Merge pull request 'MemoryStore.Search decodes and unmarshals every row before keeping topK' (#195) from task/643-memorystore-search-decodes-and-unmarshal into master

CLAUDE.md

@@ -460,8 +460,11 @@ start of a session rather than one lookup per first use:
 ToolSearch("select:mcp__vikunja__list_tasks,mcp__vikunja__get_task_details,mcp__vikunja__create_task,mcp__vikunja__update_task")
 ```
 
-`update_task` carrying a `description` resets `done` to false, so closing a task with a
-write-up takes two calls: the description, then `done: true`.
+**Close a finished task with `done: true` and nothing else** (owner's call, 07-08-2026).
+Do not write a completion summary into the description on the way out. It is lost anyway,
+and the durable record is the commit messages and the merged PR. Note that `update_task`
+carrying a `description` resets `done` to false, which is why a write-up ever took two
+calls.
 
 ## Session workflow
 

internal/store/memory.go

@@ -68,6 +68,13 @@ func (m *MemoryStore) Insert(ctx context.Context, id string, vec []float32, meta
 // Rows under memory.NonRecallPrefix are excluded in SQL. They are speaker
 // voiceprints sharing this table, and note recall must not rank them; see that
 // constant for why the previous arrangement only appeared to do this.
+//
+// Every row is still scored, because a full scan is what picks the winners.
+// What the scan does NOT do is pay for a row it is about to discard: the score
+// is read straight off the stored bytes without materializing a []float32, and
+// the meta blob is copied and unmarshalled only for a row that has entered the
+// topK. Losers cost one dot product and nothing else. Ranking is unchanged —
+// same scores, same order, same ties.
 func (m *MemoryStore) Search(ctx context.Context, vec []float32, topK int) ([]memory.Result, error) {
 	if topK <= 0 {
 		topK = 10
@@ -80,30 +87,127 @@ func (m *MemoryStore) Search(ctx context.Context, vec []float32, topK int) ([]me
 	}
 	defer rows.Close()
 
-	var out []memory.Result
+	// sql.RawBytes hands us the driver's own buffer, valid only until the next
+	// Next(). Nothing here outlives the row except what topK.offer copies on a
+	// survivor, so the three columns cost no allocation per row.
+	var id, blob, metaJSON sql.RawBytes
+	top := newTopK(topK)
 	for rows.Next() {
-		var id, metaJSON string
-		var blob []byte
 		if err := rows.Scan(&id, &blob, &metaJSON); err != nil {
 			return nil, fmt.Errorf("memory: row: %w", err)
 		}
-		meta := map[string]string{}
-		if err := json.Unmarshal([]byte(metaJSON), &meta); err != nil {
-			return nil, fmt.Errorf("memory: unmarshal meta for %q: %w", id, err)
-		}
-		out = append(out, memory.Result{ID: id, Score: dot(vec, decodeVec(blob)), Meta: meta})
+		top.offer(dotBlob(vec, blob), id, metaJSON)
 	}
 	if err := rows.Err(); err != nil {
 		return nil, fmt.Errorf("memory: rows: %w", err)
 	}
 
-	sort.Slice(out, func(i, j int) bool { return out[i].Score > out[j].Score })
-	if topK < len(out) {
-		out = out[:topK]
+	survivors := top.sorted()
+	out := make([]memory.Result, 0, len(survivors))
+	for _, c := range survivors {
+		meta := map[string]string{}
+		if err := json.Unmarshal(c.meta, &meta); err != nil {
+			return nil, fmt.Errorf("memory: unmarshal meta for %q: %w", c.id, err)
+		}
+		out = append(out, memory.Result{ID: c.id, Score: c.score, Meta: meta})
 	}
 	return out, nil
 }
 
+// candidate is one row that is currently in the topK: its score, its id, and
+// its meta blob copied out of the driver's buffer. The copy is the price of
+// surviving, and only survivors pay it.
+type candidate struct {
+	score float64
+	id    string
+	meta  []byte
+}
+
+// topK keeps the k highest-scoring candidates seen so far as a min-heap, so the
+// weakest survivor is always heap[0] and one comparison decides whether a new
+// row is worth copying. k is 10 in practice, so the heap is tiny and the whole
+// structure fits in cache.
+//
+// It is a plain slice with hand-written sift operations rather than
+// container/heap, because that interface boxes every element into an `any` on
+// Push and costs an allocation per surviving row.
+type topK struct {
+	k    int
+	heap []candidate
+}
+
+func newTopK(k int) *topK {
+	return &topK{k: k, heap: make([]candidate, 0, k)}
+}
+
+// offer admits a row if it beats the weakest survivor, or if the heap is not
+// full yet. id and meta are the driver's buffers and are copied here, never
+// retained.
+//
+// A row that only ties the weakest survivor does not displace it, so among
+// equal scores the earliest k rows are kept. The full sort this replaced used
+// sort.Slice, which is not stable, so it broke such a tie arbitrarily. That is
+// the ONE observable difference between the two, and it is deliberate:
+// deterministic beats arbitrary.
+//
+// It is not academic. Under the real embedder an exact tie means duplicate
+// vectors and nothing in the recall eval moved (V-643). Under the hash
+// embedder the eval's deterministic floor uses, ties are everywhere — it is
+// bag-of-words, so every note sharing no word with the query scores exactly 0
+// — and recall@3 on that run moved 74.1% to 81.5% purely because the zeros now
+// come out in a fixed order. Neither number measures retrieval. recall@1 and
+// false recall, which the eval actually asserts, are unchanged on both runs.
+func (t *topK) offer(score float64, id, meta []byte) {
+	if t.k == 0 {
+		return
+	}
+	if len(t.heap) < t.k {
+		t.heap = append(t.heap, candidate{score: score, id: string(id), meta: append([]byte(nil), meta...)})
+		t.up(len(t.heap) - 1)
+		return
+	}
+	if score <= t.heap[0].score {
+		return
+	}
+	t.heap[0] = candidate{score: score, id: string(id), meta: append([]byte(nil), meta...)}
+	t.down(0)
+}
+
+func (t *topK) up(i int) {
+	for i > 0 {
+		parent := (i - 1) / 2
+		if t.heap[parent].score <= t.heap[i].score {
+			return
+		}
+		t.heap[parent], t.heap[i] = t.heap[i], t.heap[parent]
+		i = parent
+	}
+}
+
+func (t *topK) down(i int) {
+	for {
+		l, r, small := 2*i+1, 2*i+2, i
+		if l < len(t.heap) && t.heap[l].score < t.heap[small].score {
+			small = l
+		}
+		if r < len(t.heap) && t.heap[r].score < t.heap[small].score {
+			small = r
+		}
+		if small == i {
+			return
+		}
+		t.heap[small], t.heap[i] = t.heap[i], t.heap[small]
+		i = small
+	}
+}
+
+// sorted drains the heap into descending score order — what Search returns.
+func (t *topK) sorted() []candidate {
+	out := t.heap
+	sort.Slice(out, func(i, j int) bool { return out[i].score > out[j].score })
+	return out
+}
+
 // ByPrefix returns every row whose id starts with prefix, vectors included.
 //
 // This is not a similarity query and deliberately does not score anything:
@@ -240,6 +344,26 @@ func decodeVec(b []byte) []float32 {
 	return v
 }
 
+// dotBlob is dot against a vector still in its stored encoding, so scoring a
+// row the query is about to discard does not allocate the []float32 that
+// decodeVec would build. Same arithmetic, same order of operations, so it
+// returns bit-identical scores to dot(a, decodeVec(b)).
+//
+// A blob whose length isn't a multiple of 4 is truncated to the whole-element
+// prefix, matching decodeVec, and a length mismatch is 0, matching dot.
+func dotBlob(a []float32, b []byte) float64 {
+	n := len(b) / 4
+	if len(a) != n || n == 0 {
+		return 0
+	}
+	var sum float64
+	for i := 0; i < n; i++ {
+		f := math.Float32frombits(binary.LittleEndian.Uint32(b[4*i:]))
+		sum += float64(a[i]) * float64(f)
+	}
+	return sum
+}
+
 // dot is the cosine similarity for L2-normalized vectors (mismatched lengths ⇒
 // 0, matching internal/memory's cosine).
 func dot(a, b []float32) float64 {

internal/store/memory_bench_test.go

@@ -0,0 +1,77 @@
+package store
+
+import (
+	"context"
+	"fmt"
+	"math"
+	"math/rand"
+	"path/filepath"
+	"testing"
+)
+
+// benchDim is the resident embedder's width (multilingual-e5-small, 384), so
+// the per-row decode cost the benchmark measures is the real one.
+const benchDim = 384
+
+// seedMemVectors fills a fresh store with n L2-normalized rows carrying a meta
+// blob the size recall actually stores — the note text plus its type — because
+// the cost this benchmark exists to measure is unmarshalling that blob for
+// every row when only topK survivors need it.
+func seedMemVectors(tb testing.TB, n int) *MemoryStore {
+	tb.Helper()
+	path := filepath.Join(tb.TempDir(), "mem_bench.db")
+	st, err := Open(context.Background(), path)
+	if err != nil {
+		tb.Fatalf("Open: %v", err)
+	}
+	tb.Cleanup(func() { _ = st.Close() })
+	m := st.VectorMemory()
+
+	rng := rand.New(rand.NewSource(1))
+	ctx := context.Background()
+	for i := 0; i < n; i++ {
+		if err := m.Insert(ctx, fmt.Sprintf("note:%d", i), randUnitVec(rng, benchDim), map[string]string{
+			"type": "note",
+			"text": fmt.Sprintf("заметка номер %d о том, что надо не забыть сделать на неделе", i),
+		}); err != nil {
+			tb.Fatalf("Insert %d: %v", i, err)
+		}
+	}
+	return m
+}
+
+func randUnitVec(rng *rand.Rand, dim int) []float32 {
+	v := make([]float32, dim)
+	var norm float64
+	for i := range v {
+		f := rng.NormFloat64()
+		v[i] = float32(f)
+		norm += f * f
+	}
+	norm = math.Sqrt(norm)
+	for i := range v {
+		v[i] = float32(float64(v[i]) / norm)
+	}
+	return v
+}
+
+// BenchmarkMemoryStoreSearch measures one recall query against a store of n
+// rows. Row counts bracket the documented scale: 1000 is a plausible today,
+// 10000 is the "thousands, not millions" ceiling the type doc claims a full
+// scan is fine at.
+func BenchmarkMemoryStoreSearch(b *testing.B) {
+	for _, n := range []int{1000, 10000} {
+		b.Run(fmt.Sprintf("rows=%d", n), func(b *testing.B) {
+			m := seedMemVectors(b, n)
+			q := randUnitVec(rand.New(rand.NewSource(2)), benchDim)
+			ctx := context.Background()
+			b.ReportAllocs()
+			b.ResetTimer()
+			for i := 0; i < b.N; i++ {
+				if _, err := m.Search(ctx, q, 10); err != nil {
+					b.Fatal(err)
+				}
+			}
+		})
+	}
+}

internal/store/memory_search_test.go

@@ -0,0 +1,107 @@
+package store
+
+import (
+	"context"
+	"fmt"
+	"math/rand"
+	"sort"
+	"testing"
+
+	"github.com/kami/maven/internal/memory"
+)
+
+// naiveSearch is the implementation Search replaced: score every row into a
+// slice, sort the whole slice, truncate. It stays in the test file as the
+// reference the bounded-heap version is judged against, because "recall must
+// not change" is a claim about output, not about the code that produces it.
+func naiveSearch(t *testing.T, m *MemoryStore, vec []float32, topK int) []memory.Result {
+	t.Helper()
+	rows, err := m.db.QueryContext(context.Background(),
+		`SELECT id, vec FROM memory_vectors WHERE id NOT LIKE ? ESCAPE '\'`,
+		escapeLike(memory.NonRecallPrefix)+"%")
+	if err != nil {
+		t.Fatalf("naive scan: %v", err)
+	}
+	defer rows.Close()
+	var out []memory.Result
+	for rows.Next() {
+		var id string
+		var blob []byte
+		if err := rows.Scan(&id, &blob); err != nil {
+			t.Fatalf("naive row: %v", err)
+		}
+		out = append(out, memory.Result{ID: id, Score: dot(vec, decodeVec(blob))})
+	}
+	if err := rows.Err(); err != nil {
+		t.Fatalf("naive rows: %v", err)
+	}
+	sort.Slice(out, func(i, j int) bool { return out[i].Score > out[j].Score })
+	if topK < len(out) {
+		out = out[:topK]
+	}
+	return out
+}
+
+// TestMemoryStoreSearchMatchesNaive is the constraint on V-643: the bounded
+// heap must return exactly what a full scan and sort returned. Distinct random
+// vectors, so no two scores tie and the ranking is total — a mismatch here is
+// arithmetic or heap logic, not a tie-break difference.
+func TestMemoryStoreSearchMatchesNaive(t *testing.T) {
+	ctx := context.Background()
+	m := newMemTestStore(t).VectorMemory()
+
+	rng := rand.New(rand.NewSource(7))
+	const rows, dim = 500, 64
+	for i := 0; i < rows; i++ {
+		if err := m.Insert(ctx, fmt.Sprintf("n%d", i), randUnitVec(rng, dim), map[string]string{
+			"text": fmt.Sprintf("note %d", i),
+		}); err != nil {
+			t.Fatalf("Insert %d: %v", i, err)
+		}
+	}
+
+	for _, topK := range []int{1, 3, 10, 50, rows, rows + 100} {
+		q := randUnitVec(rng, dim)
+		got, err := m.Search(ctx, q, topK)
+		if err != nil {
+			t.Fatalf("Search topK=%d: %v", topK, err)
+		}
+		want := naiveSearch(t, m, q, topK)
+		if len(got) != len(want) {
+			t.Fatalf("topK=%d: got %d results, naive returned %d", topK, len(got), len(want))
+		}
+		for i := range want {
+			if got[i].ID != want[i].ID {
+				t.Errorf("topK=%d rank %d: got %q, naive says %q", topK, i, got[i].ID, want[i].ID)
+			}
+			if got[i].Score != want[i].Score {
+				t.Errorf("topK=%d rank %d (%s): score %v, naive says %v",
+					topK, i, got[i].ID, got[i].Score, want[i].Score)
+			}
+		}
+		if len(got) > 0 && got[0].Meta["text"] == "" {
+			t.Errorf("topK=%d: survivor %s has no meta — it was never unmarshalled", topK, got[0].ID)
+		}
+	}
+}
+
+// TestDotBlobMatchesDot pins the claim in dotBlob's doc comment: reading the
+// vector out of its stored bytes is bit-identical to decoding it first. Scores
+// feed a gate with a 0.008 margin, so "close enough" is not the bar.
+func TestDotBlobMatchesDot(t *testing.T) {
+	rng := rand.New(rand.NewSource(11))
+	for i := 0; i < 200; i++ {
+		a := randUnitVec(rng, 384)
+		b := randUnitVec(rng, 384)
+		if got, want := dotBlob(a, encodeVec(b)), dot(a, b); got != want {
+			t.Fatalf("dotBlob = %v, dot = %v", got, want)
+		}
+	}
+	// Length mismatch is 0 in both, and so is an empty vector.
+	if got := dotBlob([]float32{1, 0}, encodeVec([]float32{1, 0, 0})); got != 0 {
+		t.Errorf("mismatched lengths scored %v, want 0", got)
+	}
+	if got := dotBlob(nil, nil); got != 0 {
+		t.Errorf("empty scored %v, want 0", got)
+	}
+}