# Why Top-Down Truncation Breaks AI Agents (And How Even-Span Fixes It) > Source: > Published: 2026-09-27 18:43:48+00:00 Most AI coding context generators have a hidden design flaw: they truncate long files sequentially from line 1 downward until they hit a token budget limit. If a file has 1,200 lines and your budget allows 400 lines, the model receives lines 1 to 400. Everything from line 401 to 1200 vanishes. In production codebases, this is fatal: When the agent cannot see `module.exports` or class registrations at the bottom, it assumes they do not exist and generates duplicate or broken code. To solve this without blowing the token budget, TokenCap implements even-span distribution in `src/pack/evenSpan.js`. The algorithm divides the file into balanced intervals and samples structural slices while preserving AST function signatures: ``` // src/pack/evenSpan.js overview function computeEvenSpans(lineCount, maxLines, anchorPoints) { // Guarantees head imports, core anchor blocks, and tail exports // are represented proportionally within the allocated budget. } ``` Instead of: ``` Lines 1 - 350: Captured Lines 351 - 1200: [TRUNCATED] ``` Even-span provides: ``` Lines 1 - 80: Header, configuration, types ... [140 lines folded] ... Lines 220 - 310: Core logic and targeted symbols ... [290 lines folded] ... Lines 600 - 680: Lifecycle handlers and bottom exports ``` Every span boundary snaps cleanly to structural declaration boundaries rather than slicing mid-statement. Run `tokencap make` to inspect how your large files are budgeted. Read more at tokencap.vansharora.app