Keyboard shortcuts

Press ← or → to navigate between chapters

Press S or / to search in the book

Press ? to show this help

Press Esc to hide this help

Model: openai/gpt-5.4 Token Usage（estimated）: ~2,900 tokens Generated: 2026-04-01 Book: Claude Code VS OpenCode: Architecture, Design & The Road Ahead

附录E：参考文献

以下文献与文章构成了本书的重要参考背景，包括官方工程博客、协议文档、行业分析和学术论文。由于编码智能体的发展速度远快于传统教材更新速度，本书有意把高质量工程文章也视为一手资料。

  1. Anthropic. “Building Effective AI Agents.” 2024-12-19。
    URL: https://www.anthropic.com/research/building-effective-agents

  2. Anthropic. “Effective context engineering for AI agents.” 2025-09-29。
    URL: https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents

  3. Anthropic. “Beyond permission prompts: making Claude Code more secure and autonomous.” 2025-10-20。
    URL: https://www.anthropic.com/engineering/claude-code-sandboxing

  4. Anthropic. “How we built our multi-agent research system.” 2025-06-13。
    URL: https://www.anthropic.com/engineering/built-multi-agent-research-system

  5. Anthropic. “Writing effective tools for agents — with agents.” 2025-09-11。
    URL: https://www.anthropic.com/engineering/writing-tools-for-agents

  6. Model Context Protocol. Official Documentation.
    URL: https://modelcontextprotocol.io/introduction

  7. Model Context Protocol. Official Registry.
    URL: https://registry.modelcontextprotocol.io/

  8. Zylos Research. “AI Coding Agents 2025-2026: State of the Art.” 2026-01-09。
    URL: https://zylos.ai/research/2026-01-09-ai-coding-agents

  9. Zylos Research. “AI Agent Plugin and Extension Architecture.” 2026-02-21。
    URL: https://zylos.ai/research/2026-02-21-ai-agent-plugin-extension-architecture

  10. GuruSup. “Agent Orchestration Patterns: Swarm vs Mesh vs Hierarchical.” 2026-03-14。
    URL: https://gurusup.com/en/blog/agent-orchestration-patterns

  11. GuruSup. “Agent Communication Protocols: MCP vs A2A and Why They Matter.” 2026-03-16。
    URL: https://gurusup.com/blog/agent-communication-protocols-mcp-a2a

  12. Kang, Minki et al. “Acon: Optimizing Context Compression for Long-horizon LLM Agents.” arXiv。
    URL: https://arxiv.org/abs/2510.00615

  13. Morph Team. “We Tested 15 AI Coding Agents (2026). Only 3 Changed How We Ship.” 2026-03-01。
    URL: https://morphllm.com/ai-coding-agent

  14. Yao, Shunyu et al. “ReAct: Synergizing Reasoning and Acting in Language Models.” 2022。
    URL: https://arxiv.org/abs/2210.03629

  15. Jimenez, Carlos E. et al. “SWE-bench: Can Language Models Resolve Real-World GitHub Issues?” 2023。
    URL: https://arxiv.org/abs/2310.06770

关于资料类型的一点说明

上面的资料里，既有 arXiv 论文，也有厂商工程博客和行业研究文章。对于今天的 Agent 工程来说，这种混合引用是必要的。因为很多关键术语、实现策略和架构模式，在经典 CS 教科书里还没有稳定命名，但在一线系统中已经成为真实存在的工程问题，例如 context engineering、tool quality、agent orchestration、sandbox autonomy 等。因此，本书把这些高质量工程文章视为“时代文献”，而不仅仅是宣传材料。