Fix kbsearch ranking, --root filter, and daemon start

.github/workflows/ci.yml

@@ -42,6 +42,10 @@ jobs:
           go vet ./...
           go test ./... -count=1
 
+      - name: kbsearch ranking tests (no cgo / no ladybug)
+        working-directory: bin/kbsearch
+        run: go test ./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"

PLAN.md

@@ -116,11 +116,12 @@ Common props on every node/edge: `root`, `confidence`, `evidence[]`, `how`,
 
 `.github/workflows/ci.yml`:
 
-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.
+1. go vet + go test ./... (Go tools; root module)
+2. `go test ./rank` in `bin/kbsearch` (cgo-free ranking + flag parser; nested module still needs ladybug for the rest)
+3. python -m unittest discover (Py tools)
+4. bin/facts/audit self  (lexicon internal consistency)
+5. bin/kb/eval            (recall@5 ≥ 0.95, gates index regressions)
+6. 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.

bin/kbsearch/brain.go

@@ -5,6 +5,7 @@ import (
 	"fmt"
 	"os"
 	"path/filepath"
+	"strings"
 
 	lbug "github.com/LadybugDB/go-ladybug"
 )
@@ -44,10 +45,10 @@ func dbPath() string {
 }
 
 func openBrain() error {
-	return openWithOpts(2, eps())
+	return openWithSandbox(eps())
 }
 
-func openWithOpts(allow int, epsv string) error {
+func openWithSandbox(epsv string) error {
 	cfg := lbug.DefaultSystemConfig()
 	cfg.MaxNumThreads = 8
 	cfg.BufferPoolSize = 1 << 30 // 1GB
@@ -57,20 +58,30 @@ func openWithOpts(allow int, 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
@@ -85,4 +96,4 @@ func closeBrain() {
 		db.Close()
 		db = nil
 	}
-}
+}

bin/kbsearch/main.go

@@ -8,7 +8,9 @@
 //	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).
+// daemon over localhost HTTP (KBSEARCH_PORT, default 17830) and starts one in
+// the background when none answers. KBSEARCH_NO_DAEMON=1 skips that and embeds
+// in-process instead.
 package main
 
 import (
@@ -41,4 +43,4 @@ func main() {
 		return
 	}
 	os.Exit(runSearch(os.Args[1:]))
-}
+}

bin/kbsearch/rank/args.go

@@ -0,0 +1,72 @@
+package rank
+
+import (
+	"fmt"
+	"strconv"
+	"strings"
+)
+
+const Usage = `usage: kbsearch "query" [--root facts|info] [--repo REPO] [-n N] [--json]
+       kbsearch serve [port]
+       kbsearch --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
+}

bin/kbsearch/rank/query.go

@@ -0,0 +1,9 @@
+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"

bin/kbsearch/rank/rank.go

@@ -0,0 +1,100 @@
+// Package rank is the cgo-free ranking and CLI parsing for kbsearch.
+// 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
+}