[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-ai-coding-assistant":3},{"tag":4,"articles":11},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":10},"55edd876-93ec-49c7-84bb-6603240949d8","AI coding assistant","ai-coding-assistant",5,"AI coding assistant 指的是能在編輯器、CLI 或工作流中協助補全、重構、生成測試與執行指令的工具。它的重點不只在提速，也牽涉模型來源、上下文壓縮、token 成本、供應鏈安全與企業採購判斷。","AI coding assistants sit inside editors, terminals, and agent workflows to help with completion, refactoring, test generation, and command execution. What matters is not only speed, but model provenance, context handling, token cost, supply-chain risk, and how teams evaluate adoption.",[12,21],{"id":13,"slug":14,"title":15,"summary":16,"category":17,"image_url":18,"cover_image":18,"language":19,"created_at":20},"029add1b-4386-4970-bd37-45809d6f7f2f","why-ibm-bob-right-kind-ai-coding-assistant-en","Why IBM’s Bob is the right kind of AI coding assistant","IBM’s Bob is the right kind of coding assistant because it is built to work across the software lifecycle, not just autocomplete code.","tools","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778664645900-cyz4.png","en","2026-05-13T09:30:22.413196+00:00",{"id":22,"slug":23,"title":24,"summary":25,"category":17,"image_url":26,"cover_image":26,"language":19,"created_at":27},"7b35c61d-4183-4923-a6ec-97ae00153530","claude-code-compaction-context-management-en","Claude Code压缩机制：长对话如何省上下文","Claude Code用多层压缩处理长对话上下文，避免200K到1M token被文件、Shell输出和编辑记录吃光。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775629324724-x24c.png","2026-04-08T06:21:47.598436+00:00"]