feat: add reasoning_effort config to enable LLM thinking mode

nanobot/providers/base.py

@@ -88,6 +88,7 @@ class LLMProvider(ABC):
         model: str | None = None,
         max_tokens: int = 4096,
         temperature: float = 0.7,
+        reasoning_effort: str | None = None,
     ) -> LLMResponse:
         """
         Send a chat completion request.

nanobot/providers/custom_provider.py

@@ -18,13 +18,16 @@ class CustomProvider(LLMProvider):
         self._client = AsyncOpenAI(api_key=api_key, base_url=api_base)
 
     async def chat(self, messages: list[dict[str, Any]], tools: list[dict[str, Any]] | None = None,
-                   model: str | None = None, max_tokens: int = 4096, temperature: float = 0.7) -> LLMResponse:
+                   model: str | None = None, max_tokens: int = 4096, temperature: float = 0.7,
+                   reasoning_effort: str | None = None) -> LLMResponse:
         kwargs: dict[str, Any] = {
             "model": model or self.default_model,
             "messages": self._sanitize_empty_content(messages),
             "max_tokens": max(1, max_tokens),
             "temperature": temperature,
         }
+        if reasoning_effort:
+            kwargs["reasoning_effort"] = reasoning_effort
         if tools:
             kwargs.update(tools=tools, tool_choice="auto")
         try:

nanobot/providers/litellm_provider.py

@@ -178,6 +178,7 @@ class LiteLLMProvider(LLMProvider):
         model: str | None = None,
         max_tokens: int = 4096,
         temperature: float = 0.7,
+        reasoning_effort: str | None = None,
     ) -> LLMResponse:
         """
         Send a chat completion request via LiteLLM.
@@ -224,6 +225,10 @@ class LiteLLMProvider(LLMProvider):
         if self.extra_headers:
             kwargs["extra_headers"] = self.extra_headers
         
+        if reasoning_effort:
+            kwargs["reasoning_effort"] = reasoning_effort
+            kwargs["drop_params"] = True
+        
         if tools:
             kwargs["tools"] = tools
             kwargs["tool_choice"] = "auto"

nanobot/providers/openai_codex_provider.py

@@ -31,6 +31,7 @@ class OpenAICodexProvider(LLMProvider):
         model: str | None = None,
         max_tokens: int = 4096,
         temperature: float = 0.7,
+        reasoning_effort: str | None = None,
     ) -> LLMResponse:
         model = model or self.default_model
         system_prompt, input_items = _convert_messages(messages)