Fix idle timer review issues

internal/app/timers.go

@@ -12,9 +12,9 @@ import (
 type pendingTimerKind string
 
 const (
-	timerKindDelay    pendingTimerKind = "delay"
-	timerKindIdleAny  pendingTimerKind = "idle_any"
-	timerKindIdleAll  pendingTimerKind = "idle_all"
+	timerKindDelay   pendingTimerKind = "delay"
+	timerKindIdleAny pendingTimerKind = "idle_any"
+	timerKindIdleAll pendingTimerKind = "idle_all"
 )
 
 const (
@@ -39,7 +39,7 @@ type pendingTimer struct {
 	kind    pendingTimerKind
 	status  string
 
-	watched    []string
+	watched      []string
 	idleBaseline map[string]bool // for idle_any: ids already idle at registration (excluded from satisfaction)
 
 	firesAt          time.Time
@@ -55,9 +55,9 @@ type pendingTimer struct {
 type timerManager struct {
 	sess *Session
 
-	mu      sync.Mutex
-	nextID  int
-	timers  map[string]*pendingTimer
+	mu     sync.Mutex
+	nextID int
+	timers map[string]*pendingTimer
 
 	// fireFn is the callback used to deliver the body to the owning
 	// process. Decoupled so tests can substitute a recorder. Defaults
@@ -134,6 +134,7 @@ func (m *timerManager) fireDelay(id string) {
 	t.status = timerStatusFired
 	owner := m.sess.FindChild(t.ownerID)
 	body, label := t.body, t.label
+	delete(m.timers, id)
 	m.mu.Unlock()
 	m.fireFn(owner, body, label)
 }
@@ -228,6 +229,7 @@ func (m *timerManager) fireIdleMaxWait(id string) {
 	t.status = timerStatusFired
 	owner := m.sess.FindChild(t.ownerID)
 	body, label := t.body, t.label
+	delete(m.timers, id)
 	m.mu.Unlock()
 	m.fireFn(owner, body, label)
 }
@@ -247,6 +249,7 @@ func (m *timerManager) onChildStateChanged(childID string, state IdleState) {
 		label string
 	}
 	var fires []firing
+	var firedIDs []string
 	for _, t := range m.timers {
 		if t.status != timerStatusPending {
 			continue
@@ -268,6 +271,7 @@ func (m *timerManager) onChildStateChanged(childID string, state IdleState) {
 				body:  t.body,
 				label: t.label,
 			})
+			firedIDs = append(firedIDs, t.id)
 		case timerKindIdleAll:
 			if m.allWatchedIdleLocked(t) {
 				t.status = timerStatusFired
@@ -279,9 +283,13 @@ func (m *timerManager) onChildStateChanged(childID string, state IdleState) {
 					body:  t.body,
 					label: t.label,
 				})
+				firedIDs = append(firedIDs, t.id)
 			}
 		}
 	}
+	for _, id := range firedIDs {
+		delete(m.timers, id)
+	}
 	m.mu.Unlock()
 	for _, f := range fires {
 		m.fireFn(f.owner, f.body, f.label)
@@ -327,6 +335,7 @@ func (m *timerManager) TimerCancel(ownerID, id string) error {
 		t.rt = nil
 	}
 	t.status = timerStatusCanceled
+	delete(m.timers, id)
 	return nil
 }
 
@@ -367,20 +376,29 @@ func (m *timerManager) TimerPause(ownerID, id string) error {
 // TimerResume re-arms a paused timer. For delay timers the remaining
 // duration is restored; idle-* timers re-attach to the state-change
 // watch list, and any remaining max-wait clock resumes.
+//
+// Idle-* timers also re-check their satisfaction condition immediately
+// on resume: idle transitions that occurred while paused are otherwise
+// missed (onChildStateChanged only sees future flips), so a child that
+// went idle during the pause window would never fire the timer. For
+// idle_any we look for any non-baseline watched child currently idle;
+// for idle_all we check whether every watched child is now idle.
 func (m *timerManager) TimerResume(ownerID, id string) error {
 	m.mu.Lock()
-	defer m.mu.Unlock()
 	t, ok := m.timers[id]
 	if !ok {
+		m.mu.Unlock()
 		return mcp.Errorf(mcp.ErrorKindNotFound, "no such timer %q", id)
 	}
 	// Empty ownerID = top-level orchestrator caller (e.g. a non-agent
 	// MCP client); allow it to manage every timer in the session.
 	// Otherwise the caller's own id must match the timer's owner.
 	if ownerID != "" && t.ownerID != ownerID {
+		m.mu.Unlock()
 		return mcp.Errorf(mcp.ErrorKindRoleForbidden, "timer %q is not owned by caller", id)
 	}
 	if t.status != timerStatusPaused {
+		m.mu.Unlock()
 		return mcp.Errorf(mcp.ErrorKindInvalidArgs, "timer %q is not paused", id)
 	}
 	t.status = timerStatusPending
@@ -397,6 +415,42 @@ func (m *timerManager) TimerResume(ownerID, id string) error {
 		t.pausedRemaining = 0
 		t.pausedWasMaxWait = false
 	}
+	// For idle-* timers, evaluate the condition right now in case a
+	// watched child went idle while paused.
+	var fireNow bool
+	var owner *Child
+	var body, label string
+	switch t.kind {
+	case timerKindIdleAny:
+		for _, wid := range t.watched {
+			if t.idleBaseline[wid] {
+				continue
+			}
+			c := m.sess.FindChild(wid)
+			if c != nil && isIdleState(c.IdleState()) {
+				fireNow = true
+				break
+			}
+		}
+	case timerKindIdleAll:
+		if m.allWatchedIdleLocked(t) {
+			fireNow = true
+		}
+	}
+	if fireNow {
+		t.status = timerStatusFired
+		if t.rt != nil {
+			t.rt.Stop()
+			t.rt = nil
+		}
+		owner = m.sess.FindChild(t.ownerID)
+		body, label = t.body, t.label
+		delete(m.timers, id)
+	}
+	m.mu.Unlock()
+	if fireNow {
+		m.fireFn(owner, body, label)
+	}
 	return nil
 }