v0.3.0
v0.3.0 — 2026-06-02
Feature release: PDF CJK text extraction, workspace per-project filtering, and a search/indexing performance pass. Backward-compatible; no schema change.
Added
- PDF CJK extraction — Shift-JIS (90ms-RKSJ), GBK, Big5-ETen, UHC, and UCS-2 CMap decoding via the
Detective-XH/pdffork (v0.6.0). PDF Info-dict fields are indexed as metadata;pdf.creation_dateis normalized to an RFC3339 UTC timestamp. - Workspace per-project filter on all workspace query tools, for scoped fan-out.
- Exact filename match surfaces the named document first in search.
Changed
- Search/graph performance — FTS5 trigram
MATCHreplaces full-table query expansion; per-candidate ranking andoperation=impacttraversal are batched (N+1 → set-based). servereconcile — startup deletion-reconcile is always-on and warm-start reconciles downtime-deleted files, closing a watcher-gap staleness window.- Internal: split the
workspace.goandsimilarity.gogod files; extracted shared indexing helpers.
Fixed
- Agent-experience (AX) surface fixes across the tool set: context dedup,
similar/nodeprovenance and parity, distinct-document counting guidance, and trace description accuracy. docgraph_contextsummary payload soft-capped at 20 KB.watchercaps fsnotify watches per process to bound fd usage underserve --workspace.
Security
- Context-pack integer args clamped at retrieval (H-24); content-trust test guard (S-1); supply-chain hardening (S-6) with
govulncheck+ SBOM CI gates.