Skip to main content
GET
/
v1
/
eval-runs
/
{run_id}
Get an eval run (optionally with embedded evidence)
curl --request GET \
  --url https://api-sandbox.featherhq.com/v1/eval-runs/{run_id} \
  --header 'x-api-key: <api-key>'
{
  "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "organization_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "session_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "evaluator_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "status": "<string>",
  "started_at": "2023-11-07T05:31:56Z",
  "finished_at": "2023-11-07T05:31:56Z",
  "error_text": "<string>",
  "prompt_snapshot": "<string>",
  "threshold_snapshot": 123,
  "severity_snapshot": "<string>",
  "format_snapshot": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "agent_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "channel": "<string>",
  "config_snapshot": {},
  "is_critical_snapshot": false,
  "scores": [
    {
      "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
      "organization_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
      "eval_run_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
      "value": 123,
      "raw_value": 123,
      "label": "<string>",
      "passed": true,
      "confidence": 123,
      "rationale": "<string>",
      "severity": "<string>",
      "blocking": true,
      "created_at": "2023-11-07T05:31:56Z",
      "evidence_observation_ids": [
        "<string>"
      ]
    }
  ],
  "session": {
    "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "channel": "<string>",
    "session_type": "<string>",
    "status": "<string>",
    "assistant_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "assistant_revision_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "subject": "<string>",
    "created_at": "2023-11-07T05:31:56Z",
    "last_activity_at": "2023-11-07T05:31:56Z"
  },
  "turns": [
    {
      "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
      "seq": 123,
      "role": "<string>",
      "content": "<string>",
      "tool_calls": [
        {}
      ],
      "tool_call_id": "<string>",
      "authored_by": "<string>",
      "created_at": "2023-11-07T05:31:56Z"
    }
  ],
  "turns_truncated": false,
  "recording": {
    "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "kind": "<string>",
    "status": "<string>",
    "duration_ms": 123,
    "manifest_key": "<string>",
    "started_at": "2023-11-07T05:31:56Z",
    "finalized_at": "2023-11-07T05:31:56Z"
  }
}

Authorizations

​
x-api-key
string
header
required

Path Parameters

​
run_id
string<uuid>
required

Query Parameters

​
include
string | null

comma-separated evidence to embed: session,turns,recording

Response

Successful Response

EvalRunResponse superset; extras stay null/[]/false unless requested.

​
id
string<uuid>
required
​
organization_id
string<uuid>
required
​
session_id
string<uuid>
required
​
evaluator_id
string<uuid>
required
​
status
string
required
​
started_at
string<date-time> | null
required
​
finished_at
string<date-time> | null
required
​
error_text
string | null
required
​
prompt_snapshot
string | null
required
​
threshold_snapshot
number | null
required
​
severity_snapshot
string
required
​
format_snapshot
string
required
​
created_at
string<date-time>
required
​
agent_id
string<uuid> | null
​
channel
string | null
​
config_snapshot
Config Snapshot · object
​
is_critical_snapshot
boolean
default:false
​
scores
EvalScoreResponse · object[]
​
session
ConversationSummary · object

Projection of the parent Conversation for the eval-run detail view.

​
turns
TurnView · object[] | null
​
turns_truncated
boolean
default:false
​
recording
RecordingRef · object

Metadata-only projection of a voice Recording (no presigned URL/bytes).