Files
beaver_project/app-instance/backend/beaver/skills/learning/evidence.py
steven_li 9d6cde2d23 feat: 将项目从nano重命名为beaver并更新相关配置
- 将所有环境变量前缀从NANO_改为BEAVER_
- 更新README.md文档内容,包括项目介绍、组件说明和快速开始指南
- 修改.gitignore文件,添加auth-portal运行时路径排除规则
- 更新app-instance镜像标签从nano/app-instance改为beaver/app-instance
- 增强技能安全检查器,支持工具前缀白名单功能
- 添加技能草稿重新检查安全性API端点
- 扩展证据选择器,收集工具调用名称用于技能学习
- 改进技能合成器,基于实际调用的工具生成工具提示
- 优化路由超时处理机制,增加重试逻辑
- 更新后端架构文档,添加可视化入口和基础概念说明
- 实现在WebSocket消息中传递工具迭代次数信息
2026-05-20 18:01:06 +08:00

120 lines
4.9 KiB
Python

"""Evidence selection for skill learning."""
from __future__ import annotations
from dataclasses import dataclass, field
from typing import Any
from beaver.engine.session.manager import SessionManager
from beaver.memory.runs.store import RunMemoryStore
@dataclass(slots=True)
class EvidencePacket:
run_ids: list[str]
session_ids: list[str]
task_summaries: list[str]
session_excerpts: list[str]
metadata: dict[str, Any] = field(default_factory=dict)
class EvidenceSelector:
def __init__(self, run_store: RunMemoryStore, session_manager: SessionManager | None = None) -> None:
self.run_store = run_store
self.session_manager = session_manager
def select_runs_for_revision(self, skill_name: str, version: str, limit: int = 5) -> list[str]:
runs = self.run_store.list_runs_by_skill(skill_name, version=version, limit=limit)
return [record.run_id for record in runs]
def select_runs_for_new_skill(self, theme: str, limit: int = 5) -> list[str]:
lowered = theme.lower().strip()
matches = []
for record in self.run_store.list_runs():
if lowered and lowered not in record.task_text.lower():
continue
matches.append(record.run_id)
return matches[-limit:]
def build_evidence_packet(self, run_ids: list[str], session_ids: list[str] | None = None) -> EvidencePacket:
runs_by_id = {record.run_id: record for record in self.run_store.list_runs()}
resolved_run_ids: list[str] = []
resolved_session_ids: list[str] = list(dict.fromkeys(session_ids or []))
task_summaries: list[str] = []
session_excerpts: list[str] = []
tool_names: list[str] = []
selected_tool_names: list[str] = []
for run_id in run_ids:
record = runs_by_id.get(run_id)
if record is None:
continue
resolved_run_ids.append(run_id)
if record.session_id not in resolved_session_ids:
resolved_session_ids.append(record.session_id)
summary = record.task_text.strip()
if summary:
task_summaries.append(summary[:400])
if self.session_manager is not None:
excerpt = self._session_excerpt(record.session_id, run_id)
if excerpt:
session_excerpts.append(excerpt)
run_tool_names, run_selected_tool_names = self._run_tool_names(record.session_id, run_id)
tool_names.extend(run_tool_names)
selected_tool_names.extend(run_selected_tool_names)
return EvidencePacket(
run_ids=resolved_run_ids,
session_ids=resolved_session_ids,
task_summaries=task_summaries[:8],
session_excerpts=session_excerpts[:6],
metadata={
"bounded": True,
"tool_names": _unique_strings(tool_names),
"selected_tool_names": _unique_strings(selected_tool_names),
},
)
def _session_excerpt(self, session_id: str, run_id: str) -> str:
if self.session_manager is None:
return ""
events = self.session_manager.get_run_event_records(session_id, run_id)
visible: list[str] = []
for event in events:
if not event.context_visible or not event.content:
continue
visible.append(f"{event.role}: {event.content.strip()}")
return "\n".join(visible[:12])[:2000]
def _run_tool_names(self, session_id: str, run_id: str) -> tuple[list[str], list[str]]:
if self.session_manager is None:
return [], []
names: list[str] = []
selected_names: list[str] = []
for event in self.session_manager.get_run_event_records(session_id, run_id):
if event.tool_name:
names.append(event.tool_name)
if event.tool_calls:
for call in event.tool_calls:
if not isinstance(call, dict):
continue
name = call.get("name")
function = call.get("function")
if not name and isinstance(function, dict):
name = function.get("name")
if name:
names.append(str(name))
if event.event_type == "tool_selection_snapshotted" and isinstance(event.event_payload, dict):
selected = event.event_payload.get("tool_names")
if isinstance(selected, list):
selected_names.extend(str(item) for item in selected if str(item).strip())
return _unique_strings(names), _unique_strings(selected_names)
def _unique_strings(values: list[str]) -> list[str]:
result: list[str] = []
for value in values:
cleaned = str(value).strip()
if cleaned and cleaned not in result:
result.append(cleaned)
return result