Get a journey run
The full record, including per-session attempts and targetSummaries.
Read canceled before reporting a failure: a stopped run carries status: "failed".
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.
Path Parameters
ID of the hosted project that contains the server.
Eval run ID, as returned by POST /eval-runs.
Response
The run.
Poll until it leaves running.
running, completed, partial, failed, rate_limited True when somebody STOPPED this run. Check this before showing a run as a failure: a cancelled run reports status: "failed", because cancellation is recorded as a marker rather than a status of its own.
True when the runner went silent and the watchdog settled the run. Distinct from a run that failed while still reporting.
Epoch milliseconds.
The batch this run was launched with. Sibling runs of one co-launched wave share it; a solo relaunch is a wave of one. Absent on a run launched without one.
Raw marker behind canceled / stale.
The persona AS PINNED AT LAUNCH, from the run's immutable snapshot — not the persona's current values, which may have been edited since.
Per-session execution records. Present on the single-run read only — lists stay compact.
The same counts as summary, broken down per target.
Epoch milliseconds of the runner's last check-in. A long-stale heartbeat on a running run is what the watchdog acts on.
The common actionable-insights envelope. Present on the DETAIL response only — lists stay compact — and absent when the caller may not have it or the deployment cannot produce one. Treat absence exactly like status: "not_available".

