fix: configure Codex provider authentication

src/cognitive_agent/server.py

@@ -1834,11 +1834,16 @@ class SeatDemoHandler(BaseHTTPRequestHandler):
     def _handle_codex_vehicle_control(self) -> None:
         """Run an allowlisted MCP tool over the authenticated loopback bridge."""
 
+        try:
+            content_length = int(self.headers.get("Content-Length", "0"))
+        except ValueError:
+            content_length = 0
         if not self._is_unproxied_loopback_request():
             self._json(
                 {"error": "local_access_required", "message": "仅允许本机 Codex 工具调用。"},
                 HTTPStatus.FORBIDDEN,
             )
+            self._drain_rejected_request_body(content_length, max_bytes=32 * 1024)
             return
         if not self.assistant.authenticate_internal_request(
             self.headers.get("X-N7-Internal-Token", "")
@@ -1847,6 +1852,7 @@ class SeatDemoHandler(BaseHTTPRequestHandler):
                 {"error": "invalid_internal_token", "message": "Codex 工具认证失败。"},
                 HTTPStatus.FORBIDDEN,
             )
+            self._drain_rejected_request_body(content_length, max_bytes=32 * 1024)
             return
         try:
             payload = self._read_json_body(max_bytes=32 * 1024)
@@ -2846,17 +2852,22 @@ class SeatDemoHandler(BaseHTTPRequestHandler):
             if slot_acquired:
                 self.speech_preview_http_slots.release()
 
-    def _drain_rejected_request_body(self, content_length: int) -> None:
-        """Gracefully finish an early-rejected POST without doing speech work.
+    def _drain_rejected_request_body(
+        self,
+        content_length: int,
+        *,
+        max_bytes: int = 2 * 1024 * 1024,
+    ) -> None:
+        """Gracefully finish an early-rejected POST without processing its payload.
 
         Closing a Windows socket while its peer's request body is still unread can
         replace an already-written HTTP error with TCP RST.  Flush the rejection
         first, then briefly discard a valid-sized body so clients reliably receive
-        the 4xx response.  The preview/transcriber concurrency gates still run
-        before any audio is read or decoded.
+        the 4xx response. Callers choose a strict size ceiling, and authorization or
+        concurrency gates still run before any payload is read or decoded.
         """
 
-        if content_length <= 0 or content_length > 2 * 1024 * 1024:
+        if content_length <= 0 or content_length > max_bytes:
             return
         self.close_connection = True
         try: