> ## Documentation Index
> Fetch the complete documentation index at: https://agentdiff.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Evaluate Run

> Complete a run and evaluate against test assertions

## Request

```bash theme={null}
POST /api/platform/evaluateRun
```

### Body Parameters

<ParamField body="runId" type="string" required>
  Run ID from `startRun`
</ParamField>

### Example Request

```bash theme={null}
curl -X POST https://api.agentdiff.dev/api/platform/evaluateRun \
  -H "X-API-Key: ad_live_sk_..." \
  -H "Content-Type: application/json" \
  -d '{
    "runId": "run-xyz789"
  }'
```

## Response

<ResponseField name="runId" type="string">
  Run identifier
</ResponseField>

<ResponseField name="status" type="string">
  Final status: `"passed"` or `"failed"`
</ResponseField>

<ResponseField name="passed" type="boolean">
  Whether all assertions passed
</ResponseField>

<ResponseField name="score" type="object">
  Score details
</ResponseField>

<ResponseField name="failures" type="array">
  List of failed assertions with details
</ResponseField>

### Example Response (Passed)

```json theme={null}
{
  "runId": "run-xyz789",
  "status": "passed",
  "passed": true,
  "score": {
    "passed": 2,
    "total": 2,
    "percent": 100.0
  },
  "failures": []
}
```

### Example Response (Failed)

```json theme={null}
{
  "runId": "run-xyz789",
  "status": "failed",
  "passed": false,
  "score": {
    "passed": 1,
    "total": 2,
    "percent": 50.0
  },
  "failures": [
    "assertion#2 messages expected count 1 but got 0"
  ]
}
```

## What Happens

1. **After snapshot**: Current database state is captured
2. **Diff computed**: Before/after states compared
3. **Assertions evaluated**: Test assertions checked against diff
4. **Results stored**: Results saved for later retrieval
5. **Replication stopped**: WAL capture ends

<Note>
  Use this when you have a test with assertions. For just getting the diff without assertions, use `diffRun` instead.
</Note>

## Errors

| Error                   | Status | Description                      |
| ----------------------- | ------ | -------------------------------- |
| `run_not_found`         | 404    | Run doesn't exist                |
| `run_already_completed` | 400    | Run already evaluated            |
| `no_test_defined`       | 400    | No test associated with this run |

## SDK Usage

<CodeGroup>
  ```python Python theme={null}
  result = client.evaluate_run(runId=run.runId)

  print(f"Passed: {result.passed}")
  print(f"Score: {result.score['percent']}%")
  if result.failures:
      for f in result.failures:
          print(f"  Failed: {f}")
  ```

  ```typescript TypeScript theme={null}
  const result = await client.evaluateRun({ runId: run.runId });

  console.log(`Passed: ${result.passed}`);
  console.log(`Score: ${result.score.percent}%`);
  if (result.failures) {
    result.failures.forEach(f => console.log(`  Failed: ${f}`));
  }
  ```
</CodeGroup>