docs: add edelweiss to GitHub safety rules

- bin/chats/: env-based paths, no /mnt/ /home/ hardcodes
- bin/edelweiss-pilot: remove curasoft, use DOCS_BASE env var
- bin/facts/crm: use KNOWLEDGE_MESH_SEED env var
- compose.edelweiss.yml: remove curasoft volumes, use DOCS_BASE
- docs/chat-import-plan.md: link to Gitea issue, no secrets
- bin/seed-edelweiss-facts.py: removed (curasoft-only)

.github/workflows/ci.yml

@@ -19,10 +19,6 @@ jobs:
         with:
           fetch-depth: 0
 
-      - uses: actions/setup-go@v5
-        with:
-          go-version-file: go.mod
-
       - name: Install uv
         uses: astral-sh/setup-uv@v6
         with:
@@ -36,20 +32,16 @@ jobs:
           bash -n bin/db/psql-yq
           bash -n bin/db/ssh-tunnel
           bash -n bin/docker-entrypoint
-          bash -n bin/kb/search
 
       - name: Python unit tests (offline, vendored tools)
         run: |
           uv run python -m unittest discover -s bin/tools -t .
 
-      - name: Go tests (root module, no ladybug cgo)
+      - name: Go tests (server + watch packages)
         run: |
           go vet ./...
           go test ./... -count=1
 
-      - name: brain ranking tests (no cgo / no ladybug)
-        run: go test ./internal/brain/rank -count=1
-
       - name: facts/audit self (lexicon consistency, no network)
         run: |
           ./bin/facts/audit self 2>/dev/null || echo "audit: not yet implemented; gate skipped"

.gitignore

@@ -10,4 +10,3 @@ __pycache__/
 .env
 .secrets/
 lib-ladybug/
-go.work.local

AGENTS.md

@@ -24,7 +24,7 @@ Read first: [PLAN](PLAN.md) → [docs](docs/).
 2. **Read-only data sources.** Ladybug `var/kb.lbug` and Postgres are opened
    read-only for queries. Index rebuilds write to `var/` (gitignored).
 3. **PII.** `brain-test`, `cs_brain` client data is never read or quoted.
-4. **No main pushes.** Feature branches + GitHub PR (`gh`); CI (Actions) must be green. Work board: [Gitea issues](https://git.produktor.io/eSlider/2dph/issues).
+4. **No main pushes.** Feature branches + PR via `gh`; CI must be green.
 5. **TDD.** Failing test before tool code. Unit tests run offline against
    fixtures; network/db calls are wrapped.
 6. **docs reflect behaviour.** Any change updates `docs/` + `PLAN.md` status.
@@ -35,16 +35,11 @@ Read first: [PLAN](PLAN.md) → [docs](docs/).
 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 get.go stats.go eval.go watch.go
-bin/chats/    sync.go import.go facts.go apply.go; libs in internal/chats
-bin/mail/     sync.go import.go (index_mail → brain/index.go)
-bin/markdown/ import.go (mistune leafs)
-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)
-internal/     shared Go (brain/rank is cgo-free; chats parsers; gitlog; websearch)
-bin/watch/    corpus watcher (used by bin/brain/watch.go)
+bin/          self-describing tools bin/{subject}/{method} (shebang)
+bin/serve.go  async Go HTTP server entry (self-executing go run shebang)
+bin/watch/    corpus watcher Go package (mtimes, no inotify deps)
+bin/server/   async Go HTTP server (goroutines, bounded worker pool)
+bin/mail/     mail pipeline: sync (Go), import (md), index_mail (rebuild)
 bin/tools/    vendored python libs behind bin/* (kblib, yamlout, websearch)
 bin/docker-entrypoint  container entrypoint (brain index|search|serve|watch)
 compose.yaml  docker composition (root level, not docker/)
@@ -57,9 +52,8 @@ 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/brain/index.go --rebuild                                            # rebuild brain incl. all mail (fresh DB)
+bin/mail/import --from-raw var/mail                                     # message.json → message.md (convert only)
+bin/mail/index_mail                                                     # rebuild brain incl. all mail (fresh DB)
 ```
 
 - `sync` (Go) downloads messages + attachments; Gmail uses paginated list +
@@ -68,7 +62,7 @@ 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`. Ladybug
+- `index_mail` always rebuilds from scratch (repo corpus + mail). Ladybug
   corrupts its WAL when brand-new leafs are bulk-inserted while FTS/vector
   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
@@ -79,13 +73,7 @@ bin/brain/index.go --rebuild                                            # rebuil
 ```bash
 bin/facts/audit ["self"|"facts"|"info"|"stale"]   # 2-source + staleness gate
 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/get.go <id> [--body]
-bin/markdown/import.go [dir]                      # mistune leaves → YAML
-bin/git/import.go [REPO] [--json] [--limit N]     # go-git history → commit leafs
-bin/web/search.go "query" [--json]                # SearXNG; throttled ≠ absence
-bin/postgres/query.go --profile onlyoffice -c 'SELECT 1'
+bin/kb/search "query" [--hop N] [--repo X]        # deduction search → YAML
 bin/md/tables                                     # what the graph holds → YAML
 bin/brain/deduce "question"                       # thinking wrapper
 ```

PLAN.md

@@ -26,10 +26,10 @@ 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`); Python remains for index/write 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)`. Auto-pair docker ps × compose × ssh-config × docs. |
 | D9 | facts/goal model | Who / What / How / Where / When + evidence + confidence on every edge. |
@@ -37,12 +37,9 @@ detective method: **a fact needs ≥2 independent sources or it is
 | D11 | strong/weak | `root` column: `facts` (strong) vs `info` (weak). Answer is `confirmed` only from facts root. |
 | D12 | transactional | facts and info split by root but **written in the same Ladybug transaction (ACID)** on every write. |
 | D13 | portfolio | start graph `(Person:eslider)-[:HAS]->(Portfolio)`, associate other natural/juristic persons later. |
-| 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. |
+| D14 | tooling style | `bin/{subject}/{method}` self-describing: shebang line 1, usage comment from line 2. Go shebang: `///usr/bin/env go run "$0" "$@"; exit`. |
+| D15 | repo | GitHub `eSlider/2dph`, public (like sibling repos), push/commit via `gh`, TDD + commit every change, CI/CD. |
 | 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 sources → web), not every edit. Missing graph ≠ “does not exist”. |
-| D18 | reasoner | Pluggable OpenAI-compatible URL. RAM: Qwen3.5-9B. Quality: Bonsai-27B or Qwen3.6-27B. No official Qwen3.6-9B. |
-| 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`. |
 
 ## Architecture
 
@@ -50,25 +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, db-yaml, brain, diataxis-docs)
+  skills/                   in-project skills (web-search, db-yaml, kb-search, agent-cost, diataxis-docs, …)
   bin/
     facts/extract           auto-pair 2 sources → lexicon yaml + graph
     facts/audit             ["self"|"facts"|"info"|"stale"] 2-source + staleness gate
-    kb/index                Python write path (called by bin/brain/index.go)
-    brain/index.go          rebuild FTS + HNSW (incl. --with-mail)
-    brain/get.go stats.go eval.go watch.go
-    brain/search.go         deduction: facts → info → web-search
-    brain/serve.go          HTTP API in-process (internal/httpapi + internal/brain)
-    mail/import.go          JSON → markdown (no brain write)
-    markdown/import.go      mistune leaves
-    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)
-    chats/sync.go import.go facts.go apply.go
-                            (libs in internal/chats; no chats index)
-    md/import               (deprecated; bin/markdown/import.go)
+    kb/index                build FTS + HNSW from corpus
+    kb/search               deduction: facts → info → web-search; --hop N
+    kb/get  kb/stats  kb/eval
+    md/import  md/select  md/tables  md/gaps     (mistune)
     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)
@@ -115,26 +103,24 @@ 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
-   deprecation shim.
+   indexing stay separate for crash safety.
 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)
-2. `go test ./internal/brain/rank` (cgo-free ranking + flag parser)
-3. python -m unittest discover -s bin/tools (includes published-docs SoT)
-4. bin/facts/audit self  (lexicon internal consistency)
-5. bin/brain/eval.go       (recall@5 ≥ 0.95, gates index regressions)
-6. md-docs build/lint if docs tooling arrives.
+1. go vet + go test ./... (Go tools)
+2. python -m unittest discover + pytest (Py tools)
+3. bin/facts/audit self  (lexicon internal consistency)
+4. bin/kb/eval            (recall@5 ≥ 0.95, gates index regressions)
+5. 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.
@@ -143,7 +129,7 @@ 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, db-yaml, 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

README.md

@@ -30,9 +30,9 @@ graph TB
     subgraph dph["2dph tools"]
         EX["bin/facts/extract<br/>2-source pairing"]
         AU["bin/facts/audit<br/>confidence + staleness"]
-        IDX["bin/brain/index.go<br/>chunk + embed"]
-        MD["bin/markdown/import.go<br/>mistune leaves"]
-        SR["bin/brain/search.go<br/>deduction"]
+        IDX["bin/kb/index<br/>chunk + embed"]
+        MD["bin/md/import<br/>mistune leaves"]
+        SR["bin/kb/search<br/>deduction + --hop"]
     end
 
     subgraph store["Ladybug var/kb.lbug"]
@@ -85,40 +85,21 @@ fact; conflicting sources or a single source → `hypothesis` → `(not confirme
 ## Deduction search
 
 ```bash
-bin/brain/search.go "Matrix federation over HTTPS"   # facts → info → web-search
-bin/brain/search.go "onlyoffice postgres" --root facts
-bin/brain/search.go "where is cs-lexicon" --json | yq '.'
-bin/brain/get.go <id> --body                         # full chunk on demand
-bin/brain/stats.go                                   # index health
-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
+bin/kb/search "Matrix federation over HTTPS"      # facts → info → web-search
+bin/kb/search "what runs on arc-2" --hop 1        # walk graph edges
+bin/kb/search "where is cs-lexicon" --json | yq '.'  # YAML by default
+bin/kb/get <id> --body                            # full chunk on demand
+bin/kb/stats                                      # index health
+bin/kb/eval                                       # recall@5 gate
 ```
 
 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/brain/index.go --rebuild                                            # rebuild brain (incl. mail)
-bin/brain/search.go "invoice from last week"                            # same search over mail leafs
+bin/mail/import --from-raw var/mail                                     # JSON → markdown
+bin/mail/index_mail                                                     # rebuild brain incl. mail
+bin/kb/search "Mietwagen Nürnberg invoice"                              # now answers from mail
 ```
 
 ## Storage
@@ -128,7 +109,7 @@ bin/brain/search.go "invoice from last week"                            # same s
   readers. **Never `DROP INDEX` FTS/VECTOR** on Ladybug 0.19: DROP leaves
   ghost catalog tables (`_0_Leaf_vec_UPPER`) so recreate fails while
   `SHOW_INDEXES` omits HNSW. Fresh indexes = delete `var/kb.lbug` +
-  `bin/brain/index.go --rebuild`. Use `ensure_indexes()` after upserts.
+  `bin/kb/index --rebuild`. Use `ensure_indexes()` after upserts.
 - **model2vec** — `potion-multilingual-128M` static embeddings (256-dim),
   CPU-fast, deterministic, no Ollama runtime dependency.
 - facts and info split semantically by `root` column but written inside the
@@ -136,10 +117,10 @@ bin/brain/search.go "invoice from last week"                            # same s
 
 ## Tooling conventions
 
-`bin/{subject}/{method}.go` — self-describing: shebang on line 1, usage comment
-from line 2. Shared code in `internal/`. YAML default output, `--json` for
-machines. Tests gate every commit. HTTP: `bin/brain/serve.go` calls
-`internal/brain` in-process (`/health` `/search` `/get` `/stats` `/audit` `/ingest`).
+`bin/{subject}/{method}` — self-describing: shebang on line 1, usage comment
+from line 2. bash + python primary; golang via the Go shebang when a compiled
+helper is right. YAML default output, `--json` for machines. Everything that
+touches network/db is read-only, throttled, cached. Tests gate every commit.
 
 ## Development
 
@@ -155,7 +136,7 @@ Docker (optional, cached model + var volumes):
 ```bash
 docker compose run --rm brain index            # (re)index corpus
 docker compose run --rm brain search "query"   # one-shot query
-docker compose run --rm brain serve            # bin/brain/serve.go
+docker compose run --rm brain serve            # async Go HTTP server
 docker compose up brain-watch                  # auto re-index on change
 ```
 
@@ -167,7 +148,4 @@ docker compose up brain-watch                  # auto re-index on change
   skills (`web-search`, `db-yaml`, …) that 2dph integrates
 - detective method — the two-source method
 
-Work board (issues): [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, execution status, and v2 open questions.
+See [PLAN.md](PLAN.md) for decisions, execution status, and v2 open questions.

bin/brain/doc.go

@@ -1,3 +0,0 @@
-// Commands in this directory are shebang mains (search.go, serve.go, index.go,
-// get.go, stats.go, eval.go, watch.go), each behind an exclusive build tag.
-package main

bin/brain/eval.go

@@ -1,20 +0,0 @@
-//usr/bin/env go run -tags=brain_eval "$0" "$@"; exit
-//go:build brain_eval
-//
-// bin/brain/eval.go - recall@5 gate.
-//
-//	./bin/brain/eval.go
-//	./bin/brain/eval.go --json
-//
-// 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/eval", os.Args[1:]))
-}

bin/brain/get.go

@@ -1,20 +0,0 @@
-//usr/bin/env go run -tags=brain_get "$0" "$@"; exit
-//go:build brain_get
-//
-// bin/brain/get.go - read one leaf by id.
-//
-//	./bin/brain/get.go <id>
-//	./bin/brain/get.go <id> --body
-//
-// 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/get", 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 is always a rebuild when mail is included (live FTS/HNSW + bulk
-// insert corrupts Ladybug 0.19 WAL). `add` is v2.
-// 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

@@ -1,23 +0,0 @@
-//usr/bin/env go run -tags=system_ladybug "$0" "$@"; exit
-//go:build cgo && system_ladybug
-//
-// bin/brain/search.go - deduction search over the 2dph brain.
-//
-//	./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 (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
-
-import (
-	"os"
-
-	"github.com/eSlider/2dph/internal/brain"
-)
-
-func main() {
-	os.Exit(brain.Main(os.Args[1:]))
-}

bin/brain/serve.go

@@ -1,31 +0,0 @@
-//usr/bin/env go run -tags=brain_serve,system_ladybug "$0" "$@"; exit
-//go:build brain_serve && cgo && system_ladybug
-//
-// bin/brain/serve.go - HTTP API (in-process ladybug search).
-//
-//	KB_ROOT=/path/to/2dph ./bin/brain/serve.go
-//	KB_WORKERS=4 KB_PORT=8630 ./bin/brain/serve.go
-//
-// 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"
-)
-
-func main() {
-	if os.Getenv("KB_ROOT") == "" {
-		if wd, err := os.Getwd(); err == nil {
-			os.Setenv("KB_ROOT", wd)
-		}
-	}
-	if err := brain.Ready(); err != nil {
-		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

@@ -1,20 +0,0 @@
-//usr/bin/env go run -tags=brain_stats "$0" "$@"; exit
-//go:build brain_stats
-//
-// bin/brain/stats.go - index health.
-//
-//	./bin/brain/stats.go
-//	./bin/brain/stats.go --json
-//
-// 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/stats", 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/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
-// bin/brain/index.go (not this subject).
-func writeFactsMarkdown(facts []ExtractedFact) {
-	mdDir := filepath.Join(Dir(), "facts")
+func writeFactsToBrain(root string, facts []ExtractedFact) {
+	indexScript := filepath.Join(root, "bin", "kb", "index")
+	if _, err := os.Stat(indexScript); os.IsNotExist(err) {
+		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/go.mod

@@ -0,0 +1,3 @@
+module github.com/eSlider/2dph/bin/chats
+
+go 1.25.0

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/main.go

@@ -0,0 +1,116 @@
+// 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":
+			fmt.Fprintf(os.Stderr, "chats: LinkedIn not implemented yet\n")
+			os.Exit(1)
+		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/refresh-linkedin-session

@@ -1,155 +0,0 @@
-#!/usr/bin/env python3
-"""chats/refresh-linkedin-session - refresh LinkedIn MCP session from webtop CDP.
-
-  bin/chats/refresh-linkedin-session [--cdp URL] [--root DIR]
-"""
-
-Reads the current LinkedIn cookies out of the running Thorium browser in the
-work-webtop container via CDP (Network.getAllCookies), copies the live browser
-profile onto the source profile directory, and rewrites the portable
-cookies.json + source-state.json that mcp-server-linkedin requires.
-
-Usage:
-  refresh-linkedin-session [--cdp http://127.0.0.1:9222] [--root /var/tmp/liprofile]
-                           [--container work-webtop] [--profile thorium-profile]
-
-After the headless driver uses a copied profile, LinkedIn rotates the session
-in that copy, so this must run before every sync.
-"""
-
-import asyncio
-import json
-import os
-import shutil
-import subprocess
-import sys
-import tempfile
-import urllib.request
-
-import websockets
-
-
-def cdp_tab(ws_json):
-    for t in ws_json:
-        if t.get("webSocketDebuggerUrl"):
-            return t["webSocketDebuggerUrl"]
-    return None
-
-
-async def get_cookies(ws_url):
-    async with websockets.connect(ws_url, max_size=50_000_000) as ws:
-        await ws.send(json.dumps({"id": 1, "method": "Network.getAllCookies", "params": {}}))
-        resp = await ws.recv()
-        return json.loads(resp).get("result", {}).get("cookies", [])
-
-
-def write_source_state(root, profile_dir):
-    # Reuse the linkedin-mcp-server session_state module to write a valid
-    # source-state.json (same schema the daemon reads).
-    try:
-        from linkedin_mcp_server.session_state import canonical, write_source_state
-
-        write_source_state(canonical(__import__("pathlib").Path(profile_dir)))
-        return
-    except Exception:
-        pass
-    # Fallback: minimal schema-compatible state.
-    import uuid
-
-    state = {
-        "version": 1,
-        "source_runtime_id": "linux-amd64-host",
-        "login_generation": str(uuid.uuid4()),
-        "created_at": None,
-        "profile_path": profile_dir,
-        "cookies_path": os.path.join(root, "cookies.json"),
-    }
-    from datetime import datetime, timezone
-
-    state["created_at"] = datetime.now(timezone.utc).isoformat()
-    with open(os.path.join(root, "source-state.json"), "w") as f:
-        json.dump(state, f, indent=2)
-
-
-def main():
-    args = sys.argv[1:]
-    cdp = "http://127.0.0.1:9222"
-    root = "/var/tmp/liprofile"
-    container = "work-webtop"
-    cprofile = "thorium-profile"
-    for i in range(0, len(args), 2):
-        k = args[i]
-        v = args[i + 1] if i + 1 < len(args) else ""
-        if k == "--cdp":
-            cdp = v
-        elif k == "--root":
-            root = v
-        elif k == "--container":
-            container = v
-        elif k == "--profile":
-            cprofile = v
-
-    profile_dir = os.path.join(root, "profile")
-    os.makedirs(profile_dir, exist_ok=True)
-
-    # 1. Clear stale daemon/browser locks so the server can claim the profile.
-    for lock in ("profile-claim.lock", "profile.lock", "daemon.lock", "lease.lock"):
-        p = os.path.join(root, lock)
-        if os.path.exists(p):
-            os.remove(p)
-    for name in os.listdir(profile_dir):
-        if name.startswith("Singleton"):
-            os.remove(os.path.join(profile_dir, name))
-    for name in os.listdir(root):
-        if name.startswith("invalid-state-"):
-            shutil.rmtree(os.path.join(root, name), ignore_errors=True)
-
-    # 1. Copy the live browser profile (cookies DB + Local State) so the
-    #    session the driver launches carries the current login.
-    subprocess.run(
-        ["docker", "cp", f"{container}:/config/{cprofile}/Default", os.path.join(profile_dir, "Default")],
-        check=True, capture_output=True,
-    )
-    subprocess.run(
-        ["docker", "cp", f"{container}:/config/{cprofile}/Local State", os.path.join(profile_dir, "Local State")],
-        check=True, capture_output=True,
-    )
-    for lock in ("SingletonLock", "SingletonCookie", "SingletonSocket"):
-        p = os.path.join(profile_dir, lock)
-        if os.path.exists(p):
-            os.remove(p)
-
-    # 2. Pull the live cookies out of the running browser.
-    with urllib.request.urlopen(f"{cdp}/json", timeout=5) as r:
-        tabs = json.loads(r.read())
-    ws_url = cdp_tab(tabs)
-    if not ws_url:
-        sys.stderr.write("refresh-linkedin-session: no CDP tab\n")
-        sys.exit(1)
-    cookies = asyncio.run(get_cookies(ws_url))
-
-    li = [c for c in cookies if "linkedin" in c.get("domain", "")]
-    out = []
-    for c in li:
-        domain = c.get("domain", "")
-        if domain in (".www.linkedin.com", "www.linkedin.com"):
-            domain = ".linkedin.com"
-        out.append({
-            "name": c["name"],
-            "value": c["value"].strip('"'),
-            "domain": domain,
-            "path": c.get("path", "/"),
-            "expires": c.get("expires", -1),
-            "httpOnly": c.get("httpOnly", False),
-            "secure": c.get("secure", False),
-            "sameSite": c.get("sameSite", "None"),
-        })
-    with open(os.path.join(root, "cookies.json"), "w") as f:
-        json.dump(out, f, indent=2)
-
-    write_source_state(root, profile_dir)
-    sys.stderr.write(f"refresh-linkedin-session: {len(out)} cookies, profile refreshed\n")
-
-
-if __name__ == "__main__":
-    main()

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/doc.go

@@ -1,2 +0,0 @@
-// Deprecated shebang mains at bin root (serve.go is tagged brain_serve).
-package main

bin/docker-entrypoint

@@ -2,10 +2,10 @@
 # bin/docker-entrypoint - run 2dph tools inside the container.
 #
 #   brain                 shell (default)
-#   brain search <q>      bin/brain/search.go
-#   brain index           bin/kb/index --with-mail
-#   brain watch <dir>     compiled /app/bin/watch (bin/brain/watch.go)
-#   brain serve           compiled /app/bin/serve (bin/brain/serve.go)
+#   brain search <q>      bin/kb/search
+#   brain index           bin/kb/index
+#   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
 #
@@ -18,7 +18,7 @@ shift || true
 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/git/import

@@ -1,26 +1,154 @@
 #!/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(
-        "bin/git/import is deprecated; use bin/git/import.go (go-git)",
-        file=sys.stderr,
-    )
-    target = ROOT / "bin" / "git" / "import.go"
-    os.execvp("go", ["go", "run", str(target), *argv])
-    return 1
+    import argparse
+    p = argparse.ArgumentParser(description="import git history into the brain")
+    p.add_argument("repo", nargs="?", default=None)
+    p.add_argument("--root", default=None, help="directory of repos to import (each git dir separately)")
+    p.add_argument("--limit", type=int, default=0)
+    p.add_argument("--since", default="")
+    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__":
-    sys.exit(main(sys.argv[1:]))
+    sys.exit(main(sys.argv[1:]))

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/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

@@ -1,37 +1,34 @@
 #!/usr/bin/env bash
-# bin/kb/search — deprecated wrapper. Use bin/brain/search.go.
-# Sets CGO for ladybug, builds a binary (embed daemon needs a real executable),
-# then execs it. Prints one deprecation line.
+# bin/kb/search - Go deduction search over the brain (model served by daemon).
+# Builds the kbsearch binary on first run / when source changes, then execs it.
 set -euo pipefail
 
-ROOT="$(cd "$(dirname "$0")/../.." && pwd)"
-BIN="$ROOT/var/bin/brain-search"
-SRC="$ROOT/internal/brain"
-CMD="$ROOT/bin/brain"
+KB="$(cd "$(dirname "$0")/../.." && pwd)"
+BIN="$KB/var/bin/kbsearch"
+SRC="$KB/bin/kbsearch"
 
-mkdir -p "$ROOT/var/bin"
+mkdir -p "$KB/var/bin"
 
+# Rebuild if binary missing or any .go source newer
 need_build=0
 if [ ! -x "$BIN" ]; then
-	need_build=1
+    need_build=1
 else
-	while IFS= read -r -d '' f; do
-		if [ "$f" -nt "$BIN" ]; then
-			need_build=1
-			break
-		fi
-	done < <(find "$SRC" "$CMD" -name '*.go' -print0 2>/dev/null)
+    # Check if any .go in kbsearch is newer than binary
+    while IFS= read -r -d '' f; do
+        if [ "$f" -nt "$BIN" ]; then
+            need_build=1
+            break
+        fi
+    done < <(find "$SRC" -name '*.go' -print0 2>/dev/null)
 fi
 
 if [ "$need_build" -eq 1 ]; then
-	echo "Building brain/search..." >&2
-	(
-		cd "$ROOT" &&
-			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
+    echo "Building kbsearch..." >&2
+    (cd "$SRC" && \
+        CGO_CFLAGS="-I$KB/lib-ladybug" \
+        CGO_LDFLAGS="-L$KB/lib-ladybug -Wl,-rpath,$KB/lib-ladybug" \
+        go build -tags system_ladybug -o "$BIN" .) || exit 1
 fi
 
-echo "bin/kb/search is deprecated; use bin/brain/search.go" >&2
-exec "$BIN" "$@"
+exec "$BIN" "$@"

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/kbsearch/brain.go

@@ -1,12 +1,10 @@
-//go:build cgo && system_ladybug
-
-package brain
+// Brain connection management using go-ladybug.
+package main
 
 import (
 	"fmt"
 	"os"
 	"path/filepath"
-	"strings"
 
 	lbug "github.com/LadybugDB/go-ladybug"
 )
@@ -46,10 +44,10 @@ func dbPath() string {
 }
 
 func openBrain() error {
-	return openWithSandbox(eps())
+	return openWithOpts(2, eps())
 }
 
-func openWithSandbox(epsv string) error {
+func openWithOpts(allow int, epsv string) error {
 	cfg := lbug.DefaultSystemConfig()
 	cfg.MaxNumThreads = 8
 	cfg.BufferPoolSize = 1 << 30 // 1GB
@@ -59,30 +57,20 @@ func openWithSandbox(epsv string) error {
 	if err != nil {
 		return fmt.Errorf("OpenDatabase: %w", err)
 	}
+	if epsv != "" {
+		if _, err := conn.Query("SET STREAM_SANDBOX = '" + epsv + "'"); err != nil {
+			return err
+		}
+	}
 
 	conn, err = lbug.OpenConnection(db)
 	if err != nil {
-		closeBrain()
 		return fmt.Errorf("OpenConnection: %w", err)
 	}
-	// Session settings need a live connection; running this before
-	// OpenConnection dereferenced a nil *Connection.
-	if epsv != "" {
-		if strings.ContainsAny(epsv, "'\\") {
-			closeBrain()
-			return fmt.Errorf("SET STREAM_SANDBOX: invalid value")
-		}
-		if _, err := conn.Query("SET STREAM_SANDBOX = '" + epsv + "'"); err != nil {
-			closeBrain()
-			return fmt.Errorf("SET STREAM_SANDBOX: %w", err)
-		}
-	}
 	if _, err := conn.Query("LOAD EXTENSION FTS"); err != nil {
-		closeBrain()
 		return fmt.Errorf("LOAD EXTENSION FTS: %w", err)
 	}
 	if _, err := conn.Query("LOAD EXTENSION VECTOR"); err != nil {
-		closeBrain()
 		return fmt.Errorf("LOAD EXTENSION VECTOR: %w", err)
 	}
 	return nil
@@ -97,4 +85,4 @@ func closeBrain() {
 		db.Close()
 		db = nil
 	}
-}
+}

bin/kbsearch/go.mod

@@ -0,0 +1,23 @@
+module github.com/eSlider/2dph/bin/kbsearch
+
+go 1.26.0
+
+require (
+	github.com/LadybugDB/go-ladybug v0.17.0
+	github.com/chewxy/math32 v1.11.2
+	github.com/daulet/tokenizers v1.27.0
+)
+
+require (
+	github.com/apache/arrow-go/v18 v18.6.0 // indirect
+	github.com/goccy/go-json v0.10.6 // indirect
+	github.com/google/flatbuffers v25.12.19+incompatible // indirect
+	github.com/google/uuid v1.6.0 // indirect
+	github.com/klauspost/compress v1.18.5 // indirect
+	github.com/klauspost/cpuid/v2 v2.3.0 // indirect
+	github.com/pierrec/lz4/v4 v4.1.26 // indirect
+	github.com/shopspring/decimal v1.4.0 // indirect
+	github.com/zeebo/xxh3 v1.1.0 // indirect
+	golang.org/x/exp v0.0.0-20260112195511-716be5621a96 // indirect
+	golang.org/x/sys v0.43.0 // indirect
+)

bin/kbsearch/go.sum

@@ -0,0 +1,44 @@
+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/andybalholm/brotli v1.2.1 h1:R+f5xP285VArJDRgowrfb9DqL18yVK0gKAW/F+eTWro=
+github.com/andybalholm/brotli v1.2.1/go.mod h1:rzTDkvFWvIrjDXZHkuS16NPggd91W3kUSvPlQ1pLaKY=
+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/chewxy/math32 v1.11.2 h1:IufN08Zwr1NKuWfY+4Tz55BcwKmyKKNdOP7KtumehnM=
+github.com/chewxy/math32 v1.11.2/go.mod h1:dOB2rcuFrCn6UHrze36WSLVPKtzPMRAQvBvUwkSsLqs=
+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 v1.1.2-0.20180830191138-d8f796af33cc h1:U9qPSI2PIWSS1VwoXQT9A3Wy9MM3WgvqSxFWenqJduM=
+github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/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/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/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
+github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
+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/pierrec/lz4/v4 v4.1.26 h1:GrpZw1gZttORinvzBdXPUXATeqlJjqUG/D87TKMnhjY=
+github.com/pierrec/lz4/v4 v4.1.26/go.mod h1:EoQMVJgeeEOMsCqCzqFm2O0cJvljX2nGZjcRIPL34O4=
+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/shopspring/decimal v1.4.0 h1:bxl37RwXBklmTi0C79JfXCEBD1cqqHt0bbgBAGFp81k=
+github.com/shopspring/decimal v1.4.0/go.mod h1:gawqmDU56v4yIKSwfBSFip1HdCCXN8/+DMd9qYNcwME=
+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/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/exp v0.0.0-20260112195511-716be5621a96 h1:Z/6YuSHTLOHfNFdb8zVZomZr7cqNgTJvA8+Qz75D8gU=
+golang.org/x/exp v0.0.0-20260112195511-716be5621a96/go.mod h1:nzimsREAkjBCIEFtHiYkrJyT+2uy9YZJB7H1k68CXZU=
+golang.org/x/sys v0.43.0 h1:Rlag2XtaFTxp19wS8MXlJwTvoh8ArU6ezoyFsMyCTNI=
+golang.org/x/sys v0.43.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
+gonum.org/v1/gonum v0.17.0 h1:VbpOemQlsSMrYmn7T2OUvQ4dqxQXU+ouZFQsZOx50z4=
+gonum.org/v1/gonum v0.17.0/go.mod h1:El3tOrEuMpv2UdMrbNlKEh9vd86bmQ6vqIcDwxEOc1E=
+gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
+gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

bin/kbsearch/main.go

@@ -0,0 +1,44 @@
+// bin/kbsearch - the Go implementation of bin/kb/search (nested module so the
+// root `go test ./...` and CI never compile it against native ladyships).
+//
+// Usage (built/run by ./bin/kb/search):
+//
+//	kbsearch "query" [--root facts|info] [--repo P] [-n N] [--json]
+//	kbsearch serve [port]           start the embedding daemon
+//	kbsearch --list-model           print the resolved model dir
+//
+// The potion-multilingual model is loaded only in `serve`; a CLI reuses the
+// daemon over localhost HTTP (falling back to in-process embedding).
+package main
+
+import (
+	"fmt"
+	"log"
+	"os"
+	"strconv"
+)
+
+func main() {
+	if len(os.Args) > 1 && os.Args[1] == "serve" {
+		port := 17830
+		if len(os.Args) > 2 {
+			if p, err := strconv.Atoi(os.Args[2]); err == nil {
+				port = p
+			}
+		}
+		if err := serve(port); err != nil {
+			log.Fatalf("kbsearch serve: %v", err)
+		}
+		return
+	}
+	if len(os.Args) > 1 && os.Args[1] == "--list-model" {
+		dir, err := modelDir()
+		if err != nil {
+			fmt.Fprintln(os.Stderr, err)
+			os.Exit(1)
+		}
+		fmt.Println(dir)
+		return
+	}
+	os.Exit(runSearch(os.Args[1:]))
+}

bin/kbsearch/model.go

@@ -1,11 +1,9 @@
-//go:build cgo && system_ladybug
-
 // StaticModel wraps the potion-multilingual-128m embedding model.
 //
 // Mirrors model2vec.StaticModel: tokenizer (daulet Unigram) + safetensors matrix.
 // Embed(text) applies the same preprocessing: median_token_length pre-truncation,
 // add_special_tokens=false, drop unk (id=1), truncate to 512, mean pool, L2 normalize +1e-32.
-package brain
+package main
 
 import (
 	"encoding/json"

bin/kbsearch/modeldir.go

@@ -1,4 +1,5 @@
-package brain
+// modelDir returns the resolved potion-multilingual-128m model directory.
+package main
 
 import (
 	"fmt"

bin/kbsearch/search.go

@@ -1,6 +1,5 @@
-//go:build cgo && system_ladybug
-
-package brain
+// Hybrid FTS + vector search implementation, plus daemon client/server.
+package main
 
 import (
 	"bytes"
@@ -14,12 +13,12 @@ import (
 	"os"
 	"os/exec"
 	"path/filepath"
+	"sort"
 	"strconv"
-	"syscall"
+	"strings"
 	"time"
 
 	lbug "github.com/LadybugDB/go-ladybug"
-	"github.com/eSlider/2dph/internal/brain/rank"
 )
 
 const defaultPort = 17830
@@ -27,15 +26,45 @@ const daemonPath = "/embed"
 const healthPath = "/health"
 
 func runSearch(args []string) int {
-	opt, err := rank.ParseArgs(args)
-	if err != nil {
-		fmt.Fprintf(os.Stderr, "brain/search: %v\n%s\n", err, rank.Usage)
-		return 2
-	}
-	root, repo, limit, query := opt.Root, opt.Repo, opt.Limit, opt.Query
-	jsonOut := opt.JSONOut
+	// Manual flag parsing to allow flags after query (like Python argparse)
+	root := ""
+	repo := ""
+	limit := 20
+	jsonOut := false
+	listModel := false
 
-	if opt.ListModel {
+	var queryArgs []string
+	for i := 0; i < len(args); i++ {
+		switch args[i] {
+		case "--root":
+			if i+1 < len(args) {
+				root = args[i+1]
+				i++
+			}
+		case "--repo":
+			if i+1 < len(args) {
+				repo = args[i+1]
+				i++
+			}
+		case "-n":
+			if i+1 < len(args) {
+				if n, err := strconv.Atoi(args[i+1]); err == nil {
+					limit = n
+				}
+				i++
+			}
+		case "--json":
+			jsonOut = true
+		case "--list-model":
+			listModel = true
+		default:
+			if !strings.HasPrefix(args[i], "-") {
+				queryArgs = append(queryArgs, args[i])
+			}
+		}
+	}
+
+	if listModel {
 		dir, err := modelDir()
 		if err != nil {
 			fmt.Fprintln(os.Stderr, err)
@@ -45,19 +74,47 @@ func runSearch(args []string) int {
 		return 0
 	}
 
+	query := strings.TrimSpace(strings.Join(queryArgs, " "))
+	if query == "" {
+		fmt.Fprintln(os.Stderr, "usage: kbsearch \"query\" [--root facts|info] [--repo REPO] [-n N] [--json]")
+		return 1
+	}
+
 	if err := openBrain(); err != nil {
 		fmt.Fprintf(os.Stderr, "open brain: %v\n", err)
 		return 1
 	}
 	defer closeBrain()
 
-	hits, err := searchHits(query, root, repo, limit)
+	emb, err := embedQuery(query)
 	if err != nil {
-		fmt.Fprintf(os.Stderr, "search: %v\n", err)
+		fmt.Fprintf(os.Stderr, "embed: %v\n", err)
 		return 1
 	}
 
-	results := hits
+	fts, err := queryFTS(query, limit*3)
+	if err != nil {
+		fmt.Fprintf(os.Stderr, "fts: %v\n", err)
+		return 1
+	}
+
+	var vec []Hit
+	if vec, err = queryVector(emb, limit*3); err != nil {
+		fmt.Fprintf(os.Stderr, "vec: %v\n", err)
+	}
+
+	results := hybrid(fts, vec, limit)
+
+	if root != "" {
+		results = filterRoot(results, root)
+	}
+	if repo != "" {
+		results = filterRepo(results, repo)
+	}
+	if len(results) > limit {
+		results = results[:limit]
+	}
+
 	for i := range results {
 		if results[i].Text != "" {
 			runes := []rune(results[i].Text)
@@ -85,22 +142,6 @@ func runSearch(args []string) int {
 	return 0
 }
 
-func searchHits(query, root, repo string, limit int) ([]Hit, error) {
-	emb, err := embedQuery(query)
-	if err != nil {
-		return nil, fmt.Errorf("embed: %w", err)
-	}
-	fts, err := queryFTS(query, limit*3)
-	if err != nil {
-		return nil, fmt.Errorf("fts: %w", err)
-	}
-	var vec []Hit
-	if vec, err = queryVector(emb, limit*3); err != nil {
-		fmt.Fprintf(os.Stderr, "vec: %v\n", err)
-	}
-	return rank.RankAndFilter(fts, vec, root, repo, limit), nil
-}
-
 func b2i(err error) int {
 	if err != nil {
 		return 1
@@ -109,7 +150,10 @@ func b2i(err error) int {
 }
 
 func queryFTS(text string, limit int) ([]Hit, error) {
-	stmt, err := conn.Prepare(rank.FTSStmt)
+	stmt, err := conn.Prepare(
+		"CALL QUERY_FTS_INDEX('Leaf', 'id', $q) " +
+			"RETURN node.id, node.text, node.root, node.source, score ORDER BY score LIMIT $n",
+	)
 	if err != nil {
 		return nil, err
 	}
@@ -126,7 +170,10 @@ func queryVector(emb []float64, limit int) ([]Hit, error) {
 	for i, v := range emb {
 		embList[i] = v
 	}
-	stmt, err := conn.Prepare(rank.VecStmt)
+	stmt, err := conn.Prepare(
+		"CALL QUERY_VECTOR_INDEX('Leaf', 'Leaf_vec', $q, $n) " +
+			"RETURN node.id, node.text, node.root, node.source, distance ORDER BY distance LIMIT $n",
+	)
 	if err != nil {
 		return nil, err
 	}
@@ -168,10 +215,10 @@ func rowsToHits(res *lbug.QueryResult) ([]Hit, error) {
 
 // JSON output types
 type jsonOut struct {
-	Query      string    `json:"query"`
-	RootFilter string    `json:"root_filter"`
-	Count      int       `json:"count"`
-	Results    []jsonHit `json:"results"`
+	Query      string     `json:"query"`
+	RootFilter string     `json:"root_filter"`
+	Count      int        `json:"count"`
+	Results    []jsonHit  `json:"results"`
 }
 
 type jsonHit struct {
@@ -201,6 +248,70 @@ func toJSONOut(hits []Hit, query, rootFilter string) *jsonOut {
 	}
 }
 
+func hybrid(fts, vec []Hit, limit int) []Hit {
+	byID := make(map[string]Hit)
+	rrf := make(map[string]float64)
+
+	for rank, h := range fts {
+		byID[h.ID] = h
+		rrf[h.ID] += 1.0 / (60 + float64(rank+1))
+	}
+	for rank, h := range vec {
+		if _, ok := byID[h.ID]; !ok {
+			byID[h.ID] = h
+		} else {
+			existing := byID[h.ID]
+			if existing.Score == 0 {
+				existing.Score = h.Score
+				byID[h.ID] = existing
+			}
+		}
+		rrf[h.ID] += 1.0 / (60 + float64(rank+1))
+	}
+
+	type scored struct {
+		id  string
+		rrf float64
+	}
+	var scoredList []scored
+	for id, v := range rrf {
+		scoredList = append(scoredList, scored{id, v})
+	}
+	sort.Slice(scoredList, func(i, j int) bool {
+		return scoredList[i].rrf > scoredList[j].rrf
+	})
+
+	var out []Hit
+	for i, s := range scoredList {
+		if i >= limit {
+			break
+		}
+		h := byID[s.id]
+		out = append(out, h)
+	}
+	return out
+}
+
+func filterRoot(hits []Hit, root string) []Hit {
+	var out []Hit
+	for _, h := range hits {
+		if h.Root == root {
+			out = append(out, h)
+		}
+	}
+	return out
+}
+
+func filterRepo(hits []Hit, repo string) []Hit {
+	var out []Hit
+	for _, h := range hits {
+		if strings.Contains(h.Source, repo) {
+			out = append(out, h)
+		}
+	}
+	return out
+}
+
 func resultsToDicts(hits []Hit) []any {
 	out := make([]any, len(hits))
 	for i, h := range hits {
@@ -252,7 +363,7 @@ func serve(port int) error {
 	})
 
 	addr := fmt.Sprintf("127.0.0.1:%d", port)
-	log.Printf("brain search daemon listening on %s", addr)
+	log.Printf("kbsearch daemon listening on %s", addr)
 	return http.ListenAndServe(addr, mux)
 }
 
@@ -271,16 +382,10 @@ func embedQuery(text string) ([]float64, error) {
 			port = p
 		}
 	}
-	if emb, err := tryDaemon(text, port); err == nil {
+	emb, err := tryDaemon(text, port)
+	if err == nil {
 		return emb, nil
 	}
-	if os.Getenv("KBSEARCH_NO_DAEMON") == "" {
-		if err := ensureDaemon(port); err == nil {
-			if emb, err := tryDaemon(text, port); err == nil {
-				return emb, nil
-			}
-		}
-	}
 
 	model, err := loadModel()
 	if err != nil {
@@ -342,13 +447,9 @@ func ensureDaemon(port int) error {
 	cmd.Dir, _ = filepath.Split(self)
 	cmd.Stdout = nil
 	cmd.Stderr = nil
-	cmd.SysProcAttr = &syscall.SysProcAttr{Setsid: true}
 	if err := cmd.Start(); err != nil {
 		return err
 	}
-	if cmd.Process != nil {
-		_ = cmd.Process.Release()
-	}
 
 	for i := 0; i < 40; i++ {
 		time.Sleep(250 * time.Millisecond)
@@ -361,22 +462,4 @@ func ensureDaemon(port int) error {
 		}
 	}
 	return fmt.Errorf("daemon failed to start on port %d", port)
-}
-
-// Main is the bin/brain/search.go entry: search, serve, or --list-model.
-func Main(args []string) int {
-	if len(args) > 0 && args[0] == "serve" {
-		port := defaultPort
-		if len(args) > 1 {
-			if p, err := strconv.Atoi(args[1]); err == nil {
-				port = p
-			}
-		}
-		if err := serve(port); err != nil {
-			log.Printf("brain/search serve: %v", err)
-			return 1
-		}
-		return 0
-	}
-	return runSearch(args)
-}
+}

bin/kbsearch/types.go

@@ -0,0 +1,16 @@
+// Common types and helpers for kbsearch.
+package main
+
+import "os"
+
+func eps() string { return os.Getenv("KBTEST_EPS") }
+
+// Hit is one search result, mirroring the python script's dict shape.
+type Hit struct {
+	ID      string  `json:"id"`
+	Text    string  `json:"text"`
+	Root    string  `json:"root"`
+	Source  string  `json:"-"` // for repo filtering, not in output
+	Score   float64 `json:"score"`
+	Snippet string  `json:"snippet,omitempty"`
+}

bin/kbsearch/yaml.go

@@ -1,5 +1,5 @@
 // YAML emitter ported from bin/kb/yamlout.py — preserves insertion order.
-package brain
+package main
 
 import (
 	"fmt"

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
-crash in native docling and must not leave the brain DB mid-transaction.
+Indexing is a separate step (bin/mail/index_mail): conversion can crash in
+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
-shim always rebuilds (repo corpus + var/mail). Conversion stays in mail/import.
+Ladybug corrupts its WAL when brand-new leafs are bulk-inserted while the
+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(
-        "bin/mail/index_mail is deprecated; use bin/brain/index.go --rebuild --with-mail",
-        file=sys.stderr,
-    )
-    index = ROOT / "bin" / "kb" / "index"
-    os.execv(sys.executable, [sys.executable, str(index), "--rebuild", "--with-mail", *argv])
-    return 1
+    p = argparse.ArgumentParser(description="rebuild the brain incl. all mail")
+    p.add_argument("--dry-run", action="store_true", help="count only, write nothing")
+    p.add_argument("--limit", type=int, default=0, help="cap messages included")
+    p.add_argument("--since", default="", help="only messages dated >= YYYY-MM-DD")
+    p.add_argument("--json", action="store_true")
+    a = p.parse_args(argv)
+
+    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/mail/sync/cli.go

@@ -32,7 +32,6 @@ func ParseCLI(args []string) (CLIConfig, int, error) {
 		offset = fs.Int("offset", 0, "skip first N messages per source")
 		force  = fs.Bool("force", false, "overwrite existing message.json + attachments")
 		dryRun = fs.Bool("dry-run", false, "list message counts without writing")
-		query  = fs.String("query", "in:inbox", "Gmail search query (gmail source only)")
 		srcs   = fs.String("source", "onlyoffice", "comma list: onlyoffice,gmail (default onlyoffice)")
 		help   = fs.Bool("help", false, "usage")
 	)
@@ -61,7 +60,6 @@ func ParseCLI(args []string) (CLIConfig, int, error) {
 		Offset:  *offset,
 		Force:   *force,
 		DryRun:  *dryRun,
-		Query:   *query,
 		Policy:  RetryPolicy{},
 	}
 	cli := CLIConfig{Sync: cfg, Env: *env, Sources: *srcs}
@@ -97,7 +95,7 @@ func Main(args []string) int {
 		return code
 	}
 	if cli.Help {
-		fmt.Fprintln(os.Stderr, "usage: bin/mail/sync.go [--source onlyoffice,gmail] [--query GMAIL_Q] [--limit N] [--offset N] [--workers N] [--force] [--dry-run]")
+		fmt.Fprintln(os.Stderr, "usage: bin/mail/sync.go [--source onlyoffice,gmail] [--limit N] [--offset N] [--workers N] [--force] [--dry-run]")
 		return 0
 	}
 	ctx, cancel := context.WithTimeout(context.Background(), 6*time.Hour)

bin/mail/sync/sync.go

@@ -112,7 +112,6 @@ type SyncConfig struct {
 	Offset  int                // skip first N messages per source
 	Force   bool               // overwrite existing message.json + attachments
 	DryRun  bool               // list without writing
-	Query   string             // Gmail search query; default in:inbox
 	Policy  RetryPolicy
 }
 
@@ -137,17 +136,9 @@ type ooSource struct {
 	c    *OOClient
 	page int
 }
-// gmailAPI is the Gmail client surface gmailSource needs. *GmailClient implements it.
-type gmailAPI interface {
-	ListIDs(ctx context.Context, q string, maxIDs int, pageToken string) ([]string, string, error)
-	GetMessage(ctx context.Context, id string) (*Message, error)
-	DownloadAttachment(ctx context.Context, msgID, attID string) ([]byte, error)
-}
-
 type gmailSource struct {
-	c     gmailAPI
-	cur   string
-	query string
+	c   *GmailClient
+	cur string
 }
 
 func (s *ooSource) Folder() string      { return "inbox" }
@@ -180,11 +171,7 @@ func (s *ooSource) DownloadAttachment(ctx context.Context, msg *Message, att Att
 }
 
 func (s *gmailSource) ListIDs(ctx context.Context, limit int, cursor string) ([]string, string, error) {
-	q := s.query
-	if q == "" {
-		q = "in:inbox"
-	}
-	ids, next, err := s.c.ListIDs(ctx, q, limit, cursor)
+	ids, next, err := s.c.ListIDs(ctx, "in:inbox", limit, cursor)
 	return ids, next, err
 }
 
@@ -220,7 +207,7 @@ func Run(ctx context.Context, cfg SyncConfig) (*SyncStats, error) {
 		if err != nil {
 			return nil, fmt.Errorf("gmail init: %w", err)
 		}
-		sources = append(sources, &gmailSource{c: gm, query: cfg.Query})
+		sources = append(sources, &gmailSource{c: gm})
 	}
 	if len(sources) == 0 {
 		return nil, errors.New("sync: no source configured (need OO, Gmail, or both)")

bin/mail/sync/sync_test.go

@@ -221,71 +221,6 @@ func TestCollectParts(t *testing.T) {
 	}
 }
 
-type fakeGmailAPI struct {
-	lastQ     string
-	lastLimit int
-	ids       []string
-}
-
-func (f *fakeGmailAPI) ListIDs(_ context.Context, q string, maxIDs int, _ string) ([]string, string, error) {
-	f.lastQ = q
-	f.lastLimit = maxIDs
-	return f.ids, "", nil
-}
-func (f *fakeGmailAPI) GetMessage(context.Context, string) (*Message, error) {
-	return nil, errors.New("unused")
-}
-func (f *fakeGmailAPI) DownloadAttachment(context.Context, string, string) ([]byte, error) {
-	return nil, errors.New("unused")
-}
-
-func TestGmailSourcePassesQueryToListIDs(t *testing.T) {
-	fake := &fakeGmailAPI{ids: []string{"m1"}}
-	src := &gmailSource{c: fake, query: "from:alice@example.com"}
-	ids, _, err := src.ListIDs(context.Background(), 10, "")
-	if err != nil {
-		t.Fatal(err)
-	}
-	if fake.lastQ != "from:alice@example.com" {
-		t.Fatalf("ListIDs q=%q, want from:alice@example.com", fake.lastQ)
-	}
-	if fake.lastLimit != 10 {
-		t.Fatalf("ListIDs limit=%d, want 10", fake.lastLimit)
-	}
-	if len(ids) != 1 || ids[0] != "m1" {
-		t.Fatalf("ids=%v", ids)
-	}
-}
-
-func TestGmailSourceEmptyQueryDefaultsToInbox(t *testing.T) {
-	fake := &fakeGmailAPI{}
-	src := &gmailSource{c: fake, query: ""}
-	if _, _, err := src.ListIDs(context.Background(), 5, ""); err != nil {
-		t.Fatal(err)
-	}
-	if fake.lastQ != "in:inbox" {
-		t.Fatalf("empty query q=%q, want in:inbox", fake.lastQ)
-	}
-}
-
-func TestParseCLIGmailQuery(t *testing.T) {
-	cli, code, err := ParseCLI([]string{
-		"--source", "gmail",
-		"--query", "from:letrado@example.com",
-		"--out", t.TempDir(),
-		"--dry-run",
-	})
-	if err != nil || code != 0 {
-		t.Fatalf("ParseCLI: code=%d err=%v", code, err)
-	}
-	if cli.Sync.Query != "from:letrado@example.com" {
-		t.Fatalf("query=%q", cli.Sync.Query)
-	}
-	if cli.Sync.Gmail == nil {
-		t.Fatal("gmail source not configured")
-	}
-}
-
 func b64(s string) string {
 	return base64.URLEncoding.EncodeToString([]byte(s))
 }

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

@@ -1,20 +0,0 @@
-//usr/bin/env go run -tags=markdown_import "$0" "$@"; exit
-//go:build markdown_import
-//
-// bin/markdown/import.go - split markdown into leafs (mistune).
-//
-//	./bin/markdown/import.go [dir]
-//	./bin/markdown/import.go --files a.md,b.md --json
-//
-// 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/md/import", os.Args[1:]))
-}

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/serve.go

@@ -1,22 +1,27 @@
-//usr/bin/env go run -tags=brain_serve "$0" "$@"; exit
-//go:build brain_serve
+//usr/bin/env go run "$0" "$@"; exit
+// bin/serve.go - async Go HTTP server for the 2dph brain (see bin/server).
 //
-// bin/serve.go — deprecated; use bin/brain/serve.go.
+//	KB_ROOT=/path/to/2dph ./bin/serve.go        # serve the brain
+//	KB_SEARCH_CMD=... KB_WORKERS=4 KB_PORT=8630 ./bin/serve.go
+//
+// Shebang trick: the first line is a Go `//` comment; when executed, env runs
+// `go run "$0"` so this file doubles as an executable script. The real code
+// lives in the importable package (module path, never a relative import).
+// NOTE: never run `gofmt -w` on this file - it rewrites `//usr/bin/env` to
+// `// usr/...` and breaks the shebang.
 package main
 
 import (
-	"fmt"
 	"os"
 
-	"github.com/eSlider/2dph/internal/httpapi"
+	"github.com/eSlider/2dph/bin/server"
 )
 
 func main() {
-	fmt.Fprintln(os.Stderr, "bin/serve.go is deprecated; use bin/brain/serve.go")
-	if os.Getenv("KB_ROOT") == "" {
+	if env := os.Getenv("KB_ROOT"); env == "" {
 		if wd, err := os.Getwd(); err == nil {
 			os.Setenv("KB_ROOT", wd)
 		}
 	}
-	httpapi.Run(nil)
+	server.Run()
 }

bin/server/server.go

@@ -0,0 +1,154 @@
+// Package server serves the 2dph brain over HTTP.
+//
+// Async by design: every request runs on its own goroutine, and CPU-heavy
+// searches are serialized through a bounded worker pool (a counting
+// semaphore) so N requests can't spawn N Python interpreters at once.
+//
+// Used by bin/serve.go which is a self-executing shebang script:
+//
+//	///usr/bin/env go run "$0" "$@"; exit
+//	package main
+//	import "github.com/eSlider/2dph/bin/server"
+//	func main() { server.Run() }
+package server
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"log"
+	"net/http"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"strconv"
+	"strings"
+	"time"
+)
+
+type Searcher interface {
+	Search(ctx context.Context, query string, limit int) ([]byte, error)
+}
+
+type Server struct {
+	searcher  Searcher
+	semaphore chan struct{}
+}
+
+const defaultPort = 8630
+
+func NewServer(searcher Searcher, workers int) http.Handler {
+	return &Server{
+		searcher:  searcher,
+		semaphore: make(chan struct{}, workers),
+	}
+}
+
+func (s *Server) ServeHTTP(w http.ResponseWriter, r *http.Request) {
+	switch {
+	case r.URL.Path == "/health":
+		writeJSON(w, http.StatusOK, map[string]any{"status": "ok"})
+	case r.URL.Path == "/search":
+		s.handleSearch(w, r)
+	default:
+		writeJSON(w, http.StatusNotFound, map[string]any{"error": "not found"})
+	}
+}
+
+func (s *Server) handleSearch(w http.ResponseWriter, r *http.Request) {
+	q := strings.TrimSpace(r.URL.Query().Get("q"))
+	if q == "" {
+		writeJSON(w, http.StatusBadRequest, map[string]any{"error": "q required"})
+		return
+	}
+	limit := 10
+	if raw := r.URL.Query().Get("n"); raw != "" {
+		n, err := strconv.Atoi(raw)
+		if err != nil || n < 1 || n > 100 {
+			writeJSON(w, http.StatusBadRequest, map[string]any{"error": "n must be int 1..100"})
+			return
+		}
+		limit = n
+	}
+
+	// Worker pool: block until a slot frees, so burst concurrency still
+	// bounds memory (no unbounded python processes).
+	select {
+	case s.semaphore <- struct{}{}:
+		defer func() { <-s.semaphore }()
+	case <-r.Context().Done():
+		return
+	}
+
+	body, err := s.searcher.Search(r.Context(), q, limit)
+	if err != nil {
+		writeJSON(w, http.StatusGatewayTimeout, map[string]any{"error": err.Error()})
+		return
+	}
+	writeRaw(w, http.StatusOK, body)
+}
+
+func writeJSON(w http.ResponseWriter, code int, obj any) {
+	body, _ := json.Marshal(obj)
+	writeRaw(w, code, body)
+}
+
+func writeRaw(w http.ResponseWriter, code int, body []byte) {
+	w.Header().Set("Content-Type", "application/json")
+	w.Header().Set("Content-Length", strconv.Itoa(len(body)))
+	w.WriteHeader(code)
+	w.Write(body)
+}
+
+// brainSearcher shells out to bin/kb/search --json. A single python search
+// is bounded and short-lived; the worker pool keeps at most N live.
+type brainSearcher struct {
+	cmdPath string
+	timeout time.Duration
+}
+
+func (b *brainSearcher) Search(ctx context.Context, query string, limit int) ([]byte, error) {
+	ctx, cancel := context.WithTimeout(ctx, b.timeout)
+	defer cancel()
+	cmd := exec.CommandContext(ctx, b.cmdPath, "--json", "-n", strconv.Itoa(limit), query)
+	out, err := cmd.Output()
+	if err != nil {
+		var exitErr *exec.ExitError
+		if errors.As(err, &exitErr) {
+			return nil, errors.New("search backend failed: " + strings.TrimSpace(string(exitErr.Stderr)))
+		}
+		return nil, err
+	}
+	return out, nil
+}
+
+// Run starts the HTTP server. Reads env: KB_SEARCH_CMD (default bin/kb/search,
+// relative to the repo root given by KB_ROOT), KB_WORKERS (default 4), KB_PORT
+// (default 8630).
+func Run() {
+	root := os.Getenv("KB_ROOT")
+	searchPath := os.Getenv("KB_SEARCH_CMD")
+	if searchPath == "" {
+		searchPath = filepath.Join(root, "bin", "kb", "search")
+	}
+	workers := 4
+	if raw := os.Getenv("KB_WORKERS"); raw != "" {
+		if n, err := strconv.Atoi(raw); err == nil && n > 0 {
+			workers = n
+		}
+	}
+	port := defaultPort
+	if raw := os.Getenv("KB_PORT"); raw != "" {
+		if n, err := strconv.Atoi(raw); err == nil && n > 0 {
+			port = n
+		}
+	}
+
+	searcher := &brainSearcher{cmdPath: searchPath, timeout: 60 * time.Second}
+	handler := NewServer(searcher, workers)
+	addr := "127.0.0.1:" + strconv.Itoa(port)
+	log.Printf("serve: %s (workers=%d)", addr, workers)
+	if err := http.ListenAndServe(addr, handler); err != nil {
+		log.Fatal(err)
+	}
+}

bin/server/server_test.go

@@ -1,12 +1,10 @@
-package httpapi
+package server
 
 import (
 	"context"
 	"encoding/json"
 	"net/http"
 	"net/http/httptest"
-	"os"
-	"strings"
 	"sync"
 	"sync/atomic"
 	"testing"
@@ -48,26 +46,6 @@ func (f *fakeSearcher) Search(ctx context.Context, query string, limit int) ([]b
 	return []byte(`{"query":"` + query + `","count":0,"results":[]}`), nil
 }
 
-func (f *fakeSearcher) Get(_ context.Context, id string, body bool) ([]byte, error) {
-	out := map[string]any{"id": id, "root": "info"}
-	if body {
-		out["text"] = "fake body"
-	}
-	return json.Marshal(out)
-}
-
-func (f *fakeSearcher) Stats(context.Context) ([]byte, error) {
-	return []byte(`{"total":0,"by_root":{}}`), nil
-}
-
-func (f *fakeSearcher) Audit(context.Context) ([]byte, error) {
-	return []byte(`{"status":"ok"}`), nil
-}
-
-func (f *fakeSearcher) Ingest(context.Context) ([]byte, error) {
-	return []byte(`{"mode":"rebuild","command":"bin/brain/index.go --rebuild"}`), nil
-}
-
 func (f *fakeSearcher) count() int {
 	f.mu.Lock()
 	defer f.mu.Unlock()
@@ -163,58 +141,6 @@ func TestSearchRejectsBadLimit(t *testing.T) {
 	}
 }
 
-func TestGetLeaf(t *testing.T) {
-	fs := &fakeSearcher{callback: func(q string, limit int) ([]byte, error) {
-		return []byte(`{}`), nil
-	}}
-	h := NewServer(fs, 1)
-	if code, _ := get(t, h, "/get"); code != http.StatusBadRequest {
-		t.Fatalf("missing id code = %d, want 400", code)
-	}
-	code, body := get(t, h, "/get?id=leaf-1&body=1")
-	if code != http.StatusOK {
-		t.Fatalf("get code = %d, want 200 body=%s", code, body)
-	}
-	if !strings.Contains(string(body), "leaf-1") {
-		t.Fatalf("get body %s missing id", body)
-	}
-}
-
-func TestStatsAuditIngest(t *testing.T) {
-	h := NewServer(&fakeSearcher{}, 1)
-	for _, path := range []string{"/stats", "/audit", "/ingest"} {
-		code, body := get(t, h, path)
-		if code != http.StatusOK {
-			t.Fatalf("%s code = %d, want 200 (%s)", path, code, body)
-		}
-		if !json.Valid(body) {
-			t.Fatalf("%s body not json: %s", path, body)
-		}
-	}
-}
-
-func TestHTTPPackageDoesNotExecPython(t *testing.T) {
-	raw, err := os.ReadFile("server.go")
-	if err != nil {
-		t.Fatal(err)
-	}
-	lower := strings.ToLower(string(raw))
-	if strings.Contains(lower, "python3") || strings.Contains(lower, "bin/kb/search") {
-		t.Fatal("httpapi must not exec Python or bin/kb/search")
-	}
-}
-
-func TestDefaultSearchCmdIsBrainNotPython(t *testing.T) {
-	t.Setenv("KB_SEARCH_CMD", "")
-	cmd := defaultSearchCmd("/repo")
-	if strings.Contains(strings.ToLower(cmd), "python") {
-		t.Fatalf("search path still python: %s", cmd)
-	}
-	if !strings.Contains(cmd, "brain") {
-		t.Fatalf("search path must be the Go brain binary, got %s", cmd)
-	}
-}
-
 func TestSearchTimeout(t *testing.T) {
 	fs := &fakeSearcher{delay: time.Second}
 	h := NewServer(fs, 1)

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
-the version graph File-[:HAS_VERSION]->Commit-[:AUTHORED]->Person.
+Pure, testable functions. Field grammar (see bin/git/import):
+
+  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, "
@@ -57,4 +114,4 @@ def index_commits(conn, commits: list[Commit], repo: str) -> int:
             conn.execute("MATCH (f:File {id:$fid}), (c:Commit {id:$sha}) "
                          "MERGE (f)-[:HAS_VERSION]->(c)",
                          parameters={"fid": f"{repo}:{path}", "sha": c.sha})
-    return len(commits)
+    return len(commits)

bin/tools/kblib.py

@@ -135,7 +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)
@@ -145,7 +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:
@@ -158,7 +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)
@@ -237,6 +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

@@ -1,121 +0,0 @@
-"""D14 layout: bin/{subject}/{method}.go, libs in internal/, one go.mod."""
-from __future__ import annotations
-
-import unittest
-from pathlib import Path
-
-ROOT = Path(__file__).resolve().parents[2]
-
-
-class BinLayoutTest(unittest.TestCase):
-    def test_brain_search_shebang_exists(self) -> None:
-        p = ROOT / "bin" / "brain" / "search.go"
-        self.assertTrue(p.is_file(), "missing bin/brain/search.go")
-        first = p.read_text().splitlines()[0]
-        self.assertTrue(
-            first.startswith("//usr/bin/env go run"),
-            f"shebang first line, got {first!r}",
-        )
-
-    def test_no_nested_go_mod_under_bin(self) -> None:
-        nested = list((ROOT / "bin").rglob("go.mod"))
-        self.assertEqual(nested, [], f"nested go.mod files: {nested}")
-
-    def test_rank_lives_in_internal_brain(self) -> None:
-        self.assertTrue(
-            (ROOT / "internal" / "brain" / "rank" / "rank.go").is_file(),
-            "ranking must live in internal/brain/rank (cgo-free)",
-        )
-        self.assertFalse(
-            (ROOT / "bin" / "kbsearch").exists(),
-            "bin/kbsearch nested module must be gone",
-        )
-
-    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", "get.go", "stats.go", "eval.go", "watch.go"):
-            self._assert_shebang(f"bin/brain/{method}")
-
-    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_shebang(self) -> None:
-        self._assert_shebang("bin/markdown/import.go")
-
-    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)

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]
@@ -71,4 +68,4 @@ class GitGraphTest(unittest.TestCase):
 
 
 if __name__ == "__main__":
-    unittest.main()
+    unittest.main()

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_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

@@ -1,77 +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_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",
-        ]
-        # 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",
-            )

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
-	// root (from KB_ROOT). Defaults to `python3 <root>/bin/kb/index --with-mail`.
+	// IndexCmd is the kb/index command template. %s is replaced by the repo
+	// 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") {
-		t.Fatalf("default index cmd = %q, want kb/index", opts.IndexCmd)
-	}
-	if !strings.Contains(opts.IndexCmd, "--with-mail") {
-		t.Fatalf("default index cmd must include --with-mail, got %q", opts.IndexCmd)
+	if opts.IndexCmd == "" {
+		t.Fatal("default index cmd is empty")
 	}
 }

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:
-    print(
-        "bin/web/search is deprecated; use bin/web/search.go",
-        file=sys.stderr,
-    )
-    target = ROOT / "bin" / "web" / "search.go"
-    os.execvp("go", ["go", "run", str(target), *argv])
-    return 1
+def load_config() -> dict:
+    if not CONFIG.exists():
+        sys.exit(f"no credentials at {CONFIG} (mode 600, BRAIN_SEARCH_URL/USER/PASS)")
+    conf = {}
+    for line in CONFIG.read_text().splitlines():
+        line = line.strip()
+        if not line or line.startswith("#") or "=" not in line:
+            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

@@ -61,21 +61,6 @@ services:
     restart: unless-stopped
     stop_grace_period: 20s
 
-  # 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
-
 volumes:
   kb-model:
   kb-var:

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

@@ -6,10 +6,5 @@ Brain/ops/eSlider stack. Facts need proof or they are
 
 - [PLAN.md](../PLAN.md) — decisions, execution order, open questions (v2)
 - [design](design.md) — schema, deduction model, sources
-- [Gitea issues](https://git.produktor.io/eSlider/2dph/issues) — work board (origin)
 
-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 until File/FROM_FILE edges exist.
-
-Published docs live here and mirror the project state.
+Published docs live here and mirror the project state.

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/chats/import.go
-./bin/chats/facts.go
-./bin/chats/apply.go --dry-run
+./bin/chat sync telegram --limit 100
+./bin/chat import
+./bin/chat index
+./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

@@ -1,33 +0,0 @@
-# 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

@@ -17,15 +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
-     (`bin/web/search.go`; status `throttled` is not evidence of absence)
 ```
 
-`--hop` is not implemented yet (needs File/FROM_FILE edges). The flag is an
-error; it is not a graph walk.
+`--hop N` follows graph edges (sibling leaves under a heading, owning file,
+`related:` files, vector-neighbour leaves) — the deduction walk.
 
 ## Who / What / How / Where / When + evidence
 
@@ -47,8 +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
-binary); conversion prints leafs, brain write is `bin/brain/index.go`.
+content leaf.
 
 `bin/facts/audit stale` flags leafs whose observed revision is behind the
 corpus HEAD.

go.mod

@@ -1,52 +1,8 @@
 module github.com/eSlider/2dph
 
-go 1.26
+go 1.25.0
 
 require (
-	github.com/LadybugDB/go-ladybug v0.17.0
 	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 v0.0.0-20260410095643-746e56fc9e2f // 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 +1,14 @@
-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 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 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 v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=
-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/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
+github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
+github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 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/crypto v0.53.0 h1:QZ4Muo8THX6CizN2vPPd5fBGHyogrdK9fG4wLPFUsto=
-golang.org/x/crypto v0.53.0/go.mod h1:DNLU434OwVakk9PzuwV8w62mAJpRJL3vsgcfp4Qnsio=
-golang.org/x/exp v0.0.0-20260410095643-746e56fc9e2f h1:W3F4c+6OLc6H2lb//N1q4WpJkhzJCK5J6kUi1NTVXfM=
-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=
+github.com/stretchr/testify v1.7.0 h1:nwc3DEeHmmLAfoZucVR881uASk0Mfjw8xYJ99tb5CcY=
+github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
 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=

go.work

@@ -1,3 +0,0 @@
-go 1.26
-
-use .

internal/brain/doc.go

@@ -1,3 +0,0 @@
-// Package brain is deduction search over Ladybug (FTS + HNSW).
-// Query/embed code that needs cgo lives behind the system_ladybug tag.
-package brain

internal/brain/http.go

@@ -1,154 +0,0 @@
-//go:build cgo && system_ladybug
-
-package brain
-
-import (
-	"bytes"
-	"context"
-	"encoding/json"
-	"fmt"
-)
-
-// 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(_ 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)
-		}
-	}
-	var buf bytes.Buffer
-	enc := json.NewEncoder(&buf)
-	enc.SetEscapeHTML(false)
-	if err := enc.Encode(toJSONOut(hits, query, "")); 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(context.Context) ([]byte, error) {
-	return json.Marshal(map[string]any{
-		"mode":    "rebuild",
-		"command": "bin/brain/index.go --rebuild",
-		"add":     "v2",
-	})
-}
-
-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/rank/args.go

@@ -1,72 +0,0 @@
-package rank
-
-import (
-	"fmt"
-	"strconv"
-	"strings"
-)
-
-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`
-
-type Options struct {
-	Query     string
-	Root      string
-	Repo      string
-	Limit     int
-	JSONOut   bool
-	ListModel bool
-}
-
-// ParseArgs reads flags. Unknown flags are an error: silently dropping them
-// meant `--hop 1` vanished and its argument `1` was appended to the query.
-// --hop is recognised so it cannot be swallowed; it is not implemented until
-// File/FROM_FILE edges exist.
-func ParseArgs(args []string) (Options, error) {
-	opt := Options{Limit: 20}
-	var queryArgs []string
-
-	for i := 0; i < len(args); i++ {
-		arg := args[i]
-		wantsValue := arg == "--root" || arg == "--repo" || arg == "-n" || arg == "--hop"
-		if wantsValue && i+1 >= len(args) {
-			return opt, fmt.Errorf("%s needs a value", arg)
-		}
-		switch arg {
-		case "--root":
-			i++
-			opt.Root = args[i]
-			if opt.Root != "facts" && opt.Root != "info" {
-				return opt, fmt.Errorf("--root must be facts or info, got %q", opt.Root)
-			}
-		case "--repo":
-			i++
-			opt.Repo = args[i]
-		case "-n":
-			i++
-			n, err := strconv.Atoi(args[i])
-			if err != nil || n < 1 {
-				return opt, fmt.Errorf("-n must be a positive integer, got %q", args[i])
-			}
-			opt.Limit = n
-		case "--hop":
-			return opt, fmt.Errorf("--hop is not implemented yet (needs File/FROM_FILE edges)")
-		case "--json":
-			opt.JSONOut = true
-		case "--list-model":
-			opt.ListModel = true
-		default:
-			if strings.HasPrefix(arg, "-") {
-				return opt, fmt.Errorf("unknown flag %q", arg)
-			}
-			queryArgs = append(queryArgs, arg)
-		}
-	}
-
-	opt.Query = strings.TrimSpace(strings.Join(queryArgs, " "))
-	if opt.Query == "" && !opt.ListModel {
-		return opt, fmt.Errorf("no query given")
-	}
-	return opt, nil
-}

internal/brain/rank/query.go

@@ -1,9 +0,0 @@
-package rank
-
-// BM25 ranks best-first, so the top hits are the *highest* scores; cosine
-// distance ranks best-first ascending. Both mirror kblib.py.
-const FTSStmt = "CALL QUERY_FTS_INDEX('Leaf', 'id', $q) " +
-	"RETURN node.id, node.text, node.root, node.source, score ORDER BY score DESC LIMIT $n"
-
-const VecStmt = "CALL QUERY_VECTOR_INDEX('Leaf', 'Leaf_vec', $q, $n) " +
-	"RETURN node.id, node.text, node.root, node.source, distance ORDER BY distance LIMIT $n"

internal/brain/rank/rank.go

@@ -1,100 +0,0 @@
-// Package rank is the cgo-free ranking and CLI parsing for brain search.
-// CI can `go test ./rank` without the native ladybug library.
-package rank
-
-import (
-	"sort"
-	"strings"
-)
-
-// Hit is one search result, mirroring the python script's dict shape.
-type Hit struct {
-	ID      string  `json:"id"`
-	Text    string  `json:"text"`
-	Root    string  `json:"root"`
-	Source  string  `json:"-"`
-	Score   float64 `json:"score"`
-	Snippet string  `json:"snippet,omitempty"`
-}
-
-// rrfK dampens the contribution of low ranks; same constant as kblib.py.
-const rrfK = 60
-
-// RankAndFilter fuses the two hit lists, applies --root/--repo, then cuts to
-// limit. Cutting first dropped every matching leaf ranked below the cut, so
-// `--root facts` came back empty whenever info leafs filled the top N.
-// limit <= 0 keeps everything.
-func RankAndFilter(fts, vec []Hit, root, repo string, limit int) []Hit {
-	out := Hybrid(fts, vec, 0)
-	if root != "" {
-		out = FilterRoot(out, root)
-	}
-	if repo != "" {
-		out = FilterRepo(out, repo)
-	}
-	if limit > 0 && len(out) > limit {
-		out = out[:limit]
-	}
-	return out
-}
-
-// Hybrid merges FTS and vector hits by reciprocal rank fusion.
-// limit <= 0 returns the full fused list.
-func Hybrid(fts, vec []Hit, limit int) []Hit {
-	byID := make(map[string]Hit, len(fts)+len(vec))
-	rrf := make(map[string]float64, len(fts)+len(vec))
-
-	for i, h := range fts {
-		byID[h.ID] = h
-		rrf[h.ID] += 1.0 / (rrfK + float64(i+1))
-	}
-	for i, h := range vec {
-		if existing, ok := byID[h.ID]; !ok {
-			byID[h.ID] = h
-		} else if existing.Score == 0 {
-			existing.Score = h.Score
-			byID[h.ID] = existing
-		}
-		rrf[h.ID] += 1.0 / (rrfK + float64(i+1))
-	}
-
-	ids := make([]string, 0, len(rrf))
-	for id := range rrf {
-		ids = append(ids, id)
-	}
-	sort.Slice(ids, func(i, j int) bool {
-		if rrf[ids[i]] != rrf[ids[j]] {
-			return rrf[ids[i]] > rrf[ids[j]]
-		}
-		return ids[i] < ids[j]
-	})
-	if limit > 0 && len(ids) > limit {
-		ids = ids[:limit]
-	}
-
-	out := make([]Hit, 0, len(ids))
-	for _, id := range ids {
-		out = append(out, byID[id])
-	}
-	return out
-}
-
-func FilterRoot(hits []Hit, root string) []Hit {
-	var out []Hit
-	for _, h := range hits {
-		if h.Root == root {
-			out = append(out, h)
-		}
-	}
-	return out
-}
-
-func FilterRepo(hits []Hit, repo string) []Hit {
-	var out []Hit
-	for _, h := range hits {
-		if strings.Contains(h.Source, repo) {
-			out = append(out, h)
-		}
-	}
-	return out
-}

internal/brain/rank/rank_test.go

@@ -1,149 +0,0 @@
-// Unit tests for ranking/filtering and CLI parsing (no db, no model, offline).
-package rank
-
-import (
-	"strings"
-	"testing"
-)
-
-func h(id, root, source string) Hit {
-	return Hit{ID: id, Text: id, Root: root, Source: source}
-}
-
-func ids(hits []Hit) []string {
-	out := make([]string, len(hits))
-	for i, hit := range hits {
-		out[i] = hit.ID
-	}
-	return out
-}
-
-func eq(t *testing.T, got []Hit, want ...string) {
-	t.Helper()
-	g := ids(got)
-	if len(g) != len(want) {
-		t.Fatalf("got %v, want %v", g, want)
-	}
-	for i := range want {
-		if g[i] != want[i] {
-			t.Fatalf("got %v, want %v", g, want)
-		}
-	}
-}
-
-// A facts leaf that ranks below the limit in the unfiltered list must still
-// be returned for --root facts. Filtering after truncation loses it.
-func TestRankAndFilterFiltersBeforeLimit(t *testing.T) {
-	fts := []Hit{
-		h("i1", "info", "docs/a.md"),
-		h("i2", "info", "docs/b.md"),
-		h("i3", "info", "docs/c.md"),
-		h("f1", "facts", "docker ps x compose"),
-	}
-	eq(t, RankAndFilter(fts, nil, "facts", "", 2), "f1")
-}
-
-func TestRankAndFilterRepoFiltersBeforeLimit(t *testing.T) {
-	fts := []Hit{
-		h("a", "info", "eSlider/2dph:README.md"),
-		h("b", "info", "eSlider/2dph:PLAN.md"),
-		h("c", "info", "eSlider/ops:compose.yaml"),
-	}
-	eq(t, RankAndFilter(fts, nil, "", "ops", 2), "c")
-}
-
-func TestRankAndFilterTruncatesToLimit(t *testing.T) {
-	fts := []Hit{h("a", "info", "x"), h("b", "info", "x"), h("c", "info", "x")}
-	eq(t, RankAndFilter(fts, nil, "", "", 2), "a", "b")
-}
-
-func TestRankAndFilterLimitZeroKeepsAll(t *testing.T) {
-	fts := []Hit{h("a", "info", "x"), h("b", "info", "x")}
-	eq(t, RankAndFilter(fts, nil, "", "", 0), "a", "b")
-}
-
-func TestHybridFusesBothRetrievers(t *testing.T) {
-	fts := []Hit{h("only-fts", "info", "x"), h("both", "info", "x")}
-	vec := []Hit{h("only-vec", "info", "x"), h("both", "info", "x")}
-	eq(t, Hybrid(fts, vec, 0), "both", "only-fts", "only-vec")
-}
-
-func TestHybridTiesAreDeterministic(t *testing.T) {
-	fts := []Hit{h("b", "info", "x"), h("a", "info", "x")}
-	first := ids(Hybrid(fts, nil, 0))
-	for i := 0; i < 50; i++ {
-		got := ids(Hybrid(fts, nil, 0))
-		for j := range first {
-			if got[j] != first[j] {
-				t.Fatalf("unstable order: %v then %v", first, got)
-			}
-		}
-	}
-}
-
-func TestHybridKeepsVectorScoreForSharedHit(t *testing.T) {
-	fts := []Hit{{ID: "x", Root: "info", Score: 0}}
-	vec := []Hit{{ID: "x", Root: "info", Score: 0.87}}
-	got := Hybrid(fts, vec, 0)
-	if len(got) != 1 || got[0].Score != 0.87 {
-		t.Fatalf("got %+v, want score 0.87", got)
-	}
-}
-
-// The old parser dropped unknown flags and appended their arguments to the
-// query, so `search "q" --hop 1` searched for "q 1". --hop is not implemented
-// here (needs File edges); it must still fail closed instead of changing q.
-func TestParseHopIsNotSwallowedIntoTheQuery(t *testing.T) {
-	_, err := ParseArgs([]string{"what runs on arc-2", "--hop", "1"})
-	if err == nil {
-		t.Fatal("expected --hop to error (not implemented), not be swallowed")
-	}
-	if !strings.Contains(err.Error(), "--hop") {
-		t.Fatalf("error should name --hop, got %v", err)
-	}
-}
-
-func TestParseRejectsUnknownFlags(t *testing.T) {
-	if _, err := ParseArgs([]string{"query", "--nope"}); err == nil {
-		t.Fatal("unknown flag accepted")
-	}
-}
-
-func TestParseRejectsBadValues(t *testing.T) {
-	for _, args := range [][]string{
-		{"q", "-n", "zero"},
-		{"q", "-n", "0"},
-		{"q", "--root", "nonsense"},
-		{"q", "--hop"},
-		{"--json"},
-	} {
-		if _, err := ParseArgs(args); err == nil {
-			t.Errorf("accepted %v", args)
-		}
-	}
-}
-
-func TestParseDefaults(t *testing.T) {
-	opt, err := ParseArgs([]string{"two", "words", "--json"})
-	if err != nil || opt.Query != "two words" || opt.Limit != 20 || !opt.JSONOut {
-		t.Fatalf("got %+v err=%v", opt, err)
-	}
-}
-
-func TestListModelNeedsNoQuery(t *testing.T) {
-	if _, err := ParseArgs([]string{"--list-model"}); err != nil {
-		t.Fatalf("unexpected error: %v", err)
-	}
-}
-
-func TestUsageNamesBrainSearch(t *testing.T) {
-	if !strings.Contains(Usage, "bin/brain/search.go") {
-		t.Fatalf("usage must name bin/brain/search.go, got:\n%s", Usage)
-	}
-}
-
-func TestFTSQueryOrdersByScoreDescending(t *testing.T) {
-	if !strings.Contains(FTSStmt, "ORDER BY score DESC") {
-		t.Fatalf("FTS query must order by score DESC, got:\n%s", FTSStmt)
-	}
-}

internal/brain/types.go

@@ -1,13 +0,0 @@
-package brain
-
-import (
-	"os"
-
-	"github.com/eSlider/2dph/internal/brain/rank"
-)
-
-func eps() string { return os.Getenv("KBTEST_EPS") }
-
-// Hit is the search hit type; ranking lives in package rank so CI can test
-// it without the native ladybug library.
-type Hit = rank.Hit

internal/chats/linkedin.go

@@ -1,669 +0,0 @@
-package chats
-
-import (
-	"bufio"
-	"context"
-	"encoding/json"
-	"fmt"
-	"os"
-	"os/exec"
-	"path/filepath"
-	"regexp"
-	"strings"
-	"time"
-)
-
-type LinkedInMCPSource struct {
-	userDataDir string
-	limit       int
-}
-
-type lnInboxItem struct {
-	ThreadID         string `json:"thread_id"`
-	Participants     string `json:"participants"`
-	LastMessage      string `json:"last_message"`
-	LastMessageDate  string `json:"last_message_date"`
-	Unread           bool   `json:"unread"`
-}
-
-// mcp-server-linkedin v4.22 returns get_inbox / get_conversation as
-// {url, sections:{inbox|conversation: textblob}, references:{...}}.
-// The conversation list lives in references (kind=conversation); messages live
-// in the sections text blob, delimited by "<From> sent the following message
-// at <time>" markers. See testdata/linkedin_*.json for the wire shape.
-
-type lnEnvelope struct {
-	URL        string          `json:"url"`
-	Sections   map[string]any  `json:"sections"`
-	References map[string]any  `json:"references"`
-}
-
-type lnReference struct {
-	Kind    string `json:"kind"`
-	URL     string `json:"url"`
-	Text    string `json:"text"`
-	Context string `json:"context"`
-}
-
-type lnMessage struct {
-	From string `json:"from"`
-	Date string `json:"date"`
-	Text string `json:"text"`
-}
-
-var (
-	lnWeekdays = map[string]time.Weekday{
-		"SUNDAY": time.Sunday, "MONDAY": time.Monday, "TUESDAY": time.Tuesday,
-		"WEDNESDAY": time.Wednesday, "THURSDAY": time.Thursday,
-		"FRIDAY": time.Friday, "SATURDAY": time.Saturday,
-	}
-	lnMsgStartRe = regexp.MustCompile(`^(.+?) sent the following messages? at (.+)$`)
-	lnTimeRe     = regexp.MustCompile(`\d{1,2}:\d{2}\s*[AP]M`)
-)
-
-func isWeekdayLine(s string) bool {
-	if _, ok := lnWeekdays[s]; ok {
-		return true
-	}
-	switch s {
-	case "TODAY", "YESTERDAY", "THIS WEEK", "LAST WEEK":
-		return true
-	}
-	return lnMonthDayRe.MatchString(s)
-}
-
-var lnMonthDayRe = regexp.MustCompile(`^[A-Z]{3}\s+\d{1,2}$`)
-
-// parseLinkedInInbox extracts conversations from a get_inbox response.
-func parseLinkedInInbox(text string) []lnInboxItem {
-	var env lnEnvelope
-	if err := json.Unmarshal([]byte(text), &env); err != nil {
-		return nil
-	}
-	refs, _ := env.References["inbox"].([]any)
-	var items []lnInboxItem
-	for _, r := range refs {
-		rr, ok := r.(map[string]any)
-		if !ok {
-			continue
-		}
-		if rr["kind"] != "conversation" {
-			continue
-		}
-		u, _ := rr["url"].(string)
-		tid := threadIDFromURL(u)
-		if !validThreadID(tid) {
-			continue
-		}
-		name, _ := rr["text"].(string)
-		items = append(items, lnInboxItem{
-			ThreadID:     tid,
-			Participants: name,
-		})
-	}
-	return items
-}
-
-// parseLinkedInConversation parses the sections.conversation text blob into
-// messages. Messages are delimited by "<From> sent the following message(s) at
-// <time>" lines; each message body runs until the next marker. Day headers
-// (all-caps weekdays) provide date context; times are mapped to the most
-// recent matching weekday.
-func parseLinkedInConversation(text string) []lnMessage {
-	var env lnEnvelope
-	if err := json.Unmarshal([]byte(text), &env); err != nil {
-		return nil
-	}
-	blob, _ := env.Sections["conversation"].(string)
-	if blob == "" {
-		return nil
-	}
-
-	var msgs []lnMessage
-	var cur *lnMessage
-	var body []string
-	day := ""
-
-	flush := func() {
-		if cur == nil {
-			return
-		}
-		cur.Text = strings.TrimSpace(strings.Join(body, "\n"))
-		if ts := linkedInTimestamp(day, cur.Date); ts != "" {
-			cur.Date = ts
-		}
-		if cur.Text != "" {
-			msgs = append(msgs, *cur)
-		}
-		cur = nil
-		body = nil
-	}
-
-	for _, raw := range strings.Split(blob, "\n") {
-		line := strings.TrimSpace(raw)
-		if line == "" {
-			continue
-		}
-		if isWeekdayLine(line) {
-			if line != day {
-				// A new day header terminates the previous message,
-				// which must keep the earlier date context.
-				flush()
-			}
-			day = line
-			continue
-		}
-		if m := lnMsgStartRe.FindStringSubmatch(line); m != nil {
-			flush()
-			cur = &lnMessage{From: strings.TrimSpace(m[1]), Date: strings.TrimSpace(m[2])}
-			continue
-		}
-		if cur == nil {
-			continue
-		}
-		// Skip "View X's profile" and the "<From> (pronouns) <time>" header.
-		if strings.HasPrefix(line, "View ") && strings.HasSuffix(line, "'s profile") {
-			continue
-		}
-		if strings.HasPrefix(line, cur.From) && lnTimeRe.MatchString(line) {
-			continue
-		}
-		body = append(body, line)
-	}
-	flush()
-	return msgs
-}
-
-// linkedInTimestamp maps a weekday, relative, or MON DD date header + clock
-// string to a timestamp, or returns "" when the clock cannot be parsed.
-func linkedInTimestamp(day, clock string) string {
-	t, err := time.Parse("3:04 PM", clock)
-	if err != nil {
-		return ""
-	}
-	now := time.Now()
-	var d time.Time
-	if wd, ok := lnWeekdays[day]; ok {
-		diff := (int(now.Weekday()) - int(wd) + 7) % 7
-		d = now.AddDate(0, 0, -diff)
-	} else {
-		switch day {
-		case "TODAY":
-			d = now
-		case "YESTERDAY":
-			d = now.AddDate(0, 0, -1)
-		case "THIS WEEK":
-			diff := int(now.Weekday())
-			d = now.AddDate(0, 0, -diff)
-		case "LAST WEEK":
-			diff := int(now.Weekday()) + 7
-			d = now.AddDate(0, 0, -diff)
-		default:
-			if m := lnMonthDayRe.FindStringSubmatch(day); m != nil {
-				// MON DD without a year: resolve to the most recent
-				// occurrence that is not in the future.
-				d = monthDayDate(day, now)
-				if d.IsZero() {
-					return t.Format("15:04")
-				}
-			} else {
-				// No date context; keep bare clock time.
-				return t.Format("15:04")
-			}
-		}
-	}
-	res := time.Date(d.Year(), d.Month(), d.Day(), t.Hour(), t.Minute(), 0, 0, time.UTC)
-	return res.UTC().Format(time.RFC3339)
-}
-
-var lnMonths = map[string]time.Month{
-	"JAN": time.January, "FEB": time.February, "MAR": time.March,
-	"APR": time.April, "MAY": time.May, "JUN": time.June,
-	"JUL": time.July, "AUG": time.August, "SEP": time.September,
-	"OCT": time.October, "NOV": time.November, "DEC": time.December,
-}
-
-// monthDayDate resolves "MON DD" to the most recent occurrence of that date,
-// preferring the current year and falling back to the previous year when the
-// date is in the future. Returns zero time when unresolvable.
-func monthDayDate(day string, now time.Time) time.Time {
-	parts := strings.Fields(day)
-	if len(parts) != 2 {
-		return time.Time{}
-	}
-	mo, ok := lnMonths[parts[0]]
-	if !ok {
-		return time.Time{}
-	}
-	var dd int
-	if _, err := fmt.Sscanf(parts[1], "%d", &dd); err != nil {
-		return time.Time{}
-	}
-	if dd < 1 || dd > 31 {
-		return time.Time{}
-	}
-	d := time.Date(now.Year(), mo, dd, 0, 0, 0, 0, time.UTC)
-	if d.After(now) {
-		d = d.AddDate(-1, 0, 0)
-	}
-	if d.After(now) {
-		return time.Time{}
-	}
-	return d
-}
-
-func threadIDFromURL(u string) string {
-	u = strings.TrimSuffix(u, "/")
-	idx := strings.LastIndex(u, "/")
-	if idx < 0 {
-		return ""
-	}
-	return u[idx+1:]
-}
-
-// validThreadID rejects path segments that are not real thread ids (e.g. the
-// literal "thread" or an empty trailing segment).
-func validThreadID(id string) bool {
-	if id == "" || id == "thread" {
-		return false
-	}
-	return true
-}
-
-func NewLinkedInMCPSource(userDataDir string) *LinkedInMCPSource {
-	return &LinkedInMCPSource{userDataDir: userDataDir}
-}
-
-func (s *LinkedInMCPSource) Name() string { return "linkedin" }
-
-func (s *LinkedInMCPSource) Sync(ctx context.Context, outDir string, limit int) error {
-	if limit > 0 {
-		s.limit = limit
-	}
-
-	// getConversation fetches one thread, recreating the MCP server when it
-	// wedges. A single 429 makes mcp-server-linkedin close its browser and
-	// refuse every later call ("still has a browser open"), so a broken server
-	// must be restarted rather than hammered.
-	getConversation := func(threadID string) ([]lnMessage, error) {
-		client, err := newLinkedInMCP(ctx, s.userDataDir)
-		if err != nil {
-			return nil, fmt.Errorf("linkedin mcp: %w", err)
-		}
-		defer client.Close()
-		msgs, err := client.GetConversation(ctx, "", threadID, msgLimitFor(s.limit))
-		if err != nil && wedged(err) {
-			fmt.Fprintf(os.Stderr, "chats: %s: server wedged, restarting broker\n", threadID)
-			time.Sleep(5 * time.Second)
-			client2, cerr := newLinkedInMCP(ctx, s.userDataDir)
-			if cerr == nil {
-				defer client2.Close()
-				msgs, err = client2.GetConversation(ctx, "", threadID, msgLimitFor(s.limit))
-			}
-		}
-		return msgs, err
-	}
-
-	client, err := newLinkedInMCP(ctx, s.userDataDir)
-	if err != nil {
-		return fmt.Errorf("linkedin mcp: %w", err)
-	}
-	inbox, err := client.GetInbox(ctx, 50)
-	if err != nil {
-		client.Close()
-		return fmt.Errorf("get_inbox: %w", err)
-	}
-	client.Close()
-	if len(inbox) == 0 {
-		fmt.Println("chats: no LinkedIn conversations found")
-		return nil
-	}
-
-	fmt.Printf("chats: found %d LinkedIn conversations\n", len(inbox))
-
-	for _, conv := range inbox {
-		convID := sanitizeDir(conv.ThreadID)
-		if convID == "" {
-			convID = fmt.Sprintf("conv_%d", time.Now().UnixNano())
-		}
-
-		parts := strings.SplitN(conv.Participants, ",", 2)
-		chatName := strings.TrimSpace(parts[0])
-		if chatName == "" {
-			chatName = convID
-		}
-
-		chatDir := filepath.Join(outDir, "linkedin", convID)
-		if err := os.MkdirAll(chatDir, 0755); err != nil {
-			fmt.Fprintf(os.Stderr, "chats: mkdir %s: %v\n", chatDir, err)
-			continue
-		}
-
-		msgs, err := getConversation(conv.ThreadID)
-		if err != nil {
-			fmt.Fprintf(os.Stderr, "chats: get_conversation %s: %v\n", convID, err)
-			continue
-		}
-
-		jsonlPath := filepath.Join(chatDir, "messages.jsonl")
-
-		// A rate-limited response can parse to zero messages. Never clobber
-		// previously synced data with an empty file.
-		if len(msgs) == 0 {
-			fmt.Fprintf(os.Stderr, "chats: %s (%s): 0 messages parsed, keeping existing file\n", chatName, convID)
-			continue
-		}
-
-		f, err := os.Create(jsonlPath)
-		if err != nil {
-			fmt.Fprintf(os.Stderr, "chats: create %s: %v\n", jsonlPath, err)
-			continue
-		}
-
-		enc := json.NewEncoder(f)
-		written := 0
-		for i, m := range msgs {
-			text := m.Text
-			if text == "" {
-				continue
-			}
-
-			ts := m.Date
-			if t, err := time.Parse("2006-01-02T15:04:05Z07:00", m.Date); err == nil {
-				ts = t.UTC().Format(time.RFC3339)
-			} else if t, err := time.Parse(time.RFC3339, m.Date); err == nil {
-				ts = t.UTC().Format(time.RFC3339)
-			}
-
-			chatMsg := Message{
-				ID:        fmt.Sprintf("li_%s_%d", convID, i),
-				Timestamp: ts,
-				From:      m.From,
-				Text:      text,
-				Platform:  "linkedin",
-			}
-			if err := enc.Encode(chatMsg); err != nil {
-				fmt.Fprintf(os.Stderr, "chats: encode: %v\n", err)
-				continue
-			}
-			written++
-		}
-		f.Close()
-
-		fmt.Printf("chats: synced %s (%s) — %d messages\n", chatName, convID, written)
-
-		// Pause between conversations to reduce LinkedIn rate limiting.
-		select {
-		case <-ctx.Done():
-			return ctx.Err()
-		case <-time.After(2 * time.Second):
-		}
-	}
-
-	return nil
-}
-
-type linkedInMCPClient struct {
-	cmd    *exec.Cmd
-	stdin  *bufio.Writer
-	stdout *bufio.Scanner
-	msgID  int
-}
-
-func newLinkedInMCP(ctx context.Context, userDataDir string) (*linkedInMCPClient, error) {
-	args := []string{
-		"mcp-server-linkedin@latest",
-		"--user-data-dir", userDataDir,
-		"--no-auto-import",
-		"--no-daemon",
-		"--transport", "stdio",
-		"--login-timeout", "10",
-		"--browser-wait", "1",
-		"--browser-idle-timeout", "10",
-		"--log-level", "ERROR",
-	}
-
-	cmd := exec.CommandContext(ctx, "uvx", args...)
-	cmd.Env = os.Environ()
-
-	stdin, err := cmd.StdinPipe()
-	if err != nil {
-		return nil, fmt.Errorf("stdin pipe: %w", err)
-	}
-	stdout, err := cmd.StdoutPipe()
-	if err != nil {
-		return nil, fmt.Errorf("stdout pipe: %w", err)
-	}
-	cmd.Stderr = os.Stderr
-
-	if err := cmd.Start(); err != nil {
-		return nil, fmt.Errorf("start: %w", err)
-	}
-
-	c := &linkedInMCPClient{
-		cmd:    cmd,
-		stdin:  bufio.NewWriter(stdin),
-		stdout: bufio.NewScanner(stdout),
-		msgID:  0,
-	}
-	c.stdout.Buffer(make([]byte, 1<<20), 1<<20)
-
-	if err := c.initialize(ctx); err != nil {
-		c.Close()
-		return nil, fmt.Errorf("init: %w", err)
-	}
-	return c, nil
-}
-
-func (c *linkedInMCPClient) nextID() int {
-	c.msgID++
-	return c.msgID
-}
-
-func (c *linkedInMCPClient) initialize(ctx context.Context) error {
-	params := map[string]interface{}{
-		"protocolVersion": "2024-11-05",
-		"capabilities":    map[string]interface{}{},
-		"clientInfo": map[string]string{
-			"name":    "chats-sync",
-			"version": "0.1.0",
-		},
-	}
-	_, err := c.send(ctx, "initialize", params)
-	return err
-}
-
-func (c *linkedInMCPClient) send(ctx context.Context, method string, params interface{}) (json.RawMessage, error) {
-	id := c.nextID()
-	req := map[string]interface{}{
-		"jsonrpc": "2.0",
-		"id":      id,
-		"method":  method,
-	}
-	if params != nil {
-		req["params"] = params
-	}
-	body, err := json.Marshal(req)
-	if err != nil {
-		return nil, fmt.Errorf("marshal: %w", err)
-	}
-
-	if _, err := c.stdin.Write(body); err != nil {
-		return nil, fmt.Errorf("write: %w", err)
-	}
-	if err := c.stdin.WriteByte('\n'); err != nil {
-		return nil, fmt.Errorf("newline: %w", err)
-	}
-	if err := c.stdin.Flush(); err != nil {
-		return nil, fmt.Errorf("flush: %w", err)
-	}
-
-	for c.stdout.Scan() {
-		line := c.stdout.Text()
-		if line == "" {
-			continue
-		}
-		var resp struct {
-			JSONRPC string          `json:"jsonrpc"`
-			ID      int             `json:"id"`
-			Result  json.RawMessage `json:"result,omitempty"`
-			Error   *struct {
-				Code    int    `json:"code"`
-				Message string `json:"message"`
-			} `json:"error,omitempty"`
-		}
-		if err := json.Unmarshal([]byte(line), &resp); err != nil {
-			return nil, fmt.Errorf("unmarshal: %w\nline: %s", err, line[:min(len(line), 500)])
-		}
-		if resp.Error != nil {
-			return nil, fmt.Errorf("rpc error %d: %s", resp.Error.Code, resp.Error.Message)
-		}
-		return resp.Result, nil
-	}
-	return nil, fmt.Errorf("no response: %w", c.stdout.Err())
-}
-
-// msgLimitFor returns the per-conversation message cap for a sync.
-func msgLimitFor(limit int) int {
-	if limit > 0 {
-		return limit
-	}
-	return 100
-}
-
-// wedged reports whether a conversation fetch failure means the MCP server
-// closed its browser and will refuse every later call.
-func wedged(err error) bool {
-	return strings.Contains(err.Error(), "still has a browser open")
-}
-
-// callTool invokes an MCP tool, retrying transient (rate-limit) failures.
-func (c *linkedInMCPClient) callTool(ctx context.Context, name string, params map[string]interface{}) (json.RawMessage, error) {
-	var lastErr error
-	for attempt := 0; attempt < 3; attempt++ {
-		if attempt > 0 {
-			delay := time.Duration(1<<uint(attempt)) * 5 * time.Second
-			select {
-			case <-ctx.Done():
-				return nil, ctx.Err()
-			case <-time.After(delay):
-			}
-		}
-		result, err := c.send(ctx, "tools/call", map[string]interface{}{
-			"name":      name,
-			"arguments": params,
-		})
-		if err == nil {
-			// Tool-level errors surface as a successful RPC with an
-			// isError=true content entry.
-			if hint := toolErrorHint(result); hint != "" {
-				lastErr = fmt.Errorf("%s error: %s", name, hint)
-				if !isTransientLinkedInError(lastErr.Error()) {
-					return nil, lastErr
-				}
-				continue
-			}
-			return result, nil
-		}
-		lastErr = err
-		if !isTransientLinkedInError(err.Error()) {
-			return nil, err
-		}
-	}
-	return nil, fmt.Errorf("%s: %w", name, lastErr)
-}
-
-// toolErrorHint returns the tool's error text when the result has isError set.
-func toolErrorHint(result json.RawMessage) string {
-	var toolRes struct {
-		Content []struct {
-			Type string `json:"type"`
-			Text string `json:"text"`
-		} `json:"content"`
-		IsError bool `json:"isError"`
-	}
-	if err := json.Unmarshal(result, &toolRes); err != nil || !toolRes.IsError {
-		return ""
-	}
-	if len(toolRes.Content) > 0 {
-		return toolRes.Content[0].Text
-	}
-	return "unknown tool error"
-}
-
-// isTransientLinkedInError reports whether a fetch failed due to rate limiting
-// or a transient server error, which may succeed on retry.
-func isTransientLinkedInError(msg string) bool {
-	return strings.Contains(msg, "503") || strings.Contains(msg, "429") ||
-		strings.Contains(msg, "ERR_HTTP_RESPONSE_CODE_FAILURE") ||
-		strings.Contains(msg, "ERR_ABORTED") ||
-		strings.Contains(msg, "Error calling tool") ||
-		strings.Contains(msg, "Unexpected error") ||
-		strings.Contains(msg, "still has a browser open")
-}
-
-func (c *linkedInMCPClient) GetInbox(ctx context.Context, limit int) ([]lnInboxItem, error) {
-	params := map[string]interface{}{
-		"limit": limit,
-	}
-	result, err := c.callTool(ctx, "get_inbox", params)
-	if err != nil {
-		return nil, err
-	}
-
-	var toolRes struct {
-		Content []struct {
-			Type string `json:"type"`
-			Text string `json:"text"`
-		} `json:"content"`
-		IsError bool `json:"isError"`
-	}
-	if err := json.Unmarshal(result, &toolRes); err != nil {
-		return nil, fmt.Errorf("unmarshal tool: %w", err)
-	}
-	if len(toolRes.Content) == 0 {
-		return nil, nil
-	}
-
-	text := toolRes.Content[0].Text
-	return parseLinkedInInbox(text), nil
-}
-
-func (c *linkedInMCPClient) GetConversation(ctx context.Context, username, threadID string, limit int) ([]lnMessage, error) {
-	params := map[string]interface{}{
-		"linkedin_username": username,
-		"thread_id":         threadID,
-		"index":             limit,
-	}
-	result, err := c.callTool(ctx, "get_conversation", params)
-	if err != nil {
-		return nil, err
-	}
-
-	var toolRes struct {
-		Content []struct {
-			Type string `json:"type"`
-			Text string `json:"text"`
-		} `json:"content"`
-		IsError bool `json:"isError"`
-	}
-	if err := json.Unmarshal(result, &toolRes); err != nil {
-		return nil, fmt.Errorf("unmarshal tool: %w", err)
-	}
-	if len(toolRes.Content) == 0 {
-		return nil, nil
-	}
-
-	text := toolRes.Content[0].Text
-	return parseLinkedInConversation(text), nil
-}
-
-func (c *linkedInMCPClient) Close() error {
-	if c.stdin != nil {
-		c.stdin.Flush()
-	}
-	if c.cmd != nil && c.cmd.Process != nil {
-		c.cmd.Process.Kill()
-	}
-	return nil
-}

internal/chats/linkedin_test.go

@@ -1,215 +0,0 @@
-package chats
-
-import (
-	"errors"
-	"os"
-	"path/filepath"
-	"strings"
-	"testing"
-	"time"
-)
-
-func readFixture(t *testing.T, name string) string {
-	t.Helper()
-	data, err := os.ReadFile(filepath.Join("testdata", name))
-	if err != nil {
-		t.Fatal(err)
-	}
-	return string(data)
-}
-
-// TestParseLinkedInInbox verifies get_inbox parsing against the v4.22 wire
-// format (testdata/linkedin_inbox.json — synthetic Alice/Bob/Charlie).
-func TestParseLinkedInInbox(t *testing.T) {
-	text := readFixture(t, "linkedin_inbox.json")
-	items := parseLinkedInInbox(text)
-	if len(items) != 2 {
-		t.Fatalf("expected 2 conversations (empty thread url skipped), got %d", len(items))
-	}
-
-	first := items[0]
-	if first.ThreadID == "" {
-		t.Error("expected thread id extracted from reference url")
-	}
-	if first.Participants != "Alice Example" {
-		t.Errorf("participants=%q, want Alice Example", first.Participants)
-	}
-	if !strings.HasPrefix(first.ThreadID, "2-") {
-		t.Errorf("unexpected thread id format %q", first.ThreadID)
-	}
-	if items[1].Participants != "Charlie Example" {
-		t.Errorf("second participant=%q, want Charlie Example", items[1].Participants)
-	}
-}
-
-// TestParseLinkedInInboxBadJSON verifies a non-JSON response yields no items
-// rather than a panic or error.
-func TestParseLinkedInInboxBadJSON(t *testing.T) {
-	if got := parseLinkedInInbox("Session expired"); len(got) != 0 {
-		t.Fatalf("expected no items for non-JSON, got %d", len(got))
-	}
-}
-
-// TestParseLinkedInConversation verifies message extraction from the sections
-// blob (testdata/linkedin_conversation.json — synthetic Alice/Bob).
-func TestParseLinkedInConversation(t *testing.T) {
-	text := readFixture(t, "linkedin_conversation.json")
-	msgs := parseLinkedInConversation(text)
-	if len(msgs) != 2 {
-		t.Fatalf("expected 2 messages, got %d", len(msgs))
-	}
-
-	if msgs[0].From != "Alice Example" {
-		t.Errorf("from=%q, want Alice Example", msgs[0].From)
-	}
-	if !strings.Contains(msgs[0].Text, "Senior Software Engineer") {
-		t.Errorf("alice text missing role, got %q", msgs[0].Text)
-	}
-	if msgs[0].Date == "" {
-		t.Error("expected message date")
-	}
-	if msgs[1].From != "Bob Example" {
-		t.Errorf("from=%q, want Bob Example", msgs[1].From)
-	}
-}
-
-// TestParseLinkedInConversationEmpty verifies empty/non-JSON blobs parse to
-// zero messages.
-func TestParseLinkedInConversationEmpty(t *testing.T) {
-	if got := parseLinkedInConversation("no data here"); len(got) != 0 {
-		t.Fatalf("expected 0 messages, got %d", len(got))
-	}
-}
-
-// TestLinkedInTimestamp verifies weekday+clock resolution to a recent UTC date.
-func TestLinkedInTimestamp(t *testing.T) {
-	// The most recent Wednesday before/equal to "now".
-	ts := linkedInTimestamp("WEDNESDAY", "10:02 AM")
-	parsed, err := time.Parse(time.RFC3339, ts)
-	if err != nil {
-		t.Fatalf("unparseable timestamp %q: %v", ts, err)
-	}
-	if parsed.Weekday() != time.Wednesday {
-		t.Errorf("expected Wednesday, got %s", parsed.Weekday())
-	}
-	if parsed.Hour() != 10 || parsed.Minute() != 2 {
-		t.Errorf("expected 10:02, got %02d:%02d", parsed.Hour(), parsed.Minute())
-	}
-
-	now := time.Now()
-	diff := now.Sub(parsed)
-	if diff < 0 || diff > 7*24*time.Hour {
-		t.Errorf("timestamp %s is not within the last week of %s", parsed, now)
-	}
-
-	if got := linkedInTimestamp("MONDAY", "garbage"); got != "" {
-		t.Errorf("expected empty for bad clock, got %q", got)
-	}
-	if got := linkedInTimestamp("", "1:22 PM"); got != "13:22" {
-		t.Errorf("expected bare 13:22 for missing weekday, got %q", got)
-	}
-
-	// Relative day headers must resolve to full dates, not bare clocks.
-	today := linkedInTimestamp("TODAY", "9:42 AM")
-	yp, err := time.Parse(time.RFC3339, today)
-	if err != nil {
-		t.Fatalf("TODAY unparseable %q: %v", today, err)
-	}
-	if yp.Year() != now.Year() || yp.Month() != now.Month() || yp.Day() != now.Day() {
-		t.Errorf("TODAY expected %v, got %v", now, yp)
-	}
-	yest := linkedInTimestamp("YESTERDAY", "3:00 PM")
-	yp, err = time.Parse(time.RFC3339, yest)
-	if err != nil {
-		t.Fatalf("YESTERDAY unparseable %q: %v", yest, err)
-	}
-	if yp.Day() != now.AddDate(0, 0, -1).Day() {
-		t.Errorf("YESTERDAY expected day %d, got %d", now.AddDate(0, 0, -1).Day(), yp.Day())
-	}
-
-	// MON DD header (e.g. "JUN 25"): must resolve to a full date. The
-	// timestamp should fall within the current year (falling back to the
-	// prior year if the date would be in the future).
-	md := linkedInTimestamp("JUN 25", "10:48 AM")
-	mp, err := time.Parse(time.RFC3339, md)
-	if err != nil {
-		t.Fatalf("MON DD unparseable %q: %v", md, err)
-	}
-	if mp.Year() != now.Year() && mp.Year() != now.Year()-1 {
-		t.Errorf("JUN 25 expected year %d or %d, got %d", now.Year(), now.Year()-1, mp.Year())
-	}
-	if mp.Month() != time.June || mp.Day() != 25 {
-		t.Errorf("JUN 25 expected Jun 25, got %s %d", mp.Month(), mp.Day())
-	}
-	if mp.After(now) {
-		t.Errorf("JUN 25 resolved to the future: %s > %s", mp, now)
-	}
-}
-
-// TestTransientLinkedInError verifies rate-limit errors are retryable but
-// genuine failures are not.
-func TestTransientLinkedInError(t *testing.T) {
-	retryable := []string{
-		"get_conversation error: Error calling tool 'get_conversation'",
-		"get_conversation error: Unexpected error in get_conversation: net::ERR_HTTP_RESPONSE_CODE_FAILURE",
-		"rpc error 503: rate limited",
-		"rpc error 429: too many requests",
-		"get_conversation: get_conversation error: This server still has a browser open on the profile.",
-	}
-	for _, msg := range retryable {
-		if !isTransientLinkedInError(msg) {
-			t.Errorf("expected %q to be transient", msg)
-		}
-	}
-	permanent := []string{
-		"get_inbox error: bad credentials",
-		"rpc error -32602: Invalid request parameters",
-		"unmarshal: unexpected end of JSON input",
-	}
-	for _, msg := range permanent {
-		if isTransientLinkedInError(msg) {
-			t.Errorf("expected %q to be permanent", msg)
-		}
-	}
-}
-
-// TestMsgLimitFor verifies the per-conversation message cap resolution.
-func TestMsgLimitFor(t *testing.T) {
-	if got := msgLimitFor(0); got != 100 {
-		t.Errorf("expected default 100, got %d", got)
-	}
-	if got := msgLimitFor(5); got != 5 {
-		t.Errorf("expected 5, got %d", got)
-	}
-}
-
-// TestWedged verifies the browser-open failure is recognized as a wedge.
-func TestWedged(t *testing.T) {
-	if !wedged(errors.New("get_conversation error: This server still has a browser open on the profile")) {
-		t.Error("expected wedged error to be recognized")
-	}
-	if wedged(errors.New("get_conversation error: bad thing")) {
-		t.Error("unexpected wedge detection")
-	}
-}
-
-// TestThreadIDFromURL verifies thread id extraction.
-func TestThreadIDFromURL(t *testing.T) {
-	cases := []struct {
-		url, want string
-	}{
-		{"/messaging/thread/2-abc123/", "2-abc123"},
-		{"/messaging/thread/2-abc123", "2-abc123"},
-		{"", ""},
-		{"/messaging/thread/", ""},
-	}
-	for _, c := range cases {
-		got := threadIDFromURL(c.url)
-		if c.want == "" && validThreadID(got) {
-			t.Errorf("threadIDFromURL(%q) = %q, want empty", c.url, got)
-		}
-		if c.want != "" && got != c.want {
-			t.Errorf("threadIDFromURL(%q) = %q, want %q", c.url, got, c.want)
-		}
-	}
-}

internal/chats/paths.go

@@ -1,39 +0,0 @@
-package chats
-
-import (
-	"os"
-	"strings"
-)
-
-// Root locates the 2dph project root (KB_ROOT, or walk up for var/ or .git).
-func Root() 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 "."
-}
-
-// Dir is var/chats under the project root.
-func Dir() string {
-	return Root() + "/var/chats"
-}

internal/chats/sync_linkedin.go

@@ -1,105 +0,0 @@
-package chats
-
-import (
-	"context"
-	"flag"
-	"fmt"
-	"os"
-	"os/exec"
-	"path/filepath"
-	"time"
-)
-
-func checkLinkedInSession(userDataDir string) (bool, error) {
-	// Validate the source-session files without launching a browser. A full
-	// `--status` run spawns Chromium and loads /feed/, doubling the automation
-	// exposed to LinkedIn (429 rate limits) before the sync even starts.
-	root := filepath.Dir(userDataDir)
-	sessionFiles := []string{
-		filepath.Join(root, "source-state.json"),
-		filepath.Join(root, "cookies.json"),
-		filepath.Join(userDataDir, "Default", "Cookies"),
-	}
-	for _, f := range sessionFiles {
-		if _, err := os.Stat(f); err != nil {
-			return true, fmt.Errorf("missing session file %s", f)
-		}
-	}
-	return false, nil
-}
-
-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")
-	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 sync linkedin [--limit N] [--refresh]")
-		return 0
-	}
-
-	userDataDir := envVar("LINKEDIN_USER_DATA_DIR", "")
-	if userDataDir == "" {
-		home, _ := os.UserHomeDir()
-		userDataDir = home + "/.linkedin-mcp/profile"
-	}
-
-	if *refresh {
-		if code := refreshLinkedInSession(userDataDir); code != 0 {
-			return code
-		}
-	}
-
-	// Check session files first (no browser launch).
-	loginNeeded, err := checkLinkedInSession(userDataDir)
-	if err != nil {
-		fmt.Fprintf(os.Stderr, "chats: linkedin status check: %v\n", err)
-	}
-	if loginNeeded {
-		fmt.Fprintf(os.Stderr, "chats: LinkedIn session missing. Run:\n")
-		fmt.Fprintf(os.Stderr, "  chats sync linkedin --refresh\n")
-		fmt.Fprintf(os.Stderr, "or point LINKEDIN_USER_DATA_DIR at a valid session\n")
-		return 1
-	}
-
-	src := NewLinkedInMCPSource(userDataDir)
-
-	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Minute)
-	defer cancel()
-
-	start := time.Now()
-	if err := src.Sync(ctx, Dir(), *limit); err != nil {
-		fmt.Fprintf(os.Stderr, "chats sync linkedin: %v\n", err)
-		return 1
-	}
-	fmt.Printf("chats sync linkedin: completed in %s\n", time.Since(start).Round(time.Millisecond))
-	return 0
-}
-
-// refreshLinkedInSession re-syncs the LinkedIn source session from the live
-// webtop browser via the vendored refresh-linkedin-session helper.
-func refreshLinkedInSession(userDataDir string) int {
-	exe, err := os.Executable()
-	if err != nil {
-		fmt.Fprintf(os.Stderr, "chats: resolve executable: %v\n", err)
-		return 1
-	}
-	helper := filepath.Join(filepath.Dir(exe), "refresh-linkedin-session")
-	if _, err := os.Stat(helper); err != nil {
-		// Fall back to the source tree helper next to this command file.
-		helper = "bin/chats/refresh-linkedin-session"
-	}
-	root := filepath.Dir(userDataDir)
-	cmd := exec.Command(helper, "--root", root)
-	cmd.Stdout = os.Stderr
-	cmd.Stderr = os.Stderr
-	if err := cmd.Run(); err != nil {
-		fmt.Fprintf(os.Stderr, "chats: linkedin session refresh: %v\n", err)
-		return 1
-	}
-	return 0
-}

internal/chats/testdata/linkedin_conversation.json

@@ -1,12 +0,0 @@
-{
-  "url": "https://www.linkedin.com/messaging/thread/2-YWxpY2UtYm9iLXRocmVhZC0xMjM=/",
-  "sections": {
-    "conversation": "WEDNESDAY\nAlice Example sent the following message at 10:02 AM\nView Alice Example's profile\nAlice Example  (She/Her)  10:02 AM\nHi Bob, we have a Senior Software Engineer role that matches your Go and Python background. Happy to share more if you are open to a chat.\n\nBob Example sent the following messages at 1:22 PM\nView Bob Example's profile\nBob Example  1:22 PM\nHi Alice, thanks for reaching out — yes, I am open to exploring a Senior Software Engineer role. Happy to do a short video call.\n"
-  },
-  "references": {
-    "conversation": [
-      {"kind": "person", "url": "/in/alice-example/", "text": "Alice Example"},
-      {"kind": "person", "url": "/in/bob-example/", "text": "Bob Example"}
-    ]
-  }
-}

internal/chats/testdata/linkedin_inbox.json

@@ -1,34 +0,0 @@
-{
-  "url": "https://www.linkedin.com/messaging/",
-  "sections": {
-    "inbox": "Messaging\nInbox\nConversation List\nAlice Example\nExciting opportunity for a senior software engineer\n"
-  },
-  "references": {
-    "inbox": [
-      {
-        "kind": "conversation",
-        "url": "/messaging/thread/2-YWxpY2UtYm9iLXRocmVhZC0xMjM=/",
-        "context": "inbox",
-        "text": "Alice Example"
-      },
-      {
-        "kind": "person",
-        "url": "/in/alice-example/",
-        "text": "Alice Example",
-        "context": "inbox"
-      },
-      {
-        "kind": "conversation",
-        "url": "/messaging/thread/2-Y2hhcmxpZS1ib2ItdGhyZWFkLTQ1Ng==/",
-        "context": "inbox",
-        "text": "Charlie Example"
-      },
-      {
-        "kind": "conversation",
-        "url": "/messaging/thread/",
-        "context": "inbox",
-        "text": "should-be-skipped"
-      }
-    ]
-  }
-}

internal/cmdbin/exec.go

@@ -1,54 +0,0 @@
-package cmdbin
-
-import (
-	"errors"
-	"os"
-	"os/exec"
-	"path/filepath"
-	"strings"
-)
-
-// Root is the 2dph checkout (KB_ROOT, or walk up for .git / var).
-func Root() 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(filepath.Join(wd, ".git")); err == nil {
-			return wd
-		}
-		if _, err := os.Stat(filepath.Join(wd, "var")); err == nil {
-			return wd
-		}
-		parent := filepath.Dir(wd)
-		if parent == wd {
-			break
-		}
-		wd = parent
-	}
-	return "."
-}
-
-// ExecFile runs repo-relative path (python/bash shebang scripts) with stdio.
-func ExecFile(rel string, args []string) int {
-	path := filepath.Join(Root(), filepath.FromSlash(rel))
-	cmd := exec.Command(path, args...)
-	cmd.Stdin = os.Stdin
-	cmd.Stdout = os.Stdout
-	cmd.Stderr = os.Stderr
-	cmd.Dir = Root()
-	if err := cmd.Run(); err != nil {
-		if ee, ok := err.(*exec.ExitError); ok {
-			return ee.ExitCode()
-		}
-		if errors.Is(err, os.ErrNotExist) || strings.Contains(err.Error(), "no such file") {
-			return 127
-		}
-		return 1
-	}
-	return 0
-}

internal/cmdbin/exec_test.go

@@ -1,34 +0,0 @@
-package cmdbin
-
-import (
-	"os"
-	"path/filepath"
-	"testing"
-)
-
-func TestRootHonorsKBROOT(t *testing.T) {
-	dir := t.TempDir()
-	t.Setenv("KB_ROOT", dir)
-	if got := Root(); got != dir {
-		t.Fatalf("Root() = %q, want %q", got, dir)
-	}
-}
-
-func TestExecFileMissingIs127(t *testing.T) {
-	t.Setenv("KB_ROOT", t.TempDir())
-	if code := ExecFile("no/such-tool", nil); code != 127 {
-		t.Fatalf("exit = %d, want 127", code)
-	}
-}
-
-func TestExecFileRuns(t *testing.T) {
-	root := t.TempDir()
-	script := filepath.Join(root, "echo.sh")
-	if err := os.WriteFile(script, []byte("#!/bin/sh\nexit 3\n"), 0o755); err != nil {
-		t.Fatal(err)
-	}
-	t.Setenv("KB_ROOT", root)
-	if code := ExecFile("echo.sh", nil); code != 3 {
-		t.Fatalf("exit = %d, want 3", code)
-	}
-}

internal/gitlog/gitlog.go

@@ -1,180 +0,0 @@
-// Package gitlog reads commit history with go-git (no git binary).
-package gitlog
-
-import (
-	"errors"
-	"fmt"
-	"path"
-	"path/filepath"
-	"sort"
-	"strings"
-	"time"
-
-	"github.com/go-git/go-git/v5"
-	"github.com/go-git/go-git/v5/plumbing/object"
-)
-
-type Options struct {
-	Limit int
-	Since time.Time
-}
-
-type Commit struct {
-	SHA     string   `json:"sha"`
-	Author  string   `json:"author"`
-	Email   string   `json:"email"`
-	Date    string   `json:"date"`
-	Subject string   `json:"subject"`
-	Files   []string `json:"files"`
-}
-
-type Leaf struct {
-	Source  string `json:"source"`
-	Repo    string `json:"repo"`
-	Heading string `json:"heading"`
-	Text    string `json:"text"`
-	Type    string `json:"type"`
-	Status  string `json:"status"`
-	Related string `json:"related"`
-}
-
-// Log walks commits from HEAD, newest first, skipping merges.
-func Log(repo string, opt Options) ([]Commit, error) {
-	r, err := git.PlainOpen(repo)
-	if err != nil {
-		return nil, err
-	}
-	logOpt := &git.LogOptions{Order: git.LogOrderCommitterTime}
-	if !opt.Since.IsZero() {
-		t := opt.Since
-		logOpt.Since = &t
-	}
-	iter, err := r.Log(logOpt)
-	if err != nil {
-		return nil, err
-	}
-	defer iter.Close()
-
-	var out []Commit
-	err = iter.ForEach(func(c *object.Commit) error {
-		if c.NumParents() > 1 {
-			return nil
-		}
-		if opt.Limit > 0 && len(out) >= opt.Limit {
-			return Stop
-		}
-		files, ferr := changedFiles(c)
-		if ferr != nil {
-			return ferr
-		}
-		out = append(out, Commit{
-			SHA:     c.Hash.String(),
-			Author:  c.Author.Name,
-			Email:   c.Author.Email,
-			Date:    c.Author.When.Format(time.RFC3339),
-			Subject: firstLine(c.Message),
-			Files:   files,
-		})
-		return nil
-	})
-	if errors.Is(err, Stop) {
-		err = nil
-	}
-	return out, err
-}
-
-// Stop ends a log walk early (limit reached).
-var Stop = fmt.Errorf("gitlog: stop")
-
-func changedFiles(c *object.Commit) ([]string, error) {
-	var names []string
-	if c.NumParents() == 0 {
-		t, err := c.Tree()
-		if err != nil {
-			return nil, err
-		}
-		err = t.Files().ForEach(func(f *object.File) error {
-			names = append(names, f.Name)
-			return nil
-		})
-		sort.Strings(names)
-		return names, err
-	}
-	parent, err := c.Parent(0)
-	if err != nil {
-		return nil, err
-	}
-	from, err := parent.Tree()
-	if err != nil {
-		return nil, err
-	}
-	to, err := c.Tree()
-	if err != nil {
-		return nil, err
-	}
-	changes, err := object.DiffTree(from, to)
-	if err != nil {
-		return nil, err
-	}
-	for _, ch := range changes {
-		name := ch.To.Name
-		if name == "" {
-			name = ch.From.Name
-		}
-		if name != "" {
-			names = append(names, name)
-		}
-	}
-	sort.Strings(names)
-	return names, nil
-}
-
-func firstLine(msg string) string {
-	msg = strings.ReplaceAll(msg, "\r\n", "\n")
-	if i := strings.IndexByte(msg, '\n'); i >= 0 {
-		return strings.TrimSpace(msg[:i])
-	}
-	return strings.TrimSpace(msg)
-}
-
-func ToLeaf(c Commit, repo string) Leaf {
-	short := c.SHA
-	if len(short) > 12 {
-		short = short[:12]
-	}
-	head := fmt.Sprintf("commit %s — %s", short, c.Subject)
-	body := []string{
-		fmt.Sprintf("commit %s in %s — %s", short, repo, c.Subject),
-		fmt.Sprintf("Author: %s <%s>", c.Author, c.Email),
-		fmt.Sprintf("Date: %s", c.Date),
-	}
-	if len(c.Files) > 0 {
-		body = append(body, "Changing: "+strings.Join(c.Files, ", "))
-	}
-	return Leaf{
-		Source:  repo + "@" + c.SHA,
-		Repo:    repo,
-		Heading: head,
-		Text:    strings.Join(body, "\n"),
-		Type:    "commit",
-		Status:  "current",
-		Related: strings.Join(c.Files, ","),
-	}
-}
-
-func RepoName(repo string) (string, error) {
-	r, err := git.PlainOpen(repo)
-	if err != nil {
-		return filepath.Base(repo), err
-	}
-	rem, err := r.Remote("origin")
-	if err != nil {
-		return filepath.Base(repo), nil
-	}
-	urls := rem.Config().URLs
-	if len(urls) == 0 {
-		return filepath.Base(repo), nil
-	}
-	u := strings.TrimSuffix(strings.TrimSuffix(urls[0], "/"), ".git")
-	return path.Base(strings.ReplaceAll(u, "\\", "/")), nil
-}