Compare commits

..

2 Commits

Author SHA1 Message Date
kami dfb8d26b62 Fix kill-maven.sh so it actually kills llama-server
The MODEL default was LFM2, but the deploy runs Qwen3.5-0.8B, so the
pkill pattern matched nothing and the server survived every kill.
Now matches any llama-server serving a .gguf, so changing the model in
deploy/mavend.json cannot break the script again. MODEL still narrows it.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
2026-07-31 02:15:30 +04:00
kami bf99fd4192 Add a voice.llm_router flag, default off
Wires cmd/mavend/voice.go to build the LLM router when the operator asks
for it. Default false, so nothing changes on the deploy box.
Look at pickLLMRouter: the flag on with no llama-server logs one line and
keeps the classifier, it never fails a turn.
The default stays off until the router can refuse (#359) and the extractor
runs on LLM decisions — both noted as TODOs in config.go.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
2026-07-31 02:15:30 +04:00
12 changed files with 152 additions and 878 deletions
-180
View File
@@ -1,180 +0,0 @@
package main
import (
"context"
"log"
"time"
"github.com/kami/maven/internal/dialogue"
"github.com/kami/maven/internal/router"
)
// clarifyTTL — how long a parked question stays answerable. Same 90s as the
// confirm gate, for the same reason: an answer is a same-breath gesture, and a
// stale question must not eat an unrelated later utterance.
const clarifyTTL = 90 * time.Second
// wantedSlots — what each intent needs before she can act on it. First entry is
// the one she asks about; the rest are only used to decide act-vs-drop.
//
// Intents not listed here are never worth a question: note and query act on the
// raw utterance, chat and system have nothing to fill in. For those a clarify
// decision keeps the canned "не поняла" reply — inventing a question for noise
// is worse than admitting she missed it.
var wantedSlots = map[router.Intent][]dialogue.Slot{
router.IntentReminder: {dialogue.SlotTime},
router.IntentFact: {dialogue.SlotKey},
router.IntentAct: {dialogue.SlotFn},
}
// clarifyQuestions — one short question per missing slot.
//
// These are fixed templates, not model output. The resident model is a 0.8B; it
// would wander, and a question whose wording changes every time is harder to
// answer than a blunt one that always reads the same. They are infinitive
// questions, so there is no gender agreement to get wrong; the feminine
// self-reference lives in the reply she gives when she drops the request.
var clarifyQuestions = map[dialogue.Slot]string{
dialogue.SlotTime: "На когда напомнить?",
dialogue.SlotKey: "Что записать?",
dialogue.SlotFn: "Что сделать?",
}
// clarifyDropped — she asked once, the answer still did not fill the gap, so
// the request is gone. Said plainly, once, with no second question.
const clarifyDropped = "Не разобрала — скажи целиком, пожалуйста."
// missingFor returns the slots a decision still needs, most important first.
// Empty ⇒ there is nothing identifiable to ask about.
func missingFor(dec router.Decision) []dialogue.Slot {
return dialogue.StillMissing(wantedSlots[dec.Intent], toDialogueSlots(dec.Slots))
}
// clarifyQuestion picks the one question to ask for a clarify decision. Returns
// ("", false) when she has no idea what is missing.
//
// One question about one thing: if two slots are missing she asks about the
// first and lets the rest go. Two questions in a row is an interrogation.
func clarifyQuestion(dec router.Decision) (dialogue.Slot, string, bool) {
missing := missingFor(dec)
if len(missing) == 0 {
return "", "", false
}
q, ok := clarifyQuestions[missing[0]]
if !ok {
return "", "", false
}
return missing[0], q, true
}
// 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(dec router.Decision) (string, bool) {
if h.clarifyStore == nil {
return "", false
}
slot, question, ok := clarifyQuestion(dec)
if !ok {
return "", false
}
h.clarifyStore.Put(voiceDialogueID, &dialogue.PendingQuestion{
Intent: dialogue.Intent(dec.Intent),
Slots: toDialogueSlots(dec.Slots),
Missing: []dialogue.Slot{slot},
Utterance: dec.Utterance,
Asked: h.now(),
TTL: clarifyTTL,
Attempts: 1, // asked once; MaxAttempts is 1, so there is no second ask
})
log.Printf("voice: clarify — asked about %s for intent=%s", slot, dec.Intent)
return question, true
}
// resolveClarifyAnswer reads an utterance as the answer to a parked question.
// Returns ("", false) when no live question is parked (or it expired), so the
// caller routes the utterance normally as a fresh request. Sibling of
// resolveConfirm and checked in the same place.
//
// The answer is parsed with the same extractor the router uses, for the intent
// she parked — no second parser. If it still does not fill the gap the request
// is dropped: she does not ask again.
func (h *reactiveHandler) resolveClarifyAnswer(ctx context.Context, text string) (string, bool) {
if h.clarifyStore == nil {
return "", false
}
q := h.clarifyStore.Get(voiceDialogueID, h.now())
if q == nil {
return "", false
}
// One shot either way: the question is consumed whether or not the answer
// works, so a failed answer can't leave the question armed.
h.clarifyStore.Delete(voiceDialogueID)
intent := router.Intent(q.Intent)
answer := h.extractor.Extract(ctx, intent, text, h.now())
merged := q.Answer(text, toDialogueSlots(answer))
if len(dialogue.StillMissing(q.Missing, merged)) > 0 {
log.Printf("voice: clarify — answer %q did not fill %v, dropping", text, q.Missing)
return clarifyDropped, true
}
// Rebuild the decision as if it had routed cleanly, then run it down the
// normal path. Clarify is deliberately false and the intent is unchanged:
// filling in an argument never grants authority, so the completed decision
// still meets the allowlist and the destructive-act confirm gate in
// applyAction exactly like any other decision.
dec := router.Decision{
Utterance: q.Utterance,
Stage: 2,
Intent: intent,
Slots: applyDialogueSlots(answer, merged),
}
return h.finishClarified(ctx, dec), true
}
// finishClarified runs a completed decision through the same steps a freshly
// routed one takes: remember the turn, act, then phrase.
func (h *reactiveHandler) finishClarified(ctx context.Context, dec router.Decision) string {
if h.dialogueSessions != nil {
now := h.now()
prev := h.dialogueSessions.Get(voiceDialogueID, now)
dec = followUpMerge(prev, dec, now)
h.rememberTurn(prev, dec, now)
}
reply := h.applyAction(ctx, dec)
if reply == "" {
reply = h.replier.Reply(dec)
}
return reply
}
// rememberTurn stores this turn as the dialogue session the next follow-up
// inherits from, carrying up to 4 prior turns of history for anaphora. Capped so
// one long conversation can't grow the session unboundedly.
func (h *reactiveHandler) rememberTurn(prev *dialogue.Session, dec router.Decision, now time.Time) {
var history []dialogue.Turn
if prev != nil {
history = append(history, dialogue.Turn{
Intent: prev.Intent,
Slots: prev.Slots,
Text: prev.Slots.Text,
})
maxHist := len(prev.History)
if maxHist > 3 {
maxHist = 3
}
history = append(history, prev.History[:maxHist]...)
}
ttl := time.Duration(0) // use the store default (2 min)
if dec.Intent == router.IntentChat {
ttl = 15 * time.Minute // conversational turns should last longer
}
h.dialogueSessions.Put(voiceDialogueID, &dialogue.Session{
Intent: dialogue.Intent(dec.Intent),
Slots: toDialogueSlots(dec.Slots),
Timestamp: now,
TTL: ttl,
History: history,
})
}
-238
View File
@@ -1,238 +0,0 @@
package main
import (
"context"
"os"
"path/filepath"
"strings"
"testing"
"time"
"github.com/kami/maven/internal/dialogue"
"github.com/kami/maven/internal/ipc"
"github.com/kami/maven/internal/router"
"github.com/kami/maven/internal/store"
"github.com/kami/maven/internal/tool"
"github.com/kami/maven/internal/voice"
)
// newClarifyHandler builds a handler with the clarify path wired and no model:
// stub date parser, the real fact parser, and a matcher over whatever tools the
// test enabled. `now` is fixed so TTL behaviour is testable.
func newClarifyHandler(t *testing.T) (*reactiveHandler, *store.Store, *time.Time) {
t.Helper()
st := newTestStore(t)
api := ipc.NewStoreAPI(st)
now := time.Date(2026, 7, 31, 9, 0, 0, 0, time.UTC)
matcher := tool.NewMatcher(api)
h := &reactiveHandler{
api: api,
dataStore: st,
tools: tool.NewExecutor(api, 2*time.Second),
matcher: matcher,
replier: voice.NewStubReplier(),
now: func() time.Time { return now },
dialogueSessions: dialogue.NewSessionStore(2 * time.Minute),
clarifyStore: dialogue.NewClarifyStore(clarifyTTL),
extractor: router.Extractor{
Time: router.StubDateTimeParser{},
Acts: matcher,
Facts: router.DefaultFactParser{},
},
}
return h, st, &now
}
func clarifyDec(intent router.Intent, slots router.Slots, utterance string) router.Decision {
return router.Decision{Utterance: utterance, Stage: 3, Intent: intent, Slots: slots, Clarify: true}
}
// TestClarifyQuestionForMissingSlot pins which question goes with which gap, and
// which intents get no question at all.
func TestClarifyQuestionForMissingSlot(t *testing.T) {
cases := []struct {
name string
dec router.Decision
want string
asked bool
}{
{"reminder without a time", clarifyDec(router.IntentReminder, router.Slots{Text: "напомни позвонить маме"}, "напомни позвонить маме"), "На когда напомнить?", true},
{"fact without a key", clarifyDec(router.IntentFact, router.Slots{Text: "запиши"}, "запиши"), "Что записать?", true},
{"act without a fn", clarifyDec(router.IntentAct, router.Slots{Text: "сделай это"}, "сделай это"), "Что сделать?", true},
{"reminder that already has a time", clarifyDec(router.IntentReminder, router.Slots{HasTime: true}, "напомни в 11"), "", false},
{"chat is never worth a question", clarifyDec(router.IntentChat, router.Slots{Text: "мгм"}, "мгм"), "", false},
{"query is never worth a question", clarifyDec(router.IntentQuery, router.Slots{Text: "а"}, "а"), "", false},
}
for _, tc := range cases {
_, got, asked := clarifyQuestion(tc.dec)
if asked != tc.asked || got != tc.want {
t.Errorf("%s: got (%q, %v), want (%q, %v)", tc.name, got, asked, tc.want, tc.asked)
}
}
}
// TestClarifyReminderCompletesOnAnswer is the whole point of the feature: she
// asks for the missing time and the answer creates the reminder.
func TestClarifyReminderCompletesOnAnswer(t *testing.T) {
ctx := context.Background()
h, st, _ := newClarifyHandler(t)
question, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{Text: "напомни позвонить маме"}, "напомни позвонить маме"))
if !asked || question != "На когда напомнить?" {
t.Fatalf("expected the time question, got %q asked=%v", question, asked)
}
reply, handled := h.resolveClarifyAnswer(ctx, "в 11:00")
if !handled {
t.Fatal("the answer to an open question must be consumed as an answer")
}
if reply == clarifyDropped {
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 reminder lost the original request: %q", reminders[0].Payload)
}
if h.clarifyStore.Get(voiceDialogueID, h.now()) != nil {
t.Fatal("the question must be cleared once answered")
}
}
// TestClarifyFactCompletesOnAnswer — the fact path, where the answer carries
// both the key and the value.
func TestClarifyFactCompletesOnAnswer(t *testing.T) {
ctx := context.Background()
h, st, _ := newClarifyHandler(t)
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 == clarifyDropped {
t.Fatalf("answer should complete the fact, handled=%v reply=%q", handled, reply)
}
if fact, err := st.LatestFact(ctx, "water"); err != nil || fact.Key != "water" {
t.Fatalf("clarified fact was not written: fact=%+v err=%v", fact, err)
}
}
// TestClarifyAnswerAfterTTLIsANewRequest — a late answer is not an answer.
func TestClarifyAnswerAfterTTLIsANewRequest(t *testing.T) {
ctx := context.Background()
h, st, now := newClarifyHandler(t)
if _, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
t.Fatal("expected a question")
}
*now = now.Add(clarifyTTL + time.Second)
if reply, handled := h.resolveClarifyAnswer(ctx, "в 11:00"); handled {
t.Fatalf("an answer past the TTL must fall through to normal routing, got %q", reply)
}
if reminders, err := st.DueReminders(ctx, now.Add(48*time.Hour)); err != nil || len(reminders) != 0 {
t.Fatalf("expired question must not create anything: reminders=%v err=%v", reminders, err)
}
}
// TestClarifyUnclearAnswerDropsWithoutAskingAgain — MaxAttempts is 1.
func TestClarifyUnclearAnswerDropsWithoutAskingAgain(t *testing.T) {
ctx := context.Background()
h, st, _ := newClarifyHandler(t)
if _, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
t.Fatal("expected a question")
}
reply, handled := h.resolveClarifyAnswer(ctx, "ну не знаю")
if !handled || reply != clarifyDropped {
t.Fatalf("an unclear answer should drop the request, handled=%v reply=%q", handled, reply)
}
if strings.Contains(reply, "?") {
t.Fatalf("she must not ask a second question: %q", reply)
}
if h.clarifyStore.Get(voiceDialogueID, h.now()) != nil {
t.Fatal("a dropped request must leave no armed question")
}
if reminders, err := st.DueReminders(ctx, h.now().Add(48*time.Hour)); err != nil || len(reminders) != 0 {
t.Fatalf("a dropped request must not create anything: reminders=%v err=%v", reminders, err)
}
}
// TestClarifiedActOffAllowlistIsStillRefused — clarification fills in an
// argument, it never grants authority.
func TestClarifiedActOffAllowlistIsStillRefused(t *testing.T) {
ctx := context.Background()
h, st, _ := newClarifyHandler(t)
marker := filepath.Join(t.TempDir(), "not-allowed-ran")
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)
if !handled {
t.Fatal("the answer should be consumed")
}
if strings.Contains(reply, "готово") {
t.Fatalf("an act that is not on the allowlist must not report success: %q", reply)
}
if _, err := os.Stat(marker); !os.IsNotExist(err) {
t.Fatalf("a clarified act off the allowlist ran anyway: %v", err)
}
if tools, err := st.ListTools(ctx, "enabled"); err != nil || len(tools) != 0 {
t.Fatalf("clarify must not enable a tool: tools=%+v err=%v", tools, err)
}
}
// TestClarifiedDestructiveActStillNeedsConfirm — the confirm gate survives the
// clarify path.
func TestClarifiedDestructiveActStillNeedsConfirm(t *testing.T) {
ctx := context.Background()
h, st, _ := newClarifyHandler(t)
marker := filepath.Join(t.TempDir(), "destructive-ran")
if err := st.EnableTool(ctx, "delete_backups", []string{"touch", marker}, true, "test", h.now()); err != nil {
t.Fatal(err)
}
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")
if !handled {
t.Fatal("the answer should be consumed")
}
if !strings.Contains(reply, "да") || h.pending == nil {
t.Fatalf("a clarified destructive act must still park a confirm: reply=%q pending=%+v", reply, h.pending)
}
if _, err := os.Stat(marker); !os.IsNotExist(err) {
t.Fatalf("a clarified destructive act ran before confirmation: %v", err)
}
}
// TestNoQuestionWhenNothingIsMissing — noise keeps the canned reply, so she
// never invents a question for nothing.
func TestNoQuestionWhenNothingIsMissing(t *testing.T) {
h, _, _ := newClarifyHandler(t)
for _, dec := range []router.Decision{
clarifyDec(router.IntentChat, router.Slots{Text: "эм"}, "эм"),
clarifyDec(router.IntentQuery, router.Slots{Text: "ммм"}, "ммм"),
clarifyDec(router.IntentNote, router.Slots{Text: "..."}, "..."),
} {
if question, asked := h.askClarify(dec); asked {
t.Fatalf("intent %s should keep the canned reply, got %q", dec.Intent, question)
}
}
if h.clarifyStore.Get(voiceDialogueID, h.now()) != nil {
t.Fatal("noise must not park a question")
}
}
// TestNoPendingQuestionFallsThrough — with nothing parked, an utterance routes
// normally.
func TestNoPendingQuestionFallsThrough(t *testing.T) {
h, _, _ := newClarifyHandler(t)
if reply, handled := h.resolveClarifyAnswer(context.Background(), "напомни в 11:00"); handled {
t.Fatalf("no open question ⇒ must not be treated as an answer, got %q", reply)
}
}
+28
View File
@@ -0,0 +1,28 @@
package main
import (
"testing"
"time"
"github.com/kami/maven/internal/llm"
)
func TestPickLLMRouterOff(t *testing.T) {
if r := pickLLMRouter(false, llm.New("http://127.0.0.1:1", time.Second)); r != nil {
t.Error("flag off should give no LLM router")
}
}
// The operator can turn the flag on without an LLM phraser configured. That must
// leave the classifier running, not panic.
func TestPickLLMRouterOnWithoutClient(t *testing.T) {
if r := pickLLMRouter(true, nil); r != nil {
t.Error("no llama-server should give no LLM router")
}
}
func TestPickLLMRouterOn(t *testing.T) {
if r := pickLLMRouter(true, llm.New("http://127.0.0.1:1", time.Second)); r == nil {
t.Error("flag on with a client should give an LLM router")
}
}
+73 -46
View File
@@ -199,8 +199,6 @@ func wireVoice(cfg *config.Config, coreAPI ipc.CoreAPI, phr phraser.Phraser, mem
if lp, ok := phr.(*phraser.LLMPhraser); ok {
llmClient = llm.New(lp.BaseURL(), 60*time.Second)
}
// LLM router disabled — the classifier handles routing reliably.
// ----- router (the cascade; floor examples seed the classifier) -----
// The act matcher's allowlist is exactly the enabled tool names — the
// router only matches acts the executor can run (one source of truth).
@@ -208,7 +206,11 @@ func wireVoice(cfg *config.Config, coreAPI ipc.CoreAPI, phr phraser.Phraser, mem
if threshold <= 0 {
threshold = config.DefaultRouterThreshold
}
rtr := buildRouter(emb, matcher, threshold, nil) // LLM router disabled
// Both routing paths are weak on held-out utterances — the classifier gets
// 36.8% of intents right, the resident model 50.0% and much slower. Off by
// default (see config.VoiceConfig.LLMRouter); the classifier always stays
// wired as the fallback, so a model error never breaks a turn.
rtr := buildRouter(emb, matcher, threshold, pickLLMRouter(cfg.Voice.LLMRouter, llmClient))
// ----- sessions registry (shared with voicesink) -----
sessions := voice.NewSessions()
@@ -226,8 +228,6 @@ func wireVoice(cfg *config.Config, coreAPI ipc.CoreAPI, phr phraser.Phraser, mem
// ----- dialogue (multi-turn slot carry-over; 2-min follow-up window) -----
dialogueSessions := dialogue.NewSessionStore(2 * time.Minute)
clarifyStore := dialogue.NewClarifyStore(clarifyTTL)
timeParser := router.NewPythonDateParser()
// ----- replier (LLM-backed when the engine is on, Stub floor otherwise) -----
replier := voice.Replier(voice.NewStubReplier())
@@ -252,10 +252,8 @@ func wireVoice(cfg *config.Config, coreAPI ipc.CoreAPI, phr phraser.Phraser, mem
memStore: memStore,
dataStore: dataStore,
dialogueSessions: dialogueSessions,
clarifyStore: clarifyStore,
extractor: router.Extractor{Time: timeParser, Acts: matcher, Facts: router.DefaultFactParser{}},
queryMinScore: cfg.Voice.QueryMinScore,
timeParser: timeParser,
timeParser: router.NewPythonDateParser(),
ecosystem: eco,
}
@@ -308,14 +306,6 @@ type reactiveHandler struct {
// box → one session slot, keyed voiceDialogueID). nil ⇒ no carry-over.
dialogueSessions *dialogue.SessionStore
// clarifyStore parks the request behind an open question she asked (see
// clarify.go). nil ⇒ she falls back to the canned "не поняла" reply.
clarifyStore *dialogue.ClarifyStore
// extractor parses the answer to an open question, with the same parsers
// the router's own stage-2 uses.
extractor router.Extractor
// pending destructive-act confirmation. A destructive act replies with a
// "выполнить X? да/нет" prompt and parks here; the NEXT utterance is read as
// the y/n answer. ponytail: single slot, single-user box — a second act
@@ -390,13 +380,6 @@ func (h *reactiveHandler) HandlePushToTalk(ctx context.Context, req voice.PushTo
return h.reply(ctx, reply, nil)
}
// 1b2. clarify answer — if she asked a question last turn, this utterance is
// its answer, not a fresh command. After the confirm check: a y/n gate is
// armed by her own prompt and is the narrower claim on the utterance.
if reply, handled := h.resolveClarifyAnswer(ctx, text); handled {
return h.reply(ctx, reply, nil)
}
// 1c. quiet-hours toggle — keyword match, not classifier-dependent.
// "тихий режим" / "quiet on" would route through the classifier
// unreliably (it's a command, not a free-form query), so we match it
@@ -426,16 +409,34 @@ func (h *reactiveHandler) HandlePushToTalk(ctx context.Context, req voice.PushTo
prev := h.dialogueSessions.Get(voiceDialogueID, now)
dec = followUpMerge(prev, dec, now)
if !dec.Clarify {
h.rememberTurn(prev, dec, now)
}
}
// 2c. clarify — she is not sure. If one named thing is missing, ask about it
// and park the request (clarify.go); otherwise the replier's canned reply
// stands.
if dec.Clarify {
if question, asked := h.askClarify(dec); asked {
return h.reply(ctx, question, nil)
// Build history: carry over up to 4 prior turns for cross-intent
// reference. The most recent prior turn is prepended to history.
var history []dialogue.Turn
if prev != nil {
history = append(history, dialogue.Turn{
Intent: prev.Intent,
Slots: prev.Slots,
Text: prev.Slots.Text, // the prior turn's utterance
})
// Cap history depth so one long conversation can't grow
// the session unboundedly.
maxHist := len(prev.History)
if maxHist > 3 {
maxHist = 3
}
history = append(history, prev.History[:maxHist]...)
}
ttl := time.Duration(0) // use default (2 min)
if dec.Intent == router.IntentChat {
ttl = 15 * time.Minute // conversational turns should last longer
}
h.dialogueSessions.Put(voiceDialogueID, &dialogue.Session{
Intent: dialogue.Intent(dec.Intent),
Slots: toDialogueSlots(dec.Slots),
Timestamp: now,
TTL: ttl,
History: history,
})
}
}
@@ -466,11 +467,6 @@ func (h *reactiveHandler) handleText(ctx context.Context, text string) string {
return reply
}
// 1b2. clarify answer — same check as HandlePushToTalk.
if reply, handled := h.resolveClarifyAnswer(ctx, text); handled {
return reply
}
// 2. router — classify the utterance.
dec, err := h.router.Route(ctx, text, h.now())
if err != nil {
@@ -488,14 +484,30 @@ func (h *reactiveHandler) handleText(ctx context.Context, text string) string {
prev := h.dialogueSessions.Get(voiceDialogueID, now)
dec = followUpMerge(prev, dec, now)
if !dec.Clarify {
h.rememberTurn(prev, dec, now)
}
}
// 2c. clarify — same as HandlePushToTalk: ask about the one missing thing.
if dec.Clarify {
if question, asked := h.askClarify(dec); asked {
return question
var history []dialogue.Turn
if prev != nil {
history = append(history, dialogue.Turn{
Intent: prev.Intent,
Slots: prev.Slots,
Text: prev.Slots.Text,
})
maxHist := len(prev.History)
if maxHist > 3 {
maxHist = 3
}
history = append(history, prev.History[:maxHist]...)
}
ttl := time.Duration(0)
if dec.Intent == router.IntentChat {
ttl = 15 * time.Minute
}
h.dialogueSessions.Put(voiceDialogueID, &dialogue.Session{
Intent: dialogue.Intent(dec.Intent),
Slots: toDialogueSlots(dec.Slots),
Timestamp: now,
TTL: ttl,
History: history,
})
}
}
@@ -1038,6 +1050,21 @@ func (h *reactiveHandler) reply(ctx context.Context, text string, _ []string) (v
return voice.PushToTalkResp{ReplyText: text, ReplyAudio: audioOut}, nil
}
// pickLLMRouter returns the LLM router when the operator asked for it and there
// is a llama-server to talk to, and nil otherwise. nil is safe: the cascade then
// routes with the classifier, so an unusable setting costs accuracy, not turns.
func pickLLMRouter(enabled bool, c *llm.Client) *router.LLMRouter {
if !enabled {
return nil
}
if c == nil {
log.Printf("voice: voice.llm_router is on but there is no llama-server to route with (the phraser is not an LLM phraser) — using the classifier instead")
return nil
}
log.Printf("voice: LLM router enabled")
return router.NewLLMRouter(c)
}
// buildRouter constructs the reactive-path router with the given embedder
// and confidence threshold.
// - stage-0 grammars from DefaultActMatcher whose fn allowlist is exactly
+1
View File
@@ -40,6 +40,7 @@
"tokenizer_path": "/opt/maven/models/embedder/tokenizer.json",
"lib_path": "/opt/maven/lib/libonnxruntime.so"
},
"llm_router": false,
"tool_timeout": "30s",
"tools": [
{ "name": "status", "cmd": ["systemctl", "status"], "scope": "homelab", "destructive": false },
+14
View File
@@ -257,6 +257,20 @@ type VoiceConfig struct {
// Default 0.35 if unset.
RouterThreshold float64 `json:"router_threshold,omitempty"`
// LLMRouter — route with the resident model instead of the embedding
// classifier. Measured on the held-out fixture (ROUTING-EVAL-31-07-2026.md)
// the model gets 50.0% of intents right against the classifier's 36.8%, but
// it costs about 800ms per turn instead of 30ms.
//
// TODO: the default stays false until two things land.
// 1. The LLM router cannot refuse. LLMRouter.Route hardcodes
// Confidence: 1.0, so the stage-3 clarify gate never fires and an
// unclear utterance becomes a confident wrong action (Vikunja #359).
// 2. Extractor.Extract never runs on an LLM decision, so acts arrive with
// no Fn and reminders with no Time.
// Turning this on today makes routing more accurate and less safe.
LLMRouter bool `json:"llm_router,omitempty"`
// QueryMinScore — the note-recall confidence gate. Top cosine below this
// ⇒ "I don't know" instead of a guess. Tuned for the ONNX embedder (0.55);
// the HashEmbedder floor scores lexically and may never clear it. 0.55
+22
View File
@@ -171,6 +171,28 @@ func TestWeatherConfigNilOK(t *testing.T) {
}
}
func TestLLMRouterDefaultsOff(t *testing.T) {
p := writeConfig(t, `{"voice":{"enabled":true,"bind":"127.0.0.1:9100"}}`)
c, err := Load(p)
if err != nil {
t.Fatalf("Load: %v", err)
}
if c.Voice.LLMRouter {
t.Error("voice.llm_router absent should mean false")
}
}
func TestLLMRouterRead(t *testing.T) {
p := writeConfig(t, `{"voice":{"enabled":true,"bind":"127.0.0.1:9100","llm_router":true}}`)
c, err := Load(p)
if err != nil {
t.Fatalf("Load: %v", err)
}
if !c.Voice.LLMRouter {
t.Error("voice.llm_router true was not read")
}
}
func TestDurationRoundTrip(t *testing.T) {
d := Duration(15 * time.Minute)
b, err := d.MarshalJSON()
-171
View File
@@ -1,171 +0,0 @@
package dialogue
import (
"sync"
"time"
)
// Slot names one field of Slots. Named type, not a free string, so a missing
// slot cannot be misspelled — the question phrasing switches on these.
type Slot string
const (
SlotTime Slot = "time" // Slots.Time / HasTime
SlotKey Slot = "key" // Slots.Key / HasKey
SlotValue Slot = "value" // Slots.Value (paired with Key)
SlotFn Slot = "fn" // Slots.Fn / HasFn
SlotText Slot = "text" // Slots.Text
)
// MaxAttempts is 1 because Maven is not a nag (DESIGN.md § Non-goals). She asks
// one clarifying question. If the answer still leaves the slot empty she drops
// the request instead of asking again.
const MaxAttempts = 1
// PendingQuestion is what Maven holds while she waits for an answer to an open
// question. Unlike the yes/no confirms in cmd/mavend/voice.go, the answer here
// is free text that fills a missing slot rather than a verdict.
type PendingQuestion struct {
Intent Intent // what the router already guessed
Slots Slots // what it already filled
Missing []Slot // what is still empty, in the order to ask about
Utterance string // the user's original raw words
Asked time.Time
TTL time.Duration
Attempts int // questions already asked; capped by MaxAttempts
}
func (q *PendingQuestion) IsExpired(now time.Time) bool {
return now.After(q.Asked.Add(q.TTL))
}
// CanAsk reports whether Maven may ask another question about this request.
func (q *PendingQuestion) CanAsk() bool {
return q.Attempts < MaxAttempts
}
// TODO: the daemon will phrase the question text from Missing (one short ru
// question per Slot, feminine self-reference) and speak it here.
// ClarifyStore holds the parked questions. Same shape and locking as
// SessionStore: keyed by dialogue id, expired entries dropped on read.
type ClarifyStore struct {
mu sync.RWMutex
questions map[string]*PendingQuestion
defaultTTL time.Duration
}
func NewClarifyStore(defaultTTL time.Duration) *ClarifyStore {
if defaultTTL <= 0 {
// Short, like confirmTTL in voice.go: a clarifying question is a
// same-breath gesture, a stale one should not eat a later utterance.
defaultTTL = 90 * time.Second
}
return &ClarifyStore{
questions: make(map[string]*PendingQuestion),
defaultTTL: defaultTTL,
}
}
// TODO: the daemon will Put a question here when Decision.Clarify fires, in
// place of the flat "не разобрала" reply (cmd/mavend/voice.go).
func (s *ClarifyStore) Put(id string, q *PendingQuestion) {
if q.TTL <= 0 {
q.TTL = s.defaultTTL
}
s.mu.Lock()
s.questions[id] = q
s.mu.Unlock()
}
// TODO: the daemon will Get on the next turn, parse that turn into Slots, call
// Answer, and Delete — the open-question twin of resolveConfirm.
func (s *ClarifyStore) Get(id string, now time.Time) *PendingQuestion {
s.mu.RLock()
q, ok := s.questions[id]
s.mu.RUnlock()
if !ok {
return nil
}
if q.IsExpired(now) {
s.Delete(id)
return nil
}
return q
}
func (s *ClarifyStore) Delete(id string) {
s.mu.Lock()
delete(s.questions, id)
s.mu.Unlock()
}
// Answer merges the slots parsed from the user's answer into the parked ones.
// Only the slots listed in Missing are filled, and an already filled slot is
// never overwritten — the answer completes the original request, it does not
// restate it. Parsing the answer text into `answer` is the caller's job; this
// package must stay free of internal/router.
func (q *PendingQuestion) Answer(text string, answer Slots) Slots {
out := q.Slots
for _, slot := range q.Missing {
switch slot {
case SlotTime:
if !out.HasTime && answer.HasTime {
out.Time = answer.Time
out.HasTime = true
}
case SlotKey:
if !out.HasKey && answer.HasKey {
out.Key = answer.Key
out.HasKey = true
}
case SlotValue:
if out.Value == "" && answer.Value != "" {
out.Value = answer.Value
}
case SlotFn:
if !out.HasFn && answer.HasFn {
out.Fn = answer.Fn
out.HasFn = true
if len(out.Args) == 0 {
out.Args = append([]string(nil), answer.Args...)
}
}
case SlotText:
if out.Text == "" {
if answer.Text != "" {
out.Text = answer.Text
} else {
// No parse for a text slot — the raw answer IS the text.
out.Text = text
}
}
}
}
return out
}
// StillMissing lists the slots that are empty in s, out of the ones asked for.
// The caller uses it to decide between acting and dropping the request.
func StillMissing(want []Slot, s Slots) []Slot {
var out []Slot
for _, slot := range want {
empty := false
switch slot {
case SlotTime:
empty = !s.HasTime
case SlotKey:
empty = !s.HasKey
case SlotValue:
empty = s.Value == ""
case SlotFn:
empty = !s.HasFn
case SlotText:
empty = s.Text == ""
}
if empty {
out = append(out, slot)
}
}
return out
}
-225
View File
@@ -1,225 +0,0 @@
package dialogue
import (
"testing"
"time"
)
var base = time.Date(2026, 7, 31, 12, 0, 0, 0, time.UTC)
func TestPendingQuestionIsExpired(t *testing.T) {
cases := []struct {
name string
ttl time.Duration
now time.Time
want bool
}{
{"fresh", time.Minute, base.Add(10 * time.Second), false},
{"exactly at ttl", time.Minute, base.Add(time.Minute), false},
{"past ttl", time.Minute, base.Add(2 * time.Minute), true},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
q := &PendingQuestion{Asked: base, TTL: tc.ttl}
if got := q.IsExpired(tc.now); got != tc.want {
t.Fatalf("IsExpired = %v, want %v", got, tc.want)
}
})
}
}
func TestClarifyStoreGetPutDelete(t *testing.T) {
s := NewClarifyStore(time.Minute)
if got := s.Get("voice", base); got != nil {
t.Fatalf("empty store returned %+v", got)
}
q := &PendingQuestion{Intent: IntentReminder, Missing: []Slot{SlotTime}, Asked: base}
s.Put("voice", q)
if q.TTL != time.Minute {
t.Fatalf("Put did not apply the default TTL, got %v", q.TTL)
}
if got := s.Get("voice", base.Add(time.Second)); got != q {
t.Fatalf("Get returned %+v, want the parked question", got)
}
// Expired questions are dropped on read, not returned.
if got := s.Get("voice", base.Add(2*time.Minute)); got != nil {
t.Fatalf("expired Get returned %+v", got)
}
if got := s.Get("voice", base); got != nil {
t.Fatalf("expired question was not deleted: %+v", got)
}
s.Put("voice", &PendingQuestion{Asked: base, TTL: time.Hour})
s.Delete("voice")
if got := s.Get("voice", base); got != nil {
t.Fatalf("Delete left %+v", got)
}
}
func TestNewClarifyStoreDefaultTTL(t *testing.T) {
s := NewClarifyStore(0)
q := &PendingQuestion{Asked: base}
s.Put("voice", q)
if q.TTL != 90*time.Second {
t.Fatalf("TTL = %v, want 90s", q.TTL)
}
}
func TestAnswerFillsOnlyMissingSlots(t *testing.T) {
answerTime := base.Add(3 * time.Hour)
other := base.Add(9 * time.Hour)
cases := []struct {
name string
parked Slots
missing []Slot
text string
answer Slots
want Slots
}{
{
name: "fills the missing time",
parked: Slots{Text: "напомни позвонить"},
missing: []Slot{SlotTime},
text: "в три",
answer: Slots{Time: answerTime, HasTime: true},
want: Slots{Text: "напомни позвонить", Time: answerTime, HasTime: true},
},
{
name: "does not overwrite a filled time",
parked: Slots{Time: other, HasTime: true},
missing: []Slot{SlotTime},
text: "в три",
answer: Slots{Time: answerTime, HasTime: true},
want: Slots{Time: other, HasTime: true},
},
{
name: "ignores slots that were not missing",
parked: Slots{Key: "water", HasKey: true},
missing: []Slot{SlotValue},
text: "два литра",
answer: Slots{Key: "sleep", HasKey: true, Value: "2l"},
want: Slots{Key: "water", HasKey: true, Value: "2l"},
},
{
name: "fills key when empty",
parked: Slots{},
missing: []Slot{SlotKey, SlotValue},
text: "воды",
answer: Slots{Key: "water", HasKey: true, Value: `"drank"`},
want: Slots{Key: "water", HasKey: true, Value: `"drank"`},
},
{
name: "fills fn and its args",
parked: Slots{},
missing: []Slot{SlotFn},
text: "перезапусти nginx",
answer: Slots{Fn: "restart", Args: []string{"nginx"}, HasFn: true},
want: Slots{Fn: "restart", Args: []string{"nginx"}, HasFn: true},
},
{
name: "keeps existing args when fn was already known",
parked: Slots{Fn: "restart", Args: []string{"nginx"}, HasFn: true},
missing: []Slot{SlotFn},
text: "останови postgres",
answer: Slots{Fn: "stop", Args: []string{"postgres"}, HasFn: true},
want: Slots{Fn: "restart", Args: []string{"nginx"}, HasFn: true},
},
{
name: "raw answer becomes the text when nothing was parsed",
parked: Slots{},
missing: []Slot{SlotText},
text: "купить хлеб",
answer: Slots{},
want: Slots{Text: "купить хлеб"},
},
{
name: "parsed text wins over the raw answer",
parked: Slots{},
missing: []Slot{SlotText},
text: "запиши купить хлеб",
answer: Slots{Text: "купить хлеб"},
want: Slots{Text: "купить хлеб"},
},
{
name: "empty answer leaves the slot missing",
parked: Slots{Text: "напомни"},
missing: []Slot{SlotTime},
text: "не знаю",
answer: Slots{},
want: Slots{Text: "напомни"},
},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
q := &PendingQuestion{Slots: tc.parked, Missing: tc.missing, Asked: base}
got := q.Answer(tc.text, tc.answer)
if got.Time != tc.want.Time || got.HasTime != tc.want.HasTime ||
got.Key != tc.want.Key || got.HasKey != tc.want.HasKey ||
got.Value != tc.want.Value || got.Text != tc.want.Text ||
got.Fn != tc.want.Fn || got.HasFn != tc.want.HasFn {
t.Fatalf("Answer = %+v, want %+v", got, tc.want)
}
if len(got.Args) != len(tc.want.Args) {
t.Fatalf("Args = %v, want %v", got.Args, tc.want.Args)
}
for i := range got.Args {
if got.Args[i] != tc.want.Args[i] {
t.Fatalf("Args = %v, want %v", got.Args, tc.want.Args)
}
}
})
}
}
func TestCanAskCapsAtOneQuestion(t *testing.T) {
if MaxAttempts != 1 {
t.Fatalf("MaxAttempts = %d, want 1 (Maven asks once, she is not a nag)", MaxAttempts)
}
q := &PendingQuestion{Asked: base}
if !q.CanAsk() {
t.Fatal("a fresh question should be askable")
}
q.Attempts = MaxAttempts
if q.CanAsk() {
t.Fatal("the question should not be asked twice")
}
}
func TestStillMissing(t *testing.T) {
want := []Slot{SlotTime, SlotKey, SlotValue, SlotFn, SlotText}
cases := []struct {
name string
slots Slots
want []Slot
}{
{"all empty", Slots{}, want},
{
name: "all filled",
slots: Slots{Time: base, HasTime: true, Key: "water", HasKey: true, Value: "1l", Fn: "restart", HasFn: true, Text: "t"},
want: nil,
},
{
name: "only value left",
slots: Slots{Time: base, HasTime: true, Key: "water", HasKey: true, Fn: "restart", HasFn: true, Text: "t"},
want: []Slot{SlotValue},
},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
got := StillMissing(want, tc.slots)
if len(got) != len(tc.want) {
t.Fatalf("StillMissing = %v, want %v", got, tc.want)
}
for i := range got {
if got[i] != tc.want[i] {
t.Fatalf("StillMissing = %v, want %v", got, tc.want)
}
}
})
}
}
-4
View File
@@ -21,7 +21,6 @@ type Slots struct {
Time time.Time
HasTime bool
Key string
Value string // payload for a fact key, mirrors router.Slots.Value
HasKey bool
Text string
Fn string
@@ -105,9 +104,6 @@ func InheritSlots(prev, cur Slots) Slots {
out.Key = prev.Key
out.HasKey = true
}
if out.Value == "" && prev.Value != "" {
out.Value = prev.Value
}
if out.Text == "" && prev.Text != "" {
out.Text = prev.Text
}
-10
View File
@@ -113,14 +113,4 @@ func TestInheritSlots(t *testing.T) {
if inherited6.Text != "какая погода в москве" {
t.Error("should inherit text when current is empty")
}
prevValue := Slots{Key: "water", HasKey: true, Value: `"drank"`}
inherited7 := InheritSlots(prevValue, Slots{})
if inherited7.Value != `"drank"` {
t.Error("should inherit value when current is empty")
}
kept := InheritSlots(prevValue, Slots{Value: "2l"})
if kept.Value != "2l" {
t.Error("should keep current value")
}
}
+14 -4
View File
@@ -7,12 +7,22 @@
set -euo pipefail
# The llama-server the phraser spawns has NO "maven" in its command line (its
# args are `-m /path/to/LFM2.5-...gguf --port ...`), so a `llama-server.*maven`
# args are `-m /path/to/<model>.gguf --port ...`), so a `llama-server.*maven`
# pattern matches nothing and leaks it — the exact bug that let orphans pile up
# and OOM the box. Match the model instead. Override MODEL if you change it.
MODEL="${MODEL:-LFM2}"
# and OOM the box.
#
# We used to match the model name, defaulting to LFM2. The deploy now runs
# Qwen3.5-0.8B, so that default matched nothing and the server survived every
# kill. Match any llama-server serving a .gguf instead, so swapping the model in
# deploy/mavend.json cannot break this script again. Set MODEL to narrow it if
# some other llama-server on this box must be left alone.
MODEL="${MODEL:-}"
PAT='mavend|mavsttd|mavttsd|mavweb|mavpoll|mavenclient'
LLM="llama-server.*${MODEL}"
if [ -n "$MODEL" ]; then
LLM="llama-server.*${MODEL}"
else
LLM='llama-server.*\.gguf'
fi
echo "--- Sending graceful SIGTERM to Maven services ---"
pkill -TERM -f "$PAT" || true