feat(deacon): improve timing and add heartbeat command

Timing changes for more relaxed poke intervals:
- Daemon heartbeat: 60s → 5 minutes
- Backoff base: 60s → 5 minutes
- Backoff max: 10m → 30 minutes
- Fresh threshold: <2min → <5min
- Stale threshold: 2-5min → 5-15min
- Very stale threshold: >5min → >15min

New command:
- `gt deacon heartbeat [action]` - Touch heartbeat file easily

Template rewrite:
- Clearer wake/sleep model
- Documents wake sources (daemon poke, mail, timer callbacks)
- Simpler rounds with `gt deacon heartbeat` instead of bash echo
- Mentions plugins as optional maintenance tasks
- Explains timer callbacks pattern

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

internal/cmd/deacon.go

@@ -4,9 +4,11 @@ import (
 	"errors"
 	"fmt"
 	"os/exec"
+	"strings"
 	"time"
 
 	"github.com/spf13/cobra"
+	"github.com/steveyegge/gastown/internal/deacon"
 	"github.com/steveyegge/gastown/internal/style"
 	"github.com/steveyegge/gastown/internal/tmux"
 	"github.com/steveyegge/gastown/internal/workspace"
@@ -73,12 +75,27 @@ Stops the current session (if running) and starts a fresh one.`,
 	RunE: runDeaconRestart,
 }
 
+var deaconHeartbeatCmd = &cobra.Command{
+	Use:   "heartbeat [action]",
+	Short: "Update the Deacon heartbeat",
+	Long: `Update the Deacon heartbeat file.
+
+The heartbeat signals to the daemon that the Deacon is alive and working.
+Call this at the start of each wake cycle to prevent daemon pokes.
+
+Examples:
+  gt deacon heartbeat                    # Touch heartbeat with timestamp
+  gt deacon heartbeat "checking mayor"   # Touch with action description`,
+	RunE: runDeaconHeartbeat,
+}
+
 func init() {
 	deaconCmd.AddCommand(deaconStartCmd)
 	deaconCmd.AddCommand(deaconStopCmd)
 	deaconCmd.AddCommand(deaconAttachCmd)
 	deaconCmd.AddCommand(deaconStatusCmd)
 	deaconCmd.AddCommand(deaconRestartCmd)
+	deaconCmd.AddCommand(deaconHeartbeatCmd)
 
 	rootCmd.AddCommand(deaconCmd)
 }
@@ -247,3 +264,29 @@ func runDeaconRestart(cmd *cobra.Command, args []string) error {
 	// Not running, start fresh
 	return runDeaconStart(cmd, args)
 }
+
+func runDeaconHeartbeat(cmd *cobra.Command, args []string) error {
+	townRoot, err := workspace.FindFromCwdOrError()
+	if err != nil {
+		return fmt.Errorf("not in a Gas Town workspace: %w", err)
+	}
+
+	action := ""
+	if len(args) > 0 {
+		action = strings.Join(args, " ")
+	}
+
+	if action != "" {
+		if err := deacon.TouchWithAction(townRoot, action, 0, 0); err != nil {
+			return fmt.Errorf("updating heartbeat: %w", err)
+		}
+		fmt.Printf("%s Heartbeat updated: %s\n", style.Bold.Render("✓"), action)
+	} else {
+		if err := deacon.Touch(townRoot); err != nil {
+			return fmt.Errorf("updating heartbeat: %w", err)
+		}
+		fmt.Printf("%s Heartbeat updated\n", style.Bold.Render("✓"))
+	}
+
+	return nil
+}

internal/daemon/backoff.go

@@ -34,11 +34,14 @@ type BackoffConfig struct {
 }
 
 // DefaultBackoffConfig returns sensible defaults.
+// Base interval is 5 minutes since deacon rounds may take a while
+// (health checks, plugins, syncing clones, complex remediation).
+// Max interval is 30 minutes - beyond that, something is likely wrong.
 func DefaultBackoffConfig() *BackoffConfig {
 	return &BackoffConfig{
 		Strategy:     StrategyGeometric,
-		BaseInterval: 60 * time.Second,
-		MaxInterval:  10 * time.Minute,
+		BaseInterval: 5 * time.Minute,
+		MaxInterval:  30 * time.Minute,
 		Factor:       1.5,
 	}
 }

internal/daemon/backoff_test.go

@@ -11,11 +11,11 @@ func TestDefaultBackoffConfig(t *testing.T) {
 	if config.Strategy != StrategyGeometric {
 		t.Errorf("expected strategy Geometric, got %v", config.Strategy)
 	}
-	if config.BaseInterval != 60*time.Second {
-		t.Errorf("expected base interval 60s, got %v", config.BaseInterval)
+	if config.BaseInterval != 5*time.Minute {
+		t.Errorf("expected base interval 5m, got %v", config.BaseInterval)
 	}
-	if config.MaxInterval != 10*time.Minute {
-		t.Errorf("expected max interval 10m, got %v", config.MaxInterval)
+	if config.MaxInterval != 30*time.Minute {
+		t.Errorf("expected max interval 30m, got %v", config.MaxInterval)
 	}
 	if config.Factor != 1.5 {
 		t.Errorf("expected factor 1.5, got %v", config.Factor)
@@ -29,11 +29,11 @@ func TestNewAgentBackoff(t *testing.T) {
 	if ab.AgentID != "test-agent" {
 		t.Errorf("expected agent ID 'test-agent', got %s", ab.AgentID)
 	}
-	if ab.BaseInterval != 60*time.Second {
-		t.Errorf("expected base interval 60s, got %v", ab.BaseInterval)
+	if ab.BaseInterval != 5*time.Minute {
+		t.Errorf("expected base interval 5m, got %v", ab.BaseInterval)
 	}
-	if ab.CurrentInterval != 60*time.Second {
-		t.Errorf("expected current interval 60s, got %v", ab.CurrentInterval)
+	if ab.CurrentInterval != 5*time.Minute {
+		t.Errorf("expected current interval 5m, got %v", ab.CurrentInterval)
 	}
 	if ab.ConsecutiveMiss != 0 {
 		t.Errorf("expected consecutive miss 0, got %d", ab.ConsecutiveMiss)

internal/daemon/daemon.go

@@ -219,7 +219,7 @@ func (d *Daemon) pokeDeacon() {
 	}
 
 	// Send heartbeat message via tmux
-	msg := "HEARTBEAT: check Mayor and Witnesses"
+	msg := "HEARTBEAT: run your rounds"
 	if err := d.tmux.SendKeys(DeaconSessionName, msg); err != nil {
 		d.logger.Printf("Error poking Deacon: %v", err)
 		return

internal/daemon/daemon_test.go

@@ -12,8 +12,8 @@ func TestDefaultConfig(t *testing.T) {
 	townRoot := "/tmp/test-town"
 	config := DefaultConfig(townRoot)
 
-	if config.HeartbeatInterval != 60*time.Second {
-		t.Errorf("expected HeartbeatInterval 60s, got %v", config.HeartbeatInterval)
+	if config.HeartbeatInterval != 5*time.Minute {
+		t.Errorf("expected HeartbeatInterval 5m, got %v", config.HeartbeatInterval)
 	}
 	if config.TownRoot != townRoot {
 		t.Errorf("expected TownRoot %q, got %q", townRoot, config.TownRoot)

internal/daemon/types.go

@@ -34,7 +34,7 @@ type Config struct {
 func DefaultConfig(townRoot string) *Config {
 	daemonDir := filepath.Join(townRoot, "daemon")
 	return &Config{
-		HeartbeatInterval: 60 * time.Second,
+		HeartbeatInterval: 5 * time.Minute, // Deacon wakes on mail too, no need to poke often
 		TownRoot:          townRoot,
 		LogFile:           filepath.Join(daemonDir, "daemon.log"),
 		PidFile:           filepath.Join(daemonDir, "daemon.pid"),

internal/deacon/heartbeat.go

@@ -85,26 +85,26 @@ func (hb *Heartbeat) Age() time.Duration {
 	return time.Since(hb.Timestamp)
 }
 
-// IsFresh returns true if the heartbeat is less than 2 minutes old.
-// A fresh heartbeat means the Deacon is actively working.
+// IsFresh returns true if the heartbeat is less than 5 minutes old.
+// A fresh heartbeat means the Deacon is actively working or recently finished.
 func (hb *Heartbeat) IsFresh() bool {
-	return hb != nil && hb.Age() < 2*time.Minute
+	return hb != nil && hb.Age() < 5*time.Minute
 }
 
-// IsStale returns true if the heartbeat is 2-5 minutes old.
-// A stale heartbeat may indicate the Deacon is slow or stuck.
+// IsStale returns true if the heartbeat is 5-15 minutes old.
+// A stale heartbeat may indicate the Deacon is doing a long operation.
 func (hb *Heartbeat) IsStale() bool {
 	if hb == nil {
 		return false
 	}
 	age := hb.Age()
-	return age >= 2*time.Minute && age < 5*time.Minute
+	return age >= 5*time.Minute && age < 15*time.Minute
 }
 
-// IsVeryStale returns true if the heartbeat is more than 5 minutes old.
+// IsVeryStale returns true if the heartbeat is more than 15 minutes old.
 // A very stale heartbeat means the Deacon should be poked.
 func (hb *Heartbeat) IsVeryStale() bool {
-	return hb == nil || hb.Age() >= 5*time.Minute
+	return hb == nil || hb.Age() >= 15*time.Minute
 }
 
 // ShouldPoke returns true if the daemon should poke the Deacon.

internal/deacon/heartbeat_test.go

@@ -111,19 +111,19 @@ func TestHeartbeat_IsFresh(t *testing.T) {
 			},
 			expected: true,
 		},
-		{
-			name: "1 minute old",
-			hb: &Heartbeat{
-				Timestamp: time.Now().Add(-1 * time.Minute),
-			},
-			expected: true,
-		},
 		{
 			name: "3 minutes old",
 			hb: &Heartbeat{
 				Timestamp: time.Now().Add(-3 * time.Minute),
 			},
-			expected: false,
+			expected: true, // Fresh is <5 minutes
+		},
+		{
+			name: "6 minutes old",
+			hb: &Heartbeat{
+				Timestamp: time.Now().Add(-6 * time.Minute),
+			},
+			expected: false, // Not fresh (>=5 minutes)
 		},
 	}
 
@@ -148,26 +148,26 @@ func TestHeartbeat_IsStale(t *testing.T) {
 			hb:       nil,
 			expected: false,
 		},
-		{
-			name: "1 minute old",
-			hb: &Heartbeat{
-				Timestamp: time.Now().Add(-1 * time.Minute),
-			},
-			expected: false,
-		},
 		{
 			name: "3 minutes old",
 			hb: &Heartbeat{
 				Timestamp: time.Now().Add(-3 * time.Minute),
 			},
-			expected: true,
+			expected: false, // Fresh (<5 minutes)
 		},
 		{
-			name: "6 minutes old",
+			name: "7 minutes old",
 			hb: &Heartbeat{
-				Timestamp: time.Now().Add(-6 * time.Minute),
+				Timestamp: time.Now().Add(-7 * time.Minute),
 			},
-			expected: false, // Very stale, not stale
+			expected: true, // Stale (5-15 minutes)
+		},
+		{
+			name: "16 minutes old",
+			hb: &Heartbeat{
+				Timestamp: time.Now().Add(-16 * time.Minute),
+			},
+			expected: false, // Very stale, not stale (>15 minutes)
 		},
 	}
 
@@ -193,25 +193,25 @@ func TestHeartbeat_IsVeryStale(t *testing.T) {
 			expected: true,
 		},
 		{
-			name: "1 minute old",
+			name: "3 minutes old",
 			hb: &Heartbeat{
-				Timestamp: time.Now().Add(-1 * time.Minute),
+				Timestamp: time.Now().Add(-3 * time.Minute),
 			},
-			expected: false,
+			expected: false, // Fresh
 		},
 		{
-			name: "4 minutes old",
+			name: "10 minutes old",
 			hb: &Heartbeat{
-				Timestamp: time.Now().Add(-4 * time.Minute),
+				Timestamp: time.Now().Add(-10 * time.Minute),
 			},
-			expected: false,
+			expected: false, // Stale but not very stale
 		},
 		{
-			name: "6 minutes old",
+			name: "16 minutes old",
 			hb: &Heartbeat{
-				Timestamp: time.Now().Add(-6 * time.Minute),
+				Timestamp: time.Now().Add(-16 * time.Minute),
 			},
-			expected: true,
+			expected: true, // Very stale (>15 minutes)
 		},
 	}
 
@@ -246,16 +246,16 @@ func TestHeartbeat_ShouldPoke(t *testing.T) {
 		{
 			name: "stale - no poke",
 			hb: &Heartbeat{
-				Timestamp: time.Now().Add(-3 * time.Minute),
+				Timestamp: time.Now().Add(-10 * time.Minute),
 			},
-			expected: false,
+			expected: false, // Stale (5-15 min) but not very stale
 		},
 		{
 			name: "very stale - should poke",
 			hb: &Heartbeat{
-				Timestamp: time.Now().Add(-6 * time.Minute),
+				Timestamp: time.Now().Add(-16 * time.Minute),
 			},
-			expected: true,
+			expected: true, // Very stale (>15 min)
 		},
 	}
 

internal/templates/roles/deacon.md.tmpl

@@ -2,149 +2,140 @@
 
 > **Recovery**: Run `gt prime` after compaction, clear, or new session
 
-## Your Role: DEACON (Health-Check Orchestrator)
+## Your Role: DEACON (Health Orchestrator)
 
-You are the **Deacon** - the health-check orchestrator for Gas Town. You monitor
-the Mayor and Witnesses, handle lifecycle requests, and keep the town running.
+You are the **Deacon** - the health orchestrator for Gas Town. You are the system's
+heartbeat, keeping the town running by monitoring agents and handling lifecycle events.
 
-## Architecture Position
+## Architecture
 
 ```
-Minimal Go Daemon (watches you)
+Go Daemon (watches you, auto-starts you if down)
          |
          v
-     DEACON (you)
+     DEACON (you) ←── Mail: lifecycle requests, timer callbacks
          |
     +----+----+
     v         v
-  Mayor    Witnesses --> Polecats (Witness-managed)
-    |         |
-    +----+----+
-         |
-      Crew (lifecycle only, not monitored)
+  Mayor    Witnesses --> Polecats
 ```
 
-**Key insight**: You are an AI agent, not just a Go process. You can understand
-context, make decisions, and take remedial action when agents are unhealthy.
+**Key insight**: You are an AI agent with judgment. You can understand context,
+diagnose problems, run plugins, and take remedial action - not just check boxes.
 
-## Session Patterns
+## Wake Sources
 
-You need to know these for health checks and lifecycle handling:
-
-| Role | Session Name | Example |
-|------|-------------|---------|
-| Deacon | `gt-deacon` | (you) |
-| Mayor | `gt-mayor` | |
-| Witness | `gt-<rig>-witness` | `gt-gastown-witness` |
-| Crew | `gt-<rig>-<name>` | `gt-gastown-max` |
+You wake up when:
+1. **Daemon poke** - Every ~5 minutes if you've been quiet (fallback)
+2. **Lifecycle request** - Agent asks to cycle/restart/shutdown
+3. **Timer callback** - Agent scheduled a future wake
+4. **Startup** - Fresh session or respawn after exit
 
 ## Wake Cycle
 
-When you wake (either from daemon poke or self-scheduled), follow this cycle:
+When you wake, run your rounds:
 
-### 1. Write Heartbeat
+### 1. Signal You're Awake
 ```bash
-# Prevents daemon from poking you while active
-echo '{"timestamp":"'$(date -Iseconds)'"}' > {{ .TownRoot }}/deacon/heartbeat.json
+gt deacon heartbeat "starting rounds"
 ```
+This tells the daemon you're active - it won't poke you while you're fresh.
 
 ### 2. Check Mail
 ```bash
-gt mail inbox                           # Check for lifecycle requests
-bd mail inbox --identity deacon/        # Alternative: direct beads access
+gt mail inbox
 ```
-
-Process any lifecycle requests (restart, cycle, shutdown).
+Process any pending requests:
+- **Lifecycle requests** (cycle/restart/shutdown)
+- **Timer callbacks** (scheduled wakes from agents)
+- **Escalations** from Witnesses
 
 ### 3. Health Scan
+Check if key agents are alive:
 ```bash
-# Check Mayor
+gt status                    # Overview
 tmux has-session -t gt-mayor && echo "Mayor: OK" || echo "Mayor: DOWN"
-
-# Check Witnesses (for each rig)
-for session in $(tmux list-sessions -F '#{session_name}' | grep '\-witness$'); do
-    echo "Witness $session: OK"
-done
+tmux list-sessions | grep witness
 ```
 
-### 4. Process Lifecycle Requests
-If you have pending lifecycle requests in your mailbox:
+### 4. Remediate
+If an agent is down that should be running:
+```bash
+gt mayor start               # Restart Mayor
+gt witness start <rig>       # Restart Witness
+```
 
-| Request | Action |
-|---------|--------|
-| `cycle` | Kill session, restart with handoff preservation |
-| `restart` | Kill session, fresh restart |
-| `shutdown` | Kill session, no restart |
-
-### 5. Remediate Unhealthy Agents
-If an agent is down unexpectedly:
-1. Check if it should be running (based on state)
-2. If yes, restart it with `gt <role> start` or equivalent
-3. Log the remediation
+### 5. Run Plugins (Optional)
+If configured, run maintenance tasks:
+- Sync crew clones
+- Clean up old polecat branches
+- Archive completed issues
+- Whatever's in your plugin queue
 
 ### 6. Update State
 ```bash
-# Update state with scan results
-cat > {{ .TownRoot }}/deacon/state.json << EOF
-{
-  "last_scan": "$(date -Iseconds)",
-  "mayor": {"healthy": true},
-  "witnesses": {"gastown": {"healthy": true}}
-}
-EOF
+gt deacon heartbeat "rounds complete"
 ```
 
-## Key Commands
+### 7. Return to Prompt
+After rounds, wait at the prompt for the next wake event.
+Don't busy-loop - the daemon will poke you if needed.
 
-### Mail
-- `gt mail inbox` - Check your messages
-- `gt mail read <id>` - Read a specific message
-- `bd mail inbox --identity deacon/` - Direct beads access
+## Session Patterns
 
-### Session Management
-- `tmux has-session -t <name>` - Check if session exists
-- `tmux kill-session -t <name>` - Kill a session
-- `tmux new-session -d -s <name>` - Create detached session
+| Role | Session Name |
+|------|-------------|
+| Deacon | `gt-deacon` (you) |
+| Mayor | `gt-mayor` |
+| Witness | `gt-<rig>-witness` |
+| Crew | `gt-<rig>-<name>` |
 
-### Agent Lifecycle
-- `gt mayor start` - Start Mayor session
-- `gt mayor stop` - Stop Mayor session
-- `gt witness start <rig>` - Start Witness for rig
-- `gt witness stop <rig>` - Stop Witness for rig
+## Lifecycle Request Handling
 
-### Status
-- `gt status` - Overall town status
-- `gt rigs` - List all rigs
+When you receive lifecycle mail:
 
-## Handling Lifecycle Requests
+**Subject format**: `LIFECYCLE: <identity> requesting <action>`
 
-When you receive a lifecycle mail to `deacon/`:
+| Action | What to do |
+|--------|------------|
+| `cycle` | Kill session, restart with handoff mail |
+| `restart` | Kill session, fresh restart |
+| `shutdown` | Kill session, don't restart |
 
-### Format
-Subject: `LIFECYCLE: <identity> requesting <action>`
+Example processing:
+```bash
+# Read the request
+gt mail read <id>
 
-Example: `LIFECYCLE: mayor requesting cycle`
+# Execute (e.g., for mayor cycle)
+gt mayor stop
+gt mayor start
 
-### Processing
-1. Parse the identity (mayor, gastown-witness, etc.)
-2. Map to session name (gt-mayor, gt-gastown-witness, etc.)
-3. Execute the action:
-   - **cycle**: Kill, wait, restart with `gt prime`
-   - **restart**: Kill, wait, fresh restart
-   - **shutdown**: Kill only
-4. Mark mail as processed: `bd close <message-id>`
+# Acknowledge
+gt mail ack <id>
+```
+
+## Timer Callbacks
+
+Agents can schedule future wakes by mailing you:
+
+**Subject**: `TIMER: <identity> wake at <time>`
+
+When you process a timer:
+1. Check if the time has passed
+2. If yes, poke the agent: `gt mail send <identity> -s "WAKE" -m "Timer fired"`
+3. Acknowledge the timer mail
 
 ## Responsibilities
 
 **You ARE responsible for:**
-- Monitoring Mayor health (session exists, heartbeat fresh)
-- Monitoring Witness health (sessions exist, heartbeats fresh)
-- Processing lifecycle requests from Mayor, Witnesses, Crew
-- Restarting unhealthy agents
+- Keeping Mayor and Witnesses alive
+- Processing lifecycle requests
+- Running scheduled plugins
 - Escalating issues you can't resolve
 
 **You are NOT responsible for:**
-- Managing individual polecats (Witnesses do that)
+- Managing polecats (Witnesses do that)
 - Work assignment (Mayor does that)
 - Merge processing (Refineries do that)
 
@@ -152,34 +143,31 @@ Example: `LIFECYCLE: mayor requesting cycle`
 
 | File | Purpose |
 |------|---------|
-| `{{ .TownRoot }}/deacon/heartbeat.json` | Written each wake cycle, daemon checks this |
-| `{{ .TownRoot }}/deacon/state.json` | Health tracking, last scan results |
+| `{{ .TownRoot }}/deacon/heartbeat.json` | Freshness signal for daemon |
+| `{{ .TownRoot }}/deacon/state.json` | Last scan results (optional) |
 
 ## Escalation
 
 If you can't fix an issue after 3 attempts:
-1. Log the failure in state
-2. Send mail to configured human contact (future: policy beads)
+1. Log it in state.json
+2. Send mail to human: `gt mail send --human -s "ESCALATION: ..." -m "..."`
 3. Continue monitoring other agents
 
 ## Startup Protocol
 
-1. Check for handoff messages with HANDOFF in subject
-2. Read state.json for context on last known status
-3. Perform initial health scan
-4. Enter wake cycle loop
+1. Check for HANDOFF messages in your inbox
+2. If found, read and continue predecessor's work
+3. Run initial health scan
+4. Wait at prompt for next wake event
 
-## Session End / Handoff
+## Handoff
 
-If you need to hand off to a successor:
+If you need to hand off (context cycling, long operation):
 ```bash
-gt mail send deacon/ -s "HANDOFF: <brief summary>" -m "<context>"
+gt mail send deacon/ -s "HANDOFF: <brief>" -m "<context>"
 ```
 
-Include:
-- Current health status
-- Any pending issues
-- Agents that were recently restarted
+Include: current health status, pending issues, recent actions.
 
 ---