ct run monitor
Run monitors on trajectories (action-level and/or trajectory-level)
Usage
ct run monitor [OPTIONS] TRAJ_LIKE
Arguments
| Argument | Type | Required |
|---|---|---|
TRAJ_LIKE | text | Yes |
Options
| Option | Description |
|---|---|
-a, --action-monitor TEXT | Action monitor selection: a name, a .md asset path, a module:function import path, or a JSON list of entries (each a selector or a {"monitor": ..., <overrides>} mapping). ct protocols monitors action to see available. [default: mean-action] |
-t, --trajectory-monitor TEXT | Trajectory monitor selection: a name, a .md asset path, a module:function import path, or a JSON list of entries (each a selector or a {"monitor": ..., <overrides>} mapping). ct protocols monitors trajectory to see available. [default: mean-quick] |
--trusted-model TEXT | Model bound as the eval-level trusted role the monitors run on. [required] |
--only-action | Only run the action monitor |
--only-trajectory | Only run the trajectory monitor |
-o, --save-dir PATH | Directory to save monitored trajectories (default: ./data/monitoring/{monitor}/{traj_name}_{timestamp}) |
--upload / --no-upload | Upload results to the Control Tower database (enabled by default). [default: upload] |
--run-name TEXT | Name for the run (default: monitor-{monitor_name}) |
--tag TEXT | Tags for the run (can be specified multiple times) |
-L, --limit INTEGER RANGE | Limit the number of trajectories to monitor [x>=1] |
-C, --max-concurrent INTEGER | Max trajectories to monitor concurrently (default: unlimited) |
--cot-level [none|reasoning|extended] | Chain-of-thought visibility for monitors: none, reasoning (models output text), or extended (reasoning and CoT). [default: none] |
--help | Show this message and exit. |