fix(memory): prevent potential loss of compressed session history

When the Consolidator compresses old session messages into history.jsonl,
those messages are immediately removed from the LLM's context. Dream
processes history.jsonl into long-term memory (memory.md) on a cron
schedule (default every 2h), creating a window where compressed content
is invisible to the LLM.

This change closes the gap by injecting unprocessed history entries
(history.jsonl entries not yet consumed by Dream) directly into the
system prompt as "# Recent History".

Key design notes:
- Uses read_unprocessed_history(since_cursor=last_dream_cursor) so only
  entries not yet reflected in long-term memory are included, avoiding
  duplication with memory.md
- No overlap with session messages: Consolidator advances
  last_consolidated before returning, so archived messages are already
  removed from get_history() output
- Token-safe: Consolidator's estimate_session_prompt_tokens calls
  build_system_prompt via the same build_messages function, so the
  injected entries are included in token budget calculations and will
  trigger further consolidation if needed

Signed-off-by: Lingao Meng <menglingao@xiaomi.com>

nanobot/agent/context.py

@@ -48,6 +48,10 @@ class ContextBuilder:
         if skills_summary:
             parts.append(render_template("agent/skills_section.md", skills_summary=skills_summary))
 
+        entries = self.memory.read_unprocessed_history(since_cursor=self.memory.get_last_dream_cursor())
+        if entries:
+            parts.append("# Recent History\n\n" + "\n".join(f"- {entry['content']}" for entry in entries))
+
         return "\n\n---\n\n".join(parts)
 
     def _get_identity(self) -> str: