The integration cascade stored its top layer differently from the two below it: org (L2) and user (L3) plugin config lived in PocketBase, in a pluginSettings field, while the global (L1) layer sat in a plugins.json next to the binary. That split was accretion rather than design - the file was the whole store in the v1 MVP, and the per-tenant layers were later built on PocketBase and layered on top of it instead of replacing it. It also cost something real. plugins.json was a second state store with different durability from pb_data: its own volume, its own ownership, its own backup. Losing pb_data is unmissable; losing api_data was silent, which is how "every plugin comes back disabled after a redeploy" happened. L1 now lives in the app_settings collection - one record keyed "global", holding its settings in a pluginSettings field, the same mechanism and the same field name the layers below use. The documents still differ in shape, because only L1 carries enable state and the registration of external plugins, but the storage is no longer a special case. The Manager grows a Store seam (PocketBase in production, file for the import, memory for tests) and, more importantly, a loaded gate. Settings in a database mean the store can be unreachable at boot - a cold stack, or a service account still to be set from the panel. That must not read as "no plugins configured", or the first save would write emptiness over real settings. So until a read succeeds the Manager stays unloaded, every mutation is refused, /api/admin/plugins* answers 503, and a background retry backs off to two minutes. The same gate covers a document that will not parse: it is never replaced by one built from an empty map, which is a stronger guarantee than the .corrupt backup it replaces. Writing to a store also revealed a hole in the previous fix. Classifying a save failure as errPersist was left to each Store, and a store that returned a plain error would fall through to the "saved, but the plugin failed to start" branch and be reported as a 200 - the same silent-success bug through a different door. The Manager now classifies, whatever the Store returns; a test pins it. Upgrades are automatic: on the first boot that finds no settings in the database, an existing plugins.json is imported and renamed to plugins.json.migrated. The import is refused if the store is merely unreachable, or if the file does not parse, so a stale or broken file can never overwrite live settings. /data is still needed - the panel rewrites .env there when it retargets PocketBase - but plugin settings no longer depend on it. 21 tests in internal/plugins cover both stores, including the production path against a fake PocketBase: create-then-update of the singleton, round-trip across a restart, an outage that leaves settings intact, a missing collection reading as not-ready rather than empty, and the import running exactly once. go build, go vet and go test ./... pass. Schema changes are mirrored into scripts/setup-pocketbase.mjs as that file requires. Not verified: no Docker CLI here, so no image was built and the bootstrap of app_settings against a real PocketBase is untested outside the fake. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
104 lines
3.5 KiB
Go
104 lines
3.5 KiB
Go
// Command server runs the DriverVault API Server. It is the single gateway
|
|
// between clients (web app, phone app, Home Assistant plugin, ESP32 device) and
|
|
// the PocketBase database kept behind it — clients never talk to PocketBase
|
|
// directly. It also serves the superadmin web panel at the server root.
|
|
package main
|
|
|
|
import (
|
|
"context"
|
|
"errors"
|
|
"log"
|
|
"net/http"
|
|
"os"
|
|
"os/signal"
|
|
"syscall"
|
|
"time"
|
|
|
|
"drivervault/apiserver/internal/api"
|
|
"drivervault/apiserver/internal/bootstrap"
|
|
"drivervault/apiserver/internal/config"
|
|
"drivervault/apiserver/internal/pb"
|
|
)
|
|
|
|
func main() {
|
|
log.SetFlags(log.LstdFlags | log.Lmsgprefix)
|
|
log.SetPrefix("[api] ")
|
|
|
|
cfg := config.Load()
|
|
|
|
client := pb.New(cfg.PocketBaseURL, cfg.PocketBaseAdminEmail, cfg.PocketBaseAdminPassword)
|
|
|
|
// Authenticate the service account up front so the first request doesn't pay
|
|
// for it. A failure is NOT fatal: the PocketBase connection is editable at
|
|
// runtime from the panel, so a superadmin must be able to log in and fix a
|
|
// bad address or bad credentials.
|
|
if cfg.AdminConfigured() {
|
|
authCtx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
|
|
if err := client.Authenticate(authCtx); err != nil {
|
|
log.Printf("WARNING: PocketBase service account auth failed (%s): %v", cfg.PocketBaseURL, err)
|
|
log.Printf("fix it under Settings → PocketBase in the panel at %s", cfg.Addr)
|
|
} else {
|
|
log.Printf("authenticated to PocketBase at %s", cfg.PocketBaseURL)
|
|
}
|
|
cancel()
|
|
} else {
|
|
log.Println("WARNING: POCKETBASE_ADMIN_EMAIL/PASSWORD unset — management endpoints return 503 until configured")
|
|
}
|
|
|
|
// Bring PocketBase up to the expected schema (create missing collections,
|
|
// reconcile existing ones) and ensure the super-admin. Idempotent, so it runs
|
|
// on every boot. Non-fatal: a fresh PocketBase that isn't reachable yet, or a
|
|
// bad service account, must not stop the panel from coming up so a superadmin
|
|
// can log in and fix the connection.
|
|
if cfg.Bootstrap && cfg.AdminConfigured() {
|
|
bootCtx, cancel := context.WithTimeout(context.Background(), 60*time.Second)
|
|
if err := bootstrap.Run(bootCtx, client, bootstrap.Options{
|
|
UsersCollection: cfg.UsersCollection,
|
|
SuperAdminEmail: cfg.SuperAdminEmail,
|
|
SuperAdminPassword: cfg.SuperAdminPassword,
|
|
SuperAdminName: cfg.SuperAdminName,
|
|
}); err != nil {
|
|
log.Printf("WARNING: bootstrap failed: %v", err)
|
|
} else {
|
|
log.Println("bootstrap: PocketBase schema ready")
|
|
}
|
|
cancel()
|
|
}
|
|
|
|
srv := api.New(cfg, client)
|
|
|
|
// Not fatal: the plugin settings live in PocketBase, which may not be
|
|
// reachable yet on a cold stack or before a service account is configured.
|
|
// StartPlugins logs the reason and retries in the background; the plugin
|
|
// endpoints answer 503 until the read succeeds.
|
|
_ = srv.StartPlugins()
|
|
|
|
httpServer := &http.Server{
|
|
Addr: cfg.Addr,
|
|
Handler: srv.Handler(),
|
|
ReadHeaderTimeout: 10 * time.Second,
|
|
IdleTimeout: 60 * time.Second,
|
|
}
|
|
|
|
go func() {
|
|
log.Printf("listening on %s (PocketBase: %s, panel at /)", cfg.Addr, cfg.PocketBaseURL)
|
|
if err := httpServer.ListenAndServe(); err != nil && !errors.Is(err, http.ErrServerClosed) {
|
|
log.Fatalf("server error: %v", err)
|
|
}
|
|
}()
|
|
|
|
// Graceful shutdown on SIGINT/SIGTERM.
|
|
stop := make(chan os.Signal, 1)
|
|
signal.Notify(stop, os.Interrupt, syscall.SIGTERM)
|
|
<-stop
|
|
log.Println("shutting down...")
|
|
|
|
ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
|
|
defer cancel()
|
|
srv.Stop(ctx)
|
|
if err := httpServer.Shutdown(ctx); err != nil {
|
|
log.Printf("shutdown error: %v", err)
|
|
}
|
|
log.Println("stopped")
|
|
}
|