport",
"x-generated": "2026-10-29",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/cekura-ai-openapi.json#/components/schemas/SchemaCombinedResultsReport",
"type": "object",
"properties": {
"status": {
"type": "string",
"description": "Always 'completed' — the report is computed on read, not queued."
},
"success_rate": {
"type": "number",
"format": "double",
"description": "Percentage of runs that passed, across every result in the report"
},
"total_runs_count": {
"type": "integer",
"description": "Runs in the report, including those still executing"
},
"completed_runs_count": {
"type": "integer",
"description": "Runs that reached a terminal state (completed, failed, timeout or cancelled)"
},
"success_runs_count": {
"type": "integer",
"description": "Completed runs that passed"
},
"failed_runs_count": {
"type": "integer",
"description": "Completed runs that failed"
},
"agent": {
"type": "integer",
"description": "ID of the agent the results belong to"
},
"agent_version": {
"oneOf": [
{},
{
"type": "null"
}
],
"description": "\nAgent version every result ran against, or `null` when the results did not all run against the same version.\n\nExample:\n```json\n{\n \"history_id\": 812,\n \"version_id\": \"v3\",\n \"version_name\": \"Pricing prompt fix\",\n \"is_current\": true\n}\n```\n"
},
"overall_evaluation": {
"description": "\nAggregate evaluation across all runs in the report.\n\n- `success_rate` — percentage of runs that passed\n- `metric_summary` — keyed by metric ID. Every entry has `id`, `name`, `type`, `score`, `errors` (the scenarios whose runs failed the metric, with the failing run IDs) and `overall_explanation`. Enum metrics add `enums` (per enum value: `score` as a percentage, `count` and `runs`), numeric metrics add percentiles such as `p50`, and critical metrics add `categories` keyed by category ID\n- `worst_performing_metrics` — `binary_adherence` lists the IDs of binary metrics that did not pass on every run, lowest pass rate first\n- `numeric_metrics` — numeric metric averages with their percentiles, plus average ringing duration when available\n- `enum_metrics` — the metric ID of every enum evaluation, one entry per evaluated run\n- `extra_metrics` — derived figures such as average ringing duration and expected-outcome score\n\nExample:\n```json\n{\n \"success_rate\": 66.67,\n \"metric_summary\": {\n \"101\": {\n \"id\": 101,\n \"name\": \"Politeness\",\n \"type\": \"binary\",\n \"vocera_defined_metric_code\": \"\",\n \"score\": 0.67,\n \"overall_explanation\": [],\n \"errors\": [\n {\n \"id\": 3120,\n \"name\": \"Asks for pricing\",\n \"agent\": 42,\n \"personality\": 7,\n \"personality_name\": \"Busy professional\",\n \"retell_agent_id\": \"\",\n \"instructions\": \"\",\n \"is_simulating\": false,\n \"runs\": [90012]\n }\n ]\n },\n \"102\": {\n \"id\": 102,\n \"name\": \"Sentiment\",\n \"type\": \"enum\",\n \"vocera_defined_metric_code\": \"\",\n \"score\": null,\n \"overall_explanation\": [],\n \"errors\": [],\n \"enums\": {\n \"positive\": {\"score\": 100.0, \"count\": 3, \"runs\": [{\"id\": 90011}, {\"id\": 90012}, {\"id\": 90013}]}\n }\n },\n \"103\": {\n \"id\": 103,\n \"name\": \"Latency\",\n \"type\": \"numeric\",\n \"vocera_defined_metric_code\": \"\",\n \"score\": 850.0,\n \"p50\": 800.0,\n \"overall_explanation\": [],\n \"errors\": []\n },\n \"104\": {\n \"id\": 104,\n \"name\": \"Critical Deviations\",\n \"type\": \"binary\",\n \"vocera_defined_metric_code\": \"\",\n \"score\": 0.67,\n \"overall_explanation\": [],\n \"errors\": [],\n \"categories\": {\n \"55\": {\n \"id\": 55,\n \"category\": \"Wrong price quoted\",\n \"runs\": [{\"id\": 90012}],\n \"runs_count\": 1,\n \"priority_counts\": {\"critical\": 1, \"non-critical\": 0, \"not_a_bug\": 0},\n \"scenarios\": {}\n }\n }\n }\n },\n \"worst_performing_metrics\": {\"binary_adherence\": [101, 104]},\n \"numeric_metrics\": [\n {\"name\": \"Latency\", \"type\": \"numeric\", \"value\": 850.0, \"percentiles\": {\"p50\": 800.0}},\n {\"name\": \"Average Ringing Duration\", \"type\": \"numeric\", \"value\": 2.5, \"percentiles\": {\"p50\": 2.5}}\n ],\n \"enum_metrics\": [102, 102, 102],\n \"extra_metrics\": [\n {\"name\": \"Average Ringing Duration\", \"type\": \"numeric\", \"value\": 2.5, \"percentiles\": {\"p50\": 2.5}},\n {\"name\": \"Expected Outcome\", \"type\": \"numeric\", \"value\": 3.33}\n ]\n}\n```\n"
},
"metrics": {
"description": "\nMetrics configured on the agent.\n\nExample:\n```json\n[\n {\n \"id\": 101,\n \"name\": \"Politeness\",\n \"eval_type\": \"binary\",\n \"simulation_enabled\": true,\n \"observability_enabled\": true,\n \"function_name\": null,\n \"vocera_defined_metric_code\": \"\"\n }\n]\n```\n"
},
"critical_categories": {
"description": "\nCritical-issue categories found across the runs, most critical first. Categories marked as not a bug and evaluations marked as wrong are excluded.\n\nExample:\n```json\n[\n {\n \"id\": 55,\n \"category\": \"Wrong price quoted\",\n \"scenarios\": {},\n \"runs_count\": 1,\n \"runs\": [{\"id\": 90012}],\n \"priority_counts\": {\"critical\": 1, \"non-critical\": 0, \"not_a_bug\": 0}\n }\n]\n```\n"
},
"runs_by_tags": {
"description": "\nKeyed by scenario tag: the IDs of the runs whose scenario carries the tag and the success rate (percentage) of those runs.\n\nExample:\n```json\n{\n \"billing\": {\"runs\": [90013, 90012, 90011], \"success_rate\": 66.67}\n}\n```\n"
},
"latency_data": {
"description": "\nResponse latency in milliseconds across all measured turns of all runs.\n\nExample:\n```json\n{\"mean\": 800.0, \"median\": 800.0, \"p50\": 800.0, \"p95\": 890.0, \"p99\": 898.0}\n```\n"
},
"failed_reasons": {
"description": "\nFailure issues merged and deduplicated across the results, ranked by how many runs they affect.\n\nExample:\n```json\n{\n \"issues\": [\n {\n \"rank\": 1,\n \"title\": \"Missed pricing\",\n \"description\": \"The agent never shared pricing when asked.\",\n \"run_ids\": [90012],\n \"affected_count\": 1\n }\n ],\n \"total_failed_runs\": 1\n}\n```\n"
},
"performance_metrics": {
"description": "\nPer-metric performance across the runs, rubric metrics first. `aggregate_unit` is `percent`, `value`, `score` or an empty string. `passed` and `threshold_text` come from the project rubric; `passed` is `null` and `in_rubric` is `false` for metrics without a rubric rule. Enum metrics add `enum_run_ids` (run IDs per enum value), rating metrics add `score_range_run_ids` and expected-outcome metrics add `review_required_run_ids`.\n\nExample:\n```json\n[\n {\n \"metric_id\": 101,\n \"metric_name\": \"Politeness\",\n \"eval_type\": \"binary\",\n \"aggregate_value\": 66.7,\n \"aggregate_unit\": \"percent\",\n \"passed\": false,\n \"threshold_text\": \">= 80%\",\n \"evaluated_runs_count\": 3,\n \"evaluated_run_ids\": [90013, 90012, 90011],\n \"failing_run_ids\": [90012],\n \"passing_run_ids\": [90013, 90011],\n \"in_rubric\": true\n },\n {\n \"metric_id\": 105,\n \"metric_name\": \"Clarity\",\n \"eval_type\": \"continuous_qualitative\",\n \"aggregate_value\": 4.0,\n \"aggregate_unit\": \"score\",\n \"passed\": null,\n \"threshold_text\": \"\",\n \"evaluated_runs_count\": 3,\n \"evaluated_run_ids\": [90013, 90012, 90011],\n \"failing_run_ids\": [],\n \"passing_run_ids\": [],\n \"in_rubric\": false,\n \"score_range_run_ids\": {\"0-50\": [], \"50-75\": [], \">75\": [90013, 90012, 90011]}\n }\n]\n```\n"
},
"runs": {
"description": "\nEvery run in the report, keyed by run ID. Present only when `ql` selects it (e.g. `{*}`); the default `{-runs}` omits it.\n\nExample:\n```json\n{\n \"90012\": {\n \"id\": 90012,\n \"result_id\": 5591,\n \"result_name\": \"Nightly regression\",\n \"scenario\": 3120,\n \"scenario_name\": \"Asks for pricing\",\n \"personality_name\": \"Busy professional\",\n \"test_profile_name\": null,\n \"expected_outcome\": {\"score\": 0},\n \"success\": false,\n \"status\": \"completed\",\n \"evaluation_status\": \"failure\",\n \"evaluation\": {\n \"metrics\": [\n {\n \"id\": 101,\n \"name\": \"Politeness\",\n \"type\": \"binary\",\n \"score\": false,\n \"score_normalized\": 0,\n \"explanation\": [\"The agent interrupted the caller twice.\"],\n \"extra\": {},\n \"vocera_defined_metric_code\": \"\",\n \"function_name\": null,\n \"thumbs_up\": null\n },\n {\n \"id\": 102,\n \"name\": \"Sentiment\",\n \"type\": \"enum\",\n \"enum\": \"positive\",\n \"explanation\": [],\n \"extra\": {},\n \"vocera_defined_metric_code\": \"\",\n \"function_name\": null,\n \"thumbs_up\": null\n }\n ]\n },\n \"timestamp\": \"2026-09-24T08:43:10.473761Z\",\n \"executed_at\": \"2026-09-24T08:43:12.000000Z\",\n \"duration\": \"01:00\",\n \"error_message\": \"\",\n \"metadata\": {\"ringing_duration\": 2.5},\n \"inbound_number\": \"\",\n \"outbound_dial_window_opens_at\": null,\n \"outbound_dial_window_seconds\": null,\n \"outbound_dial_window_closes_at\": null\n }\n}\n```\n"
}
},
"required": [
"agent",
"agent_version",
"completed_runs_count",
"critical_categories",
"failed_reasons",
"failed_runs_count",
"latency_data",
"metrics",
"overall_evaluation",
"performance_metrics",
"runs_by_tags",
"status",
"success_rate",
"success_runs_count",
"total_runs_count"
]
}Work with this as data
Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for schemas
4 MCP tools reach this
find_json_schemasBrowse and filter every JSON Schema in the catalog.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/cekura-ai-schema-combined-results-report"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"Discovery needs no key. Ratings and market analysis are Pro.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.