fix responses codex client metadata

llmcore.py

@@ -1,7 +1,7 @@
 import os, json, re, time, requests, sys, threading, urllib3, base64, importlib, uuid, pathlib
 from datetime import datetime
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
-_RESP_CACHE_KEY = str(uuid.uuid4())
+_RESP_CACHE_KEY = str(uuid.uuid4()); _RESP_CODEX_KEY = str(uuid.uuid4())
 _ROOT = os.path.dirname(os.path.abspath(__file__))
 if _ROOT not in sys.path: sys.path.append(_ROOT)
 
@@ -408,7 +408,8 @@ def _openai_stream(sess, messages):
     if api_mode == "responses":
         url = auto_make_url(sess.api_base, "responses")
         payload = {"model": model, "input": _to_responses_input(messages), "stream": sess.stream, 
-                   "prompt_cache_key": _RESP_CACHE_KEY, "instructions": sess.system or "You are an Omnipotent Executor."}
+                   "prompt_cache_key": _RESP_CACHE_KEY, "instructions": sess.system or "You are an Omnipotent Executor.",
+                   "client_metadata": {"x-codex-window-id": f"{_RESP_CACHE_KEY}:0","x-codex-installation-id": _RESP_CODEX_KEY}}
         if sess.reasoning_effort: payload["reasoning"] = {"effort": sess.reasoning_effort}
         if sess.max_tokens: payload["max_output_tokens"] = sess.max_tokens
     else:
@@ -739,7 +740,7 @@ class NativeClaudeSession(BaseSession):
         return MockResponse(thinking, content, tool_calls, str(content_blocks))
 
 class NativeOAISession(NativeClaudeSession):
-    native_ua = "codex_cli_rs/0.139.0 (Windows 10.0.26200; x86_64) unknown"
+    native_ua = "codex_exec/0.139.0 (Windows 10.0.26200; x86_64) unknown (codex_exec; 0.139.0)"
     def raw_ask(self, messages):
         messages = _fix_messages(messages)
         messages = _ensure_thinking_blocks(messages, self.model)