refactor: chats method shebangs; drop chats index (D14). (#11)

Parsers and commands live in internal/chats. bin/chats/{sync,import,facts,apply}.go
are tagged shebang mains. Brain ingest is not a chats command.

AGENTS.md

@@ -37,7 +37,8 @@ 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; libs in internal/brain and internal/httpapi
-internal/     shared Go (brain/rank is cgo-free)
+bin/chats/    sync.go import.go facts.go apply.go; libs in internal/chats
+internal/     shared Go (brain/rank is cgo-free; chats parsers too)
 bin/watch/    corpus watcher (internal via bin/brain/watch later)
 bin/mail/     mail pipeline: sync (Go), import (md), index_mail (rebuild)
 bin/tools/    vendored python libs behind bin/* (kblib, yamlout, websearch)

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 | import `web-search`, retire local `searxng-ops`. Vendored here, no remote link. |
+| D3 | web search | Vendored client; SearXNG URL is config. Optional Compose instance (sanitized settings). Do not run a second copy on a host that already has one. Empty/`throttled` ≠ “nothing exists”. |
 | 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** (Kuzu successor, MIT, embedded, native FTS+vector+Cypher). Python binding for `bin/*`; Go shebang for golang tools. |
+| D6 | graph engine | **LadybugDB**. Go is the service (`bin/brain/search.go`, `internal/brain`); Python remains for index/write until the Go write path is safe. |
 | 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. |
@@ -40,6 +40,8 @@ detective method: **a fact needs ≥2 independent sources or it is
 | D14 | tooling style | `bin/{subject}/{method}.go` shebang (e.g. `bin/brain/search.go`). Shared code in `internal/`. One root `go.mod` + `go.work`. No `bin/*/main.go`, no nested modules. |
 | D15 | repo | Gitea [`eSlider/2dph`](https://git.produktor.io/eSlider/2dph) is origin + [issues](https://git.produktor.io/eSlider/2dph/issues). GitHub `eSlider/2dph` is the public clone (PRs + Actions CI). No direct `main` pushes. TDD → PR → CI green → merge. |
 | D16 | contradictions | ≥2 yes vs ≥2 no → unrelated sources conflict → hypothesis → `(not confirmed)`. Resolution (authority, staleness adjudication) = **v2**, tracked as open question. |
+| D17 | assertion gate | Fact-check every *claim* (facts → info → live 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. |
 
 ## Architecture
 
@@ -51,9 +53,12 @@ detective method: **a fact needs ≥2 independent sources or it is
   bin/
     facts/extract           auto-pair 2 sources → lexicon yaml + graph
     facts/audit             ["self"|"facts"|"info"|"stale"] 2-source + staleness gate
-    kb/index                build FTS + HNSW from corpus
+    kb/index                build FTS + HNSW from corpus (Python, for now)
-    kb/search               deduction: facts → info → web-search; --hop N
+    brain/search.go         deduction: facts → info → web-search
     kb/get  kb/stats  kb/eval
+    brain/serve.go          HTTP API (internal/httpapi)
+    chats/sync.go import.go facts.go apply.go
+                            (libs in internal/chats; no chats index)
     md/import  md/select  md/tables  md/gaps     (mistune)
     brain/extract  brain/audit   brain/deduce    (thinking wrapper)
     web/search               (vendored)
@@ -110,19 +115,18 @@ Common props on every node/edge: `root`, `confidence`, `evidence[]`, `how`,
    corrupts its WAL on bulk-insert into an already-indexed DB. Conversion and
    indexing stay separate for crash safety.
 4. Result: 17,835 messages → 28,918 info leafs, FTS + HNSW healthy, searchable
-   via `bin/kb/search`.
+   via `bin/brain/search.go`.
 
 ## CI/CD pipeline (D15)
 
 `.github/workflows/ci.yml`:
 
-1. go vet + go test ./... (Go tools; root module)
+1. go vet + go test ./... (root module; packages without ladybug cgo)
-2. `go test ./rank` in `bin/kbsearch` (cgo-free ranking + flag parser; nested module still needs ladybug for the rest)
+2. `go test ./internal/brain/rank` (cgo-free ranking + flag parser)
-3. `go test ./...` in `bin/chats` (Telegram + LinkedIn parsers; nested module)
+3. python -m unittest discover -s bin/tools (includes published-docs SoT)
-4. python -m unittest discover (Py tools)
+4. bin/facts/audit self  (lexicon internal consistency)
-5. bin/facts/audit self  (lexicon internal consistency)
+5. bin/kb/eval            (recall@5 ≥ 0.95, gates index regressions)
-6. bin/kb/eval            (recall@5 ≥ 0.95, gates index regressions)
+6. md-docs build/lint if docs tooling arrives.
-7. md-docs build/lint if docs tooling arrives.
 
 Feedback loop: every commit → PR → CI → green/gate → merge. Same discipline as
 `db/tech-poc`: contract first where there is an OpenAPI/message shape.

README.md

@@ -32,7 +32,7 @@ graph TB
         AU["bin/facts/audit<br/>confidence + staleness"]
         IDX["bin/kb/index<br/>chunk + embed"]
         MD["bin/md/import<br/>mistune leaves"]
-        SR["bin/kb/search<br/>deduction + --hop"]
+        SR["bin/brain/search.go<br/>deduction"]
     end
 
     subgraph store["Ladybug var/kb.lbug"]
@@ -85,21 +85,23 @@ fact; conflicting sources or a single source → `hypothesis` → `(not confirme
 ## Deduction search
 
 ```bash
-bin/kb/search "Matrix federation over HTTPS"      # facts → info → web-search
+bin/brain/search.go "Matrix federation over HTTPS"   # facts → info → web-search
-bin/kb/search "what runs on arc-2" --hop 1        # walk graph edges
+bin/brain/search.go "onlyoffice postgres" --root facts
-bin/kb/search "where is cs-lexicon" --json | yq '.'  # YAML by default
+bin/brain/search.go "where is cs-lexicon" --json | yq '.'
 bin/kb/get <id> --body                               # full chunk on demand
 bin/kb/stats                                         # index health
 bin/kb/eval                                          # 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`.
+
 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 --from-raw var/mail                                     # JSON → markdown
 bin/mail/index_mail                                                     # rebuild brain incl. mail
-bin/kb/search "Mietwagen Nürnberg invoice"                              # now answers from mail
+bin/brain/search.go "invoice from last week"                            # same search over mail leafs
 ```
 
 ## Storage
@@ -117,10 +119,10 @@ bin/kb/search "Mietwagen Nürnberg invoice"                              # now a
 
 ## Tooling conventions
 
-`bin/{subject}/{method}` — self-describing: shebang on line 1, usage comment
+`bin/{subject}/{method}.go` — self-describing: shebang on line 1, usage comment
-from line 2. bash + python primary; golang via the Go shebang when a compiled
+from line 2. Shared code in `internal/`. YAML default output, `--json` for
-helper is right. YAML default output, `--json` for machines. Everything that
+machines. Tests gate every commit. HTTP: `bin/brain/serve.go` (default search
-touches network/db is read-only, throttled, cached. Tests gate every commit.
+binary `var/bin/brain-search`, not Python).
 
 ## Development
 
@@ -136,7 +138,7 @@ 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            # async Go HTTP server
+docker compose run --rm brain serve            # bin/brain/serve.go
 docker compose up brain-watch                  # auto re-index on change
 ```
 

bin/chats/apply.go

@@ -0,0 +1,19 @@
+//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/doc.go

@@ -0,0 +1,4 @@
+// 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

@@ -0,0 +1,20 @@
+//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/import.go

@@ -0,0 +1,20 @@
+//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/index_cmd.go

@@ -1,56 +0,0 @@
-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

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

bin/chats/sync.go

@@ -0,0 +1,41 @@
+//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/tools/test_bin_layout.py

@@ -34,3 +34,32 @@ class BinLayoutTest(unittest.TestCase):
     def test_no_main_go_under_bin_brain(self) -> None:
         main = ROOT / "bin" / "brain" / "main.go"
         self.assertFalse(main.exists(), "bin/brain/main.go is not a method")
+
+    def test_chats_methods_are_shebangs_not_main(self) -> None:
+        chats = ROOT / "bin" / "chats"
+        self.assertFalse(
+            (chats / "main.go").exists(),
+            "bin/chats/main.go is a dispatcher, not a method",
+        )
+        self.assertFalse(
+            (chats / "index_cmd.go").exists(),
+            "chats index is a brain write hiding under the wrong subject",
+        )
+        for method in ("sync.go", "import.go", "facts.go", "apply.go"):
+            p = chats / method
+            self.assertTrue(p.is_file(), f"missing bin/chats/{method}")
+            first = p.read_text().splitlines()[0]
+            self.assertTrue(
+                first.startswith("//usr/bin/env go run"),
+                f"{method} shebang, got {first!r}",
+            )
+
+    def test_chats_lib_lives_in_internal(self) -> None:
+        self.assertTrue(
+            (ROOT / "internal" / "chats" / "linkedin.go").is_file(),
+            "LinkedIn parser must live in internal/chats",
+        )
+        self.assertFalse(
+            (ROOT / "bin" / "chats" / "linkedin.go").exists(),
+            "parser must not stay under bin/chats as a second main",
+        )

bin/tools/test_published_docs.py

@@ -0,0 +1,48 @@
+"""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_docs_do_not_claim_hop_walks(self) -> None:
+        paths = [
+            ROOT / "README.md",
+            ROOT / "docs" / "design.md",
+            ROOT / "skills" / "kb-search" / "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",
+            )

docs/README.md

@@ -8,4 +8,7 @@ Brain/ops/eSlider stack. Facts need proof or they are
 - [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`). `--hop` is
+not a walk; the flag errors until File/FROM_FILE edges exist.
+
 Published docs live here and mirror the project state.

docs/chat-import-plan.md

@@ -15,9 +15,10 @@ OO_CLI                     (default: $HOME/go/bin/oo)
 ## Quick reference
 
 ```
-./bin/chat sync telegram --limit 100
+./bin/chats/sync.go telegram --limit 100
-./bin/chat import
+./bin/chats/import.go
-./bin/chat index
+./bin/chats/facts.go
-./bin/chat facts
+./bin/chats/apply.go --dry-run
-./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

@@ -17,14 +17,14 @@ as one consistent state.
 ## Deduction search
 
 ```
-bin/kb/search "question"
+bin/brain/search.go "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
 ```
 
-`--hop N` follows graph edges (sibling leaves under a heading, owning file,
+`--hop` is not implemented yet (needs File/FROM_FILE edges). The flag is an
-`related:` files, vector-neighbour leaves) — the deduction walk.
+error; it is not a graph walk.
 
 ## Who / What / How / Where / When + evidence
 

internal/chats/apply.go

@@ -1,4 +1,4 @@
-package main
+package chats
 
 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(chatsDir(), "facts", "chat-facts.json")
+	factsPath := filepath.Join(Dir(), "facts", "chat-facts.json")
 	data, err := os.ReadFile(factsPath)
 	if err != nil {
 		if os.IsNotExist(err) {

internal/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 main
+package chats
 
 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)
 	}
 

internal/chats/facts.go

@@ -1,13 +1,11 @@
-package main
+package chats
 
 import (
 	"bufio"
-	"bytes"
 	"encoding/json"
 	"flag"
 	"fmt"
 	"os"
-	"os/exec"
 	"path/filepath"
 	"regexp"
 	"strings"
@@ -77,7 +75,7 @@ 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)
@@ -89,7 +87,7 @@ func runFacts(args []string) int {
 		return 0
 	}
 
-	root := chatsDir()
+	root := Dir()
 	telegramDir := filepath.Join(root, "telegram")
 
 	entries, err := os.ReadDir(telegramDir)
@@ -149,7 +147,7 @@ func runFacts(args []string) int {
 	}
 	fmt.Printf("chats facts: saved to %s\n", factsPath)
 
-	writeFactsToBrain(root, allFacts)
+	writeFactsMarkdown(allFacts)
 
 	return 0
 }
@@ -273,14 +271,10 @@ func filterFacts(facts []ExtractedFact, factType string) []ExtractedFact {
 	return result
 }
 
-func writeFactsToBrain(root string, facts []ExtractedFact) {
+// writeFactsMarkdown stores a sidecar for humans. Brain ingest is
-	indexScript := filepath.Join(root, "bin", "kb", "index")
+// bin/brain/index.go (not this subject).
-	if _, err := os.Stat(indexScript); os.IsNotExist(err) {
+func writeFactsMarkdown(facts []ExtractedFact) {
-		fmt.Fprintf(os.Stderr, "chats facts: kb/index not found, skipping brain write\n")
+	mdDir := filepath.Join(Dir(), "facts")
-		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
@@ -288,7 +282,7 @@ func writeFactsToBrain(root string, facts []ExtractedFact) {
 
 	var sb strings.Builder
 	sb.WriteString("---\n")
-	sb.WriteString("root: facts\n")
+	sb.WriteString("root: info\n")
 	sb.WriteString("---\n\n")
 	sb.WriteString("# Chat-Derived Facts\n\n")
 	for _, f := range facts {
@@ -302,15 +296,5 @@ func writeFactsToBrain(root string, 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()))
 }

internal/chats/import.go

@@ -1,4 +1,4 @@
-package main
+package chats
 
 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 := chatsDir()
+	root := Dir()
 	mdRoot := filepath.Join(root, "md")
 	glob := filepath.Join(root, "telegram", "*", "messages.jsonl")
 

internal/chats/linkedin.go

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

internal/chats/linkedin_test.go

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

internal/chats/mcpclient.go

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

internal/chats/paths.go

@@ -0,0 +1,39 @@
+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/source.go

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

internal/chats/sync_linkedin.go

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

internal/chats/sync_telegram.go

@@ -1,4 +1,4 @@
-package main
+package chats
 
 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, chatsDir(), *limit); err != nil {
+	if err := src.Sync(ctx, Dir(), *limit); err != nil {
 		fmt.Fprintf(os.Stderr, "chats sync telegram: %v\n", err)
 		return 1
 	}

skills/diataxis-docs/SKILL.md

@@ -30,12 +30,11 @@ related:
 ---
 ```
 
-`bin/kb/index` reads this. `type` becomes a searchable column and `related`
+`bin/kb/index` reads this. `type` becomes a searchable column. `related:` is
-becomes a graph edge:
+frontmatter for humans; graph hops from it are not implemented yet.
 
 ```bash
-bin/kb/search "deploy" --type howto
+bin/brain/search.go "deploy"
-bin/kb/search "Stecktafel" --hop 1     # follow links and related
 ```
 
 ## Audit checklist
@@ -46,8 +45,7 @@ bin/kb/search "Stecktafel" --hop 1     # follow links and related
    The indexer chunks on H2, so split files also search better.
 3. Is `status: archive` set on anything superseded? Archived files stay indexed
    but stop competing with current ones for a reader's attention.
-4. Does every explanation link the reference it explains, and vice versa? That
+4. Does every explanation link the reference it explains, and vice versa?
-   link is what `--hop 1` walks.
 
 ## Rule
 

skills/kb-search/SKILL.md

@@ -2,9 +2,10 @@
 name: kb-search
 description: >-
   Deduction search over the 2dph brain (Ladybug graph: ops corpus, portfolio,
-  ssh hosts) with bin/kb/search instead of reading files or grepping repos.
+  ssh hosts) with bin/brain/search.go instead of reading files or grepping
-  Use whenever a question starts with "where is", "what runs on", "which file
+  repos. Use whenever a question starts with "where is", "what runs on",
-  describes", "who is", "how is X done", before opening any documentation.
+  "which file describes", "who is", "how is X done", before opening any
+  documentation.
 ---
 
 # kb-search — deduction over facts and info
@@ -22,15 +23,17 @@ second independent source when local roots cannot confirm. An answer is
 `(not confirmed)`.
 
 ```bash
-bin/kb/search "Matrix federation"                # pointers + snippets, YAML
+bin/brain/search.go "Matrix federation"                # pointers + snippets, YAML
-bin/kb/search "what runs on arc-2" --hop 1       # follow graph edges
+bin/brain/search.go "onlyoffice postgres" --root facts # restrict to confirmed
-bin/kb/search "onlyoffice postgres" --root facts # restrict to confirmed
+bin/brain/search.go "where is cs-lexicon" --json | yq '.[].ref'
-bin/kb/search "where is cs-lexicon" --json | yq '.[].ref'
 bin/kb/get <id> --body                                 # full chunk only when needed
 bin/kb/stats                                           # index health
 bin/kb/eval                                            # recall@5 >= 0.95 gate
 ```
 
+`bin/kb/search` is a deprecated wrapper. `--hop` errors (File/FROM_FILE edges
+are not wired yet); do not treat it as a graph walk.
+
 ## Rules
 
 - Search before you read. Never grep a repo for a concept the graph covers.
@@ -38,8 +41,6 @@ bin/kb/eval                                      # recall@5 >= 0.95 gate
   facts first, then info leafs clearly marked `(not confirmed)`.
 - If recall looks wrong, run `bin/kb/eval`; it gates control questions and
   should stay at or above 95% recall@5.
-- `--hop N` follows sibling leaves, owning files, `related:` links and
-  vector-neighbours — that is the deduction walk, not random expansion.
 - Escalate to `web-search` (the `web-search` skill) as the independent second
   source when both local roots cannot confirm; never report an unconfirmed
   single-source local answer as fact.

skills/web-search/SKILL.md

@@ -18,9 +18,10 @@ bin/web/search "postgres partial index" --lang en --fresh year
 
 ## Web or knowledge base
 
-`bin/kb/search` holds our own facts: the ops stack, portfolio, ssh hosts, the
+`bin/brain/search.go` holds our own facts: the ops stack, portfolio, ssh hosts,
-lexicon. Go there first. Reach for `bin/web/search` when the answer is outside
+the lexicon. Go there first. Reach for `bin/web/search` when the answer is
-our repos: upstream library behaviour, vendor documentation, public standards.
+outside our repos: upstream library behaviour, vendor documentation, public
+standards.
 
 Keep the two apart. A finding is stronger when the reader can see that one
 source was ours and one was not.