thermograph/backend/daemon/main.go

// thermograph-daemon owns the backend's long-lived stateful I/O — the Discord
// gateway websocket (IDENTIFY/RESUME/heartbeat/backoff) and the recurring-job
// timers — and nothing else. Anything that needs data calls back into the
// Python app over its internal-only HTTP routes (see internal/apiclient).
//
// This replaces the two in-process background jobs web/app.py used to start
// under leader election. One daemon process replaces the election entirely:
// there is exactly one replica of this container, so the single-connection
// invariant (Discord tolerates only one gateway session per token; duplicated
// APScheduler replicas would repeat every job) holds by deployment shape
// rather than by runtime coordination.
package main

import (
	"context"
	"log/slog"
	"os"
	"os/signal"
	"sync"
	"syscall"
	"time"

	"thermograph/daemon/internal/apiclient"
	"thermograph/daemon/internal/config"
	"thermograph/daemon/internal/cron"
	"thermograph/daemon/internal/gateway"
)

// shutdownGrace bounds how long we wait for the gateway and cron halves to
// stop after a signal. Long enough for the gateway to close its session
// cleanly (a dirty exit leaves Discord holding a stale session), short enough
// to stay inside a container runtime's stop timeout so we exit on our own
// terms rather than being SIGKILLed mid-close.
const shutdownGrace = 10 * time.Second

func main() {
	os.Exit(run())
}

// run is main minus os.Exit, so deferred cleanup actually runs.
func run() int {
	// Everything to stdout: the container collects stdout, nothing else.
	logger := slog.New(slog.NewTextHandler(os.Stdout, nil))

	// Refuse to start on bad config rather than running half-configured: a
	// daemon that cannot authenticate to the backend can only fail silently.
	cfg, err := config.Load()
	if err != nil {
		logger.Error("invalid configuration; refusing to start", "err", err)
		return 1
	}

	// One context for everything long-lived; SIGINT/SIGTERM cancels it so the
	// gateway can close its session cleanly (Discord treats an abrupt drop
	// worse than a clean close for RESUME purposes).
	ctx, stop := signal.NotifyContext(context.Background(), os.Interrupt, syscall.SIGTERM)
	defer stop()

	api := apiclient.New(cfg.APIBase, cfg.InternalToken)

	logger.Info("thermograph-daemon starting",
		"api", cfg.APIBase,
		"discord", cfg.DiscordEnabled,
		"warm_cities_interval", cfg.WarmCitiesInterval,
		"indexnow_interval", cfg.IndexNowInterval)

	var wg sync.WaitGroup

	// The cron half runs unconditionally — it is the floor of what this
	// daemon does, gateway or not.
	wg.Add(1)
	go func() {
		defer wg.Done()
		cron.Run(ctx, logger,
			cron.Job{
				Name:     "warm-cities",
				Interval: cfg.WarmCitiesInterval,
				Run:      func(ctx context.Context) error { return api.WarmCities(ctx) },
			},
			cron.Job{
				Name:     "indexnow",
				Interval: cfg.IndexNowInterval,
				Run:      func(ctx context.Context) error { return api.IndexNow(ctx) },
			},
		)
	}()

	if cfg.DiscordEnabled {
		wg.Add(1)
		go func() {
			defer wg.Done()
			// A fatal gateway error (bad token, disallowed intents) must not
			// take the cron half down: the schedule is independently useful,
			// and exiting here would turn a Discord misconfiguration into a
			// crash-loop that also stops warm-cities/IndexNow. Log loudly and
			// keep running instead.
			if err := gateway.Run(ctx, cfg, api); err != nil && ctx.Err() == nil {
				logger.Error("discord gateway exited with a fatal error; cron jobs keep running without it",
					"err", err)
			}
		}()
	} else {
		// An unconfigured deploy must pay nothing, same as the Python side:
		// no connection, no retries — just say so once and run cron-only.
		logger.Info("discord gateway disabled (THERMOGRAPH_DISCORD_BOT not truthy or no bot token); running cron-only")
	}

	<-ctx.Done()
	// Restore default signal handling immediately: a second SIGINT/SIGTERM
	// during the grace period kills us the ordinary way instead of being
	// swallowed by the (already-cancelled) NotifyContext.
	stop()
	logger.Info("shutting down", "grace", shutdownGrace)

	done := make(chan struct{})
	go func() {
		wg.Wait()
		close(done)
	}()
	select {
	case <-done:
		logger.Info("shutdown complete")
	case <-time.After(shutdownGrace):
		// This process is the sole holder of the gateway connection, so a
		// clean close matters — but a wedged goroutine must not hold the
		// container's stop hostage forever.
		logger.Warn("shutdown grace period elapsed before all loops stopped; exiting anyway")
	}
	return 0
}