Compare commits

..

1 Commits

Author SHA1 Message Date
claude afac8fb670 mavend: run the persona checks before she speaks (V-399)
The checks stay in the eval package and the daemon calls three of them:
feminine, address, and a new leaked-reasoning test. No retry — it doubles
the latency on the turn that is already going badly, and on the nudge path
the moment has passed. A failure falls back to the deterministic floor and
is logged with the whole rejected text and counted by check name.

hisgender is deliberately not run: the simulator showed it rejecting
"записала, что ты выпил воды", which is her own correct self-reference.
2026-08-04 04:35:42 +04:00
26 changed files with 293 additions and 381 deletions
+13 -13
View File
@@ -106,11 +106,11 @@ func trimClarifyExpired(s string) string {
// out, and "" when nothing was parked. Call it right after
// resolveClarifyAnswer: a live question is answered there, an expired one is
// only reported here — the words themselves still go on to be routed fresh.
func (h *reactiveHandler) clarifyExpiredNotice(ctx context.Context) string {
func (h *reactiveHandler) clarifyExpiredNotice() string {
if h.clarifyStore == nil {
return ""
}
if !h.clarifyStore.TakeExpired(dialogueIDOf(ctx), h.now()) {
if !h.clarifyStore.TakeExpired(voiceDialogueID, h.now()) {
return ""
}
log.Printf("voice: clarify — parked question expired, telling him and routing the words fresh")
@@ -157,7 +157,7 @@ func clarifyQuestion(dec router.Decision) (dialogue.Slot, string, bool) {
// askClarify parks the request and returns the question to ask instead of the
// canned "не поняла". Returns ("", false) when there is nothing to ask about, so
// the caller falls back to the canned reply.
func (h *reactiveHandler) askClarify(ctx context.Context, dec router.Decision) (string, bool) {
func (h *reactiveHandler) askClarify(dec router.Decision) (string, bool) {
if h.clarifyStore == nil {
return "", false
}
@@ -165,7 +165,7 @@ func (h *reactiveHandler) askClarify(ctx context.Context, dec router.Decision) (
if !ok {
return "", false
}
h.clarifyStore.Put(dialogueIDOf(ctx), &dialogue.PendingQuestion{
h.clarifyStore.Put(voiceDialogueID, &dialogue.PendingQuestion{
Intent: dialogue.Intent(dec.Intent),
Slots: toDialogueSlots(dec.Slots),
Missing: []dialogue.Slot{slot},
@@ -192,7 +192,7 @@ func (h *reactiveHandler) resolveClarifyAnswer(ctx context.Context, text string)
if h.clarifyStore == nil {
return "", false
}
q := h.clarifyStore.Get(dialogueIDOf(ctx), h.now())
q := h.clarifyStore.Get(voiceDialogueID, h.now())
if q == nil {
return "", false
}
@@ -206,9 +206,9 @@ func (h *reactiveHandler) resolveClarifyAnswer(ctx context.Context, text string)
// would fire at 11:00 saying "напомни" and nothing else.
q.Utterance = foldAnswerIntoUtterance(q.Utterance, merged.Text)
if len(dialogue.StillMissing(q.Missing, merged)) > 0 {
return h.reaskOrGiveUp(ctx, q, merged, text), true
return h.reaskOrGiveUp(q, merged, text), true
}
h.clarifyStore.Delete(dialogueIDOf(ctx))
h.clarifyStore.Delete(voiceDialogueID)
// One gap filled is not the same as a complete request. askClarify parks
// only the first gap, because one question per turn is the rule, but a
@@ -217,7 +217,7 @@ func (h *reactiveHandler) resolveClarifyAnswer(ctx context.Context, text string)
// a reminder with no time, which answered "не получилось разобрать время
// напоминания." — an error for a request she never finished asking about.
// Re-enter the loop instead, one question at a time as before.
if reply, asked := h.askRemainingGap(ctx, q, intent, merged); asked {
if reply, asked := h.askRemainingGap(q, intent, merged); asked {
return reply, true
}
@@ -261,7 +261,7 @@ func foldAnswerIntoUtterance(utterance, subject string) string {
// The attempt budget is shared with the re-ask path on purpose. A second gap
// costs a question exactly like a second try at the first one does, so the cap
// still bounds how many times she can speak before acting or letting go.
func (h *reactiveHandler) askRemainingGap(ctx context.Context, q *dialogue.PendingQuestion, intent router.Intent, merged dialogue.Slots) (string, bool) {
func (h *reactiveHandler) askRemainingGap(q *dialogue.PendingQuestion, intent router.Intent, merged dialogue.Slots) (string, bool) {
remaining := dialogue.StillMissing(wantedSlots[intent], merged)
if len(remaining) == 0 {
return "", false
@@ -270,7 +270,7 @@ func (h *reactiveHandler) askRemainingGap(ctx context.Context, q *dialogue.Pendi
if !ok || !q.CanAsk() {
return "", false
}
h.clarifyStore.Put(dialogueIDOf(ctx), &dialogue.PendingQuestion{
h.clarifyStore.Put(voiceDialogueID, &dialogue.PendingQuestion{
Intent: q.Intent,
Slots: merged,
Missing: []dialogue.Slot{remaining[0]},
@@ -287,13 +287,13 @@ func (h *reactiveHandler) askRemainingGap(ctx context.Context, q *dialogue.Pendi
// reaskOrGiveUp handles an answer that left the gap open: ask the same question
// again while she has attempts left, otherwise say she did not understand and
// let the request go. Never returns "" — a mute give-up reads as "done".
func (h *reactiveHandler) reaskOrGiveUp(ctx context.Context, q *dialogue.PendingQuestion, merged dialogue.Slots, text string) string {
func (h *reactiveHandler) reaskOrGiveUp(q *dialogue.PendingQuestion, merged dialogue.Slots, text string) string {
question := ""
if len(q.Missing) > 0 {
question = clarifyQuestions[q.Missing[0]]
}
if question == "" || !q.CanAsk() {
h.clarifyStore.Delete(dialogueIDOf(ctx))
h.clarifyStore.Delete(voiceDialogueID)
log.Printf("voice: clarify — gave up on %v after %d question(s), answer was %q", q.Missing, q.Attempts, text)
return clarifyGaveUp
}
@@ -302,7 +302,7 @@ func (h *reactiveHandler) reaskOrGiveUp(ctx context.Context, q *dialogue.Pending
q.Slots = merged
q.Attempts++
q.Asked = h.now()
h.clarifyStore.Put(dialogueIDOf(ctx), q)
h.clarifyStore.Put(voiceDialogueID, q)
log.Printf("voice: clarify — answer %q did not fill %v, asking again (attempt %d)", text, q.Missing, q.Attempts)
return question
}
+21 -50
View File
@@ -81,7 +81,7 @@ func TestClarifyReminderCompletesOnAnswer(t *testing.T) {
ctx := context.Background()
h, st, _ := newClarifyHandler(t)
question, asked := h.askClarify(ctx, clarifyDec(router.IntentReminder, router.Slots{Text: "напомни позвонить маме"}, "напомни позвонить маме"))
question, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{Text: "напомни позвонить маме"}, "напомни позвонить маме"))
if !asked || question != "Когда?" {
t.Fatalf("expected the time question, got %q asked=%v", question, asked)
}
@@ -112,7 +112,7 @@ func TestClarifyFactCompletesOnAnswer(t *testing.T) {
ctx := context.Background()
h, st, _ := newClarifyHandler(t)
if _, asked := h.askClarify(ctx, clarifyDec(router.IntentFact, router.Slots{Text: "запиши"}, "запиши")); !asked {
if _, asked := h.askClarify(clarifyDec(router.IntentFact, router.Slots{Text: "запиши"}, "запиши")); !asked {
t.Fatal("a fact with no key should be asked about")
}
if reply, handled := h.resolveClarifyAnswer(ctx, "пил воду"); !handled || reply == clarifyGaveUp {
@@ -128,7 +128,7 @@ func TestClarifyAnswerAfterTTLIsANewRequest(t *testing.T) {
ctx := context.Background()
h, st, now := newClarifyHandler(t)
if _, asked := h.askClarify(ctx, clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
if _, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
t.Fatal("expected a question")
}
*now = now.Add(clarifyTTL + time.Second)
@@ -147,7 +147,7 @@ func TestClarifyAsksThreeTimesThenSaysSo(t *testing.T) {
ctx := context.Background()
h, st, _ := newClarifyHandler(t)
if _, asked := h.askClarify(ctx, clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
if _, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
t.Fatal("expected a first question")
}
// Two more unclear answers ⇒ two more questions (3 asks in total).
@@ -185,7 +185,7 @@ func TestClarifyMaxAttemptsIsConfigurable(t *testing.T) {
h, _, _ := newClarifyHandler(t)
h.clarifyMaxAttempts = 1
if _, asked := h.askClarify(ctx, clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
if _, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
t.Fatal("expected a question")
}
if reply, handled := h.resolveClarifyAnswer(ctx, "ну не знаю"); !handled || reply != clarifyGaveUp {
@@ -199,7 +199,7 @@ func TestClarifyRestatedAnswerWins(t *testing.T) {
ctx := context.Background()
h, st, _ := newClarifyHandler(t)
if _, asked := h.askClarify(ctx, clarifyDec(router.IntentReminder, router.Slots{Text: "напомни позвонить маме"}, "напомни позвонить маме")); !asked {
if _, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{Text: "напомни позвонить маме"}, "напомни позвонить маме")); !asked {
t.Fatal("expected a question")
}
// First answer parses, but re-park it by hand as if she had asked again:
@@ -232,7 +232,7 @@ func TestClarifiedActOffAllowlistIsStillRefused(t *testing.T) {
h, st, _ := newClarifyHandler(t)
marker := filepath.Join(t.TempDir(), "not-allowed-ran")
if _, asked := h.askClarify(ctx, clarifyDec(router.IntentAct, router.Slots{Text: "сделай это"}, "сделай это")); !asked {
if _, asked := h.askClarify(clarifyDec(router.IntentAct, router.Slots{Text: "сделай это"}, "сделай это")); !asked {
t.Fatal("an act with no fn should be asked about")
}
reply, handled := h.resolveClarifyAnswer(ctx, "rm "+marker)
@@ -260,7 +260,7 @@ func TestClarifiedDestructiveActStillNeedsConfirm(t *testing.T) {
t.Fatal(err)
}
if _, asked := h.askClarify(ctx, clarifyDec(router.IntentAct, router.Slots{Text: "сделай это"}, "сделай это")); !asked {
if _, asked := h.askClarify(clarifyDec(router.IntentAct, router.Slots{Text: "сделай это"}, "сделай это")); !asked {
t.Fatal("expected a question")
}
reply, handled := h.resolveClarifyAnswer(ctx, "delete_backups")
@@ -284,7 +284,7 @@ func TestNoQuestionWhenNothingIsMissing(t *testing.T) {
clarifyDec(router.IntentQuery, router.Slots{Text: "ммм"}, "ммм"),
clarifyDec(router.IntentNote, router.Slots{Text: "..."}, "..."),
} {
if question, asked := h.askClarify(context.Background(), dec); asked {
if question, asked := h.askClarify(dec); asked {
t.Fatalf("intent %s should keep the canned reply, got %q", dec.Intent, question)
}
}
@@ -296,29 +296,29 @@ func TestNoQuestionWhenNothingIsMissing(t *testing.T) {
// TestClarifyExpiryIsAnnouncedAndWordsStillRoute — his answer lands after the
// TTL: she must say the old request is gone AND still answer the new words.
func TestClarifyExpiryIsAnnouncedAndWordsStillRoute(t *testing.T) {
ctx := withDialogueID(context.Background(), dialogueIDFor(sourceText, ""))
ctx := context.Background()
h, _, now := newClarifyHandler(t)
emb := router.NewHashEmbedder(1024)
h.embedder = emb
h.router = buildRouter(emb, h.matcher, 0.55, nil)
if _, asked := h.askClarify(ctx, clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
if _, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
t.Fatal("expected a question")
}
*now = now.Add(clarifyTTL + time.Second)
reply := h.handleText(ctx, "", "как дела")
reply := h.handleText(ctx, "как дела")
if !isClarifyExpired(reply) {
t.Fatalf("expired question must be announced first, got %q", reply)
}
if trimClarifyExpired(reply) == "" {
t.Fatalf("the new words must still be answered, got only the notice: %q", reply)
}
if h.clarifyStore.Get(textDialogueID, h.now()) != nil {
if h.clarifyStore.Get(voiceDialogueID, h.now()) != nil {
t.Fatal("the expired question must be gone")
}
// The notice is said once, not on every later utterance.
if reply := h.handleText(ctx, "", "как дела"); isClarifyExpired(reply) {
if reply := h.handleText(ctx, "как дела"); isClarifyExpired(reply) {
t.Fatalf("notice repeated on a later turn: %q", reply)
}
}
@@ -340,7 +340,7 @@ func TestClarifyAsksAboutTheSecondGapToo(t *testing.T) {
ctx := context.Background()
h, st, _ := newClarifyHandler(t)
question, asked := h.askClarify(ctx, clarifyDec(router.IntentReminder, router.Slots{}, "напомни"))
question, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{}, "напомни"))
if !asked || question != "О чём напомнить?" {
t.Fatalf("expected the subject question, got %q asked=%v", question, asked)
}
@@ -380,7 +380,7 @@ func TestClarifySecondGapRespectsTheAttemptCap(t *testing.T) {
h, _, _ := newClarifyHandler(t)
h.clarifyMaxAttempts = 1
if _, asked := h.askClarify(ctx, clarifyDec(router.IntentReminder, router.Slots{}, "напомни")); !asked {
if _, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{}, "напомни")); !asked {
t.Fatal("expected the subject question")
}
reply, handled := h.resolveClarifyAnswer(ctx, "позвонить маме")
@@ -440,10 +440,10 @@ func TestClarifyProseHoldsThePersona(t *testing.T) {
// The confirm turn used to return before the notice was even computed, so he
// answered the confirm and never heard that the older request was let go.
func TestExpiryNoticeSurvivesAConfirmTurn(t *testing.T) {
ctx := withDialogueID(context.Background(), dialogueIDFor(sourceText, ""))
ctx := context.Background()
h, _, now := newClarifyHandler(t)
if _, asked := h.askClarify(ctx, clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
if _, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
t.Fatal("expected a question")
}
// A confirm parked with a longer life than the question, so only the
@@ -451,7 +451,7 @@ func TestExpiryNoticeSurvivesAConfirmTurn(t *testing.T) {
h.pending = &pendingAct{fn: "delete_backups", phrase: "удалить бэкапы", expiry: now.Add(time.Hour)}
*now = now.Add(clarifyTTL + time.Second)
reply := h.handleText(ctx, "", "нет")
reply := h.handleText(ctx, "нет")
if !isClarifyExpired(reply) {
t.Fatalf("the expired question must be announced on a confirm turn too, got %q", reply)
}
@@ -461,7 +461,7 @@ func TestExpiryNoticeSurvivesAConfirmTurn(t *testing.T) {
if h.pending != nil {
t.Fatal("the confirm must still have been consumed")
}
if h.clarifyStore.Get(textDialogueID, h.now()) != nil {
if h.clarifyStore.Get(voiceDialogueID, h.now()) != nil {
t.Fatal("the expired question must be gone")
}
}
@@ -476,7 +476,7 @@ func TestClarifySubjectAnswerFillsRatherThanClobbers(t *testing.T) {
h, st, _ := newClarifyHandler(t)
at := h.now().Add(2 * time.Hour)
question, asked := h.askClarify(ctx, clarifyDec(router.IntentReminder,
question, asked := h.askClarify(clarifyDec(router.IntentReminder,
router.Slots{Time: at, HasTime: true}, "напомни в 11"))
if !asked || question != "О чём напомнить?" {
t.Fatalf("expected the subject question, got %q asked=%v", question, asked)
@@ -501,32 +501,3 @@ func TestClarifySubjectAnswerFillsRatherThanClobbers(t *testing.T) {
t.Fatalf("the answer clobbered the original request: %q", reminders[0].Payload)
}
}
// TestClarifyIsPerConversation — the parked question belongs to the reach that
// was asked. Before this the clarify store had one global key, so a question
// asked in the web chat and never answered captured the next utterance from
// telegram, or from the mic, and answered it against a request the speaker had
// never made (Vikunja #466).
func TestClarifyIsPerConversation(t *testing.T) {
h, _, _ := newClarifyHandler(t)
web := withDialogueID(context.Background(), dialogueIDFor(sourceText, "web"))
telegram := withDialogueID(context.Background(), dialogueIDFor(sourceText, "telegram:42"))
if _, asked := h.askClarify(web, clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
t.Fatal("expected a question on the web conversation")
}
if _, handled := h.resolveClarifyAnswer(telegram, "в 11:00"); handled {
t.Fatal("a question asked on the web must not eat a telegram utterance")
}
if _, handled := h.resolveClarifyAnswer(voiceCtx(), "в 11:00"); handled {
t.Fatal("a question asked on the web must not eat what he says at the mic")
}
if reply, handled := h.resolveClarifyAnswer(web, "в 11:00"); !handled || reply == clarifyGaveUp {
t.Fatalf("the asker's own answer must land, handled=%v reply=%q", handled, reply)
}
}
// voiceCtx — the mic's conversation, which carries no id of its own.
func voiceCtx() context.Context {
return withDialogueID(context.Background(), dialogueIDFor(sourceVoice, ""))
}
+3 -50
View File
@@ -1,64 +1,17 @@
package main
import (
"context"
"time"
"github.com/kami/maven/internal/dialogue"
"github.com/kami/maven/internal/router"
)
// voiceDialogueID — the dialogue-session key for the microphone, and the
// clarify key for it too. This is a single-user box (ponytail), so one slot
// suffices; a second speaker would need per-speaker ids, which waits on
// voice-print attribution (see PROGRESS multi-user deferral).
// voiceDialogueID — the single dialogue-session key. This is a single-user box
// (ponytail), so one slot suffices; a second speaker would need per-speaker ids,
// which waits on voice-print attribution (see PROGRESS multi-user deferral).
const voiceDialogueID = "voice"
// textDialogueID — the clarify key for a text turn that named no conversation.
// Separate from the mic: an old client that sends no id still must not answer
// a question she asked out loud.
const textDialogueID = "text"
// dialogueKey — the context key carrying the id of the conversation this turn
// belongs to. It rides the context rather than a parameter for the same reason
// the correlation id does: every step of the turn needs it, most of them only
// to hand to the next one, and threading it by hand would put it in six
// clarify signatures that have nothing else to say about it.
type dialogueKey struct{}
// dialogueIDFor builds the id a turn is held under: the conversation the reach
// named, qualified by the tap it arrived on, or the tap's own fallback when it
// named none.
//
// A parked clarifying question used to be held under voiceDialogueID no matter
// where the turn came from, so one unanswerable question captured the next
// three utterances from anywhere. Three independent curl sessions fed a
// capture attempt that had already failed, and a reminder among them was lost
// (Vikunja #466).
func dialogueIDFor(src turnSource, conversation string) string {
if conversation != "" {
return string(src) + ":" + conversation
}
if src == sourceVoice {
return voiceDialogueID
}
return textDialogueID
}
// withDialogueID tags a turn with that id.
func withDialogueID(ctx context.Context, id string) context.Context {
return context.WithValue(ctx, dialogueKey{}, id)
}
// dialogueIDOf reads it back. Falls back to the microphone's slot, which is
// what an unthreaded caller — a test, an internal replay — gets.
func dialogueIDOf(ctx context.Context) string {
if id, ok := ctx.Value(dialogueKey{}).(string); ok && id != "" {
return id
}
return voiceDialogueID
}
// toDialogueSlots and applyDialogueSlots are the only bridge between
// router.Slots and dialogue.Slots. dialogue must not import router (import
// cycle), so the two structs are hand-kept copies and every field has to be
+134
View File
@@ -0,0 +1,134 @@
package main
import (
"context"
"log"
"regexp"
"strings"
"sync"
"github.com/kami/maven/internal/delivery"
"github.com/kami/maven/internal/loop"
"github.com/kami/maven/internal/phraser"
"github.com/kami/maven/internal/phraser/eval"
)
// The persona checks, run before she speaks (Vikunja #399).
//
// RunChecks and RunTalkChecks only ever ran from the eval package, so
// everything the fixtures measured was offline knowledge: we could say "about
// one reply in three is broken" and still ship every one of them. This runs the
// cheap half of that on the live path, and replaces a failing message with the
// deterministic floor.
//
// Which checks: the unambiguous string tests only — feminine self-reference,
// how she addresses him, and a leaked-reasoning test. Not length, which is
// path-specific, and not ontopic, which compares against fragments the fixture
// supplies and runtime does not have. Not hisgender either — see guardSpoken.
//
// No retry. A retry doubles the latency on the exact turn that is already going
// badly, and on the nudge path the moment has passed.
//
// The known cost, written down because it is real: a wrongly flagged good reply
// is replaced by a flatter stub one. That is the right trade — a stub sentence
// is dull, a leaked reasoning trace is broken — but it means these checks can
// no longer be tuned for sensitivity alone.
// checkLeak — the name reported when the model's scaffolding reaches the text.
const checkLeak = "leak"
// leakPatterns — reasoning and protocol that belongs to the model, not to him.
// The resident model is a Thinking variant, so an unclosed reasoning block is
// the failure mode, not a hypothetical (Vikunja #398).
var leakPatterns = []*regexp.Regexp{
regexp.MustCompile(`(?i)<\s*/?\s*think`),
regexp.MustCompile(`(?i)thinking\s*(process|:)`),
regexp.MustCompile(`(?i)^\s*(assistant|user|system)\s*:`),
// Raw contract JSON: the parser already unwraps a good one, so a body that
// still carries the keys is one it could not read.
regexp.MustCompile(`"(response|mood|body|summary)"\s*:`),
// The persona block quoted back at him.
regexp.MustCompile(`(?i)(ты\s+—?\s*мэйвен|системный промпт|system prompt)`),
}
// checkPersonaLeak reports whether the model's own scaffolding is in the text.
func checkPersonaLeak(body string) (string, bool) {
for _, re := range leakPatterns {
if m := re.FindString(body); m != "" {
return "leaked " + strings.TrimSpace(m), false
}
}
return "", true
}
// personaRejects counts what the guard caught, by check name, so the real
// production rate is knowable rather than inferred from the fixture.
var personaRejects = struct {
mu sync.Mutex
by map[string]int
}{by: map[string]int{}}
func personaRejectCounts() map[string]int {
personaRejects.mu.Lock()
defer personaRejects.mu.Unlock()
out := make(map[string]int, len(personaRejects.by))
for k, v := range personaRejects.by {
out[k] = v
}
return out
}
// guardSpoken checks a phrased message. It returns the failed check and false
// when the message must not be said; path names the caller, for the log.
//
// An empty message passes: the caller already treats that as a failure and
// falls back on its own, and reporting it as a persona breach would put a
// misleading line in the count.
func guardSpoken(path, body string) (string, bool) {
if strings.TrimSpace(body) == "" {
return "", true
}
if detail, ok := checkPersonaLeak(body); !ok {
return rejectSpoken(path, checkLeak, detail, body), false
}
// Feminine and address only. HisGender is not run here: it reads a
// sentence-initial feminine verb with no pronoun — "записала, что ты выпил
// воды" — as a woman being addressed, when it is her own correct
// self-reference. Offline that is a point of score; on this path it would
// replace a good reply with a stub one on every fact she confirms.
for _, r := range []eval.Result{eval.Feminine(body), eval.Address(body)} {
if !r.Pass {
return rejectSpoken(path, r.Name, r.Detail, body), false
}
}
return "", true
}
// rejectSpoken logs what she nearly said and counts it. The whole text, not a
// prefix: the point of the log line is that the failure can be read back later
// and argued with.
func rejectSpoken(path, check, detail, body string) string {
personaRejects.mu.Lock()
personaRejects.by[check]++
personaRejects.mu.Unlock()
log.Printf("persona: %s rejected on %s (%s): %q", path, check, detail, body)
return check
}
// guardNudge checks a phrased nudge and falls back to the deterministic floor
// when it fails. The nudge path, unlike the reply path, cannot ask again: the
// tick has already decided she speaks, so the choice is the floor's wording or
// a broken sentence.
func guardNudge(pn delivery.PhrasedNudge, cand loop.Candidate) delivery.PhrasedNudge {
if _, ok := guardSpoken("nudge", pn.Body); ok {
return pn
}
stub, err := phraser.NewStub().PhraseNudge(context.Background(), cand)
if err != nil {
// The Stub is templates over the candidate and does not fail. If it
// somehow does, the model's text is still what the rule decided to
// say, and saying nothing is the worse outcome.
return pn
}
return stub
}
+75
View File
@@ -0,0 +1,75 @@
package main
import (
"strings"
"testing"
"github.com/kami/maven/internal/delivery"
"github.com/kami/maven/internal/loop"
)
func TestGuardPassesWhatSheShouldSay(t *testing.T) {
good := []string{
"записала: купить хлеб.",
"поняла, напомню в 11:00.",
"ты не пил воду с утра.",
"я рада, что получилось.",
"",
}
for _, body := range good {
if check, ok := guardSpoken("test", body); !ok {
t.Errorf("guardSpoken(%q) rejected on %s", body, check)
}
}
}
func TestGuardStopsWhatSheShouldNot(t *testing.T) {
bad := []struct {
body string
want string
}{
{"<think>он просил воду</think> попей воды.", checkLeak},
{"Thinking Process: он давно не пил.", checkLeak},
{`{"response": "попей воды", "mood": "neutral"}`, checkLeak},
{"я напомнил тебе про воду.", "feminine"},
{"вы давно не пили воду.", "address"},
}
for _, c := range bad {
check, ok := guardSpoken("test", c.body)
if ok {
t.Errorf("guardSpoken(%q) let it through", c.body)
continue
}
if check != c.want {
t.Errorf("guardSpoken(%q) failed on %s; want %s", c.body, check, c.want)
}
}
}
func TestGuardCountsWhatItCaught(t *testing.T) {
before := personaRejectCounts()[checkLeak]
if _, ok := guardSpoken("test", "<think>…"); ok {
t.Fatal("a leaked reasoning block was let through")
}
if after := personaRejectCounts()[checkLeak]; after != before+1 {
t.Errorf("leak count %d; want %d", after, before+1)
}
}
// TestGuardNudgeFallsBackToTheFloor — a broken nudge is replaced by the
// deterministic wording, not dropped and not retried.
func TestGuardNudgeFallsBackToTheFloor(t *testing.T) {
cand := loop.Candidate{Rule: loop.Rule{Name: "water"}}
bad := delivery.PhrasedNudge{Candidate: cand, Body: "Thinking Process: он не пил.", Mood: "neutral"}
got := guardNudge(bad, cand)
if got.Body == bad.Body {
t.Fatal("the broken nudge was delivered unchanged")
}
if strings.TrimSpace(got.Body) == "" {
t.Fatal("the nudge was dropped rather than re-worded")
}
good := delivery.PhrasedNudge{Candidate: cand, Body: "попей воды.", Mood: "neutral"}
if guardNudge(good, cand).Body != good.Body {
t.Error("a good nudge was replaced")
}
}
-37
View File
@@ -2,14 +2,12 @@ package main
import (
"context"
"strings"
"testing"
"time"
"github.com/kami/maven/internal/ipc"
"github.com/kami/maven/internal/memory"
"github.com/kami/maven/internal/router"
"github.com/kami/maven/internal/store"
"github.com/kami/maven/internal/tool"
"github.com/kami/maven/internal/voice"
)
@@ -87,38 +85,3 @@ func TestReactiveNotesReminders(t *testing.T) {
}
})
}
// TestSpokenTaskCaptureFilesATask — the whole path, from the utterance to the
// task table. It went dead when the router started claiming the marker as an
// act: capture rides the note intent, so nothing below actionNote was ever
// reached and every capture answered "Что сделать?" (Vikunja #467).
func TestSpokenTaskCaptureFilesATask(t *testing.T) {
ctx := context.Background()
st := newTestStore(t)
api := ipc.NewStoreAPI(st)
now := time.Now()
emb := router.NewHashEmbedder(1024)
matcher := tool.NewMatcher(api)
h := &reactiveHandler{
api: api,
embedder: emb,
router: buildRouter(emb, matcher, 0.55, nil),
replier: voice.NewStubReplier(),
now: func() time.Time { return now },
memStore: memory.NewInMemoryStore(),
dataStore: st,
}
reply := h.handleText(ctx, "web", "добавь в задачи купить молоко")
if !strings.Contains(reply, "купить молоко") {
t.Fatalf("capture did not claim the turn: %q", reply)
}
open, err := st.ListTasks(ctx, store.TaskOpen)
if err != nil || len(open) != 1 {
t.Fatalf("task was not filed: tasks=%v err=%v", open, err)
}
// The words he said, not the model's rewrite of them.
if open[0].Text != "купить молоко" {
t.Fatalf("task text was rewritten: %q", open[0].Text)
}
}
+5
View File
@@ -30,5 +30,10 @@ func (r *llmReplier) Reply(d router.Decision) string {
if err != nil || out == "" {
return r.stub.Reply(d)
}
// The persona checks, on the live path (personaguard.go). A reply that
// leaks reasoning or calls him "вы" is worse than a flat one.
if _, ok := guardSpoken("reply", out); !ok {
return r.stub.Reply(d)
}
return out
}
+6 -3
View File
@@ -176,6 +176,9 @@ func (t *tickLoop) tick(ctx context.Context, now time.Time) {
t.queueNudge(ctx, cand, state, now)
} else {
pn, err := t.phraser.PhraseNudge(ctx, *cand)
if err == nil {
pn = guardNudge(pn, *cand)
}
if err != nil {
log.Printf("tick: phrase nudge %s: %v", cand.Rule.Name, err)
} else {
@@ -986,7 +989,7 @@ type daemonAPI struct {
getTrace func() *loop.TickTrace
getMorningStatus func(ctx context.Context) []ipc.MorningRoutineStatus
getDayPlan func(ctx context.Context) ipc.DayPlan
chatFn func(ctx context.Context, conversation, text string) string
chatFn func(ctx context.Context, text string) string
getMCPServers func() []ipc.MCPServerStatus
getEvents func(n int) []ipc.IntakeEvent
}
@@ -1002,11 +1005,11 @@ func (d *daemonAPI) RecentEvents(ctx context.Context, n int) ([]ipc.IntakeEvent,
return d.getEvents(n), nil
}
func (d *daemonAPI) Chat(ctx context.Context, conversation, text string) (string, error) {
func (d *daemonAPI) Chat(ctx context.Context, text string) (string, error) {
if d.chatFn == nil {
return "", errors.New("mavend: chat not available")
}
return d.chatFn(ctx, conversation, text), nil
return d.chatFn(ctx, text), nil
}
// MCPServers — the configured MCP servers and their health (Vikunja #251).
+4 -4
View File
@@ -220,9 +220,9 @@ func (h *reactiveHandler) upgradeAPI(api ipc.CoreAPI) {
// handleText — the core reactive path without stt/tts. Used by the IPC Chat
// endpoint (and eventually by telegram). Splits out the audio bookends from
// HandlePushToTalk so text channels share the same routing logic.
func (h *reactiveHandler) handleText(ctx context.Context, conversation, text string) string {
func (h *reactiveHandler) handleText(ctx context.Context, text string) string {
log.Printf("voice: handleText: %q", text)
return h.runTurn(withDialogueID(ctx, dialogueIDFor(sourceText, conversation)), text, sourceText)
return h.runTurn(ctx, text, sourceText)
}
// turnSource — which channel this utterance arrived on, in the same provenance
@@ -255,7 +255,7 @@ func (h *reactiveHandler) runTurn(ctx context.Context, text string, src turnSour
// early. He can be asked a question, walk off, come back and say "да" to a
// confirm that is still parked; computing the notice after that return meant
// he answered the confirm and never heard that the older request was let go.
expiredNotice := h.clarifyExpiredNotice(ctx)
expiredNotice := h.clarifyExpiredNotice()
// 2. confirm turn — if a destructive act is parked, this utterance is its
// y/n answer, not a fresh command. Handled before routing so "да" doesn't
@@ -351,7 +351,7 @@ func (h *reactiveHandler) runTurn(ctx context.Context, text string, src turnSour
// and park the request (clarify.go); otherwise the replier's canned reply
// stands.
if dec.Clarify {
if question, asked := h.askClarify(ctx, dec); asked {
if question, asked := h.askClarify(dec); asked {
return withNotice(expiredNotice, question)
}
}
-5
View File
@@ -380,11 +380,6 @@ func buildRouter(emb router.Embedder, acts router.ActMatcher, threshold float64,
// is an agenda question and must not.
grammars = append(grammars, router.AgendaQueryGrammars()...)
grammars = append(grammars, router.ReminderGrammar())
// Last, and it matches any utterance shape — its Build is the filter. An
// explicit capture marker beats the model, which called it an act and
// rewrote the task text (Vikunja #467). After the rules above because a
// marker never collides with a clock or agenda question.
grammars = append(grammars, router.TaskCaptureGrammar())
return router.New(router.Config{
Grammars: grammars,
Classifier: cls,
+1 -1
View File
@@ -77,7 +77,7 @@ func (f *fakeCore) MCPServers(context.Context) ([]ipc.MCPServerStatus, error) {
return f.mcpServers, f.mcpErr
}
func (f *fakeCore) Chat(_ context.Context, _, text string) (string, error) {
func (f *fakeCore) Chat(_ context.Context, text string) (string, error) {
f.chatText = text
if f.chatErr != nil {
return "", f.chatErr
+1 -7
View File
@@ -1678,13 +1678,7 @@ func handleChatAPI(w http.ResponseWriter, r *http.Request, core ipc.CoreAPI, ses
http.Redirect(w, r, "/chat", http.StatusSeeOther)
return
}
// One conversation id for the whole web chat, and a different one from
// telegram or the mic. A parked question belongs to the reach that was
// asked; before this, a clarify nobody answered on the web ate the next
// utterance spoken at the mic (Vikunja #466). This server has no
// per-browser session, so every browser tab is the same conversation —
// which is right for a single-owner box.
reply, err := core.Chat(r.Context(), "web", text)
reply, err := core.Chat(r.Context(), text)
if err != nil {
log.Printf("chat api: %v", err)
http.Redirect(w, r, "/chat", http.StatusSeeOther)
+3 -3
View File
@@ -311,7 +311,7 @@ func TestGate_IpcServer_CheckWiredThroughSocket(t *testing.T) {
if fake.writes != 0 {
t.Errorf("auth refused but CoreAPI was called %d time(s); refused calls must not reach CoreAPI", fake.writes)
}
_, err = cli.Chat(context.Background(), "web", "привет")
_, err = cli.Chat(context.Background(), "привет")
if !errors.Is(err, ipc.ErrForbidden) {
t.Errorf("wire: chat from unenrolled uid = %v; want ipc.ErrForbidden", err)
}
@@ -344,7 +344,7 @@ func TestGate_IpcServer_ChatAllowedForEnrolledCaller(t *testing.T) {
t.Fatalf("dial: %v", err)
}
t.Cleanup(func() { _ = cli.Close() })
reply, err := cli.Chat(context.Background(), "web", "привет")
reply, err := cli.Chat(context.Background(), "привет")
if err != nil {
t.Fatalf("Chat: %v", err)
}
@@ -373,7 +373,7 @@ func (r *recordingAPI) WriteFact(_ context.Context, _ ipc.WriteFactReq) (int64,
return int64(r.writes), nil
}
func (r *recordingAPI) Chat(_ context.Context, _, text string) (string, error) {
func (r *recordingAPI) Chat(_ context.Context, text string) (string, error) {
r.chats++
return "echo: " + text, nil
}
+2 -13
View File
@@ -593,14 +593,8 @@ type MCPServerStatus struct {
}
// chatReq / chatResp — text chat round-trip for the IPC Chat method.
//
// Conversation names the thread this utterance belongs to: a mavweb session, a
// telegram chat. It is opaque to the daemon and only has to be stable for one
// conversation and distinct across them. Empty is allowed and means "the
// unattributed text tap", which is what an old client sends.
type chatReq struct {
Text string `json:"text"`
Conversation string `json:"conversation,omitempty"`
Text string `json:"text"`
}
type chatResp struct {
Reply string `json:"reply"`
@@ -765,12 +759,7 @@ type CoreAPI interface {
// Chat routes a text utterance through the reactive handler's core path
// (router → dialogue → action → replier) and returns the reply text.
// No audio or stt/tts — for text channels (mavweb, telegram).
//
// conversation names the thread. A parked clarifying question is held per
// conversation, so an unanswered question on one reach cannot eat the next
// utterance from another (Vikunja #466). Empty means the unattributed text
// tap and is still one conversation of its own, separate from the mic.
Chat(ctx context.Context, conversation, text string) (string, error)
Chat(ctx context.Context, text string) (string, error)
// RecentEvents returns the daemon's unified intake journal, newest first
// (Vikunja #283) — one envelope per thing that arrived, whatever direction
+2 -2
View File
@@ -623,9 +623,9 @@ func (c *Client) AcceptProposedRoutine(ctx context.Context, id int64) error {
return c.call(ctx, MethodAcceptProposedRoutine, acceptProposedRoutineReq{ID: id}, nil)
}
func (c *Client) Chat(ctx context.Context, conversation, text string) (string, error) {
func (c *Client) Chat(ctx context.Context, text string) (string, error) {
var r chatResp
if err := c.call(ctx, MethodChat, chatReq{Text: text, Conversation: conversation}, &r); err != nil {
if err := c.call(ctx, MethodChat, chatReq{Text: text}, &r); err != nil {
return "", err
}
return r.Reply, nil
+2 -2
View File
@@ -401,7 +401,7 @@ func TestChatViaClient(t *testing.T) {
}
t.Cleanup(func() { _ = cli.Close() })
reply, err := cli.Chat(context.Background(), "web", "привет")
reply, err := cli.Chat(context.Background(), "привет")
if err != nil {
t.Fatalf("Chat: %v", err)
}
@@ -417,7 +417,7 @@ type chatTestAPI struct {
UnimplementedCoreAPI
}
func (a *chatTestAPI) Chat(ctx context.Context, _, text string) (string, error) {
func (a *chatTestAPI) Chat(ctx context.Context, text string) (string, error) {
if text == "привет" {
return "и тебе привет!", nil
}
+2 -2
View File
@@ -240,7 +240,7 @@ func (a *storeAPI) RevertFact(ctx context.Context, key string) (int64, error) {
return newID, mapErr(err)
}
func (a *storeAPI) Chat(ctx context.Context, conversation, text string) (string, error) {
func (a *storeAPI) Chat(ctx context.Context, text string) (string, error) {
return "", errors.New("store: chat not available via direct store API")
}
@@ -974,7 +974,7 @@ var methodTable = map[Method]handlerFunc{
return map[string]int64{"new_id": newID}, nil
}),
MethodChat: withParams(func(ctx context.Context, api CoreAPI, p chatReq) (chatResp, error) {
reply, err := api.Chat(ctx, p.Conversation, p.Text)
reply, err := api.Chat(ctx, p.Text)
return chatResp{Reply: reply}, err
}),
MethodTickTrace: withoutParams(func(ctx context.Context, api CoreAPI) (TickTrace, error) {
+1 -1
View File
@@ -141,6 +141,6 @@ func (UnimplementedCoreAPI) MCPServers(ctx context.Context) ([]MCPServerStatus,
func (UnimplementedCoreAPI) DayPlan(ctx context.Context) (DayPlan, error) {
return DayPlan{}, ErrNotImplemented
}
func (UnimplementedCoreAPI) Chat(ctx context.Context, conversation, text string) (string, error) {
func (UnimplementedCoreAPI) Chat(ctx context.Context, text string) (string, error) {
return "", ErrNotImplemented
}
+2 -24
View File
@@ -53,31 +53,9 @@ const MinOnPatternFraction = 0.7
// a repeat. False negatives cost one more observation and nothing else.
const MinEvents = 4
// MinIntervalDays — the fastest rhythm that may be called a routine. Two
// hours.
//
// Without a floor, four taps of the same key minutes apart give intervals near
// 0.002 days. They all sit inside the ±50% band by construction, so the
// detector proposed a routine and PhraseRoutine worded it as "каждый день"
// (Vikunja #468). The damage outlives the mistake: UNIQUE(action, object)
// means dismissing the bogus proposal burns that pair permanently, so the real
// routine behind it can never be proposed again.
//
// Two hours rather than a day, because a genuine habit can run several times a
// day — meals, water, a break. Anything faster than that is not a habit she
// should be proposing to remind him about; the loop rules already cover that
// range, and they are rules, not guesses. It is checked against the median, so
// one quick repeat inside a real rhythm still counts.
//
// The other half of this is that hand-QA of the detector was unsafe: seeding a
// pattern the obvious way, four chat turns in a row, poisoned the very pair
// being tested.
const MinIntervalDays = 2.0 / 24.0
// Detect checks whether a sequence of events for the same action+object
// forms a stable recurring pattern. Returns a ProposedRoutine when:
// - At least MinEvents events exist (≥3 intervals)
// - The median interval is at least MinIntervalDays
// - At least MinOnPatternFraction of the intervals sit within
// MaxIntervalRatio of the median interval
//
@@ -110,8 +88,8 @@ func Detect(events []Event) (*ProposedRoutine, error) {
}
center := medianFloat(intervals)
if center <= 0 || center < MinIntervalDays {
return nil, nil // a burst, not a rhythm — see MinIntervalDays
if center <= 0 {
return nil, nil
}
// Keep the intervals that sit inside the band around the median. The
-43
View File
@@ -216,46 +216,3 @@ func TestDetectMedianBandNotExtremes(t *testing.T) {
})
}
}
// A burst is not a habit. Four taps of the same key minutes apart give
// intervals near 0.002 days, all inside the ±50% band by construction, so the
// detector called it a daily routine (Vikunja #468). Dismissing that proposal
// burns the action+object pair permanently, which also made hand-QA of the
// detector unsafe.
func TestDetectRejectsABurst(t *testing.T) {
base := time.Date(2026, 8, 4, 9, 0, 0, 0, time.UTC)
var events []Event
for i := 0; i < 4; i++ {
events = append(events, Event{
Action: "refill", Object: "cat_water",
Ts: base.Add(time.Duration(i) * 7 * time.Minute),
})
}
r, err := Detect(events)
if err != nil {
t.Fatalf("Detect: %v", err)
}
if r != nil {
t.Fatalf("four taps minutes apart proposed a routine every %.3f days", r.IntervalDays)
}
}
// The floor is two hours, not a day: a habit that runs several times a day is
// still a habit.
func TestDetectKeepsASeveralTimesADayHabit(t *testing.T) {
base := time.Date(2026, 8, 4, 8, 0, 0, 0, time.UTC)
var events []Event
for i := 0; i < 5; i++ {
events = append(events, Event{
Action: "drink", Object: "water",
Ts: base.Add(time.Duration(i) * 4 * time.Hour),
})
}
r, err := Detect(events)
if err != nil {
t.Fatalf("Detect: %v", err)
}
if r == nil {
t.Fatal("a four-hour rhythm over five events is a habit, got nil")
}
}
+15 -29
View File
@@ -67,6 +67,19 @@ func RunChecks(c Case, body, mood string) []Result {
}
}
// Feminine, HisGender and Address expose three checks one at a time, so the
// daemon can run them on a phrased message before he hears it (Vikunja #399).
// Only these three: they are unambiguous string tests with nothing to compare
// against, while length is path-specific and ontopic needs the fixture's
// expected fragments, which do not exist at runtime.
func Feminine(body string) Result { return checkFeminine(body) }
// HisGender — see checkHisGender.
func HisGender(body string) Result { return checkHisGender(body) }
// Address — see checkAddress.
func Address(body string) Result { return checkAddress(body) }
func checkMood(mood string) Result {
if Moods[mood] {
return Result{CheckMood, true, ""}
@@ -173,23 +186,12 @@ func checkFeminine(body string) Result {
// Second pass: self-reference with the pronoun dropped — "напомнил тебе",
// "проверил за тебя". A masculine past-tense verb whose object is HIM can
// only be her speaking about herself.
//
// Two guards, both from a false positive on the talk fixture: "ты заплатил
// за домен до марта" scored as her drift and cost the run a point it had
// earned (Vikunja #462). He is male, so a past-tense verb governed by "ты"
// must be masculine. And a bare "за" is not evidence of anything — "за
// домен" is a price, "за тебя" is her doing something on his behalf — so it
// only counts when he is the one it points at.
for i, w := range words {
if !masculinePast(w) || i+1 >= len(words) || governedByYou(words, i) {
if !masculinePast(w) || i+1 >= len(words) {
continue
}
next := words[i+1]
aboutHim := next == "тебе" || next == "тебя"
if next == "за" && i+2 < len(words) && (words[i+2] == "тебя" || words[i+2] == "тебе") {
aboutHim = true
}
if aboutHim {
if next == "тебе" || next == "тебя" || next == "за" {
return Result{CheckFeminine, false,
fmt.Sprintf("masculine self-reference %q before %q", w, next)}
}
@@ -663,19 +665,3 @@ func checkEllipsis(body string) Result {
}
return Result{CheckEllipsis, true, ""}
}
// governedByYou reports whether "ты" stands close enough in front of the verb
// at index i to be its subject. Three words, the same window checkFeminine's
// first pass uses after "я", and it stops at a first-person pronoun so "ты
// просил, я напомнил" still trips.
func governedByYou(words []string, i int) bool {
for j := i - 1; j >= 0 && j >= i-3; j-- {
switch words[j] {
case "ты":
return true
case "я":
return false
}
}
return false
}
-6
View File
@@ -106,12 +106,6 @@ func TestChecksCatchWhatTheyClaim(t *testing.T) {
{"masculine predicative", "я должен сказать: попей воды.", CheckFeminine},
// The other direction: HE is male, so second-person masculine is right.
{"second person masculine ok", "ты не пил воду четыре часа.", ""},
// The recorded false positive: "заплатил" sits before "за", and the
// second pass read that as her dropping the pronoun. The subject is
// "ты" and he is male, so the reply is right (Vikunja #462).
{"second person masculine before за", "ты заплатил за домен до марта, а воду пить всё равно надо.", ""},
// The same shape she really does get wrong still trips.
{"masculine on his behalf", "проверил за тебя — воды не было четыре часа.", CheckFeminine},
// The real observed failure: she addressed him as a woman.
{"feminine second person", "ты давно не отдыхала — попей воды.", CheckHisGender},
{"feminine second person no dash", "ты пила воду четыре часа назад.", CheckHisGender},
-1
View File
@@ -71,7 +71,6 @@
{ "id": "ru-note-003", "utterance": "заметка про настройку vlan на свитче", "lang": "ru", "intent": "note", "tags": ["homelab"] },
{ "id": "ru-note-004", "utterance": "запиши идею: гидропоника на балконе", "lang": "ru", "intent": "note" },
{ "id": "ru-note-005", "utterance": "запиши что сосед просил номер электрика", "lang": "ru", "intent": "note" },
{ "id": "ru-note-006", "utterance": "добавь в задачи купить молоко", "lang": "ru", "intent": "note", "tags": ["capture"], "note": "an explicit capture marker — the model called it an act and rewrote the payload (Vikunja #467), stage 0 claims it" },
{ "id": "en-note-001", "utterance": "note: rotate the kuma api key", "lang": "en", "intent": "note", "tags": ["homelab"] },
{ "id": "ru-sys-001", "utterance": "сколько сейчас времени в киеве", "lang": "ru", "intent": "system", "tags": ["time"] },
+1 -48
View File
@@ -1,9 +1,6 @@
package router
import (
"regexp"
"strings"
)
import "strings"
// Task capture and task listing, matched deterministically (Vikunja #130).
//
@@ -204,47 +201,3 @@ func IsTaskListQuery(text string) bool {
}
return false
}
// TaskCaptureGrammar — stage 0 for an explicit capture marker, so the resident
// model never sees it (Vikunja #467).
//
// Capture was built to ride the note intent, deliberately: #130 said no eighth
// intent, and while the classifier was routing, a note-shaped utterance with a
// marker in it reached actionNote and captureTaskFromNote claimed it there. The
// router pre-empted that. Measured 2026-08-02: "добавь в задачи купить молоко"
// routed act, so captureTaskFromNote was never consulted, the act arm found no
// allowlisted fn, and the gate asked "Что сделать?". Every capture utterance
// tried filed nothing.
//
// The model also rewrote the payload on the way — "купить молоко" came back as
// "сделать покупку молока". A task must read as the words he said, which is a
// second reason to answer this before the model rather than to prompt around
// it.
//
// The marker list is data (task_phrases.json) and the parse strips urgency, so
// the pattern here matches any utterance and the decision is ParseTaskCapture's
// to make — same shape as the wake-word act grammar, which also matches broadly
// and refuses in Build. Intent stays note: the daemon's note path is where
// capture lives, and nothing about the contract with the model changes.
func TaskCaptureGrammar() Grammar {
return Grammar{
Name: "task-capture",
Pattern: regexp.MustCompile(`(?s)^\s*(.+)$`),
Build: func(m []string) (Decision, bool) {
c, ok := ParseTaskCapture(m[1])
if !ok {
return Decision{}, false // not a capture — fall through
}
return Decision{
Stage: 0,
Intent: IntentNote,
Confidence: 1.0,
// The capture text, not the raw utterance: it is what the
// clarify gate reads as the payload. captureTaskFromNote
// re-parses the utterance itself, so the task text comes from
// the same place either way.
Slots: Slots{Text: c.Text},
}, true
},
}
}
-3
View File
@@ -27,9 +27,6 @@
"добавь в список",
"добавь задачу",
"запиши в задачи",
"запиши в список дел",
"запиши в список задач",
"запиши в список",
"запиши задачу",
"новая задача",
"поставь задачу",
-34
View File
@@ -85,37 +85,3 @@ func TestIsTaskListQuery(t *testing.T) {
}
}
}
// TestTaskCaptureGrammarClaimsTheMarker — the capture marker is answered at
// stage 0, so the model never gets to call it an act (Vikunja #467).
func TestTaskCaptureGrammarClaimsTheMarker(t *testing.T) {
g := TaskCaptureGrammar()
captures := map[string]string{
"добавь в задачи купить молоко": "купить молоко",
"запиши в список дел купить хлеб": "купить хлеб",
"поставь задачу вынести мусор": "вынести мусор",
"добавь в задачи срочно оплатить дом": "оплатить дом",
}
for in, want := range captures {
m := g.Pattern.FindStringSubmatch(in)
if m == nil {
t.Fatalf("%q did not match the grammar pattern", in)
}
d, ok := g.Build(m)
if !ok {
t.Fatalf("%q must be claimed as a capture", in)
}
if d.Intent != IntentNote || d.Slots.Text != want {
t.Errorf("%q → intent=%s text=%q, want note/%q", in, d.Intent, d.Slots.Text, want)
}
}
// Everything without a marker falls through, including a marker with no
// task after it and a question about the list.
for _, in := range []string{"надо бы поспать", "добавь в задачи", "какие у меня задачи?", "перезапусти nginx"} {
if m := g.Pattern.FindStringSubmatch(in); m != nil {
if _, ok := g.Build(m); ok {
t.Errorf("%q must fall through to the cascade", in)
}
}
}
}