SyslogSolution/prose-contracts
7
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: agent health check v2 — CT liveness, config validation, wrapper integrity, vault emptiness
PR Pipeline — Authorize → Validate → Review → Merge / auth (pull_request) Successful in 2s
Details
PR Pipeline — Authorize → Validate → Review → Merge / validate (pull_request) Failing after 2s
Details
PR Pipeline — Authorize → Validate → Review → Merge / lint (pull_request) Skipped
Details
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (pull_request) Skipped
Details
PR Pipeline — Authorize → Validate → Review → Merge / gate (pull_request) Skipped
Details

Browse Source 
Gaps fixed:
- Koby (.129) and Koonimo (.114) now have SSH hosts — no longer skipped
- Agent key lookup uses correct {NAME}_LITELLM_API_KEY format
- New CT liveness check via pct status on PVE nodes
- New config YAML integrity check via yaml.safe_load()
- New wrapper/CLI integrity check (hermes wrapper, infisical path, hermes-real)
- New vault secret non-emptiness check
- Ops escalation: failures produce ALERT lines for cron capture
This commit is contained in:
root
2026-07-26 12:06:32 +00:00
parent c380196fab
commit de9adb13cf
4 changed files with 318 additions and 67 deletions
Download Patch File Download Diff File Expand all files Collapse all files
litellm-self-heal.prose.md
+1 -1
View File
@@ -102,7 +102,7 @@ Request → nginx:80 → LiteLLM:4000 → GPU(llama-server, parallel 2)
- **Health-check script** (`/opt/inference-harness/scripts/litellm-health-check.sh` on CT 116): `gpu-fleet` check fails only on **critical** alerts (warnings are informational). Tests `strix-moe` (not `ornith-1.0-35b`).
- **GPU monitor** (`/root/scripts/gpu-monitor-server.py` on pi .24): runs as **systemd unit `gpu-monitor.service`** (was bare `&` process). `gpu_count` includes Strix Halo (was 2, now 3). VRAM alert thresholds: warning 93%, critical 97% (raised from 90/95 — 128K context steady-state is ~70% on RTX 3090, not a fault).
- **Agent key monitor** (`/root/scripts/agent-health-check.py` on pi .24, cron `*/10`): reads each agent's **live** `LITELLM_API_KEY` from its gateway process env via SSH — never hardcodes keys (hardcoded keys rot on rotation and caused 9×401/30min). Fleet roster: abiba, tanko, mumuni, koby, koonimo (legacy `tdunna`/`baggy` removed — never existed).
- **Agent key monitor** (`/root/scripts/agent-health-check.py` on pi .24, cron `*/10`): v2 (2026-07-26) — reads each agent's **agent-specific** `{NAME}_LITELLM_API_KEY` from Infisical vault (not the shared master key). Covers: LiteLLM keys, GPU ports, agent gateways (all 5 agents now SSHa ble), CT liveness (pct status on PVE nodes), config.yaml YAML integrity, wrapper/CLI integrity, vault secret non-emptiness checks. Fleet roster: tanko (.122), mumuni (.123), koby (.129), koonimo (.114), abiba (.24). Legacy `tdunna`/`baggy` replaced with canonical agent hostnames.
- **Stale keys cleaned**: `daily-infra-report.py` SYNTHETIC_API_KEY was stale (`sk-U_ydi3B` → 401); now reads `LITELLM_MASTER_KEY` from env. Deprecated scripts (`router-original.py`, `router-phase0-backup.py`, `apply-fixes.py`) still reference `sk-syslog-local-master-key` but do not actively poll LiteLLM.
## Maintains