Preview deterministic draft evaluators against stored evidence
Requires suite configuration permission and a terminal run. Reserves a 60-second deterministic-preview cooldown, independent of judge previews. Supply the returned continuation object with the unchanged draft to read the next bounded population. Reads at most 100 iterations within a 30-second operation deadline; partial evidence is explicitly ungradable. Runs no model calls and never overwrites original verdicts. Draft assertions explicitly replace, extend, or inherit the frozen rules.
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 Path Parameters
ID of the hosted project that contains the server.
Eval run ID, as returned by POST /eval-runs.
Body
Response
Draft evidence comparison.

