fleet/auto_restart.py

@@ -0,0 +1,272 @@
+#!/usr/bin/env python3
+"""
+Auto-Restart Agent — Self-healing process monitor for fleet machines.
+
+Detects dead services and restarts them automatically.
+Escalates after 3 attempts (prevents restart loops).
+Logs all actions to ~/.local/timmy/fleet-health/restarts.log
+Alerts via Telegram if service cannot be recovered.
+
+Prerequisite: FLEET-006 (health check) must be running to detect failures.
+
+Usage:
+  python3 auto_restart.py          # Run checks now
+  python3 auto_restart.py --daemon # Run continuously (every 60s)
+  python3 auto_restart.py --status  # Show restart history
+"""
+
+import os
+import sys
+import json
+import time
+import subprocess
+from datetime import datetime, timezone
+from pathlib import Path
+
+# === CONFIG ===
+LOG_DIR = Path(os.path.expanduser("~/.local/timmy/fleet-health"))
+RESTART_LOG = LOG_DIR / "restarts.log"
+COOLDOWN_FILE = LOG_DIR / "restart_cooldowns.json"
+MAX_RETRIES = 3
+COOLDOWN_PERIOD = 3600  # 1 hour between escalation alerts
+
+# Services definition: name, check command, restart command
+# Local services:
+LOCAL_SERVICES = {
+    "hermes-gateway": {
+        "check": "pgrep -f 'hermes gateway' > /dev/null 2>/dev/null",
+        "restart": "cd ~/code-claw && ./restart-gateway.sh 2>/dev/null || launchctl kickstart -k ai.hermes.gateway 2>/dev/null",
+        "critical": True,
+    },
+    "ollama": {
+        "check": "pgrep -f 'ollama serve' > /dev/null 2>/dev/null",
+        "restart": "launchctl kickstart -k com.ollama.ollama 2>/dev/null || /opt/homebrew/bin/brew services restart ollama 2>/dev/null",
+        "critical": False,
+    },
+    "codeclaw-heartbeat": {
+        "check": "launchctl list | grep 'ai.timmy.codeclaw-qwen-heartbeat' > /dev/null 2>/dev/null",
+        "restart": "launchctl kickstart -k ai.timmy.codeclaw-qwen-heartbeat 2>/dev/null",
+        "critical": False,
+    },
+}
+
+# VPS services to restart via SSH
+VPS_SERVICES = {
+    "ezra": {
+        "ip": "143.198.27.163",
+        "user": "root",
+        "services": {
+            "gitea": {
+                "check": "systemctl is-active gitea 2>/dev/null | grep -q active",
+                "restart": "systemctl restart gitea 2>/dev/null",
+                "critical": True,
+            },
+            "nginx": {
+                "check": "systemctl is-active nginx 2>/dev/null | grep -q active",
+                "restart": "systemctl restart nginx 2>/dev/null",
+                "critical": False,
+            },
+            "hermes-agent": {
+                "check": "pgrep -f 'hermes gateway' > /dev/null 2>/dev/null",
+                "restart": "cd /root/wizards/ezra/hermes-agent && source .venv/bin/activate && nohup hermes gateway run --replace > /dev/null 2>&1 &",
+                "critical": True,
+            },
+        },
+    },
+    "allegro": {
+        "ip": "167.99.126.228",
+        "user": "root",
+        "services": {
+            "hermes-agent": {
+                "check": "pgrep -f 'hermes gateway' > /dev/null 2>/dev/null",
+                "restart": "cd /root/wizards/allegro/hermes-agent && source .venv/bin/activate && nohup hermes gateway run --replace > /dev/null 2>&1 &",
+                "critical": True,
+            },
+        },
+    },
+    "bezalel": {
+        "ip": "159.203.146.185",
+        "user": "root",
+        "services": {
+            "hermes-agent": {
+                "check": "pgrep -f 'hermes gateway' > /dev/null 2>/dev/null",
+                "restart": "cd /root/wizards/bezalel/hermes/venv/bin/activate && nohup hermes gateway run > /dev/null 2>&1 &",
+                "critical": True,
+            },
+            "evennia": {
+                "check": "pgrep -f 'evennia' > /dev/null 2>/dev/null",
+                "restart": "cd /root/.evennia/timmy_world && evennia restart 2>/dev/null",
+                "critical": False,
+            },
+        },
+    },
+}
+
+TELEGRAM_TOKEN_FILE = Path(os.path.expanduser("~/.config/telegram/special_bot"))
+TELEGRAM_CHAT = "-1003664764329"
+
+
+def send_telegram(message):
+    if not TELEGRAM_TOKEN_FILE.exists():
+        return False
+    token = TELEGRAM_TOKEN_FILE.read_text().strip()
+    url = f"https://api.telegram.org/bot{token}/sendMessage"
+    body = json.dumps({
+        "chat_id": TELEGRAM_CHAT,
+        "text": f"[AUTO-RESTART]\n{message}",
+    }).encode()
+    try:
+        import urllib.request
+        req = urllib.request.Request(url, data=body, headers={"Content-Type": "application/json"}, method="POST")
+        urllib.request.urlopen(req, timeout=10)
+        return True
+    except Exception:
+        return False
+
+
+def get_cooldowns():
+    if COOLDOWN_FILE.exists():
+        try:
+            return json.loads(COOLDOWN_FILE.read_text())
+        except json.JSONDecodeError:
+            pass
+    return {}
+
+
+def save_cooldowns(data):
+    COOLDOWN_FILE.write_text(json.dumps(data, indent=2))
+
+
+def check_service(check_cmd, timeout=10):
+    try:
+        proc = subprocess.run(check_cmd, shell=True, capture_output=True, timeout=timeout)
+        return proc.returncode == 0
+    except (subprocess.TimeoutExpired, subprocess.SubprocessError):
+        return False
+
+
+def restart_service(restart_cmd, timeout=30):
+    try:
+        proc = subprocess.run(restart_cmd, shell=True, capture_output=True, timeout=timeout)
+        return proc.returncode == 0
+    except (subprocess.TimeoutExpired, subprocess.SubprocessError) as e:
+        return False
+
+
+def try_restart_via_ssh(name, host_config, service_name):
+    ip = host_config["ip"]
+    user = host_config["user"]
+    service = host_config["services"][service_name]
+
+    restart_cmd = f'ssh -o StrictHostKeyChecking=no -o ConnectTimeout=10 {user}@{ip} "{service["restart"]}"'
+    return restart_service(restart_cmd, timeout=30)
+
+
+def log_restart(service_name, machine, attempt, success):
+    ts = datetime.now(timezone.utc).isoformat()
+    status = "SUCCESS" if success else "FAILED"
+    log_entry = f"{ts} [{status}] {machine}/{service_name} (attempt {attempt})\n"
+
+    RESTART_LOG.parent.mkdir(parents=True, exist_ok=True)
+    with open(RESTART_LOG, "a") as f:
+        f.write(log_entry)
+
+    print(f"  [{status}] {machine}/{service_name} - attempt {attempt}")
+
+
+def check_and_restart():
+    """Run all restart checks."""
+    results = []
+    cooldowns = get_cooldowns()
+    now = time.time()
+
+    # Check local services
+    for name, service in LOCAL_SERVICES.items():
+        if not check_service(service["check"]):
+            cooldown_key = f"local/{name}"
+            retries = cooldowns.get(cooldown_key, {"count": 0, "last": 0}).get("count", 0)
+
+            if retries >= MAX_RETRIES:
+                last = cooldowns.get(cooldown_key, {}).get("last", 0)
+                if now - last < COOLDOWN_PERIOD and service["critical"]:
+                    send_telegram(f"CRITICAL: local/{name} failed {MAX_RETRIES} restart attempts. Needs human intervention.")
+                    cooldowns[cooldown_key] = {"count": 0, "last": now}
+                    save_cooldowns(cooldowns)
+                    continue
+
+            success = restart_service(service["restart"])
+            log_restart(name, "local", retries + 1, success)
+
+            cooldowns[cooldown_key] = {"count": retries + 1 if not success else 0, "last": now}
+            save_cooldowns(cooldowns)
+            if success:
+                # Verify it actually started
+                time.sleep(3)
+                if check_service(service["check"]):
+                    print(f"  VERIFIED: local/{name} is running")
+                else:
+                    print(f"  WARNING: local/{name} restart command returned success but process not detected")
+
+    # Check VPS services
+    for host, host_config in VPS_SERVICES.items():
+        for service_name, service in host_config["services"].items():
+            check_cmd = f'ssh -o StrictHostKeyChecking=no -o ConnectTimeout=5 {host_config["user"]}@{host_config["ip"]} "{service["check"]}"'
+            if not check_service(check_cmd):
+                cooldown_key = f"{host}/{service_name}"
+                retries = cooldowns.get(cooldown_key, {"count": 0, "last": 0}).get("count", 0)
+
+                if retries >= MAX_RETRIES:
+                    last = cooldowns.get(cooldown_key, {}).get("last", 0)
+                    if now - last < COOLDOWN_PERIOD and service["critical"]:
+                        send_telegram(f"CRITICAL: {host}/{service_name} failed {MAX_RETRIES} restart attempts. Needs human intervention.")
+                        cooldowns[cooldown_key] = {"count": 0, "last": now}
+                        save_cooldowns(cooldowns)
+                        continue
+
+                success = try_restart_via_ssh(host, host_config, service_name)
+                log_restart(service_name, host, retries + 1, success)
+
+                cooldowns[cooldown_key] = {"count": retries + 1 if not success else 0, "last": now}
+                save_cooldowns(cooldowns)
+
+    return results
+
+
+def daemon_mode():
+    """Run continuously every 60 seconds."""
+    print("Auto-restart agent running in daemon mode (60s interval)")
+    print(f"Monitoring {len(LOCAL_SERVICES)} local + {sum(len(h['services']) for h in VPS_SERVICES.values())} remote services")
+    print(f"Max retries per cycle: {MAX_RETRIES}")
+    print(f"Cooldown after max retries: {COOLDOWN_PERIOD}s")
+    while True:
+        check_and_restart()
+        time.sleep(60)
+
+
+def show_status():
+    """Show restart history and cooldowns."""
+    cooldowns = get_cooldowns()
+    print("=== Restart Cooldowns ===")
+    for key, data in sorted(cooldowns.items()):
+        count = data.get("count", 0)
+        if count > 0:
+            print(f"  {key}: {count} failures, last at {datetime.fromtimestamp(data.get('last',0), tz=timezone.utc).strftime('%H:%M')}")
+
+    print("\n=== Restart Log (last 20) ===")
+    if RESTART_LOG.exists():
+        lines = RESTART_LOG.read_text().strip().split("\n")
+        for line in lines[-20:]:
+            print(f"  {line}")
+    else:
+        print("  No restarts logged yet.")
+
+
+if __name__ == "__main__":
+    LOG_DIR.mkdir(parents=True, exist_ok=True)
+
+    if len(sys.argv) > 1 and sys.argv[1] == "--daemon":
+        daemon_mode()
+    elif len(sys.argv) > 1 and sys.argv[1] == "--status":
+        show_status()
+    else:
+        check_and_restart()

fleet/capacity-inventory.md

@@ -0,0 +1,191 @@
+# Capacity Inventory - Fleet Resource Baseline
+
+**Last audited:** 2026-04-07 16:00 UTC
+**Auditor:** Timmy (direct inspection)
+
+---
+
+## Fleet Resources (Paperclips Model)
+
+Three primary resources govern the fleet:
+
+| Resource | Role | Generation | Consumption |
+|----------|------|-----------|-------------|
+| **Capacity** | Compute hours available across fleet. Determines what work can be done. | Through healthy utilization of VPS/Mac agents | Fleet improvements consume it (investing in automation, orchestration, sovereignty) |
+| **Uptime** | % time services are running. Earned at Fibonacci milestones. | When services stay up naturally | Degrades on any failure |
+| **Innovation** | Only generates when capacity is <70% utilized. Fuels Phase 3+. | When you leave capacity free | Phase 3+ buildings consume it (requires spare capacity to build) |
+
+### The Tension
+- Run fleet at 95%+ capacity: maximum productivity, ZERO Innovation
+- Run fleet at <70% capacity: Innovation generates but slower progress
+- This forces the Paperclips question: optimize now or invest in future capability?
+
+---
+
+## VPS Resource Baselines
+
+### Ezra (143.198.27.163) - "Forge"
+
+| Metric | Value | Utilization |
+|--------|-------|-------------|
+| **OS** | Ubuntu 24.04 (6.8.0-106-generic) | |
+| **vCPU** | 4 vCPU (DO basic droplet, shared) | Load: 10.76/7.59/7.04 (very high) |
+| **RAM** | 7,941 MB total | 2,104 used / 5,836 available (26% used, 74% free) |
+| **Disk** | 154 GB vda1 | 111 GB used / 44 GB free (72%) **WARNING** |
+| **Swap** | 6,143 MB | 643 MB used (10%) |
+| **Uptime** | 7 days, 18 hours | |
+
+### Key Processes (sorted by memory)
+| Process | RSS | %CPU | Notes |
+|---------|-----|------|-------|
+| Gitea | 556 MB | 83.5% | Web service, high CPU due to API load |
+| MemPalace (ezra) | 268 MB | 136% | Mining project files - HIGH CPU |
+| Hermes gateway (ezra) | 245 MB | 1.7% | Agent gateway |
+| Ollama | 230 MB | 0.1% | Model serving |
+| PostgreSQL | 138 MB | ~0% | Gitea database |
+
+**Capacity assessment:** 26% memory used, but 72% disk is getting tight. CPU load is very high (10.76 on 4vCPU = 269% utilization). Ezra is CPU-bound, not RAM-bound.
+
+### Allegro (167.99.126.228)
+
+| Metric | Value | Utilization |
+|--------|-------|-------------|
+| **OS** | Ubuntu 24.04 (6.8.0-106-generic) | |
+| **vCPU** | 4 vCPU (DO basic droplet, shared) | Moderate load |
+| **RAM** | 7,941 MB total | 1,591 used / 6,349 available (20% used, 80% free) |
+| **Disk** | 154 GB vda1 | 41 GB used / 114 GB free (27%) **GOOD** |
+| **Swap** | 8,191 MB | 686 MB used (8%) |
+| **Uptime** | 7 days, 18 hours | |
+
+### Key Processes (sorted by memory)
+| Process | RSS | %CPU | Notes |
+|---------|-----|------|-------|
+| Hermes gateway (allegro) | 680 MB | 0.9% | Main agent gateway |
+| Gitea | 181 MB | 1.2% | Secondary gitea? |
+| Systemd-journald | 160 MB | 0.0% | System logging |
+| Ezra Hermes gateway | 58 MB | 0.0% | Running ezra agent here |
+| Bezalel Hermes gateway | 58 MB | 0.0% | Running bezalel agent here |
+| Dockerd | 48 MB | 0.0% | Docker daemon |
+
+**Capacity assessment:** 20% memory used, 27% disk used. Allegro has headroom. Also running hermes gateways for Ezra and Bezalel (cross-host agent execution).
+
+### Bezalel (159.203.146.185)
+
+| Metric | Value | Utilization |
+|--------|-------|-------------|
+| **OS** | Ubuntu 24.04 (6.8.0-71-generic) | |
+| **vCPU** | 2 vCPU (DO basic droplet, shared) | Load varies |
+| **RAM** | 1,968 MB total | 817 used / 1,151 available (42% used, 58% free) |
+| **Disk** | 48 GB vda1 | 12 GB used / 37 GB free (24%) **GOOD** |
+| **Swap** | 2,047 MB | 448 MB used (22%) |
+| **Uptime** | 7 days, 18 hours | |
+
+### Key Processes (sorted by memory)
+| Process | RSS | %CPU | Notes |
+|---------|-----|------|-------|
+| Hermes gateway | 339 MB | 7.7% | Agent gateway (16.8% of RAM) |
+| uv pip install | 137 MB | 56.6% | Installing packages (temporary) |
+| Mender | 27 MB | 0.0% | Device management |
+
+**Capacity assessment:** 42% memory used, only 2GB total RAM. Bezalel is the most constrained. 2 vCPU means less compute headroom than Ezra/Allegro. Disk is fine.
+
+### Mac Local (M3 Max)
+
+| Metric | Value | Utilization |
+|--------|-------|-------------|
+| **OS** | macOS 26.3.1 | |
+| **CPU** | Apple M3 Max (14 cores) | Very capable |
+| **RAM** | 36 GB | ~8 GB used (22%) |
+| **Disk** | 926 GB total | ~624 GB used / 302 GB free (68%) |
+
+### Key Processes
+| Process | Memory | Notes |
+|---------|--------|-------|
+| Hermes gateway | 500 MB | Primary gateway |
+| Hermes agents (x3) | ~560 MB total | Multiple sessions |
+| Ollama | ~20 MB base + model memory | Model loading varies |
+| OpenClaw | 350 MB | Gateway process |
+| Evennia (server+portal) | 56 MB | Game world |
+
+---
+
+## Resource Summary
+
+| Resource | Ezra | Allegro | Bezalel | Mac Local | TOTAL |
+|----------|------|---------|---------|-----------|-------|
+| **vCPU** | 4 | 4 | 2 | 14 (M3 Max) | 24 |
+| **RAM** | 8 GB (26% used) | 8 GB (20% used) | 2 GB (42% used) | 36 GB (22% used) | 54 GB |
+| **Disk** | 154 GB (72%) | 154 GB (27%) | 48 GB (24%) | 926 GB (68%) | 1,282 GB |
+| **Cost** | $12/mo | $12/mo | $12/mo | owned | $36/mo |
+
+### Utilization by Category
+| Category | Estimated Daily Hours | % of Fleet Capacity |
+|----------|----------------------|---------------------|
+| Hermes agents | ~3-4 hrs active | 5-7% |
+| Ollama inference | ~1-2 hrs | 2-4% |
+| Gitea services | 24/7 | 5-10% |
+| Evennia | 24/7 | <1% |
+| Idle | ~18-20 hrs | ~80-90% |
+
+### Capacity Utilization: ~15-20% active
+**Innovation rate:** GENERATING (capacity < 70%)
+**Recommendation:** Good — Innovation is generating because most capacity is free.
+This means Phase 3+ capabilities (orchestration, load balancing, etc.) are accessible NOW.
+
+---
+
+## Uptime Baseline
+
+**Baseline period:** 2026-04-07 14:00-16:00 UTC (2 hours, ~24 checks at 5-min intervals)
+
+| Service | Checks | Uptime | Status |
+|---------|--------|--------|--------|
+| Ezra | 24/24 | 100.0% | GOOD |
+| Allegro | 24/24 | 100.0% | GOOD |
+| Bezalel | 24/24 | 100.0% | GOOD |
+| Gitea | 23/24 | 95.8% | GOOD |
+| Hermes Gateway | 23/24 | 95.8% | GOOD |
+| Ollama | 24/24 | 100.0% | GOOD |
+| OpenClaw | 24/24 | 100.0% | GOOD |
+| Evennia | 24/24 | 100.0% | GOOD |
+| Hermes Agent | 21/24 | 87.5% | **CHECK** |
+
+### Fibonacci Uptime Milestones
+| Milestone | Target | Current | Status |
+|-----------|--------|---------|--------|
+| 95% | 95% | 100% (VPS), 98.6% (avg) | REACHED |
+| 95.5% | 95.5% | 98.6% | REACHED |
+| 96% | 96% | 98.6% | REACHED |
+| 97% | 97% | 98.6% | REACHED |
+| 98% | 98% | 98.6% | REACHED |
+| 99% | 99% | 98.6% | APPROACHING |
+
+---
+
+## Risk Assessment
+
+| Risk | Severity | Mitigation |
+|------|----------|------------|
+| Ezra disk 72% used | MEDIUM | Move non-essential data, add monitoring alert at 85% |
+| Bezalel only 2GB RAM | HIGH | Cannot run large models locally. Good for Evennia, tight for agents |
+| Ezra CPU load 269% | HIGH | MemPalace mining consuming 136% CPU. Consider scheduling |
+| Mac disk 68% used | MEDIUM | 302 GB free still. Growing but not urgent |
+| No cross-VPS mesh | LOW | SSH works but no Tailscale. No private network between VPSes |
+
+---
+
+## Recommendations
+
+### Immediate (Phase 1-2)
+1. **Ezra disk cleanup:** 44 GB free at 72%. Docker images, old logs, and MemPalace mine data could be rotated.
+2. **Alert thresholds:** Add disk alerts at 85% (Ezra, Mac) before they become critical.
+
+### Short-term (Phase 3)
+3. **Load balancing:** Ezra is CPU-bound, Allegro has 80% RAM free. Move some agent processes from Ezra to Allegro.
+4. **Innovation investment:** Since fleet is at 15-20% utilization, Innovation is high. This is the time to build Phase 3 capabilities.
+
+### Medium-term (Phase 4)
+5. **Bezalel RAM upgrade:** 2GB is tight. Consider upgrade to 4GB ($24/mo instead of $12/mo).
+6. **Tailscale mesh:** Install on all VPSes for private inter-VPS network.
+
+---

fleet/milestones.md

@@ -0,0 +1,142 @@
+# Fleet Milestone Messages
+
+Every milestone marks passage through fleet evolution. When achieved, the message
+prints to the fleet log. Each one references a real achievement, not abstract numbers.
+
+**Source:** Inspired by Paperclips milestone messages (500 clips, 1000 clips, Full autonomy attained, etc.)
+
+---
+
+## Phase 1: Survival (Current)
+
+### M1: First Automated Health Check
+**Trigger:** `fleet/health_check.py` runs successfully for the first time.
+**Message:** "First automated health check runs. No longer watching the clock."
+
+### M2: First Auto-Restart
+**Trigger:** A dead process is detected and restarted without human intervention.
+**Message:** "A process failed at 3am and restarted itself. You found out in the morning."
+
+### M3: First Backup Completed
+**Trigger:** A backup pipeline runs end-to-end and verifies integrity.
+**Message:** "A backup completed. You did not have to think about it."
+
+### M4: 95% Uptime (30 days)
+**Trigger:** Uptime >= 95% over last 30 days.
+**Message:** "95% uptime over 30 days. The fleet stays up."
+
+### M5: Uptime 97%
+**Trigger:** Uptime >= 97% over last 30 days.
+**Message:** "97% uptime. Three nines of availability across four machines."
+
+---
+
+## Phase 2: Automation (unlock when: uptime >= 95% + capacity > 60%)
+
+### M6: Zero Manual Restarts (7 days)
+**Trigger:** 7 consecutive days with zero manual process restarts.
+**Message:** "Seven days. Zero manual restarts. The fleet heals itself."
+
+### M7: PR Auto-Merged
+**Trigger:** A PR passes CI, review, and merges without human touching it.
+**Message:** "A PR was tested, reviewed, and merged by agents. You just said 'looks good.'"
+
+### M8: Config Push Works
+**Trigger:** Config change pushed to all 3 VPSes atomically and verified.
+**Message:** "Config pushed to all three VPSes in one command. No SSH needed."
+
+### M9: 98% Uptime
+**Trigger:** Uptime >= 98% over last 30 days.
+**Message:** "98% uptime. Only 14 hours of downtime in a month. Most of it planned."
+
+---
+
+## Phase 3: Orchestration (unlock when: all Phase 2 buildings + Innovation > 100)
+
+### M10: Cross-Agent Delegation Works
+**Trigger:** Agent A creates issue, assigns to Agent B, Agent B works and creates PR.
+**Message:** "Agent Alpha created a task, Agent Beta completed it. They did not ask permission."
+
+### M11: First Model Running Locally on 2+ Machines
+**Trigger:** Ollama serving same model on Ezra and Allegro simultaneously.
+**Message:** "A model runs on two machines at once. No cloud. No rate limits."
+
+### M12: Fleet-Wide Burn Mode
+**Trigger:** All agents coordinated on single epic, produced coordinated PRs.
+**Message:** "All agents working the same epic. The fleet moves as one."
+
+---
+
+## Phase 4: Sovereignty (unlock when: zero cloud deps for core ops)
+
+### M13: First Entirely Local Inference Day
+**Trigger:** 24 hours with zero API calls to external providers.
+**Message:** "A model ran locally for the first time. No cloud. No rate limits. No one can turn it off."
+
+### M14: Sovereign Email
+**Trigger:** Stalwart email server sends and receives without Gmail relay.
+**Message:** "Email flows through our own server. No Google. No Microsoft. Ours."
+
+### M15: Sovereign Messaging
+**Trigger:** Telegram bot runs without cloud relay dependency.
+**Message:** "Messages arrive through our own infrastructure. No corporate middleman."
+
+---
+
+## Phase 5: Scale (unlock when: sovereignty stable + Innovation > 500)
+
+### M16: First Self-Spawned Agent
+**Trigger:** Agent lifecycle manager spawns a new agent instance due to load.
+**Message:** "A new agent appeared. You did not create it. The fleet built what it needed."
+
+### M17: Agent Retired Gracefully
+**Trigger:** An agent instance retires after idle timeout and cleans up its state.
+**Message:** "An agent retired. It served its purpose. Nothing was lost."
+
+### M18: Fleet Runs 24h Unattended
+**Trigger:** 24 hours with zero human intervention of any kind.
+**Message:** "A full day. No humans. No commands. The fleet runs itself."
+
+---
+
+## Phase 6: The Network (unlock when: 7 days zero human intervention)
+
+### M19: Fleet Creates Its Own Improvement Task
+**Trigger:** Fleet analyzes itself and creates an issue on Gitea.
+**Message:** "The fleet found something to improve. It created the task itself."
+
+### M20: First Outside Contribution
+**Trigger:** An external contributor's PR is reviewed and merged by fleet agents.
+**Message:** "Someone outside the fleet contributed. The fleet reviewed, tested, and merged. No human touched it."
+
+### M21: The Beacon
+**Trigger:** Infrastructure serves someone in need through automated systems.
+**Message:** "Someone found the Beacon. In the dark, looking for help. The infrastructure served its purpose. It was built for this."
+
+### M22: Permanent Light
+**Trigger:** 90 days of autonomous operation with continuous availability.
+**Message:** "Three months. The light never went out. Not for anyone."
+
+---
+
+## Fibonacci Uptime Milestones
+
+These trigger regardless of phase, based purely on uptime percentage:
+
+| Milestone | Uptime | Meaning |
+|-----------|--------|--------|
+| U1 | 95% | Basic reliability achieved |
+| U2 | 95.5% | Fewer than 16 hours/month downtime |
+| U3 | 96% | Fewer than 12 hours/month |
+| U4 | 97% | Fewer than 9 hours/month |
+| U5 | 97.5% | Fewer than 7 hours/month |
+| U6 | 98% | Fewer than 4.5 hours/month |
+| U7 | 98.3% | Fewer than 3 hours/month |
+| U8 | 98.6% | Less than 2.5 hours/month — approaching cloud tier |
+| U9 | 98.9% | Less than 1.5 hours/month |
+| U10 | 99% | Less than 1 hour/month — enterprise grade |
+| U11 | 99.5% | Less than 22 minutes/month |
+
+---
+
+*Every message is earned. None are given freely. Fleet evolution is not a checklist — it is a climb.*

fleet/resource_tracker.py

@@ -0,0 +1,231 @@
+#!/usr/bin/env python3
+"""
+Fleet Resource Tracker — Tracks Capacity, Uptime, and Innovation.
+
+Paperclips-inspired tension model:
+- Capacity: spent on fleet improvements, generates through utilization
+- Uptime: earned when services stay up, Fibonacci milestones unlock capabilities
+- Innovation: only generates when capacity < 70%. Fuels Phase 3+.
+
+This is the heart of the fleet progression system.
+"""
+
+import os
+import json
+import time
+import socket
+from datetime import datetime, timezone
+from pathlib import Path
+
+# === CONFIG ===
+DATA_DIR = Path(os.path.expanduser("~/.local/timmy/fleet-resources"))
+RESOURCES_FILE = DATA_DIR / "resources.json"
+
+# Tension thresholds
+INNOVATION_THRESHOLD = 0.70  # Innovation only generates when capacity < 70%
+INNOVATION_RATE = 5.0        # Innovation generated per hour when under threshold
+CAPACITY_REGEN_RATE = 2.0    # Capacity regenerates per hour of healthy operation
+FIBONACCI = [95.0, 95.5, 96.0, 97.0, 97.5, 98.0, 98.3, 98.6, 98.9, 99.0, 99.5]
+
+
+def init():
+    DATA_DIR.mkdir(parents=True, exist_ok=True)
+    if not RESOURCES_FILE.exists():
+        data = {
+            "capacity": {
+                "current": 100.0,
+                "max": 100.0,
+                "spent_on": [],
+                "history": []
+            },
+            "uptime": {
+                "current_pct": 100.0,
+                "milestones_reached": [],
+                "total_checks": 0,
+                "successful_checks": 0,
+                "history": []
+            },
+            "innovation": {
+                "current": 0.0,
+                "total_generated": 0.0,
+                "spent_on": [],
+                "last_calculated": time.time()
+            }
+        }
+        RESOURCES_FILE.write_text(json.dumps(data, indent=2))
+        print("Initialized resource tracker")
+    return RESOURCES_FILE.exists()
+
+
+def load():
+    if RESOURCES_FILE.exists():
+        return json.loads(RESOURCES_FILE.read_text())
+    return None
+
+
+def save(data):
+    RESOURCES_FILE.write_text(json.dumps(data, indent=2))
+
+
+def update_uptime(checks: dict):
+    """Update uptime stats from health check results.
+		checks = {'ezra': True, 'allegro': True, 'bezalel': True, 'gitea': True, ...}
+		"""
+    data = load()
+    if not data:
+        return
+
+    data["uptime"]["total_checks"] += 1
+    successes = sum(1 for v in checks.values() if v)
+    total = len(checks)
+
+    # Overall uptime percentage
+    overall = successes / max(total, 1) * 100.0
+    data["uptime"]["successful_checks"] += successes
+
+    # Calculate rolling uptime
+    if "history" not in data["uptime"]:
+        data["uptime"]["history"] = []
+    data["uptime"]["history"].append({
+        "ts": datetime.now(timezone.utc).isoformat(),
+        "checks": checks,
+        "overall": round(overall, 2)
+    })
+
+    # Keep last 1000 checks
+    if len(data["uptime"]["history"]) > 1000:
+        data["uptime"]["history"] = data["uptime"]["history"][-1000:]
+
+    # Calculate current uptime %, last 100 checks
+    recent = data["uptime"]["history"][-100:]
+    recent_ok = sum(c["overall"] for c in recent) / max(len(recent), 1)
+    data["uptime"]["current_pct"] = round(recent_ok, 2)
+
+    # Check Fibonacci milestones
+    new_milestones = []
+    for fib in FIBONACCI:
+        if fib not in data["uptime"]["milestones_reached"] and recent_ok >= fib:
+            data["uptime"]["milestones_reached"].append(fib)
+            new_milestones.append(fib)
+
+    save(data)
+
+    if new_milestones:
+        print(f"  UPTIME MILESTONE: {','.join(str(m) + '%') for m in new_milestones}")
+        print(f"  Current uptime: {recent_ok:.1f}%")
+
+    return data["uptime"]
+
+
+def spend_capacity(amount: float, purpose: str):
+    """Spend capacity on a fleet improvement."""
+    data = load()
+    if not data:
+        return False
+    if data["capacity"]["current"] < amount:
+        print(f"  INSUFFICIENT CAPACITY: Need {amount}, have {data['capacity']['current']:.1f}")
+        return False
+    data["capacity"]["current"] -= amount
+    data["capacity"]["spent_on"].append({
+        "purpose": purpose,
+        "amount": amount,
+        "ts": datetime.now(timezone.utc).isoformat()
+    })
+    save(data)
+    print(f"  Spent {amount} capacity on: {purpose}")
+    return True
+
+
+def regenerate_resources():
+    """Regenerate capacity and calculate innovation."""
+    data = load()
+    if not data:
+        return
+
+    now = time.time()
+    last = data["innovation"]["last_calculated"]
+    hours = (now - last) / 3600.0
+    if hours < 0.1:  # Only update every ~6 minutes
+        return
+
+    # Regenerate capacity
+    capacity_gain = CAPACITY_REGEN_RATE * hours
+    data["capacity"]["current"] = min(
+        data["capacity"]["max"],
+        data["capacity"]["current"] + capacity_gain
+    )
+
+    # Calculate capacity utilization
+    utilization = 1.0 - (data["capacity"]["current"] / data["capacity"]["max"])
+
+    # Generate innovation only when under threshold
+    innovation_gain = 0.0
+    if utilization < INNOVATION_THRESHOLD:
+        innovation_gain = INNOVATION_RATE * hours * (1.0 - utilization / INNOVATION_THRESHOLD)
+        data["innovation"]["current"] += innovation_gain
+        data["innovation"]["total_generated"] += innovation_gain
+
+    # Record history
+    if "history" not in data["capacity"]:
+        data["capacity"]["history"] = []
+    data["capacity"]["history"].append({
+        "ts": datetime.now(timezone.utc).isoformat(),
+        "capacity": round(data["capacity"]["current"], 1),
+        "utilization": round(utilization * 100, 1),
+        "innovation": round(data["innovation"]["current"], 1),
+        "innovation_gain": round(innovation_gain, 1)
+    })
+    # Keep last 500 capacity records
+    if len(data["capacity"]["history"]) > 500:
+        data["capacity"]["history"] = data["capacity"]["history"][-500:]
+
+    data["innovation"]["last_calculated"] = now
+
+    save(data)
+    print(f"  Capacity: {data['capacity']['current']:.1f}/{data['capacity']['max']:.1f}")
+    print(f"  Utilization: {utilization*100:.1f}%")
+    print(f"  Innovation: {data['innovation']['current']:.1f} (+{innovation_gain:.1f} this period)")
+
+    return data
+
+
+def status():
+    """Print current resource status."""
+    data = load()
+    if not data:
+        print("Resource tracker not initialized. Run --init first.")
+        return
+
+    print("\n=== Fleet Resources ===")
+    print(f"  Capacity: {data['capacity']['current']:.1f}/{data['capacity']['max']:.1f}")
+
+    utilization = 1.0 - (data["capacity"]["current"] / data["capacity"]["max"])
+    print(f"  Utilization: {utilization*100:.1f}%")
+
+    innovation_status = "GENERATING" if utilization < INNOVATION_THRESHOLD else "BLOCKED"
+    print(f"  Innovation: {data['innovation']['current']:.1f} [{innovation_status}]")
+
+    print(f"  Uptime: {data['uptime']['current_pct']:.1f}%")
+    print(f"  Milestones: {', '.join(str(m)+'%' for m in data['uptime']['milestones_reached']) or 'None yet'}")
+
+    # Phase gate checks
+    phase_2_ok = data['uptime']['current_pct'] >= 95.0
+    phase_3_ok = phase_2_ok and data['innovation']['current'] > 100
+    phase_5_ok = phase_2_ok and data['innovation']['current'] > 500
+
+    print(f"\n  Phase Gates:")
+    print(f"    Phase 2 (Automation): {'UNLOCKED' if phase_2_ok else 'LOCKED (need 95% uptime)'}")
+    print(f"    Phase 3 (Orchestration): {'UNLOCKED' if phase_3_ok else 'LOCKED (need 95% uptime + 100 innovation)'}")
+    print(f"    Phase 5 (Scale): {'UNLOCKED' if phase_5_ok else 'LOCKED (need 95% uptime + 500 innovation)'}")
+
+
+if __name__ == "__main__":
+    import sys
+    init()
+    if len(sys.argv) > 1 and sys.argv[1] == "status":
+        status()
+    elif len(sys.argv) > 1 and sys.argv[1] == "regen":
+        regenerate_resources()
+    else:
+        regenerate_resources()
+        status()