|
|
|
|
| """
|
| 14_msg_proxy.py - a small logging / rewriting proxy between Claude Code and llama-server's /v1/messages endpoint.
|
|
|
| python 14_msg_proxy.py listens on 127.0.0.1:18082, forwards to 127.0.0.1:18080, streams the answer back, and appends every
|
| /v1/messages request body to /content/proxy_log.jsonl. fix() is the hook for rewriting a request
|
| (the chat template of Qwen3.8 rejects some shapes that Claude Code sends).
|
| """
|
| import http.client
|
| import http.server
|
| import json
|
| import time
|
|
|
| UP = ("127.0.0.1", 18080)
|
| CRLF = bytes([13, 10])
|
|
|
|
|
| def fix(d):
|
| """Qwen3.8's chat template raises 'System message must be at the beginning' for a system-role entry in `messages`, which Claude Code sends
|
| after the user turn. Fold every such entry into the last user message as an extra text block (nothing is dropped)."""
|
| msgs = d.get("messages") or []
|
| keep, extra = [], []
|
| for m in msgs:
|
| if m.get("role") == "system":
|
| c = m.get("content")
|
| text = c if isinstance(c, str) else chr(10).join(b.get("text", "") for b in c if isinstance(b, dict) and b.get("type") == "text")
|
| if text.strip():
|
| extra.append(text)
|
| else:
|
| keep.append(m)
|
| if len(keep) != len(msgs):
|
| block = dict(type="text", text=(chr(10) * 2).join(extra) if extra else "(no content)")
|
| for m in reversed(keep):
|
| if m.get("role") == "user":
|
| c = m.get("content")
|
| m["content"] = ([dict(type="text", text=c)] if isinstance(c, str) else list(c)) + [block]
|
| break
|
| else:
|
| keep.append(dict(role="user", content=[block]))
|
| d["messages"] = keep
|
| return d
|
|
|
|
|
| class H(http.server.BaseHTTPRequestHandler):
|
| protocol_version = "HTTP/1.1"
|
|
|
| def log_message(self, *a):
|
| pass
|
|
|
| def handle_any(self):
|
| n = int(self.headers.get("Content-Length") or 0)
|
| body = self.rfile.read(n) if n else b""
|
| if self.path.startswith("/v1/messages") and body:
|
| try:
|
| d = json.loads(body)
|
| with open("/content/proxy_log.jsonl", "a") as f:
|
| f.write(json.dumps(dict(t=time.time(), path=self.path, req=d))[:600000] + "\n")
|
| body = json.dumps(fix(d)).encode()
|
| except Exception as e:
|
| open("/content/proxy_err.log", "a").write(repr(e) + "\n")
|
| c = http.client.HTTPConnection(*UP, timeout=7200)
|
| hdr = dict((k, v) for k, v in self.headers.items() if k.lower() not in ("host", "content-length", "connection", "accept-encoding", "transfer-encoding"))
|
| c.request(self.command, self.path, body, hdr)
|
| r = c.getresponse()
|
| with open("/content/proxy_status.log", "a") as f:
|
| f.write(f"{time.time():.0f} {self.command} {self.path} {r.status}\n")
|
| self.send_response(r.status)
|
| for k, v in r.getheaders():
|
| if k.lower() not in ("transfer-encoding", "connection", "content-length"):
|
| self.send_header(k, v)
|
| self.send_header("Transfer-Encoding", "chunked")
|
| self.end_headers()
|
| while True:
|
| chunk = r.read1(65536)
|
| if not chunk:
|
| break
|
| self.wfile.write(b"%x" % len(chunk) + CRLF + chunk + CRLF)
|
| self.wfile.flush()
|
| self.wfile.write(b"0" + CRLF + CRLF)
|
| self.wfile.flush()
|
|
|
| do_GET = do_POST = do_PUT = do_DELETE = handle_any
|
|
|
|
|
| if __name__ == "__main__":
|
| http.server.ThreadingHTTPServer(("127.0.0.1", 18082), H).serve_forever()
|
|
|
