Self-Correction

How OpenHelm automatically retries failed runs with corrective context.

Automatic Self-Correction

When a job run fails, OpenHelm can automatically create a *corrective run* — a follow-up execution that includes context about what went wrong and any correction guidance you've provided.

How It Works

A run finishes with a non-zero exit code (failure)
OpenHelm queues a corrective run with the original prompt plus the failure context appended
The corrective run executes at the lowest priority, after all scheduled runs
If the corrective run also fails, the cycle repeats up to the configured retry limit
Once the retry limit is exhausted, the job is marked as permanent_failure and surfaced in the Inbox

Correction Notes

Each job has an optional Correction note field. Text entered here is appended to the prompt of every corrective run for that job. Use this to provide guidance for recovering from the specific failures that job tends to encounter:

If tests fail due to missing dependencies, run `npm install` first.
Check .env.example for required environment variables that may need to be set.

Configuration

Control self-correction in Settings:

Setting	Description
Auto-correction enabled	Toggle automatic corrective runs on or off
Max correction retries	How many times to retry before marking as permanent failure

The Inbox

The Inbox surfaces runs that require human attention — jobs that have exhausted their automatic retries, and any run where Claude Code explicitly requested human input.

For each inbox item, you can:

Dismiss — acknowledge the failure and take no further action
Try again — queue an immediate manual re-run with the original prompt
Do something different — provide new instructions and queue a corrective run incorporating your guidance