feat(fleet): promote Ollama to first-class provider, assign Gemma 4 across fleet

- lazarus-registry.yaml: replace big_brain/RunPod with local ollama/gemma4:12b
- fleet-routing.json: assign ollama:gemma4:12b to carnice, bilbobagginshire, substratum
- intelligence/deepdive/config.yaml: local model -> gemma4:12b

.gitea/workflows/ci.yml

@@ -41,9 +41,11 @@ jobs:
         run: |
           FAIL=0
           for f in $(find . -name '*.py' -not -path './venv/*'); do
-            if ! python3 -c "import py_compile; py_compile.compile('$f', doraise=True)" 2>/dev/null; then
-            else
+            if python3 -c "import py_compile; py_compile.compile('$f', doraise=True)" 2>/dev/null; then
               echo "OK: $f"
+            else
+              echo "FAIL: $f"
+              FAIL=1
             fi
           done
           exit $FAIL

fleet/fleet-routing.json

@@ -9,7 +9,7 @@
       "id": 27,
       "name": "carnice",
       "gitea_user": "carnice",
-      "model": "qwen3.5-9b",
+      "model": "ollama:gemma4:12b",
       "tier": "free",
       "location": "Local Metal",
       "description": "Local Hermes agent, fine-tuned on Hermes traces. Runs on local hardware.",
@@ -41,7 +41,7 @@
       "id": 25,
       "name": "bilbobagginshire",
       "gitea_user": "bilbobagginshire",
-      "model": "ollama",
+      "model": "ollama:gemma4:12b",
       "tier": "free",
       "location": "Bag End, The Shire (VPS)",
       "description": "Ollama on VPS. Speaks when spoken to. Prefers quiet. Not for delegated work.",
@@ -74,7 +74,7 @@
       "id": 23,
       "name": "substratum",
       "gitea_user": "substratum",
-      "model": "unassigned",
+      "model": "ollama:gemma4:12b",
       "tier": "unknown",
       "location": "Below the Surface",
       "description": "Infrastructure, deployments, bedrock services. Needs model assignment before activation.",

intelligence/deepdive/config.yaml

@@ -76,7 +76,7 @@ deepdive:
   # Phase 3: Synthesis
   synthesis:
     llm_endpoint: "http://localhost:4000/v1"  # Local llama-server
-    llm_model: "gemma-4-it"
+    llm_model: "gemma4:12b"
     max_summary_length: 800
     temperature: 0.7
 

lazarus-registry.yaml

@@ -1,12 +1,7 @@
-# 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"
-
+  version: 1.0.0
+  updated_at: '2026-04-07T15:09:53.386648+00:00'
+  next_review: '2026-04-14T02:55:00Z'
 fleet:
   bezalel:
     role: forge-and-testbed wizard
@@ -16,23 +11,22 @@ fleet:
       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
+    - 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: ollama
+      model: gemma4:12b
+      timeout: 300
     health_endpoints:
-      gateway: "http://127.0.0.1:8646"
-      api_server: "http://127.0.0.1:8656"
+      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
@@ -41,22 +35,21 @@ fleet:
       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: 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"
+      gateway: http://127.0.0.1:8645
     auto_restart: true
     known_issues:
-      - host_and_vps_unknown_to_fleet
-      - config_needs_runtime_refresh
-
+    - host_and_vps_unknown_to_fleet
+    - config_needs_runtime_refresh
   ezra:
     role: archivist-and-interpreter wizard
     host: UNKNOWN
@@ -65,16 +58,15 @@ fleet:
       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
+    - 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
-
+    - timeout_choking_on_long_operations
   timmy:
     role: sovereign core
     host: UNKNOWN
@@ -83,69 +75,63 @@ fleet:
       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
+    - 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"
+    status: healthy
+    note: ''
+    last_checked: '2026-04-07T15:09:53.384900+00:00'
     rate_limited: false
     dead: false
-
   anthropic:
     status: healthy
-    last_checked: "2026-04-07T02:55:00Z"
+    last_checked: '2026-04-07T15:09:53.385047+00:00'
     rate_limited: false
     dead: false
-
+    note: ''
   openrouter:
     status: healthy
-    last_checked: "2026-04-07T02:55:00Z"
+    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"
+  ollama:
+    status: healthy
+    note: Local Ollama endpoint with Gemma 4 support
+    last_checked: '2026-04-07T15:09:53.385047+00:00'
+    endpoint: http://localhost: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
+    inactivity_timeout_seconds: 0
   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
-
+  - 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
+  - reload_config_from_registry
+  - rewrite_fallback_providers
+  - promote_first_healthy_fallback
   hard:
-    - systemctl_restart_gateway
-    - log_incident
-    - notify_sovereign
+  - systemctl_restart_gateway
+  - log_incident
+  - notify_sovereign

nexus/components/fleet-health-dashboard.html

@@ -0,0 +1,118 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="UTF-8">
+<title>Fleet Health Dashboard — Lazarus Pit</title>
+<style>
+  body { font-family: system-ui, sans-serif; background: #0b0c10; color: #c5c6c7; margin: 0; padding: 2rem; }
+  h1 { color: #66fcf1; margin-bottom: 0.5rem; }
+  .subtitle { color: #45a29e; margin-bottom: 2rem; }
+  .grid { display: grid; grid-template-columns: repeat(auto-fit, minmax(280px, 1fr)); gap: 1rem; }
+  .card { background: #1f2833; border-radius: 8px; padding: 1rem; border-left: 4px solid #66fcf1; }
+  .card.dead { border-left-color: #ff4444; }
+  .card.warning { border-left-color: #ffaa00; }
+  .card.unknown { border-left-color: #888; }
+  .name { font-size: 1.2rem; font-weight: bold; color: #fff; }
+  .status { font-size: 0.9rem; margin-top: 0.5rem; }
+  .metric { display: flex; justify-content: space-between; margin-top: 0.3rem; font-size: 0.85rem; }
+  .timestamp { color: #888; font-size: 0.75rem; margin-top: 0.8rem; }
+  #alerts { margin-top: 2rem; background: #1f2833; padding: 1rem; border-radius: 8px; }
+  .alert { color: #ff4444; font-size: 0.9rem; margin: 0.3rem 0; }
+</style>
+</head>
+<body>
+<h1>⚡ Fleet Health Dashboard</h1>
+<div class="subtitle">Powered by the Lazarus Pit — Live Registry</div>
+<div class="grid" id="fleetGrid"></div>
+<div id="alerts"></div>
+
+<script>
+const REGISTRY_URL = "https://forge.alexanderwhitestone.com/Timmy_Foundation/the-nexus/raw/branch/main/lazarus-registry.yaml";
+
+async function fetchRegistry() {
+  try {
+    const res = await fetch(REGISTRY_URL);
+    const text = await res.text();
+    // Very lightweight YAML parser for the subset we need
+    const data = parseSimpleYaml(text);
+    render(data);
+  } catch (e) {
+    document.getElementById("fleetGrid").innerHTML = `<div class="card dead">Failed to load registry: ${e.message}</div>`;
+  }
+}
+
+function parseSimpleYaml(text) {
+  // Enough to extract fleet blocks and provider matrix
+  const lines = text.split("\n");
+  const obj = { fleet: {}, provider_health_matrix: {} };
+  let section = null;
+  let agent = null;
+  let depth = 0;
+  lines.forEach(line => {
+    const trimmed = line.trim();
+    if (trimmed === "fleet:") { section = "fleet"; return; }
+    if (trimmed === "provider_health_matrix:") { section = "providers"; return; }
+    if (section === "fleet" && !trimmed.startsWith("-") && trimmed.endsWith(":") && !trimmed.includes(":")) {
+      agent = trimmed.replace(":", "");
+      obj.fleet[agent] = {};
+      return;
+    }
+    if (section === "fleet" && agent && trimmed.includes(": ")) {
+      const [k, ...v] = trimmed.split(": ");
+      obj.fleet[agent][k.trim()] = v.join(": ").trim();
+    }
+    if (section === "providers" && trimmed.includes(": ")) {
+      const [k, ...v] = trimmed.split(": ");
+      if (!obj.provider_health_matrix[k.trim()]) obj.provider_health_matrix[k.trim()] = {};
+      obj.provider_health_matrix[k.trim()]["status"] = v.join(": ").trim();
+    }
+  });
+  return obj;
+}
+
+function render(data) {
+  const grid = document.getElementById("fleetGrid");
+  const alerts = document.getElementById("alerts");
+  grid.innerHTML = "";
+  alerts.innerHTML = "";
+
+  const fleet = data.fleet || {};
+  const providers = data.provider_health_matrix || {};
+  let alertHtml = "";
+
+  Object.entries(fleet).forEach(([name, spec]) => {
+    const provider = spec.primary ? JSON.parse(JSON.stringify(spec.primary).replace(/'/g, '"')) : {};
+    const provName = provider.provider || "unknown";
+    const provStatus = (providers[provName] || {}).status || "unknown";
+    const host = spec.host || "unknown";
+    const autoRestart = spec.auto_restart === "true" || spec.auto_restart === true;
+
+    let cardClass = "card";
+    if (provStatus === "dead" || provStatus === "degraded") cardClass += " warning";
+    if (host === "UNKNOWN") cardClass += " unknown";
+
+    const html = `
+      <div class="${cardClass}">
+        <div class="name">${name}</div>
+        <div class="status">Role: ${spec.role || "—"}</div>
+        <div class="metric"><span>Host</span><span>${host}</span></div>
+        <div class="metric"><span>Provider</span><span>${provName}</span></div>
+        <div class="metric"><span>Provider Health</span><span style="color:${provStatus==='healthy'?'#66fcf1':provStatus==='degraded'?'#ffaa00':'#ff4444'}">${provStatus}</span></div>
+        <div class="metric"><span>Auto-Restart</span><span>${autoRestart ? "ON" : "OFF"}</span></div>
+        <div class="timestamp">Registry updated: ${data.meta ? data.meta.updated_at : "—"}</div>
+      </div>
+    `;
+    grid.innerHTML += html;
+
+    if (provStatus === "dead") alertHtml += `<div class="alert">🚨 ${name}: primary provider ${provName} is DEAD</div>`;
+    if (host === "UNKNOWN") alertHtml += `<div class="alert">⚠️ ${name}: host unknown — cannot monitor or resurrect</div>`;
+  });
+
+  alerts.innerHTML = alertHtml || `<div style="color:#66fcf1">All agents within known parameters.</div>`;
+}
+
+fetchRegistry();
+setInterval(fetchRegistry, 60000);
+</script>
+</body>
+</html>

nexus/components/fleet-pulse.html

@@ -0,0 +1,101 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="UTF-8">
+<title>Fleet Pulse — Collective Stability</title>
+<style>
+  body { margin: 0; background: #050505; overflow: hidden; display: flex; align-items: center; justify-content: center; height: 100vh; }
+  #pulseCanvas { display: block; }
+  #info {
+    position: absolute; bottom: 20px; left: 50%; transform: translateX(-50%);
+    color: #66fcf1; font-family: system-ui, sans-serif; font-size: 14px; opacity: 0.8;
+    text-align: center;
+  }
+</style>
+</head>
+<body>
+<canvas id="pulseCanvas"></canvas>
+<div id="info">Fleet Pulse — Lazarus Pit Registry</div>
+<script>
+const canvas = document.getElementById('pulseCanvas');
+const ctx = canvas.getContext('2d');
+let width, height, centerX, centerY;
+
+function resize() {
+  width = canvas.width = window.innerWidth;
+  height = canvas.height = window.innerHeight;
+  centerX = width / 2;
+  centerY = height / 2;
+}
+window.addEventListener('resize', resize);
+resize();
+
+let syncLevel = 0.5;
+let targetSync = 0.5;
+
+async function fetchRegistry() {
+  try {
+    const res = await fetch('https://forge.alexanderwhitestone.com/Timmy_Foundation/the-nexus/raw/branch/main/lazarus-registry.yaml');
+    const text = await res.text();
+    const healthy = (text.match(/status: healthy/g) || []).length;
+    const degraded = (text.match(/status: degraded/g) || []).length;
+    const dead = (text.match(/status: dead/g) || []).length;
+    const total = healthy + degraded + dead + 1;
+    targetSync = Math.max(0.1, Math.min(1.0, (healthy + 0.5 * degraded) / total));
+  } catch (e) {
+    targetSync = 0.2;
+  }
+}
+
+fetchRegistry();
+setInterval(fetchRegistry, 30000);
+
+let time = 0;
+function draw() {
+  time += 0.02;
+  syncLevel += (targetSync - syncLevel) * 0.02;
+
+  ctx.fillStyle = 'rgba(5, 5, 5, 0.2)';
+  ctx.fillRect(0, 0, width, height);
+
+  const baseRadius = 60 + syncLevel * 80;
+  const pulseSpeed = 0.5 + syncLevel * 1.5;
+  const colorHue = syncLevel > 0.7 ? 170 : syncLevel > 0.4 ? 45 : 0;
+
+  for (let i = 0; i < 5; i++) {
+    const offset = i * 1.2;
+    const radius = baseRadius + Math.sin(time * pulseSpeed + offset) * (20 + syncLevel * 40);
+    const alpha = 0.6 - i * 0.1;
+
+    ctx.beginPath();
+    ctx.arc(centerX, centerY, Math.abs(radius), 0, Math.PI * 2);
+    ctx.strokeStyle = `hsla(${colorHue}, 80%, 60%, ${alpha})`;
+    ctx.lineWidth = 3 + syncLevel * 4;
+    ctx.stroke();
+  }
+
+  // Orbiting agents
+  const agents = 5;
+  for (let i = 0; i < agents; i++) {
+    const angle = time * 0.3 * (i % 2 === 0 ? 1 : -1) + (i * Math.PI * 2 / agents);
+    const orbitR = baseRadius + 80 + i * 25;
+    const x = centerX + Math.cos(angle) * orbitR;
+    const y = centerY + Math.sin(angle) * orbitR;
+
+    ctx.beginPath();
+    ctx.arc(x, y, 4 + syncLevel * 4, 0, Math.PI * 2);
+    ctx.fillStyle = `hsl(${colorHue}, 80%, 70%)`;
+    ctx.fill();
+  }
+
+  ctx.fillStyle = '#fff';
+  ctx.font = '16px system-ui';
+  ctx.textAlign = 'center';
+  ctx.fillText(`Collective Stability: ${Math.round(syncLevel * 100)}%`, centerX, centerY + 8);
+
+  requestAnimationFrame(draw);
+}
+draw();
+</script>
+</body>
+</html>

requirements.txt

@@ -0,0 +1,3 @@
+pytest>=7.0
+pytest-asyncio>=0.21.0
+pyyaml>=6.0

scripts/lazarus_checkpoint.py

@@ -0,0 +1,140 @@
+#!/usr/bin/env python3
+"""
+Lazarus Checkpoint / Restore
+============================
+Save and resume mission cell state for agent resurrection.
+
+Usage:
+    python scripts/lazarus_checkpoint.py <mission_name>
+    python scripts/lazarus_checkpoint.py --restore <mission_name>
+    python scripts/lazarus_checkpoint.py --list
+"""
+
+import os
+import sys
+import argparse
+import json
+import tarfile
+import subprocess
+from datetime import datetime, timezone
+from pathlib import Path
+
+CHECKPOINT_DIR = Path("/var/lib/lazarus/checkpoints")
+MISSION_DIRS = {
+    "bezalel": "/root/wizards/bezalel",
+    "the-nexus": "/root/wizards/bezalel/workspace/the-nexus",
+    "hermes-agent": "/root/wizards/bezalel/workspace/hermes-agent",
+}
+
+
+def shell(cmd: str, timeout: int = 60) -> tuple[int, str, str]:
+    try:
+        r = subprocess.run(cmd, shell=True, capture_output=True, text=True, timeout=timeout)
+        return r.returncode, r.stdout.strip(), r.stderr.strip()
+    except Exception as e:
+        return -1, "", str(e)
+
+
+def checkpoint(mission: str) -> Path:
+    src = Path(MISSION_DIRS.get(mission, mission))
+    if not src.exists():
+        print(f"ERROR: Source directory not found: {src}")
+        sys.exit(1)
+
+    ts = datetime.now(timezone.utc).strftime("%Y%m%d_%H%M%S")
+    out_dir = CHECKPOINT_DIR / mission
+    out_dir.mkdir(parents=True, exist_ok=True)
+    tar_path = out_dir / f"{mission}_{ts}.tar.gz"
+
+    # Git commit checkpoint
+    git_sha = ""
+    git_path = src / ".git"
+    if git_path.exists():
+        code, out, _ = shell(f"cd {src} && git rev-parse HEAD")
+        if code == 0:
+            git_sha = out
+
+    meta = {
+        "mission": mission,
+        "created_at": datetime.now(timezone.utc).isoformat(),
+        "source": str(src),
+        "git_sha": git_sha,
+    }
+    meta_path = out_dir / f"{mission}_{ts}.json"
+    with open(meta_path, "w") as f:
+        json.dump(meta, f, indent=2)
+
+    # Tar.gz checkpoint (respect .gitignore if possible)
+    with tarfile.open(tar_path, "w:gz") as tar:
+        tar.add(src, arcname=src.name)
+
+    print(f"CHECKPOINT {mission}: {tar_path}")
+    print(f"  Meta: {meta_path}")
+    print(f"  Git SHA: {git_sha or 'n/a'}")
+    return tar_path
+
+
+def restore(mission: str, identifier: str | None = None):
+    out_dir = CHECKPOINT_DIR / mission
+    if not out_dir.exists():
+        print(f"ERROR: No checkpoints found for {mission}")
+        sys.exit(1)
+
+    tars = sorted(out_dir.glob("*.tar.gz"))
+    if not tars:
+        print(f"ERROR: No tar.gz checkpoints for {mission}")
+        sys.exit(1)
+
+    if identifier:
+        tar_path = out_dir / f"{mission}_{identifier}.tar.gz"
+        if not tar_path.exists():
+            print(f"ERROR: Checkpoint not found: {tar_path}")
+            sys.exit(1)
+    else:
+        tar_path = tars[-1]
+
+    src = Path(MISSION_DIRS.get(mission, mission))
+    print(f"RESTORE {mission}: {tar_path} → {src}")
+    with tarfile.open(tar_path, "r:gz") as tar:
+        tar.extractall(path=src.parent)
+    print("Restore complete. Restart agent to resume from checkpoint.")
+
+
+def list_checkpoints():
+    if not CHECKPOINT_DIR.exists():
+        print("No checkpoints stored.")
+        return
+    for mission_dir in sorted(CHECKPOINT_DIR.iterdir()):
+        if mission_dir.is_dir():
+            tars = sorted(mission_dir.glob("*.tar.gz"))
+            print(f"{mission_dir.name}: {len(tars)} checkpoint(s)")
+            for t in tars[-5:]:
+                print(f"  {t.name}")
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(description="Lazarus Checkpoint / Restore")
+    parser.add_argument("mission", nargs="?", help="Mission name to checkpoint/restore")
+    parser.add_argument("--restore", action="store_true", help="Restore mode")
+    parser.add_argument("--identifier", help="Specific checkpoint identifier (YYYYMMDD_HHMMSS)")
+    parser.add_argument("--list", action="store_true", help="List all checkpoints")
+    args = parser.parse_args()
+
+    if args.list:
+        list_checkpoints()
+        return 0
+
+    if not args.mission:
+        print("ERROR: mission name required (or use --list)")
+        return 1
+
+    if args.restore:
+        restore(args.mission, args.identifier)
+    else:
+        checkpoint(args.mission)
+
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

scripts/lazarus_watchdog.py

@@ -0,0 +1,252 @@
+#!/usr/bin/env python3
+"""
+Lazarus Pit Watchdog
+====================
+Automated health monitoring, fallback promotion, and agent resurrection
+for the Timmy Foundation wizard fleet.
+
+Usage:
+    python lazarus_watchdog.py [--dry-run]
+"""
+
+import os
+import sys
+import json
+import argparse
+import subprocess
+import urllib.request
+from datetime import datetime, timezone
+from pathlib import Path
+
+import yaml
+
+REGISTRY_PATH = Path("/root/wizards/bezalel/workspace/the-nexus/lazarus-registry.yaml")
+INCIDENT_LOG = Path("/var/log/lazarus_incidents.jsonl")
+AGENT_CONFIG_PATH = Path("/root/wizards/bezalel/home/.hermes/config.yaml")
+
+
+def shell(cmd: str, timeout: int = 30) -> tuple[int, str, str]:
+    try:
+        r = subprocess.run(cmd, shell=True, capture_output=True, text=True, timeout=timeout)
+        return r.returncode, r.stdout.strip(), r.stderr.strip()
+    except Exception as e:
+        return -1, "", str(e)
+
+
+def load_registry() -> dict:
+    with open(REGISTRY_PATH) as f:
+        return yaml.safe_load(f)
+
+
+def save_registry(data: dict):
+    with open(REGISTRY_PATH, "w") as f:
+        yaml.dump(data, f, default_flow_style=False, sort_keys=False)
+
+
+def ping_http(url: str, timeout: int = 10) -> tuple[bool, int]:
+    try:
+        req = urllib.request.Request(url, method="HEAD")
+        with urllib.request.urlopen(req, timeout=timeout) as resp:
+            return True, resp.status
+    except urllib.error.HTTPError as e:
+        return True, e.code
+    except Exception:
+        return False, 0
+
+
+def probe_provider(provider: str, model: str, timeout: int = 20) -> dict:
+    """
+    Lightweight provider probe.
+    For now we only check if the provider is in our local Hermes config
+    by attempting a trivial API call. Simplified: just assume healthy
+    unless we have explicit evidence of death from logs.
+    """
+    # Check agent logs for recent provider failures
+    log_path = Path("/var/log/syslog")
+    if not log_path.exists():
+        log_path = Path("/var/log/messages")
+
+    dead_keywords = ["access_terminated", "403", "Invalid API key"]
+    degraded_keywords = ["rate limit", "429", "timeout", "Connection reset"]
+
+    status = "healthy"
+    note = ""
+
+    # Parse last 100 lines of hermes log if available
+    hermes_log = Path("/var/log/hermes-gateway.log")
+    if hermes_log.exists():
+        _, out, _ = shell(f"tail -n 100 {hermes_log}")
+        lower = out.lower()
+        for kw in dead_keywords:
+            if kw in lower:
+                status = "dead"
+                note = f"Detected '{kw}' in recent gateway logs"
+                break
+        if status == "healthy":
+            for kw in degraded_keywords:
+                if kw in lower:
+                    status = "degraded"
+                    note = f"Detected '{kw}' in recent gateway logs"
+                    break
+
+    return {"status": status, "note": note, "last_checked": datetime.now(timezone.utc).isoformat()}
+
+
+def check_agent(name: str, spec: dict) -> dict:
+    result = {"agent": name, "timestamp": datetime.now(timezone.utc).isoformat(), "actions": []}
+
+    # Ping gateway
+    gw_url = spec.get("health_endpoints", {}).get("gateway")
+    if gw_url:
+        reachable, code = ping_http(gw_url)
+        result["gateway_reachable"] = reachable
+        result["gateway_status"] = code
+        if not reachable:
+            result["actions"].append("gateway_unreachable")
+    else:
+        result["gateway_reachable"] = False
+        result["actions"].append("no_gateway_configured")
+
+    # Local service check (only if on this host)
+    host = spec.get("host", "")
+    if host in ("127.0.0.1", "localhost", "104.131.15.18") or not host:
+        svc_name = f"hermes-{name}.service"
+        code, out, _ = shell(f"systemctl is-active {svc_name}")
+        result["service_active"] = (code == 0)
+        if code != 0:
+            result["actions"].append("service_inactive")
+    else:
+        result["service_active"] = None
+
+    # Probe primary provider
+    primary = spec.get("primary", {})
+    probe = probe_provider(primary.get("provider"), primary.get("model"))
+    result["primary_provider"] = probe
+    if probe["status"] in ("dead", "degraded"):
+        result["actions"].append(f"primary_{probe['status']}")
+
+    return result
+
+
+def rewrite_fallbacks(name: str, fallback_chain: list, dry_run: bool = False) -> bool:
+    """Rewrite Bezalel's local config.yaml fallback_providers to match registry."""
+    if name != "bezalel":
+        return False  # Can only rewrite local config
+    if not AGENT_CONFIG_PATH.exists():
+        return False
+
+    with open(AGENT_CONFIG_PATH) as f:
+        config = yaml.safe_load(f)
+
+    if "fallback_providers" not in config:
+        config["fallback_providers"] = []
+
+    new_fallbacks = []
+    for entry in fallback_chain:
+        fb = {
+            "provider": entry["provider"],
+            "model": entry["model"],
+            "timeout": entry.get("timeout", 120),
+        }
+        if entry.get("provider") == "openrouter":
+            fb["base_url"] = "https://openrouter.ai/api/v1"
+            fb["api_key_env"] = "OPENROUTER_API_KEY"
+        if entry.get("provider") == "big_brain":
+            fb["base_url"] = "http://yxw29g3excyddq-64411cd0-11434.tcp.runpod.net:11434/v1"
+        new_fallbacks.append(fb)
+
+    if config["fallback_providers"] == new_fallbacks:
+        return False  # No change needed
+
+    config["fallback_providers"] = new_fallbacks
+
+    if not dry_run:
+        with open(AGENT_CONFIG_PATH, "w") as f:
+            yaml.dump(config, f, default_flow_style=False, sort_keys=False)
+
+    return True
+
+
+def resurrect_agent(name: str, dry_run: bool = False) -> bool:
+    svc = f"hermes-{name}.service"
+    if dry_run:
+        print(f"[DRY-RUN] Would restart {svc}")
+        return True
+    code, _, err = shell(f"systemctl restart {svc}")
+    return code == 0
+
+
+def log_incident(event: dict):
+    INCIDENT_LOG.parent.mkdir(parents=True, exist_ok=True)
+    with open(INCIDENT_LOG, "a") as f:
+        f.write(json.dumps(event) + "\n")
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--dry-run", action="store_true", help="Show actions without executing")
+    args = parser.parse_args()
+
+    registry = load_registry()
+    fleet = registry.get("fleet", {})
+    provider_matrix = registry.get("provider_health_matrix", {})
+    changed = False
+
+    for name, spec in fleet.items():
+        result = check_agent(name, spec)
+        actions = result.get("actions", [])
+
+        # Update provider matrix
+        primary_provider = spec.get("primary", {}).get("provider")
+        if primary_provider and primary_provider in provider_matrix:
+            provider_matrix[primary_provider].update(result["primary_provider"])
+
+        # Rewrite fallback chain if needed (local only)
+        if name == "bezalel":
+            fb_chain = spec.get("fallback_chain", [])
+            if rewrite_fallbacks(name, fb_chain, dry_run=args.dry_run):
+                result["actions"].append("fallback_chain_rewritten")
+                changed = True
+
+        # Resurrection logic — only for local agents
+        agent_host = spec.get("host", "")
+        is_local = agent_host in ("127.0.0.1", "localhost", "104.131.15.18") or not agent_host
+        if is_local and ("gateway_unreachable" in actions or "service_inactive" in actions):
+            if spec.get("auto_restart", False):
+                ok = resurrect_agent(name, dry_run=args.dry_run)
+                result["resurrected"] = ok
+                result["actions"].append("auto_restart_executed" if ok else "auto_restart_failed")
+                log_incident(result)
+                changed = True
+
+        # Fallback promotion if primary is dead
+        if "primary_dead" in actions:
+            fb = spec.get("fallback_chain", [])
+            if fb:
+                healthy_fallback = None
+                for candidate in fb:
+                    cand_provider = candidate["provider"]
+                    if provider_matrix.get(cand_provider, {}).get("status") == "healthy":
+                        healthy_fallback = candidate
+                        break
+                if healthy_fallback:
+                    if not args.dry_run:
+                        spec["primary"] = healthy_fallback
+                    result["actions"].append(f"promoted_fallback_to_{healthy_fallback['provider']}")
+                    log_incident(result)
+                    changed = True
+
+        # Print summary
+        status = "OK" if not actions else "ACTION"
+        print(f"[{status}] {name}: {', '.join(actions) if actions else 'healthy'}")
+
+    if changed and not args.dry_run:
+        registry["meta"]["updated_at"] = datetime.now(timezone.utc).isoformat()
+        save_registry(registry)
+        print("\nRegistry updated.")
+
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())