LOT 1 - Optimizare script build -Instalare mono comanda

ai_platform/modules/llm-inference/src/llm_inference/backends/vllm_backend.py

@@ -105,6 +105,21 @@ class VLLMBackend(LLMBackend):
         """Backend identifier name."""
         return "vllm"
 
+    def _apply_thinking_default(self, kwargs: dict[str, object]) -> dict[str, object]:
+        """Default reasoning models to non-thinking output for clean answers.
+
+        Injects ``extra_body={"chat_template_kwargs": {"enable_thinking": False}}``
+        unless the caller already supplied ``chat_template_kwargs``. Lets JSON-parsing
+        consumers (extractors, video semantic, brain) get the final answer directly.
+        """
+        if not getattr(self._settings, "vllm_disable_thinking", True):
+            return kwargs
+        extra = dict(kwargs.get("extra_body") or {})  # type: ignore[arg-type]
+        ctk = dict(extra.get("chat_template_kwargs") or {})
+        ctk.setdefault("enable_thinking", False)
+        extra["chat_template_kwargs"] = ctk
+        return {**kwargs, "extra_body": extra}
+
     async def complete(
         self,
         messages: list[ChatMessage],
@@ -127,6 +142,8 @@ class VLLMBackend(LLMBackend):
             LLMTimeoutError: If the request times out.
         """
 
+        kwargs = self._apply_thinking_default(kwargs)
+
         async def _do_complete() -> CompletionResponse:
             response = await self._client.chat.completions.create(
                 model=model,
@@ -240,6 +257,7 @@ class VLLMBackend(LLMBackend):
             LLMTimeoutError: If the request times out.
         """
         stream = None
+        kwargs = self._apply_thinking_default(kwargs)
         try:
             stream = await self._client.chat.completions.create(
                 model=model,

ai_platform/modules/llm-inference/src/llm_inference/config.py

@@ -111,6 +111,16 @@ class LLMSettings(BaseSettings):
         default=None,
         description="API key for vLLM server (if required)",
     )
+    vllm_disable_thinking: bool = Field(
+        default=True,
+        description=(
+            "Inject chat_template_kwargs={'enable_thinking': False} on vLLM chat "
+            "requests so reasoning models (e.g. Qwen3.5) return the final answer "
+            "directly instead of a 'thinking' preamble — required for callers that "
+            "parse JSON (extractors sentiment/OCR, video semantic, brain). Callers "
+            "may override by passing their own chat_template_kwargs."
+        ),
+    )
 
     # llama.cpp settings
     llamacpp_base_url: str = Field(