Make locative recall prove identity, not overlap (V-719)
The spare-key note scored 0.832 to 0.867 against a spare passport, a blue shirt, a blue document box and a car key. Score and margin cannot separate those: the right note runs 0.817 to 0.892 and the silent cases 0.787 to 0.874, so the ranges overlap and structure has to decide. RecallAllowed now takes two structural facts from the router. A locative question must corroborate every identity term against the candidate's subject, read up to its first dictionary-proven verb, so a location object in the note cannot answer for the thing being located. A turn that is not question-shaped needs a named shared topic even when it ends in '?', which is what "я отменил напоминание про молоко" lacked when it recalled an unrelated note at 0.825 with no runner-up to fail the margin. query_min_score moves 0.55 to 0.80 for tokenizer rev 2. The held-out fixture answers 14/27 real recalls and 0/14 false ones. LocativeAnswerVerifier is the resident-model second opinion, kept behind the deterministic gate and wired into nothing. The measurement that says why is docs/evals/2026-08-15-locative-answerability-verifier.md. --no-verify: master is the working branch this session by the owner's call. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
@@ -193,9 +193,9 @@ func TestQueryRecallNoteCanWin(t *testing.T) {
|
||||
t.Run("the better-matching fact answers", func(t *testing.T) {
|
||||
h, _ := buildRecallHandler(t, q, []recallCase{
|
||||
{text: "молоко стоит в холодильнике", score: 0.80, kind: "note"},
|
||||
{text: "купил молоко в среду", score: 0.95, kind: "fact"},
|
||||
{text: "молоко было в холодильнике в среду", score: 0.95, kind: "fact"},
|
||||
})
|
||||
if reply := askQuery(t, h, q); reply != "купил молоко в среду" {
|
||||
if reply := askQuery(t, h, q); reply != "молоко было в холодильнике в среду" {
|
||||
t.Errorf("reply %q, want the fact read back", reply)
|
||||
}
|
||||
})
|
||||
@@ -212,3 +212,63 @@ func TestQueryRecallNoteCanWin(t *testing.T) {
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
// TestQueryRecallRequiresStructuralOrTopicEvidence — the whole-assistant
|
||||
// cold-start regression. The routing heads called an ordinary past-tense
|
||||
// report a query; with one note in the store the margin gate has no runner-up,
|
||||
// and cosine 0.825 was enough to speak a completely unrelated spare-key note.
|
||||
// A bare question mark does not turn the proposition into an open information
|
||||
// question, negation must not weaken the refusal, and a locative question must
|
||||
// corroborate the target it asks Maven to locate (V-719).
|
||||
func TestQueryRecallRequiresStructuralOrTopicEvidence(t *testing.T) {
|
||||
const unrelated = "запомни: запасной ключ лежит в синей коробке"
|
||||
for _, tc := range []struct {
|
||||
query string
|
||||
score float64
|
||||
}{
|
||||
{"я отменил напоминание про молоко", 0.825031306},
|
||||
{"я отменил напоминание про молоко?", 0.825031306},
|
||||
{"я не отменил напоминание про молоко", 0.825031306},
|
||||
{"я не отменил напоминание про молоко?", 0.825031306},
|
||||
{"где мой паспорт?", 0.817210},
|
||||
{"где я отменил напоминание про молоко?", 0.805800},
|
||||
{"где лежит синяя рубашка?", 0.837694},
|
||||
{"где лежит синяя папка?", 0.837472},
|
||||
{"где мой запасной паспорт?", 0.831662},
|
||||
{"где лежит запасная флешка?", 0.838980},
|
||||
{"где находится синяя коробка с документами?", 0.866553},
|
||||
{"где лежит ключ от машины?", 0.843853},
|
||||
{"где синяя коробка?", 0.90},
|
||||
} {
|
||||
t.Run(tc.query, func(t *testing.T) {
|
||||
h, phr := buildRecallHandler(t, tc.query, []recallCase{
|
||||
{text: unrelated, score: tc.score, kind: "note"},
|
||||
})
|
||||
reply := askQuery(t, h, tc.query)
|
||||
if strings.Contains(reply, "запасной ключ") {
|
||||
t.Fatalf("unrelated note escaped into reply %q", reply)
|
||||
}
|
||||
if len(phr.notes) != 0 {
|
||||
t.Fatalf("unrelated note reached the phraser: %q", phr.notes)
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
// Voice punctuation is optional. A nominal request with no interrogative
|
||||
// still works when the candidate itself corroborates the named topic.
|
||||
const nominal = "адрес домашнего сервера"
|
||||
h, _ := buildRecallHandler(t, nominal, []recallCase{
|
||||
{text: "домашний сервер на 192.168.1.104", score: 0.90, kind: "note"},
|
||||
})
|
||||
if reply := askQuery(t, h, nominal); !strings.Contains(reply, "домашний сервер") {
|
||||
t.Fatalf("nominal recall lost its shared-topic answer: %q", reply)
|
||||
}
|
||||
|
||||
const locative = "где лежит запасной ключ?"
|
||||
h, _ = buildRecallHandler(t, locative, []recallCase{
|
||||
{text: "запасной ключ лежит в синей коробке", score: 0.90, kind: "note"},
|
||||
})
|
||||
if reply := askQuery(t, h, locative); !strings.Contains(reply, "запасной ключ") {
|
||||
t.Fatalf("locative recall lost its corroborated target: %q", reply)
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user