pdftotext still wins on born-digital PDFs. Empty text layers go through pdftoppm + tesseract eng+deu. Optional OCR_ENGINE=paddle. Gitea #6.
2.2 KiB
type, status, related
| type | status | related | |||
|---|---|---|---|---|---|
| explanation | current |
|
Gap to v1 — detective brain
Goal: a brain that does not assert without proof. Search is deduction
(facts ≥2 sources → info → web). confirmed only from the facts root.
v1 is a living graph the agent can write and walk, not “more RAG”.
Epic: Gitea #16. Milestone: v1 detective brain. Decisions: PLAN.md.
In (do not reopen)
Read path Go + Zig CGO (D21). HTTP + OpenAPI + MCP (D20). PicoClaw compose
profile + CPU reasoner (D18). Mail sync → import → rebuild. D14 shebangs.
Compose api (no CPython) / index (Python write). Issues #1–#5, #7–#13.
#15 lever/loop.
#14 bin/brain/add.go /
POST /ingest (Python kblib.add_leafs; no Go upsert port).
#17 --hop N walks
FROM_FILE / HAS_VERSION / AUTHORED.
#18 --with-facts /
--with-chats on rebuild (WhatsApp out of v1).
#19 CI recall SoT =
bin/brain/eval.go via Zig.
Epic #16 closed.
v2
#6 OCR — pdftotext then
pdftoppm + tesseract eng+deu. Optional ocr-paddle.
#29 OQ1 contradiction
resolution. #30 OQ3 duckdb-md.
Blockers
None for epic #16 (closed). Remaining v2: OQ1, OQ3, OQ4.
question
│
├─ FTS + HNSW ← in
├─ facts / info roots ← in
├─ web (D17) ← in
├─ brain/add ACID ← in
├─ Cypher hop ← in
└─ facts+chats corpus ← in
Not v1
OQ1 contradiction resolution, OQ3 duckdb-md export, OQ4 YAML-first leafs. OCR (OQ2) is in: tesseract, not docling.
Close epic #16 when
Children #14, #15, #17, #18, #19 are closed. MCP tool order stays gated by tests.