Commit graph

37 commits

Author SHA1 Message Date
Research Assistant
eb3b73ae78 docs: prune superseded OCR worktree plans 2026-06-09 12:55:05 +08:00
Research Assistant
0aab860cf2 feat: OCR risk convergence — scored figure/table matching, layout confidence, insert scorer, health uncertainty metrics
- Figure matching: nearest-asset → scored multi-candidate selection with ambiguous state
- Table matching: vertical-nearest → score-based selection with prev/next page window
- Layout confidence: PageLayoutProfile gains confidence/evidence; eligible-body block filter
- Tail reorder: guarded by layout + tail confidence (low confidence preserves raw order)
- Structured insert: direct promotion → scorer + candidate + fallback state
- Health: adds 14 uncertainty metrics (ambiguous matches, unresolved clusters, forced inserts, low tail confidence)
- Audit: docs/ocr/high-risk-rule-audit.md documents 8 hard-rule decisions mapped to plans
- Spec + 6 implementation plans for agentic execution
2026-06-08 13:43:48 +08:00
Research Assistant
687332d126 docs: correct span_metadata source to PDF (not PaddleOCR), revise plan 2026-06-06 11:42:14 +08:00
Research Assistant
bdb3eae8ac docs: add unified span metadata spec and integration plan 2026-06-06 11:06:39 +08:00
Research Assistant
d52ea37e92 feat(ocr): tail regime remediation + style-aware heading profiles + boundary detection
- Task: Bidirectional body/backmatter boundary detection (forward/backward spine + tail spread reconciliation)
- Task: Style-aware heading profiles from PDF span_metadata (extract, cluster, disambiguate)
- Task: Lock tests for tail-candidate overreach, cross-page continuation, style-aware heading detection
- 296/296 tests pass, real-paper 7C8829BD verified
2026-06-05 22:47:13 +08:00
Research Assistant
bef8360cbd docs: add OCR structured pipeline design spec 2026-06-04 22:41:52 +08:00
Research Assistant
2ab524aecf feat: ocr reading-order fixes, single-source fulltext, redo closed-loop, release notes & manual 2026-06-01 18:12:31 +08:00
Research Assistant
03ad9ce64f feat: stabilize paperforge query planning 2026-05-27 21:20:15 +08:00
Research Assistant
3619fe264f Revert "test: clean up brittle and low-value tests"
This reverts commit 5ad9a54a66.
2026-05-24 19:59:24 +08:00
Research Assistant
5ad9a54a66 test: clean up brittle and low-value tests
- Remove 4 broken Python test files (ld_deep x3, path_normalization)
- Fix 2 vector_db tests to use correct mock target (get_collection)
- Remove 2 JS test files (settings-panels, vector-ready — trivial)
- Trim 3 buildRuntimeInstallCommand tests from errors.test.ts
- Narrow CI unit-tests to only run tests/unit/ (gate-level)
2026-05-24 19:59:14 +08:00
Research Assistant
1b0aecf48e docs: add pdf annotation layer design spec and implementation plan 2026-05-20 15:33:13 +08:00
Research Assistant
cc5fa0658f fix: add return type annotation to main() and indent=2 to early-exit json.dump calls 2026-05-19 14:41:06 +08:00
Research Assistant
19c28a8b91 chore: commit session work before hotfix switch 2026-05-18 22:47:30 +08:00
Research Assistant
add220d93c feat(discussion): remove JSON output and markdown escaping 2026-05-18 21:09:54 +08:00
Research Assistant
d5956ec5b1 docs: v3 — snapshot mandate, degradation policy, first-launch migration, async refresh 2026-05-15 22:31:37 +08:00
Research Assistant
cfcc7fc471 docs: revise JS-first memory state — Python writes snapshots, JS reads files only 2026-05-15 22:24:26 +08:00
Research Assistant
e528a4eb7f docs: JS-native memory state — spec, plan, and UX audit 2026-05-15 22:11:45 +08:00
Research Assistant
075c9107bf docs: add memory runtime health spec and regression helpers 2026-05-15 01:29:54 +08:00
Research Assistant
fb02280a7d spec: remove copy icon — clean click-to-copy with dashed underline only 2026-05-14 01:31:43 +08:00
Research Assistant
1e1acb2e82 spec: dashboard copy interaction + per-paper metadata enhancement 2026-05-14 01:21:52 +08:00
Research Assistant
8351319bcb docs(spec): 10-point memory layer performance optimization 2026-05-13 16:52:10 +08:00
Research Assistant
aa4c4991fd docs(spec): log format validation, reading-log import/lookup, methodology skill, dashboard SQLite 2026-05-13 16:02:50 +08:00
Research Assistant
8d3e4432c3 chore: add pre-commit JS syntax hook + stage missing vector CLI files 2026-05-12 23:34:24 +08:00
Research Assistant
9a48784b90 docs(spec): add Phase 7 vector retrieval — ChromaDB + local/API embedding + chunking 2026-05-12 21:43:34 +08:00
Research Assistant
55b5191d86 fix(spec): add DEFAULT_SETTINGS whitelist note, source: paperforge requirement, CLI toggle read 2026-05-12 21:19:21 +08:00
Research Assistant
85e35b0cfa docs(spec): plugin settings redesign — tabbed UI, skill manager, feature toggles, vector DB panel 2026-05-12 21:11:15 +08:00
Research Assistant
a886c9111d docs(spec): add Phase 6 — paper_events, reading/working logs, vector retrieval 2026-05-12 20:48:09 +08:00
Research Assistant
9dbdeaad46 test(memory): verify agent-context on test vault — 150 papers, 26 collections, 4 rules 2026-05-12 20:00:16 +08:00
Research Assistant
50f71a82ee docs(spec): add Memory Layer Phase 2-5 design (agent-context, dashboard, refresh, retrieve) 2026-05-12 19:44:38 +08:00
Research Assistant
8335bce992 bump: 1.5.5 -> 1.5.6rc1 (Memory Layer RC1) 2026-05-12 18:11:37 +08:00
Research Assistant
2e0657479a feat: PyPI publish support — install paperforge from PyPI with git fallback 2026-05-11 18:04:17 +08:00
Research Assistant
566697fc31 chore: remove CI workflows pending rewrite 2026-05-11 17:00:23 +08:00
Research Assistant
30f9613482 merge: integrate dashboard-refine (deep-finalize + slug-freeze) into skill-refine
Resolved conflicts:
- styles.css: take dashboard-refine (more refined CSS)
- SKILL.md, deep-reading.md, paper-resolution.md: take skill-refine (modular skill redesign)
2026-05-10 23:28:13 +08:00
Research Assistant
9b88c441b0 refactor(skills): modular literature-qa skill with router-first architecture
- Replace 6 scattered pf-*.md files with single SKILL.md router + 4 reference files
- Add paper_resolver.py: deterministic key/DOI/field search (4 subcommands)
- Remove pf-sync/ocr/status (CLI-only commands, no skill wrapper needed)
- Move chart-reading/ into references/ for flat structure
- Make ld_deep.py --vault optional (auto-detect from cwd)
- Add 26 unit tests for paper_resolver
- All paths dynamically resolved from paperforge.json, zero hardcoding
2026-05-10 20:56:28 +08:00
Research Assistant
61822c8a94 docs: add dashboard ui refinement specs and plans 2026-05-10 20:52:21 +08:00
Research Assistant
fb934b7d40 docs(spec): add multi-agent platform design spec 2026-04-28 15:51:03 +08:00
Research Assistant
c4390f4124 docs: pf-deep skill refactoring design (atoms/molecules/compounds) 2026-04-27 23:56:55 +08:00