Add reranking, RRF fusion, bench harness, tag contexts, and data ingestion

Implements five of the six enhancements from docs/kb-enhancements-proposal.htm,
closing the retrieval-quality gap identified in the qmd review.

- Cross-encoder reranking: new kb/reranker.py loads an optional reranking
  model at startup (KB_RERANK_ENABLED, KB_RERANKER_MODEL,
  KB_RERANK_CANDIDATES). Search degrades gracefully to plain hybrid
  retrieval when the model is absent. Exposed via a "rerank" block in
  /status, a rerank flag on search, and --no-rerank in the CLI.
- RRF rank fusion: FTS and vector lists now merge by reciprocal rank
  fusion with a top-rank bonus, replacing the old score blend. Scores are
  comparable across queries.
- Bench harness and explain traces: kb bench runs a query fixture against
  each backend and reports precision@k, recall and MRR. --explain returns a
  per-result score breakdown.
- Tag context descriptions: tags carry an optional one-line description
  (kb tag-describe), returned as tag_contexts with search results. Adds a
  tags.description column migration.
- Structured data ingestion: .json/.yaml/.toml files ingest as text via the
  new "data" doc type, pretty-printing minified JSON before chunking.

Query expansion (proposal item 5) is deliberately left out pending bench
results. Requires engine v3.3.0.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

client/cmd/add.go

@@ -38,6 +38,10 @@ var supportedExts = map[string]bool{
 	".py":   true,
 	".sh":   true,
 	".go":   true,
+	".json": true,
+	".yaml": true,
+	".yml":  true,
+	".toml": true,
 }
 
 var addfileCmd = &cobra.Command{

client/cmd/bench.go

@@ -0,0 +1,376 @@
+package cmd
+
+import (
+	"encoding/json"
+	"fmt"
+	"os"
+	"strings"
+	"time"
+
+	"github.com/kb-search/kb/internal/api"
+	"github.com/kb-search/kb/internal/output"
+	"github.com/spf13/cobra"
+)
+
+var benchCmd = &cobra.Command{
+	Use:   "bench <fixture.json>",
+	Short: "Benchmark search quality against a query fixture",
+	Long: `Run a fixture of queries with known-relevant documents against each
+search backend (fts, vec, hybrid, rerank) and report precision@k, recall
+and MRR per backend. Use this to baseline search quality before ranking
+changes and to measure their effect. See docs/bench-example.json for the
+fixture format.`,
+	Args: cobra.ExactArgs(1),
+	RunE: runBench,
+}
+
+func init() {
+	benchCmd.Flags().Int("top", 0, "override result count per query (k)")
+	benchCmd.Flags().String("backends", "fts,vec,hybrid,rerank", "comma-separated backends to run")
+	rootCmd.AddCommand(benchCmd)
+}
+
+type benchSelector struct {
+	DocumentID    int64  `json:"document_id"`
+	SourcePath    string `json:"source_path"`
+	TitleContains string `json:"title_contains"`
+}
+
+type benchQuery struct {
+	ID       string          `json:"id"`
+	Query    string          `json:"query"`
+	Tags     []string        `json:"tags"`
+	DocType  string          `json:"doc_type"`
+	Top      int             `json:"top"`
+	Relevant []benchSelector `json:"relevant"`
+	Notes    string          `json:"notes"`
+}
+
+type benchFixture struct {
+	Description string       `json:"description"`
+	Top         int          `json:"top"`
+	Queries     []benchQuery `json:"queries"`
+}
+
+type benchDoc struct {
+	DocumentID int64
+	Title      string
+	SourcePath string
+}
+
+type queryResult struct {
+	ID        string  `json:"id"`
+	Precision float64 `json:"precision"`
+	Recall    float64 `json:"recall"`
+	MRR       float64 `json:"mrr"`
+	LatencyMS float64 `json:"latency_ms"`
+	Returned  int     `json:"returned"`
+}
+
+type backendResult struct {
+	Precision    float64       `json:"precision"`
+	Recall       float64       `json:"recall"`
+	MRR          float64       `json:"mrr"`
+	AvgLatencyMS float64       `json:"avg_latency_ms"`
+	Queries      []queryResult `json:"queries"`
+}
+
+func loadFixture(path string) (*benchFixture, error) {
+	data, err := os.ReadFile(path)
+	if err != nil {
+		return nil, fmt.Errorf("cannot read fixture: %w", err)
+	}
+	var fx benchFixture
+	if err := json.Unmarshal(data, &fx); err != nil {
+		return nil, fmt.Errorf("invalid fixture JSON: %w", err)
+	}
+	if len(fx.Queries) == 0 {
+		return nil, fmt.Errorf("fixture has no queries")
+	}
+	for i, q := range fx.Queries {
+		if q.Query == "" {
+			return nil, fmt.Errorf("query %d: missing query text", i)
+		}
+		if len(q.Relevant) == 0 {
+			return nil, fmt.Errorf("query %q: no relevant selectors", q.Query)
+		}
+		for j, sel := range q.Relevant {
+			set := 0
+			if sel.DocumentID != 0 {
+				set++
+			}
+			if sel.SourcePath != "" {
+				set++
+			}
+			if sel.TitleContains != "" {
+				set++
+			}
+			if set != 1 {
+				return nil, fmt.Errorf("query %q selector %d: exactly one of document_id, source_path, title_contains must be set", q.Query, j)
+			}
+		}
+	}
+	return &fx, nil
+}
+
+func (s benchSelector) matches(doc benchDoc) bool {
+	switch {
+	case s.DocumentID != 0:
+		return doc.DocumentID == s.DocumentID
+	case s.SourcePath != "":
+		return doc.SourcePath == s.SourcePath
+	case s.TitleContains != "":
+		return strings.Contains(strings.ToLower(doc.Title), strings.ToLower(s.TitleContains))
+	}
+	return false
+}
+
+// dedupeByDocument collapses ranked chunks into ranked documents, keeping the
+// best (first) position for each document.
+func dedupeByDocument(docs []benchDoc) []benchDoc {
+	seen := map[int64]bool{}
+	var out []benchDoc
+	for _, d := range docs {
+		if seen[d.DocumentID] {
+			continue
+		}
+		seen[d.DocumentID] = true
+		out = append(out, d)
+	}
+	return out
+}
+
+// scoreQuery computes document-level precision, recall and MRR for one
+// query's ranked document list against the relevant-document selectors.
+func scoreQuery(ranked []benchDoc, relevant []benchSelector) (precision, recall, mrr float64) {
+	if len(ranked) == 0 {
+		return 0, 0, 0
+	}
+
+	matchedDocs := 0
+	firstMatch := 0
+	selectorHit := make([]bool, len(relevant))
+	for i, doc := range ranked {
+		docMatched := false
+		for j, sel := range relevant {
+			if sel.matches(doc) {
+				docMatched = true
+				selectorHit[j] = true
+			}
+		}
+		if docMatched {
+			matchedDocs++
+			if firstMatch == 0 {
+				firstMatch = i + 1
+			}
+		}
+	}
+
+	selectorsMatched := 0
+	for _, hit := range selectorHit {
+		if hit {
+			selectorsMatched++
+		}
+	}
+
+	precision = float64(matchedDocs) / float64(len(ranked))
+	recall = float64(selectorsMatched) / float64(len(relevant))
+	if firstMatch > 0 {
+		mrr = 1.0 / float64(firstMatch)
+	}
+	return precision, recall, mrr
+}
+
+// rerankAvailable probes engine status for a loaded reranker.
+func rerankAvailable(client *api.Client) bool {
+	resp, err := client.Get("/api/v1/status")
+	if err != nil {
+		return false
+	}
+	var status struct {
+		Rerank struct {
+			Enabled bool `json:"enabled"`
+			Loaded  bool `json:"loaded"`
+		} `json:"rerank"`
+	}
+	if err := api.DecodeJSON(resp, &status); err != nil {
+		return false
+	}
+	return status.Rerank.Enabled && status.Rerank.Loaded
+}
+
+func benchSearch(client *api.Client, q benchQuery, backend string, top int) ([]benchDoc, float64, error) {
+	body := map[string]interface{}{
+		"query": q.Query,
+		"top":   top,
+	}
+	if len(q.Tags) > 0 {
+		body["tags"] = q.Tags
+	}
+	if q.DocType != "" {
+		body["doc_type"] = q.DocType
+	}
+	switch backend {
+	case "fts":
+		body["fts_only"] = true
+	case "vec":
+		body["vec_only"] = true
+	case "hybrid":
+		body["rerank"] = false
+	case "rerank":
+		body["rerank"] = true
+	}
+
+	start := time.Now()
+	resp, err := client.Post("/api/v1/search", body)
+	if err != nil {
+		return nil, 0, err
+	}
+	if err := api.CheckError(resp); err != nil {
+		return nil, 0, err
+	}
+	var result struct {
+		Results []struct {
+			DocumentID int64  `json:"document_id"`
+			Title      string `json:"title"`
+			SourcePath string `json:"source_path"`
+		} `json:"results"`
+	}
+	if err := api.DecodeJSON(resp, &result); err != nil {
+		return nil, 0, err
+	}
+	latency := float64(time.Since(start).Microseconds()) / 1000.0
+
+	var docs []benchDoc
+	for _, r := range result.Results {
+		docs = append(docs, benchDoc{DocumentID: r.DocumentID, Title: r.Title, SourcePath: r.SourcePath})
+	}
+	return dedupeByDocument(docs), latency, nil
+}
+
+func runBench(cmd *cobra.Command, args []string) error {
+	topFlag, _ := cmd.Flags().GetInt("top")
+	backendsFlag, _ := cmd.Flags().GetString("backends")
+
+	fx, err := loadFixture(args[0])
+	if err != nil {
+		return err
+	}
+
+	var backends []string
+	for _, b := range strings.Split(backendsFlag, ",") {
+		b = strings.TrimSpace(b)
+		if b == "" {
+			continue
+		}
+		switch b {
+		case "fts", "vec", "hybrid", "rerank":
+			backends = append(backends, b)
+		default:
+			return fmt.Errorf("unknown backend %q (valid: fts, vec, hybrid, rerank)", b)
+		}
+	}
+	if len(backends) == 0 {
+		return fmt.Errorf("no backends selected")
+	}
+
+	client := api.NewClient()
+
+	rerankSkipped := false
+	if contains(backends, "rerank") && !rerankAvailable(client) {
+		backends = remove(backends, "rerank")
+		rerankSkipped = true
+		if len(backends) == 0 {
+			return fmt.Errorf("reranking is not available on this engine (requires engine with reranker enabled)")
+		}
+	}
+
+	results := map[string]*backendResult{}
+	for _, backend := range backends {
+		br := &backendResult{}
+		for _, q := range fx.Queries {
+			top := 10
+			if fx.Top > 0 {
+				top = fx.Top
+			}
+			if q.Top > 0 {
+				top = q.Top
+			}
+			if topFlag > 0 {
+				top = topFlag
+			}
+
+			ranked, latency, err := benchSearch(client, q, backend, top)
+			if err != nil {
+				return fmt.Errorf("backend %s, query %q: %w", backend, q.Query, err)
+			}
+			p, r, m := scoreQuery(ranked, q.Relevant)
+			id := q.ID
+			if id == "" {
+				id = q.Query
+			}
+			br.Queries = append(br.Queries, queryResult{
+				ID: id, Precision: p, Recall: r, MRR: m,
+				LatencyMS: latency, Returned: len(ranked),
+			})
+		}
+		n := float64(len(br.Queries))
+		for _, qr := range br.Queries {
+			br.Precision += qr.Precision / n
+			br.Recall += qr.Recall / n
+			br.MRR += qr.MRR / n
+			br.AvgLatencyMS += qr.LatencyMS / n
+		}
+		results[backend] = br
+	}
+
+	if output.IsJSON() {
+		output.PrintJSON(map[string]interface{}{
+			"description":    fx.Description,
+			"query_count":    len(fx.Queries),
+			"backends":       results,
+			"rerank_skipped": rerankSkipped,
+		})
+		return nil
+	}
+
+	if fx.Description != "" {
+		fmt.Printf("%s (%d queries)\n\n", fx.Description, len(fx.Queries))
+	}
+	headers := []string{"Backend", "Precision", "Recall", "MRR", "Avg ms"}
+	var rows [][]string
+	for _, backend := range backends {
+		br := results[backend]
+		rows = append(rows, []string{
+			backend,
+			fmt.Sprintf("%.3f", br.Precision),
+			fmt.Sprintf("%.3f", br.Recall),
+			fmt.Sprintf("%.3f", br.MRR),
+			fmt.Sprintf("%.0f", br.AvgLatencyMS),
+		})
+	}
+	output.PrintTable(headers, rows)
+	if rerankSkipped {
+		fmt.Println("\nrerank: n/a (reranker not enabled on this engine)")
+	}
+	return nil
+}
+
+func contains(ss []string, s string) bool {
+	for _, v := range ss {
+		if v == s {
+			return true
+		}
+	}
+	return false
+}
+
+func remove(ss []string, s string) []string {
+	var out []string
+	for _, v := range ss {
+		if v != s {
+			out = append(out, v)
+		}
+	}
+	return out
+}

client/cmd/bench_test.go

@@ -0,0 +1,143 @@
+package cmd
+
+import (
+	"math"
+	"os"
+	"path/filepath"
+	"testing"
+)
+
+func writeFixture(t *testing.T, content string) string {
+	t.Helper()
+	path := filepath.Join(t.TempDir(), "fixture.json")
+	if err := os.WriteFile(path, []byte(content), 0o644); err != nil {
+		t.Fatal(err)
+	}
+	return path
+}
+
+func TestLoadFixture_Valid(t *testing.T) {
+	path := writeFixture(t, `{
+		"description": "test",
+		"top": 5,
+		"queries": [
+			{"id": "q1", "query": "hello", "relevant": [{"document_id": 7}]}
+		]
+	}`)
+	fx, err := loadFixture(path)
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if fx.Top != 5 || len(fx.Queries) != 1 || fx.Queries[0].Relevant[0].DocumentID != 7 {
+		t.Errorf("fixture parsed incorrectly: %+v", fx)
+	}
+}
+
+func TestLoadFixture_RejectsEmptyRelevant(t *testing.T) {
+	path := writeFixture(t, `{"queries": [{"query": "hello", "relevant": []}]}`)
+	if _, err := loadFixture(path); err == nil {
+		t.Error("expected error for query with no relevant selectors")
+	}
+}
+
+func TestLoadFixture_RejectsMultiFieldSelector(t *testing.T) {
+	path := writeFixture(t, `{"queries": [
+		{"query": "hello", "relevant": [{"document_id": 1, "source_path": "/x"}]}
+	]}`)
+	if _, err := loadFixture(path); err == nil {
+		t.Error("expected error for selector with two fields set")
+	}
+}
+
+func TestSelectorMatching(t *testing.T) {
+	doc := benchDoc{DocumentID: 42, Title: "M38T Owner's Manual", SourcePath: "/data/m38t.pdf"}
+
+	cases := []struct {
+		name string
+		sel  benchSelector
+		want bool
+	}{
+		{"document_id match", benchSelector{DocumentID: 42}, true},
+		{"document_id miss", benchSelector{DocumentID: 43}, false},
+		{"source_path match", benchSelector{SourcePath: "/data/m38t.pdf"}, true},
+		{"source_path miss", benchSelector{SourcePath: "/data/other.pdf"}, false},
+		{"title_contains case-insensitive", benchSelector{TitleContains: "m38t owner"}, true},
+		{"title_contains miss", benchSelector{TitleContains: "workshop"}, false},
+	}
+	for _, tc := range cases {
+		if got := tc.sel.matches(doc); got != tc.want {
+			t.Errorf("%s: got %v, want %v", tc.name, got, tc.want)
+		}
+	}
+}
+
+func TestDedupeByDocument(t *testing.T) {
+	docs := []benchDoc{
+		{DocumentID: 1, Title: "a"},
+		{DocumentID: 2, Title: "b"},
+		{DocumentID: 1, Title: "a-again"},
+		{DocumentID: 3, Title: "c"},
+	}
+	out := dedupeByDocument(docs)
+	if len(out) != 3 || out[0].DocumentID != 1 || out[1].DocumentID != 2 || out[2].DocumentID != 3 {
+		t.Errorf("dedupe failed: %+v", out)
+	}
+	if out[0].Title != "a" {
+		t.Errorf("dedupe must keep first (best-ranked) occurrence, got %q", out[0].Title)
+	}
+}
+
+func approxEqual(a, b float64) bool {
+	return math.Abs(a-b) < 1e-9
+}
+
+func TestScoreQuery_HandComputed(t *testing.T) {
+	// Ranked docs: 10, 20, 30, 40. Relevant: 20 and 40.
+	ranked := []benchDoc{
+		{DocumentID: 10}, {DocumentID: 20}, {DocumentID: 30}, {DocumentID: 40},
+	}
+	relevant := []benchSelector{{DocumentID: 20}, {DocumentID: 40}}
+
+	p, r, m := scoreQuery(ranked, relevant)
+	if !approxEqual(p, 0.5) { // 2 of 4 returned docs are relevant
+		t.Errorf("precision: got %v, want 0.5", p)
+	}
+	if !approxEqual(r, 1.0) { // both relevant docs found
+		t.Errorf("recall: got %v, want 1.0", r)
+	}
+	if !approxEqual(m, 0.5) { // first relevant doc at rank 2
+		t.Errorf("mrr: got %v, want 0.5", m)
+	}
+}
+
+func TestScoreQuery_NoMatches(t *testing.T) {
+	ranked := []benchDoc{{DocumentID: 1}}
+	relevant := []benchSelector{{DocumentID: 99}}
+	p, r, m := scoreQuery(ranked, relevant)
+	if p != 0 || r != 0 || m != 0 {
+		t.Errorf("expected all-zero metrics, got p=%v r=%v mrr=%v", p, r, m)
+	}
+}
+
+func TestScoreQuery_PartialRecall(t *testing.T) {
+	// Only one of three relevant docs returned, at rank 1.
+	ranked := []benchDoc{{DocumentID: 5}, {DocumentID: 6}}
+	relevant := []benchSelector{{DocumentID: 5}, {DocumentID: 7}, {DocumentID: 8}}
+	p, r, m := scoreQuery(ranked, relevant)
+	if !approxEqual(p, 0.5) {
+		t.Errorf("precision: got %v, want 0.5", p)
+	}
+	if !approxEqual(r, 1.0/3.0) {
+		t.Errorf("recall: got %v, want 1/3", r)
+	}
+	if !approxEqual(m, 1.0) {
+		t.Errorf("mrr: got %v, want 1.0", m)
+	}
+}
+
+func TestScoreQuery_EmptyResults(t *testing.T) {
+	p, r, m := scoreQuery(nil, []benchSelector{{DocumentID: 1}})
+	if p != 0 || r != 0 || m != 0 {
+		t.Errorf("expected zeros for empty results, got p=%v r=%v mrr=%v", p, r, m)
+	}
+}

client/cmd/search.go

@@ -23,6 +23,8 @@ func init() {
 	searchCmd.Flags().Bool("fts-only", false, "use full-text search only")
 	searchCmd.Flags().Bool("vec-only", false, "use vector search only")
 	searchCmd.Flags().Float64("threshold", 0, "minimum score threshold")
+	searchCmd.Flags().Bool("explain", false, "include per-result score breakdown")
+	searchCmd.Flags().Bool("no-rerank", false, "skip cross-encoder reranking (lower latency)")
 	rootCmd.AddCommand(searchCmd)
 }
 
@@ -33,16 +35,18 @@ func runSearch(cmd *cobra.Command, args []string) error {
 	ftsOnly, _ := cmd.Flags().GetBool("fts-only")
 	vecOnly, _ := cmd.Flags().GetBool("vec-only")
 	threshold, _ := cmd.Flags().GetFloat64("threshold")
+	explain, _ := cmd.Flags().GetBool("explain")
+	noRerank, _ := cmd.Flags().GetBool("no-rerank")
 
 	body := map[string]interface{}{
 		"query": args[0],
 		"top":   top,
 	}
 	if tags != "" {
-		body["tags"] = tags
+		body["tags"] = splitTags(tags)
 	}
 	if docType != "" {
-		body["type"] = docType
+		body["doc_type"] = docType
 	}
 	if ftsOnly {
 		body["fts_only"] = true
@@ -53,6 +57,12 @@ func runSearch(cmd *cobra.Command, args []string) error {
 	if threshold > 0 {
 		body["threshold"] = threshold
 	}
+	if explain {
+		body["explain"] = true
+	}
+	if noRerank {
+		body["rerank"] = false
+	}
 
 	client := api.NewClient()
 	resp, err := client.Post("/api/v1/search", body)
@@ -66,13 +76,17 @@ func runSearch(cmd *cobra.Command, args []string) error {
 	}
 
 	var result struct {
-		Results []struct {
+		Reranked bool `json:"reranked"`
+		Results  []struct {
 			Score         float64                `json:"score"`
+			DocumentID    int64                  `json:"document_id"`
 			Title         string                 `json:"title"`
 			DocType       string                 `json:"doc_type"`
 			Tags          []string               `json:"tags"`
+			TagContexts   map[string]string      `json:"tag_contexts"`
 			ChunkMetadata map[string]interface{} `json:"chunk_metadata"`
 			Text          string                 `json:"text"`
+			Explain       map[string]interface{} `json:"explain"`
 		} `json:"results"`
 	}
 
@@ -94,13 +108,17 @@ func runSearch(cmd *cobra.Command, args []string) error {
 		return nil
 	}
 
+	if result.Reranked {
+		fmt.Println("(reranked)")
+	}
+
 	for i, r := range result.Results {
 		snippet := r.Text
 		if len(snippet) > 200 {
 			snippet = snippet[:200] + "..."
 		}
 
-		fmt.Printf("\n%d. [%.4f] %s\n", i+1, r.Score, r.Title)
+		fmt.Printf("\n%d. [%.4f] %s (doc:%d)\n", i+1, r.Score, r.Title, r.DocumentID)
 
 		location := ""
 		if page, ok := r.ChunkMetadata["page"]; ok && page != nil {
@@ -123,12 +141,63 @@ func runSearch(cmd *cobra.Command, args []string) error {
 		if len(r.Tags) > 0 {
 			fmt.Printf("   Tags: %s\n", joinStrings(r.Tags))
 		}
+		for _, tag := range r.Tags {
+			if desc, ok := r.TagContexts[tag]; ok && desc != "" {
+				fmt.Printf("   Context: %s — %s\n", tag, desc)
+			}
+		}
+		if r.Explain != nil {
+			fmt.Printf("   Score: %s\n", formatExplain(r.Explain))
+		}
 		fmt.Printf("   %s\n", snippet)
 	}
 	fmt.Println()
 	return nil
 }
 
+// formatExplain renders the engine's explain breakdown as one line, e.g.
+// "fts score=4.213 rank=2 (rrf 0.016129) | vec score=0.512 rank=1 (rrf 0.016393) | bonus 0.05 | final 0.082522"
+func formatExplain(e map[string]interface{}) string {
+	num := func(key string) (float64, bool) {
+		v, ok := e[key].(float64)
+		return v, ok
+	}
+	var parts []string
+	for _, arm := range []string{"fts", "vec"} {
+		score, hasScore := num(arm + "_score")
+		if !hasScore {
+			continue
+		}
+		part := fmt.Sprintf("%s score=%.4f", arm, score)
+		if rank, ok := num(arm + "_rank"); ok {
+			part += fmt.Sprintf(" rank=%d", int(rank))
+		}
+		if rrf, ok := num("rrf_" + arm); ok {
+			part += fmt.Sprintf(" (rrf %.6f)", rrf)
+		}
+		parts = append(parts, part)
+	}
+	if bonus, ok := num("bonus"); ok && bonus > 0 {
+		parts = append(parts, fmt.Sprintf("bonus %.2f", bonus))
+	}
+	for _, key := range []string{"pre_rerank_rank", "rerank_score", "blend_weight"} {
+		if v, ok := num(key); ok {
+			parts = append(parts, fmt.Sprintf("%s %.4f", key, v))
+		}
+	}
+	if final, ok := num("final_score"); ok {
+		parts = append(parts, fmt.Sprintf("final %.6f", final))
+	}
+	result := ""
+	for i, p := range parts {
+		if i > 0 {
+			result += " | "
+		}
+		result += p
+	}
+	return result
+}
+
 func joinStrings(ss []string) string {
 	result := ""
 	for i, s := range ss {

client/cmd/search_test.go

@@ -0,0 +1,67 @@
+package cmd
+
+import (
+	"bytes"
+	"encoding/json"
+	"io"
+	"net/http"
+	"net/http/httptest"
+	"reflect"
+	"testing"
+)
+
+func TestSearchCmd_SendsDocTypeAndTagsList(t *testing.T) {
+	var captured map[string]interface{}
+	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if r.URL.Path != "/api/v1/search" {
+			t.Errorf("unexpected path: %s", r.URL.Path)
+		}
+		body, _ := io.ReadAll(r.Body)
+		if err := json.Unmarshal(body, &captured); err != nil {
+			t.Fatalf("failed to decode request body: %v", err)
+		}
+		w.Header().Set("Content-Type", "application/json")
+		w.Write([]byte(`{"query":"q","results":[],"total_matches":0,"returned":0}`))
+	}))
+	defer server.Close()
+
+	var stdout bytes.Buffer
+	rootCmd.SetOut(&stdout)
+	rootCmd.SetArgs([]string{
+		"search", "oil level",
+		"--engine", server.URL,
+		"--format", "json",
+		"--type", "pdf",
+		"--tags", "manuals, ops,",
+	})
+
+	if err := rootCmd.Execute(); err != nil {
+		t.Fatalf("search command failed: %v", err)
+	}
+
+	if captured == nil {
+		t.Fatal("no request captured by test server")
+	}
+	if got := captured["doc_type"]; got != "pdf" {
+		t.Errorf("expected doc_type=pdf in body, got %v (full body: %v)", got, captured)
+	}
+	if _, present := captured["type"]; present {
+		t.Error("body must not contain legacy 'type' key")
+	}
+	tags, ok := captured["tags"].([]interface{})
+	if !ok {
+		t.Fatalf("expected tags to be a JSON array, got %T (%v)", captured["tags"], captured["tags"])
+	}
+	want := []interface{}{"manuals", "ops"}
+	if !reflect.DeepEqual(tags, want) {
+		t.Errorf("expected tags %v, got %v", want, tags)
+	}
+}
+
+func TestSplitTags(t *testing.T) {
+	got := splitTags(" a ,b,, c ")
+	want := []string{"a", "b", "c"}
+	if !reflect.DeepEqual(got, want) {
+		t.Errorf("splitTags: expected %v, got %v", want, got)
+	}
+}

client/cmd/tagdescribe.go

@@ -0,0 +1,62 @@
+package cmd
+
+import (
+	"fmt"
+	"os"
+
+	"github.com/kb-search/kb/internal/api"
+	"github.com/kb-search/kb/internal/output"
+	"github.com/spf13/cobra"
+)
+
+var tagDescribeCmd = &cobra.Command{
+	Use:   "tag-describe <tag> [description]",
+	Short: "Set a one-line context description on a tag",
+	Long: `Attach a short description to a tag (e.g. "Lab operations runbooks").
+Descriptions are returned as tag_contexts with every search result on a
+document carrying the tag, helping consumers judge relevance.
+
+Omit the description (or pass "") to clear it.`,
+	Args: cobra.RangeArgs(1, 2),
+	RunE: runTagDescribe,
+}
+
+func init() {
+	rootCmd.AddCommand(tagDescribeCmd)
+}
+
+func runTagDescribe(cmd *cobra.Command, args []string) error {
+	description := ""
+	if len(args) == 2 {
+		description = args[1]
+	}
+
+	body := map[string]interface{}{"description": description}
+
+	client := api.NewClient()
+	resp, err := client.Put("/api/v1/tags/"+args[0]+"/description", body)
+	if err != nil {
+		fmt.Fprintln(os.Stderr, err)
+		os.Exit(1)
+	}
+	if err := api.CheckError(resp); err != nil {
+		fmt.Fprintln(os.Stderr, err)
+		os.Exit(1)
+	}
+
+	if output.IsJSON() {
+		var raw interface{}
+		if err := api.DecodeJSON(resp, &raw); err != nil {
+			return fmt.Errorf("failed to decode response: %w", err)
+		}
+		output.PrintJSON(raw)
+		return nil
+	}
+
+	if description == "" {
+		fmt.Printf("Description cleared for tag %q\n", args[0])
+	} else {
+		fmt.Printf("Tag %q: %s\n", args[0], description)
+	}
+	return nil
+}

client/cmd/tags.go

@@ -41,8 +41,9 @@ func runTags(cmd *cobra.Command, args []string) error {
 	}
 
 	var tags []struct {
-		Name  string `json:"name"`
-		Count int    `json:"count"`
+		Name        string `json:"name"`
+		Count       int    `json:"count"`
+		Description string `json:"description"`
 	}
 	if err := api.DecodeJSON(resp, &tags); err != nil {
 		return fmt.Errorf("failed to decode response: %w", err)
@@ -53,10 +54,10 @@ func runTags(cmd *cobra.Command, args []string) error {
 		return nil
 	}
 
-	headers := []string{"TAG", "COUNT"}
+	headers := []string{"TAG", "COUNT", "DESCRIPTION"}
 	var rows [][]string
 	for _, t := range tags {
-		rows = append(rows, []string{t.Name, fmt.Sprintf("%d", t.Count)})
+		rows = append(rows, []string{t.Name, fmt.Sprintf("%d", t.Count), t.Description})
 	}
 	output.PrintTable(headers, rows)
 	return nil