Troubleshooting Rocky Provider Setup
Provider setup failures can come from auth, model names, rate limits, network issues, or environment variables. Troubleshooting should confirm each layer without exposing keys.
When this matters
This page is for operators who want Rocky to produce usable work without turning the system into a mystery box. Use it when you need a practical path, a clear verification step, and a boundary between suggestion and action.
The operating pattern
- Check configured provider. Identify which provider and model Rocky is trying to use.
- Verify auth state. Use provider-specific status commands or harmless test calls.
- Inspect environment names. Confirm expected env vars or secret mounts exist without printing values.
- Test a tiny request. Use a low-cost prompt and capture status/error class.
- Document fallback behavior. Know whether the system has fallback models or should stop on failure.
Pre-flight checklist
- Provider and model are named
- Credentials are present but not printed
- A small live test ran
- Error class is captured
- Fallback policy is known
Common failure modes
- Token printing: Never display secrets to prove configuration.
- Wrong model string: A valid provider with an invalid model name still fails.
- Silent fallback: Unexpected fallback can hide the real problem.
Verification
A page is not done because it was drafted. Verify the source, run the workflow, inspect the output, and record what changed. If a step touches money, customers, accounts, permissions, or private data, keep it behind an explicit human approval gate.