Docker Build / docker (push) Successful in 38s
## Summary
- `POST /update` on the master (outside OIDC, bearer `UPDATER_API_KEY`; unset → 503). Matches `image` against `image_repo` on all agents, marks `available_*` on every match, starts webhook-triggered jobs for `auto` services targeting `<image_repo>:<tag>` (followed tag when no tag is given), and waits for them up to `UPDATE_TIMEOUT` (default 5m). 404 on no match, 500 if any auto job failed or timed out, otherwise 200.
- Manual/auto toggle per service on the overview and service page (`POST /services/{id}/mode`, CSRF); auto is blocked for self, `build:` and container services with the reason shown. "Update available" badge and an "Available" row.
- `FinishJob` clears `available_*` only when the successful job was created for that exact ref, after it was reported. Migration `0003_webhook.sql`, phase-3 plan doc, README / gitea-action README / CLAUDE.md / deploy example updated. `action.yml` unchanged.
Closes #8
## Behaviour changes for CI
- Mixed results now return 500 (the old 207 is gone); no match returns 404 instead of 200.
- With a `tag`, Compose services get pinned to `<image_repo>:<tag>` via `compose.override.yaml`; the tag must be a pushed tag.
- `busy` (job already active) and `refused` (not updatable) are reported but return 200.
- The reverse proxy read timeout must exceed `UPDATE_TIMEOUT`.
## Test plan
- [x] `go test ./...` and `go test -race ./internal/agent/... ./internal/master/... ./internal/e2e/`
- [x] `go test -tags integration ./internal/master/store/` against throwaway Postgres
- [x] UI verified in browser (mode toggle, disabled reason, badge via SSE, Available row)
- [ ] Manual: webhook with manual service → `marked` + badge
- [ ] Manual: webhook with auto service → waits, `succeeded`, badge cleared, override pinned
- [ ] Manual: wrong token 401, unknown image 404, offline agent 500
- [ ] Gitea action pointed at the master's `/update` in a real CI run
Reviewed-on: #22
149 lines
4.5 KiB
Go
149 lines
4.5 KiB
Go
// Command updater-master serves the package-updater UI and accepts agent
|
|
// connections.
|
|
package main
|
|
|
|
import (
|
|
"context"
|
|
"crypto/tls"
|
|
"errors"
|
|
"fmt"
|
|
"net"
|
|
"net/http"
|
|
"os"
|
|
"os/signal"
|
|
"strings"
|
|
"syscall"
|
|
"time"
|
|
|
|
"github.com/shcizo/package-updater/internal/logging"
|
|
"github.com/shcizo/package-updater/internal/master/config"
|
|
"github.com/shcizo/package-updater/internal/master/events"
|
|
"github.com/shcizo/package-updater/internal/master/hub"
|
|
"github.com/shcizo/package-updater/internal/master/jobs"
|
|
"github.com/shcizo/package-updater/internal/master/store"
|
|
"github.com/shcizo/package-updater/internal/master/web"
|
|
"github.com/shcizo/package-updater/internal/master/webauth"
|
|
"github.com/shcizo/package-updater/internal/master/webhook"
|
|
"github.com/shcizo/package-updater/internal/pin"
|
|
)
|
|
|
|
// Build info is injected at link time via -ldflags="-X main.version=...".
|
|
var version = "dev"
|
|
|
|
func main() {
|
|
if err := run(); err != nil {
|
|
fmt.Fprintln(os.Stderr, "fatal:", err)
|
|
os.Exit(1)
|
|
}
|
|
}
|
|
|
|
func run() error {
|
|
cfg, err := config.Load()
|
|
if err != nil {
|
|
return err
|
|
}
|
|
logger := logging.New(cfg.LogLevel)
|
|
ctx, stop := signal.NotifyContext(context.Background(), syscall.SIGINT, syscall.SIGTERM)
|
|
defer stop()
|
|
|
|
st, err := store.Open(ctx, cfg.DatabaseURL)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
defer st.Close()
|
|
|
|
key, err := st.LoadOrCreateIdentity(ctx, pin.GenerateKey)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
cert, err := pin.Certificate(key)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
fingerprint, err := pin.Fingerprint(key.Public())
|
|
if err != nil {
|
|
return err
|
|
}
|
|
logger.Info("master_starting", "version", version, "master_key", fingerprint)
|
|
|
|
broker := events.NewBroker()
|
|
agentHub := hub.New(st, broker, logger)
|
|
jobService := jobs.New(st, agentHub, broker, cfg.AgentImage, logger)
|
|
|
|
provider, err := webauth.NewOIDCProvider(ctx, webauth.OIDCConfig{
|
|
Issuer: cfg.OIDCIssuer, ClientID: cfg.OIDCClientID, ClientSecret: cfg.OIDCClientSecret,
|
|
RedirectURL: cfg.PublicURL + "/auth/callback",
|
|
})
|
|
if err != nil {
|
|
return err
|
|
}
|
|
auth := webauth.New(provider, st, cfg.AllowedGroup, strings.HasPrefix(cfg.PublicURL, "https://"), logger)
|
|
|
|
ui, err := web.New(st, agentHub, jobService, broker, web.Config{
|
|
AgentURL: cfg.AgentURL, MasterKey: fingerprint, AgentImage: cfg.AgentImage,
|
|
}, logger)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
mux := http.NewServeMux()
|
|
mux.HandleFunc("GET /healthz", func(w http.ResponseWriter, r *http.Request) {
|
|
if err := st.Ping(r.Context()); err != nil {
|
|
http.Error(w, "database unreachable", http.StatusServiceUnavailable)
|
|
return
|
|
}
|
|
_, _ = w.Write([]byte("ok"))
|
|
})
|
|
// The webhook does its own bearer-token check, so it sits outside the
|
|
// OIDC login like /healthz.
|
|
mux.Handle("POST /update", webhook.New(st, jobService, broker, webhook.Config{
|
|
Token: cfg.UpdaterAPIKey, Timeout: cfg.UpdateTimeout, PublicURL: cfg.PublicURL,
|
|
}, logger))
|
|
if cfg.UpdaterAPIKey == "" {
|
|
logger.Warn("webhook_disabled", "reason", "UPDATER_API_KEY not set")
|
|
}
|
|
mux.HandleFunc("GET /auth/login", auth.Login)
|
|
mux.HandleFunc("GET /auth/callback", auth.Callback)
|
|
mux.Handle("POST /auth/logout", auth.Require(http.HandlerFunc(auth.Logout)))
|
|
ui.Register(mux, auth.Require)
|
|
|
|
// BaseContext ties every request context to the signal context, so on
|
|
// shutdown the long-lived SSE handlers and agent connections return
|
|
// instead of holding Shutdown until its timeout.
|
|
baseContext := func(net.Listener) context.Context { return ctx }
|
|
|
|
// No WriteTimeout on either server: SSE streams, agent connections and
|
|
// POST /update (which waits up to UPDATE_TIMEOUT) are long-lived by design.
|
|
webSrv := &http.Server{
|
|
Addr: ":" + cfg.Port, Handler: mux, ReadHeaderTimeout: 10 * time.Second,
|
|
BaseContext: baseContext,
|
|
}
|
|
|
|
agentMux := http.NewServeMux()
|
|
agentMux.Handle("GET /agent", agentHub)
|
|
agentSrv := &http.Server{
|
|
Addr: ":" + cfg.AgentPort, Handler: agentMux, ReadHeaderTimeout: 10 * time.Second,
|
|
TLSConfig: &tls.Config{Certificates: []tls.Certificate{cert}, MinVersion: tls.VersionTLS13},
|
|
BaseContext: baseContext,
|
|
}
|
|
|
|
errCh := make(chan error, 2)
|
|
go func() { errCh <- webSrv.ListenAndServe() }()
|
|
go func() { errCh <- agentSrv.ListenAndServeTLS("", "") }()
|
|
logger.Info("listening", "web", webSrv.Addr, "agents", agentSrv.Addr)
|
|
|
|
select {
|
|
case <-ctx.Done():
|
|
logger.Info("shutdown_signal")
|
|
case err := <-errCh:
|
|
if !errors.Is(err, http.ErrServerClosed) {
|
|
return err
|
|
}
|
|
}
|
|
shutdownCtx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
|
|
defer cancel()
|
|
_ = webSrv.Shutdown(shutdownCtx)
|
|
_ = agentSrv.Shutdown(shutdownCtx)
|
|
return nil
|
|
}
|