gjm
ec5292debe
基座（cad_mcp_frame）: - 新增 RecvOneFrame: 以 '\n' 为消息边界分帧，去掉单次 recv(2048) 限制（上限 8MB）； 用 select 短探测兼容不发 '\n' 的旧客户端；clientSocket 设 SO_RCVTIMEO 防卸载卡死 - JSON-RPC id 支持 string/number；无 id 的通知不回包 - isError 映射: 协议级错误保留顶层 error，工具执行错误转 result.isError=true - 响应补 '\n' 作为消息边界 Agent（新增 dwg_review 包）: - mcp_client: 唯一 TCP/JSON-RPC 封装（单飞锁/分帧/重试/兼容 error 与 isError） - cad_tools: 从 tools/list 动态建表，含 15 个只读白名单 - phases: planning -> evidence -> review（受控只读取证子循环）-> report - annotator: 批注回写 AI_REVIEW 层，支持 dry-run 与撤销 - config: 配置全部走环境变量；Windows 下回退读注册表以读到新设的系统变量 其它: 新增 verify_mcp_frame.py 验证脚本；.gitignore 补 Python/AutoCAD 锁文件规则； ai.memory 记录架构决策与实测结论
102 lines
3.4 KiB
Python
102 lines
3.4 KiB
Python
"""LLM 封装（文本 + 视觉），统一超时 / 重试 / 截图预处理。
|
|
|
|
默认走 DeepSeek（视觉模型 deepseek-flash）。密钥从环境变量读取，禁止硬编码。
|
|
"""
|
|
|
|
import base64
|
|
import io
|
|
import time
|
|
|
|
from openai import OpenAI
|
|
|
|
from . import config
|
|
|
|
try: # 可选依赖：仅用于截图下采样
|
|
from PIL import Image
|
|
|
|
HAS_PIL = True
|
|
except ImportError: # pragma: no cover
|
|
HAS_PIL = False
|
|
|
|
|
|
class LlmError(Exception):
|
|
pass
|
|
|
|
|
|
def downsample_image_b64(b64, mime="image/png", max_edge=None, quality=None):
|
|
"""把 base64 截图下采样并转 JPEG，降低视觉 token 成本。
|
|
|
|
缺少 Pillow 或参数为 0 时原样返回 (b64, mime)。
|
|
"""
|
|
max_edge = config.IMAGE_MAX_EDGE if max_edge is None else max_edge
|
|
quality = config.IMAGE_JPEG_QUALITY if quality is None else quality
|
|
if not HAS_PIL or max_edge <= 0:
|
|
return b64, mime
|
|
try:
|
|
img = Image.open(io.BytesIO(base64.b64decode(b64)))
|
|
if img.mode not in ("RGB", "L"):
|
|
img = img.convert("RGB")
|
|
w, h = img.size
|
|
scale = max_edge / float(max(w, h))
|
|
if scale < 1.0:
|
|
img = img.resize(
|
|
(max(1, int(w * scale)), max(1, int(h * scale))), Image.LANCZOS
|
|
)
|
|
buf = io.BytesIO()
|
|
img.save(buf, format="JPEG", quality=quality)
|
|
return base64.b64encode(buf.getvalue()).decode("ascii"), "image/jpeg"
|
|
except Exception:
|
|
return b64, mime
|
|
|
|
|
|
class LlmClient:
|
|
"""统一的 LLM 调用入口。"""
|
|
|
|
def __init__(self, api_key=None, base_url=None, model=None):
|
|
key = config.API_KEY if api_key is None else api_key
|
|
if not key:
|
|
raise LlmError("未配置 DEEPSEEK_API_KEY 环境变量")
|
|
self.model = model or config.MODEL_NAME
|
|
self._client = OpenAI(api_key=key, base_url=base_url or config.BASE_URL)
|
|
|
|
def chat(self, messages, *, tools=None, timeout=None, retries=None):
|
|
"""发起一次对话补全，返回原始 response。"""
|
|
retries = config.LLM_RETRIES if retries is None else retries
|
|
last = None
|
|
for attempt in range(retries + 1):
|
|
try:
|
|
kwargs = {
|
|
"model": self.model,
|
|
"messages": messages,
|
|
"timeout": timeout or config.LLM_TIMEOUT,
|
|
}
|
|
if tools:
|
|
kwargs["tools"] = tools
|
|
return self._client.chat.completions.create(**kwargs)
|
|
except Exception as exc: # noqa: BLE001 - 统一包装为 LlmError
|
|
last = exc
|
|
if attempt < retries:
|
|
time.sleep(0.5 * (2 ** attempt))
|
|
continue
|
|
raise LlmError(f"LLM 调用失败: {exc}") from exc
|
|
raise LlmError(f"LLM 调用失败: {last}")
|
|
|
|
def chat_text(self, system, user, **kwargs):
|
|
"""纯文本对话，返回助手文本。"""
|
|
resp = self.chat(
|
|
[
|
|
{"role": "system", "content": system},
|
|
{"role": "user", "content": user},
|
|
],
|
|
**kwargs,
|
|
)
|
|
return resp.choices[0].message.content
|
|
|
|
@staticmethod
|
|
def image_content(b64, mime="image/png"):
|
|
"""构造 OpenAI/DeepSeek 视觉消息里的图片内容块。"""
|
|
return {
|
|
"type": "image_url",
|
|
"image_url": {"url": f"data:{mime};base64,{b64}"},
|
|
}
|