Ty
15f6a6c713
Add operator health checks (make doctor) wrapping platform CLIs, and the fixtures-only daily board skill library with unit tests (make verify).
1.5 KiB
1.5 KiB
Operations (day-2)
Status: Doctor (S6) implemented.
Health checks (doctor)
# Run all health checks (human-readable)
make doctor
# or
./scripts/doctor.sh
# Machine-readable JSON summary
./scripts/doctor.sh --json
What doctor checks:
| Check | What it validates | Severity |
|---|---|---|
| Docker | Daemon running and accessible | Critical |
| nemohermes CLI | Installed and versioned | Critical |
| openshell CLI | Installed and versioned | Critical |
| Sandbox | nemohermes <name> doctor healthy |
Critical |
| Policy | lumina-inference preset applied |
Warning |
| Skills | Skill directories with SKILL.md present | Warning |
| Inference endpoint | /v1/models reachable from .env URL |
Critical |
| Inference gateway | openshell inference get configured |
Warning |
Exit codes: 0 = all critical checks passed; 1 = one or more critical failures.
Platform diagnostics
# Sandbox status
nemohermes <sandbox-name> status
# Sandbox doctor (platform-level)
nemohermes <sandbox-name> doctor
# Sandbox logs
nemohermes <sandbox-name> logs --follow
# Gateway status
openshell status
# Inference config
openshell inference get
# Policy presets
nemohermes <sandbox-name> policy-list
Log levels
| Level | Default | Use |
|---|---|---|
| production | Yes | Redacted events, errors, health |
| debug | Off | Operator troubleshooting |
| trace | Off | Dev only |