feat: Multi-Model Memory Reader with Modular Parser Architecture

[CaralHsi]

Description

Summary:

🎯 Overview

Implements a comprehensive multi-model memory reader system that extends SimpleStructMemReader to handle multimodal messages (text, files, images, audio, etc.) with a clean, modular parser architecture.

✨ Key Features

1. MultiModelStructMemReader

• ✅ Inherits from SimpleStructMemReader for code reuse
• ✅ Processes multimodal scene data in fast/fine modes
• ✅ Aligned custom_tags and info handling with parent class

2. Modular Parser System

Each parser is responsible for its own message type:

• UserParser: Multimodal user messages (text + file + image, etc.)
• AssistantParser/SystemParser/ToolParser: Role-based messages
• TextContentParser/FileContentParser: Raw content parts
• StringParser: Simple string messages

3. Source Management Pattern

• Each parser implements create_source() and rebuild_from_source()
• Multimodal messages create one SourceMessage per content part
• Preserves original_part for perfect reconstruction

📊 Changes

Core Files

• multi_model_struct.py: Main reader implementation
• multi_model_parser.py: Unified dispatcher
• base.py: Abstract parser interface
• 7 specific parsers: User, Assistant, System, Tool, Text, File, String

🔧 Technical Highlights

1. Parser Responsibility: Each parser manages its own source creation/rebuilding
2. Multimodal Support: One SourceMessage per content part with original_part preservation
3. Inheritance: Reuses windowing, chunking, LLM infrastructure
4. API Alignment: Consistent with SimpleStructMemReader patterns

🚀 Future Work

• Implement parse_fine() in all parsers
• Add image/audio parser support
• Optimize parallel LLM calls
• Complete message splitting logic

Fix: #(issue)

Docs Issue/PR: (docs-issue-or-pr-link)

Reviewer: @(reviewer)

Checklist:

• I have performed a self-review of my own code | 我已自行检查了自己的代码
• I have commented my code in hard-to-understand areas | 我已在难以理解的地方对代码进行了注释
• I have added tests that prove my fix is effective or that my feature works | 我已添加测试以证明我的修复有效或功能正常
• I have created related documentation issue/PR in MemOS-Docs (if applicable) | 我已在 MemOS-Docs 中创建了相关的文档 issue/PR（如果适用）
• I have linked the issue to this PR (if applicable) | 我已将 issue 链接到此 PR（如果适用）
• I have mentioned the person who will review this PR | 我已提及将审查此 PR 的人