Merge: keeper-mjxpe1ku - Add ensure semantics to witness/refinery start

internal/cmd/witness.go

@@ -284,7 +284,8 @@ func witnessSessionName(rigName string) string {
 }
 
 // ensureWitnessSession creates a witness tmux session if it doesn't exist.
-// Returns true if a new session was created, false if it already existed.
+// Returns true if a new session was created, false if it already existed (and is healthy).
+// Implements 'ensure' semantics: if session exists but Claude is dead (zombie), kills and recreates.
 func ensureWitnessSession(rigName string, r *rig.Rig) (bool, error) {
 	t := tmux.NewTmux()
 	sessionName := witnessSessionName(rigName)
@@ -296,8 +297,17 @@ func ensureWitnessSession(rigName string, r *rig.Rig) (bool, error) {
 	}
 
 	if running {
+		// Session exists - check if Claude is actually running (healthy vs zombie)
+		if t.IsClaudeRunning(sessionName) {
+			// Healthy - Claude is running
 			return false, nil
 		}
+		// Zombie - tmux alive but Claude dead. Kill and recreate.
+		fmt.Printf("%s Detected zombie session (tmux alive, Claude dead). Recreating...\n", style.Dim.Render("⚠"))
+		if err := t.KillSession(sessionName); err != nil {
+			return false, fmt.Errorf("killing zombie session: %w", err)
+		}
+	}
 
 	// Working directory is the witness's rig clone (if it exists) or witness dir
 	// This ensures gt prime detects the Witness role correctly

internal/refinery/manager.go

@@ -137,8 +137,17 @@ func (m *Manager) Start(foreground bool) error {
 	// Background mode: check if session already exists
 	running, _ := t.HasSession(sessionID)
 	if running {
+		// Session exists - check if Claude is actually running (healthy vs zombie)
+		if t.IsClaudeRunning(sessionID) {
+			// Healthy - Claude is running
 			return ErrAlreadyRunning
 		}
+		// Zombie - tmux alive but Claude dead. Kill and recreate.
+		fmt.Fprintln(m.output, "⚠ Detected zombie session (tmux alive, Claude dead). Recreating...")
+		if err := t.KillSession(sessionID); err != nil {
+			return fmt.Errorf("killing zombie session: %w", err)
+		}
+	}
 
 	// Also check via PID for backwards compatibility
 	if ref.State == StateRunning && ref.PID > 0 && util.ProcessExists(ref.PID) {