Merge branch 'main' into main

nanobot/providers/base.py

@@ -21,7 +21,8 @@ class LLMResponse:
     finish_reason: str = "stop"
     usage: dict[str, int] = field(default_factory=dict)
     reasoning_content: str | None = None  # Kimi, DeepSeek-R1 etc.
-
+    thinking_blocks: list[dict] | None = None  # Anthropic extended thinking
+    
     @property
     def has_tool_calls(self) -> bool:
         """Check if response contains tool calls."""
@@ -88,6 +89,7 @@ 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

@@ -14,7 +14,7 @@ from nanobot.providers.registry import find_by_model, find_gateway
 
 # Standard OpenAI chat-completion message keys plus reasoning_content for
 # thinking-enabled models (Kimi k2.5, DeepSeek-R1, etc.).
-_ALLOWED_MSG_KEYS = frozenset({"role", "content", "tool_calls", "tool_call_id", "name", "reasoning_content"})
+_ALLOWED_MSG_KEYS = frozenset({"role", "content", "tool_calls", "tool_call_id", "name", "reasoning_content", "thinking_blocks"})
 _ALNUM = string.ascii_letters + string.digits
 
 def _short_tool_id() -> str:
@@ -176,6 +176,7 @@ 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.
@@ -221,7 +222,11 @@ class LiteLLMProvider(LLMProvider):
         # Pass extra headers (e.g. APP-Code for AiHubMix)
         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"
@@ -264,13 +269,15 @@ class LiteLLMProvider(LLMProvider):
             }
 
         reasoning_content = getattr(message, "reasoning_content", None) or None
-
+        thinking_blocks = getattr(message, "thinking_blocks", None) or None
+        
         return LLMResponse(
             content=message.content,
             tool_calls=tool_calls,
             finish_reason=choice.finish_reason or "stop",
             usage=usage,
             reasoning_content=reasoning_content,
+            thinking_blocks=thinking_blocks,
         )
 
     def get_default_model(self) -> str:

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)