Compare commits

...

1 Commits

Author SHA1 Message Date
kami 93c1a41d4a 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
2026-07-31 11:47:57 +04:00
4 changed files with 54 additions and 20 deletions
+5 -5
View File
@@ -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
// 36.8% of intents right, the resident model 50.0% and much slower. Off by
// default (see config.VoiceConfig.LLMRouter); the classifier always stays
// wired as the fallback, so a model error never breaks a turn.
rtr := buildRouter(emb, matcher, threshold, pickLLMRouter(cfg.Voice.LLMRouter, llmClient))
// The resident model routes by default: 63.2% of held-out intents right
// against the classifier's 50.0%, at about 1s a turn instead of 30ms (see
// config.VoiceConfig.LLMRouter). The classifier always stays wired as the
// fallback, so a model error never breaks a turn.
rtr := buildRouter(emb, matcher, threshold, pickLLMRouter(cfg.Voice.UseLLMRouter(), llmClient))
// ----- sessions registry (shared with voicesink) -----
sessions := voice.NewSessions()
+1 -1
View File
@@ -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 },
+32 -10
View File
@@ -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)
// the model gets 50.0% of intents right against the classifier's 36.8%, but
// it costs about 800ms per turn instead of 30ms.
// classifier. On by default since Vikunja #320.
//
// TODO: the default stays false until this lands.
// Extractor.Extract never runs on an LLM decision, so acts arrive with no
// Fn and reminders with no Time. Turning this on today makes routing more
// accurate and less safe.
// Measured on the held-out fixture (ROUTING-EVAL-31-07-2026.md): 63.2% of
// intents right against the classifier's 50.0%, and no route errors. It
// costs about 1s per turn instead of 30ms.
//
// The router can now refuse: it answers "unknown" when it cannot route, and
// the turn drops to the classifier and its clarify gate (Vikunja #359).
LLMRouter bool `json:"llm_router,omitempty"`
// It is safe to leave on. The model can refuse it answers "unknown" when
// it cannot route, and the turn drops to the classifier and its clarify
// 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 == "" {
+16 -4
View File
@@ -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 {
t.Error("voice.llm_router absent should mean false")
if !c.Voice.UseLLMRouter() {
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")
}
}