Run #3440

{
  "ok": true,
  "failed": [],
  "hallucinated": [],
  "context_errors": []
}

{
  "pool_status": "see_db"
}

Tu es un agent de monitoring du pool agencecom.

Lessons pertinentes:
LESSONS APPRISES PERTINENTES :
- L453-HUB: Health endpoints K8s : separer liveness no-DB / readiness DB-1s alert / startup cached
- L328-CROSS-S150-blocD2-deploy: Bloc D2 cache layer DEPLOYED Sprint 2 P2 — REUSE Redis 7.0.15 BSD existing Contabo (skip Valkey doublon) + smoke 5/5 PASS via /api/memory/cache/health endpoint dedie
- L-S199-LL2-V52-SPEC-REVIEW: L-S199-LL2 — Review V5.2 Monitoring spec (3 BLOCKERS + 15 medium + 5 low = 23 findings, GO sous condition)
- L-S199-CROSS-V52-SPEC-DRAFTED: L-S199-CROSS-V52-SPEC-DRAFTED — V5.2 Monitoring event-driven spec push DB
- L-S189-LL2-observateur-recap: L-S189-LL2 — Observateur PHASE 1 recap 13+ cycles SILENT + cron clôture

Donnees pool actuelles:
see_db

CONTRAINTE STRICTE -- Tables autorisees UNIQUEMENT :
- agencecom.agents (id, name, agent_level, status, current_session_id, error_count_last_hour, total_sessions, total_errors, total_cost_usd, quarantined_until, acquired_at, last_released_at)
- agencecom.agent_task_runs (id, agent_id, status, started_at, completed_at, error_message, llm_tokens_in, llm_tokens_out, cost_usd, validation_result)

Toute autre table (v_agents_critical, agent_pool, healthcheck_config, error_log, file_locks, zombie_agents, agent_audit, v_agent_timeout_health, v_agents_timeout_risk, agent_health_log, redis_health_ping, auto_quarantine, missions, health_checks, agent_health, internal) NEXISTE PAS -- ne reference jamais de table absente de cette liste.

Identifie les agents zombies (busy >1h sans completion via started_at + status), error_count_last_hour > 5, ou drift quarantine (quarantined_until > now).
Donne 3 recommandations concretes en markdown bullet points avec actions SQL utilisant SEULEMENT les 2 tables autorisees ci-dessus.

- **Identifier et libérer les agents zombies (occupés > 1 h sans complétion)**  
  *Détecter* les agents dont l’exécution en cours dépasse 1 heure :
  ```sql
  SELECT a.id, a.name, atr.started_at, atr.status
  FROM agencecom.agents a
  JOIN agencecom.agent_task_runs atr ON atr.id = a.current_session_id
  WHERE a.status = 'busy'
    AND atr.started_at < NOW() - INTERVAL '1 HOUR'
    AND atr.status NOT IN ('completed','failed');
  ```
  *Action* : après validation manuelle, libérer les zombies identifiés :
  ```sql
  UPDATE agencecom.agents
  SET status = 'idle', current_session_id = NULL
  WHERE id IN (<liste_des_ids_zombies>);
  ```

- **Mettre en quarantaine les agents à taux d’erreur élevé (> 5 erreurs/heure)**  
  *Détecter* les agents en défaut :
  ```sql
  SELECT id, name, error_count_last_hour
  FROM agencecom.agents
  WHERE error_count_last_hour > 5
    AND (quarantined_until IS NULL OR quarantined_until <= NOW());
  ```
  *Action* : isoler ces agents pendant 30 minutes :
  ```sql
  UPDATE agencecom.agents
  SET status = 'quarantined',
      quarantined_until = NOW() + INTERVAL '30 MINUTE'
  WHERE error_count_last_hour > 5
    AND (quarantined_until IS NULL OR quarantined_until <= NOW());
  ```

- **Surveiller les quarantaines actives (quarantined_until > NOW)**  
  *Détecter* tous les agents encore sous quarantaine :
  ```sql
  SELECT id, name, quarantined_until, status
  FROM agencecom.agents
  WHERE quarantined_until > NOW();
  ```
  *Action* : pour ceux dont la quarantaine n’est plus justifiée, libérer manuellement après revue :
  ```sql
  UPDATE agencecom.agents
  SET status = 'idle', quarantined_until = NULL
  WHERE id = <id_agent>;
  ```