Fix DEFAULT_MAX_ASYNC hardcoding

[Copilot]

DEFAULT_MAX_ASYNC was hardcoded to 8 in src/rag.py. Changed to read from environment variable MAX_ASYNC with fallback to 8.

Changes

• src/rag.py: Read DEFAULT_MAX_ASYNC from MAX_ASYNC env var

# Before
DEFAULT_MAX_ASYNC = 8

# After
DEFAULT_MAX_ASYNC = int(os.getenv("MAX_ASYNC", "8"))

Note: This constant appears unused in current code (config.llm.max_async is used instead), but fix addresses the issue as stated.

Original prompt

---

This section details on the original issue you should resolve

<issue_title>DEFAULT_MAX_ASYNC hardcoded</issue_title>
<issue_description>## 问题描述
默认最大并发数硬编码。

受影响的文件

• src/rag.py 行 31

硬编码值

• DEFAULT_MAX_ASYNC = 8

解决方案

应该从环境变量读取。</issue_description>

Comments on the Issue (you are @copilot in this section)

• Fixes DEFAULT_MAX_ASYNC hardcoded #24

---

💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.