fix zombie leak, add quiet-hours toggle, improve query reply, configurable router threshold, JS dashboard
This commit is contained in:
kami
@@ -0,0 +1,212 @@
|
||||
// Package main is mavend — maven's daemon.
|
||||
//
|
||||
// "core = the only key-holder": one process holds the unlocked store + the
|
||||
// trigger loop; modules are separate processes, key-free, fail-independent.
|
||||
// the daemon wires Store → Gatherer → Tick → phraser → delivery, runs the 60s
|
||||
// ticker, owns the cold-start unlock dance, and exposes the CoreAPI boundary
|
||||
// over a unix socket for modules (router/delivery/poller/...) to call.
|
||||
//
|
||||
// Floor (this file): pluggable seams wired with the deterministic Stubs.
|
||||
// - phraser Stub (no LLM)
|
||||
// - voice sink wired via wireVoice: embedder/classifier seeded with ~10
|
||||
// examples across 5 intents; stt + tts stubs in-process by default,
|
||||
// remote module sockets when configured; TCP listener on voice.bind.
|
||||
// The voice sink (voicesink.Sink via Sessions) is wired into the
|
||||
// dispatcher — the reactive path (push-to-talk) AND proactive nudges
|
||||
// (care-when-present, sev3/sev4 present) both route through the same
|
||||
// stt→router→tts→client pipeline.
|
||||
// - auth FloorEnrollment + nil Session — cold-start unlock assumed: today
|
||||
// the store opens plain sqlite (sqlcipher deferred). the daemon runs
|
||||
// "unlocked" — the locked-until-asserted dance lands with the Session
|
||||
// verifier + ask-password transport (open spec item).
|
||||
//
|
||||
// Everything wired here is swappable at the construction seam — every module
|
||||
// behind an interface — without changing the loop. Wire a real phraser, voice
|
||||
// sink, or session verifier, and the daemon's main loop is unchanged.
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"flag"
|
||||
"fmt"
|
||||
"log"
|
||||
"net"
|
||||
"os"
|
||||
"os/signal"
|
||||
"sync"
|
||||
"syscall"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/auth"
|
||||
"github.com/kami/maven/internal/config"
|
||||
"github.com/kami/maven/internal/delivery"
|
||||
"github.com/kami/maven/internal/delivery/ntfysink"
|
||||
"github.com/kami/maven/internal/delivery/telegramsink"
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/loop"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
func main() {
|
||||
if err := run(os.Args[1:]); err != nil {
|
||||
fmt.Fprintln(os.Stderr, "mavend:", err)
|
||||
os.Exit(1)
|
||||
}
|
||||
}
|
||||
|
||||
func run(args []string) error {
|
||||
cfgPath := flag.String("config", defaultConfigPath(), "path to mavend JSON config")
|
||||
flag.CommandLine.Parse(args)
|
||||
cfg, err := config.Load(*cfgPath)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
ctx, stop := signal.NotifyContext(context.Background(), syscall.SIGINT, syscall.SIGTERM, syscall.SIGHUP)
|
||||
defer stop()
|
||||
|
||||
// ----- store (the unlocked handle; core = the only key-holder) -----
|
||||
st, err := store.Open(ctx, cfg.DBPath)
|
||||
if err != nil {
|
||||
return fmt.Errorf("open store: %w", err)
|
||||
}
|
||||
defer st.Close()
|
||||
|
||||
// ----- loop: rules + gatherer -----
|
||||
|
||||
rules := loop.DefaultRules()
|
||||
gatherer := loop.NewGatherer(st, rules)
|
||||
|
||||
// ----- phraser (LLM-backed when configured, Stub floor otherwise) -----
|
||||
var phr phraser.Phraser = phraser.NewStub()
|
||||
if cfg.Phraser != nil {
|
||||
pc := phraser.Config{
|
||||
ModelPath: cfg.Phraser.ModelPath,
|
||||
BinPath: cfg.Phraser.BinPath,
|
||||
Listen: cfg.Phraser.Listen,
|
||||
NGpuLayers: cfg.Phraser.NGpuLayers,
|
||||
NCtx: cfg.Phraser.NCtx,
|
||||
Timeout: time.Duration(cfg.Phraser.Timeout),
|
||||
}
|
||||
if pc.BinPath == "" {
|
||||
pc.BinPath = "llama-server"
|
||||
}
|
||||
if pc.Listen == "" {
|
||||
pc.Listen = "127.0.0.1:0"
|
||||
}
|
||||
if pc.NCtx <= 0 {
|
||||
pc.NCtx = 2048
|
||||
}
|
||||
if pc.Timeout <= 0 {
|
||||
pc.Timeout = 30 * time.Second
|
||||
}
|
||||
var err error
|
||||
phr, err = phraser.NewLLMPhraser(ctx, pc)
|
||||
if err != nil {
|
||||
return fmt.Errorf("phraser: %w", err)
|
||||
}
|
||||
}
|
||||
defer phr.Close()
|
||||
|
||||
// ----- voice: reactive audio path (TCP listener + stt/router/tts) -----
|
||||
voiceW, err := wireVoice(cfg, ipc.NewStoreAPI(st))
|
||||
if err != nil {
|
||||
return fmt.Errorf("wire voice: %w", err)
|
||||
}
|
||||
defer voiceW.close()
|
||||
|
||||
// ----- delivery: sinks + dispatcher -----
|
||||
var ntfy delivery.Sink
|
||||
if cfg.Ntfy != nil {
|
||||
s, err := ntfysink.New(*cfg.Ntfy)
|
||||
if err != nil {
|
||||
return fmt.Errorf("wire ntfy sink: %w", err)
|
||||
}
|
||||
ntfy = s
|
||||
}
|
||||
var telegram delivery.Sink
|
||||
if cfg.Telegram != nil {
|
||||
s, err := telegramsink.New(*cfg.Telegram)
|
||||
if err != nil {
|
||||
return fmt.Errorf("wire telegram sink: %w", err)
|
||||
}
|
||||
telegram = s
|
||||
}
|
||||
// Voice sink: nil when voice is not enabled — the dispatcher's nil-sink
|
||||
// path skips ChannelVoice silently, just like the pre-voice floor).
|
||||
var voiceSink delivery.Sink
|
||||
if voiceW != nil {
|
||||
voiceSink = voiceW.voiceSink
|
||||
}
|
||||
dispatcher := delivery.NewDispatcher(delivery.Config{
|
||||
Ntfy: ntfy,
|
||||
Telegram: telegram,
|
||||
Voice: voiceSink,
|
||||
// AckTracker nil ⇒ repeat-til-ack disabled in the dispatcher. We
|
||||
// drive repeats from store.UnackedTelegramRules + Dispatcher.RepeatUnacked
|
||||
// below, which uses the nudges table's outcome=pending row itself as
|
||||
// the ack-or-not state — the production ack source. The AckTracker
|
||||
// interface stays reserved for an in-memory cache if the daemon ever
|
||||
// wants to drive repeats without the SQL hit; the table IS the truth.
|
||||
Nudges: st, // *store.Store satisfies delivery.NudgeRecorder
|
||||
Reminders: st, // *store.Store satisfies delivery.ReminderCompleter
|
||||
})
|
||||
|
||||
// ----- the proactive loop driver (60s ticker, lives HERE per spec) -----
|
||||
tickInterval := time.Duration(cfg.TickInterval)
|
||||
repeatInterval := time.Duration(cfg.RepeatInterval)
|
||||
autotuneInterval := time.Duration(cfg.AutotuneInterval)
|
||||
loop := newTickLoop(st, gatherer, dispatcher, phr, rules, tickInterval, repeatInterval, autotuneInterval)
|
||||
|
||||
// ----- IPC boundary (core ↔ modules) -----
|
||||
coreAPI := ipc.NewStoreAPI(st)
|
||||
srv, err := ipc.Listen(cfg.SocketPath, coreAPI)
|
||||
if err != nil {
|
||||
return fmt.Errorf("ipc listen: %w", err)
|
||||
}
|
||||
// auth floor: any same-uid caller is fully trusted (FloorEnrollment +
|
||||
// FloorSession — L3, step-up satisfied). The cold-start unlock dance and a
|
||||
// real passkey Session are the open spec items; today the daemon runs
|
||||
// unlocked — plain sqlite, sqlcipher deferred. FloorSession keeps the floor
|
||||
// consistent so the authed mavweb /tools page can EnableTool (AuthStepUp)
|
||||
// against the local socket; the passkey verifier swaps FloorSession later.
|
||||
srv.Check = (&auth.Gate{Enrollment: auth.NewFloorEnrollment(), Session: auth.FloorSession{}}).Check
|
||||
|
||||
var wg sync.WaitGroup
|
||||
wg.Add(1)
|
||||
go func() {
|
||||
defer wg.Done()
|
||||
if err := srv.Serve(); err != nil && !errors.Is(err, net.ErrClosed) {
|
||||
log.Printf("ipc serve: %v", err)
|
||||
}
|
||||
}()
|
||||
log.Printf("mavend: ipc listening on %s", srv.Path())
|
||||
|
||||
if voiceW != nil {
|
||||
wg.Add(1)
|
||||
go func() {
|
||||
defer wg.Done()
|
||||
if err := voiceW.server.Serve(); err != nil && !errors.Is(err, net.ErrClosed) {
|
||||
log.Printf("voice serve: %v", err)
|
||||
}
|
||||
}()
|
||||
log.Printf("mavend: voice listening on %s", voiceW.server.Addr())
|
||||
}
|
||||
|
||||
wg.Add(1)
|
||||
go func() {
|
||||
defer wg.Done()
|
||||
loop.run(ctx)
|
||||
}()
|
||||
|
||||
<-ctx.Done()
|
||||
log.Printf("mavend: shutdown signal received")
|
||||
if err := srv.Close(); err != nil {
|
||||
log.Printf("ipc close: %v", err)
|
||||
}
|
||||
wg.Wait()
|
||||
log.Printf("mavend: bye")
|
||||
return nil
|
||||
}
|
||||
@@ -0,0 +1,43 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"database/sql"
|
||||
"fmt"
|
||||
"os"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
func main() {
|
||||
ctx := context.Background()
|
||||
st, err := store.Open(ctx, "/tmp/maven-test.db")
|
||||
if err != nil {
|
||||
fmt.Fprintln(os.Stderr, "open:", err)
|
||||
os.Exit(1)
|
||||
}
|
||||
defer st.Close()
|
||||
|
||||
now := time.Now()
|
||||
_, err = st.WriteFact(ctx, now.Add(-4*time.Hour), store.KindSelf, "water", "1", "tap:voice", 1.0, sql.NullInt64{})
|
||||
if err != nil {
|
||||
fmt.Fprintln(os.Stderr, "write water fact:", err)
|
||||
os.Exit(1)
|
||||
}
|
||||
fmt.Println("seeded water fact 4h ago")
|
||||
|
||||
_, err = st.WriteFact(ctx, now.Add(-time.Minute), store.KindSelf, "desk_active", "1", "presence", 1.0, sql.NullInt64{})
|
||||
if err != nil {
|
||||
fmt.Fprintln(os.Stderr, "write desk_active fact:", err)
|
||||
os.Exit(1)
|
||||
}
|
||||
fmt.Println("seeded desk_active (presence) 1m ago")
|
||||
|
||||
_, err = st.SetValue(ctx, store.KindConfig, "quiet_hours", "config", "false", now)
|
||||
if err != nil {
|
||||
fmt.Fprintln(os.Stderr, "write quiet_hours:", err)
|
||||
os.Exit(1)
|
||||
}
|
||||
fmt.Println("seeded quiet_hours=false")
|
||||
}
|
||||
@@ -0,0 +1,249 @@
|
||||
// mavend/tick.go — the proactive loop driver.
|
||||
//
|
||||
// Per spec the 60s schedule loop (`for { tick; sleep }`) lives in the daemon
|
||||
// main, NOT in `internal/loop/` — that keeps the loop package pure + unit-
|
||||
// testable without time side effects. the driver here is the ONE impure
|
||||
// orchestrator: it gathers state under the store lock, runs the pure Tick,
|
||||
// phrases the candidate, dispatches it, then handles reminders + sev4 repeats
|
||||
// and runs the feedback auto-tuner on its own slow cadence.
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"log"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/delivery"
|
||||
"github.com/kami/maven/internal/loop"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
// tickLoop — the impure driver. holds everything wired at daemon construction
|
||||
// that the per-tick path needs. the rules slice is read-only here; the gatherer
|
||||
// already captured it, but we keep it for a possible future re-seed path.
|
||||
type tickLoop struct {
|
||||
store *store.Store
|
||||
gatherer *loop.Gatherer
|
||||
dispatcher *delivery.Dispatcher
|
||||
phraser phraser.Phraser
|
||||
rules []loop.Rule
|
||||
|
||||
tickInterval time.Duration
|
||||
repeatInterval time.Duration
|
||||
autotuneInterval time.Duration // 0 ⇒ autotune disabled (gatherer falls back to static Base)
|
||||
|
||||
// lastPhrase caches the phraser output per rule so the sev4 repeat path
|
||||
// can re-send roughly what the user was first alerted with (an alarm
|
||||
// that re-phrases differently every 5m is hostile; the same terse body
|
||||
// IS the insistence signal). keyed by rule name. nil phrase for a rule
|
||||
// = no successful initial dispatch yet (cold-start edge — fall back to
|
||||
// a generic body).
|
||||
mu sync.Mutex
|
||||
lastPhrase map[string]delivery.PhrasedNudge
|
||||
}
|
||||
|
||||
func newTickLoop(
|
||||
st *store.Store,
|
||||
g *loop.Gatherer,
|
||||
d *delivery.Dispatcher,
|
||||
p phraser.Phraser,
|
||||
rules []loop.Rule,
|
||||
tickInterval, repeatInterval, autotuneInterval time.Duration,
|
||||
) *tickLoop {
|
||||
return &tickLoop{
|
||||
store: st,
|
||||
gatherer: g,
|
||||
dispatcher: d,
|
||||
phraser: p,
|
||||
rules: rules,
|
||||
tickInterval: tickInterval,
|
||||
repeatInterval: repeatInterval,
|
||||
autotuneInterval: autotuneInterval,
|
||||
lastPhrase: make(map[string]delivery.PhrasedNudge),
|
||||
}
|
||||
}
|
||||
|
||||
// run drives the loop until ctx is canceled. one tick per tickInterval;
|
||||
// the first tick fires immediately so a freshly-started daemon doesn't sit
|
||||
// idle for 60s before its first evaluation (cold-start responsiveness). the
|
||||
// feedback auto-tuner runs on its own slower ticker (autotuneInterval) so it
|
||||
// doesn't write a feedback fact every tick — append-only facts would churn.
|
||||
func (t *tickLoop) run(ctx context.Context) {
|
||||
t.tick(ctx, time.Now())
|
||||
ticker := time.NewTicker(t.tickInterval)
|
||||
defer ticker.Stop()
|
||||
|
||||
var autotune *time.Ticker
|
||||
var autotuneC <-chan time.Time
|
||||
if t.autotuneInterval > 0 {
|
||||
autotune = time.NewTicker(t.autotuneInterval)
|
||||
defer autotune.Stop()
|
||||
autotuneC = autotune.C
|
||||
}
|
||||
|
||||
for {
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
return
|
||||
case now := <-ticker.C:
|
||||
t.tick(ctx, now)
|
||||
case <-autotuneC:
|
||||
t.tune(ctx)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// tick — one pass of the proactive loop. gathers, decides, phrases, delivers.
|
||||
// errors at any sub-step are logged and the tick continues / aborts as the
|
||||
// layer warrants: a gather failure aborts (no consistent snapshot ⇒ no
|
||||
// decisions); a phrase/dispatch failure logs the failure and continues so a
|
||||
// transient delivery fault doesn't kill the whole loop.
|
||||
func (t *tickLoop) tick(ctx context.Context, now time.Time) {
|
||||
state, due, err := t.gatherer.GatherState(ctx, now)
|
||||
if err != nil {
|
||||
log.Printf("tick: gather: %v", err)
|
||||
return
|
||||
}
|
||||
|
||||
// proactive: at most one candidate, max severity.
|
||||
if cand := loop.Tick(state, t.rules); cand != nil {
|
||||
pn, err := t.phraser.PhraseNudge(ctx, *cand)
|
||||
if err != nil {
|
||||
log.Printf("tick: phrase nudge %s: %v", cand.Rule.Name, err)
|
||||
} else {
|
||||
t.cachePhrase(pn)
|
||||
if _, err := t.dispatcher.DispatchNudge(ctx, pn, now); err != nil {
|
||||
log.Printf("tick: dispatch nudge %s: %v", cand.Rule.Name, err)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// reminders: gate-bypassing class. fired once, marked after a successful
|
||||
// delivery. a failed send leaves the reminder pending — the next tick
|
||||
// re-gathers and re-attempts.
|
||||
for _, d := range loop.RemindDecisions(state, due) {
|
||||
pr, err := t.phraser.PhraseReminder(ctx, d)
|
||||
if err != nil {
|
||||
log.Printf("tick: phrase reminder %d: %v", d.Reminder.ID, err)
|
||||
continue
|
||||
}
|
||||
if _, err := t.dispatcher.DispatchReminder(ctx, pr, now); err != nil {
|
||||
log.Printf("tick: dispatch reminder %d: %v", d.Reminder.ID, err)
|
||||
}
|
||||
}
|
||||
|
||||
// sev4-away repeats: re-send un-acked telegram nudges per repeatInterval.
|
||||
// the source of ack truth IS the nudges table (outcome=pending ⇒ not
|
||||
// acked); store.UnackedTelegramRules surfaces the keys. body/summary come
|
||||
// from the cached phrase from the initial dispatch — see lastPhrase notes.
|
||||
// if not cached (cold-start mid-alarm), fall back to a terse generic body.
|
||||
keys, err := t.store.UnackedTelegramRules(ctx)
|
||||
if err != nil {
|
||||
log.Printf("tick: unacked telegram rules: %v", err)
|
||||
return
|
||||
}
|
||||
if len(keys) == 0 {
|
||||
return
|
||||
}
|
||||
for _, key := range keys {
|
||||
body, summary := t.repeatPhrase(key)
|
||||
if _, err := t.dispatcher.RepeatUnacked(ctx, []string{key}, now, t.repeatInterval, body, summary); err != nil {
|
||||
log.Printf("tick: repeat telegram %s: %v", key, err)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// cachePhrase keeps the latest phrased nudge per rule for the sev4-repeat
|
||||
// path. writing under a mutex; the repeat path reads under the same. the
|
||||
// cache is bounded by the rule count (≤ ~30 per spec) so eviction is not a
|
||||
// concern at this scale.
|
||||
func (t *tickLoop) cachePhrase(pn delivery.PhrasedNudge) {
|
||||
t.mu.Lock()
|
||||
t.lastPhrase[pn.Candidate.Rule.Name] = pn
|
||||
t.mu.Unlock()
|
||||
}
|
||||
|
||||
func (t *tickLoop) repeatPhrase(rule string) (body, summary string) {
|
||||
t.mu.Lock()
|
||||
pn, ok := t.lastPhrase[rule]
|
||||
t.mu.Unlock()
|
||||
if !ok || pn.Summary == "" {
|
||||
// cold-start mid-alarm: no cached phrase. a deliberately terse generic
|
||||
// body — the alarm IS the insistence; the wording repeats, the ring
|
||||
// is what changes. the LLM phraser impl will refresh this on its next
|
||||
// tick when the rule re-fires through Tick.
|
||||
return fmt.Sprintf("maven: %s still active", rule), rule
|
||||
}
|
||||
return pn.Body, pn.Summary
|
||||
}
|
||||
|
||||
// tune — the feedback auto-tuner's impure step. runs on a slow cadence
|
||||
// (autotuneInterval, see run) so it doesn't write a fact every tick. for each
|
||||
// rule:
|
||||
// 1. read store.RecentOutcomes for the last TuneSampleN resolved outcomes.
|
||||
// 2. if there's not enough signal (TuneMinOutcomes), leave Base alone.
|
||||
// 3. compute the tuned cooldown with loop.TuneCooldown (pure).
|
||||
// 4. read the currently-persisted feedback fact; if the tuned value equals
|
||||
// it, skip the write (RecentOutcomes is itself steady ⇒ no churn).
|
||||
// 5. else write a `facts (kind=config, source=feedback, key=cooldown:<rule>)`
|
||||
// row. the Gatherer reads it next tick.
|
||||
//
|
||||
// Error at any step logs + continues to the next rule — a transient store
|
||||
// fault on one rule must not abort tuning for the rest.
|
||||
func (t *tickLoop) tune(ctx context.Context) {
|
||||
now := time.Now()
|
||||
for _, r := range t.rules {
|
||||
outcomes, err := t.store.RecentOutcomes(ctx, r.Name, loop.TuneSampleN)
|
||||
if err != nil {
|
||||
log.Printf("tune: outcomes %s: %v", r.Name, err)
|
||||
continue
|
||||
}
|
||||
if len(outcomes) < loop.TuneMinOutcomes {
|
||||
continue // sparse — no signal yet, don't whipsaw on first sight.
|
||||
}
|
||||
tuned := loop.TuneCooldown(r, outcomes)
|
||||
|
||||
// the currently-persisted tuned base, if any. equal ⇒ skip the write
|
||||
// (RecentOutcomes is monotone-steady between resolved outcomes).
|
||||
if cur, ok := t.currentTunedBase(ctx, r); ok && cur == tuned {
|
||||
continue
|
||||
}
|
||||
if _, err := t.store.SetValue(
|
||||
ctx, store.KindConfig, loop.FeedbackKey(r), loop.FeedbackSource,
|
||||
tuned, now,
|
||||
); err != nil {
|
||||
log.Printf("tune: persist %s: %v", r.Name, err)
|
||||
continue
|
||||
}
|
||||
log.Printf("tune: %s cooldown -> %v", r.Name, tuned)
|
||||
}
|
||||
}
|
||||
|
||||
// currentTunedBase — read the persisted feedback cooldown fact back into a
|
||||
// duration. (dur, false) when no feedback fact exists yet OR it's malformed;
|
||||
// the caller treats that as "differ from anything we'd write — write."
|
||||
func (t *tickLoop) currentTunedBase(ctx context.Context, r loop.Rule) (time.Duration, bool) {
|
||||
f, err := t.store.LatestFactBySource(ctx, loop.FeedbackKey(r), loop.FeedbackSource)
|
||||
if err != nil {
|
||||
return 0, false
|
||||
}
|
||||
return loop.ParseCooldownFact(f)
|
||||
}
|
||||
|
||||
// defaultConfigPath — the config file path the daemon loads if -config wasn't
|
||||
// passed. XDG_CONFIG_HOME/maven/mavend.json, falling back to ~/.config/maven.
|
||||
func defaultConfigPath() string {
|
||||
if x := os.Getenv("XDG_CONFIG_HOME"); x != "" {
|
||||
return filepath.Join(x, "maven", "mavend.json")
|
||||
}
|
||||
home, err := os.UserHomeDir()
|
||||
if err != nil || home == "" {
|
||||
return "mavend.json"
|
||||
}
|
||||
return filepath.Join(home, ".config", "maven", "mavend.json")
|
||||
}
|
||||
@@ -0,0 +1,288 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"path/filepath"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/delivery"
|
||||
"github.com/kami/maven/internal/loop"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
// fakeSink — captures every Send for assertion. implements delivery.Sink.
|
||||
type fakeSink struct {
|
||||
sends []delivery.Sendable
|
||||
}
|
||||
|
||||
func (f *fakeSink) Send(_ context.Context, s delivery.Sendable) error {
|
||||
f.sends = append(f.sends, s)
|
||||
return nil
|
||||
}
|
||||
|
||||
func newTestStore(t *testing.T) *store.Store {
|
||||
t.Helper()
|
||||
path := filepath.Join(t.TempDir(), "mavend_test.db")
|
||||
st, err := store.Open(context.Background(), path)
|
||||
if err != nil {
|
||||
t.Fatalf("store.Open: %v", err)
|
||||
}
|
||||
t.Cleanup(func() { _ = st.Close() })
|
||||
return st
|
||||
}
|
||||
|
||||
func newTestTickLoop(t *testing.T, st *store.Store, sink delivery.Sink) *tickLoop {
|
||||
t.Helper()
|
||||
rules := loop.DefaultRules()
|
||||
g := loop.NewGatherer(st, rules)
|
||||
d := delivery.NewDispatcher(delivery.Config{
|
||||
Voice: sink,
|
||||
Ntfy: sink,
|
||||
Telegram: sink,
|
||||
Nudges: st,
|
||||
Reminders: st,
|
||||
})
|
||||
return newTickLoop(st, g, d, phraser.NewStub(), rules, time.Second, 5*time.Minute, 0)
|
||||
}
|
||||
|
||||
// refNow — fixed tick time so presence decay + since durations are deterministic.
|
||||
func refNow() time.Time { return time.Date(2026, 6, 30, 12, 0, 0, 0, time.UTC) }
|
||||
|
||||
// markPresent seeds desk_active + page_heartbeat with fresh ts so presence
|
||||
// resolves to Present for the given tick time (cold-start is away; ENTER at
|
||||
// 0.55 — a fresh desk_active alone gives 0.90, well over).
|
||||
func markPresent(t *testing.T, st *store.Store, ctx context.Context, now time.Time) {
|
||||
t.Helper()
|
||||
for _, key := range []string{"desk_active", "page_heartbeat"} {
|
||||
if _, err := st.SetValue(ctx, store.KindSelf, key, "tap:desk", map[string]bool{key: true}, now); err != nil {
|
||||
t.Fatalf("seed %s: %v", key, err)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestTickColdStoreSendsNothing(t *testing.T) {
|
||||
// The "shuts up when uncertain" floor: no facts ⇒ every rule's
|
||||
// InertWhenNoData keys are missing ⇒ gate skips them. the loop's silence
|
||||
// is the default outcome of a tick on an empty store.
|
||||
st := newTestStore(t)
|
||||
ctx := context.Background()
|
||||
sink := &fakeSink{}
|
||||
tl := newTestTickLoop(t, st, sink)
|
||||
|
||||
tl.tick(ctx, refNow())
|
||||
|
||||
if len(sink.sends) != 0 {
|
||||
t.Fatalf("cold-store tick sent %d; want 0 (shuts up when no data)", len(sink.sends))
|
||||
}
|
||||
}
|
||||
|
||||
func TestTickWaterFiresWhenDueAndPresent(t *testing.T) {
|
||||
// water fact 4h ago ⇒ since(water)=4h ≥ 3h ⇒ predicate true. presence
|
||||
// present ⇒ sev1 care gate holds (no quiet/cal/cooldown). routing for
|
||||
// sev1 present is [voice] — one send captured.
|
||||
st := newTestStore(t)
|
||||
ctx := context.Background()
|
||||
now := refNow()
|
||||
markPresent(t, st, ctx, now)
|
||||
if _, err := st.SetValue(ctx, store.KindSelf, "water", "tap:water", map[string]int{"ml": 0}, now.Add(-4*time.Hour)); err != nil {
|
||||
t.Fatalf("seed water: %v", err)
|
||||
}
|
||||
sink := &fakeSink{}
|
||||
tl := newTestTickLoop(t, st, sink)
|
||||
|
||||
tl.tick(ctx, now)
|
||||
|
||||
if len(sink.sends) != 1 {
|
||||
t.Fatalf("tick sends = %d, want 1 (water, voice only)", len(sink.sends))
|
||||
}
|
||||
if got, want := sink.sends[0].RuleName, "water"; got != want {
|
||||
t.Errorf("send rule = %q, want %q", got, want)
|
||||
}
|
||||
if got, want := sink.sends[0].Channel, delivery.ChannelVoice; got != want {
|
||||
t.Errorf("send channel = %v, want voice (sev1 present)", got)
|
||||
}
|
||||
if sink.sends[0].Body == "" {
|
||||
t.Error("phraser Stub produced an empty body for the water nudge")
|
||||
}
|
||||
|
||||
// one nudge row recorded with channel=voice — verify the dispatch path
|
||||
// wrote through to the store (the feedback loop's only input). RecentOutcomes
|
||||
// filters to resolved rows, so confirm the recorded nudge exists via LastNudge.
|
||||
n, err := st.LastNudge(ctx, "water")
|
||||
if err != nil {
|
||||
t.Fatalf("LastNudge: %v", err)
|
||||
}
|
||||
if n.Channel != string(delivery.ChannelVoice) {
|
||||
t.Errorf("recorded nudge channel = %q, want %q", n.Channel, delivery.ChannelVoice)
|
||||
}
|
||||
}
|
||||
|
||||
func TestTickCooldownSuppressesSecondSend(t *testing.T) {
|
||||
// After a water nudge, the gate's cooldown (DefaultRules sets water
|
||||
// base cooldown = 30m) suppresses the same rule on the next tick.
|
||||
st := newTestStore(t)
|
||||
ctx := context.Background()
|
||||
now := refNow()
|
||||
markPresent(t, st, ctx, now)
|
||||
if _, err := st.SetValue(ctx, store.KindSelf, "water", "tap:water", map[string]int{"ml": 0}, now.Add(-4*time.Hour)); err != nil {
|
||||
t.Fatalf("seed water: %v", err)
|
||||
_ = err
|
||||
}
|
||||
sink := &fakeSink{}
|
||||
tl := newTestTickLoop(t, st, sink)
|
||||
|
||||
tl.tick(ctx, now) // fires
|
||||
tl.tick(ctx, now.Add(time.Minute)) // still within 30m cooldown ⇒ suppressed
|
||||
|
||||
if len(sink.sends) != 1 {
|
||||
t.Fatalf("sends after second tick = %d, want 1 (cooldown should suppress)", len(sink.sends))
|
||||
}
|
||||
}
|
||||
|
||||
func TestTickReminderFiresOnceAndMarkedFired(t *testing.T) {
|
||||
// A due reminder bypasses the gate. away (no presence probes ⇒ cold
|
||||
// start away) routes the reminder to [ntfy]. the dispatcher marks the
|
||||
// reminder fired only after at least one channel succeeded; verify by
|
||||
// re-ticking and confirming it isn't re-dispatched (DueReminders returns
|
||||
// only `status == pending AND fire_ts <= now`).
|
||||
st := newTestStore(t)
|
||||
ctx := context.Background()
|
||||
now := refNow()
|
||||
if _, err := st.CreateReminder(ctx, now.Add(-time.Minute), `{"text":"stand up"}`); err != nil {
|
||||
t.Fatalf("CreateReminder: %v", err)
|
||||
}
|
||||
sink := &fakeSink{}
|
||||
tl := newTestTickLoop(t, st, sink)
|
||||
|
||||
tl.tick(ctx, now)
|
||||
if got, want := len(sink.sends), 1; got != want {
|
||||
t.Fatalf("reminder tick sends = %d, want 1 (away → ntfy)", got)
|
||||
}
|
||||
if sink.sends[0].Channel != delivery.ChannelNtfy {
|
||||
t.Errorf("reminder channel = %v, want ntfy (away)", sink.sends[0].Channel)
|
||||
}
|
||||
if sink.sends[0].Body != "stand up" {
|
||||
t.Errorf("reminder body = %q, want %q (router payload text)", sink.sends[0].Body, "stand up")
|
||||
}
|
||||
if sink.sends[0].Kind != delivery.KindReminder {
|
||||
t.Errorf("reminder kind = %v, want %v", sink.sends[0].Kind, delivery.KindReminder)
|
||||
}
|
||||
|
||||
// re-tick: the reminder is no longer pending (marked fired) ⇒ not in
|
||||
// DueReminders ⇒ the reminder path is silent.
|
||||
sink.sends = nil
|
||||
tl.tick(ctx, now.Add(time.Minute))
|
||||
if len(sink.sends) != 0 {
|
||||
t.Fatalf("second reminder tick sends = %d, want 0 (fired once)", len(sink.sends))
|
||||
}
|
||||
}
|
||||
|
||||
// TestTuneWritesFeedbackCooldownToStore — the daemon's impure tune() step end
|
||||
// to end: seed a rule with ≥ TuneMinOutcomes resolved `ignored` outcomes,
|
||||
// call tune(), assert it wrote a `cooldown:<rule>` (source=feedback) fact that
|
||||
// the gatherer then reads back as the active cooldown base. This is the closed
|
||||
// feedback loop: outcomes → tune → write → gather → gate sees the tuned base.
|
||||
func TestTuneWritesFeedbackCooldownToStore(t *testing.T) {
|
||||
st := newTestStore(t)
|
||||
ctx := context.Background()
|
||||
now := refNow()
|
||||
|
||||
sink := &fakeSink{}
|
||||
tl := newTestTickLoop(t, st, sink)
|
||||
|
||||
// seed enough resolved `ignored` nudge outcomes to trip the tuner (above
|
||||
// TuneMinOutcomes). all-ignored ⇒ factor 1.5 ⇒ base × 1.5; clamped to Max.
|
||||
r := loop.WaterRule()
|
||||
for i := 0; i < loop.TuneSampleN; i++ {
|
||||
id, err := st.RecordNudge(ctx, r.Name, "voice", "drink water", now.Add(-time.Hour))
|
||||
if err != nil {
|
||||
t.Fatalf("RecordNudge %d: %v", i, err)
|
||||
}
|
||||
if err := st.ResolveNudge(ctx, id, store.NudgeIgnored, now); err != nil {
|
||||
t.Fatalf("ResolveNudge %d: %v", i, err)
|
||||
}
|
||||
}
|
||||
|
||||
tl.tune(ctx)
|
||||
|
||||
// the gatherer should now use the tuned base (clamped to WaterRule.Max =
|
||||
// 6h) as the cooldown base for `water`. verify via the cooldown-until
|
||||
// field by seeding a water nudge + asserting cooldown = sendTs + Max.
|
||||
// (we read the persisted tuned base directly rather than going via gather
|
||||
// so the assertion isolates tune()'s write from the gatherer path.)
|
||||
fb, err := st.LatestFactBySource(ctx, loop.FeedbackKey(r), loop.FeedbackSource)
|
||||
if err != nil {
|
||||
t.Fatalf("LatestFactBySource: %v (no feedback fact written?)", err)
|
||||
}
|
||||
tuned, ok := loop.ParseCooldownFact(fb)
|
||||
if !ok {
|
||||
t.Fatalf("ParseCooldownFact: not ok (value %q)", fb.Value)
|
||||
}
|
||||
if tuned != 45*time.Minute {
|
||||
t.Fatalf("all-ignored: base 30m × 1.5 = 45m (no — under WaterRule.Max 6h so unclamped): want 45m, got %v", tuned)
|
||||
}
|
||||
|
||||
// idempotent: a second tune() with the same outcomes writes nothing new
|
||||
// (RecentOutcomes is steady between resolves; the persisted value equals
|
||||
// the computed one ⇒ skip).
|
||||
fb1 := fb
|
||||
tl.tune(ctx)
|
||||
fb2, err := st.LatestFactBySource(ctx, loop.FeedbackKey(r), loop.FeedbackSource)
|
||||
if err != nil {
|
||||
t.Fatalf("LatestFactBySource second call: %v", err)
|
||||
}
|
||||
if fb2.ID != fb1.ID {
|
||||
t.Fatalf("tune() re-wrote identical value: fact id %d → %d (should skip when unchanged)",
|
||||
fb1.ID, fb2.ID)
|
||||
}
|
||||
|
||||
// flip the outcomes pattern to `acted`: next tune() writes a new value,
|
||||
// shorter than Max. RecentOutcomes is sorted DESC ts,id, so re-seeding
|
||||
// newer-acted nudges makes them dominate the older-ignored set.
|
||||
for i := 0; i < loop.TuneSampleN; i++ {
|
||||
id, err := st.RecordNudge(ctx, r.Name, "voice", "drink water", now.Add(time.Minute+time.Duration(i)*time.Second))
|
||||
if err != nil {
|
||||
t.Fatalf("RecordNudge acted %d: %v", i, err)
|
||||
}
|
||||
if err := st.ResolveNudge(ctx, id, store.NudgeActed, now); err != nil {
|
||||
t.Fatalf("ResolveNudge acted %d: %v", i, err)
|
||||
}
|
||||
}
|
||||
tl.tune(ctx)
|
||||
fb3, err := st.LatestFactBySource(ctx, loop.FeedbackKey(r), loop.FeedbackSource)
|
||||
if err != nil {
|
||||
t.Fatalf("LatestFactBySource post-flip: %v", err)
|
||||
}
|
||||
tuned3, ok := loop.ParseCooldownFact(fb3)
|
||||
if !ok {
|
||||
t.Fatalf("ParseCooldownFact post-flip: not ok (value %q)", fb3.Value)
|
||||
}
|
||||
if tuned3 >= r.Cooldown.Max {
|
||||
t.Fatalf("acted-dominated outcomes should shrink cooldown below Max: got %v (Max %v)",
|
||||
tuned3, r.Cooldown.Max)
|
||||
}
|
||||
if tuned3 < r.Cooldown.Min {
|
||||
t.Fatalf("tuned cooldown below Min envelope: got %v (Min %v) — clamp broken",
|
||||
tuned3, r.Cooldown.Min)
|
||||
}
|
||||
|
||||
// the gatherer actually reads it back: assert CooldownUntil for water is
|
||||
// derived from the tuned base (not the rule's static Base) when a real
|
||||
// nudge exists. seed a water nudge now and gather.
|
||||
nudgeTs := now.Add(2 * time.Minute)
|
||||
if _, err := st.RecordNudge(ctx, r.Name, "voice", "drink water", nudgeTs); err != nil {
|
||||
t.Fatalf("final RecordNudge: %v", err)
|
||||
}
|
||||
g := loop.NewGatherer(st, loop.DefaultRules())
|
||||
snap, _, err := g.GatherState(ctx, now.Add(3*time.Minute))
|
||||
if err != nil {
|
||||
t.Fatalf("GatherState: %v", err)
|
||||
}
|
||||
wantUntil := nudgeTs.Add(tuned3)
|
||||
if got := snap.CooldownUntil[r.Name]; got != wantUntil {
|
||||
t.Fatalf("gatherer used tuned base: CooldownUntil want %v, got %v",
|
||||
wantUntil, got)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,853 @@
|
||||
// Package main is mavend's voice wiring + reactive handler.
|
||||
//
|
||||
// Two responsibilities for the audio path:
|
||||
//
|
||||
// 1. CONSTRUCTION: read cfg.Voice, build the stt/tts/transcribers (Stub
|
||||
// in-process by default, Remote via worker socket when configured),
|
||||
// the router (stage-0 grammar + HashEmbedder classifier seeded with
|
||||
// floor examples — production swaps in the ONNX multilingual model
|
||||
// later), the voice TCP listener, the sessions registry, the
|
||||
// voicesink, and wire the voicesink into the dispatcher's Voice slot.
|
||||
//
|
||||
// 2. HANDLER: a concrete voice.Handler that processes PushToTalk
|
||||
// requests: stt → router → action → replier → tts → reply. The
|
||||
// handler is what makes the audio round-trip "live". It wires to the
|
||||
// CoreAPI in-process (the daemon already has it as ipc.NewStoreAPI(st)
|
||||
// for module-IPC — the reactive path uses the same CoreAPI off the
|
||||
// same store; both are the "core = the only key-holder" path through
|
||||
// the daemon-embedded adapter).
|
||||
//
|
||||
// The "actions" handled today (per spec order; some deferred):
|
||||
//
|
||||
// - IntentFact: WriteFact via CoreAPI. The router's Slots.Key/Value feed
|
||||
// the write; Source = "tap:voice" (the voice path is a tap, value=1.0
|
||||
// confidence — the user said it out loud, maven trusts the capture).
|
||||
// - IntentReminder: CreateReminder via CoreAPI. The router already
|
||||
// resolved relative→absolute at capture ("in 4h" → fire_ts); the
|
||||
// CoreAPI stores it as-is.
|
||||
// - IntentAct: the tool executor runs the matched fn against the store's
|
||||
// ENABLED allowlist (internal/tool). A verb not on it is scaffolded as a
|
||||
// 'proposed' tool a human enables on the authed mavweb surface (never
|
||||
// voice). Destructive tools run only after a spoken confirm turn.
|
||||
// - IntentNote: chroma/vector-store deferred. The handler replies
|
||||
// "saved" without persisting — a stub on the way to chroma.
|
||||
// - IntentQuery: RAG-over-chroma deferred. The handler replies "I'll
|
||||
// look that up later" — same shape as the other deferred slots.
|
||||
// - Clarify: the router's stage-3 confidence gate fired; reply "didn't
|
||||
// catch that, can you rephrase?"
|
||||
//
|
||||
// The Replier (voice.StubReplier today) renders the reply TEXT across all
|
||||
// these branches. The TTS synthesiser (tts.Stub today) renders that text
|
||||
// to audio. The PushToTalkResp carries BOTH so the client can play (audio)
|
||||
// AND log (text) for tests asserting the round-trip.
|
||||
package main
|
||||
|
||||
import (
|
||||
"bufio"
|
||||
"context"
|
||||
"errors"
|
||||
"fmt"
|
||||
"log"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/audio"
|
||||
"github.com/kami/maven/internal/config"
|
||||
"github.com/kami/maven/internal/delivery"
|
||||
"github.com/kami/maven/internal/delivery/voicesink"
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/stt"
|
||||
"github.com/kami/maven/internal/tool"
|
||||
"github.com/kami/maven/internal/tts"
|
||||
"github.com/kami/maven/internal/voice"
|
||||
"github.com/kami/maven/internal/worker"
|
||||
)
|
||||
|
||||
// voiceWiring — everything the daemon needs to run the audio path. Held by
|
||||
// cmd/mavend/main.go alongside the other wirings; closed on shutdown.
|
||||
type voiceWiring struct {
|
||||
server *voice.Server
|
||||
sessions *voice.Sessions
|
||||
voiceSink delivery.Sink
|
||||
embedder router.Embedder
|
||||
// worker clients (set when configured as Remote): closed on shutdown so
|
||||
// mavsttd / mavttsd don't keep a stale conn into a restarting daemon.
|
||||
sttClient *worker.Client
|
||||
ttsClient *worker.Client
|
||||
}
|
||||
|
||||
// close releases the listener + worker conns. Safe to call on nil (when
|
||||
// voice is not wired — wireVoice returns nil,nil).
|
||||
func (w *voiceWiring) close() {
|
||||
if w == nil {
|
||||
return
|
||||
}
|
||||
if w.embedder != nil {
|
||||
_ = w.embedder.Close()
|
||||
}
|
||||
if w.server != nil {
|
||||
_ = w.server.Close()
|
||||
}
|
||||
if w.sttClient != nil {
|
||||
_ = w.sttClient.Close()
|
||||
}
|
||||
if w.ttsClient != nil {
|
||||
_ = w.ttsClient.Close()
|
||||
}
|
||||
}
|
||||
|
||||
// wireVoice builds the audio path from cfg + a CoreAPI + a router. Returns
|
||||
// nil wiring + nil error when voice isn't enabled (the caller's voice sink
|
||||
// stays nil; the dispatcher's ChannelVoice routing drops silently).
|
||||
//
|
||||
// When voice is enabled, MUST wire a voicesink into the dispatcher's Voice
|
||||
// slot using w.sessions (the caller does that — see main.go).
|
||||
func wireVoice(cfg *config.Config, coreAPI ipc.CoreAPI) (*voiceWiring, error) {
|
||||
if cfg.Voice == nil || !cfg.Voice.Enabled {
|
||||
return nil, nil
|
||||
}
|
||||
w := &voiceWiring{}
|
||||
|
||||
// ----- stt (Stub in-process OR Remote via worker socket) -----
|
||||
var transcriber stt.Transcriber
|
||||
if cfg.Voice.Stt != nil && cfg.Voice.Stt.Socket != "" {
|
||||
c := worker.Dial(cfg.Voice.Stt.Socket)
|
||||
w.sttClient = c
|
||||
lang := cfg.Voice.Stt.Lang
|
||||
if lang == "" {
|
||||
lang = cfg.Voice.Lang
|
||||
}
|
||||
transcriber = stt.NewRemote(c, lang)
|
||||
} else {
|
||||
transcriber = stt.NewStub()
|
||||
}
|
||||
|
||||
// ----- tts (Stub in-process OR Remote) -----
|
||||
var synthesizer tts.Synthesizer
|
||||
if cfg.Voice.Tts != nil && cfg.Voice.Tts.Socket != "" {
|
||||
c := worker.Dial(cfg.Voice.Tts.Socket)
|
||||
w.ttsClient = c
|
||||
lang := cfg.Voice.Tts.Lang
|
||||
if lang == "" {
|
||||
lang = cfg.Voice.Lang
|
||||
}
|
||||
synthesizer = tts.NewRemote(c, lang, cfg.Voice.Tts.Voice)
|
||||
} else {
|
||||
synthesizer = tts.NewStub()
|
||||
}
|
||||
|
||||
// ----- router: embedder (ONNX when configured, floor HashEmbedder otherwise) -----
|
||||
var emb router.Embedder
|
||||
if cfg.Voice.Embedder != nil {
|
||||
onnx, err := router.NewONNXEmbedder(
|
||||
cfg.Voice.Embedder.ModelPath,
|
||||
cfg.Voice.Embedder.TokenizerPath,
|
||||
cfg.Voice.Embedder.LibPath,
|
||||
)
|
||||
if err != nil {
|
||||
w.close()
|
||||
return nil, fmt.Errorf("embedder: %w", err)
|
||||
}
|
||||
log.Printf("voice: onnx embedder loaded (%d dim)", onnx.Dim())
|
||||
emb = onnx
|
||||
} else {
|
||||
emb = router.NewHashEmbedder(1024)
|
||||
}
|
||||
w.embedder = emb
|
||||
|
||||
// ----- tool executor (the enabled act allowlist, store-backed) -----
|
||||
// Config tools are the declarative bootstrap: seed them into the store as
|
||||
// enabled (editing mavend.json IS the human enable act). Ad-hoc tools are
|
||||
// enabled later through the authed mavweb surface. The executor + matcher
|
||||
// both read the store live, so a newly-enabled tool is runnable without a
|
||||
// daemon restart.
|
||||
seedTools(coreAPI, cfg.Voice.Tools)
|
||||
exec := tool.NewExecutor(coreAPI, time.Duration(cfg.Voice.ToolTimeout))
|
||||
matcher := tool.NewMatcher(coreAPI)
|
||||
|
||||
// ----- router (the cascade; floor examples seed the classifier) -----
|
||||
// The act matcher's allowlist is exactly the enabled tool names — the
|
||||
// router only matches acts the executor can run (one source of truth).
|
||||
threshold := cfg.Voice.RouterThreshold
|
||||
if threshold <= 0 {
|
||||
threshold = config.DefaultRouterThreshold
|
||||
}
|
||||
rtr := buildRouter(emb, matcher, threshold)
|
||||
|
||||
// ----- sessions registry (shared with voicesink) -----
|
||||
sessions := voice.NewSessions()
|
||||
w.sessions = sessions
|
||||
|
||||
// ----- voice sink (proactive nudges: dispatcher → voicesink → tts → push to client) -----
|
||||
w.voiceSink = voicesink.New(synthesizer, sessions)
|
||||
|
||||
// ----- the handler (the reactive path; closes over stt / tts / router / coreAPI) -----
|
||||
h := &reactiveHandler{
|
||||
stt: transcriber,
|
||||
tts: synthesizer,
|
||||
router: rtr,
|
||||
embedder: emb,
|
||||
api: coreAPI,
|
||||
tools: exec,
|
||||
replier: voice.NewStubReplier(),
|
||||
now: time.Now,
|
||||
}
|
||||
|
||||
// ----- the server (TCP listener) -----
|
||||
srv := voice.NewServer(cfg.Voice.Bind, h, sessions)
|
||||
if err := srv.Listen(); err != nil {
|
||||
w.close()
|
||||
return nil, fmt.Errorf("voice listen: %w", err)
|
||||
}
|
||||
w.server = srv
|
||||
|
||||
return w, nil
|
||||
}
|
||||
|
||||
// reactiveHandler — voice.Handler implementation. One method: turn a
|
||||
// PushToTalkReq into a reply (audio + text). The handler is concurrency-
|
||||
// safe (the wired stt/tts/router/api all are); called from per-conn
|
||||
// goroutines on the voice.Server.
|
||||
type reactiveHandler struct {
|
||||
stt stt.Transcriber
|
||||
tts tts.Synthesizer
|
||||
router *router.Router
|
||||
embedder router.Embedder // reused for note write/query (same model as the classifier)
|
||||
api ipc.CoreAPI
|
||||
tools *tool.Executor
|
||||
replier voice.Replier
|
||||
now func() time.Time
|
||||
|
||||
// pending destructive-act confirmation. A destructive act replies with a
|
||||
// "выполнить X? да/нет" prompt and parks here; the NEXT utterance is read as
|
||||
// the y/n answer. ponytail: single slot, single-user box — a second act
|
||||
// while one waits overwrites it (last-asked wins); expires after confirmTTL.
|
||||
mu sync.Mutex
|
||||
pending *pendingAct
|
||||
}
|
||||
|
||||
// pendingAct — a destructive act awaiting a spoken confirm.
|
||||
type pendingAct struct {
|
||||
fn string
|
||||
args []string
|
||||
phrase string
|
||||
expiry time.Time
|
||||
}
|
||||
|
||||
// confirmTTL — how long a parked destructive confirm stays answerable. Short:
|
||||
// a confirm is a same-breath gesture; a stale prompt shouldn't fire on an
|
||||
// unrelated later "да".
|
||||
const confirmTTL = 90 * time.Second
|
||||
|
||||
// HandlePushToTalk — the full reactive round-trip. Each step's failure
|
||||
// surfaces as a short reply text + empty audio OR an error; the voice
|
||||
// server translates an error into a wire RpcError. Today the handler
|
||||
// prefers a canned error-reply over an error return (a user-facing "didn't
|
||||
// catch that" is better than a wire error the client surfaces as
|
||||
// "internal"); the only error returned is a synthesizer fault (no audio
|
||||
// to ship back).
|
||||
func (h *reactiveHandler) HandlePushToTalk(ctx context.Context, req voice.PushToTalkReq, _ uint64) (voice.PushToTalkResp, error) {
|
||||
// 1. stt — transcribe the audio.
|
||||
text, _, err := h.stt.Transcribe(ctx, req.Audio)
|
||||
if err != nil {
|
||||
log.Printf("voice: stt error: %v", err)
|
||||
return h.reply(ctx, "не получилось разобрать речь — попробуй ещё раз.", nil)
|
||||
}
|
||||
if text == "" {
|
||||
return h.reply(ctx, "ничего не услышала — попробуй ещё раз.", nil)
|
||||
}
|
||||
log.Printf("voice: stt → %q", text)
|
||||
|
||||
// 1b. confirm turn — if a destructive act is parked, this utterance is its
|
||||
// y/n answer, not a fresh command. Handled before routing so "да" doesn't
|
||||
// get classified as some other intent.
|
||||
if reply, handled := h.resolveConfirm(ctx, text); handled {
|
||||
return h.reply(ctx, reply, nil)
|
||||
}
|
||||
|
||||
// 2. router — classify the utterance.
|
||||
dec, err := h.router.Route(ctx, text, h.now())
|
||||
if err != nil {
|
||||
// ErrNoIntents ⇒ classifier unseeded (cold boot). reply with a
|
||||
// "still warming up" rather than a wire error.
|
||||
if errors.Is(err, router.ErrNoIntents) {
|
||||
return h.reply(ctx, "я ещё не понимаю свободную речь — скоро научусь.", nil)
|
||||
}
|
||||
log.Printf("voice: router error: %v", err)
|
||||
return h.reply(ctx, "не получилось разобрать команду.", nil)
|
||||
}
|
||||
|
||||
// 3. action — execute the decision's intent. errors here surface as
|
||||
// short reply text (the user wants to know the action didn't land);
|
||||
// the round-trip stays alive.
|
||||
replyText := h.applyAction(ctx, dec)
|
||||
|
||||
// 4. replier — phrase the reply across the router decision.
|
||||
if replyText == "" {
|
||||
replyText = h.replier.Reply(dec)
|
||||
}
|
||||
|
||||
// 5. tts — synthesise the reply text; return to the voice server which
|
||||
// ships it back on the conn.
|
||||
return h.reply(ctx, replyText, nil)
|
||||
}
|
||||
|
||||
// applyAction — executes the router's Decision. Intent-by-intent:
|
||||
//
|
||||
// - IntentFact: WriteFact via CoreAPI. Source = "tap:voice" (a voice
|
||||
// capture is a tap; confidence 1.0).
|
||||
// - IntentReminder: CreateReminder via CoreAPI.
|
||||
// - IntentAct: tool-executor deferred (no-op today; the reply says so).
|
||||
// - IntentNote / IntentQuery: chroma/RAG deferred (no-op; reply says so).
|
||||
// - Clarify: the router's stage-3 fired; no action.
|
||||
//
|
||||
// Returns "" when the Replier should phrase the reply (the default path);
|
||||
// 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
|
||||
}
|
||||
switch dec.Intent {
|
||||
case router.IntentFact:
|
||||
if !dec.Slots.HasKey {
|
||||
return "не разобрала, что записать — попробуй иначе."
|
||||
}
|
||||
now := h.now()
|
||||
req := ipc.WriteFactReq{
|
||||
Ts: now,
|
||||
Kind: "self",
|
||||
Key: dec.Slots.Key,
|
||||
Value: dec.Slots.Value,
|
||||
Source: "tap:voice",
|
||||
Confidence: 1.0,
|
||||
}
|
||||
if _, err := h.api.WriteFact(ctx, req); err != nil {
|
||||
log.Printf("voice: write fact: %v", err)
|
||||
return "не получилось сохранить факт."
|
||||
}
|
||||
return "" // replier phrases the success reply
|
||||
|
||||
case router.IntentReminder:
|
||||
if !dec.Slots.HasTime {
|
||||
return "не получилось разобрать время напоминания."
|
||||
}
|
||||
payload := `{"text":` + jsonString(dec.Utterance) + `}`
|
||||
if _, err := h.api.CreateReminder(ctx, dec.Slots.Time, payload); err != nil {
|
||||
log.Printf("voice: create reminder: %v", err)
|
||||
return "не получилось поставить напоминание."
|
||||
}
|
||||
return ""
|
||||
|
||||
case router.IntentAct:
|
||||
// tool executor: run the matched fn against the enabled allowlist.
|
||||
// HasFn=false ⇒ no allowlist match: scaffold a 'proposed' tool the user
|
||||
// can enable on the authed surface ("earn the right to ask").
|
||||
if !dec.Slots.HasFn {
|
||||
return h.proposeGap(ctx, dec)
|
||||
}
|
||||
out, err := h.tools.Exec(ctx, dec.Slots.Fn, dec.Slots.Args, false)
|
||||
if err != nil {
|
||||
switch {
|
||||
case errors.Is(err, tool.ErrNeedsConfirm):
|
||||
// destructive: park it and ask. The next utterance answers.
|
||||
phrase := actPhrase(dec.Slots.Fn, dec.Slots.Args)
|
||||
h.park(dec.Slots.Fn, dec.Slots.Args, phrase)
|
||||
return "выполнить «" + phrase + "»? скажи «да» или «нет»."
|
||||
case errors.Is(err, tool.ErrNotEnabled):
|
||||
return h.proposeGap(ctx, dec)
|
||||
}
|
||||
log.Printf("voice: tool %s: %v", dec.Slots.Fn, err)
|
||||
if out != "" {
|
||||
return "не получилось выполнить команду: " + firstLine(out)
|
||||
}
|
||||
return "не получилось выполнить команду."
|
||||
}
|
||||
if out != "" {
|
||||
return "готово: " + firstLine(out)
|
||||
}
|
||||
return "готово."
|
||||
|
||||
case router.IntentSystem:
|
||||
// Quiet-hours toggle — "quiet on" / "тихий режим" — writes
|
||||
// a config fact the gate reads. Check before the query-only path.
|
||||
if reply := h.handleQuietToggle(ctx, dec); reply != "" {
|
||||
return reply
|
||||
}
|
||||
// System-status queries return to the Replier for phrasing.
|
||||
// The handler emits the current answer inline (no DB / RAG needed).
|
||||
return h.replySystem(ctx, dec)
|
||||
|
||||
case router.IntentNote:
|
||||
// embed the note text with the same model the classifier uses, persist
|
||||
// via CoreAPI (source=tap:voice). Semantic recall lives in `notes`, not
|
||||
// facts — no predicate reads it (spec's two-memory split).
|
||||
vec, err := h.embedder.Embed(ctx, dec.Utterance)
|
||||
if err != nil {
|
||||
log.Printf("voice: embed note: %v", err)
|
||||
return "не получилось сохранить заметку."
|
||||
}
|
||||
if _, err := h.api.WriteNote(ctx, h.now(), dec.Utterance, vec, "tap:voice"); err != nil {
|
||||
log.Printf("voice: write note: %v", err)
|
||||
return "не получилось сохранить заметку."
|
||||
}
|
||||
return "" // replier phrases the "saved" reply
|
||||
|
||||
case router.IntentQuery:
|
||||
vec, err := h.embedder.Embed(ctx, dec.Utterance)
|
||||
if err != nil {
|
||||
log.Printf("voice: embed query: %v", err)
|
||||
return "не получилось найти ответ."
|
||||
}
|
||||
notes, err := h.api.QueryNotes(ctx, vec, 5)
|
||||
if err != nil {
|
||||
log.Printf("voice: query notes: %v", err)
|
||||
return "не получилось найти ответ."
|
||||
}
|
||||
// Confidence gate: below threshold, say "I don't know" rather than read
|
||||
// back the least-unrelated note — a confident wrong recall is worse than
|
||||
// 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 {
|
||||
return "у меня нет заметок по этому вопросу."
|
||||
}
|
||||
// Full RAG (phraser-composed) is deferred — this is the browse surface.
|
||||
// Return a summary of the best match(es) so the user gets context, not just
|
||||
// one verbatim snippet. The phraser seam in the replier will natural-language
|
||||
// the results when the LLM-backed Replier swaps in.
|
||||
if len(notes) == 1 {
|
||||
return "ты записал: " + notes[0].Text
|
||||
}
|
||||
var b strings.Builder
|
||||
b.WriteString("вот что нашла: ")
|
||||
for i, n := range notes {
|
||||
if i > 0 {
|
||||
b.WriteString("; ")
|
||||
}
|
||||
b.WriteString(n.Text)
|
||||
}
|
||||
return b.String()
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
var ruWeekdays = []string{
|
||||
"воскресенье", "понедельник", "вторник", "среда",
|
||||
"четверг", "пятница", "суббота",
|
||||
}
|
||||
|
||||
var ruMonths = []string{
|
||||
"января", "февраля", "марта", "апреля", "мая", "июня",
|
||||
"июля", "августа", "сентября", "октября", "ноября", "декабря",
|
||||
}
|
||||
|
||||
func ruPlural(n int, one, two, many string) string {
|
||||
n = n % 100
|
||||
if n > 10 && n < 20 {
|
||||
return many
|
||||
}
|
||||
n = n % 10
|
||||
switch n {
|
||||
case 1:
|
||||
return one
|
||||
case 2, 3, 4:
|
||||
return two
|
||||
default:
|
||||
return many
|
||||
}
|
||||
}
|
||||
|
||||
// handleQuietToggle — checks if the utterance toggles quiet hours.
|
||||
// Writes a `quiet_hours` config fact (value "true"/"false") so the loop
|
||||
// gate reads it next tick. Returns a reply text, or "" if no match.
|
||||
func (h *reactiveHandler) handleQuietToggle(ctx context.Context, dec router.Decision) string {
|
||||
u := strings.ToLower(dec.Utterance)
|
||||
// Match: "quiet on" / "quiet off" / "тихий режим" / "не беспокоить" etc.
|
||||
var on, off bool
|
||||
for _, kw := range []string{"quiet on", "quiet mode", "тихий режим", "не беспокоить", "не шуми"} {
|
||||
if strings.Contains(u, kw) {
|
||||
on = true
|
||||
break
|
||||
}
|
||||
}
|
||||
for _, kw := range []string{"quiet off", "quiet end", "выключи тихий", "отключи тихий", "шумный режим"} {
|
||||
if strings.Contains(u, kw) {
|
||||
off = true
|
||||
break
|
||||
}
|
||||
}
|
||||
if !on && !off {
|
||||
return ""
|
||||
}
|
||||
now := h.now()
|
||||
val := "false"
|
||||
reply := "тихий режим выключен."
|
||||
if on {
|
||||
val = "true"
|
||||
reply = "тихий режим включён. буду реже напоминать."
|
||||
}
|
||||
if _, err := h.api.WriteFact(ctx, ipc.WriteFactReq{
|
||||
Ts: now,
|
||||
Kind: "config",
|
||||
Key: "quiet_hours",
|
||||
Value: val,
|
||||
Source: "tap:voice",
|
||||
Confidence: 1.0,
|
||||
}); err != nil {
|
||||
log.Printf("voice: write quiet_hours: %v", err)
|
||||
return "не получилось переключить тихий режим."
|
||||
}
|
||||
return reply
|
||||
}
|
||||
|
||||
// replySystem answers system-observable queries using the handler's clock
|
||||
// and (in future) system interfaces. The decision's utterance is parsed
|
||||
// for keywords to determine what the user is asking about.
|
||||
func (h *reactiveHandler) replySystem(ctx context.Context, dec router.Decision) string {
|
||||
u := strings.ToLower(dec.Utterance)
|
||||
now := h.now()
|
||||
|
||||
switch {
|
||||
case strings.Contains(u, "час") || strings.Contains(u, "врем"):
|
||||
h := now.Hour()
|
||||
m := now.Minute()
|
||||
hourWord := ruPlural(h, "час", "часа", "часов")
|
||||
if m == 0 {
|
||||
return fmt.Sprintf("сейчас %d %s ровно", h, hourWord)
|
||||
}
|
||||
minWord := ruPlural(m, "минута", "минуты", "минут")
|
||||
return fmt.Sprintf("сейчас %d %s %d %s", h, hourWord, m, minWord)
|
||||
case strings.Contains(u, "день") || strings.Contains(u, "числ"):
|
||||
dow := ruWeekdays[now.Weekday()]
|
||||
month := ruMonths[now.Month()-1]
|
||||
return fmt.Sprintf("сегодня %s, %d %s %d года", dow, now.Day(), month, now.Year())
|
||||
case strings.Contains(u, "погод") || strings.Contains(u, "градус") || strings.Contains(u, "дожд") || strings.Contains(u, "холод") || strings.Contains(u, "тепл"):
|
||||
return "погода пока не подключена — нужен внешний сервис."
|
||||
case strings.Contains(u, "кто дома") || strings.Contains(u, "человек дома"):
|
||||
return "присутствие пока не подключено к голосовому запросу."
|
||||
case strings.Contains(u, "памят") || strings.Contains(u, "процессор") || strings.Contains(u, "загрузк") || strings.Contains(u, "статус") || strings.Contains(u, "работа") || strings.Contains(u, "сервис") || strings.Contains(u, "диск") || strings.Contains(u, "ip") || strings.Contains(u, "аптайм") || strings.Contains(u, "трафик") || strings.Contains(u, "интернет"):
|
||||
return "системная статистика пока не подключена."
|
||||
default:
|
||||
return "пока не умею отвечать на этот вопрос."
|
||||
}
|
||||
}
|
||||
|
||||
// reply wraps a text reply through TTS to produce a PushToTalkResp. If TTS
|
||||
// fails, the response carries an empty audio + the text — the client can
|
||||
// still display text if it can't play. The routedChannels field is
|
||||
// reserved for a future "the dispatcher also forwarded to ntfy/telegram"
|
||||
// reply (today the reactive path doesn't dispatch nudges; that's the loop
|
||||
// tick's job).
|
||||
func (h *reactiveHandler) reply(ctx context.Context, text string, _ []string) (voice.PushToTalkResp, error) {
|
||||
log.Printf("voice: reply → %q", text)
|
||||
audioOut, err := h.tts.Synthesize(ctx, text)
|
||||
if err != nil {
|
||||
log.Printf("voice: tts error: %v", err)
|
||||
return voice.PushToTalkResp{ReplyText: text, ReplyAudio: audio.Audio{}}, nil
|
||||
}
|
||||
return voice.PushToTalkResp{ReplyText: text, ReplyAudio: audioOut}, nil
|
||||
}
|
||||
|
||||
// buildRouter constructs the reactive-path router with the given embedder
|
||||
// and confidence threshold.
|
||||
// - stage-0 grammars from DefaultActMatcher whose fn allowlist is exactly
|
||||
// the enabled tool names (actFns) — the router only matches acts the
|
||||
// executor can run. Empty ⇒ every act refuses at the matcher.
|
||||
// - The embedder is provided by wireVoice: HashEmbedder (floor) when no
|
||||
// embedder config is present, or the ONNX multilingual model when
|
||||
// configured — same interface, one constructor change.
|
||||
// - 6 bootstrap examples covering the 5 intents + one compound-capture
|
||||
// placeholder. Spec calls for ~10 per intent at production; this is the
|
||||
// bootstrapping floor swapped by tuning the seed set later.
|
||||
// - Threshold is from voice.router_threshold config (default 0.35).
|
||||
func buildRouter(emb router.Embedder, acts router.ActMatcher, threshold float64) *router.Router {
|
||||
cls := router.NewClassifier(emb)
|
||||
seedClassifier(cls)
|
||||
return router.New(router.Config{
|
||||
Grammars: router.DefaultGrammars(acts),
|
||||
Classifier: cls,
|
||||
Extractor: router.Extractor{
|
||||
Time: router.StubDateTimeParser{},
|
||||
Acts: acts,
|
||||
Facts: router.DefaultFactParser{},
|
||||
},
|
||||
Threshold: threshold,
|
||||
})
|
||||
}
|
||||
|
||||
// seedDir is the directory containing intent seed files. Each file is named
|
||||
// <intent>.txt and contains one training example per line (blank lines and
|
||||
// lines starting with # are ignored). Relative to the working directory.
|
||||
const seedDir = "models/seeds"
|
||||
|
||||
// seedClassifier floors the embedded examples so the cold-boot path
|
||||
// doesn't return ErrNoIntents. Loads examples from seedDir — one file per
|
||||
// intent (act.txt, reminder.txt, fact.txt, note.txt, query.txt). When the
|
||||
// classifier can't decide it falls through to Clarify — the last-resort
|
||||
// path asks the user to rephrase rather than guessing wrong.
|
||||
func seedClassifier(c *router.Classifier) {
|
||||
intents := []router.Intent{
|
||||
router.IntentAct,
|
||||
router.IntentReminder,
|
||||
router.IntentFact,
|
||||
router.IntentNote,
|
||||
router.IntentQuery,
|
||||
router.IntentSystem,
|
||||
}
|
||||
total := 0
|
||||
for _, intent := range intents {
|
||||
n, err := loadSeedFile(c, intent)
|
||||
if err != nil {
|
||||
log.Printf("voice: seed %s: %v", intent, err)
|
||||
continue
|
||||
}
|
||||
total += n
|
||||
}
|
||||
log.Printf("voice: loaded %d seed examples from %s", total, seedDir)
|
||||
}
|
||||
|
||||
func loadSeedFile(c *router.Classifier, intent router.Intent) (int, error) {
|
||||
path := filepath.Join(seedDir, string(intent)+".txt")
|
||||
f, err := os.Open(path)
|
||||
if err != nil {
|
||||
return 0, fmt.Errorf("open %s: %w", path, err)
|
||||
}
|
||||
defer f.Close()
|
||||
|
||||
var count int
|
||||
sc := bufio.NewScanner(f)
|
||||
for sc.Scan() {
|
||||
line := strings.TrimSpace(sc.Text())
|
||||
if line == "" || strings.HasPrefix(line, "#") {
|
||||
continue
|
||||
}
|
||||
if err := c.AddExample(context.Background(), intent, line); err != nil {
|
||||
log.Printf("voice: seed %s: skipping %q: %v", intent, line, err)
|
||||
continue
|
||||
}
|
||||
count++
|
||||
}
|
||||
if err := sc.Err(); err != nil {
|
||||
return count, fmt.Errorf("scan %s: %w", path, err)
|
||||
}
|
||||
return count, nil
|
||||
}
|
||||
|
||||
// jsonString — a one-line JSON string encoder without dragging encoding/json
|
||||
// into the top of this file. Used to wrap a reminder payload's text field;
|
||||
// the router's reminder Slots are already absolute (DateTimeParser resolved
|
||||
// relative→absolute), the payload shape is conventional {"text":...}.
|
||||
func jsonString(s string) string {
|
||||
return jsonStringImpl(s)
|
||||
}
|
||||
|
||||
// park stores a destructive act awaiting confirmation. Overwrites any prior
|
||||
// pending (last-asked wins — single-user box).
|
||||
func (h *reactiveHandler) park(fn string, args []string, phrase string) {
|
||||
h.mu.Lock()
|
||||
h.pending = &pendingAct{fn: fn, args: args, phrase: phrase, expiry: h.now().Add(confirmTTL)}
|
||||
h.mu.Unlock()
|
||||
}
|
||||
|
||||
// resolveConfirm interprets an utterance as the answer to a parked destructive
|
||||
// act. Returns (reply, true) when it consumed the utterance as a y/n answer;
|
||||
// (\"\", false) when there's nothing pending (or the parked act expired), so the
|
||||
// caller routes the utterance normally. An unrecognised answer cancels the
|
||||
// pending act and routes normally — a confirm that can't be answered clearly is
|
||||
// safer abandoned than left armed.
|
||||
func (h *reactiveHandler) resolveConfirm(ctx context.Context, text string) (string, bool) {
|
||||
h.mu.Lock()
|
||||
p := h.pending
|
||||
if p == nil {
|
||||
h.mu.Unlock()
|
||||
return "", false
|
||||
}
|
||||
if h.now().After(p.expiry) {
|
||||
h.pending = nil
|
||||
h.mu.Unlock()
|
||||
return "", false
|
||||
}
|
||||
switch classifyConfirm(text) {
|
||||
case confirmYes:
|
||||
h.pending = nil
|
||||
h.mu.Unlock()
|
||||
out, err := h.tools.Exec(ctx, p.fn, p.args, true) // confirmed
|
||||
if err != nil {
|
||||
log.Printf("voice: tool %s (confirmed): %v", p.fn, err)
|
||||
if out != "" {
|
||||
return "не получилось выполнить команду: " + firstLine(out), true
|
||||
}
|
||||
return "не получилось выполнить команду.", true
|
||||
}
|
||||
if out != "" {
|
||||
return "готово: " + firstLine(out), true
|
||||
}
|
||||
return "готово.", true
|
||||
case confirmNo:
|
||||
h.pending = nil
|
||||
h.mu.Unlock()
|
||||
return "отменила.", true
|
||||
default:
|
||||
// unclear answer: abandon the confirm, route this utterance normally.
|
||||
h.pending = nil
|
||||
h.mu.Unlock()
|
||||
return "", false
|
||||
}
|
||||
}
|
||||
|
||||
// proposeGap scaffolds a 'proposed' tool for an act whose verb isn't enabled.
|
||||
// maven drafts the registration (name = the verb, provenance = the utterance);
|
||||
// a human enables it on the authed surface. She suggests, never enables.
|
||||
func (h *reactiveHandler) proposeGap(ctx context.Context, dec router.Decision) string {
|
||||
name := firstWord(stripWake(dec.Utterance))
|
||||
if name == "" {
|
||||
return "не разобрала команду — попробуй иначе."
|
||||
}
|
||||
newly, err := h.api.ProposeTool(ctx, name, dec.Utterance, h.now())
|
||||
if err != nil {
|
||||
log.Printf("voice: propose tool %q: %v", name, err)
|
||||
return "команды «" + name + "» нет в списке разрешённых."
|
||||
}
|
||||
if newly {
|
||||
return "команды «" + name + "» нет в списке. Предложила её добавить — включи через клиент."
|
||||
}
|
||||
return "команды «" + name + "» пока нет в списке — она уже предложена, включи через клиент."
|
||||
}
|
||||
|
||||
// confirmVerdict — the parse of a y/n confirm answer.
|
||||
type confirmVerdict int
|
||||
|
||||
const (
|
||||
confirmUnknown confirmVerdict = iota
|
||||
confirmYes
|
||||
confirmNo
|
||||
)
|
||||
|
||||
// classifyConfirm reads a short ru/en yes-or-no answer. Substring match on the
|
||||
// stems so inflections/fillers ("да, давай", "нет, отмени") still land.
|
||||
func classifyConfirm(text string) confirmVerdict {
|
||||
t := strings.ToLower(strings.TrimSpace(text))
|
||||
// negatives first — "не надо" contains no "да", but check no-stems before
|
||||
// yes so a leading "нет" isn't shadowed.
|
||||
for _, no := range []string{"нет", "не надо", "отмен", "стоп", "no", "cancel", "stop", "don't"} {
|
||||
if strings.Contains(t, no) {
|
||||
return confirmNo
|
||||
}
|
||||
}
|
||||
for _, yes := range []string{"да", "ага", "давай", "подтвер", "конечно", "yes", "yeah", "yep", "confirm", "ок", "okay", "ok"} {
|
||||
if strings.Contains(t, yes) {
|
||||
return confirmYes
|
||||
}
|
||||
}
|
||||
return confirmUnknown
|
||||
}
|
||||
|
||||
// actPhrase renders "fn arg1 arg2" for the confirm prompt.
|
||||
func actPhrase(fn string, args []string) string {
|
||||
if len(args) == 0 {
|
||||
return fn
|
||||
}
|
||||
return fn + " " + strings.Join(args, " ")
|
||||
}
|
||||
|
||||
// stripWake removes a leading "maven," wake token so the verb is the first word.
|
||||
func stripWake(u string) string {
|
||||
u = strings.TrimSpace(u)
|
||||
low := strings.ToLower(u)
|
||||
if strings.HasPrefix(low, "maven") {
|
||||
u = strings.TrimSpace(u[len("maven"):])
|
||||
u = strings.TrimLeft(u, ",:; ")
|
||||
}
|
||||
return u
|
||||
}
|
||||
|
||||
// firstWord returns the first whitespace-delimited token (lowercased) — the
|
||||
// proposed tool's name.
|
||||
func firstWord(s string) string {
|
||||
f := strings.Fields(s)
|
||||
if len(f) == 0 {
|
||||
return ""
|
||||
}
|
||||
return strings.ToLower(f[0])
|
||||
}
|
||||
|
||||
// seedTools upserts the config-declared tools into the store as enabled. Editing
|
||||
// mavend.json is a human act, so a config tool is enabled by definition; this
|
||||
// makes the declarative config the reproducible bootstrap while the store stays
|
||||
// the single runtime source of truth (mavweb enables ad-hoc ones on top).
|
||||
func seedTools(api ipc.CoreAPI, tools []config.ToolConfig) {
|
||||
ctx := context.Background()
|
||||
now := time.Now()
|
||||
n := 0
|
||||
for _, tc := range tools {
|
||||
if tc.Name == "" || len(tc.Cmd) == 0 {
|
||||
log.Printf("voice: skipping malformed tool config %+v", tc)
|
||||
continue
|
||||
}
|
||||
if err := api.EnableTool(ctx, tc.Name, tc.Cmd, tc.Destructive, now); err != nil {
|
||||
log.Printf("voice: seed tool %q: %v", tc.Name, err)
|
||||
continue
|
||||
}
|
||||
n++
|
||||
}
|
||||
log.Printf("voice: seeded %d act tools from config", n)
|
||||
}
|
||||
|
||||
// firstLine — the first non-empty line of a tool's output, for a short spoken
|
||||
// reply (the full output goes to the log, not the TTS). Trimmed to keep the
|
||||
// utterance sane if a command dumps a wall of text.
|
||||
func firstLine(s string) string {
|
||||
for _, line := range strings.Split(s, "\n") {
|
||||
line = strings.TrimSpace(line)
|
||||
if line != "" {
|
||||
if len(line) > 200 {
|
||||
line = line[:200]
|
||||
}
|
||||
return line
|
||||
}
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
func jsonStringImpl(s string) string {
|
||||
// minimal JSON string escape — quotes + backslash + control chars.
|
||||
// adequate for the reminder payload's text field; not a general JSON
|
||||
// encoder. The chroma / RAG modules (when they land) use a real json
|
||||
// encoder for richer payloads. Keep it inline here so the import
|
||||
// direction stays narrow.
|
||||
var b []byte
|
||||
b = append(b, '"')
|
||||
for _, r := range s {
|
||||
switch r {
|
||||
case '"':
|
||||
b = append(b, '\\', '"')
|
||||
case '\\':
|
||||
b = append(b, '\\', '\\')
|
||||
case '\n':
|
||||
b = append(b, '\\', 'n')
|
||||
case '\r':
|
||||
b = append(b, '\\', 'r')
|
||||
case '\t':
|
||||
b = append(b, '\\', 't')
|
||||
default:
|
||||
if r < 0x20 {
|
||||
b = append(b, []byte(fmt.Sprintf("\\u%04x", r))...)
|
||||
} else {
|
||||
b = append(b, []byte(string(r))...)
|
||||
}
|
||||
}
|
||||
}
|
||||
b = append(b, '"')
|
||||
return string(b)
|
||||
}
|
||||
Reference in New Issue
Block a user