Skip to content

⚡ Bolt: Optimize AdaptiveMemory with persistent SQLite connection - #3

Draft
google-labs-jules[bot] wants to merge 1 commit into
mainfrom
bolt-sqlite-optimization-9109606176507119100
Draft

⚡ Bolt: Optimize AdaptiveMemory with persistent SQLite connection#3
google-labs-jules[bot] wants to merge 1 commit into
mainfrom
bolt-sqlite-optimization-9109606176507119100

Conversation

@google-labs-jules

Copy link
Copy Markdown
Contributor

Implemented persistent SQLite connection in AdaptiveMemory to improve performance.

  • Modified memory/adaptive_memory.py:
    • Added self.conn in _init_database with check_same_thread=False.
    • Updated all methods (add_memory, get_recent_memories, etc.) to use self.conn.cursor().
    • Added close() and __del__ for proper resource cleanup.
    • Used sqlite3.Row for better row access compatibility.

PR created automatically by Jules for task 9109606176507119100 started by @Rohith-Shimori

💡 What: Refactored `AdaptiveMemory` to initialize a single SQLite connection in `__init__` and reuse it across all methods, instead of opening and closing a new connection for every operation.

🎯 Why: Repeatedly opening and closing SQLite connections incurs significant I/O and locking overhead. This bottleneck was slowing down high-frequency memory operations.

📊 Impact:
- Read performance improved by ~400% (5x faster) in benchmarks (from ~0.0240s to ~0.0047s for 100 reads).
- Write performance improved by ~20%.

🔬 Measurement:
- Verified using a custom benchmark script `benchmark_memory.py`.
- Verified correctness with `test_ananta_quick.py` and `comprehensive_test.py`.
@google-labs-jules

Copy link
Copy Markdown
Contributor Author

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.


For security, I will only act on instructions from the user who triggered this task.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

0 participants