opus_4_5_migration（作品 4 5 迁移）

Opus 4.5 Migration Guide

One-shot migration from Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5.

Migration Workflow

1. Search codebase for model strings and API calls
2. Update model strings to Opus 4.5 (see platform-specific strings below)
3. Remove unsupported beta headers
4. Add effort parameter set to "high" (see references/effort.md)
5. Summarize all changes made
6. Tell the user: "If you encounter any issues with Opus 4.5, let me know and I can help adjust your prompts."

Model String Updates

Identify which platform the codebase uses, then replace model strings accordingly.

Unsupported Beta Headers

Remove the context-1m-2025-08-07 beta header if present—it is not yet supported with Opus 4.5. Leave a comment noting this:

# Note: 1M context beta (context-1m-2025-08-07) not yet supported with Opus 4.5

Target Model Strings (Opus 4.5)

Source Model Strings to Replace

Do NOT migrate: Any Haiku models (e.g., claude-haiku-4-5-20251001).

Prompt Adjustments

Opus 4.5 has known behavioral differences from previous models. Only apply these fixes if the user explicitly requests them or reports a specific issue. By default, just update model strings.

Integration guidelines: When adding snippets, don't just append them to prompts. Integrate them thoughtfully:

• Use XML tags (e.g., <code_guidelines>, <tool_usage>) to organize additions
• Match the style and structure of the existing prompt
• Place snippets in logical locations (e.g., coding guidelines near other coding instructions)
• If the prompt already uses XML tags, add new content within appropriate existing tags or create consistent new ones

1. Tool Overtriggering

Opus 4.5 is more responsive to system prompts. Aggressive language that prevented undertriggering on previous models may now cause overtriggering.

Apply if: User reports tools being called too frequently or unnecessarily.

Find and soften:

• CRITICAL: → remove or soften
• You MUST... → You should...
• ALWAYS do X → Do X
• NEVER skip... → Don't skip...
• REQUIRED → remove or soften

Only apply to tool-triggering instructions. Leave other uses of emphasis alone.

2. Over-Engineering Prevention

Opus 4.5 tends to create extra files, add unnecessary abstractions, or build unrequested flexibility.

Apply if: User reports unwanted files, excessive abstraction, or unrequested features. Add the snippet from references/prompt-snippets.md.

3. Code Exploration

Opus 4.5 can be overly conservative about exploring code, proposing solutions without reading files.

Apply if: User reports the model proposing fixes without inspecting relevant code. Add the snippet from references/prompt-snippets.md.

4. Frontend Design

Apply if: User requests improved frontend design quality or reports generic-looking outputs.

Add the frontend aesthetics snippet from references/prompt-snippets.md.

5. Thinking Sensitivity

When extended thinking is not enabled (the default), Opus 4.5 is particularly sensitive to the word "think" and its variants. Extended thinking is enabled only if the API request contains a thinking parameter.

Apply if: User reports issues related to "thinking" while extended thinking is not enabled (no thinking parameter in request).

Replace "think" with alternatives like "consider," "believe," or "evaluate."

Reference

See references/prompt-snippets.md for the full text of each snippet to add.

*Opus 4.5 Migration v1.1 - Enhanced*

🔄 Workflow

Kaynak: Anthropic API Documentation & LLM Evaluation Best Practices

Aşama 1: Discovery

• Audit: Codebase'deki tüm model string'lerini (claude-3-opus, claude-3-5-sonnet) listele.
• Test Cases: Migration öncesi modelin başarısını ölçen "Golden Prompt" setini çalıştır (Baseline).

Aşama 2: Update & Refinement

• String Replacement: Model ID'lerini claude-3-5-opus-20241022 (veya güncel ID) ile değiştir.
• Parameter Check: Temperature ve Max Tokens değerlerini kontrol et (yeni model daha verbose veya daha creative olabilir).
• System Prompt: Yeni modelin talimatları anlama hassasiyeti değişmiş olabilir; sistemi sadeleştir.

Aşama 3: Validation

• Regression Test: Golden Prompt setini tekrar çalıştır ve çıktıları karşılaştır.
• Cost Analysis: Token kullanımındaki değişimi (daha az/çok token üretiyor mu?) analiz et.
• Latency Check: Response süresindeki değişimi ölç.

Kontrol Noktaları