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/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