为什么 Claude Code 会导致本地 LLM 推理崩溃

import json, threading, queue, time
from http.server import HTTPServer, BaseHTTPRequestHandler
from urllib.request import Request, urlopen

# 本地 llama-server 地址
TARGET = "http://127.0.0.1:8080"
request_queue = queue.Queue()
response_slots = {}
slot_lock = threading.Lock()

def worker():
    """串行化处理请求的工作线程"""
    while True:
        req_id, method, path, headers, body = request_queue.get()
        try:
            req = Request(f"{TARGET}{path}", data=body, method=method)
            for k, v in headers.items():
                req.add_header(k, v)
            resp = urlopen(req, timeout=600)
            with slot_lock:
                response_slots[req_id] = ("ok", resp.status, dict(resp.getheaders()), resp.read())
        except Exception as e:
            with slot_lock:
                response_slots[req_id] = ("error", 502, {}, str(e).encode())
        finally:
            request_queue.task_done()

threading.Thread(target=worker, daemon=True).start()

class SmartProxy(BaseHTTPRequestHandler):
    def do_POST(self):
        length = int(self.headers.get("Content-Length", 0))
        body = self.rfile.read(length)
        data = json.loads(body)
        model = data.get("model", "")

        # 1. 拦截令牌计数请求
        if "count_tokens" in self.path:
            resp = json.dumps({"input_tokens": 1000}).encode()
            self.send_response(200)
            self.send_header("Content-Type", "application/json")
            self.end_headers()
            self.wfile.write(resp)
            return

        # 2. 伪造 Haiku 响应（内务处理）
        if "haiku" in model.lower():
            fake = {
                "id": "msg_fake", "type": "message", "role": "assistant",
                "content": [{"type": "text", "text": "OK"}],
                "model": model, "usage": {"input_tokens": 10, "output_tokens": 1}
            }
            self.send_response(200)
            self.send_header("Content-Type", "application/json")
            self.end_headers()
            self.wfile.write(json.dumps(fake).encode())
            return

        # 3. 将真实推理请求放入队列串行执行
        req_id = time.time()
        request_queue.put((req_id, "POST", self.path, {"Content-Type": "application/json"}, body))

        while req_id not in response_slots:
            time.sleep(0.1)

        _, code, h, d = response_slots.pop(req_id)
        self.send_response(code)
        self.send_header("Content-Type", "application/json")
        self.send_header("Content-Length", str(len(d)))
        self.end_headers()
        self.wfile.write(d)

print("Proxy running on http://127.0.0.1:9090")
HTTPServer(("127.0.0.1", 9090), SmartProxy).serve_forever()