mcp 2.x already on main (#10). Ports citations, eval k-curve/pvalue/trace, heading-recursive chunking (keeps MAX_CHARS=4000), and nomic embed-time prefixes.
Does not change BM25-first retrieval — gold set is 6 queries (2 still TODO/empty expected). Permutation tests will usually be significant: no. After merge, dispatch image-only so CI --rebuilds the index with prefixes.
mcp 2.x already on main (#10). Ports citations, eval k-curve/pvalue/trace, heading-recursive chunking (keeps MAX_CHARS=4000), and nomic embed-time prefixes.
Does **not** change BM25-first retrieval — gold set is 6 queries (2 still TODO/empty expected). Permutation tests will usually be `significant: no`. After merge, dispatch image-only so CI --rebuilds the index with prefixes.
Closes #12
mcp 2.x already on origin/main (#10). Does not change BM25-first
search_docs — n=6 is too small to flip the default.
- Numbered [1] citations via docs_mcp/format.py
- Eval P@1 + JSONL sidecar + eval.pvalue + eval.trace
- Heading-recursive chunker, keep chunk-0 and MAX_CHARS=4000
- Nomic prefixes at embed time only; stored text unprefixed
Closes#12
claude
merged commit 169816d98d into main2026-09-30 08:33:17 -04:00
claude
deleted branch issue-122026-09-30 08:33:17 -04:00
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
mcp 2.x already on main (#10). Ports citations, eval k-curve/pvalue/trace, heading-recursive chunking (keeps MAX_CHARS=4000), and nomic embed-time prefixes.
Does not change BM25-first retrieval — gold set is 6 queries (2 still TODO/empty expected). Permutation tests will usually be
significant: no. After merge, dispatch image-only so CI --rebuilds the index with prefixes.Closes #12