internal/runmgr/subagent_n2_test.go

@@ -138,3 +138,72 @@ func TestSpawnBackgroundRecordsDetach(t *testing.T) {
 	}
 }
 
+
+// N3 WP1：done.json 语义分流——优雅停机写的 interrupted 不挡续跑（一次且仅一次）；
+// completed 终态挡续跑。
+func TestResumeAfterGracefulInterruptMarker(t *testing.T) {
+	runner := &gateRunner{parts: []core.Part{{Type: core.PartText, Text: "续跑结果"}}}
+	c, st := newSpawnEnv(t, runner)
+	c.mgr.runner = noopRunner{}
+	ws := t.TempDir()
+	c.mgr.SetWorkspaceRoot(ws)
+	parentRun := c.run
+	if err := st.CreateRun(&parentRun); err != nil {
+		t.Fatal(err)
+	}
+	child := core.Run{
+		ID: store.NewID("run"), ParentRunID: c.run.ID, ConversationID: c.run.ConversationID,
+		ProjectID: c.run.ProjectID, Owner: c.run.Owner, Kind: core.RunSubagent, ProfileID: c.run.ProfileID,
+		Status: core.RunRunning, CreatedAt: time.Now().UTC(),
+	}
+	if err := st.CreateRun(&child); err != nil {
+		t.Fatal(err)
+	}
+	c.mgr.writeSubagentRequest(child, "agent.sub.explore", "检索", "原始任务", "原始提示", true)
+	// 模拟优雅停机：partial 转录 + done.json{status:"interrupted"}。
+	c.mgr.writeSubagentTranscript(child, []core.Part{{Type: core.PartText, Text: "半截现场"}}, "interrupted")
+	if _, err := st.SealInterrupted(child.ID); err != nil {
+		t.Fatal(err)
+	}
+	before, _ := st.SubagentRunIDs(c.run.ConversationID)
+	c.mgr.ResumeInterruptedChildren()
+	ids, _ := st.SubagentRunIDs(c.run.ConversationID)
+	if len(ids) != len(before)+1 {
+		t.Fatalf("优雅停机现场应被续跑一次：before=%v after=%v", before, ids)
+	}
+	c.mgr.ResumeInterruptedChildren()
+	ids2, _ := st.SubagentRunIDs(c.run.ConversationID)
+	if len(ids2) != len(ids) {
+		t.Fatalf("重复续跑：%v → %v", ids, ids2)
+	}
+}
+
+func TestResumeSkipsCompletedMarker(t *testing.T) {
+	c, st := newSpawnEnv(t, &gateRunner{})
+	c.mgr.runner = noopRunner{}
+	ws := t.TempDir()
+	c.mgr.SetWorkspaceRoot(ws)
+	parentRun := c.run
+	if err := st.CreateRun(&parentRun); err != nil {
+		t.Fatal(err)
+	}
+	child := core.Run{
+		ID: store.NewID("run"), ParentRunID: c.run.ID, ConversationID: c.run.ConversationID,
+		ProjectID: c.run.ProjectID, Owner: c.run.Owner, Kind: core.RunSubagent, ProfileID: c.run.ProfileID,
+		Status: core.RunRunning, CreatedAt: time.Now().UTC(),
+	}
+	if err := st.CreateRun(&child); err != nil {
+		t.Fatal(err)
+	}
+	c.mgr.writeSubagentRequest(child, "agent.sub.explore", "检索", "原始任务", "", true)
+	c.mgr.writeSubagentTranscript(child, []core.Part{{Type: core.PartText, Text: "已完成"}}, "completed")
+	if _, err := st.SealInterrupted(child.ID); err != nil {
+		t.Fatal(err)
+	}
+	before, _ := st.SubagentRunIDs(c.run.ConversationID)
+	c.mgr.ResumeInterruptedChildren()
+	ids, _ := st.SubagentRunIDs(c.run.ConversationID)
+	if len(ids) != len(before) {
+		t.Fatalf("completed 终态不得续跑：before=%v after=%v", before, ids)
+	}
+}

internal/runmgr/subagent_transcript.go

@@ -86,6 +86,22 @@ func (m *Manager) writeSubagentTranscript(run core.Run, parts []core.Part, statu
 	}
 }
 
+// doneStatus 读 done.json 的 status（无文件或不可读按 "interrupted" 处理——
+// 缺标记本身就是中断现场）。
+func doneStatus(dir string) string {
+	body, err := os.ReadFile(filepath.Join(dir, "done.json"))
+	if err != nil {
+		return "interrupted"
+	}
+	var done struct {
+		Status string `json:"status"`
+	}
+	if json.Unmarshal(body, &done) != nil || done.Status == "" {
+		return "interrupted"
+	}
+	return done.Status
+}
+
 // readSubagentRequest 读 request.json（无文件返回 nil, nil）。
 func readSubagentRequest(dir string) (*subagentRequest, error) {
 	body, err := os.ReadFile(filepath.Join(dir, "request.json"))
@@ -116,7 +132,9 @@ func (m *Manager) ResumeInterruptedChildren() {
 		if dir == "" {
 			continue
 		}
-		if fileExists(filepath.Join(dir, "done.json")) || fileExists(filepath.Join(dir, "resumed.json")) {
+		// done.json 语义分流（N3 WP1）：终态（completed/failed/cancelled）挡续跑；
+		// interrupted 不挡——优雅停机与崩溃都是可续跑现场。
+		if doneStatus(dir) != "interrupted" || fileExists(filepath.Join(dir, "resumed.json")) {
 			continue
 		}
 		req, err := readSubagentRequest(dir)

internal/runtime/llm_test.go

@@ -784,7 +784,8 @@ func TestLLMRunnerForgedToolMarkerTriggersGuard(t *testing.T) {
 	if calls != 2 {
 		t.Fatalf("stream calls = %d, want 2", calls)
 	}
-	var placeholder bool
+	// N6（N3 WP1）：伪造正文不得作为 assistant 的话术回放；更正以 user
+	// 消息出现（不再改写 assistant）。
 	for _, m := range replay {
 		if m.Role != agentllm.RoleAssistant {
 			continue
@@ -792,12 +793,15 @@ func TestLLMRunnerForgedToolMarkerTriggersGuard(t *testing.T) {
 		if strings.Contains(m.Content, "run_python") {
 			t.Fatalf("forged body was replayed: %q", m.Content)
 		}
-		if strings.Contains(m.Content, "已作废") {
-			placeholder = true
+	}
+	var correction bool
+	for _, m := range replay {
+		if m.Role == agentllm.RoleUser && strings.Contains(m.Content, "已作废") {
+			correction = true
 		}
 	}
-	if !placeholder {
-		t.Fatalf("correction replay missing placeholder, got %#v", replay)
+	if !correction {
+		t.Fatalf("correction replay missing user note, got %#v", replay)
 	}
 	texts := textParts(rc.assistant)
 	if len(texts) != 2 || !texts[0].Process || texts[1].Process {