""" 查找树节点 Tool - 人设树节点查询 功能： 1. 获取人设树的常量节点（全局常量、局部常量） 2. 获取符合条件概率阈值的节点（按条件概率排序返回 topN） """ import importlib.util import json from pathlib import Path from typing import Any, Optional try: from agent.tools import tool, ToolResult, ToolContext except ImportError: def tool(*args, **kwargs): return lambda f: f ToolResult = None # 仅用 main() 测核心逻辑时可无 agent ToolContext = None # 加载同目录层级的 conditional_ratio_calc（不依赖包结构） _utils_dir = Path(__file__).resolve().parent.parent / "utils" _cond_spec = importlib.util.spec_from_file_location( "conditional_ratio_calc", _utils_dir / "conditional_ratio_calc.py", ) _cond_mod = importlib.util.module_from_spec(_cond_spec) _cond_spec.loader.exec_module(_cond_mod) calc_node_conditional_ratio = _cond_mod.calc_node_conditional_ratio # 相对本文件：tools -> overall_derivation，input 在 overall_derivation 下 _BASE_INPUT = Path(__file__).resolve().parent.parent / "input" def _tree_dir(account_name: str) -> Path: """人设树目录：../input/{account_name}/原始数据/tree/""" return _BASE_INPUT / account_name / "原始数据" / "tree" def _load_trees(account_name: str) -> list[tuple[str, dict]]: """加载该账号下所有维度的人设树。返回 [(维度名, 根节点 dict), ...]。""" td = _tree_dir(account_name) if not td.is_dir(): return [] result = [] for p in td.glob("*.json"): try: with open(p, "r", encoding="utf-8") as f: data = json.load(f) for dim_name, root in data.items(): if isinstance(root, dict): result.append((dim_name, root)) break except Exception: continue return result def _iter_all_nodes(account_name: str): """遍历该账号下所有人设树节点，产出 (节点名称, 父节点名称, 节点 dict)。""" for dim_name, root in _load_trees(account_name): def walk(parent_name: str, node_dict: dict): for name, child in (node_dict.get("children") or {}).items(): if not isinstance(child, dict): continue yield (name, parent_name, child) yield from walk(name, child) yield from walk(dim_name, root) # --------------------------------------------------------------------------- # 1. 获取人设树常量节点 # --------------------------------------------------------------------------- def get_constant_nodes(account_name: str) -> list[dict[str, Any]]: """ 获取人设树的常量节点。 - 全局常量：_is_constant=True - 局部常量：_is_local_constant=True 且 _is_constant=False 返回列表项：节点名称、概率(_ratio)、常量类型。 """ result = [] for node_name, _parent, node in _iter_all_nodes(account_name): is_const = node.get("_is_constant") is True is_local = node.get("_is_local_constant") is True if is_const: const_type = "全局常量" elif is_local and not is_const: const_type = "局部常量" else: continue ratio = node.get("_ratio") result.append({ "节点名称": node_name, "概率": ratio, "常量类型": const_type, }) result.sort(key=lambda x: (x["概率"] is None, -(x["概率"] or 0))) return result # --------------------------------------------------------------------------- # 2. 获取符合条件概率阈值的节点 # --------------------------------------------------------------------------- def get_nodes_by_conditional_ratio( account_name: str, derived_list: list[tuple[str, str]], threshold: float, top_n: int, ) -> list[dict[str, Any]]: """ 获取人设树中条件概率 >= threshold 的节点，按条件概率降序，返回前 top_n 个。 derived_list: 已推导列表，每项 (已推导的选题点, 推导来源人设树节点)。 返回列表项：节点名称、条件概率、父节点名称。 """ base_dir = _BASE_INPUT node_to_parent: dict[str, str] = {} for node_name, parent_name, _ in _iter_all_nodes(account_name): node_to_parent[node_name] = parent_name scored: list[tuple[str, float, str]] = [] for node_name, parent_name in node_to_parent.items(): ratio = calc_node_conditional_ratio( account_name, derived_list, node_name, base_dir=base_dir ) if ratio >= threshold: scored.append((node_name, ratio, parent_name)) scored.sort(key=lambda x: x[1], reverse=True) top = scored[:top_n] return [ {"节点名称": name, "条件概率": ratio, "父节点名称": parent} for name, ratio, parent in top ] def _parse_derived_list(derived_items: list[dict[str, str]]) -> list[tuple[str, str]]: """将 agent 传入的 [{"topic": "x", "source_node": "y"}, ...] 转为 DerivedItem 列表。""" out = [] for item in derived_items: if isinstance(item, dict): topic = item.get("topic") or item.get("已推导的选题点") source = item.get("source_node") or item.get("推导来源人设树节点") if topic is not None and source is not None: out.append((str(topic).strip(), str(source).strip())) elif isinstance(item, (list, tuple)) and len(item) >= 2: out.append((str(item[0]).strip(), str(item[1]).strip())) return out # --------------------------------------------------------------------------- # Agent Tools（参考 glob_tool 封装） # --------------------------------------------------------------------------- @tool(description="获取人设树的常量节点（全局常量、局部常量）。输入账号名，返回节点名称、概率、常量类型。") async def find_tree_constant_nodes( account_name: str, context: Optional[ToolContext] = None, ) -> ToolResult: """ 获取人设树的常量节点。 读取该账号 input/{account_name}/原始数据/tree/ 下的人设树 JSON， 筛选 _is_constant=true（全局常量）或 _is_local_constant=true 且 _is_constant=false（局部常量）的节点， 返回：节点名称、概率(_ratio)、常量类型。 """ tree_dir = _tree_dir(account_name) if not tree_dir.is_dir(): return ToolResult( title="人设树目录不存在", output=f"目录不存在: {tree_dir}", error="Directory not found", ) try: items = get_constant_nodes(account_name) if not items: output = "未找到常量节点" else: lines = [f"- {x['节点名称']}\t概率={x['概率']}\t{x['常量类型']}" for x in items] output = "\n".join(lines) return ToolResult( title=f"常量节点 ({account_name})", output=output, metadata={"account_name": account_name, "count": len(items), "items": items}, ) except Exception as e: return ToolResult( title="获取常量节点失败", output=str(e), error=str(e), ) @tool( description="获取人设树中条件概率不低于阈值的节点，按条件概率从高到低返回 topN。" "输入：账号名、已推导选题点列表、条件概率阈值、topN。" ) async def find_tree_nodes_by_conditional_ratio( account_name: str, derived_items: list[dict[str, str]], conditional_ratio_threshold: float, top_n: int = 20, context: Optional[ToolContext] = None, ) -> ToolResult: """ 获取人设树中符合条件概率阈值的节点。 已推导选题点 derived_items：每项为 {\"topic\": \"已推导选题点\", \"source_node\": \"推导来源人设树节点\"}。 返回：节点名称、条件概率、父节点名称，按条件概率降序最多 top_n 条。 """ tree_dir = _tree_dir(account_name) if not tree_dir.is_dir(): return ToolResult( title="人设树目录不存在", output=f"目录不存在: {tree_dir}", error="Directory not found", ) try: derived_list = _parse_derived_list(derived_items) if not derived_list: return ToolResult( title="参数无效", output="derived_items 不能为空，且每项需包含 topic 与 source_node（或 已推导的选题点 与 推导来源人设树节点）", error="Invalid derived_items", ) items = get_nodes_by_conditional_ratio( account_name, derived_list, conditional_ratio_threshold, top_n ) if not items: output = f"未找到条件概率 >= {conditional_ratio_threshold} 的节点" else: lines = [ f"- {x['节点名称']}\t条件概率={x['条件概率']}\t父节点={x['父节点名称']}" for x in items ] output = "\n".join(lines) return ToolResult( title=f"条件概率节点 ({account_name}, 阈值={conditional_ratio_threshold})", output=output, metadata={ "account_name": account_name, "threshold": conditional_ratio_threshold, "top_n": top_n, "count": len(items), "items": items, }, ) except Exception as e: return ToolResult( title="按条件概率查询节点失败", output=str(e), error=str(e), ) def main() -> None: """本地测试：用家有大志账号测常量节点与条件概率节点，有 agent 时再跑一遍 tool 接口。""" import asyncio account_name = "家有大志" derived_items = [ {"topic": "分享", "source_node": "分享"}, ] conditional_ratio_threshold = 0.1 top_n = 10 # 1）常量节点 constant_nodes = get_constant_nodes(account_name) print(f"账号: {account_name} — 常量节点共 {len(constant_nodes)} 个（前 50 个）:") for x in constant_nodes[:50]: print(f" - {x['节点名称']}\t概率={x['概率']}\t{x['常量类型']}") print() # 2）条件概率节点（核心函数） derived_list = _parse_derived_list(derived_items) ratio_nodes = get_nodes_by_conditional_ratio( account_name, derived_list, conditional_ratio_threshold, top_n ) print(f"条件概率节点 阈值={conditional_ratio_threshold}, top_n={top_n}, 共 {len(ratio_nodes)} 个:") for x in ratio_nodes: print(f" - {x['节点名称']}\t条件概率={x['条件概率']}\t父节点={x['父节点名称']}") print() # 3）有 agent 时通过 tool 接口再跑一遍 if ToolResult is not None: async def run_tools(): r1 = await find_tree_constant_nodes(account_name) print("--- find_tree_constant_nodes ---") print(r1.output[:200] + "..." if len(r1.output) > 200 else r1.output) r2 = await find_tree_nodes_by_conditional_ratio( account_name, derived_items=derived_items, conditional_ratio_threshold=conditional_ratio_threshold, top_n=top_n, ) print("\n--- find_tree_nodes_by_conditional_ratio ---") print(r2.output) asyncio.run(run_tools()) if __name__ == "__main__": main()