qing
67acae708c
波次 4 LLM 健壮性（T10/T19/T20/T21/T23 + T14 复现证伪）： - T10 调度器 await 改 wait_for 硬超时兜底（task_timeout+30s 宽限）， 软取消够不到的卡死路径不再永久停摆调度循环 - T19 FailoverClient 异常收窄为瞬时白名单（Connection/Timeout/ ChunkedEncoding），MissingSchema 等永久配置错误不再污染冷却表 - T20 流式未收到 [DONE] 抛 TransientLLMError，回答无声截断可感知 - T21 env 覆盖黑名单 filter_env_overrides（LD_*/DYLD_*/PATH 等）， executors 两处 + process_manager 接入 - T23 压缩后 tool 配对双向修复（失配 tool_calls 剥离防 API 400） - T14 FTS5 复现证伪：JOIN 别名场景表名 MATCH 正常，无需修复 波次 5 权限隔离（T22/T-L17/T-L18；T1/T2 产品决策：仅告警/维持现状）： - T22a TOOL_PROFILE_TASK 定时任务精简工具面（无 update_identity/ update_soul/set_proxy） - T22b ProcessManager owner 隔离：bg_write/bg_kill 属主校验， 观察面共享；DeepSeekChat 新增 owner_id 传导 - T1 绑定非回环地址时启动显著告警 - T-L17 model_config env 名按域名推荐（防跨厂商凭据外发） - T-L18 list_profiles 过滤控制字符（防 ANSI 注入） 测试：test_n_fixes.py 增至 62 项；全量 598 passed / 1 failed （Windows 向 ping 用例，环境项），零回归。审计报告补记 §24.7~24.11， README 同步 owner 隔离语义。八轮审计 T 系列 28 项全部处置完毕。
425 lines
18 KiB
Python
425 lines
18 KiB
Python
#!/usr/bin/env python3
|
||
"""
|
||
tools.process_tools - 后台进程管理工具
|
||
|
||
五个 worker 执行面工具，配合 subsystems.process_manager.ProcessManager：
|
||
- BgRunTool : bg_run 后台启动长驻进程，立即返回句柄
|
||
- BgWriteTool : bg_write 向后台进程 stdin 写入（watermark 写读对齐）
|
||
- BgListTool : bg_list 列出全部后台进程（运行中/已退出）
|
||
- BgOutputTool : bg_output 拉取输出（tail 尾部 / since 游标增量）
|
||
- BgKillTool : bg_kill 终止指定后台进程（关stdin→SIGTERM→SIGKILL）
|
||
|
||
设计语义（与用户约定的三决策）：
|
||
- 用户中断（Ctrl+C/取消事件）不影响后台进程
|
||
- aibox 进程退出时默认终止全部，bg_run detach=true 豁免
|
||
- 注册表全局共享：任何子代理可管理其他子代理启动的进程
|
||
|
||
交互语义：
|
||
- stdin 为管道：行协议程序（REPL/问答 CLI）可 bg_write 写入；
|
||
watermark = [stdin] 回显行序号，bg_output(since=watermark) 即本条
|
||
输入的响应（写读对齐）
|
||
- bg_run log_file=true 时输出 tee 到 workspace/bg_<句柄>.log（无界
|
||
全档），可被原生工具（run_command tail/cat）读取
|
||
|
||
依赖：common (ConfigManager, constants) + tools.base.Tool +
|
||
subsystems.process_manager（get_process_manager 单例）
|
||
不反向依赖 aibox 任何符号。
|
||
"""
|
||
|
||
from typing import Dict
|
||
|
||
from common import ConfigManager, constants
|
||
from subsystems.process_manager import get_process_manager, ProcessManager
|
||
from .base import Tool
|
||
|
||
|
||
def _enabled() -> bool:
|
||
"""后台进程功能开关：commands.enabled 与 background_processes.enabled
|
||
双闸（后台执行本质仍是命令执行，前者关闭时一并拒绝）"""
|
||
return constants.COMMANDS_ENABLED and constants.BG_PROCESSES_ENABLED
|
||
|
||
|
||
def _fmt_duration(seconds: float) -> str:
|
||
"""秒数 → 人读时长（如 3h05m / 12.5s）"""
|
||
try:
|
||
seconds = float(seconds)
|
||
except (TypeError, ValueError):
|
||
return "?"
|
||
if seconds < 60:
|
||
return f"{seconds:.1f}s"
|
||
m, s = divmod(int(seconds), 60)
|
||
if m < 60:
|
||
return f"{m}m{s:02d}s"
|
||
h, m = divmod(m, 60)
|
||
return f"{h}h{m:02d}m{s:02d}s"
|
||
|
||
|
||
def _coerce_int(value, default=None):
|
||
"""命令面输入规整（W 批惯例）：LLM 可能传字符串数字，统一安全转 int"""
|
||
if value is None:
|
||
return default
|
||
try:
|
||
return int(value)
|
||
except (TypeError, ValueError):
|
||
return default
|
||
|
||
|
||
def _coerce_bool(value, default: bool) -> bool:
|
||
"""命令面输入规整：LLM 可能传字符串 "false"/"0"，统一安全转 bool"""
|
||
if value is None:
|
||
return default
|
||
if isinstance(value, bool):
|
||
return value
|
||
if isinstance(value, str):
|
||
return value.strip().lower() not in ("false", "0", "no", "off", "")
|
||
return bool(value)
|
||
|
||
|
||
class BgRunTool(Tool):
|
||
"""后台启动长驻进程"""
|
||
|
||
def __init__(self, manager: ProcessManager = None, logger=None, owner: str = None):
|
||
super().__init__(logger)
|
||
self.manager = manager or get_process_manager(logger)
|
||
# T22：属主标识——写入/终止权限隔离（观察面 list/output 不限）
|
||
self.owner = owner
|
||
|
||
def get_name(self) -> str:
|
||
return "bg_run"
|
||
|
||
def get_description(self) -> str:
|
||
return ("后台启动长驻进程（如 dev server、训练任务、watch 监控），立即返回句柄不阻塞。"
|
||
"与 run_command 的区别：run_command 同步等待命令结束（超时即杀），适合短命令；"
|
||
"bg_run 适合需要持续运行的进程，启动后用 bg_list 查看状态、bg_output 拉取输出、"
|
||
"bg_kill 终止。stdin 为管道：行协议交互程序（REPL/问答式 CLI）可用 bg_write 写入。"
|
||
"注意：用户中断不影响后台进程；aibox 退出时后台进程默认被终止，"
|
||
"需要跨重启存活的进程用 detach=true（随后无法再经句柄管理）。")
|
||
|
||
def get_parameters(self) -> Dict:
|
||
return {
|
||
"type": "object",
|
||
"properties": {
|
||
"command": {
|
||
"type": "string",
|
||
"description": "要执行的命令（shell 命令行）",
|
||
},
|
||
"proc_name": {
|
||
"type": "string",
|
||
"description": "进程标签（可选，便于识别，≤64 字符，默认取命令前 40 字符）",
|
||
},
|
||
"work_dir": {
|
||
"type": "string",
|
||
"description": "工作目录（默认 ~/.aibox/workspace）",
|
||
},
|
||
"env": {
|
||
"type": "object",
|
||
"description": "额外的环境变量",
|
||
},
|
||
"detach": {
|
||
"type": "boolean",
|
||
"description": "aibox 退出时不终止该进程（默认 false；detach 后进程脱离句柄管理）",
|
||
},
|
||
"log_file": {
|
||
"type": "boolean",
|
||
"description": "同时镜像全程输出到 workspace/bg_<句柄>.log（无界全档，可被 run_command 的 tail/cat 读取；默认 false 仅环形缓冲）",
|
||
},
|
||
},
|
||
"required": ["command"],
|
||
}
|
||
|
||
def execute(self, command: str = None, proc_name: str = None,
|
||
work_dir: str = None, env: Dict = None,
|
||
detach: bool = False, log_file: bool = False, **kwargs) -> str:
|
||
if error := self.validate_params(["command"], command=command):
|
||
return error
|
||
if not _enabled():
|
||
return "❌ 后台进程功能已禁用（commands.enabled 或 background_processes.enabled 为 false）"
|
||
|
||
# T18：LLM 可能传字符串 "false"，裸 bool("false") is True——
|
||
# detach 误开致进程脱离管理、log_file 误开，统一规整
|
||
detach = _coerce_bool(detach, False)
|
||
log_file = _coerce_bool(log_file, False)
|
||
|
||
result = self.manager.start(command, name=proc_name, work_dir=work_dir,
|
||
env=env, detach=detach, log_file=log_file,
|
||
owner=self.owner)
|
||
if not result.get("ok"):
|
||
return self.format_result(False, "后台进程启动失败",
|
||
{"错误": result.get("error", "未知错误")})
|
||
data = {
|
||
"句柄": result["handle"],
|
||
"PID": result["pid"],
|
||
"名称": result["name"],
|
||
"detach": "是（aibox 退出不终止）" if result.get("detach") else "否（aibox 退出时终止）",
|
||
"后续": f"bg_output 拉取输出 / bg_list 查看状态 / bg_kill 终止（句柄 #{result['handle']}）",
|
||
}
|
||
if result.get("log_file"):
|
||
data["日志镜像"] = result["log_file"]
|
||
return self.format_result(True, f"后台进程已启动（#{result['handle']}）", data)
|
||
|
||
|
||
class BgWriteTool(Tool):
|
||
"""向后台进程 stdin 写入（交互式问答）"""
|
||
|
||
def __init__(self, manager: ProcessManager = None, logger=None, owner: str = None):
|
||
super().__init__(logger)
|
||
self.manager = manager or get_process_manager(logger)
|
||
# T22：属主标识——仅属主可写（他人 stdin 不容注入）
|
||
self.owner = owner
|
||
|
||
def get_name(self) -> str:
|
||
return "bg_write"
|
||
|
||
def get_description(self) -> str:
|
||
return ("向后台进程的标准输入写入一行（行协议交互：REPL / 问答式 CLI）。"
|
||
"返回 watermark 水位：bg_output(handle=..., since=watermark) 得到的必然且仅是"
|
||
"本条输入引发的进程响应（写读对齐，不含 [stdin] 回显行）。"
|
||
"适用前提：进程按行读 stdin 并及时输出——建议启动时强制行缓冲"
|
||
"（python -i -u、PYTHONUNBUFFERED=1、stdbuf -oL），否则响应可能滞留子进程缓冲。"
|
||
"限制：无 TTY，全屏程序（vim/top 等）不可用；喂密码类交互（如 sudo -S）会留在"
|
||
"对话记录中，敏感凭据请改用环境变量注入。")
|
||
|
||
def get_parameters(self) -> Dict:
|
||
return {
|
||
"type": "object",
|
||
"properties": {
|
||
"handle": {
|
||
"type": "integer",
|
||
"description": "bg_run 返回的句柄编号",
|
||
},
|
||
"text": {
|
||
"type": "string",
|
||
"description": "要写入的文本（默认追加换行；多行输入会折叠为单行回显）",
|
||
},
|
||
"append_newline": {
|
||
"type": "boolean",
|
||
"description": "写入后是否自动补换行（默认 true；false 发送原始字节）",
|
||
},
|
||
"wait_lines": {
|
||
"type": "integer",
|
||
"description": "写完同步等待 N 行响应再返回（默认 0 立即返回，用 bg_output 轮询）",
|
||
},
|
||
"wait_timeout": {
|
||
"type": "number",
|
||
"description": "同步等待响应的超时秒数（默认 5，上限 60）",
|
||
},
|
||
},
|
||
"required": ["handle", "text"],
|
||
}
|
||
|
||
def execute(self, handle=None, text: str = None, append_newline=True,
|
||
wait_lines=None, wait_timeout=None, **kwargs) -> str:
|
||
if error := self.validate_params(["handle", "text"], handle=handle, text=text):
|
||
return error
|
||
if not _enabled():
|
||
return "❌ 后台进程功能已禁用"
|
||
|
||
handle = _coerce_int(handle)
|
||
if handle is None:
|
||
return "❌ 错误：handle 必须是整数句柄"
|
||
wait_i = _coerce_int(wait_lines, 0)
|
||
wait_t = _coerce_int(wait_timeout, 5)
|
||
|
||
result = self.manager.write(
|
||
handle, text,
|
||
append_newline=_coerce_bool(append_newline, True),
|
||
wait_lines=max(0, wait_i),
|
||
wait_timeout=wait_t,
|
||
owner=self.owner,
|
||
)
|
||
if not result.get("ok"):
|
||
return self.format_result(False, f"写入后台进程 #{handle} 失败",
|
||
{"错误": result.get("error", "未知错误")})
|
||
|
||
data = {
|
||
"句柄": handle,
|
||
"已写入": f"{result['sent_bytes']} 字节",
|
||
"watermark": result["watermark"],
|
||
"对齐读取": f"bg_output(handle={handle}, since={result['watermark']}) → 本条输入的响应",
|
||
}
|
||
if "wait" in result:
|
||
w = result["wait"]
|
||
data["等待输出"] = w.get("output") or "(超时未收到响应)"
|
||
data["next_cursor"] = w.get("next_cursor")
|
||
if w.get("timed_out"):
|
||
data["警告"] = "等待响应超时（进程可能无输出或缓冲滞留），可用 bg_output 轮询"
|
||
return self.format_result(True, f"已写入后台进程 #{handle}", data)
|
||
|
||
|
||
class BgListTool(Tool):
|
||
"""列出后台进程"""
|
||
|
||
def __init__(self, manager: ProcessManager = None, logger=None):
|
||
super().__init__(logger)
|
||
self.manager = manager or get_process_manager(logger)
|
||
|
||
def get_name(self) -> str:
|
||
return "bg_list"
|
||
|
||
def get_description(self) -> str:
|
||
return ("列出全部后台进程（含已退出的，保留尾部输出供验尸）。运行中在前。"
|
||
"输出包含句柄/名称/PID/状态/运行时长，用句柄配合 bg_output/bg_kill 管理。")
|
||
|
||
def get_parameters(self) -> Dict:
|
||
return {"type": "object", "properties": {}}
|
||
|
||
def execute(self, **kwargs) -> str:
|
||
if not _enabled():
|
||
return "❌ 后台进程功能已禁用"
|
||
procs = self.manager.list_procs()
|
||
if not procs:
|
||
return "✅ 当前没有后台进程（bg_run 启动）"
|
||
lines = []
|
||
status_emoji = {"running": "🟢", "exited": "⚪", "killed": "🔴", "expired": "⏹️"}
|
||
for p in procs:
|
||
emoji = status_emoji.get(p["status"], "❔")
|
||
extra = ""
|
||
if p["status"] == "running":
|
||
extra = f"运行 {_fmt_duration(p['runtime_sec'])}"
|
||
else:
|
||
extra = f"已结束（{_fmt_duration(p['runtime_sec'])}，返回码 {p['exit_code']}）"
|
||
detach_tag = " [detach]" if p["detach"] else ""
|
||
lines.append(f"{emoji} #{p['handle']} {p['name']}{detach_tag} "
|
||
f"(pid {p['pid']}, {extra})")
|
||
lines.append(f" 命令: {p['command']}")
|
||
running = sum(1 for p in procs if p["status"] == "running")
|
||
header = f"共 {len(procs)} 个后台进程（运行中 {running}）"
|
||
return "✅ " + header + "\n" + "\n".join(lines)
|
||
|
||
|
||
class BgOutputTool(Tool):
|
||
"""拉取后台进程输出"""
|
||
|
||
def __init__(self, manager: ProcessManager = None, logger=None):
|
||
super().__init__(logger)
|
||
self.manager = manager or get_process_manager(logger)
|
||
|
||
def get_name(self) -> str:
|
||
return "bg_output"
|
||
|
||
def get_description(self) -> str:
|
||
return ("拉取后台进程输出。两种模式：tail=N 取最近 N 行（默认 50）；"
|
||
"since=游标 增量拉取上次读取之后的新输出（游标用上次返回的 next_cursor）。"
|
||
"长驻进程轮询建议用 since 模式避免重复传输旧输出。")
|
||
|
||
def get_parameters(self) -> Dict:
|
||
return {
|
||
"type": "object",
|
||
"properties": {
|
||
"handle": {
|
||
"type": "integer",
|
||
"description": "bg_run 返回的句柄编号",
|
||
},
|
||
"tail": {
|
||
"type": "integer",
|
||
"description": "取最近 N 行（默认 50；与 since 二选一）",
|
||
},
|
||
"since": {
|
||
"type": "integer",
|
||
"description": "增量游标：上次返回的 next_cursor，取此序号之后的新行（与 tail 二选一）",
|
||
},
|
||
"max_bytes": {
|
||
"type": "integer",
|
||
"description": "本次拉取最大字节数（默认 64KB，上限 1MB）",
|
||
},
|
||
},
|
||
"required": ["handle"],
|
||
}
|
||
|
||
def execute(self, handle=None, tail=None, since=None, max_bytes=None, **kwargs) -> str:
|
||
if error := self.validate_params(["handle"], handle=handle):
|
||
return error
|
||
if not _enabled():
|
||
return "❌ 后台进程功能已禁用"
|
||
|
||
handle = _coerce_int(handle)
|
||
if handle is None:
|
||
return "❌ 错误：handle 必须是整数句柄"
|
||
since_i = _coerce_int(since)
|
||
tail_i = _coerce_int(tail)
|
||
|
||
result = self.manager.get_output(handle, tail=tail_i, since=since_i,
|
||
max_bytes=_coerce_int(max_bytes, 65536))
|
||
if not result.get("ok"):
|
||
return self.format_result(False, "拉取输出失败",
|
||
{"错误": result.get("error", "未知错误")})
|
||
|
||
data = {
|
||
"状态": result["status"] + (f"（返回码 {result['exit_code']}）"
|
||
if result["exit_code"] is not None else ""),
|
||
"本次行数": result["lines"],
|
||
"next_cursor": result["next_cursor"],
|
||
}
|
||
if result.get("truncated"):
|
||
data["警告"] = "输出超过本次字节上限，已截断（提高 max_bytes 或用 since 分段拉取）"
|
||
if result.get("evicted"):
|
||
data["提示"] = (f"有 {result['evicted']} 行早期输出因环形缓冲淘汰不可读取"
|
||
"（需要完整日志请让进程重定向到文件）")
|
||
output = result.get("output") or "(本次无新输出)"
|
||
data["输出"] = output
|
||
return self.format_result(True, f"后台进程 #{handle} 输出", data)
|
||
|
||
|
||
class BgKillTool(Tool):
|
||
"""终止后台进程"""
|
||
|
||
def __init__(self, manager: ProcessManager = None, logger=None, owner: str = None):
|
||
super().__init__(logger)
|
||
self.manager = manager or get_process_manager(logger)
|
||
# T22：属主标识——仅属主可终止（防提示注入跨会话杀 dev server）
|
||
self.owner = owner
|
||
|
||
def get_name(self) -> str:
|
||
return "bg_kill"
|
||
|
||
def get_description(self) -> str:
|
||
return ("终止后台进程（整个进程组，含子进程）。默认先 SIGTERM 优雅终止，"
|
||
"宽限期内未退出再 SIGKILL；force=true 直接 SIGKILL。对已退出进程幂等。")
|
||
|
||
def get_parameters(self) -> Dict:
|
||
return {
|
||
"type": "object",
|
||
"properties": {
|
||
"handle": {
|
||
"type": "integer",
|
||
"description": "bg_run 返回的句柄编号",
|
||
},
|
||
"force": {
|
||
"type": "boolean",
|
||
"description": "跳过优雅终止直接 SIGKILL（默认 false）",
|
||
},
|
||
"grace": {
|
||
"type": "number",
|
||
"description": "SIGTERM 后等待进程退出的宽限秒数（默认 3，上限 30）",
|
||
},
|
||
},
|
||
"required": ["handle"],
|
||
}
|
||
|
||
def execute(self, handle=None, force: bool = False, grace: float = 3.0, **kwargs) -> str:
|
||
if error := self.validate_params(["handle"], handle=handle):
|
||
return error
|
||
if not _enabled():
|
||
return "❌ 后台进程功能已禁用"
|
||
|
||
handle = _coerce_int(handle)
|
||
if handle is None:
|
||
return "❌ 错误：handle 必须是整数句柄"
|
||
|
||
# T18：force 字符串 "false" 会被裸 bool 判为 True，跳过宽限直接 SIGKILL
|
||
force = _coerce_bool(force, False)
|
||
|
||
result = self.manager.kill(handle, force=force, grace=grace, owner=self.owner)
|
||
if not result.get("ok"):
|
||
return self.format_result(False, f"终止后台进程 #{handle} 失败",
|
||
{"错误": result.get("error", "未知错误")})
|
||
data = {
|
||
"句柄": handle,
|
||
"状态": result["status"],
|
||
}
|
||
if result.get("exit_code") is not None:
|
||
data["返回码"] = result["exit_code"]
|
||
if result.get("already_finished"):
|
||
return self.format_result(True, f"后台进程 #{handle} 此前已结束", data)
|
||
return self.format_result(True, f"后台进程 #{handle} 已终止", data)
|