abb15cd49d
All checks were successful
ci/woodpecker/push/default Pipeline was successful
emo cares about ha-sofia + his Sofia smart-home devices (Tuya, the MPPT ATS, the Барзини → Статус dashboard), and only about the cluster when it's breaking those. Rewrite his vendored cluster-health into an ha-sofia-focused, read-only variant: - leads with ha-sofia's in-cluster dependency chain (tuya-bridge + the cloudflared/Traefik/DNS/TLS reachability path), all checkable read-only; - fixes the script path to emo's own clone (/home/emo/code) — he can't read wizard's tree — and runs it --no-fix (he's cluster read-only); - loads emo's own HA token (see below) so the ha-sofia checks (26-29, 45) actually run for him; documents the host-SSH/Vault checks that skip; - triages: cluster FAIL/WARN matters only if on his chain; everything else is a one-line "admin's area"; escalate via /file-issue since he can't fix. This snapshot copy is now an emo-specific variant, intentionally diverged from the canonical 47-check admin skill — README updated to say "do not re-sync from canonical". Token: a dedicated long-lived HA token (client_name emo-cluster-health) was minted on ha-sofia via the admin account and stored emo-readable at /home/emo/.config/cluster-health/haos_token (600). It carries admin HA scope (HA only mints tokens for the authenticating account); independently revocable. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| SKILL.md | ||