Cron: Pool Health Check

cron-pool-health-check

Dispatch →

Configuration

CRON-MONITORING

deepseek-v4-pro

pool: default

enabled

Max tokens: 4000

Temp: 0.2

Max workers: 1

Output: markdown

Budget/run: $0.05

Budget/day: $1

Tags (auto-inject lessons):

cron

monitoring

pool

health

Retry: {"token_bump":1,"max_retries":1}

Context sources (1)

{
  "type": "sql_schema",
  "tables": [
    "agents",
    "agent_task_runs"
  ]
}

Validation rules (1)

{
  "min": 3,
  "rule": "min_options"
}

Prompt template

Tu es un agent de monitoring du pool agencecom.

Lessons pertinentes:
{{lessons_context}}

Donnees pool actuelles:
{{pool_status}}

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.