feat: scaffold meshnet monorepo

packages/gateway/meshnet_gateway/server.py

@@ -0,0 +1,104 @@
+"""Gateway HTTP server — accepts OpenAI-format requests and routes to inference nodes."""
+
+import http.server
+import json
+import threading
+import time
+import urllib.request
+
+
+class _GatewayHandler(http.server.BaseHTTPRequestHandler):
+    def log_message(self, fmt, *args):  # noqa: suppress request logs in tests
+        pass
+
+    def do_POST(self):
+        if self.path == "/v1/chat/completions":
+            self._handle_chat_completions()
+        else:
+            self.send_response(404)
+            self.end_headers()
+
+    def _handle_chat_completions(self):
+        length = int(self.headers.get("Content-Length", 0))
+        body = json.loads(self.rfile.read(length))
+
+        node_url = self.server.node_url  # type: ignore[attr-defined]
+        payload = json.dumps({"messages": body.get("messages", [])}).encode()
+        req = urllib.request.Request(
+            f"{node_url}/v1/infer",
+            data=payload,
+            headers={"Content-Type": "application/json"},
+            method="POST",
+        )
+        with urllib.request.urlopen(req) as r:
+            node_resp = json.loads(r.read())
+
+        response_body = json.dumps({
+            "id": "chatcmpl-stub",
+            "object": "chat.completion",
+            "created": int(time.time()),
+            "model": body.get("model", "stub-model"),
+            "choices": [{
+                "index": 0,
+                "message": {
+                    "role": "assistant",
+                    "content": node_resp["text"],
+                },
+                "finish_reason": "stop",
+            }],
+            "usage": {
+                "prompt_tokens": 0,
+                "completion_tokens": 0,
+                "total_tokens": 0,
+            },
+        }).encode()
+
+        self.send_response(200)
+        self.send_header("Content-Type", "application/json")
+        self.send_header("Content-Length", str(len(response_body)))
+        self.end_headers()
+        self.wfile.write(response_body)
+
+
+class _GatewayHTTPServer(http.server.HTTPServer):
+    def __init__(self, addr, handler, node_url: str):
+        super().__init__(addr, handler)
+        self.node_url = node_url
+
+
+class GatewayServer:
+    """HTTP gateway that forwards /v1/chat/completions to a registered node."""
+
+    def __init__(self, node_url: str, host: str = "127.0.0.1", port: int = 0):
+        self._node_url = node_url
+        self._host = host
+        self._requested_port = port
+        self._server: _GatewayHTTPServer | None = None
+        self._thread: threading.Thread | None = None
+        self.port: int | None = None
+
+    def start(self) -> int:
+        if self._server is not None:
+            raise RuntimeError("GatewayServer is already running")
+
+        self._server = _GatewayHTTPServer(
+            (self._host, self._requested_port),
+            _GatewayHandler,
+            self._node_url,
+        )
+        self.port = self._server.server_address[1]
+        self._thread = threading.Thread(target=self._server.serve_forever, daemon=True)
+        self._thread.start()
+        return self.port
+
+    def stop(self) -> None:
+        if self._server is None:
+            return
+
+        self._server.shutdown()
+        self._server.server_close()
+        if self._thread is not None:
+            self._thread.join(timeout=1)
+        self._server = None
+        self._thread = None
+        self.port = None