Merge pull request 'Bug: the memory index stores the raw utterance as a fact's recall text, and nothing ever deletes a fact vector' (#100) from task/493-bug-the-memory-index-stores-the-raw-utte into task/470-bug-a-question-writes-invented-knowledge

Reviewed-on: #100

cmd/mavend/actions_fact.go

@@ -7,6 +7,7 @@ import (
 
 	"github.com/kami/maven/internal/ipc"
 	"github.com/kami/maven/internal/router"
+	"github.com/kami/maven/internal/store"
 )
 
 // actionFact handles router.IntentFact: persist a tapped self-fact, index
@@ -63,17 +64,25 @@ func (h *reactiveHandler) actionFact(ctx context.Context, dec router.Decision) s
 		log.Printf("voice: write fact: %v", err)
 		return "не получилось сохранить факт."
 	}
-	// Index the fact utterance in long-term memory (best-effort, must not
-	// fail the fact write). Facts aren't in the notes table, so this is the
-	// only recall path for them — "когда я пил воду?" reads back from here.
+	// Index the fact in long-term memory (best-effort, must not fail the fact
+	// write). Facts aren't in the notes table, so this is the only recall path
+	// for them — "когда я пил воду?" reads back from here.
+	//
+	// The indexed text is the fact, not the utterance (#493). queryMemory
+	// returns a fact's stored text verbatim, so what goes in here is what he
+	// hears; storing the utterance meant recall answered with his own sentence
+	// rather than the value. The utterance stays alongside as provenance —
+	// readable on /trace, never the answer and never embedded.
 	if h.memStore != nil {
-		if vec, err := router.EmbedPassage(ctx, h.embedder, dec.Utterance); err != nil {
+		text := store.FactRecallText(dec.Slots.Key, dec.Slots.Value)
+		if vec, err := router.EmbedPassage(ctx, h.embedder, text); err != nil {
 			log.Printf("voice: embed fact for memory: %v", err)
 		} else if err := h.memStore.Insert(ctx, "fact:"+dec.Slots.Key+":"+strconv.FormatInt(now.Unix(), 10), vec, map[string]string{
-			"source": "voice",
-			"type":   "fact",
-			"text":   dec.Utterance,
-			"ts":     strconv.FormatInt(now.Unix(), 10),
+			"source":    "voice",
+			"type":      "fact",
+			"text":      text,
+			"utterance": dec.Utterance,
+			"ts":        strconv.FormatInt(now.Unix(), 10),
 		}); err != nil {
 			log.Printf("voice: memory insert fact: %v", err)
 		}

cmd/mavend/factgate_test.go

@@ -78,6 +78,22 @@ func TestActionFact_ExplicitCaptureStillWrites(t *testing.T) {
 	if f.Confidence != 1.0 {
 		t.Errorf("confidence = %v, want 1.0 for a value he said", f.Confidence)
 	}
+	// #493: what recall reads back is the fact, not the sentence he said.
+	// queryMemory returns a fact's text verbatim, so the utterance sitting here
+	// meant "запиши что я пил воду" was the answer to "когда я пил воду?".
+	hits, err := h.memStore.Search(ctx, mustEmbedPassage(t, h, "вода"), 3)
+	if err != nil {
+		t.Fatalf("memory search: %v", err)
+	}
+	if len(hits) != 1 {
+		t.Fatalf("the fact was not indexed once: %+v", hits)
+	}
+	if got := hits[0].Meta["text"]; got != "water — вода" {
+		t.Errorf("indexed text = %q, want the fact", got)
+	}
+	if got := hits[0].Meta["utterance"]; got != "запиши что я пил воду" {
+		t.Errorf("utterance provenance = %q, want it kept alongside", got)
+	}
 }
 
 func TestFactConfidence(t *testing.T) {

cmd/mavend/voicewire.go

@@ -146,6 +146,7 @@ func wireVoice(cfg *config.Config, coreAPI ipc.CoreAPI, phr phraser.Phraser, mem
 		emb = router.NewHashEmbedder(1024)
 	}
 	w.embedder = emb
+	repairFactVectors(dataStore, emb)
 	checkStoredEmbedder(dataStore, emb)
 
 	// ----- tool executor (the enabled act allowlist, store-backed) -----
@@ -473,6 +474,36 @@ func seedTools(api ipc.CoreAPI, tools []config.ToolConfig) {
 	log.Printf("voice: seeded %d act tools from config", n)
 }
 
+// repairFactVectors brings stored fact vectors in line with the facts they name
+// (#493), once per box, before the embedder marker is even looked at.
+//
+// Automatic and not a flag, unlike -reembed: only voice-tapped facts are in
+// this index, so the work is tens of embeddings rather than the thousands of
+// notes that made the backfill a deliberate act. And the box that needs it is
+// broken in a way nobody can see — recall answers with the wrong text and
+// nothing logs an error — so waiting for an operator to know to run it is how
+// the defect survived four restarts in the first place.
+func repairFactVectors(dataStore *store.Store, emb router.Embedder) {
+	if dataStore == nil {
+		return
+	}
+	res, err := dataStore.RepairFactVectors(context.Background(),
+		// EmbedPassage, the stored side, same as every other writer of these
+		// vectors.
+		func(ctx context.Context, text string) ([]float32, error) {
+			return router.EmbedPassage(ctx, emb, text)
+		})
+	if err != nil {
+		log.Printf("voice: fact vector repair failed, no marker written and nothing half-done — retried next start: %v", err)
+		return
+	}
+	if res.Skipped || res.Rewritten+res.Dropped == 0 {
+		return
+	}
+	log.Printf("voice: fact vector repair — %d re-embedded from the fact they name, %d dropped as voided or superseded, %d already right, took %s (#493)",
+		res.Rewritten, res.Dropped, res.Kept, res.Took.Round(time.Millisecond))
+}
+
 // reembedOnStart is the -reembed flag (set in run()). Opt-in on purpose: see
 // runReembed.
 var reembedOnStart bool

docs/qa.md

@@ -498,12 +498,21 @@ rejects `https://api.openai.com`, and forget really deletes
 (`internal/store/memory.go:145` is a real `DELETE`, not a tombstone). Vision is
 19/19, speaker 22/22, media 16/16.
 
-**470 got worse.** Both poisoned facts show `voided` on `/history`, and the
-defect survives. Re-measured at 15:42, after four restarts: `почему небо синее?`
-still answers `какая последняя версия языка Go?` with no `search:` line. What
-comes back is the question he typed, not the value the fact held. So the poison
-is a vector in the memory index, and `revert` does not remove it. There is
-currently no documented way to repair a poisoned box.
+**470 got worse, then closed.** Both poisoned facts showed `voided` on
+`/history` and the defect survived. Re-measured at 15:42, after four restarts:
+`почему небо синее?` still answered `какая последняя версия языка Go?` with no
+`search:` line. What came back was the question he typed, not the value the fact
+held. So the poison was a vector in the memory index, and `revert` did not
+remove it.
+
+Repaired in two parts. 470 stopped the writes: a question is never a fact, and a
+void drops the key's vectors. 493 fixed what the index holds. A fact is indexed
+as the fact and not as the utterance, and a correction drops its superseded
+vector too.
+
+A poisoned box now repairs itself on the next start. `RepairFactVectors`
+re-embeds every fact vector from the fact it names, and deletes the voided and
+superseded ones. It runs once, guarded by a marker, and logs what it did.
 
 ---
 

internal/store/facts.go

@@ -47,6 +47,39 @@ func (s *Store) WriteFact(ctx context.Context, ts time.Time, kind FactKind, key,
 	return id, nil
 }
 
+// FactRecallText is the text a fact is indexed under and read back as (#493).
+//
+// It used to be the utterance that wrote the fact, so recall of ANY
+// voice-tapped fact answered with the sentence he said instead of the value
+// stored: `go_version = 1.20` was indexed as "какая последняя версия языка
+// Go?", and that question is what came back. The poisoned rows made the defect
+// visible; the shape was wrong for legitimate facts too.
+//
+// The key is spoken with its underscores dropped, because a key is written for
+// the store and this string is read out loud.
+func FactRecallText(key, value string) string {
+	spoken := strings.TrimSpace(strings.ReplaceAll(key, "_", " "))
+	v := strings.TrimSpace(DecodeFactValue(value))
+	switch {
+	case v == "":
+		return spoken
+	case spoken == "":
+		return v
+	}
+	return spoken + " — " + v
+}
+
+// DecodeFactValue unwraps a stored value for reading. The column holds raw json
+// when the writer serialized one (SetValue, CorrectValue) and a plain string
+// when it did not (a voice tap), so a reader that wants the text handles both.
+func DecodeFactValue(value string) string {
+	var s string
+	if err := json.Unmarshal([]byte(value), &s); err == nil {
+		return s
+	}
+	return value
+}
+
 // LatestFact returns the latest non-voided fact for key, or ErrNoFact.
 // "Non-voided" = no later row has voids_id pointing at it. We resolve this by
 // taking the newest row whose id is not referenced by any voids_id.
@@ -291,6 +324,20 @@ func (s *Store) CorrectValue(ctx context.Context, key, source string, value any,
 	if err != nil {
 		return 0, fmt.Errorf("last insert id: %w", err)
 	}
+	// The same repair a void needs, for the same reason (#493). A correction
+	// supersedes the value, and the vector still holds the old one, so recall
+	// kept answering with the value he had just corrected. Dropping it costs
+	// the key its recall vector until the fact is tapped again: this layer has
+	// no embedder, and a missing vector loses a question while a stale one
+	// answers it wrongly.
+	//
+	// Best-effort: the corrected row is committed, and a correction that lands
+	// beats one that fails on cleanup.
+	if n, derr := s.VectorMemory().DeletePrefix(ctx, "fact:"+key+":"); derr != nil {
+		log.Printf("store: correct %q: memory vectors survive: %v", key, derr)
+	} else if n > 0 {
+		log.Printf("store: correct %q: dropped %d superseded memory vector(s)", key, n)
+	}
 	return newID, nil
 }
 

internal/store/factvectors.go

@@ -0,0 +1,177 @@
+package store
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"strconv"
+	"strings"
+	"time"
+)
+
+// metaKeyFactVectorShape names the shape the stored fact vectors were written
+// in. It exists so the repair below runs once per box instead of on every
+// start: the rows it fixes were written by a code path that no longer exists,
+// and once fixed nothing writes that shape again.
+const metaKeyFactVectorShape = "fact_vector_shape"
+
+// factVectorShapeFact is the shape FactRecallText produces. Anything else in
+// the marker (including nothing, which is every box written before #493) means
+// the fact vectors still hold utterances.
+const factVectorShapeFact = "fact-text (#493)"
+
+// FactVectorRepair is what one repair run did, for logging.
+type FactVectorRepair struct {
+	Skipped   bool // marker already matched — nothing to do
+	Rewritten int  // rows re-embedded from the fact they name
+	Dropped   int  // rows deleted: voided, superseded, or naming no fact at all
+	Kept      int  // rows already holding the right text
+	Took      time.Duration
+}
+
+// RepairFactVectors brings the fact rows of memory_vectors in line with the
+// facts they name, and is the operator recovery a poisoned box had no path to
+// (#470 point 4, #493).
+//
+// Three defects put wrong text in that index, and all three are write-path
+// fixes that do nothing for rows already stored:
+//
+//   - the indexed text was the utterance, so every fact row reads back a
+//     sentence rather than a value;
+//   - a void left its vector behind, so retracted junk kept answering;
+//   - a correction left its vector behind, so the superseded value did.
+//
+// So each fact row is resolved against the fact store and one of three things
+// happens. It is dropped when the key has no fact, when the newest row for the
+// key is a void marker, or when a newer vector for the same key exists — a
+// superseded value has no business claiming a turn. It is re-embedded when its
+// text is not what FactRecallText says the fact is. Otherwise it is left alone.
+//
+// Idempotent, and safe to interrupt: every step compares before writing and the
+// marker is written last, so a run that dies partway is simply redone.
+func (s *Store) RepairFactVectors(ctx context.Context, embed EmbedFunc) (FactVectorRepair, error) {
+	start := time.Now()
+	var res FactVectorRepair
+
+	shape, err := s.Meta(ctx, metaKeyFactVectorShape)
+	if err != nil {
+		return res, err
+	}
+	if shape == factVectorShapeFact {
+		res.Skipped = true
+		res.Took = time.Since(start)
+		return res, nil
+	}
+
+	rows, err := s.db.QueryContext(ctx, `SELECT id, meta FROM memory_vectors`)
+	if err != nil {
+		return res, fmt.Errorf("repair fact vectors: read: %w", err)
+	}
+	type factVec struct {
+		id, key string
+		meta    map[string]string
+		ts      int64
+	}
+	var vecs []factVec
+	newest := map[string]int64{} // key → newest ts seen for it
+	for rows.Next() {
+		var id, metaJSON string
+		if err := rows.Scan(&id, &metaJSON); err != nil {
+			rows.Close()
+			return res, fmt.Errorf("repair fact vectors: row: %w", err)
+		}
+		meta := map[string]string{}
+		if err := json.Unmarshal([]byte(metaJSON), &meta); err != nil {
+			rows.Close()
+			return res, fmt.Errorf("repair fact vectors: meta for %q: %w", id, err)
+		}
+		if meta["type"] != "fact" {
+			continue
+		}
+		key, ts, ok := splitFactVectorID(id)
+		if !ok {
+			continue
+		}
+		vecs = append(vecs, factVec{id: id, key: key, meta: meta, ts: ts})
+		if ts > newest[key] {
+			newest[key] = ts
+		}
+	}
+	rows.Close()
+	if err := rows.Err(); err != nil {
+		return res, fmt.Errorf("repair fact vectors: rows: %w", err)
+	}
+
+	for _, v := range vecs {
+		drop := v.ts < newest[v.key]
+		var want string
+		if !drop {
+			f, ferr := s.LatestFact(ctx, v.key)
+			switch {
+			case errors.Is(ferr, ErrNoFact):
+				drop = true
+			case ferr != nil:
+				return res, fmt.Errorf("repair fact vectors: fact %q: %w", v.key, ferr)
+			case DecodeFactValue(f.Value) == "voided":
+				drop = true
+			default:
+				want = FactRecallText(v.key, f.Value)
+			}
+		}
+		if drop {
+			if err := s.VectorMemory().Delete(ctx, v.id); err != nil {
+				return res, err
+			}
+			res.Dropped++
+			continue
+		}
+		if v.meta["text"] == want {
+			res.Kept++
+			continue
+		}
+		vec, err := embed(ctx, want)
+		if err != nil {
+			return res, fmt.Errorf("repair fact vectors: embed %q: %w", v.id, err)
+		}
+		// The whole meta blob is rewritten in Go rather than patched in SQL,
+		// because json_set needs the JSON1 extension and this store is opened
+		// through sqlcipher.
+		v.meta["text"] = want
+		metaJSON, err := json.Marshal(v.meta)
+		if err != nil {
+			return res, fmt.Errorf("repair fact vectors: meta %q: %w", v.id, err)
+		}
+		if _, err := s.db.ExecContext(ctx,
+			`UPDATE memory_vectors SET vec = ?, meta = ? WHERE id = ?`,
+			encodeVec(vec), string(metaJSON), v.id); err != nil {
+			return res, fmt.Errorf("repair fact vectors: write %q: %w", v.id, err)
+		}
+		res.Rewritten++
+	}
+
+	if err := s.SetMeta(ctx, metaKeyFactVectorShape, factVectorShapeFact); err != nil {
+		return res, err
+	}
+	res.Took = time.Since(start)
+	return res, nil
+}
+
+// splitFactVectorID reads the key and write time back out of a fact vector's
+// id, which the write path builds as `fact:<key>:<unix>`. A key may hold a
+// colon, the timestamp may not, so the split is from the right.
+func splitFactVectorID(id string) (key string, ts int64, ok bool) {
+	rest, found := strings.CutPrefix(id, "fact:")
+	if !found {
+		return "", 0, false
+	}
+	cut := strings.LastIndex(rest, ":")
+	if cut <= 0 {
+		return "", 0, false
+	}
+	ts, err := strconv.ParseInt(rest[cut+1:], 10, 64)
+	if err != nil {
+		return "", 0, false
+	}
+	return rest[:cut], ts, true
+}

internal/store/factvectors_test.go

@@ -0,0 +1,151 @@
+package store
+
+import (
+	"context"
+	"database/sql"
+	"testing"
+	"time"
+)
+
+// The write-path half of #493: recall of a fact must read back the fact, not
+// the sentence he happened to say.
+func TestFactRecallText(t *testing.T) {
+	for _, tc := range []struct {
+		name, key, value, want string
+	}{
+		{"json value", "go_version", `"1.20"`, "go version — 1.20"},
+		{"plain value", "water", "выпил", "water — выпил"},
+		{"no value", "shower", "", "shower"},
+		{"underscores are spoken as spaces", "espresso_machine", `"чистая"`, "espresso machine — чистая"},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			if got := FactRecallText(tc.key, tc.value); got != tc.want {
+				t.Fatalf("FactRecallText(%q, %q) = %q; want %q", tc.key, tc.value, got, tc.want)
+			}
+		})
+	}
+}
+
+// A correction left the superseded value in the index, so recall answered with
+// the value he had just corrected (#493).
+func TestCorrectValueDropsMemoryVectors(t *testing.T) {
+	ctx := context.Background()
+	s := newTestStore(t)
+	now := time.Now()
+	mem := s.VectorMemory()
+
+	if _, err := s.WriteFact(ctx, now, KindSelf, "go_version", `"1.20"`, "tap:voice", 1.0, sql.NullInt64{}); err != nil {
+		t.Fatalf("WriteFact: %v", err)
+	}
+	if err := mem.Insert(ctx, "fact:go_version:1", []float32{1, 0, 0}, map[string]string{
+		"type": "fact", "text": "go version — 1.20",
+	}); err != nil {
+		t.Fatalf("Insert: %v", err)
+	}
+	if _, err := s.CorrectValue(ctx, "go_version", "feedback", "1.25", now.Add(time.Minute)); err != nil {
+		t.Fatalf("CorrectValue: %v", err)
+	}
+	got, err := mem.ByPrefix(ctx, "fact:")
+	if err != nil {
+		t.Fatalf("ByPrefix: %v", err)
+	}
+	if len(got) != 0 {
+		t.Fatalf("after the correction the index still holds %+v; the superseded value must not answer", got)
+	}
+}
+
+// The recovery path a poisoned box had none of (#470 point 4, #493): rows
+// written before the fix hold utterances, voided junk and superseded values,
+// and no write-path change reaches any of them.
+func TestRepairFactVectors(t *testing.T) {
+	ctx := context.Background()
+	s := newTestStore(t)
+	now := time.Now()
+	mem := s.VectorMemory()
+	embed := func(ctx context.Context, text string) ([]float32, error) {
+		return []float32{float32(len(text)), 1, 0}, nil
+	}
+
+	// A live fact indexed under the question that wrote it — the defect.
+	if _, err := s.WriteFact(ctx, now, KindSelf, "water", `"выпил"`, "tap:voice", 1.0, sql.NullInt64{}); err != nil {
+		t.Fatalf("WriteFact water: %v", err)
+	}
+	if err := mem.Insert(ctx, "fact:water:100", []float32{9, 9, 9}, map[string]string{
+		"type": "fact", "source": "voice", "text": "запиши что я пил воду",
+	}); err != nil {
+		t.Fatalf("Insert water: %v", err)
+	}
+	// A voided fact whose vector survived the void.
+	if _, err := s.WriteFact(ctx, now, KindSelf, "go_version", `"1.20"`, "tap:voice", 1.0, sql.NullInt64{}); err != nil {
+		t.Fatalf("WriteFact go_version: %v", err)
+	}
+	if _, _, err := s.VoidLatestFact(ctx, "go_version", "feedback", now.Add(time.Minute)); err != nil {
+		t.Fatalf("VoidLatestFact: %v", err)
+	}
+	if err := mem.Insert(ctx, "fact:go_version:100", []float32{9, 9, 9}, map[string]string{
+		"type": "fact", "text": "какая последняя версия языка Go?",
+	}); err != nil {
+		t.Fatalf("Insert go_version: %v", err)
+	}
+	// A key with two vectors: only the newest may answer.
+	if _, err := s.WriteFact(ctx, now, KindSelf, "mood", `"устал"`, "tap:voice", 1.0, sql.NullInt64{}); err != nil {
+		t.Fatalf("WriteFact mood: %v", err)
+	}
+	for _, ts := range []string{"100", "200"} {
+		if err := mem.Insert(ctx, "fact:mood:"+ts, []float32{9, 9, 9}, map[string]string{
+			"type": "fact", "text": "мне грустно",
+		}); err != nil {
+			t.Fatalf("Insert mood %s: %v", ts, err)
+		}
+	}
+	// A note must be left entirely alone.
+	if err := mem.Insert(ctx, "note:7", []float32{5, 5, 5}, map[string]string{
+		"type": "note", "text": "сеть тормозит по вечерам",
+	}); err != nil {
+		t.Fatalf("Insert note: %v", err)
+	}
+
+	res, err := s.RepairFactVectors(ctx, embed)
+	if err != nil {
+		t.Fatalf("RepairFactVectors: %v", err)
+	}
+	if res.Rewritten != 2 || res.Dropped != 2 {
+		t.Fatalf("repair reported %+v; want 2 rewritten (water, newest mood) and 2 dropped (voided go_version, superseded mood)", res)
+	}
+
+	got, err := mem.ByPrefix(ctx, "fact:")
+	if err != nil {
+		t.Fatalf("ByPrefix: %v", err)
+	}
+	texts := map[string]string{}
+	for _, r := range got {
+		texts[r.ID] = r.Meta["text"]
+	}
+	if len(texts) != 2 {
+		t.Fatalf("the index holds %+v; want only fact:water:100 and fact:mood:200", texts)
+	}
+	if texts["fact:water:100"] != "water — выпил" {
+		t.Fatalf("water reads back %q; want the fact, not the utterance", texts["fact:water:100"])
+	}
+	if texts["fact:mood:200"] != "mood — устал" {
+		t.Fatalf("mood reads back %q", texts["fact:mood:200"])
+	}
+	// Provenance the row already carried must survive the rewrite.
+	for _, r := range got {
+		if r.ID == "fact:water:100" && r.Meta["source"] != "voice" {
+			t.Fatalf("water lost its source meta: %+v", r.Meta)
+		}
+	}
+	if notes, err := mem.ByPrefix(ctx, "note:"); err != nil || len(notes) != 1 {
+		t.Fatalf("the note row was touched: %+v (err %v)", notes, err)
+	}
+
+	// Marker written, so a second run is free and changes nothing.
+	again, err := s.RepairFactVectors(ctx, embed)
+	if err != nil {
+		t.Fatalf("second RepairFactVectors: %v", err)
+	}
+	if !again.Skipped {
+		t.Fatalf("second run did work: %+v; the marker must make it a no-op", again)
+	}
+}