⚡ Bolt: Use AsyncGroq for non-blocking LLM calls

[Adityasingh-8858]

💡 What: Replaced the synchronous Groq client with AsyncGroq inside FastAPI endpoints. Added the required await statements for the chat.completions.create calls.
🎯 Why: In FastAPI, using synchronous blocking operations (like external HTTP requests to the Groq API) inside an async def endpoint prevents the main event loop from processing any other incoming requests. This leads to severe performance degradation under concurrent loads.
📊 Impact: Prevents event loop blocking during external AI network requests, which enables the backend to handle concurrent requests seamlessly and scale efficiently.
🔬 Measurement: Verify by running the backend test suite (cd backend && PYTHONPATH=. pytest -v -p anyio -p asyncio -o asyncio_mode=auto). All tests pass, proving that the async adaptation behaves identically functionally while operating without blocking the thread. Additionally, load testing concurrent requests to /initiate-transfer would demonstrate unblocked throughput compared to sequential waiting.

---

PR created automatically by Jules for task 17164051398032665602 started by @Deepaksingh7238

[google-labs-jules]

👋 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.

[Copilot]

Pull request overview

This PR updates the FastAPI backend to use Groq’s async client so LLM completion calls don’t block the event loop, improving concurrency under load.

Changes:

• Switched Groq client import/initialization from Groq to AsyncGroq.
• Added await to chat.completions.create(...) calls in async endpoints.
• Added an internal Bolt note documenting the optimization.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

File	Description
backend/main.py	Converts Groq completion calls to non-blocking async calls within FastAPI endpoints.
.jules/bolt.md	Documents the rationale and action taken for the async Groq optimization.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Lazy-initializing the global groq_client without synchronization can race under concurrent requests (multiple AsyncGroq instances may be created and one discarded without being closed). To avoid resource leaks and non-deterministic initialization, initialize the client once in lifespan or guard the initialization with an asyncio.Lock and ensure any extra created client is closed.

[Copilot]

groq_client is a global AsyncGroq client but it’s never closed on shutdown. Async clients typically hold an underlying HTTP connection pool; leaving it open can leak sockets and can prevent clean shutdowns. Consider instantiating AsyncGroq during app startup (lifespan) and awaiting the SDK’s async close method during shutdown (or use an async context manager) instead of leaving a global client unclosed.