Merge pull request 'Move STT and TTS to the workstation, where the microphone already is' (#208) from task/486-move-stt-and-tts-to-the-workstation-wher into master

internal/config/workstation.go

@@ -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"
 }