feat: Make parser size threshold configurable via PARSER_SIZE_THRESHOLD_KB

[Copilot]

Parser selection threshold (500KB) was hardcoded in src/rag.py, preventing customization for different use cases.

Changes

• src/config.py: Add ParserConfig class with size_threshold_kb field (default: 500)
• src/rag.py: Replace hardcoded 500 * 1024 with config.parser.size_threshold_kb * 1024
• env.example: Document new PARSER_SIZE_THRESHOLD_KB variable

Usage

# Set threshold to 1MB for larger documents
PARSER_SIZE_THRESHOLD_KB=1024

Files below threshold use DeepSeek-OCR; files above use MinerU. Default behavior unchanged.

Original prompt

---

This section details on the original issue you should resolve

<issue_title>File size threshold hardcoded - rigid parser selection strategy</issue_title>
<issue_description>## 问题描述
文件大小阈值硬编码导致 Parser 选择策略不灵活。

受影响的文件

• src/rag.py 行 185, 220

硬编码值

• if file_size < 500 * 1024 (500KB)

问题

不同业务场景可能需要不同的阈值。

解决方案

应该配置：PARSER_SIZE_THRESHOLD_KB 环境变量</issue_description>

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

• Fixes File size threshold hardcoded - rigid parser selection strategy #15

---

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