new summary after merge

docs/operations.md

@@ -150,7 +150,7 @@ Every session gets byre's guidance (`guidance` in `internal/agents/guidance.go`)
 
 A turn whose final message asks the human something in prose is bounced once (`takeBounce` in `internal/agents/guidance.go`): if `ask_human` wasn't called during the turn and the final message has a sentence ending in `?` outside code spans, code blocks, quotes and blockquotes, the agent is told to ask through `ask_human` and carries on. For Claude this is a Stop hook (`bounceProseQuestion`) that blocks the stop; Claude Code reports the block as a "Stop hook error" notification, which is expected. For Codex, byre doesn't end its turn on `turn/completed`: it records the nudge as a `byre` `user.message` with `mid_turn: true` and starts another Codex turn with it, and only that turn's end ends byre's turn. The per-turn flags reset when the next user message is sent. An agent told explicitly to ask in plain text will refuse the bounce.
 
-A turn's final message is its summary, and it lives only in the transcript: nothing is filed in the inbox, so the human reads it once. When a task turn ends normally (not an error, not interrupted, not a handoff) with non-empty `result` text and didn't call `ask_human`, its `turn.ended` event carries `summary: true`. That flag drives the lead's "finished a turn" signal and the "Turn summaries" notification (see "Lead agent" and "Notifications"). A turn that asked a question has no summary, since the final message comes after the question it explains; the guidance tells agents to put everything the human needs in the question's context. There is no report tool: models write a closing recap whatever they are told, so byre uses it rather than asking for a second one.
+A turn's final message is its summary, and it lives only in the transcript: nothing is filed in the inbox, so the human reads it once. When a task turn ends normally (not an error, not interrupted, not a handoff) with non-empty `result` text, didn't call `ask_human`, and isn't a Merge turn or discard turn (the task closes right after one, so its final message is never left to read), its `turn.ended` event carries `summary: true`. A Merge turn that called `stop_merge` keeps the task open and does carry it. That flag drives the lead's "finished a turn" signal and the "Turn summaries" notification (see "Lead agent" and "Notifications"). A turn that asked a question has no summary, since the final message comes after the question it explains; the guidance tells agents to put everything the human needs in the question's context. There is no report tool: models write a closing recap whatever they are told, so byre uses it rather than asking for a second one.
 
 Every turn starts as soon as it is sent; byre doesn't cap how many run at once. Whether a turn resumes the Claude conversation is decided by whether the session has ever sent one.
 

internal/agents/manager.go

@@ -842,12 +842,6 @@ func (m *Manager) turnEnded(ctx context.Context, l *live, res endResult) error {
 	if sha != "" {
 		payload["commit"] = sha
 	}
-	switch {
-	case handoff:
-		payload["handoff"] = true
-	case finished && !compacting && !asked:
-		payload["summary"] = true
-	}
 	discard, err := m.store.GetDiscard(ctx, l.taskID)
 	if err != nil {
 		return err
@@ -861,6 +855,12 @@ func (m *Manager) turnEnded(ctx context.Context, l *live, res endResult) error {
 	}
 	snapshot := discard.State == store.DiscardNone
 	review := snapshot && mergingBy == ""
+	switch {
+	case handoff:
+		payload["handoff"] = true
+	case finished && !compacting && !asked && review:
+		payload["summary"] = true
+	}
 	go m.closeMergedSubtasks(l.taskID, l.dir)
 	if payload["summary"] == true && snapshot {
 		go m.reportToParent(l.taskID, res.result)