Propose a revised prompt
Rewrite the agent’s prompt from this cycle’s verdicts, fixing the rows marked bad without losing the ones marked good. Needs at least one bad row. Only the prompt is proposed — the output shape, model and tools are never machine-written — and every declared placeholder is verified to survive before the proposal is shown.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Path Parameters
Body
A request for a revised prompt, optionally critiquing a prior proposal.
What to change about the proposal already on screen.
2000Response
Successful Response
A whole training session, as the reviewer's page polls it.
Everything the page needs in one payload: the phase (status), the
cycle, the rows with their results and critiques, and the pending proposal
when there is one.
How far the current cycle's run has got.
A pending prompt revision, alongside what it would replace.
Where a session's training inputs came from.
table, manual Where a training session stands — the state the reviewer's screen shows.
One enum rather than a separate lifecycle flag and phase, because the
phase IS the state: a session is either waiting on the machine
(RUNNING), waiting on the reviewer (REVIEWING, PROPOSED), or
finished. Callers never derive the screen from row counts.
running, reviewing, proposed, completed, abandoned