Route with the resident model by default

The two things that made this unsafe are fixed: the router can now
refuse, and slot extraction runs on its decisions.

On the held-out fixture it gets 63.2% of intents right against the
classifier's 50.0%, with no route errors. It costs about a second a
turn instead of 30ms.

The flag is a pointer now, so leaving it out of the config means on
and only writing false turns it off.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ

cmd/mavend/voice.go

@@ -206,11 +206,11 @@ func wireVoice(cfg *config.Config, coreAPI ipc.CoreAPI, phr phraser.Phraser, mem
 	if threshold <= 0 {
 		threshold = config.DefaultRouterThreshold
 	}
-	// Both routing paths are weak on held-out utterances — the classifier gets
+	// The resident model routes by default: 63.2% of held-out intents right
-	// 36.8% of intents right, the resident model 50.0% and much slower. Off by
+	// against the classifier's 50.0%, at about 1s a turn instead of 30ms (see
-	// default (see config.VoiceConfig.LLMRouter); the classifier always stays
+	// config.VoiceConfig.LLMRouter). The classifier always stays wired as the
-	// wired as the fallback, so a model error never breaks a turn.
+	// fallback, so a model error never breaks a turn.
-	rtr := buildRouter(emb, matcher, threshold, pickLLMRouter(cfg.Voice.LLMRouter, llmClient))
+	rtr := buildRouter(emb, matcher, threshold, pickLLMRouter(cfg.Voice.UseLLMRouter(), llmClient))
 
 	// ----- sessions registry (shared with voicesink) -----
 	sessions := voice.NewSessions()

deploy/mavend.json

@@ -40,7 +40,7 @@
       "tokenizer_path": "/opt/maven/models/embedder/multilingual-e5-small/tokenizer.json",
       "lib_path": "/opt/maven/lib/libonnxruntime.so"
     },
-    "llm_router": false,
+    "llm_router": true,
     "tool_timeout": "30s",
     "tools": [
       { "name": "status",     "cmd": ["systemctl", "status"],         "scope": "homelab", "destructive": false },

internal/config/config.go

@@ -258,18 +258,25 @@ type VoiceConfig struct {
 	RouterThreshold float64 `json:"router_threshold,omitempty"`
 
 	// LLMRouter — route with the resident model instead of the embedding
-	// classifier. Measured on the held-out fixture (ROUTING-EVAL-31-07-2026.md)
+	// classifier. On by default since Vikunja #320.
-	// the model gets 50.0% of intents right against the classifier's 36.8%, but
-	// it costs about 800ms per turn instead of 30ms.
 	//
-	// TODO: the default stays false until this lands.
+	// Measured on the held-out fixture (ROUTING-EVAL-31-07-2026.md): 63.2% of
-	// Extractor.Extract never runs on an LLM decision, so acts arrive with no
+	// intents right against the classifier's 50.0%, and no route errors. It
-	// Fn and reminders with no Time. Turning this on today makes routing more
+	// costs about 1s per turn instead of 30ms.
-	// accurate and less safe.
 	//
-	// The router can now refuse: it answers "unknown" when it cannot route, and
+	// It is safe to leave on. The model can refuse — it answers "unknown" when
-	// the turn drops to the classifier and its clarify gate (Vikunja #359).
+	// it cannot route, and the turn drops to the classifier and its clarify
-	LLMRouter bool `json:"llm_router,omitempty"`
+	// gate. Any LLM error does the same, so a turn never breaks on the model.
+	// Slot extraction runs on LLM decisions too, so acts get their Fn and
+	// reminders their Time.
+	//
+	// Set it false to go back to the classifier, e.g. on a box with no
+	// llama-server or when 1s a turn is too slow.
+	//
+	// It is a pointer so that "missing from the file" and "explicitly false"
+	// are different things: missing means on, false means off. Read it with
+	// UseLLMRouter(), not directly.
+	LLMRouter *bool `json:"llm_router,omitempty"`
 
 	// QueryMinScore — the note-recall confidence gate. Top cosine below this
 	// ⇒ "I don't know" instead of a guess. Tuned for the ONNX embedder (0.55);
@@ -405,6 +412,8 @@ const (
 	DefaultRouterThreshold  = 0.55
 	DefaultQueryMinScore    = 0.55
 	DefaultToolTimeout      = 30 * time.Second
+	// DefaultLLMRouter — route with the resident model unless told otherwise.
+	DefaultLLMRouter = true
 
 	DefaultFactEnrichmentInterval = 30 * time.Second
 )
@@ -489,6 +498,10 @@ func (c *Config) applyDefaults() {
 		if c.Voice.ToolTimeout <= 0 {
 			c.Voice.ToolTimeout = Duration(DefaultToolTimeout)
 		}
+		if c.Voice.LLMRouter == nil {
+			on := DefaultLLMRouter
+			c.Voice.LLMRouter = &on
+		}
 	}
 
 	// routines: default severity to care-class (1) — the safe floor: a
@@ -507,6 +520,15 @@ func (c *Config) applyDefaults() {
 	}
 }
 
+// UseLLMRouter reports whether to route with the resident model. Unset means
+// on; only an explicit false in the config turns it off.
+func (v *VoiceConfig) UseLLMRouter() bool {
+	if v == nil || v.LLMRouter == nil {
+		return DefaultLLMRouter
+	}
+	return *v.LLMRouter
+}
+
 func (c *Config) validate() error {
 	if c.Phraser != nil {
 		if c.Phraser.ModelPath == "" {

internal/config/config_test.go

@@ -171,14 +171,26 @@ func TestWeatherConfigNilOK(t *testing.T) {
 	}
 }
 
-func TestLLMRouterDefaultsOff(t *testing.T) {
+func TestLLMRouterDefaultsOn(t *testing.T) {
 	p := writeConfig(t, `{"voice":{"enabled":true,"bind":"127.0.0.1:9100"}}`)
 	c, err := Load(p)
 	if err != nil {
 		t.Fatalf("Load: %v", err)
 	}
-	if c.Voice.LLMRouter {
+	if !c.Voice.UseLLMRouter() {
-		t.Error("voice.llm_router absent should mean false")
+		t.Error("voice.llm_router absent should mean on")
+	}
+}
+
+// Missing and explicitly false must not mean the same thing.
+func TestLLMRouterExplicitFalseTurnsItOff(t *testing.T) {
+	p := writeConfig(t, `{"voice":{"enabled":true,"bind":"127.0.0.1:9100","llm_router":false}}`)
+	c, err := Load(p)
+	if err != nil {
+		t.Fatalf("Load: %v", err)
+	}
+	if c.Voice.UseLLMRouter() {
+		t.Error("voice.llm_router false should turn it off")
 	}
 }
 
@@ -188,7 +200,7 @@ func TestLLMRouterRead(t *testing.T) {
 	if err != nil {
 		t.Fatalf("Load: %v", err)
 	}
-	if !c.Voice.LLMRouter {
+	if !c.Voice.UseLLMRouter() {
 		t.Error("voice.llm_router true was not read")
 	}
 }