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": 1.0,
                "resolved": 1.0,
            },
            "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

Import a finished coding-agent run

Uploads one completed harness job — the run and its trials — directly, so results never round-trip through external storage the way the Hugging Face importer does. Every task_id must already exist in the target suite version’s manifest; unknown ids are rejected rather than invented, because a typo would otherwise import as a task the suite does not have and read as a model that never covered the version. The run is recorded as completed and is not executed: this is a write, not a run request, so no workflow is started. Trials that cover every task of the version get task_ids: null, which is what lets the run rank as a complete sweep. Trajectories are NOT part of this payload — a full 91-task run measured 8.3 MB of them — so upload each one against PUT /evals/runs/{run_id}/samples/{sample_index}/trajectory afterwards. Pass idempotency_key and a retried upload returns the first run instead of doubling the trials behind a board row.

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": 1.0,
                "resolved": 1.0,
            },
            "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
}

Authorizations

Authorization

string

header

required

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>.

Headers

X-On-Behalf-Of

string

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

Body

application/json

suite_id

string

required

Existing suite to import into. Its manifest defines the task set, so create the suite first.

Minimum string length: 1

agent_name

string

required

The harness agent, e.g. omp.

Required string length: 1 - 128

model

string

required

Required string length: 1 - 255

suite_version

integer

Defaults to the suite's active version.

Required range: 1 <= x <= 2147483647

agent_version

string | null

Maximum string length: 64

agent_effort

string | null

Reasoning-effort setting, e.g. medium. Part of the leaderboard's row identity, so the same agent and model at two efforts stay two rows.

Maximum string length: 32

cost_usd

number | null

Total spend for the job. Falls back to the sum of the trials' own costs when omitted.

Required range: x >= 0

created_at

integer

When the job ran, unix seconds. Defaults to now — set it when backfilling, since the board orders by this.

Required range: -9007199254740991 < x <= 9007199254740991

metadata

object

Show child attributes

idempotency_key

string

Reusing a key returns the run created the first time instead of importing a second copy. Without one, a retried upload silently doubles the trials behind a board row.

Required string length: 1 - 255

trials

object[]

May be empty when opening a run to stream trials into. A one-shot import sends them all here.

Maximum array length: 1000

Show child attributes

expected_trials

integer

How many trials the job will produce. Sets the run's total up front so the console shows real progress (12/89) while it streams, instead of 12/12 that grows.

Required range: 0 <= x <= 1000

finalize

boolean

default:true

False opens the run in_progress for POST /evals/runs/{run_id}/trials to fill. Leaderboards only count completed runs, so a streaming run stays off the board until it is finalized.

Response

200 - application/json

string

required

object

any

required

suite_id

string

required

suite_version

integer

required

Required range: -9007199254740991 <= x <= 9007199254740991

suite_version_id

string

required

org_id

string

required

The org that owns this run.

team_id

string

required

The team that owns this run.

status

enum<string>

required

Available options:

queued,

in_progress,

finalizing,

completed,

failed,

cancelling,

cancelled

models

string[]

required

task_ids

string[] | null

required

judge_model

string | null

required

embedding_model

string | null

required

generation

object

required

Show child attributes

request_counts

object

required

Show child attributes

metrics

object | null

required

Show child attributes

error

object | null

required

Show child attributes

artifact_file_ids

string[]

required

metadata

object

required

Show child attributes

agent_name

string | null

required

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

required

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

agent_effort

string | null

required

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

required

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

tokens

object

required

Token totals for the run, summed over its samples when it finalized. Each is null when nothing reported that figure, which is a different fact from zero and must not render as free.

Show child attributes

created_at

integer

required

Required range: -9007199254740991 <= x <= 9007199254740991

started_at

integer | null

required

Required range: -9007199254740991 <= x <= 9007199254740991

completed_at

integer | null

required

Required range: -9007199254740991 <= x <= 9007199254740991

cancelled_at

integer | null

required

Required range: -9007199254740991 <= x <= 9007199254740991

failed_at

integer | null

required

Required range: -9007199254740991 <= x <= 9007199254740991

⌘I

Overview

Responses and conversations

Models and routing

Images and audio

Files and retrieval

Agents

Tools and sandbox

Evals and feedback

Compute

Repositories

Dataset generations

Organizations and access

Usage and budgets

Application utilities

Analytics

Legacy APIs

Additional APIs

Import a finished coding-agent run

Authorizations

Headers

Body

Response