- Get Started

Troubleshooting

OpenFlows is a distributed system: a Coder control plane, a Redis state store, a Coder AI Gateway, an orchestrator process running in a NEXUS workspace, and a fleet of ephemeral worker workspaces. When something fails, the failure can appear anywhere in that chain. This guide walks through common failures, diagnostics, and how to read the artifacts the system leaves behind, especially STATUS.json.

The first rule of troubleshooting is to check the controller log. The NEXUS workspace writes to /tmp/openflows-controller.log, and that log contains structured events from the controller and every worker. The second rule is to check Redis, which is the source of truth for ticket and worker state. The third rule is to read STATUS.json when a worker writes one; it is the worker's own statement of what went wrong.

Common Failures

FailureSymptom / Cause
Coder unreachableNEXUS cannot provision or destroy workspaces. Check CODER_URL and CODER_NEXUS_TOKEN.
GitHub external auth expiredWorkers lose git push/pull access. Re-authenticate in Coder admin or user settings.
Worker timeoutA FORGE or SENTINEL workspace exceeded its step timeout. Check workspace logs and LLM gateway health.
SENTINEL rejection loopSENTINEL rejects every segment repeatedly. Escalate to AwaitingHuman and review the plan.
Merge conflictPR is no longer mergeable. VESSEL retries; if unresolved, escalate to AwaitingHuman.
Redis connection lostAll state operations fail. Controller enters degraded mode and retries.
AI Gateway 429Rate limit hit. Back off and scale gateway capacity if sustained.
STATUS.json blockedAgent wrote a blocked status. Read the blocker object for the exact question.

Diagnostics

The openflows doctor command runs a battery of health checks against the orchestrator, Coder, Redis, and the AI Gateway. Run it from the NEXUS workspace before digging into manual logs.

bash
openflows doctor --tenant my-team

The doctor command checks:

If doctor reports a failure, it prints a remediation hint. If it reports all green but the system still misbehaves, the issue is likely in the LLM-driven agent logic, not the infrastructure.

Continue reading

See Connectivity & Auth for Coder, token, and GitHub external auth issues. See Worker & Pipeline Issues for worker timeouts, SENTINEL loops, merge conflicts, and STATUS.json.