Compare commits
6 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| a1f811d4c8 | |||
| 7ab38cd7f7 | |||
| 6a85e71077 | |||
| bf6c2bf1a6 | |||
| 1558233665 | |||
| 5afa2dfb38 |
@@ -16,7 +16,7 @@ PIPER_BIN := $(shell pwd)/deps/piper/piper
|
||||
PIPER_MODEL := $(shell pwd)/models/tts/ru_RU-irina-medium.onnx
|
||||
PIPER_ESPEAK := $(shell pwd)/deps/piper/espeak-ng-data
|
||||
|
||||
.PHONY: simulate stt-fixtures test-stt-golden all build build-stt build-tts build-daemon build-client build-waked build-web build-poll build-caldav clean test fmt-check vet run-stt run-tts run-web download-embedder deps-go eval-router eval-recall eval-phrasing eval-models build-gpud
|
||||
.PHONY: simulate stt-fixtures test-stt-golden all build build-stt build-tts build-daemon build-client build-waked build-web build-poll build-caldav clean test fmt-check vet run-stt run-tts run-web download-embedder deps-go deps-sentinel tidy eval-router eval-recall eval-phrasing eval-models build-gpud
|
||||
|
||||
all: build
|
||||
|
||||
@@ -74,7 +74,7 @@ run-web: build-web
|
||||
# base.Tool(), which only stats pkg/tool and exits. So build them in once here.
|
||||
GO_TARBALL := go$(GO_VERSION).linux-amd64.tar.gz
|
||||
GO_SHA256 := 9e9b755d63b36acf30c12a9a3fc379243714c1c6d3dd72861da637f336ebb35b
|
||||
deps-go:
|
||||
deps-go: deps-sentinel
|
||||
@mkdir -p deps/go
|
||||
cd deps/go && curl -fLO 'https://go.dev/dl/$(GO_TARBALL)'
|
||||
cd deps/go && echo '$(GO_SHA256) $(GO_TARBALL)' | sha256sum -c -
|
||||
@@ -84,6 +84,25 @@ deps-go:
|
||||
done
|
||||
$(GO) version
|
||||
|
||||
# deps/go.mod — the sentinel that stops the module walk at deps/ (Vikunja #454).
|
||||
# The vendored toolchain lives inside the module tree, so `go mod tidy` walked
|
||||
# Go's own compiler-error fixtures and died on files that are malformed on
|
||||
# purpose ("unicode//utf8": double slash). A nested module is not part of the
|
||||
# parent, so one three-line file ends the walk. deps/ is gitignored, so it is
|
||||
# generated here rather than committed, and every target that populates deps/
|
||||
# writes it.
|
||||
deps-sentinel:
|
||||
@mkdir -p deps
|
||||
@printf 'module github.com/kami/maven/deps\n\ngo 1.21\n' > deps/go.mod
|
||||
|
||||
# Run the tidy the sentinel makes possible. Not part of `test`: it rewrites
|
||||
# go.mod, and a build target that edits the module file is a surprise.
|
||||
# vendor/ is committed, so a tidy that drops a requirement must be followed by
|
||||
# a re-vendor or the next build fails on "inconsistent vendoring".
|
||||
tidy: deps-sentinel
|
||||
GOTOOLCHAIN=local GOFLAGS=-mod=mod $(GO) mod tidy
|
||||
GOTOOLCHAIN=local GOFLAGS=-mod=mod $(GO) mod vendor
|
||||
|
||||
# fmt-check fails if any file needs gofmt. docs/design.md has always said `make
|
||||
# test` gates on gofmt and vet; it did not, so nine files quietly drifted.
|
||||
# Run `gofmt -w` on whatever this prints.
|
||||
@@ -178,7 +197,7 @@ run-tts: build-tts
|
||||
./mavttsd -socket /tmp/maven/tts.sock \
|
||||
-piper $(PIPER_BIN) -model $(PIPER_MODEL) -espeak_data $(PIPER_ESPEAK)
|
||||
|
||||
deps: deps-whisper deps-piper
|
||||
deps: deps-sentinel deps-whisper deps-piper
|
||||
|
||||
deps-whisper:
|
||||
cd deps/whisper.cpp && cmake -B build -DCMAKE_BUILD_TYPE=Release \
|
||||
|
||||
@@ -4,6 +4,7 @@ import (
|
||||
"context"
|
||||
"log"
|
||||
|
||||
"github.com/kami/maven/internal/dialogue"
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/store"
|
||||
@@ -70,7 +71,16 @@ func (h *reactiveHandler) queryTasks(ctx context.Context, t *queryTurn) (string,
|
||||
log.Printf("voice: list tasks: %v", err)
|
||||
return "не получилось посмотреть задачи.", true
|
||||
}
|
||||
return tasks.FormatRU(tasks.Rank(taskItems(live), h.now())), true
|
||||
ranked := tasks.Rank(taskItems(live), h.now())
|
||||
// Bind what she is about to say, in the order she says it, so "второй"
|
||||
// means the second task he heard (ordinal.go).
|
||||
spoken := tasks.Spoken(ranked)
|
||||
cands := make([]dialogue.Candidate, 0, len(spoken))
|
||||
for _, r := range spoken {
|
||||
cands = append(cands, dialogue.Candidate{Kind: "task", Ref: r.ID, Label: r.Text})
|
||||
}
|
||||
h.offerCandidates(cands)
|
||||
return tasks.FormatRU(ranked), true
|
||||
}
|
||||
|
||||
// taskItems maps wire rows onto the ranker's input. Written here rather than in
|
||||
|
||||
@@ -0,0 +1,145 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"log"
|
||||
"strings"
|
||||
"unicode"
|
||||
|
||||
"github.com/kami/maven/internal/dialogue"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
// Ordinal selection over a list she just read (Vikunja #448).
|
||||
//
|
||||
// The dialogue session already carried the intent, the slots and the history.
|
||||
// What it did not carry was the list: she recited five tasks, he said "второй",
|
||||
// and there was nothing for that word to point at, so it routed as a fresh
|
||||
// utterance and meant nothing.
|
||||
//
|
||||
// Candidates are bound when she speaks the list, in the order she spoke it (see
|
||||
// tasks.Spoken). Binding afterwards would resolve "второй" against a fresh
|
||||
// query, and the list can change between two turns.
|
||||
//
|
||||
// An ordinal with no verb is read back, not acted on: "второй" names a task, it
|
||||
// does not say what to do with it. Acting on the bare word would guess, and a
|
||||
// wrong guess here closes work he never finished.
|
||||
|
||||
// candidateOrdinals — the words that pick a position, by index. Prefix match,
|
||||
// because Russian declines them: "первый", "первую", "первое".
|
||||
var candidateOrdinals = []struct {
|
||||
word string
|
||||
nth int
|
||||
}{
|
||||
{"перв", 1}, {"втор", 2}, {"трет", 3}, {"четв", 4}, {"пят", 5},
|
||||
{"first", 1}, {"second", 2}, {"third", 3},
|
||||
}
|
||||
|
||||
// candidateDigits — "второй" said as a number. Matched whole, never by prefix:
|
||||
// "15" starts with "1" and is a time, not a position.
|
||||
var candidateDigits = map[string]int{"1": 1, "2": 2, "3": 3, "4": 4, "5": 5}
|
||||
|
||||
// candidateLast — "последний" picks the end of the list whatever its length.
|
||||
var candidateLast = []string{"последн", "last"}
|
||||
|
||||
// parseOrdinal reads which position he named. 0 and false when he named none.
|
||||
// A negative result means the last one.
|
||||
func parseOrdinal(text string) (int, bool) {
|
||||
// Token by token, not substring: " 1" would otherwise match inside
|
||||
// "напомни в 15:00" and turn a reminder into a selection.
|
||||
for _, tok := range strings.FieldsFunc(strings.ToLower(text), func(r rune) bool {
|
||||
return !unicode.IsLetter(r) && !unicode.IsDigit(r)
|
||||
}) {
|
||||
for _, w := range candidateLast {
|
||||
if strings.HasPrefix(tok, w) {
|
||||
return -1, true
|
||||
}
|
||||
}
|
||||
if n, ok := candidateDigits[tok]; ok {
|
||||
return n, true
|
||||
}
|
||||
for _, o := range candidateOrdinals {
|
||||
// Prefix, because Russian declines them: "первый", "первую".
|
||||
if strings.HasPrefix(tok, o.word) {
|
||||
return o.nth, true
|
||||
}
|
||||
}
|
||||
}
|
||||
return 0, false
|
||||
}
|
||||
|
||||
// candidateVerbs — what he wants done with the one he picked. Nothing here is
|
||||
// destructive: a task moves forward or is dropped, and both are recorded with a
|
||||
// provenance the /tasks page shows.
|
||||
var candidateVerbs = []struct {
|
||||
words []string
|
||||
status string
|
||||
say string
|
||||
}{
|
||||
{[]string{"готов", "сделал", "выполнил", "закрыл", "done"}, store.TaskDone, "закрыла"},
|
||||
{[]string{"не надо", "убери", "отмени", "не буду", "drop"}, store.TaskDropped, "убрала"},
|
||||
{[]string{"подтвержда", "беру", "да,", "буду делать"}, store.TaskOpen, "взяла в работу"},
|
||||
}
|
||||
|
||||
func parseCandidateVerb(text string) (status, say string, ok bool) {
|
||||
s := strings.ToLower(strings.TrimSpace(text))
|
||||
for _, v := range candidateVerbs {
|
||||
for _, w := range v.words {
|
||||
if strings.Contains(s, w) {
|
||||
return v.status, v.say, true
|
||||
}
|
||||
}
|
||||
}
|
||||
return "", "", false
|
||||
}
|
||||
|
||||
// offerCandidates records the list she just read, so his next words can pick
|
||||
// from it. Best effort: no session store, or a session that expired between the
|
||||
// question and the answer, means the words route normally.
|
||||
func (h *reactiveHandler) offerCandidates(cands []dialogue.Candidate) {
|
||||
if h.dialogueSessions == nil || len(cands) == 0 {
|
||||
return
|
||||
}
|
||||
h.dialogueSessions.SetCandidates(voiceDialogueID, h.now(), cands)
|
||||
}
|
||||
|
||||
// resolveCandidate handles "второй", "первую сделал", "последнюю убери" against
|
||||
// the list she just read.
|
||||
func (h *reactiveHandler) resolveCandidate(ctx context.Context, text string) (string, bool) {
|
||||
if h.dialogueSessions == nil {
|
||||
return "", false
|
||||
}
|
||||
sess := h.dialogueSessions.Get(voiceDialogueID, h.now())
|
||||
if sess == nil || len(sess.Candidates) == 0 {
|
||||
return "", false
|
||||
}
|
||||
nth, ok := parseOrdinal(text)
|
||||
if !ok {
|
||||
return "", false
|
||||
}
|
||||
if nth < 0 {
|
||||
nth = len(sess.Candidates)
|
||||
}
|
||||
if nth > len(sess.Candidates) {
|
||||
// Claim the turn: he is picking from her list and named a position she
|
||||
// did not read. Routing it fresh would answer something else entirely.
|
||||
return fmt.Sprintf("я назвала только %d.", len(sess.Candidates)), true
|
||||
}
|
||||
pick := sess.Candidates[nth-1]
|
||||
status, say, hasVerb := parseCandidateVerb(text)
|
||||
if !hasVerb || pick.Kind != "task" {
|
||||
// Read it back and keep the list: naming one is often the first half of
|
||||
// a sentence, and the second half is the next turn.
|
||||
return pick.Label, true
|
||||
}
|
||||
if err := h.api.SetTaskStatus(ctx, pick.Ref, status, h.now(), "tap:voice"); err != nil {
|
||||
log.Printf("voice: candidate %d → %s: %v", pick.Ref, status, err)
|
||||
return "не получилось изменить задачу.", true
|
||||
}
|
||||
// Spent: the list she read is no longer the list, and a second ordinal
|
||||
// against it would close the wrong task.
|
||||
h.dialogueSessions.SetCandidates(voiceDialogueID, h.now(), nil)
|
||||
log.Printf("voice: candidate %d (%q) → %s", pick.Ref, pick.Label, status)
|
||||
return say + ": " + pick.Label, true
|
||||
}
|
||||
@@ -0,0 +1,128 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/dialogue"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
func TestParseOrdinalReadsThePosition(t *testing.T) {
|
||||
cases := []struct {
|
||||
text string
|
||||
want int
|
||||
ok bool
|
||||
}{
|
||||
{"второй", 2, true},
|
||||
{"вторую сделал", 2, true},
|
||||
{"первую убери", 1, true},
|
||||
{"последнюю не надо", -1, true},
|
||||
{"3", 3, true},
|
||||
{"the second one", 2, true},
|
||||
// No position named.
|
||||
{"какие у меня задачи", 0, false},
|
||||
{"", 0, false},
|
||||
// A digit inside a time is not a position.
|
||||
{"напомни в 15:00", 0, false},
|
||||
}
|
||||
for _, c := range cases {
|
||||
got, ok := parseOrdinal(c.text)
|
||||
if ok != c.ok || (ok && got != c.want) {
|
||||
t.Errorf("parseOrdinal(%q) = %d,%v; want %d,%v", c.text, got, ok, c.want, c.ok)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestOrdinalPassesWithNothingOffered(t *testing.T) {
|
||||
h, _, _ := newClarifyHandler(t)
|
||||
if _, handled := h.resolveCandidate(context.Background(), "второй"); handled {
|
||||
t.Error("an ordinal with no list behind it was claimed")
|
||||
}
|
||||
}
|
||||
|
||||
func TestOrdinalReadsBackWithoutAVerb(t *testing.T) {
|
||||
h, st, _ := newClarifyHandler(t)
|
||||
ctx := context.Background()
|
||||
ids := seedTasks(t, st, "купить хлеб", "позвонить маме")
|
||||
putCandidates(h, ids, "купить хлеб", "позвонить маме")
|
||||
|
||||
reply, handled := h.resolveCandidate(ctx, "второй")
|
||||
if !handled || !strings.Contains(reply, "позвонить маме") {
|
||||
t.Fatalf("a bare ordinal did not read the task back: %q handled=%v", reply, handled)
|
||||
}
|
||||
// Still live: naming one is often the first half of a sentence.
|
||||
if _, handled := h.resolveCandidate(ctx, "первый"); !handled {
|
||||
t.Error("the list was spent by a read-back")
|
||||
}
|
||||
}
|
||||
|
||||
func TestOrdinalWithAVerbMovesTheTask(t *testing.T) {
|
||||
h, st, _ := newClarifyHandler(t)
|
||||
ctx := context.Background()
|
||||
ids := seedTasks(t, st, "купить хлеб", "позвонить маме")
|
||||
putCandidates(h, ids, "купить хлеб", "позвонить маме")
|
||||
|
||||
reply, handled := h.resolveCandidate(ctx, "первую сделал")
|
||||
if !handled || !strings.Contains(reply, "купить хлеб") {
|
||||
t.Fatalf("the pick was not acted on: %q handled=%v", reply, handled)
|
||||
}
|
||||
live, err := st.ListTasks(ctx, "live")
|
||||
if err != nil {
|
||||
t.Fatalf("list tasks: %v", err)
|
||||
}
|
||||
for _, task := range live {
|
||||
if task.ID == ids[0] {
|
||||
t.Fatalf("task %d is still live after he closed it", task.ID)
|
||||
}
|
||||
}
|
||||
// Spent: a second ordinal against a list that no longer holds would close
|
||||
// the wrong task.
|
||||
if _, handled := h.resolveCandidate(ctx, "второй"); handled {
|
||||
t.Error("the list survived the pick it was spent on")
|
||||
}
|
||||
}
|
||||
|
||||
func TestOrdinalPastTheEndSaysHowMany(t *testing.T) {
|
||||
h, st, _ := newClarifyHandler(t)
|
||||
ids := seedTasks(t, st, "купить хлеб")
|
||||
putCandidates(h, ids, "купить хлеб")
|
||||
|
||||
reply, handled := h.resolveCandidate(context.Background(), "третий")
|
||||
if !handled || !strings.Contains(reply, "1") {
|
||||
t.Fatalf("a position she never read was not answered: %q handled=%v", reply, handled)
|
||||
}
|
||||
}
|
||||
|
||||
// ordinalNow — a fixed capture time; the ranker only needs the rows to exist.
|
||||
var ordinalNow = time.Date(2026, 8, 4, 9, 0, 0, 0, time.UTC)
|
||||
|
||||
func seedTasks(t *testing.T, st *store.Store, texts ...string) []int64 {
|
||||
t.Helper()
|
||||
ctx := context.Background()
|
||||
var ids []int64
|
||||
for _, text := range texts {
|
||||
res, err := st.CaptureTask(ctx, store.Task{
|
||||
Text: text,
|
||||
Source: "tap:voice",
|
||||
Status: store.TaskOpen,
|
||||
CreatedTs: ordinalNow,
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatalf("capture task: %v", err)
|
||||
}
|
||||
ids = append(ids, res.ID)
|
||||
}
|
||||
return ids
|
||||
}
|
||||
|
||||
func putCandidates(h *reactiveHandler, ids []int64, labels ...string) {
|
||||
cands := make([]dialogue.Candidate, 0, len(ids))
|
||||
for i, id := range ids {
|
||||
cands = append(cands, dialogue.Candidate{Kind: "task", Ref: id, Label: labels[i]})
|
||||
}
|
||||
h.dialogueSessions.Put(voiceDialogueID, &dialogue.Session{Timestamp: h.now()})
|
||||
h.offerCandidates(cands)
|
||||
}
|
||||
@@ -0,0 +1,197 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"log"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// Conversation repair (Vikunja #455).
|
||||
//
|
||||
// The classifier has been able to learn from a correction since it was
|
||||
// written — CorrectMisroute appends the utterance as a new example for the
|
||||
// intent he names, append-only, no retrain. Nothing in the daemon could reach
|
||||
// it: the only caller was a test. So the mechanism existed and the behaviour
|
||||
// did not.
|
||||
//
|
||||
// This is the reachable half. He says she got it wrong and names what it
|
||||
// should have been, she redoes the previous utterance under that intent, and
|
||||
// she says out loud that the correction landed — because a correction he
|
||||
// cannot see is indistinguishable from one that was dropped.
|
||||
//
|
||||
// Taken before routing, like the confirm and clarify turns: "нет, это была
|
||||
// заметка" is an answer to the previous turn, not a fresh command, and routing
|
||||
// it as one files the correction itself as a note.
|
||||
|
||||
// routedTurn — the previous utterance and where it went, which is all a
|
||||
// correction needs to point at.
|
||||
type routedTurn struct {
|
||||
utterance string
|
||||
intent router.Intent
|
||||
at time.Time
|
||||
}
|
||||
|
||||
// repairWindow — how long a turn stays correctable. Long enough that he can
|
||||
// hear the wrong answer, think, and say so; short enough that "это заметка"
|
||||
// half an hour later is a fresh sentence and not a verdict on something he has
|
||||
// forgotten.
|
||||
const repairWindow = 5 * time.Minute
|
||||
|
||||
// repairMarkers — the ways he says she got it wrong. One of these must appear:
|
||||
// naming an intent alone is an ordinary sentence ("напиши заметку"), and
|
||||
// treating it as a correction would rewrite the last turn every time he used
|
||||
// the word.
|
||||
var repairMarkers = []string{
|
||||
"не так поняла",
|
||||
"неправильно поняла",
|
||||
"ты не поняла",
|
||||
"не поняла меня",
|
||||
"ты ошиблась",
|
||||
"это не",
|
||||
"а не",
|
||||
"не про то",
|
||||
"got it wrong",
|
||||
"not a ",
|
||||
"that was wrong",
|
||||
}
|
||||
|
||||
// repairIntents — the words he uses for each intent. Prefixes, because Russian
|
||||
// declines them: "заметка", "заметку", "заметкой".
|
||||
var repairIntents = []struct {
|
||||
word string
|
||||
intent router.Intent
|
||||
say string
|
||||
}{
|
||||
{"заметк", router.IntentNote, "заметка"},
|
||||
{"напоминани", router.IntentReminder, "напоминание"},
|
||||
{"напомнить", router.IntentReminder, "напоминание"},
|
||||
{"факт", router.IntentFact, "факт"},
|
||||
{"вопрос", router.IntentQuery, "вопрос"},
|
||||
{"команд", router.IntentAct, "команда"},
|
||||
{"note", router.IntentNote, "заметка"},
|
||||
{"reminder", router.IntentReminder, "напоминание"},
|
||||
{"fact", router.IntentFact, "факт"},
|
||||
{"question", router.IntentQuery, "вопрос"},
|
||||
}
|
||||
|
||||
// parseRepair reads a spoken correction: a marker saying she was wrong, plus
|
||||
// the intent it should have been.
|
||||
//
|
||||
// The negated half is skipped. "это заметка, а не напоминание" names both
|
||||
// intents, and the one he is correcting TO is the one he did not put "не" in
|
||||
// front of.
|
||||
func parseRepair(utterance string) (router.Intent, string, bool) {
|
||||
s := strings.ToLower(strings.TrimSpace(utterance))
|
||||
if s == "" {
|
||||
return "", "", false
|
||||
}
|
||||
// A leading "нет" is a marker on its own — "нет, это заметка" is the
|
||||
// shortest correction he actually says. Only leading: "нет" in the middle
|
||||
// of a sentence is an ordinary word.
|
||||
marked := strings.HasPrefix(s, "нет") || strings.HasPrefix(s, "no,")
|
||||
for _, m := range repairMarkers {
|
||||
if marked || strings.Contains(s, m) {
|
||||
marked = true
|
||||
break
|
||||
}
|
||||
}
|
||||
if !marked {
|
||||
return "", "", false
|
||||
}
|
||||
best, say, at := router.Intent(""), "", -1
|
||||
for _, w := range repairIntents {
|
||||
i := strings.Index(s, w.word)
|
||||
if i < 0 || negatedAt(s, i) {
|
||||
continue
|
||||
}
|
||||
// Leftmost wins: "это заметка, а не напоминание" corrects to the first.
|
||||
if at < 0 || i < at {
|
||||
best, say, at = w.intent, w.say, i
|
||||
}
|
||||
}
|
||||
if at < 0 {
|
||||
return "", "", false
|
||||
}
|
||||
return best, say, true
|
||||
}
|
||||
|
||||
// negatedAt reports whether the word at i is the one he is ruling out. Only
|
||||
// the words immediately before it are read, so "не напоминание, а заметка"
|
||||
// negates the first and leaves the second alone.
|
||||
func negatedAt(s string, i int) bool {
|
||||
before := strings.TrimSpace(s[:i])
|
||||
return strings.HasSuffix(before, "не") || strings.HasSuffix(before, "not")
|
||||
}
|
||||
|
||||
// recordTurn keeps the utterance a correction would point at. Only turns she
|
||||
// acted on: a clarify asked instead of acting, so there is nothing yet to be
|
||||
// wrong about.
|
||||
func (h *reactiveHandler) recordTurn(utterance string, intent router.Intent) {
|
||||
h.mu.Lock()
|
||||
defer h.mu.Unlock()
|
||||
h.lastRouted = &routedTurn{utterance: utterance, intent: intent, at: h.now()}
|
||||
}
|
||||
|
||||
func (h *reactiveHandler) takeLastTurn() *routedTurn {
|
||||
h.mu.Lock()
|
||||
defer h.mu.Unlock()
|
||||
last := h.lastRouted
|
||||
// Taken, not read: one utterance is corrected once. Saying "нет, не так"
|
||||
// twice would otherwise redo the same request twice.
|
||||
h.lastRouted = nil
|
||||
return last
|
||||
}
|
||||
|
||||
// resolveRepair handles a spoken correction of the previous turn: teach the
|
||||
// classifier, redo the request under the corrected intent, and say so.
|
||||
func (h *reactiveHandler) resolveRepair(ctx context.Context, text string) (string, bool) {
|
||||
corrected, say, ok := parseRepair(text)
|
||||
if !ok || h.router == nil {
|
||||
return "", false
|
||||
}
|
||||
last := h.takeLastTurn()
|
||||
if last == nil || h.now().Sub(last.at) > repairWindow {
|
||||
return "", false
|
||||
}
|
||||
if last.intent == corrected {
|
||||
// She already did what he is asking for. Correcting the classifier
|
||||
// here would teach it the label it produced, and redoing the request
|
||||
// would file it twice.
|
||||
return "", false
|
||||
}
|
||||
learned := true
|
||||
if err := h.router.CorrectMisroute(ctx, last.utterance, corrected); err != nil {
|
||||
// The redo is still worth doing: he asked for something and it did not
|
||||
// happen. Only the learning half is lost, and he is told so.
|
||||
log.Printf("voice: repair: could not learn %q as %s: %v", last.utterance, corrected, err)
|
||||
learned = false
|
||||
}
|
||||
log.Printf("voice: repair — %q was %s, corrected to %s (learned=%v)", last.utterance, last.intent, corrected, learned)
|
||||
|
||||
dec := router.Decision{
|
||||
Utterance: last.utterance,
|
||||
Stage: 2,
|
||||
Intent: corrected,
|
||||
Slots: h.extractor.Extract(ctx, corrected, last.utterance, h.now()),
|
||||
}
|
||||
// A reminder's Text is what she says at the hour and stays empty when it
|
||||
// was not spoken, so the gap is asked about rather than filled with the
|
||||
// whole sentence. Everywhere else the utterance IS the payload.
|
||||
if dec.Slots.Text == "" && corrected != router.IntentReminder {
|
||||
dec.Slots.Text = last.utterance
|
||||
}
|
||||
return repairLine(say, learned) + " " + h.finishClarified(ctx, dec), true
|
||||
}
|
||||
|
||||
// repairLine — what she says before redoing it, so the correction is visible
|
||||
// and not just filed. Feminine, informal, no apology: he corrected a routing
|
||||
// call, he did not complain about her.
|
||||
func repairLine(say string, learned bool) string {
|
||||
if !learned {
|
||||
return "поняла, это " + say + " — переделываю, но запомнить поправку не вышло."
|
||||
}
|
||||
return "поняла, это " + say + " — запомнила."
|
||||
}
|
||||
@@ -0,0 +1,119 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
func TestParseRepairReadsTheCorrectedIntent(t *testing.T) {
|
||||
cases := []struct {
|
||||
utterance string
|
||||
want router.Intent
|
||||
ok bool
|
||||
}{
|
||||
{"нет, ты не поняла, это заметка", router.IntentNote, true},
|
||||
{"нет, это заметка", router.IntentNote, true},
|
||||
{"это не напоминание, а заметка", router.IntentNote, true},
|
||||
{"это заметка, а не напоминание", router.IntentNote, true},
|
||||
{"ты не так поняла — это факт", router.IntentFact, true},
|
||||
{"неправильно поняла, это был вопрос", router.IntentQuery, true},
|
||||
{"you got it wrong, that was a note", router.IntentNote, true},
|
||||
// No marker: an ordinary request that happens to name an intent.
|
||||
{"запиши заметку купить хлеб", "", false},
|
||||
{"напомни мне про заметку", "", false},
|
||||
// A marker with no intent named: nothing to correct to.
|
||||
{"ты не так поняла", "", false},
|
||||
{"", "", false},
|
||||
}
|
||||
for _, c := range cases {
|
||||
got, _, ok := parseRepair(c.utterance)
|
||||
if ok != c.ok || (ok && got != c.want) {
|
||||
t.Errorf("parseRepair(%q) = %q,%v; want %q,%v", c.utterance, got, ok, c.want, c.ok)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// TestRepairTeachesTheClassifierAndRedoesTheTurn is the whole feature: the
|
||||
// previous utterance is filed under the intent he named, the classifier keeps
|
||||
// it as an example, and he hears that it landed.
|
||||
func TestRepairTeachesTheClassifierAndRedoesTheTurn(t *testing.T) {
|
||||
h, st, now := newClarifyHandler(t)
|
||||
emb := router.NewHashEmbedder(256)
|
||||
cls := router.NewClassifier(emb)
|
||||
h.embedder = emb
|
||||
h.router = router.New(router.Config{Classifier: cls, Extractor: h.extractor})
|
||||
ctx := context.Background()
|
||||
|
||||
h.recordTurn("купить хлеб", router.IntentFact)
|
||||
reply, handled := h.resolveRepair(ctx, "нет, ты не поняла, это заметка")
|
||||
if !handled {
|
||||
t.Fatal("a spoken correction was not handled")
|
||||
}
|
||||
if !strings.Contains(reply, "заметка") {
|
||||
t.Errorf("the correction is not named out loud: %q", reply)
|
||||
}
|
||||
if strings.Contains(reply, "не вышло") {
|
||||
t.Errorf("learning failed unexpectedly: %q", reply)
|
||||
}
|
||||
|
||||
ex := cls.Examples(router.IntentNote)
|
||||
if len(ex) != 1 || ex[0].Text != "купить хлеб" {
|
||||
t.Fatalf("the classifier did not learn the correction: %+v", ex)
|
||||
}
|
||||
notes, err := st.RecentNotes(ctx, 5)
|
||||
if err != nil {
|
||||
t.Fatalf("recent notes: %v", err)
|
||||
}
|
||||
if len(notes) != 1 || !strings.Contains(notes[0].Text, "купить хлеб") {
|
||||
t.Fatalf("the request was not redone as a note: %+v", notes)
|
||||
}
|
||||
_ = now
|
||||
}
|
||||
|
||||
func TestRepairNeedsARecentTurnToPointAt(t *testing.T) {
|
||||
h, _, now := newClarifyHandler(t)
|
||||
h.router = router.New(router.Config{Classifier: router.NewClassifier(router.NewHashEmbedder(256))})
|
||||
ctx := context.Background()
|
||||
|
||||
// Nothing said yet.
|
||||
if _, handled := h.resolveRepair(ctx, "нет, это заметка"); handled {
|
||||
t.Error("a correction with no previous turn was handled")
|
||||
}
|
||||
// Said, but long ago.
|
||||
h.recordTurn("купить хлеб", router.IntentFact)
|
||||
*now = now.Add(repairWindow + time.Minute)
|
||||
if _, handled := h.resolveRepair(ctx, "нет, это заметка"); handled {
|
||||
t.Error("a correction outside the window was handled")
|
||||
}
|
||||
}
|
||||
|
||||
func TestRepairIsSpentOnce(t *testing.T) {
|
||||
h, _, _ := newClarifyHandler(t)
|
||||
emb := router.NewHashEmbedder(256)
|
||||
h.embedder = emb
|
||||
h.router = router.New(router.Config{Classifier: router.NewClassifier(emb), Extractor: h.extractor})
|
||||
ctx := context.Background()
|
||||
|
||||
h.recordTurn("купить хлеб", router.IntentFact)
|
||||
if _, handled := h.resolveRepair(ctx, "нет, это заметка"); !handled {
|
||||
t.Fatal("the first correction was not handled")
|
||||
}
|
||||
if _, handled := h.resolveRepair(ctx, "нет, это заметка"); handled {
|
||||
t.Error("the same turn was corrected twice")
|
||||
}
|
||||
}
|
||||
|
||||
// TestRepairPassesWhenSheAlreadyDidThat — he names the intent she used. There
|
||||
// is nothing to teach and redoing it would file the request a second time.
|
||||
func TestRepairPassesWhenSheAlreadyDidThat(t *testing.T) {
|
||||
h, _, _ := newClarifyHandler(t)
|
||||
h.router = router.New(router.Config{Classifier: router.NewClassifier(router.NewHashEmbedder(256))})
|
||||
h.recordTurn("купить хлеб", router.IntentNote)
|
||||
if _, handled := h.resolveRepair(context.Background(), "нет, это заметка"); handled {
|
||||
t.Error("a correction to the intent she already used was handled")
|
||||
}
|
||||
}
|
||||
@@ -161,6 +161,7 @@ type reactiveHandler struct {
|
||||
// the y/n answer. ponytail: single slot, single-user box — a second act
|
||||
// while one waits overwrites it (last-asked wins); expires after confirmTTL.
|
||||
mu sync.Mutex
|
||||
lastRouted *routedTurn // the previous acted turn, for a spoken correction (repair.go)
|
||||
pending *pendingAct
|
||||
pendingRoutine *pendingRoutineConfirm // routine proposal awaiting y/n
|
||||
pendingHexis *pendingHexisExec // mutating Hexis capability awaiting y/n
|
||||
@@ -299,6 +300,22 @@ func (h *reactiveHandler) runTurn(ctx context.Context, text string, src turnSour
|
||||
return withNotice(expiredNotice, reply)
|
||||
}
|
||||
|
||||
// 4d. spoken correction — "нет, это была заметка" points at the previous
|
||||
// turn and names what it should have been (repair.go). Before routing,
|
||||
// like the confirm and clarify turns: routing the correction as a fresh
|
||||
// utterance files the correction itself instead of fixing anything.
|
||||
if reply, handled := h.resolveRepair(ctx, text); handled {
|
||||
return withNotice(expiredNotice, reply)
|
||||
}
|
||||
|
||||
// 4e. ordinal selection — "второй", "первую сделал" pick from the list she
|
||||
// just read (ordinal.go). Before routing, and only when a list is actually
|
||||
// bound to the session: with nothing offered, "второй" is an ordinary word
|
||||
// and keeps routing.
|
||||
if reply, handled := h.resolveCandidate(ctx, text); handled {
|
||||
return withNotice(expiredNotice, reply)
|
||||
}
|
||||
|
||||
// 5. route. An elliptical follow-up — "а завтра?" — is answered from the
|
||||
// previous turn instead (continuation.go): the intent is the part it is
|
||||
// missing, so no amount of routing recovers it, and the model's guess
|
||||
@@ -359,6 +376,13 @@ func (h *reactiveHandler) runTurn(ctx context.Context, text string, src turnSour
|
||||
}
|
||||
}
|
||||
|
||||
// Remember what this turn was routed as, so the next utterance can correct
|
||||
// it. Only turns she acts on: a clarify asked instead of acting, so there
|
||||
// is nothing yet to be wrong about.
|
||||
if !dec.Clarify {
|
||||
h.recordTurn(text, dec.Intent)
|
||||
}
|
||||
|
||||
// 8. action — execute the decision's intent. errors here surface as
|
||||
// short reply text (the user wants to know the action didn't land);
|
||||
// the round-trip stays alive.
|
||||
|
||||
+14
-1
@@ -23,6 +23,7 @@ import (
|
||||
"syscall"
|
||||
|
||||
"github.com/kami/maven/internal/audio"
|
||||
"github.com/kami/maven/internal/tts"
|
||||
"github.com/kami/maven/internal/worker"
|
||||
)
|
||||
|
||||
@@ -39,15 +40,27 @@ func run(args []string) error {
|
||||
model := flag.String("model", "", "path to piper onnx model file")
|
||||
espeakData := flag.String("espeak_data", "", "path to espeak-ng data directory")
|
||||
tashkeelModel := flag.String("tashkeel_model", "", "path to libtashkeel onnx model")
|
||||
lexiconPath := flag.String("lexicon", "", "path to the pronunciation dictionary (json, name to spelling)")
|
||||
|
||||
flag.CommandLine.Parse(args)
|
||||
|
||||
ctx, stop := signal.NotifyContext(context.Background(), syscall.SIGINT, syscall.SIGTERM, syscall.SIGHUP)
|
||||
defer stop()
|
||||
|
||||
// Read before the handler is built: a dictionary he asked for and that
|
||||
// cannot be read is a startup failure, not a warning. Saying names wrong
|
||||
// in silence is the thing it exists to stop.
|
||||
lex, err := tts.LoadLexicon(*lexiconPath)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if lex.Size() > 0 {
|
||||
log.Printf("mavttsd: pronunciation dictionary: %d names from %s", lex.Size(), *lexiconPath)
|
||||
}
|
||||
|
||||
var s worker.Synthesizer
|
||||
if *piperBin != "" && *model != "" {
|
||||
s = newPiperHandler(*piperBin, *model, *espeakData, *tashkeelModel)
|
||||
s = newPiperHandler(*piperBin, *model, *espeakData, *tashkeelModel, lex)
|
||||
log.Printf("mavttsd: using piper tts (%s, model=%s)", *piperBin, *model)
|
||||
} else {
|
||||
log.Printf("mavttsd: no piper/model specified, using stub handler")
|
||||
|
||||
@@ -7,6 +7,7 @@ import (
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/audio"
|
||||
"github.com/kami/maven/internal/tts"
|
||||
"github.com/kami/maven/internal/worker"
|
||||
)
|
||||
|
||||
@@ -117,3 +118,18 @@ func abs(n int) int {
|
||||
}
|
||||
return n
|
||||
}
|
||||
|
||||
// The dictionary that ships in deploy/ must parse and must be non-empty. It is
|
||||
// data, so nothing else would catch a trailing comma before the voice did.
|
||||
func TestShippedLexiconLoads(t *testing.T) {
|
||||
lex, err := tts.LoadLexicon(filepath.Join("..", "..", "deploy", "tts-lexicon.json"))
|
||||
if err != nil {
|
||||
t.Fatalf("deploy/tts-lexicon.json: %v", err)
|
||||
}
|
||||
if lex.Size() < 10 {
|
||||
t.Errorf("shipped dictionary holds %d names, want the full list", lex.Size())
|
||||
}
|
||||
if got := lex.Apply("задача в Vikunja"); got == "задача в Vikunja" {
|
||||
t.Error("the shipped dictionary did not rewrite a name it lists")
|
||||
}
|
||||
}
|
||||
|
||||
@@ -9,6 +9,7 @@ import (
|
||||
"os/exec"
|
||||
|
||||
"github.com/kami/maven/internal/audio"
|
||||
"github.com/kami/maven/internal/tts"
|
||||
"github.com/kami/maven/internal/worker"
|
||||
)
|
||||
|
||||
@@ -18,15 +19,20 @@ type piperHandler struct {
|
||||
configPath string
|
||||
espeakData string
|
||||
tashkeelModel string
|
||||
// lexicon rewrites service ids and Latin names into the spelling the
|
||||
// Russian voice reads correctly (Vikunja #458). Nil-safe: an unconfigured
|
||||
// dictionary rewrites nothing.
|
||||
lexicon *tts.Lexicon
|
||||
}
|
||||
|
||||
func newPiperHandler(piperPath, modelPath, espeakData, tashkeelModel string) *piperHandler {
|
||||
func newPiperHandler(piperPath, modelPath, espeakData, tashkeelModel string, lexicon *tts.Lexicon) *piperHandler {
|
||||
return &piperHandler{
|
||||
piperPath: piperPath,
|
||||
modelPath: modelPath,
|
||||
configPath: modelPath + ".json",
|
||||
espeakData: espeakData,
|
||||
tashkeelModel: tashkeelModel,
|
||||
lexicon: lexicon,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -66,7 +72,14 @@ func (h *piperHandler) Synthesize(ctx context.Context, req worker.SynthesizeReq)
|
||||
return worker.SynthesizeResp{}, fmt.Errorf("piper: start: %w", err)
|
||||
}
|
||||
|
||||
if _, err := io.WriteString(stdin, req.Text); err != nil {
|
||||
// The dictionary is applied here, at the last edge before the voice: every
|
||||
// caller's text passes through this one point, and nothing upstream has to
|
||||
// know how a name is spelled out loud.
|
||||
text := req.Text
|
||||
if h.lexicon != nil {
|
||||
text = h.lexicon.Apply(text)
|
||||
}
|
||||
if _, err := io.WriteString(stdin, text); err != nil {
|
||||
stdin.Close()
|
||||
stdout.Close()
|
||||
_ = cmd.Wait()
|
||||
|
||||
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"Maven": "Мэйвен",
|
||||
"Nexus": "Нексус",
|
||||
"Praxis": "Праксис",
|
||||
"Hexis": "Хексис",
|
||||
"Vikunja": "Викунья",
|
||||
"SearXNG": "сёрчиксэнджи",
|
||||
"Kiwix": "Кивикс",
|
||||
"Gitea": "Гитея",
|
||||
"Home Assistant": "Хоум Ассистент",
|
||||
"Docker": "Докер",
|
||||
"Telegram": "Телеграм",
|
||||
"ntfy": "энтифай",
|
||||
"homesrv": "хоумсёрв",
|
||||
"workpc": "воркписи",
|
||||
"whisper": "виспер",
|
||||
"piper": "пайпер",
|
||||
"llama-server": "лама сервер",
|
||||
"Qwen": "Квен",
|
||||
"CalDAV": "калдав",
|
||||
"IMAP": "аймап",
|
||||
"API": "эй-пи-ай",
|
||||
"CPU": "си-пи-ю",
|
||||
"GPU": "джи-пи-ю",
|
||||
"RAM": "оперативная память",
|
||||
"SSD": "эс-эс-ди",
|
||||
"uptime": "аптайм",
|
||||
"backup": "бэкап",
|
||||
"deploy": "деплой"
|
||||
}
|
||||
@@ -223,6 +223,41 @@ Not alternatives — layers:
|
||||
Router contract: `[{"intent":<enum>, key?, value?, text?, verb?}, ...]` over
|
||||
7 intents (`fact, reminder, note, query, act, chat, system`).
|
||||
|
||||
#### "второй" points at the list she just read
|
||||
|
||||
Landed 2026-08-04 (Vikunja #448). The dialogue session carried the intent, the
|
||||
slots and the history, and not the list. She recited five tasks, he said
|
||||
"второй", and the word had nothing to point at.
|
||||
|
||||
`Session.Candidates` holds what she just offered, bound at the moment she speaks
|
||||
it and in the order she speaks it (`tasks.Spoken`). Binding afterwards would
|
||||
resolve the word against a fresh query, and the list changes between two turns.
|
||||
`cmd/mavend/ordinal.go` reads the position before routing and dispatches on the
|
||||
candidate's kind.
|
||||
|
||||
An ordinal with no verb is read back, not acted on — "второй" names a task, it
|
||||
does not say what to do with it. With a verb ("первую сделал", "последнюю
|
||||
убери") the task moves and the list is spent, because a second ordinal against a
|
||||
list that no longer holds closes the wrong work. A position she never read is
|
||||
answered with how many she did read, not routed as a fresh sentence.
|
||||
|
||||
#### Saying she got it wrong is a feature
|
||||
|
||||
Landed 2026-08-04 (Vikunja #455). `Router.CorrectMisroute` could always append a
|
||||
corrected utterance as a new classifier example, and until now nothing in the
|
||||
daemon called it, so the mechanism existed and the behaviour did not.
|
||||
|
||||
`cmd/mavend/repair.go` reaches it. He says she got it wrong and names what it
|
||||
should have been — "нет, это заметка", "это не напоминание, а факт" — and three
|
||||
things happen in one turn: the classifier learns the utterance under the named
|
||||
intent, the request is redone under it, and she says the correction landed. The
|
||||
utterance he is correcting TO is the one with no "не" in front of it.
|
||||
|
||||
Read before routing, next to the confirm and clarify turns, because a correction
|
||||
routed as a fresh utterance files the correction itself. One turn is correctable
|
||||
once, inside five minutes, and only turns she acted on — a clarify asked instead
|
||||
of acting, so there is nothing yet to be wrong about.
|
||||
|
||||
#### A restart expires a parked question
|
||||
|
||||
Decided 2026-08-04 (Vikunja #385). The follow-up dialogue session survives a
|
||||
|
||||
@@ -90,6 +90,13 @@ export LD_LIBRARY_PATH="$ROOT/deps/piper"
|
||||
|
||||
Without `-piper` it runs as a stub.
|
||||
|
||||
`-lexicon deploy/tts-lexicon.json` adds the pronunciation dictionary: a flat
|
||||
JSON object of name to Russian spelling, applied to the text just before piper
|
||||
reads it. It is how `Vikunja` is said as a word rather than spelled out, and how
|
||||
`SearXNG` and `homesrv` are said at all. Off unless the flag is set; a path that
|
||||
is set and unreadable stops mavttsd rather than letting it say names wrong in
|
||||
silence. Adding a name needs a restart of mavttsd and nothing else.
|
||||
|
||||
## mavweb — PWA voice bridge (WebSocket ↔ TCP)
|
||||
|
||||
No CGo, no deps; builds with stock Go.
|
||||
|
||||
@@ -15,7 +15,6 @@ require github.com/kami/hexis v0.0.0
|
||||
require (
|
||||
github.com/dustin/go-humanize v1.0.1 // indirect
|
||||
github.com/google/uuid v1.6.0 // indirect
|
||||
github.com/kami/praxis v0.0.0
|
||||
github.com/mattn/go-isatty v0.0.20 // indirect
|
||||
github.com/ncruces/go-strftime v1.0.0 // indirect
|
||||
github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec // indirect
|
||||
@@ -25,8 +24,4 @@ require (
|
||||
modernc.org/memory v1.11.0 // indirect
|
||||
)
|
||||
|
||||
replace github.com/kami/praxis v0.0.0 => /home/kami/apps/praxis
|
||||
|
||||
replace github.com/kami/nexus v0.0.0 => /home/kami/apps/nexus
|
||||
|
||||
replace github.com/kami/hexis v0.0.0 => /home/kami/apps/hexis
|
||||
|
||||
@@ -42,12 +42,27 @@ type Turn struct {
|
||||
Text string // raw utterance
|
||||
}
|
||||
|
||||
// Candidate — one item she just read out loud, kept so his next words can
|
||||
// pick it ("второй", "первую сделал"). Vikunja #448.
|
||||
//
|
||||
// Bound at the moment she speaks the list, not resolved afterwards: the list
|
||||
// can change between two turns, and "второй" means the second thing she said,
|
||||
// not the second row of a fresh query.
|
||||
type Candidate struct {
|
||||
Kind string // what it is, e.g. "task" — the resolver dispatches on this
|
||||
Ref int64 // the row it points at
|
||||
Label string // what she called it, so she can repeat it back
|
||||
}
|
||||
|
||||
type Session struct {
|
||||
Intent Intent
|
||||
Slots Slots
|
||||
Timestamp time.Time
|
||||
TTL time.Duration
|
||||
History []Turn // most recent turns, newest last; used for anaphora + cross-intent
|
||||
// Candidates — the list she just offered, in the order she said it. Empty
|
||||
// on every turn that offered no choice, which is most of them.
|
||||
Candidates []Candidate
|
||||
}
|
||||
|
||||
func (s *Session) IsExpired(now time.Time) bool {
|
||||
@@ -143,6 +158,26 @@ func (s *SessionStore) Put(id string, sess *Session) {
|
||||
s.save(id, sess)
|
||||
}
|
||||
|
||||
// SetCandidates attaches a just-spoken list to the live session.
|
||||
//
|
||||
// In place rather than through Put, because the turn was already remembered by
|
||||
// the time the answer was built: replacing the session here would drop the
|
||||
// slots the next follow-up inherits. No session, no candidates — a choice with
|
||||
// no turn behind it has nothing to be a choice about.
|
||||
func (s *SessionStore) SetCandidates(id string, now time.Time, cands []Candidate) {
|
||||
s.mu.Lock()
|
||||
sess, ok := s.sessions[id]
|
||||
if ok && !sess.IsExpired(now) {
|
||||
sess.Candidates = cands
|
||||
} else {
|
||||
ok = false
|
||||
}
|
||||
s.mu.Unlock()
|
||||
if ok {
|
||||
s.save(id, sess)
|
||||
}
|
||||
}
|
||||
|
||||
func (s *SessionStore) Delete(id string) {
|
||||
s.mu.Lock()
|
||||
delete(s.sessions, id)
|
||||
|
||||
@@ -2,6 +2,7 @@ package router
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"log"
|
||||
"time"
|
||||
)
|
||||
@@ -201,5 +202,10 @@ func (r *Router) gateLLMDecision(d *Decision) {
|
||||
// retrain). Same shape as nudges.outcome tuning cooldowns: more reliable over
|
||||
// time, introspectable, no model surgery.
|
||||
func (r *Router) CorrectMisroute(ctx context.Context, utterance string, corrected Intent) error {
|
||||
if r == nil || r.classifier == nil {
|
||||
// The LLM router can run with no classifier wired. The correction has
|
||||
// nowhere to land then, and the caller redoes the request anyway.
|
||||
return errors.New("router: no classifier to correct")
|
||||
}
|
||||
return r.classifier.AddExample(ctx, corrected, utterance)
|
||||
}
|
||||
|
||||
@@ -268,3 +268,26 @@ func pluralTasksRU(n int) string {
|
||||
}
|
||||
return "задач"
|
||||
}
|
||||
|
||||
// Spoken — the tasks FormatRU actually named, in the order it named them
|
||||
// (Vikunja #448). "второй" has to mean the second thing she said, so the list
|
||||
// an ordinal resolves against is built here and not by a caller guessing how
|
||||
// the renderer split and truncated it.
|
||||
func Spoken(ranked []Ranked) []Ranked {
|
||||
var open, cands []Ranked
|
||||
for _, r := range ranked {
|
||||
if r.Status == StatusCandidate {
|
||||
cands = append(cands, r)
|
||||
} else {
|
||||
open = append(open, r)
|
||||
}
|
||||
}
|
||||
out := make([]Ranked, 0, 2*SpokenLimit)
|
||||
for _, group := range [][]Ranked{open, cands} {
|
||||
if len(group) > SpokenLimit {
|
||||
group = group[:SpokenLimit]
|
||||
}
|
||||
out = append(out, group...)
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
@@ -0,0 +1,128 @@
|
||||
package tts
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"os"
|
||||
"regexp"
|
||||
"sort"
|
||||
"strings"
|
||||
)
|
||||
|
||||
// Pronunciation dictionary (Vikunja #458).
|
||||
//
|
||||
// piper reads a Russian sentence with a Russian voice, and a Latin service id
|
||||
// inside that sentence comes out as letters or as noise: "Vikunja" is spelled
|
||||
// out, "SearXNG" is unreadable, and "homesrv" is read as if it were a word. The
|
||||
// fix is not a code change per name — it is a file of replacements applied to
|
||||
// the text before piper sees it.
|
||||
//
|
||||
// Spelling, not phonemes. piper has no lexicon input of its own here, so the
|
||||
// only lever is the text, and the entry for a name is how it should be spelled
|
||||
// in Russian for the voice to say it right. That also means a wrong entry is
|
||||
// visible: it is a word, and it is read out loud.
|
||||
//
|
||||
// The dictionary is data, so it ships as a file rather than a table in Go. A
|
||||
// name added to it needs no rebuild and no deploy of the daemon that owns the
|
||||
// text — only a restart of mavttsd, which is the process that reads it.
|
||||
|
||||
// Lexicon rewrites names into the spelling the voice reads correctly.
|
||||
//
|
||||
// The zero value is usable and rewrites nothing, so a daemon with no dictionary
|
||||
// configured behaves exactly as it did before this existed.
|
||||
type Lexicon struct {
|
||||
// Rules are held in one alternation rather than as a map, so a text is
|
||||
// scanned once however many entries there are, and the longest name wins
|
||||
// where two overlap ("Home Assistant" before "Home").
|
||||
re *regexp.Regexp
|
||||
// by lower-cased name, because the match is case-insensitive and the
|
||||
// replacement is not derived from what was matched.
|
||||
by map[string]string
|
||||
}
|
||||
|
||||
// LoadLexicon reads a dictionary file: a flat JSON object of name to spelling.
|
||||
//
|
||||
// {"Vikunja": "Викунья", "SearXNG": "сёрчиксэнджи"}
|
||||
//
|
||||
// An empty path returns an empty Lexicon and no error — the dictionary is off
|
||||
// unless configured, like every other optional capability. A path that is set
|
||||
// and unreadable IS an error: he asked for it, and silently saying names wrong
|
||||
// is the failure this exists to remove.
|
||||
func LoadLexicon(path string) (*Lexicon, error) {
|
||||
if strings.TrimSpace(path) == "" {
|
||||
return &Lexicon{}, nil
|
||||
}
|
||||
raw, err := os.ReadFile(path)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("tts: lexicon %s: %w", path, err)
|
||||
}
|
||||
var entries map[string]string
|
||||
if err := json.Unmarshal(raw, &entries); err != nil {
|
||||
return nil, fmt.Errorf("tts: lexicon %s: %w", path, err)
|
||||
}
|
||||
return NewLexicon(entries), nil
|
||||
}
|
||||
|
||||
// NewLexicon builds a lexicon from entries already in memory.
|
||||
func NewLexicon(entries map[string]string) *Lexicon {
|
||||
names := make([]string, 0, len(entries))
|
||||
by := make(map[string]string, len(entries))
|
||||
for name, say := range entries {
|
||||
name = strings.TrimSpace(name)
|
||||
if name == "" || strings.TrimSpace(say) == "" {
|
||||
continue
|
||||
}
|
||||
names = append(names, name)
|
||||
by[strings.ToLower(name)] = say
|
||||
}
|
||||
if len(names) == 0 {
|
||||
return &Lexicon{}
|
||||
}
|
||||
// Longest first: "Home Assistant" must match before "Home" does, and Go's
|
||||
// regexp alternation is leftmost-first, not longest-match.
|
||||
sort.Slice(names, func(i, j int) bool { return len(names[i]) > len(names[j]) })
|
||||
quoted := make([]string, len(names))
|
||||
for i, n := range names {
|
||||
quoted[i] = regexp.QuoteMeta(n)
|
||||
}
|
||||
// The boundaries are written out rather than left to \b, which is ASCII-only
|
||||
// and never fires next to a Cyrillic letter — so "в Vikunja," would not
|
||||
// match with \b on the left in a Russian sentence.
|
||||
pattern := `(?i)(^|[^\p{L}\p{N}_])(` + strings.Join(quoted, "|") + `)($|[^\p{L}\p{N}_])`
|
||||
return &Lexicon{re: regexp.MustCompile(pattern), by: by}
|
||||
}
|
||||
|
||||
// Apply rewrites every name in the text. Text with no name in it comes back
|
||||
// unchanged and untouched.
|
||||
func (l *Lexicon) Apply(text string) string {
|
||||
if l == nil || l.re == nil || text == "" {
|
||||
return text
|
||||
}
|
||||
// Twice, because two names separated by a single space share the character
|
||||
// between them and one pass consumes it: "Nexus Praxis" would leave the
|
||||
// second name alone otherwise.
|
||||
out := l.replaceOnce(text)
|
||||
return l.replaceOnce(out)
|
||||
}
|
||||
|
||||
func (l *Lexicon) replaceOnce(text string) string {
|
||||
return l.re.ReplaceAllStringFunc(text, func(m string) string {
|
||||
groups := l.re.FindStringSubmatch(m)
|
||||
if groups == nil {
|
||||
return m
|
||||
}
|
||||
say, ok := l.by[strings.ToLower(groups[2])]
|
||||
if !ok {
|
||||
return m
|
||||
}
|
||||
return groups[1] + say + groups[3]
|
||||
})
|
||||
}
|
||||
|
||||
// Size reports how many names are loaded, for the startup log line.
|
||||
func (l *Lexicon) Size() int {
|
||||
if l == nil {
|
||||
return 0
|
||||
}
|
||||
return len(l.by)
|
||||
}
|
||||
@@ -0,0 +1,85 @@
|
||||
package tts
|
||||
|
||||
import (
|
||||
"os"
|
||||
"path/filepath"
|
||||
"testing"
|
||||
)
|
||||
|
||||
func TestLexiconRewritesNames(t *testing.T) {
|
||||
lex := NewLexicon(map[string]string{
|
||||
"Vikunja": "Викунья",
|
||||
"Home Assistant": "Хоум Ассистент",
|
||||
"Home": "Хоум",
|
||||
"GPU": "джи-пи-ю",
|
||||
})
|
||||
for _, tc := range []struct{ in, want string }{
|
||||
{"задача в Vikunja готова", "задача в Викунья готова"},
|
||||
// Case-insensitive: the router and the model both change the case of a
|
||||
// name on the way through.
|
||||
{"открой vikunja.", "открой Викунья."},
|
||||
// Longest first, or "Home Assistant" is read as "Хоум Assistant".
|
||||
{"Home Assistant не отвечает", "Хоум Ассистент не отвечает"},
|
||||
// Two names in a row share the space between them, which one pass
|
||||
// would consume.
|
||||
{"GPU GPU", "джи-пи-ю джи-пи-ю"},
|
||||
// Not a word boundary: a name inside a longer token is left alone.
|
||||
{"vikunjaless", "vikunjaless"},
|
||||
{"ничего не совпало", "ничего не совпало"},
|
||||
{"", ""},
|
||||
} {
|
||||
if got := lex.Apply(tc.in); got != tc.want {
|
||||
t.Errorf("Apply(%q) = %q, want %q", tc.in, got, tc.want)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// The zero value and an unconfigured path rewrite nothing, so a daemon with no
|
||||
// dictionary behaves as it did before this existed.
|
||||
func TestLexiconOffByDefault(t *testing.T) {
|
||||
var zero *Lexicon
|
||||
if got := zero.Apply("Vikunja"); got != "Vikunja" {
|
||||
t.Errorf("nil lexicon rewrote %q", got)
|
||||
}
|
||||
lex, err := LoadLexicon("")
|
||||
if err != nil {
|
||||
t.Fatalf("LoadLexicon(\"\"): %v", err)
|
||||
}
|
||||
if lex.Size() != 0 || lex.Apply("Vikunja") != "Vikunja" {
|
||||
t.Errorf("empty path produced a live lexicon of %d names", lex.Size())
|
||||
}
|
||||
}
|
||||
|
||||
// A path he set and that cannot be read is a startup failure. Saying names
|
||||
// wrong in silence is what the dictionary exists to stop.
|
||||
func TestLexiconLoadErrors(t *testing.T) {
|
||||
if _, err := LoadLexicon(filepath.Join(t.TempDir(), "nope.json")); err == nil {
|
||||
t.Error("a missing dictionary must be an error")
|
||||
}
|
||||
bad := filepath.Join(t.TempDir(), "bad.json")
|
||||
if err := os.WriteFile(bad, []byte("{not json"), 0o644); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, err := LoadLexicon(bad); err == nil {
|
||||
t.Error("an unparseable dictionary must be an error")
|
||||
}
|
||||
}
|
||||
|
||||
func TestLexiconRoundTripsAFile(t *testing.T) {
|
||||
path := filepath.Join(t.TempDir(), "lex.json")
|
||||
if err := os.WriteFile(path, []byte(`{"Praxis":"Праксис"," ":"skipped","Nexus":""}`), 0o644); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
lex, err := LoadLexicon(path)
|
||||
if err != nil {
|
||||
t.Fatalf("LoadLexicon: %v", err)
|
||||
}
|
||||
// Blank names and blank spellings are dropped: an entry that says nothing
|
||||
// would delete the word it matched.
|
||||
if lex.Size() != 1 {
|
||||
t.Fatalf("Size = %d, want 1", lex.Size())
|
||||
}
|
||||
if got := lex.Apply("Praxis молчит"); got != "Праксис молчит" {
|
||||
t.Errorf("Apply = %q", got)
|
||||
}
|
||||
}
|
||||
Vendored
-3
@@ -15,8 +15,6 @@ github.com/google/uuid
|
||||
# github.com/kami/hexis v0.0.0 => /home/kami/apps/hexis
|
||||
## explicit; go 1.25.5
|
||||
github.com/kami/hexis/pkg/client
|
||||
# github.com/kami/praxis v0.0.0 => /home/kami/apps/praxis
|
||||
## explicit; go 1.23
|
||||
# github.com/mattn/go-isatty v0.0.20
|
||||
## explicit; go 1.15
|
||||
github.com/mattn/go-isatty
|
||||
@@ -79,4 +77,3 @@ modernc.org/memory
|
||||
modernc.org/sqlite
|
||||
modernc.org/sqlite/lib
|
||||
modernc.org/sqlite/vtab
|
||||
# github.com/kami/nexus v0.0.0 => /home/kami/apps/nexus
|
||||
|
||||
Reference in New Issue
Block a user