Vellum/cmd/vellum/main.go
mithral fd377a7446 Offer transcoding as a resolve engine, as the last resort
Fourth and final step of ADR-008's server half. When nothing the client
declared can direct-play a file and this host can re-encode, resolve now
answers playable with engine "transcode". The client sees a string it already
understands, so the frozen JSON contract did not change.

The ordering is the whole point and is asserted directly: transcoding sits
after the direct-play loop, so a file that plays directly never pays for it.
Re-encoding something a client could already decode would burn the GPU and
lose quality for nothing, which is the failure mode ADR-008 rejects by
choosing direct play first. Verified red-green - hoisting the check above the
loop fails with "direct play must always win".

The capability is resolved once at boot and passed in, not read inside a
request: detection spawns ffmpeg to prove the encoder works, and that must
never happen on the request path. It is also passed rather than read from the
transcode package so the tests can drive both answers without hardware.

TranscodeID is deliberately not a registry entry. Every other engine is
something a client declares; this one is the server's own capability, so it
is not advertised in /playback/engines and a client must not name it.

On a host with no usable encoder canTranscode is false and every answer is
byte-identical to what it was before any of this existed - which is this
deployment, and is why ADR-002 still holds for it.
2026-10-12 12:03:41 -04:00

256 lines
9.4 KiB
Go

// Command vellum is the unified media server: one process, one database,
// every media type.
package main
import (
"context"
"encoding/json"
"errors"
"fmt"
"log/slog"
"net/http"
"os"
"os/signal"
"syscall"
"time"
"github.com/mithral/vellum/internal/auth"
"github.com/mithral/vellum/internal/catalog"
"github.com/mithral/vellum/internal/cli"
"github.com/mithral/vellum/internal/core"
"github.com/mithral/vellum/internal/discovery"
"github.com/mithral/vellum/internal/home"
"github.com/mithral/vellum/internal/httpapi"
"github.com/mithral/vellum/internal/jellyfin"
"github.com/mithral/vellum/internal/jobs"
"github.com/mithral/vellum/internal/library"
"github.com/mithral/vellum/internal/media"
"github.com/mithral/vellum/internal/metadata"
"github.com/mithral/vellum/internal/modules/comics"
"github.com/mithral/vellum/internal/modules/ebooks"
"github.com/mithral/vellum/internal/modules/games"
_ "github.com/mithral/vellum/internal/modules/photos" // registers the thumbnail extractor
"github.com/mithral/vellum/internal/playback"
"github.com/mithral/vellum/internal/providers"
"github.com/mithral/vellum/internal/scanner"
"github.com/mithral/vellum/internal/search"
"github.com/mithral/vellum/internal/subsonic"
"github.com/mithral/vellum/internal/transcode"
"github.com/mithral/vellum/migrations"
)
// version is overridden at build time with -ldflags "-X main.version=...".
var version = "dev"
func main() {
cfg, err := core.LoadConfig()
if err != nil {
fmt.Fprintln(os.Stderr, "vellum: fatal:", err)
os.Exit(1)
}
log := core.NewLogger(cfg.LogLevel, cfg.LogFormat)
// Administrative subcommands run instead of the server. This is the way
// back in when someone is locked out, and the way to take a backup while
// the server is stopped.
if handled, err := cli.Run(os.Args[1:], cfg, log); handled {
if err != nil {
fmt.Fprintln(os.Stderr, "vellum:", err)
os.Exit(1)
}
return
}
if err := run(cfg, log); err != nil {
fmt.Fprintln(os.Stderr, "vellum: fatal:", err)
os.Exit(1)
}
}
func run(cfg core.Config, log *slog.Logger) error {
log.Info("starting vellum", "version", version, "listen", cfg.Listen)
if err := cfg.Validate(); err != nil {
return err
}
db, err := core.OpenDB(cfg.DBPath)
if err != nil {
return err
}
defer db.Close()
migCtx, cancelMig := context.WithTimeout(context.Background(), 60*time.Second)
err = core.Migrate(migCtx, db, migrations.FS, log)
cancelMig()
if err != nil {
return err
}
api := httpapi.New(db, log, version)
authenticator := auth.NewAuthenticator(db, cfg.CookieName, cfg.SessionTTL, cfg.CookieSecure, log)
authenticator.TrustedProxies = cfg.TrustedProxies
if !cfg.CookieSecure {
log.Warn("VELLUM_COOKIE_SECURE is false; session cookies will be sent over plain HTTP. " +
"Set it to true when serving over TLS.")
}
if err := auth.EnsureAdminFromEnv(context.Background(), db, log, cfg.AdminUser, cfg.AdminPassword); err != nil {
return fmt.Errorf("bootstrap admin: %w", err)
}
authHandlers := auth.NewHandlers(authenticator, log)
authHandlers.Register(api.Mux())
api.SetAuth(authenticator)
// Background work: a table-backed queue in the same database. Created
// before the modules so a module's handlers can enqueue work.
queue := jobs.New(db, log)
library.NewHandlers(db, log, authenticator, queue).Register(api.Mux())
// Transcode sessions. Hardware-gated per ADR-008, so a host with no usable
// encoder answers "unavailable" on these routes rather than pretending.
// Owned here rather than inside the media handlers so the deferred Shutdown
// stops a running ffmpeg instead of leaving it behind the server.
sessions := transcode.New()
defer sessions.Shutdown()
media.NewHandlers(db, log, authenticator, cfg.ConfigDir, sessions).Register(api.Mux())
// The landing screen is an aggregate over items, not an item resource, so it
// is mounted by its own package.
home.NewHandlers(db, log, authenticator).Register(api.Mux())
ebooks.NewHandlers(db, log, authenticator).Register(api.Mux())
comics.NewHandlers(db, log, authenticator).Register(api.Mux())
games.NewHandlers(db, log, authenticator).Register(api.Mux())
search.NewHandlers(db, log, authenticator).Register(api.Mux())
// Playback engine registry + selection. Vellum never transcodes, so the
// server reports what is inside a file and matches it against the engines the
// CLIENT declares — a browser offers "html5", a native client can offer mpv.
// ADR-008: transcode capability is resolved ONCE, at boot. Detection spawns
// ffmpeg to prove the encoder actually encodes, so it must never run inside
// a request. On a host with no usable encoder this is false and every
// resolve answer is what it was before transcoding existed.
canTranscode := transcode.Detect().Available()
playback.NewHandlers(catalog.New(db), log, authenticator, canTranscode).Register(api.Mux())
// Client compatibility layers. Neither speaks the session cookie; both
// authenticate with an api_tokens credential and then go through the same
// grant chokepoint as the web app. They mount at the root because that is
// where the real clients look, and both report SupportsTranscoding=false:
// this server has no CPU for it, so a client that demands a transcode is
// refused rather than left waiting for one that will never start.
jellyfin.NewHandlers(db, log, authenticator).Register(api.Mux())
subsonic.NewHandlers(db, log, authenticator).Register(api.Mux())
// Scans run on the queue rather than inside the request: a real library
// takes longer than any sensible timeout, and a hanging request is
// indistinguishable from a broken server. The result is written back so
// the UI can read progress.
queue.Register(library.ScanJobKind, func(ctx context.Context, payload json.RawMessage) error {
var p library.ScanPayload
if err := json.Unmarshal(payload, &p); err != nil {
return fmt.Errorf("scan: bad payload: %w", err)
}
lib, err := library.Get(ctx, db, p.LibraryID)
if err != nil {
return nil // deleted since the job was queued
}
res, err := scanner.Scan(ctx, db, lib, log)
if jobID, ok := jobs.JobID(ctx); ok {
if serr := jobs.SetResult(ctx, db, jobID, res); serr != nil {
log.Warn("record scan result", "err", serr)
}
}
return err
})
// Providers are registered primary-first; a fallback is only consulted
// when the primary returns nothing.
providers.Register(providers.NewOpenLibrary())
providers.Register(providers.NewGoogleBooks())
providers.Register(providers.NewMusicBrainz())
if cfg.ComicVineAPIKey != "" {
providers.Register(providers.NewComicVine(cfg.ComicVineAPIKey))
} else {
log.Info("comic metadata disabled: set VELLUM_COMICVINE_API_KEY to enable ComicVine lookups")
}
if cfg.IGDBClientID != "" && cfg.IGDBClientSecret != "" {
providers.Register(providers.NewIGDB(cfg.IGDBClientID, cfg.IGDBClientSecret))
} else {
log.Info("game metadata disabled: set VELLUM_IGDB_CLIENT_ID and VELLUM_IGDB_CLIENT_SECRET to enable IGDB lookups")
}
if cfg.TMDBAPIKey != "" {
providers.Register(providers.NewTMDB(cfg.TMDBAPIKey))
} else {
log.Info("video metadata disabled: set VELLUM_TMDB_API_KEY to enable TMDB movie and TV lookups")
}
if cfg.TPDBAPIKey != "" {
providers.Register(providers.NewThePornDB(cfg.TPDBAPIKey))
} else {
log.Info("adult metadata disabled: set VELLUM_TPDB_API_KEY to enable ThePornDB lookups")
}
enricher := metadata.NewEnricher(db, log, cfg.ConfigDir)
queue.Register(metadata.JobKind, enricher.Handle)
metadata.NewHandlers(db, log, authenticator, queue).Register(api.Mux())
// Anything left 'running' belongs to a previous process that died mid-job.
// Requeue before the workers start, or it stays 'running' forever and the
// UI polls a job that will never move.
if n, err := queue.RecoverStale(context.Background()); err != nil {
log.Warn("recover stale jobs", "err", err)
} else if n > 0 {
log.Info("requeued jobs left running by a previous process", "count", n)
}
jobCtx, cancelJobs := context.WithCancel(context.Background())
defer cancelJobs()
go queue.Run(jobCtx)
// mDNS: advertise on the LAN so clients browse to this server instead of
// being handed a URL. Cancelled with the job queue so the records are
// withdrawn before the process exits.
kinds := make([]string, 0)
for _, mt := range library.SupportedTypes() {
kinds = append(kinds, mt.Kind)
}
go discovery.Start(jobCtx, cfg, version, kinds, log)
srv := &http.Server{
Addr: cfg.Listen,
Handler: api.Handler(),
// ReadHeaderTimeout protects against slowloris. WriteTimeout is
// deliberately zero: streaming large media files must not be cut off.
ReadHeaderTimeout: 10 * time.Second,
ReadTimeout: cfg.ReadTimeout,
WriteTimeout: cfg.WriteTimeout,
IdleTimeout: cfg.IdleTimeout,
ErrorLog: nil,
}
errCh := make(chan error, 1)
go func() {
log.Info("listening", "addr", cfg.Listen, "data_dir", cfg.DataDir)
if err := srv.ListenAndServe(); err != nil && !errors.Is(err, http.ErrServerClosed) {
errCh <- err
}
}()
stop := make(chan os.Signal, 1)
signal.Notify(stop, os.Interrupt, syscall.SIGTERM)
select {
case err := <-errCh:
return fmt.Errorf("http server: %w", err)
case sig := <-stop:
log.Info("shutting down", "signal", sig.String())
}
shutdownCtx, cancel := context.WithTimeout(context.Background(), cfg.ShutdownGrace)
defer cancel()
if err := srv.Shutdown(shutdownCtx); err != nil {
return fmt.Errorf("graceful shutdown: %w", err)
}
cancelJobs()
log.Info("stopped")
return nil
}