policies
List policy evaluation audit rows (what enforcement happened, newest-first)
get/v1/policies/evaluations
Query parameters
conversation_idstring uuid nullable
policy_idstring uuid nullable
result'pass' | 'fail' | 'error' | 'skipped'
Outcome of one evaluation of a policy check.
enforcement_point'input' | 'pre_tool' | 'post_tool' | 'agent_response'
Where in a turn a policy's check fires (v2: one point per policy).
agent_response is the single author-facing reply point — the v1 response (per-streamed-unit) + post_response (complete reply) split is an internal runtime detail now, selected by the platform-derived enforcement strategy (buffer-and-gate vs per-unit), not an authored distinction.
limitinteger
cursorstring nullable
Response
Successful Response