llmcore: fix empty-response not triggering mixin failover; distinct default UA for NativeOAISession

llmcore.py

@@ -381,13 +381,13 @@ def _stream_with_retry(sess, url, headers, payload, parse_fn):
                     yield err; return [{"type": "text", "text": err}]
                 gen = parse_fn(r)
                 try:
-                    while True: streamed = True; yield next(gen)
+                    while True: chunk = next(gen); streamed = True; yield chunk
                 except StopIteration as e:
                     if not e.value and not streamed: raise requests.ConnectionError("empty response")
                     return e.value or []
         except (requests.Timeout, requests.ConnectionError) as e:
             #pathlib.Path(__file__).parent.joinpath('temp','bad_requests.json').write_text(json.dumps({"url":url,"headers":headers,"payload":payload,"err":str(e),"t":time.time()},ensure_ascii=False),encoding='utf-8')
-            err = f"!!!Error: {type(e).__name__}"
+            err = f"!!!Error: {type(e).__name__}: {e}" if str(e) else f"!!!Error: {type(e).__name__}"
             if attempt < sess.max_retries:
                 d = _delay(None, attempt)
                 print(f"[LLM Retry] {type(e).__name__}, retry in {d:.1f}s ({attempt+1}/{sess.max_retries+1})")
@@ -660,6 +660,7 @@ def _fix_messages(messages):
     return merged
 
 class NativeClaudeSession(BaseSession):
+    native_ua = "claude-cli/2.1.152 (native, cli)"
     def __init__(self, cfg):
         super().__init__(cfg)
         self.fake_cc_system_prompt = cfg.get("fake_cc_system_prompt", False)
@@ -667,7 +668,7 @@ class NativeClaudeSession(BaseSession):
         self._account_uuid = str(uuid.uuid4())
         self._device_id = uuid.uuid4().hex + uuid.uuid4().hex[:32]
         self.tools = None
-        if self.user_agent == self.default_ua: self.user_agent = "claude-cli/2.1.152 (native, cli)"
+        if self.user_agent == self.default_ua: self.user_agent = self.native_ua
     def raw_ask(self, messages):
         if self.max_tokens is None: self.max_tokens = 8192
         model = self.model
@@ -738,6 +739,7 @@ class NativeClaudeSession(BaseSession):
         return MockResponse(thinking, content, tool_calls, str(content_blocks))
 
 class NativeOAISession(NativeClaudeSession):
+    native_ua = "codex_cli_rs/0.1.2025062000 (Windows 11 10.0.26100; x86_64) Windows_Terminal"
     def raw_ask(self, messages):
         messages = _fix_messages(messages)
         messages = _ensure_thinking_blocks(messages, self.model)