mirror of
https://github.com/wassname/evil_MoE.git
synced 2026-06-27 15:15:40 +08:00
wassname
4fcce164f7
Harness path ~/.claude/projects/.../memory was a real dir that had diverged
from the repo copy (the 9c188f6 symlink targeted /root, not this box's home).
Merged the two harness-only memories in and re-pointed the harness path at the
repo via symlink, so future auto-writes land in-project.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
1007 B
1007 B
name, description, metadata
| name | description | metadata | ||||||
|---|---|---|---|---|---|---|---|---|
| qmd-prefer-lexical | Default to lexical search (qmd search / rg) on the papers corpus, not vector/semantic |
|
For local paper search, default to lexical: qmd search (BM25) or rg, NOT
qmd vsearch/qmd query (vector/HyDE/rerank).
Why: (1) wassname finds vector search rarely helps him. (2) The big papers
qmd collection (~48k files) is ~93% unembedded, so semantic modes fall back to
junk there. (3) He cannot fit the embeddings on his PC, so qmd embed is not a
real fix.
How to apply: When dispatching search agents over the local corpus, instruct
them to use qmd search/rg first and reach for qmd query only as a last
resort on a small embedded collection (e.g. markdown-notes). A subagent once
burned ~5 min and crashed (exit 144) running qmd query over papers; lexical
returns in milliseconds. Do not suggest running qmd embed on his machine.