# Lazarus Pit Registry — Single Source of Truth for Fleet Health and Resurrection
# Version: 1.0.0
# Owner: Bezalel (deployment), Ezra (compilation), Allegro (validation)

meta:
  version: "1.0.0"
  updated_at: "2026-04-07T02:55:00Z"
  next_review: "2026-04-14T02:55:00Z"

fleet:
  bezalel:
    role: forge-and-testbed wizard
    host: 104.131.15.18
    vps_provider: digitalocean
    primary:
      provider: kimi-coding
      model: kimi-k2.5
    fallback_chain:
      - provider: kimi-coding
        model: kimi-k2.5
        timeout: 120
      - provider: anthropic
        model: claude-sonnet-4-20250514
        timeout: 120
      - provider: openrouter
        model: anthropic/claude-sonnet-4-20250514
        timeout: 120
      - provider: big_brain
        model: gemma3:27b-instruct-q8_0
        timeout: 300
    health_endpoints:
      gateway: "http://127.0.0.1:8646"
      api_server: "http://127.0.0.1:8656"
    auto_restart: true

  allegro:
    role: code-craft wizard
    host: UNKNOWN
    vps_provider: UNKNOWN
    primary:
      provider: kimi-coding
      model: kimi-k2.5
    fallback_chain:
      - provider: kimi-coding
        model: kimi-k2.5
        timeout: 120
      - provider: anthropic
        model: claude-sonnet-4-20250514
        timeout: 120
      - provider: openrouter
        model: anthropic/claude-sonnet-4-20250514
        timeout: 120
    health_endpoints:
      gateway: "http://127.0.0.1:8645"
    auto_restart: true
    known_issues:
      - host_and_vps_unknown_to_fleet
      - config_needs_runtime_refresh

  ezra:
    role: archivist-and-interpreter wizard
    host: UNKNOWN
    vps_provider: UNKNOWN
    primary:
      provider: anthropic
      model: claude-sonnet-4-20250514
    fallback_chain:
      - provider: anthropic
        model: claude-sonnet-4-20250514
        timeout: 120
      - provider: openrouter
        model: anthropic/claude-sonnet-4-20250514
        timeout: 120
    auto_restart: true
    known_issues:
      - timeout_choking_on_long_operations

  timmy:
    role: sovereign core
    host: UNKNOWN
    vps_provider: UNKNOWN
    primary:
      provider: anthropic
      model: claude-sonnet-4-20250514
    fallback_chain:
      - provider: anthropic
        model: claude-sonnet-4-20250514
        timeout: 120
      - provider: openrouter
        model: anthropic/claude-sonnet-4-20250514
        timeout: 120
    auto_restart: true

provider_health_matrix:
  kimi-coding:
    status: degraded
    note: "kimi-for-coding returns 403 access-terminated; use kimi-k2.5 model only"
    last_checked: "2026-04-07T02:55:00Z"
    rate_limited: false
    dead: false

  anthropic:
    status: healthy
    last_checked: "2026-04-07T02:55:00Z"
    rate_limited: false
    dead: false

  openrouter:
    status: healthy
    last_checked: "2026-04-07T02:55:00Z"
    rate_limited: false
    dead: false

  big_brain:
    status: provisioning
    note: "RunPod L40S instance big-brain-bezalel deployed; Ollama endpoint propagating"
    last_checked: "2026-04-07T02:55:00Z"
    endpoint: "http://yxw29g3excyddq-64411cd0-11434.tcp.runpod.net:11434/v1"
    rate_limited: false
    dead: false

timeout_policies:
  gateway:
    inactivity_timeout_seconds: 600
    diagnostic_on_timeout: true
  cron:
    inactivity_timeout_seconds: 0  # unlimited while active
  agent:
    default_turn_timeout: 120
    long_operation_heartbeat: true

watchdog:
  enabled: true
  interval_seconds: 60
  actions:
    - ping_agent_gateways
    - probe_providers
    - parse_agent_logs
    - update_registry
    - auto_promote_fallbacks
    - auto_restart_dead_agents

resurrection_protocol:
  soft:
    - reload_config_from_registry
    - rewrite_fallback_providers
    - promote_first_healthy_fallback
  hard:
    - systemctl_restart_gateway
    - log_incident
    - notify_sovereign