Merge pull request #538 from Re-bin/main

feat: add interleaved chain-of-thought to agent loop

nanobot/agent/context.py

@@ -103,7 +103,7 @@ IMPORTANT: When responding to direct questions or conversations, reply directly
 Only use the 'message' tool when you need to send a message to a specific chat channel (like WhatsApp).
 For normal conversation, just respond with text - do not call the message tool.
 
-Always be helpful, accurate, and concise. When using tools, explain what you're doing.
+Always be helpful, accurate, and concise. When using tools, think step by step: what you know, what you need, and why you chose this tool.
 When remembering something, write to {workspace_path}/memory/MEMORY.md"""
     
     def _load_bootstrap_files(self) -> str:

nanobot/agent/loop.py

@@ -225,6 +225,8 @@ 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."})
             else:
                 # No tool calls, we're done
                 final_content = response.content
@@ -330,6 +332,8 @@ 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."})
             else:
                 final_content = response.content
                 break