fix: fall back to secondary LLM when the primary call raises

Primary model errors (HTTP 4xx/5xx, connection failures) raised out of
_call_llm uncaught, skipping the fallback branch entirely — fallback
only ran when the primary returned an empty/"can't answer" string.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

AI/talk_handler.py

@@ -614,17 +614,21 @@ async def _call_llm(
 ) -> str:
     disable_thinking = FORCE_DISABLE_THINKING if disable_thinking is None else disable_thinking
 
-    result = await _call_single_model(
+    try:
-        messages,
+        result = await _call_single_model(
-        api_url=LLAMA_API_URL,
+            messages,
-        api_key=LLAMA_API_KEY,
+            api_url=LLAMA_API_URL,
-        model=LLAMA_MODEL,
+            api_key=LLAMA_API_KEY,
-        max_tokens=max_tokens,
+            model=LLAMA_MODEL,
-        temperature=temperature,
+            max_tokens=max_tokens,
-        top_p=top_p,
+            temperature=temperature,
-        disable_thinking=disable_thinking,
+            top_p=top_p,
-        reasoning_budget=reasoning_budget,
+            disable_thinking=disable_thinking,
-    )
+            reasoning_budget=reasoning_budget,
+        )
+    except Exception:
+        logger.exception("Primary model call failed")
+        result = ""
 
     # Если основная модель не смогла ответить — пробуем fallback
     if LLAMA_FALLBACK_API_URL and (not result or _CANT_ANSWER_RE.search(result)):