Cyrene_v2/internal/services/channelbridge/reload.go

package channelbridge

// This file holds the hot-reload machinery for the channel bridge (design/04
// §3.1). The panel saves a platform's account config to channels.json and calls
// Bridge.Reload(platform): the factory rebuilds that platform's adapters, they
// connect first (new messages use the new config), then the old adapters are
// gracefully stopped. A message already in flight finishes on its old adapter
// because processing is spawned with the bridge-lifetime context, not the
// per-adapter read context that reload cancels.

import (
	"context"
	"errors"
	"fmt"

	"git.yeij.top/AskaEth/Cyrene_v2/internal/channel/adapter"
)

// PlatformFactory rebuilds the adapters for a platform from its current effective
// account config (channels.json, falling back to env). It is injected so the
// bridge can hot-replace a platform's adapters when the panel saves a new config
// without a restart. The concrete implementation lives in the composition root
// (cmd/cyrene), which owns the platform adapter constructors.
type PlatformFactory interface {
	// Build returns the adapters for platform from its effective account config.
	// The returned slice may be empty when the platform has no configured account.
	Build(platform string) ([]adapter.PlatformAdapter, error)
}

// ErrNilFactory is returned when a reload is requested without a platform factory
// injected (no hot-reload configuration source).
var ErrNilFactory = errors.New("channelbridge: nil platform factory")

// ErrBridgeClosed is returned when a reload is requested on a stopped bridge.
var ErrBridgeClosed = errors.New("channelbridge: bridge is not running")

// connectAndRun dials a single adapter (bound by connectTimeout) and, on success,
// installs its inbound handler and launches its read loop under a per-adapter
// context. The per-adapter context is what a hot reload cancels to stop the old
// read loop; message processing is spawned with the bridge-lifetime context so an
// in-flight message started before a Reload completes on its old adapter.
func (b *Bridge) connectAndRun(a adapter.PlatformAdapter) {
	if a == nil {
		return
	}
	if !b.configured(a) {
		b.log.Warn("channel skipped: no credentials", "channel", a.Name())
		return
	}
	connCtx, cancel := context.WithTimeout(context.Background(), connectTimeout)
	err := a.Connect(connCtx)
	cancel()
	if err != nil {
		b.log.Warn("channel connect failed, leaving disconnected",
			"channel", a.Name(), "error", err)
		return
	}

	// Close over the adapter so the inbound callback knows which account received
	// the message — required for multi-account reply routing and for reading that
	// account's allow/deny lists (design/16 §4.6 §5).
	a.SetMessageHandler(func(_ context.Context, msg adapter.UnifiedMessage) {
		b.onMessage(b.ctx, msg, a)
	})
	b.mu.Lock()
	if b.closed {
		b.mu.Unlock()
		ctx, c := context.WithTimeout(context.Background(), connectTimeout)
		_ = a.Disconnect(ctx)
		c()
		return
	}
	readCtx, rcancel := context.WithCancel(b.ctx)
	b.readCancels[a.Name()] = rcancel
	b.connected[a.Name()] = true
	b.mu.Unlock()
	b.wg.Add(1)
	go b.readLoop(a, readCtx)
	b.log.Info("channel connected", "channel", a.Name())
}

// Reload rebuilds the adapters for a platform from its current effective config
// (via the injected factory) and hot-replaces the running ones without a restart
// (design/04 §3.1). The rebuilt adapters connect first; messages that arrived on
// the old adapters finish on them, and new messages are picked up by the new
// configuration. An account that was removed stops its old adapter, and an
// unchanged-name account stops the old adapter once the new one is live.
func (b *Bridge) Reload(platform string) error {
	if b.factory == nil {
		return ErrNilFactory
	}
	b.mu.Lock()
	started := b.started
	closed := b.closed
	b.mu.Unlock()
	if !started || closed {
		return ErrBridgeClosed
	}

	newAdapters, err := b.factory.Build(platform)
	if err != nil {
		return fmt.Errorf("channelbridge: build %s: %w", platform, err)
	}
	old, oldCancels := b.adapterSnap(platform)
	newNames := make(map[string]bool, len(newAdapters))
	for _, a := range newAdapters {
		newNames[a.Name()] = true
	}
	for _, a := range newAdapters {
		b.connectAndRun(a)
	}
	for _, o := range old {
		if newNames[o.Name()] {
			// Same-name account replaced by the rebuilt adapter: stop the old read
			// loop but leave the registry entry — it now points at the new adapter.
			b.cancelAndDisconnect(o, oldCancels[o.Name()])
			continue
		}
		// Account removed (or renamed) entirely: stop it and drop its registry
		// entries, so a subsequent snapshot no longer sees it.
		b.removeAdapter(o, oldCancels[o.Name()])
	}
	b.log.Info("channel reloaded", "platform", platform, "adapters", len(newAdapters))
	return nil
}

// adapterSnap returns the adapters currently registered for a platform, together
// with the context-cancel func that controls each one's read loop. It is used by
// Reload to stop the old adapters after the rebuilt ones are live.
func (b *Bridge) adapterSnap(platform string) ([]adapter.PlatformAdapter, map[string]context.CancelFunc) {
	b.mu.RLock()
	defer b.mu.RUnlock()
	var list []adapter.PlatformAdapter
	cancels := make(map[string]context.CancelFunc)
	for name, a := range b.adapters {
		if basePlatform(name) != platform {
			continue
		}
		list = append(list, a)
		if c, ok := b.readCancels[name]; ok {
			cancels[name] = c
		}
	}
	return list, cancels
}

// cancelAndDisconnect stops an adapter's read loop and tears down its session.
// It never touches the registry map: callers that replace a same-name adapter
// want the (new) entry to stay, and callers that remove an account use
// removeAdapter.
func (b *Bridge) cancelAndDisconnect(o adapter.PlatformAdapter, c context.CancelFunc) {
	if c != nil {
		c()
	}
	ctx, cancel := context.WithTimeout(context.Background(), connectTimeout)
	_ = o.Disconnect(ctx)
	cancel()
	b.log.Info("channel (reload) stopped", "channel", o.Name())
}

// removeAdapter stops an account's adapter and drops its registry entries. It is
// only called for names that were NOT rebuilt by Reload, so the delete can never
// remove a replacement adapter that now owns the name.
func (b *Bridge) removeAdapter(o adapter.PlatformAdapter, c context.CancelFunc) {
	b.cancelAndDisconnect(o, c)
	name := o.Name()
	b.mu.Lock()
	delete(b.adapters, name)
	delete(b.connected, name)
	delete(b.readCancels, name)
	b.mu.Unlock()
	b.log.Info("channel (reload) removed", "channel", name)
}