4.1 routing quality + 4.4 persona prompt
- VoiceConfig: add QueryMinScore (default 0.55) + Persona config fields - voice.go: remove queryMinScore const, wire from cfg.Voice.QueryMinScore as reactiveHandler field - llmphraser.go: add Persona to Config, prepend to system prompts in chat and query paths (systemPrompt/querySystemPrompt methods) - main.go: pass personaFromCfg into both phraser config blocks - Makefile: add download-embedder target (Xenova/paraphrase-multilingual- MiniLM-L12-v2, ~90MB ONNX) - AGENTS.md: document embedder model download + libonnxruntime setup - server.go: fix pre-existing wg.Add vs wg.Wait data race using accept mutex. make test green, zero races across all 29 packages.
This commit is contained in:
kami
@@ -36,6 +36,44 @@ $R/mavweb -addr 127.0.0.1:9299 -core $R/mavend.sock &
|
||||
can snap mid-layout and silently drop elements (the PWA lang toggle
|
||||
"disappeared" this way).
|
||||
|
||||
## Embedder model for intent routing
|
||||
|
||||
The router uses a multilingual sentence embedder to classify intents and recall
|
||||
notes. Without it, the floor `HashEmbedder` is used — deterministic but weak
|
||||
(Russian recall rarely clears the confidence gate, many commands fall to
|
||||
"clarify").
|
||||
|
||||
**Download the embedder** (ONNX, ~90 MB):
|
||||
|
||||
```sh
|
||||
make download-embedder
|
||||
```
|
||||
|
||||
This fetches `paraphrase-multilingual-MiniLM-L12-v2` (384-dim, 12-layer,
|
||||
supports 50+ languages including Russian) to `models/embedder/`.
|
||||
|
||||
**Also need ONNX Runtime** (`libonnxruntime.so`):
|
||||
|
||||
```sh
|
||||
curl -sL "https://github.com/microsoft/onnxruntime/releases/download/v1.15.1/onnxruntime-linux-x64-1.15.1.tgz" | tar xz
|
||||
sudo cp onnxruntime-linux-x64-1.15.1/lib/libonnxruntime.so* /usr/local/lib/
|
||||
```
|
||||
|
||||
**Configure in `deploy/mavend.json`**:
|
||||
|
||||
```json
|
||||
"voice": {
|
||||
"embedder": {
|
||||
"model_path": "models/embedder/model_quantized.onnx",
|
||||
"tokenizer_path": "models/embedder/tokenizer.json",
|
||||
"lib_path": "/usr/local/lib/libonnxruntime.so"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
Without the embedder block, the daemon uses `HashEmbedder` (works, but weak on
|
||||
Russian recall — you may see many "clarify" responses).
|
||||
|
||||
## Web UI conventions
|
||||
|
||||
- All server-rendered pages share `cmd/mavweb/static/ui.css` (served at
|
||||
|
||||
@@ -8,7 +8,7 @@ PIPER_BIN := $(shell pwd)/deps/piper/piper
|
||||
PIPER_MODEL := $(shell pwd)/models/tts/ru_RU-irina-medium.onnx
|
||||
PIPER_ESPEAK := $(shell pwd)/deps/piper/espeak-ng-data
|
||||
|
||||
.PHONY: all build build-stt build-tts build-daemon build-client build-web build-poll build-caldav clean test run-stt run-tts run-web
|
||||
.PHONY: all build build-stt build-tts build-daemon build-client build-web build-poll build-caldav clean test run-stt run-tts run-web download-embedder
|
||||
|
||||
all: build
|
||||
|
||||
@@ -71,5 +71,30 @@ deps-piper:
|
||||
-o /tmp/piper.tar.gz
|
||||
tar -xzf /tmp/piper.tar.gz -C deps/
|
||||
|
||||
EMBEDDER_DIR := $(shell pwd)/models/embedder
|
||||
EMBEDDER_MODEL_URL := https://huggingface.co/Xenova/paraphrase-multilingual-MiniLM-L12-v2/resolve/main/onnx/model_quantized.onnx
|
||||
EMBEDDER_TOKENIZER_URL := https://huggingface.co/Xenova/paraphrase-multilingual-MiniLM-L12-v2/resolve/main/tokenizer.json
|
||||
|
||||
download-embedder:
|
||||
mkdir -p $(EMBEDDER_DIR)
|
||||
curl -sL "$(EMBEDDER_MODEL_URL)" -o "$(EMBEDDER_DIR)/model_quantized.onnx"
|
||||
curl -sL "$(EMBEDDER_TOKENIZER_URL)" -o "$(EMBEDDER_DIR)/tokenizer.json"
|
||||
@echo ""
|
||||
@echo "embedder model downloaded to $(EMBEDDER_DIR)/"
|
||||
@echo "To use it, add to mavend.json:"
|
||||
@echo ' "voice": {'
|
||||
@echo ' ...'
|
||||
@echo ' "embedder": {'
|
||||
@echo ' "model_path": "$(EMBEDDER_DIR)/model_quantized.onnx",'
|
||||
@echo ' "tokenizer_path": "$(EMBEDDER_DIR)/tokenizer.json",'
|
||||
@echo ' "lib_path": "/path/to/libonnxruntime.so"'
|
||||
@echo ' }'
|
||||
@echo ' }'
|
||||
@echo ""
|
||||
@echo "Install libonnxruntime.so from: https://github.com/microsoft/onnxruntime/releases"
|
||||
@echo "e.g. on x86_64 Linux:"
|
||||
@echo ' curl -sL "https://github.com/microsoft/onnxruntime/releases/download/v1.15.1/onnxruntime-linux-x64-1.15.1.tgz" | tar xz'
|
||||
@echo ' sudo cp onnxruntime-linux-x64-1.15.1/lib/libonnxruntime.so* /usr/local/lib/'
|
||||
|
||||
clean:
|
||||
rm -f mavend mavenclient mavsttd mavttsd mavweb mavpoll mavcaldav
|
||||
|
||||
@@ -213,6 +213,7 @@ func run(args []string) error {
|
||||
NGpuLayers: cfg.Phraser.NGpuLayers,
|
||||
NCtx: cfg.Phraser.NCtx,
|
||||
Timeout: time.Duration(cfg.Phraser.Timeout),
|
||||
Persona: personaFromCfg(cfg),
|
||||
}
|
||||
if pc.BinPath == "" {
|
||||
pc.BinPath = "llama-server"
|
||||
@@ -364,6 +365,7 @@ func run(args []string) error {
|
||||
NGpuLayers: cfg.Phraser.NGpuLayers,
|
||||
NCtx: cfg.Phraser.NCtx,
|
||||
Timeout: time.Duration(cfg.Phraser.Timeout),
|
||||
Persona: personaFromCfg(cfg),
|
||||
}
|
||||
if pc.BinPath == "" {
|
||||
pc.BinPath = "llama-server"
|
||||
@@ -494,3 +496,13 @@ func run(args []string) error {
|
||||
log.Printf("mavend: bye")
|
||||
return nil
|
||||
}
|
||||
|
||||
// personaFromCfg extracts the voice persona from the config, or returns ""
|
||||
// when voice isn't configured. Used to pass a character prompt into the
|
||||
// LLM phraser without requiring voice to be enabled.
|
||||
func personaFromCfg(cfg *config.Config) string {
|
||||
if cfg.Voice != nil {
|
||||
return cfg.Voice.Persona
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
+9
-7
@@ -228,6 +228,7 @@ func wireVoice(cfg *config.Config, coreAPI ipc.CoreAPI, phr phraser.Phraser, mem
|
||||
weatherLocation: weatherLocation,
|
||||
memStore: memStore,
|
||||
dialogueSessions: dialogueSessions,
|
||||
queryMinScore: cfg.Voice.QueryMinScore,
|
||||
}
|
||||
|
||||
// ----- the server (TCP listener) -----
|
||||
@@ -261,6 +262,12 @@ type reactiveHandler struct {
|
||||
|
||||
memStore memory.Store
|
||||
|
||||
// queryMinScore — the note-recall confidence gate. Top cosine below this ⇒
|
||||
// "I don't know" instead of a guess. Tuned for the ONNX embedder; a knob, not
|
||||
// load-bearing math (same posture as the presence thresholds). Set by
|
||||
// wireVoice from VoiceConfig; default 0.55.
|
||||
queryMinScore float64
|
||||
|
||||
// dialogueSessions carries slots across turns for follow-ups (single-user
|
||||
// box → one session slot, keyed voiceDialogueID). nil ⇒ no carry-over.
|
||||
dialogueSessions *dialogue.SessionStore
|
||||
@@ -376,11 +383,6 @@ func (h *reactiveHandler) HandlePushToTalk(ctx context.Context, req voice.PushTo
|
||||
// returns a non-empty string when the action path wants to OVERRIDE the
|
||||
// reply text (e.g. an action error the user should hear SPECIFICALLY, not
|
||||
// a generic "ok"). Errors surface as a short reply text the user hears.
|
||||
// queryMinScore — the note-recall confidence gate. Top cosine below this ⇒
|
||||
// "no note" instead of a guess. Hand-tuned for the ONNX embedder; a knob, not
|
||||
// load-bearing math (same posture as the presence thresholds).
|
||||
const queryMinScore = 0.55
|
||||
|
||||
func (h *reactiveHandler) applyAction(ctx context.Context, dec router.Decision) string {
|
||||
if dec.Clarify {
|
||||
return "" // the Replier phrases clarify
|
||||
@@ -541,13 +543,13 @@ func (h *reactiveHandler) applyAction(ctx context.Context, dec router.Decision)
|
||||
// a gap (spec's "not a guesser-of-truth"). Same instinct as the loop's
|
||||
// since(key)==null → don't fire. Tuned for the ONNX embedder; the Hash
|
||||
// floor scores lexically and may rarely clear it.
|
||||
if len(notes) == 0 || notes[0].Score < queryMinScore {
|
||||
if len(notes) == 0 || notes[0].Score < h.queryMinScore {
|
||||
// Long-term memory recall (notes + facts) before general knowledge:
|
||||
// the notes table can't answer fact questions, but the memory store
|
||||
// indexes both. Only runs when notes-RAG already gave up → additive.
|
||||
if h.memStore != nil {
|
||||
if hits, herr := h.memStore.Search(ctx, vec, 3); herr == nil {
|
||||
if text, ok := bestRecall(hits, queryMinScore); ok {
|
||||
if text, ok := bestRecall(hits, h.queryMinScore); ok {
|
||||
return text
|
||||
}
|
||||
}
|
||||
|
||||
@@ -189,6 +189,18 @@ type VoiceConfig struct {
|
||||
// Default 0.35 if unset.
|
||||
RouterThreshold float64 `json:"router_threshold,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
|
||||
// default if unset.
|
||||
QueryMinScore float64 `json:"query_min_score,omitempty"`
|
||||
|
||||
// Persona — optional prompt prefix that tunes maven's character. Prepended
|
||||
// to every LLM system prompt (nudge phrasing, note queries, general
|
||||
// knowledge). Empty string ⇒ current hardcoded persona (feminine-gendered
|
||||
// Russian self-reference). Example: "Be formal and answer in English only."
|
||||
Persona string `json:"persona,omitempty"`
|
||||
|
||||
// Weather — the weather provider config. nil ⇒ the daemon wires
|
||||
// the stub provider (returns ErrNotConfigured — "погода не настроена").
|
||||
// Set provider to "open-meteo" to use the keyless Open-Meteo API.
|
||||
@@ -309,6 +321,7 @@ const (
|
||||
DefaultRepeatInterval = 5 * time.Minute
|
||||
DefaultAutotuneInterval = 10 * time.Minute
|
||||
DefaultRouterThreshold = 0.35
|
||||
DefaultQueryMinScore = 0.55
|
||||
DefaultToolTimeout = 30 * time.Second
|
||||
)
|
||||
|
||||
@@ -379,6 +392,9 @@ func (c *Config) applyDefaults() {
|
||||
if c.Voice.RouterThreshold <= 0 {
|
||||
c.Voice.RouterThreshold = DefaultRouterThreshold
|
||||
}
|
||||
if c.Voice.QueryMinScore <= 0 {
|
||||
c.Voice.QueryMinScore = DefaultQueryMinScore
|
||||
}
|
||||
if c.Voice.ToolTimeout <= 0 {
|
||||
c.Voice.ToolTimeout = Duration(DefaultToolTimeout)
|
||||
}
|
||||
|
||||
+16
-3
@@ -281,9 +281,10 @@ type Server struct {
|
||||
api atomic.Value // stores CoreAPI
|
||||
path string
|
||||
|
||||
ln net.Listener
|
||||
wg sync.WaitGroup
|
||||
done chan struct{}
|
||||
ln net.Listener
|
||||
wg sync.WaitGroup
|
||||
done chan struct{}
|
||||
accept sync.Mutex // guards wg.Add vs Close's wg.Wait sequence
|
||||
|
||||
// Check — optional authorization hook. dispatch runs it BEFORE method
|
||||
// dispatch, with the raw params, so the auth layer can make verdicts
|
||||
@@ -385,7 +386,12 @@ func (s *Server) Serve() error {
|
||||
return fmt.Errorf("ipc: accept: %w", err)
|
||||
}
|
||||
}
|
||||
// wg.Add under accept mutex so Close's wg.Wait (also under accept) sees
|
||||
// a consistent counter — a connection accepted just before Close closes
|
||||
// the listener must be tracked before Wait starts.
|
||||
s.accept.Lock()
|
||||
s.wg.Add(1)
|
||||
s.accept.Unlock()
|
||||
go func(c net.Conn) {
|
||||
defer s.wg.Done()
|
||||
defer c.Close()
|
||||
@@ -747,7 +753,14 @@ func (s *Server) Close() error {
|
||||
close(s.done)
|
||||
}
|
||||
err := s.ln.Close()
|
||||
// Under accept lock: after the listener closes, no new Accept can complete,
|
||||
// so no new wg.Add will be called. The Wait is safe to observe the wg
|
||||
// counter because any in-flight Accept that already got a conn either
|
||||
// already called wg.Add (before releasing the lock) or will see the closed
|
||||
// listener error and not call wg.Add at all.
|
||||
s.accept.Lock()
|
||||
s.wg.Wait()
|
||||
s.accept.Unlock()
|
||||
_ = os.Remove(s.path)
|
||||
return err
|
||||
}
|
||||
|
||||
@@ -37,6 +37,7 @@ type Config struct {
|
||||
NGpuLayers int
|
||||
NCtx int
|
||||
Timeout time.Duration
|
||||
Persona string // optional prompt prefix tuning maven's character
|
||||
}
|
||||
|
||||
func DefaultConfig(modelPath string) Config {
|
||||
@@ -185,7 +186,7 @@ func (p *LLMPhraser) PhraseQuery(ctx context.Context, utterance string, notes []
|
||||
if len(notes) == 1 {
|
||||
notes[0] = strings.TrimSpace(notes[0])
|
||||
}
|
||||
sys := "You are maven, a self-hosted personal assistant answering from your notes. Answer briefly and naturally in Russian starting with \"вот что я нашла: \". Respond with just the answer text, no JSON wrapper."
|
||||
sys := p.querySystemPrompt()
|
||||
prompt := fmt.Sprintf(
|
||||
`The user asks: "%s". Your notes matching the query contain: "%s". Answer them naturally and briefly. If the notes don't answer the question, say so.`,
|
||||
utterance, strings.Join(notes, `"; "`),
|
||||
@@ -248,7 +249,7 @@ type chatResp struct {
|
||||
}
|
||||
|
||||
func (p *LLMPhraser) chat(ctx context.Context, userPrompt string) (string, error) {
|
||||
return p.chatWithSystem(ctx, systemPrompt(), userPrompt, 256)
|
||||
return p.chatWithSystem(ctx, p.systemPrompt(), userPrompt, 256)
|
||||
}
|
||||
|
||||
func (p *LLMPhraser) chatWithSystem(ctx context.Context, system, user string, maxTokens int) (string, error) {
|
||||
@@ -295,8 +296,22 @@ func (p *LLMPhraser) chatWithSystem(ctx context.Context, system, user string, ma
|
||||
return cr.Choices[0].Message.Content, nil
|
||||
}
|
||||
|
||||
func systemPrompt() string {
|
||||
return `You are maven, a self-hosted personal assistant. Generate brief, natural nudge messages in the user's language (Russian or English). Respond ONLY with valid JSON: {"body": "full voice message", "summary": "brief away-channel version (<60 chars)"}. body is what the user hears on voice; summary is for push notifications (ntfy/telegram) — minimal, no exfil detail.`
|
||||
func (p *LLMPhraser) systemPrompt() string {
|
||||
base := `You are maven, a self-hosted personal assistant. Generate brief, natural nudge messages in the user's language (Russian or English). Respond ONLY with valid JSON: {"body": "full voice message", "summary": "brief away-channel version (<60 chars)"}. body is what the user hears on voice; summary is for push notifications (ntfy/telegram) — minimal, no exfil detail.`
|
||||
if p.cfg.Persona != "" {
|
||||
base = p.cfg.Persona + "\n\n" + base
|
||||
}
|
||||
return base
|
||||
}
|
||||
|
||||
// querySystemPrompt returns the system prompt for PhraseQuery (notes + general
|
||||
// knowledge). Prepends the configured persona when set.
|
||||
func (p *LLMPhraser) querySystemPrompt() string {
|
||||
base := "You are maven, a self-hosted personal assistant answering from your notes. Answer briefly and naturally in Russian starting with \"вот что я нашла: \". Respond with just the answer text, no JSON wrapper."
|
||||
if p.cfg.Persona != "" {
|
||||
base = p.cfg.Persona + "\n\n" + base
|
||||
}
|
||||
return base
|
||||
}
|
||||
|
||||
func buildNudgePrompt(c loop.Candidate) string {
|
||||
|
||||
Reference in New Issue
Block a user