Run #3435

{
  "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.

## Recommandations de monitoring – Agents problématiques

- **Agents zombies (tâche active >1h sans complétion)**  
  *Détection* : croiser `agent_task_runs` et `agents` pour repérer toute tâche au statut `'running'`, démarrée depuis plus d’une heure et jamais complétée.  
  *Action* : forcer l’échec de la tâche et placer l’agent en quarantaine immédiate.  
  ```sql
  -- Identifier les zombies
  SELECT a.id, a.name, r.id AS task_id, r.started_at
  FROM agencecom.agents a
  JOIN agencecom.agent_task_runs r ON a.id = r.agent_id
  WHERE r.status = 'running'
    AND r.started_at < NOW() - INTERVAL '1 hour'
    AND r.completed_at IS NULL;

  -- Nettoyer : terminer la tâche et quarantiner l’agent
  UPDATE agencecom.agent_task_runs
  SET status = 'timeout', completed_at = NOW(), error_message = 'Zombie task – killed by monitor'
  WHERE id IN (
    SELECT r.id
    FROM agencecom.agents a
    JOIN agencecom.agent_task_runs r ON a.id = r.agent_id
    WHERE r.status = 'running'
      AND r.started_at < NOW() - INTERVAL '1 hour'
      AND r.completed_at IS NULL
  );

  UPDATE agencecom.agents
  SET status = 'quarantined', quarantined_until = NOW() + INTERVAL '30 minutes'
  WHERE id IN (
    SELECT DISTINCT a.id
    FROM agencecom.agents a
    JOIN agencecom.agent_task_runs r ON a.id = r.agent_id
    WHERE r.status = 'running'
      AND r.started_at < NOW() - INTERVAL '1 hour'
      AND r.completed_at IS NULL
  );
  ```

- **Agents en surchauffe d’erreurs (error_count_last_hour > 5)**  
  *Détection* : lecture directe de la table `agents`.  
  *Action* : isoler l’agent pour éviter la propagation des défaillances.  
  ```sql
  -- Repérage
  SELECT id, name, error_count_last_hour
  FROM agencecom.agents
  WHERE error_count_last_hour > 5;

  -- Quarantaine automatique pour 10 minutes
  UPDATE agencecom.agents
  SET status = 'quarantined',
      quarantined_until = NOW() + INTERVAL '10 minutes'
  WHERE error_count_last_hour > 5
    AND status != 'quarantined';
  ```

- **Dérive de quarantaine (quarantined_until > now() mais statut incohérent)**  
  *Détection* : comparer `quarantined_until` et `status` dans `agents`.  
  *Action* : remettre le statut à `'quarantined'` pour rétablir la cohérence.  
  ```sql
  -- Agents actifs malgré une quarantaine théorique
  SELECT id, name, quarantined_until, status
  FROM agencecom.agents
  WHERE quarantined_until > NOW()
    AND status != 'quarantined';

  -- Correction
  UPDATE agencecom.agents
  SET status = 'quarantined'
  WHERE quarantined_until > NOW()
    AND status != 'quarantined';
  ```