errors at top of status are distracting

docs/operations.md

@@ -264,7 +264,7 @@ Every change broadcasts `admin.health`. A Claude `rejected` status still drives
 Agent health is `internal/agents/health.go`:
 
 - **Processes.** `agent_processes` lists every process byre is tracking (idle sessions keep theirs), with session, task, vendor, pid, the session's state, `last_event_at` (when the process last wrote any line to stdout, or when it started; `claude.Session.LastLine`) and `health`. `health` is `exited` when the stream has closed or `kill(pid, 0)` says the pid is gone, `stuck` when the session is `running` and nothing has arrived for `StuckAfter`, otherwise `ok`. The stream does mark long tool calls: while a tool runs, Claude Code sends a `tool_progress` line with `"heartbeat": true` every 30 seconds, so a long `go test` keeps `last_event_at` fresh and a silent stream means nothing is happening.
-- **Zombies.** `running_without_process`: a session marked `running` whose process byre isn't tracking or has `exited`. `process_without_session`: a `claude` child of the byre process (from `ps -A -o pid=,ppid=,comm=`) whose pid belongs to no tracked process, or a tracked process still alive for a `completed` session. A live process for an `idle` session is normal and not a zombie.
+- **Zombies.** `running_without_process`: a session marked `running` whose process byre isn't tracking or has `exited`. `process_without_session`: a `claude` child of the byre process (from `ps -A -o pid=,ppid=,comm=`) whose pid belongs to no tracked process, or a tracked process still alive for a `completed` session. A live process for an `idle` session is normal and not a zombie. While a session's process is starting (in `Manager.starting`, between its turn marking it `running` and its process being tracked), neither kind is reported: that session isn't a `running_without_process`, and no untracked `claude` child is a `process_without_session`, since the starting one can't be told apart from an orphan until it is tracked. A real orphan shows at the next check with nothing starting. `Manager.Health` reads the `running` sessions and the `claude` children first and the tracked and starting processes after them, so a start seen in either is already registered by then.
 - **Watching.** `Manager.Watch` recomputes health every `healthInterval`. When the set of problems (non-`ok` processes and zombies) changes, it logs each new one as `agent health problem` and broadcasts an unstored `admin.health` event (`seq` 0). Nothing is killed or repaired automatically.
 - **Protocol errors.** `internal/claude` reports a stdout line that isn't a JSON object, doesn't parse, or has a `type` outside `knownTypes` (the line is still passed on), and the manager adds lines whose content it fails to decode. `protocol_errors.counts` counts them per vendor since byre started; `recent` holds the last `keptBadLines`, newest first, each with session, time, reason, the raw line cut to `badLineBytes` and its full `size`. They live in memory only, and each one also broadcasts `admin.health`.
 

internal/agents/health.go

@@ -107,11 +107,26 @@ type procInfo struct {
 }
 
 func (m *Manager) Health(ctx context.Context) (Health, error) {
+	running, err := m.store.SessionsInState(ctx, api.AgentSessionStateRunning)
+	if err != nil {
+		return Health{}, err
+	}
+
+	children, err := claudeChildren(ctx, os.Getpid())
+	if err != nil {
+		return Health{}, err
+	}
+
+	// Snapshot live and starting after running and children, so a start that shows in either is already registered.
 	m.mu.Lock()
 	all := []*live{}
 	for _, l := range m.live {
 		all = append(all, l)
 	}
+	starting := map[string]bool{}
+	for id := range m.starting {
+		starting[id] = true
+	}
 	m.mu.Unlock()
 
 	procs := []procInfo{}
@@ -132,20 +147,10 @@ func (m *Manager) Health(ctx context.Context) (Health, error) {
 		})
 	}
 
-	running, err := m.store.SessionsInState(ctx, api.AgentSessionStateRunning)
-	if err != nil {
-		return Health{}, err
-	}
-
-	children, err := claudeChildren(ctx, os.Getpid())
-	if err != nil {
-		return Health{}, err
-	}
-
-	return assess(time.Now(), procs, running, children), nil
+	return assess(time.Now(), procs, running, children, starting), nil
 }
 
-func assess(now time.Time, procs []procInfo, running []api.AgentSession, children []int) Health {
+func assess(now time.Time, procs []procInfo, running []api.AgentSession, children []int, starting map[string]bool) Health {
 	slices.SortFunc(procs, func(a, b procInfo) int { return strings.Compare(a.sessionID, b.sessionID) })
 
 	h := Health{Processes: []api.AgentProcess{}, Zombies: []api.Zombie{}}
@@ -187,7 +192,7 @@ func assess(now time.Time, procs []procInfo, running []api.AgentSession, childre
 
 	for _, sess := range running {
 		p, ok := bySession[sess.Id]
-		if ok && !p.exited {
+		if (ok && !p.exited) || starting[sess.Id] {
 			continue
 		}
 		detail := "no agent process"
@@ -203,7 +208,7 @@ func assess(now time.Time, procs []procInfo, running []api.AgentSession, childre
 	}
 
 	for _, pid := range children {
-		if tracked[pid] {
+		if tracked[pid] || len(starting) > 0 {
 			continue
 		}
 		h.Zombies = append(h.Zombies, api.Zombie{