Re-score run
Re-score ONE finished eval run with the current metric judge and replace its persisted metric results, the run-scoped twin of evaluate_call. Use after editing a metric's judge prompt to see how a past run scores now, without re-running the agent. Resolves the run to its session and re-runs the same /debug/metrics engine; idempotent (replaces the run's stored verdicts). Fails when the run has no session. Returns the metric count re-evaluated.
Authorization
bearerAuth A personal access token from Settings > API tokens.
In: header
Header Parameters
A key you choose, such as a UUID, that makes this POST safe to retry. Within 24 hours the same key and request answers with the first successful answer and runs nothing, the same key with a different request answers 422 idempotency_key_reused, and a key whose request is still running answers 409 idempotency_key_in_use. A failed request keeps nothing, so the same key runs it again.
1 <= length <= 255Request Body
application/json
TypeScript Definitions
Use the request body type in TypeScript.
Response Body
application/json
application/problem+json
application/problem+json
application/problem+json
application/problem+json
application/problem+json
application/problem+json
application/problem+json
curl -X POST "https://example.com/operations/rescore_run" \ -H "Content-Type: application/json" \ -d '{ "runId": "string", "agent": "string" }'{}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}Re-score batch POST
Re-score EVERY run in a finished batch with the current metric judge, the batch-scoped twin of rescore_run. Use after editing a metric's judge prompt to re-grade a whole batch against the new judge without re-running the agent. Bounded concurrency keeps it from flooding the judge; per-run failures are reported but don't abort the rest. A batch re-score is N judge passes, so the credit gate runs before the fan-out. Returns the per-run re-scored / failed counts.
Reset build to defaults POST
Reset the current draft's build config to the platform defaults: model, speech-to-text engine, voice, speech settings and office-ambience all fall back to the platform default (nothing pinned). Agent-level config is left untouched, variables, knowledge, keyterms, pronunciation and privacy all stay as they are. Only works on a draft; if the current version is published, create a draft first.