Frozen run · 2026-08-30
Performance analysis
On three coding tasks, correctness was tied. Every arm hit the full rubric. Lucider query packs were about 3× smaller than Aider chat+map and 30–100× smaller than concatenating the corpus.
| Task | Raw | Aider | Lucider pack | Quality |
|---|---|---|---|---|
Zod parseWithDefault |
145 633 | 4 399 | 1 406 | 13/13 |
Zod listConstraints |
145 941 | 13 183 | 4 520 | 16/16 |
| Hono pipeline | 153 215 | 7 124 | 2 156 | 16/16 |
Do not dump the index
The catalog belongs on disk. Pasting a full Lucider index into the model loses to a small repo map on unlabeled trees:
| Corpus | Raw | Aider map | Lucider body-off | Lucider body-on |
|---|---|---|---|---|
| Shop (annotated) | 613 | 603 | 300 | 901 |
| Zod v4/core (unlabeled) | 145 259 | 2 138 | 37 086 | 138 762 |
Lucider src/ |
11 151 | 2 032 | 2 147 | 11 960 |
--default-body on is right for a query slice. It is wrong for
“paste the whole digest.” Use
lucider src --query login --depth 1.
Method
Each agent received one context file. Same hidden rubric. Raw = concatenated
production sources. Aider = focus files plus
--show-repo-map --map-tokens 1024. Lucider = annotated index slices plus
--query / --depth — never the full unlabeled graph.
Corpora: Zod @93f3ab3 v4/core (21 files); Hono @e2740d5
production src/ (123 files).
Limitations
-
Parsers see function, class, method, interface, type, enum — not
export const(ZodsafeParse, Honocompose). Authored text on a nearby type covers the gap today. - Query ranking is substring
includes; inspect the pack. - Best packs need
ai-context,ai-ignore,ai-deps. - One agent family, three tasks, two libraries — token ratio at matched quality, not a leaderboard.