tutanota/src/common/api/main/EventController.ts
map 5293be6a4a
Implement spam training data sync and add TutanotaModelV98
We sync the spam training data encrypted through our server to make
sure that all clients for a specific user behave the same when
classifying mails. Additionally, this enables the spam classification
in the webApp. We compress the training data vectors
(see clientSpamTrainingDatum) before uploading to our server using
SparseVectorCompressor.ts. When a user has the ClientSpamClassification
enabled, the spam training data sync will happen for every mail
received.

ClientSpamTrainingDatum are not stored in the CacheStorage.
No entityEvents are emitted for this type.
However, we retrieve creations and updates for ClientSpamTrainingData
through the modifiedClientSpamTrainingDataIndex.

We calculate a threshold per classifier based on the dataset ham to spam
ratio, we also subsample our training data to cap the ham to spam ratio
within a certain limit.

Co-authored-by: jomapp <17314077+jomapp@users.noreply.github.com>
Co-authored-by: das <das@tutao.de>
Co-authored-by: abp <abp@tutao.de>
Co-authored-by: Kinan <104761667+kibibytium@users.noreply.github.com>
Co-authored-by: sug <sug@tutao.de>
Co-authored-by: nif <nif@tutao.de>
Co-authored-by: map <mpfau@users.noreply.github.com>
2025-11-18 13:56:19 +01:00

61 lines
2.2 KiB
TypeScript

import { identity } from "@tutao/tutanota-utils"
import type { LoginController } from "./LoginController"
import stream from "mithril/stream"
import Stream from "mithril/stream"
import { assertMainOrNode } from "../common/Env"
import { WebsocketCounterData } from "../entities/sys/TypeRefs"
import { EntityUpdateData } from "../common/utils/EntityUpdateUtils.js"
assertMainOrNode()
export type ExposedEventController = Pick<EventController, "onEntityUpdateReceived" | "onCountersUpdateReceived">
const TAG = "[EventController]"
export type EntityEventsListener = (updates: ReadonlyArray<EntityUpdateData>, eventOwnerGroupId: Id) => Promise<unknown>
export class EventController {
private countersStream: Stream<WebsocketCounterData> = stream()
private entityListeners: Set<EntityEventsListener> = new Set()
constructor(private readonly logins: LoginController) {}
addEntityListener(listener: EntityEventsListener) {
if (this.entityListeners.has(listener)) {
console.warn(TAG, "Adding the same listener twice!")
} else {
this.entityListeners.add(listener)
}
}
removeEntityListener(listener: EntityEventsListener) {
const wasRemoved = this.entityListeners.delete(listener)
if (!wasRemoved) {
console.warn(TAG, "Could not remove listener, possible leak?", listener)
}
}
getCountersStream(): Stream<WebsocketCounterData> {
// Create copy so it's never ended
return this.countersStream.map(identity)
}
async onEntityUpdateReceived(entityUpdates: readonly EntityUpdateData[], eventOwnerGroupId: Id): Promise<void> {
if (this.logins.isUserLoggedIn()) {
// the UserController must be notified first as other event receivers depend on it to be up-to-date
await this.logins.getUserController().entityEventsReceived(entityUpdates, eventOwnerGroupId)
}
for (const listener of this.entityListeners) {
// run listeners async to speed up processing
// we ran it sequentially before to prevent parallel loading of instances
// this should not be a problem anymore as we prefetch now
// noinspection ES6MissingAwait
listener(entityUpdates, eventOwnerGroupId)
}
}
async onCountersUpdateReceived(update: WebsocketCounterData): Promise<void> {
this.countersStream(update)
}
}