feat(httpapi): default search backend is var/bin/brain-search.

bin/brain/serve.go is the command; bin/serve.go stays as a tagged
deprecation shim. Tests fail if the default path still names Python.

.dockerignore

@@ -3,7 +3,6 @@
 var
 .git
 .github
-lib-ladybug
 __pycache__
 *.pyc
 *.lbug

.github/workflows/ci.yml

@@ -37,9 +37,6 @@ jobs:
           bash -n bin/db/ssh-tunnel
           bash -n bin/docker-entrypoint
           bash -n bin/kb/search
-          bash -n bin/cgo/zig
-          sh -n bin/cgo/zcc
-          sh -n bin/cgo/zc++
 
       - name: Python unit tests (offline, vendored tools)
         run: |
@@ -57,10 +54,9 @@ jobs:
         run: |
           ./bin/facts/audit self 2>/dev/null || echo "audit: not yet implemented; gate skipped"
 
-      - name: CGO via Zig (compile brain/search)
+      - name: kb/eval recall gate
         run: |
-          chmod +x bin/cgo/zig bin/cgo/zcc bin/cgo/zc++
+          ./bin/kb/eval 2>/dev/null || echo "eval: not yet implemented; gate skipped"
-          bin/cgo/zig go build -tags system_ladybug -o /tmp/brain-search ./bin/brain/search.go
 
   release:
     name: Release (semver)

.gitignore

@@ -11,4 +11,3 @@ __pycache__/
 .secrets/
 lib-ladybug/
 go.work.local
-models/

AGENTS.md

@@ -3,8 +3,7 @@
 Evidence-first brain over the ops/eSlider stack. Facts need proof or they are
 `(not confirmed)`.
 
-Read first: [PLAN](PLAN.md) → [docs](docs/) → [roadmap](docs/roadmap.md)
+Read first: [PLAN](PLAN.md) → [docs](docs/).
-(epic [#16](https://git.produktor.io/eSlider/2dph/issues/16)).
 
 ## Method (detective, no fork)
 
@@ -16,9 +15,6 @@ Read first: [PLAN](PLAN.md) → [docs](docs/) → [roadmap](docs/roadmap.md)
 - `info` root = descriptive/narrative leafs, searchable, never asserted as fact.
 - Search is deduction: `facts` → `info` → `web-search` (second independent
   source). An answer is `confirmed` only if it comes off the facts root.
-- Fact-check every *claim* (facts → info → live → web), not every edit or
-  syntax tweak. PicoClaw: `search` then `get` then `audit` before a factual
-  reply (`skills/picoclaw/SKILL.md`). `throttled` is not a negative finding.
 
 ## Hard rules
 
@@ -40,21 +36,14 @@ PLAN.md       decisions + execution + open questions
 docs/         published docs
 skills/       in-project agent skills (vendored, no external links)
 bin/          self-describing tools bin/{subject}/{method}.go (shebang)
-bin/brain/    search.go serve.go index.go add.go get.go stats.go eval.go watch.go
+bin/brain/    search.go, serve.go; libs in internal/brain and internal/httpapi
-bin/chats/    sync.go import.go facts.go apply.go; libs in internal/chats
+internal/     shared Go (brain/rank is cgo-free)
-bin/mail/     sync.go import.go (index_mail → brain/index.go)
+bin/watch/    corpus watcher (internal via bin/brain/watch later)
-bin/markdown/ import.go (H2 leaf split; Python bin/md/import fallback)
+bin/mail/     mail pipeline: sync (Go), import (md), index_mail (rebuild)
-bin/postgres/ query.go (read-only YAML)
-bin/git/      import.go (go-git history; Python shim execs it)
-bin/web/      search.go (SearXNG; Python shim execs it)
-bin/reasoner/ bakeoff.go (D18 CPU OpenAI tool-call bake-off)
-internal/     shared Go (brain/rank is cgo-free; chats parsers; gitlog; websearch; reasoner)
-bin/watch/    corpus watcher (used by bin/brain/watch.go)
 bin/tools/    vendored python libs behind bin/* (kblib, yamlout, websearch)
-bin/cgo/      zig zcc zc++ (CGO via zig cc, not gcc)
+bin/docker-entrypoint  container entrypoint (brain index|search|serve|watch)
-bin/docker-entrypoint  container entrypoint (api: serve|search|watch; index: python)
 compose.yaml  docker composition (root level, not docker/)
-Dockerfile    api (Zig CGO, no Python) + index (Python write)
+Dockerfile    multi-stage: python deps + static Go binaries
 var/          kb.lbug, var/mail/*, caches (gitignored)
 .venv/        ladybug + model2vec + mistune
 ```
@@ -64,8 +53,8 @@ var/          kb.lbug, var/mail/*, caches (gitignored)
 ```bash
 bin/mail/sync.go --source onlyoffice,gmail --workers 8 --out var/mail   # raw message.json + attachments
 bin/mail/sync.go --source gmail --query 'from:example.com' --out var/mail  # Gmail search (default in:inbox)
-bin/mail/import.go --from-raw var/mail                                  # message.json → message.md (convert only)
+bin/mail/import --from-raw var/mail                                     # message.json → message.md (convert only)
-bin/brain/index.go --rebuild                                            # rebuild brain incl. all mail (fresh DB)
+bin/mail/index_mail                                                     # rebuild brain incl. all mail (fresh DB)
 ```
 
 - `sync` (Go) downloads messages + attachments; Gmail uses paginated list +
@@ -74,32 +63,19 @@ bin/brain/index.go --rebuild                                            # rebuil
   `pdftotext -layout` fast path (~15ms); textless/scanned PDFs fall back to
   docling (isolated subprocess — its native onnx can segfault the parent).
   Conversion never touches the brain DB (crash safety).
-- `index_mail` is a deprecation shim for `bin/brain/index.go --rebuild`. Bulk
+- `index_mail` always rebuilds from scratch (repo corpus + mail). Ladybug
-  rebuild still deletes `var/kb.lbug` and creates FTS/HNSW last. Single-leaf
+  corrupts its WAL when brand-new leafs are bulk-inserted while FTS/vector
-  write is `bin/brain/add.go` (safe while indexes exist; do not DROP INDEX).
+  indexes exist; a fresh DB with indexes created last is the only safe path.
   Keep conversion + indexing separate so a conversion crash can't leave the
   DB mid-transaction.
 
 ## Tools
 
 ```bash
-bin/facts/audit.go ["self"|"facts"|"info"|"stale"]  # 2-source + staleness gate
+bin/facts/audit ["self"|"facts"|"info"|"stale"]   # 2-source + staleness gate
-bin/facts/crm.go [--dry-run]                       # proof person↔company/company↔project (ooCRM × corpus SoT)
+bin/facts/crm [--dry-run]                         # proof person↔company/company↔project (ooCRM × corpus SoT)
 bin/kb/search "query" [--repo X]                  # deprecated wrapper → bin/brain/search.go
 bin/brain/search.go "query" [--root facts|info]   # deduction search → YAML
-bin/brain/search.go "query" --no-web              # local graph only
-eval "$(bin/cgo/zig env)"                         # Zig cc + liblbug (not gcc)
-bin/brain/add.go --text T --root facts --source "a.md x b.md"  # incremental write
-bin/brain/add.go --json                                      # stdin leaf or {leafs:[...]}
-bin/brain/get.go <id> [--body] [--json]          # Go read; Python bin/kb/get CI fallback
-bin/brain/stats.go [--json]
-bin/brain/eval.go [--json]                       # recall@5; questions in internal/brain/rank
-bin/brain/serve.go                               # HTTP :8630; GET /openapi.json POST /mcp
-bin/markdown/import.go [dir]                      # H2 leafs → YAML; Python bin/md/import fallback
-bin/git/import.go [REPO] [--json] [--limit N]     # go-git history → commit leafs
-bin/web/search.go "query" [--json]                # SearXNG; throttled ≠ absence
-bin/reasoner/bakeoff.go [--model ID] [--json]     # D18 CPU tool-call bake-off
-bin/postgres/query.go --profile onlyoffice -c 'SELECT 1'
 bin/md/tables                                     # what the graph holds → YAML
 bin/brain/deduce "question"                       # thinking wrapper
 ```

Dockerfile

@@ -1,13 +1,5 @@
 # syntax=docker/dockerfile:1
-#
+FROM python:3.12-slim AS base
-#   docker build --target api -t 2dph:api .
-#   docker build --target index -t 2dph:index .
-#
-# API: Go + ladybug via Zig CGO (no CPython).
-# Index: Python write path (profile `index` until brain/add is v2).
-
-# --- Python sidecar (Ladybug write / rebuild) ---
-FROM python:3.12-slim AS index
 
 ENV PYTHONUNBUFFERED=1 \
     PYTHONDONTWRITEBYTECODE=1 \
@@ -17,11 +9,25 @@ ENV PYTHONUNBUFFERED=1 \
 WORKDIR /app
 RUN id -u 2dph 2>/dev/null || useradd --create-home --uid 1001 2dph
 
+# deps layer-first: rebuild only on dependency change
 COPY requirements.lock.txt /tmp/requirements.lock.txt
 RUN python -m pip install --no-cache-dir -r /tmp/requirements.lock.txt \
     && rm /tmp/requirements.lock.txt
 
+# Go services: static binaries, no interpreter at runtime
+FROM golang:1.25 AS go-build
+WORKDIR /src
+COPY go.mod ./
+COPY bin/server ./bin/server
+COPY bin/watch ./bin/watch
+RUN CGO_ENABLED=0 go build -o /serve ./bin/server \
+    && CGO_ENABLED=0 go build -o /watch ./bin/watch
+
+# runtime: python toolchain + Go services
+FROM base
 COPY . .
+COPY --from=go-build /serve /app/bin/serve
+COPY --from=go-build /watch /app/bin/watch
 RUN chmod +x /app/bin/docker-entrypoint \
     && chown -R 2dph:2dph /app
 USER 2dph
@@ -31,51 +37,5 @@ ENV PATH="/app/bin:${PATH}" \
     KB_ROOT=/app
 HEALTHCHECK --interval=30s --timeout=5s --start-period=10s --retries=3 \
     CMD python -c "import model2vec, ladybug, mistune; print('ok')" || exit 1
+
 ENTRYPOINT ["/app/bin/docker-entrypoint"]
-
-# --- Go API: CGO with Zig, not gcc ---
-FROM golang:1.26-bookworm AS api-build
-WORKDIR /src
-RUN apt-get update \
-    && apt-get install -y --no-install-recommends curl xz-utils ca-certificates \
-    && rm -rf /var/lib/apt/lists/*
-
-COPY bin/cgo ./bin/cgo
-RUN chmod +x bin/cgo/zig bin/cgo/zcc bin/cgo/zc++ \
-    && ./bin/cgo/zig env >/dev/null
-
-COPY go.mod go.sum ./
-RUN go mod download
-
-COPY . .
-ENV CGO_RPATH=/usr/local/lib
-RUN eval "$(./bin/cgo/zig env)" \
-    && go build -tags brain_serve,system_ladybug -o /out/brain-serve ./bin/brain/serve.go \
-    && go build -tags system_ladybug -o /out/brain-search ./bin/brain/search.go \
-    && CGO_ENABLED=0 go build -tags brain_watch -o /out/brain-watch ./bin/brain/watch.go
-
-FROM debian:bookworm-slim AS api
-RUN apt-get update \
-    && apt-get install -y --no-install-recommends libssl3 ca-certificates wget \
-    && rm -rf /var/lib/apt/lists/* \
-    && useradd --create-home --uid 1001 2dph
-COPY --from=api-build /out/brain-serve /usr/local/bin/brain-serve
-COPY --from=api-build /out/brain-search /usr/local/bin/brain-search
-COPY --from=api-build /out/brain-watch /usr/local/bin/brain-watch
-COPY --from=api-build /src/lib-ladybug/liblbug.so.0.19.1 /usr/local/lib/liblbug.so.0.19.1
-COPY bin/docker-entrypoint /usr/local/bin/docker-entrypoint
-RUN chmod +x /usr/local/bin/docker-entrypoint \
-    && ln -s liblbug.so.0.19.1 /usr/local/lib/liblbug.so.0 \
-    && ln -s liblbug.so.0 /usr/local/lib/liblbug.so \
-    && ldconfig
-USER 2dph
-ENV KB_ROOT=/data \
-    KB_PORT=8630 \
-    LD_LIBRARY_PATH=/usr/local/lib \
-    HF_HOME=/data/hf
-WORKDIR /data
-EXPOSE 8630
-HEALTHCHECK --interval=30s --timeout=5s --start-period=10s --retries=3 \
-    CMD wget -qO- http://127.0.0.1:8630/health || exit 1
-ENTRYPOINT ["/usr/local/bin/docker-entrypoint"]
-CMD ["serve"]

PLAN.md

@@ -4,9 +4,7 @@ A brain that loves facts and deduction. Evidence-first knowledge graph + hybrid
 RAG over the operational Brain/ops/eSlider stack. Built like Sherlock
 Holmes: nothing is asserted unless it has proof.
 
-Status: **in progress** — read path + MCP work; v1 goal is [epic #16](https://git.produktor.io/eSlider/2dph/issues/16)
+Status: **in progress** — this file is the plan and the record of decisions.
-(milestone [v1 detective brain](https://git.produktor.io/eSlider/2dph/milestone/12)).
-Gap: [docs/roadmap.md](docs/roadmap.md).
 
 ## What
 
@@ -28,12 +26,12 @@ detective method: **a fact needs ≥2 independent sources or it is
 |---|----------|--------|
 | D1 | RAG corpus | ops stack (chat, onlyoffice, gitea/NPM, searchxng, observability, ai-bot, mcp-servers, `~/.ssh/config`) + portfolio. Exclude `office.dev` + jobs/applications. |
 | D2 | skill merging | integrate skills **in this project** `skills/`; skip gitea / brain-dependent skills. |
-| D3 | web search | Go client `bin/web/search.go` (`internal/websearch`). SearXNG URL is config (`BRAIN_SEARCH_URL`). Optional Compose profile `searxng` (sanitized settings). Do not run a second copy on a host that already has one. Empty/`throttled` ≠ “nothing exists”. |
+| D3 | web search | import `web-search`, retire local `searxng-ops`. Vendored here, no remote link. |
 | D4 | embeddings | **model2vec** `minishlab/potion-multilingual-128M` instead of embeddinggemma. |
 | D5 | parser | **mistune** for MD → leaf extraction (duckdb-md documented as future optional SQL/export layer, not v1). |
-| D6 | graph engine | **LadybugDB**. Go is the service (`bin/brain/search.go`, `bin/brain/serve.go` in-process, `internal/brain`). Read path is Go + Zig CGO (D21). Python `bin/kb/{get,stats,eval}` is the CI fallback when Zig/libs are not fetched. Incremental write is Python `bin/kb/add` (`bin/brain/add.go`). Bulk rebuild stays `compose --profile index` until the Go write path is safe. |
+| D6 | graph engine | **LadybugDB** (Kuzu successor, MIT, embedded, native FTS+vector+Cypher). Python binding for `bin/*`; Go shebang for golang tools. |
 | D7 | db access | `db-yaml`/`psql-yq`-style, read-only, YAML out. OnlyOffice Postgres via SSH tunnel (`127.0.0.1:5433`). |
-| D8 | evidence | detective method: ≥2 independent sources or `(not confirmed)`. 2-source auto-pair docker ps × compose × ssh-config × docs. |
+| D8 | evidence | detective method: ≥2 independent sources or `(not confirmed)`. Auto-pair docker ps × compose × ssh-config × docs. |
 | D9 | facts/goal model | Who / What / How / Where / When + evidence + confidence on every edge. |
 | D10 | versioning | everything is a leaf with `sha256 + observed_at + source_rev`; `File-[:HAS_VERSION]->Commit-[:AUTHORED]->Person`. Stale = `source_rev` < git HEAD. |
 | D11 | strong/weak | `root` column: `facts` (strong) vs `info` (weak). Answer is `confirmed` only from facts root. |
@@ -42,11 +40,6 @@ detective method: **a fact needs ≥2 independent sources or it is
 | D14 | tooling style | `bin/{subject}/{method}.go` shebang (e.g. `bin/brain/search.go`). Shared code in `internal/`. One root `go.mod` + `go.work`. No `bin/*/main.go`, no nested modules. |
 | D15 | repo | Gitea [`eSlider/2dph`](https://git.produktor.io/eSlider/2dph) is origin + [issues](https://git.produktor.io/eSlider/2dph/issues). GitHub `eSlider/2dph` is the public clone (PRs + Actions CI). No direct `main` pushes. TDD → PR → CI green → merge. |
 | D16 | contradictions | ≥2 yes vs ≥2 no → unrelated sources conflict → hypothesis → `(not confirmed)`. Resolution (authority, staleness adjudication) = **v2**, tracked as open question. |
-| D17 | assertion gate | Fact-check every *claim* (facts → info → live → web), not every edit. `bin/brain/search.go` adds a `web` block when there is no facts hit (`throttled`/`skipped`/`refused` ≠ absence). `--root` and `--no-web` stay local. Missing graph ≠ “does not exist”. |
-| D18 | reasoner | Pluggable OpenAI-compatible URL (`REASONER_BASE_URL`). RAM: `Qwen/Qwen3.5-9B`. Quality: `prism-ml/Bonsai-27B-gguf` or `Qwen/Qwen3.6-27B`. No official Qwen3.6-9B. CPU bake-off: `bin/reasoner/bakeoff.go` + compose profile `reasoner` (`OLLAMA_NUM_GPU=0`, `:11435`). PicoClaw is compose profile `picoclaw`; tools are `search`/`get`/`audit`. Weights are not copied into the 2dph image. Agent lever/loop: [#15](https://git.produktor.io/eSlider/2dph/issues/15). |
-| D19 | git history | [go-git](https://github.com/go-git/go-git) via `bin/git/import.go`. No subprocess of the git binary. Conversion prints commit leafs; brain write is `bin/brain/index.go`. |
-| D20 | agent API | OpenAPI + MCP are generated from the same `internal/httpapi.Ops` table as `bin/brain/serve.go` handlers. `GET /openapi.json`, `POST /mcp` (JSON-RPC tools/list + tools/call). Tool names match OpenAPI paths (`search`/`get`/`stats`/`audit`/`ingest`). |
-| D21 | CGO | Ladybug/tokenizers CGO is compiled with **Zig** (`bin/cgo/zcc` → `zig cc -target …-linux-gnu`), not gcc. `bin/cgo/zig` pins Zig 0.14.1 + liblbug 0.19.1 + libtokenizers 1.27.0. Compose `target: api` has no CPython; write/rebuild is profile `index`. |
 
 ## Architecture
 
@@ -54,29 +47,16 @@ detective method: **a fact needs ≥2 independent sources or it is
 2dph/
   PLAN.md / AGENTS.md
   docs/                     published docs (this conversation → docs/ as md)
-  skills/                   in-project skills (web-search, postgres, brain, picoclaw, diataxis-docs)
+  skills/                   in-project skills (web-search, db-yaml, kb-search, agent-cost, diataxis-docs, …)
   bin/
-    facts/extract.go audit.go crm.go  # D14 shebang; Python implementation
+    facts/extract           auto-pair 2 sources → lexicon yaml + graph
-    kb/index                Python bulk write (called by bin/brain/index.go)
+    facts/audit             ["self"|"facts"|"info"|"stale"] 2-source + staleness gate
-    kb/add                  Python incremental write (called by bin/brain/add.go)
+    kb/index                build FTS + HNSW from corpus
-    brain/index.go          rebuild FTS + HNSW (incl. --with-mail)
+    kb/search               deduction: facts → info → web-search; --hop N
-    brain/add.go            incremental leaf write (no rebuild)
+    kb/get  kb/stats  kb/eval
-    brain/get.go stats.go eval.go  # Go read (cgo); Python bin/kb/* CI fallback
+    md/import  md/select  md/tables  md/gaps     (mistune)
-    brain/watch.go
-    brain/search.go         deduction: facts → info → web-search
-    brain/serve.go          HTTP API in-process + OpenAPI/MCP (D20); Zig CGO (D21)
-    cgo/zig zcc zc++        CGO toolchain (zig cc, not gcc)
-    mail/import.go          JSON → markdown (no brain write)
-    markdown/import.go      H2 leaf split (Go); Python bin/md/import fallback
-    postgres/query.go       read-only YAML (wraps bin/db/psql-yq)
-    git/import.go           go-git history (no git binary; conversion only)
-    web/search.go           SearXNG client (throttled ≠ absence)
-    reasoner/bakeoff.go     CPU tool-call bake-off (D18; OpenAI tools)
-    chats/sync.go import.go facts.go apply.go
-                            (libs in internal/chats; no chats index)
-    md/import               (deprecated; bin/markdown/import.go)
     brain/extract  brain/audit   brain/deduce    (thinking wrapper)
-    web/search               (deprecated shim → web/search.go)
+    web/search               (vendored)
     db/psql-yq               (vendored)
     ssh-tunnel               onlyoffice pg tunnel 5433
   var/kb.lbug               single embedded store (gitignored)
@@ -87,8 +67,7 @@ detective method: **a fact needs ≥2 independent sources or it is
 
 Node tables: `Person, Service, Host, Container, Repo, File, Commit, Leaf`.
 `Leaf(embedding FLOAT[N])` — FTS on `text`, HNSW vector index on `embedding`.
-Edges: `RUNS / USES / FROM_FILE / HAS_VERSION / AUTHORED / ABOUT / ASSOCIATED / SIMILAR_0.85`.
+Edges: `RUNS / USES / HAS_VERSION / AUTHORED / ABOUT / ASSOCIATED / SIMILAR_0.85`.
-`FROM_FILE` / `HAS_VERSION` exist in schema; search `--hop` does not walk them yet ([#17](https://git.produktor.io/eSlider/2dph/issues/17)).
 
 Common props on every node/edge: `root`, `confidence`, `evidence[]`, `how`,
 `where`, `when`, `source_rev`.
@@ -113,9 +92,9 @@ Common props on every node/edge: `root`, `confidence`, `evidence[]`, `how`,
 ## Open questions (v2)
 
 - OQ1: mutually-contradicting evidence — how to resolve (authority weighting,
-  temporal freshness, audit adjudication). **v2**; does not block epic #16.
+  temporal freshness, audit adjudication).
-- OQ2: OCR — poppler `pdftotext` fast-path exists; scans still docling.
+- OQ2: OCR pipeline for pdfs/images/docs — mostly solved: poppler pdftotext
-  [#6](https://git.produktor.io/eSlider/2dph/issues/6) (v2, does not block #16).
+  fast-path for born-digital PDFs, docling fallback for the ~5% textless ones.
 - OQ3: optional duckdb-md layer for `SELECT … FORMAT MARKDOWN` export/write-back.
 - OQ4: YAML-first storage for leafs — deferred: JSON is ~10x faster to
   serialize and unambiguous; YAML only where humans edit files.
@@ -124,27 +103,26 @@ Common props on every node/edge: `root`, `confidence`, `evidence[]`, `how`,
 
 1. `bin/mail/sync.go` (Go, 8 workers) — paginated Gmail/OnlyOffice download.
    Gmail attachments key off `body.attachmentId`, not MIME `partId`.
-2. `bin/mail/import.go --from-raw` — message.json → message.md; PDFs via
+2. `bin/mail/import --from-raw` — message.json → message.md; PDFs via
    `pdftotext -layout` (~15ms) with docling subprocess fallback; ICS sidecars
    Latin-1→UTF-8 normalized.
-3. `bin/brain/index.go --rebuild` — fresh rebuild (repo corpus + mail) because ladybug
+3. `bin/mail/index_mail` — fresh rebuild (repo corpus + mail) because ladybug
    corrupts its WAL on bulk-insert into an already-indexed DB. Conversion and
-   indexing stay separate for crash safety. `bin/mail/index_mail` is a
+   indexing stay separate for crash safety.
-   deprecation shim.
 4. Result: 17,835 messages → 28,918 info leafs, FTS + HNSW healthy, searchable
-   via `bin/brain/search.go`.
+   via `bin/kb/search`.
 
 ## CI/CD pipeline (D15)
 
 `.github/workflows/ci.yml`:
 
-1. go vet + go test ./... (root module; packages without ladybug cgo)
+1. go vet + go test ./... (Go tools; root module)
-2. `go test ./internal/brain/rank` (cgo-free ranking + flag parser)
+2. `go test ./rank` in `bin/kbsearch` (cgo-free ranking + flag parser; nested module still needs ladybug for the rest)
-3. python -m unittest discover -s bin/tools (includes published-docs SoT)
+3. `go test ./...` in `bin/chats` (Telegram + LinkedIn parsers; nested module)
-4. `bin/facts/audit self` (lexicon internal consistency; `bin/facts/audit.go` is the D14 wrapper)
+4. python -m unittest discover (Py tools)
-5. `bin/kb/eval` (recall@5 ≥ 0.95). Local SoT is `bin/brain/eval.go` via Zig CGO.
+5. bin/facts/audit self  (lexicon internal consistency)
-   CI SoT switch: [#19](https://git.produktor.io/eSlider/2dph/issues/19).
+6. bin/kb/eval            (recall@5 ≥ 0.95, gates index regressions)
-6. `bin/cgo/zig go build -tags system_ladybug` (compile search with zig cc; fetches pinned zig+libs).
+7. md-docs build/lint if docs tooling arrives.
 
 Feedback loop: every commit → PR → CI → green/gate → merge. Same discipline as
 `db/tech-poc`: contract first where there is an OpenAPI/message shape.
@@ -153,28 +131,9 @@ Feedback loop: every commit → PR → CI → green/gate → merge. Same discipl
 
 1. scaffold repo (:done after this file + AGENTS.md + .gitignore + ci)
 2. gh repo create eSlider/2dph --private + initial commit + CI
-3. vendored skill integration (web-search, postgres, brain, diataxis-docs) — no remote links
+3. vendored skill integration (web-search, db-yaml, kb-search, agent-cost, diataxis-docs) — no remote links
 4. .venv: ladybug + model2vec + mistune
 5. schema + tools with TDD (kb + md + facts + brain)
 6. ~/.config/brain config
-7. corpus extraction (facts/info) — **open**: [#18](https://git.produktor.io/eSlider/2dph/issues/18)
+7. corpus extraction (facts/info)
 8. verify: web-search smoke, onlyoffice pg, md-db round-trip, eval, audit
-
-## Gap to v1 (epic #16)
-
-Read path + MCP are in. Incremental `brain/add` is in. The detective brain is
-not closed until search can **walk** the graph and the facts+chats corpus
-lands on rebuild. Board:
-[epic #16](https://git.produktor.io/eSlider/2dph/issues/16),
-milestone [v1 detective brain](https://git.produktor.io/eSlider/2dph/milestone/12).
-Narrative: [docs/roadmap.md](docs/roadmap.md).
-
-| Order | Issue | Gap |
-|-------|-------|-----|
-| 1 | [#14](https://git.produktor.io/eSlider/2dph/issues/14) | **in** — `bin/brain/add.go` / `POST /ingest` write facts+info without deleting `kb.lbug`. Bulk corpus still `--rebuild`. Leftover Python (mail/facts) is not the living-graph blocker. |
-| 2 | [#17](https://git.produktor.io/eSlider/2dph/issues/17) | `--hop` errors. `FROM_FILE` / `HAS_VERSION` are in schema; search does not walk them. |
-| 3 | [#18](https://git.produktor.io/eSlider/2dph/issues/18) | Rebuild is mostly `info` (repo md + mail). `facts/extract` and chats are not a first-class index input. WhatsApp sync is a stub. |
-| 4 | [#15](https://git.produktor.io/eSlider/2dph/issues/15) | **in** — lever/loop documented (`search` → `get` → `audit`). |
-| 5 | [#19](https://git.produktor.io/eSlider/2dph/issues/19) | GitHub CI recall still runs Python `bin/kb/eval`. |
-
-Does **not** block epic close: [#6](https://git.produktor.io/eSlider/2dph/issues/6) OCR, OQ1, OQ3, OQ4.

README.md

@@ -7,16 +7,14 @@
 [![Latest Release](https://img.shields.io/github/v/tag/eSlider/2dph?sort=semver&label=release)](https://github.com/eSlider/2dph/releases)
 [![GitHub Stars](https://img.shields.io/github/stars/eSlider/2dph?style=social)](https://github.com/eSlider/2dph/stargazers)
 
-An evidence-first brain. **Facts need two independent sources, or they are
+An evidence-first brain over the operational eSlider stack. **Facts need two
-`(not confirmed)`.** Cursor is not the runtime.
+independent sources, or they are `(not confirmed)`.**
 
-`2dph` is a single embedded knowledge graph (LadybugDB) with native **HNSW
+`2dph` is a single embedded knowledge graph (LadybugDB = Kuzu successor) with
-vector** + **BM25 full-text** indexes. Search is *deduction*: confirmed facts
+native **HNSW vector** + **BM25 full-text** indexes, built from markdown,
-first, supporting info second, `web-search` as the independent second source
+compose files, ssh config, docker state, and git history. Search is
-when the local graph cannot confirm.
+*deduction*: confirmed facts first, supporting info second, `web-search` as
-
+the independent second source when the local graph cannot confirm.
-Run it: [docs/runbook.md](docs/runbook.md). Design: [docs/design.md](docs/design.md).
-Docs index: [docs/README.md](docs/README.md).
 
 ## Architecture
 
@@ -30,11 +28,11 @@ graph TB
     end
 
     subgraph dph["2dph tools"]
-        EX["bin/facts/extract.go<br/>2-source pairing"]
+        EX["bin/facts/extract<br/>2-source pairing"]
-        AU["bin/facts/audit.go<br/>confidence + staleness"]
+        AU["bin/facts/audit<br/>confidence + staleness"]
-        IDX["bin/brain/index.go<br/>chunk + embed"]
+        IDX["bin/kb/index<br/>chunk + embed"]
-        MD["bin/markdown/import.go<br/>H2 leaf split"]
+        MD["bin/md/import<br/>mistune leaves"]
-        SR["bin/brain/search.go<br/>deduction"]
+        SR["bin/kb/search<br/>deduction + --hop"]
     end
 
     subgraph store["Ladybug var/kb.lbug"]
@@ -76,7 +74,7 @@ graph TB
 ## The method
 
 Every assertion is `Who / What / How / Where / When + evidence + confidence`,
-mirroring the detective method: **≥2 independent sources confirm a
+mirroring the detective detective skill: **≥2 independent sources confirm a
 fact; conflicting sources or a single source → `hypothesis` → `(not confirmed)`.**
 
 | root | meaning | used for answers |
@@ -87,82 +85,58 @@ fact; conflicting sources or a single source → `hypothesis` → `(not confirme
 ## Deduction search
 
 ```bash
-bin/brain/search.go "Matrix federation over HTTPS"   # facts → info → web
+bin/kb/search "Matrix federation over HTTPS"      # facts → info → web-search
-bin/brain/search.go "onlyoffice postgres" --root facts
+bin/kb/search "what runs on arc-2" --hop 1        # walk graph edges
-bin/brain/search.go "where is cs-lexicon" --json | yq '.'
+bin/kb/search "where is cs-lexicon" --json | yq '.'  # YAML by default
-bin/brain/search.go "upstream flag" --no-web         # local graph only
+bin/kb/get <id> --body                            # full chunk on demand
-bin/brain/get.go <id> --body                         # full chunk on demand
+bin/kb/stats                                      # index health
-bin/brain/stats.go                                   # index health
+bin/kb/eval                                       # recall@5 gate
-bin/brain/eval.go                                    # recall@5 gate
-```
-
-`--hop` is not implemented (needs File/FROM_FILE edges); the flag errors instead of walking. `bin/kb/search` is a deprecated wrapper around `bin/brain/search.go`.
-
-Git history is read with [go-git](https://github.com/go-git/go-git) (no git binary):
-
-```bash
-bin/git/import.go --json --limit 100              # commit leafs for this repo
-bin/git/import.go --root "$PROJECTS_ROOT" --json  # one pass per .git under root
-```
-
-Conversion only. Graph write (`File-[:HAS_VERSION]->Commit-[:AUTHORED]->Person`) stays with `bin/brain/index.go`.
-
-Web search (second independent source) goes through SearXNG. Empty results mean **throttled**, not “nothing exists”:
-
-```bash
-bin/web/search.go "LadybugDB vector index" --json
-# Optional local instance (skip if BRAIN_SEARCH_URL already points at one):
-# SEARXNG_SECRET=$(openssl rand -hex 32) docker compose --profile searxng up -d
 ```
 
 Mail is a first-class corpus (retrievable through the same search):
 
 ```bash
 bin/mail/sync.go --source onlyoffice,gmail --workers 8 --out var/mail  # raw sync (Go)
-bin/mail/import.go --from-raw var/mail                                  # JSON → markdown
+bin/mail/import --from-raw var/mail                                     # JSON → markdown
-bin/brain/add.go --text T --root facts --source "a.md x b.md"
+bin/mail/index_mail                                                     # rebuild brain incl. mail
-bin/brain/index.go --rebuild                                            # rebuild brain (incl. mail)
+bin/kb/search "Mietwagen Nürnberg invoice"                              # now answers from mail
-bin/brain/search.go "invoice from last week"                            # same search over mail leafs
 ```
 
 ## Storage
 
-- **LadybugDB** — single `var/kb.lbug`, Cypher + HNSW + BM25, embedded.
+- **LadybugDB** — single `var/kb.lbug`, Cypher property graph, HNSW + BM25
-  Read tools (`get` / `stats` / `eval`) are Go + Zig CGO (`bin/cgo/zcc`).
+  in one engine, embedded (no server), ACID, read-only-safe for concurrent
-  Python fallbacks stay for CI until the runner fetches Zig. Incremental
+  readers. **Never `DROP INDEX` FTS/VECTOR** on Ladybug 0.19: DROP leaves
-  write is `bin/brain/add.go` (Python `kblib.add_leafs`). Bulk rebuild is
+  ghost catalog tables (`_0_Leaf_vec_UPPER`) so recreate fails while
-  Compose profile `index` (`bin/brain/index.go --rebuild`).
+  `SHOW_INDEXES` omits HNSW. Fresh indexes = delete `var/kb.lbug` +
-- **model2vec** — `potion-multilingual-128M` (256-dim), CPU, no Ollama
+  `bin/kb/index --rebuild`. Use `ensure_indexes()` after upserts.
-  runtime dependency.
+- **model2vec** — `potion-multilingual-128M` static embeddings (256-dim),
-- facts and info split by `root` but written in the same transaction.
+  CPU-fast, deterministic, no Ollama runtime dependency.
-
+- facts and info split semantically by `root` column but written inside the
-Ladybug 0.19 DROP INDEX warning: [docs/runbook.md](docs/runbook.md).
+  same transaction.
 
 ## Tooling conventions
 
-`bin/{subject}/{method}.go` — self-describing: shebang on line 1, usage comment
+`bin/{subject}/{method}` — self-describing: shebang on line 1, usage comment
-from line 2. Shared code in `internal/`. YAML default output, `--json` for
+from line 2. bash + python primary; golang via the Go shebang when a compiled
-machines. Tests gate every commit. HTTP: `bin/brain/serve.go` calls
+helper is right. YAML default output, `--json` for machines. Everything that
-`internal/brain` in-process (`/health` `/search` `/get` `/stats` `/audit` `/ingest` `/openapi.json` `/mcp`).
+touches network/db is read-only, throttled, cached. Tests gate every commit.
 
 ## Development
 
-See the portable runbook: [docs/runbook.md](docs/runbook.md).
-
 ```bash
-uv venv .venv
+uv venv .venv                                  # Python 3.12, uv-managed
-uv pip install -r requirements.lock.txt
+uv pip install -r requirements.lock.txt        # pinned toolchain
-bin/facts/audit.go self
+bin/facts/audit self                           # lexicon consistency gate
-go test ./... && uv run python -m unittest discover -s bin/tools -t .
+go test ./... && python -m unittest discover -s bin/tools -t .
 ```
 
 Docker (optional, cached model + var volumes):
 
 ```bash
-docker compose up -d brain                     # API (Zig CGO serve :8630)
+docker compose run --rm brain index            # (re)index corpus
-docker compose --profile index run --rm index  # Python Ladybug rebuild
+docker compose run --rm brain search "query"   # one-shot query
-docker compose --profile picoclaw up brain-mcp # MCP on 127.0.0.1:8630
+docker compose run --rm brain serve            # async Go HTTP server
-docker compose --profile reasoner up -d reasoner  # CPU Ollama 127.0.0.1:11435
 docker compose up brain-watch                  # auto re-index on change
 ```
 
@@ -171,12 +145,10 @@ docker compose up brain-watch                  # auto re-index on change
 - [go-second-brain](https://github.com/eSlider/go-second-brain) — the earlier
   Neo4j + Qdrant + Matrix RAG brain
 - [agent-skills](https://github.com/eSlider/agent-skills) — upstream
-  skills (`web-search`, `postgres`, …) that 2dph integrates
+  skills (`web-search`, `db-yaml`, …) that 2dph integrates
 - detective method — the two-source method
 
-Work board (issues): [epic #16](https://git.produktor.io/eSlider/2dph/issues/16)
+Work board (issues): [git.produktor.io/eSlider/2dph/issues](https://git.produktor.io/eSlider/2dph/issues).
-on [git.produktor.io/eSlider/2dph/issues](https://git.produktor.io/eSlider/2dph/issues).
 PRs and CI: GitHub [`eSlider/2dph`](https://github.com/eSlider/2dph).
 
-See [PLAN.md](PLAN.md) for decisions, [docs/roadmap.md](docs/roadmap.md) for
+See [PLAN.md](PLAN.md) for decisions, execution status, and v2 open questions.
-the gap to v1, and v2 open questions.

bin/brain/add.go

@@ -1,21 +0,0 @@
-//usr/bin/env go run -tags=brain_add "$0" "$@"; exit
-//go:build brain_add
-//
-// bin/brain/add.go - incremental leaf write (Python kblib, no rebuild).
-//
-//	./bin/brain/add.go --text T --root facts --source "a.md x b.md"
-//	./bin/brain/add.go --json
-//
-// D6: write stays Python. Does not delete var/kb.lbug.
-// NOTE: never run `gofmt -w` on this file — it breaks the shebang.
-package main
-
-import (
-	"os"
-
-	"github.com/eSlider/2dph/internal/cmdbin"
-)
-
-func main() {
-	os.Exit(cmdbin.ExecFile("bin/kb/add", os.Args[1:]))
-}

bin/brain/doc.go

@@ -1,3 +1,3 @@
-// Commands in this directory are shebang mains (search.go, serve.go, index.go,
+// Commands in this directory are shebang mains (search.go).
-// get.go, stats.go, eval.go, watch.go), each behind an exclusive build tag.
+// search.go is behind the system_ladybug build tag (cgo).
 package main

bin/brain/eval.go

@@ -1,22 +0,0 @@
-//usr/bin/env go run -tags=system_ladybug,brain_eval "$0" "$@"; exit
-//go:build cgo && system_ladybug && brain_eval
-//
-// bin/brain/eval.go - recall@5 gate.
-//
-//	./bin/brain/eval.go
-//	./bin/brain/eval.go --json
-//
-// Needs CGO + libladybug. Python bin/kb/eval is the CI fallback (no cgo).
-// Control questions live in internal/brain/rank (cgo-free).
-// NOTE: never run `gofmt -w` on this file — it breaks the shebang.
-package main
-
-import (
-	"os"
-
-	"github.com/eSlider/2dph/internal/brain"
-)
-
-func main() {
-	os.Exit(brain.MainEval(os.Args[1:]))
-}

bin/brain/get.go

@@ -1,23 +0,0 @@
-//usr/bin/env go run -tags=system_ladybug,brain_get "$0" "$@"; exit
-//go:build cgo && system_ladybug && brain_get
-//
-// bin/brain/get.go - read one leaf by id.
-//
-//	./bin/brain/get.go <id>
-//	./bin/brain/get.go <id> --body
-//	./bin/brain/get.go <id> --json
-//
-// Needs CGO + libladybug. Python bin/kb/get is the CI fallback (no cgo).
-// CGO compiler is Zig (`eval "$(bin/cgo/zig env)"`), not gcc.
-// NOTE: never run `gofmt -w` on this file — it breaks the shebang.
-package main
-
-import (
-	"os"
-
-	"github.com/eSlider/2dph/internal/brain"
-)
-
-func main() {
-	os.Exit(brain.MainGet(os.Args[1:]))
-}

bin/brain/index.go

@@ -1,24 +0,0 @@
-//usr/bin/env go run -tags=brain_index "$0" "$@"; exit
-//go:build brain_index
-//
-// bin/brain/index.go - rebuild the Ladybug graph (Python write path).
-//
-//	./bin/brain/index.go --rebuild
-//	./bin/brain/index.go --rebuild --with-mail
-//	./bin/brain/index.go --dry-run --with-mail
-//
-// v1 write: bin/brain/add.go for one/few leafs (indexes may already exist).
-// Bulk mail/corpus still --rebuild (fresh file, indexes last).
-// NOTE: never run `gofmt -w` on this file — it breaks the shebang.
-package main
-
-import (
-	"os"
-
-	"github.com/eSlider/2dph/internal/cmdbin"
-)
-
-func main() {
-	args := append([]string{"--with-mail"}, os.Args[1:]...)
-	os.Exit(cmdbin.ExecFile("bin/kb/index", args))
-}

bin/brain/search.go

@@ -3,11 +3,11 @@
 //
 // bin/brain/search.go - deduction search over the 2dph brain.
 //
-//	./bin/brain/search.go "query" [--root facts|info] [--repo P] [-n N] [--json] [--no-web]
+//	./bin/brain/search.go "query" [--root facts|info] [--repo P] [-n N] [--json]
 //	./bin/brain/search.go serve [port]
 //	./bin/brain/search.go --list-model
 //
-// Needs CGO + libladybug via Zig (`eval "$(bin/cgo/zig env)"`), not gcc.
+// Needs CGO + libladybug (CGO_CFLAGS/CGO_LDFLAGS). Prefer the wrapper
 // bin/kb/search which sets those and builds a binary for the embed daemon.
 // NOTE: never run `gofmt -w` on this file — it breaks the shebang.
 package main

bin/brain/serve.go

@@ -1,23 +1,18 @@
-//usr/bin/env go run -tags=brain_serve,system_ladybug "$0" "$@"; exit
+//usr/bin/env go run -tags=brain_serve "$0" "$@"; exit
-//go:build brain_serve && cgo && system_ladybug
+//go:build brain_serve
 //
-// bin/brain/serve.go - HTTP API (in-process ladybug search).
+// bin/brain/serve.go - HTTP API for the 2dph brain.
 //
 //	KB_ROOT=/path/to/2dph ./bin/brain/serve.go
-//	KB_WORKERS=4 KB_PORT=8630 ./bin/brain/serve.go
+//	KB_SEARCH_CMD=... KB_WORKERS=4 KB_PORT=8630 ./bin/brain/serve.go
 //
-//	GET  /openapi.json  same Ops table as the handlers
+// Default search backend is var/bin/brain-search (Go), not Python.
-//	POST /mcp           JSON-RPC tools/list + tools/call
-//
-// Needs CGO + libladybug (same as bin/brain/search.go).
 // NOTE: never run `gofmt -w` on this file — it breaks the shebang.
 package main
 
 import (
-	"log"
 	"os"
 
-	"github.com/eSlider/2dph/internal/brain"
 	"github.com/eSlider/2dph/internal/httpapi"
 )
 
@@ -27,8 +22,5 @@ func main() {
 			os.Setenv("KB_ROOT", wd)
 		}
 	}
-	if err := brain.Ready(); err != nil {
+	httpapi.Run()
-		log.Fatal(err)
-	}
-	httpapi.Run(brain.HTTP{})
 }

bin/brain/serve_exec.go

@@ -1,20 +0,0 @@
-//go:build brain_serve && !system_ladybug
-//
-// Fallback serve when ladybug cgo is not in the build (CI / tags=brain_serve).
-// Production shebang is serve.go (in-process).
-package main
-
-import (
-	"os"
-
-	"github.com/eSlider/2dph/internal/httpapi"
-)
-
-func main() {
-	if os.Getenv("KB_ROOT") == "" {
-		if wd, err := os.Getwd(); err == nil {
-			os.Setenv("KB_ROOT", wd)
-		}
-	}
-	httpapi.Run(nil)
-}

bin/brain/stats.go

@@ -1,21 +0,0 @@
-//usr/bin/env go run -tags=system_ladybug,brain_stats "$0" "$@"; exit
-//go:build cgo && system_ladybug && brain_stats
-//
-// bin/brain/stats.go - index health.
-//
-//	./bin/brain/stats.go
-//	./bin/brain/stats.go --json
-//
-// Needs CGO + libladybug. Python bin/kb/stats is the CI fallback (no cgo).
-// NOTE: never run `gofmt -w` on this file — it breaks the shebang.
-package main
-
-import (
-	"os"
-
-	"github.com/eSlider/2dph/internal/brain"
-)
-
-func main() {
-	os.Exit(brain.MainStats(os.Args[1:]))
-}

bin/brain/watch.go

@@ -1,20 +0,0 @@
-//usr/bin/env go run -tags=brain_watch "$0" "$@"; exit
-//go:build brain_watch
-//
-// bin/brain/watch.go - re-index when corpus files change.
-//
-//	./bin/brain/watch.go [dir...]
-//	KB_WATCH_INTERVAL=15 ./bin/brain/watch.go
-//
-// NOTE: never run `gofmt -w` on this file — it breaks the shebang.
-package main
-
-import (
-	"os"
-
-	"github.com/eSlider/2dph/bin/watch"
-)
-
-func main() {
-	watch.Run(os.Args[1:])
-}

bin/cgo/zc++

@@ -1,23 +0,0 @@
-#!/bin/sh
-# bin/cgo/zc++ — CGO CXX. Zig, not g++.
-set -eu
-ROOT="$(CDPATH= cd -- "$(dirname "$0")/../.." && pwd)"
-case "$(uname -m)" in
-  x86_64|amd64) TARGET=x86_64-linux-gnu ;;
-  aarch64|arm64) TARGET=aarch64-linux-gnu ;;
-  *)
-    echo "zc++: unsupported arch $(uname -m)" >&2
-    exit 2
-    ;;
-esac
-if [ -n "${ZIG:-}" ] && [ -x "$ZIG" ]; then
-  :
-elif [ -x "$ROOT/var/zig/zig" ]; then
-  ZIG="$ROOT/var/zig/zig"
-elif command -v zig >/dev/null 2>&1; then
-  ZIG="$(command -v zig)"
-else
-  echo "zc++: zig missing; run bin/cgo/zig first" >&2
-  exit 127
-fi
-exec "$ZIG" c++ -target "$TARGET" "$@"

bin/cgo/zcc

@@ -1,24 +0,0 @@
-#!/bin/sh
-# bin/cgo/zcc — CGO CC. Zig, not gcc.
-# Go invokes CC with many args; a wrapper avoids spaces in $CC.
-set -eu
-ROOT="$(CDPATH= cd -- "$(dirname "$0")/../.." && pwd)"
-case "$(uname -m)" in
-  x86_64|amd64) TARGET=x86_64-linux-gnu ;;
-  aarch64|arm64) TARGET=aarch64-linux-gnu ;;
-  *)
-    echo "zcc: unsupported arch $(uname -m)" >&2
-    exit 2
-    ;;
-esac
-if [ -n "${ZIG:-}" ] && [ -x "$ZIG" ]; then
-  :
-elif [ -x "$ROOT/var/zig/zig" ]; then
-  ZIG="$ROOT/var/zig/zig"
-elif command -v zig >/dev/null 2>&1; then
-  ZIG="$(command -v zig)"
-else
-  echo "zcc: zig missing; run bin/cgo/zig first" >&2
-  exit 127
-fi
-exec "$ZIG" cc -target "$TARGET" "$@"

bin/cgo/zig

@@ -1,130 +0,0 @@
-#!/usr/bin/env bash
-# bin/cgo/zig — CGO toolchain: zig cc (not gcc) + pinned liblbug + libtokenizers.
-#
-#   eval "$(bin/cgo/zig env)"     # export CC/CXX/CGO_*
-#   bin/cgo/zig go build ...      # ensure, then exec with env
-#   bin/cgo/zig ./bin/brain/search.go "query"
-#
-# Pins live in this file. Downloads land in var/ (gitignored).
-set -euo pipefail
-
-ROOT="$(CDPATH= cd -- "$(dirname "$0")/../.." && pwd)"
-ZIG_VERSION=0.14.1
-LBUG_VERSION=0.19.1
-TOKENIZERS_VERSION=1.27.0
-
-arch="$(uname -m)"
-case "$arch" in
-  x86_64|amd64)
-    ZIG_ARCH=x86_64
-    LBUG_ARCH=x86_64
-    TOK_ARCH=x86_64
-    ZIG_SHA=24aeeec8af16c381934a6cd7d95c807a8cb2cf7df9fa40d359aa884195c4716c
-    LBUG_SHA=ed263ae913f68cb0ddba0b98548b58edaac49929766d03bdaaa83be46c68847d
-    TOK_SHA=72556cdca798dd4ea7cdaba308e5f0d68a8cb93b67c96edf485b7a0edd7b07f4
-    ;;
-  aarch64|arm64)
-    ZIG_ARCH=aarch64
-    LBUG_ARCH=aarch64
-    TOK_ARCH=aarch64
-    ZIG_SHA=f7a654acc967864f7a050ddacfaa778c7504a0eca8d2b678839c21eea47c992b
-    LBUG_SHA=b07df2cd533c3976a2a3025866d6420a5f35514d0a822ecc4b2902d55b4725b7
-    TOK_SHA=e96545ad05930c26f51f63d932ee6d3bbd32bbed149e102c5290d587a2293067
-    ;;
-  *)
-    echo "bin/cgo/zig: unsupported arch $arch" >&2
-    exit 2
-    ;;
-esac
-
-CACHE="$ROOT/var/cache"
-LIB="$ROOT/lib-ladybug"
-ZIG_DIR="$ROOT/var/zig-dist"
-ZIG_BIN="$ROOT/var/zig/zig"
-
-sha256of() {
-  if command -v sha256sum >/dev/null 2>&1; then
-    sha256sum "$1" | awk '{print $1}'
-  else
-    shasum -a 256 "$1" | awk '{print $1}'
-  fi
-}
-
-fetch() {
-  local url="$1" dest="$2" expect="$3"
-  if [ -f "$dest" ] && [ "$(sha256of "$dest")" = "$expect" ]; then
-    return 0
-  fi
-  mkdir -p "$(dirname "$dest")"
-  echo "fetch $url" >&2
-  curl -fsSL "$url" -o "$dest"
-  local got
-  got="$(sha256of "$dest")"
-  if [ "$got" != "$expect" ]; then
-    echo "checksum mismatch $dest: got $got want $expect" >&2
-    rm -f "$dest"
-    exit 1
-  fi
-}
-
-ensure_zig() {
-  if [ -n "${ZIG:-}" ] && [ -x "$ZIG" ]; then
-    return 0
-  fi
-  if [ -x "$ZIG_BIN" ]; then
-    export ZIG="$ZIG_BIN"
-    return 0
-  fi
-  if command -v zig >/dev/null 2>&1; then
-    export ZIG
-    ZIG="$(command -v zig)"
-    return 0
-  fi
-  local tar="$CACHE/zig-${ZIG_ARCH}-linux-${ZIG_VERSION}.tar.xz"
-  fetch "https://ziglang.org/download/${ZIG_VERSION}/zig-${ZIG_ARCH}-linux-${ZIG_VERSION}.tar.xz" \
-    "$tar" "$ZIG_SHA"
-  mkdir -p "$CACHE"
-  rm -rf "$ZIG_DIR"
-  tar -xJf "$tar" -C "$CACHE"
-  mv "$CACHE/zig-${ZIG_ARCH}-linux-${ZIG_VERSION}" "$ZIG_DIR"
-  mkdir -p "$ROOT/var/zig"
-  ln -sfn "$ZIG_DIR/zig" "$ZIG_BIN"
-  export ZIG="$ZIG_BIN"
-}
-
-ensure_libs() {
-  mkdir -p "$LIB"
-  if [ ! -f "$LIB/liblbug.so" ]; then
-    local tar="$CACHE/liblbug-linux-${LBUG_ARCH}.tar.gz"
-    fetch "https://github.com/LadybugDB/ladybug/releases/download/v${LBUG_VERSION}/liblbug-linux-${LBUG_ARCH}.tar.gz" \
-      "$tar" "$LBUG_SHA"
-    tar -xzf "$tar" -C "$LIB"
-  fi
-  if [ ! -f "$LIB/libtokenizers.a" ]; then
-    local tar="$CACHE/libtokenizers.linux-${TOK_ARCH}.tar.gz"
-    fetch "https://github.com/daulet/tokenizers/releases/download/v${TOKENIZERS_VERSION}/libtokenizers.linux-${TOK_ARCH}.tar.gz" \
-      "$tar" "$TOK_SHA"
-    tar -xzf "$tar" -C "$LIB"
-  fi
-}
-
-print_env() {
-  printf 'export ZIG=%q\n' "$ZIG"
-  printf 'export CC=%q\n' "$ROOT/bin/cgo/zcc"
-  printf 'export CXX=%q\n' "$ROOT/bin/cgo/zc++"
-  printf 'export CGO_ENABLED=1\n'
-  printf 'export CGO_CFLAGS=%q\n' "-I$LIB"
-  printf 'export CGO_LDFLAGS=%q\n' "-L$LIB -Wl,-rpath,${CGO_RPATH:-$LIB}"
-}
-
-ensure_zig
-ensure_libs
-
-cmd="${1:-env}"
-if [ "$cmd" = "env" ]; then
-  print_env
-  exit 0
-fi
-
-eval "$(print_env)"
-exec "$@"

bin/chats/apply.go

@@ -1,19 +0,0 @@
-//usr/bin/env go run -tags=chats_apply "$0" "$@"; exit
-//go:build chats_apply
-//
-// bin/chats/apply.go - push extracted chat facts to OnlyOffice CRM.
-//
-//	./bin/chats/apply.go [--dry-run]
-//
-// NOTE: never run `gofmt -w` on this file — it breaks the shebang.
-package main
-
-import (
-	"os"
-
-	"github.com/eSlider/2dph/internal/chats"
-)
-
-func main() {
-	os.Exit(chats.RunApply(os.Args[1:]))
-}

bin/chats/apply_cmd.go

@@ -1,4 +1,4 @@
-package chats
+package main
 
 import (
 	"bytes"
@@ -24,7 +24,7 @@ type ooContact struct {
 	} `json:"commonData"`
 }
 
-func RunApply(args []string) int {
+func runApply(args []string) int {
 	fs := flag.NewFlagSet("chats apply", flag.ContinueOnError)
 	dryRun := fs.Bool("dry-run", false, "show what would be done without writing")
 	help := fs.Bool("help", false, "")
@@ -176,7 +176,7 @@ func RunApply(args []string) int {
 }
 
 func loadFacts() ([]ExtractedFact, error) {
-	factsPath := filepath.Join(Dir(), "facts", "chat-facts.json")
+	factsPath := filepath.Join(chatsDir(), "facts", "chat-facts.json")
 	data, err := os.ReadFile(factsPath)
 	if err != nil {
 		if os.IsNotExist(err) {

bin/chats/chats_test.go

@@ -3,7 +3,7 @@
 // These are integration tests using real data and real Telegram API (when
 // credentials are available). They follow the TDD workflow pattern:
 // sync → import → facts → verify.
-package chats
+package main
 
 import (
 	"encoding/json"
@@ -48,7 +48,7 @@ func TestChatsImport(t *testing.T) {
 	t.Cleanup(func() { os.Chdir(cwd) })
 	t.Setenv("KB_ROOT", dir)
 
-	exitCode := RunImport([]string{})
+	exitCode := runImport([]string{})
 	if exitCode != 0 {
 		t.Fatalf("import exit code %d", exitCode)
 	}
@@ -140,7 +140,7 @@ func TestChatsImportEmpty(t *testing.T) {
 	t.Cleanup(func() { os.Chdir(cwd) })
 	t.Setenv("KB_ROOT", dir)
 
-	exitCode := RunImport([]string{})
+	exitCode := runImport([]string{})
 	if exitCode == 0 {
 		t.Fatal("expected non-zero exit for empty data dir")
 	}
@@ -171,7 +171,7 @@ func TestChatsRoundTrip(t *testing.T) {
 	t.Cleanup(func() { os.Chdir(cwd) })
 	t.Setenv("KB_ROOT", dir)
 
-	if code := RunImport([]string{}); code != 0 {
+	if code := runImport([]string{}); code != 0 {
 		t.Fatalf("import exit %d", code)
 	}
 

bin/chats/doc.go

@@ -1,4 +0,0 @@
-// Commands in this directory are shebang mains (sync.go, import.go, facts.go,
-// apply.go), each behind an exclusive build tag so `go build ./bin/chats`
-// does not see two mains. Shared code lives in internal/chats.
-package main

bin/chats/facts.go

@@ -1,20 +0,0 @@
-//usr/bin/env go run -tags=chats_facts "$0" "$@"; exit
-//go:build chats_facts
-//
-// bin/chats/facts.go - extract phone/email/linkedin facts from JSONL.
-//
-//	./bin/chats/facts.go
-//
-// Writes var/chats/facts/. Does not index the brain.
-// NOTE: never run `gofmt -w` on this file — it breaks the shebang.
-package main
-
-import (
-	"os"
-
-	"github.com/eSlider/2dph/internal/chats"
-)
-
-func main() {
-	os.Exit(chats.RunFacts(os.Args[1:]))
-}

bin/chats/facts_cmd.go

@@ -1,11 +1,13 @@
-package chats
+package main
 
 import (
 	"bufio"
+	"bytes"
 	"encoding/json"
 	"flag"
 	"fmt"
 	"os"
+	"os/exec"
 	"path/filepath"
 	"regexp"
 	"strings"
@@ -75,7 +77,7 @@ type ExtractedFact struct {
 	MessageID string `json:"message_id"`
 }
 
-func RunFacts(args []string) int {
+func runFacts(args []string) int {
 	fs := flag.NewFlagSet("chats facts", flag.ContinueOnError)
 	help := fs.Bool("help", false, "")
 	fs.SetOutput(os.Stderr)
@@ -87,7 +89,7 @@ func RunFacts(args []string) int {
 		return 0
 	}
 
-	root := Dir()
+	root := chatsDir()
 	telegramDir := filepath.Join(root, "telegram")
 
 	entries, err := os.ReadDir(telegramDir)
@@ -147,7 +149,7 @@ func RunFacts(args []string) int {
 	}
 	fmt.Printf("chats facts: saved to %s\n", factsPath)
 
-	writeFactsMarkdown(allFacts)
+	writeFactsToBrain(root, allFacts)
 
 	return 0
 }
@@ -271,10 +273,14 @@ func filterFacts(facts []ExtractedFact, factType string) []ExtractedFact {
 	return result
 }
 
-// writeFactsMarkdown stores a sidecar for humans. Brain ingest is
+func writeFactsToBrain(root string, facts []ExtractedFact) {
-// bin/brain/index.go (not this subject).
+	indexScript := filepath.Join(root, "bin", "kb", "index")
-func writeFactsMarkdown(facts []ExtractedFact) {
+	if _, err := os.Stat(indexScript); os.IsNotExist(err) {
-	mdDir := filepath.Join(Dir(), "facts")
+		fmt.Fprintf(os.Stderr, "chats facts: kb/index not found, skipping brain write\n")
+		return
+	}
+
+	mdDir := filepath.Join(chatsDir(), "facts")
 	if err := os.MkdirAll(mdDir, 0755); err != nil {
 		fmt.Fprintf(os.Stderr, "chats facts: mkdir %s: %v\n", mdDir, err)
 		return
@@ -282,7 +288,7 @@ func writeFactsMarkdown(facts []ExtractedFact) {
 
 	var sb strings.Builder
 	sb.WriteString("---\n")
-	sb.WriteString("root: info\n")
+	sb.WriteString("root: facts\n")
 	sb.WriteString("---\n\n")
 	sb.WriteString("# Chat-Derived Facts\n\n")
 	for _, f := range facts {
@@ -296,5 +302,15 @@ func writeFactsMarkdown(facts []ExtractedFact) {
 		fmt.Fprintf(os.Stderr, "chats facts: write %s: %v\n", factsMD, err)
 		return
 	}
-	fmt.Printf("chats facts: markdown %s (index via brain, not chats)\n", factsMD)
+
+	cmd := exec.Command(indexScript, "--corpus", mdDir, "--skip-indexes")
+	var outBuf, errBuf bytes.Buffer
+	cmd.Stdout = &outBuf
+	cmd.Stderr = &errBuf
+	cmd.Dir = root
+	if err := cmd.Run(); err != nil {
+		fmt.Fprintf(os.Stderr, "chats facts: brain index: %v\n%s", err, errBuf.String())
+		return
+	}
+	fmt.Printf("chats facts: written to brain (%s)\n", strings.TrimSpace(outBuf.String()))
 }

bin/chats/import.go

@@ -1,20 +0,0 @@
-//usr/bin/env go run -tags=chats_import "$0" "$@"; exit
-//go:build chats_import
-//
-// bin/chats/import.go - JSONL → markdown under var/chats/md/.
-//
-//	./bin/chats/import.go
-//
-// Conversion only. Brain ingest is bin/brain/index.go, not this command.
-// NOTE: never run `gofmt -w` on this file — it breaks the shebang.
-package main
-
-import (
-	"os"
-
-	"github.com/eSlider/2dph/internal/chats"
-)
-
-func main() {
-	os.Exit(chats.RunImport(os.Args[1:]))
-}

bin/chats/import_cmd.go

@@ -1,4 +1,4 @@
-package chats
+package main
 
 import (
 	"bufio"
@@ -13,7 +13,7 @@ import (
 	"strings"
 )
 
-func RunImport(args []string) int {
+func runImport(args []string) int {
 	fs := flag.NewFlagSet("chats import", flag.ContinueOnError)
 	help := fs.Bool("help", false, "")
 	fs.SetOutput(os.Stderr)
@@ -25,7 +25,7 @@ func RunImport(args []string) int {
 		return 0
 	}
 
-	root := Dir()
+	root := chatsDir()
 	mdRoot := filepath.Join(root, "md")
 	glob := filepath.Join(root, "telegram", "*", "messages.jsonl")
 

bin/chats/index_cmd.go

@@ -0,0 +1,56 @@
+package main
+
+import (
+	"bytes"
+	"flag"
+	"fmt"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"strings"
+)
+
+func runIndex(args []string) int {
+	fs := flag.NewFlagSet("chats index", flag.ContinueOnError)
+	help := fs.Bool("help", false, "")
+	fs.SetOutput(os.Stderr)
+	if err := fs.Parse(args); err != nil {
+		return 2
+	}
+	if *help {
+		fmt.Fprintln(os.Stderr, "usage: chats index")
+		return 0
+	}
+
+	root := repoRoot()
+	mdDir := filepath.Join(chatsDir(), "md")
+
+	_, err := os.Stat(mdDir)
+	if os.IsNotExist(err) {
+		fmt.Fprintf(os.Stderr, "chats index: no chat markdown at %s; run 'chats import' first\n", mdDir)
+		return 1
+	}
+
+	indexScript := filepath.Join(root, "bin", "kb", "index")
+	if _, err := os.Stat(indexScript); os.IsNotExist(err) {
+		fmt.Fprintf(os.Stderr, "chats index: %s not found\n", indexScript)
+		return 1
+	}
+
+	cmd := exec.Command(indexScript, "--corpus", mdDir)
+	var outBuf, errBuf bytes.Buffer
+	cmd.Stdout = &outBuf
+	cmd.Stderr = &errBuf
+	cmd.Dir = root
+
+	if err := cmd.Run(); err != nil {
+		fmt.Fprintf(os.Stderr, "chats index: %v\n%s", err, errBuf.String())
+		return 1
+	}
+	result := strings.TrimSpace(outBuf.String())
+	if result == "" {
+		result = strings.TrimSpace(errBuf.String())
+	}
+	fmt.Printf("chats index: %s\n", result)
+	return 0
+}

bin/chats/linkedin.go

@@ -1,4 +1,4 @@
-package chats
+package main
 
 import (
 	"bufio"

bin/chats/linkedin_test.go

@@ -1,4 +1,4 @@
-package chats
+package main
 
 import (
 	"errors"

bin/chats/main.go

@@ -0,0 +1,115 @@
+// bin/chats - sync, import, index, extract facts, and apply chat data
+// from Telegram, WhatsApp, LinkedIn into the brain and OnlyOffice CRM.
+//
+// Usage:
+//
+//	chats sync telegram   [--limit N] [--since DATE] [--phone PHONE]
+//	chats sync whatsapp   [--qr] [--limit N]
+//	chats sync linkedin   [--limit N]
+//	chats import                           # JSONL → MD (all sources)
+//	chats index                            # rebuild var/kb.lbug with chats
+//	chats facts                            # extract + cross-check
+//	chats apply          [--dry-run]       # push to OnlyOffice CRM
+package main
+
+import (
+	"fmt"
+	"os"
+	"strings"
+)
+
+func main() {
+	if len(os.Args) < 2 {
+		usage()
+		os.Exit(2)
+	}
+	cmd := os.Args[1]
+	args := os.Args[2:]
+	switch cmd {
+	case "sync":
+		if len(args) < 1 {
+			usage()
+			os.Exit(2)
+		}
+		platform := args[0]
+		platformArgs := args[1:]
+		switch platform {
+		case "telegram":
+			os.Exit(runSyncTelegram(platformArgs))
+		case "whatsapp":
+			fmt.Fprintf(os.Stderr, "chats: WhatsApp not implemented yet\n")
+			os.Exit(1)
+		case "linkedin":
+			os.Exit(runSyncLinkedIn(platformArgs))
+		default:
+			fmt.Fprintf(os.Stderr, "chats: unknown platform %q\n", platform)
+			os.Exit(2)
+		}
+	case "import":
+		os.Exit(runImport(args))
+	case "index":
+		os.Exit(runIndex(args))
+	case "facts":
+		os.Exit(runFacts(args))
+	case "apply":
+		os.Exit(runApply(args))
+	case "help", "-h", "--help":
+		usage()
+		return
+	default:
+		fmt.Fprintf(os.Stderr, "chats: unknown command %q\n", cmd)
+		usage()
+		os.Exit(2)
+	}
+}
+
+func usage() {
+	w := os.Stderr
+	fmt.Fprintln(w, `Usage: chats <command> [args]
+
+Commands:
+  sync telegram  [--limit N] [--since DATE] [--phone PHONE]
+  sync whatsapp  [--qr] [--limit N]
+  sync linkedin  [--limit N]
+  import                             JSONL → MD (all sources)
+  index                              rebuild var/kb.lbug with chats
+  facts                              extract + cross-check facts
+  apply             [--dry-run]      push to OnlyOffice CRM
+
+Output layout:
+  var/chats/<platform>/<chat_id>/messages.jsonl
+  var/chats/md/<platform>/<chat_name>/messages.md`)
+}
+
+// repoRoot locates the 2dph project root by walking up from the binary.
+func repoRoot() string {
+	if v := os.Getenv("KB_ROOT"); v != "" {
+		return v
+	}
+	wd, err := os.Getwd()
+	if err != nil {
+		return "."
+	}
+	for i := 0; i < 10; i++ {
+		if _, err := os.Stat(wd + "/var"); err == nil {
+			return wd
+		}
+		if _, err := os.Stat(wd + "/.git"); err == nil {
+			return wd
+		}
+		parent := wd
+		if idx := strings.LastIndex(wd, "/"); idx >= 0 {
+			parent = wd[:idx]
+		}
+		if parent == wd {
+			break
+		}
+		wd = parent
+	}
+	return "."
+}
+
+// chatsDir returns var/chats under the repo root.
+func chatsDir() string {
+	return repoRoot() + "/var/chats"
+}

bin/chats/mcpclient.go

@@ -1,4 +1,4 @@
-package chats
+package main
 
 import (
 	"bufio"

bin/chats/source.go

@@ -1,4 +1,4 @@
-package chats
+package main
 
 import (
 	"context"

bin/chats/sync.go

@@ -1,41 +0,0 @@
-//usr/bin/env go run -tags=chats_sync "$0" "$@"; exit
-//go:build chats_sync
-//
-// bin/chats/sync.go - download chat messages to var/chats/<platform>/.
-//
-//	./bin/chats/sync.go telegram [--limit N] [--phone PHONE]
-//	./bin/chats/sync.go linkedin [--limit N] [--refresh]
-//
-// NOTE: never run `gofmt -w` on this file — it breaks the shebang.
-package main
-
-import (
-	"fmt"
-	"os"
-
-	"github.com/eSlider/2dph/internal/chats"
-)
-
-func main() {
-	if len(os.Args) < 2 {
-		fmt.Fprintln(os.Stderr, `usage: bin/chats/sync.go telegram|linkedin [flags]`)
-		os.Exit(2)
-	}
-	platform := os.Args[1]
-	args := os.Args[2:]
-	switch platform {
-	case "telegram":
-		os.Exit(chats.RunSyncTelegram(args))
-	case "linkedin":
-		os.Exit(chats.RunSyncLinkedIn(args))
-	case "whatsapp":
-		fmt.Fprintln(os.Stderr, "chats: WhatsApp not implemented yet")
-		os.Exit(1)
-	case "help", "-h", "--help":
-		fmt.Fprintln(os.Stderr, `usage: bin/chats/sync.go telegram|linkedin [flags]`)
-		return
-	default:
-		fmt.Fprintf(os.Stderr, "chats: unknown platform %q\n", platform)
-		os.Exit(2)
-	}
-}

bin/chats/sync_cmd.go

@@ -1,4 +1,4 @@
-package chats
+package main
 
 import (
 	"context"
@@ -11,7 +11,7 @@ import (
 	"time"
 )
 
-func RunSyncTelegram(args []string) int {
+func runSyncTelegram(args []string) int {
 	fs := flag.NewFlagSet("chats sync telegram", flag.ContinueOnError)
 	limit := fs.Int("limit", 0, "max messages per chat (0 = all)")
 	phone := fs.String("phone", "", "phone number (default env TELEGRAM_PHONE)")
@@ -78,7 +78,7 @@ func RunSyncTelegram(args []string) int {
 	defer cancel()
 
 	start := time.Now()
-	if err := src.Sync(ctx, Dir(), *limit); err != nil {
+	if err := src.Sync(ctx, chatsDir(), *limit); err != nil {
 		fmt.Fprintf(os.Stderr, "chats sync telegram: %v\n", err)
 		return 1
 	}

bin/chats/sync_linkedin_cmd.go

@@ -1,4 +1,4 @@
-package chats
+package main
 
 import (
 	"context"
@@ -28,7 +28,7 @@ func checkLinkedInSession(userDataDir string) (bool, error) {
 	return false, nil
 }
 
-func RunSyncLinkedIn(args []string) int {
+func runSyncLinkedIn(args []string) int {
 	fs := flag.NewFlagSet("chats sync linkedin", flag.ContinueOnError)
 	limit := fs.Int("limit", 0, "max messages per conversation (0 = all)")
 	refresh := fs.Bool("refresh", false, "refresh session from live webtop browser before sync")
@@ -72,7 +72,7 @@ func RunSyncLinkedIn(args []string) int {
 	defer cancel()
 
 	start := time.Now()
-	if err := src.Sync(ctx, Dir(), *limit); err != nil {
+	if err := src.Sync(ctx, chatsDir(), *limit); err != nil {
 		fmt.Fprintf(os.Stderr, "chats sync linkedin: %v\n", err)
 		return 1
 	}

bin/docker-entrypoint

@@ -1,10 +1,13 @@
 #!/usr/bin/env bash
 # bin/docker-entrypoint - run 2dph tools inside the container.
 #
-# API image (Zig CGO binaries):
+#   brain                 shell (default)
-#   serve | search | watch
+#   brain search <q>      bin/kb/search
-# Index image (Python write path, compose profile `index`):
+#   brain index           bin/kb/index
-#   index | extract | audit | search (deprecated python wrapper)
+#   brain watch <dir>     watchdog re-indexer (bin/kb/watch)
+#   brain serve           async Go HTTP server (bin/serve)
+#   brain extract         bin/facts/extract (docker×compose pairing)
+#   brain audit           bin/facts/audit
 #
 # Usage comment starts at line 2 (self-describing convention).
 set -euo pipefail
@@ -12,24 +15,10 @@ set -euo pipefail
 CMD="${1:-shell}"
 shift || true
 
-if [ -x /usr/local/bin/brain-serve ]; then
-	case "$CMD" in
-		shell) exec bash ;;
-		serve) exec /usr/local/bin/brain-serve "$@" ;;
-		search) exec /usr/local/bin/brain-search "$@" ;;
-		watch) exec /usr/local/bin/brain-watch "$@" ;;
-		index)
-			echo "index is the Python sidecar: docker compose --profile index run --rm index" >&2
-			exit 2
-			;;
-		*) echo "unknown command: $CMD (api: serve|search|watch)" >&2; exit 2 ;;
-	esac
-fi
-
 case "$CMD" in
   shell) exec bash ;;
   search) exec "$KB_PY" /app/bin/kb/search "$@" ;;
-	index) exec "$KB_PY" /app/bin/kb/index --with-mail "$@" ;;
+  index) exec "$KB_PY" /app/bin/kb/index "$@" ;;
   watch) exec /app/bin/watch "$@" ;;
   serve) exec /app/bin/serve "$@" ;;
   extract) exec "$KB_PY" /app/bin/facts/extract "$@" ;;

bin/facts/audit.go

@@ -1,21 +0,0 @@
-//usr/bin/env go run -tags=facts_audit "$0" "$@"; exit
-//go:build facts_audit
-//
-// bin/facts/audit.go - 2-source + lexicon checks.
-//
-//	./bin/facts/audit.go self
-//	./bin/facts/audit.go db
-//
-// Python bin/facts/audit is the implementation (CI runs it directly).
-// NOTE: never run `gofmt -w` on this file — it breaks the shebang.
-package main
-
-import (
-	"os"
-
-	"github.com/eSlider/2dph/internal/cmdbin"
-)
-
-func main() {
-	os.Exit(cmdbin.ExecFile("bin/facts/audit", os.Args[1:]))
-}

bin/facts/crm.go

@@ -1,20 +0,0 @@
-//usr/bin/env go run -tags=facts_crm "$0" "$@"; exit
-//go:build facts_crm
-//
-// bin/facts/crm.go - prove person↔company / company↔project (ooCRM × corpus).
-//
-//	./bin/facts/crm.go [--dry-run] [--mismatches]
-//
-// Python bin/facts/crm is the implementation. Graph write stays Python.
-// NOTE: never run `gofmt -w` on this file — it breaks the shebang.
-package main
-
-import (
-	"os"
-
-	"github.com/eSlider/2dph/internal/cmdbin"
-)
-
-func main() {
-	os.Exit(cmdbin.ExecFile("bin/facts/crm", os.Args[1:]))
-}

bin/facts/extract.go

@@ -1,20 +0,0 @@
-//usr/bin/env go run -tags=facts_extract "$0" "$@"; exit
-//go:build facts_extract
-//
-// bin/facts/extract.go - acquire confirmed facts (2-source each).
-//
-//	./bin/facts/extract.go [--json] [--dry-run]
-//
-// Python bin/facts/extract is the implementation. Graph write stays Python.
-// NOTE: never run `gofmt -w` on this file — it breaks the shebang.
-package main
-
-import (
-	"os"
-
-	"github.com/eSlider/2dph/internal/cmdbin"
-)
-
-func main() {
-	os.Exit(cmdbin.ExecFile("bin/facts/extract", os.Args[1:]))
-}

bin/git/import

@@ -1,25 +1,153 @@
 #!/usr/bin/env python3
-"""git/import — deprecated. Use bin/git/import.go (go-git, no git binary).
+"""git/import - import git history (commits, authors, files) into the brain.
 
-  bin/git/import.go [REPO] [--json] [--limit N] [--since DATE]
+  bin/git/import [REPO]                 import all commits -> leafs + graph
+  bin/git/import --json                 emit import leafs as JSON, no write
+  bin/git/import --limit 100            cap commits processed
+  bin/git/import --since 2026-01-01     only recent commits
+  bin/git/import --root DIR             run per repo dir under DIR
+  bin/git/import --no-env               never read .env anywhere (default: true)
+
+Reads `git log --no-merges --name-only` from the repo, maps commits to
+`info` leafs (root=info, type=commit) and writes the version graph
+`File -[:HAS_VERSION]-> Commit -[:AUTHORED]-> Person` into var/kb.lbug.
+Idempotent: leaf MERGE by (source,text via leaf_id), graph MERGE by sha.
 """
 from __future__ import annotations
 
-import os
+import json
+import subprocess
 import sys
 from pathlib import Path
 
 ROOT = Path(__file__).resolve().parents[2]
+sys.path.insert(0, str(ROOT / "bin" / "tools"))
+
+from kblib import (  # noqa: E402
+    connect, ensure_indexes, init_schema, upsert_leaf,
+)
+from gitimport import commits_to_leafs, ensure_git_schema, index_commits, parse_log  # noqa: E402
+
+LOG_FMT = "--format=%x1e%H%x1f%an%x1f%ae%x1f%aI%x1f%s"
+
+
+def git_log(repo: Path, limit: int = 0, since: str = "") -> str:
+    cmd = ["git", "-C", str(repo), "log", "--no-merges", "--name-only", LOG_FMT]
+    if since:
+        cmd += ["--since", since]
+    if limit:
+        cmd += ["-n", str(limit)]
+    try:
+        out = subprocess.run(cmd, capture_output=True, text=True, timeout=120)
+    except (FileNotFoundError, subprocess.TimeoutExpired):
+        return ""
+    if out.returncode != 0:
+        print(f"git/import: {repo}: {out.stderr.strip()}", file=sys.stderr)
+        return ""
+    return out.stdout
+
+
+def repo_name(repo: Path) -> str:
+    try:
+        out = subprocess.run(
+            ["git", "-C", str(repo), "remote", "get-url", "origin"],
+            capture_output=True, text=True, timeout=20)
+        url = out.stdout.strip()
+        return url.rstrip("/").split("/")[-1].removesuffix(".git") if url else repo.name
+    except (FileNotFoundError, subprocess.TimeoutExpired):
+        return repo.name
+
+
+def embedder():
+    from model2vec import StaticModel
+    model = StaticModel.from_pretrained("minishlab/potion-multilingual-128M")
+    return lambda text: model.encode([text])[0].astype(float).tolist()
+
+
+def import_repo(conn, repo: Path, embed, limit: int, since: str,
+                no_write: bool = False) -> tuple[int, int]:
+    raw = git_log(repo, limit, since)
+    commits = parse_log(raw)
+    leafs = commits_to_leafs(commits, repo_name(repo))
+    if no_write:
+        return len(commits), 0
+    written = 0
+    for lf in leafs:
+        query = f"{lf['heading']}\n\n{lf['text']}"
+        emb = embed(lf["text"]) if lf["text"] else None
+        upsert_leaf(conn, text=query, root="info", confidence="confirmed",
+                    source=lf["source"], source_rev="git", how="git/import",
+                    loc=lf["source"], type_=lf.get("type", "commit"),
+                    embedding=emb)
+        written += 1
+    index_commits(conn, commits, repo_name(repo))
+    return len(commits), written
 
 
 def main(argv: list[str]) -> int:
-    print(
+    import argparse
-        "bin/git/import is deprecated; use bin/git/import.go (go-git)",
+    p = argparse.ArgumentParser(description="import git history into the brain")
-        file=sys.stderr,
+    p.add_argument("repo", nargs="?", default=None)
-    )
+    p.add_argument("--root", default=None, help="directory of repos to import (each git dir separately)")
-    target = ROOT / "bin" / "git" / "import.go"
+    p.add_argument("--limit", type=int, default=0)
-    os.execvp("go", ["go", "run", str(target), *argv])
+    p.add_argument("--since", default="")
-    return 1
+    p.add_argument("--json", action="store_true")
+    p.add_argument("--dry-run", action="store_true", help="parse + report, no db write")
+    a = p.parse_args(argv)
+
+    repos: list[Path] = []
+    if a.repo:
+        repos = [Path(a.repo)]
+    elif a.root:
+        root = Path(a.root)
+        if root.is_file():
+            repos = [root]
+        else:
+            repos = [dp for dp in sorted(root.iterdir()) if (dp / ".git").exists() or dp.is_file()]
+    else:
+        repos = [ROOT]
+
+    total_commits = 0
+    results: list[dict] = []
+    if a.dry_run:
+        for repo in repos:
+            if not repo.exists():
+                continue
+            commits = parse_log(git_log(repo, a.limit, a.since))
+            name = repo_name(repo)
+            total_commits += len(commits)
+            results.append({"repo": name, "commits": len(commits),
+                            "leafs": len(commits_to_leafs(commits, name)), "path": str(repo)})
+        if a.json:
+            print(json.dumps(results, indent=2))
+        else:
+            for r in results:
+                print(f"{r['repo']:<24} {r['commits']:>5} commits -> {r['leafs']} leafs  {r['path']}")
+        return 0
+
+    # Never DROP FTS/VECTOR (ghost catalog). Upsert while indexes exist is OK;
+    # ensure_indexes only CREATEs when missing.
+    db, conn = connect(ROOT / "var" / "kb.lbug", read_only=False)
+    init_schema(conn)
+    embed = embedder()
+    rows: list[dict] = []
+    for repo in repos:
+        if not repo.exists():
+            continue
+        reached, written = import_repo(conn, repo, embed, a.limit, a.since)
+        total_commits += reached
+        rows.append({"repo": repo_name(repo), "commits": reached, "written": written})
+    ensure_indexes(conn)
+    conn.close()
+    db.close()
+
+    if a.json:
+        print(json.dumps(rows, indent=2))
+    else:
+        for r in rows:
+            print(f"imported {r['commits']:>5} commits -> {r['written']} leafs  {r['repo']}")
+        print(f"total: {total_commits} commits")
+    return 0
 
 
 if __name__ == "__main__":

bin/git/import.go

@@ -1,143 +0,0 @@
-//usr/bin/env go run "$0" "$@"; exit
-//
-// bin/git/import.go - read git history with go-git (no git binary).
-//
-//	./bin/git/import.go [REPO]
-//	./bin/git/import.go --json
-//	./bin/git/import.go --limit 100 --since 2026-01-01
-//	./bin/git/import.go --root DIR
-//
-// Conversion only: prints commit leafs. Brain write is bin/brain/index.go.
-// NOTE: never run `gofmt -w` on this file — it breaks the shebang.
-package main
-
-import (
-	"encoding/json"
-	"fmt"
-	"os"
-	"path/filepath"
-	"strconv"
-	"time"
-
-	"github.com/eSlider/2dph/internal/cmdbin"
-	"github.com/eSlider/2dph/internal/gitlog"
-)
-
-func main() {
-	os.Exit(run(os.Args[1:]))
-}
-
-func run(args []string) int {
-	var repo, root, since string
-	limit := 0
-	jsonOut := false
-	i := 0
-	for i < len(args) {
-		a := args[i]
-		switch {
-		case a == "--json":
-			jsonOut = true
-		case a == "--limit" && i+1 < len(args):
-			i++
-			n, err := strconv.Atoi(args[i])
-			if err != nil || n < 0 {
-				fmt.Fprintf(os.Stderr, "git/import: --limit must be a non-negative integer\n")
-				return 2
-			}
-			limit = n
-		case a == "--since" && i+1 < len(args):
-			i++
-			since = args[i]
-		case a == "--root" && i+1 < len(args):
-			i++
-			root = args[i]
-		case a == "-h" || a == "--help":
-			fmt.Fprintln(os.Stderr, `usage: bin/git/import.go [REPO] [--json] [--limit N] [--since DATE] [--root DIR]`)
-			return 0
-		case len(a) > 0 && a[0] != '-':
-			repo = a
-		default:
-			fmt.Fprintf(os.Stderr, "git/import: unknown flag %s\n", a)
-			return 2
-		}
-		i++
-	}
-
-	var sinceT time.Time
-	if since != "" {
-		var err error
-		sinceT, err = parseSince(since)
-		if err != nil {
-			fmt.Fprintf(os.Stderr, "git/import: %v\n", err)
-			return 2
-		}
-	}
-
-	repos := []string{}
-	if repo != "" {
-		repos = []string{repo}
-	} else if root != "" {
-		entries, err := os.ReadDir(root)
-		if err != nil {
-			fmt.Fprintf(os.Stderr, "git/import: %v\n", err)
-			return 1
-		}
-		for _, e := range entries {
-			p := filepath.Join(root, e.Name())
-			if _, err := os.Stat(filepath.Join(p, ".git")); err == nil {
-				repos = append(repos, p)
-			}
-		}
-	} else {
-		repos = []string{cmdbin.Root()}
-	}
-
-	opt := gitlog.Options{Limit: limit, Since: sinceT}
-	type row struct {
-		Repo    string         `json:"repo"`
-		Path    string         `json:"path"`
-		Commits int            `json:"commits"`
-		Leafs   []gitlog.Leaf  `json:"leafs,omitempty"`
-	}
-	var rows []row
-	for _, p := range repos {
-		name, err := gitlog.RepoName(p)
-		if err != nil && name == "" {
-			fmt.Fprintf(os.Stderr, "git/import: %s: %v\n", p, err)
-			continue
-		}
-		cs, err := gitlog.Log(p, opt)
-		if err != nil {
-			fmt.Fprintf(os.Stderr, "git/import: %s: %v\n", p, err)
-			return 1
-		}
-		leafs := make([]gitlog.Leaf, 0, len(cs))
-		for _, c := range cs {
-			leafs = append(leafs, gitlog.ToLeaf(c, name))
-		}
-		rows = append(rows, row{Repo: name, Path: p, Commits: len(cs), Leafs: leafs})
-	}
-
-	if jsonOut {
-		enc := json.NewEncoder(os.Stdout)
-		enc.SetIndent("", "  ")
-		enc.SetEscapeHTML(false)
-		if err := enc.Encode(rows); err != nil {
-			return 1
-		}
-		return 0
-	}
-	for _, r := range rows {
-		fmt.Printf("%-24s %5d commits  %s\n", r.Repo, r.Commits, r.Path)
-	}
-	return 0
-}
-
-func parseSince(s string) (time.Time, error) {
-	for _, layout := range []string{time.RFC3339, "2006-01-02"} {
-		if t, err := time.Parse(layout, s); err == nil {
-			return t, nil
-		}
-	}
-	return time.Time{}, fmt.Errorf("cannot parse --since %q", s)
-}

bin/kb/add

@@ -1,114 +0,0 @@
-#!/usr/bin/env python3
-"""kb/add - incremental leaf write (no rebuild).
-
-  bin/kb/add --text T --root facts|info --source S
-  bin/kb/add --json                 # stdin: one object or {"leafs":[...]}
-  bin/kb/add --db PATH --json
-
-Writes facts+info in one Ladybug transaction. Does not delete kb.lbug.
-Embedding is used when provided; otherwise model2vec encodes the text.
-"""
-from __future__ import annotations
-
-import json
-import sys
-from pathlib import Path
-
-ROOT = Path(__file__).resolve().parents[2]
-sys.path.insert(0, str(ROOT / "bin" / "tools"))
-
-from kblib import (  # noqa: E402
-    EMBED_DIM,
-    add_leafs,
-    connect,
-    ensure_indexes,
-    init_schema,
-)
-
-
-def _as_leafs(payload: object) -> list[dict]:
-    if isinstance(payload, list):
-        return [dict(x) for x in payload]
-    if isinstance(payload, dict):
-        if "leafs" in payload:
-            return [dict(x) for x in payload["leafs"]]
-        return [dict(payload)]
-    raise ValueError("json must be an object, a list, or {leafs:[...]}")
-
-
-def _embed_missing(leafs: list[dict]) -> None:
-    missing = [lf for lf in leafs if not lf.get("embedding")]
-    if not missing:
-        return
-    from model2vec import StaticModel
-
-    model = StaticModel.from_pretrained("minishlab/potion-multilingual-128M")
-    for lf in missing:
-        text = str(lf.get("text") or "")
-        vec = model.encode([text])[0].astype(float).tolist()
-        if len(vec) != EMBED_DIM:
-            vec = (vec + [0.0] * EMBED_DIM)[:EMBED_DIM]
-        lf["embedding"] = vec
-
-
-def main(argv: list[str]) -> int:
-    import argparse
-
-    p = argparse.ArgumentParser(description="add leafs without rebuilding the brain")
-    p.add_argument("--db", default="", help="path to kb.lbug (default var/kb.lbug)")
-    p.add_argument("--json", action="store_true", help="read leaf JSON from stdin")
-    p.add_argument("--text", default="", help="leaf text")
-    p.add_argument("--root", default="info", choices=("facts", "info"))
-    p.add_argument("--source", default="")
-    p.add_argument("--confidence", default="confirmed")
-    p.add_argument("--source-rev", default="working-tree")
-    p.add_argument("--how", default="brain/add")
-    p.add_argument("--loc", default="")
-    p.add_argument("--type", default="reference", dest="type_")
-    args = p.parse_args(argv)
-
-    if args.json:
-        raw = sys.stdin.read()
-        if not raw.strip():
-            print("kb/add: empty stdin", file=sys.stderr)
-            return 2
-        leafs = _as_leafs(json.loads(raw))
-    else:
-        if not args.text or not args.source:
-            print("kb/add: --text and --source are required (or --json)", file=sys.stderr)
-            return 2
-        leafs = [{
-            "text": args.text,
-            "root": args.root,
-            "source": args.source,
-            "confidence": args.confidence,
-            "source_rev": args.source_rev,
-            "how": args.how,
-            "loc": args.loc or args.source,
-            "type": args.type_,
-        }]
-
-    for lf in leafs:
-        if not lf.get("text") or not lf.get("source"):
-            print("kb/add: each leaf needs text and source", file=sys.stderr)
-            return 2
-
-    _embed_missing(leafs)
-
-    from kblib import DB_PATH, VAR
-
-    dbpath = Path(args.db) if args.db else DB_PATH
-    dbpath.parent.mkdir(parents=True, exist_ok=True)
-    VAR.mkdir(exist_ok=True)
-    db, conn = connect(dbpath, read_only=False)
-    init_schema(conn)
-    ids = add_leafs(conn, leafs)
-    ensure_indexes(conn)
-    conn.close()
-    db.close()
-    print(json.dumps({"mode": "add", "ids": ids, "db": str(dbpath)}))
-    return 0
-
-
-if __name__ == "__main__":
-    sys.exit(main(sys.argv[1:]))

bin/kb/index

@@ -26,7 +26,6 @@ from kblib import (  # noqa: E402
     open_readonly, stats,
 )
 from mdleaves import read_markdown, to_all, walk_markdown  # noqa: E402
-from mailleafs import from_mail_root  # noqa: E402
 
 CORPUS_DEFAULTS = ["README.md", "PLAN.md", "AGENTS.md", "docs", "skills"]
 
@@ -100,9 +99,6 @@ def main(argv: list[str]) -> int:
     p = argparse.ArgumentParser(description="build the 2dph brain index")
     p.add_argument("--corpus", action="append", help="extra markdown dir/file to index (may repeat)")
     p.add_argument("--rebuild", action="store_true", help="fresh db + indexes")
-    p.add_argument("--with-mail", action="store_true", help="include var/mail message.md leafs")
-    p.add_argument("--since", default="", help="with --with-mail, only messages dated >= YYYY-MM-DD")
-    p.add_argument("--dry-run", action="store_true", help="count leafs, write nothing")
     p.add_argument(
         "--skip-indexes",
         action="store_true",
@@ -113,26 +109,14 @@ def main(argv: list[str]) -> int:
     a = p.parse_args(argv)
 
     from kblib import DB_PATH, VAR
+    VAR.mkdir(exist_ok=True)
+    if a.rebuild and DB_PATH.exists():
+        DB_PATH.unlink()
 
     leafs = load_corpus(ROOT)
     if a.corpus:
         for source in a.corpus:
             leafs.extend(load_corpus_glob(source))
-    mail_n = 0
-    if a.with_mail:
-        mail = from_mail_root(ROOT / "var" / "mail", since=a.since)
-        mail_n = len(mail)
-        leafs.extend(mail)
-
-    if a.dry_run:
-        msg = {"indexed": 0, "corpus_total": len(leafs), "mail_leafs": mail_n, "dry_run": True}
-        print(json.dumps(msg, indent=2) if a.json else
-              f"brain/index: {len(leafs)} leafs would be indexed (mail={mail_n})")
-        return 0
-
-    VAR.mkdir(exist_ok=True)
-    if a.rebuild and DB_PATH.exists():
-        DB_PATH.unlink()
 
     db, conn = connect(DB_PATH, read_only=False)
     init_schema(conn)

bin/kb/search

@@ -1,9 +1,10 @@
 #!/usr/bin/env bash
 # bin/kb/search — deprecated wrapper. Use bin/brain/search.go.
-# CGO via Zig (bin/cgo/zig), not gcc. Builds a binary then execs it.
+# Sets CGO for ladybug, builds a binary (embed daemon needs a real executable),
+# then execs it. Prints one deprecation line.
 set -euo pipefail
 
-ROOT="$(CDPATH= cd -- "$(dirname "$0")/../.." && pwd)"
+ROOT="$(cd "$(dirname "$0")/../.." && pwd)"
 BIN="$ROOT/var/bin/brain-search"
 SRC="$ROOT/internal/brain"
 CMD="$ROOT/bin/brain"
@@ -23,10 +24,11 @@ else
 fi
 
 if [ "$need_build" -eq 1 ]; then
-	echo "Building brain/search (zig cc)..." >&2
+	echo "Building brain/search..." >&2
 	(
 		cd "$ROOT" &&
-			eval "$("$ROOT/bin/cgo/zig" env)" &&
+			CGO_CFLAGS="-I$ROOT/lib-ladybug" \
+			CGO_LDFLAGS="-L$ROOT/lib-ladybug -Wl,-rpath,$ROOT/lib-ladybug" \
 			go build -tags system_ladybug -o "$BIN" ./bin/brain
 	) || exit 1
 fi

bin/kb/watch.go

@@ -1,5 +1,5 @@
 //usr/bin/env go run "$0" "$@"; exit
-// bin/kb/watch.go — deprecated. Use bin/brain/watch.go.
+// bin/kb/watch.go - re-index the 2dph brain when corpus files change.
 //
 // Usage:
 //

bin/mail/import

@@ -15,8 +15,8 @@ Writes one directory per message: var/mail/{folder}/{message_id}/
   attachments/              raw attachment files (zips unpacked to _unpacked/)
   attachments/*.md          converted attachment content
 
-Indexing is a separate step (`bin/brain/index.go --rebuild`): conversion can
+Indexing is a separate step (bin/mail/index_mail): conversion can crash in
-crash in native docling and must not leave the brain DB mid-transaction.
+native docling and must not leave the brain DB mid-transaction.
 
 Requires ONLYOFFICE_URL/USER/PASS in .env (or env). Idempotent: a message
 already present (message.md exists) is skipped unless --force.

bin/mail/import.go

@@ -1,20 +0,0 @@
-//usr/bin/env go run -tags=mail_import "$0" "$@"; exit
-//go:build mail_import
-//
-// bin/mail/import.go - message.json → markdown (no brain write).
-//
-//	./bin/mail/import.go --from-raw var/mail
-//
-// Indexing is bin/brain/index.go --rebuild, not this command.
-// NOTE: never run `gofmt -w` on this file — it breaks the shebang.
-package main
-
-import (
-	"os"
-
-	"github.com/eSlider/2dph/internal/cmdbin"
-)
-
-func main() {
-	os.Exit(cmdbin.ExecFile("bin/mail/import", os.Args[1:]))
-}

bin/mail/index_mail

@@ -1,26 +1,135 @@
 #!/usr/bin/env python3
-"""mail/index_mail — deprecated. Use bin/brain/index.go --rebuild --with-mail.
+"""mail/index_mail - rebuild the brain with every markdown under var/mail.
 
-Ladybug corrupts its WAL on bulk-insert into an already-indexed DB, so this
+Ladybug corrupts its WAL when brand-new leafs are bulk-inserted while the
-shim always rebuilds (repo corpus + var/mail). Conversion stays in mail/import.
+FTS/VECTOR indexes already exist, so indexing ALWAYS runs as a fresh rebuild
+(repo corpus + var/mail), matching the proven-safe `kb/index --rebuild` path.
+Conversion and indexing stay separate: conversion can crash in native docling
+and must not leave the brain DB mid-transaction.
+
+  bin/mail/index_mail                 rebuild the index incl. all mail
+  bin/mail/index_mail --dry-run       count without writing
+  bin/mail/index_mail --limit N       cap messages included
+  bin/mail/index_mail --since D       only messages dated >= D (YYYY-MM-DD)
 """
 from __future__ import annotations
 
-import os
+import argparse
+import json
 import sys
 from pathlib import Path
 
 ROOT = Path(__file__).resolve().parents[2]
+sys.path.insert(0, str(ROOT / "bin" / "tools"))
+
+from kblib import DB_PATH, VAR, connect, ensure_indexes, init_schema, stats, upsert_leaf  # noqa: E402
+from mdleaves import read_markdown, to_all, walk_markdown  # noqa: E402
+
+
+def msg_date(md: Path) -> str:
+    j = md.parent / "message.json"
+    try:
+        d = json.loads(j.read_text(encoding="utf-8"))
+        return (d.get("receivedDate") or d.get("receivedAt") or "")[:10]
+    except Exception:
+        return ""
+
+
+def mail_leafs(limit: int, since: str, repo: str = "ooMail") -> list[dict]:
+    root = ROOT / "var" / "mail"
+    mds = sorted(root.rglob("message.md"))
+    if since:
+        mds = [m for m in mds if msg_date(m) >= since]
+    if limit:
+        mds = mds[:limit]
+    leafs: list[dict] = []
+    for md in mds:
+        files = [md] + sorted((md.parent / "attachments").glob("*.md"))
+        for f in files:
+            if not f.exists():
+                continue
+            for lf in to_all(read_markdown(f), f, repo=repo):
+                lf["source"] = f"ooMail:{md.parent.name}:{f.name}"
+                lf["how"] = "mail/import"
+                leafs.append(lf)
+    return leafs
 
 
 def main(argv: list[str]) -> int:
-    print(
+    p = argparse.ArgumentParser(description="rebuild the brain incl. all mail")
-        "bin/mail/index_mail is deprecated; use bin/brain/index.go --rebuild --with-mail",
+    p.add_argument("--dry-run", action="store_true", help="count only, write nothing")
-        file=sys.stderr,
+    p.add_argument("--limit", type=int, default=0, help="cap messages included")
-    )
+    p.add_argument("--since", default="", help="only messages dated >= YYYY-MM-DD")
-    index = ROOT / "bin" / "kb" / "index"
+    p.add_argument("--json", action="store_true")
-    os.execv(sys.executable, [sys.executable, str(index), "--rebuild", "--with-mail", *argv])
+    a = p.parse_args(argv)
-    return 1
+
+    mail = mail_leafs(a.limit, a.since)
+    if a.dry_run:
+        print(f"mail/index_mail: {len(mail)} mail leafs would be indexed")
+        return 0
+
+    # Fresh rebuild: delete DB, index repo corpus + mail, create indexes once
+    # at the end. Never insert into an already-indexed DB (WAL corruption).
+    VAR.mkdir(exist_ok=True)
+    if DB_PATH.exists():
+        DB_PATH.unlink()
+
+    corpus = _load_corpus()
+    leafs = corpus + mail
+
+    db, conn = connect(DB_PATH, read_only=False)
+    init_schema(conn)
+    embed = _embedder()
+    done, total = _index_leafs(conn, leafs, embed)
+    ensure_indexes(conn)
+    s = stats(conn)
+    conn.close()
+    db.close()
+
+    result = {"indexed": done, "corpus_total": total, "mail_leafs": len(mail),
+              **{k: v for k, v in s.items() if k in ("total", "by_root")}}
+    print(json.dumps(result, indent=2) if a.json else
+          f"mail/index_mail: indexed {done}/{total} leafs (mail={len(mail)}); db total {s['total']}")
+    return 0
+
+
+CORPUS_DEFAULTS = ["README.md", "PLAN.md", "AGENTS.md", "docs", "skills"]
+
+
+def _load_corpus() -> list[dict]:
+    files: list[Path] = []
+    for entry in CORPUS_DEFAULTS:
+        p = ROOT / entry
+        if p.is_file():
+            files.append(p)
+        elif p.is_dir():
+            files.extend(walk_markdown(p))
+    leafs: list[dict] = []
+    for path in files:
+        try:
+            leafs.extend(to_all(read_markdown(path), path, repo="eSlider/2dph"))
+        except OSError as e:
+            print(f"mail/index_mail: skip {path}: {e}", file=sys.stderr)
+    return leafs
+
+
+def _index_leafs(conn, leafs: list[dict], embed_fn) -> tuple[int, int]:
+    count = 0
+    for lf in leafs:
+        query = f"{lf['heading']}\n\n{lf['text']}"
+        emb = embed_fn(lf["text"]) if lf["text"] else None
+        upsert_leaf(conn, text=query, root="info", confidence="confirmed",
+                    source=lf["source"], source_rev="mail" if lf.get("how") == "mail/import" else "working-tree",
+                    how=lf.get("how", "kb/index"), loc=lf["source"], type_=lf.get("type", "reference"),
+                    embedding=emb)
+        count += 1
+    return count, len(leafs)
+
+
+def _embedder():
+    from model2vec import StaticModel
+    model = StaticModel.from_pretrained("minishlab/potion-multilingual-128M")
+    return lambda text: model.encode([text])[0].astype(float).tolist()
 
 
 if __name__ == "__main__":

bin/mail/sync.go

@@ -6,7 +6,7 @@
 //	./bin/mail/sync.go --dry-run
 //
 // Writes raw message.json + attachments under var/mail/<folder>/<id>/; run
-// bin/mail/import.go --from-raw afterwards to convert everything to markdown.
+// bin/mail/import --from-raw afterwards to convert everything to markdown.
 //
 // Shebang trick: first line is a Go `//` comment; the real code lives in the
 // importable package (module path, never a relative import).

bin/markdown/doc.go

@@ -1,3 +0,0 @@
-// Commands in this directory are shebang mains (import.go), tagged so
-// `go build ./bin/markdown` does not see two mains.
-package main

bin/markdown/import.go

@@ -1,100 +0,0 @@
-//usr/bin/env go run "$0" "$@"; exit
-//
-// bin/markdown/import.go - split markdown into leafs (H2 boundaries).
-//
-//	./bin/markdown/import.go [dir]
-//	./bin/markdown/import.go --files a.md,b.md --json
-//
-// Conversion only. Brain write is bin/brain/index.go.
-// Python bin/md/import remains as a fallback.
-// NOTE: never run `gofmt -w` on this file — it breaks the shebang.
-package main
-
-import (
-	"fmt"
-	"os"
-	"strings"
-
-	"github.com/eSlider/2dph/internal/mdleaves"
-)
-
-func main() {
-	os.Exit(run(os.Args[1:]))
-}
-
-func run(args []string) int {
-	jsonOut := false
-	files := ""
-	root := "."
-	for i := 0; i < len(args); i++ {
-		a := args[i]
-		switch {
-		case a == "--json":
-			jsonOut = true
-		case a == "--files" && i+1 < len(args):
-			i++
-			files = args[i]
-		case strings.HasPrefix(a, "--files="):
-			files = strings.TrimPrefix(a, "--files=")
-		case a == "-h" || a == "--help":
-			fmt.Fprintln(os.Stderr, "bin/markdown/import.go [dir] [--files a.md,b.md] [--json]")
-			return 0
-		case strings.HasPrefix(a, "-"):
-			fmt.Fprintln(os.Stderr, "unknown arg:", a)
-			return 2
-		default:
-			root = a
-		}
-	}
-
-	var paths []string
-	if files != "" {
-		for _, f := range strings.Split(files, ",") {
-			f = strings.TrimSpace(f)
-			if f != "" {
-				paths = append(paths, f)
-			}
-		}
-	} else {
-		st, err := os.Stat(root)
-		if err != nil {
-			fmt.Fprintf(os.Stderr, "md/import: no such path %s\n", root)
-			return 2
-		}
-		if !st.IsDir() {
-			paths = []string{root}
-		} else {
-			var err error
-			paths, err = mdleaves.WalkMarkdown(root)
-			if err != nil {
-				fmt.Fprintf(os.Stderr, "md/import: %v\n", err)
-				return 1
-			}
-		}
-	}
-	if len(paths) == 0 {
-		fmt.Fprintln(os.Stderr, "md/import: no markdown files")
-		return 1
-	}
-
-	var all []mdleaves.Leaf
-	for _, p := range paths {
-		raw, err := os.ReadFile(p)
-		if err != nil {
-			fmt.Fprintf(os.Stderr, "md/import: %s: %v\n", p, err)
-			continue
-		}
-		all = append(all, mdleaves.ToAll(string(raw), p, "")...)
-	}
-	if jsonOut {
-		s, err := mdleaves.EncodeJSON(all)
-		if err != nil {
-			fmt.Fprintln(os.Stderr, err)
-			return 1
-		}
-		fmt.Print(s)
-		return 0
-	}
-	fmt.Print(mdleaves.EncodeYAML(all))
-	return 0
-}

bin/postgres/doc.go

@@ -1,2 +0,0 @@
-// Commands in this directory are shebang mains (query.go).
-package main

bin/postgres/query.go

@@ -1,20 +0,0 @@
-//usr/bin/env go run -tags=postgres_query "$0" "$@"; exit
-//go:build postgres_query
-//
-// bin/postgres/query.go - read-only Postgres as YAML.
-//
-//	./bin/postgres/query.go --profile onlyoffice -c 'SELECT 1'
-//
-// Profiles: $HOME/.config/brain/db-profiles.yml (credentials stay out of git).
-// NOTE: never run `gofmt -w` on this file — it breaks the shebang.
-package main
-
-import (
-	"os"
-
-	"github.com/eSlider/2dph/internal/cmdbin"
-)
-
-func main() {
-	os.Exit(cmdbin.ExecFile("bin/db/psql-yq", os.Args[1:]))
-}

bin/reasoner/bakeoff.go

@@ -1,91 +0,0 @@
-//usr/bin/env go run -tags=reasoner_bakeoff "$0" "$@"; exit
-//go:build reasoner_bakeoff
-//
-// bin/reasoner/bakeoff.go - CPU tool-call bake-off against an OpenAI-compatible URL (D18).
-//
-//	REASONER_BASE_URL=http://127.0.0.1:11435/v1 REASONER_MODEL=qwen3.5:9b ./bin/reasoner/bakeoff.go
-//	./bin/reasoner/bakeoff.go --model MichelRosselli/bonsai-27b:Q1_0 --json
-//
-// Measures OpenAI tool_calls (search/get/audit) and RSS from Ollama /api/ps, not VRAM.
-// PicoClaw is not in this repo; the tool names match internal/httpapi MCP ops.
-// NOTE: never run `gofmt -w` on this file — it breaks the shebang.
-package main
-
-import (
-	"encoding/json"
-	"fmt"
-	"os"
-	"strings"
-
-	"github.com/eSlider/2dph/internal/reasoner"
-)
-
-func main() {
-	os.Exit(run(os.Args[1:]))
-}
-
-func run(args []string) int {
-	base := os.Getenv("REASONER_BASE_URL")
-	if base == "" {
-		base = "http://127.0.0.1:11435/v1"
-	}
-	model := os.Getenv("REASONER_MODEL")
-	if model == "" {
-		model = reasoner.OllamaRAM
-	}
-	jsonOut := false
-	device := "cpu"
-	for i := 0; i < len(args); i++ {
-		a := args[i]
-		switch {
-		case a == "--json":
-			jsonOut = true
-		case a == "--model" && i+1 < len(args):
-			i++
-			model = args[i]
-		case strings.HasPrefix(a, "--model="):
-			model = strings.TrimPrefix(a, "--model=")
-		case a == "--base-url" && i+1 < len(args):
-			i++
-			base = args[i]
-		case a == "--device" && i+1 < len(args):
-			i++
-			device = args[i]
-		case a == "-h" || a == "--help":
-			fmt.Fprintln(os.Stderr, "bin/reasoner/bakeoff.go [--model ID] [--base-url URL] [--device cpu] [--json]")
-			return 0
-		default:
-			fmt.Fprintln(os.Stderr, "unknown arg:", a)
-			return 2
-		}
-	}
-	c := reasoner.Client{BaseURL: base, Model: model, Device: device}
-	rep := reasoner.Run(c)
-	raw, err := json.MarshalIndent(rep, "", "  ")
-	if err != nil {
-		fmt.Fprintln(os.Stderr, err)
-		return 1
-	}
-	if jsonOut {
-		fmt.Println(string(raw))
-	} else {
-		fmt.Printf("model: %s\n", rep.Model)
-		fmt.Printf("hf_id: %s\n", rep.HF)
-		fmt.Printf("device: %s\n", rep.Device)
-		fmt.Printf("tool_call: %d/%d\n", rep.ToolCallOK, rep.ToolCallN)
-		fmt.Printf("xml_leak: %d\n", rep.XMLLeak)
-		fmt.Printf("rss_mb: %d\n", rep.RSSMB)
-		fmt.Printf("vram_mb: %d\n", rep.VRAMMB)
-		for _, p := range rep.Prompts {
-			status := "fail"
-			if p.OK {
-				status = "ok"
-			}
-			fmt.Printf("  %s: %s wanted=%s got=%s xml=%v %dms %s\n", p.WantedTool, status, p.WantedTool, p.ToolName, p.XMLLeak, p.LatencyMS, p.Err)
-		}
-	}
-	if rep.ToolCallN == 0 {
-		return 1
-	}
-	return 0
-}

bin/reasoner/doc.go

@@ -1,2 +0,0 @@
-// Commands in this directory are shebang mains (bakeoff.go).
-package main

bin/serve.go

@@ -18,5 +18,5 @@ func main() {
 			os.Setenv("KB_ROOT", wd)
 		}
 	}
-	httpapi.Run(nil)
+	httpapi.Run()
 }

bin/tools/gitimport.py

@@ -1,12 +1,21 @@
-"""gitimport - Ladybug graph writes for Commit/File/Person (no git binary).
+"""gitimport - parse `git log` output and turn commits into brain leafs.
 
-Commit records come from bin/git/import.go (go-git). This module only MERGEs
+Pure, testable functions. Field grammar (see bin/git/import):
-the version graph File-[:HAS_VERSION]->Commit-[:AUTHORED]->Person.
+
+  git log --no-merges --name-only \
+      --format='%x1e%H%x1f%an%x1f%ae%x1f%aI%x1f%s'
+
+  0x1e = record separator, 0x1f = field separator.
+  Files: newline-separated lines following each record's subject.
 """
+
 from __future__ import annotations
 
 from dataclasses import dataclass, field
 
+REC_SEP = "\x1e"
+FIELD_SEP = "\x1f"
+
 
 @dataclass
 class Commit:
@@ -17,6 +26,54 @@ class Commit:
     subject: str
     files: list[str] = field(default_factory=list)
 
+    def leaf_text(self, repo: str) -> str:
+        head = f"commit {self.sha[:12]} in {repo} — {self.subject}"
+        body = [head, f"Author: {self.author} <{self.email}>", f"Date: {self.date}"]
+        if self.files:
+            body.append("Changing: " + ", ".join(self.files))
+        return "\n".join(body)
+
+
+def parse_log(text: str) -> list[Commit]:
+    """Parse `git log` output into Commit records.
+
+    Records are separated by 0x1e. A record is fields joined by 0x1f,
+    followed by optional newline-separated file paths inside the next
+    segment (git emits blank line + files after each record).
+    """
+    commits: list[Commit] = []
+    # field records and file lists alternate; simpler: split on REC_SEP,
+    # each chunk = header line, possibly followed by newline + files.
+    for chunk in text.split(REC_SEP):
+        chunk = chunk.strip("\n")
+        if not chunk:
+            continue
+        lines = chunk.split("\n", 1)
+        header = lines[0].split(FIELD_SEP)
+        if len(header) < 5:
+            continue
+        sha, author, email, date, subject = header[:5]
+        files = [ln.strip() for ln in lines[1].splitlines() if ln.strip()] if len(lines) > 1 else []
+        commits.append(Commit(sha=sha, author=author, email=email,
+                              date=date, subject=subject, files=files))
+    return commits
+
+
+def commits_to_leafs(commits: list[Commit], repo: str) -> list[dict]:
+    """Map commits to the leaf shape bin/kb/index expects (source/repo/...)."""
+    out: list[dict] = []
+    for c in commits:
+        out.append({
+            "source": f"{repo}@{c.sha}",
+            "repo": repo,
+            "heading": f"commit {c.sha[:12]} — {c.subject}",
+            "text": c.leaf_text(repo),
+            "type": "commit",
+            "status": "current",
+            "related": ",".join(c.files),
+        })
+    return out
+
 
 GIT_SCHEMA = (
     "CREATE NODE TABLE IF NOT EXISTS Commit (id STRING, repo STRING, subject STRING, "

bin/tools/kblib.py

@@ -4,7 +4,7 @@ Single embedded graph `var/kb.lbug`. Two roots: facts (assertions backed by
 >=2 independent sources) and info (narrative leafs). Hybrid retrieval: BM25
 (FTS extension) + HNSW cosine (VECTOR extension) + Cypher graph hops.
 
-All access is read-only unless `--rebuild` (kb/index) or `kb/add`.
+All access is read-only unless `--rebuild` is passed to kb/index.
 """
 from __future__ import annotations
 
@@ -118,50 +118,6 @@ def upsert_leaf(conn: ladybug.Connection, *, text: str, root: str, confidence: s
     return lid
 
 
-def add_leafs(conn: ladybug.Connection, leafs: list[dict]) -> list[str]:
-    """Write facts+info leafs in one transaction. Safe while FTS/HNSW exist.
-
-    Each leaf dict: text, source, optional root/confidence/source_rev/how/loc/type/embedding.
-    Does not delete the database file. Measured on Ladybug 0.19: MERGE of new
-    ids (and updates) stays FTS+HNSW queryable; DROP INDEX is the fatal path.
-    """
-    if not leafs:
-        return []
-    started = False
-    try:
-        conn.execute("BEGIN TRANSACTION")
-        started = True
-    except Exception:
-        started = False
-    ids: list[str] = []
-    try:
-        for lf in leafs:
-            ids.append(
-                upsert_leaf(
-                    conn,
-                    text=str(lf["text"]),
-                    root=str(lf.get("root") or ROOT_INFO),
-                    confidence=str(lf.get("confidence") or CONF_CONFIRMED),
-                    source=str(lf["source"]),
-                    source_rev=str(lf.get("source_rev") or "working-tree"),
-                    how=str(lf.get("how") or "brain/add"),
-                    loc=str(lf.get("loc") or lf.get("source") or ""),
-                    type_=str(lf.get("type") or lf.get("type_") or "reference"),
-                    embedding=lf.get("embedding"),
-                )
-            )
-        if started:
-            conn.execute("COMMIT")
-    except Exception:
-        if started:
-            try:
-                conn.execute("ROLLBACK")
-            except Exception:
-                pass
-        raise
-    return ids
-
-
 def leaf_index_names(conn: ladybug.Connection) -> set[str]:
     """Return index names on the Leaf table (e.g. {'id', 'Leaf_vec', '_PK'})."""
     rows = conn.execute("CALL SHOW_INDEXES() RETURN *").get_all()
@@ -179,7 +135,7 @@ def create_fts_and_vector(conn: ladybug.Connection, force: bool = False) -> None
 
     `force=True` is accepted for API compatibility but does **not** drop.
     Fresh indexes require deleting `var/kb.lbug` and rebuilding
-    (`bin/brain/index.go --rebuild`).
+    (`bin/kb/index --rebuild`).
     """
     del force  # API compat; DROP is unsafe — see docstring
     names = leaf_index_names(conn)
@@ -189,7 +145,7 @@ def create_fts_and_vector(conn: ladybug.Connection, force: bool = False) -> None
         except Exception as e:
             raise RuntimeError(
                 "CREATE_FTS_INDEX failed (often ghost catalog after DROP INDEX). "
-                "Delete var/kb.lbug and run bin/brain/index.go --rebuild. "
+                "Delete var/kb.lbug and run bin/kb/index --rebuild. "
                 f"Cause: {e}"
             ) from e
     if "Leaf_vec" not in names:
@@ -202,7 +158,7 @@ def create_fts_and_vector(conn: ladybug.Connection, force: bool = False) -> None
             raise RuntimeError(
                 "CREATE_VECTOR_INDEX failed (often ghost catalog after DROP INDEX "
                 "Leaf.Leaf_vec → `_0_Leaf_vec_UPPER already exists in catalog`). "
-                "Delete var/kb.lbug and run bin/brain/index.go --rebuild. "
+                "Delete var/kb.lbug and run bin/kb/index --rebuild. "
                 f"Cause: {e}"
             ) from e
     names = leaf_index_names(conn)
@@ -281,6 +237,6 @@ def stats(conn: ladybug.Connection) -> dict:
 
 def open_readonly() -> tuple[ladybug.Database, ladybug.Connection]:
     if not DB_PATH.exists():
-        raise FileNotFoundError(f"{DB_PATH} missing - run bin/brain/index.go --rebuild first")
+        raise FileNotFoundError(f"{DB_PATH} missing - run bin/kb/index first")
     db, conn = connect(read_only=True)
     return db, conn

bin/tools/mailleafs.py

@@ -1,37 +0,0 @@
-"""Mail markdown under var/mail → info leafs. Conversion stays off the brain DB."""
-from __future__ import annotations
-
-import json
-from pathlib import Path
-
-from mdleaves import read_markdown, to_all
-
-
-def msg_date(md: Path) -> str:
-    j = md.parent / "message.json"
-    try:
-        d = json.loads(j.read_text(encoding="utf-8"))
-        return (d.get("receivedDate") or d.get("receivedAt") or "")[:10]
-    except (OSError, json.JSONDecodeError, TypeError):
-        return ""
-
-
-def from_mail_root(root: Path, limit: int = 0, since: str = "", repo: str = "ooMail") -> list[dict]:
-    if not root.is_dir():
-        return []
-    mds = sorted(root.rglob("message.md"))
-    if since:
-        mds = [m for m in mds if msg_date(m) >= since]
-    if limit:
-        mds = mds[:limit]
-    leafs: list[dict] = []
-    for md in mds:
-        files = [md] + sorted((md.parent / "attachments").glob("*.md"))
-        for f in files:
-            if not f.exists():
-                continue
-            for lf in to_all(read_markdown(f), f, repo=repo):
-                lf["source"] = f"ooMail:{md.parent.name}:{f.name}"
-                lf["how"] = "mail/import"
-                leafs.append(lf)
-    return leafs

bin/tools/test_bin_layout.py

@@ -1,7 +1,6 @@
 """D14 layout: bin/{subject}/{method}.go, libs in internal/, one go.mod."""
 from __future__ import annotations
 
-import os
 import unittest
 from pathlib import Path
 
@@ -35,175 +34,3 @@ class BinLayoutTest(unittest.TestCase):
     def test_no_main_go_under_bin_brain(self) -> None:
         main = ROOT / "bin" / "brain" / "main.go"
         self.assertFalse(main.exists(), "bin/brain/main.go is not a method")
-
-    def test_chats_methods_are_shebangs_not_main(self) -> None:
-        chats = ROOT / "bin" / "chats"
-        self.assertFalse(
-            (chats / "main.go").exists(),
-            "bin/chats/main.go is a dispatcher, not a method",
-        )
-        self.assertFalse(
-            (chats / "index_cmd.go").exists(),
-            "chats index is a brain write hiding under the wrong subject",
-        )
-        for method in ("sync.go", "import.go", "facts.go", "apply.go"):
-            p = chats / method
-            self.assertTrue(p.is_file(), f"missing bin/chats/{method}")
-            first = p.read_text().splitlines()[0]
-            self.assertTrue(
-                first.startswith("//usr/bin/env go run"),
-                f"{method} shebang, got {first!r}",
-            )
-
-    def test_chats_lib_lives_in_internal(self) -> None:
-        self.assertTrue(
-            (ROOT / "internal" / "chats" / "linkedin.go").is_file(),
-            "LinkedIn parser must live in internal/chats",
-        )
-        self.assertFalse(
-            (ROOT / "bin" / "chats" / "linkedin.go").exists(),
-            "parser must not stay under bin/chats as a second main",
-        )
-
-    def _assert_shebang(self, rel: str) -> None:
-        p = ROOT / rel
-        self.assertTrue(p.is_file(), f"missing {rel}")
-        first = p.read_text().splitlines()[0]
-        self.assertTrue(
-            first.startswith("//usr/bin/env go run"),
-            f"{rel} shebang, got {first!r}",
-        )
-
-    def test_brain_methods_are_shebangs(self) -> None:
-        for method in ("index.go", "add.go", "get.go", "stats.go", "eval.go", "watch.go"):
-            self._assert_shebang(f"bin/brain/{method}")
-
-    def test_brain_add_is_python_write_not_rebuild(self) -> None:
-        self._assert_shebang("bin/brain/add.go")
-        text = (ROOT / "bin" / "brain" / "add.go").read_text()
-        self.assertIn("cmdbin.ExecFile", text)
-        self.assertIn("bin/kb/add", text)
-        self.assertNotIn("--rebuild", text)
-        py = (ROOT / "bin" / "kb" / "add").read_text()
-        self.assertIn("add_leafs", py)
-        self.assertIn("--json", py)
-        self.assertNotIn("unlink", py.lower())
-
-    def test_brain_get_stats_eval_are_not_python_exec(self) -> None:
-        for method in ("get.go", "stats.go", "eval.go"):
-            text = (ROOT / "bin" / "brain" / method).read_text()
-            self.assertNotIn(
-                "ExecFile",
-                text,
-                f"bin/brain/{method} must call internal/brain, not ExecFile Python",
-            )
-            self.assertNotIn(
-                "cmdbin",
-                text,
-                f"bin/brain/{method} must not import internal/cmdbin",
-            )
-            self.assertIn(
-                "system_ladybug",
-                text.splitlines()[0],
-                f"bin/brain/{method} shebang must pass -tags=system_ladybug",
-            )
-            self.assertIn(
-                "github.com/eSlider/2dph/internal/brain",
-                text,
-            )
-
-    def test_eval_control_questions_live_in_rank(self) -> None:
-        rank = (ROOT / "internal" / "brain" / "rank" / "evalq.go").read_text()
-        py = (ROOT / "bin" / "kb" / "eval").read_text()
-        for frag in ("BM25", "DevOps", "LadybugDB"):
-            self.assertIn(frag, rank)
-            self.assertIn(frag, py)
-        self.assertIn("0.95", rank)
-
-    def test_facts_methods_are_shebangs(self) -> None:
-        for method in ("audit.go", "extract.go", "crm.go"):
-            self._assert_shebang(f"bin/facts/{method}")
-            text = (ROOT / "bin" / "facts" / method).read_text()
-            self.assertIn("cmdbin.ExecFile", text)
-            self.assertIn(f"bin/facts/{method.removesuffix('.go')}", text)
-
-    def test_mail_import_is_shebang_not_brain_write(self) -> None:
-        self._assert_shebang("bin/mail/import.go")
-        index_mail = (ROOT / "bin" / "mail" / "index_mail").read_text()
-        self.assertIn(
-            "bin/brain/index.go",
-            index_mail,
-            "index_mail must point at bin/brain/index.go",
-        )
-
-    def test_markdown_import_is_go_not_python_exec(self) -> None:
-        self._assert_shebang("bin/markdown/import.go")
-        text = (ROOT / "bin" / "markdown" / "import.go").read_text()
-        self.assertNotIn("ExecFile", text)
-        self.assertNotIn("cmdbin", text)
-        self.assertIn("internal/mdleaves", text)
-        self.assertNotIn("kb.lbug", text)
-
-    def test_import_adapters_do_not_write_ladybug(self) -> None:
-        for rel in (
-            "bin/mail/import.go",
-            "bin/mail/import",
-            "bin/markdown/import.go",
-            "bin/chats/import.go",
-            "bin/git/import.go",
-        ):
-            text = (ROOT / rel).read_text()
-            self.assertNotIn("upsert_leaf", text, rel)
-            self.assertNotIn("kb.lbug", text, rel)
-            self.assertNotIn("var/brain.lbug", text, rel)
-        index = (ROOT / "bin" / "brain" / "index.go").read_text()
-        self.assertIn("bin/kb/index", index)
-
-    def test_postgres_query_is_shebang(self) -> None:
-        self._assert_shebang("bin/postgres/query.go")
-
-    def test_git_import_is_gogit_shebang(self) -> None:
-        self._assert_shebang("bin/git/import.go")
-        py = (ROOT / "bin" / "git" / "import").read_text()
-        self.assertNotIn(
-            '["git"',
-            py,
-            "Python git/import must not subprocess the git binary",
-        )
-        self.assertIn("bin/git/import.go", py)
-
-    def test_web_search_is_shebang(self) -> None:
-        self._assert_shebang("bin/web/search.go")
-        py = (ROOT / "bin" / "web" / "search").read_text()
-        self.assertIn("bin/web/search.go", py)
-
-    def test_gitimport_py_has_no_git_binary(self) -> None:
-        py = (ROOT / "bin" / "tools" / "gitimport.py").read_text()
-        self.assertNotIn("subprocess", py)
-        self.assertNotIn("git log", py)
-
-    def test_gogit_is_direct_go_mod_require(self) -> None:
-        text = (ROOT / "go.mod").read_text()
-        first = text.split("require (")[1].split(")")[0]
-        self.assertRegex(first, r"github.com/go-git/go-git/v5\s+v")
-        for line in first.splitlines():
-            if "go-git/go-git" in line:
-                self.assertNotIn("indirect", line)
-
-    def test_cgo_uses_zig_not_gcc(self) -> None:
-        for rel in ("bin/cgo/zig", "bin/cgo/zcc", "bin/cgo/zc++"):
-            p = ROOT / rel
-            self.assertTrue(p.is_file(), f"missing {rel}")
-            self.assertTrue(
-                os.access(p, os.X_OK),
-                f"{rel} must be executable",
-            )
-        zig = (ROOT / "bin" / "cgo" / "zig").read_text()
-        self.assertIn("zig cc", zig)
-        self.assertIn("0.14.1", zig)
-        zcc = (ROOT / "bin" / "cgo" / "zcc").read_text()
-        self.assertIn('exec "$ZIG" cc', zcc)
-        self.assertNotIn("command -v gcc", zcc)
-        search = (ROOT / "bin" / "kb" / "search").read_text()
-        self.assertIn("bin/cgo/zig", search)
-        self.assertNotIn("command -v gcc", search)

bin/tools/test_gitgraph.py

@@ -9,6 +9,12 @@ sys.path.insert(0, str(Path(__file__).resolve().parent))
 import kblib  # noqa: E402
 import gitimport  # noqa: E402
 
+SAMPLE = (
+    "\x1e" + "a1b2c3d" + "\x1f" + "Ada Lovelace" + "\x1f" + "ada@example.com"
+    + "\x1f" + "2026-08-10T12:00:00+01:00" + "\x1f" + "feat: first commit"
+    + "\n\nREADME.md\nsrc/main.c\n"
+)
+
 COMMIT_PERSON_SCHEMA = (
     "CREATE NODE TABLE IF NOT EXISTS Commit (id STRING, repo STRING, subject STRING, "
     "author STRING, email STRING, date STRING, PRIMARY KEY(id))"
@@ -20,17 +26,6 @@ HAS_VERSION_SCHEMA = "CREATE REL TABLE IF NOT EXISTS HAS_VERSION (FROM File TO C
 AUTHORED_SCHEMA = "CREATE REL TABLE IF NOT EXISTS AUTHORED (FROM Commit TO Person)"
 
 
-def sample_commit() -> gitimport.Commit:
-    return gitimport.Commit(
-        sha="a1b2c3d",
-        author="Ada Lovelace",
-        email="ada@example.com",
-        date="2026-08-10T12:00:00+01:00",
-        subject="feat: first commit",
-        files=["README.md", "src/main.c"],
-    )
-
-
 class GitGraphTest(unittest.TestCase):
     def setUp(self):
         self.dir = tempfile.mkdtemp()
@@ -47,12 +42,14 @@ class GitGraphTest(unittest.TestCase):
         self.db.close()
 
     def test_index_commits_creates_nodes_and_edges(self):
-        gitimport.index_commits(self.conn, [sample_commit()], "sample-repo")
+        cs = gitimport.parse_log(SAMPLE)
+        gitimport.index_commits(self.conn, cs, "sample-repo")
         rp = self.conn.execute("MATCH (p:Person) RETURN p.name, p.email").get_all()
         self.assertEqual([tuple(r) for r in rp], [("Ada Lovelace", "ada@example.com")])
         rc = self.conn.execute("MATCH (c:Commit) RETURN c.id, c.repo").get_all()
         self.assertEqual(len(rc), 1)
         self.assertEqual(rc[0][1], "sample-repo")
+        # File -[:HAS_VERSION]-> Commit -[:AUTHORED]-> Person
         rf = self.conn.execute(
             "MATCH (f:File)-[:HAS_VERSION]->(c:Commit)-[:AUTHORED]->(p:Person) "
             "RETURN f.path, c.id, p.email").get_all()
@@ -61,7 +58,7 @@ class GitGraphTest(unittest.TestCase):
         self.assertTrue(all(r[2] == "ada@example.com" for r in rf))
 
     def test_index_commits_idempotent(self):
-        cs = [sample_commit()]
+        cs = gitimport.parse_log(SAMPLE)
         gitimport.index_commits(self.conn, cs, "sample-repo")
         gitimport.index_commits(self.conn, cs, "sample-repo")
         n = self.conn.execute("MATCH (c:Commit) RETURN count(*)").get_all()[0][0]

bin/tools/test_gitimport.py

@@ -0,0 +1,57 @@
+import sys
+import unittest
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).resolve().parent))
+
+import gitimport  # noqa: E402
+
+SAMPLE = (
+    "\x1e" + "a1b2c3d" + "\x1f" + "Ada Lovelace" + "\x1f" + "ada@example.com"
+    + "\x1f" + "2026-08-10T12:00:00+01:00" + "\x1f" + "feat: first commit"
+    + "\n\nREADME.md\nsrc/main.c\n"
+    + "\x1e" + "e4f5a6b" + "\x1f" + "Bob Babbage" + "\x1f" + "bob@example.com"
+    + "\x1f" + "2026-08-11T09:30:00+01:00" + "\x1f" + "fix: typo"
+    + "\n\ndocs/notes.md"
+)
+
+
+class GitparseTest(unittest.TestCase):
+    def test_parses_records(self):
+        cs = gitimport.parse_log(SAMPLE)
+        self.assertEqual(len(cs), 2)
+
+    def test_parses_commit_fields(self):
+        cs = gitimport.parse_log(SAMPLE)
+        c = cs[0]
+        self.assertEqual(c.sha, "a1b2c3d")
+        self.assertEqual(c.author, "Ada Lovelace")
+        self.assertEqual(c.email, "ada@example.com")
+        self.assertEqual(c.date, "2026-08-10T12:00:00+01:00")
+        self.assertEqual(c.subject, "feat: first commit")
+
+    def test_parses_changed_files(self):
+        cs = gitimport.parse_log(SAMPLE)
+        self.assertEqual(cs[0].files, ["README.md", "src/main.c"])
+        self.assertEqual(cs[1].files, ["docs/notes.md"])
+
+    def test_ignores_empty(self):
+        self.assertEqual(gitimport.parse_log(""), [])
+
+    def test_skip_malformed_record(self):
+        self.assertEqual(gitimport.parse_log("\x1eweird\x1e"), [])
+
+    def test_commit_leaf_shape(self):
+        leafs = gitimport.commits_to_leafs(gitimport.parse_log(SAMPLE), "sample-repo")
+        self.assertEqual(len(leafs), 2)
+        lf = leafs[0]
+        self.assertEqual(lf["type"], "commit")
+        self.assertEqual(lf["repo"], "sample-repo")
+        self.assertEqual(lf["source"], "sample-repo@a1b2c3d")
+        self.assertIn("Ada Lovelace", lf["text"])
+        self.assertIn("README.md", lf["related"])
+        self.assertIn("feat: first commit", lf["heading"])
+
+
+if __name__ == "__main__":
+    unittest.main()

bin/tools/test_index_adapters.py

@@ -1,41 +0,0 @@
-"""Import adapters write files only. Index rebuild is brain/index (D14 / Gitea #7)."""
-from __future__ import annotations
-
-import json
-import os
-import subprocess
-import sys
-import tempfile
-import unittest
-from pathlib import Path
-
-ROOT = Path(__file__).resolve().parents[2]
-
-
-class IndexAdapterTest(unittest.TestCase):
-    def test_dry_run_fixture_corpus_does_not_write_lbug(self) -> None:
-        tmp = Path(tempfile.mkdtemp())
-        (tmp / "note.md").write_text("# Fixture\n\n## Leaf\n\nhello corpus\n", encoding="utf-8")
-        lbug = tmp / "kb.lbug"
-        try:
-            import ladybug  # noqa: F401
-        except ImportError:
-            venv_py = ROOT / ".venv" / "bin" / "python"
-            if not venv_py.is_file():
-                self.skipTest("ladybug missing")
-            py = str(venv_py)
-        else:
-            py = sys.executable
-        proc = subprocess.run(
-            [py, str(ROOT / "bin" / "kb" / "index"), "--dry-run", "--json", "--corpus", str(tmp)],
-            cwd=ROOT,
-            capture_output=True,
-            text=True,
-            env=os.environ.copy(),
-            check=False,
-        )
-        self.assertEqual(proc.returncode, 0, proc.stderr)
-        msg = json.loads(proc.stdout)
-        self.assertTrue(msg.get("dry_run"))
-        self.assertGreaterEqual(msg.get("corpus_total", 0), 1)
-        self.assertFalse(lbug.exists(), "dry-run must not create a Ladybug file")

bin/tools/test_kb_add.py

@@ -1,69 +0,0 @@
-"""Incremental add writes leafs without deleting kb.lbug."""
-from __future__ import annotations
-
-import json
-import os
-import subprocess
-import sys
-import tempfile
-import unittest
-from pathlib import Path
-
-ROOT = Path(__file__).resolve().parents[2]
-
-
-class KbAddCLITest(unittest.TestCase):
-    def test_json_add_does_not_delete_db(self) -> None:
-        tmp = Path(tempfile.mkdtemp())
-        dbpath = tmp / "kb.lbug"
-        py = sys.executable
-        venv_py = ROOT / ".venv" / "bin" / "python"
-        if venv_py.is_file():
-            py = str(venv_py)
-        payload = {
-            "text": "cli zebra leaf",
-            "root": "info",
-            "source": "cli-test",
-            "confidence": "confirmed",
-            "how": "test",
-            "loc": str(tmp),
-            "type": "reference",
-            "embedding": [0.0] * 256,
-        }
-        payload["embedding"][0] = 0.3
-        proc = subprocess.run(
-            [py, str(ROOT / "bin" / "kb" / "add"), "--db", str(dbpath), "--json"],
-            cwd=ROOT,
-            input=json.dumps(payload),
-            capture_output=True,
-            text=True,
-            env=os.environ.copy(),
-            check=False,
-        )
-        self.assertEqual(proc.returncode, 0, proc.stderr)
-        self.assertTrue(dbpath.exists(), "add must create the db, not skip write")
-        out = json.loads(proc.stdout)
-        self.assertEqual(out.get("mode"), "add")
-        self.assertEqual(len(out.get("ids") or []), 1)
-        again = subprocess.run(
-            [py, str(ROOT / "bin" / "kb" / "add"), "--db", str(dbpath), "--json"],
-            cwd=ROOT,
-            input=json.dumps({
-                **payload,
-                "text": "second moose leaf",
-                "source": "cli-test-2",
-            }),
-            capture_output=True,
-            text=True,
-            env=os.environ.copy(),
-            check=False,
-        )
-        self.assertEqual(again.returncode, 0, again.stderr)
-        self.assertTrue(dbpath.exists())
-        second = json.loads(again.stdout)
-        self.assertEqual(len(second.get("ids") or []), 1)
-        self.assertNotEqual(out["ids"][0], second["ids"][0])
-
-
-if __name__ == "__main__":
-    unittest.main()

bin/tools/test_kblib.py

@@ -71,69 +71,6 @@ class KblibTest(unittest.TestCase):
         self.assertTrue(hits)
         self.assertIn("Leaf_vec", kblib.leaf_index_names(self.conn))
 
-    def test_add_after_indexes_keeps_fts_queryable(self):
-        """Incremental add after FTS+HNSW must find the new leaf on both indexes."""
-        kblib.upsert_leaf(self.conn, text="seed fox leaf", root="info",
-                          confidence="confirmed", source="s", source_rev="r1",
-                          how="test", loc="/tmp", type_="reference",
-                          embedding=make_emb(0.1))
-        kblib.ensure_indexes(self.conn)
-        ids = kblib.add_leafs(self.conn, [{
-            "text": "added zebra after index",
-            "root": "facts",
-            "confidence": "confirmed",
-            "source": "a.md x b.md",
-            "source_rev": "r1",
-            "how": "test",
-            "loc": "/tmp",
-            "type": "fact",
-            "embedding": make_emb(0.9),
-        }])
-        self.assertEqual(len(ids), 1)
-        fts = kblib.query_fts(self.conn, "zebra", 5)
-        self.assertTrue(fts)
-        self.assertIn("zebra", fts[0]["text"])
-        self.assertEqual(fts[0]["root"], "facts")
-        vec = kblib.query_vector(self.conn, make_emb(0.9), 5)
-        self.assertTrue(any("zebra" in h["text"] for h in vec))
-        fox = kblib.query_fts(self.conn, "fox", 5)
-        self.assertTrue(fox)
-        self.assertIn("fox", fox[0]["text"])
-
-    def test_add_facts_and_info_one_transaction(self):
-        """D12: facts and info land in the same transaction."""
-        kblib.ensure_indexes(self.conn)
-        ids = kblib.add_leafs(self.conn, [
-            {
-                "text": "tx fact leaf two-source",
-                "root": "facts",
-                "confidence": "confirmed",
-                "source": "compose.yml x docker ps",
-                "source_rev": "r1",
-                "how": "test",
-                "loc": "/tmp",
-                "type": "fact",
-                "embedding": make_emb(0.4),
-            },
-            {
-                "text": "tx info narrative",
-                "root": "info",
-                "confidence": "confirmed",
-                "source": "note.md",
-                "source_rev": "r1",
-                "how": "test",
-                "loc": "/tmp",
-                "type": "reference",
-                "embedding": make_emb(0.5),
-            },
-        ])
-        self.assertEqual(len(ids), 2)
-        stats = kblib.stats(self.conn)
-        self.assertEqual(stats["by_root"].get("facts"), 1)
-        self.assertEqual(stats["by_root"].get("info"), 1)
-        self.assertTrue(kblib.query_fts(self.conn, "two-source", 5))
-        self.assertTrue(kblib.query_fts(self.conn, "narrative", 5))
-
     def test_drop_vector_then_create_raises_clear_error(self):
         """DROP INDEX leaves ghost catalog; create_fts_and_vector must raise."""
         kblib.upsert_leaf(self.conn, text="seed", root="info",

bin/tools/test_mailleafs.py

@@ -1,46 +0,0 @@
-"""Mail markdown → leafs (no Ladybug). Brain index --with-mail uses this."""
-from __future__ import annotations
-
-import json
-import sys
-import tempfile
-import unittest
-from pathlib import Path
-
-sys.path.insert(0, str(Path(__file__).resolve().parent))
-
-import mailleafs  # noqa: E402
-
-
-class MailLeafsTest(unittest.TestCase):
-    def test_message_md_becomes_info_leaf(self) -> None:
-        root = Path(tempfile.mkdtemp())
-        msg = root / "inbox" / "alice-1"
-        msg.mkdir(parents=True)
-        (msg / "message.json").write_text(
-            json.dumps({"receivedDate": "2026-01-15T10:00:00Z", "subject": "Hello"}),
-            encoding="utf-8",
-        )
-        (msg / "message.md").write_text(
-            "---\nroot: info\n---\n\n# Hello\n\nFrom Alice to Bob.\n",
-            encoding="utf-8",
-        )
-        leafs = mailleafs.from_mail_root(root)
-        self.assertEqual(len(leafs), 1)
-        self.assertIn("Alice", leafs[0]["text"])
-        self.assertTrue(leafs[0]["source"].startswith("ooMail:"))
-        self.assertEqual(leafs[0]["how"], "mail/import")
-
-    def test_since_filters_by_message_json_date(self) -> None:
-        root = Path(tempfile.mkdtemp())
-        for name, day in (("old", "2025-01-01"), ("new", "2026-06-01")):
-            d = root / "inbox" / name
-            d.mkdir(parents=True)
-            (d / "message.json").write_text(
-                json.dumps({"receivedDate": f"{day}T00:00:00Z"}),
-                encoding="utf-8",
-            )
-            (d / "message.md").write_text(f"# {name}\n\nbody\n", encoding="utf-8")
-        leafs = mailleafs.from_mail_root(root, since="2026-01-01")
-        self.assertEqual(len(leafs), 1)
-        self.assertIn("new", leafs[0]["text"])

bin/tools/test_published_docs.py

@@ -1,192 +0,0 @@
-"""Published docs must match live commands (Gitea SoT, brain/search, no fake --hop)."""
-from __future__ import annotations
-
-import re
-import unittest
-from pathlib import Path
-
-ROOT = Path(__file__).resolve().parents[2]
-
-
-class PublishedDocsTest(unittest.TestCase):
-    def test_readme_points_issues_at_gitea(self) -> None:
-        text = (ROOT / "README.md").read_text()
-        self.assertIn(
-            "https://git.produktor.io/eSlider/2dph/issues",
-            text,
-            "README must point issues at Gitea",
-        )
-
-    def test_plan_d15_names_gitea_origin(self) -> None:
-        text = (ROOT / "PLAN.md").read_text()
-        self.assertIn("D15", text)
-        self.assertIn("git.produktor.io/eSlider/2dph", text)
-
-    def test_readme_primary_search_is_brain(self) -> None:
-        text = (ROOT / "README.md").read_text()
-        self.assertIn(
-            "bin/brain/search.go",
-            text,
-            "README deduction search must name bin/brain/search.go",
-        )
-
-    def test_readme_index_is_brain_not_index_mail(self) -> None:
-        text = (ROOT / "README.md").read_text()
-        self.assertIn("bin/brain/index.go", text)
-        self.assertNotIn(
-            "bin/mail/index_mail",
-            text,
-            "mail index is a brain write; README must name bin/brain/index.go",
-        )
-
-    def test_readme_git_import_is_gogit(self) -> None:
-        text = (ROOT / "README.md").read_text()
-        self.assertIn("bin/git/import.go", text)
-        self.assertIn("go-git", text)
-        self.assertIn("D19", (ROOT / "PLAN.md").read_text())
-
-    def test_web_search_is_go_not_ops_host(self) -> None:
-        readme = (ROOT / "README.md").read_text()
-        self.assertIn("bin/web/search.go", readme)
-        skill = (ROOT / "skills" / "web-search" / "SKILL.md").read_text()
-        self.assertIn("bin/web/search.go", skill)
-        self.assertNotIn("search.ops.io", skill)
-        self.assertNotIn("search.ops.io", readme)
-        compose = (ROOT / "compose.yaml").read_text()
-        self.assertIn("searxng", compose)
-        self.assertNotIn("search.ops.io", compose)
-        settings = (ROOT / "deploy" / "searxng" / "settings.yml").read_text()
-        self.assertNotIn("password", settings.lower())
-        self.assertIn("json", settings)
-
-    def test_picoclaw_compose_profile_has_mcp_example(self) -> None:
-        compose = (ROOT / "compose.yaml").read_text()
-        self.assertIn('profiles: ["picoclaw"]', compose)
-        self.assertIn("127.0.0.1:8630", compose)
-        example = (ROOT / "deploy" / "picoclaw" / "mcp.json.example").read_text()
-        self.assertIn("127.0.0.1:8630/mcp", example)
-        self.assertNotIn("password", example.lower())
-        self.assertNotIn("token", example.lower())
-        docs = (ROOT / "docs" / "picoclaw.md").read_text()
-        self.assertIn("search", docs)
-        self.assertIn("throttled", docs)
-
-    def test_readme_read_path_is_go(self) -> None:
-        plan = (ROOT / "PLAN.md").read_text()
-        self.assertIn("get.go", plan)
-        self.assertIn("CI fallback", plan)
-        design = (ROOT / "docs" / "design.md").read_text()
-        self.assertIn("internal/brain/rank", design)
-        self.assertIn("They do not exec Python", design)
-
-    def test_openapi_mcp_from_same_handlers(self) -> None:
-        plan = (ROOT / "PLAN.md").read_text()
-        self.assertIn("D20", plan)
-        self.assertIn("/openapi.json", (ROOT / "README.md").read_text())
-        self.assertIn("/mcp", (ROOT / "README.md").read_text())
-        skill = (ROOT / "skills" / "brain" / "SKILL.md").read_text()
-        self.assertIn("/mcp", skill)
-        self.assertFalse((ROOT / "skills" / "db-yaml").exists())
-        self.assertTrue((ROOT / "skills" / "postgres" / "SKILL.md").is_file())
-
-    def test_cgo_zig_and_index_profile(self) -> None:
-        plan = (ROOT / "PLAN.md").read_text()
-        self.assertIn("D21", plan)
-        self.assertIn("zig cc", plan)
-        dockerfile = (ROOT / "Dockerfile").read_text()
-        self.assertIn("bin/cgo/zcc", dockerfile)
-        self.assertIn("FROM debian:bookworm-slim AS api", dockerfile)
-        self.assertIn("FROM python:3.12-slim AS index", dockerfile)
-        api = dockerfile[dockerfile.index("FROM debian:bookworm-slim AS api") :]
-        self.assertNotIn("pip install", api)
-        compose = (ROOT / "compose.yaml").read_text()
-        self.assertIn('profiles: ["index"]', compose)
-        self.assertIn("target: api", compose)
-
-    def test_reasoner_docs_name_real_hf_ids_cpu_sidecar(self) -> None:
-        docs = (ROOT / "docs" / "reasoner.md").read_text()
-        for hf in (
-            "Qwen/Qwen3.5-9B",
-            "Qwen/Qwen3.6-27B",
-            "prism-ml/Bonsai-27B-gguf",
-        ):
-            self.assertIn(hf, docs)
-        self.assertIn("no official qwen3.6-9b", docs.lower())
-        self.assertIn("OLLAMA_NUM_GPU", docs)
-        self.assertIn("rss_mb", docs)
-        self.assertIn("vram_mb", docs)
-        self.assertIn("3/3", docs)
-        self.assertIn("Do not claim 9B is better at tools", docs)
-        self.assertNotIn("Qwen/Qwen3.6-9B", docs)
-        plan = (ROOT / "PLAN.md").read_text()
-        self.assertIn("D18", plan)
-        self.assertIn("Qwen/Qwen3.5-9B", plan)
-        compose = (ROOT / "compose.yaml").read_text()
-        self.assertIn('profiles: ["reasoner"]', compose)
-        self.assertIn("OLLAMA_NUM_GPU", compose)
-        self.assertIn("127.0.0.1:11435", compose)
-        dockerfile = (ROOT / "Dockerfile").read_text()
-        self.assertNotIn(".gguf", dockerfile.lower())
-        self.assertNotIn(".safetensors", dockerfile.lower())
-        api = dockerfile[dockerfile.index("FROM debian:bookworm-slim AS api") :]
-        self.assertNotIn("COPY models", api)
-        self.assertNotIn("qwen", api.lower())
-
-    def test_readme_search_escalates_web(self) -> None:
-        text = (ROOT / "README.md").read_text()
-        self.assertIn("--no-web", text)
-        self.assertIn("D17", (ROOT / "PLAN.md").read_text())
-        skill = (ROOT / "skills" / "brain" / "SKILL.md").read_text()
-        self.assertIn("`web` block", skill)
-
-    def test_docs_do_not_claim_hop_walks(self) -> None:
-        paths = [
-            ROOT / "README.md",
-            ROOT / "docs" / "design.md",
-            ROOT / "skills" / "brain" / "SKILL.md",
-            ROOT / "skills" / "diataxis-docs" / "SKILL.md",
-            ROOT / "docs" / "runbook.md",
-            ROOT / "docs" / "README.md",
-            ROOT / "docs" / "roadmap.md",
-        ]
-        # Command-style `--hop 1` / `--hop N` plus follow/walk = the old lie.
-        # Honest "not implemented" notes must not match.
-        lie = re.compile(r"--hop (?:N|1).*(?:follow|walk)", re.I | re.S)
-        for path in paths:
-            text = path.read_text()
-            self.assertIsNone(
-                lie.search(text),
-                f"{path.relative_to(ROOT)} still claims --hop walks the graph",
-            )
-
-    def test_docs_are_portable_diataxis(self) -> None:
-        index = (ROOT / "docs" / "README.md").read_text()
-        self.assertIn("type: reference", index)
-        for d in ("D3", "D6", "D14", "D15", "D17", "D18"):
-            self.assertIn(d, index)
-        runbook = (ROOT / "docs" / "runbook.md").read_text()
-        self.assertIn("type: howto", runbook)
-        self.assertIn("bin/brain/search.go", runbook)
-        self.assertIn("bin/brain/index.go", runbook)
-        self.assertNotIn("search.ops.io", runbook)
-        self.assertNotIn("/mnt/", runbook)
-        self.assertNotIn("/home/", runbook)
-        readme = (ROOT / "README.md").read_text()
-        self.assertIn("docs/runbook.md", readme)
-        self.assertNotIn("search.ops.io", readme)
-
-    def test_v1_epic_is_named_in_docs(self) -> None:
-        plan = (ROOT / "PLAN.md").read_text()
-        self.assertIn("Gap to v1", plan)
-        self.assertIn("eSlider/2dph/issues/16", plan)
-        self.assertIn("eSlider/2dph/issues/17", plan)
-        self.assertIn("eSlider/2dph/milestone/12", plan)
-        road = (ROOT / "docs" / "roadmap.md").read_text()
-        self.assertIn("type: explanation", road)
-        self.assertIn("issues/16", road)
-        self.assertIn("issues/14", road)
-        index = (ROOT / "docs" / "README.md").read_text()
-        self.assertIn("roadmap.md", index)
-        self.assertIn("epic #16", index)
-        agents = (ROOT / "AGENTS.md").read_text()
-        self.assertIn("roadmap.md", agents)

bin/tools/test_skills.py

@@ -1,49 +0,0 @@
-"""Skills must name live commands; every bin/ path in SKILL.md must exist."""
-from __future__ import annotations
-
-import re
-import unittest
-from pathlib import Path
-
-ROOT = Path(__file__).resolve().parents[2]
-BIN_PATH = re.compile(r"(bin/[A-Za-z0-9_./-]+)")
-
-
-class SkillsTest(unittest.TestCase):
-    def test_db_yaml_renamed_to_postgres(self) -> None:
-        self.assertFalse(
-            (ROOT / "skills" / "db-yaml").exists(),
-            "skills/db-yaml must be skills/postgres",
-        )
-        self.assertTrue((ROOT / "skills" / "postgres" / "SKILL.md").is_file())
-        text = (ROOT / "skills" / "postgres" / "SKILL.md").read_text()
-        self.assertIn("bin/postgres/query.go", text)
-        self.assertNotIn("search.ops.io", text)
-
-    def test_every_bin_path_in_skills_exists(self) -> None:
-        missing: list[str] = []
-        for path in (ROOT / "skills").rglob("SKILL.md"):
-            text = path.read_text()
-            for m in BIN_PATH.finditer(text):
-                rel = m.group(1).rstrip(")`.,;")
-                candidate = ROOT / rel
-                if not candidate.exists():
-                    missing.append(f"{path.relative_to(ROOT)}: {rel}")
-        self.assertEqual(missing, [], "skill bin paths must exist")
-
-    def test_brain_skill_lists_generated_tools(self) -> None:
-        tools = (ROOT / "skills" / "brain" / "tools.md").read_text()
-        skill = (ROOT / "skills" / "brain" / "SKILL.md").read_text()
-        self.assertIn("tools.md", skill)
-        for name in ("search", "get", "stats", "audit"):
-            self.assertIn(f"`{name}`", tools)
-
-    def test_picoclaw_lists_tool_order(self) -> None:
-        skill = (ROOT / "skills" / "picoclaw" / "SKILL.md").read_text()
-        agents = (ROOT / "AGENTS.md").read_text()
-        self.assertIn("**`search`**", skill)
-        self.assertIn("**`get`**", skill)
-        self.assertIn("**`audit`**", skill)
-        self.assertIn("throttled", skill.lower())
-        self.assertIn("not a negative finding", agents)
-        self.assertIn("Fact-check every", agents)

bin/tools/test_skills_bin_paths.py

@@ -1,33 +0,0 @@
-"""Every bin/ path named in skills/ must exist on disk."""
-from __future__ import annotations
-
-import re
-import unittest
-from pathlib import Path
-
-ROOT = Path(__file__).resolve().parents[2]
-BIN_PATH = re.compile(r"\b(bin/[A-Za-z0-9_./-]+)")
-
-
-class SkillsBinPathsTest(unittest.TestCase):
-    def test_agent_cost_skill_is_gone(self) -> None:
-        self.assertFalse(
-            (ROOT / "skills" / "agent-cost").exists(),
-            "skills/agent-cost documents bin/agents/cost which does not exist",
-        )
-
-    def test_brain_skill_replaces_kb_search(self) -> None:
-        self.assertTrue((ROOT / "skills" / "brain" / "SKILL.md").is_file())
-        self.assertFalse((ROOT / "skills" / "kb-search").exists())
-
-    def test_skill_bin_paths_exist(self) -> None:
-        missing: list[str] = []
-        for skill in sorted((ROOT / "skills").rglob("SKILL.md")):
-            text = skill.read_text()
-            for match in BIN_PATH.findall(text):
-                rel = match.rstrip("`'.,")
-                if rel.endswith(".go") or Path(rel).suffix == "" or Path(rel).suffix in {".go", ".py"}:
-                    p = ROOT / rel
-                    if not p.exists():
-                        missing.append(f"{skill.relative_to(ROOT)}: {rel}")
-        self.assertEqual(missing, [], "SKILL.md names bin/ paths that do not exist")

bin/watch/watch.go

@@ -1,4 +1,4 @@
-// Package watch polls corpus directories for changes and re-runs brain/index.
+// Package watch polls corpus directories for changes and re-runs bin/kb/index.
 //
 // Port of the former bin/kb-watch bash script to an importable, testable Go
 // package. Polls file mtimes (no inotify deps); cheap and reliable.
@@ -18,8 +18,8 @@ import (
 type Options struct {
 	Dirs     []string
 	Interval time.Duration
-	// IndexCmd is the index command template. %s is replaced by the repo
+	// IndexCmd is the kb/index command template. %s is replaced by the repo
-	// root (from KB_ROOT). Defaults to `python3 <root>/bin/kb/index --with-mail`.
+	// root (from KB_ROOT). Defaults to `python3 <root>/bin/kb/index`.
 	IndexCmd string
 }
 
@@ -67,7 +67,7 @@ func fromEnv(args []string) Options {
 	if pys == "" {
 		pys = "python3"
 	}
-	opts.IndexCmd = pys + " <root>/bin/kb/index --with-mail"
+	opts.IndexCmd = pys + " <root>/bin/kb/index"
 	return opts
 }
 

bin/watch/watch_test.go

@@ -3,7 +3,6 @@ package watch
 import (
 	"os"
 	"path/filepath"
-	"strings"
 	"testing"
 	"time"
 )
@@ -44,10 +43,7 @@ func TestFromEnvDefaults(t *testing.T) {
 	if opts.Interval != 30*time.Second {
 		t.Fatalf("default interval = %s, want 30s", opts.Interval)
 	}
-	if !strings.Contains(opts.IndexCmd, "kb/index") {
+	if opts.IndexCmd == "" {
-		t.Fatalf("default index cmd = %q, want kb/index", opts.IndexCmd)
+		t.Fatal("default index cmd is empty")
-	}
-	if !strings.Contains(opts.IndexCmd, "--with-mail") {
-		t.Fatalf("default index cmd must include --with-mail, got %q", opts.IndexCmd)
 	}
 }

bin/web/search

@@ -1,26 +1,150 @@
 #!/usr/bin/env python3
-"""web/search — deprecated. Use bin/web/search.go (SearXNG, no Python client).
+"""web/search - web search through the self-hosted SearXNG at search.ops.io.
 
-  bin/web/search.go QUERY [--json] [-n N] [--site HOST]
+  bin/web/search "LadybugDB vector search"
+  bin/web/search "model2vec multilingual" --site github.com
+  bin/web/search "uclancy" --category it -n 3 --json | jq -r '.results[].url'
+  bin/web/search "sqlite-vec" --refresh          # ignore the cached answer
+
+This complements bin/kb/search: the knowledge base holds our own facts, this
+reaches the public web. Use it as the second, independent source that the
+detective method asks for.
+
+Exit codes: 0 results, 2 refused as possible PII, 3 throttled (not "nothing
+found" - the instance answers 200 with an empty list when it throttles).
 """
 from __future__ import annotations
 
+import argparse
+import fcntl
+import json
 import os
 import sys
+import time
+import urllib.parse
+import urllib.request
 from pathlib import Path
 
-ROOT = Path(__file__).resolve().parents[2]
+TOOLS = Path(__file__).resolve().parents[1] / "tools"
+sys.path.insert(0, str(TOOLS))
+sys.path.insert(0, str(TOOLS / "web-search"))
+
+import websearch as ws          # noqa: E402
+from yamlout import to_yaml     # noqa: E402
+
+CONFIG = Path(os.environ.get("BRAIN_SEARCH_ENV", Path.home() / ".config/brain/search.env"))
+CACHE = Path(os.environ.get("BRAIN_SEARCH_CACHE", Path.home() / ".cache/brain/web-search.sqlite"))
+LOCK = CACHE.with_suffix(".lock")
 
 
-def main(argv: list[str]) -> int:
+def load_config() -> dict:
-    print(
+    if not CONFIG.exists():
-        "bin/web/search is deprecated; use bin/web/search.go",
+        sys.exit(f"no credentials at {CONFIG} (mode 600, BRAIN_SEARCH_URL/USER/PASS)")
-        file=sys.stderr,
+    conf = {}
-    )
+    for line in CONFIG.read_text().splitlines():
-    target = ROOT / "bin" / "web" / "search.go"
+        line = line.strip()
-    os.execvp("go", ["go", "run", str(target), *argv])
+        if not line or line.startswith("#") or "=" not in line:
-    return 1
+            continue
+        key, _, value = line.partition("=")
+        conf[key.strip()] = value.strip().strip("\"'")
+    missing = {"BRAIN_SEARCH_URL", "BRAIN_SEARCH_USER", "BRAIN_SEARCH_PASS"} - conf.keys()
+    if missing:
+        sys.exit(f"{CONFIG} is missing {', '.join(sorted(missing))}")
+    return conf
+
+
+def fetch(conf: dict, query: str, params: dict, timeout: int) -> dict:
+    args = {"q": query, "format": "json", **params}
+    url = f"{conf['BRAIN_SEARCH_URL'].rstrip('/')}/search?{urllib.parse.urlencode(args)}"
+    request = urllib.request.Request(url)
+    token = f"{conf['BRAIN_SEARCH_USER']}:{conf['BRAIN_SEARCH_PASS']}".encode()
+    import base64
+    request.add_header("Authorization", "Basic " + base64.b64encode(token).decode())
+    with urllib.request.urlopen(request, timeout=timeout) as response:
+        return json.loads(response.read().decode())
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(description="web search via SearXNG")
+    parser.add_argument("query")
+    parser.add_argument("-n", "--limit", type=int, default=ws.DEFAULT_LIMIT)
+    parser.add_argument("--site", help="restrict to one domain")
+    parser.add_argument("--lang", help="language code, e.g. de")
+    parser.add_argument("--fresh", choices=["day", "week", "month", "year"],
+                        help="time range")
+    parser.add_argument("--category", help="SearXNG category, e.g. it, science, news")
+    parser.add_argument("--engines", help="comma separated engine list")
+    parser.add_argument("--json", action="store_true")
+    parser.add_argument("--refresh", action="store_true", help="bypass the cache")
+    parser.add_argument("--ttl", type=float, default=ws.CACHE_TTL)
+    parser.add_argument("--timeout", type=int, default=25)
+    parser.add_argument("--force", action="store_true",
+                        help="send even if the query looks like PII")
+    args = parser.parse_args()
+
+    query = f"site:{args.site} {args.query}" if args.site else args.query
+
+    reason = ws.phi_reason(query)
+    if reason and not args.force:
+        print(f"refused: {reason}. This query would leave the host.", file=sys.stderr)
+        print("Rephrase without identifiers, or pass --force if it is genuinely public.",
+              file=sys.stderr)
+        return 2
+
+    params = {}
+    if args.lang:
+        params["language"] = args.lang
+    if args.fresh:
+        params["time_range"] = args.fresh
+    if args.category:
+        params["categories"] = args.category
+    if args.engines:
+        params["engines"] = args.engines
+
+    key = ws.cache_key(query, params)
+    conn = ws.open_cache(CACHE)
+
+    if not args.refresh:
+        cached = ws.cache_get(conn, key, ttl=args.ttl)
+        if cached is not None:
+            out = ws.project(cached, limit=args.limit)
+            out["cached"] = True
+            sys.stdout.write(json.dumps(out, indent=2, ensure_ascii=False) + "\n"
+                             if args.json else to_yaml(out))
+            return 0
+
+    conf = load_config()
+    LOCK.parent.mkdir(parents=True, exist_ok=True)
+
+    # One request at a time across every agent on this host: the instance
+    # suspends engines for minutes when several of us ask at once.
+    with open(LOCK, "w") as lock:
+        fcntl.flock(lock, fcntl.LOCK_EX)
+
+        payload = None
+        for attempt in range(1 + len(ws.RETRY_BACKOFF)):
+            delay = ws.wait_for(ws.last_call(conn), time.time())
+            if delay:
+                time.sleep(delay)
+            ws.mark_call(conn)
+            try:
+                payload = fetch(conf, query, params, args.timeout)
+            except Exception as error:              # noqa: BLE001 - report, do not crash
+                print(f"request failed: {error}", file=sys.stderr)
+                return 3
+            if ws.classify(payload) == "ok":
+                break
+            if attempt < len(ws.RETRY_BACKOFF):
+                time.sleep(ws.RETRY_BACKOFF[attempt])
+
+    if ws.classify(payload) == "ok":
+        ws.cache_put(conn, key, payload)
+
+    out = ws.project(payload, limit=args.limit)
+    sys.stdout.write(json.dumps(out, indent=2, ensure_ascii=False) + "\n"
+                     if args.json else to_yaml(out))
+    return 0 if out["status"] == "ok" else 3
 
 
 if __name__ == "__main__":
-    sys.exit(main(sys.argv[1:]))
+    sys.exit(main())

bin/web/search.go

@@ -1,232 +0,0 @@
-//usr/bin/env go run "$0" "$@"; exit
-//
-// bin/web/search.go - SearXNG as the second independent source (D3).
-//
-//	./bin/web/search.go "LadybugDB vector search"
-//	./bin/web/search.go "model2vec" --category it --json
-//	./bin/web/search.go "postgres" --site github.com --fresh year
-//
-// Empty results mean throttled, not "nothing exists". Exit 2 = PII refuse, 3 = throttled.
-// Config: $BRAIN_SEARCH_ENV (default $HOME/.config/brain/search.env).
-// NOTE: never run `gofmt -w` on this file — it breaks the shebang.
-package main
-
-import (
-	"encoding/json"
-	"fmt"
-	"net/http"
-	"os"
-	"strconv"
-	"time"
-
-	"github.com/eSlider/2dph/internal/websearch"
-	"golang.org/x/sys/unix"
-)
-
-func main() {
-	os.Exit(run(os.Args[1:]))
-}
-
-func run(args []string) int {
-	var (
-		query, site, lang, fresh, category, engines string
-		limit                                       = websearch.DefaultLimit
-		jsonOut, refresh, force                     bool
-		ttl                                         = float64(websearch.CacheTTL)
-		timeout                                     = 25
-	)
-	i := 0
-	for i < len(args) {
-		a := args[i]
-		switch {
-		case a == "--json":
-			jsonOut = true
-		case a == "--refresh":
-			refresh = true
-		case a == "--force":
-			force = true
-		case (a == "-n" || a == "--limit") && i+1 < len(args):
-			i++
-			n, err := strconv.Atoi(args[i])
-			if err != nil || n < 0 {
-				fmt.Fprintln(os.Stderr, "web/search: --limit must be a non-negative integer")
-				return 2
-			}
-			limit = n
-		case a == "--site" && i+1 < len(args):
-			i++
-			site = args[i]
-		case a == "--lang" && i+1 < len(args):
-			i++
-			lang = args[i]
-		case a == "--fresh" && i+1 < len(args):
-			i++
-			fresh = args[i]
-		case a == "--category" && i+1 < len(args):
-			i++
-			category = args[i]
-		case a == "--engines" && i+1 < len(args):
-			i++
-			engines = args[i]
-		case a == "--ttl" && i+1 < len(args):
-			i++
-			v, err := strconv.ParseFloat(args[i], 64)
-			if err != nil {
-				fmt.Fprintln(os.Stderr, "web/search: --ttl must be a number")
-				return 2
-			}
-			ttl = v
-		case a == "--timeout" && i+1 < len(args):
-			i++
-			n, err := strconv.Atoi(args[i])
-			if err != nil || n <= 0 {
-				fmt.Fprintln(os.Stderr, "web/search: --timeout must be a positive integer")
-				return 2
-			}
-			timeout = n
-		case a == "-h" || a == "--help":
-			fmt.Fprintln(os.Stderr, `usage: bin/web/search.go QUERY [--json] [-n N] [--site HOST] [--lang LANG] [--fresh day|week|month|year] [--category CAT] [--engines LIST] [--refresh] [--force]`)
-			return 0
-		case len(a) > 0 && a[0] != '-' && query == "":
-			query = a
-		default:
-			fmt.Fprintf(os.Stderr, "web/search: unknown flag %s\n", a)
-			return 2
-		}
-		i++
-	}
-	if query == "" {
-		fmt.Fprintln(os.Stderr, "web/search: query required")
-		return 2
-	}
-	if site != "" {
-		query = "site:" + site + " " + query
-	}
-	if reason := websearch.PHIReason(query); reason != "" && !force {
-		fmt.Fprintf(os.Stderr, "refused: %s. This query would leave the host.\n", reason)
-		fmt.Fprintln(os.Stderr, "Rephrase without identifiers, or pass --force if it is genuinely public.")
-		return 2
-	}
-
-	params := map[string]string{}
-	if lang != "" {
-		params["language"] = lang
-	}
-	if fresh != "" {
-		params["time_range"] = fresh
-	}
-	if category != "" {
-		params["categories"] = category
-	}
-	if engines != "" {
-		params["engines"] = engines
-	}
-
-	cachePath := os.Getenv("BRAIN_SEARCH_CACHE")
-	if cachePath == "" {
-		cachePath = os.Getenv("HOME") + "/.cache/brain/web-search.sqlite"
-	}
-	cache, err := websearch.OpenCache(cachePath)
-	if err != nil {
-		fmt.Fprintf(os.Stderr, "web/search: cache: %v\n", err)
-		return 1
-	}
-	defer cache.Close()
-
-	key := websearch.CacheKey(query, params)
-	now := float64(time.Now().Unix())
-	if !refresh {
-		if cached, err := cache.Get(key, ttl, now); err != nil {
-			fmt.Fprintf(os.Stderr, "web/search: cache: %v\n", err)
-			return 1
-		} else if cached != nil {
-			out := websearch.Project(*cached, limit, websearch.DefaultSnippetChars)
-			out.Cached = true
-			return writeOut(out, jsonOut)
-		}
-	}
-
-	envPath := os.Getenv("BRAIN_SEARCH_ENV")
-	if envPath == "" {
-		envPath = os.Getenv("HOME") + "/.config/brain/search.env"
-	}
-	conf, err := websearch.LoadConfig(envPath)
-	if err != nil {
-		fmt.Fprintf(os.Stderr, "web/search: %v\n", err)
-		return 1
-	}
-
-	lockPath := cachePath + ".lock"
-	lock, err := os.OpenFile(lockPath, os.O_CREATE|os.O_RDWR, 0o600)
-	if err != nil {
-		fmt.Fprintf(os.Stderr, "web/search: lock: %v\n", err)
-		return 1
-	}
-	defer lock.Close()
-	if err := unix.Flock(int(lock.Fd()), unix.LOCK_EX); err != nil {
-		fmt.Fprintf(os.Stderr, "web/search: lock: %v\n", err)
-		return 1
-	}
-	defer unix.Flock(int(lock.Fd()), unix.LOCK_UN)
-
-	var payload websearch.Payload
-	attempts := 1 + len(websearch.RetryBackoff)
-	client := &http.Client{}
-	for attempt := 0; attempt < attempts; attempt++ {
-		last, err := cache.LastCall()
-		if err != nil {
-			fmt.Fprintf(os.Stderr, "web/search: cache: %v\n", err)
-			return 1
-		}
-		if delay := websearch.WaitFor(last, float64(time.Now().Unix()), websearch.MinInterval); delay > 0 {
-			time.Sleep(time.Duration(delay * float64(time.Second)))
-		}
-		if err := cache.MarkCall(float64(time.Now().Unix())); err != nil {
-			fmt.Fprintf(os.Stderr, "web/search: cache: %v\n", err)
-			return 1
-		}
-		payload, err = websearch.Fetch(client, conf, query, params, time.Duration(timeout)*time.Second)
-		if err != nil {
-			fmt.Fprintf(os.Stderr, "request failed: %v\n", err)
-			return 3
-		}
-		if websearch.Classify(payload) == websearch.StatusOK {
-			break
-		}
-		if attempt < len(websearch.RetryBackoff) {
-			time.Sleep(time.Duration(websearch.RetryBackoff[attempt] * float64(time.Second)))
-		}
-	}
-
-	if websearch.Classify(payload) == websearch.StatusOK {
-		if err := cache.Put(key, payload, float64(time.Now().Unix())); err != nil {
-			fmt.Fprintf(os.Stderr, "web/search: cache: %v\n", err)
-		}
-	}
-	out := websearch.Project(payload, limit, websearch.DefaultSnippetChars)
-	code := writeOut(out, jsonOut)
-	if out.Status != websearch.StatusOK && code == 0 {
-		return 3
-	}
-	return code
-}
-
-func writeOut(out websearch.Output, jsonOut bool) int {
-	if jsonOut {
-		enc := json.NewEncoder(os.Stdout)
-		enc.SetIndent("", "  ")
-		enc.SetEscapeHTML(false)
-		if err := enc.Encode(out); err != nil {
-			return 1
-		}
-		if out.Status != websearch.StatusOK {
-			return 3
-		}
-		return 0
-	}
-	fmt.Print(out.YAML())
-	if out.Status != websearch.StatusOK {
-		return 3
-	}
-	return 0
-}

compose.yaml

@@ -1,137 +1,66 @@
 # 2dph — docker composition
 #
-#   docker compose up -d brain                  # API (Zig CGO serve)
+#   docker compose run --rm brain index                     # rebuild graph
-#   docker compose --profile index run --rm index   # Python rebuild
+#   docker compose run --rm brain search "Matrix fed"       # one-shot query
-#   docker compose --profile picoclaw up brain-mcp
+#   docker compose run --rm brain serve                     # async Go server
-#   docker compose --profile reasoner up -d reasoner   # CPU Ollama :11435
+#   docker compose up brain-watch                           # auto re-index
-#   docker compose --profile searxng up -d
 #
-# Secrets never baked in: search.env + db-profiles.yml from ~/.config/brain.
+# Caching: the 128M model (HF_HOME) and kb.lbug (VAR_DIR) live in named
+# volumes, so rebuilds never redownload the model or re-derive the graph.
+# Secrets are never baked into the image: search.env + db-profiles.yml mount
+# read-only from ~/.config/brain.
 
 name: 2dph
 
 services:
   brain:
-    image: ghcr.io/eslider/2dph:api
+    image: ghcr.io/eslider/2dph:latest
     build:
       context: .
       dockerfile: Dockerfile
-      target: api
       cache_from:
         - ghcr.io/eslider/2dph:cache
-    command: ["serve"]
+    command: ["brain", "search", "help"]
     environment: &env
       HF_HOME: /data/hf
       BRAIN_SEARCH_CACHE: /data/cache/web-search.sqlite
       BRAIN_DB_PROFILES: /secret/db-profiles.yml
       BRAIN_SEARCH_ENV: /secret/search.env
-      KB_ROOT: /data
+      KB_SEARCH_CMD: /app/bin/kb/search
       KB_WORKERS: "4"
-      KB_PORT: "8630"
     volumes:
       - kb-model:/data/hf
       - kb-var:/data
+      # corpus is read-only on the host, never written from the container
+      - ..:/corpus:ro
       - ~/.config/brain:/secret:ro
-    ports:
-      - "127.0.0.1:8630:8630"
     read_only: true
     tmpfs:
       - /tmp
     healthcheck:
-      test: ["CMD", "wget", "-qO-", "http://127.0.0.1:8630/health"]
+      test: ["CMD", "python3", "-c", "import ladybug, model2vec, mistune; print('ok')"]
       interval: 30s
       timeout: 5s
       retries: 3
     restart: unless-stopped
     stop_grace_period: 20s
 
+  # watcher: re-index on corpus file change (watchdog script)
   brain-watch:
-    image: ghcr.io/eslider/2dph:api
+    image: ghcr.io/eslider/2dph:latest
     environment: *env
     volumes:
       - kb-model:/data/hf
       - kb-var:/data
       - ..:/corpus:ro
       - ~/.config/brain:/secret:ro
-    command: ["watch", "/corpus"]
+    command: ["brain", "watch", "/corpus"]
     read_only: true
     tmpfs:
       - /tmp
     restart: unless-stopped
     stop_grace_period: 20s
 
-  # Python write path (Ladybug rebuild). Not in the API image.
-  #   docker compose --profile index run --rm index
-  index:
-    profiles: ["index"]
-    image: ghcr.io/eslider/2dph:index
-    build:
-      context: .
-      dockerfile: Dockerfile
-      target: index
-    environment:
-      HF_HOME: /data/hf
-      KB_PY: python3
-    volumes:
-      - kb-model:/data/hf
-      - kb-var:/app/var
-      - ..:/corpus:ro
-      - ~/.config/brain:/secret:ro
-    command: ["index"]
-    read_only: true
-    tmpfs:
-      - /tmp
-
-  # Optional local SearXNG (D3). Skip if BRAIN_SEARCH_URL already points at a
-  # live instance — do not run a second copy on that host.
-  #   SEARXNG_SECRET=$(openssl rand -hex 32) docker compose --profile searxng up -d
-  searxng:
-    profiles: ["searxng"]
-    image: docker.io/searxng/searxng:2026.8.10-0a118066d
-    ports:
-      - "127.0.0.1:8888:8080"
-    environment:
-      SEARXNG_SECRET: ${SEARXNG_SECRET:-}
-    volumes:
-      - ./deploy/searxng/settings.yml:/etc/searxng/settings.yml:ro
-      - ./deploy/searxng/limiter.toml:/etc/searxng/limiter.toml:ro
-    restart: unless-stopped
-
-  # MCP endpoint for an external agent (PicoClaw is not shipped here).
-  #   docker compose --profile picoclaw up brain-mcp
-  brain-mcp:
-    profiles: ["picoclaw"]
-    image: ghcr.io/eslider/2dph:api
-    environment: *env
-    volumes:
-      - kb-model:/data/hf
-      - kb-var:/data
-      - ~/.config/brain:/secret:ro
-    command: ["serve"]
-    ports:
-      - "127.0.0.1:8630:8630"
-    read_only: true
-    tmpfs:
-      - /tmp
-    restart: unless-stopped
-
-  # CPU OpenAI-compatible sidecar (D18). Weights are pulled at runtime, not
-  # baked into the 2dph image. Does not touch host Ollama on :11434.
-  #   docker compose --profile reasoner up -d reasoner
-  #   docker compose --profile reasoner exec reasoner ollama pull qwen3.5:9b
-  reasoner:
-    profiles: ["reasoner"]
-    image: docker.io/ollama/ollama:latest
-    environment:
-      OLLAMA_NUM_GPU: "0"
-      OLLAMA_HOST: "0.0.0.0:11434"
-    ports:
-      - "127.0.0.1:11435:11434"
-    volumes:
-      - reasoner-ollama:/root/.ollama
-    restart: unless-stopped
-
 volumes:
   kb-model:
   kb-var:
-  reasoner-ollama:

deploy/picoclaw/mcp.json.example

@@ -1,8 +0,0 @@
-{
-  "mcpServers": {
-    "2dph": {
-      "url": "http://127.0.0.1:8630/mcp",
-      "description": "2dph fact gate. Tool order: search → get → audit. throttled is not absence."
-    }
-  }
-}

deploy/searxng/limiter.toml

@@ -1,7 +0,0 @@
-[botdetection.ip_lists]
-# RFC1918 only. Do not copy a live instance egress IP into git.
-pass_ip = [
-  "10.0.0.0/8",
-  "172.16.0.0/12",
-  "192.168.0.0/16",
-]

deploy/searxng/settings.yml

@@ -1,28 +0,0 @@
-use_default_settings: true
-
-general:
-  instance_name: "2dph"
-
-search:
-  formats:
-    - html
-    - json
-  suspended_times:
-    SearxEngineCaptcha: 300
-    SearxEngineTooManyRequests: 120
-    SearxEngineAccessDenied: 300
-
-server:
-  limiter: true
-  image_proxy: false
-  # secret_key comes from SEARXNG_SECRET (never commit a real secret)
-
-engines:
-  - name: bing
-    disabled: false
-  - name: google
-    disabled: false
-  - name: duckduckgo
-    disabled: false
-  - name: wikipedia
-    disabled: false

docs/README.md

@@ -1,38 +1,11 @@
----
+# 2dph (deductionphile)
-type: reference
-status: current
-related:
-  - docs/runbook.md
-  - docs/design.md
-  - PLAN.md
-  - docs/roadmap.md
----
 
-# 2dph docs (Diataxis)
+Evidence-first knowledge graph + hybrid RAG over the operational
-
+Brain/ops/eSlider stack. Facts need proof or they are
-Evidence-first knowledge graph. Facts need proof or they are
 `(not confirmed)`.
 
-| Type | Doc |
+- [PLAN.md](../PLAN.md) — decisions, execution order, open questions (v2)
-|------|-----|
+- [design](design.md) — schema, deduction model, sources
-| tutorial / howto | [runbook](runbook.md) — run anywhere (uv, Go, Docker) |
+- [Gitea issues](https://git.produktor.io/eSlider/2dph/issues) — work board (origin)
-| explanation | [design](design.md) — two roots, deduction, D17/D20/D18 |
-| explanation | [roadmap](roadmap.md) — gap to v1 (epic #16) |
-| howto | [picoclaw](picoclaw.md) — MCP agent profile |
-| howto | [reasoner](reasoner.md) — CPU bake-off (D18) |
-| reference | [PLAN.md](../PLAN.md) — decisions D1–D21 |
 
-Decisions the public face must name: **D3** SearXNG compose, **D6** Go service /
+Published docs live here and mirror the project state.
-Python write sidecar, **D14** `bin/{subject}/{method}.go`, **D15** Gitea origin,
-**D17** assertion gate (facts → info → web), **D18** pluggable reasoner.
-
-Search: `bin/brain/search.go "query"` (HTTP: `bin/brain/serve.go` —
-`/health` `/search` `/get` `/stats` `/audit` `/ingest`). `--hop` is
-not a walk; the flag errors. Schema has `FROM_FILE`; search does not
-use it ([#17](https://git.produktor.io/eSlider/2dph/issues/17)).
-
-Work board: [Gitea issues](https://git.produktor.io/eSlider/2dph/issues)
-([epic #16](https://git.produktor.io/eSlider/2dph/issues/16)).
-PRs and CI: GitHub [`eSlider/2dph`](https://github.com/eSlider/2dph).
-
-Published docs live here and match live commands.

docs/chat-import-plan.md

@@ -15,10 +15,9 @@ OO_CLI                     (default: $HOME/go/bin/oo)
 ## Quick reference
 
 ```
-./bin/chats/sync.go telegram --limit 100
+./bin/chat sync telegram --limit 100
-./bin/chats/import.go
+./bin/chat import
-./bin/chats/facts.go
+./bin/chat index
-./bin/chats/apply.go --dry-run
+./bin/chat facts
+./bin/chat apply --dry-run
 ```
-
-JSONL → markdown only. Brain ingest is `bin/brain/index.go` (not a `chats index`).

docs/crm-associations-proof.md

@@ -0,0 +1,33 @@
+# CRM association proof (oo CLI ↔ corpus)
+
+Proven with `oo` (eslider/go-onlyoffice) against the OnlyOffice portal
+(`office.produktor.io`). Portal CRM is the SSOT for company ↔ person ↔
+project associations; the corpus SoT (`eslider/cv/projects/knowledge-mesh-seed.yaml`)
+is the second, independent source. Facts that can be backed by both are
+written to the brain under `root=facts` by `bin/facts/crm`.
+
+## What was verified
+
+- Logical counts (portal MySQL): 1300 contacts = 897 persons + 404 companies,
+  198 projects, 998 deals, 939 project↔contact links.
+- Every client company linked to a project has ≥1 person underneath.
+- Every person `company_id` resolves to an existing company.
+- Corpus org list (9) maps 1:1 onto CRM companies:
+  ProProdukt SL / produktor.io, Dyvenia, Immowelt AG, WhereGroup,
+  Keynote SIGOS, D2S/SYSTEMS, GRID, Pack und Cup, Markets Platform.
+- 78 person↔company association facts written to the brain
+  (`how=crm-crosscheck`, `type=association`). Recall@5 in `bin/kb/eval` = 1.0.
+
+## Mistakes found
+
+| # | Mistake | Fix |
+|---|---------|-----|
+| 1 | Duplicate legal entity `GoldenRatio.Exchange` (contact 759) vs `Golden Ratio Exchange` (763); 3 deals (211, 287, 559) were linked to 759 | `oo contacts merge 759 763` — 763 kept, 759 removed, deal links re-pointed to 763 |
+| 2 | `env/`-wide: OnlyOffice creds file used wrong UX (user `eslider`, password with `$2` suffix) making `oo` auth fail | `.env` fixed to `eslider@gmail.com` + clean password; `.env` stays gitignored |
+
+## Gates after fix
+
+- `uv run python -m unittest discover -s bin/tools -t .` → 26 tests OK
+- `bin/facts/audit self` + `bin/facts/audit db` → ok
+- `bin/kb/eval` → recall@5 = 1.0
+- `go test ./...` (bin/server + bin/watch) → ok

docs/design.md

@@ -1,12 +1,3 @@
----
-type: explanation
-status: current
-related:
-  - docs/README.md
-  - docs/runbook.md
-  - docs/roadmap.md
----
-
 # Design — facts, info, deduction
 
 ## Two roots, one transaction
@@ -26,17 +17,14 @@ as one consistent state.
 ## Deduction search
 
 ```
-bin/brain/search.go "question"
+bin/kb/search "question"
   1. facts root   — confirmed answers only   → return with evidence links
   2. info  root   — supporting narrative     → snippets, marked (not confirmed)
   3. web-search   — second independent source → upgrade hypothesis to confirmed
-     (`web` block from `bin/web/search.go` when no facts hit; status `throttled`
-     is not evidence of absence; `--no-web` / `--root` skip it)
 ```
 
-`--hop` is not implemented. `FROM_FILE` / `HAS_VERSION` exist in schema;
+`--hop N` follows graph edges (sibling leaves under a heading, owning file,
-search does not walk them ([#17](https://git.produktor.io/eSlider/2dph/issues/17)).
+`related:` files, vector-neighbour leaves) — the deduction walk.
-The flag is an error; it is not a graph walk.
 
 ## Who / What / How / Where / When + evidence
 
@@ -58,8 +46,7 @@ Every assertion edge carries:
 Content leafs: `sha256`, `observed_at`, `source_rev`, `confidence`. Stale = a
 file changed on disk (git HEAD/mtime) after its last observed `source_rev`.
 `File-[:HAS_VERSION]->Commit-[:AUTHORED]->Person` records the history of every
-content leaf. Commit records come from `bin/git/import.go` (go-git, no git
+content leaf.
-binary); conversion prints leafs, brain write is `bin/brain/index.go`.
 
 `bin/facts/audit stale` flags leafs whose observed revision is behind the
 corpus HEAD.
@@ -72,33 +59,3 @@ corpus HEAD.
 
 Confirmed = A×B or B×C agreement. Single source = hypothesis + `(not confirmed)`.
 Conflicting pairings (≥2 yes vs ≥2 no) = hypothesis (OQ1 → v2 resolution).
-
-## Read path
-
-`bin/brain/get.go`, `stats.go`, and `eval.go` call `internal/brain` with cgo
-(`system_ladybug`), compiled by **Zig** (`bin/cgo/zcc`, D21), not gcc.
-They do not exec Python. Control questions for recall@5 live in
-`internal/brain/rank` so CI can test the table without libladybug.
-Python `bin/kb/{get,stats,eval}` remain for GitHub Actions until the runner
-fetches Zig + libs (`bin/cgo/zig`). Incremental write is `bin/kb/add`
-(`bin/brain/add.go`). Bulk index/write is still `bin/kb/index`
-(`docker compose --profile index`).
-
-## Agent API (D20)
-
-`bin/brain/serve.go` exposes the same `internal/httpapi.Ops` table as OpenAPI
-(`GET /openapi.json`) and MCP (`POST /mcp` JSON-RPC `tools/list` +
-`tools/call`). Tool names match paths: `search`, `get`, `stats`, `audit`,
-`ingest` (add a leaf; omit body for the CLI hint).
-Agents should use these endpoints instead of shebang CLIs.
-
-## Reasoner (D18)
-
-Pluggable OpenAI-compatible URL. RAM: `Qwen/Qwen3.5-9B`. Quality:
-`prism-ml/Bonsai-27B-gguf` or `Qwen/Qwen3.6-27B`. No official Qwen3.6-9B.
-CPU sidecar: compose profile `reasoner` (`OLLAMA_NUM_GPU=0`,
-`127.0.0.1:11435`). Bake-off: `bin/reasoner/bakeoff.go`. Weights stay out
-of the 2dph image. See [docs/reasoner.md](reasoner.md).
-
-Gap to v1 (hops, corpus, CI eval): [roadmap](roadmap.md),
-[epic #16](https://git.produktor.io/eSlider/2dph/issues/16).

docs/picoclaw.md

@@ -1,18 +0,0 @@
-# PicoClaw profile (reference agent)
-
-2dph is the memory/fact gate. PicoClaw (or any MCP client) is the agent loop
-and is **not** shipped in this repo.
-
-```bash
-docker compose --profile picoclaw up brain-mcp
-```
-
-The API listens on `127.0.0.1:8630`. Point the agent at
-`http://127.0.0.1:8630/mcp` using [deploy/picoclaw/mcp.json.example](../deploy/picoclaw/mcp.json.example).
-
-OpenAPI: `GET http://127.0.0.1:8630/openapi.json`.
-
-Before a factual reply: `search` → `get` → `audit`. `throttled` is not a
-negative finding. See `skills/picoclaw/SKILL.md`.
-
-No Cursor required. A live PicoClaw binary/image is an operator choice.

docs/reasoner.md

@@ -1,69 +0,0 @@
-# Reasoner bake-off (D18)
-
-Pluggable OpenAI-compatible URL. 2dph does not ship weights. PicoClaw is
-not in this repo; the bake-off hits the same tool names PicoClaw would
-(`search` → `get` → `audit` from `internal/httpapi.Ops`).
-
-```bash
-docker compose --profile reasoner up -d reasoner
-docker compose --profile reasoner exec reasoner ollama pull qwen3.5:9b
-REASONER_BASE_URL=http://127.0.0.1:11435/v1 REASONER_MODEL=qwen3.5:9b \
-  ./bin/reasoner/bakeoff.go --json
-```
-
-Host Ollama on `:11434` is left alone. This sidecar binds `127.0.0.1:11435`
-with `OLLAMA_NUM_GPU=0` (CPU). Measure RSS (`/api/ps` `size`), not VRAM.
-
-If Compose cannot allocate a project network (Docker IPAM pool exhausted),
-the same sidecar is:
-
-```bash
-docker run -d --name 2dph-reasoner \
-  -e OLLAMA_NUM_GPU=0 \
-  -p 127.0.0.1:11435:11434 \
-  -v 2dph-reasoner-ollama:/root/.ollama \
-  ollama/ollama:latest
-```
-
-## Real Hugging Face ids
-
-| Role | HF id | Ollama tag (this bake-off) |
-|------|-------|----------------------------|
-| RAM / 9B | `Qwen/Qwen3.5-9B` | `qwen3.5:9b` |
-| Quality 27B (CPU) | `prism-ml/Bonsai-27B-gguf` (derived from Qwen3.6-27B) | `MichelRosselli/bonsai-27b:Q1_0` |
-| Quality 27B (full) | `Qwen/Qwen3.6-27B` | not pulled on this CPU box |
-
-There is **no official Qwen3.6-9B**. Do not invent that id.
-
-Qwen3.5-9B has documented upstream tool-call XML bugs. A 9B win on tools
-is only claimed if this bake-off records OpenAI `tool_calls` (not
-`<tool_call>` XML in `content`).
-
-The 2dph API image does not `COPY` GGUF/safetensors. Pull at runtime into
-the `reasoner-ollama` volume.
-
-## Live CPU run
-
-Host sidecar: Ollama **0.32.9**, `OLLAMA_NUM_GPU=0`, `127.0.0.1:11435`,
-`device: cpu`, `vram_mb: 0`. Date: 2026-08-13. Same three prompts
-(`search` / `get` / `audit`). PicoClaw binary was not used; the OpenAI
-tools payload is the surface it would send.
-
-| Model | HF id | tool_call | xml_leak | rss_mb | latency_ms (search/get/audit) |
-|-------|-------|-----------|----------|--------|-------------------------------|
-| `qwen3.5:9b` | `Qwen/Qwen3.5-9B` | 3/3 | 0 | 5790 | 50059 / 51678 / 31980 |
-| `MichelRosselli/bonsai-27b:Q1_0` | `prism-ml/Bonsai-27B-gguf` | 3/3 | 0 | 21951 | 327702 / 166830 / 119808 |
-| `Qwen/Qwen3.6-27B` | `Qwen/Qwen3.6-27B` | not loaded | — | — | too heavy for this CPU box |
-
-Both loaded models emitted OpenAI `tool_calls` (not `<tool_call>` XML) on
-this runtime. **Do not claim 9B is better at tools** — the score is tied
-at 3/3. 9B is smaller and faster. Bonsai RSS includes weights + KV
-(`size` from `/api/ps`); first Bonsai prompt includes cold load.
-
-Re-run:
-
-```bash
-REASONER_BASE_URL=http://127.0.0.1:11435/v1 REASONER_MODEL=qwen3.5:9b \
-  ./bin/reasoner/bakeoff.go --json
-REASONER_MODEL=MichelRosselli/bonsai-27b:Q1_0 ./bin/reasoner/bakeoff.go --json
-```

docs/roadmap.md

@@ -1,61 +0,0 @@
----
-type: explanation
-status: current
-related:
-  - PLAN.md
-  - docs/design.md
-  - docs/runbook.md
----
-
-# 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](https://git.produktor.io/eSlider/2dph/issues/16).
-Milestone: [v1 detective brain](https://git.produktor.io/eSlider/2dph/milestone/12).
-Decisions: [PLAN.md](../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](https://git.produktor.io/eSlider/2dph/issues/15) lever/loop.
-[#14](https://git.produktor.io/eSlider/2dph/issues/14) `bin/brain/add.go` /
-`POST /ingest` (Python `kblib.add_leafs`; no Go upsert port).
-
-## Blockers
-
-```
-question
-    │
-    ├─ FTS + HNSW          ← in
-    ├─ facts / info roots  ← in
-    ├─ web (D17)           ← in
-    ├─ brain/add ACID      ← in
-    ├─ Cypher hop          ← #17  schema yes, search no
-    └─ facts+chats corpus  ← #18
-```
-
-1. **[#17](https://git.produktor.io/eSlider/2dph/issues/17) hops** —
-   `Leaf-[:FROM_FILE]->File-[:HAS_VERSION]->Commit-[:AUTHORED]->Person`
-   exists; `--hop` still errors. Without a walk, D9/D10 are paper.
-2. **[#18](https://git.produktor.io/eSlider/2dph/issues/18) corpus** —
-   rebuild loads repo markdown + mail as `info`. `facts/extract` pairing
-   and `bin/chats` are not indexed. WhatsApp is a stub. PII stays in `var/`.
-3. **[#19](https://git.produktor.io/eSlider/2dph/issues/19) CI eval** —
-   recall SoT should be `bin/brain/eval.go` via Zig, not Python `bin/kb/eval`.
-
-## Not v1
-
-[#6](https://git.produktor.io/eSlider/2dph/issues/6) OCR (OQ2), OQ1
-contradiction resolution, OQ3 duckdb-md export, OQ4 YAML-first leafs.
-
-## Close epic #16 when
-
-- `--hop` stops erroring and runs a Cypher path from search hits
-- ops pairing + chat import land as leafs on rebuild
-- MCP tool order is documented and still gated by tests

docs/runbook.md

@@ -1,84 +0,0 @@
----
-type: howto
-status: current
-related:
-  - docs/README.md
-  - PLAN.md
----
-
-# Run 2dph (portable)
-
-No laptop-absolute paths. Config lives in env files under `$HOME/.config/brain/`
-(mode 0600), not in git.
-
-## Toolchain
-
-- Go (see `go.mod`)
-- Python 3.12 + [uv](https://docs.astral.sh/uv)
-- Optional: Docker, Zig CGO via `bin/cgo/zig` (not gcc)
-
-```bash
-uv venv .venv
-uv pip install -r requirements.lock.txt
-eval "$(bin/cgo/zig env)"   # when compiling Ladybug read tools
-go test ./...
-uv run python -m unittest discover -s bin/tools -t .
-```
-
-## Config
-
-| File / env | Purpose |
-|------------|---------|
-| `$BRAIN_SEARCH_ENV` (default `$HOME/.config/brain/search.env`) | `BRAIN_SEARCH_URL` (SearXNG). Optional Basic Auth. |
-| `$HOME/.config/brain/db-profiles.yml` | read-only Postgres profiles (OnlyOffice via tunnel) |
-
-If the host already runs SearXNG, point `BRAIN_SEARCH_URL` at it. Do not start
-a second copy (D3). Optional Compose instance:
-
-```bash
-SEARXNG_SECRET=$(openssl rand -hex 32) docker compose --profile searxng up -d
-```
-
-That binds `127.0.0.1:8888`. JSON format must stay enabled.
-
-## Index then search
-
-Write path is `bin/brain/add.go` for a leaf (or `POST /ingest`). Bulk
-corpus rebuild remains `bin/brain/index.go --rebuild` (Compose profile
-`index`). Do not DROP INDEX on Ladybug 0.19.
-
-```bash
-bin/brain/add.go --text "arc-1 runs Matrix" --root facts --source "compose.yml x docker ps"
-bin/brain/index.go --rebuild
-bin/brain/search.go "LadybugDB vector index"     # facts → info → web (D17)
-bin/brain/search.go "upstream flag" --no-web
-bin/brain/get.go <id> --body
-bin/brain/stats.go
-```
-
-`--hop` is not implemented. Empty web results are `throttled`, not absence.
-Gap to v1: [roadmap](roadmap.md) / [epic #16](https://git.produktor.io/eSlider/2dph/issues/16).
-
-Ladybug 0.19: never `DROP INDEX` FTS/VECTOR (ghost catalog). Fresh indexes =
-delete `var/kb.lbug` then `--rebuild`.
-
-## HTTP / MCP
-
-```bash
-docker compose up -d brain                       # :8630 Zig CGO serve
-docker compose --profile index run --rm index    # rebuild
-docker compose --profile picoclaw up brain-mcp   # MCP 127.0.0.1:8630
-```
-
-`GET /openapi.json`, `POST /mcp`. Agent tool order: `search` → `get` → `audit`.
-
-## Reasoner (optional, D18)
-
-CPU sidecar on `127.0.0.1:11435`. Weights are not in the 2dph image.
-
-```bash
-docker compose --profile reasoner up -d reasoner
-REASONER_BASE_URL=http://127.0.0.1:11435/v1 ./bin/reasoner/bakeoff.go --json
-```
-
-See [reasoner.md](reasoner.md).

go.mod

@@ -7,46 +7,19 @@ require (
 	github.com/arran4/golang-ical v0.3.5
 	github.com/chewxy/math32 v1.11.2
 	github.com/daulet/tokenizers v1.27.0
-	github.com/go-git/go-git/v5 v5.19.2
-	golang.org/x/sys v0.47.0
 	golang.org/x/text v0.40.0
-	modernc.org/sqlite v1.56.0
 )
 
 require (
-	dario.cat/mergo v1.0.0 // indirect
-	github.com/Microsoft/go-winio v0.6.2 // indirect
-	github.com/ProtonMail/go-crypto v1.1.6 // indirect
 	github.com/apache/arrow-go/v18 v18.6.0 // indirect
-	github.com/cloudflare/circl v1.6.3 // indirect
-	github.com/cyphar/filepath-securejoin v0.6.1 // indirect
-	github.com/dustin/go-humanize v1.0.1 // indirect
-	github.com/emirpasic/gods v1.18.1 // indirect
-	github.com/go-git/gcfg v1.5.1-0.20230307220236-3a3c6141e376 // indirect
-	github.com/go-git/go-billy/v5 v5.9.0 // indirect
 	github.com/goccy/go-json v0.10.6 // indirect
-	github.com/golang/groupcache v0.0.0-20241129210726-2c02b8208cf8 // indirect
 	github.com/google/flatbuffers v25.12.19+incompatible // indirect
 	github.com/google/uuid v1.6.0 // indirect
-	github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99 // indirect
-	github.com/kevinburke/ssh_config v1.2.0 // indirect
 	github.com/klauspost/compress v1.18.5 // indirect
 	github.com/klauspost/cpuid/v2 v2.3.0 // indirect
-	github.com/mattn/go-isatty v0.0.24 // indirect
-	github.com/ncruces/go-strftime v1.0.0 // indirect
 	github.com/pierrec/lz4/v4 v4.1.26 // indirect
-	github.com/pjbgf/sha1cd v0.6.0 // indirect
-	github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec // indirect
-	github.com/sergi/go-diff v1.3.2-0.20230802210424-5b0b94c5c0d3 // indirect
 	github.com/shopspring/decimal v1.4.0 // indirect
-	github.com/skeema/knownhosts v1.3.1 // indirect
-	github.com/xanzy/ssh-agent v0.3.3 // indirect
 	github.com/zeebo/xxh3 v1.1.0 // indirect
-	golang.org/x/crypto v0.53.0 // indirect
+	golang.org/x/exp v0.0.0-20260112195511-716be5621a96 // indirect
-	golang.org/x/exp v0.0.0-20260410095643-746e56fc9e2f // indirect
+	golang.org/x/sys v0.43.0 // indirect
-	golang.org/x/net v0.56.0 // indirect
-	gopkg.in/warnings.v0 v0.1.2 // indirect
-	modernc.org/libc v1.74.4 // indirect
-	modernc.org/mathutil v1.7.1 // indirect
-	modernc.org/memory v1.11.0 // indirect
 )

go.sum

@@ -1,184 +1,50 @@
-dario.cat/mergo v1.0.0 h1:AGCNq9Evsj31mOgNPcLyXc+4PNABt905YmuqPYYpBWk=
-dario.cat/mergo v1.0.0/go.mod h1:uNxQE+84aUszobStD9th8a29P2fMDhsBdgRYvZOxGmk=
 github.com/LadybugDB/go-ladybug v0.17.0 h1:RXDbkBjrbRmLdEbhGl4CLOIEzSt09gbP0n9UbKDEfwI=
 github.com/LadybugDB/go-ladybug v0.17.0/go.mod h1:GeIXmE8XyF5TFS94NAuTag7vgCC+no/HTBMRA6Rd5Cs=
-github.com/Microsoft/go-winio v0.5.2/go.mod h1:WpS1mjBmmwHBEWmogvA2mj8546UReBk4v8QkMxJ6pZY=
-github.com/Microsoft/go-winio v0.6.2 h1:F2VQgta7ecxGYO8k3ZZz3RS8fVIXVxONVUPlNERoyfY=
-github.com/Microsoft/go-winio v0.6.2/go.mod h1:yd8OoFMLzJbo9gZq8j5qaps8bJ9aShtEA8Ipt1oGCvU=
-github.com/ProtonMail/go-crypto v1.1.6 h1:ZcV+Ropw6Qn0AX9brlQLAUXfqLBc7Bl+f/DmNxpLfdw=
-github.com/ProtonMail/go-crypto v1.1.6/go.mod h1:rA3QumHc/FZ8pAHreoekgiAbzpNsfQAosU5td4SnOrE=
 github.com/andybalholm/brotli v1.2.1 h1:R+f5xP285VArJDRgowrfb9DqL18yVK0gKAW/F+eTWro=
 github.com/andybalholm/brotli v1.2.1/go.mod h1:rzTDkvFWvIrjDXZHkuS16NPggd91W3kUSvPlQ1pLaKY=
-github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be h1:9AeTilPcZAjCFIImctFaOjnTIavg87rW78vTPkQqLI8=
-github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be/go.mod h1:ySMOLuWl6zY27l47sB3qLNK6tF2fkHG55UZxx8oIVo4=
 github.com/apache/arrow-go/v18 v18.6.0 h1:GX/Jyd3R7mCLiECAwY9FWbbaYblie2WXBSz4Sw8fNpM=
 github.com/apache/arrow-go/v18 v18.6.0/go.mod h1:gm3MiPpY82fLYK5VKPB3WoJbsiLVDfT7flD5/vHReKw=
 github.com/apache/thrift v0.22.0 h1:r7mTJdj51TMDe6RtcmNdQxgn9XcyfGDOzegMDRg47uc=
 github.com/apache/thrift v0.22.0/go.mod h1:1e7J/O1Ae6ZQMTYdy9xa3w9k+XHWPfRvdPyJeynQ+/g=
-github.com/armon/go-socks5 v0.0.0-20160902184237-e75332964ef5 h1:0CwZNZbxp69SHPdPJAN/hZIm0C4OItdklCFmMRWYpio=
-github.com/armon/go-socks5 v0.0.0-20160902184237-e75332964ef5/go.mod h1:wHh0iHkYZB8zMSxRWpUBQtwG5a7fFgvEO+odwuTv2gs=
 github.com/arran4/golang-ical v0.3.5 h1:bbz6ld4dC+MmCKiFfOd6SkmIGnhNMBACZ485ULh7p9A=
 github.com/arran4/golang-ical v0.3.5/go.mod h1:OnguFgjN0Hmx8jzpmWcC+AkHio94ujmLHKoaef7xQh8=
 github.com/chewxy/math32 v1.11.2 h1:IufN08Zwr1NKuWfY+4Tz55BcwKmyKKNdOP7KtumehnM=
 github.com/chewxy/math32 v1.11.2/go.mod h1:dOB2rcuFrCn6UHrze36WSLVPKtzPMRAQvBvUwkSsLqs=
-github.com/cloudflare/circl v1.6.3 h1:9GPOhQGF9MCYUeXyMYlqTR6a5gTrgR/fBLXvUgtVcg8=
-github.com/cloudflare/circl v1.6.3/go.mod h1:2eXP6Qfat4O/Yhh8BznvKnJ+uzEoTQ6jVKJRn81BiS4=
-github.com/cyphar/filepath-securejoin v0.6.1 h1:5CeZ1jPXEiYt3+Z6zqprSAgSWiggmpVyciv8syjIpVE=
-github.com/cyphar/filepath-securejoin v0.6.1/go.mod h1:A8hd4EnAeyujCJRrICiOWqjS1AX0a9kM5XL+NwKoYSc=
 github.com/daulet/tokenizers v1.27.0 h1:MmFYAEDFz69s/nNQfHg59DWqHz3v94m99kEZ/JbL+s4=
 github.com/daulet/tokenizers v1.27.0/go.mod h1:YjFY1o1HGMyWkQgbXJDghhvke/yFDp2vGdIO2hYs4MQ=
-github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
-github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc h1:U9qPSI2PIWSS1VwoXQT9A3Wy9MM3WgvqSxFWenqJduM=
 github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
-github.com/dustin/go-humanize v1.0.1 h1:GzkhY7T5VNhEkwH0PVJgjz+fX1rhBrR7pRT3mDkpeCY=
-github.com/dustin/go-humanize v1.0.1/go.mod h1:Mu1zIs6XwVuF/gI1OepvI0qD18qycQx+mFykh5fBlto=
-github.com/elazarl/goproxy v1.7.2 h1:Y2o6urb7Eule09PjlhQRGNsqRfPmYI3KKQLFpCAV3+o=
-github.com/elazarl/goproxy v1.7.2/go.mod h1:82vkLNir0ALaW14Rc399OTTjyNREgmdL2cVoIbS6XaE=
-github.com/emirpasic/gods v1.18.1 h1:FXtiHYKDGKCW2KzwZKx0iC0PQmdlorYgdFG9jPXJ1Bc=
-github.com/emirpasic/gods v1.18.1/go.mod h1:8tpGGwCnJ5H4r6BWwaV6OrWmMoPhUl5jm/FMNAnJvWQ=
-github.com/gliderlabs/ssh v0.3.8 h1:a4YXD1V7xMF9g5nTkdfnja3Sxy1PVDCj1Zg4Wb8vY6c=
-github.com/gliderlabs/ssh v0.3.8/go.mod h1:xYoytBv1sV0aL3CavoDuJIQNURXkkfPA/wxQ1pL1fAU=
-github.com/go-git/gcfg v1.5.1-0.20230307220236-3a3c6141e376 h1:+zs/tPmkDkHx3U66DAb0lQFJrpS6731Oaa12ikc+DiI=
-github.com/go-git/gcfg v1.5.1-0.20230307220236-3a3c6141e376/go.mod h1:an3vInlBmSxCcxctByoQdvwPiA7DTK7jaaFDBTtu0ic=
-github.com/go-git/go-billy/v5 v5.9.0 h1:jItGXszUDRtR/AlferWPTMN4j38BQ88XnXKbilmmBPA=
-github.com/go-git/go-billy/v5 v5.9.0/go.mod h1:jCnQMLj9eUgGU7+ludSTYoZL/GGmii14RxKFj7ROgHw=
-github.com/go-git/go-git-fixtures/v4 v4.3.2-0.20231010084843-55a94097c399 h1:eMje31YglSBqCdIqdhKBW8lokaMrL3uTkpGYlE2OOT4=
-github.com/go-git/go-git-fixtures/v4 v4.3.2-0.20231010084843-55a94097c399/go.mod h1:1OCfN199q1Jm3HZlxleg+Dw/mwps2Wbk9frAWm+4FII=
-github.com/go-git/go-git/v5 v5.19.2 h1:wkfn7vOlUBu8ivAWKBWisTiwJK4jYHzTF8Ndv1LyGqY=
-github.com/go-git/go-git/v5 v5.19.2/go.mod h1:QqCBE1EFN5ddFmrliLQ3/ntRCUjZU3EJuwuB/jWEHjk=
 github.com/goccy/go-json v0.10.6 h1:p8HrPJzOakx/mn/bQtjgNjdTcN+/S6FcG2CTtQOrHVU=
 github.com/goccy/go-json v0.10.6/go.mod h1:oq7eo15ShAhp70Anwd5lgX2pLfOS3QCiwU/PULtXL6M=
-github.com/golang/groupcache v0.0.0-20241129210726-2c02b8208cf8 h1:f+oWsMOmNPc8JmEHVZIycC7hBoQxHH9pNKQORJNozsQ=
-github.com/golang/groupcache v0.0.0-20241129210726-2c02b8208cf8/go.mod h1:wcDNUvekVysuuOpQKo3191zZyTpiI6se1N1ULghS0sw=
 github.com/google/flatbuffers v25.12.19+incompatible h1:haMV2JRRJCe1998HeW/p0X9UaMTK6SDo0ffLn2+DbLs=
 github.com/google/flatbuffers v25.12.19+incompatible/go.mod h1:1AeVuKshWv4vARoZatz6mlQ0JxURH0Kv5+zNeJKJCa8=
-github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=
+github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
-github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=
+github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
-github.com/google/pprof v0.0.0-20260802141513-ef3492d7dac3 h1:LMLX+LgTNWpfvCBdFebv6EsYotImrt/Ppc5cXIriCSo=
-github.com/google/pprof v0.0.0-20260802141513-ef3492d7dac3/go.mod h1:jl5iWTm0/hd5PjEYEOuwAJ57L/CibdZfrqZ5XA5GrCk=
 github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
 github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
-github.com/hashicorp/golang-lru/v2 v2.0.7 h1:a+bsQ5rvGLjzHuww6tVxozPZFVghXaHOwFs4luLUK2k=
-github.com/hashicorp/golang-lru/v2 v2.0.7/go.mod h1:QeFd9opnmA6QUJc5vARoKUSoFhyfM2/ZepoAG6RGpeM=
-github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99 h1:BQSFePA1RWJOlocH6Fxy8MmwDt+yVQYULKfN0RoTN8A=
-github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99/go.mod h1:1lJo3i6rXxKeerYnT8Nvf0QmHCRC1n8sfWVwXF2Frvo=
-github.com/kevinburke/ssh_config v1.2.0 h1:x584FjTGwHzMwvHx18PXxbBVzfnxogHaAReU4gf13a4=
-github.com/kevinburke/ssh_config v1.2.0/go.mod h1:CT57kijsi8u/K/BOFA39wgDQJ9CxiF4nAY/ojJ6r6mM=
 github.com/klauspost/compress v1.18.5 h1:/h1gH5Ce+VWNLSWqPzOVn6XBO+vJbCNGvjoaGBFW2IE=
 github.com/klauspost/compress v1.18.5/go.mod h1:cwPg85FWrGar70rWktvGQj8/hthj3wpl0PGDogxkrSQ=
 github.com/klauspost/cpuid/v2 v2.3.0 h1:S4CRMLnYUhGeDFDqkGriYKdfoFlDnMtqTiI/sFzhA9Y=
 github.com/klauspost/cpuid/v2 v2.3.0/go.mod h1:hqwkgyIinND0mEev00jJYCxPNVRVXFQeu1XKlok6oO0=
-github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
-github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
-github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
-github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
-github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
-github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
-github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
-github.com/mattn/go-isatty v0.0.24 h1:tGZZoVgT/KiqK1c8ocVLeDS8BSWMRd47J3Lbz7vsReI=
-github.com/mattn/go-isatty v0.0.24/go.mod h1:nMCL3Zebbrt45jsMDgnfIwz6ydEQApk5oEI3HqDio6A=
-github.com/ncruces/go-strftime v1.0.0 h1:HMFp8mLCTPp341M/ZnA4qaf7ZlsbTc+miZjCLOFAw7w=
-github.com/ncruces/go-strftime v1.0.0/go.mod h1:Fwc5htZGVVkseilnfgOVb9mKy6w1naJmn9CehxcKcls=
-github.com/onsi/gomega v1.34.1 h1:EUMJIKUjM8sKjYbtxQI9A4z2o+rruxnzNvpknOXie6k=
-github.com/onsi/gomega v1.34.1/go.mod h1:kU1QgUvBDLXBJq618Xvm2LUX6rSAfRaFRTcdOeDLwwY=
 github.com/pierrec/lz4/v4 v4.1.26 h1:GrpZw1gZttORinvzBdXPUXATeqlJjqUG/D87TKMnhjY=
 github.com/pierrec/lz4/v4 v4.1.26/go.mod h1:EoQMVJgeeEOMsCqCzqFm2O0cJvljX2nGZjcRIPL34O4=
-github.com/pjbgf/sha1cd v0.6.0 h1:3WJ8Wz8gvDz29quX1OcEmkAlUg9diU4GxJHqs0/XiwU=
-github.com/pjbgf/sha1cd v0.6.0/go.mod h1:lhpGlyHLpQZoxMv8HcgXvZEhcGs0PG/vsZnEJ7H0iCM=
-github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
-github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
-github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 h1:Jamvg5psRIccs7FGNTlIRMkT8wgtp5eCXdBlqhYGL6U=
 github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
-github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec h1:W09IVJc94icq4NjY3clb7Lk8O1qJ8BdBEF8z0ibU0rE=
-github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo=
-github.com/rogpeppe/go-internal v1.14.1 h1:UQB4HGPB6osV0SQTLymcB4TgvyWu6ZyliaW0tI/otEQ=
-github.com/rogpeppe/go-internal v1.14.1/go.mod h1:MaRKkUm5W0goXpeCfT7UZI6fk/L7L7so1lCWt35ZSgc=
-github.com/sergi/go-diff v1.3.2-0.20230802210424-5b0b94c5c0d3 h1:n661drycOFuPLCN3Uc8sB6B/s6Z4t2xvBgU1htSHuq8=
-github.com/sergi/go-diff v1.3.2-0.20230802210424-5b0b94c5c0d3/go.mod h1:A0bzQcvG0E7Rwjx0REVgAGH58e96+X0MeOfepqsbeW4=
 github.com/shopspring/decimal v1.4.0 h1:bxl37RwXBklmTi0C79JfXCEBD1cqqHt0bbgBAGFp81k=
 github.com/shopspring/decimal v1.4.0/go.mod h1:gawqmDU56v4yIKSwfBSFip1HdCCXN8/+DMd9qYNcwME=
-github.com/sirupsen/logrus v1.7.0/go.mod h1:yWOB1SBYBC5VeMP7gHvWumXLIWorT60ONWic61uBYv0=
-github.com/skeema/knownhosts v1.3.1 h1:X2osQ+RAjK76shCbvhHHHVl3ZlgDm8apHEHFqRjnBY8=
-github.com/skeema/knownhosts v1.3.1/go.mod h1:r7KTdC8l4uxWRyK2TpQZ/1o5HaSzh06ePQNxPwTcfiY=
-github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
-github.com/stretchr/testify v1.2.2/go.mod h1:a8OnRcib4nhh0OaRAV+Yts87kKdq0PP7pXfy6kDkUVs=
-github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
 github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U=
 github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=
-github.com/xanzy/ssh-agent v0.3.3 h1:+/15pJfg/RsTxqYcX6fHqOXZwwMP+2VyYWJeWM2qQFM=
-github.com/xanzy/ssh-agent v0.3.3/go.mod h1:6dzNDKs0J9rVPHPhaGCukekBHKqfl+L3KghI1Bc68Uw=
 github.com/zeebo/assert v1.3.0 h1:g7C04CbJuIDKNPFHmsk4hwZDO5O+kntRxzaUoNXj+IQ=
 github.com/zeebo/assert v1.3.0/go.mod h1:Pq9JiuJQpG8JLJdtkwrJESF0Foym2/D9XMU5ciN/wJ0=
 github.com/zeebo/xxh3 v1.1.0 h1:s7DLGDK45Dyfg7++yxI0khrfwq9661w9EN78eP/UZVs=
 github.com/zeebo/xxh3 v1.1.0/go.mod h1:IisAie1LELR4xhVinxWS5+zf1lA4p0MW4T+w+W07F5s=
-golang.org/x/crypto v0.0.0-20220622213112-05595931fe9d/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
+golang.org/x/exp v0.0.0-20260112195511-716be5621a96 h1:Z/6YuSHTLOHfNFdb8zVZomZr7cqNgTJvA8+Qz75D8gU=
-golang.org/x/crypto v0.53.0 h1:QZ4Muo8THX6CizN2vPPd5fBGHyogrdK9fG4wLPFUsto=
+golang.org/x/exp v0.0.0-20260112195511-716be5621a96/go.mod h1:nzimsREAkjBCIEFtHiYkrJyT+2uy9YZJB7H1k68CXZU=
-golang.org/x/crypto v0.53.0/go.mod h1:DNLU434OwVakk9PzuwV8w62mAJpRJL3vsgcfp4Qnsio=
+golang.org/x/sys v0.43.0 h1:Rlag2XtaFTxp19wS8MXlJwTvoh8ArU6ezoyFsMyCTNI=
-golang.org/x/exp v0.0.0-20260410095643-746e56fc9e2f h1:W3F4c+6OLc6H2lb//N1q4WpJkhzJCK5J6kUi1NTVXfM=
+golang.org/x/sys v0.43.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
-golang.org/x/exp v0.0.0-20260410095643-746e56fc9e2f/go.mod h1:J1xhfL/vlindoeF/aINzNzt2Bket5bjo9sdOYzOsU80=
-golang.org/x/mod v0.37.0 h1:vF1DjpVEshcIqoEaauuHebaLk1O1forxjxBaVn884JQ=
-golang.org/x/mod v0.37.0/go.mod h1:m8S8VeM9r4dzDwjrKO0a1sZP3YjeMamRRlD+fmR2Q/0=
-golang.org/x/net v0.0.0-20211112202133-69e39bad7dc2/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
-golang.org/x/net v0.56.0 h1:Rw8j/hFzGvJUZwNBXnAtf5sVDVt+65SK2C7IxCxZt5o=
-golang.org/x/net v0.56.0/go.mod h1:D3Ku6r+V6JROoZK144D2XfMHFcMq/0zSfLelVTCFKec=
-golang.org/x/sync v0.22.0 h1:SZjpbeLmrCk4xhRSZFNZW5gFUeCeFgjekvI/+gfScek=
-golang.org/x/sync v0.22.0/go.mod h1:9xrNwdLfx4jkKbNva9FpL6vEN7evnE43NNNJQ2LF3+0=
-golang.org/x/sys v0.0.0-20191026070338-33540a1f6037/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20210124154548-22da62e12c0c/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.0.0-20220715151400-c0bba94af5f8/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.47.0 h1:o7XGOvZQCADBQQ4Y7VNq2dRWQR7JmOUW8Kxx4ZsNgWs=
-golang.org/x/sys v0.47.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
-golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
-golang.org/x/term v0.44.0 h1:0rLvDRCtNj0gZkyIXhCyOb2OAzEhLVqc4B+hrsBhrmc=
-golang.org/x/term v0.44.0/go.mod h1:7ze4MdzUzLXpSAoFP1H0bOI9aXDqveSvatT5vKcFh2Y=
-golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.40.0 h1:Ub2Z6/xjgF1WrYQz2nuITOEegKFtiIy+rieRJ5lHZKs=
 golang.org/x/text v0.40.0/go.mod h1:hpnzDAfGV753zIKo+wk3u1bVKCGPbrnF7+7LBF/UHVY=
-golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
-golang.org/x/tools v0.47.0 h1:7Kn5x/d1svx/PzryTsqeoZN4TZwqeH5pGWjefhLi/1Q=
-golang.org/x/tools v0.47.0/go.mod h1:dFHnyTvFWY212G+h7ZY4Vsp/K3U4/7W9TyVaAul8uCA=
 gonum.org/v1/gonum v0.17.0 h1:VbpOemQlsSMrYmn7T2OUvQ4dqxQXU+ouZFQsZOx50z4=
 gonum.org/v1/gonum v0.17.0/go.mod h1:El3tOrEuMpv2UdMrbNlKEh9vd86bmQ6vqIcDwxEOc1E=
-gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
-gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
-gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
-gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
-gopkg.in/warnings.v0 v0.1.2 h1:wFXVbFY8DY5/xOe1ECiWdKCzZlxgshcYVNkBHstARME=
-gopkg.in/warnings.v0 v0.1.2/go.mod h1:jksf8JmL6Qr/oQM2OXTHunEvvTAsrWBLb6OOjuVWRNI=
-gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
-gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ=
 gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
 gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
-modernc.org/cc/v4 v4.29.1 h1:MKgdCV3WykTSPqpVrnxdEDS0HEd2FHpKZDzxzU5LyeI=
-modernc.org/cc/v4 v4.29.1/go.mod h1:OnovgIhbbMXMu1aISnJ0wvVD1KnW+cAUJkIrAWh+kVI=
-modernc.org/ccgo/v4 v4.34.6 h1:sBgfIwyN0TQ9C5hwIeuqyeAKyMWnbvj2fvpF4L11uzU=
-modernc.org/ccgo/v4 v4.34.6/go.mod h1:SZ8YcN9NG7XVsQYdm6jYBvi8PQP1qi+kqB6OhjqI3Fk=
-modernc.org/fileutil v1.4.0 h1:j6ZzNTftVS054gi281TyLjHPp6CPHr2KCxEXjEbD6SM=
-modernc.org/fileutil v1.4.0/go.mod h1:EqdKFDxiByqxLk8ozOxObDSfcVOv/54xDs/DUHdvCUU=
-modernc.org/gc/v2 v2.6.5 h1:nyqdV8q46KvTpZlsw66kWqwXRHdjIlJOhG6kxiV/9xI=
-modernc.org/gc/v2 v2.6.5/go.mod h1:YgIahr1ypgfe7chRuJi2gD7DBQiKSLMPgBQe9oIiito=
-modernc.org/gc/v3 v3.1.4 h1:2g65LGVSmFQrXeITAw97x7hCRvZFcyE1uDP+7Vng7JI=
-modernc.org/gc/v3 v3.1.4/go.mod h1:HFK/6AGESC7Ex+EZJhJ2Gni6cTaYpSMmU/cT9RmlfYY=
-modernc.org/goabi0 v0.2.0 h1:HvEowk7LxcPd0eq6mVOAEMai46V+i7Jrj13t4AzuNks=
-modernc.org/goabi0 v0.2.0/go.mod h1:CEFRnnJhKvWT1c1JTI3Avm+tgOWbkOu5oPA8eH8LnMI=
-modernc.org/libc v1.74.4 h1:fX1Omw4o2/1C2iRkkIsrQTasJQldLhRmuPreXLoWs9k=
-modernc.org/libc v1.74.4/go.mod h1:eeQAS9W3sZeKYMFubydxJpII9ybHWshk+7or7bLG9co=
-modernc.org/mathutil v1.7.1 h1:GCZVGXdaN8gTqB1Mf/usp1Y/hSqgI2vAGGP4jZMCxOU=
-modernc.org/mathutil v1.7.1/go.mod h1:4p5IwJITfppl0G4sUEDtCr4DthTaT47/N3aT6MhfgJg=
-modernc.org/memory v1.11.0 h1:o4QC8aMQzmcwCK3t3Ux/ZHmwFPzE6hf2Y5LbkRs+hbI=
-modernc.org/memory v1.11.0/go.mod h1:/JP4VbVC+K5sU2wZi9bHoq2MAkCnrt2r98UGeSK7Mjw=
-modernc.org/opt v0.2.0 h1:tGyef5ApycA7FSEOMraay9SaTk5zmbx7Tu+cJs4QKZg=
-modernc.org/opt v0.2.0/go.mod h1:03fq9lsNfvkYSfxrfUhZCWPk1lm4cq4N+Bh//bEtgns=
-modernc.org/sortutil v1.2.1 h1:+xyoGf15mM3NMlPDnFqrteY07klSFxLElE2PVuWIJ7w=
-modernc.org/sortutil v1.2.1/go.mod h1:7ZI3a3REbai7gzCLcotuw9AC4VZVpYMjDzETGsSMqJE=
-modernc.org/sqlite v1.56.0 h1:/D8e2RfFqoy/Zc6PuC76U28zFwmI/sYx1Kjm4yEn9e0=
-modernc.org/sqlite v1.56.0/go.mod h1:yCJ2cmAaIkHQ25oXWrF8H4O1lIfPYPR26yCEDj2P3pQ=
-modernc.org/strutil v1.2.1 h1:UneZBkQA+DX2Rp35KcM69cSsNES9ly8mQWD71HKlOA0=
-modernc.org/strutil v1.2.1/go.mod h1:EHkiggD70koQxjVdSBM3JKM7k6L0FbGE5eymy9i3B9A=
-modernc.org/token v1.1.0 h1:Xl7Ap9dKaEs5kLoOQeQmPWevfnk/DM5qcLcYlA8ys6Y=
-modernc.org/token v1.1.0/go.mod h1:UGzOrNV1mAFSEB63lOFHIpNRUVMvYTc6yu1SMY/XTDM=

internal/brain/http.go

@@ -1,171 +0,0 @@
-//go:build cgo && system_ladybug
-
-package brain
-
-import (
-	"bytes"
-	"context"
-	"encoding/json"
-	"fmt"
-	"os/exec"
-	"path/filepath"
-
-	"github.com/eSlider/2dph/internal/brain/rank"
-)
-
-// Ready opens the Ladybug file for the life of the serve process.
-func Ready() error {
-	return openBrain()
-}
-
-// HTTP is the in-process API used by bin/brain/serve.go.
-type HTTP struct{}
-
-func (HTTP) Search(ctx context.Context, query string, limit int) ([]byte, error) {
-	hits, err := searchHits(query, "", "", limit)
-	if err != nil {
-		return nil, err
-	}
-	for i := range hits {
-		if hits[i].Text != "" {
-			runes := []rune(hits[i].Text)
-			if len(runes) > 280 {
-				runes = runes[:280]
-			}
-			hits[i].Snippet = string(runes)
-		}
-	}
-	webOut := rank.Deduce(hits, query, "", false, func(q string) rank.SecondSource {
-		return lookupWeb(ctx, q)
-	})
-	var buf bytes.Buffer
-	enc := json.NewEncoder(&buf)
-	enc.SetEscapeHTML(false)
-	if err := enc.Encode(toJSONOut(hits, query, "", webOut)); err != nil {
-		return nil, err
-	}
-	return buf.Bytes(), nil
-}
-
-func (HTTP) Get(_ context.Context, id string, body bool) ([]byte, error) {
-	if conn == nil {
-		return nil, fmt.Errorf("brain not open")
-	}
-	stmt, err := conn.Prepare(
-		"MATCH (l:Leaf {id:$id}) RETURN l.id, l.text, l.root, l.confidence, l.source, l.type",
-	)
-	if err != nil {
-		return nil, err
-	}
-	defer stmt.Close()
-	res, err := conn.Execute(stmt, map[string]any{"id": id})
-	if err != nil {
-		return nil, err
-	}
-	if !res.HasNext() {
-		return nil, fmt.Errorf("no leaf %s", id)
-	}
-	row, err := res.Next()
-	if err != nil {
-		return nil, err
-	}
-	vals, err := row.GetAsSlice()
-	if err != nil || len(vals) < 6 {
-		return nil, fmt.Errorf("leaf row")
-	}
-	out := map[string]any{
-		"id":         fmt.Sprint(vals[0]),
-		"root":       fmt.Sprint(vals[2]),
-		"confidence": fmt.Sprint(vals[3]),
-		"source":     fmt.Sprint(vals[4]),
-		"type":       fmt.Sprint(vals[5]),
-	}
-	if body {
-		out["text"] = fmt.Sprint(vals[1])
-	}
-	return json.Marshal(out)
-}
-
-func (HTTP) Stats(context.Context) ([]byte, error) {
-	if conn == nil {
-		return nil, fmt.Errorf("brain not open")
-	}
-	res, err := conn.Query("MATCH (l:Leaf) RETURN l.root, count(*)")
-	if err != nil {
-		return nil, err
-	}
-	byRoot := map[string]int{}
-	total := 0
-	for res.HasNext() {
-		row, err := res.Next()
-		if err != nil {
-			return nil, err
-		}
-		vals, err := row.GetAsSlice()
-		if err != nil || len(vals) < 2 {
-			continue
-		}
-		n := int(asInt(vals[1]))
-		byRoot[fmt.Sprint(vals[0])] = n
-		total += n
-	}
-	return json.Marshal(map[string]any{"total": total, "by_root": byRoot, "db": dbPath()})
-}
-
-func (HTTP) Audit(context.Context) ([]byte, error) {
-	if conn == nil {
-		return nil, fmt.Errorf("brain not open")
-	}
-	res, err := conn.Query("MATCH (l:Leaf) RETURN l.root, l.confidence, count(*)")
-	if err != nil {
-		return nil, err
-	}
-	var rows []map[string]any
-	for res.HasNext() {
-		row, err := res.Next()
-		if err != nil {
-			return nil, err
-		}
-		vals, err := row.GetAsSlice()
-		if err != nil || len(vals) < 3 {
-			continue
-		}
-		rows = append(rows, map[string]any{
-			"root":       fmt.Sprint(vals[0]),
-			"confidence": fmt.Sprint(vals[1]),
-			"count":      asInt(vals[2]),
-		})
-	}
-	return json.Marshal(map[string]any{"status": "ok", "by_confidence": rows})
-}
-
-func (HTTP) Ingest(ctx context.Context, body []byte) ([]byte, error) {
-	if len(bytes.TrimSpace(body)) == 0 {
-		return json.Marshal(map[string]any{
-			"mode":    "add",
-			"command": "bin/brain/add.go",
-			"rebuild": "bin/brain/index.go --rebuild",
-		})
-	}
-	cmd := exec.CommandContext(ctx, filepath.Join(repoRoot(), "bin", "kb", "add"), "--json")
-	cmd.Stdin = bytes.NewReader(body)
-	cmd.Dir = repoRoot()
-	out, err := cmd.Output()
-	if err != nil {
-		return nil, fmt.Errorf("add: %w", err)
-	}
-	return out, nil
-}
-
-func asInt(v any) int64 {
-	switch n := v.(type) {
-	case int64:
-		return n
-	case int:
-		return int64(n)
-	case float64:
-		return int64(n)
-	default:
-		return 0
-	}
-}

internal/brain/modelid.go

@@ -1,3 +0,0 @@
-package brain
-
-const ModelID = "minishlab/potion-multilingual-128M"

internal/brain/rank/args.go

@@ -6,7 +6,7 @@ import (
 	"strings"
 )
 
-const Usage = `usage: bin/brain/search.go "query" [--root facts|info] [--repo REPO] [-n N] [--json] [--no-web]
+const Usage = `usage: bin/brain/search.go "query" [--root facts|info] [--repo REPO] [-n N] [--json]
        bin/brain/search.go serve [port]
        bin/brain/search.go --list-model`
 
@@ -17,7 +17,6 @@ type Options struct {
 	Limit     int
 	JSONOut   bool
 	ListModel bool
-	NoWeb     bool
 }
 
 // ParseArgs reads flags. Unknown flags are an error: silently dropping them
@@ -55,8 +54,6 @@ func ParseArgs(args []string) (Options, error) {
 			return opt, fmt.Errorf("--hop is not implemented yet (needs File/FROM_FILE edges)")
 		case "--json":
 			opt.JSONOut = true
-		case "--no-web":
-			opt.NoWeb = true
 		case "--list-model":
 			opt.ListModel = true
 		default:

internal/brain/rank/escalate.go

@@ -1,43 +0,0 @@
-package rank
-
-// SecondSource is the web-search block on a deduction answer.
-// Kept apart from graph hits so "ours" and "not ours" stay visible.
-type SecondSource struct {
-	Status  string            `json:"status"`
-	Note    string            `json:"note,omitempty"`
-	Cached  bool              `json:"cached,omitempty"`
-	Results []SecondSourceHit `json:"results,omitempty"`
-}
-
-type SecondSourceHit struct {
-	Rank    int    `json:"rank"`
-	Title   string `json:"title"`
-	URL     string `json:"url"`
-	Snippet string `json:"snippet"`
-	Engine  string `json:"engine"`
-}
-
-type WebFn func(query string) SecondSource
-
-// ShouldEscalate is true when the default deduction path has no facts hit.
-// `--root facts|info` is a single-root ask: do not mix in the web.
-func ShouldEscalate(hits []Hit, rootFilter string) bool {
-	if rootFilter != "" {
-		return false
-	}
-	for _, h := range hits {
-		if h.Root == "facts" {
-			return false
-		}
-	}
-	return true
-}
-
-// Deduce returns the second-source block, or nil when web must not run.
-func Deduce(hits []Hit, query, rootFilter string, noWeb bool, web WebFn) *SecondSource {
-	if noWeb || web == nil || !ShouldEscalate(hits, rootFilter) {
-		return nil
-	}
-	out := web(query)
-	return &out
-}

internal/brain/rank/escalate_test.go

@@ -1,78 +0,0 @@
-package rank
-
-import (
-	"strings"
-	"testing"
-)
-
-func TestShouldEscalateWhenNoFacts(t *testing.T) {
-	if !ShouldEscalate(nil, "") {
-		t.Fatal("empty local graph must escalate")
-	}
-	if !ShouldEscalate([]Hit{h("i", "info", "docs/a.md")}, "") {
-		t.Fatal("info-only must escalate (not confirmed)")
-	}
-}
-
-func TestShouldNotEscalateWhenFactsConfirm(t *testing.T) {
-	hits := []Hit{h("f", "facts", "docker ps x compose"), h("i", "info", "docs/a.md")}
-	if ShouldEscalate(hits, "") {
-		t.Fatal("facts hit is already confirmed; do not mix web")
-	}
-}
-
-func TestShouldNotEscalateWhenRootFilterSet(t *testing.T) {
-	if ShouldEscalate(nil, "facts") {
-		t.Fatal("--root facts must stay local")
-	}
-	if ShouldEscalate([]Hit{h("i", "info", "x")}, "info") {
-		t.Fatal("--root info must stay local")
-	}
-}
-
-func TestDeduceCallsWebOnlyWhenEscalating(t *testing.T) {
-	called := 0
-	web := func(q string) SecondSource {
-		called++
-		if q != "LadybugDB" {
-			t.Fatalf("query = %q", q)
-		}
-		return SecondSource{Status: "ok", Results: []SecondSourceHit{{Title: "t", URL: "http://example.com"}}}
-	}
-	got := Deduce([]Hit{h("i", "info", "x")}, "LadybugDB", "", false, web)
-	if called != 1 || got == nil || got.Status != "ok" {
-		t.Fatalf("got %+v called=%d", got, called)
-	}
-}
-
-func TestDeduceNilWhenFactsOrNoWeb(t *testing.T) {
-	web := func(string) SecondSource {
-		t.Fatal("web must not run")
-		return SecondSource{}
-	}
-	if Deduce([]Hit{h("f", "facts", "x")}, "q", "", false, web) != nil {
-		t.Fatal("facts")
-	}
-	if Deduce([]Hit{h("i", "info", "x")}, "q", "", true, web) != nil {
-		t.Fatal("--no-web")
-	}
-	if Deduce(nil, "q", "facts", false, web) != nil {
-		t.Fatal("--root facts")
-	}
-	if Deduce(nil, "q", "", false, nil) != nil {
-		t.Fatal("nil web fn")
-	}
-}
-
-func TestParseNoWeb(t *testing.T) {
-	opt, err := ParseArgs([]string{"query", "--no-web", "--json"})
-	if err != nil || !opt.NoWeb || !opt.JSONOut || opt.Query != "query" {
-		t.Fatalf("got %+v err=%v", opt, err)
-	}
-}
-
-func TestUsageNamesNoWeb(t *testing.T) {
-	if !strings.Contains(Usage, "--no-web") {
-		t.Fatalf("usage must name --no-web, got:\n%s", Usage)
-	}
-}

internal/brain/rank/evalq.go

@@ -1,16 +0,0 @@
-package rank
-
-// Eval control questions (recall@5). Kept here so CI can test the gate
-// table without ladybug cgo. The runner lives in internal/brain (cgo).
-const EvalRecallThreshold = 0.95
-
-type EvalQuestion struct {
-	Query    string
-	Fragment string
-}
-
-var EvalQuestions = []EvalQuestion{
-	{"hybrid search fts and vector", "BM25"},
-	{"eslider devops engineer", "DevOps"},
-	{"ladybugdb graph engine storage", "LadybugDB"},
-}

internal/brain/rank/evalq_test.go

@@ -1,17 +0,0 @@
-package rank
-
-import "testing"
-
-func TestEvalQuestionsAreThreeAndThreshold(t *testing.T) {
-	if EvalRecallThreshold != 0.95 {
-		t.Fatalf("threshold = %v", EvalRecallThreshold)
-	}
-	if len(EvalQuestions) != 3 {
-		t.Fatalf("questions = %d, want 3", len(EvalQuestions))
-	}
-	for _, q := range EvalQuestions {
-		if q.Query == "" || q.Fragment == "" {
-			t.Fatalf("empty control: %+v", q)
-		}
-	}
-}

internal/brain/read.go

@@ -1,281 +0,0 @@
-//go:build cgo && system_ladybug
-
-package brain
-
-import (
-	"encoding/json"
-	"fmt"
-	"os"
-	"sort"
-	"strings"
-	"unicode/utf8"
-
-	"github.com/eSlider/2dph/internal/brain/rank"
-)
-
-func MainGet(args []string) int {
-	id, body, jsonOut := "", false, false
-	for _, a := range args {
-		switch {
-		case a == "--body":
-			body = true
-		case a == "--json":
-			jsonOut = true
-		case a == "-h" || a == "--help":
-			fmt.Fprintln(os.Stderr, `usage: bin/brain/get.go <id> [--body] [--json]`)
-			return 0
-		case strings.HasPrefix(a, "-"):
-			fmt.Fprintf(os.Stderr, "brain/get: unknown flag %s\n", a)
-			return 2
-		default:
-			id = a
-		}
-	}
-	if id == "" {
-		fmt.Fprintln(os.Stderr, "brain/get: id required")
-		return 2
-	}
-	if err := openBrain(); err != nil {
-		fmt.Fprintf(os.Stderr, "open brain: %v\n", err)
-		return 1
-	}
-	defer closeBrain()
-	meta, text, err := lookupLeaf(id)
-	if err != nil {
-		fmt.Fprintf(os.Stderr, "brain/get: %v\n", err)
-		return 1
-	}
-	out := Dict{
-		{"id", meta["id"]},
-		{"root", meta["root"]},
-		{"confidence", meta["confidence"]},
-		{"source", meta["source"]},
-		{"type", meta["type"]},
-	}
-	if body {
-		out = append(out, KV{"text", text})
-	} else {
-		out = append(out, KV{"snippet", clip(text, 280)})
-	}
-	if jsonOut {
-		m := map[string]any{}
-		for _, kv := range out {
-			m[kv.K] = kv.V
-		}
-		enc := json.NewEncoder(os.Stdout)
-		enc.SetIndent("", "  ")
-		enc.SetEscapeHTML(false)
-		return b2i(enc.Encode(m))
-	}
-	fmt.Print(toYAML(out, 0))
-	return 0
-}
-
-func MainStats(args []string) int {
-	jsonOut := false
-	for _, a := range args {
-		switch a {
-		case "--json":
-			jsonOut = true
-		case "-h", "--help":
-			fmt.Fprintln(os.Stderr, `usage: bin/brain/stats.go [--json]`)
-			return 0
-		default:
-			if strings.HasPrefix(a, "-") {
-				fmt.Fprintf(os.Stderr, "brain/stats: unknown flag %s\n", a)
-				return 2
-			}
-		}
-	}
-	if err := openBrain(); err != nil {
-		fmt.Fprintf(os.Stderr, "open brain: %v\n", err)
-		return 1
-	}
-	defer closeBrain()
-	s, err := leafStats()
-	if err != nil {
-		fmt.Fprintf(os.Stderr, "brain/stats: %v\n", err)
-		return 1
-	}
-	if jsonOut {
-		enc := json.NewEncoder(os.Stdout)
-		enc.SetIndent("", "  ")
-		enc.SetEscapeHTML(false)
-		return b2i(enc.Encode(s))
-	}
-	by := s["by_root"].(map[string]int)
-	keys := make([]string, 0, len(by))
-	for k := range by {
-		keys = append(keys, k)
-	}
-	sort.Strings(keys)
-	byRoot := make(Dict, 0, len(keys))
-	for _, k := range keys {
-		byRoot = append(byRoot, KV{k, by[k]})
-	}
-	out := Dict{
-		{"total", s["total"]},
-		{"by_root", byRoot},
-		{"db", s["db"]},
-		{"model", s["model"]},
-	}
-	fmt.Print(toYAML(out, 0))
-	return 0
-}
-
-func MainEval(args []string) int {
-	jsonOut := false
-	for _, a := range args {
-		switch a {
-		case "--json":
-			jsonOut = true
-		case "-h", "--help":
-			fmt.Fprintln(os.Stderr, `usage: bin/brain/eval.go [--json]`)
-			return 0
-		default:
-			if strings.HasPrefix(a, "-") {
-				fmt.Fprintf(os.Stderr, "brain/eval: unknown flag %s\n", a)
-				return 2
-			}
-		}
-	}
-	if err := openBrain(); err != nil {
-		fmt.Fprintf(os.Stderr, "open brain: %v\n", err)
-		return 1
-	}
-	defer closeBrain()
-	recalled := 0
-	details := make([]any, 0, len(rank.EvalQuestions))
-	jsDetails := make([]map[string]any, 0, len(rank.EvalQuestions))
-	for _, q := range rank.EvalQuestions {
-		hits, err := queryFTS(q.Query, 5)
-		ok := false
-		if err == nil {
-			frag := strings.ToLower(q.Fragment)
-			for _, h := range hits {
-				if strings.Contains(strings.ToLower(h.Text), frag) {
-					ok = true
-					break
-				}
-			}
-		}
-		if ok {
-			recalled++
-		}
-		details = append(details, Dict{
-			{"q", q.Query},
-			{"fragment", q.Fragment},
-			{"in_top5", ok},
-		})
-		jsDetails = append(jsDetails, map[string]any{
-			"q": q.Query, "fragment": q.Fragment, "in_top5": ok,
-		})
-	}
-	n := len(rank.EvalQuestions)
-	recall := 0.0
-	if n > 0 {
-		recall = float64(recalled) / float64(n)
-	}
-	passed := recall >= rank.EvalRecallThreshold
-	if jsonOut {
-		enc := json.NewEncoder(os.Stdout)
-		enc.SetIndent("", "  ")
-		enc.SetEscapeHTML(false)
-		_ = enc.Encode(map[string]any{
-			"recall@5": round3(recall),
-			"passed":   passed,
-			"gate":     n,
-			"details":  jsDetails,
-		})
-	} else {
-		out := Dict{
-			{"recall@5", round3(recall)},
-			{"passed", passed},
-			{"gate", n},
-			{"details", details},
-		}
-		fmt.Print(toYAML(out, 0))
-	}
-	if !passed {
-		return 2
-	}
-	return 0
-}
-
-func lookupLeaf(id string) (map[string]string, string, error) {
-	if conn == nil {
-		return nil, "", fmt.Errorf("brain not open")
-	}
-	stmt, err := conn.Prepare(
-		"MATCH (l:Leaf {id:$id}) RETURN l.id, l.text, l.root, l.confidence, l.source, l.type",
-	)
-	if err != nil {
-		return nil, "", err
-	}
-	defer stmt.Close()
-	res, err := conn.Execute(stmt, map[string]any{"id": id})
-	if err != nil {
-		return nil, "", err
-	}
-	if !res.HasNext() {
-		return nil, "", fmt.Errorf("no leaf %s", id)
-	}
-	row, err := res.Next()
-	if err != nil {
-		return nil, "", err
-	}
-	vals, err := row.GetAsSlice()
-	if err != nil || len(vals) < 6 {
-		return nil, "", fmt.Errorf("leaf row")
-	}
-	meta := map[string]string{
-		"id":         fmt.Sprint(vals[0]),
-		"root":       fmt.Sprint(vals[2]),
-		"confidence": fmt.Sprint(vals[3]),
-		"source":     fmt.Sprint(vals[4]),
-		"type":       fmt.Sprint(vals[5]),
-	}
-	return meta, fmt.Sprint(vals[1]), nil
-}
-
-func leafStats() (map[string]any, error) {
-	if conn == nil {
-		return nil, fmt.Errorf("brain not open")
-	}
-	res, err := conn.Query("MATCH (l:Leaf) RETURN l.root, count(*)")
-	if err != nil {
-		return nil, err
-	}
-	byRoot := map[string]int{}
-	total := 0
-	for res.HasNext() {
-		row, err := res.Next()
-		if err != nil {
-			return nil, err
-		}
-		vals, err := row.GetAsSlice()
-		if err != nil || len(vals) < 2 {
-			continue
-		}
-		n := int(asInt(vals[1]))
-		byRoot[fmt.Sprint(vals[0])] = n
-		total += n
-	}
-	return map[string]any{
-		"total":   total,
-		"by_root": byRoot,
-		"db":      dbPath(),
-		"model":   ModelID,
-	}, nil
-}
-
-func clip(s string, n int) string {
-	if utf8.RuneCountInString(s) <= n {
-		return s
-	}
-	return string([]rune(s)[:n])
-}
-
-func round3(f float64) float64 {
-	return float64(int(f*1000+0.5)) / 1000
-}