Get agent evaluation results
Fetch the computed result summary projection for an agent evaluation.
Returns the precomputed evaluation-run-summary projection for the run:
aggregate metrics (mean_score, p95_latency_ms, error_category_counts),
completion counts, and the projection’s provenance (policy_id,
source_data_plane_version). Because these values are served from a projection
rather than computed live, the response carries freshness metadata (synced_at,
freshness_seconds) indicating how stale the summary is — use it to decide
whether to wait and re-poll. For the evaluation’s configuration and raw progress
rather than computed metrics, use GET /v5/agent-evaluations/{evaluation_id}.
Gated by the SGP_TWO_PLANE_AGENT_EVALS_ENABLED feature flag and requires read
access; the request is proxied to the agent-eval control service, which returns
503 if it is unreachable.
Authorizations
Headers
Path Parameters
Response
Successful Response
pending, running, completed, failed 
