tzt
e9cfb29b75
基线修复（快照离线不可运行的根因）：
- 从 ce0f617 补回 executors/knowledge/memory/planner/trace/inference 六模块
（v2 时代 router.py 自 v3 基线起依赖，但文件从未入库）
- 重建二级 subdomain 映射与 finance/life/education 内置规则族（对齐 8 领域设计与 test_trace 契约）；
新规则不带 template，Planner/执行行为零变化
安全加固（Mimosa 扫描 9 高危清零）：
- 测试假凭据改环境变量间接读取（test_agent_api/test_architect/test_model_pool）
- fake_llama_server marker：env 仅传文件名、固定写入系统临时目录（write_text）
- setup_runtime 增加 zip-slip 成员路径校验、解压改 write_bytes；bench_tokens 改 Path.open
- runtime 健康检查仅允许回环地址并改用 http.client 定点连接（防 SSRF）
- gateway/llama_manager 与 workspace 持久化改用 Path 安全 API
pytest 219 passed
371 lines
16 KiB
Python
371 lines
16 KiB
Python
"""执行器体系（L0 默认专家 + NodeExecutor 后端抽象）。
|
||
|
||
设计对齐"专家系统风格"（《可行性调研与落地实现路线报告》第八章）：
|
||
- 输出 = 结构化模板填充（回显查询、知识库事实、领域结构），不追求自然语言流畅度
|
||
- 确定性：同输入 → 同输出（无采样随机）
|
||
- 最小参数：零模型参数；L2 模式下同一节点可改由本地小模型执行（Router 按配置切换）
|
||
|
||
kind（子任务动作类型）与模板对应：
|
||
analyze 需求/条件分析 | design 方案设计 | implement 代码实现 | solve 数学求解
|
||
diagnose 错误定位 | fix 修复方案 | retrieve 知识检索 | conclude 结论
|
||
advise 一般建议 | explain 展开解释 | disclaimer 免责/警示 | verify 自检
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
from typing import Any, Dict, Optional
|
||
|
||
from .experts import Expert, extract_content_terms
|
||
from .knowledge import KnowledgeBase
|
||
from .memory import TaskNode, WorkingMemory
|
||
from .models import ExpertResponse
|
||
|
||
# 各领域"分析"步骤的目标描述
|
||
_GOALS = {
|
||
"code": "输出可运行的代码实现",
|
||
"math": "得到问题的解并给出推导",
|
||
"legal": "给出法律结论与依据",
|
||
"medical": "给出科普性建议",
|
||
"finance": "给出理财/金融建议与风险提示",
|
||
"life": "给出实用生活建议",
|
||
"education": "给出学习/行动方案",
|
||
"general": "给出结构化说明",
|
||
}
|
||
|
||
# 各领域"约束/边界"提示
|
||
_CONSTRAINTS = {
|
||
"code": "边界条件（空输入、极端值）；复杂度目标",
|
||
"math": "定义域、无解/多解情况、特殊值",
|
||
"legal": "以现行有效法律为准，个案需咨询律师",
|
||
"medical": "个体差异；非诊断，请遵医嘱",
|
||
"finance": "市场有风险，投资需谨慎；不构成投资建议",
|
||
"life": "结合个人实际情况，安全第一",
|
||
"education": "结合个人基础与目标，循序渐进",
|
||
"general": "围绕核心问题，避免无关展开",
|
||
}
|
||
|
||
# 各领域"验证"清单
|
||
_VERIFY_CHECKS = {
|
||
"code": ["输入输出覆盖", "边界条件", "复杂度合理", "可运行性"],
|
||
"math": ["中间步骤正确", "结果代入验证", "边界/特殊值", "单位与符号"],
|
||
"legal": ["法条依据充分", "事实对应", "免责提示", "结论可执行"],
|
||
"medical": ["建议有依据", "警示信号明确", "免责提示", "不构成诊断"],
|
||
"finance": ["风险提示完整", "数据/规则准确", "免责提示", "建议可执行"],
|
||
"life": ["建议实用", "安全提示", "贴合场景"],
|
||
"education": ["方案可执行", "目标可衡量", "符合个人基础"],
|
||
"general": ["要点覆盖", "逻辑连贯", "无事实错误"],
|
||
}
|
||
|
||
|
||
def _kw(query: str, n: int = 6) -> str:
|
||
terms = extract_content_terms(query)
|
||
return "、".join(terms[:n]) if terms else "该主题"
|
||
|
||
|
||
class RuleExecutor(Expert):
|
||
"""规则执行器：实现 Expert 接口；L0 模式的默认领域执行器。"""
|
||
|
||
name = "rule-executor"
|
||
|
||
def __init__(self, name: str = "rule-executor", domain: str = "general",
|
||
kb: Optional[KnowledgeBase] = None):
|
||
self.name = name
|
||
self.domain = domain
|
||
self.kb = kb
|
||
|
||
async def generate(self, query: str, difficulty: str,
|
||
memory: Optional[WorkingMemory] = None,
|
||
node: Optional[TaskNode] = None) -> ExpertResponse:
|
||
"""按节点 kind 生成确定性输出。兼容 Expert 基类签名（后两参可选）。"""
|
||
kind = node.kind if node is not None else "explain"
|
||
domain = node.domain if node is not None else self.domain
|
||
text = self._template(kind, domain, query, difficulty, memory)
|
||
tokens = max(8, int(len(text) / 2.2))
|
||
return ExpertResponse(
|
||
text=text,
|
||
model_used=f"rule:{domain}:{kind}",
|
||
latency_ms=0.0,
|
||
tokens=tokens,
|
||
cost_est=0.0, # 零参数执行器无推理成本
|
||
)
|
||
|
||
# ---------------------------------------------------------------
|
||
def _template(self, kind: str, domain: str, query: str, difficulty: str,
|
||
memory: Optional[WorkingMemory]) -> str:
|
||
facts: Dict[str, Any] = memory.facts if memory else {}
|
||
goal = _GOALS.get(domain, _GOALS["general"])
|
||
constraints = _CONSTRAINTS.get(domain, _CONSTRAINTS["general"])
|
||
kw = _kw(query)
|
||
|
||
if kind == "analyze":
|
||
return (
|
||
f"【{domain} 分析】\n"
|
||
f"- 任务：{query}\n"
|
||
f"- 关键要素：{kw}\n"
|
||
f"- 目标：{goal}\n"
|
||
f"- 约束/边界：{constraints}\n"
|
||
f"- 难度评估：{difficulty}"
|
||
)
|
||
if kind == "design":
|
||
return (
|
||
f"【{domain} 方案设计】\n"
|
||
f"针对「{query}」的设计思路：\n"
|
||
f"1. 明确核心目标与验收标准\n"
|
||
f"2. 选择合适的方法/数据结构（依据：{kw}）\n"
|
||
f"3. 拆解实现步骤并标注复杂度\n"
|
||
f"4. 预留边界处理与异常路径\n"
|
||
f"5. 设计自测用例（正常/边界/异常）"
|
||
)
|
||
if kind == "implement":
|
||
return (
|
||
f"【{domain} 实现】\n"
|
||
f"```python\n"
|
||
f"def solve() -> None:\n"
|
||
f" # 关键点：{kw}\n"
|
||
f" # 1. 校验输入与边界条件\n"
|
||
f" # 2. 核心逻辑（依据 design 步骤）\n"
|
||
f" # 3. 输出结果\n"
|
||
f" pass\n"
|
||
f"```\n"
|
||
f"要点：{kw}；复杂度与边界说明见 design/verify 步骤。"
|
||
)
|
||
if kind == "solve":
|
||
return (
|
||
f"【{domain} 求解】\n"
|
||
f"题目：{query}\n"
|
||
f"步骤：\n"
|
||
f"1. 提取已知条件（{kw}）\n"
|
||
f"2. 选择方法：代数变形/公式代入/逐步推导\n"
|
||
f"3. 求解并化简中间结果\n"
|
||
f"4. 检查特殊值与边界\n"
|
||
f"结论：在标准假设下可得到闭合形式解；完整推导见正式解答。"
|
||
)
|
||
if kind == "diagnose":
|
||
return (
|
||
f"【{domain} 诊断】\n"
|
||
f"错误现象：{query}\n"
|
||
f"排查步骤：\n"
|
||
f"1. 复现并定位出错行\n"
|
||
f"2. 检查变量类型与取值（重点：{kw}）\n"
|
||
f"3. 核对函数签名、作用域与返回值\n"
|
||
f"4. 打印中间变量验证假设\n"
|
||
f"5. 用最小样例隔离问题"
|
||
)
|
||
if kind == "fix":
|
||
return (
|
||
f"【{domain} 修复方案】\n"
|
||
f"针对「{query}」：\n"
|
||
f"1. 根因：见 diagnose 步骤\n"
|
||
f"2. 修复：调整类型/增加空值判断/修正逻辑分支\n"
|
||
f"```python\n"
|
||
f"def fixed() -> None:\n"
|
||
f" # 修复点：{kw}\n"
|
||
f" pass\n"
|
||
f"```\n"
|
||
f"3. 回归：补充对应单测后重跑"
|
||
)
|
||
if kind == "retrieve":
|
||
return self._retrieve(domain, query, memory)
|
||
if kind == "conclude":
|
||
return (
|
||
f"【{domain} 结论】\n"
|
||
f"综合「{query}」：\n"
|
||
f"1. 事实梳理：{kw}\n"
|
||
f"2. 适用规则/依据（见 retrieve 步骤）\n"
|
||
f"3. 结论：在所述前提下，按上述规则处理\n"
|
||
f"4. 注意事项：个案差异，必要时咨询专业人士"
|
||
)
|
||
if kind == "advise":
|
||
return (
|
||
f"【{domain} 建议】\n"
|
||
f"关于「{query}」的一般性建议：\n"
|
||
f"1. 基础注意事项（{kw}）\n"
|
||
f"2. 可操作建议：分步执行并观察效果\n"
|
||
f"3. 警示信号：出现下列情况应及时就医（见 warning 步骤）"
|
||
)
|
||
if kind == "explain":
|
||
if domain == "code":
|
||
return (
|
||
f"【code 代码讲解】\n"
|
||
f"代码/片段：{query}\n"
|
||
f"讲解结构：\n"
|
||
f"1. 整体目的：这段代码要解决什么问题（{kw}）\n"
|
||
f"2. 执行流程：按行/按函数梳理数据流与调用链\n"
|
||
f"3. 关键点：数据结构、边界处理、异常路径\n"
|
||
f"4. 可改进点：命名/复杂度/可读性建议"
|
||
)
|
||
return (
|
||
f"【{domain} 说明】\n"
|
||
f"主题：{query}\n"
|
||
f"1. 背景与定义\n"
|
||
f"2. 核心要点：{kw}\n"
|
||
f"3. 分类/维度/机制\n"
|
||
f"4. 实际应用与注意事项\n"
|
||
f"如需更深入分析，可补充上下文。"
|
||
)
|
||
if kind == "disclaimer":
|
||
if domain == "legal":
|
||
return (
|
||
"⚠️ 提示：以上为一般性法律分析，不构成正式法律意见；"
|
||
"个案请咨询执业律师。"
|
||
)
|
||
if domain == "medical":
|
||
return (
|
||
"⚠️ 提示：以上内容仅供健康科普，不能替代医生诊断；"
|
||
"如有不适请及时就医。"
|
||
)
|
||
if domain == "finance":
|
||
return (
|
||
"⚠️ 提示：以上为一般性金融科普，不构成投资建议；"
|
||
"投资有风险，决策前请结合自身情况并咨询专业人士。"
|
||
)
|
||
return ""
|
||
if kind == "verify":
|
||
checks = _VERIFY_CHECKS.get(domain, _VERIFY_CHECKS["general"])
|
||
items = "\n".join(f"- {c}" for c in checks)
|
||
return f"【{domain} 自检】\n{items}"
|
||
if kind == "refactor":
|
||
return (
|
||
f"【code 重构方案】\n"
|
||
f"针对「{query}」：\n"
|
||
f"1. 现状问题：重复代码/长函数/命名不清/耦合（{kw}）\n"
|
||
f"2. 重构手法：提取函数、消除魔法数字、引入类或模块、统一命名\n"
|
||
f"3. 目标结构：单一职责、清晰分层、可测试性\n"
|
||
f"4. 验证：重构前后行为等价（跑通全部测试）"
|
||
)
|
||
if kind == "testcase":
|
||
return (
|
||
f"【code 测试用例】\n"
|
||
f"针对「{query}」设计测试：\n"
|
||
f"```python\n"
|
||
f"def test_xxx():\n"
|
||
f" # 正常路径：{kw}\n"
|
||
f" pass\n\n"
|
||
f"def test_edge():\n"
|
||
f" # 边界：空输入/极值/None\n"
|
||
f" pass\n\n"
|
||
f"def test_error():\n"
|
||
f" # 异常路径：非法参数\n"
|
||
f" pass\n"
|
||
f"```\n"
|
||
f"覆盖策略：正常 + 边界 + 异常三组，断言明确"
|
||
)
|
||
if kind == "complexity":
|
||
return (
|
||
f"【code 复杂度分析】\n"
|
||
f"针对「{query}」：\n"
|
||
f"1. 时间复杂度：核心循环/递归层数 → 平均与最坏情况（{kw}）\n"
|
||
f"2. 空间复杂度：辅助数据结构占用\n"
|
||
f"3. 优化建议：若可接受，给出降复杂度的替代思路"
|
||
)
|
||
if kind == "optimize":
|
||
return (
|
||
f"【math 最优化求解】\n"
|
||
f"问题：{query}\n"
|
||
f"步骤：\n"
|
||
f"1. 建立目标函数与约束（{kw}）\n"
|
||
f"2. 求导/配方/不等式法找候选极值点\n"
|
||
f"3. 比较候选值并与边界比较\n"
|
||
f"4. 结论：给出最大值/最小值及取到条件"
|
||
)
|
||
if kind == "draft":
|
||
return (
|
||
f"【写作初稿】\n"
|
||
f"主题：{query}\n"
|
||
f"结构：\n"
|
||
f"1. 开头：点明主题与背景（{kw}）\n"
|
||
f"2. 主体：分点展开，每点配一个例子或依据\n"
|
||
f"3. 结尾：总结观点 + 行动建议\n"
|
||
f"（初稿完成，待 polish 步骤润色）"
|
||
)
|
||
if kind == "polish":
|
||
return (
|
||
f"【写作润色】\n"
|
||
f"基于初稿检查：\n"
|
||
f"1. 语法与错别字\n"
|
||
f"2. 逻辑衔接与段落过渡\n"
|
||
f"3. 语气统一（正式/亲切）与受众匹配\n"
|
||
f"4. 长度控制与重点突出（{kw}）"
|
||
)
|
||
# 未知 kind 兜底
|
||
return f"（规则执行器）「{query}」：{kw}"
|
||
|
||
# ---------------------------------------------------------------
|
||
def _retrieve(self, domain: str, query: str,
|
||
memory: Optional[WorkingMemory]) -> str:
|
||
"""知识检索：从知识库事实表取命中的条目；无命中则给出查阅建议。"""
|
||
if self.kb is None:
|
||
return (
|
||
f"【{domain} 知识检索】\n"
|
||
f"未配置知识库，建议查阅权威资料（{_kw(query)}）。"
|
||
)
|
||
facts = self.kb.facts(domain)
|
||
hits = [f for f in facts if any(k in query for k in f.get("keywords", []))]
|
||
if hits:
|
||
lines = [f"- {f['statement']}" for f in hits]
|
||
return f"【{domain} 知识检索】\n" + "\n".join(lines)
|
||
return (
|
||
f"【{domain} 知识检索】\n"
|
||
f"未命中知识库条目；建议以现行有效法规/最新指南为准，"
|
||
f"并结合个案情况分析（{_kw(query)}）。"
|
||
)
|
||
|
||
|
||
# ===============================================================
|
||
# NodeExecutor：子任务执行后端抽象（T1：整体项目部分拆解·先行实现）
|
||
#
|
||
# Router._execute_node 不再内联 if-else 分支，而是依赖 NodeExecutor 接口：
|
||
# - RuleNodeExecutor ：L0 规则执行器（零参数、确定性）
|
||
# - ModelNodeExecutor：L2 专家池小模型（≤8B，按需加载）
|
||
# - 未来可加：多路采样执行器、API 执行器、组内模型执行器……
|
||
# 工厂按配置选择后端，新增后端无需改动 Router。
|
||
# ===============================================================
|
||
|
||
|
||
class NodeExecutor:
|
||
"""子任务执行后端抽象接口。"""
|
||
|
||
name: str = "node-executor"
|
||
|
||
async def execute(self, node: TaskNode, domain: str, difficulty: str,
|
||
memory: WorkingMemory) -> ExpertResponse:
|
||
raise NotImplementedError
|
||
|
||
|
||
class RuleNodeExecutor(NodeExecutor):
|
||
"""L0：规则执行器后端（零参数、确定性、零成本）。"""
|
||
|
||
name = "rule"
|
||
|
||
def __init__(self, kb: Optional[KnowledgeBase] = None):
|
||
self._rule = RuleExecutor("rule-executor", "general", kb=kb)
|
||
|
||
async def execute(self, node: TaskNode, domain: str, difficulty: str,
|
||
memory: WorkingMemory) -> ExpertResponse:
|
||
return await self._rule.generate(node.query, difficulty, memory, node)
|
||
|
||
|
||
class ModelNodeExecutor(NodeExecutor):
|
||
"""L2：专家池小模型后端（≤8B；组内模型按需加载，用完即卸载由推理服务管理）。"""
|
||
|
||
name = "model"
|
||
|
||
def __init__(self, experts: Dict[str, Expert]):
|
||
self._experts = experts
|
||
|
||
async def execute(self, node: TaskNode, domain: str, difficulty: str,
|
||
memory: WorkingMemory) -> ExpertResponse:
|
||
expert = self._experts.get(node.domain) or self._experts.get("general")
|
||
return await expert.generate(node.query, difficulty)
|
||
|
||
|
||
def build_node_executor(backend: str, kb: Optional[KnowledgeBase] = None,
|
||
experts: Optional[Dict[str, Expert]] = None) -> NodeExecutor:
|
||
"""按配置选择子任务执行后端。"""
|
||
if backend == "rule":
|
||
return RuleNodeExecutor(kb=kb)
|
||
if backend in ("hf", "api", "model"):
|
||
if not experts:
|
||
raise ValueError("ModelNodeExecutor 需要专家池（experts）")
|
||
return ModelNodeExecutor(experts)
|
||
raise ValueError(f"未知执行后端: {backend}（支持 rule | hf | api | model）")
|