kami/Maven
1
0
Fork 0
Code Issues 1 Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Let a note win a recall, not only a fact (#373)

Browse Source 
The memory pass ran only after the notes-only gate had already rejected
the same note at the same score. Notes and facts share one vector index,
so a note that failed there failed again — the branch could only ever
return a fact.

Now the memory pass runs first: one search over everything Maven
remembers, one gate, and the memory that clearly matches best answers
(a note gets phrased, a fact is read back). The notes-only pass stays
behind it for notes the vector index does not hold. No threshold moved,
so the set of questions answered is unchanged — only which memory
answers them.

Fixture gained two mixed note+fact cases, so the answerable count goes
25 -> 27: hash recall@1 36.0% -> 37.0% (ratchet 0.32 unchanged, comment
updated), e5 recall@1 72.0% -> 70.4%, false recall still 1/5.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
This commit is contained in:
kami
2026-07-31 13:30:38 +04:00
parent 1bd2acdc2a
commit 98ee701e03
8 changed files with 266 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cmd/mavend/voice.go
+32 -10
View File
@@ -775,11 +775,43 @@ func (h *reactiveHandler) applyAction(ctx context.Context, dec router.Decision)
log.Printf("voice: embed query: %v", err)
return "не получилось найти ответ."
}
// Long-term memory first: ONE search over everything Maven remembers
// (notes and facts share this index) and ONE confidence gate, so the
// memory that is clearly the best match answers — a note just as much
// as a fact.
//
// This used to run only after the notes-only gate below had already
// rejected the same note at the same score, which no note could ever
// survive a second time: the branch could only return a fact (#373).
// Order, not the gate, was the bug — the set of questions Maven answers
// is unchanged, only which memory gets to answer them.
if h.memStore != nil {
if hits, herr := h.memStore.Search(ctx, vec, 3); herr == nil {
if hit, ok := bestRecall(hits, h.queryMinScore, h.queryMinMargin); ok {
text := hit.Meta["text"]
// A note is phrased in Maven's voice; a fact is read back
// as it was stored.
if hit.Meta["type"] == "note" {
if reply, perr := h.phraser.PhraseQuery(ctx, dec.Utterance, []string{text}); perr == nil && reply != "" {
return reply
}
}
return text
}
} else {
log.Printf("voice: memory search: %v", herr)
}
}
notes, err := h.api.QueryNotes(ctx, vec, 5)
if err != nil {
log.Printf("voice: query notes: %v", err)
return "не получилось найти ответ."
}
// Notes-only pass, for notes the vector index above does not hold (an
// older note written before it existed). Same gate, notes-only
// candidates.
//
// Confidence gate: below it, say "I don't know" rather than read back
// the least-unrelated note — a confident wrong recall is worse than a
// gap (spec's "not a guesser-of-truth"). Same instinct as the loop's
@@ -791,16 +823,6 @@ func (h *reactiveHandler) applyAction(ctx context.Context, dec router.Decision)
noteScores[i] = n.Score
}
if !memory.ConfidentScores(noteScores, h.queryMinScore, h.queryMinMargin) {
// Long-term memory recall (notes + facts) before general knowledge:
// the notes table can't answer fact questions, but the memory store
// indexes both. Only runs when notes-RAG already gave up → additive.
if h.memStore != nil {
if hits, herr := h.memStore.Search(ctx, vec, 3); herr == nil {
if text, ok := bestRecall(hits, h.queryMinScore, h.queryMinMargin); ok {
return text
}
}
}
// Try general knowledge from the phraser before giving up
reply, err := h.phraser.PhraseQuery(ctx, dec.Utterance, nil)
if err != nil || reply == "" {