f299bae77b
Add OPS repo presence detection in supervisor-run.sh with degraded mode support: - Detect if OPS_REPO_ROOT is missing and log WARNING message - Set OPS_REPO_DEGRADED=1 flag and configure fallback paths - Bundle minimal knowledge files as fallback for degraded mode - Update formula to use OPS_KNOWLEDGE_ROOT, OPS_JOURNAL_ROOT, OPS_VAULT_ROOT - Support local vault destination and journal fallback when ops repo absent Knowledge files bundled: disk.md, memory.md, ci.md, git.md, dev-agent.md, review-agent.md, forge.md The supervisor now runs with full functionality when ops repo is available, or gracefully degrades to local paths when absent, making the failure mode explicit rather than silent.
23 lines
712 B
Markdown
23 lines
712 B
Markdown
# Review Agent — Best Practices
|
|
|
|
## Review Agent Issues
|
|
|
|
When review agent encounters issues with PRs:
|
|
|
|
### Stale PR Handling
|
|
- PRs stale >20min (CI done, no push since) → file vault item for dev-agent
|
|
- Do NOT push branches or attempt merges directly
|
|
- File vault item with:
|
|
- What: Stale PR requiring push
|
|
- Why: Factory degraded
|
|
- Unblocks: dev-agent will push the branch
|
|
|
|
### Circular Dependencies
|
|
- Check backlog for issues with circular `Depends on` refs
|
|
- Use `lib/parse-deps.sh` to analyze dependency graph
|
|
- Report to planner for resolution
|
|
|
|
### Prevention
|
|
- Review agent only reads PRs, never modifies
|
|
- Use vault items for actions requiring dev-agent
|
|
- Monitor for PRs stuck in review state
|