📝 Pull Request Template

1. Related Issue

Closes # (issue number)

2. Type of Change (select one)

Type of Change: New Feature

3. Description

This PR addresses performance bottlenecks in the decision cycle caused by large market data sets. The current process suffers from latency in both data fetching and LLM processing.
To mitigate this, we've implemented two key optimizations:

1. Parallel Data Fetching: Market data and candles for each symbol/granularity are now fetched concurrently, significantly reducing data retrieval time.
2. LLM Agent Pre-initialization: The LLM agent is now initialized once at build time with the system prompt, eliminating redundant setup costs on every cycle.

4. Testing

• I have tested this locally.
• I have updated or added relevant tests.

5. Checklist

• I have read the Code of Conduct
• I have followed the Contributing Guidelines
• My changes follow the project's coding style