Python (SDK)

from meetkai_mka1 import SDK


with SDK(
    bearer_auth="<YOUR_BEARER_TOKEN_HERE>",
) as sdk:

    res = sdk.llm.evals.import_agent_run(suite_id="eval_suite_aa87e2b1112a455b8deabed784372198", agent_name="omp", model="meetkai:functionary-urdu-mini-pak", suite_version=1, agent_version="17.3.8", agent_effort="medium", cost_usd=3.77, created_at=1704067200, metadata={
        "harness": "harbor",
        "benchmark": "terminal-bench-2.1",
    }, idempotency_key="harbor-job-2026-08-23-luna-medium", trials=[
        {
            "task_id": "fix-permissions",
            "sample_index": 0,
            "prompt": "The test suite fails because the fixture directory is not writable. Fix it.",
            "target": "all tests pass",
            "output_text": "9 passed in 2.25s",
            "scores": {
                "reward": 1,
                "resolved": 1,
            },
            "cost_usd": 0.0279,
            "input_tokens": 658456,
            "output_tokens": 6489,
            "cached_tokens": 658366,
        },
    ], finalize=True)

    # Handle response
    print(res)

import { SDK } from "@meetkai/mka1";

const sdk = new SDK({
  bearerAuth: "<YOUR_BEARER_TOKEN_HERE>",
});

async function run() {
  const result = await sdk.llm.evals.importAgentRun({
    importAgentRunRequest: {
      suiteId: "eval_suite_aa87e2b1112a455b8deabed784372198",
      suiteVersion: 1,
      agentName: "omp",
      agentVersion: "17.3.8",
      agentEffort: "medium",
      model: "meetkai:functionary-urdu-mini-pak",
      costUsd: 3.77,
      createdAt: 1704067200,
      metadata: {
        "harness": "harbor",
        "benchmark": "terminal-bench-2.1",
      },
      idempotencyKey: "harbor-job-2026-08-23-luna-medium",
      trials: [
        {
          taskId: "fix-permissions",
          sampleIndex: 0,
          prompt: "The test suite fails because the fixture directory is not writable. Fix it.",
          target: "all tests pass",
          outputText: "9 passed in 2.25s",
          scores: {
            "reward": 1,
            "resolved": 1,
          },
          costUsd: 0.0279,
          inputTokens: 658456,
          outputTokens: 6489,
          cachedTokens: 658366,
        },
      ],
    },
  });

  console.log(result);
}

run();

using MeetKai.MKA1;
using MeetKai.MKA1.Types.Components;
using System.Collections.Generic;

var sdk = new SDK(bearerAuth: "<YOUR_BEARER_TOKEN_HERE>");

var res = await sdk.Llm.Evals.ImportAgentRunAsync(body: new ImportAgentRunRequest() {
    SuiteId = "eval_suite_aa87e2b1112a455b8deabed784372198",
    SuiteVersion = 1,
    AgentName = "omp",
    AgentVersion = "17.3.8",
    AgentEffort = "medium",
    Model = "meetkai:functionary-urdu-mini-pak",
    CostUsd = 3.77D,
    CreatedAt = 1704067200,
    Metadata = new Dictionary<string, string>() {
        { "harness", "harbor" },
        { "benchmark", "terminal-bench-2.1" },
    },
    IdempotencyKey = "harbor-job-2026-08-23-luna-medium",
    Trials = new List<ImportAgentRunRequestTrial>() {
        new ImportAgentRunRequestTrial() {
            TaskId = "fix-permissions",
            SampleIndex = 0,
            Prompt = "The test suite fails because the fixture directory is not writable. Fix it.",
            Target = "all tests pass",
            OutputText = "9 passed in 2.25s",
            Scores = new Dictionary<string, double>() {
                { "reward", 1D },
                { "resolved", 1D },
            },
            CostUsd = 0.0279D,
            InputTokens = 658456,
            OutputTokens = 6489,
            CachedTokens = 658366,
        },
    },
});

// handle response

curl --request POST \
  --url https://apigw.mka1.com/api/v1/llm/evals/imports/agent-run \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "suite_id": "eval_suite_aa87e2b1112a455b8deabed784372198",
  "suite_version": 1,
  "agent_name": "omp",
  "agent_version": "17.3.8",
  "agent_effort": "medium",
  "model": "meetkai:functionary-urdu-mini-pak",
  "cost_usd": 3.77,
  "created_at": 1704067200,
  "idempotency_key": "harbor-job-2026-08-23-luna-medium",
  "metadata": {
    "harness": "harbor",
    "benchmark": "terminal-bench-2.1"
  },
  "trials": [
    {
      "task_id": "fix-permissions",
      "sample_index": 0,
      "status": "completed",
      "prompt": "The test suite fails because the fixture directory is not writable. Fix it.",
      "target": "all tests pass",
      "output_text": "9 passed in 2.25s",
      "scores": {
        "reward": 1,
        "resolved": 1
      },
      "cost_usd": 0.0279,
      "input_tokens": 658456,
      "output_tokens": 6489,
      "cached_tokens": 658366
    }
  ]
}
'

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    suite_id: 'eval_suite_aa87e2b1112a455b8deabed784372198',
    suite_version: 1,
    agent_name: 'omp',
    agent_version: '17.3.8',
    agent_effort: 'medium',
    model: 'meetkai:functionary-urdu-mini-pak',
    cost_usd: 3.77,
    created_at: 1704067200,
    idempotency_key: 'harbor-job-2026-08-23-luna-medium',
    metadata: {harness: 'harbor', benchmark: 'terminal-bench-2.1'},
    trials: [
      {
        task_id: 'fix-permissions',
        sample_index: 0,
        status: 'completed',
        prompt: 'The test suite fails because the fixture directory is not writable. Fix it.',
        target: 'all tests pass',
        output_text: '9 passed in 2.25s',
        scores: {reward: 1, resolved: 1},
        cost_usd: 0.0279,
        input_tokens: 658456,
        output_tokens: 6489,
        cached_tokens: 658366
      }
    ]
  })
};

fetch('https://apigw.mka1.com/api/v1/llm/evals/imports/agent-run', 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://apigw.mka1.com/api/v1/llm/evals/imports/agent-run",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'suite_id' => 'eval_suite_aa87e2b1112a455b8deabed784372198',
    'suite_version' => 1,
    'agent_name' => 'omp',
    'agent_version' => '17.3.8',
    'agent_effort' => 'medium',
    'model' => 'meetkai:functionary-urdu-mini-pak',
    'cost_usd' => 3.77,
    'created_at' => 1704067200,
    'idempotency_key' => 'harbor-job-2026-08-23-luna-medium',
    'metadata' => [
        'harness' => 'harbor',
        'benchmark' => 'terminal-bench-2.1'
    ],
    'trials' => [
        [
                'task_id' => 'fix-permissions',
                'sample_index' => 0,
                'status' => 'completed',
                'prompt' => 'The test suite fails because the fixture directory is not writable. Fix it.',
                'target' => 'all tests pass',
                'output_text' => '9 passed in 2.25s',
                'scores' => [
                                'reward' => 1,
                                'resolved' => 1
                ],
                'cost_usd' => 0.0279,
                'input_tokens' => 658456,
                'output_tokens' => 6489,
                'cached_tokens' => 658366
        ]
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

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

curl_close($curl);

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

package main

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

func main() {

	url := "https://apigw.mka1.com/api/v1/llm/evals/imports/agent-run"

	payload := strings.NewReader("{\n  \"suite_id\": \"eval_suite_aa87e2b1112a455b8deabed784372198\",\n  \"suite_version\": 1,\n  \"agent_name\": \"omp\",\n  \"agent_version\": \"17.3.8\",\n  \"agent_effort\": \"medium\",\n  \"model\": \"meetkai:functionary-urdu-mini-pak\",\n  \"cost_usd\": 3.77,\n  \"created_at\": 1704067200,\n  \"idempotency_key\": \"harbor-job-2026-08-23-luna-medium\",\n  \"metadata\": {\n    \"harness\": \"harbor\",\n    \"benchmark\": \"terminal-bench-2.1\"\n  },\n  \"trials\": [\n    {\n      \"task_id\": \"fix-permissions\",\n      \"sample_index\": 0,\n      \"status\": \"completed\",\n      \"prompt\": \"The test suite fails because the fixture directory is not writable. Fix it.\",\n      \"target\": \"all tests pass\",\n      \"output_text\": \"9 passed in 2.25s\",\n      \"scores\": {\n        \"reward\": 1,\n        \"resolved\": 1\n      },\n      \"cost_usd\": 0.0279,\n      \"input_tokens\": 658456,\n      \"output_tokens\": 6489,\n      \"cached_tokens\": 658366\n    }\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://apigw.mka1.com/api/v1/llm/evals/imports/agent-run")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"suite_id\": \"eval_suite_aa87e2b1112a455b8deabed784372198\",\n  \"suite_version\": 1,\n  \"agent_name\": \"omp\",\n  \"agent_version\": \"17.3.8\",\n  \"agent_effort\": \"medium\",\n  \"model\": \"meetkai:functionary-urdu-mini-pak\",\n  \"cost_usd\": 3.77,\n  \"created_at\": 1704067200,\n  \"idempotency_key\": \"harbor-job-2026-08-23-luna-medium\",\n  \"metadata\": {\n    \"harness\": \"harbor\",\n    \"benchmark\": \"terminal-bench-2.1\"\n  },\n  \"trials\": [\n    {\n      \"task_id\": \"fix-permissions\",\n      \"sample_index\": 0,\n      \"status\": \"completed\",\n      \"prompt\": \"The test suite fails because the fixture directory is not writable. Fix it.\",\n      \"target\": \"all tests pass\",\n      \"output_text\": \"9 passed in 2.25s\",\n      \"scores\": {\n        \"reward\": 1,\n        \"resolved\": 1\n      },\n      \"cost_usd\": 0.0279,\n      \"input_tokens\": 658456,\n      \"output_tokens\": 6489,\n      \"cached_tokens\": 658366\n    }\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://apigw.mka1.com/api/v1/llm/evals/imports/agent-run")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"suite_id\": \"eval_suite_aa87e2b1112a455b8deabed784372198\",\n  \"suite_version\": 1,\n  \"agent_name\": \"omp\",\n  \"agent_version\": \"17.3.8\",\n  \"agent_effort\": \"medium\",\n  \"model\": \"meetkai:functionary-urdu-mini-pak\",\n  \"cost_usd\": 3.77,\n  \"created_at\": 1704067200,\n  \"idempotency_key\": \"harbor-job-2026-08-23-luna-medium\",\n  \"metadata\": {\n    \"harness\": \"harbor\",\n    \"benchmark\": \"terminal-bench-2.1\"\n  },\n  \"trials\": [\n    {\n      \"task_id\": \"fix-permissions\",\n      \"sample_index\": 0,\n      \"status\": \"completed\",\n      \"prompt\": \"The test suite fails because the fixture directory is not writable. Fix it.\",\n      \"target\": \"all tests pass\",\n      \"output_text\": \"9 passed in 2.25s\",\n      \"scores\": {\n        \"reward\": 1,\n        \"resolved\": 1\n      },\n      \"cost_usd\": 0.0279,\n      \"input_tokens\": 658456,\n      \"output_tokens\": 6489,\n      \"cached_tokens\": 658366\n    }\n  ]\n}"

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

{
  "id": "eval_run_aa87e2b1112a455b8deabed784372198",
  "object": "eval.run",
  "suite_id": "eval_suite_aa87e2b1112a455b8deabed784372198",
  "suite_version": 1,
  "suite_version_id": "eval_sver_aa87e2b1112a455b8deabed784372198",
  "org_id": "org-acme",
  "team_id": "team-research",
  "status": "completed",
  "models": [
    "auto"
  ],
  "task_ids": null,
  "judge_model": "auto",
  "embedding_model": "auto",
  "generation": {
    "temperature": 0,
    "max_output_tokens": 512
  },
  "request_counts": {
    "total": 100,
    "completed": 10,
    "failed": 0
  },
  "metrics": null,
  "error": null,
  "artifact_file_ids": [],
  "metadata": {
    "purpose": "mvp"
  },
  "agent_name": "omp",
  "agent_version": null,
  "agent_effort": null,
  "cost_usd": null,
  "created_at": 1704067200,
  "started_at": 1704067210,
  "completed_at": null,
  "cancelled_at": null,
  "failed_at": null
}

Evals

Importar una ejecución finalizada de un agente de codificación

Carga directamente un trabajo de harness completado — la ejecución y sus pruebas —, por lo que los resultados nunca hacen un ida y vuelta a través de almacenamiento externo, como hace el importador de Hugging Face. Cada task_id ya debe existir en el manifiesto de la versión del conjunto de destino; los ids desconocidos se rechazan en lugar de inventarse, porque de lo contrario un error tipográfico se importaría como una tarea que el conjunto no tiene y se leería como un modelo que nunca cubrió la versión. La ejecución se registra como completed y no se ejecuta: esto es una escritura, no una solicitud de ejecución, así que no se inicia ningún flujo de trabajo. Las pruebas que cubren todas las tareas de la versión reciben task_ids: null, que es lo que permite que la ejecución se clasifique como un barrido completo. Las trayectorias NO forman parte de este payload — una ejecución completa de 91 tareas midió 8.3 MB de ellas —, así que cárgalas cada una después contra PUT /evals/runs/{run_id}/samples/{sample_index}/trajectory. Pasa idempotency_key y una carga reintentada devolverá la primera ejecución en lugar de duplicar las pruebas detrás de una fila del tablero.

POST

api

llm

evals

imports

agent-run

Python (SDK)

from meetkai_mka1 import SDK


with SDK(
    bearer_auth="<YOUR_BEARER_TOKEN_HERE>",
) as sdk:

    res = sdk.llm.evals.import_agent_run(suite_id="eval_suite_aa87e2b1112a455b8deabed784372198", agent_name="omp", model="meetkai:functionary-urdu-mini-pak", suite_version=1, agent_version="17.3.8", agent_effort="medium", cost_usd=3.77, created_at=1704067200, metadata={
        "harness": "harbor",
        "benchmark": "terminal-bench-2.1",
    }, idempotency_key="harbor-job-2026-08-23-luna-medium", trials=[
        {
            "task_id": "fix-permissions",
            "sample_index": 0,
            "prompt": "The test suite fails because the fixture directory is not writable. Fix it.",
            "target": "all tests pass",
            "output_text": "9 passed in 2.25s",
            "scores": {
                "reward": 1,
                "resolved": 1,
            },
            "cost_usd": 0.0279,
            "input_tokens": 658456,
            "output_tokens": 6489,
            "cached_tokens": 658366,
        },
    ], finalize=True)

    # Handle response
    print(res)

import { SDK } from "@meetkai/mka1";

const sdk = new SDK({
  bearerAuth: "<YOUR_BEARER_TOKEN_HERE>",
});

async function run() {
  const result = await sdk.llm.evals.importAgentRun({
    importAgentRunRequest: {
      suiteId: "eval_suite_aa87e2b1112a455b8deabed784372198",
      suiteVersion: 1,
      agentName: "omp",
      agentVersion: "17.3.8",
      agentEffort: "medium",
      model: "meetkai:functionary-urdu-mini-pak",
      costUsd: 3.77,
      createdAt: 1704067200,
      metadata: {
        "harness": "harbor",
        "benchmark": "terminal-bench-2.1",
      },
      idempotencyKey: "harbor-job-2026-08-23-luna-medium",
      trials: [
        {
          taskId: "fix-permissions",
          sampleIndex: 0,
          prompt: "The test suite fails because the fixture directory is not writable. Fix it.",
          target: "all tests pass",
          outputText: "9 passed in 2.25s",
          scores: {
            "reward": 1,
            "resolved": 1,
          },
          costUsd: 0.0279,
          inputTokens: 658456,
          outputTokens: 6489,
          cachedTokens: 658366,
        },
      ],
    },
  });

  console.log(result);
}

run();

using MeetKai.MKA1;
using MeetKai.MKA1.Types.Components;
using System.Collections.Generic;

var sdk = new SDK(bearerAuth: "<YOUR_BEARER_TOKEN_HERE>");

var res = await sdk.Llm.Evals.ImportAgentRunAsync(body: new ImportAgentRunRequest() {
    SuiteId = "eval_suite_aa87e2b1112a455b8deabed784372198",
    SuiteVersion = 1,
    AgentName = "omp",
    AgentVersion = "17.3.8",
    AgentEffort = "medium",
    Model = "meetkai:functionary-urdu-mini-pak",
    CostUsd = 3.77D,
    CreatedAt = 1704067200,
    Metadata = new Dictionary<string, string>() {
        { "harness", "harbor" },
        { "benchmark", "terminal-bench-2.1" },
    },
    IdempotencyKey = "harbor-job-2026-08-23-luna-medium",
    Trials = new List<ImportAgentRunRequestTrial>() {
        new ImportAgentRunRequestTrial() {
            TaskId = "fix-permissions",
            SampleIndex = 0,
            Prompt = "The test suite fails because the fixture directory is not writable. Fix it.",
            Target = "all tests pass",
            OutputText = "9 passed in 2.25s",
            Scores = new Dictionary<string, double>() {
                { "reward", 1D },
                { "resolved", 1D },
            },
            CostUsd = 0.0279D,
            InputTokens = 658456,
            OutputTokens = 6489,
            CachedTokens = 658366,
        },
    },
});

// handle response

curl --request POST \
  --url https://apigw.mka1.com/api/v1/llm/evals/imports/agent-run \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "suite_id": "eval_suite_aa87e2b1112a455b8deabed784372198",
  "suite_version": 1,
  "agent_name": "omp",
  "agent_version": "17.3.8",
  "agent_effort": "medium",
  "model": "meetkai:functionary-urdu-mini-pak",
  "cost_usd": 3.77,
  "created_at": 1704067200,
  "idempotency_key": "harbor-job-2026-08-23-luna-medium",
  "metadata": {
    "harness": "harbor",
    "benchmark": "terminal-bench-2.1"
  },
  "trials": [
    {
      "task_id": "fix-permissions",
      "sample_index": 0,
      "status": "completed",
      "prompt": "The test suite fails because the fixture directory is not writable. Fix it.",
      "target": "all tests pass",
      "output_text": "9 passed in 2.25s",
      "scores": {
        "reward": 1,
        "resolved": 1
      },
      "cost_usd": 0.0279,
      "input_tokens": 658456,
      "output_tokens": 6489,
      "cached_tokens": 658366
    }
  ]
}
'

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    suite_id: 'eval_suite_aa87e2b1112a455b8deabed784372198',
    suite_version: 1,
    agent_name: 'omp',
    agent_version: '17.3.8',
    agent_effort: 'medium',
    model: 'meetkai:functionary-urdu-mini-pak',
    cost_usd: 3.77,
    created_at: 1704067200,
    idempotency_key: 'harbor-job-2026-08-23-luna-medium',
    metadata: {harness: 'harbor', benchmark: 'terminal-bench-2.1'},
    trials: [
      {
        task_id: 'fix-permissions',
        sample_index: 0,
        status: 'completed',
        prompt: 'The test suite fails because the fixture directory is not writable. Fix it.',
        target: 'all tests pass',
        output_text: '9 passed in 2.25s',
        scores: {reward: 1, resolved: 1},
        cost_usd: 0.0279,
        input_tokens: 658456,
        output_tokens: 6489,
        cached_tokens: 658366
      }
    ]
  })
};

fetch('https://apigw.mka1.com/api/v1/llm/evals/imports/agent-run', 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://apigw.mka1.com/api/v1/llm/evals/imports/agent-run",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'suite_id' => 'eval_suite_aa87e2b1112a455b8deabed784372198',
    'suite_version' => 1,
    'agent_name' => 'omp',
    'agent_version' => '17.3.8',
    'agent_effort' => 'medium',
    'model' => 'meetkai:functionary-urdu-mini-pak',
    'cost_usd' => 3.77,
    'created_at' => 1704067200,
    'idempotency_key' => 'harbor-job-2026-08-23-luna-medium',
    'metadata' => [
        'harness' => 'harbor',
        'benchmark' => 'terminal-bench-2.1'
    ],
    'trials' => [
        [
                'task_id' => 'fix-permissions',
                'sample_index' => 0,
                'status' => 'completed',
                'prompt' => 'The test suite fails because the fixture directory is not writable. Fix it.',
                'target' => 'all tests pass',
                'output_text' => '9 passed in 2.25s',
                'scores' => [
                                'reward' => 1,
                                'resolved' => 1
                ],
                'cost_usd' => 0.0279,
                'input_tokens' => 658456,
                'output_tokens' => 6489,
                'cached_tokens' => 658366
        ]
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

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

curl_close($curl);

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

package main

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

func main() {

	url := "https://apigw.mka1.com/api/v1/llm/evals/imports/agent-run"

	payload := strings.NewReader("{\n  \"suite_id\": \"eval_suite_aa87e2b1112a455b8deabed784372198\",\n  \"suite_version\": 1,\n  \"agent_name\": \"omp\",\n  \"agent_version\": \"17.3.8\",\n  \"agent_effort\": \"medium\",\n  \"model\": \"meetkai:functionary-urdu-mini-pak\",\n  \"cost_usd\": 3.77,\n  \"created_at\": 1704067200,\n  \"idempotency_key\": \"harbor-job-2026-08-23-luna-medium\",\n  \"metadata\": {\n    \"harness\": \"harbor\",\n    \"benchmark\": \"terminal-bench-2.1\"\n  },\n  \"trials\": [\n    {\n      \"task_id\": \"fix-permissions\",\n      \"sample_index\": 0,\n      \"status\": \"completed\",\n      \"prompt\": \"The test suite fails because the fixture directory is not writable. Fix it.\",\n      \"target\": \"all tests pass\",\n      \"output_text\": \"9 passed in 2.25s\",\n      \"scores\": {\n        \"reward\": 1,\n        \"resolved\": 1\n      },\n      \"cost_usd\": 0.0279,\n      \"input_tokens\": 658456,\n      \"output_tokens\": 6489,\n      \"cached_tokens\": 658366\n    }\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://apigw.mka1.com/api/v1/llm/evals/imports/agent-run")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"suite_id\": \"eval_suite_aa87e2b1112a455b8deabed784372198\",\n  \"suite_version\": 1,\n  \"agent_name\": \"omp\",\n  \"agent_version\": \"17.3.8\",\n  \"agent_effort\": \"medium\",\n  \"model\": \"meetkai:functionary-urdu-mini-pak\",\n  \"cost_usd\": 3.77,\n  \"created_at\": 1704067200,\n  \"idempotency_key\": \"harbor-job-2026-08-23-luna-medium\",\n  \"metadata\": {\n    \"harness\": \"harbor\",\n    \"benchmark\": \"terminal-bench-2.1\"\n  },\n  \"trials\": [\n    {\n      \"task_id\": \"fix-permissions\",\n      \"sample_index\": 0,\n      \"status\": \"completed\",\n      \"prompt\": \"The test suite fails because the fixture directory is not writable. Fix it.\",\n      \"target\": \"all tests pass\",\n      \"output_text\": \"9 passed in 2.25s\",\n      \"scores\": {\n        \"reward\": 1,\n        \"resolved\": 1\n      },\n      \"cost_usd\": 0.0279,\n      \"input_tokens\": 658456,\n      \"output_tokens\": 6489,\n      \"cached_tokens\": 658366\n    }\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://apigw.mka1.com/api/v1/llm/evals/imports/agent-run")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"suite_id\": \"eval_suite_aa87e2b1112a455b8deabed784372198\",\n  \"suite_version\": 1,\n  \"agent_name\": \"omp\",\n  \"agent_version\": \"17.3.8\",\n  \"agent_effort\": \"medium\",\n  \"model\": \"meetkai:functionary-urdu-mini-pak\",\n  \"cost_usd\": 3.77,\n  \"created_at\": 1704067200,\n  \"idempotency_key\": \"harbor-job-2026-08-23-luna-medium\",\n  \"metadata\": {\n    \"harness\": \"harbor\",\n    \"benchmark\": \"terminal-bench-2.1\"\n  },\n  \"trials\": [\n    {\n      \"task_id\": \"fix-permissions\",\n      \"sample_index\": 0,\n      \"status\": \"completed\",\n      \"prompt\": \"The test suite fails because the fixture directory is not writable. Fix it.\",\n      \"target\": \"all tests pass\",\n      \"output_text\": \"9 passed in 2.25s\",\n      \"scores\": {\n        \"reward\": 1,\n        \"resolved\": 1\n      },\n      \"cost_usd\": 0.0279,\n      \"input_tokens\": 658456,\n      \"output_tokens\": 6489,\n      \"cached_tokens\": 658366\n    }\n  ]\n}"

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

{
  "id": "eval_run_aa87e2b1112a455b8deabed784372198",
  "object": "eval.run",
  "suite_id": "eval_suite_aa87e2b1112a455b8deabed784372198",
  "suite_version": 1,
  "suite_version_id": "eval_sver_aa87e2b1112a455b8deabed784372198",
  "org_id": "org-acme",
  "team_id": "team-research",
  "status": "completed",
  "models": [
    "auto"
  ],
  "task_ids": null,
  "judge_model": "auto",
  "embedding_model": "auto",
  "generation": {
    "temperature": 0,
    "max_output_tokens": 512
  },
  "request_counts": {
    "total": 100,
    "completed": 10,
    "failed": 0
  },
  "metrics": null,
  "error": null,
  "artifact_file_ids": [],
  "metadata": {
    "purpose": "mvp"
  },
  "agent_name": "omp",
  "agent_version": null,
  "agent_effort": null,
  "cost_usd": null,
  "created_at": 1704067200,
  "started_at": 1704067210,
  "completed_at": null,
  "cancelled_at": null,
  "failed_at": null
}

Autorizaciones

Authorization

string

header

requerido

Gateway auth: send Authorization: Bearer <mka1-api-key>. For multi-user server-side integrations, you can also send X-On-Behalf-Of: <external-user-id>.

Encabezados

X-On-Behalf-Of

string

Optional external end-user identifier forwarded by the API gateway.

Cuerpo

application/json

suite_id

string

requerido

Suite existente para importar. Su manifiesto define el conjunto de tareas, así que cree primero la suite.

Minimum string length: 1

agent_name

string

requerido

El agente de arnés, p. ej. omp.

Required string length: 1 - 128

model

string

requerido

Required string length: 1 - 255

suite_version

integer

Por defecto, se usa la versión activa del conjunto.

Rango requerido: 1 <= x <= 2147483647

agent_version

string | null

Maximum string length: 64

agent_effort

string | null

Configuración del nivel de razonamiento, por ejemplo medium. Forma parte de la identidad de la fila de la tabla de clasificación, por lo que el mismo agente y modelo con dos niveles de esfuerzo siguen siendo dos filas.

Maximum string length: 32

cost_usd

number | null

Gasto total del trabajo. Si se omite, recurre a la suma de los costes propios de las pruebas.

Rango requerido: x >= 0

created_at

integer

Cuando se ejecutó el trabajo, en segundos Unix. Por defecto es ahora; configúrelo al hacer backfilling, ya que el tablero ordena por esto.

Rango requerido: -9007199254740991 < x <= 9007199254740991

metadata

object

Show child attributes

idempotency_key

string

Reutilizar una clave devuelve la ejecución creada la primera vez en lugar de importar una segunda copia. Sin una, una carga reintentada duplica silenciosamente los ensayos detrás de una fila del tablero.

Required string length: 1 - 255

trials

object[]

Puede estar vacío al abrir una ejecución para transmitir ensayos. Una importación única los envía todos aquí.

Maximum array length: 1000

Show child attributes

expected_trials

integer

Cuántos intentos producirá el trabajo. Establece el total de la ejecución por adelantado para que la consola muestre el progreso real (12/89) mientras se transmite, en lugar de 12/12 que va aumentando.

Rango requerido: 0 <= x <= 1000

finalize

boolean

predeterminado:true

False abre la ejecución in_progress para POST /evals/runs/{run_id}/trials para completar. Los marcadores solo cuentan las ejecuciones completadas, por lo que una ejecución en streaming permanece fuera de la tabla hasta que se finaliza.

Respuesta

200 - application/json

Está bien

string

requerido

object

any

requerido

suite_id

string

requerido

suite_version

integer

requerido

Rango requerido: -9007199254740991 <= x <= 9007199254740991

suite_version_id

string

requerido

org_id

string

requerido

The org that owns this run.

team_id

string

requerido

The team that owns this run.

status

enum<string>

requerido

Opciones disponibles:

queued,

in_progress,

finalizing,

completed,

failed,

cancelling,

cancelled

models

string[]

requerido

task_ids

string[] | null

requerido

judge_model

string | null

requerido

embedding_model

string | null

requerido

generation

object

requerido

Show child attributes

request_counts

object

requerido

Show child attributes

metrics

object | null

requerido

Show child attributes

error

object | null

requerido

Show child attributes

artifact_file_ids

string[]

requerido

metadata

object

requerido

Show child attributes

agent_name

string | null

requerido

Coding-agent harness that produced this run (e.g. omp, claude-code). Null for every non-harness eval kind — a null here is not a missing value, it means the run is not an agent run.

agent_version

string | null

requerido

Version of agent_name, as the harness reported it. Null when agent_name is.

agent_effort

string | null

requerido

Reasoning-effort setting the agent ran at (e.g. medium, xhigh). Part of the leaderboard's row identity: the same agent and model at two efforts are two rows, not one. Null when agent_name is.

cost_usd

number | null

requerido

Total spend for the run in USD. Null when the harness did not report cost.

created_at

integer

requerido

Rango requerido: -9007199254740991 <= x <= 9007199254740991

started_at

integer | null

requerido

Rango requerido: -9007199254740991 <= x <= 9007199254740991

completed_at

integer | null

requerido

Rango requerido: -9007199254740991 <= x <= 9007199254740991

cancelled_at

integer | null

requerido

Rango requerido: -9007199254740991 <= x <= 9007199254740991

failed_at

integer | null

requerido

Rango requerido: -9007199254740991 <= x <= 9007199254740991

⌘I

Responses API

Agents API

Platform APIs

Administration

Sandbox API

Compute API

Repositories API

Deprecated

Other

Importar una ejecución finalizada de un agente de codificación

Autorizaciones

Encabezados

Cuerpo

Respuesta