Claude Opus 4.7登陸Claude Code，更具Agent特性、精準且擅長長時任務
AI 語音朗讀 · Edge TTS
Claude Opus 4.7登陸Claude Code，更具Agent特性、精準且擅長長時任務。
「Opus 4.7」已於Claude Code上線，展現更強的Agent性、更高的精準度，並大幅提升長時間運作效能。它能跨工作階段攜帶上下文，並有效處理歧義情境，讓單一提示即可推進更複雜任務。
Agent強化與單提示能力
Opus 4.7讓使用者以單一提示推動更遠端任務，涵蓋多檔案變更、歧義除錯，以及整個服務的程式碼審核。過去因模型易漂移而需拆分成小塊的任務，如今可一氣呵成，避免中斷。
Max使用者自動模式
針對Max使用者推出自動模式，徹底移除權限提示流程：僅需給Claude任務，讓它自主執行，返回時即為已驗證的成果，大幅簡化操作。
預設努力等級與資源管理
Claude Code預設努力等級升至「xhigh」，這是介於high與max間的新層級，提供更細緻的推理/延遲權衡控制。相較4.6，4.7思考更深入，token消耗更高，使用者需透過努力等級、任務預算或提示簡潔來管理。
效能升級總結
Opus 4.7解決了舊版在長程工作與歧義處理的痛點，讓Claude Code更適合專業程式開發情境，作者Boris Cherny迫不及待想聽取使用者回饋。
Opus 4.7 is in Claude Code today. It's more agentic, more precise, and a lot better at long-running work. It carries context across sessions and handles ambiguity much better. https://t.co/4XyR5aWR24
— Boris Cherny (@bcherny) April 16, 2026
With 4.7 you can push a lot further with one prompt. That means multi-file changes, ambiguous debugging, code review across a whole service. The stuff you used to break into small chunks because the model would drift.
— Boris Cherny (@bcherny) April 16, 2026
We're also rolling out auto mode for Max users. This means no more permission prompts — give Claude a task, let it run, come back to verified work.
— Boris Cherny (@bcherny) April 16, 2026
In Claude Code the default effort is now xhigh, a new level between high and max giving finer control over the reasoning/latency tradeoff. 4.7 thinks more, so token use runs higher than 4.6. Manage it with effort, task budgets, or prompting for brevity.
— Boris Cherny (@bcherny) April 16, 2026
Can’t wait to hear what you think!
— Boris Cherny (@bcherny) April 16, 2026