feat(planner): finding 当场唤醒 + planner N 秒心跳触发(任务参数,默认5min)

触发机制补两条(见 docs/planner-trigger-impl-plan.md)：

1) finding 当场唤醒：worker 飞行中 report_finding 落库即唤醒本任务 planner，
   不再等 worker 整趟收工才反应。
   - worker.Execute 加 notify 入参并 SetNotify(补上 worker toolset 之前缺失的接线)
   - addFinding 写 KindFinding 成功后调 notify(只对 finding,不对 fact)
   - engine 两处 worker.Execute 调用传 t.Notify

2) planner N 秒心跳：距上轮规划结束/任务开始满 N 秒且期间无触发 → 触发一轮，
   兜底卡死 + 唤醒去监督飞行中的 worker(steer/kill) + 周期复查。
   - plannerLoop 重构为 runRound 闭包 + 三臂 select(ctx/notify/heartbeat)
   - 心跳在 loop 入口臂 = 从任务 start 计时(覆盖 seed 跳过首轮)，每轮结束重臂
   - 新增任务参数 plan_heartbeat_seconds，下限=默认=300(5min),低于自动抬到300
   - DB 迁移：schema.sql 加列 + ALTER ADD COLUMN IF NOT EXISTS 补旧库
   - 全链路接线：db.CreateTask/manager/server HTTP/orchestration spawn_task
   - 前端：api.createTask 传参 + 建任务表单新增"planner 心跳(分钟)"字段

agent/tools.go

@@ -647,6 +647,9 @@ func (t *ToolSet) addFinding() actool.CoreTool {
 					_ = t.ts.Link(intent, db.RelYields, id) // chain: intent -> finding
 				}
 				_, _ = t.ts.AddStandaloneFinding(t.taskID, id, a.VulnClass, a.Severity, a.Summary, a.Evidence, t.worker, anchors)
+				if t.notify != nil {
+					t.notify() // 确证漏洞落库 → 当场唤醒本任务 planner（不等 worker 收工，debounce 合并）
+				}
 			} else {
 				// conversation context: no exploration store available, cannot record finding
 				return actool.Errorf("report_finding 需要任务上下文（exploration store 未初始化）"), nil

agent/worker.go

@@ -234,11 +234,13 @@ func renderWorkerGraphOverview(data map[string]any) string {
 
 // Execute runs one intent. hooks (the per-task Guard) gates every tool call; may
 // be nil. emit, if non-nil, receives one ActivityRecord per execution step.
+// notify, if non-nil, is called when this worker writes a finding (report_finding)
+// so the task's planner wakes mid-flight instead of waiting for the worker to finish.
 // Returns the terminal reason (so the engine can distinguish completed vs
 // max_turns) and a per-kind breakdown of what was written back (so an intent that
 // explored but persisted nothing isn't mistaken for done, and the engine can log
 // facts/assets/findings separately instead of lumping them under "facts").
-func (w *Worker) Execute(ctx context.Context, name string, taskID int64, as *db.AssetStore, ts *db.ExplorationStore, intent *db.Node, hooks harness.HookRunner, emit func(db.Activity), enr EnrichTrigger) (harness.TerminalReason, WriteCounts, error) {
+func (w *Worker) Execute(ctx context.Context, name string, taskID int64, as *db.AssetStore, ts *db.ExplorationStore, intent *db.Node, hooks harness.HookRunner, emit func(db.Activity), enr EnrichTrigger, notify func()) (harness.TerminalReason, WriteCounts, error) {
 	tsx := NewToolSet(ts, name)
 	tsx.SetTaskID(taskID)
 	if as != nil {
@@ -246,6 +248,7 @@ func (w *Worker) Execute(ctx context.Context, name string, taskID int64, as *db.
 	}
 	tsx.SetOwnerNode(intent.ID) // assets this worker discovers anchor to its intent → visible to the task
 	tsx.SetEnrich(enr)          // async DNS/HTTP auto-completion for assets this worker writes
+	tsx.SetNotify(notify)       // finding 写回时当场唤醒本任务 planner（report_finding 触发）
 	// base = built-in worker tools ∪ host tools (traffic) ∪ default tools (incl. Bash);
 	// then augment with the agent's visible skills/MCP. During the SDK settlement
 	// phase, Bash is hidden via Settlement.DisabledTools (no local gating needed).