feat(app-instance): 集成Beaver后端并更新配置管理
集成新的Beaver后端服务到应用实例中，替换原有的nanobot实现。 主要变更包括： - 在Dockerfile和环境配置中添加Beaver相关路径和配置变量 - 更新工作目录结构从.nanobot到.beaver - 实现Beaver引擎加载器，支持配置文件加载和工具组装 - 添加内置工具如ListDirectoryTool、ReadFileTool、SearchFilesTool - 更新消息处理流程，支持通道适配器和网关模式 - 重构技能系统，支持显式工具提示和嵌入式检索 - 改进错误处理和生命周期管理 此变更使应用实例能够使用统一的Beaver后端进行AI代理运行时管理。
This commit is contained in:
@ -1,7 +1,12 @@
|
||||
"""Skill system for Beaver."""
|
||||
"""Skill system for Beaver.
|
||||
|
||||
from .assembler import SkillAssembler, SkillAssemblyResult, SkillEmbeddingRetriever
|
||||
from .catalog import SkillRecord, SkillsLoader
|
||||
顶层包保持 lazy export，避免只导入 catalog/loader 时顺带拉起
|
||||
SkillAssembler -> provider -> litellm 这条重依赖链。
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any
|
||||
|
||||
__all__ = [
|
||||
"SkillAssembler",
|
||||
@ -10,3 +15,22 @@ __all__ = [
|
||||
"SkillRecord",
|
||||
"SkillsLoader",
|
||||
]
|
||||
|
||||
|
||||
def __getattr__(name: str) -> Any:
|
||||
if name in {"SkillAssembler", "SkillAssemblyResult", "SkillEmbeddingRetriever"}:
|
||||
from .assembler import SkillAssembler, SkillAssemblyResult, SkillEmbeddingRetriever
|
||||
|
||||
return {
|
||||
"SkillAssembler": SkillAssembler,
|
||||
"SkillAssemblyResult": SkillAssemblyResult,
|
||||
"SkillEmbeddingRetriever": SkillEmbeddingRetriever,
|
||||
}[name]
|
||||
if name in {"SkillRecord", "SkillsLoader"}:
|
||||
from .catalog import SkillRecord, SkillsLoader
|
||||
|
||||
return {
|
||||
"SkillRecord": SkillRecord,
|
||||
"SkillsLoader": SkillsLoader,
|
||||
}[name]
|
||||
raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
|
||||
|
||||
@ -1,188 +1,9 @@
|
||||
"""Embedding-based skill candidate retrieval.
|
||||
|
||||
当前实现使用 OpenAI-compatible `/v1/embeddings` 接口调用
|
||||
阿里云百炼 `text-embedding-v4` 做最小语义召回：
|
||||
1. 复用当前 provider 的 `api_key/api_base`
|
||||
2. 先用 embedding 相似度召回一小批候选
|
||||
3. 再交给上层 LLM selector 做最终技能选择
|
||||
"""
|
||||
"""Embedding-based skill candidate retrieval."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import math
|
||||
import os
|
||||
import json
|
||||
from urllib import request
|
||||
from typing import Any
|
||||
from beaver.foundation.embedding import EmbeddingRetriever
|
||||
|
||||
|
||||
class SkillEmbeddingRetriever:
|
||||
class SkillEmbeddingRetriever(EmbeddingRetriever):
|
||||
"""用 OpenAI-compatible embeddings API 为 skill 选择做候选召回。"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
api_key_env: str = "OPENAI_API_KEY",
|
||||
api_base_env: str = "OPENAI_API_BASE",
|
||||
model: str = "text-embedding-v4",
|
||||
timeout_seconds: float = 20.0,
|
||||
) -> None:
|
||||
self.api_key_env = api_key_env
|
||||
self.api_base_env = api_base_env
|
||||
self.model = model
|
||||
self.timeout_seconds = timeout_seconds
|
||||
|
||||
async def retrieve(
|
||||
self,
|
||||
*,
|
||||
query: str,
|
||||
candidates: list[dict[str, str]],
|
||||
top_k: int = 12,
|
||||
api_key: str | None = None,
|
||||
api_base: str | None = None,
|
||||
model: str | None = None,
|
||||
) -> list[dict[str, str]]:
|
||||
"""按 embedding 相似度召回 top-k 候选。
|
||||
|
||||
如果没有可用的 API Key / base URL，或者 embedding 调用失败，
|
||||
当前阶段先退回到“全部候选交给 LLM selector”。
|
||||
"""
|
||||
|
||||
if not candidates:
|
||||
return []
|
||||
|
||||
resolved_api_key = api_key or os.getenv(self.api_key_env)
|
||||
resolved_api_base = api_base or os.getenv(self.api_base_env)
|
||||
if not resolved_api_key or not resolved_api_base:
|
||||
return candidates
|
||||
|
||||
try:
|
||||
query_embedding = await self._embed_texts(
|
||||
api_key=resolved_api_key,
|
||||
api_base=resolved_api_base,
|
||||
texts=[query],
|
||||
model=model or self.model,
|
||||
)
|
||||
candidate_texts = [self._candidate_text(item) for item in candidates]
|
||||
candidate_embeddings = await self._embed_texts(
|
||||
api_key=resolved_api_key,
|
||||
api_base=resolved_api_base,
|
||||
texts=candidate_texts,
|
||||
model=model or self.model,
|
||||
)
|
||||
except Exception:
|
||||
return candidates
|
||||
|
||||
if not query_embedding or not query_embedding[0] or len(candidate_embeddings) != len(candidates):
|
||||
return candidates
|
||||
|
||||
query_vector = query_embedding[0]
|
||||
scored: list[tuple[float, dict[str, str]]] = []
|
||||
for candidate, vector in zip(candidates, candidate_embeddings, strict=False):
|
||||
if not vector:
|
||||
continue
|
||||
scored.append((self._cosine_similarity(query_vector, vector), candidate))
|
||||
|
||||
scored.sort(key=lambda item: item[0], reverse=True)
|
||||
return [item[1] for item in scored[:top_k]]
|
||||
|
||||
async def _embed_texts(
|
||||
self,
|
||||
*,
|
||||
api_key: str,
|
||||
api_base: str,
|
||||
texts: list[str],
|
||||
model: str,
|
||||
) -> list[list[float]]:
|
||||
"""调用 OpenAI-compatible embeddings 接口。
|
||||
|
||||
当前对齐的是你们实际在用的网关配置：
|
||||
- `POST {api_base}/embeddings`
|
||||
- `model=text-embedding-v4`
|
||||
- `encoding_format=float`
|
||||
"""
|
||||
|
||||
all_vectors: list[list[float]] = []
|
||||
endpoint = self._normalize_embeddings_endpoint(api_base)
|
||||
for start in range(0, len(texts), 10):
|
||||
batch = texts[start:start + 10]
|
||||
payload = await self._post_embeddings(
|
||||
endpoint=endpoint,
|
||||
api_key=api_key,
|
||||
model=model,
|
||||
texts=batch,
|
||||
)
|
||||
embeddings = payload.get("data") or []
|
||||
embeddings = sorted(embeddings, key=lambda item: item.get("index", 0))
|
||||
all_vectors.extend([list(item.get("embedding") or []) for item in embeddings])
|
||||
return all_vectors
|
||||
|
||||
async def _post_embeddings(
|
||||
self,
|
||||
*,
|
||||
endpoint: str,
|
||||
api_key: str,
|
||||
model: str,
|
||||
texts: list[str],
|
||||
) -> dict[str, Any]:
|
||||
return await asyncio.to_thread(
|
||||
self._post_embeddings_sync,
|
||||
endpoint=endpoint,
|
||||
api_key=api_key,
|
||||
model=model,
|
||||
texts=texts,
|
||||
)
|
||||
|
||||
def _post_embeddings_sync(
|
||||
self,
|
||||
*,
|
||||
endpoint: str,
|
||||
api_key: str,
|
||||
model: str,
|
||||
texts: list[str],
|
||||
) -> dict[str, Any]:
|
||||
body = json.dumps(
|
||||
{
|
||||
"model": model,
|
||||
"input": texts if len(texts) > 1 else texts[0],
|
||||
"encoding_format": "float",
|
||||
}
|
||||
).encode("utf-8")
|
||||
req = request.Request(
|
||||
endpoint,
|
||||
data=body,
|
||||
headers={
|
||||
"Authorization": f"Bearer {api_key}",
|
||||
"Content-Type": "application/json",
|
||||
},
|
||||
method="POST",
|
||||
)
|
||||
with request.urlopen(req, timeout=self.timeout_seconds) as response:
|
||||
return json.loads(response.read().decode("utf-8"))
|
||||
|
||||
@staticmethod
|
||||
def _candidate_text(candidate: dict[str, str]) -> str:
|
||||
name = (candidate.get("name") or "").strip()
|
||||
description = (candidate.get("description") or "").strip()
|
||||
return f"{name}\n{description}".strip()
|
||||
|
||||
@staticmethod
|
||||
def _normalize_embeddings_endpoint(api_base: str) -> str:
|
||||
base = api_base.rstrip("/")
|
||||
if base.endswith("/embeddings"):
|
||||
return base
|
||||
if base.endswith("/v1"):
|
||||
return f"{base}/embeddings"
|
||||
return f"{base}/v1/embeddings"
|
||||
|
||||
@staticmethod
|
||||
def _cosine_similarity(left: list[float], right: list[float]) -> float:
|
||||
if not left or not right or len(left) != len(right):
|
||||
return -1.0
|
||||
dot = sum(a * b for a, b in zip(left, right, strict=False))
|
||||
left_norm = math.sqrt(sum(a * a for a in left))
|
||||
right_norm = math.sqrt(sum(b * b for b in right))
|
||||
if left_norm == 0 or right_norm == 0:
|
||||
return -1.0
|
||||
return dot / (left_norm * right_norm)
|
||||
|
||||
@ -63,6 +63,11 @@ class SkillAssembler:
|
||||
api_key=embedding_runtime.api_key if embedding_runtime is not None else None,
|
||||
api_base=embedding_runtime.api_base if embedding_runtime is not None else None,
|
||||
model=embedding_runtime.model if embedding_runtime is not None else None,
|
||||
extra_headers=embedding_runtime.extra_headers if embedding_runtime is not None else None,
|
||||
timeout_seconds=(
|
||||
embedding_runtime.request_timeout_seconds if embedding_runtime is not None else None
|
||||
),
|
||||
fallback_top_k=None,
|
||||
)
|
||||
if not candidates:
|
||||
return SkillAssemblyResult()
|
||||
|
||||
@ -18,6 +18,7 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
import json
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
@ -111,6 +112,32 @@ class SkillsLoader:
|
||||
metadata, _ = parse_frontmatter(content)
|
||||
return metadata
|
||||
|
||||
def get_skill_tool_hints(self, name: str) -> list[str]:
|
||||
"""读取 skill 显式声明的推荐工具。
|
||||
|
||||
第一版只信任显式 metadata，不从正文里猜：
|
||||
- `tools: read_file, search_files`
|
||||
- `tools: ["read_file", "search_files"]`
|
||||
- YAML-like list:
|
||||
tools:
|
||||
- read_file
|
||||
- search_files
|
||||
- 兼容 metadata JSON blob 里的 `tools`
|
||||
"""
|
||||
|
||||
frontmatter = self.get_skill_metadata(name) or {}
|
||||
meta_blob = parse_skill_metadata_blob(frontmatter.get("metadata", ""))
|
||||
names = [
|
||||
*self._coerce_tool_names(frontmatter.get("tools")),
|
||||
*self._coerce_tool_names(meta_blob.get("tools")),
|
||||
*self._coerce_tool_names(meta_blob.get("required_tools")),
|
||||
]
|
||||
result: list[str] = []
|
||||
for item in names:
|
||||
if item and item not in result:
|
||||
result.append(item)
|
||||
return result
|
||||
|
||||
def load_skills_for_context(self, skill_names: list[str]) -> str:
|
||||
"""加载指定 skills 的正文，并整理成上下文块。"""
|
||||
|
||||
@ -253,6 +280,26 @@ class SkillsLoader:
|
||||
result.append(record.name)
|
||||
return result
|
||||
|
||||
@staticmethod
|
||||
def _coerce_tool_names(value: Any) -> list[str]:
|
||||
if value is None:
|
||||
return []
|
||||
if isinstance(value, str):
|
||||
raw = value.strip()
|
||||
if not raw:
|
||||
return []
|
||||
if raw.startswith("["):
|
||||
try:
|
||||
parsed = json.loads(raw)
|
||||
except Exception:
|
||||
parsed = None
|
||||
if isinstance(parsed, list):
|
||||
return [str(item).strip() for item in parsed if str(item).strip()]
|
||||
return [item.strip() for item in raw.split(",") if item.strip()]
|
||||
if isinstance(value, (list, tuple, set)):
|
||||
return [str(item).strip() for item in value if str(item).strip()]
|
||||
return []
|
||||
|
||||
def _find_record(self, name: str) -> SkillRecord | None:
|
||||
for record in self.list_skills(filter_unavailable=False):
|
||||
if record.name == name:
|
||||
|
||||
@ -20,7 +20,7 @@ import shutil
|
||||
from typing import Any
|
||||
|
||||
|
||||
def parse_frontmatter(content: str) -> tuple[dict[str, str], str]:
|
||||
def parse_frontmatter(content: str) -> tuple[dict[str, Any], str]:
|
||||
"""解析 Markdown 文件顶部的极简 frontmatter。
|
||||
|
||||
当前先只支持最常见的：
|
||||
@ -43,12 +43,36 @@ def parse_frontmatter(content: str) -> tuple[dict[str, str], str]:
|
||||
if match is None:
|
||||
return {}, content
|
||||
|
||||
metadata: dict[str, str] = {}
|
||||
for line in match.group(1).splitlines():
|
||||
metadata: dict[str, Any] = {}
|
||||
lines = match.group(1).splitlines()
|
||||
index = 0
|
||||
while index < len(lines):
|
||||
line = lines[index]
|
||||
if ":" not in line:
|
||||
index += 1
|
||||
continue
|
||||
key, value = line.split(":", 1)
|
||||
metadata[key.strip()] = value.strip().strip('"\'')
|
||||
key = key.strip()
|
||||
value = value.strip()
|
||||
if not value:
|
||||
items: list[str] = []
|
||||
lookahead = index + 1
|
||||
while lookahead < len(lines):
|
||||
candidate = lines[lookahead]
|
||||
stripped = candidate.strip()
|
||||
if not stripped:
|
||||
lookahead += 1
|
||||
continue
|
||||
if not stripped.startswith("- "):
|
||||
break
|
||||
items.append(stripped[2:].strip().strip('"\''))
|
||||
lookahead += 1
|
||||
if items:
|
||||
metadata[key] = items
|
||||
index = lookahead
|
||||
continue
|
||||
metadata[key] = value.strip('"\'')
|
||||
index += 1
|
||||
body = content[match.end():].strip()
|
||||
return metadata, body
|
||||
|
||||
|
||||
Reference in New Issue
Block a user