Why Top-Down Truncation Breaks AI Agents (And How Even-Span Fixes It)

Question

Top-down file truncation is why coding agents hallucinate exports on large files.

If you have an 800-line controller and clip at line 300, the model never sees lines 301 to 800 where the route handlers and export maps live.

We wrote evenSpan.js in TokenCap to sample files across their full length rather than chopping off the tail.

It preserves:

1. Top imports and configuration
2. Middle targeted function bodies
3. Bottom module exports and registrations

Everything snaps to real AST boundaries so syntax does not break.

Inspect the implementation and docs at tokencap.vansharora.app