Merge PR #1330: fix thinking mode support (reasoning_content + thinking_blocks)

nanobot/agent/context.py

@@ -150,6 +150,7 @@ Reply directly with text for conversations. Only use the 'message' tool to send
         content: str | None,
         tool_calls: list[dict[str, Any]] | None = None,
         reasoning_content: str | None = None,
+        thinking_blocks: list[dict] | None = None,
     ) -> list[dict[str, Any]]:
         """Add an assistant message to the message list."""
         msg: dict[str, Any] = {"role": "assistant", "content": content}
@@ -157,5 +158,7 @@ Reply directly with text for conversations. Only use the 'message' tool to send
             msg["tool_calls"] = tool_calls
         if reasoning_content is not None:
             msg["reasoning_content"] = reasoning_content
+        if thinking_blocks:
+            msg["thinking_blocks"] = thinking_blocks
         messages.append(msg)
         return messages

nanobot/agent/loop.py

@@ -218,6 +218,7 @@ class AgentLoop:
                 messages = self.context.add_assistant_message(
                     messages, response.content, tool_call_dicts,
                     reasoning_content=response.reasoning_content,
+                    thinking_blocks=response.thinking_blocks,
                 )
 
                 for tool_call in response.tool_calls:
@@ -238,6 +239,7 @@ class AgentLoop:
                     break
                 messages = self.context.add_assistant_message(
                     messages, clean, reasoning_content=response.reasoning_content,
+                    thinking_blocks=response.thinking_blocks,
                 )
                 final_content = clean
                 break
@@ -451,7 +453,7 @@ class AgentLoop:
         """Save new-turn messages into session, truncating large tool results."""
         from datetime import datetime
         for m in messages[skip:]:
-            entry = {k: v for k, v in m.items() if k != "reasoning_content"}
+            entry = dict(m)
             role, content = entry.get("role"), entry.get("content")
             if role == "assistant" and not content and not entry.get("tool_calls"):
                 continue  # skip empty assistant messages — they poison session context

nanobot/providers/base.py

@@ -21,6 +21,7 @@ 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:

nanobot/providers/litellm_provider.py

@@ -16,7 +16,7 @@ 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:
@@ -271,6 +271,7 @@ 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,
@@ -278,6 +279,7 @@ class LiteLLMProvider(LLMProvider):
             finish_reason=choice.finish_reason or "stop",
             usage=usage,
             reasoning_content=reasoning_content,
+            thinking_blocks=thinking_blocks,
         )
     
     def get_default_model(self) -> str: