Files
wangxiaolei 4314b8f1ee fix: synchronize remote debugging plugins across cluster nodes (#589)
Remote debugging plugins were not being synchronized across cluster nodes,
causing "no plugin available nodes found" errors when trying to invoke
plugins from different nodes.

1. **Remote debugging plugins not registered to cluster** - The
   `ClusterTunnel` notifier was not being added to ControlPanel
2. **Plugin ID inconsistency** - Remote plugins used different plugin_id
   formats during installation vs. querying
3. **Non-idempotent registration** - `RegisterPlugin` failed on reconnection
   with "plugin has been registered" error

- **internal/types/models/curd/atomic.go**:
  - Unify plugin_id calculation for remote plugins (author/name without version)
  - Remove plugin_id from plugin query conditions
  - Clear old cache when plugin_id is updated

- **internal/cluster/plugin.go**:
  - Make `RegisterPlugin` idempotent by updating existing plugin instead
    of returning error

- **internal/core/control_panel/daemon.go**:
  - Add cluster field to ControlPanel
  - Add SetCluster() method for lazy cluster initialization

- **internal/core/control_panel/server_debugger.go**:
  - Register remote debugging plugins to cluster on connection
  - Unregister from cluster on disconnection

- **internal/core/plugin_manager/manager.go**:
  - Add SetCluster() method to set cluster after initialization

- **internal/server/server.go**:
  - Call SetCluster() instead of AddClusterTunnel()

Only remote debugging plugins are synchronized across cluster nodes.
Local plugins run only on the node where they are installed and are
not registered to the cluster.

- Error handling improvements using `errors.Is()` instead of `==`
- Handle 404 for missing plugin assets gracefully
- Handle already-installed debugging plugins gracefully

- Remote debugging plugin can be invoked from any node in the cluster
- Plugin reconnection works without errors
- Cache invalidation works correctly when plugin_id changes
2026-03-05 14:46:13 +08:00

133 lines
4.0 KiB
Go

package server
import (
"github.com/getsentry/sentry-go"
"github.com/langgenius/dify-cloud-kit/oss"
"github.com/langgenius/dify-cloud-kit/oss/factory"
"github.com/langgenius/dify-plugin-daemon/internal/cluster"
"github.com/langgenius/dify-plugin-daemon/internal/core/persistence"
"github.com/langgenius/dify-plugin-daemon/internal/core/plugin_manager"
"github.com/langgenius/dify-plugin-daemon/internal/db"
"github.com/langgenius/dify-plugin-daemon/internal/tasks"
"github.com/langgenius/dify-plugin-daemon/internal/types/app"
"github.com/langgenius/dify-plugin-daemon/pkg/utils/cache"
"github.com/langgenius/dify-plugin-daemon/pkg/utils/log"
"github.com/langgenius/dify-plugin-daemon/pkg/utils/routine"
)
func initOSS(config *app.Config) oss.OSS {
// init storage
var storage oss.OSS
var err error
storage, err = factory.Load(config.PluginStorageType, oss.OSSArgs{
Local: &oss.Local{
Path: config.PluginStorageLocalRoot,
},
S3: &oss.S3{
UseAws: config.S3UseAWS,
Endpoint: config.S3Endpoint,
UsePathStyle: config.S3UsePathStyle,
AccessKey: config.AWSAccessKey,
SecretKey: config.AWSSecretKey,
Bucket: config.PluginStorageOSSBucket,
Region: config.AWSRegion,
UseIamRole: config.S3UseAwsManagedIam,
},
TencentCOS: &oss.TencentCOS{
Region: config.TencentCOSRegion,
Endpoint: config.TencentCOSEndpoint,
SecretID: config.TencentCOSSecretId,
SecretKey: config.TencentCOSSecretKey,
Bucket: config.PluginStorageOSSBucket,
},
AzureBlob: &oss.AzureBlob{
ConnectionString: config.AzureBlobStorageConnectionString,
ContainerName: config.AzureBlobStorageContainerName,
},
GoogleCloudStorage: &oss.GoogleCloudStorage{
Bucket: config.PluginStorageOSSBucket,
CredentialsB64: config.GoogleCloudStorageCredentialsB64,
},
AliyunOSS: &oss.AliyunOSS{
Region: config.AliyunOSSRegion,
Endpoint: config.AliyunOSSEndpoint,
AccessKey: config.AliyunOSSAccessKeyID,
SecretKey: config.AliyunOSSAccessKeySecret,
AuthVersion: config.AliyunOSSAuthVersion,
Path: config.AliyunOSSPath,
Bucket: config.PluginStorageOSSBucket,
CloudBoxId: config.AliyunOSSCloudBoxId,
},
HuaweiOBS: &oss.HuaweiOBS{
AccessKey: config.HuaweiOBSAccessKey,
SecretKey: config.HuaweiOBSSecretKey,
Server: config.HuaweiOBSServer,
Bucket: config.PluginStorageOSSBucket,
PathStyle: config.HuaweiOBSPathStyle,
},
VolcengineTOS: &oss.VolcengineTOS{
Region: config.VolcengineTOSRegion,
Endpoint: config.VolcengineTOSEndpoint,
AccessKey: config.VolcengineTOSAccessKey,
SecretKey: config.VolcengineTOSSecretKey,
Bucket: config.PluginStorageOSSBucket,
},
})
if err != nil {
log.Panic("failed to create storage", "error", err)
}
return storage
}
func (app *App) Run(config *app.Config) {
// init routine pool
if config.SentryEnabled {
routine.InitPool(config.RoutinePoolSize, sentry.ClientOptions{
Dsn: config.SentryDSN,
AttachStacktrace: config.SentryAttachStacktrace,
TracesSampleRate: config.SentryTracesSampleRate,
SampleRate: config.SentrySampleRate,
EnableTracing: config.SentryTracingEnabled,
})
} else {
routine.InitPool(config.RoutinePoolSize)
}
// init db
db.Init(config)
// init oss
oss := initOSS(config)
// create manager
app.pluginManager = plugin_manager.InitGlobalManager(oss, config)
// create cluster
app.cluster = cluster.NewCluster(config)
// set cluster to control panel for remote debugging plugin synchronization
app.pluginManager.SetCluster(app.cluster)
// init manager
app.pluginManager.Launch(config)
// init persistence
persistence.InitPersistence(oss, config)
// launch cluster
app.cluster.Launch()
// setup signal handler, for a graceful shutdown to cleanup resources like async tasks
tasks.SetupSignalHandler()
tasks.RegisterFinalizers(tasks.RecycleTasks)
tasks.RegisterFinalizers(cache.ReleaseAllLocks)
tasks.MonitorTimeoutTasks(app.cluster, config)
// start http server
app.server(config)
// block
select {}
}