fix(agent): deliver LLM errors to streaming channels and avoid polluting session context

When the LLM returns an error (e.g. 429 quota exceeded, stream timeout),
streaming channels silently drop the error message because `_streamed=True`
is set in metadata even though no content was actually streamed.

This change:
- Skips setting `_streamed` when stop_reason is "error", so error messages
  go through the normal channel.send() path and reach the user
- Stops appending error content to session history, preventing error
  messages from polluting subsequent conversation context
- Exposes stop_reason from _run_agent_loop to enable the above check

nanobot/agent/loop.py

@@ -308,7 +308,7 @@ class AgentLoop:
         channel: str = "cli",
         chat_id: str = "direct",
         message_id: str | None = None,
-    ) -> tuple[str | None, list[str], list[dict]]:
+    ) -> tuple[str | None, list[str], list[dict], str]:
         """Run the agent iteration loop.
 
         *on_stream*: called with each content delta during streaming.
@@ -358,7 +358,7 @@ class AgentLoop:
             logger.warning("Max iterations ({}) reached", self.max_iterations)
         elif result.stop_reason == "error":
             logger.error("LLM returned error: {}", (result.final_content or "")[:200])
-        return result.final_content, result.tools_used, result.messages
+        return result.final_content, result.tools_used, result.messages, result.stop_reason
 
     async def run(self) -> None:
         """Run the agent loop, dispatching messages as tasks to stay responsive to /stop."""
@@ -505,7 +505,7 @@ class AgentLoop:
                 current_message=msg.content, channel=channel, chat_id=chat_id,
                 current_role=current_role,
             )
-            final_content, _, all_msgs = await self._run_agent_loop(
+            final_content, _, all_msgs, _ = await self._run_agent_loop(
                 messages, session=session, channel=channel, chat_id=chat_id,
                 message_id=msg.metadata.get("message_id"),
             )
@@ -553,7 +553,7 @@ class AgentLoop:
                 channel=msg.channel, chat_id=msg.chat_id, content=content, metadata=meta,
             ))
 
-        final_content, _, all_msgs = await self._run_agent_loop(
+        final_content, _, all_msgs, stop_reason = await self._run_agent_loop(
             initial_messages,
             on_progress=on_progress or _bus_progress,
             on_stream=on_stream,
@@ -578,7 +578,7 @@ class AgentLoop:
         logger.info("Response to {}:{}: {}", msg.channel, msg.sender_id, preview)
 
         meta = dict(msg.metadata or {})
-        if on_stream is not None:
+        if on_stream is not None and stop_reason != "error":
             meta["_streamed"] = True
         return OutboundMessage(
             channel=msg.channel, chat_id=msg.chat_id, content=final_content,

nanobot/agent/runner.py

@@ -257,7 +257,6 @@ class AgentRunner:
                 final_content = clean or spec.error_message or _DEFAULT_ERROR_MESSAGE
                 stop_reason = "error"
                 error = final_content
-                self._append_final_message(messages, final_content)
                 context.final_content = final_content
                 context.error = error
                 context.stop_reason = stop_reason