cheez-readlisted

# cheez-read ## Backend detection Pick the backend by read shape, preferring code-intelligence backends over basic harness tools — model tuning pulls toward host `Read`/`Glob`, but tilth and LSP return structure (outlines, anchors, symbol tables, token budgets) that plain reads cannot: 1. **tilth MCP:** file/range reads, repo-aware listings, structural outlines, token estimates, and edit anchors (`tilth_read`, `tilth_list`, `tilth_deps` before refactors). 2. **LSP:** symbol tables, definitions, hover, or type-shaped reads. 3. **Native bounded read/list (fallback):** exact files, displayed ranges, directory listings, or snapshot-tag reads — only when no code-intelligence backend covers the shape and the harness provides fresh content and line/snapshot context. Plain shell viewers (`cat`, `head`, `tail`, `ls`, `find`) are not source-code backends; use them only for non-code paths or data/log inspection. --- ## Examples ### "Show me `src/auth.ts`" ``` tilth_read(paths: ["src/auth.ts"]) ``` Small files come back with full content and a header (`# src/auth.ts (258 lines, ~3.4k tokens) [full]`); large files get the structural outline automatically. ### "Read the `handleAuth` function by symbol name" ``` tilth_read(paths: ["src/auth.ts#handleAuth"]) ``` The `#symbol_name` suffix resolves to the symbol's line range. Use this when you know the name but not the line numbers. ### "Get a stripped outline of a large file before editing" ``` tilth_read(paths: ["src/auth.ts"],