Run a suite against pinned assistant versions
Application-scoped assistant control plane. External pipelines, dataset ingestion, and training run in the builder's infrastructure. Eval suites run fixture tool-mode jobs or disposable offline Linux desktops through Temporal. Metrics/artifacts are externally reported; reference URLs are never fetched. Model credentials are write-only. Pull subscriptions replay unacknowledged events. Resource lists return up to 200 recent records; trigger lists return an ID next_cursor for after, and message and delivery feeds use sequence cursors.
/v1/applications/{id}/eval-runsPath parameters
idstringrequiredMin length: 1
Headers
Idempotency-KeystringrequiredRequired. Identical retries return the original response; changed input returns 409. Keys are shared across this application's assistant API mutations.
Pattern: ^[\x21-\x7e]{1,200}$
Body
suite_idstringrequiredMin length: 1 · Max length: 200
harness_version_idstringMin length: 1 · Max length: 200
assistant_version_idsarray<string>Min items: 1 · Max items: 2
variantsarray<object>Min items: 1 · Max items: 4
Item fields
labelstringMin length: 1 · Max length: 60
assistant_version_idstringrequiredMin length: 1 · Max length: 200
harness_version_idstringMin length: 1 · Max length: 200
modelstringMin length: 1 · Max length: 200
reasoning_effortstringAllowed: "none""minimal""low""medium""high""xhigh""max"
samplingobjectObject fields
temperaturenumberMinimum: 0 · Maximum: 2
top_pnumberMaximum: 1
seedintegerMinimum: -9007199254740991 · Maximum: 9007199254740991
logprobsbooleantop_logprobsintegerMinimum: 0 · Maximum: 20
return_token_idsbooleansplitstringPattern: ^[a-zA-Z0-9_.-]{1,100}$
task_keysarray<string>Min items: 1 · Max items: 2000
repetitionsintegerDefault: 1 · Minimum: 1 · Maximum: 16
concurrencyintegerDefault: 1 · Minimum: 1 · Maximum: 8
case_timeout_secondsintegerDefault: 120 · Minimum: 5 · Maximum: 600
max_stepsintegerDefault: 20 · Minimum: 1 · Maximum: 100
max_cost_usdnumberMaximum: 1000
labelstringMin length: 1 · Max length: 100
Response
202Run a suite against pinned assistant versions
X-Request-IdstringServer-generated request identifier for logs and support.
application/json
idstringrequiredMin length: 1
created_atstringrequiredFormat: date-time · Pattern: ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d:[0-5]\d(?:\.\d+)?(?:Z|([+-](?:[01]\d|2[0-3]):[0-5]\d)))$
application_idstringrequiredMin length: 1
suite_idstringrequiredMin length: 1
definition_jsonobjectrequiredAdditional keys: any
result_jsonobject | nullrequiredrewardsobjectObject fields
variantsarray<object>requiredItem fields
variant_indexintegerrequiredMinimum: -9007199254740991 · Maximum: 9007199254740991
samplesintegerrequiredMinimum: -9007199254740991 · Maximum: 9007199254740991
scoredintegerrequiredMinimum: -9007199254740991 · Maximum: 9007199254740991
unscoredintegerrequiredMinimum: -9007199254740991 · Maximum: 9007199254740991
meannumber | nullrequiredsdnumber | nullrequiredci95array<any> | nullrequiredhistogramarray<integer>requiredMin items: 10 · Max items: 10
pass_at_kobjectrequiredAdditional keys: number
scorersarray<object>requiredItem fields
kindstringrequiredscorerstringrequiredmeannumber | nullrequiredscoredintegerrequiredMinimum: -9007199254740991 · Maximum: 9007199254740991
unscoredintegerrequiredMinimum: -9007199254740991 · Maximum: 9007199254740991
Additional keys: any
Additional keys: any
comparisonsarray<object>requiredItem fields
variant_indexintegerrequiredMinimum: -9007199254740991 · Maximum: 9007199254740991
baseline_indexintegerrequiredMinimum: -9007199254740991 · Maximum: 9007199254740991
pairedintegerrequiredMinimum: -9007199254740991 · Maximum: 9007199254740991
mean_differencenumber | nullrequiredci95array<any> | nullrequiredAdditional keys: any
Additional keys: any
4XX400 invalid input; 401 missing/revoked credentials; 403 disallowed operation/application; 404 missing or inaccessible resource; 409 conflicting submission/version/state; 413 body too large; 415 unsupported content type. Inspect error.code, not message text.
X-Request-IdstringServer-generated request identifier for logs and support.
application/json
errorobjectrequiredObject fields
codestringrequiredmessagestringrequiredrequest_idstringrequiredAdditional keys: any
5XX500 unexpected failure or 503 unavailable dependency. A failed response does not prove that a submission was not committed. Retry job/flow admission with the same key and body.
X-Request-IdstringServer-generated request identifier for logs and support.
application/json
errorobjectrequiredObject fields
codestringrequiredmessagestringrequiredrequest_idstringrequiredAdditional keys: any