nanobot/agent/loop.py

@@ -372,8 +372,9 @@ class AgentLoop:
                     messages = self.context.add_tool_result(
                         messages, tool_call.id, tool_call.name, result
                     )
-                # Interleaved CoT: reflect before next action
-                messages.append({"role": "user", "content": "Reflect on the results and decide next steps."})
+                # Interleaved CoT: reflect before next action (skip when thinking is active)
+                if not getattr(self.provider, 'thinking_budget', 0):
+                    messages.append({"role": "user", "content": "Reflect on the results and decide next steps."})
             else:
                 # No tool calls, we're done
                 final_content = response.content
@@ -486,8 +487,9 @@ class AgentLoop:
                     messages = self.context.add_tool_result(
                         messages, tool_call.id, tool_call.name, result
                     )
-                # Interleaved CoT: reflect before next action
-                messages.append({"role": "user", "content": "Reflect on the results and decide next steps."})
+                # Interleaved CoT: reflect before next action (skip when thinking is active)
+                if not getattr(self.provider, 'thinking_budget', 0):
+                    messages.append({"role": "user", "content": "Reflect on the results and decide next steps."})
             else:
                 final_content = response.content
                 break

nanobot/providers/anthropic_oauth.py

@@ -230,6 +230,19 @@ class AnthropicOAuthProvider(LLMProvider):
         """Make request to Anthropic API."""
         client = await self._get_client()
 
+        # Cache the last user message so conversation history is cached across turns
+        if messages:
+            last = messages[-1]
+            if last.get("role") == "user":
+                content = last["content"]
+                if isinstance(content, str):
+                    last = {**last, "content": [{"type": "text", "text": content, "cache_control": {"type": "ephemeral"}}]}
+                elif isinstance(content, list) and content:
+                    new_content = list(content)
+                    new_content[-1] = {**new_content[-1], "cache_control": {"type": "ephemeral"}}
+                    last = {**last, "content": new_content}
+                messages = messages[:-1] + [last]
+
         payload: dict[str, Any] = {
             "model": model,
             "messages": messages,