# cc-steer refine


Refine every accepted steering event into atomic training pairs.


``` bash
cc-steer refine [OPTIONS]
```


Incremental and idempotent: pairs commit per event as soon as each call completes, failed events stay pending and are retried on the next run, and re-running over a fully refined corpus is a no-op. A pass that changes data syncs the dataset to HuggingFace; `--no-sync` skips it.


<span class="gd-details-chevron" aria-hidden="true"></span>Full --help output


    Usage: cc-steer refine [OPTIONS]

      Refine every accepted steering event into atomic training pairs.

      Incremental and idempotent: pairs commit per event as soon as each call
      completes, failed events stay pending and are retried on the next run, and
      re-running over a fully refined corpus is a no-op. A pass that changes data
      syncs the dataset to HuggingFace; ``--no-sync`` skips it.

    Options:
      --model [small|medium|large]  Refiner model tier.  [default: medium]
      --limit INTEGER               Refine at most this many events this pass.
      --concurrency INTEGER         Maximum concurrent claude subshells.
                                    [default: 8]
      --db FILE                     Database path. Defaults to ~/.cc-
                                    steer/feedback.db.
      --sync / --no-sync            Rebuild the derived dataset and push it to
                                    your private HuggingFace repo when the pass
                                    changed data.  [default: sync]
      --help                        Show this message and exit.


# Options


`--model: CHOICE = medium`  
Refiner model tier.

`--limit: INTEGER`  
Refine at most this many events this pass.

`--concurrency: INTEGER = 8`  
Maximum concurrent claude subshells.

`--db: FILE`  
Database path. Defaults to ~/.cc-steer/feedback.db.

`--sync, --no-sync`  
Rebuild the derived dataset and push it to your private HuggingFace repo when the pass changed data.