Merge the llm_router flag and the kill-maven fix

This commit is contained in:
kami
2026-07-31 02:17:00 +04:00
6 changed files with 99 additions and 7 deletions
+14
View File
@@ -257,6 +257,20 @@ type VoiceConfig struct {
// Default 0.35 if unset.
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.
//
// TODO: the default stays false until two things land.
// 1. The LLM router cannot refuse. LLMRouter.Route hardcodes
// Confidence: 1.0, so the stage-3 clarify gate never fires and an
// unclear utterance becomes a confident wrong action (Vikunja #359).
// 2. 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.
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);
// the HashEmbedder floor scores lexically and may never clear it. 0.55
+22
View File
@@ -171,6 +171,28 @@ func TestWeatherConfigNilOK(t *testing.T) {
}
}
func TestLLMRouterDefaultsOff(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")
}
}
func TestLLMRouterRead(t *testing.T) {
p := writeConfig(t, `{"voice":{"enabled":true,"bind":"127.0.0.1:9100","llm_router":true}}`)
c, err := Load(p)
if err != nil {
t.Fatalf("Load: %v", err)
}
if !c.Voice.LLMRouter {
t.Error("voice.llm_router true was not read")
}
}
func TestDurationRoundTrip(t *testing.T) {
d := Duration(15 * time.Minute)
b, err := d.MarshalJSON()