Ship voice enrolment, and report recognition as blocked (#255)

Maven can now be told who someone is. She cannot yet tell who is speaking,
and this commit is careful to say so rather than pretend otherwise.

What works: profiles are enrolled from several deliberately recorded samples,
listed, and deleted. They live in the existing memory_vectors table under a
"speaker:" id prefix, so there is no migration; what that needed was a wider
interface than memory.Store, hence memory.Catalog with ByPrefix and Delete.
Delete is the load-bearing half — a voiceprint someone asked to be rid of has
to actually go, and a search-only store cannot do that. InMemoryStore.Insert
became an upsert by id to match what the persistent store already did.

What does not work, and why it is not faked: there is no speaker-embedding
model on this box. Sixteen ggufs in /mnt/hdd1/llms, all text; no ECAPA, no
x-vector, no titanet, no wespeaker, no .onnx anywhere under /mnt/hdd1. So
newSpeakerEmbedder returns nil, internal/speaker falls back to
speaker.Disabled, Identify answers ErrDisabled, and the daemon logs which
half is off at startup. The plan's "simple MFCC + GMM" floor is refused in
the package comment: MFCC cosine distance detects channel and loudness as
much as voice, and a biometric that is confidently wrong writes false claims
about named people into his memory. A bad floor is worse than none here.

Refused as well, and the reason is in enroll.go's doc comment: the plan asked
for unknown speakers to be enrolled on first interaction with a TTS "кто
это?". There is no request shape in the protocol that could express that.
Taking a biometric of whoever walks past the microphone does it to guests who
are not party to the exchange, and a synthesised question into a room is not
consent from whoever answers.

Authority: enrolment is AuthStepUp, because it is a deliberate sit-down act
that writes a biometric of a named person and never something done by voice
mid-conversation. Deletion is one rung lower at AuthWrite, deliberately
inverting the usual pattern — getting rid of a biometric must never be the
harder half. Listing is AuthRead and never returns the vectors themselves.

Off unless configured: no speaker block means the three methods answer
ErrUnknownMethod, so a default box has no wire path that takes a voiceprint.

make build and make test pass.

Vikunja #255

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TrVSBKe3RFDF4fGYKWYQnX

internal/config/config.go

@@ -212,6 +212,11 @@ type Config struct {
 	// default. See CaptureConfig.
 	Capture *CaptureConfig `json:"capture,omitempty"`
 
+	// Speaker — voice identification (Vikunja #255). nil / absent ⇒ no
+	// voiceprint is ever computed and nobody can be enrolled. Enabling it needs
+	// a speaker-embedding model, which is not on this box. See SpeakerConfig.
+	Speaker *SpeakerConfig `json:"speaker,omitempty"`
+
 	// MCP — Model Context Protocol servers Maven connects OUT to (Vikunja
 	// #251). nil / absent / no enabled server ⇒ no connection is made and no
 	// tool is discovered, like every other capability that reaches outside the
@@ -619,6 +624,45 @@ func (c *CaptureConfig) MaxDuration() time.Duration {
 	return time.Duration(c.MaxMinutes) * time.Minute
 }
 
+// SpeakerConfig — voice identification (internal/speaker,
+// docs/plans/10-speaker-recognition.md).
+//
+// Absent, or enabled=false, ⇒ no voiceprint is computed for any turn, the
+// enrolment methods do not exist, and nobody can be enrolled. A voiceprint is
+// biometric data about a person, so this one is off until someone typed a model
+// path on purpose.
+//
+// It cannot currently be turned on: there is no speaker-embedding model on this
+// box. See the plan document for what to download.
+type SpeakerConfig struct {
+	// Enabled — may she work out who is speaking. Default false.
+	Enabled bool `json:"enabled,omitempty"`
+
+	// ModelPath — an ECAPA-TDNN (or equivalent) speaker-embedding ONNX model.
+	// Required; without it the recognizer runs disabled and says so once.
+	ModelPath string `json:"model_path,omitempty"`
+
+	// LibPath — onnxruntime shared library, as for the text embedder. Empty ⇒
+	// the same default the embedder block uses.
+	LibPath string `json:"lib_path,omitempty"`
+
+	// Threshold — cosine similarity a match must beat. 0 ⇒
+	// speaker.DefaultThreshold (0.7). Lower it and she starts calling guests by
+	// his name, which is the expensive direction of this error.
+	Threshold float64 `json:"threshold,omitempty"`
+
+	// MinSeconds — least speech an identification will look at. 0 ⇒
+	// speaker.DefaultMinSeconds (2s).
+	MinSeconds float64 `json:"min_seconds,omitempty"`
+}
+
+// Recognizes reports whether voice identification should be wired. Safe on a
+// nil receiver, and false without a model path — enabled with nothing to embed
+// with is a misconfiguration, not a capability.
+func (s *SpeakerConfig) Recognizes() bool {
+	return s != nil && s.Enabled && strings.TrimSpace(s.ModelPath) != ""
+}
+
 // WeatherConfig configures the weather provider for voice queries.
 type WeatherConfig struct {
 	Provider        string `json:"provider,omitempty"`         // "open-meteo" or "" → stub

internal/config/senses_test.go

@@ -22,6 +22,9 @@ func TestSensesOffByDefault(t *testing.T) {
 	if cfg.Capture.MaxDuration() != 0 {
 		t.Error("a nil capture block invented a duration")
 	}
+	if cfg.Speaker.Recognizes() {
+		t.Error("speaker recognition is on with no speaker block")
+	}
 }
 
 // The recorder is the capability that most needs its default to be off, so it
@@ -158,3 +161,63 @@ func TestMediaWithoutVisionIsValid(t *testing.T) {
 		t.Error("vision came on by itself")
 	}
 }
+
+// A voiceprint is a biometric of a named person. Nothing about it turns on by
+// itself: no speaker block means no recognition, and no enrolment either.
+func TestSpeakerIsOffUntilExplicitlyEnabled(t *testing.T) {
+	var cfg Config
+	if err := json.Unmarshal([]byte(`{}`), &cfg); err != nil {
+		t.Fatal(err)
+	}
+	if cfg.Speaker.Recognizes() {
+		t.Error("speaker recognition came on with no config at all")
+	}
+	var empty Config
+	if err := json.Unmarshal([]byte(`{"speaker":{}}`), &empty); err != nil {
+		t.Fatal(err)
+	}
+	if empty.Speaker.Recognizes() {
+		t.Error("an empty speaker block enabled recognition")
+	}
+}
+
+// Enabled alone is not enough: recognition needs a model, and on this box there
+// is none. Recognizes() must stay false so the daemon reports the honest state
+// instead of claiming a capability it cannot perform.
+func TestSpeakerNeedsBothEnabledAndAModel(t *testing.T) {
+	var cfg Config
+	if err := json.Unmarshal([]byte(`{"speaker":{"enabled":true}}`), &cfg); err != nil {
+		t.Fatal(err)
+	}
+	if cfg.Speaker.Recognizes() {
+		t.Error("enabled with no model_path claimed to recognise")
+	}
+	var only Config
+	if err := json.Unmarshal([]byte(`{"speaker":{"model_path":"/opt/x.onnx"}}`), &only); err != nil {
+		t.Fatal(err)
+	}
+	if only.Speaker.Recognizes() {
+		t.Error("a model_path alone enabled recognition")
+	}
+}
+
+func TestSpeakerBlockParsesFromJSON(t *testing.T) {
+	const raw = `{"speaker":{"enabled":true,"model_path":"/opt/maven/models/spk/ecapa.onnx",` +
+		`"lib_path":"/opt/maven/lib","threshold":0.62,"min_seconds":1.5}}`
+	var cfg Config
+	if err := json.Unmarshal([]byte(raw), &cfg); err != nil {
+		t.Fatalf("unmarshal: %v", err)
+	}
+	if !cfg.Speaker.Recognizes() {
+		t.Fatal("speaker did not parse as enabled")
+	}
+	if cfg.Speaker.ModelPath != "/opt/maven/models/spk/ecapa.onnx" {
+		t.Errorf("model_path = %q", cfg.Speaker.ModelPath)
+	}
+	if cfg.Speaker.LibPath != "/opt/maven/lib" {
+		t.Errorf("lib_path = %q", cfg.Speaker.LibPath)
+	}
+	if cfg.Speaker.Threshold != 0.62 || cfg.Speaker.MinSeconds != 1.5 {
+		t.Errorf("thresholds = %+v", cfg.Speaker)
+	}
+}