Build findings for an eval run
Builds (or with force, rebuilds) a settled run’s findings from its recorded evidence: the findings an analysis explains. Deterministic, with no model call, no credits and no quota.
202: scheduled, not done. Poll the run detail’s insights.unifiedFindings.job until its status is completed. On a run that has never been analyzed, a finished build starts the analysis automatically; otherwise request it with POST /projects/{projectId}/eval-runs/{runId}/insights.
409 while a build is running, when findings exist and force is absent, and while the run is still running or grading.
Authorizations
MCPJam API key (sk_…). Create one at Settings → API keys. Guest sessions cannot use the API, and API keys cannot manage other API keys.
Headers
Which vocabulary this request and its response speak. Absent means 1, which is byte-for-byte today's contract: the same request fields, the same refusals, the same response projection. 2 is the canonical vocabulary. Any other value is a 400 with code: "VALIDATION_ERROR".
Today it decides one thing: the spelling of an evaluator's policy role. Vocabulary 1 accepts and returns gating; vocabulary 2 accepts both spellings and returns the canonical required. Sending required without the header is a 400, deliberately: vocabulary 1 is not widened to meet vocabulary 2 half way, because a boundary that accepts a spelling it does not announce is one two implementations can disagree about.
A response that varies by vocabulary sends Vary: x-mcpjam-eval-vocabulary.
1, 2 
