Files
noema/cmd/noemad/main.go
T
Andy Dixon d9c6ffa30f feat: add provider-neutral LLM layer with secrets, budgets, recording and prompts
Phase 7 (ADR-0004). Cognitive code asks the router for a role; the
router maps roles to configured models with ordered fallbacks, applies
global and per-mind daily token budgets and a concurrency limit, records
every call (request, response, usage, latency, cost, seed, request hash)
and can serve recordings back for exact replay. Providers are raw HTTP
clients for OpenAI-compatible, Anthropic and Ollama endpoints, with
embedding support for the embed role wired into memory retrieval.

Secrets are references only: env:, file:, or enc: values encrypted with
AES-256-GCM under NOEMA_MASTER_KEY; keys are resolved at call time and
never rendered, logged or exported. Outbound HTTP refuses private and
loopback addresses at dial time unless a provider explicitly allows it,
bounds redirects and caps bodies. Provider errors are scrubbed.

Prompts are named, versioned rows with system and user templates and an
optional JSON schema; untrusted text enters only through delimited data
blocks. Six defaults are seeded and never overwritten. The UI adds the
LLM page (providers, models, role matrix, usage, errors, budgets), a
provider page with connectivity test, and a prompt manager with editor,
test runner, history, restore, clone and diff. CLI: provider, prompt.
2026-06-23 23:43:33 +01:00

206 lines
7.5 KiB
Go

// Command noemad is the Noema daemon: API server, web UI, scheduler,
// integration manager and cognitive workers in one process.
package main
import (
"context"
"errors"
"flag"
"fmt"
"net/http"
"os"
"os/signal"
"syscall"
"time"
"github.com/andydixon/noema/internal/api"
"github.com/andydixon/noema/internal/app"
"github.com/andydixon/noema/internal/audit"
"github.com/andydixon/noema/internal/auth"
"github.com/andydixon/noema/internal/beliefs"
"github.com/andydixon/noema/internal/brain"
"github.com/andydixon/noema/internal/cognition"
"github.com/andydixon/noema/internal/config"
evstore "github.com/andydixon/noema/internal/events"
"github.com/andydixon/noema/internal/llm/prompts"
"github.com/andydixon/noema/internal/llm/router"
"github.com/andydixon/noema/internal/memory"
"github.com/andydixon/noema/internal/minds"
"github.com/andydixon/noema/internal/observability"
"github.com/andydixon/noema/internal/scheduler"
"github.com/andydixon/noema/internal/security/secrets"
"github.com/andydixon/noema/internal/storage"
"github.com/andydixon/noema/internal/ui"
"github.com/andydixon/noema/internal/version"
"github.com/andydixon/noema/migrations"
"github.com/andydixon/noema/pkg/events"
"github.com/andydixon/noema/pkg/ids"
)
func main() {
if err := run(); err != nil {
fmt.Fprintln(os.Stderr, "noemad:", err)
os.Exit(1)
}
}
func run() error {
var (
cfgPath = flag.String("config", "", "path to JSON config file (optional)")
migrate = flag.Bool("migrate", true, "apply pending migrations at start")
show = flag.Bool("version", false, "print version and exit")
)
flag.Parse()
if *show {
fmt.Println(version.Version)
return nil
}
cfg, err := config.Load(*cfgPath, os.LookupEnv)
if err != nil {
return err
}
log := observability.NewLogger(os.Stderr, cfg.LogLevel, cfg.LogFormat)
log.Info("starting noemad", "version", version.Version, "env", cfg.Env, "addr", cfg.HTTPAddr)
log.Debug("configuration", "config", fmt.Sprintf("%+v", cfg.Redacted()))
ctx, stop := signal.NotifyContext(context.Background(), syscall.SIGINT, syscall.SIGTERM)
defer stop()
db, err := storage.Open(ctx, cfg.DatabaseURL)
if err != nil {
return err
}
defer db.Close()
if *migrate {
applied, err := storage.MigrateUp(ctx, db, migrations.FS)
if err != nil {
return fmt.Errorf("migrate: %w", err)
}
if len(applied) > 0 {
log.Info("applied migrations", "migrations", applied)
}
}
metrics := observability.NewMetrics()
authSvc := auth.NewService(db, cfg.SessionIdleTTL, cfg.SessionAbsoluteTTL)
auditLog := audit.New(db, log)
deps := app.Deps{Config: cfg, Log: log, DB: db, Auth: authSvc, Audit: auditLog, Metrics: metrics, Minds: minds.NewStore(db), Events: evstore.NewStore(db, evstore.NewBus(200), metrics), Migrations: migrations.FS, Started: time.Now()}
if err := bootstrapAdmin(ctx, deps); err != nil {
return err
}
group := scheduler.NewGroup(ctx, log)
sec, err := secrets.New(cfg.MasterKey)
if err != nil {
return err
}
deps.Secrets = sec
if !sec.CanEncrypt() {
log.Warn("NOEMA_MASTER_KEY not set: API keys must be given as env: or file: references")
}
deps.LLMStore = router.NewStore(db)
deps.LLM = router.NewRouter(deps.LLMStore, sec, log, metrics, cfg.MaxConcurrentLLM)
deps.LLM.DailyTokenBudget = cfg.DailyTokenBudget
deps.LLM.MindBudget = func(id ids.ID) int64 {
m, err := deps.Minds.Get(ctx, id)
if err != nil {
return 0
}
return m.Config.DailyTokenBudget
}
deps.Prompts = prompts.NewStore(db)
if n, err := deps.Prompts.SeedDefaults(ctx); err != nil {
return fmt.Errorf("seed prompts: %w", err)
} else if n > 0 {
log.Info("installed default prompts", "count", n)
}
deps.Memory = memory.NewStore(ctx, db, deps.LLM.Embedder(ctx))
deps.Beliefs = beliefs.NewStore(db)
registry := brain.NewRegistry().AddProcess(cognition.Attend{}).AddProcess(cognition.Retrieve{}).AddProcess(cognition.Associate{})
cognition.Handlers{Memory: deps.Memory, Beliefs: deps.Beliefs}.Register(registry)
deps.Brain = brain.NewManager(brain.Config{DB: db, Events: deps.Events, Minds: deps.Minds, Registry: registry, Pool: scheduler.NewPool(cfg.MaxWorkers),
Log: log, Metrics: metrics, Services: brain.Services{Events: deps.Events, Memory: deps.Memory, Beliefs: deps.Beliefs, LLM: deps.LLM, Prompts: deps.Prompts}}, group)
group.Every("memory.decay", 6*time.Hour, func(ctx context.Context) error { return decayMemories(ctx, deps) })
group.Every("memory.embed", time.Minute, func(ctx context.Context) error { _, err := deps.Memory.EmbedMissing(ctx, 50); return err })
if err := deps.Brain.Start(ctx); err != nil {
return fmt.Errorf("start minds: %w", err)
}
var srv *api.Server
uiHandler, err := ui.New(deps, func(r *http.Request) any { return srv.Status(r.Context()) },
func(r *http.Request, id ids.ID) (api.EventContext, error) { return srv.Context(r, id) },
func(r *http.Request, m minds.Mind) (api.WorkspaceView, error) { return srv.Workspace(r.Context(), m) },
func(r *http.Request, mind, id ids.ID) (api.MemoryDetail, error) { return srv.MemoryDetail(r, mind, id) },
func(r *http.Request, mind, id ids.ID) (api.BeliefDetail, error) { return srv.BeliefDetail(r, mind, id) },
func() beliefs.Emitter { return srv.Emitter() })
if err != nil {
return err
}
srv = api.New(deps, uiHandler)
httpSrv := &http.Server{Addr: cfg.HTTPAddr, Handler: srv.Handler(), ReadHeaderTimeout: 10 * time.Second,
ReadTimeout: 30 * time.Second, IdleTimeout: 120 * time.Second, MaxHeaderBytes: 64 << 10}
group.Go("http", func(ctx context.Context) error {
errc := make(chan error, 1)
go func() { errc <- httpSrv.ListenAndServe() }() // owned: joined via errc below
select {
case err := <-errc:
if errors.Is(err, http.ErrServerClosed) {
return nil
}
return err
case <-ctx.Done():
shutdownCtx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
defer cancel()
return httpSrv.Shutdown(shutdownCtx)
}
})
group.Every("auth.sweep", 5*time.Minute, func(context.Context) error { authSvc.SweepLimiter(); return nil })
group.Every("auth.purge", time.Hour, authSvc.PurgeExpiredSessions)
log.Info("noemad ready", "url", "http://"+cfg.HTTPAddr)
<-ctx.Done()
log.Info("shutting down")
return group.Stop()
}
// bootstrapAdmin creates the first administrator from the environment when the
// users table is empty, so headless deployments can start without the setup page.
func bootstrapAdmin(ctx context.Context, d app.Deps) error {
n, err := d.Auth.CountUsers(ctx)
if err != nil {
return err
}
if n > 0 || d.Config.BootstrapAdminPassword == "" {
return nil
}
u, err := d.Auth.CreateUser(ctx, d.Config.BootstrapAdminUser, d.Config.BootstrapAdminPassword, auth.RoleAdministrator)
if err != nil {
return fmt.Errorf("bootstrap admin: %w", err)
}
d.Audit.Log(ctx, "user.bootstrap", "user", u.ID.String(), map[string]any{"username": u.Username, "via": "environment"})
d.Log.Info("created bootstrap administrator", "username", u.Username)
return nil
}
// decayMemories lowers activation of unused memories for every mind and leaves
// one summary event per mind so the decay is visible without spamming.
func decayMemories(ctx context.Context, d app.Deps) error {
list, err := d.Minds.List(ctx, false)
if err != nil {
return err
}
for _, m := range list {
n, err := d.Memory.Decay(ctx, m.ID, 14*24*time.Hour)
if err != nil {
return err
}
if n > 0 {
d.Events.Append(ctx, events.New{MindID: m.ID, Type: events.MemoryDecayed, Source: "memory.decay", Summary: fmt.Sprintf("activation decayed on %d memories", n), //nolint:errcheck
Salience: 0.05, Confidence: 1, Metadata: map[string]any{"count": n}})
}
}
return nil
}