Files
Maven/cmd/mavend/main.go
T
kami ad074cea31 Swap the resident model without restarting mavend (#250)
Loading a different gguf was a one-line edit to phraser.model_path plus a
restart. It is now an owner-triggered IPC call, off unless configured.

internal/phraser/swap.go holds the safety properties as code:

  - Never two models resident. The old llama-server is killed and reaped
    before the new one is launched. One 1.7B fits the Vega iGPU; a
    blue/green overlap would OOM the box, so it is not offered.
  - Atomic from a turn's point of view. Swap drains the in-flight turns
    (they finish on the old model), then refuses arrivals with ErrSwapping
    until the new server has answered /v1/models. No turn ever sees half a
    swap; refused turns fall back to the classifier cascade.
  - A failed load rolls back. If the new model does not start or does not
    probe, the previous one is reloaded and the call returns RolledBack
    with the error. If the rollback also fails the daemon says so and
    degrades to the classifier rather than pretending to serve.

Holders of the completion client are re-pointed, not rebuilt: llm.Client
guards its base URL and LLMPhraser.OnSwap re-points it, so the router, the
replier, the mail extractor and the memory evaluator follow the new port
without knowing a swap happened.

Reach is deliberately narrow. phraser.swap_models is an exact-match
allowlist of absolute paths a human wrote, rejected at startup otherwise,
so "swap the model" can never mean "load any file on my disk"; the running
model is always swappable back to. MethodSwapModel is AuthStepUp, the same
rung as mutating the tool allowlist, and /models gates POST through the
same stepUpOK the tools page uses. Nothing calls Swap on a timer and no
act, intent or utterance reaches it.

Vikunja #250
2026-08-01 03:59:08 +04:00

621 lines
20 KiB
Go

// 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).
//
// Cold-start unlock (2026-07-06):
//
// When a passkey credential is enrolled AND no env key is set, the daemon
// starts in LOCKED mode: the IPC server runs but rejects all store methods
// except MethodAssertStepUp and MethodUnlock. A passkey assertion followed
// by MethodUnlock (with the same credential's public key) unwraps the at-rest
// AES-256 key from a wrapped blob on disk (HKDF-SHA256 + AES-GCM) and opens
// the encrypted store. After unlock, the daemon wires voice, loop, and
// delivery and runs normally.
//
// Fallback: when db_key_env is set (or no wrapped file exists), the daemon
// starts unlocked from the env key (pre-unlock behavior). Enrolling a passkey
// while unlocked calls MethodStoreEncryptionKey to wrap the env key and
// persist the wrapped blob — enabling cold-start unlock on the next boot
// after the env key is removed.
package main
import (
"context"
"encoding/json"
"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/persona"
"github.com/kami/maven/internal/phraser"
"github.com/kami/maven/internal/store"
"github.com/kami/maven/internal/webauthn"
)
var errLocked = errors.New("mavend: daemon locked — complete passkey assertion first")
// daemonLock tracks whether the daemon is in locked (pre-unlock) mode.
// In locked mode, all CoreAPI methods return errLocked. The unlock path
// replaces the CoreAPI with the real store adapter and flips the flag.
type daemonLock struct {
mu sync.Mutex
locked bool
}
func newDaemonLock(locked bool) *daemonLock {
return &daemonLock{locked: locked}
}
func (l *daemonLock) isLocked() bool {
l.mu.Lock()
defer l.mu.Unlock()
return l.locked
}
func (l *daemonLock) unlock() {
l.mu.Lock()
defer l.mu.Unlock()
l.locked = false
}
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")
wrappedKeyPath := flag.String("wrapped-key-file", "", "path to wrapped encryption key blob (enables cold-start unlock)")
reembed := flag.Bool("reembed", false, "re-embed every stored note and fact with the configured embedder, then serve normally (run once after an embedder swap)")
flag.CommandLine.Parse(args)
reembedOnStart = *reembed
cfg, err := config.Load(*cfgPath)
if err != nil {
return err
}
ctx, stop := signal.NotifyContext(context.Background(), syscall.SIGINT, syscall.SIGTERM, syscall.SIGHUP)
defer stop()
// ----- encryption key: env key → wrapped key → plaintext -----
// Priority: env key (from config/docker) > wrapped key (cold-start unlock) > plaintext (dev/CI).
// When a wrapped key file exists AND no env key is set, the daemon starts
// LOCKED and waits for a passkey assertion to unwrap it.
envKey, err := cfg.DBEncryptionKey()
if err != nil {
return err
}
wrappedExists := false
if *wrappedKeyPath != "" {
if _, err := os.Stat(*wrappedKeyPath); err == nil {
wrappedExists = true
} else if !errors.Is(err, os.ErrNotExist) {
return fmt.Errorf("check wrapped key: %w", err)
}
} else {
// default path alongside the config
defaultWrapped := cfg.DefaultWrappedKeyPath()
if _, err := os.Stat(defaultWrapped); err == nil {
*wrappedKeyPath = defaultWrapped
wrappedExists = true
}
}
locked := wrappedExists && envKey == nil
dl := newDaemonLock(locked)
var st *store.Store
var envKeyBytes []byte // kept for WrapKeyFn (enrollment wraps this key)
if !locked {
// Normal boot: env key or plaintext (dev/CI)
if envKey != nil {
envKeyBytes = make([]byte, len(envKey))
copy(envKeyBytes, envKey)
st, err = store.OpenEncrypted(ctx, cfg.DBPath, cfg.DBTmpfs, envKey)
} else {
st, err = store.Open(ctx, cfg.DBPath)
}
if err != nil {
return fmt.Errorf("open store: %w", err)
}
defer st.Close()
}
// ----- daemon components (only wired when unlocked) -----
// Pre-declare so the unlock path can wire them later.
var (
gatherer *loop.Gatherer
rules []loop.Rule
phr phraser.Phraser
voiceW *voiceWiring
dispatcher *delivery.Dispatcher
tl *tickLoop
coreAPI ipc.CoreAPI
eco *ecosystemWiring
factWorker *factEnrichmentWorker
evalWorker *memoryEvalWorker // nil ⇒ memory evaluation off (the default)
feedWkr *feedWorker // nil ⇒ no feed is read (the default)
crawlWkr *crawlWorker // nil ⇒ no page is watched (the default)
)
if !locked {
rules = loop.DefaultRules()
gatherer = loop.NewGatherer(st, rules)
if cfg.QuietHours != nil {
gatherer.SetQuietHours(cfg.QuietHours.Start, cfg.QuietHours.End)
}
// phraser
phr = 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),
LLMNudges: cfg.Phraser.LLMNudges,
ContextBlock: contextBlockFn(cfg, time.Now),
}
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)
}
}
// ecosystem — nexus + hexis + praxis (all over HTTP; no direct DB access)
eco = wireEcosystem(cfg)
// voice
voiceW, err = wireVoice(cfg, ipc.NewStoreAPI(st), phr, st.VectorMemory(), st, eco)
if err != nil {
return fmt.Errorf("wire voice: %w", err)
}
// delivery
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
}
var voiceSink delivery.Sink
if voiceW != nil {
voiceSink = voiceW.voiceSink
}
// A crashed prior run may have left "pending" delivery attempts (send
// may have landed externally, then the process died before recording
// it) — reconcile them to "unknown" before the tick loop resumes
// sending, so nothing auto-resends into that ambiguity.
if _, err := st.ReconcileStaleDeliveryAttempts(context.Background(), time.Now()); err != nil {
log.Printf("delivery outbox reconcile: %v", err)
}
dispatcher = delivery.NewDispatcher(delivery.Config{
Ntfy: ntfy,
Telegram: telegram,
Voice: voiceSink,
Ack: st,
Nudges: st,
Reminders: st,
Outbox: st,
})
// tick loop
tickInterval := time.Duration(cfg.TickInterval)
repeatInterval := time.Duration(cfg.RepeatInterval)
autotuneInterval := time.Duration(cfg.AutotuneInterval)
tl = newTickLoop(st, gatherer, dispatcher, phr, rules, tickInterval, repeatInterval, autotuneInterval, cfg.Digest, routinesFromConfig(cfg.Routines), config.MorningRoutinesFromConfig(cfg.MorningRoutines), cfg.PatternProposals)
factWorker = newFactEnrichmentWorker(st, eco, time.Duration(cfg.FactEnrichmentInterval))
evalWorker = newMemoryEvalWorker(st, phr, cfg)
feedWkr = newFeedWorker(ipc.NewStoreAPI(st), embedderOf(voiceW), cfg)
crawlWkr = newCrawlWorker(newCrawler(cfg), ipc.NewStoreAPI(st), embedderOf(voiceW), cfg)
coreAPI = &daemonAPI{
CoreAPI: ipc.NewStoreAPI(st),
getTrace: tl.trace,
getMorningStatus: func(ctx context.Context) []ipc.MorningRoutineStatus { return tl.morningStatus(ctx, time.Now()) },
getDayPlan: func(ctx context.Context) ipc.DayPlan { return tl.dayPlan(ctx, time.Now()) },
}
if voiceW != nil && voiceW.handler != nil {
api := coreAPI.(*daemonAPI)
api.chatFn = voiceW.handler.handleText
}
} else {
// locked mode: no real store yet, so there's no meaningful CoreAPI to
// serve. srv.Check below is the actual guard — every CoreAPI call is
// refused before it reaches this value. This is just a safe non-nil
// placeholder: if the guard is ever bypassed by a bug, calls land
// here and fail loudly with ipc.ErrNotImplemented instead of a nil
// dereference or, worse, silently succeeding.
coreAPI = ipc.UnimplementedCoreAPI{}
}
// ----- IPC boundary (core ↔ modules) -----
srv, err := ipc.Listen(cfg.SocketPath, coreAPI)
if err != nil {
return fmt.Errorf("ipc listen: %w", err)
}
passkeySess := webauthn.NewPasskeySession(5 * time.Minute)
// Set Server.Check — the single authorization guard, run once by
// Server.dispatch before any CoreAPI method is called (see
// internal/ipc/server.go). In locked mode this is the ONLY thing
// standing between an unauthenticated caller and the store: it must
// default-deny, with an explicit allowlist for the two methods the
// unlock flow itself needs (MethodAssertStepUp, MethodUnlock — neither
// of which touches CoreAPI; dispatch handles them directly via
// srv.StepUp/srv.UnlockFn). Forgetting to allowlist a new unlock-path
// method fails safe (denied); forgetting to guard a new CoreAPI method
// is impossible because there is nothing left to forget — every method
// not in the allowlist is refused by construction.
if locked {
srv.Check = func(ctx context.Context, m ipc.Method, _ json.RawMessage) error {
switch m {
case ipc.MethodAssertStepUp, ipc.MethodUnlock:
return nil // allowed in locked mode
default:
return errLocked
}
}
} else {
srv.Check = (&auth.Gate{Enrollment: auth.NewFloorEnrollment(), Session: passkeySess}).Check
}
srv.StepUp = func(ctx context.Context) error { return passkeySess.Assert(ctx, auth.Scope{}) }
// Mail ingestion (Vikunja #246): the hook stays nil unless an email block is
// configured and there is a llama-server to extract with, in which case
// ipc.MethodIngestMail reports ErrUnknownMethod.
if !locked {
wireMailIntake(srv, st, phr, cfg)
wireModelSwap(srv, phr, cfg)
}
// WrapKeyFn — wraps the env key with a passkey credential public key and
// persists the wrapped blob. Only wired when the daemon has the key in
// memory (env key mode). Called by mavweb after passkey enrollment.
if envKeyBytes != nil {
srv.WrapKeyFn = func(ctx context.Context, publicKey []byte) error {
blob, err := webauthn.WrapKey(envKeyBytes, publicKey)
if err != nil {
return fmt.Errorf("wrap encryption key: %w", err)
}
wp := *wrappedKeyPath
if wp == "" {
wp = cfg.DefaultWrappedKeyPath()
}
if err := os.WriteFile(wp, blob, 0o600); err != nil {
return fmt.Errorf("write wrapped key: %w", err)
}
log.Printf("mavend: wrapped encryption key with passkey credential (%d bytes)", len(blob))
return nil
}
}
// UnlockFn — cold-start unlock: unwraps the encryption key from the wrapped
// blob using the passkey credential public key, opens the store, wires all
// daemon components, and replaces the locked API.
if locked {
srv.UnlockFn = func(ctx context.Context, publicKey []byte) error {
wp := *wrappedKeyPath
blob, err := os.ReadFile(wp)
if err != nil {
return fmt.Errorf("read wrapped key: %w", err)
}
key, err := webauthn.UnwrapKey(blob, publicKey)
if err != nil {
return fmt.Errorf("unwrap key: %w", err)
}
// Open the store with the unwrapped key.
st, err = store.OpenEncrypted(ctx, cfg.DBPath, cfg.DBTmpfs, key)
if err != nil {
return fmt.Errorf("unlock store: %w", err)
}
// Wire everything.
rules = loop.DefaultRules()
gatherer = loop.NewGatherer(st, rules)
if cfg.QuietHours != nil {
gatherer.SetQuietHours(cfg.QuietHours.Start, cfg.QuietHours.End)
}
phr = 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),
LLMNudges: cfg.Phraser.LLMNudges,
ContextBlock: contextBlockFn(cfg, time.Now),
}
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
}
phr, err = phraser.NewLLMPhraser(ctx, pc)
if err != nil {
return fmt.Errorf("phraser: %w", err)
}
}
eco = wireEcosystem(cfg)
voiceW, err = wireVoice(cfg, ipc.NewStoreAPI(st), phr, st.VectorMemory(), st, eco)
if err != nil {
return fmt.Errorf("wire voice: %w", err)
}
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
}
var voiceSink delivery.Sink
if voiceW != nil {
voiceSink = voiceW.voiceSink
}
if _, err := st.ReconcileStaleDeliveryAttempts(context.Background(), time.Now()); err != nil {
log.Printf("delivery outbox reconcile: %v", err)
}
dispatcher = delivery.NewDispatcher(delivery.Config{
Ntfy: ntfy,
Telegram: telegram,
Voice: voiceSink,
Ack: st,
Nudges: st,
Reminders: st,
Outbox: st,
})
tickInterval := time.Duration(cfg.TickInterval)
repeatInterval := time.Duration(cfg.RepeatInterval)
autotuneInterval := time.Duration(cfg.AutotuneInterval)
tl = newTickLoop(st, gatherer, dispatcher, phr, rules, tickInterval, repeatInterval, autotuneInterval, cfg.Digest, routinesFromConfig(cfg.Routines), config.MorningRoutinesFromConfig(cfg.MorningRoutines), cfg.PatternProposals)
factWorker = newFactEnrichmentWorker(st, eco, time.Duration(cfg.FactEnrichmentInterval))
evalWorker = newMemoryEvalWorker(st, phr, cfg)
feedWkr = newFeedWorker(ipc.NewStoreAPI(st), embedderOf(voiceW), cfg)
crawlWkr = newCrawlWorker(newCrawler(cfg), ipc.NewStoreAPI(st), embedderOf(voiceW), cfg)
// Swap the CoreAPI from the locked placeholder to the real store adapter.
newAPI := &daemonAPI{
CoreAPI: ipc.NewStoreAPI(st),
getTrace: tl.trace,
getMorningStatus: func(ctx context.Context) []ipc.MorningRoutineStatus { return tl.morningStatus(ctx, time.Now()) },
getDayPlan: func(ctx context.Context) ipc.DayPlan { return tl.dayPlan(ctx, time.Now()) },
}
if voiceW != nil && voiceW.handler != nil {
newAPI.chatFn = voiceW.handler.handleText
}
srv.SetAPI(newAPI)
srv.Check = (&auth.Gate{Enrollment: auth.NewFloorEnrollment(), Session: passkeySess}).Check
wireMailIntake(srv, st, phr, cfg)
wireModelSwap(srv, phr, cfg)
// Start voice server.
if voiceW != nil {
var wg sync.WaitGroup
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())
}
// Start tick loop.
go func() {
tl.run(ctx)
}()
// Start fact-entity enrichment worker.
go func() {
factWorker.run(ctx)
}()
// Start background memory evaluation (nil unless configured).
if evalWorker != nil {
go func() {
evalWorker.run(ctx)
}()
}
// Start feed reading (nil unless configured).
if feedWkr != nil {
go func() {
feedWkr.run(ctx)
}()
}
// Start the watched-page crawls (nil unless configured).
if crawlWkr != nil {
go func() {
crawlWkr.run(ctx)
}()
}
dl.unlock()
log.Printf("mavend: unlocked via passkey assertion")
return nil
}
}
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 !locked && 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())
}
if !locked {
wg.Add(1)
go func() {
defer wg.Done()
tl.run(ctx)
}()
wg.Add(1)
go func() {
defer wg.Done()
factWorker.run(ctx)
}()
if evalWorker != nil {
wg.Add(1)
go func() {
defer wg.Done()
evalWorker.run(ctx)
}()
}
if feedWkr != nil {
wg.Add(1)
go func() {
defer wg.Done()
feedWkr.run(ctx)
}()
}
if crawlWkr != nil {
wg.Add(1)
go func() {
defer wg.Done()
crawlWkr.run(ctx)
}()
}
}
<-ctx.Done()
log.Printf("mavend: shutdown signal received")
if err := srv.Close(); err != nil {
log.Printf("ipc close: %v", err)
}
if voiceW != nil {
voiceW.close()
}
wg.Wait()
log.Printf("mavend: bye")
return nil
}
// personaFacts reads the optional, deployment-specific facts (his name, his
// city, the free-text persona string) out of the config. Everything here may
// be empty — the context block is correct without any of it.
func personaFacts(cfg *config.Config) persona.Facts {
f := persona.Facts{
// Telegram lives outside the voice block, so it counts either way.
Telegram: cfg.Telegram != nil && cfg.Telegram.BotToken != "" && cfg.Telegram.ChatID != "",
}
if cfg.Voice == nil {
return f
}
f.OwnerName = cfg.Voice.OwnerName
f.City = cfg.Voice.City
f.Static = cfg.Voice.Persona
// Same test wireVoice uses to pick the real provider over the stub.
f.Weather = cfg.Voice.Weather != nil && cfg.Voice.Weather.Provider == "open-meteo"
f.Tools = len(cfg.Voice.Tools) > 0
return f
}
// contextBlockFn returns the per-turn renderer of the shared context block.
// Per turn, not once at startup, because the block states the current time.
func contextBlockFn(cfg *config.Config, now func() time.Time) func() string {
f := personaFacts(cfg)
return func() string { return f.Block(now()) }
}