feat(agent): auto-resume interrupted downloads after a daemon restart

A daemon restart used to abandon in-flight downloads: the in-memory queue was
lost and the web doesn't re-dispatch a stuck task, so the user had to retry
manually. The bytes already persisted (mmap + anacrolix's piece-completion DB
keyed by info_hash; debrid via Range; usenet via its tracker) — the daemon just
didn't re-attempt the work.

ActiveTaskStore persists each in-flight download's agent.Task payload to
active-tasks.json; the daemon re-submits them on startup so the downloaders
resume the partial data. manager.Submit now dedups (the startup re-submit and a
later web re-dispatch can't both run), and recordFinished removes a task from
the store only on a genuine terminal — shuttingDown (set before Shutdown cancels
the task contexts) keeps shutdown-interrupted tasks so they resume next start.
Stream/seed/upgrade tasks aren't persisted; ForceStart is cleared on resume.
This commit is contained in:
Deivid Soto 2026-05-31 22:44:05 +02:00
parent b708bb8ab2
commit 445da233c0
6 changed files with 399 additions and 9 deletions

View file

@ -316,6 +316,11 @@ func runDaemonStart() error {
},
}, reporter, torrentDl, debridDl, usenetDl)
// Resume store: persist in-flight downloads so a daemon restart can re-submit
// them (the downloaders resume the partial data). Wire it before any Submit.
taskStore := agent.NewActiveTaskStore()
manager.SetTaskStore(taskStore)
// Create persistent stream server
streamSrv := engine.NewStreamServer(cfg.Download.StreamPort)
streamSrv.SetUPnPEnabled(cfg.Download.EnableUPnP)
@ -426,6 +431,20 @@ func runDaemonStart() error {
}
}
// Resume downloads interrupted by the previous shutdown/crash. Re-submit
// each persisted task; its downloader picks up the partial data (torrent via
// the piece-completion DB, debrid via Range, usenet via its tracker). Done
// before the sync loop starts; a later web re-dispatch of the same id is
// deduped by the manager.
if resume := taskStore.Load(); len(resume) > 0 {
log.Printf("[resume] re-submitting %d interrupted download(s)", len(resume))
for _, t := range resume {
t.ForceStart = false // respect MaxConcurrent on bulk auto-resume
log.Printf("[resume] %s — %s", agent.ShortID(t.ID), t.Title)
manager.Submit(ctx, t)
}
}
// Wire: sync receives control signals → act on manager
d.OnControlAction = func(action, taskID string, deleteFiles bool) {
switch action {
@ -847,13 +866,16 @@ func runDaemonStart() error {
cancelStreamContexts()
cancelAllPlayerSessions()
streamSrv.Shutdown(context.Background())
cancel()
// Give active downloads 30s to finish
// Drain active downloads BEFORE cancelling the daemon context. Shutdown
// sets shuttingDown + cancels each task context itself, so interrupted
// downloads keep their resume-store entry. Cancelling the shared ctx first
// would make them look like genuine failures and wipe the entry → no resume.
shutdownCtx, shutdownCancel := context.WithTimeout(context.Background(), 30*time.Second)
defer shutdownCancel()
manager.Shutdown(shutdownCtx)
cancel()
d.Deregister()
fmt.Println(" Daemon stopped.")
return nil