Get a simulation run
Returns one simulation run with its frozen scenario batch and every episode’s current record, including each episode’s session link and verdict once settled.
Authorizations
A Recursion API key, created in the console under API keys.
Headers
Optional tenant consistency check. When present, it must name the tenant bound to the API key, including when x-organization-id is default.
1Organization in which to act. Required for a tenant-scoped API key. Optional for an organization-scoped key, where it must name that same organization. The value may be an organization id or default.
1Path Parameters
Simulation run id.
Response
OK
Whether integration writes executed for real.
-9007199254740991 <= x <= 9007199254740991-9007199254740991 <= x <= 9007199254740991-9007199254740991 <= x <= 9007199254740991The frozen scenario batch, exactly as validated at admission.
SHA-256 of the frozen scenario batch.
Run lifecycle. Episode verdicts, not run status, say whether the agent passed.
pending, running, completed, failed, cancelled Canonical member URL for polling this run.
Aggregated cost of the episode and rubric grader sessions in micro-USD, recorded when the run settles. For a cancelled or failed run it is the spend known at settlement, while its sessions were still stopping.
-9007199254740991 <= x <= 9007199254740991Why the run failed, when it did.