fix: bug: supervisor hardcodes ops repo expectation — fails silently on deployments without one (#544)

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.

knowledge/disk.md

@@ -0,0 +1,35 @@
+# Disk Management — Best Practices
+
+## Disk Pressure Response (P1)
+
+When disk usage exceeds 80%, take these actions in order:
+
+### Immediate Actions
+1. **Docker cleanup** (safe, low impact):
+   ```bash
+   sudo docker system prune -f
+   ```
+
+2. **Aggressive Docker cleanup** (if still >80%):
+   ```bash
+   sudo docker system prune -a -f
+   ```
+   This removes unused images in addition to containers/volumes.
+
+3. **Log rotation**:
+   ```bash
+   for f in "$FACTORY_ROOT"/{dev,review,supervisor,gardener,planner,predictor}/*.log; do
+     [ -f "$f" ] && [ "$(du -k "$f" | cut -f1)" -gt 10240 ] && truncate -s 0 "$f"
+   done
+   ```
+
+### Prevention
+- Monitor disk with alerts at 70% (warning) and 80% (critical)
+- Set up automatic log rotation for agent logs
+- Clean up old Docker images regularly
+- Consider using separate partitions for `/var/lib/docker`
+
+### When to Escalate
+- Disk stays >80% after cleanup (indicates legitimate growth)
+- No unused Docker images to clean
+- Critical data filling disk (check /home, /var/log)