Worker startup cleanup previously deleted every container whose name started with codex-, including the codex-postgres database container. On the external host the first worker restart after the prod-grade deploy deleted codex-postgres, leaving the control plane unable to connect to Postgres (connection refused on 127.0.0.1:5432, server auto-restart loop). Fix: cleanup only deletes codex-<32-hex task id> containers, which is exactly the name DockerExecutor gives task containers; infrastructure names like codex-postgres never match and are never deleted. Regression test covers postgres + non-hex names.
607 lines
26 KiB
Python
607 lines
26 KiB
Python
"""沙箱执行器:可插拔的任务执行接口。
|
||
|
||
零第三方依赖,只用 Python 标准库;不重写 agent 逻辑。
|
||
|
||
- Executor:基类,子类必须实现 execute(task)。
|
||
- LocalExecutor:先行实现,复用 host.py 现有 worktree + codex 沙箱,
|
||
通过 host.py CLI 子进程做只读查询封装;不直接跑模型。
|
||
- DockerExecutor:已接通。docker run --rm,任务 worktree 挂载到
|
||
/work(可写)、代码目录挂载到 /app:ro(只读),--cpus/--memory
|
||
资源限额,--user 非 root,-e 只传 env_key 名(不带值,key 缺失
|
||
时不启动容器);超时与取消时 docker kill + rm -f,不留僵尸
|
||
容器。网络白名单不在本类里假装实现(见 cloud/README.md)。
|
||
- CloudExecutor:占位,未接通云端执行。
|
||
"""
|
||
|
||
import json
|
||
import os
|
||
import re
|
||
import shutil
|
||
import subprocess
|
||
import sys
|
||
|
||
MAX_STDOUT_CHARS = 2000
|
||
|
||
|
||
class Executor:
|
||
"""执行器基类。
|
||
|
||
task 是 dict,含 id、project_id、repo、prompt、branch(可选)。
|
||
execute(task) -> dict,至少含 executor、task_id、status、stdout。
|
||
"""
|
||
|
||
def execute(self, task) -> dict:
|
||
raise NotImplementedError("子类必须实现 execute(task)")
|
||
|
||
|
||
def _truncate_stdout(text):
|
||
if text is None:
|
||
return ""
|
||
return str(text)[:MAX_STDOUT_CHARS]
|
||
|
||
|
||
def _default_runner(cmd):
|
||
"""subprocess.run 的薄封装:捕获输出、文本模式。"""
|
||
return subprocess.run(cmd, capture_output=True, text=True)
|
||
|
||
|
||
class LocalExecutor(Executor):
|
||
"""本地执行器:调 host.py CLI 子进程做执行封装。
|
||
|
||
真正跑模型回合的 dispatch/run 由控制面在确认模型 key 供给后才
|
||
调用,本模块只做执行器骨架和 CLI 调用封装。因此 execute() 在此
|
||
只发 host.py 的只读命令(例如 status),绝不在 execute 里直接
|
||
跑模型回合;需要跑模型时,控制面另行调用 host.py dispatch/run。
|
||
|
||
构造函数:LocalExecutor(host_py_path, config_path=None, runner=None)。
|
||
runner 默认是 subprocess.run 的薄封装;单测可注入假 runner,假
|
||
runner 返回 CompletedProcess 风格的 result 对象(含 returncode、
|
||
stdout),本类只读这两个字段,不依赖其它字段。
|
||
|
||
execute() 之外另有 dispatch_task()/run_task():它们是 worker
|
||
派发时调 host.py 真实子命令的入口——dispatch 对应 host.py 的
|
||
dispatch(建任务并跑一轮 turn),run 对应 host.py 的 run
|
||
(在已有 host 任务上再跑一轮 turn)。两者都只发真实存在的
|
||
host.py 子命令,不编造命令名;execute() 本身仍只发只读 status,
|
||
绝不在 execute 里直接跑模型回合(见 test_queue_sandbox 的断言)。
|
||
"""
|
||
|
||
def __init__(self, host_py_path, config_path=None, runner=None,
|
||
repo=None):
|
||
self.host_py_path = host_py_path
|
||
self.config_path = config_path
|
||
self.runner = runner if runner is not None else _default_runner
|
||
self.repo = repo
|
||
|
||
def _base_command(self):
|
||
cmd = [sys.executable, self.host_py_path]
|
||
if self.config_path is not None:
|
||
cmd += ["--config", self.config_path]
|
||
return cmd
|
||
|
||
def _command(self, task_id):
|
||
cmd = self._base_command()
|
||
cmd += ["status", "--task", str(task_id)]
|
||
return cmd
|
||
|
||
def _result_from_runner(self, task_id, result):
|
||
"""把 runner 返回值统一成 execute() 同款结果 dict。
|
||
|
||
host.py dispatch/run 成功时打印 JSON(含 status/text),
|
||
失败时以 SystemExit(1) 退出并打印错误文本。因此:returncode
|
||
非 0 一律 failed;returncode 为 0 时优先取 JSON 里的 status
|
||
(completed 外的状态,如 timeout,均按失败计,worker 侧再
|
||
判断是否可 fallback),取不到 JSON 时按 completed 计。
|
||
"""
|
||
returncode = getattr(result, "returncode", 1)
|
||
stdout = _truncate_stdout(getattr(result, "stdout", ""))
|
||
status = "failed"
|
||
if returncode == 0:
|
||
status = "completed"
|
||
try:
|
||
parsed = json.loads(stdout)
|
||
except (TypeError, ValueError):
|
||
parsed = None
|
||
if isinstance(parsed, dict) and parsed.get("status"):
|
||
status = ("completed" if parsed["status"] == "completed"
|
||
else "failed")
|
||
host_status = parsed["status"]
|
||
else:
|
||
host_status = None
|
||
else:
|
||
host_status = None
|
||
return {
|
||
"executor": "local",
|
||
"task_id": task_id,
|
||
"status": status,
|
||
"stdout": stdout,
|
||
"returncode": returncode,
|
||
"host_status": host_status,
|
||
# host.py 的 RuntimeError(如“任务已存在”)走 traceback 到
|
||
# stderr,worker 判断 dispatch 续跑时需要它;execute()
|
||
# 的旧结果 dict 不含此字段,保持不变。
|
||
"stderr": _truncate_stdout(getattr(result, "stderr", "")),
|
||
}
|
||
|
||
def _host_name(self, task):
|
||
"""cloud 任务 id -> host 任务名:只保留安全字符。
|
||
|
||
server 生成的 id 本就是 uuid hex,走这一步只是防御自定义 id;
|
||
同一 id 每次算出同一名字,dispatch 失败后的 run 续跑才能
|
||
找到同一个 host 任务。
|
||
"""
|
||
raw = str(task.get("id"))
|
||
return re.sub(r"[^A-Za-z0-9_.-]", "-", raw)
|
||
|
||
def dispatch_task(self, task) -> dict:
|
||
"""调 host.py dispatch:建 host 任务并跑一轮 turn。
|
||
|
||
命令:host.py [--config CFG] dispatch --name <host 名>
|
||
--task <prompt> [--repo <repo>]。repo 取任务的 repo 字段,
|
||
没有则取构造时传的 repo,都没有则不传(此时 host.py 用其
|
||
配置文件里的 repo,配置里也没有时 host.py 自己报错,
|
||
worker 把该报错原样写回 failed,不编造成功)。
|
||
"""
|
||
if not isinstance(task, dict) or task.get("id") is None:
|
||
raise ValueError("任务缺少 id")
|
||
if not task.get("prompt"):
|
||
raise ValueError("任务缺少 prompt")
|
||
cmd = self._base_command()
|
||
cmd += ["dispatch", "--name", self._host_name(task),
|
||
"--task", task["prompt"]]
|
||
repo = task.get("repo") or self.repo
|
||
if repo:
|
||
cmd += ["--repo", repo]
|
||
return self._result_from_runner(
|
||
task["id"], self.runner(cmd))
|
||
|
||
def run_task(self, task) -> dict:
|
||
"""调 host.py run:在已有 host 任务上再跑一轮 turn。
|
||
|
||
命令:host.py [--config CFG] run --task <host 名>
|
||
--prompt <prompt>。worker 只在 dispatch 报“任务已存在”时
|
||
用它续跑,不用它做首次派发。
|
||
"""
|
||
if not isinstance(task, dict) or task.get("id") is None:
|
||
raise ValueError("任务缺少 id")
|
||
if not task.get("prompt"):
|
||
raise ValueError("任务缺少 prompt")
|
||
cmd = self._base_command()
|
||
cmd += ["run", "--task", self._host_name(task),
|
||
"--prompt", task["prompt"]]
|
||
return self._result_from_runner(
|
||
task["id"], self.runner(cmd))
|
||
|
||
def popen_task(self, task, kind="dispatch"):
|
||
"""进程组启动 host.py 子进程,返回 Popen(供真取消用)。
|
||
|
||
start_new_session=True 让子进程自成进程组,worker 取消时
|
||
killpg 才能连同子孙一起杀掉。注意:只有默认 runner(真实
|
||
subprocess)时才用本方法;单测注入的假 runner 走同步路径,
|
||
不走这里。
|
||
"""
|
||
if not isinstance(task, dict) or task.get("id") is None:
|
||
raise ValueError("任务缺少 id")
|
||
if not task.get("prompt"):
|
||
raise ValueError("任务缺少 prompt")
|
||
cmd = self._base_command()
|
||
if kind == "run":
|
||
cmd += ["run", "--task", self._host_name(task),
|
||
"--prompt", task["prompt"]]
|
||
else:
|
||
cmd += ["dispatch", "--name", self._host_name(task),
|
||
"--task", task["prompt"]]
|
||
repo = task.get("repo") or self.repo
|
||
if repo:
|
||
cmd += ["--repo", repo]
|
||
return subprocess.Popen(cmd, stdout=subprocess.PIPE,
|
||
stderr=subprocess.PIPE, text=True,
|
||
start_new_session=True)
|
||
|
||
def execute(self, task) -> dict:
|
||
task_id = task.get("id") if isinstance(task, dict) else None
|
||
if task_id is None:
|
||
raise ValueError("任务缺少 id")
|
||
result = self.runner(self._command(task_id))
|
||
returncode = getattr(result, "returncode", 1)
|
||
stdout = _truncate_stdout(getattr(result, "stdout", ""))
|
||
return {
|
||
"executor": "local",
|
||
"task_id": task_id,
|
||
"status": "completed" if returncode == 0 else "failed",
|
||
"stdout": stdout,
|
||
"returncode": returncode,
|
||
}
|
||
|
||
|
||
class DockerExecutor(Executor):
|
||
"""容器执行器(已接通,命令构造可测,真实 docker 需外部主机)。
|
||
|
||
设计(与 LocalExecutor 对齐,区别只在“进程跑在哪”):
|
||
- 容器内跑的仍是 host.py:代码目录以只读方式挂载到 /app,
|
||
容器内命令就是 python3 /app/host.py dispatch/run/status,
|
||
不重写 agent 逻辑;任务自己的 worktree 挂载到 /work(可写),
|
||
绝不挂载宿主根目录、绝不挂载任何含密钥的目录。
|
||
- 容器名:codex-<host 任务名>,host 任务名只保留安全字符,
|
||
同一任务每次算出同一名字,取消时才能按名杀容器。
|
||
- key:只把 env_key 名以 `-e <名>` 传给 docker(docker 从宿主
|
||
进程环境里取值注入容器),命令列表里绝不出现 key 的值;
|
||
key 缺失时在调 runner 之前就明确失败,容器根本不启动。
|
||
本类只查 env 映射里的存在性与非空,绝不打印、记录 key 的值。
|
||
- 资源:--cpus / --memory 可配置,默认 2 核 / 2G,写进文档。
|
||
- 清理:docker run --rm,失败也 --rm;超时或取消时先
|
||
docker kill 再 docker rm -f,绝不留僵尸容器。
|
||
- 网络诚实边界:docker run 默认 bridge 网络;本类不做 egress
|
||
白名单——真正的“只放行模型 API”需要宿主防火墙/代理规则,
|
||
那是部署项,不是本类假装做到的(见 cloud/README.md)。
|
||
|
||
构造函数:DockerExecutor(host_py_path=None, config_path=None,
|
||
runner=None, image="codex-app-server:latest", cpus="2",
|
||
memory="2g", user="1000:1000", worktrees_root=None,
|
||
env=None, env_key="XCM_API_KEY", timeout=None)。
|
||
host_py_path 缺省时取 cloud/ 上一级的 host.py(与 worker
|
||
CLI 的缺省规则一致),以便 DockerExecutor() 无参调用仍可用。
|
||
runner 默认是带 timeout 的 subprocess 封装;单测注入的假
|
||
runner 可以只接受 cmd 一个参数(本类遇 TypeError 时回退
|
||
到只传 cmd 调用),也可以接受 (cmd, timeout=...)。
|
||
docker 二进制缺失时 raise RuntimeError("docker not available"),
|
||
绝不静默降级为本地执行。
|
||
"""
|
||
|
||
def __init__(self, host_py_path=None, config_path=None, runner=None,
|
||
image="codex-app-server:latest", cpus="2", memory="2g",
|
||
user="1000:1000", worktrees_root=None, env=None,
|
||
env_key="XCM_API_KEY", timeout=None, extra_mounts=None):
|
||
if host_py_path is None:
|
||
here = os.path.dirname(os.path.abspath(__file__))
|
||
host_py_path = os.path.join(os.path.dirname(here), "host.py")
|
||
self.host_py_path = host_py_path
|
||
self.config_path = config_path
|
||
self.runner = runner if runner is not None else _docker_default_runner
|
||
self.image = image
|
||
self.cpus = str(cpus)
|
||
self.memory = str(memory)
|
||
self.user = user
|
||
self.worktrees_root = worktrees_root
|
||
self._env = env if env is not None else os.environ
|
||
self.env_key = env_key
|
||
self.timeout = timeout
|
||
self.extra_mounts = self._parse_extra_mounts(extra_mounts)
|
||
|
||
@staticmethod
|
||
def _parse_extra_mounts(extra_mounts):
|
||
"""解析额外挂载,格式 host:container 或 host:container:ro/rw。
|
||
|
||
安全红线(违反时直接抛错,绝不静默放行):宿主路径必须
|
||
是绝对路径且必须已存在(文件挂载时 docker 对不存在路径
|
||
会自动建目录,极易把文件挂载变成目录挂载);容器路径
|
||
必须是绝对路径,不能是 / 或 /app 本身(那会整体覆盖
|
||
只读代码挂载);宿主路径不能是 /、/etc、/root,也不能
|
||
在 /etc/codex-app-server 之下(那里放着 key 文件)。
|
||
"""
|
||
if not extra_mounts:
|
||
return []
|
||
if isinstance(extra_mounts, str):
|
||
extra_mounts = [m for m in extra_mounts.split(",") if m.strip()]
|
||
out = []
|
||
for spec in extra_mounts:
|
||
parts = spec.split(":")
|
||
if len(parts) not in (2, 3):
|
||
raise ValueError("extra mount 格式必须是 host:container[:ro|rw]: %s" % spec)
|
||
host_p, cont_p = parts[0], parts[1]
|
||
mode = parts[2] if len(parts) == 3 else "rw"
|
||
if mode not in ("ro", "rw"):
|
||
raise ValueError("extra mount 模式只能是 ro 或 rw: %s" % spec)
|
||
if not os.path.isabs(host_p) or not os.path.isabs(cont_p):
|
||
raise ValueError("extra mount 路径必须是绝对路径: %s" % spec)
|
||
if host_p in ("/", "/etc", "/root") or host_p.startswith("/etc/codex-app-server"):
|
||
raise ValueError("extra mount 拒绝危险宿主路径: %s" % spec)
|
||
if cont_p in ("/", "/app"):
|
||
raise ValueError("extra mount 拒绝覆盖容器根或 /app 本身: %s" % spec)
|
||
if not os.path.exists(host_p):
|
||
raise ValueError("extra mount 宿主路径不存在,拒绝挂载: %s" % spec)
|
||
out.append((host_p, cont_p, mode))
|
||
return out
|
||
|
||
# -- 名字 / 路径 ---------------------------------------------------
|
||
def _host_name(self, task):
|
||
raw = str(task.get("id"))
|
||
return re.sub(r"[^A-Za-z0-9_.-]", "-", raw)
|
||
|
||
def container_name(self, task):
|
||
"""任务派生的容器名:codex-<安全字符任务名>。"""
|
||
return "codex-" + self._host_name(task)
|
||
|
||
def _app_dir(self):
|
||
"""代码目录:host_py_path 所在的目录,挂载到 /app:ro。"""
|
||
return os.path.dirname(os.path.abspath(self.host_py_path))
|
||
|
||
def _worktree_for(self, task):
|
||
"""任务自己的 worktree:显式字段优先,否则按派生目录。
|
||
|
||
显式字段 worktree > cwd;都没有时用 worktrees_root/<host 名>
|
||
(未传 worktrees_root 时默认在 host.py 同级的 work/
|
||
docker-worktrees 下)。本方法不建目录:docker -v 对不存
|
||
在的宿主路径会自动建目录,测试里传显式 worktree 即可
|
||
避免任何副作用。
|
||
"""
|
||
if task.get("worktree"):
|
||
return task["worktree"]
|
||
if task.get("cwd"):
|
||
return task["cwd"]
|
||
root = self.worktrees_root
|
||
if root is None:
|
||
root = os.path.join(self._app_dir(), "work", "docker-worktrees")
|
||
return os.path.join(root, self._host_name(task))
|
||
|
||
# -- 前置检查 ------------------------------------------------------
|
||
def _check_docker(self):
|
||
if shutil.which("docker") is None:
|
||
raise RuntimeError("docker not available")
|
||
|
||
def _check_key(self):
|
||
"""key 门:只查存在性与非空,值本身绝不返回、不打印。"""
|
||
if not self.env_key:
|
||
return
|
||
try:
|
||
value = self._env.get(self.env_key)
|
||
except Exception:
|
||
value = None
|
||
if value is None or value == "":
|
||
raise RuntimeError(
|
||
"Missing environment variable: %s" % self.env_key)
|
||
|
||
# -- 命令构造 ------------------------------------------------------
|
||
def build_run_command(self, task, inner_cmd):
|
||
"""构造完整的 docker run 命令(纯函数,可单测断言)。
|
||
|
||
顺序固定:docker run --rm --name <容器名> --user <用户>
|
||
--cpus <核数> --memory <内存> -v <worktree>:/work
|
||
-v <代码目录>:/app:ro -w /work [-e <env_key名>]
|
||
<镜像> <容器内命令...>。-e 只传名字,不带 =值。
|
||
"""
|
||
self._check_docker()
|
||
self._check_key()
|
||
cmd = ["docker", "run", "--rm",
|
||
"--name", self.container_name(task),
|
||
"--user", self.user,
|
||
"--cpus", self.cpus,
|
||
"--memory", self.memory,
|
||
"-v", "%s:/work" % self._worktree_for(task),
|
||
"-v", "%s:/app:ro" % self._app_dir(),
|
||
"-w", "/work"]
|
||
# 额外挂载放在基础挂载之后:/app/work 这类子路径挂载会
|
||
# 覆盖 /app:ro 的对应子路径,让容器内 host.py 能写
|
||
# work/ 和 host-state.json,同时代码主体仍只读。
|
||
for host_p, cont_p, mode in self.extra_mounts:
|
||
cmd += ["-v", "%s:%s:%s" % (host_p, cont_p, mode)]
|
||
if self.env_key:
|
||
cmd += ["-e", self.env_key]
|
||
cmd += [self.image]
|
||
cmd += list(inner_cmd)
|
||
return cmd
|
||
|
||
def _inner_host_command(self, *args):
|
||
"""容器内 host.py 命令:python3 /app/host.py [args...]。
|
||
|
||
config_path 若已给,容器内用 /app/<basename> 指代它——
|
||
调用方须保证配置文件就在代码目录里(host.py 配置约定
|
||
本就放在项目目录);不在代码目录时不静默猜路径,
|
||
由 _inner_host_command 的调用方在传 config 前自行确认。
|
||
这里只做最简单的同名映射,不展开宿主绝对路径进容器。
|
||
"""
|
||
cmd = ["python3", "/app/host.py"]
|
||
if self.config_path is not None:
|
||
cmd += ["--config",
|
||
"/app/" + os.path.basename(self.config_path)]
|
||
cmd += list(args)
|
||
return cmd
|
||
|
||
# -- runner 调用 / 清理 --------------------------------------------
|
||
def _call_runner(self, cmd):
|
||
"""调 runner:优先传 timeout,假 runner 只接受 cmd 时回退。"""
|
||
try:
|
||
return self.runner(cmd, timeout=self.timeout)
|
||
except TypeError:
|
||
return self.runner(cmd)
|
||
|
||
def list_containers(self, prefix="codex-"):
|
||
"""列出名字以 prefix 开头的容器(默认 codex-),失败返回 []。
|
||
|
||
用 `docker ps -a --format {{.Names}}`,输出按行取容器名;
|
||
runner 抛异常或输出不可解析时返回空列表,调用方(worker
|
||
启动清理)据此只记日志、不炸掉 worker。
|
||
"""
|
||
try:
|
||
result = self._call_runner(
|
||
["docker", "ps", "-a", "--format", "{{.Names}}"])
|
||
except Exception:
|
||
return []
|
||
out = getattr(result, "stdout", "") or ""
|
||
names = []
|
||
for line in str(out).splitlines():
|
||
name = line.strip()
|
||
if name and name.startswith(prefix):
|
||
names.append(name)
|
||
return names
|
||
|
||
# 任务容器名是 codex-<32 位 hex 任务 id>(见 _container_name)。
|
||
# 启动清理只能删这种容器,绝不能按 "codex-" 前缀全删:基础设施
|
||
# 容器也叫 codex-*(例如 codex-postgres),按前缀删会把数据库
|
||
# 容器当成残留任务容器杀掉(2026-10-26 实测:worker 重启时
|
||
# codex-postgres 就是这样被删掉,导致控制面连不上 Postgres)。
|
||
_TASK_CONTAINER_RE = re.compile(r"^codex-[0-9a-f]{32}$")
|
||
|
||
def cleanup_stale_containers(self, prefix="codex-"):
|
||
"""清理上一轮残留的任务容器:只删 codex-<32 位 hex 任务 id>。
|
||
|
||
返回已清理的容器名列表;单个容器清理失败只跳过它(kill
|
||
本身尽力而为),列出失败时返回 [],绝不抛异常。
|
||
基础设施容器(如 codex-postgres)名字不匹配任务 id 正则,
|
||
永远不会被这里删掉。
|
||
"""
|
||
cleaned = []
|
||
for name in self.list_containers(prefix=prefix):
|
||
if not self._TASK_CONTAINER_RE.match(name):
|
||
continue
|
||
try:
|
||
if self.kill_container(name):
|
||
cleaned.append(name)
|
||
except Exception:
|
||
continue
|
||
return cleaned
|
||
|
||
def kill_container(self, task_or_name):
|
||
"""杀容器:docker kill + docker rm -f,尽力而为不抛异常。
|
||
|
||
task_or_name 可以是任务 dict(取容器名)或容器名字符串。
|
||
返回 True 表示至少 kill 或 rm 其中一步成功执行(runner
|
||
未抛异常),False 表示两步都失败或 docker 不存在。
|
||
取消路径调用它,绝不只改数据库状态。
|
||
"""
|
||
name = (self.container_name(task_or_name)
|
||
if isinstance(task_or_name, dict) else str(task_or_name))
|
||
ok = False
|
||
for cmd in (["docker", "kill", name],
|
||
["docker", "rm", "-f", name]):
|
||
try:
|
||
self._call_runner(cmd)
|
||
ok = True
|
||
except Exception:
|
||
continue
|
||
return ok
|
||
|
||
def _run_in_container(self, task, inner_cmd):
|
||
"""在容器里跑一轮内层命令,返回 LocalExecutor 同款结果 dict。
|
||
|
||
超时:runner 抛 subprocess.TimeoutExpired(或同名异常)
|
||
时先 kill+rm 容器,再返回 failed(stdout 截断 + timeout
|
||
说明,returncode 为 None);其它 runner 异常也如实返回
|
||
failed,不编造成功。
|
||
"""
|
||
task_id = task.get("id") if isinstance(task, dict) else None
|
||
if task_id is None:
|
||
raise ValueError("任务缺少 id")
|
||
cmd = self.build_run_command(task, inner_cmd)
|
||
try:
|
||
result = self._call_runner(cmd)
|
||
except Exception as exc:
|
||
if exc.__class__.__name__ == "TimeoutExpired":
|
||
self.kill_container(task)
|
||
return {
|
||
"executor": "docker", "task_id": task_id,
|
||
"status": "failed", "stdout": "docker run timeout",
|
||
"returncode": None, "host_status": None, "stderr": "",
|
||
"container": self.container_name(task),
|
||
}
|
||
return {
|
||
"executor": "docker", "task_id": task_id,
|
||
"status": "failed",
|
||
"stdout": _truncate_stdout(str(exc)),
|
||
"returncode": None, "host_status": None, "stderr": "",
|
||
"container": self.container_name(task),
|
||
}
|
||
fake = SimpleNamespaceShim(result)
|
||
parsed = _parse_host_result(task_id, fake)
|
||
parsed["executor"] = "docker"
|
||
parsed["container"] = self.container_name(task)
|
||
return parsed
|
||
|
||
def dispatch_task(self, task) -> dict:
|
||
"""容器内调 host.py dispatch:建 host 任务并跑一轮 turn。"""
|
||
if not isinstance(task, dict) or task.get("id") is None:
|
||
raise ValueError("任务缺少 id")
|
||
if not task.get("prompt"):
|
||
raise ValueError("任务缺少 prompt")
|
||
inner = self._inner_host_command(
|
||
"dispatch", "--name", self._host_name(task),
|
||
"--task", task["prompt"])
|
||
repo = task.get("repo")
|
||
if repo:
|
||
inner += ["--repo", repo]
|
||
return self._run_in_container(task, inner)
|
||
|
||
def run_task(self, task) -> dict:
|
||
"""容器内调 host.py run:在已有 host 任务上再跑一轮 turn。"""
|
||
if not isinstance(task, dict) or task.get("id") is None:
|
||
raise ValueError("任务缺少 id")
|
||
if not task.get("prompt"):
|
||
raise ValueError("任务缺少 prompt")
|
||
inner = self._inner_host_command(
|
||
"run", "--task", self._host_name(task),
|
||
"--prompt", task["prompt"])
|
||
return self._run_in_container(task, inner)
|
||
|
||
def execute(self, task) -> dict:
|
||
"""只读执行:容器内调 host.py status,不直接跑模型回合。
|
||
|
||
与 LocalExecutor.execute 对齐:execute 本身只发 status,
|
||
跑模型请走 dispatch_task/run_task(worker 派发路径)。
|
||
"""
|
||
if not isinstance(task, dict) or task.get("id") is None:
|
||
raise ValueError("任务缺少 id")
|
||
inner = self._inner_host_command(
|
||
"status", "--task", self._host_name(task))
|
||
return self._run_in_container(task, inner)
|
||
|
||
|
||
class SimpleNamespaceShim:
|
||
"""把 runner 返回值统一成 returncode/stdout/stderr 三字段。"""
|
||
|
||
def __init__(self, result):
|
||
self.returncode = getattr(result, "returncode", 1)
|
||
self.stdout = getattr(result, "stdout", "")
|
||
self.stderr = getattr(result, "stderr", "")
|
||
|
||
|
||
def _parse_host_result(task_id, fake):
|
||
"""LocalExecutor._result_from_runner 的无类版本,供 Docker 用。
|
||
|
||
host.py 成功时打印 JSON(含 status/text),失败时非 0 退出;
|
||
returncode 非 0 一律 failed;为 0 时优先取 JSON 里的 status,
|
||
completed 外的状态均按 failed 计。
|
||
"""
|
||
returncode = getattr(fake, "returncode", 1)
|
||
stdout = _truncate_stdout(getattr(fake, "stdout", ""))
|
||
status = "failed"
|
||
host_status = None
|
||
if returncode == 0:
|
||
status = "completed"
|
||
try:
|
||
parsed = json.loads(stdout)
|
||
except (TypeError, ValueError):
|
||
parsed = None
|
||
if isinstance(parsed, dict) and parsed.get("status"):
|
||
host_status = parsed["status"]
|
||
status = ("completed" if host_status == "completed"
|
||
else "failed")
|
||
return {
|
||
"executor": "docker",
|
||
"task_id": task_id,
|
||
"status": status,
|
||
"stdout": stdout,
|
||
"returncode": returncode,
|
||
"host_status": host_status,
|
||
"stderr": _truncate_stdout(getattr(fake, "stderr", "")),
|
||
}
|
||
|
||
|
||
def _docker_default_runner(cmd, timeout=None):
|
||
"""docker 的默认 runner:subprocess.run,支持 timeout。"""
|
||
return subprocess.run(cmd, capture_output=True, text=True,
|
||
timeout=timeout)
|
||
|
||
|
||
class CloudExecutor(Executor):
|
||
"""云端执行器(占位,未接通)。
|
||
|
||
execute(task) 一律 raise RuntimeError,绝不假装已接通云端。
|
||
接通前提:真实云账号 + 预算上限配置,届时由控制面注入凭证与
|
||
限额后再替换本占位实现。
|
||
"""
|
||
|
||
def execute(self, task) -> dict:
|
||
raise RuntimeError(
|
||
"cloud executor not connected: missing cloud account "
|
||
"and budget limit")
|