307 lines
14 KiB
Python
307 lines
14 KiB
Python
"""声明式工具注册表(§3.4 / §7.5 #7;从 agent_builder.build_agent 析出,2026-07-23)。
|
||
|
||
背景:此前 build_agent 里 ~220 行工具注册,同一个「有 key/开关才注册」意图用了
|
||
四种写法(inline getenv / `*_configured()` 助手 / `Config.load()` 返 None / caps
|
||
开关),约定靠注释里的"沿用范式"口头传承。本模块把它收敛为一张表:
|
||
|
||
(组名, gate, factory)
|
||
|
||
- gate:零参 -> bool。env key / 渠道开关 / 能力开关全走这一种形态,False 则该组
|
||
工具对本 run 不存在(agent 看不到一个永远报错的工具 —— §7.5 #7 红线的代码强制)。
|
||
- factory:零参 -> list[Tool]。变体选择(如 seedance/vision 取 yaml 第一个 variant)
|
||
在 factory 里做,选不出返 [] 即自然不挂。
|
||
|
||
新增工具 = 表里加一行。ToolContext 装 build_agent 已解析好的上下文(路径 / 身份 /
|
||
媒体配置),factory 从 ctx 取参 —— 不在本模块重复读 env / yaml。
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import os
|
||
from dataclasses import dataclass
|
||
from pathlib import Path
|
||
from typing import Any, Callable, Optional
|
||
from uuid import UUID
|
||
|
||
from tools.ask_user import AskUserTool
|
||
from tools.check_process import CheckProcessTool
|
||
from tools.documents import DocumentDownloadTool, DocumentListKbTool, DocumentSearchTool
|
||
from tools.external_systems import (
|
||
ExternalSystemCallTool,
|
||
ExternalSystemListTool,
|
||
ExternalSystemResultReadTool,
|
||
ExternalSystemSearchTool,
|
||
)
|
||
from tools.fs import EditTool, GlobTool, GrepTool, ReadTool, WriteTool
|
||
from tools.gpt_image import GptImageTool
|
||
from tools.look_at_image import LookAtImageTool
|
||
from tools.materials_project import (
|
||
MaterialsProjectGetEntriesTool,
|
||
MaterialsProjectGetStructureTool,
|
||
MaterialsProjectSearchSummaryTool,
|
||
)
|
||
from tools.office_to_pdf import OfficeToPdfTool
|
||
from tools.read_document import ReadDocumentTool
|
||
from tools.rename_working_dir import RenameWorkingDirTool
|
||
from tools.run_python import RunPythonTool
|
||
from tools.schedule import (
|
||
ScheduleCancelTool, ScheduleCreateTool, ScheduleListTool, ScheduleUpdateTool,
|
||
)
|
||
from tools.seedance import SeedanceTool
|
||
from tools.seedream import SeedreamTool
|
||
from tools.send_email import SendEmailTool, smtp_configured
|
||
from tools.shell import ShellTool
|
||
from tools.skill_authoring import ForkSkillTool, SaveSkillTool
|
||
from tools.skill_tool import LoadSkillTool
|
||
from tools.task_progress import TaskProgressTool
|
||
from tools.transcribe_audio import TranscribeAudioTool
|
||
from tools.web_fetch import WebFetchTool
|
||
from tools.web_search import WebSearchTool
|
||
from tools.wechat_bot import WechatPushTool, wechat_push_available
|
||
|
||
from core.asr_lfasr import is_configured as lfasr_configured
|
||
from core.bocha_client import BochaConfig
|
||
from core.task_actions import DeferredTaskActions
|
||
|
||
|
||
@dataclass
|
||
class ToolContext:
|
||
"""build_agent 解析好的、工具装配需要的全部上下文。"""
|
||
tool_base: Path # fs/shell 类工具的 base_dir(cwd / task 目录)
|
||
ur_path: Path # user_root(输出渲染相对路径 + host-side 落点)
|
||
working_dir_path: Path # 该 task 的宿主工作目录绝对路径
|
||
task_id: UUID
|
||
uid: UUID
|
||
cfg: dict # config/agent.yaml(quotas 段)
|
||
caps: Any # ModelCapabilities(enable_run_python)
|
||
skills: Any # SkillRegistry
|
||
cancel_check: Optional[Callable[[], bool]]
|
||
scheduled_run: bool
|
||
deferred_actions: DeferredTaskActions
|
||
# 媒体(上游已 load 一次,避免重复读 yaml):
|
||
ark_cfg: Any # ArkConfig | None(豆包;None=ARK_API_KEY 缺)
|
||
img_provider: str # "doubao" / "unifyllm" / ""
|
||
img_key: str # 选中的 image variant key
|
||
img_cfg: Optional[dict] # 选中的 image variant 配置(None=不挂图像工具)
|
||
img_provider_cfg: Any # 该 provider 的 ArkConfig
|
||
video_variant: str # caller 指定的 video variant key(空=yaml 第一个)
|
||
office_to_pdf_available: bool # backend host 是否可调用 LibreOffice
|
||
|
||
|
||
def _env_set(name: str) -> Callable[[], bool]:
|
||
return lambda: bool(os.getenv(name, "").strip())
|
||
|
||
|
||
def _pick_variant(section: dict, preferred: str = "") -> tuple[str, Optional[dict]]:
|
||
"""从 yaml 段选 variant:preferred 命中优先,否则第一个 dict 条目;无 → ("", None)。"""
|
||
if preferred:
|
||
v = section.get(preferred)
|
||
if isinstance(v, dict):
|
||
return preferred, v
|
||
for key, v in section.items():
|
||
if isinstance(v, dict):
|
||
return key, v
|
||
return "", None
|
||
|
||
|
||
def build_tools(ctx: ToolContext) -> dict[str, Any]:
|
||
"""按注册表装配本 run 的工具集。gate=False / factory 返 [] 的组自然不挂。"""
|
||
base = dict(base_dir=ctx.tool_base, user_root=ctx.ur_path)
|
||
wd_base = dict(base_dir=ctx.working_dir_path, user_root=ctx.ur_path)
|
||
quotas = ctx.cfg.get("quotas") or {}
|
||
images_per_day = int(quotas.get("images_per_day", 0))
|
||
videos_per_day = int(quotas.get("videos_per_day", 0))
|
||
|
||
def _core() -> list:
|
||
# shell/run_python 带 task_id:background=true 的 bg proc 状态锚定
|
||
# `<user_root>/.zcbot_procs/<task_id>/`(DESIGN §8.12)。check_process 是它们的
|
||
# 配套查询/终止工具,host in-process(docker 模式下状态文件也在宿主侧)。
|
||
# web_fetch 无需 API key,始终可用。
|
||
return [
|
||
TaskProgressTool(**base),
|
||
AskUserTool(**base),
|
||
ReadTool(**base), WriteTool(**base), EditTool(**base),
|
||
GlobTool(**base), GrepTool(**base),
|
||
ShellTool(task_id=str(ctx.task_id), **base),
|
||
CheckProcessTool(task_id=str(ctx.task_id), **base),
|
||
WebFetchTool(**base),
|
||
]
|
||
|
||
def _task_actions() -> list:
|
||
from tools.publish_artifacts import PublishArtifactsTool
|
||
return [
|
||
RenameWorkingDirTool(
|
||
ctx.deferred_actions,
|
||
working_dir=ctx.working_dir_path,
|
||
**base,
|
||
),
|
||
PublishArtifactsTool(
|
||
working_dir=ctx.working_dir_path,
|
||
**wd_base,
|
||
),
|
||
]
|
||
|
||
def _document_search() -> list:
|
||
return [
|
||
DocumentListKbTool(**base),
|
||
DocumentSearchTool(**base),
|
||
DocumentDownloadTool(working_dir=ctx.working_dir_path, **base),
|
||
]
|
||
|
||
def _materials_project() -> list:
|
||
return [
|
||
MaterialsProjectSearchSummaryTool(working_dir=ctx.working_dir_path, **base),
|
||
MaterialsProjectGetStructureTool(working_dir=ctx.working_dir_path, **base),
|
||
MaterialsProjectGetEntriesTool(working_dir=ctx.working_dir_path, **base),
|
||
]
|
||
|
||
def _external_systems() -> list:
|
||
result_budget: dict[str, int] = {}
|
||
return [
|
||
ExternalSystemListTool(ctx.uid, **base),
|
||
ExternalSystemSearchTool(ctx.uid, **base),
|
||
ExternalSystemCallTool(
|
||
ctx.uid,
|
||
task_id=ctx.task_id,
|
||
result_budget=result_budget,
|
||
**wd_base,
|
||
),
|
||
ExternalSystemResultReadTool(
|
||
ctx.uid,
|
||
task_id=ctx.task_id,
|
||
result_budget=result_budget,
|
||
**wd_base,
|
||
),
|
||
]
|
||
|
||
def _load_skill() -> list:
|
||
# LoadSkillTool 返回头里的 dir 由 registry 按 skill.source 给容器内路径
|
||
# (内置 → /sandbox/skills,用户 → /workspace/.skills);host backend → host 绝对路径。
|
||
return [LoadSkillTool(registry=ctx.skills, **base)]
|
||
|
||
def _skill_authoring() -> list:
|
||
# 用户 skill 创作:恒挂(每个用户都能造自己的 skill)。host-side 直接写
|
||
# user_root/.skills —— 不走沙箱 fs(其 base_dir 锚 cwd / 容器 wd,够不到 .skills)。
|
||
d = ctx.ur_path / ".skills"
|
||
return [
|
||
SaveSkillTool(d, ctx.skills, **base),
|
||
ForkSkillTool(d, ctx.skills, **base),
|
||
]
|
||
|
||
def _schedules() -> list:
|
||
# 定时任务管理(§8.5)增删查。user_id 由 ctor 注入,不信模型传的 id。
|
||
return [
|
||
ScheduleCreateTool(ctx.uid, **base),
|
||
ScheduleListTool(ctx.uid, **base),
|
||
ScheduleUpdateTool(ctx.uid, **base),
|
||
ScheduleCancelTool(ctx.uid, **base),
|
||
]
|
||
|
||
def _send_email() -> list:
|
||
# base_dir 用 working_dir_path(宿主 task 目录):send_email 在宿主进程读附件,
|
||
# docker 下 agent 给的相对路径相对容器 workdir=task_dir,翻回宿主即 working_dir_path;
|
||
# tool 内 _resolve_user_file 再处理 /workspace 容器绝对路径。
|
||
return [SendEmailTool(**wd_base)]
|
||
|
||
def _wechat_push() -> list:
|
||
# base_dir 同 send_email(宿主进程读待发文件)。交互与定时 run 都可用
|
||
# (定时简报可主动推回用户微信,24h 窗口内)。
|
||
return [WechatPushTool(ctx.uid, task_id=ctx.task_id, **wd_base)]
|
||
|
||
def _run_python() -> list:
|
||
return [RunPythonTool(task_id=str(ctx.task_id), **base)]
|
||
|
||
def _office_to_pdf() -> list:
|
||
# LibreOffice 只装在 backend host；Docker agent 通过 typed tool 转换用户目录内
|
||
# 已有 Office 文件，不在沙盒 shell 里寻找/安装 soffice。
|
||
return [OfficeToPdfTool(**wd_base)]
|
||
|
||
def _image() -> list:
|
||
# 图像生成跨 provider 二选一(选择在 build_agent 上半部定好,与 system prompt
|
||
# 媒体段同源);本次 run 锁定该 variant,下一条消息可重选。
|
||
if ctx.img_cfg is None:
|
||
return []
|
||
cls_kwargs: dict[str, Any] = dict(
|
||
image_variant_cfg=ctx.img_cfg, variant_key=ctx.img_key,
|
||
working_dir=ctx.working_dir_path, task_id=ctx.task_id, user_id=ctx.uid,
|
||
daily_limit=images_per_day, **base,
|
||
)
|
||
if ctx.img_provider == "doubao":
|
||
return [SeedreamTool(ark_cfg=ctx.img_provider_cfg, **cls_kwargs)]
|
||
return [GptImageTool(gw_cfg=ctx.img_provider_cfg, **cls_kwargs)]
|
||
|
||
def _video() -> list:
|
||
# 视频仍豆包独有。cancel_check:轮询期(典型 30-90s)响应用户停止按钮;
|
||
# 远端 cgt 任务无 cancel API,best-effort 不动远端。
|
||
key, v = _pick_variant(ctx.ark_cfg.raw.get("video") or {}, ctx.video_variant)
|
||
if v is None:
|
||
return []
|
||
return [SeedanceTool(
|
||
ark_cfg=ctx.ark_cfg, video_variant_cfg=v, variant_key=key,
|
||
working_dir=ctx.working_dir_path, task_id=ctx.task_id, user_id=ctx.uid,
|
||
cancel_check=ctx.cancel_check, daily_limit=videos_per_day, **base,
|
||
)]
|
||
|
||
def _vision() -> list:
|
||
# 看图 + 文档理解共用 vision variant(读图不分档,固定第一个)。
|
||
key, v = _pick_variant(ctx.ark_cfg.raw.get("vision") or {})
|
||
if v is None:
|
||
return []
|
||
kw = dict(
|
||
ark_cfg=ctx.ark_cfg, vision_variant_cfg=v, variant_key=key,
|
||
working_dir=ctx.working_dir_path, task_id=ctx.task_id, user_id=ctx.uid,
|
||
**base,
|
||
)
|
||
return [LookAtImageTool(**kw), ReadDocumentTool(**kw)]
|
||
|
||
def _transcribe() -> list:
|
||
# 录音文件转写(讯飞 LFASR,与 IAT 听写是两个服务两套 key)。
|
||
return [TranscribeAudioTool(
|
||
working_dir=ctx.working_dir_path, cancel_check=ctx.cancel_check, **base,
|
||
)]
|
||
|
||
def _web_search() -> list:
|
||
cfg = BochaConfig.load()
|
||
assert cfg is not None
|
||
return [WebSearchTool(cfg=cfg)]
|
||
|
||
# ── 注册表:(组名, gate, factory)。gate 判定统一零参 bool;新工具在此加行 ──
|
||
registry: list[tuple[str, Callable[[], bool], Callable[[], list]]] = [
|
||
("core", lambda: True, _core),
|
||
# 当前 working_dir 只能延迟到交互 run 收尾后改名；定时 run 不允许自行改目录。
|
||
("task_actions", lambda: not ctx.scheduled_run, _task_actions),
|
||
# Secret-bearing 域工具一律 host-side、仅对应 env 存在才注册(§7.5 #7):
|
||
# key 绝不进 run_python / 沙箱。
|
||
("document_search", _env_set("DOCUMENT_SEARCH_API_KEY"), _document_search),
|
||
("materials_project", _env_set("MP_API_KEY"), _materials_project),
|
||
("external_systems", lambda: _external_systems_available(ctx.uid), _external_systems),
|
||
("load_skill", lambda: bool(ctx.skills.skills), _load_skill),
|
||
("skill_authoring", lambda: True, _skill_authoring),
|
||
# 定时 run 内不挂 schedule_*(防任务造任务自我繁殖);仅交互对话可建/管 job。
|
||
("schedules", lambda: not ctx.scheduled_run, _schedules),
|
||
("send_email", smtp_configured, _send_email),
|
||
("wechat_push", wechat_push_available, _wechat_push),
|
||
("run_python", lambda: ctx.caps.enable_run_python, _run_python),
|
||
("office_to_pdf", lambda: ctx.office_to_pdf_available, _office_to_pdf),
|
||
("image", lambda: ctx.img_cfg is not None, _image),
|
||
("video", lambda: ctx.ark_cfg is not None, _video),
|
||
("vision", lambda: ctx.ark_cfg is not None, _vision),
|
||
("transcribe_audio", lfasr_configured, _transcribe),
|
||
("web_search", lambda: BochaConfig.load() is not None, _web_search),
|
||
]
|
||
|
||
tools: dict[str, Any] = {}
|
||
for _name, gate, factory in registry:
|
||
if gate():
|
||
for t in factory():
|
||
tools[t.name] = t
|
||
return tools
|
||
|
||
|
||
def _external_systems_available(user_id: UUID) -> bool:
|
||
"""DB/env 双 gate；失败即不挂工具，不给模型一个永远报错的入口。"""
|
||
try:
|
||
from core.external_systems.service import external_system_tools_available
|
||
return external_system_tools_available(user_id)
|
||
except Exception:
|
||
return False
|