token-budget-advisor

原文涵盖的主题

• Token Budget Advisor (TBA)
• When to Use
• How It Works
• Step 1 — Estimate input tokens
• Step 2 — Estimate response size by complexity
• Step 3 — Present depth options
• Step 4 — Respond at the chosen level
• Shortcuts — skip the question

Intercept the response flow to offer the user a choice about response depth before Claude answers. User wants to control how long or detailed a response is User mentions tokens, budget, depth, or response length User says "short version", "tldr", "brief", "al 25%", "exhaustive", etc. Any time the user wants to choose depth/detail level upfront Do not trigger when: user already set a level this session (maintain it silently), or the answer is trivially one line. Use the repository's canonical context-budget heuristics to estimate the prompt's token count mentally. Use the same calibration guidance as context-budget: prose: words × 1.3 code-heavy or mixed/code blocks: chars / 4 For mixed content, use the dominant content type and keep the estimate heuristic. Classify the prompt, then apply the multiplier range to get the full response window: | Complexity | Multiplier range | Example prompts | |--------------|------------------|------------------------------------------------------| | Simple | 3× – 8× | "What is X?", yes/no, single fact | | Medium | 8× – 20× | "How does X work?" | | Medium-High | 10× – 25× | Code request with context | | Complex | 15× – 40× | Multi-part analysis, com

这里只展示节选，请以完整原文和当前要求为准。