_build_result applied the noise-label filter to every item in the range,
including the ones the result matched on. A hit on a footnote or index
entry returned its section with the matched text removed, the clip anchor
could not find the evidence and fell back to a prefix window, and the
un-merge path rebuilt through the same filter.
Noise is now a set of positions computed once per group by
_noise_positions: noise-labelled items minus the matched ones.
_expand_outward and _build_result take that set instead of a flag, so the
matched item is kept in content and counted toward the budget.
Footnotes leave the noise set. They carry sources, cross-references and
clarifications, and docling attaches table and figure footnotes to the
table itself, so the filter was dropping part of the table. The noise set
is page_header, page_footer and document_index.
Refs #609
`docs/installation.md` claimed the full package contained every extra. It
pulls `docling`, `voyageai`, `cohere`, `zeroentropy`, `cross-encoder` and
`tui`, so `jina`, `s3` and `ingester` need installing separately. Without
`jina`, `provider: jina-local` falls back to no reranking. Anthropic is not
built in, and only the slim Docker image is published.
`docs/tuning.md` pointed at `claim_timeout_s`, which `WorkerConfig` now
rejects.
Context expansion is now automatic and structure-aware. For structured
documents, expands within the section containing the match. For sections
that exceed the budget or are too small, expands item-by-item outward
skipping noise labels. Unstructured documents use budget-based outward
expansion. Results sorted by relevance score.
