talon validate         # Parse/validate config + services files, print summary JSON
talon --check          # Single probe cycle, print results, exit
talon --status         # Current state machine position
talon --dry-run        # Print loaded config, exit
talon --worker-only    # Supervisor only, no infra probes
talon                  # Full daemon mode (worker + probes + escalation)

export PATH="$HOME/.cargo/bin:$PATH"
cd ~/Code/joelhooks/joelclaw/infra/talon
cargo build --release
cp target/release/talon ~/.local/bin/talon

talon (single binary)
├── Worker Supervisor Thread (only when external launchd supervisor is not loaded)
│   ├── Kill orphan on port 3111
│   ├── Spawn bun (child process)
│   ├── Signal forwarding (SIGTERM → bun)
│   ├── Health poll every 30s
│   ├── PUT sync after healthy startup
│   └── Crash recovery: exponential backoff 1s→30s
│
├── Infrastructure Probe Loop (main thread, 60s)
│   ├── Colima VM alive?
│   ├── Docker socket responding?
│   ├── Talos container running?
│   ├── k8s API reachable?
│   ├── Node Ready + schedulable?
│   ├── Flannel daemonset ready?
│   ├── Redis PONG?
│   ├── Inngest /health 200?
│   ├── Typesense /health ok?
│   └── Worker /api/inngest 200?
│
└── Escalation (on failure)
    ├── Tier 1a: bridge-heal (force-cycle Colima on localhost↔VM split-brain)
    ├── Tier 1b: k8s-reboot-heal.sh (300s timeout, RBAC drift guard, VM `br_netfilter` repair, warmup-aware post-Colima invariants including deployment readiness + ImagePullBackOff pod reset, then voice-agent stale cleanup + launchd kickstart via `infra/voice-agent/cleanup-stale.sh`)
    ├── Tier 2: pi agent (cloud model, 10min cooldown)
    ├── Tier 3: pi agent (Ollama local, network-down fallback)
    └── Tier 4: Telegram + iMessage SOS fan-out (15min critical threshold)

healthy → degraded (1 critical probe failure)
degraded → failed (3 consecutive failures)
failed → investigating (agent spawned)
investigating → healthy (probes pass again)
investigating → critical (agent failed to fix)
critical → sos (SOS sent via Telegram + iMessage)
any → healthy (all probes pass)

[launchd.gateway]
label = "com.joel.gateway"
critical = true
timeout_secs = 5

[http.gateway_slack]
url = "http://127.0.0.1:3018/health/slack"
critical = true
critical_after_consecutive_failures = 3
timeout_secs = 5

[launchd.voice_agent]
label = "com.joel.voice-agent"
critical = false
timeout_secs = 5

[script.gateway_telegram_409]
command = "test $(tail -20 /tmp/joelclaw/gateway.err 2>/dev/null | grep -c '409: Conflict') -lt 5"
critical = true
critical_after_consecutive_failures = 3
timeout_secs = 5

[script.colima_orphan_usernet]
command = "test $(pgrep -f 'limactl usernet' | wc -l) -le 2"
critical = true
critical_after_consecutive_failures = 2
timeout_secs = 5

[script.k8s_disk_pressure]
command = "! kubectl get nodes -o jsonpath='{.items[0].spec.taints}' 2>/dev/null | grep -q disk-pressure"
critical = true
critical_after_consecutive_failures = 1
timeout_secs = 10

launchctl print gui/$(id -u)/com.joel.talon | rg "state =|pid =|program =|last exit code ="

launchctl kickstart -k gui/$(id -u)/com.joel.talon

launchctl list com.joel.system-bus-worker

launchctl bootout gui/$(id -u) ~/Library/LaunchAgents/com.joel.k8s-reboot-heal.plist

# Validate config + service monitor files
talon validate | python3 -m json.tool

# Check what talon sees right now
talon --check | python3 -m json.tool

# Check state machine
talon --status | python3 -m json.tool

# Broken-pipe robustness smoke test (should exit 0)
talon --check | head -n 1 >/dev/null

# Check health endpoint payload
curl -sS http://127.0.0.1:9999/health | python3 -m json.tool

# Check talon's own logs
tail -20 ~/.local/state/talon/talon.log | python3 -m json.tool

# Check launchd
launchctl list | grep talon
tail -50 ~/.local/log/talon.err

# Manual probe test
DOCKER_HOST=unix:///Users/joel/.colima/default/docker.sock docker inspect --format '{{.State.Status}}' joelclaw-controlplane-1
kubectl exec -n joelclaw redis-0 -- redis-cli ping
kubectl auth can-i --as=apiserver-kubelet-client get nodes --subresource=proxy --all-namespaces
kubectl auth can-i --as=apiserver-kubelet-client create nodes --subresource=proxy --all-namespaces
ssh -F ~/.colima/_lima/colima/ssh.config lima-colima 'curl -sS http://127.0.0.1:8288/health'

# Force bridge repair (same behavior Talon uses for split-brain)
colima stop --force && colima start

# Manual voice-agent stale cleanup (same post-gate step k8s-reboot-heal runs)
~/Code/joelhooks/joelclaw/infra/voice-agent/cleanup-stale.sh

nestedVirtualization ON + heavy Docker build
  → Colima VZ VM crash (silent, no crash report)
    → Docker daemon restart → Talos container killed
      → Redis mid-write → AOF corruption → crash-loop
      → Restate mid-journal → stale invocations → infinite retries
      → Lima socket forwarding broken → docker CLI dead on macOS