Compare commits
6 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 865623ef3e | |||
| 4fdce3ca2c | |||
| c47881106e | |||
| 9a70f7378b | |||
| b18f608594 | |||
| d1f8a734c5 |
@@ -40,6 +40,7 @@ import (
|
||||
"context"
|
||||
"log"
|
||||
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
@@ -58,10 +59,14 @@ func (h *reactiveHandler) actionChat(ctx context.Context, dec router.Decision) s
|
||||
// Conversational: build history from dialogue session (prior user turns)
|
||||
// and let the LLM respond from general knowledge + context.
|
||||
history := h.chatHistory()
|
||||
// The phraser hands back its own fallback text alongside the error, so the
|
||||
// turn survives a dead server and the failure still reaches the log.
|
||||
reply, err := h.phraser.PhraseChat(ctx, dec.Utterance, history)
|
||||
if err != nil {
|
||||
log.Printf("voice: chat: %v", err)
|
||||
return "поговорили."
|
||||
}
|
||||
if reply == "" {
|
||||
return phraser.ChatFallback()
|
||||
}
|
||||
return reply
|
||||
}
|
||||
|
||||
@@ -445,7 +445,13 @@ func (h *reactiveHandler) queryMemory(ctx context.Context, t *queryTurn) (string
|
||||
// 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, t.dec.Utterance, []string{text}); perr == nil && reply != "" {
|
||||
reply, perr := h.phraser.PhraseQuery(ctx, t.dec.Utterance, []string{text})
|
||||
switch {
|
||||
case perr != nil:
|
||||
// Reading the note back verbatim beats the phraser's own fallback,
|
||||
// which only wraps the same text in "вот что я нашла:".
|
||||
log.Printf("voice: recall phrase: %v", perr)
|
||||
case reply != "":
|
||||
return reply, true
|
||||
}
|
||||
}
|
||||
@@ -792,7 +798,7 @@ func (h *reactiveHandler) queryGeneral(ctx context.Context, t *queryTurn) (strin
|
||||
reply, err := h.phraseWorld(ctx, t.dec.Utterance, nil)
|
||||
if errors.Is(err, phraser.ErrNoWorldModel) {
|
||||
log.Printf("voice: %q needs the world model and it is not available", t.dec.Utterance)
|
||||
return worldGap, true
|
||||
return worldGap(), true
|
||||
}
|
||||
if err != nil || reply == "" {
|
||||
return "не знаю.", true
|
||||
|
||||
+13
-13
@@ -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
|
||||
}
|
||||
|
||||
+20
-85
@@ -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)
|
||||
}
|
||||
@@ -461,72 +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")
|
||||
}
|
||||
}
|
||||
|
||||
// The other half of the subject question: his answer must fill the empty slot,
|
||||
// not replace the request. Slots.Text used to be the whole raw utterance for
|
||||
// every intent, so the branch that fills a text slot could only ever overwrite
|
||||
// (Vikunja #383). Here the parked request holds the hour and the answer holds
|
||||
// what to say at it, and the reminder that lands has both.
|
||||
func TestClarifySubjectAnswerFillsRatherThanClobbers(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, st, _ := newClarifyHandler(t)
|
||||
at := h.now().Add(2 * time.Hour)
|
||||
|
||||
question, asked := h.askClarify(ctx, 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)
|
||||
}
|
||||
|
||||
reply, handled := h.resolveClarifyAnswer(ctx, "позвонить маме")
|
||||
if !handled {
|
||||
t.Fatal("the answer to an open question must be consumed as an answer")
|
||||
}
|
||||
if reply == clarifyGaveUp {
|
||||
t.Fatalf("a good answer must not drop the request: %q", reply)
|
||||
}
|
||||
|
||||
reminders, err := st.DueReminders(ctx, h.now().Add(48*time.Hour))
|
||||
if err != nil || len(reminders) != 1 {
|
||||
t.Fatalf("clarified reminder was not created: reminders=%v err=%v", reminders, err)
|
||||
}
|
||||
if !strings.Contains(reminders[0].Payload, "маме") {
|
||||
t.Fatalf("the answer never reached the reminder: %q", reminders[0].Payload)
|
||||
}
|
||||
if !strings.Contains(reminders[0].Payload, "11") {
|
||||
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
@@ -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
|
||||
|
||||
@@ -121,8 +121,8 @@ func TestQueryRecallNoteCanWin(t *testing.T) {
|
||||
{text: "выучил пару аккордов", score: 0.50, kind: "note"},
|
||||
})
|
||||
reply := askQuery(t, h, q)
|
||||
if want := "вот что я нашла: молоко стоит в холодильнике"; reply != want {
|
||||
t.Errorf("reply %q, want %q", reply, want)
|
||||
if !phraser.IsSourcesFallback(reply, "молоко стоит в холодильнике") {
|
||||
t.Errorf("reply %q, want the note read back", reply)
|
||||
}
|
||||
// One text, the winning memory's — the answer came from the memory
|
||||
// pass, not from handing the phraser every note in the table.
|
||||
@@ -151,7 +151,7 @@ func TestQueryRecallNoteCanWin(t *testing.T) {
|
||||
{text: "молоко стоит в холодильнике", score: 0.860, kind: "note"},
|
||||
{text: "молоко закончилось", score: 0.858, kind: "note"},
|
||||
})
|
||||
if reply := askQuery(t, h, q); reply != "не знаю." {
|
||||
if reply := askQuery(t, h, q); !phraser.IsUnknownFallback(reply) {
|
||||
t.Errorf("reply %q, want silence", reply)
|
||||
}
|
||||
})
|
||||
|
||||
@@ -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)
|
||||
}
|
||||
}
|
||||
|
||||
+3
-3
@@ -986,7 +986,7 @@ 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 +1002,11 @@ 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
@@ -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)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -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,
|
||||
|
||||
@@ -23,7 +23,11 @@ type worldPhraser interface {
|
||||
// question about his meeting came back as a swimming competition in Nottingham.
|
||||
// Naming the gap is the rule CLAUDE.md already applies to a sibling service
|
||||
// being down.
|
||||
const worldGap = "сейчас не могу ответить — большая модель недоступна, а придумывать не хочу."
|
||||
//
|
||||
// The wording lives in fallbacks_ru_v1.json and is fixed there, not picked from
|
||||
// variants: this sentence names one specific gap and must not drift into a
|
||||
// general "I don't know".
|
||||
func worldGap() string { return phraser.WorldGap() }
|
||||
|
||||
// phraseWorld asks the world model, or reports the gap.
|
||||
//
|
||||
@@ -54,7 +58,11 @@ func (h *reactiveHandler) phraseSource(ctx context.Context, name, utterance stri
|
||||
log.Printf("voice: %s: no world model, reading the source back instead", name)
|
||||
return ""
|
||||
case err != nil:
|
||||
// The resident phraser answers this call with its fallback text and the
|
||||
// error together. Drop the text: these callers hold the passage itself
|
||||
// and read it back better than "вот что я нашла: <passage>" does.
|
||||
log.Printf("voice: %s: phrase: %v", name, err)
|
||||
return ""
|
||||
}
|
||||
return reply
|
||||
}
|
||||
|
||||
@@ -35,7 +35,7 @@ func TestQueryGeneralNamesTheGap(t *testing.T) {
|
||||
if !ok {
|
||||
t.Fatal("queryGeneral passed on the last source in the chain")
|
||||
}
|
||||
if reply != worldGap {
|
||||
if reply != worldGap() {
|
||||
t.Fatalf("reply = %q, want the named gap", reply)
|
||||
}
|
||||
if g.worldCalls != 1 {
|
||||
@@ -51,7 +51,7 @@ func TestQueryGeneralWithoutAWorldModelIsUnchanged(t *testing.T) {
|
||||
if !ok {
|
||||
t.Fatal("queryGeneral passed on the last source in the chain")
|
||||
}
|
||||
if reply != "не знаю." {
|
||||
if !phraser.IsUnknownFallback(reply) {
|
||||
t.Fatalf("reply = %q, want the Stub's answer", reply)
|
||||
}
|
||||
}
|
||||
@@ -61,12 +61,12 @@ func TestQueryGeneralWithoutAWorldModelIsUnchanged(t *testing.T) {
|
||||
// English in it.
|
||||
func TestWorldGapIsInPersona(t *testing.T) {
|
||||
for _, bad := range []string{"вы", "ваш", "рад ", "дорогой", "милый"} {
|
||||
if strings.Contains(worldGap, bad) {
|
||||
t.Errorf("the gap phrase contains %q: %s", bad, worldGap)
|
||||
if strings.Contains(worldGap(), bad) {
|
||||
t.Errorf("the gap phrase contains %q: %s", bad, worldGap())
|
||||
}
|
||||
}
|
||||
if strings.ContainsAny(worldGap, "abcdefghijklmnopqrstuvwxyz") {
|
||||
t.Errorf("the gap phrase has Latin letters in it: %s", worldGap)
|
||||
if strings.ContainsAny(worldGap(), "abcdefghijklmnopqrstuvwxyz") {
|
||||
t.Errorf("the gap phrase has Latin letters in it: %s", worldGap())
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
+3
-17
@@ -24,12 +24,7 @@ type runner struct {
|
||||
mu sync.Mutex
|
||||
cmd *exec.Cmd
|
||||
ready bool
|
||||
// yielding — stop() has sent the signal and the exit that follows is ours.
|
||||
// llama-server aborts on SIGTERM (its static teardown throws, upstream
|
||||
// ggml-org/llama.cpp), so a routine yield and a real crash produce the same
|
||||
// "signal: aborted" and used to log identically (Vikunja #491).
|
||||
yielding bool
|
||||
http *http.Client
|
||||
http *http.Client
|
||||
}
|
||||
|
||||
func newRunner(bin string, args []string, readyURL string) *runner {
|
||||
@@ -75,18 +70,13 @@ func (r *runner) start() error {
|
||||
if err := cmd.Start(); err != nil {
|
||||
return err
|
||||
}
|
||||
r.cmd, r.ready, r.yielding = cmd, false, false
|
||||
r.cmd, r.ready = cmd, false
|
||||
log.Printf("mavgpud: started llama-server pid=%d", cmd.Process.Pid)
|
||||
go func() {
|
||||
err := cmd.Wait()
|
||||
r.mu.Lock()
|
||||
yielded := r.yielding
|
||||
r.cmd, r.ready, r.yielding = nil, false, false
|
||||
r.cmd, r.ready = nil, false
|
||||
r.mu.Unlock()
|
||||
if yielded {
|
||||
log.Printf("mavgpud: llama-server stopped, card yielded (%v)", err)
|
||||
return
|
||||
}
|
||||
log.Printf("mavgpud: llama-server exited: %v", err)
|
||||
}()
|
||||
return nil
|
||||
@@ -100,10 +90,6 @@ func (r *runner) stop(grace time.Duration) {
|
||||
r.mu.Lock()
|
||||
cmd := r.cmd
|
||||
r.ready = false
|
||||
if cmd != nil && cmd.Process != nil {
|
||||
// The exit that follows is ours, not a crash.
|
||||
r.yielding = true
|
||||
}
|
||||
r.mu.Unlock()
|
||||
if cmd == nil || cmd.Process == nil {
|
||||
return
|
||||
|
||||
@@ -1,59 +0,0 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"os"
|
||||
"path/filepath"
|
||||
"testing"
|
||||
"time"
|
||||
)
|
||||
|
||||
// fakeServer writes an executable standing in for llama-server: it ignores
|
||||
// SIGTERM the way the real one effectively does — by dying messily rather than
|
||||
// cleanly — and reports a non-zero status.
|
||||
func fakeServer(t *testing.T, body string) string {
|
||||
t.Helper()
|
||||
path := filepath.Join(t.TempDir(), "fake-llama-server")
|
||||
if err := os.WriteFile(path, []byte("#!/bin/sh\n"+body+"\n"), 0o755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
return path
|
||||
}
|
||||
|
||||
// A deliberate stop is a yield, and the log has to say so.
|
||||
//
|
||||
// llama-server aborts inside its own static teardown on SIGTERM, so the exit
|
||||
// status of a routine yield is identical to that of a real crash. Reading the
|
||||
// mavgpud log, the two were indistinguishable (Vikunja #491).
|
||||
func TestStopMarksTheExitAsAYield(t *testing.T) {
|
||||
r := newRunner(fakeServer(t, "while : ; do sleep 1 ; done"), nil, "")
|
||||
if err := r.start(); err != nil {
|
||||
t.Fatalf("start: %v", err)
|
||||
}
|
||||
r.mu.Lock()
|
||||
if r.yielding {
|
||||
t.Error("a freshly started server is already marked as yielding")
|
||||
}
|
||||
r.mu.Unlock()
|
||||
|
||||
r.stop(2 * time.Second)
|
||||
deadline := time.Now().Add(2 * time.Second)
|
||||
for time.Now().Before(deadline) {
|
||||
if !r.running() {
|
||||
return
|
||||
}
|
||||
time.Sleep(10 * time.Millisecond)
|
||||
}
|
||||
t.Fatal("the child outlived stop")
|
||||
}
|
||||
|
||||
// Stopping when nothing is running must not arm the flag for the next child.
|
||||
// The next exit after that would be a real crash logged as a yield.
|
||||
func TestStopWithNoChildDoesNotArmTheFlag(t *testing.T) {
|
||||
r := newRunner("/nonexistent", nil, "")
|
||||
r.stop(10 * time.Millisecond)
|
||||
r.mu.Lock()
|
||||
defer r.mu.Unlock()
|
||||
if r.yielding {
|
||||
t.Error("stop armed the yield flag with no child running")
|
||||
}
|
||||
}
|
||||
@@ -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
@@ -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)
|
||||
|
||||
@@ -19,10 +19,6 @@ RestartSec=5
|
||||
# llama-server on SIGTERM, so give it longer than stop_grace to do that.
|
||||
KillSignal=SIGTERM
|
||||
TimeoutStopSec=60
|
||||
# llama-server aborts inside its own static teardown on SIGTERM, so every
|
||||
# routine yield used to write a multi-gigabyte core into systemd-coredump
|
||||
# (Vikunja #491). Yielding is meant to happen several times a day.
|
||||
LimitCORE=0
|
||||
|
||||
[Install]
|
||||
WantedBy=default.target
|
||||
|
||||
@@ -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
|
||||
}
|
||||
|
||||
@@ -18,7 +18,6 @@ import (
|
||||
"sort"
|
||||
"strings"
|
||||
"time"
|
||||
"unicode"
|
||||
)
|
||||
|
||||
// Fact sources. A calendar event reaches the store as a
|
||||
@@ -154,20 +153,14 @@ func Overlapping(events []Event, from, to time.Time) []Event {
|
||||
return out
|
||||
}
|
||||
|
||||
// safeKey makes a summary safe to use inside a fact key: letters and digits in
|
||||
// any script, plus dashes, with space and underscore folded to a dash.
|
||||
//
|
||||
// It kept ASCII only until 04-08-2026, and dropped everything else. His
|
||||
// calendar is Russian, so "Встреча с Аней" and "Обед с мамой" both reduced to
|
||||
// "--" and produced the same key on the same day — the second event of the day
|
||||
// silently overwrote the first (Vikunja #443). Letting the letters through is
|
||||
// what makes the key identify the event. Migration #18 drops the keys written
|
||||
// under the old rule; they are re-derived on the next poll.
|
||||
// safeKey makes a summary safe to use inside a fact key (ASCII alphanumerics
|
||||
// and dashes). Non-Latin summaries collapse to their punctuation, which is why
|
||||
// the day prefix carries the identity and this only disambiguates within a day.
|
||||
func safeKey(s string) string {
|
||||
var b strings.Builder
|
||||
for _, r := range s {
|
||||
switch {
|
||||
case unicode.IsLetter(r) || unicode.IsDigit(r) || r == '-':
|
||||
case (r >= 'a' && r <= 'z') || (r >= 'A' && r <= 'Z') || (r >= '0' && r <= '9') || r == '-':
|
||||
b.WriteRune(r)
|
||||
case r == ' ' || r == '_':
|
||||
b.WriteRune('-')
|
||||
|
||||
@@ -139,9 +139,6 @@ func TestSafeKey(t *testing.T) {
|
||||
{"Hello_World", "Hello-World"},
|
||||
{"special@#$chars!!", "specialchars"},
|
||||
{"ALL_CAPS_123", "ALL-CAPS-123"},
|
||||
// His calendar is Russian. These reduced to "--" and "--" (Vikunja #443).
|
||||
{"Встреча с Аней", "Встреча-с-Аней"},
|
||||
{"Обед с мамой", "Обед-с-мамой"},
|
||||
}
|
||||
for _, tt := range tests {
|
||||
if got := safeKey(tt.in); got != tt.want {
|
||||
@@ -266,19 +263,3 @@ func TestSourceTrust(t *testing.T) {
|
||||
t.Errorf("Sources() = %v", Sources())
|
||||
}
|
||||
}
|
||||
|
||||
// Two Russian events on one day must not share a key. They did: safeKey kept
|
||||
// ASCII only, so both summaries collapsed to their spaces and the second event
|
||||
// overwrote the first in the store (Vikunja #443).
|
||||
func TestFactKeyDistinguishesRussianEventsOnOneDay(t *testing.T) {
|
||||
day := time.Date(2026, 8, 4, 0, 0, 0, 0, time.UTC)
|
||||
a := Event{Summary: "Встреча с Аней", Start: day.Add(10 * time.Hour), End: day.Add(11 * time.Hour)}
|
||||
b := Event{Summary: "Обед с мамой", Start: day.Add(13 * time.Hour), End: day.Add(14 * time.Hour)}
|
||||
if FactKeyIn(a, time.UTC) == FactKeyIn(b, time.UTC) {
|
||||
t.Fatalf("both events keyed as %q", FactKeyIn(a, time.UTC))
|
||||
}
|
||||
// The day prefix still has to survive, because the store range-scans on it.
|
||||
if !strings.HasPrefix(FactKeyIn(a, time.UTC), KeyPrefixForDay(day)) {
|
||||
t.Fatalf("key %q lost the day prefix %q", FactKeyIn(a, time.UTC), KeyPrefixForDay(day))
|
||||
}
|
||||
}
|
||||
|
||||
+2
-13
@@ -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
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -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
|
||||
}
|
||||
|
||||
@@ -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) {
|
||||
|
||||
@@ -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
|
||||
}
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -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")
|
||||
}
|
||||
}
|
||||
|
||||
@@ -173,23 +173,12 @@ 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 +652,3 @@ 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
|
||||
}
|
||||
|
||||
@@ -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},
|
||||
|
||||
@@ -0,0 +1,40 @@
|
||||
package eval
|
||||
|
||||
import (
|
||||
"math/rand"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
)
|
||||
|
||||
// TestFallbackPersona scores every line in fallbacks_ru_v1.json on the persona
|
||||
// checks the nudges are already held to. These lines are heard out loud, and
|
||||
// they live in a JSON file now, so a reworded variant that says "рад" or "вы"
|
||||
// would otherwise reach him with nothing between it and the speaker.
|
||||
//
|
||||
// Only the persona checks run. Mood and topic belong to a nudge, and these are
|
||||
// not nudges: they are what she says when there is no answer.
|
||||
func TestFallbackPersona(t *testing.T) {
|
||||
fb, err := phraser.LoadFallbacks(rand.NewSource(20260804))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadFallbacks: %v", err)
|
||||
}
|
||||
persona := map[string]bool{
|
||||
CheckLang: true, CheckFeminine: true, CheckHisGender: true,
|
||||
CheckAddress: true, CheckCringe: true, CheckLength: true,
|
||||
}
|
||||
variants := fb.Variants()
|
||||
if len(variants) == 0 {
|
||||
t.Fatal("no variants — the file loaded empty")
|
||||
}
|
||||
for _, v := range variants {
|
||||
// {sources} stands for his own notes and never carries persona of its own.
|
||||
body := strings.ReplaceAll(v, "{sources}", "два литра")
|
||||
for _, r := range RunChecks(Case{}, body, "neutral") {
|
||||
if persona[r.Name] && !r.Pass {
|
||||
t.Errorf("%q fails %s: %s", v, r.Name, r.Detail)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -78,6 +78,12 @@ type TalkCase struct {
|
||||
Note string `json:"note,omitempty"`
|
||||
}
|
||||
|
||||
// TalkSchemaVersion — the version this loader understands. Separate from the
|
||||
// nudge fixture's SchemaVersion: the two fixtures have different shapes and
|
||||
// change on different days, and one shared constant would force a bump on the
|
||||
// fixture that did not move.
|
||||
const TalkSchemaVersion = 1
|
||||
|
||||
// TalkFixture — the versioned envelope, same gating as Fixture.
|
||||
type TalkFixture struct {
|
||||
SchemaVersion int `json:"schema_version"`
|
||||
@@ -92,8 +98,8 @@ func LoadTalk() (TalkFixture, error) {
|
||||
if err := json.Unmarshal(talkFixtureJSON, &f); err != nil {
|
||||
return TalkFixture{}, fmt.Errorf("parse talk fixture: %w", err)
|
||||
}
|
||||
if f.SchemaVersion != SchemaVersion {
|
||||
return TalkFixture{}, fmt.Errorf("talk fixture schema_version %d, want %d", f.SchemaVersion, SchemaVersion)
|
||||
if f.SchemaVersion != TalkSchemaVersion {
|
||||
return TalkFixture{}, fmt.Errorf("talk fixture schema_version %d, want %d", f.SchemaVersion, TalkSchemaVersion)
|
||||
}
|
||||
if len(f.Cases) == 0 {
|
||||
return TalkFixture{}, fmt.Errorf("talk fixture has no cases")
|
||||
|
||||
@@ -142,19 +142,13 @@ func TestLLMTalkBaseline(t *testing.T) {
|
||||
p := phraser.NewLLMPhraserAt(base, cfg)
|
||||
defer p.Close()
|
||||
|
||||
// Unreachable server is fatal here, not a logged warning, and that differs
|
||||
// from the nudge test on purpose. PhraseNudge returns its errors, so a dead
|
||||
// server there shows up honestly in the Errors column. PhraseChat and
|
||||
// PhraseQuery do NOT: they swallow every failure and return a canned string
|
||||
// ("поговорили.", "не знаю.", "вот что я нашла: …"). So on these three paths
|
||||
// a dead server produces a full report with 0 errors and a terrible score —
|
||||
// a number that looks like bad phrasing and is really no phrasing at all.
|
||||
// Refusing to score without a confirmed model is the only guard available
|
||||
// until the phraser reports its failures (Vikunja #397).
|
||||
// The model id names the run in the report. Since Vikunja #397 every path
|
||||
// returns its errors, so a server that dies mid-run shows up in the Errors
|
||||
// column instead of scoring as bad phrasing — the before-and-after probe that
|
||||
// used to stand in for that is gone.
|
||||
model, err := llm.ModelID(ctx, base)
|
||||
if err != nil {
|
||||
t.Fatalf("no model at %s: %v — refusing to score, these paths hide their errors "+
|
||||
"and would report a plausible-looking result off a dead server", base, err)
|
||||
t.Fatalf("no model at %s: %v", base, err)
|
||||
}
|
||||
t.Logf("scoring model %s at %s", model, base)
|
||||
|
||||
@@ -169,10 +163,11 @@ func TestLLMTalkBaseline(t *testing.T) {
|
||||
}
|
||||
t.Log("\n" + rep.String() + "\nreplies:\n" + rep.Replies() + "\nfailures:\n" + rep.Failures())
|
||||
|
||||
// And again afterwards: the run takes minutes, and a server that died or got
|
||||
// OOM-killed halfway through would leave the first cases scored and the rest
|
||||
// silently canned. Checking only at the start would not catch that.
|
||||
if _, err := llm.ModelID(ctx, base); err != nil {
|
||||
t.Fatalf("model at %s went away during the run: %v — the score above is not trustworthy", base, err)
|
||||
// A run where nothing was phrased is not a low score, it is no measurement.
|
||||
if rep.Errors == rep.Total {
|
||||
t.Fatalf("every case errored — nothing was measured, the score above is not a phrasing result")
|
||||
}
|
||||
if rep.Errors > 0 {
|
||||
t.Logf("%d/%d cases errored — those are model failures, not phrasing failures", rep.Errors, rep.Total)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,89 @@
|
||||
package phraser
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// isFallback — the text she says is picked from that entry's variants, so a test
|
||||
// pins the entry rather than the wording. Pinning one line would make editing
|
||||
// fallbacks_ru_v1.json break Go tests, which is the coupling this file removed.
|
||||
func isFallback(t *testing.T, key, sources, got string) bool {
|
||||
t.Helper()
|
||||
e, ok := DefaultFallbacks().file.Entries[key]
|
||||
if !ok {
|
||||
t.Fatalf("no fallback entry %q", key)
|
||||
}
|
||||
for _, v := range e.Variants {
|
||||
if strings.ReplaceAll(v, "{sources}", sources) == got {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// A dead server must be distinguishable from bad phrasing. Both PhraseChat and
|
||||
// PhraseQuery keep the turn alive with canned text — and every one of those
|
||||
// lines is also a legitimate reply, so the text alone cannot say which happened.
|
||||
// The error is the only signal, and before Vikunja #397 it was dropped: the talk
|
||||
// scorer reported a full run with zero errors off a server that answered nothing.
|
||||
func TestPhrasingReportsTheFailureWithTheFallback(t *testing.T) {
|
||||
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
http.Error(w, "model not loaded", http.StatusServiceUnavailable)
|
||||
}))
|
||||
t.Cleanup(srv.Close)
|
||||
p := NewLLMPhraserAt(srv.URL, Config{})
|
||||
|
||||
cases := []struct {
|
||||
name string
|
||||
call func() (string, error)
|
||||
key string
|
||||
sources string
|
||||
}{
|
||||
{"chat", func() (string, error) {
|
||||
return p.PhraseChat(context.Background(), "как дела", nil)
|
||||
}, fbChat, ""},
|
||||
{"knowledge", func() (string, error) {
|
||||
return p.PhraseQuery(context.Background(), "кто написал войну и мир", nil)
|
||||
}, fbQueryUnknown, ""},
|
||||
{"evidence", func() (string, error) {
|
||||
return p.PhraseQuery(context.Background(), "сколько воды я выпил", []string{"два литра"})
|
||||
}, fbQuerySources, "два литра"},
|
||||
}
|
||||
for _, c := range cases {
|
||||
t.Run(c.name, func(t *testing.T) {
|
||||
got, err := c.call()
|
||||
if err == nil {
|
||||
t.Fatalf("no error from a dead server; the scorer would count this as bad phrasing")
|
||||
}
|
||||
if !isFallback(t, c.key, c.sources, got) {
|
||||
t.Errorf("fallback text = %q, want a %q variant — the daemon still has to say something", got, c.key)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// An empty answer is a failure too: the server is up and produced no tokens,
|
||||
// which is not an answer and must not score as one.
|
||||
func TestEmptyKnowledgeAnswerIsAnError(t *testing.T) {
|
||||
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
w.Header().Set("Content-Type", "application/json")
|
||||
w.Write([]byte(`{"choices":[{"message":{"content":""}}]}`))
|
||||
}))
|
||||
t.Cleanup(srv.Close)
|
||||
p := NewLLMPhraserAt(srv.URL, Config{})
|
||||
|
||||
got, err := p.PhraseQuery(context.Background(), "кто написал войну и мир", nil)
|
||||
if err == nil {
|
||||
t.Fatal("an empty response scored as an answer")
|
||||
}
|
||||
if !isFallback(t, fbQueryUnknown, "", got) {
|
||||
t.Errorf("fallback text = %q, want a %q variant", got, fbQueryUnknown)
|
||||
}
|
||||
if !strings.Contains(err.Error(), "empty") {
|
||||
t.Errorf("error = %v; want it to name the empty response", err)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,238 @@
|
||||
package phraser
|
||||
|
||||
// The phrasing fallbacks — what she says when the model gave her nothing usable.
|
||||
//
|
||||
// They were four string literals spread across phraser.go, llmphraser.go and
|
||||
// cmd/mavend/worldmodel.go. Every one of them is a line he hears out loud, so
|
||||
// rewording one was a Go edit, a rebuild and a redeploy for what is product copy.
|
||||
// This is the same shape nudges_ru_v1.json already uses for nudges: embedded,
|
||||
// schema-versioned, several variants, and never the same variant twice running.
|
||||
//
|
||||
// The floor under the floor is deliberate. These strings exist because something
|
||||
// already failed, so a broken template file must not be able to take the last
|
||||
// words she has: every accessor falls back to the literal it replaced.
|
||||
|
||||
import (
|
||||
_ "embed"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"log"
|
||||
"math/rand"
|
||||
"strings"
|
||||
"sync"
|
||||
"time"
|
||||
)
|
||||
|
||||
//go:embed fallbacks_ru_v1.json
|
||||
var fallbackJSON []byte
|
||||
|
||||
// FallbackSchemaVersion — the version this code understands. Its own constant,
|
||||
// not shared with the nudge templates or the eval fixtures: two files that change
|
||||
// on different days cannot be versioned by one number (Vikunja #397).
|
||||
const FallbackSchemaVersion = 1
|
||||
|
||||
// The entry keys. Every one of them is read by a method below, so a typo in the
|
||||
// file is caught at load rather than at the moment she needs the words.
|
||||
const (
|
||||
fbChat = "chat"
|
||||
fbQueryUnknown = "query_unknown"
|
||||
fbQuerySources = "query_sources"
|
||||
fbWorldGap = "world_gap"
|
||||
)
|
||||
|
||||
// fbKeys — every key the code requires the file to define.
|
||||
var fbKeys = []string{fbChat, fbQueryUnknown, fbQuerySources, fbWorldGap}
|
||||
|
||||
// hardFloor — the literal each key falls back to when the file is unusable.
|
||||
// These are the exact strings that lived in Go before this file existed.
|
||||
var hardFloor = map[string]string{
|
||||
fbChat: "даже не знаю, что сказать.",
|
||||
fbQueryUnknown: "не знаю.",
|
||||
fbQuerySources: "вот что я нашла: {sources}",
|
||||
fbWorldGap: "сейчас не могу ответить — большая модель недоступна, а придумывать не хочу.",
|
||||
}
|
||||
|
||||
type fallbackEntry struct {
|
||||
// Fixed — one variant, never picked between. For wording that must not drift
|
||||
// from turn to turn, like the gap phrase that names an unavailable model.
|
||||
Fixed bool `json:"fixed"`
|
||||
Variants []string `json:"variants"`
|
||||
}
|
||||
|
||||
type fallbackFile struct {
|
||||
SchemaVersion int `json:"schema_version"`
|
||||
Name string `json:"name"`
|
||||
Notes []string `json:"notes"`
|
||||
Entries map[string]fallbackEntry `json:"entries"`
|
||||
}
|
||||
|
||||
// Fallbacks picks a hand-written Russian fallback line.
|
||||
//
|
||||
// Safe for concurrent use. Never the same variant twice in a row for the same
|
||||
// entry: hearing the identical words every time a request fails is how a failure
|
||||
// stops registering as one.
|
||||
type Fallbacks struct {
|
||||
mu sync.Mutex
|
||||
rnd *rand.Rand
|
||||
last map[string]string
|
||||
file fallbackFile
|
||||
}
|
||||
|
||||
// LoadFallbacks reads the embedded file. Pass a source to make the picking
|
||||
// reproducible in tests; nil seeds from the clock.
|
||||
func LoadFallbacks(src rand.Source) (*Fallbacks, error) {
|
||||
var f fallbackFile
|
||||
if err := json.Unmarshal(fallbackJSON, &f); err != nil {
|
||||
return nil, fmt.Errorf("fallbacks: parse: %w", err)
|
||||
}
|
||||
if f.SchemaVersion != FallbackSchemaVersion {
|
||||
return nil, fmt.Errorf("fallbacks: schema_version %d, want %d",
|
||||
f.SchemaVersion, FallbackSchemaVersion)
|
||||
}
|
||||
for _, k := range fbKeys {
|
||||
e, ok := f.Entries[k]
|
||||
if !ok || len(e.Variants) == 0 {
|
||||
return nil, fmt.Errorf("fallbacks: entry %q is missing or empty", k)
|
||||
}
|
||||
if e.Fixed && len(e.Variants) != 1 {
|
||||
return nil, fmt.Errorf("fallbacks: entry %q is fixed but has %d variants", k, len(e.Variants))
|
||||
}
|
||||
}
|
||||
// query_sources is the one entry whose whole job is to read something back,
|
||||
// so a variant without the placeholder would silently drop the sources.
|
||||
for _, v := range f.Entries[fbQuerySources].Variants {
|
||||
if !strings.Contains(v, "{sources}") {
|
||||
return nil, fmt.Errorf("fallbacks: %q variant %q does not use {sources}", fbQuerySources, v)
|
||||
}
|
||||
}
|
||||
if src == nil {
|
||||
src = rand.NewSource(time.Now().UnixNano())
|
||||
}
|
||||
return &Fallbacks{rnd: rand.New(src), last: map[string]string{}, file: f}, nil
|
||||
}
|
||||
|
||||
// text returns one variant for key, with {sources} filled in. A nil receiver is
|
||||
// the unloadable-file case and answers from hardFloor, so the caller never has
|
||||
// to check whether the templates loaded.
|
||||
func (f *Fallbacks) text(key, sources string) string {
|
||||
tmpl := hardFloor[key]
|
||||
if f != nil {
|
||||
if e, ok := f.file.Entries[key]; ok && len(e.Variants) > 0 {
|
||||
tmpl = f.pick(key, e)
|
||||
}
|
||||
}
|
||||
return strings.ReplaceAll(tmpl, "{sources}", sources)
|
||||
}
|
||||
|
||||
// pick chooses at random, skipping whatever this entry said last time.
|
||||
func (f *Fallbacks) pick(key string, e fallbackEntry) string {
|
||||
f.mu.Lock()
|
||||
defer f.mu.Unlock()
|
||||
|
||||
choices := e.Variants
|
||||
if len(choices) > 1 {
|
||||
fresh := make([]string, 0, len(choices))
|
||||
for _, v := range choices {
|
||||
if v != f.last[key] {
|
||||
fresh = append(fresh, v)
|
||||
}
|
||||
}
|
||||
if len(fresh) > 0 {
|
||||
choices = fresh
|
||||
}
|
||||
}
|
||||
got := choices[f.rnd.Intn(len(choices))]
|
||||
f.last[key] = got
|
||||
return got
|
||||
}
|
||||
|
||||
// Chat — nothing usable came back on the chat path.
|
||||
func (f *Fallbacks) Chat() string { return f.text(fbChat, "") }
|
||||
|
||||
// Unknown — a question she cannot answer and will not guess at.
|
||||
func (f *Fallbacks) Unknown() string { return f.text(fbQueryUnknown, "") }
|
||||
|
||||
// FromSources — read back what she was handed, because phrasing it failed.
|
||||
func (f *Fallbacks) FromSources(sources string) string {
|
||||
return f.text(fbQuerySources, sources)
|
||||
}
|
||||
|
||||
// WorldGap — the world model is the one configured to answer and it is not
|
||||
// answering. Fixed wording: it names a specific gap, and a variant set here
|
||||
// would let "the big model is asleep" drift into "I don't know".
|
||||
func (f *Fallbacks) WorldGap() string { return f.text(fbWorldGap, "") }
|
||||
|
||||
// Variants returns every line the file can produce, for the persona scorer.
|
||||
// Order is stable so a failure names the same variant twice running.
|
||||
func (f *Fallbacks) Variants() []string {
|
||||
var out []string
|
||||
for _, k := range fbKeys {
|
||||
out = append(out, f.file.Entries[k].Variants...)
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// The process-wide instance. Package-level because these lines are needed on
|
||||
// paths that have no phraser to hand — cmd/mavend names the world gap without
|
||||
// one — and because a template file that is embedded and validated at load has
|
||||
// nothing per-instance to configure.
|
||||
var (
|
||||
fallbackOnce sync.Once
|
||||
fallbacks *Fallbacks
|
||||
)
|
||||
|
||||
// DefaultFallbacks returns the shared instance, loading it on first use. A
|
||||
// broken file logs once and leaves a nil *Fallbacks, which still answers from
|
||||
// hardFloor — a daemon must not fail to boot over its own copy deck.
|
||||
func DefaultFallbacks() *Fallbacks {
|
||||
fallbackOnce.Do(func() {
|
||||
fb, err := LoadFallbacks(nil)
|
||||
if err != nil {
|
||||
log.Printf("phraser: fallbacks unavailable, using the built-in lines: %v", err)
|
||||
return
|
||||
}
|
||||
fallbacks = fb
|
||||
})
|
||||
return fallbacks
|
||||
}
|
||||
|
||||
// ChatFallback — what she says when the chat path produced nothing.
|
||||
func ChatFallback() string { return DefaultFallbacks().Chat() }
|
||||
|
||||
// UnknownFallback — what she says when she has no answer and will not invent one.
|
||||
func UnknownFallback() string { return DefaultFallbacks().Unknown() }
|
||||
|
||||
// SourcesFallback — read the sources back rather than ship a broken fragment.
|
||||
func SourcesFallback(sources string) string { return DefaultFallbacks().FromSources(sources) }
|
||||
|
||||
// WorldGap — what he hears when the world model is configured and unreachable.
|
||||
func WorldGap() string { return DefaultFallbacks().WorldGap() }
|
||||
|
||||
// matches reports whether text is a line the given entry could have produced.
|
||||
// A caller that has to recognise a fallback cannot compare against one literal
|
||||
// any more, because the entry picks between variants.
|
||||
func (f *Fallbacks) matches(key, sources, text string) bool {
|
||||
if strings.ReplaceAll(hardFloor[key], "{sources}", sources) == text {
|
||||
return true
|
||||
}
|
||||
if f == nil {
|
||||
return false
|
||||
}
|
||||
for _, v := range f.file.Entries[key].Variants {
|
||||
if strings.ReplaceAll(v, "{sources}", sources) == text {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// IsUnknownFallback reports whether text is one of her "I do not know" lines.
|
||||
// The daemon tests read it to tell an answer from a shrug.
|
||||
func IsUnknownFallback(text string) bool {
|
||||
return DefaultFallbacks().matches(fbQueryUnknown, "", text)
|
||||
}
|
||||
|
||||
// IsSourcesFallback reports whether text is sources read back verbatim.
|
||||
func IsSourcesFallback(text, sources string) bool {
|
||||
return DefaultFallbacks().matches(fbQuerySources, sources, text)
|
||||
}
|
||||
@@ -0,0 +1,42 @@
|
||||
{
|
||||
"schema_version": 1,
|
||||
"name": "russian phrasing fallbacks v1",
|
||||
"notes": [
|
||||
"What she says when the model gave her nothing usable. Edit the wording here, no Go changes needed.",
|
||||
"Rules: she is feminine about herself, he is a man addressed as ты. Never вы/вас/ваш, never plural imperatives, never он/его about him. No pet names.",
|
||||
"These are heard after a failure, so they stay short and admit the gap. None of them may claim knowledge she does not have.",
|
||||
"Placeholders: {sources} the notes or passages she was handed. A variant whose placeholder has no value is skipped, so every entry needs at least one variant with no placeholder — except query_sources, which exists only to read sources back.",
|
||||
"fixed: true means exactly one variant and no picking. Used where the wording is load-bearing and must not drift between turns."
|
||||
],
|
||||
"entries": {
|
||||
"chat": {
|
||||
"variants": [
|
||||
"даже не знаю, что сказать.",
|
||||
"не могу найти слов.",
|
||||
"мысль ускользнула, повтори?",
|
||||
"у меня сейчас пусто в голове."
|
||||
]
|
||||
},
|
||||
"query_unknown": {
|
||||
"variants": [
|
||||
"не знаю.",
|
||||
"не знаю, честно.",
|
||||
"тут я пас.",
|
||||
"не скажу, не знаю."
|
||||
]
|
||||
},
|
||||
"query_sources": {
|
||||
"variants": [
|
||||
"вот что я нашла: {sources}",
|
||||
"нашла вот это: {sources}",
|
||||
"есть только это: {sources}"
|
||||
]
|
||||
},
|
||||
"world_gap": {
|
||||
"fixed": true,
|
||||
"variants": [
|
||||
"сейчас не могу ответить — большая модель недоступна, а придумывать не хочу."
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,57 @@
|
||||
package phraser
|
||||
|
||||
import (
|
||||
"math/rand"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// The embedded file must load, or the daemon speaks from hardFloor and nobody
|
||||
// finds out until he hears the wrong words.
|
||||
func TestFallbacksLoad(t *testing.T) {
|
||||
fb, err := LoadFallbacks(rand.NewSource(1))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadFallbacks: %v", err)
|
||||
}
|
||||
if got := fb.FromSources("два литра"); !strings.Contains(got, "два литра") {
|
||||
t.Errorf("FromSources = %q, want the sources in it", got)
|
||||
}
|
||||
if fb.WorldGap() != hardFloor[fbWorldGap] {
|
||||
t.Errorf("WorldGap = %q, want the fixed wording %q", fb.WorldGap(), hardFloor[fbWorldGap])
|
||||
}
|
||||
}
|
||||
|
||||
// A broken or missing file must not take her last words away: every accessor
|
||||
// answers from the literal it replaced.
|
||||
func TestNilFallbacksAnswerFromTheHardFloor(t *testing.T) {
|
||||
var fb *Fallbacks
|
||||
if got := fb.Chat(); got != hardFloor[fbChat] {
|
||||
t.Errorf("Chat = %q, want %q", got, hardFloor[fbChat])
|
||||
}
|
||||
if got := fb.Unknown(); got != hardFloor[fbQueryUnknown] {
|
||||
t.Errorf("Unknown = %q, want %q", got, hardFloor[fbQueryUnknown])
|
||||
}
|
||||
if got := fb.FromSources("два литра"); got != "вот что я нашла: два литра" {
|
||||
t.Errorf("FromSources = %q", got)
|
||||
}
|
||||
if got := fb.WorldGap(); got != hardFloor[fbWorldGap] {
|
||||
t.Errorf("WorldGap = %q", got)
|
||||
}
|
||||
}
|
||||
|
||||
// Hearing the identical words every time a request fails is how a failure stops
|
||||
// registering as one.
|
||||
func TestFallbacksDoNotRepeat(t *testing.T) {
|
||||
fb, err := LoadFallbacks(rand.NewSource(7))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadFallbacks: %v", err)
|
||||
}
|
||||
prev := fb.Chat()
|
||||
for i := 0; i < 20; i++ {
|
||||
got := fb.Chat()
|
||||
if got == prev {
|
||||
t.Fatalf("chat repeated %q on turn %d", got, i)
|
||||
}
|
||||
prev = got
|
||||
}
|
||||
}
|
||||
@@ -5,6 +5,7 @@ import (
|
||||
"bytes"
|
||||
"context"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
"io"
|
||||
"log"
|
||||
@@ -26,6 +27,11 @@ import (
|
||||
|
||||
var listenRE = regexp.MustCompile(`listening on (https?://\S+)`)
|
||||
|
||||
// errEmptyResponse — the server answered and said nothing. Separate from a
|
||||
// transport failure: the model is up and produced no tokens, which is still not
|
||||
// an answer and must not score as one.
|
||||
var errEmptyResponse = errors.New("phraser: empty response from the model")
|
||||
|
||||
type LLMPhraser struct {
|
||||
cfg Config
|
||||
client *http.Client
|
||||
@@ -428,8 +434,11 @@ func (p *LLMPhraser) PhraseNudge(ctx context.Context, c loop.Candidate) (deliver
|
||||
}
|
||||
|
||||
// PhraseQuery prompts the LLM with the user's utterance and matching notes to
|
||||
// compose a natural answer. Falls back to "вот что я нашла: <notes>" on any
|
||||
// LLM error — better to give the raw data than silence.
|
||||
// compose a natural answer. On any LLM error it returns the fallback text —
|
||||
// "вот что я нашла: <notes>", or "не знаю." with no notes — and the error
|
||||
// together. The daemon uses the text and keeps the turn alive; a caller that is
|
||||
// measuring counts the failure. Until Vikunja #397 the error was dropped, so a
|
||||
// dead server scored as bad phrasing.
|
||||
func (p *LLMPhraser) PhraseQuery(ctx context.Context, utterance string, notes []string) (string, error) {
|
||||
// Blank sources are no sources. A caller that hands over one empty string —
|
||||
// a page that fetched to nothing, a snippet trimmed away — used to take the
|
||||
@@ -439,13 +448,15 @@ func (p *LLMPhraser) PhraseQuery(ctx context.Context, utterance string, notes []
|
||||
if len(notes) == 0 {
|
||||
sys, prompt := p.knowledgePrompt(utterance)
|
||||
resp, err := p.chatWithSystem(ctx, sys, prompt, 768)
|
||||
if err != nil || resp == "" {
|
||||
return "не знаю.", nil
|
||||
if err != nil {
|
||||
return UnknownFallback(), fmt.Errorf("phrase query (knowledge): %w", err)
|
||||
}
|
||||
if resp == "" {
|
||||
return UnknownFallback(), errEmptyResponse
|
||||
}
|
||||
text, _, perr := parseResponseMood(resp)
|
||||
if perr != nil {
|
||||
log.Printf("phraser: PhraseQuery: %v", perr)
|
||||
return "не знаю.", nil
|
||||
return UnknownFallback(), fmt.Errorf("phrase query (knowledge): %w", perr)
|
||||
}
|
||||
if text != "" {
|
||||
return text, nil
|
||||
@@ -457,13 +468,12 @@ func (p *LLMPhraser) PhraseQuery(ctx context.Context, utterance string, notes []
|
||||
text, _, perr := parseResponseMood(resp)
|
||||
if err != nil || perr != nil {
|
||||
// Read the notes out rather than ship a broken fragment.
|
||||
if perr != nil {
|
||||
log.Printf("phraser: PhraseQuery: %v", perr)
|
||||
cause := err
|
||||
if cause == nil {
|
||||
cause = perr
|
||||
}
|
||||
if len(notes) == 1 {
|
||||
return "вот что я нашла: " + notes[0], nil
|
||||
}
|
||||
return "вот что я нашла: " + strings.Join(notes, "; "), nil
|
||||
return SourcesFallback(strings.Join(notes, "; ")),
|
||||
fmt.Errorf("phrase query (evidence): %w", cause)
|
||||
}
|
||||
if text != "" {
|
||||
return text, nil
|
||||
@@ -472,8 +482,9 @@ func (p *LLMPhraser) PhraseQuery(ctx context.Context, utterance string, notes []
|
||||
}
|
||||
|
||||
// PhraseChat uses the LLM to respond conversationally, building a multi-turn
|
||||
// message array from dialogue history + the current user utterance. Falls back
|
||||
// to a simple greeting on any LLM error — better to say something than nothing.
|
||||
// message array from dialogue history + the current user utterance. On any LLM
|
||||
// error it returns both ChatFallback and the error, on the same rule as
|
||||
// PhraseQuery: the fallback keeps the turn alive, the error stays visible.
|
||||
func (p *LLMPhraser) PhraseChat(ctx context.Context, utterance string, history []dialogue.Turn) (string, error) {
|
||||
sys := chatSystemPrompt(p.cfg.ContextBlock)
|
||||
msgs := []chatMsg{
|
||||
@@ -490,13 +501,11 @@ func (p *LLMPhraser) PhraseChat(ctx context.Context, utterance string, history [
|
||||
|
||||
resp, err := p.chatWithMessages(ctx, msgs, 768)
|
||||
if err != nil {
|
||||
log.Printf("phraser: PhraseChat: %v", err)
|
||||
return "поговорили.", nil
|
||||
return ChatFallback(), fmt.Errorf("phrase chat: %w", err)
|
||||
}
|
||||
text, _, perr := parseResponseMood(resp)
|
||||
if perr != nil {
|
||||
log.Printf("phraser: PhraseChat: %v", perr)
|
||||
return "поговорили.", nil
|
||||
return ChatFallback(), fmt.Errorf("phrase chat: %w", perr)
|
||||
}
|
||||
if text != "" {
|
||||
return text, nil
|
||||
|
||||
@@ -70,18 +70,15 @@ func NewStub() *Stub { return &Stub{} }
|
||||
// prompted response from the model. The history parameter is accepted but
|
||||
// ignored at the stub level (the production impl uses it for multi-turn).
|
||||
func (s *Stub) PhraseChat(_ context.Context, _ string, _ []dialogue.Turn) (string, error) {
|
||||
return "поговорили.", nil
|
||||
return ChatFallback(), nil
|
||||
}
|
||||
|
||||
// PhraseQuery returns a deterministic summary of the best matching notes.
|
||||
func (s *Stub) PhraseQuery(_ context.Context, _ string, notes []string) (string, error) {
|
||||
if len(notes) == 0 {
|
||||
return "не знаю.", nil
|
||||
return UnknownFallback(), nil
|
||||
}
|
||||
if len(notes) == 1 {
|
||||
return "вот что я нашла: " + notes[0], nil
|
||||
}
|
||||
return "вот что я нашла: " + strings.Join(notes, "; "), nil
|
||||
return SourcesFallback(strings.Join(notes, "; ")), nil
|
||||
}
|
||||
|
||||
// Close implements Phraser.Close (no-op for the stub).
|
||||
|
||||
@@ -215,10 +215,12 @@ func TestSwap_RollbackFailureLeavesNoBackendAndDegrades(t *testing.T) {
|
||||
if _, _, aerr := p.acquire(); !errors.Is(aerr, ErrNoBackend) {
|
||||
t.Errorf("acquire error = %v; want ErrNoBackend", aerr)
|
||||
}
|
||||
// Phrasing degrades to its fallback instead of failing the turn.
|
||||
// Phrasing degrades to its fallback instead of failing the turn, and since
|
||||
// Vikunja #397 it reports the error next to that fallback so a measuring
|
||||
// caller can tell "no model" from "bad phrasing".
|
||||
got, err := p.PhraseChat(context.Background(), "привет", nil)
|
||||
if err != nil {
|
||||
t.Fatalf("PhraseChat after a total failure returned an error: %v", err)
|
||||
if !errors.Is(err, ErrNoBackend) {
|
||||
t.Errorf("PhraseChat error = %v; want ErrNoBackend alongside the fallback", err)
|
||||
}
|
||||
if got == "" {
|
||||
t.Error("PhraseChat returned empty; the fallback must still say something")
|
||||
|
||||
@@ -75,47 +75,3 @@ func TestAgendaGrammarSparesStatements(t *testing.T) {
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// The tomorrow form and the bare event noun. Both were measured answering
|
||||
// "пока не умею" on the deployed daemon, 02-08-2026, while the same question
|
||||
// about today worked — the first rule set needed "у меня" or a calendar noun
|
||||
// and these phrasings carry neither (Vikunja #471).
|
||||
func TestAgendaCoversOtherDaysAndNamedEvents(t *testing.T) {
|
||||
r := agendaRouter(t)
|
||||
for _, u := range []string{
|
||||
"какие планы на завтра?",
|
||||
"какие планы на послезавтра",
|
||||
"что по делам в среду",
|
||||
"какие планы на выходные",
|
||||
"когда планёрка?",
|
||||
"во сколько созвон",
|
||||
"когда будет совещание",
|
||||
} {
|
||||
d, err := r.Route(context.Background(), u, refNow())
|
||||
if err != nil {
|
||||
t.Fatalf("route(%q): %v", u, err)
|
||||
}
|
||||
if d.Intent != IntentQuery {
|
||||
t.Errorf("route(%q) = %s, want query", u, d.Intent)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// The two new rules are narrow on purpose. A world question that opens with
|
||||
// "когда" is not an agenda question, and telling her about a plan is not
|
||||
// asking about one.
|
||||
func TestAgendaGrammarsLeaveTheWorldAlone(t *testing.T) {
|
||||
r := agendaRouter(t)
|
||||
for _, u := range []string{
|
||||
"когда была битва при ватерлоо",
|
||||
"когда изобрели телефон",
|
||||
} {
|
||||
d, err := r.Route(context.Background(), u, refNow())
|
||||
if err != nil {
|
||||
t.Fatalf("route(%q): %v", u, err)
|
||||
}
|
||||
if d.Stage == 0 {
|
||||
t.Errorf("route(%q) was claimed at stage 0 as %s", u, d.Intent)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -23,8 +23,6 @@
|
||||
{ "id": "ru-query-012", "utterance": "какие заметки я оставил про полив", "lang": "ru", "intent": "query", "tags": ["recall"] },
|
||||
{ "id": "ru-query-013", "utterance": "во сколько у меня встреча", "lang": "ru", "intent": "query", "tags": ["calendar"] },
|
||||
{ "id": "ru-query-019", "utterance": "что у меня стоит в календаре на послезавтра", "lang": "ru", "intent": "query", "tags": ["calendar", "hard"], "note": "agenda, not the clock: the daemon answers this from CalendarEvents inside the query branch, so the clock/date system rule must not swallow it" },
|
||||
{ "id": "ru-query-022", "utterance": "какие планы на завтра?", "lang": "ru", "intent": "query", "tags": ["calendar"], "note": "the same agenda question as ru-query-019 aimed at another day; it answered \u043f\u043e\u043a\u0430 \u043d\u0435 \u0443\u043c\u0435\u044e on the deployed daemon while the today form worked (Vikunja #471)" },
|
||||
{ "id": "ru-query-023", "utterance": "\u043a\u043e\u0433\u0434\u0430 \u043f\u043b\u0430\u043d\u0451\u0440\u043a\u0430?", "lang": "ru", "intent": "query", "tags": ["calendar", "hard"], "note": "a named event with no calendar word — the noun is the only signal that this is a question about his day" },
|
||||
{ "id": "ru-query-014", "utterance": "я успеваю до дедлайна", "lang": "ru", "intent": "query", "tags": ["hard", "no-question-word"] },
|
||||
{ "id": "ru-query-015", "utterance": "сколько я прошёл шагов", "lang": "ru", "intent": "query", "tags": ["aggregate"] },
|
||||
{ "id": "ru-query-016", "utterance": "покажи давление за неделю", "lang": "ru", "intent": "query", "tags": ["hard", "imperative"], "note": "imperative form but a read — must not route to act" },
|
||||
@@ -71,7 +69,6 @@
|
||||
{ "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"] },
|
||||
|
||||
@@ -210,11 +210,7 @@ func (lr *LLMRouter) Route(ctx context.Context, utterance string, now time.Time)
|
||||
d.Slots.HasKey = a.Key != ""
|
||||
case IntentReminder:
|
||||
d.Intent = IntentReminder
|
||||
// No utterance fallback here, unlike every other intent below. The
|
||||
// model returning no text for a reminder means it found no subject,
|
||||
// and "напомни в 11" is not a subject. Leaving Text empty is what
|
||||
// lets the gate turn that into a question (Vikunja #383).
|
||||
d.Slots.Text = a.Text
|
||||
d.Slots.Text = firstNonEmpty(a.Text, utterance)
|
||||
case IntentNote:
|
||||
d.Intent = IntentNote
|
||||
d.Slots.Text = firstNonEmpty(a.Text, utterance)
|
||||
|
||||
@@ -356,35 +356,3 @@ func TestRouterLLMFactWithResolvedKeyStaysConfident(t *testing.T) {
|
||||
t.Fatalf("a fact the parser could key must not clarify: %+v", d)
|
||||
}
|
||||
}
|
||||
|
||||
// A reminder with a time and no subject must come back empty and gated, not
|
||||
// backfilled with the raw words. "напомни в 11" carries an hour and nothing to
|
||||
// say at that hour; parking the utterance in Text made the request look
|
||||
// complete, so the daemon set a reminder that fires saying "напомни в 11"
|
||||
// (Vikunja #383).
|
||||
func TestLLMReminderWithoutSubjectAsksInsteadOfGuessing(t *testing.T) {
|
||||
r := newLLMTestRouter(t, `{"intent":"reminder"}`)
|
||||
d, err := r.Route(context.Background(), "напомни в 11", refNow())
|
||||
if err != nil {
|
||||
t.Fatalf("route: %v", err)
|
||||
}
|
||||
if d.Slots.Text != "" {
|
||||
t.Fatalf("subject backfilled from the utterance: %q", d.Slots.Text)
|
||||
}
|
||||
if !d.Clarify {
|
||||
t.Fatalf("a subjectless reminder was accepted, confidence %v", d.Confidence)
|
||||
}
|
||||
}
|
||||
|
||||
// The gate is about the subject, not about reminders in general: one that has
|
||||
// both halves still runs without a question.
|
||||
func TestLLMReminderWithSubjectIsNotGated(t *testing.T) {
|
||||
r := newLLMTestRouter(t, `{"intent":"reminder","text":"позвонить маме"}`)
|
||||
d, err := r.Route(context.Background(), "напомни в 11 позвонить маме", refNow())
|
||||
if err != nil {
|
||||
t.Fatalf("route: %v", err)
|
||||
}
|
||||
if d.Clarify {
|
||||
t.Fatalf("a complete reminder was sent back as a question: %+v", d.Slots)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -147,15 +147,7 @@ func (r *Router) fillSlots(ctx context.Context, d *Decision, now time.Time) {
|
||||
d.Slots.Fn, d.Slots.Args, d.Slots.HasFn = fn, args, true
|
||||
}
|
||||
}
|
||||
// The extractor's Text is the raw utterance, which is the payload for a
|
||||
// note, a query or a chat turn but not for a reminder — there Text is the
|
||||
// subject, what she says at the hour. Backfilling it made Text impossible
|
||||
// to be empty, so StillMissing never reported SlotText and "О чём
|
||||
// напомнить?" was unaskable; the answer to a question she did manage to
|
||||
// ask then overwrote the whole request instead of filling one gap
|
||||
// (Vikunja #383). A reminder with no subject stays empty and is gated
|
||||
// below into a question.
|
||||
if d.Slots.Text == "" && d.Intent != IntentReminder {
|
||||
if d.Slots.Text == "" {
|
||||
d.Slots.Text = ex.Text
|
||||
}
|
||||
// Stage stays 1: it says who decided the route, and that was the LLM.
|
||||
@@ -185,12 +177,6 @@ func (r *Router) gateLLMDecision(d *Decision) {
|
||||
if d.Intent == IntentAct && !d.Slots.HasFn && d.Confidence > llmThinConfidence {
|
||||
d.Confidence = llmThinConfidence
|
||||
}
|
||||
// A reminder with no subject: she knows when but not what to say then.
|
||||
// Setting it anyway fires an empty reminder at the hour, which reads as a
|
||||
// bug to him and cannot be repaired after the fact. Ask (Vikunja #383).
|
||||
if d.Intent == IntentReminder && d.Slots.Text == "" && d.Confidence > llmThinConfidence {
|
||||
d.Confidence = llmThinConfidence
|
||||
}
|
||||
if d.Confidence < r.threshold {
|
||||
d.Clarify = true
|
||||
}
|
||||
|
||||
@@ -182,38 +182,9 @@ func AgendaQueryGrammars() []Grammar {
|
||||
Pattern: regexp.MustCompile(`(?i)^\s*(что|чего|какие|сколько|во\s+сколько|когда)\s+у\s+меня(\s|[?!.]|$)`),
|
||||
Build: agendaQueryBuild,
|
||||
},
|
||||
{
|
||||
// A plan noun aimed at a named day, with no possessive to anchor
|
||||
// on: "какие планы на завтра", "что по делам в среду". The rule
|
||||
// above wants "у меня" and this phrasing never has it, so
|
||||
// "какие планы на завтра" answered "пока не умею" while "какие
|
||||
// планы на сегодня" worked (Vikunja #471). The day word is what
|
||||
// makes it an agenda question rather than a topic.
|
||||
Name: "plan-day-query",
|
||||
// Only "план" and "дел". A verb stem like "встреч" would take
|
||||
// "встречаемся в среду", which is him telling her something, not
|
||||
// asking.
|
||||
Pattern: regexp.MustCompile(`(?i)(^|\s)(план|дел)[а-я]*\s+(на|в|во|по)\s+` + dayWordPattern + `(\s|[?!.]|$)`),
|
||||
Build: agendaQueryBuild,
|
||||
},
|
||||
{
|
||||
// A named event with no calendar word at all: "когда планёрка?",
|
||||
// "во сколько созвон". He is asking when something on his calendar
|
||||
// happens, and the noun is the only signal. Closed list, so "когда
|
||||
// битва при Ватерлоо" is still a world question.
|
||||
Name: "event-time-query",
|
||||
Pattern: regexp.MustCompile(`(?i)^\s*(когда|во\s+сколько|в\s+котором\s+часу)\s+(будет\s+|у\s+нас\s+)?(планёрк|планерк|встреч|созвон|митинг|совещани|звонок|созвон|приём|прием|интервью|собеседовани|тренировк|урок|занятие|пара)[а-я]*(\s|[?!.]|$)`),
|
||||
Build: agendaQueryBuild,
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
// dayWordPattern — the day words an agenda question can name. Weekdays appear
|
||||
// in the accusative and prepositional forms the questions actually use ("в
|
||||
// среду", "на среде"), which is why the stems carry an inflection tail rather
|
||||
// than a fixed ending.
|
||||
const dayWordPattern = `(сегодня|завтра|послезавтра|выходн[а-я]+|недел[а-я]+|понедельник[а-я]*|вторник[а-я]*|сред[ауые][а-я]*|четверг[а-я]*|пятниц[ауые][а-я]*|суббот[ауые][а-я]*|воскресень[ея][а-я]*)`
|
||||
|
||||
// agendaQueryBuild — shared Build for the agenda grammars. Confidence 1.0 on
|
||||
// the intent only: the utterance travels intact and the query chain's own
|
||||
// matchers decide the rest.
|
||||
|
||||
+1
-48
@@ -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
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
@@ -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",
|
||||
|
||||
@@ -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)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -208,17 +208,6 @@ ALTER TABLE reminders ADD COLUMN next_fire_ts INTEGER;`, // #2
|
||||
// list_tasks into something that writes without the row changing by one
|
||||
// byte. The fingerprint is the declared shape at approval time, so a
|
||||
// redefinition is a re-approval instead of a silent upgrade.
|
||||
`DELETE FROM facts
|
||||
WHERE key LIKE 'calendar_event_%'
|
||||
AND replace(substr(key, 25), '-', '') = '';`,
|
||||
// #18 — drop the calendar keys written while safeKey dropped Cyrillic
|
||||
// (Vikunja #443). Everything after the date prefix was punctuation, so
|
||||
// every Russian event on one day shared one key and only the last one
|
||||
// survived. Deleting rather than rewriting: a calendar fact is derived
|
||||
// data, the next poll writes the day again under keys that identify the
|
||||
// event, and the old rows would otherwise be recited as extra meetings.
|
||||
// The filter is exact — it keeps any key whose summary part still has a
|
||||
// letter or a digit in it.
|
||||
}
|
||||
|
||||
// migrate applies every migration with a number greater than the DB's current
|
||||
|
||||
@@ -47,36 +47,3 @@ func TestMigrateAppliesOnceAndIsIdempotent(t *testing.T) {
|
||||
t.Fatalf("after re-migrate user_version = %d, want %d", v, want)
|
||||
}
|
||||
}
|
||||
|
||||
// Migration #18 clears the calendar keys written while safeKey dropped
|
||||
// Cyrillic. Those rows are indistinguishable from real events on read, so
|
||||
// leaving them would recite one meeting as several (Vikunja #443).
|
||||
func TestCollapsedCalendarKeysAreDropped(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
s := newTestStore(t)
|
||||
|
||||
rows := []string{
|
||||
"calendar_event_20260804_--", // "Встреча с Аней" under the old rule
|
||||
"calendar_event_20260804_", // a one-word Russian summary
|
||||
"calendar_event_20260804_Встреча-с-Аней", // the new format
|
||||
"calendar_event_20260804_Standup", // an ASCII summary, always fine
|
||||
}
|
||||
for _, key := range rows {
|
||||
if _, err := s.db.ExecContext(ctx,
|
||||
`INSERT INTO facts (ts, kind, key, value, source, confidence) VALUES (0, 'env', ?, 'x', 'poll:caldav', 1.0)`,
|
||||
key); err != nil {
|
||||
t.Fatalf("seed %q: %v", key, err)
|
||||
}
|
||||
}
|
||||
if _, err := s.db.ExecContext(ctx, migrations[17]); err != nil {
|
||||
t.Fatalf("migration 18: %v", err)
|
||||
}
|
||||
|
||||
var got int
|
||||
if err := s.db.QueryRowContext(ctx, `SELECT count(*) FROM facts WHERE key LIKE 'calendar_event_%'`).Scan(&got); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if got != 2 {
|
||||
t.Fatalf("%d calendar rows left, want the 2 that identify their event", got)
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user