Compare commits
10 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| cc32c2c4ab | |||
| a1e97c94ac | |||
| c7f59e48f4 | |||
| 50c6637c1b | |||
| ee9d55ca95 | |||
| a886217223 | |||
| de9884e063 | |||
| bbefda66e2 | |||
| a37c4138a1 | |||
| d6f391430f |
+12
-2
@@ -489,15 +489,19 @@ func (h *reactiveHandler) noteSuspended(ctx context.Context, q *dialogue.Pending
|
||||
if !q.CanResume() {
|
||||
h.clarifyStore.Delete(dialogueIDOf(ctx))
|
||||
h.noteDropped(ctx)
|
||||
log.Printf("voice: clarify — the question about %s stepped aside %d times; letting the request go", q.Missing[0], q.Suspends)
|
||||
log.Printf("voice: clarify — letting the question about %s go: %d asides in a row, %d rides in all", q.Missing[0], q.Suspends, q.Rides)
|
||||
return
|
||||
}
|
||||
q.Suspends++
|
||||
// Rides is the same event counted without the reset (V-663). Incremented
|
||||
// beside Suspends and never anywhere else, so the two cannot disagree about
|
||||
// what happened, only about how much of it they remember.
|
||||
q.Rides++
|
||||
q.Asked = h.now()
|
||||
h.clarifyStore.Put(dialogueIDOf(ctx), q)
|
||||
rt.resume = question
|
||||
rt.suspended = true
|
||||
log.Printf("voice: clarify — is its own request; suspending the question about %s and resuming it in the same reply (suspend %d of %d)", q.Missing[0], q.Suspends, dialogue.MaxSuspends)
|
||||
log.Printf("voice: clarify — is its own request; suspending the question about %s and resuming it in the same reply (suspend %d of %d, ride %d of %d)", q.Missing[0], q.Suspends, dialogue.MaxSuspends, q.Rides, dialogue.MaxRides)
|
||||
}
|
||||
|
||||
// foldAnswerIntoUtterance appends an answered subject to the original words,
|
||||
@@ -540,6 +544,11 @@ func (h *reactiveHandler) askRemainingGap(ctx context.Context, q *dialogue.Pendi
|
||||
// Suspends is not carried, and by this point it is already zero: the answer
|
||||
// path resets it (V-654). Left off the literal so the zero is stated where
|
||||
// the struct is built, rather than inherited from a field nobody names.
|
||||
//
|
||||
// Rides IS carried, and that is the whole point of it (V-663). This is the
|
||||
// same request under a second question, not a new one, so the turns it has
|
||||
// already ridden still count against it. Dropping the field here is exactly
|
||||
// the re-basing that let one question ride twenty-six replies.
|
||||
h.clarifyStore.Put(dialogueIDOf(ctx), &dialogue.PendingQuestion{
|
||||
Intent: q.Intent,
|
||||
Slots: merged,
|
||||
@@ -550,6 +559,7 @@ func (h *reactiveHandler) askRemainingGap(ctx context.Context, q *dialogue.Pendi
|
||||
TTL: clarifyTTL,
|
||||
Attempts: q.Attempts + 1,
|
||||
MaxAttempts: q.MaxAttempts,
|
||||
Rides: q.Rides,
|
||||
})
|
||||
log.Printf("voice: clarify — one gap filled, still missing %s for intent=%s, asking again (attempt %d)", remaining[0], intent, q.Attempts+1)
|
||||
return question, true
|
||||
|
||||
@@ -0,0 +1,43 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/config"
|
||||
"github.com/kami/maven/internal/stt"
|
||||
)
|
||||
|
||||
// A box with no workstation.stt block transcribes exactly as it did before the
|
||||
// seam existed: the floor is handed back untouched, and nothing probes.
|
||||
func TestSttSeamWithNoBlockIsTheFloor(t *testing.T) {
|
||||
floor := stt.NewStub()
|
||||
got, pair := sttSeam(&config.Config{}, floor)
|
||||
if pair != nil {
|
||||
t.Fatal("no block must build no pair")
|
||||
}
|
||||
if got != stt.Transcriber(floor) {
|
||||
t.Fatal("no block must hand back the floor itself")
|
||||
}
|
||||
}
|
||||
|
||||
func TestSttSeamPrefersTheWorkstation(t *testing.T) {
|
||||
cfg := &config.Config{Workstation: &config.WorkstationConfig{
|
||||
URL: "http://127.0.0.1:1",
|
||||
Stt: &config.WorkstationSttConfig{
|
||||
URL: "http://127.0.0.1:2/transcribe",
|
||||
Health: "http://127.0.0.1:2/health",
|
||||
},
|
||||
}}
|
||||
got, pair := sttSeam(cfg, stt.NewStub())
|
||||
if pair == nil {
|
||||
t.Fatal("a configured block must build a pair")
|
||||
}
|
||||
defer pair.Stop()
|
||||
if got != stt.Transcriber(pair) {
|
||||
t.Fatal("the pair is what callers must transcribe through")
|
||||
}
|
||||
// Nothing answers on port 2, so the seam is the floor until it does.
|
||||
if pair.Available() {
|
||||
t.Fatal("an unreachable workstation must not be available")
|
||||
}
|
||||
}
|
||||
@@ -186,6 +186,28 @@ func carriesReminderVerb(text string) bool {
|
||||
return false
|
||||
}
|
||||
|
||||
// isPleasantry matches the WHOLE utterance against lexicon.Pleasantries, after
|
||||
// lowercasing and dropping the punctuation a greeting carries.
|
||||
//
|
||||
// Whole utterance and not tokens. Every token rule tried here was wrong on
|
||||
// something: "вечер" answers "это утра или вечера?", "нет" answers a confirm,
|
||||
// and "спокойной" alone is not an utterance at all. A greeting is a fixed
|
||||
// phrase, so matching it as one costs nothing and claims nothing else.
|
||||
func isPleasantry(text string) bool {
|
||||
t := strings.ToLower(strings.TrimSpace(text))
|
||||
t = strings.Trim(t, " .,!?…")
|
||||
t = strings.Join(strings.Fields(t), " ")
|
||||
if t == "" {
|
||||
return false
|
||||
}
|
||||
for _, p := range lexicon.Pleasantries() {
|
||||
if t == p {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// offlineOwnRequest is the shape half of the evidence: the offline token tests,
|
||||
// which cost nothing and never depend on the model that produced the routing.
|
||||
// It is also the whole answer when there is no route to read — the classifier
|
||||
@@ -225,6 +247,16 @@ func classifyTurnRole(q *dialogue.PendingQuestion, text string, answer dialogue.
|
||||
// hour, and no route saying "question" changes that. It works because the
|
||||
// extractor no longer reads a day word as the current clock, so a sentence
|
||||
// that names no hour now fills nothing to weigh.
|
||||
// A pleasantry is neither (V-663). "спасибо" and "привет" fell through to
|
||||
// roleAnswer, so a question about a reminder's DAY was re-asked at a man
|
||||
// saying thank you, and the retry it spent was one of the three bounds
|
||||
// meant to end the ride. It is an aside: answered as itself, the question
|
||||
// resumed on the tail, no attempt spent, one ride counted. Placed above the
|
||||
// content gate because "доброе утро" has content and states nothing, so
|
||||
// neither half of the evidence below can reach it.
|
||||
if q != nil && isPleasantry(text) {
|
||||
return roleAside
|
||||
}
|
||||
own := false
|
||||
if len(ownContent(text)) > 0 {
|
||||
own = offlineOwnRequest(text) || (ok && carriesOwnRequest(routed, text))
|
||||
|
||||
@@ -372,4 +372,69 @@ func TestAnAnsweredGapResetsTheSuspendBudget(t *testing.T) {
|
||||
if q.Suspends != 0 {
|
||||
t.Fatalf("answering a gap must reset the suspend budget: suspends = %d", q.Suspends)
|
||||
}
|
||||
// The ride it already took is carried across the re-park (V-663). Resetting
|
||||
// both counters here is what let one question ride twenty-six replies.
|
||||
if q.Rides != 1 {
|
||||
t.Fatalf("the aside it already took was forgotten: rides = %d", q.Rides)
|
||||
}
|
||||
}
|
||||
|
||||
// TestTwoBoundsCannotRearmEachOther — V-663.
|
||||
//
|
||||
// MaxSuspends landed and the measurement did not move: twenty-six of 140 turns
|
||||
// carried a tail before it and twenty-six after. This is the shape it misses,
|
||||
// taken from the 2026-08-08 run, where one question rode turns 7 to 13.
|
||||
//
|
||||
// An aside spends no attempt, so MaxAttempts never reaches it. A turn that
|
||||
// reads as a failed answer zeroes Suspends, so MaxSuspends never reaches the
|
||||
// asides either. Alternating the two rearms each bound with the other's
|
||||
// traffic. Rides counts both kinds and is never reset, so it is what ends this.
|
||||
func TestTwoBoundsCannotRearmEachOther(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, _ := newRoutingClarifyHandler(t)
|
||||
id := dialogueIDFor(sourceText, "web")
|
||||
resumed, _ := clarifyResumedFor(dialogue.SlotTime)
|
||||
|
||||
if reply := h.handleText(ctx, "web", "напомни позвонить маме"); !strings.Contains(reply, "?") {
|
||||
t.Fatalf("expected the time question, got %q", reply)
|
||||
}
|
||||
|
||||
// Two asides. Each one rides and neither spends an attempt.
|
||||
for i := 0; i < 2; i++ {
|
||||
reply := h.handleText(ctx, "web", "какие у меня напоминания?")
|
||||
if !strings.HasSuffix(reply, resumed) {
|
||||
t.Fatalf("aside %d: the question must come back, got %q", i+1, reply)
|
||||
}
|
||||
}
|
||||
q := h.clarifyStore.Get(id, h.now())
|
||||
if q == nil || q.Rides != 2 || q.Suspends != 2 {
|
||||
t.Fatalf("after two asides: %+v", q)
|
||||
}
|
||||
|
||||
// A pleasantry. It used to read as a failed answer, so she re-asked the
|
||||
// question at a man saying thank you and spent an attempt doing it. Now it
|
||||
// is an aside: answered as itself, question on the tail, one more ride.
|
||||
reply := h.handleText(ctx, "web", "спасибо")
|
||||
if !strings.HasSuffix(reply, resumed) {
|
||||
t.Fatalf("a pleasantry lost the parked question: %q", reply)
|
||||
}
|
||||
q = h.clarifyStore.Get(id, h.now())
|
||||
if q == nil || q.Attempts != 1 {
|
||||
t.Fatalf("a pleasantry spent an attempt: %+v", q)
|
||||
}
|
||||
if q.Rides != 3 {
|
||||
t.Fatalf("a pleasantry rode free: %+v", q)
|
||||
}
|
||||
|
||||
// One more ride of any kind and the request goes, out loud.
|
||||
reply = h.handleText(ctx, "web", "какие у меня напоминания?")
|
||||
if !strings.Contains(reply, clarifyDropped) {
|
||||
t.Fatalf("the question rode four asides and was let go in silence: %q", reply)
|
||||
}
|
||||
if strings.HasSuffix(reply, resumed) {
|
||||
t.Fatalf("a question she has let go must not be asked again: %q", reply)
|
||||
}
|
||||
if h.clarifyStore.Get(id, h.now()) != nil {
|
||||
t.Fatal("the question must be gone once she has said she let it go")
|
||||
}
|
||||
}
|
||||
|
||||
+47
-1
@@ -53,7 +53,11 @@ type voiceWiring struct {
|
||||
// unless a `workstation` block names an address. Held here only so the
|
||||
// prober is stopped on shutdown; callers were handed it at build time.
|
||||
pair *llm.Pair
|
||||
mcp *mcpWiring
|
||||
// sttPair — CrisperWhisper 2.0 on the workstation with mavsttd as the
|
||||
// floor, nil unless the `workstation.stt` block names an address. Held for
|
||||
// the same reason as pair: to stop its prober on shutdown.
|
||||
sttPair *stt.Pair
|
||||
mcp *mcpWiring
|
||||
// home — the Home Assistant client, nil unless the `smarthome` block is
|
||||
// enabled (Vikunja #256). Its devices land in the same allowlist as every
|
||||
// other act, so nothing else here has to know about it.
|
||||
@@ -84,6 +88,9 @@ func (w *voiceWiring) close() {
|
||||
if w.pair != nil {
|
||||
w.pair.Stop()
|
||||
}
|
||||
if w.sttPair != nil {
|
||||
w.sttPair.Stop()
|
||||
}
|
||||
w.mcp.close()
|
||||
}
|
||||
|
||||
@@ -112,6 +119,7 @@ func wireVoice(cfg *config.Config, coreAPI ipc.CoreAPI, phr phraser.Phraser, mem
|
||||
} else {
|
||||
transcriber = stt.NewStub()
|
||||
}
|
||||
transcriber, w.sttPair = sttSeam(cfg, transcriber)
|
||||
w.transcriber = transcriber
|
||||
|
||||
// ----- tts (Stub in-process OR Remote) -----
|
||||
@@ -366,6 +374,44 @@ func modelSeam(cfg *config.Config, resident *llm.Client) (router.Completer, *llm
|
||||
return pair, pair
|
||||
}
|
||||
|
||||
// sttSeam builds the transcription seam the voice path and the meeting
|
||||
// recorder share. It is modelSeam for audio and follows the same rule.
|
||||
//
|
||||
// With no `workstation.stt` block it hands back the floor untouched, which is
|
||||
// today's deploy exactly. With one, it is an stt.Pair preferring CrisperWhisper
|
||||
// 2.0 on workpc, which scores 10.4% WER in Russian against the floor's 27.5%
|
||||
// (docs/evals/2026-08-09-crisperwhisper2-russian-wer.md).
|
||||
//
|
||||
// Only the silent half of the degradation rule applies here. A worse transcript
|
||||
// is still a turn, so there is nothing to name a gap about and the fallback is
|
||||
// never spoken. That is why stt.Pair has no TranscribeRemote.
|
||||
func sttSeam(cfg *config.Config, floor stt.Transcriber) (stt.Transcriber, *stt.Pair) {
|
||||
if cfg.Workstation == nil || cfg.Workstation.Stt == nil {
|
||||
return floor, nil
|
||||
}
|
||||
s := cfg.Workstation.Stt
|
||||
lang := ""
|
||||
if cfg.Voice != nil {
|
||||
lang = cfg.Voice.Lang
|
||||
if cfg.Voice.Stt != nil && cfg.Voice.Stt.Lang != "" {
|
||||
lang = cfg.Voice.Stt.Lang
|
||||
}
|
||||
}
|
||||
pair := stt.NewPair(
|
||||
stt.NewHTTPTranscriber(s.URL, s.Token, lang, time.Duration(s.Timeout)),
|
||||
floor,
|
||||
s.Health,
|
||||
time.Duration(s.Probe),
|
||||
)
|
||||
pair.Start(context.Background())
|
||||
if s.Token == "" {
|
||||
log.Print("voice: the workstation transcriber has no token, so anything on the LAN can post audio to it")
|
||||
}
|
||||
log.Printf("voice: workstation transcriber at %s, probed every %s, mavsttd as the floor",
|
||||
s.URL, time.Duration(s.Probe))
|
||||
return pair, pair
|
||||
}
|
||||
|
||||
func pickLLMRouter(enabled bool, c router.Completer) *router.LLMRouter {
|
||||
if !enabled {
|
||||
return nil
|
||||
|
||||
@@ -308,6 +308,29 @@ The count is of CONSECUTIVE step-asides. It resets the moment he answers, in
|
||||
too. "Позвонить маме" against a question about the time is still him in the
|
||||
exchange. The retry it costs is bound enough on its own.
|
||||
|
||||
#### And it may ride four turns in all
|
||||
|
||||
Decided 2026-08-08 (V-663), because the bound above did not move the number it
|
||||
was written for. Twenty-six of 140 turns carried a tail before it landed and
|
||||
twenty-six carried one after.
|
||||
|
||||
Two bounds rearm each other. An aside spends no attempt, so `MaxAttempts` never
|
||||
reaches it. A turn that reads as a failed answer zeroes `Suspends`, so
|
||||
`MaxSuspends` never reaches the asides. Alternating them, each bound is restored
|
||||
by the other's traffic. Measured on 2026-08-08: one question about a reminder's
|
||||
day rode turns 7 to 13. It ended only because turn 14 was a new request.
|
||||
|
||||
`PendingQuestion.Rides` counts the same event as `Suspends` with the resets
|
||||
taken out. It is set once, incremented only in `noteSuspended`, carried across
|
||||
the re-park in `askRemainingGap`, and read by nothing that could lower it.
|
||||
`MaxRides` is 4, one looser than `MaxSuspends` so that the tighter statement
|
||||
about a run stays reachable.
|
||||
|
||||
This is a bound, not a cure. It ends the measured ride one turn early. Most of
|
||||
that ride's length is attempts, spent because `classifyTurnRole` reads "спасибо"
|
||||
and "привет" as failed answers to a question about a day. That is the next
|
||||
thing to fix and it is not a bound.
|
||||
|
||||
The re-ask is also two sentences rather than one. It used to be spliced onto the
|
||||
answer with a comma. On a real answer that buries the question in the tail of
|
||||
one run-on thought:
|
||||
|
||||
@@ -0,0 +1,88 @@
|
||||
# The parked clarify ride, bounded and re-measured
|
||||
|
||||
Date: 2026-08-08, V-663. Same 140 turns, same driver, third and fourth runs of
|
||||
the day. Before is `d6f3914`, after is that plus two changes.
|
||||
|
||||
## What was measured before
|
||||
|
||||
One question about a reminder's day rode turns 6 to 13. It ended only because
|
||||
turn 14 was a new request. Two of those turns are the worst replies in the
|
||||
corpus:
|
||||
|
||||
```text
|
||||
спасибо -> Сейчас 21:25. В какой день?
|
||||
привет -> Сейчас 21:25. В какой день?
|
||||
```
|
||||
|
||||
V-654 had already added `MaxSuspends` and the tail count had not moved.
|
||||
|
||||
## Why three bounds let it happen
|
||||
|
||||
The TTL, `MaxAttempts` and `MaxSuspends` all exist and all were rearmed.
|
||||
|
||||
An aside spends no attempt, so `MaxAttempts` never reaches it. A turn reading as
|
||||
a failed answer zeroes `Suspends`, so `MaxSuspends` never reaches the asides.
|
||||
`спасибо` read as a failed answer. So the pleasantry both produced the reply
|
||||
above and paid for it out of the budget meant to end the ride.
|
||||
|
||||
## The two changes
|
||||
|
||||
`PendingQuestion.Rides` counts the same event as `Suspends` with the resets
|
||||
taken out. Set once, incremented only in `noteSuspended`, carried across the
|
||||
re-park in `askRemainingGap`. `MaxRides` is 4, one looser than `MaxSuspends` so
|
||||
that the tighter statement about a run stays reachable.
|
||||
|
||||
A pleasantry is an aside, not a failed answer. The set is a new closed lexicon
|
||||
entry, matched as whole utterances rather than tokens. `вечер` answers `это утра
|
||||
или вечера?` and `нет` answers a confirm. Anything that could fill a slot stays
|
||||
out.
|
||||
|
||||
## Result
|
||||
|
||||
| | before | after |
|
||||
|---|---|---|
|
||||
| turns carrying a clarify tail | 21 | 17 |
|
||||
| turns carrying any failure string | 31 | 29 |
|
||||
| the longest ride | 8 turns | 4 turns |
|
||||
|
||||
The turns carrying a tail, by number:
|
||||
|
||||
```text
|
||||
before 6 7 8 9 10 11 12 13 53 54 55 56 57 99 102 103 116 136 137 138 139
|
||||
after 6 7 8 9 53 54 55 56 57 99 100 101 116 136 137 138 139
|
||||
```
|
||||
|
||||
Turn 10 is the change. It now reads:
|
||||
|
||||
```text
|
||||
спасибо -> Прошлую просьбу отпускаю. Пожалуйста, я всегда готова помочь тебе.
|
||||
```
|
||||
|
||||
She lets the request go, says so, and answers the man. Turns 11 to 13 are clean.
|
||||
|
||||
**`MaxRides` is not what fired.** The pleasantry is an aside now, so it no
|
||||
longer breaks the run. `MaxSuspends` reached three on turn 10 and ended it.
|
||||
`Rides` is the backstop for the shape where an answer really does break the run.
|
||||
No turn in this corpus reaches it.
|
||||
|
||||
## What did not move
|
||||
|
||||
Four rides are untouched. Turns 53 to 57 are five consecutive asides against a
|
||||
reminder missing its day. Turn 58 is a new request that drops it. Nothing
|
||||
pleasant appears in that run, so neither change applies. Turns 99 to 101 shifted
|
||||
by one, and 116 and 136 to 139 are unchanged.
|
||||
|
||||
So the fix is worth four turns of twenty-one. What is left is asides against a
|
||||
question the owner never answers. `MaxSuspends` was written for that shape and
|
||||
does bound it, at four turns each.
|
||||
|
||||
## Not attributable
|
||||
|
||||
Latency moved p50 1.1s to 1.5s and p95 2.8s to 3.0s, and the 34.3s outlier in
|
||||
the earlier run is gone. Both runs had the workstation up. Read none of it as
|
||||
caused by this change.
|
||||
|
||||
One unrelated defect appeared in the after run and is recorded here because it
|
||||
is visible in the transcript. Turn 4 answered `Я записала твою привычкуRegarding
|
||||
coffee without sugar.` That is English leaking into a Russian reply with no
|
||||
space in front of it. It is a phrasing defect and it has no task yet.
|
||||
@@ -80,12 +80,53 @@ V-655 was never going to touch this. A parked clarify is dialogue state and not
|
||||
a query source. It remains the single worst thing about talking to her. The week test, the
|
||||
fortnight test and this re-run all report it unchanged.
|
||||
|
||||
## A gap in the harness
|
||||
## A gap in the harness, fixed and re-run the same day
|
||||
|
||||
`ipc.ChatReply.Source` came back empty on all 140 turns, in both runs. The
|
||||
driver reads it from the redirect query string and there is nothing there. So
|
||||
the badge that says which query source claimed a turn is invisible to the
|
||||
harness, and every finding above is read off the reply text instead.
|
||||
driver read the redirect parameter `src` and `cmd/mavweb/chat.go` writes `s`.
|
||||
So every finding above is read off the reply text instead of off the badge.
|
||||
|
||||
That is worth fixing before the next re-run. Reading the source directly would
|
||||
have shown the two homelab misses without inferring them from the wording.
|
||||
Fixed in V-662 and the 140 turns were driven a third time. Sixty-eight of them
|
||||
name a source. The rest are not query turns and never reach `queryWalk`.
|
||||
|
||||
| source | turns |
|
||||
|---|---|
|
||||
| search | 27 |
|
||||
| memory | 13 |
|
||||
| personal | 9 |
|
||||
| weather | 5 |
|
||||
| calendar | 3 |
|
||||
| attention | 3 |
|
||||
| list | 2 |
|
||||
| feeds | 2 |
|
||||
| tasks, money, self, habits | 1 each |
|
||||
|
||||
## What the badge shows that the wording did not
|
||||
|
||||
The two unfixed homelab turns are now direct evidence.
|
||||
|
||||
```text
|
||||
какая скорость у меня сейчас? -> weather
|
||||
хватает ли места под новые бэкапы? -> feeds
|
||||
```
|
||||
|
||||
Both are guessing sources claiming a turn about the box, exactly as the
|
||||
destination fixture predicted.
|
||||
|
||||
The badge also names a defect the wording hid. **Agenda questions are being
|
||||
claimed by the personal boundary and by Praxis, not by the calendar.**
|
||||
|
||||
```text
|
||||
во сколько у меня встреча? -> personal не нашла у тебя такой записи
|
||||
когда у меня встреча? -> attention у Praxis нет источников
|
||||
что у меня в понедельник? -> personal не нашла у тебя такой записи
|
||||
```
|
||||
|
||||
Calendar claimed 3 turns of the 6 that asked about the calendar. That is the
|
||||
same 3/6 the destination fixture scores and the same 3/6 every seed of the
|
||||
routing head scores. Three measurements agree. The cause is the one V-660 named. The possessive
|
||||
agenda rules claim these at stage 0 and name no destination, so the walk
|
||||
reaches `personal` and `attention` first.
|
||||
|
||||
This is the third independent confirmation that the possessive agenda rules
|
||||
should name the calendar. That call is still the owner's.
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
package config
|
||||
|
||||
import (
|
||||
"net/url"
|
||||
"strings"
|
||||
"time"
|
||||
)
|
||||
@@ -35,12 +36,54 @@ type WorkstationConfig struct {
|
||||
// 0 ⇒ DefaultWorkstationTimeout. A big model on a LAN host is slower than
|
||||
// the resident one, and a request that overruns falls back to the floor.
|
||||
Timeout Duration `json:"timeout,omitempty"`
|
||||
|
||||
// Stt — CrisperWhisper 2.0 on the same machine, a separate service on its
|
||||
// own port. Absent ⇒ every utterance goes to mavsttd, which is today.
|
||||
Stt *WorkstationSttConfig `json:"stt,omitempty"`
|
||||
}
|
||||
|
||||
// WorkstationSttConfig — speech-to-text on the workstation.
|
||||
//
|
||||
// It is a second service and not a second endpoint on mavgpud: whisper.cpp
|
||||
// cannot load CrisperWhisper 2.0 at all, because it derives its language count
|
||||
// from the vocabulary size and CW2's 51897 tokens shift seven special token
|
||||
// ids. So CW2 runs under transformers, and this block addresses it.
|
||||
//
|
||||
// Worth the trouble: CW2 turbo scores 10.4% WER in Russian against 27.5% for
|
||||
// the ggml-small.bin homesrv loads
|
||||
// (docs/evals/2026-08-09-crisperwhisper2-russian-wer.md).
|
||||
type WorkstationSttConfig struct {
|
||||
// URL — the transcribe endpoint, e.g.
|
||||
// "http://192.168.1.105:8081/transcribe". Empty ⇒ the block is normalised
|
||||
// to nil and mavsttd takes every turn.
|
||||
URL string `json:"url,omitempty"`
|
||||
|
||||
// Health — the admission endpoint. Empty ⇒ the URL's origin + "/health".
|
||||
// It answers 503 while the card is held, and that is the signal.
|
||||
Health string `json:"health,omitempty"`
|
||||
|
||||
// Token — the bearer token the service checks. Audio is the most sensitive
|
||||
// thing that crosses this seam, so a LAN deployment should set one. Write
|
||||
// it as ${MAVEN_STT_TOKEN} and keep the value in deploy/telegram.env, the
|
||||
// way every other secret in this file is written.
|
||||
Token string `json:"token,omitempty"`
|
||||
|
||||
// Probe — how often admission is re-checked. 0 ⇒ DefaultWorkstationProbe.
|
||||
Probe Duration `json:"probe,omitempty"`
|
||||
|
||||
// Timeout — the per-request budget for one utterance. 0 ⇒
|
||||
// DefaultWorkstationSttTimeout. A request that overruns falls back to
|
||||
// mavsttd, which costs a worse transcript and not the turn.
|
||||
Timeout Duration `json:"timeout,omitempty"`
|
||||
}
|
||||
|
||||
// Workstation defaults, applied in normaliseWorkstation.
|
||||
const (
|
||||
DefaultWorkstationProbe = 15 * time.Second
|
||||
DefaultWorkstationTimeout = 90 * time.Second
|
||||
// One utterance, not one completion. A voice turn waits on this, so the
|
||||
// budget is a few seconds and not a minute and a half.
|
||||
DefaultWorkstationSttTimeout = 10 * time.Second
|
||||
)
|
||||
|
||||
// normaliseWorkstation applies the block's defaults. No address, no preferred
|
||||
@@ -63,4 +106,36 @@ func (c *Config) normaliseWorkstation() {
|
||||
if w.Timeout <= 0 {
|
||||
w.Timeout = Duration(DefaultWorkstationTimeout)
|
||||
}
|
||||
normaliseWorkstationStt(w)
|
||||
}
|
||||
|
||||
// normaliseWorkstationStt applies the speech-to-text block's defaults. No
|
||||
// address, no remote: mavsttd then takes every utterance, which is today.
|
||||
func normaliseWorkstationStt(w *WorkstationConfig) {
|
||||
if w.Stt != nil && strings.TrimSpace(w.Stt.URL) == "" {
|
||||
w.Stt = nil
|
||||
}
|
||||
if w.Stt == nil {
|
||||
return
|
||||
}
|
||||
s := w.Stt
|
||||
if strings.TrimSpace(s.Health) == "" {
|
||||
s.Health = healthOrigin(s.URL)
|
||||
}
|
||||
if s.Probe <= 0 {
|
||||
s.Probe = Duration(DefaultWorkstationProbe)
|
||||
}
|
||||
if s.Timeout <= 0 {
|
||||
s.Timeout = Duration(DefaultWorkstationSttTimeout)
|
||||
}
|
||||
}
|
||||
|
||||
// healthOrigin derives the admission endpoint from the transcribe endpoint.
|
||||
// The URL names a path, so appending to it would ask for /transcribe/health.
|
||||
func healthOrigin(raw string) string {
|
||||
u, err := url.Parse(raw)
|
||||
if err != nil || u.Host == "" {
|
||||
return strings.TrimRight(raw, "/") + "/health"
|
||||
}
|
||||
return u.Scheme + "://" + u.Host + "/health"
|
||||
}
|
||||
|
||||
@@ -47,6 +47,11 @@ type PendingQuestion struct {
|
||||
// charging it a retry is the V-554 shape. See CanResume for why it is
|
||||
// counted at all.
|
||||
Suspends int
|
||||
// Rides counts every turn this question has ridden out on the end of
|
||||
// someone else's reply, over the whole life of the request. Unlike Suspends
|
||||
// it is never reset and never re-based, which is the only property that
|
||||
// matters about it (V-663).
|
||||
Rides int
|
||||
}
|
||||
|
||||
// MaxSuspends — how many times one question may step aside and come back before
|
||||
@@ -63,10 +68,52 @@ type PendingQuestion struct {
|
||||
// is that he has moved on and has not said so.
|
||||
const MaxSuspends = 3
|
||||
|
||||
// MaxRides — how many turns one question may ride out on the end of an
|
||||
// unrelated reply, counted over its whole life (V-663).
|
||||
//
|
||||
// MaxSuspends did not move the measurement it was written for. Twenty-six of
|
||||
// 140 turns carried a tail before it landed and twenty-six carried one after.
|
||||
// Every bound on this question is rearmed by something ordinary:
|
||||
//
|
||||
// - The TTL is an inactivity timer, and both noteSuspended and reaskOrGiveUp
|
||||
// restart it, so it cannot arrive while he keeps talking.
|
||||
// - Suspends is zeroed by any turn that reads as an answer, which is where
|
||||
// "спасибо" and "привет" land. It resets before anything is known to have
|
||||
// been filled.
|
||||
// - askRemainingGap builds a fresh question for the second gap, so a reminder
|
||||
// with two gaps gets a new allowance halfway through.
|
||||
//
|
||||
// So Suspends only bites on four strictly consecutive side queries with nothing
|
||||
// chat-like between them, which is not the shape real conversation has. Rides is
|
||||
// the same idea with the resets taken out: set once, incremented, carried
|
||||
// across a re-park, and read by nothing that could lower it.
|
||||
//
|
||||
// The shape it is aimed at is measured, not imagined. In the 2026-08-08 run one
|
||||
// question about a reminder's day rode turns 7 to 13 and ended only because
|
||||
// turn 14 was a new request. Three asides, then two turns that read as failed
|
||||
// answers, then two more asides. The asides spend no attempt and the answers
|
||||
// reset Suspends, so the two bounds take turns being rearmed by the other's
|
||||
// traffic.
|
||||
//
|
||||
// Four, not three. It has to be looser than MaxSuspends or that bound is dead
|
||||
// code, because Rides is never lower than Suspends and would always fire first.
|
||||
//
|
||||
// Do not read this as a fix for the whole ride. It ends the measured one a turn
|
||||
// early and no more. Most of that ride's length is attempts, spent by turns
|
||||
// like "спасибо" and "привет" being read as failed answers to a question about
|
||||
// a day. That is a defect in classifyTurnRole and not in any bound here.
|
||||
const MaxRides = 4
|
||||
|
||||
// CanResume reports whether this question may step aside once more. False ⇒ the
|
||||
// caller lets the request go and says so; it must never simply stop resuming,
|
||||
// because a question dropped in silence reads as one that was answered.
|
||||
func (q *PendingQuestion) CanResume() bool { return q.Suspends < MaxSuspends }
|
||||
//
|
||||
// Two bounds, and they answer different questions. Suspends asks whether he has
|
||||
// walked away from this exchange in the last few turns. Rides asks whether this
|
||||
// question has been riding long enough that the answer is no regardless.
|
||||
func (q *PendingQuestion) CanResume() bool {
|
||||
return q.Suspends < MaxSuspends && q.Rides < MaxRides
|
||||
}
|
||||
|
||||
// Action reads the parked question as the typed action it is assembling
|
||||
// (pending.go). Derived rather than stored: the question's fields stay the one
|
||||
|
||||
@@ -119,6 +119,11 @@ func PartsOfDay() []string { return words("parts_of_day") }
|
||||
// ReminderVerbs returns the imperatives that open a reminder.
|
||||
func ReminderVerbs() []string { return words("reminder_verbs") }
|
||||
|
||||
// Pleasantries returns the whole utterances that greet, thank or say goodbye.
|
||||
// Whole utterances and not tokens: see the set's own note for why the tokens
|
||||
// are unsafe alone.
|
||||
func Pleasantries() []string { return words("pleasantries") }
|
||||
|
||||
// TaskDoneWords returns the words that finish a task, and TaskDropWords the
|
||||
// words that abandon one. Two sets rather than one with a value, because the
|
||||
// store records which of the two happened and the caller has to say so.
|
||||
|
||||
@@ -176,6 +176,19 @@
|
||||
"morning", "afternoon", "evening", "night"
|
||||
]
|
||||
},
|
||||
"pleasantries": {
|
||||
"note": "Whole utterances that greet, thank or say goodbye. They ask for nothing and answer nothing, so a parked question must neither consume them as a failed answer nor be dropped by them (V-663). Matched as WHOLE utterances and never as tokens, because the tokens are not safe alone: \"вечер\" answers \"это утра или вечера?\" and \"нет\" answers a confirm. Anything that could fill a slot stays out. The control words (\"стоп\", \"отмена\") stay out too, because isCancel already owns them and they mean something stronger.",
|
||||
"words": [
|
||||
"привет", "приветик", "здравствуй", "здравствуйте",
|
||||
"доброе утро", "добрый день", "добрый вечер",
|
||||
"пока", "прощай", "до свидания", "спокойной ночи",
|
||||
"спасибо", "спасибо тебе", "большое спасибо", "благодарю",
|
||||
"извини", "извините", "прости", "простите",
|
||||
"hi", "hello", "hey", "bye", "goodbye",
|
||||
"good morning", "good evening", "good night",
|
||||
"thanks", "thank you", "thanks a lot", "sorry"
|
||||
]
|
||||
},
|
||||
"reminder_verbs": {
|
||||
"note": "The imperatives that mean \"remind me\", in the forms he speaks. The same kind of set as capture_verbs and decided the same way: it is her vocabulary, not a discovery about Russian (Vikunja #530). The alarm verbs joined them in V-627. \"разбуди меня в 6:30\" is a reminder that fires at the hour he gets up, and the set knew no form of it, so an alarm reached IntentReminder only by resembling one to the embedder.",
|
||||
"words": [
|
||||
|
||||
@@ -0,0 +1,92 @@
|
||||
package stt
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"context"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
"net/http"
|
||||
"strconv"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/audio"
|
||||
)
|
||||
|
||||
// HTTPTranscriber — speech-to-text on another host, over HTTP.
|
||||
//
|
||||
// mavsttd is whisper.cpp linked into a Go daemon and reached over a unix
|
||||
// socket. CrisperWhisper 2.0 cannot be reached that way: whisper.cpp derives
|
||||
// its language count from the vocabulary size, and CW2's 51897 tokens shift
|
||||
// seven special token ids. It runs under transformers instead, as a service
|
||||
// beside the model on workpc. See docs/evals/2026-08-09-crisperwhisper2-russian-wer.md.
|
||||
//
|
||||
// So this is the second transport for the same seam, not a second seam. The
|
||||
// caller still sees stt.Transcriber and one method.
|
||||
type HTTPTranscriber struct {
|
||||
url string
|
||||
token string
|
||||
lang string
|
||||
http *http.Client
|
||||
}
|
||||
|
||||
// NewHTTPTranscriber builds the remote client. token may be empty for a
|
||||
// service on a trusted socket, but audio is the most sensitive thing that
|
||||
// crosses this seam, so a LAN deployment should always set one.
|
||||
func NewHTTPTranscriber(url, token, lang string, timeout time.Duration) *HTTPTranscriber {
|
||||
return &HTTPTranscriber{
|
||||
url: url,
|
||||
token: token,
|
||||
lang: lang,
|
||||
http: &http.Client{Timeout: timeout},
|
||||
}
|
||||
}
|
||||
|
||||
// ErrFormat — the audio is not the one canonical shape. Refused at the seam
|
||||
// rather than sent to a model that expects something else.
|
||||
var ErrFormat = errors.New("stt: audio is not 16kHz mono pcm_s16le")
|
||||
|
||||
type httpTranscript struct {
|
||||
Text string `json:"text"`
|
||||
Confidence float64 `json:"confidence"`
|
||||
}
|
||||
|
||||
// Transcribe posts the raw PCM and reads back the text.
|
||||
//
|
||||
// The body is the PCM bytes themselves rather than JSON. A minute of 16kHz
|
||||
// mono is under 2MB raw and about 2.6MB base64, and the format is fixed by
|
||||
// audio.PCM16kMono, so a header carries it more cheaply than an envelope.
|
||||
func (t *HTTPTranscriber) Transcribe(ctx context.Context, a audio.Audio) (string, float64, error) {
|
||||
if !a.Format.IsValid() {
|
||||
return "", 0, ErrFormat
|
||||
}
|
||||
req, err := http.NewRequestWithContext(ctx, http.MethodPost, t.url, bytes.NewReader(a.Bytes))
|
||||
if err != nil {
|
||||
return "", 0, fmt.Errorf("stt: build request: %w", err)
|
||||
}
|
||||
req.Header.Set("Content-Type", "application/octet-stream")
|
||||
req.Header.Set("X-Sample-Rate", strconv.Itoa(a.Format.SampleRate))
|
||||
req.Header.Set("X-Channels", strconv.Itoa(a.Format.Channels))
|
||||
req.Header.Set("X-Sample-Bits", strconv.Itoa(a.Format.SampleBits))
|
||||
req.Header.Set("X-Language", t.lang)
|
||||
if t.token != "" {
|
||||
req.Header.Set("Authorization", "Bearer "+t.token)
|
||||
}
|
||||
|
||||
resp, err := t.http.Do(req)
|
||||
if err != nil {
|
||||
return "", 0, fmt.Errorf("stt: post audio: %w", err)
|
||||
}
|
||||
defer resp.Body.Close()
|
||||
if resp.StatusCode != http.StatusOK {
|
||||
return "", 0, fmt.Errorf("stt: remote returned %d", resp.StatusCode)
|
||||
}
|
||||
|
||||
var out httpTranscript
|
||||
if err := json.NewDecoder(resp.Body).Decode(&out); err != nil {
|
||||
return "", 0, fmt.Errorf("stt: decode transcript: %w", err)
|
||||
}
|
||||
return out.Text, out.Confidence, nil
|
||||
}
|
||||
|
||||
var _ Transcriber = (*HTTPTranscriber)(nil)
|
||||
@@ -0,0 +1,89 @@
|
||||
package stt
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"io"
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"strconv"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/audio"
|
||||
)
|
||||
|
||||
func TestHTTPTranscriberSendsRawPCM(t *testing.T) {
|
||||
t.Parallel()
|
||||
var gotBody []byte
|
||||
var gotHeader http.Header
|
||||
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
gotBody, _ = io.ReadAll(r.Body)
|
||||
gotHeader = r.Header.Clone()
|
||||
w.Header().Set("Content-Type", "application/json")
|
||||
_, _ = io.WriteString(w, `{"text":"привет","confidence":0.82}`)
|
||||
}))
|
||||
defer srv.Close()
|
||||
|
||||
a := audio.Audio{Format: audio.PCM16kMono, Bytes: []byte("pcm-bytes")}
|
||||
tr := NewHTTPTranscriber(srv.URL, "s3cret", "ru", 2*time.Second)
|
||||
text, conf, err := tr.Transcribe(context.Background(), a)
|
||||
if err != nil {
|
||||
t.Fatalf("Transcribe: %v", err)
|
||||
}
|
||||
if text != "привет" || conf != 0.82 {
|
||||
t.Fatalf("got %q %v", text, conf)
|
||||
}
|
||||
if string(gotBody) != "pcm-bytes" {
|
||||
t.Fatalf("body should be the PCM itself, got %q", gotBody)
|
||||
}
|
||||
if got := gotHeader.Get("X-Sample-Rate"); got != strconv.Itoa(audio.PCM16kMono.SampleRate) {
|
||||
t.Fatalf("X-Sample-Rate = %q", got)
|
||||
}
|
||||
if got := gotHeader.Get("X-Language"); got != "ru" {
|
||||
t.Fatalf("X-Language = %q", got)
|
||||
}
|
||||
// Audio is the most sensitive thing crossing this seam.
|
||||
if got := gotHeader.Get("Authorization"); got != "Bearer s3cret" {
|
||||
t.Fatalf("Authorization = %q", got)
|
||||
}
|
||||
}
|
||||
|
||||
func TestHTTPTranscriberOmitsEmptyToken(t *testing.T) {
|
||||
t.Parallel()
|
||||
var auth string
|
||||
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
auth = r.Header.Get("Authorization")
|
||||
_, _ = io.WriteString(w, `{"text":"x"}`)
|
||||
}))
|
||||
defer srv.Close()
|
||||
a := audio.Audio{Format: audio.PCM16kMono, Bytes: []byte("x")}
|
||||
if _, _, err := NewHTTPTranscriber(srv.URL, "", "ru", time.Second).Transcribe(context.Background(), a); err != nil {
|
||||
t.Fatalf("Transcribe: %v", err)
|
||||
}
|
||||
if auth != "" {
|
||||
t.Fatalf("Authorization should be absent, got %q", auth)
|
||||
}
|
||||
}
|
||||
|
||||
func TestHTTPTranscriberRefusesWrongFormat(t *testing.T) {
|
||||
t.Parallel()
|
||||
a := audio.Audio{Format: audio.Format{SampleRate: 44100, Channels: 2, SampleBits: 16, Encoding: "pcm_s16le"}}
|
||||
_, _, err := NewHTTPTranscriber("http://example.invalid", "", "ru", time.Second).Transcribe(context.Background(), a)
|
||||
if !errors.Is(err, ErrFormat) {
|
||||
t.Fatalf("want ErrFormat, got %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
func TestHTTPTranscriberErrorsOnBadStatus(t *testing.T) {
|
||||
t.Parallel()
|
||||
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
|
||||
w.WriteHeader(http.StatusUnauthorized)
|
||||
}))
|
||||
defer srv.Close()
|
||||
a := audio.Audio{Format: audio.PCM16kMono, Bytes: []byte("x")}
|
||||
_, _, err := NewHTTPTranscriber(srv.URL, "", "ru", time.Second).Transcribe(context.Background(), a)
|
||||
if err == nil {
|
||||
t.Fatal("a 401 must be an error, so the Pair falls back")
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,157 @@
|
||||
package stt
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"log"
|
||||
"net/http"
|
||||
"sync"
|
||||
"sync/atomic"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/audio"
|
||||
)
|
||||
|
||||
// Pair — a preferred transcriber on the workstation, with mavsttd as the floor.
|
||||
//
|
||||
// Same arrangement as llm.Pair and for the same reason. The microphone is at
|
||||
// workpc, the card there has 16GB, and CrisperWhisper 2.0 turbo scores 10.4%
|
||||
// WER in Russian against 27.5% for the ggml-small.bin homesrv loads
|
||||
// (docs/evals/2026-08-09-crisperwhisper2-russian-wer.md). The workstation is
|
||||
// never assumed up: it sleeps, and the card is often held by a training run.
|
||||
//
|
||||
// Speech-to-text has only the silent half of the degradation rule. A worse
|
||||
// transcript is still a turn, and there is nothing to name a gap about, so
|
||||
// Transcribe always falls back. That is the whole difference from llm.Pair,
|
||||
// which also carries CompleteRemote for callers that must refuse instead.
|
||||
type Pair struct {
|
||||
remote Transcriber
|
||||
floor Transcriber
|
||||
|
||||
// up — the cached admission answer, written only by the prober and read by
|
||||
// every turn. A voice turn must never wait on a machine that may be asleep.
|
||||
up atomic.Bool
|
||||
|
||||
health string
|
||||
interval time.Duration
|
||||
http *http.Client
|
||||
stop chan struct{}
|
||||
stopOnce sync.Once
|
||||
}
|
||||
|
||||
const (
|
||||
probeTimeout = 2 * time.Second
|
||||
defaultProbeInterval = 15 * time.Second
|
||||
)
|
||||
|
||||
// ErrNoFloor — a Pair was built with no local transcriber to fall back to. A
|
||||
// configuration mistake: the floor is what makes the remote optional.
|
||||
var ErrNoFloor = errors.New("stt: no floor transcriber")
|
||||
|
||||
// NewPair builds the two-transcriber arrangement. remote may be nil, which is
|
||||
// the unconfigured deploy: every turn goes to the floor and nothing probes.
|
||||
func NewPair(remote, floor Transcriber, health string, interval time.Duration) *Pair {
|
||||
if interval <= 0 {
|
||||
// The config normalises this, so a zero here is a caller that built the
|
||||
// Pair directly. Panicking in a ticker is the wrong way to say so.
|
||||
interval = defaultProbeInterval
|
||||
}
|
||||
return &Pair{
|
||||
remote: remote,
|
||||
floor: floor,
|
||||
health: health,
|
||||
interval: interval,
|
||||
http: &http.Client{Timeout: probeTimeout},
|
||||
stop: make(chan struct{}),
|
||||
}
|
||||
}
|
||||
|
||||
// Start begins probing. The first probe runs before the first tick, so a
|
||||
// workstation that is already up serves the first utterance rather than the
|
||||
// second. Safe with a nil remote.
|
||||
func (p *Pair) Start(ctx context.Context) {
|
||||
if p.remote == nil || p.health == "" {
|
||||
return
|
||||
}
|
||||
go func() {
|
||||
p.probe(ctx)
|
||||
t := time.NewTicker(p.interval)
|
||||
defer t.Stop()
|
||||
for {
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
return
|
||||
case <-p.stop:
|
||||
return
|
||||
case <-t.C:
|
||||
p.probe(ctx)
|
||||
}
|
||||
}
|
||||
}()
|
||||
}
|
||||
|
||||
// Stop ends the prober. Idempotent and safe from two goroutines.
|
||||
func (p *Pair) Stop() {
|
||||
p.stopOnce.Do(func() { close(p.stop) })
|
||||
}
|
||||
|
||||
// Available reports whether the workstation will transcribe right now.
|
||||
func (p *Pair) Available() bool {
|
||||
return p.remote != nil && p.up.Load()
|
||||
}
|
||||
|
||||
func (p *Pair) probe(ctx context.Context) {
|
||||
ctx, cancel := context.WithTimeout(ctx, probeTimeout)
|
||||
defer cancel()
|
||||
req, err := http.NewRequestWithContext(ctx, http.MethodGet, p.health, nil)
|
||||
if err != nil {
|
||||
p.set(false)
|
||||
return
|
||||
}
|
||||
resp, err := p.http.Do(req)
|
||||
if err != nil {
|
||||
p.set(false)
|
||||
return
|
||||
}
|
||||
defer resp.Body.Close()
|
||||
p.set(resp.StatusCode == http.StatusOK)
|
||||
}
|
||||
|
||||
// set records the admission answer and logs only transitions. A machine that
|
||||
// sleeps nightly would otherwise write one line per interval forever.
|
||||
func (p *Pair) set(up bool) {
|
||||
if p.up.Swap(up) == up {
|
||||
return
|
||||
}
|
||||
if up {
|
||||
log.Printf("stt: workstation transcriber available at %s", p.health)
|
||||
} else {
|
||||
log.Print("stt: workstation transcriber unavailable, falling back to mavsttd")
|
||||
}
|
||||
}
|
||||
|
||||
// Transcribe sends the audio to the workstation when it will take work, and to
|
||||
// mavsttd otherwise. A remote that fails mid-request falls back too, because
|
||||
// the admission answer is a cache and can be one interval out of date.
|
||||
//
|
||||
// Killing the remote mid-session must not drop the turn. That is the whole
|
||||
// point of the floor, and it is what TestPairFallsBackWhenRemoteFails pins.
|
||||
func (p *Pair) Transcribe(ctx context.Context, a audio.Audio) (string, float64, error) {
|
||||
if p.floor == nil {
|
||||
return "", 0, ErrNoFloor
|
||||
}
|
||||
if p.Available() {
|
||||
text, conf, err := p.remote.Transcribe(ctx, a)
|
||||
if err == nil {
|
||||
log.Print("stt: transcribed on the workstation")
|
||||
return text, conf, nil
|
||||
}
|
||||
// The cached answer was wrong. Correct it now rather than sending the
|
||||
// next utterance into the same hole, then fall back.
|
||||
p.set(false)
|
||||
log.Printf("stt: workstation failed mid-request, falling back: %v", err)
|
||||
}
|
||||
return p.floor.Transcribe(ctx, a)
|
||||
}
|
||||
|
||||
var _ Transcriber = (*Pair)(nil)
|
||||
@@ -0,0 +1,143 @@
|
||||
package stt
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"sync/atomic"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/audio"
|
||||
)
|
||||
|
||||
// scripted — a Transcriber that answers with a fixed text, or fails.
|
||||
type scripted struct {
|
||||
text string
|
||||
err error
|
||||
calls atomic.Int32
|
||||
}
|
||||
|
||||
func (s *scripted) Transcribe(_ context.Context, _ audio.Audio) (string, float64, error) {
|
||||
s.calls.Add(1)
|
||||
if s.err != nil {
|
||||
return "", 0, s.err
|
||||
}
|
||||
return s.text, 0.9, nil
|
||||
}
|
||||
|
||||
func sample() audio.Audio {
|
||||
return audio.Audio{Format: audio.PCM16kMono, Bytes: make([]byte, 3200)}
|
||||
}
|
||||
|
||||
// up builds a Pair whose admission answer is already true, without probing.
|
||||
func up(remote, floor Transcriber) *Pair {
|
||||
p := NewPair(remote, floor, "", time.Minute)
|
||||
p.up.Store(true)
|
||||
return p
|
||||
}
|
||||
|
||||
func TestPairPrefersTheWorkstation(t *testing.T) {
|
||||
t.Parallel()
|
||||
remote := &scripted{text: "с рабочей станции"}
|
||||
floor := &scripted{text: "с homesrv"}
|
||||
text, _, err := up(remote, floor).Transcribe(context.Background(), sample())
|
||||
if err != nil {
|
||||
t.Fatalf("Transcribe: %v", err)
|
||||
}
|
||||
if text != "с рабочей станции" {
|
||||
t.Fatalf("want the remote transcript, got %q", text)
|
||||
}
|
||||
if floor.calls.Load() != 0 {
|
||||
t.Fatalf("floor was called %d times, want 0", floor.calls.Load())
|
||||
}
|
||||
}
|
||||
|
||||
// The turn is what matters. A remote that dies mid-session must cost a worse
|
||||
// transcript and nothing else. This is the V-486 bar.
|
||||
func TestPairFallsBackWhenRemoteFails(t *testing.T) {
|
||||
t.Parallel()
|
||||
remote := &scripted{err: errors.New("connection refused")}
|
||||
floor := &scripted{text: "с homesrv"}
|
||||
p := up(remote, floor)
|
||||
|
||||
text, conf, err := p.Transcribe(context.Background(), sample())
|
||||
if err != nil {
|
||||
t.Fatalf("a failed remote must not fail the turn: %v", err)
|
||||
}
|
||||
if text != "с homesrv" {
|
||||
t.Fatalf("want the floor transcript, got %q", text)
|
||||
}
|
||||
if conf != 0.9 {
|
||||
t.Fatalf("want the floor confidence, got %v", conf)
|
||||
}
|
||||
if p.Available() {
|
||||
t.Fatal("a failed request must correct the cached admission answer")
|
||||
}
|
||||
|
||||
// The next utterance goes straight to the floor rather than into the
|
||||
// same hole.
|
||||
if _, _, err := p.Transcribe(context.Background(), sample()); err != nil {
|
||||
t.Fatalf("second turn: %v", err)
|
||||
}
|
||||
if remote.calls.Load() != 1 {
|
||||
t.Fatalf("remote called %d times, want 1", remote.calls.Load())
|
||||
}
|
||||
}
|
||||
|
||||
func TestPairWithNoRemoteIsTheFloor(t *testing.T) {
|
||||
t.Parallel()
|
||||
floor := &scripted{text: "с homesrv"}
|
||||
p := NewPair(nil, floor, "", time.Minute)
|
||||
p.Start(context.Background()) // no health url, so this is a no-op
|
||||
if p.Available() {
|
||||
t.Fatal("an unconfigured remote is never available")
|
||||
}
|
||||
text, _, err := p.Transcribe(context.Background(), sample())
|
||||
if err != nil {
|
||||
t.Fatalf("Transcribe: %v", err)
|
||||
}
|
||||
if text != "с homesrv" {
|
||||
t.Fatalf("want the floor transcript, got %q", text)
|
||||
}
|
||||
}
|
||||
|
||||
func TestPairWithNoFloorRefuses(t *testing.T) {
|
||||
t.Parallel()
|
||||
_, _, err := NewPair(nil, nil, "", time.Minute).Transcribe(context.Background(), sample())
|
||||
if !errors.Is(err, ErrNoFloor) {
|
||||
t.Fatalf("want ErrNoFloor, got %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
func TestPairProbeReadsHealth(t *testing.T) {
|
||||
t.Parallel()
|
||||
var ok atomic.Bool
|
||||
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
|
||||
if !ok.Load() {
|
||||
w.WriteHeader(http.StatusServiceUnavailable)
|
||||
return
|
||||
}
|
||||
w.WriteHeader(http.StatusOK)
|
||||
}))
|
||||
defer srv.Close()
|
||||
|
||||
p := NewPair(&scripted{text: "remote"}, &scripted{text: "floor"}, srv.URL, time.Minute)
|
||||
p.probe(context.Background())
|
||||
if p.Available() {
|
||||
t.Fatal("a 503 means the card is busy, so the workstation is not available")
|
||||
}
|
||||
ok.Store(true)
|
||||
p.probe(context.Background())
|
||||
if !p.Available() {
|
||||
t.Fatal("a 200 means the workstation will take work")
|
||||
}
|
||||
}
|
||||
|
||||
func TestPairStopIsIdempotent(t *testing.T) {
|
||||
t.Parallel()
|
||||
p := NewPair(nil, &scripted{}, "", time.Minute)
|
||||
p.Stop()
|
||||
p.Stop()
|
||||
}
|
||||
@@ -54,7 +54,11 @@ def turn(text):
|
||||
q = urllib.parse.parse_qs(urllib.parse.urlparse(loc).query)
|
||||
return {
|
||||
"reply": q.get("r", [""])[0],
|
||||
"source": q.get("src", q.get("source", [""]))[0],
|
||||
# "s", not "src". cmd/mavweb/chat.go writes the badge under that
|
||||
# name, and reading the wrong one cost both fortnight runs their
|
||||
# source column: every finding in those docs is inferred from the
|
||||
# reply wording instead.
|
||||
"source": q.get("s", [""])[0],
|
||||
"trace": q.get("t", [""])[0],
|
||||
"secs": dt,
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user