feat: 旧任务继续会话——终端任务带新消息 + 全部选项同一会话续跑

server：POST /tasks/{id}/continue（终端非 merged 任务重排队，
resume_message 列存本轮消息，不传选项沿用原值，plan/goal 冲突
与新建一致，goal_mode=1 时转新 goal 语义；CAS 防并发改状态，
审计 task_continued）；tasks.resume_message 三处迁移 + PG 建表。
worker：认领后本轮 prompt 换成续跑消息（只换内存副本），
goal 续跑走 goal-resume 而不是 goal，跑完清 resume_message
（进程被杀时不清，下次认领重跑同一条消息）。
host：goal-resume --goal-text（旧任务接续 goal 模式：跳过状态
与记录守卫，旧线程上从第 1 轮开新目标循环，新语义不限轮次；
无线程时拒绝）。
sandbox：Local/Docker goal_resume_task + popen goal-resume kind；
附带 popen goal 命令改成新语义（无验收不传 --verify，轮次 0
原样传，此前 goal 任务到本地 worker 会直接报错）。
console：详情页终端非 merged 任务出继续会话表单（消息 +
模型/强度/权限/计划/goal，模型下拉复用中转列表）。
测试：新增 test_task_continue.py 11 个 + test_host_continue.py 2 个。

cloud/worker.py

@@ -247,6 +247,8 @@ def _task_from_row(row):
         "forked_from": _col("forked_from"),
         # 环境：老行缺列时 None = 不指定环境，走项目仓库路径。
         "environment_id": _col("environment_id"),
+        # 续跑消息：老行缺列时 None = 没有待续跑消息。
+        "resume_message": _col("resume_message"),
     }
 
 
@@ -580,7 +582,8 @@ class Worker:
                 "approval": "TEXT",
                 "plan": "INTEGER",
                 "forked_from": "TEXT",
-                "environment_id": "TEXT"}.items():
+                "environment_id": "TEXT",
+                "resume_message": "TEXT"}.items():
             if name not in cols:
                 try:
                     conn.execute(
@@ -1018,7 +1021,7 @@ class Worker:
                     "host_status": None}
         fake = SimpleNamespace(returncode=proc.returncode,
                                stdout=out or "", stderr=err or "")
-        if kind == "goal" and hasattr(
+        if kind in ("goal", "goal-resume") and hasattr(
                 self.executor, "_goal_result_from_runner"):
             return self.executor._goal_result_from_runner(task_id, fake)
         if hasattr(self.executor, "_result_from_runner"):
@@ -1634,8 +1637,14 @@ class Worker:
                     effective_docker_timeout = self.task_timeout
         try:
             if self._use_popen():
+                if goal_mode and task.get("_resume"):
+                    popen_kind = "goal-resume"
+                elif goal_mode:
+                    popen_kind = "goal"
+                else:
+                    popen_kind = "dispatch"
                 result = self._execute_via_process(
-                    task, kind="goal" if goal_mode else "dispatch",
+                    task, kind=popen_kind,
                     deadline_seconds=self.task_timeout,
                     seed_host_dir=seed_host_dir)
                 combined = (result.get("stdout", "") or "") + \
@@ -1663,12 +1672,20 @@ class Worker:
                                  "stderr": ""},
                                 prep_err)
                     if goal_mode:
-                        result = self.executor.goal_task(
-                            task, timeout=effective_docker_timeout,
-                            extra_mounts=tenant_mounts,
-                            network=tenant_network,
-                            extra_env=proxy_env,
-                            seed_host_dir=seed_host_dir)
+                        if task.get("_resume"):
+                            result = self.executor.goal_resume_task(
+                                task, task["prompt"],
+                                timeout=effective_docker_timeout,
+                                extra_mounts=tenant_mounts,
+                                network=tenant_network,
+                                extra_env=proxy_env)
+                        else:
+                            result = self.executor.goal_task(
+                                task, timeout=effective_docker_timeout,
+                                extra_mounts=tenant_mounts,
+                                network=tenant_network,
+                                extra_env=proxy_env,
+                                seed_host_dir=seed_host_dir)
                     else:
                         result = self.executor.dispatch_task(
                             task, timeout=effective_docker_timeout,
@@ -1836,6 +1853,15 @@ class Worker:
             return {"dispatched": False, "reason": "already_claimed",
                     "task_id": task_id}
         task = self.get_task(task_id) or task
+        # 续跑消息：旧任务继续会话时本轮要说的话——本轮 prompt 换
+        # 成它（只换内存里的副本，原 prompt 不动）；_resume 标记
+        # 让 _run_attempt 在 goal 模式下走 goal-resume 而不是 goal
+        # （goal 会撞已存在，只有 goal-resume 能在旧线程上开新循环）。
+        resume_message = task.get("resume_message")
+        if resume_message:
+            task = dict(task)
+            task["prompt"] = resume_message
+            task["_resume"] = True
         self._audit(task["project_id"], "worker_claim",
                     "%s executor=%s" % (task_id, self._executor_name()))
         # log_event 只接受 task_id/project_id/status/message 四个
@@ -2153,6 +2179,21 @@ class Worker:
             # 补一条 worker_completed/failed 审计误导排查。
             final = "interrupted"
             self._audit(task["project_id"], "worker_interrupted", task_id)
+        if resume_message:
+            # 本轮已跑完（无论成败）：续跑消息已消费，清掉；进程
+            # 中途被杀时清不到，下次认领会重跑同一条消息——可接受
+            # 的续跑语义，不会静默丢消息。清失败不挡结果返回。
+            try:
+                conn = _db_connect(self.db_path)
+                try:
+                    conn.execute(
+                        "UPDATE tasks SET resume_message = NULL"
+                        " WHERE id = ?", (task_id,))
+                    conn.commit()
+                finally:
+                    conn.close()
+            except Exception:
+                pass
         return {"dispatched": True, "task_id": task_id,
                 "host_name": self.executor._host_name(task)
                 if hasattr(self.executor, "_host_name") else task_id,