controller: fix-3 dead-app alerting + fix-6 ring cap/spill/spam (WIP, pre-build)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017CDMFpFx84pfviCTVuGGhf

controller/internal/stacks/downstate_test.go

@@ -0,0 +1,23 @@
+package stacks
+
+import "testing"
+
+// fix-3: only stopped/exited count as "down" for a deployed app. starting/unhealthy (running),
+// restarting/deploying (transient), paused (deliberate), unknown (ambiguous) must NOT alert.
+func TestIsDownState(t *testing.T) {
+	down := []ContainerState{StateStopped, StateExited}
+	for _, s := range down {
+		if !IsDownState(s) {
+			t.Errorf("IsDownState(%q) = false, want true", s)
+		}
+	}
+	notDown := []ContainerState{
+		StateRunning, StateStarting, StateUnhealthy, StateRestarting,
+		StateDeploying, StatePaused, StateUnknown, StateNotDeployed, StateOrphaned,
+	}
+	for _, s := range notDown {
+		if IsDownState(s) {
+			t.Errorf("IsDownState(%q) = true, want false (must not manufacture a dead-app alert)", s)
+		}
+	}
+}

controller/internal/stacks/manager.go

@@ -37,6 +37,16 @@ const (
 	StateOrphaned    ContainerState = "orphaned"
 )
 
+// IsDownState reports whether a container state means a DEPLOYED app is not running and won't recover
+// on its own (fix-3, CAMPAIGN-3). Only `stopped` and `exited` qualify — a Docker "created"/"dead"
+// container (a failed-at-boot app, the F11 case) resolves to `stopped`. Deliberately NOT `starting`
+// / `unhealthy` (running, with their own health handling), `restarting` (self-recovering),
+// `deploying` (mid-deploy), `paused` (a deliberate user action), or `unknown` (ambiguous — fail-open,
+// never manufacture a dead-app alert from an inconclusive read).
+func IsDownState(s ContainerState) bool {
+	return s == StateStopped || s == StateExited
+}
+
 // ContainerInfo holds status info about a single container within a stack.
 type ContainerInfo struct {
 	Name   string         `json:"name"`
@@ -444,9 +454,10 @@ func (m *Manager) refreshStatusLocked() error {
 		totalContainers++
 	}
 
-	if m.isDebug() {
-		m.logger.Printf("[DEBUG] [stacks] refreshStatusLocked: docker ps returned %d containers across %d projects", totalContainers, len(projectContainers))
-	}
+	// fix-6: refreshStatusLocked runs every 10s (the status-refresh job) — its per-cycle enumeration
+	// lines are TRACE (dropped from the debug ring) so they don't eat the post-incident window. A real
+	// state change is logged elsewhere at INFO; a docker error returns up the stack.
+	m.logger.Printf("[TRACE] [stacks] refreshStatusLocked: docker ps returned %d containers across %d projects", totalContainers, len(projectContainers))
 
 	m.logger.Printf("[INFO] [stacks] Status refresh: %d containers across %d stacks", totalContainers, len(m.stacks))
 
@@ -473,7 +484,7 @@ func (m *Manager) refreshStatusLocked() error {
 		}
 
 		if m.isDebug() {
-			m.logger.Printf("[DEBUG] [stacks] refreshStatusLocked: stack %q → state=%s containers=%d", name, stack.State, len(stack.Containers))
+			m.logger.Printf("[TRACE] [stacks] refreshStatusLocked: stack %q → state=%s containers=%d", name, stack.State, len(stack.Containers))
 		}
 
 		stack.LastUpdated = time.Now()