Check out the newest way to compare different models for a task/agent harness: AutoEvals

Command Reference

Workers

Inspect v1 worker instances and their logs.

Inspect v1 worker (relay-monolith workers / instances) observability.

inf worker logs

Streamed logs for a v1 worker instance (paginated).

inf worker logs --worker-id <worker-id> --instance-id <instance-id>

Options

FlagRequiredDescription
--worker-id <id>YesV1 worker ID
--instance-id <id>YesInstance ID within the worker
--log-level <level>NoFilter to a log level
--limit <n>NoMax rows to return
--offset <n>NoRows to skip for paging

Generated REST verbs

inf worker exposes its read surface as generated commands. Run inf worker --help to list them and their flags.

On this page