Docker sandbox real test + cloud merge status endpoint

- DockerExecutor: extra mounts (host.py work/state, repo, codex-home
  at same paths), worker --docker-extra-mounts, container user
  configurable; Dockerfile copies codex-resources beside the codex
  binary and puts bwrap on PATH (previous /usr/local/lib layout
  made codex report bubblewrap unavailable inside the container).
- Real Docker task on external host: triple added in ~18s, merged
  inside a container, main repo now add+mul2+triple, --rm cleanup.
  Honest boundary: this host/kernel forbids unprivileged user
  namespaces, so bwrap fails on host and in containers; production
  mode here is Docker isolation + inner danger-full-access, not
  double sandboxing.
- Cloud merge status: POST /tasks/{id}/merge syncs status only
  (merge itself stays with host.py merge); completed -> merged,
  maintainer+ (approve_merge), other states and repeat calls 409,
  audit merge_task. Tests: cloud 223, host 27, all passing.

cloud/worker.py

@@ -48,6 +48,12 @@ interrupted，不用执行结果覆盖它。
 
 可注入：runner（假 CLI，见 sandbox.LocalExecutor）与 env 映射
 均可注入，单测不跑真实模型回合、不联网、不登录任何服务。
+
+执行器选择：Worker 默认用 LocalExecutor；传入 DockerExecutor
+（或 CLI --executor docker）时，派发走容器内 host.py，取消时
+按任务派生的容器名 docker kill，不只改数据库状态；本机无
+docker 时 DockerExecutor 在调 runner 前就明确报错，任务标
+failed 且 error_text 含 docker 缺失，绝不静默降级为本地执行。
 """
 
 import argparse
@@ -66,7 +72,7 @@ from cloud.db import connect as _db_connect
 from cloud.logging_config import get_logger, log_event, setup_logging
 from cloud.models import ModelRouter, is_fallbackable, record_fallback
 from cloud.queue import budget_exceeded, ready_tasks
-from cloud.sandbox import LocalExecutor
+from cloud.sandbox import DockerExecutor, LocalExecutor
 from cloud.sandbox import _default_runner as _sandbox_default_runner
 
 # 与 server.TERMINAL_STATUSES 对齐：这些状态的任务不再被认领或取消。
@@ -189,6 +195,7 @@ class Worker:
         self.process_factory = process_factory
         self._running_proc = None
         self._running_task_id = None
+        self._running_container = None
         self._loop_stop = False
         self.logger = get_logger("cloud.worker")
 
@@ -419,6 +426,18 @@ class Worker:
                 pass
             self._running_proc = None
             self._running_task_id = None
+        # Docker 取消：按任务派生的容器名真杀，不只改数据库状态。
+        # 同步路径（runner 阻塞在 docker run 里）下 _running_proc
+        # 为空，此时靠 _running_container 杀容器；kill 尽力而为，
+        # 失败也不影响后续的状态标记。
+        if self._running_task_id == task_id and \
+                self._running_container is not None and \
+                hasattr(self.executor, "kill_container"):
+            try:
+                self.executor.kill_container(self._running_container)
+            except Exception:
+                pass
+            self._running_container = None
         conn = _db_connect(self.db_path)
         try:
             cur = conn.execute(
@@ -451,6 +470,11 @@ class Worker:
         return task is not None and task["status"] == "interrupted"
 
     # -- 缺 key 门 ------------------------------------------------------
+    def _executor_name(self):
+        """执行器名：DockerExecutor -> docker，其它 -> local。"""
+        if isinstance(self.executor, DockerExecutor):
+            return "docker"
+        return "local"
     def key_available(self):
         """只查存在性：名在环境里且值非空即 True；值本身绝不返回。"""
         try:
@@ -557,7 +581,7 @@ class Worker:
             return {"dispatched": True, "task_id": task_id,
                     "host_name": self.executor._host_name(task)
                     if hasattr(self.executor, "_host_name") else task_id,
-                    "status": "failed", "executor": "local",
+                    "status": "failed", "executor": self._executor_name(),
                     "stdout": "", "error": error, "events": [],
                     "cost_record_id": None}
 
@@ -565,6 +589,15 @@ class Worker:
         fallback_count = 0
         result = None
         error = None
+        # Docker 同步路径：dispatch 阻塞在 docker run 里时，取消
+        # 线程靠 _running_container 按名杀容器（见 cancel()）。
+        if hasattr(self.executor, "container_name"):
+            try:
+                self._running_container = \
+                    self.executor.container_name(task)
+                self._running_task_id = task_id
+            except Exception:
+                self._running_container = None
         try:
             if self._use_popen():
                 result = self._execute_via_process(task)
@@ -585,6 +618,12 @@ class Worker:
                       "status": "failed", "stdout": "", "returncode": None,
                       "host_status": None, "stderr": ""}
             error = str(exc)
+        # 同步路径执行结束：清掉取消用的容器标记（取消路径里
+        # 若已清过，这里再清一次无害）。
+        self._running_container = None
+        if self._running_task_id == task_id and \
+                self._running_proc is None:
+            self._running_task_id = None
 
         # 取消优先：执行期间被 cancel 的任务保持 interrupted，
         # 绝不用执行结果覆盖它（见模块 docstring 的取消说明）。
@@ -599,7 +638,7 @@ class Worker:
             return {"dispatched": True, "task_id": task_id,
                     "host_name": self.executor._host_name(task)
                     if hasattr(self.executor, "_host_name") else task_id,
-                    "status": "interrupted", "executor": "local",
+                    "status": "interrupted", "executor": self._executor_name(),
                     "stdout": (result or {}).get("stdout", ""),
                     "error": "cancelled", "events": [],
                     "cost_record_id": None}
@@ -649,7 +688,7 @@ class Worker:
         return {"dispatched": True, "task_id": task_id,
                 "host_name": self.executor._host_name(task)
                 if hasattr(self.executor, "_host_name") else task_id,
-                "status": final, "executor": "local",
+                "status": final, "executor": self._executor_name(),
                 "stdout": stdout, "error": error, "events": events,
                 "cost_record_id": cost_id}
 
@@ -719,6 +758,21 @@ class Worker:
         return all_results
 
 
+def _build_cli_executor(args, host_py):
+    """CLI 的执行器构造：local 时返回 None（Worker 默认 LocalExecutor），
+    docker 时返回 DockerExecutor（env_key 名用 Worker 的解析规则，
+    值本身绝不从这里传——DockerExecutor 只查存在性，-e 只传名）。"""
+    if getattr(args, "executor", "local") != "docker":
+        return None
+    return DockerExecutor(
+        host_py, config_path=args.config, image=args.docker_image,
+        cpus=args.docker_cpus, memory=args.docker_memory,
+        user=args.docker_user, worktrees_root=args.docker_worktrees_root,
+        env_key=resolve_env_key(args.env_key, args.codex_config),
+        timeout=args.docker_timeout,
+        extra_mounts=args.docker_extra_mounts)
+
+
 def main(argv=None):
     """worker CLI：默认单次 run_all；--loop 进常驻循环。
 
@@ -737,6 +791,22 @@ def main(argv=None):
     parser.add_argument("--model", default=None)
     parser.add_argument("--max-turns", type=int, default=None)
     parser.add_argument("--max-tasks", type=int, default=None)
+    parser.add_argument("--executor", default="local",
+                        choices=["local", "docker"],
+                        help="执行器：local 调 host.py 子进程；docker"
+                             " 调 DockerExecutor（无 docker 时任务"
+                             "明确失败，不静默降级）")
+    parser.add_argument("--docker-image", default="codex-app-server:latest")
+    parser.add_argument("--docker-cpus", default="2")
+    parser.add_argument("--docker-memory", default="2g")
+    parser.add_argument("--docker-user", default="1000:1000")
+    parser.add_argument("--docker-worktrees-root", default=None)
+    parser.add_argument("--docker-timeout", type=float, default=None)
+    parser.add_argument("--docker-extra-mounts", default=None,
+                        help="docker 额外挂载，逗号分隔 host:container[:ro|rw]，"
+                             "用于容器内 host.py 写 work/、host-state.json，"
+                             "以及挂载原仓库和 codex-home（同路径挂载，"
+                             "容器内配置无需改路径）")
     parser.add_argument("--loop", action="store_true",
                         help="常驻循环，每 --interval 秒跑一轮")
     parser.add_argument("--interval", type=int, default=300)
@@ -750,7 +820,8 @@ def main(argv=None):
     worker = Worker(args.db, host_py, config_path=args.config,
                     repo=args.repo, env_key=args.env_key,
                     codex_config_path=args.codex_config, model=args.model,
-                    max_turns=args.max_turns)
+                    max_turns=args.max_turns,
+                    executor=_build_cli_executor(args, host_py))
     # CLI 起 worker 前先建表/迁移：全新库直接起循环不应因缺表而炸。
     try:
         from cloud.server import init_db as _init_db