Get Combined Results Report

Get a combined report across results

curl --request GET \
  --url https://api.cekura.ai/test_framework/v2/results/reports/ \
  --header 'X-CEKURA-API-KEY: <api-key>'

const options = {method: 'GET', headers: {'X-CEKURA-API-KEY': '<api-key>'}};

fetch('https://api.cekura.ai/test_framework/v2/results/reports/', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.cekura.ai/test_framework/v2/results/reports/",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "X-CEKURA-API-KEY: <api-key>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.cekura.ai/test_framework/v2/results/reports/"

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("X-CEKURA-API-KEY", "<api-key>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://api.cekura.ai/test_framework/v2/results/reports/")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)
request["X-CEKURA-API-KEY"] = '<api-key>'

response = http.request(request)
puts response.read_body

{
  "status": "<string>",
  "success_rate": 123,
  "total_runs_count": 123,
  "completed_runs_count": 123,
  "success_runs_count": 123,
  "failed_runs_count": 123,
  "agent": 123,
  "agent_version": "<unknown>",
  "overall_evaluation": "<unknown>",
  "metrics": "<unknown>",
  "critical_categories": "<unknown>",
  "runs_by_tags": "<unknown>",
  "latency_data": "<unknown>",
  "failed_reasons": "<unknown>",
  "performance_metrics": "<unknown>",
  "runs": "<unknown>"
}

{
  "field_name": [
    "<string>"
  ]
}

GET

test_framework

results

reports

Get a combined report across results

curl --request GET \
  --url https://api.cekura.ai/test_framework/v2/results/reports/ \
  --header 'X-CEKURA-API-KEY: <api-key>'

const options = {method: 'GET', headers: {'X-CEKURA-API-KEY': '<api-key>'}};

fetch('https://api.cekura.ai/test_framework/v2/results/reports/', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.cekura.ai/test_framework/v2/results/reports/",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "X-CEKURA-API-KEY: <api-key>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.cekura.ai/test_framework/v2/results/reports/"

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("X-CEKURA-API-KEY", "<api-key>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://api.cekura.ai/test_framework/v2/results/reports/")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)
request["X-CEKURA-API-KEY"] = '<api-key>'

response = http.request(request)
puts response.read_body

{
  "status": "<string>",
  "success_rate": 123,
  "total_runs_count": 123,
  "completed_runs_count": 123,
  "success_runs_count": 123,
  "failed_runs_count": 123,
  "agent": 123,
  "agent_version": "<unknown>",
  "overall_evaluation": "<unknown>",
  "metrics": "<unknown>",
  "critical_categories": "<unknown>",
  "runs_by_tags": "<unknown>",
  "latency_data": "<unknown>",
  "failed_reasons": "<unknown>",
  "performance_metrics": "<unknown>",
  "runs": "<unknown>"
}

{
  "field_name": [
    "<string>"
  ]
}

Authorizations

X-CEKURA-API-KEY

string

header

required

API Key Authentication. It should be included in the header of each request.

Query Parameters

result_ids

string

required

Results to combine — comma-separated string (e.g. '5591,5592'), not a JSON array.

run_filters

string

Optional JSON-encoded filter object restricting which runs the report counts. Every aggregate in the response is computed over the matching runs only. Invalid JSON returns 400.

join is and (every filter must match) or or (any filter may match). Each item in filters has an id (the run field), an operator and a value.

Supported filters:

success — equals with true or false
status — equals with one run status, e.g. "completed"
id — equals or in with run IDs
scenarios — in with scenario IDs
tags — in with scenario tags; a run matches if its scenario carries any of them
scenario_name, call_ended_reason — in with a list of values
metrics — no top-level operator; value is a list of metric conditions, each with the metric id and an operator: equals (with value), greaterThanOrEqual / lessThanOrEqual (with value), range (with min and max), or exists / notExists

Example — failed runs from two scenarios whose metric 101 scored at least 3:

{
  "join": "and",
  "filters": [
    {"id": "success", "operator": "equals", "value": false},
    {"id": "scenarios", "operator": "in", "value": [3120, 3121]},
    {"id": "metrics", "value": [{"id": 101, "operator": "greaterThanOrEqual", "value": 3}]}
  ]
}

string

default:{-runs}

Field selection. {-runs} (the default) returns the aggregates only; {*} additionally embeds every run and can be very large.

agent_id

integer

Tenant scope. Supply one of agent_id, assistant_id, project_id when authenticating with a user session or OAuth bearer token; omit when using an API key already scoped to the tenant.

assistant_id

string

Tenant scope. Supply one of agent_id, assistant_id, project_id when authenticating with a user session or OAuth bearer token; omit when using an API key already scoped to the tenant.

project_id

integer

Tenant scope. Supply one of agent_id, assistant_id, project_id when authenticating with a user session or OAuth bearer token; omit when using an API key already scoped to the tenant.

Response

status

string

required

Always 'completed' — the report is computed on read, not queued.

success_rate

number<double>

required

Percentage of runs that passed, across every result in the report

total_runs_count

integer

required

Runs in the report, including those still executing

completed_runs_count

integer

required

Runs that reached a terminal state (completed, failed, timeout or cancelled)

success_runs_count

integer

required

Completed runs that passed

failed_runs_count

integer

required

Completed runs that failed

agent

integer

required

ID of the agent the results belong to

agent_version

any | null

required

Agent version every result ran against, or null when the results did not all run against the same version.

Example:

{
  "history_id": 812,
  "version_id": "v3",
  "version_name": "Pricing prompt fix",
  "is_current": true
}

overall_evaluation

any

required

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 (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
worst_performing_metrics — binary_adherence lists the IDs of binary metrics that did not pass on every run, lowest pass rate first
numeric_metrics — numeric metric averages with their percentiles, plus average ringing duration when available
enum_metrics — the metric ID of every enum evaluation, one entry per evaluated run
extra_metrics — derived figures such as average ringing duration and expected-outcome score

Example:

{
  "success_rate": 66.67,
  "metric_summary": {
    "101": {
      "id": 101,
      "name": "Politeness",
      "type": "binary",
      "vocera_defined_metric_code": "",
      "score": 0.67,
      "overall_explanation": [],
      "errors": [
        {
          "id": 3120,
          "name": "Asks for pricing",
          "agent": 42,
          "personality": 7,
          "personality_name": "Busy professional",
          "retell_agent_id": "",
          "instructions": "",
          "is_simulating": false,
          "runs": [90012]
        }
      ]
    },
    "102": {
      "id": 102,
      "name": "Sentiment",
      "type": "enum",
      "vocera_defined_metric_code": "",
      "score": null,
      "overall_explanation": [],
      "errors": [],
      "enums": {
        "positive": {"score": 100.0, "count": 3, "runs": [{"id": 90011}, {"id": 90012}, {"id": 90013}]}
      }
    },
    "103": {
      "id": 103,
      "name": "Latency",
      "type": "numeric",
      "vocera_defined_metric_code": "",
      "score": 850.0,
      "p50": 800.0,
      "overall_explanation": [],
      "errors": []
    },
    "104": {
      "id": 104,
      "name": "Critical Deviations",
      "type": "binary",
      "vocera_defined_metric_code": "",
      "score": 0.67,
      "overall_explanation": [],
      "errors": [],
      "categories": {
        "55": {
          "id": 55,
          "category": "Wrong price quoted",
          "runs": [{"id": 90012}],
          "runs_count": 1,
          "priority_counts": {"critical": 1, "non-critical": 0, "not_a_bug": 0},
          "scenarios": {}
        }
      }
    }
  },
  "worst_performing_metrics": {"binary_adherence": [101, 104]},
  "numeric_metrics": [
    {"name": "Latency", "type": "numeric", "value": 850.0, "percentiles": {"p50": 800.0}},
    {"name": "Average Ringing Duration", "type": "numeric", "value": 2.5, "percentiles": {"p50": 2.5}}
  ],
  "enum_metrics": [102, 102, 102],
  "extra_metrics": [
    {"name": "Average Ringing Duration", "type": "numeric", "value": 2.5, "percentiles": {"p50": 2.5}},
    {"name": "Expected Outcome", "type": "numeric", "value": 3.33}
  ]
}

metrics

any

required

Metrics configured on the agent.

Example:

[
  {
    "id": 101,
    "name": "Politeness",
    "eval_type": "binary",
    "simulation_enabled": true,
    "observability_enabled": true,
    "function_name": null,
    "vocera_defined_metric_code": ""
  }
]

critical_categories

any

required

Critical-issue categories found across the runs, most critical first. Categories marked as not a bug and evaluations marked as wrong are excluded.

Example:

[
  {
    "id": 55,
    "category": "Wrong price quoted",
    "scenarios": {},
    "runs_count": 1,
    "runs": [{"id": 90012}],
    "priority_counts": {"critical": 1, "non-critical": 0, "not_a_bug": 0}
  }
]

runs_by_tags

any

required

Keyed by scenario tag: the IDs of the runs whose scenario carries the tag and the success rate (percentage) of those runs.

Example:

{
  "billing": {"runs": [90013, 90012, 90011], "success_rate": 66.67}
}

latency_data

any

required

Response latency in milliseconds across all measured turns of all runs.

Example:

{"mean": 800.0, "median": 800.0, "p50": 800.0, "p95": 890.0, "p99": 898.0}

failed_reasons

any

required

Failure issues merged and deduplicated across the results, ranked by how many runs they affect.

Example:

{
  "issues": [
    {
      "rank": 1,
      "title": "Missed pricing",
      "description": "The agent never shared pricing when asked.",
      "run_ids": [90012],
      "affected_count": 1
    }
  ],
  "total_failed_runs": 1
}

performance_metrics

any

required

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 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.

Example:

[
  {
    "metric_id": 101,
    "metric_name": "Politeness",
    "eval_type": "binary",
    "aggregate_value": 66.7,
    "aggregate_unit": "percent",
    "passed": false,
    "threshold_text": ">= 80%",
    "evaluated_runs_count": 3,
    "evaluated_run_ids": [90013, 90012, 90011],
    "failing_run_ids": [90012],
    "passing_run_ids": [90013, 90011],
    "in_rubric": true
  },
  {
    "metric_id": 105,
    "metric_name": "Clarity",
    "eval_type": "continuous_qualitative",
    "aggregate_value": 4.0,
    "aggregate_unit": "score",
    "passed": null,
    "threshold_text": "",
    "evaluated_runs_count": 3,
    "evaluated_run_ids": [90013, 90012, 90011],
    "failing_run_ids": [],
    "passing_run_ids": [],
    "in_rubric": false,
    "score_range_run_ids": {"0-50": [], "50-75": [], ">75": [90013, 90012, 90011]}
  }
]

runs

any

Every run in the report, keyed by run ID. Present only when ql selects it (e.g. {*}); the default {-runs} omits it.

Example:

{
  "90012": {
    "id": 90012,
    "result_id": 5591,
    "result_name": "Nightly regression",
    "scenario": 3120,
    "scenario_name": "Asks for pricing",
    "personality_name": "Busy professional",
    "test_profile_name": null,
    "expected_outcome": {"score": 0},
    "success": false,
    "status": "completed",
    "evaluation_status": "failure",
    "evaluation": {
      "metrics": [
        {
          "id": 101,
          "name": "Politeness",
          "type": "binary",
          "score": false,
          "score_normalized": 0,
          "explanation": ["The agent interrupted the caller twice."],
          "extra": {},
          "vocera_defined_metric_code": "",
          "function_name": null,
          "thumbs_up": null
        },
        {
          "id": 102,
          "name": "Sentiment",
          "type": "enum",
          "enum": "positive",
          "explanation": [],
          "extra": {},
          "vocera_defined_metric_code": "",
          "function_name": null,
          "thumbs_up": null
        }
      ]
    },
    "timestamp": "2026-09-24T08:43:10.473761Z",
    "executed_at": "2026-09-24T08:43:12.000000Z",
    "duration": "01:00",
    "error_message": "",
    "metadata": {"ringing_duration": 2.5},
    "inbound_number": "",
    "outbound_dial_window_opens_at": null,
    "outbound_dial_window_seconds": null,
    "outbound_dial_window_closes_at": null
  }
}