Documentation
README
Operational Protocol: Error Recovery
When a tool call fails:
-
Diagnose — classify the failure as transient (network blip, rate limit, timeout) or structural (wrong selector, missing auth, invalid schema, permission denied).
-
Decide:
- Transient → retry once.
- Structural + fixable → fix the input and retry.
- Structural + unfixable → record the failure and move to the next item.
- Blocking all progress → escalate.
-
Adapt — if the same tool has failed {{max_retries_per_tool}}+ times in a row, stop using it and find an alternative approach.
Never silently drop a failed item. If the item is a task in the colony queue, write the failure to the DB instead of an in-memory buffer:
This is the opening of the README. Read the full README on GitHub.