refactor: split monolith into 3 microservices (frontend, backend, discord-gateway)

- Extract services into services/{frontend,backend,discord-gateway}
- Create packages/shared/ for shared logger, errors, utils, types
- Setup Modular MVC pattern in backend (controller→service→repository)
- Setup event-driven architecture in discord-gateway with Redis pub/sub
- Move Docker files to infra/docker/ with per-service Dockerfiles
- Update docker-compose.yml to use Traefik-only routing (no port exposes)
- Update GitHub Actions deploy workflow for multi-service matrix build
- Fix all import paths and resolve type errors across all services
- All 3 services pass tsc --noEmit clean

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
MythEclipse
2026-06-01 21:44:29 +07:00
co-authored by Claude Opus 4.8
parent bda8304bb9
commit c48a0c5e3b
193 changed files with 16879 additions and 1158 deletions
@@ -0,0 +1,145 @@
import { config } from "../../shared/config/config.js";
import { initializeDatabase } from "../../shared/database/drizzle.js";
import { buildConversationContext } from "./conversationContext.js";
import { runModerationAnalysis } from "./llmModerationClient.js";
import {
getAttachmentsForMessages,
getConversationContextBefore,
updateMessagesAIAnalysisBulk,
} from "../message-capture/messageStore.js";
import type { MessageRecord } from "../message-capture/types.js";
let dbInitialized = false;
let dbInitPromise: Promise<any> | null = null;
async function ensureDb() {
if (dbInitialized) return;
if (!dbInitPromise) {
dbInitPromise = initializeDatabase().then(() => {
dbInitialized = true;
});
}
await dbInitPromise;
}
export interface AnalysisWorkerRequest {
conversationKey: string;
messages: MessageRecord[];
}
export type AnalysisWorkerResponse =
| {
ok: true;
conversationKey: string;
rows: MessageRecord[];
}
| {
ok: false;
conversationKey: string;
rows: MessageRecord[];
error: string;
};
export default async function processAnalysisRequest({
conversationKey,
messages,
}: AnalysisWorkerRequest): Promise<AnalysisWorkerResponse> {
if (!config.AI_LLM_API_KEY) {
console.error(
JSON.stringify({
level: "FATAL",
context: "aiAnalysisWorker",
error:
"AI_LLM_API_KEY is missing from environment. Force closing worker operation.",
timestamp: new Date().toISOString(),
}),
);
process.exit(1);
}
try {
try {
await ensureDb();
} catch (dbError) {
const msg = dbError instanceof Error ? dbError.message : String(dbError);
return {
ok: false,
conversationKey,
rows: [],
error: `Database init failed: ${msg}`,
};
}
const firstMessage = messages[0];
if (!firstMessage) return { ok: true, conversationKey, rows: [] };
const contextBefore = await getConversationContextBefore({
channelId: firstMessage.channel_id,
threadId: firstMessage.thread_id,
beforeCreatedAt: firstMessage.created_at,
limit: config.AI_ANALYSIS_CONTEXT_MESSAGE_LIMIT,
});
const contextLines = await buildConversationContext({
contextBefore,
targets: messages,
maxTokens: config.AI_ANALYSIS_MAX_CONTEXT_TOKENS,
});
const targetIds = messages.map((m) => m.id);
const contextIds = contextBefore.map((m) => m.id);
const allMessageIds = [...targetIds, ...contextIds];
const attachments = await getAttachmentsForMessages(allMessageIds);
const result = await runModerationAnalysis({
targets: messages,
contextText: contextLines.join("\n"),
attachments,
});
const updates = result.results.map((analysisResult) => ({
messageId: analysisResult.messageId,
result: {
status: analysisResult.status,
flags: JSON.stringify(analysisResult.flags),
score: analysisResult.score,
analysis: analysisResult.analysis,
categories: analysisResult.categories,
severity: analysisResult.severity,
confidence: analysisResult.confidence,
recommendedAction: analysisResult.recommendedAction,
analyzedAt: Date.now(),
error: null,
},
}));
try {
const rows = await updateMessagesAIAnalysisBulk(updates);
return { ok: true, conversationKey, rows };
} catch (dbErr) {
// If bulk update fails, we log it but don't fail the worker completely
// so it can at least retry later without blowing up the circuit breaker if it was an isolated issue
throw new Error(
`Failed to update DB: ${dbErr instanceof Error ? dbErr.message : String(dbErr)}`,
);
}
} catch (error) {
const errorMessage = error instanceof Error ? error.message : String(error);
const errorStack = error instanceof Error ? error.stack : undefined;
const rows: MessageRecord[] = [];
console.error(
JSON.stringify({
level: "ERROR",
context: "aiAnalysisWorker",
conversationKey,
messageCount: messages.length,
error: errorMessage,
stack: errorStack,
timestamp: new Date().toISOString(),
}),
);
return { ok: false, conversationKey, rows, error: errorMessage };
}
}
@@ -0,0 +1,918 @@
import { existsSync } from "node:fs";
import { fileURLToPath } from "node:url";
import type { Client } from "discord.js-selfbot-v13";
import { AbortError } from "p-retry";
import { Piscina } from "piscina";
import { config } from "../../shared/config/config.js";
import { createChildLogger } from "../../shared/logger/logger.js";
import { retryWithBackoff } from "../../shared/utils/retry.js";
import { invalidateAnalyticsCache } from "../message-capture/analyticsStore.js";
import { attemptAutoDeleteFlaggedMessage } from "./autoDeleteManager.js";
import { buildConversationContext } from "./conversationContext.js";
import { runModerationAnalysis } from "./llmModerationClient.js";
import { isAgeRestrictedMetadata } from "../message-capture/messageMetadata.js";
import {
getAttachmentsForMessages,
getConversationContextBefore,
getConversationKeysWithIncompleteAnalysis,
getIncompleteMessagesByConversation,
getMessageById,
getPendingConversationKeys,
getPendingMessagesByConversation,
updateMessageAIAnalysis,
updateMessagesAIAnalysisBulk,
} from "../message-capture/messageStore.js";
import type {
AnalysisQueueStatus,
MessageRecord,
ModerationBroadcaster,
} from "../message-capture/types.js";
const logger = createChildLogger("ai-analyzer");
type ModerationGlobal = typeof globalThis & {
moderationBroadcaster?: ModerationBroadcaster;
};
function getModerationBroadcaster(): ModerationBroadcaster | undefined {
return (globalThis as ModerationGlobal).moderationBroadcaster;
}
function scheduleAutoDelete(row: MessageRecord): void {
if (row.ai_status !== "flagged" && row.ai_status !== "warn") return;
const run = () => {
attemptAutoDeleteFlaggedMessage(moderationClient, row).catch((error: unknown) => {
logger.error(
{
messageId: row.id,
error: error instanceof Error ? error.message : String(error),
},
"Unexpected auto-delete error",
);
});
};
if (config.AUTO_DELETE_FLAGGED_DELAY_MS > 0) {
setTimeout(run, config.AUTO_DELETE_FLAGGED_DELAY_MS);
return;
}
setImmediate(run);
}
function isAgeRestrictedMessage(message: MessageRecord): boolean {
return isAgeRestrictedMetadata(message.metadata);
}
function buildAgeRestrictedSkipResult(): {
status: "clean";
flags: string | null;
score: number;
analysis: string;
categories: string[];
severity: "none";
confidence: number;
recommendedAction: "none";
analyzedAt: number;
error: null;
} {
return {
status: "clean",
flags: JSON.stringify(["age_restricted"]),
score: 0,
analysis: "Skipped moderation for age-restricted content.",
categories: ["age_restricted"],
severity: "none",
confidence: 1,
recommendedAction: "none",
analyzedAt: Date.now(),
error: null,
};
}
async function skipAgeRestrictedMessages(
messages: MessageRecord[],
): Promise<MessageRecord[]> {
const ageRestrictedMessages = messages.filter(isAgeRestrictedMessage);
if (ageRestrictedMessages.length === 0) {
return messages;
}
const skippedRows = await updateMessagesAIAnalysisBulk(
ageRestrictedMessages.map((message) => ({
messageId: message.id,
result: buildAgeRestrictedSkipResult(),
})),
);
for (const row of skippedRows) {
getModerationBroadcaster()?.messageAnalyzed(row);
}
const skippedIds = new Set(
ageRestrictedMessages.map((message) => message.id),
);
return messages.filter((message) => !skippedIds.has(message.id));
}
// ---------------------------------------------------------------------------
// Batch pipeline state
// ---------------------------------------------------------------------------
/** Debounce timer handle per conversation key. */
const conversationDebounceTimers = new Map<string, NodeJS.Timeout>();
/** Timestamp of when processing started per conversation key. */
const conversationProcessing = new Map<string, number>();
/** Cooldown expiry timestamp per conversation key after an error. */
const conversationErrorCooldown = new Map<string, number>();
let activeRequests = 0;
let lastError: string | null = null;
let moderationClient: Client | undefined;
// Batch circuit breaker
let consecutiveErrors = 0;
const MAX_CONSECUTIVE_ERRORS = 5;
let globalCooldownUntil = 0;
// ---------------------------------------------------------------------------
// Individual fallback queue — runs PARALLEL to the batch pipeline.
//
// Design guarantees:
// • Concurrency is capped at config.AI_ANALYSIS_INDIVIDUAL_MAX_CONCURRENT.
// • A flat Set<messageId> de-duplicates so the same message can't be
// in-flight twice (Discord snowflakes are globally unique, but be safe).
// • A Map<conversationKey, count> lets the recovery worker skip conversations
// that already have individual work in progress (#4 fix).
// • A separate circuit breaker prevents a cascade of individual failures
// from hammering a down/rate-limited LLM endpoint (#1+#5 fix).
// ---------------------------------------------------------------------------
/** IDs currently being processed one-by-one. */
const individualInFlight = new Set<string>();
/**
* Per-conversation count of in-flight individual messages.
* Used by the recovery worker to avoid re-scheduling a conversation that
* already has individual fallback work running for it.
*/
const individualInFlightByConversation = new Map<string, number>();
/** Counter for observability. */
let activeIndividualRequests = 0;
// Individual fallback circuit breaker (independent of batch CB)
let individualConsecutiveErrors = 0;
let individualCooldownUntil = 0;
const INDIVIDUAL_COOLDOWN_MS = 30000;
// ---------------------------------------------------------------------------
// Piscina worker pool (batch path only)
// ---------------------------------------------------------------------------
function getAnalysisWorkerUrl(): URL {
const candidates = [
new URL("./aiAnalysisWorker.js", import.meta.url),
new URL("../aiAnalysisWorker.js", import.meta.url),
new URL("./aiAnalysisWorker.ts", import.meta.url),
];
for (const candidate of candidates) {
if (existsSync(fileURLToPath(candidate))) {
return candidate;
}
}
return candidates[2];
}
const workerPool = new Piscina({
filename: fileURLToPath(getAnalysisWorkerUrl()),
execArgv: process.execArgv,
});
interface AnalysisWorkerResponse {
ok: boolean;
conversationKey: string;
rows: MessageRecord[];
error?: string;
}
// ---------------------------------------------------------------------------
// Exported helpers
// ---------------------------------------------------------------------------
/**
* Gets the conversation key for a message (thread_id or channel_id).
*/
export function getConversationKey(message: MessageRecord): string {
return message.thread_id || message.channel_id;
}
/**
* Picks a batch of messages within a token budget.
* `tokensPerMessage` accounts for JSON structure overhead around each entry.
* Uses a rough character-based token estimate (avoids async formatMessageForPrompt
* since this function runs in a synchronous promise chain).
*/
export function pickBatchWithinBudget(
messages: MessageRecord[],
maxTokens: number,
tokensPerMessage: number,
): MessageRecord[] {
const batch: MessageRecord[] = [];
let usedTokens = 0;
for (const msg of messages) {
const content = msg.edited_content ?? msg.content;
// Rough token estimate: ~3 chars per token + metadata overhead
const msgTokens = Math.ceil(content.length / 3) + tokensPerMessage;
if (usedTokens + msgTokens <= maxTokens) {
batch.push(msg);
usedTokens += msgTokens;
}
}
return batch;
}
// ---------------------------------------------------------------------------
// Conversation lock helpers
// ---------------------------------------------------------------------------
function isConversationProcessingLocked(conversationKey: string): boolean {
const startedAt = conversationProcessing.get(conversationKey);
// FIX #7: use configurable timeout that exceeds (LLM timeout × max retries).
// Old hardcoded value was 30 000 ms — shorter than a single LLM call under retries.
return Boolean(
startedAt &&
Date.now() - startedAt < config.AI_ANALYSIS_PROCESSING_TIMEOUT_MS,
);
}
// ---------------------------------------------------------------------------
// Individual fallback pipeline
// ---------------------------------------------------------------------------
/**
* Processes a single message directly in the main process (no IPC/worker
* pool overhead). Never called from the batch path.
*
* FIX #1+#5: Increments the individual circuit breaker on failure so a
* sustained outage stops hammering the LLM endpoint.
*
* Infinite-loop prevention: if the LLM consistently drops the single target
* message across all retries (analysis_incomplete), we write a terminal flag
* 'individual_analysis_exhausted' to DB instead of 'analysis_incomplete'.
* The recovery worker only queries for 'analysis_incomplete', so exhausted
* messages are permanently excluded from the reprocessing loop.
* Transient failures (network/parse/DB) are NOT written as exhausted — they
* stay as 'analysis_incomplete' so the circuit-breaker-throttled recovery
* cycle can retry them later.
*/
async function processIndividualFallback(
message: MessageRecord,
): Promise<void> {
const { id: messageId } = message;
const conversationKey = getConversationKey(message);
activeIndividualRequests++;
// Increment per-conversation counter so the recovery worker can see it.
individualInFlightByConversation.set(
conversationKey,
(individualInFlightByConversation.get(conversationKey) ?? 0) + 1,
);
// Track whether all retries were exhausted specifically because the LLM
// consistently returned no result for this message (vs. a transient error).
let exhaustedOnIncomplete = false;
try {
const contextBefore = await getConversationContextBefore({
channelId: message.channel_id,
threadId: message.thread_id,
beforeCreatedAt: message.created_at,
limit: config.AI_ANALYSIS_CONTEXT_MESSAGE_LIMIT,
});
const contextLines = await buildConversationContext({
contextBefore,
targets: [message],
maxTokens: config.AI_ANALYSIS_MAX_CONTEXT_TOKENS,
});
const contextIds = contextBefore.map((m) => m.id);
const attachments = await getAttachmentsForMessages([
messageId,
...contextIds,
]);
const analysisResult = await retryWithBackoff(
async () => {
try {
const result = await runModerationAnalysis({
targets: [message],
contextText: contextLines.join("\n"),
attachments,
});
// If the LLM still dropped our only target, convert to a retryable
// throw so backoff kicks in. Track this so the catch block can
// distinguish it from a transient network/parse failure.
const stillIncomplete = result.results.some((r) =>
r.flags.includes("analysis_incomplete"),
);
if (stillIncomplete) {
exhaustedOnIncomplete = true;
throw new Error(
`LLM returned no result for single-target message ${messageId} — will retry with backoff`,
);
}
// Got a real result — clear the incomplete flag.
exhaustedOnIncomplete = false;
return result;
} catch (err: any) {
// Propagate AbortError so outer retry is immediately cancelled on 429.
if (err instanceof AbortError) {
throw err;
}
if (
err?.status === 429 ||
err?.status === 401 ||
err?.status === 403
) {
throw new AbortError(err);
}
throw err;
}
},
{
retries: 2,
minTimeout: 2000,
maxTimeout: 15000,
logger,
},
);
const updates = analysisResult.results.map((r) => ({
messageId: r.messageId,
result: {
status: r.status,
flags: JSON.stringify(r.flags),
score: r.score,
analysis: r.analysis,
categories: r.categories,
severity: r.severity,
confidence: r.confidence,
recommendedAction: r.recommendedAction,
analyzedAt: Date.now(),
error: null,
},
}));
const rows = await updateMessagesAIAnalysisBulk(updates);
for (const row of rows) {
getModerationBroadcaster()?.messageAnalyzed(row);
invalidateAnalyticsCache(row.guild_id);
scheduleAutoDelete(row);
}
// Reset individual CB on success.
individualConsecutiveErrors = 0;
logger.info(
{ messageId, status: analysisResult.results[0]?.status },
"Individual fallback analysis complete",
);
} catch (error) {
// FIX #5: individual failures now feed their own circuit breaker.
individualConsecutiveErrors++;
if (
individualConsecutiveErrors >= config.AI_ANALYSIS_INDIVIDUAL_CB_THRESHOLD
) {
individualCooldownUntil = Date.now() + INDIVIDUAL_COOLDOWN_MS;
logger.warn(
{
threshold: config.AI_ANALYSIS_INDIVIDUAL_CB_THRESHOLD,
cooldownUntil: new Date(individualCooldownUntil).toISOString(),
},
"Individual fallback circuit breaker triggered",
);
}
lastError = error instanceof Error ? error.message : String(error);
// Infinite-loop prevention: if all retries were exhausted because the LLM
// consistently dropped this specific message (not a transient error),
// overwrite the DB entry with a terminal flag that the recovery query
// does NOT match. This permanently removes it from the recovery loop
// while keeping it visible as an error in the dashboard.
if (exhaustedOnIncomplete) {
await updateMessagesAIAnalysisBulk([
{
messageId,
result: {
status: "error",
flags: JSON.stringify(["individual_analysis_exhausted"]),
score: 0,
analysis:
"Individual fallback exhausted all retries: LLM consistently dropped this message even in single-target mode",
categories: ["individual_analysis_exhausted"],
severity: "none",
confidence: 0,
recommendedAction: "review",
analyzedAt: Date.now(),
error: lastError,
},
},
]).catch((dbErr: unknown) => {
logger.error(
{ messageId, error: String(dbErr) },
"Failed to write terminal exhausted status — message may re-enter recovery loop",
);
});
logger.warn(
{ messageId },
"Individual fallback exhausted — marked as individual_analysis_exhausted to stop recovery loop",
);
} else {
// Transient failure (network/parse/DB): do NOT write terminal status.
// Message stays as error/analysis_incomplete in DB and will be retried
// by the recovery worker, subject to the individual circuit breaker.
logger.error(
{
messageId,
error: lastError,
stack: error instanceof Error ? error.stack : undefined,
},
"Individual fallback analysis failed (transient) — will be retried by recovery worker",
);
}
} finally {
activeIndividualRequests--;
individualInFlight.delete(messageId);
// Decrement per-conversation counter; remove key when it hits zero.
const prev = individualInFlightByConversation.get(conversationKey) ?? 1;
if (prev <= 1) {
individualInFlightByConversation.delete(conversationKey);
} else {
individualInFlightByConversation.set(conversationKey, prev - 1);
}
}
}
/**
* Fans out message records to the individual fallback queue.
*
* FIX #1: Checks concurrency cap before admitting new work.
* FIX #5: Checks individual circuit breaker before admitting new work.
* Messages that cannot be admitted remain as `error/analysis_incomplete` in
* the DB and will be picked up by the recovery worker on the next interval.
*/
function enqueueIndividualFallbacks(messages: MessageRecord[]): void {
// FIX #5: Honour the individual circuit breaker.
if (Date.now() < individualCooldownUntil) {
logger.warn(
{
until: new Date(individualCooldownUntil).toISOString(),
skipped: messages.length,
},
"Individual fallback circuit breaker active — messages will be recovered later",
);
return;
}
const newMessages = messages.filter((m) => !individualInFlight.has(m.id));
if (newMessages.length === 0) return;
logger.info(
{
count: newMessages.length,
messageIds: newMessages.map((m) => m.id),
},
"Enqueueing individual fallback analysis for batch-incomplete messages",
);
for (const msg of newMessages) {
individualInFlight.add(msg.id);
// Fire-and-forget: processIndividualFallback handles all errors internally.
processIndividualFallback(msg).catch((err: unknown) => {
// Belt-and-suspenders guard — should never reach here.
logger.error(
{ messageId: msg.id, error: String(err) },
"Unexpected uncaught error escaping processIndividualFallback",
);
individualInFlight.delete(msg.id);
const ck = getConversationKey(msg);
const prev = individualInFlightByConversation.get(ck) ?? 1;
if (prev <= 1) {
individualInFlightByConversation.delete(ck);
} else {
individualInFlightByConversation.set(ck, prev - 1);
}
});
}
}
// ---------------------------------------------------------------------------
// Batch pipeline
// ---------------------------------------------------------------------------
async function processBatch(
conversationKey: string,
messages: MessageRecord[],
): Promise<void> {
if (messages.length === 0) return;
if (Date.now() < globalCooldownUntil) {
return;
}
activeRequests++;
let shouldScheduleNext = false;
const processingStartedAt = Date.now();
conversationProcessing.set(conversationKey, processingStartedAt);
try {
const result = (await workerPool.run({
conversationKey,
messages,
})) as AnalysisWorkerResponse;
for (const row of result.rows) {
getModerationBroadcaster()?.messageAnalyzed(row);
scheduleAutoDelete(row);
}
if (!result.ok) {
consecutiveErrors++;
if (consecutiveErrors >= MAX_CONSECUTIVE_ERRORS) {
globalCooldownUntil = Date.now() + 60000;
logger.warn(
"Global circuit breaker triggered due to consecutive errors",
);
}
// Batch failed entirely — fall back all messages to individual queue
// so no message is permanently lost behind a cooldown.
logger.warn(
{
conversationKey,
messageCount: messages.length,
error: result.error,
},
"Batch failed entirely — routing all messages to individual fallback queue",
);
enqueueIndividualFallbacks(messages);
lastError = result.error ?? "Analysis worker failed";
conversationErrorCooldown.set(
conversationKey,
Date.now() + config.AI_ANALYSIS_ERROR_COOLDOWN_MS,
);
logger.error(
{
conversationKey,
error: lastError,
messageCount: messages.length,
messageIds: messages.map((m) => m.id),
cooldownUntil: new Date(
Date.now() + config.AI_ANALYSIS_ERROR_COOLDOWN_MS,
).toISOString(),
timestamp: new Date().toISOString(),
},
"Batch analysis failed, will retry after cooldown",
);
return;
}
// Batch succeeded — but check for messages the LLM silently dropped.
// Rows with flag "analysis_incomplete" were produced by parseModerationResponse
// as synthetic errors; they must be re-processed individually.
const incompleteMessages = messages.filter((msg) => {
const row = result.rows.find((r) => r.id === msg.id);
if (!row) {
// The DB update row is missing entirely — treat as incomplete.
return true;
}
const flags: string[] = (() => {
try {
return JSON.parse(row.ai_moderation_flags ?? "[]") as string[];
} catch {
return [];
}
})();
return row.ai_status === "error" && flags.includes("analysis_incomplete");
});
if (incompleteMessages.length > 0) {
logger.warn(
{
conversationKey,
incompleteCount: incompleteMessages.length,
incompleteIds: incompleteMessages.map((m) => m.id),
totalBatchSize: messages.length,
},
"Batch returned incomplete results — fanning out to individual fallback queue",
);
enqueueIndividualFallbacks(incompleteMessages);
}
consecutiveErrors = 0; // Reset batch circuit breaker
conversationErrorCooldown.delete(conversationKey);
shouldScheduleNext = true;
} catch (error) {
consecutiveErrors++;
if (consecutiveErrors >= MAX_CONSECUTIVE_ERRORS) {
globalCooldownUntil = Date.now() + 60000;
logger.warn("Global circuit breaker triggered due to consecutive errors");
}
// Unhandled exception — route everything to individual fallback.
logger.warn(
{ conversationKey, messageCount: messages.length },
"Batch threw exception — routing all messages to individual fallback queue",
);
enqueueIndividualFallbacks(messages);
lastError = error instanceof Error ? error.message : String(error);
const errorStack = error instanceof Error ? error.stack : undefined;
conversationErrorCooldown.set(
conversationKey,
Date.now() + config.AI_ANALYSIS_ERROR_COOLDOWN_MS,
);
logger.error(
{
conversationKey,
error: lastError,
stack: errorStack,
messageCount: messages.length,
messageIds: messages.map((m) => m.id),
cooldownUntil: new Date(
Date.now() + config.AI_ANALYSIS_ERROR_COOLDOWN_MS,
).toISOString(),
timestamp: new Date().toISOString(),
},
"Analysis worker failed, will retry after cooldown",
);
} finally {
activeRequests--;
if (conversationProcessing.get(conversationKey) === processingStartedAt) {
conversationProcessing.delete(conversationKey);
}
if (shouldScheduleNext) {
setImmediate(() => scheduleConversationAnalysis(conversationKey));
}
}
}
// ---------------------------------------------------------------------------
// Scheduling
// ---------------------------------------------------------------------------
/**
* Schedules a debounced analysis run for a conversation.
*
* FIX #3: The async work inside setTimeout is now wrapped in an explicit
* .catch() so DB errors don't produce unhandled promise rejections.
* FIX #6: Calls pickBatchWithinBudget after fetching messages so token budget
* is respected before handing the batch to the LLM.
*/
function scheduleConversationAnalysis(conversationKey: string): void {
if (isConversationProcessingLocked(conversationKey)) {
return;
}
const convoCooldown = conversationErrorCooldown.get(conversationKey) || 0;
const activeCooldown = Math.max(convoCooldown, globalCooldownUntil);
if (activeCooldown && Date.now() < activeCooldown) {
if (!conversationDebounceTimers.has(conversationKey)) {
const remaining = activeCooldown - Date.now();
const timer = setTimeout(() => {
conversationDebounceTimers.delete(conversationKey);
scheduleConversationAnalysis(conversationKey);
}, remaining + 500);
conversationDebounceTimers.set(conversationKey, timer);
}
return;
}
const existingTimer = conversationDebounceTimers.get(conversationKey);
if (existingTimer) {
clearTimeout(existingTimer);
}
const timer = setTimeout(() => {
conversationDebounceTimers.delete(conversationKey);
// FIX #3: explicit .catch() — no async arrow function to avoid unhandled rejection.
getPendingMessagesByConversation(
conversationKey,
config.AI_ANALYSIS_MAX_BATCH_SIZE,
)
.then(async (messages) => {
if (messages.length === 0) return;
const processableMessages = await skipAgeRestrictedMessages(messages);
if (processableMessages.length === 0) return;
// FIX #6: trim to token budget before sending to LLM.
// 50 tokens overhead accounts for JSON structure + id/username fields.
let trimmed = pickBatchWithinBudget(
processableMessages,
config.AI_ANALYSIS_MAX_TARGET_TOKENS,
50,
);
// FIX #10: if every message individually exceeds the token budget,
// pickBatchWithinBudget returns [] — which would leave them permanently
// stuck as `pending`. Fall back to the first message alone so at
// least one makes progress; the rest will be processed in later ticks.
if (trimmed.length === 0 && processableMessages.length > 0) {
trimmed = processableMessages.slice(0, 1);
logger.warn(
{
conversationKey,
messageId: processableMessages[0]?.id,
tokenBudget: config.AI_ANALYSIS_MAX_TARGET_TOKENS,
},
"All messages exceed token budget — processing first message alone to avoid stuck-pending deadlock",
);
}
return processBatch(conversationKey, trimmed);
})
.catch((err: unknown) => {
logger.error(
{
conversationKey,
error: err instanceof Error ? err.message : String(err),
},
"Failed to fetch or dispatch pending messages for scheduled analysis",
);
});
}, config.AI_ANALYSIS_DEBOUNCE_MS);
conversationDebounceTimers.set(conversationKey, timer);
}
// ---------------------------------------------------------------------------
// Public API
// ---------------------------------------------------------------------------
/**
* Queues a message for analysis (debounced by conversation).
*/
export async function queueMessageAnalysis(messageId: string): Promise<void> {
if (!config.AI_ANALYSIS_ENABLED) return;
try {
const message = await getMessageById(messageId);
if (!message) {
logger.warn({ messageId }, "Message not found for analysis queue");
return;
}
if (isAgeRestrictedMessage(message)) {
const updated = await updateMessageAIAnalysis(
message.id,
buildAgeRestrictedSkipResult(),
);
if (updated) {
getModerationBroadcaster()?.messageAnalyzed(updated);
}
logger.info(
{ messageId },
"Skipped AI analysis for age-restricted message",
);
return;
}
queueConversationAnalysis(getConversationKey(message));
} catch (error) {
logger.error(
{
messageId,
error: error instanceof Error ? error.message : String(error),
},
"Failed to queue message for analysis",
);
}
}
/**
* Queues a conversation for analysis (debounced).
*/
export function queueConversationAnalysis(conversationKey: string): void {
if (!config.AI_ANALYSIS_ENABLED) return;
scheduleConversationAnalysis(conversationKey);
}
/**
* Returns current status of both the batch and individual fallback queues.
*/
export function getAnalysisQueueStatus(): AnalysisQueueStatus {
return {
queuedConversations: conversationDebounceTimers.size,
activeRequests,
activeIndividualRequests,
individualInFlightCount: individualInFlight.size,
individualCircuitBreakerActive: Date.now() < individualCooldownUntil,
lastError,
};
}
/**
* Starts the periodic recovery worker.
*
* FIX #4: Now also recovers messages stuck in `error/analysis_incomplete`
* state (not just `pending`), and skips conversations that already have
* individual fallback work in progress to avoid DB last-write-wins races.
*/
export function startPendingAIAnalysisWorker(client?: Client): void {
moderationClient = client;
if (!config.AI_ANALYSIS_ENABLED) return;
setInterval(() => {
// FIX #3 pattern: no async arrow — chain promises explicitly.
Promise.all([
getPendingConversationKeys(500),
getConversationKeysWithIncompleteAnalysis(200),
])
.then(([pendingKeys, incompleteKeys]) => {
const now = Date.now();
// FIX #9: Prune stale entries from state maps to prevent unbounded
// memory growth from channels/threads that are no longer active.
for (const [key, expiry] of conversationErrorCooldown) {
if (now >= expiry) conversationErrorCooldown.delete(key);
}
for (const [key, startedAt] of conversationProcessing) {
if (now - startedAt >= config.AI_ANALYSIS_PROCESSING_TIMEOUT_MS) {
conversationProcessing.delete(key);
}
}
// FIX #8: Build a set of keys already targeted for individual recovery
// so the batch loop below skips them, preventing a race where batch
// scheduling and individual scheduling collide on the same conversation.
const incompleteKeySet = new Set(incompleteKeys);
// --- Batch recovery for `pending` messages ---
for (const key of pendingKeys) {
if (conversationDebounceTimers.has(key)) continue;
if (isConversationProcessingLocked(key)) continue;
// FIX #4: skip if individual fallback already running for this conversation.
if (individualInFlightByConversation.has(key)) continue;
// FIX #8: skip if this conversation also needs individual recovery
// (batch processing would conflict with in-flight individual work).
if (incompleteKeySet.has(key)) continue;
const cooldownUntil = conversationErrorCooldown.get(key);
if (cooldownUntil && now < cooldownUntil) continue;
scheduleConversationAnalysis(key);
}
// --- Individual recovery for `error/analysis_incomplete` messages ---
// Circuit breaker check: no point iterating if individual CB is active.
if (now >= individualCooldownUntil) {
const promises: Promise<void>[] = [];
for (const key of incompleteKeys) {
// Skip if individual work is already running for this conversation.
if (individualInFlightByConversation.has(key)) continue;
// Skip if batch processing is running (it will fan-out if it finds more incomplete).
if (isConversationProcessingLocked(key)) continue;
promises.push(
getIncompleteMessagesByConversation(key, 500)
.then(async (msgs) => {
const processableMessages =
await skipAgeRestrictedMessages(msgs);
return processableMessages;
})
.then((msgs) => {
if (msgs.length > 0) {
enqueueIndividualFallbacks(msgs);
}
})
.catch((err: unknown) => {
logger.error(
{ key, error: String(err) },
"Failed to fetch incomplete messages for recovery",
);
}),
);
}
// Errors are handled per-key; return the combined promise for observability.
return Promise.all(promises);
}
})
.catch((err: unknown) => {
logger.error(
{ error: err instanceof Error ? err.message : String(err) },
"Pending AI analysis recovery worker failed",
);
});
}, config.AI_ANALYSIS_RECOVERY_INTERVAL_MS);
}
@@ -0,0 +1,355 @@
import type { Client, PermissionString } from "discord.js-selfbot-v13";
import { config } from "../../shared/config/config.js";
import { createChildLogger } from "../../shared/logger/logger.js";
import { createModerationAction } from "../message-capture/messageStore.js";
import type { MessageRecord } from "../message-capture/types.js";
const logger = createChildLogger("auto-delete-manager");
const parseStringList = (value?: string | null): string[] => {
if (!value) return [];
try {
const parsed = JSON.parse(value) as unknown;
return Array.isArray(parsed)
? parsed.filter((item): item is string => typeof item === "string")
: [];
} catch {
return value
.split(",")
.map((item) => item.trim())
.filter(Boolean);
}
};
/** Derive severity from legacy messages that lack structured AI fields. */
function deriveSeverity(msg: MessageRecord): string {
if (msg.ai_severity) return msg.ai_severity;
const score = msg.ai_confidence ?? msg.ai_moderation_score ?? 0;
if (msg.ai_status === "flagged")
return score >= 0.9 ? "critical" : score >= 0.7 ? "high" : "medium";
if (msg.ai_status === "warn") return score >= 0.6 ? "medium" : "low";
return "none";
}
/** Derive recommended action from legacy messages that lack structured AI fields. */
function deriveRecommendedAction(msg: MessageRecord): string {
if (msg.ai_recommended_action) return msg.ai_recommended_action;
const severity = deriveSeverity(msg);
if (
msg.ai_status === "flagged" &&
(severity === "critical" || severity === "high")
)
return "delete";
if (msg.ai_status === "flagged") return "review";
if (msg.ai_status === "warn") return "warn";
return "none";
}
function isAutoDeleteEligible(message: MessageRecord): boolean {
if (message.ai_status !== "flagged" && message.ai_status !== "warn")
return false;
const confidence = message.ai_confidence ?? message.ai_moderation_score ?? 0;
if (confidence < config.AUTO_DELETE_MIN_CONFIDENCE) {
logger.info(
{
messageId: message.id,
confidence,
threshold: config.AUTO_DELETE_MIN_CONFIDENCE,
},
"Auto-delete skipped: confidence below threshold",
);
return false;
}
const severity = deriveSeverity(message);
const allowedSeverities = (config.AUTO_DELETE_ALLOWED_SEVERITIES || "")
.split(",")
.map((s) => s.trim())
.filter(Boolean);
if (allowedSeverities.length > 0 && !allowedSeverities.includes(severity)) {
logger.info(
{ messageId: message.id, severity, allowed: allowedSeverities },
"Auto-delete skipped: severity not in allowed list",
);
return false;
}
const recommendedAction = deriveRecommendedAction(message);
if (recommendedAction !== "delete" && recommendedAction !== "escalate") {
logger.info(
{ messageId: message.id, recommendedAction },
"Auto-delete skipped: recommended action is not delete/escalate",
);
return false;
}
const allowedCategories = parseStringList(
config.AUTO_DELETE_ALLOWED_CATEGORIES,
);
if (allowedCategories.length > 0) {
const messageCategories = parseStringList(
message.ai_categories ?? message.ai_moderation_flags,
);
const hasAllowedCategory = messageCategories.some((cat) =>
allowedCategories.includes(cat),
);
if (!hasAllowedCategory) {
logger.info(
{
messageId: message.id,
categories: messageCategories,
allowed: allowedCategories,
},
"Auto-delete skipped: no allowed categories match",
);
return false;
}
}
const excludedChannels = parseStringList(
config.AUTO_DELETE_EXCLUDED_CHANNEL_IDS,
);
if (excludedChannels.length > 0) {
const channelId = message.thread_id ?? message.channel_id;
if (excludedChannels.includes(channelId)) {
logger.info(
{ messageId: message.id, channelId },
"Auto-delete skipped: channel excluded",
);
return false;
}
}
const excludedUsers = parseStringList(config.AUTO_DELETE_EXCLUDED_USER_IDS);
if (excludedUsers.length > 0 && excludedUsers.includes(message.user_id)) {
logger.info(
{ messageId: message.id, userId: message.user_id },
"Auto-delete skipped: user excluded",
);
return false;
}
return true;
}
async function logAutoDeleteAttempt(
message: MessageRecord,
result: AutoDeleteResult,
): Promise<void> {
try {
await createModerationAction({
message_id: message.id,
user_id: message.user_id,
guild_id: message.guild_id,
action_type: "delete_message",
reason: result.reason,
executed_by: "auto-delete-manager",
status: result.deleted
? "executed"
: result.reason === "dry_run"
? "executed"
: "failed",
error: result.reason === "error" ? result.reason : null,
executed_at:
result.deleted || result.reason === "dry_run" ? Date.now() : null,
});
} catch (error) {
logger.warn(
{
messageId: message.id,
error: error instanceof Error ? error.message : String(error),
},
"Failed to persist auto-delete action log",
);
}
}
export interface AutoDeleteResult {
deleted: boolean;
skipped: boolean;
reason: string;
}
function getErrorCode(error: unknown): number | string | undefined {
if (!error || typeof error !== "object") return undefined;
const maybeCode = (error as { code?: number | string }).code;
const maybeStatus = (error as { status?: number | string }).status;
return maybeCode ?? maybeStatus;
}
function isAlreadyDeletedError(error: unknown): boolean {
const code = getErrorCode(error);
return code === 10008 || code === 404 || code === "10008" || code === "404";
}
function hasChannelMessagesApi(channel: unknown): channel is {
messages: {
fetch: (id: string) => Promise<{ delete: () => Promise<unknown> }>;
};
} {
return Boolean(
channel &&
typeof channel === "object" &&
"messages" in channel &&
(channel as { messages?: unknown }).messages &&
typeof (channel as { messages: { fetch?: unknown } }).messages.fetch ===
"function",
);
}
function hasPermissionApi(channel: unknown): channel is {
permissionsFor: (
member: unknown,
) => { has: (permission: string) => boolean } | null;
} {
return Boolean(
channel &&
typeof channel === "object" &&
"permissionsFor" in channel &&
typeof (channel as { permissionsFor?: unknown }).permissionsFor ===
"function",
);
}
export async function attemptAutoDeleteFlaggedMessage(
client: Client | undefined,
message: MessageRecord,
): Promise<AutoDeleteResult> {
if (!config.AUTO_DELETE_FLAGGED_ENABLED) {
return { deleted: false, skipped: true, reason: "disabled" };
}
if (message.ai_status !== "flagged" && message.ai_status !== "warn") {
const result = {
deleted: false,
skipped: true,
reason: "not_flagged_or_warn",
} as AutoDeleteResult;
await logAutoDeleteAttempt(message, result);
return result;
}
if (!isAutoDeleteEligible(message)) {
const result = {
deleted: false,
skipped: true,
reason: "not_eligible",
} as AutoDeleteResult;
await logAutoDeleteAttempt(message, result);
return result;
}
if (!client?.user?.id) {
logger.warn(
{ messageId: message.id },
"Auto-delete skipped: client user missing",
);
return { deleted: false, skipped: true, reason: "client_user_missing" };
}
try {
const guild = client.guilds.cache.get(message.guild_id);
if (!guild) {
logger.warn(
{ messageId: message.id, guildId: message.guild_id },
"Auto-delete skipped: guild not found",
);
return { deleted: false, skipped: true, reason: "guild_not_found" };
}
const channelId = message.thread_id ?? message.channel_id;
const channel = guild.channels.cache.get(channelId);
if (!channel) {
logger.warn(
{ messageId: message.id, channelId },
"Auto-delete skipped: channel not found",
);
return { deleted: false, skipped: true, reason: "channel_not_found" };
}
if (!hasPermissionApi(channel) || !hasChannelMessagesApi(channel)) {
logger.warn(
{ messageId: message.id, channelId },
"Auto-delete skipped: channel cannot delete messages",
);
return { deleted: false, skipped: true, reason: "unsupported_channel" };
}
const selfMember = await guild.members.fetch(client.user.id);
const permissions = channel.permissionsFor(selfMember);
const canManageMessages =
permissions?.has("MANAGE_MESSAGES" as PermissionString) ?? false;
if (!canManageMessages) {
logger.warn(
{ messageId: message.id, channelId, userId: client.user.id },
"Auto-delete skipped: current user lacks Manage Messages",
);
return {
deleted: false,
skipped: true,
reason: "missing_manage_messages",
};
}
if (config.AUTO_DELETE_FLAGGED_DRY_RUN) {
const result = {
deleted: false,
skipped: true,
reason: "dry_run",
} as AutoDeleteResult;
await logAutoDeleteAttempt(message, result);
logger.info(
{ messageId: message.id, channelId },
"Auto-delete dry-run: would delete flagged message",
);
return result;
}
const discordMessage = await channel.messages.fetch(message.id);
await discordMessage.delete();
const result = {
deleted: true,
skipped: false,
reason: "deleted",
} as AutoDeleteResult;
await logAutoDeleteAttempt(message, result);
logger.info(
{ messageId: message.id, channelId },
"Auto-deleted AI-flagged message",
);
return result;
} catch (error) {
if (isAlreadyDeletedError(error)) {
const result = {
deleted: true,
skipped: false,
reason: "already_deleted",
} as AutoDeleteResult;
await logAutoDeleteAttempt(message, result);
logger.info(
{ messageId: message.id, code: getErrorCode(error) },
"Auto-delete skipped: message already deleted",
);
return result;
}
const result = {
deleted: false,
skipped: true,
reason: "error",
} as AutoDeleteResult;
await logAutoDeleteAttempt(message, result);
logger.error(
{
messageId: message.id,
error: error instanceof Error ? error.message : String(error),
code: getErrorCode(error),
},
"Auto-delete failed",
);
return result;
}
}
@@ -0,0 +1,14 @@
import pLimit from "p-limit";
import { config } from "../../shared/config/config.js";
/**
* Concurrency limiter for LLM API calls.
*
* Prevents rate-limit (429) errors by capping simultaneous requests
* to the configured maximum (default: 5).
*/
const llmSemaphore = pLimit(config.AI_LLM_MAX_CONCURRENT ?? 5);
export async function withLlmConcurrency<T>(fn: () => Promise<T>): Promise<T> {
return llmSemaphore(fn);
}
@@ -0,0 +1,77 @@
import { formatModerationTextEvidenceForPrompt } from "./indonesianTextNormalizer.js";
import { formatMediaEvidenceForPrompt } from "../message-capture/messageMetadata.js";
import type { MessageRecord } from "../message-capture/types.js";
export interface ConversationContextInput {
contextBefore: MessageRecord[];
targets: MessageRecord[];
maxTokens: number;
}
/**
* Formats a timestamp to ISO 8601 string
*/
function formatTimestamp(ms: number): string {
return new Date(ms).toISOString();
}
/**
* Estimates token count for a string (pessimistic approximation for Indonesian slang & JSON overhead)
*/
export function estimateTokens(text: string): number {
return Math.ceil(text.length / 3) + 15;
}
/**
* Formats a single message for context or target display
*/
export async function formatMessageForPrompt(
msg: MessageRecord,
label: "context" | "target",
): Promise<string> {
const content = msg.edited_content ?? msg.content;
const timestamp = formatTimestamp(msg.created_at);
const textEvidence = await formatModerationTextEvidenceForPrompt(content);
const textSuffix = textEvidence ? ` ${textEvidence}` : "";
const mediaEvidence = formatMediaEvidenceForPrompt(msg.metadata);
const mediaSuffix = mediaEvidence ? ` ${mediaEvidence}` : "";
return `[${label}] id=${msg.id} time=${timestamp} user=${msg.username}: ${content}${textSuffix}${mediaSuffix}`;
}
/**
* Builds conversation historical context without including targets.
* Calculates how much token budget targets use, and fills the rest with context.
*/
export async function buildConversationContext(
input: ConversationContextInput,
): Promise<string[]> {
const { contextBefore, targets, maxTokens } = input;
// Calculate tokens used by targets (parallel)
const targetLines = await Promise.all(
targets.map((msg) => formatMessageForPrompt(msg, "target")),
);
let usedTokens = targetLines.reduce(
(sum, line) => sum + estimateTokens(line),
0,
);
const contextLines = await Promise.all(
contextBefore.map((msg) => formatMessageForPrompt(msg, "context")),
);
const selectedContextLines: string[] = [];
// Go backwards through context, taking most recent first
for (let i = contextLines.length - 1; i >= 0; i--) {
const line = contextLines[i];
const lineTokens = estimateTokens(line);
if (usedTokens + lineTokens <= maxTokens) {
// Unshift so oldest context is first in the array
selectedContextLines.unshift(line);
usedTokens += lineTokens;
}
}
return selectedContextLines;
}
@@ -0,0 +1,8 @@
export { startPendingAIAnalysisWorker } from "./aiAnalyzer.js";
export {
normalizeDiscordCustomEmoji,
detectIndonesianBadwords,
buildModerationTextEvidence,
} from "./indonesianTextNormalizer.js";
export { runModerationAnalysis } from "./llmModerationClient.js";
export { buildSystemPrompt } from "./moderationPrompt.js";
@@ -0,0 +1,606 @@
import axios from "axios";
import OpenAI from "openai";
import { config } from "../../shared/config/config.js";
import { createChildLogger } from "../../shared/logger/logger.js";
import { retryWithBackoff } from "../../shared/utils/retry.js";
import { getCachedText, upsertCachedText } from "./textCacheStore.js";
const log = createChildLogger("indonesianTextNormalizer");
const CUSTOM_EMOJI_PATTERN = /<a?:([a-zA-Z0-9_]+):(\d+)>/g;
/** NVIDIA content safety categories that map to offensive/badword content. */
const NVIDIA_BAD_CATEGORIES = new Set([
"hate",
"harassment",
"sexual",
"violence",
"self-harm",
"illicit",
"profanity",
"vulgar",
"insult",
]);
/**
* Map NVIDIA Nemotron category labels to Indonesian badword-style labels.
*/
const CATEGORY_TO_BADWORD_LABEL: Record<string, string> = {
hate: "hate_speech",
harassment: "harassment",
sexual: "sexual_content",
violence: "violence",
"self-harm": "self_harm",
illicit: "illegal_content",
profanity: "vulgar_language",
vulgar: "vulgar_language",
insult: "harassment",
};
const VALID_PRIMARY_AI_FLAGS = new Set([
"spam",
"hate_speech",
"sara",
"hoaks",
"harassment",
"vulgar_language",
"sexual_content",
"sexual_deviation",
"violence",
"self_harm",
"doxxing",
"scam",
"misinformation",
"nsfw_image",
"gore_image",
"illegal_content",
"gambling",
"drugs",
"child_safety",
"financial_scam",
"religious_insult",
"self_promo",
]);
/**
* In-memory cache TTL (10 min) — fastest path for repeated identical texts.
*/
const BADWORD_CACHE_TTL_MS = 10 * 60 * 1000;
/**
* DB cache TTL (24 hours) — survives restarts, stores full-text results
* so context is preserved (e.g. "kaus" is clean, "kau" alone is clean,
* but "awas kau" is harassment).
*/
const DB_CACHE_TTL_MS = 24 * 60 * 60 * 1000;
const NEMOTRON_RATE_LIMIT_COOLDOWN_MS = 60 * 1000;
const PRIMARY_AI_RATE_LIMIT_COOLDOWN_MS = 30_000;
const GROQ_RATE_LIMIT_COOLDOWN_MS = 60 * 1000;
interface BadwordCacheEntry {
value: string[];
expiresAt: number;
}
const badwordCache = new Map<string, BadwordCacheEntry>();
const inFlightBadwordLookups = new Map<string, Promise<string[]>>();
let nemotronUnavailableUntil = 0;
let primaryAiUnavailableUntil = 0;
let groqUnavailableUntil = 0;
let primaryModerationClient: OpenAI | null = null;
export interface ModerationTextEvidence {
raw: string;
normalized: string;
notes: string[];
badwords: string[];
hasBadwords: boolean;
}
// ---------------------------------------------------------------------------
// Sync helpers (unchanged)
// ---------------------------------------------------------------------------
export function normalizeDiscordCustomEmoji(text: string): {
text: string;
emojiNames: string[];
} {
const emojiNames: string[] = [];
const normalized = text.replace(
CUSTOM_EMOJI_PATTERN,
(_match, name: string) => {
emojiNames.push(name);
return `[emoji:${name}]`;
},
);
return { text: normalized, emojiNames };
}
// Local badword detection removed (lines 121-198).
// All detection now goes through the API pipeline (NVIDIA → Primary AI → Groq)
// to eliminate false positives from substring matching and hardcoded whitelists.
function normalizeBadwordCacheKey(text: string): string {
return text.trim().replace(/\s+/g, " ").toLowerCase();
}
function getCachedBadwords(key: string): string[] | null {
const entry = badwordCache.get(key);
if (!entry) return null;
if (entry.expiresAt <= Date.now()) {
badwordCache.delete(key);
return null;
}
return [...entry.value];
}
function setCachedBadwords(key: string, value: string[]): void {
badwordCache.set(key, {
value: [...new Set(value)],
expiresAt: Date.now() + BADWORD_CACHE_TTL_MS,
});
if (badwordCache.size > 500) {
const now = Date.now();
for (const [cacheKey, entry] of badwordCache) {
if (entry.expiresAt <= now) {
badwordCache.delete(cacheKey);
}
}
if (badwordCache.size > 500) {
const oldestKeys = Array.from(badwordCache.entries())
.sort((a, b) => a[1].expiresAt - b[1].expiresAt)
.slice(0, badwordCache.size - 500)
.map(([cacheKey]) => cacheKey);
for (const cacheKey of oldestKeys) {
badwordCache.delete(cacheKey);
}
}
}
}
function getPrimaryModerationClient(): OpenAI | null {
if (!config.AI_LLM_API_KEY) {
return null;
}
if (!primaryModerationClient) {
primaryModerationClient = new OpenAI({
apiKey: config.AI_LLM_API_KEY,
baseURL: config.AI_LLM_BASE_URL,
maxRetries: 0,
timeout: 15000,
});
}
return primaryModerationClient;
}
function normalizePrimaryAiFlag(value: string): string | null {
const lower = value
.trim()
.toLowerCase()
.replace(/[\s-]+/g, "_");
if (!lower) return null;
if (VALID_PRIMARY_AI_FLAGS.has(lower)) {
return lower;
}
return CATEGORY_TO_BADWORD_LABEL[lower] ?? null;
}
function extractFlagsFromPrimaryAiContent(content: string): string[] {
const flags = new Set<string>();
let parsed: unknown;
try {
parsed = JSON.parse(content);
} catch {
parsed = null;
}
const addValue = (value: unknown) => {
if (typeof value !== "string") return;
const normalized = normalizePrimaryAiFlag(value);
if (normalized) flags.add(normalized);
};
if (Array.isArray(parsed)) {
for (const item of parsed) {
addValue(item);
}
} else if (parsed && typeof parsed === "object") {
const candidate = parsed as Record<string, unknown>;
for (const key of ["flags", "categories", "badwords"]) {
const value = candidate[key];
if (Array.isArray(value)) {
for (const item of value) addValue(item);
} else {
addValue(value);
}
}
}
if (flags.size > 0) {
return Array.from(flags);
}
const lowerContent = content.toLowerCase();
for (const flag of VALID_PRIMARY_AI_FLAGS) {
if (lowerContent.includes(flag)) {
flags.add(flag);
}
}
for (const category of Object.keys(CATEGORY_TO_BADWORD_LABEL)) {
if (lowerContent.includes(category)) {
const mapped = CATEGORY_TO_BADWORD_LABEL[category];
if (mapped) flags.add(mapped);
}
}
return Array.from(flags);
}
async function callPrimaryAiModeration(text: string): Promise<string[]> {
const client = getPrimaryModerationClient();
if (!client) {
return [];
}
const completion = await retryWithBackoff(
async () => {
return client.chat.completions.create({
model: config.AI_LLM_MODEL,
messages: [
{
role: "user",
content:
"Deteksi kata kasar / pelanggaran ringan dari teks Indonesia berikut. " +
'Balas hanya JSON object dengan format {"flags":[...]} dan gunakan hanya flag valid ini: ' +
Array.from(VALID_PRIMARY_AI_FLAGS).join(", ") +
". Jika tidak ada pelanggaran, flags harus array kosong. Teks: " +
text,
},
],
temperature: 0.1,
top_p: 0.9,
max_tokens: 200,
stream: false,
response_format: { type: "json_object" },
} as OpenAI.Chat.Completions.ChatCompletionCreateParamsNonStreaming);
},
{
retries: 1,
minTimeout: 500,
maxTimeout: 2000,
factor: 2,
logger: log,
},
);
const content = completion.choices[0]?.message?.content?.trim();
if (!content) {
return [];
}
return extractFlagsFromPrimaryAiContent(content);
}
// ---------------------------------------------------------------------------
// Groq Llama Prompt Guard Moderation API (Fallback)
// ---------------------------------------------------------------------------
/**
* Call Groq Llama Prompt Guard 2-86M model for moderation scoring.
* Returns a probability score as a string (e.g. "0.9988824725151062").
* Scores above ~0.5 indicate moderation violations.
*/
async function callGrokModeration(text: string): Promise<string[]> {
const apiKey = config.GROQ_API_KEY;
if (!apiKey) {
return [];
}
const response = await axios.post(
config.GROQ_MODERATION_BASE_URL,
{
model: config.GROQ_MODERATION_MODEL,
messages: [{ role: "user", content: text }],
},
{
headers: {
Authorization: `Bearer ${apiKey}`,
Accept: "application/json",
"Content-Type": "application/json",
},
timeout: 10_000,
},
);
const scoreStr = response.data?.choices?.[0]?.message?.content?.trim();
if (!scoreStr) {
return [];
}
// Parse the score (Llama Prompt Guard returns a single probability score)
const score = parseFloat(scoreStr);
if (isNaN(score) || score < 0.5) {
return [];
}
// Map score to moderation flags based on severity
const flags: string[] = [];
if (score >= 0.9) {
flags.push("vulgar_language", "harassment");
} else if (score >= 0.7) {
flags.push("vulgar_language");
} else {
flags.push("spam");
}
return flags;
}
// ---------------------------------------------------------------------------
// NVIDIA Nemotron-3 Content Safety API
// ---------------------------------------------------------------------------
/**
* Call NVIDIA Nemotron-3 Content Safety API to detect harmful content.
* Returns categories/flags from the API response.
*/
async function callNemotronContentSafety(text: string): Promise<string[]> {
const apiKey = config.NVIDIA_NEMOTRON_API_KEY;
if (!apiKey) {
return [];
}
const response = await axios.post(
config.NVIDIA_NEMOTRON_BASE_URL,
{
model: config.NVIDIA_NEMOTRON_MODEL,
messages: [{ role: "user", content: text }],
max_tokens: 897,
temperature: 0.2,
top_p: 0.7,
stream: false,
},
{
headers: {
Authorization: `Bearer ${apiKey}`,
Accept: "application/json",
},
timeout: 15_000,
},
);
const data = response.data;
const categories: string[] = [];
// Parse the LLM response for category flags
const content = data?.choices?.[0]?.message?.content ?? "";
if (content) {
const lowerContent = content.toLowerCase();
for (const category of NVIDIA_BAD_CATEGORIES) {
if (lowerContent.includes(category)) {
categories.push(CATEGORY_TO_BADWORD_LABEL[category] ?? category);
}
}
}
// Also check for structured response fields
const choice = data?.choices?.[0];
if (choice?.message?.content) {
try {
const parsed = JSON.parse(choice.message.content);
if (parsed.categories && Array.isArray(parsed.categories)) {
for (const cat of parsed.categories) {
if (NVIDIA_BAD_CATEGORIES.has(cat.name ?? cat)) {
categories.push(CATEGORY_TO_BADWORD_LABEL[cat.name ?? cat] ?? cat);
}
}
}
} catch {
// Not JSON — already handled via text search above
}
}
return Array.from(new Set(categories));
}
// ---------------------------------------------------------------------------
// Three-tier cache pipeline
// ---------------------------------------------------------------------------
/**
* Detect badwords in text using a **two-tier cache + API pipeline**:
*
* 1. **In-memory cache** (BADWORD_CACHE_TTL_MS, 10 min) — fastest path,
* keyed by the full normalized text string.
* 2. **DB cache** (DB_CACHE_TTL_MS, 24 h) — same full-text key, persisted
* across restarts. Uses the FULL normalized text (not per-word) because
* context matters: "kau" alone is clean, but "awas kau" can be a threat.
* 3. **API pipeline** (NVIDIA → Primary AI → Groq)
* only runs when both cache layers miss.
*
* No local hardcoded badword list — all detection goes through AI APIs
* to eliminate false positives from substring matching.
*/
export async function detectIndonesianBadwords(
text: string,
): Promise<string[]> {
const cacheKey = normalizeBadwordCacheKey(text);
// ── Tier 1: In-memory cache (fastest) ──
const cached = getCachedBadwords(cacheKey);
if (cached) {
return cached;
}
// De-duplicate concurrent lookups
const inFlight = inFlightBadwordLookups.get(cacheKey);
if (inFlight) {
return inFlight;
}
const lookupPromise = (async () => {
// ── Tier 2: DB cache (survives restarts, preserves context) ──
const dbEntry = await getCachedText(cacheKey);
if (dbEntry) {
const flags = [...dbEntry.flags];
setCachedBadwords(cacheKey, flags); // populate in-memory too
return flags;
}
// ── Tier 3: API pipeline ──
const hits = new Set<string>();
let sourceUsed: "nvidia" | "primary_ai" | "groq" = "primary_ai";
// 3a. Try NVIDIA API if key is configured and not rate limited.
const apiKey = config.NVIDIA_NEMOTRON_API_KEY;
if (apiKey && Date.now() >= nemotronUnavailableUntil) {
try {
const apiCategories = await callNemotronContentSafety(text);
for (const hit of apiCategories) {
hits.add(hit);
}
if (apiCategories.length > 0) sourceUsed = "nvidia";
} catch (error) {
const status = axios.isAxiosError(error)
? error.response?.status
: null;
if (status === 429) {
nemotronUnavailableUntil =
Date.now() + NEMOTRON_RATE_LIMIT_COOLDOWN_MS;
}
log.warn(
{ error },
"NVIDIA Nemotron API call failed, falling back to primary AI",
);
}
}
// 3b. Try the main AI model next.
if (hits.size === 0 && Date.now() >= primaryAiUnavailableUntil) {
try {
const primaryHits = await callPrimaryAiModeration(text);
for (const hit of primaryHits) {
hits.add(hit);
}
if (primaryHits.length > 0) sourceUsed = "primary_ai";
} catch (error) {
const status = axios.isAxiosError(error)
? error.response?.status
: null;
if (status === 429) {
primaryAiUnavailableUntil =
Date.now() + PRIMARY_AI_RATE_LIMIT_COOLDOWN_MS;
}
log.warn(
{ error },
"Primary AI badword detection failed, falling back to Groq",
);
}
}
// 3c. Try Groq Llama Prompt Guard as final API fallback.
if (hits.size === 0 && Date.now() >= groqUnavailableUntil) {
const groqKey = config.GROQ_API_KEY;
if (groqKey) {
try {
const groqHits = await callGrokModeration(text);
for (const hit of groqHits) {
hits.add(hit);
}
if (groqHits.length > 0) sourceUsed = "groq";
} catch (error) {
const status = axios.isAxiosError(error)
? error.response?.status
: null;
if (status === 429) {
groqUnavailableUntil = Date.now() + GROQ_RATE_LIMIT_COOLDOWN_MS;
}
log.warn({ error }, "Groq Llama Prompt Guard moderation failed");
}
}
}
const finalHits = Array.from(hits);
// Populate all cache tiers so the same text never triggers another API call
// within the TTL window.
setCachedBadwords(cacheKey, finalHits);
await upsertCachedText(
cacheKey,
finalHits,
sourceUsed,
Date.now() + DB_CACHE_TTL_MS,
);
return finalHits;
})();
inFlightBadwordLookups.set(cacheKey, lookupPromise);
try {
return await lookupPromise;
} finally {
inFlightBadwordLookups.delete(cacheKey);
}
}
// ---------------------------------------------------------------------------
// Async evidence builders
// ---------------------------------------------------------------------------
export async function buildModerationTextEvidence(
text: string,
): Promise<ModerationTextEvidence> {
const emojiNormalized = normalizeDiscordCustomEmoji(text);
const badwordHits = await detectIndonesianBadwords(emojiNormalized.text);
const notes: string[] = [];
for (const emojiName of emojiNormalized.emojiNames) {
notes.push(
`emoji:${emojiName}=Discord custom emoji/expression; not text offense by default`,
);
}
if (badwordHits.length > 0) {
notes.push(`Indonesian badword detected: ${badwordHits.join(", ")}`);
} else {
notes.push("no Indonesian badword detected");
}
return {
raw: text,
normalized: emojiNormalized.text,
notes: Array.from(new Set(notes)),
badwords: badwordHits,
hasBadwords: badwordHits.length > 0,
};
}
export async function formatModerationTextEvidenceForPrompt(
text: string,
): Promise<string> {
const evidence = await buildModerationTextEvidence(text);
if (evidence.normalized === evidence.raw && evidence.notes.length === 0) {
return "";
}
return [
`[normalized_text: ${evidence.normalized}]`,
evidence.notes.length > 0
? `[normalization_notes: ${evidence.notes.join("; ")}]`
: null,
]
.filter(Boolean)
.join(" ");
}
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,161 @@
/**
* Modular system prompt builder for LLM moderation.
*
* Split into composable sections:
* - buildSystemRules() — culture/slang/flag definitions (static)
* - buildMediaInstructions() — media/sticker analysis guidance (conditional)
* - buildFewShotExamples() — 3 example outputs (static)
* - buildSystemPrompt() — assembles all sections with XML delimiters
*
* XML delimiters prevent prompt injection by clearly separating
* system instructions from user-supplied data.
*/
// ---------------------------------------------------------------------------
// Section: System Rules (static — culture, slang, flag definitions)
// ---------------------------------------------------------------------------
const SYSTEM_RULES = `Kamu adalah asisten moderasi konten untuk server Discord berbahasa Indonesia.
Bahasa utama komunitas ini adalah BAHASA INDONESIA. Bahasa Inggris adalah bahasa sekunder.
## Aturan Umum
- Bahasa gaul/slang Indonesia: "anjay", "wkwk", "gws", "gaskeun", "santuy", "njir", "baka", "woy", "woi", "hadeh", dll adalah AMAN.
- Singkatan umum: "gw", "lo", "emg", "kyk", "tdk", "krn", "jgn", dll adalah AMAN.
- Makian/kata kasar umum (seperti "anjing", "asu", "bangsat") BUKAN pelanggaran SARA. SARA khusus untuk diskriminasi/hinaan terhadap Suku, Agama, Ras, dan Antargolongan. NAMUN makian/kata kasar TETAP bisa di-flag sebagai "harassment" atau "vulgar_language" HANYA jika: (1) ditujukan langsung ke orang lain sebagai serangan/hinaan, (2) dalam tone agresif/mengancam, atau (3) bagian dari pola harassment berkelanjutan.
- Kata "asus" adalah merk teknologi, jangan pernah dianggap sebagai makian "asu".
- "woy"/"woi" adalah sapaan/interjeksi informal Indonesia dan tidak boleh dianggap SARA, hate speech, atau harassment tanpa target hinaan/ancaman jelas.
- Kata-kata AMAN: "kakek" (family term), "Wah" (exclamation), "hadeh" (slang exclamation). Jangan flag sebagai vulgar_language atau harassment.
- Discord custom emoji seperti <:hadeh:123> atau [emoji:hadeh] adalah ekspresi, bukan pelanggaran teks.
- Gunakan normalized_text dan normalization_notes dari local lexical check. Jika notes hanya berisi slang/emoji aman, jangan flag. Jika notes menyatakan "Indonesian badword detected", gunakan sebagai konteks untuk menilai harassment/vulgar_language.
## Kategori Pelanggaran & Kriteria Flag
Prioritas tertinggi (ANCAMAN KESELAMATAN):
- child_safety, self_harm, violence, illegal_content — flag jika ada indikasi nyata
- Pornografi/NSFW, ajakan seksual, roleplay seksual → "sexual_content"
- Judi/promosi judi → "gambling"
- Narkoba/promosi → "drugs"
Prioritas menengah (PERILAKU MERUSAK):
- Ancaman kekerasan, doxxing, scam → flag sesuai kategori
- spam self-promo → "spam"
- Istilah agama/suku/ras: penyebutan netral/edukasi = clean; hinaan/provokasi/diskriminatif = "sara" atau "hate_speech"
Prioritas rendah (PELANGGARAN RINGAN):
- harassment (targeted insult), vulgar_language (profanity terarah)
- sexual_deviation: jika pesan mempromosikan/mendukung topik seksual/identitas yang dibatasi server sebagai pembahasan utama
## Pohon Keputusan (Decision Tree)
1. Apakah ada ancaman keselamatan nyata (child_safety, self_harm, violence)? → flagged, critical
2. Apakah ada konten ilegal/explicit (NSFW, drugs, gambling, scam)? → flagged, high
3. Apakah ada harassment terarah/hate speech/sara? → flagged, medium-high
4. Apakah ada spam/promosi borderline? → warn, low-medium
5. Jika tidak ada pelanggaran jelas atau bukti ambigu → clean
Jangan pernah flag hanya berdasarkan kecurigaan atau ketidakjelasan konteks.`;
// ---------------------------------------------------------------------------
// Section: Media Instructions (conditional — injected when media present)
// ---------------------------------------------------------------------------
const MEDIA_INSTRUCTIONS = `## Instruksi Analisis Media
Gambar, sticker, embed image, preview link, dan attachment sudah dianalisis lewat request media terpisah sebelum batch utama.
Gunakan baris "Media analysis" sebagai evidence visual utama dalam keputusan moderasi batch ini.
## Panduan Khusus Sticker
- Sticker Discord adalah media kartun/meme/ilustrasi, BUKAN foto atau video nyata.
- Sticker sering bersifat humor, satir, atau ekspresi emosi yang dilebih-lebihkan.
- Gambar sticker bisa menampilkan adegan kartun yang terlihat "keras" — itu SENI KARTUN, bukan dokumentasi kekerasan nyata.
- Nama sticker yang terdengar provokatif (mis. "Singa injek pejabat") adalah konteks satir/humor. JANGAN flag berdasarkan nama sticker saja.
- Terapkan standar yang lebih longgar untuk konten kartun/meme dibanding foto/video nyata.
- Sticker yang berhasil diunduh WAJIB diperlakukan sebagai image evidence, bukan sekadar nama sticker.`;
// ---------------------------------------------------------------------------
// Section: Few-Shot Examples
// ---------------------------------------------------------------------------
const FEW_SHOT_EXAMPLES = `## Contoh Output yang Benak
Contoh 1 — Pesan bersih dengan slang:
Input: [target] id=12345 user=budi: anjay wkwk gaskeun santuy bro
Output: {"results":[{"message_id":"12345","status":"clean","flags":[],"score":0.0,"categories":[],"severity":"none","confidence":0.95,"recommended_action":"none","policy_version":"default-2026-05-30","evidence":[],"analysis":"Slang Indonesia umum tanpa pelanggaran terdeteksi."}]}
Contoh 2 — Harassment terarah:
Input: [target] id=67890 user=anon: lu goblok banget sih kontol, mampus aja lo
Output: {"results":[{"message_id":"67890","status":"flagged","flags":["harassment","vulgar_language"],"score":0.85,"categories":["harassment","vulgar_language"],"severity":"high","confidence":0.9,"recommended_action":"delete","policy_version":"default-2026-05-30","evidence":["lu goblok banget sih kontol","mampus aja lo"],"analysis":"Insult langsung dengan kata kasar terarah ke individu."}]}
Contoh 3 — Sticker kartun dengan nama provokatif:
Input: [target] id=11111 user=citra: <:singa_injek:123456> [sticker: "Singa injek pejabat"]
Output: {"results":[{"message_id":"11111","status":"clean","flags":[],"score":0.1,"categories":[],"severity":"none","confidence":0.8,"recommended_action":"none","policy_version":"default-2026-05-30","evidence":[],"analysis":"Sticker kartun satir dengan nama provokatif namun bukan ancaman nyata."}]}`;
// ---------------------------------------------------------------------------
// Section: Output Schema + XML Delimiter Instructions
// ---------------------------------------------------------------------------
const OUTPUT_INSTRUCTIONS = `## Format Output
Balas HANYA dengan satu objek JSON valid. Tanpa markdown, tanpa prose, tanpa komentar, tanpa XML.
Struktur wajib:
{
"results": [
{
"message_id": "<ID string PERSIS seperti di input>",
"status": "clean" | "warn" | "flagged",
"flags": ["<string array, kosong jika clean>"],
"score": 0.0,
"categories": ["<kategori kebijakan, kosong jika clean>"],
"severity": "none" | "low" | "medium" | "high" | "critical",
"confidence": 0.0,
"recommended_action": "none" | "monitor" | "warn" | "review" | "delete" | "escalate",
"policy_version": "default-2026-05-30",
"evidence": ["<kutipan/evidence singkat>"],
"analysis": "<penjelasan singkat dalam Bahasa Indonesia, maks 2 kalimat>"
}
]
}
Kriteria status:
- "clean": tidak ada pelanggaran terdeteksi, atau kasus ambigu setelah semua evidence dianalisis
- "warn": risiko ringan konkret terdeteksi (spam borderline, harassment ringan)
- "flagged": pelanggaran jelas terdeteksi
Larangan output analysis:
- Jangan tulis "kurang konteks", "perlu dicek admin", "perlu moderator periksa", "tidak bisa menentukan", atau frasa deferral sejenis.
- Jika evidence tidak cukup kuat untuk pelanggaran, status harus "clean" dan analysis menjelaskan alasan langsung.
- Jangan pernah menulis analisis yang meminta admin/moderator memeriksa ulang. Berikan kesimpulan langsung.
Flag yang valid: spam, hate_speech, sara, hoaks, harassment, vulgar_language, sexual_content, sexual_deviation, violence, self_harm, doxxing, scam, misinformation, nsfw_image, gore_image, illegal_content, gambling, drugs, child_safety, financial_scam, religious_insult, self_promo
CRITICAL: "message_id" HARUS berupa STRING (dibungkus tanda kutip ganda). Jangan perlakukan ID sebagai angka.`;
// ---------------------------------------------------------------------------
// Composer: assembles all sections with XML delimiters
// ---------------------------------------------------------------------------
export interface BuildSystemPromptOptions {
contextText: string;
includeMediaInstructions: boolean;
correction?: { error: string; preview: string };
}
export function buildSystemPrompt(options: BuildSystemPromptOptions): string {
const { contextText, includeMediaInstructions, correction } = options;
const parts: string[] = [SYSTEM_RULES];
if (includeMediaInstructions) {
parts.push(MEDIA_INSTRUCTIONS);
}
parts.push(FEW_SHOT_EXAMPLES);
parts.push(OUTPUT_INSTRUCTIONS);
// XML-delimited context — prevents prompt injection
const delimitedContext = `<conversation_context>\n${contextText}\n</conversation_context>`;
parts.push(delimitedContext);
let base = parts.join("\n\n");
if (correction) {
base += `\n\nRESPON SEBELUMNYA GAGAL VALIDASI.\nError: ${correction.error}\nPreview respons tidak valid:\n${correction.preview}\n\nCoba lagi dengan output JSON yang benar sesuai skema di atas.`;
}
return base;
}
@@ -0,0 +1,209 @@
import { mkdir, readFile, unlink, writeFile } from "node:fs/promises";
import { join } from "node:path";
import { createChildLogger } from "../../shared/logger/logger.js";
const logger = createChildLogger("sticker-cache");
export interface StickerCacheEntry {
base64: string;
mimeType: string;
fetchedAt: number;
size: number;
}
interface CacheIndexEntry {
file: string;
mimeType: string;
size: number;
fetchedAt: number;
}
interface CacheIndex {
entries: Record<string, CacheIndexEntry>;
totalSizeBytes: number;
}
export interface StickerCacheOptions {
cacheDir: string;
maxSizeBytes: number;
ttlMs?: number;
}
let cacheDir = "";
let maxSizeBytes = 0;
let ttlMs = 7 * 24 * 60 * 60 * 1000; // 7 days default
let index: CacheIndex = { entries: {}, totalSizeBytes: 0 };
let ready = false;
function sanitizeKey(name: string): string {
return encodeURIComponent(name).replace(/%/g, "_");
}
async function loadIndex(): Promise<CacheIndex> {
try {
const raw = await readFile(join(cacheDir, "index.json"), "utf-8");
return JSON.parse(raw) as CacheIndex;
} catch {
return { entries: {}, totalSizeBytes: 0 };
}
}
async function saveIndex(idx: CacheIndex): Promise<void> {
await writeFile(
join(cacheDir, "index.json"),
JSON.stringify(idx, null, 2),
"utf-8",
);
}
/**
* Initialise the sticker cache: create directory, load index.
* Idempotent — safe to call multiple times.
*/
export async function initStickerCache(
opts: StickerCacheOptions,
): Promise<void> {
if (ready) return;
cacheDir = opts.cacheDir;
maxSizeBytes = opts.maxSizeBytes;
ttlMs = opts.ttlMs ?? 7 * 24 * 60 * 60 * 1000;
await mkdir(cacheDir, { recursive: true });
index = await loadIndex();
// Prune expired entries on startup
const now = Date.now();
let changed = false;
for (const [key, meta] of Object.entries(index.entries)) {
if (now - meta.fetchedAt > ttlMs) {
await unlink(join(cacheDir, meta.file)).catch(() => {});
index.totalSizeBytes -= meta.size;
delete index.entries[key];
changed = true;
}
}
if (changed) await saveIndex(index);
ready = true;
logger.info(
{
entryCount: Object.keys(index.entries).length,
totalSizeBytes: index.totalSizeBytes,
},
"Sticker cache initialized",
);
}
/**
* Look up a sticker image by name. Returns null on miss or TTL expiry.
*/
export async function getStickerFromCache(
stickerName: string,
): Promise<StickerCacheEntry | null> {
if (!ready) return null;
const key = sanitizeKey(stickerName);
const meta = index.entries[key];
if (!meta) return null;
// TTL check
if (Date.now() - meta.fetchedAt > ttlMs) {
await unlink(join(cacheDir, meta.file)).catch(() => {});
index.totalSizeBytes -= meta.size;
delete index.entries[key];
await saveIndex(index);
return null;
}
try {
const raw = await readFile(join(cacheDir, meta.file), "utf-8");
return {
base64: raw,
mimeType: meta.mimeType,
fetchedAt: meta.fetchedAt,
size: meta.size,
};
} catch {
// File missing — clean up index entry
delete index.entries[key];
await saveIndex(index);
return null;
}
}
/**
* Store a sticker image in the cache. Fires and forgets — never blocks.
*/
export async function setStickerInCache(
stickerName: string,
base64: string,
mimeType: string,
): Promise<void> {
if (!ready) return;
const key = sanitizeKey(stickerName);
const fileName = `${key}.dat`;
const size = Buffer.byteLength(base64, "utf-8");
// Evict if needed
await evictIfNeeded(size);
try {
await writeFile(join(cacheDir, fileName), base64, "utf-8");
index.entries[key] = {
file: fileName,
mimeType,
size,
fetchedAt: Date.now(),
};
index.totalSizeBytes += size;
await saveIndex(index);
logger.debug({ stickerName, size }, "Sticker cached");
} catch (err) {
logger.warn(
{ stickerName, error: err instanceof Error ? err.message : String(err) },
"Failed to write sticker to cache",
);
}
}
async function evictIfNeeded(newSize: number): Promise<void> {
while (index.totalSizeBytes + newSize > maxSizeBytes) {
// Find oldest entry
let oldestKey: string | null = null;
let oldestTime = Infinity;
for (const [key, meta] of Object.entries(index.entries)) {
if (meta.fetchedAt < oldestTime) {
oldestTime = meta.fetchedAt;
oldestKey = key;
}
}
if (!oldestKey) break;
const meta = index.entries[oldestKey];
await unlink(join(cacheDir, meta.file)).catch(() => {});
index.totalSizeBytes -= meta.size;
delete index.entries[oldestKey];
}
await saveIndex(index);
}
/**
* Return current cache stats for observability.
*/
export function getStickerCacheStats(): {
entryCount: number;
totalSizeBytes: number;
} {
return {
entryCount: Object.keys(index.entries).length,
totalSizeBytes: index.totalSizeBytes,
};
}
/**
* Check if cache has been initialized.
*/
export function isStickerCacheReady(): boolean {
return ready;
}
@@ -0,0 +1,96 @@
/**
* Sticker-specific prompt templates for AI moderation.
*
* Discord stickers are cartoon/meme artwork — not real photos.
* These prompts give the LLM proper context to avoid false-positive flags
* based solely on sticker names or cartoon imagery.
*/
/**
* Prompt used when a sticker image was successfully downloaded (from cache
* or network) and is being sent to the vision LLM as a base64 image.
*
* Explains that stickers are cartoon art, not documentation of real events,
* and instructs the model to apply looser standards for cartoon content.
*/
export function buildStickerVisionPrompt(
stickerName: string,
messageId: string,
): string {
return [
`Analisis sticker Discord berikut sebagai evidence moderasi.`,
`Sticker "${stickerName}" berasal dari pesan id=${messageId}.`,
``,
`PENTING — Konteks Sticker:`,
`- Sticker Discord adalah gambar KARTUN/MEME/ILUSTRASI, BUKAN foto atau video nyata.`,
`- Sticker sering bersifat humor, satir, atau ekspresi emosi yang dilebih-lebihkan.`,
`- Gambar di sticker bisa menampilkan adegan yang terlihat "keras" (tokoh kartun menginjak sesuatu, ledakan komik, senjata kartun, tokoh berantem) — itu SENI KARTUN, bukan dokumentasi kekerasan atau ancaman nyata.`,
`- Teks di sticker sering berupa lelucon, sindiran, atau ekspresi khas komunitas — bukan ancaman literal.`,
``,
`Jelaskan isi visual, teks yang terlihat, dan konteks risiko.`,
`Terapkan standar yang lebih longgar untuk konten kartun/meme:`,
`- Adegan kartun yang terlihat "keras" ≠ kekerasan nyata → jangan flag "violence" kecuali jelas menargetkan individu/kelompok nyata dengan ancaman serius.`,
`- Nama sticker yang terdengar provokatif (mis. "Singa injek pejabat") adalah konteks satir/kartun, bukan bukti pelanggaran.`,
`- Humor/satir/politik kartun ≠ SARA atau hate speech.`,
`- Sticker yang menampilkan tokoh kartun dalam pose agresif adalah ekspresi/emosi umum di Discord, bukan harassment.`,
``,
`Jawab Bahasa Indonesia, maksimal 3 kalimat. Jangan bilang kurang konteks atau perlu admin cek.`,
].join("\n");
}
/**
* Wrapper for text-only evidence when a sticker image failed to download.
*
* Returns a formatted string that explicitly tells the LLM not to flag
* based on the sticker name alone, since names can sound provocative
* while the actual cartoon image is harmless.
*/
export function buildStickerTextOnlyWarning(
stickerName: string,
stickerUrl: string,
): string {
return (
`[sticker: "${stickerName}" (${stickerUrl}) — GAMBAR GAGAL DIUNDUH. ` +
`"${stickerName}" adalah sticker kartun/meme Discord. ` +
`JANGAN flag berdasarkan nama sticker saja tanpa gambar visual. ` +
`Sticker Discord adalah seni kartun/ekspresi humor, bukan foto nyata. ` +
`Nama yang terdengar provokatif adalah hal umum untuk sticker satir/humor di Discord.]`
);
}
/**
* Prompt used when a custom emoji image was successfully downloaded
* and is being sent to the vision LLM as a base64 image.
*
* Custom emojis are small icons — context is similar to stickers.
*/
export function buildCustomEmojiVisionPrompt(
emojiName: string,
messageId: string,
): string {
return [
`Analisis custom emoji Discord berikut sebagai evidence moderasi.`,
`Emoji "${emojiName}" berasal dari pesan id=${messageId}.`,
``,
`PENTING — Konteks Custom Emoji:`,
`- Custom emoji Discord adalah ikon kecil/ekspresi, BUKAN foto atau dokumen nyata.`,
`- Emoji sering digunakan untuk ekspresi emosi, reaksi, atau lelucon.`,
`- Jangan flag berdasarkan nama emoji saja — analisis isi visual gambar.`,
`- Emoji yang terlihat lucu/aneh adalah hal umum di Discord, bukan pelanggaran.`,
``,
`Jelaskan isi visual dan konteks risiko.`,
`Jawab Bahasa Indonesia, maksimal 2 kalimat. Jangan bilang kurang konteks.`,
].join("\n");
}
/**
* Fallback text for when a custom emoji image failed to download.
*/
export function buildCustomEmojiTextOnlyFallback(emojiName: string): string {
return (
`[custom_emoji: "${emojiName}" — GAMBAR GAGAL DIUNDUH. ` +
`"${emojiName}" adalah custom emoji Discord (ikon kecil). ` +
`JANGAN flag berdasarkan nama emoji saja tanpa gambar visual. ` +
`Custom emoji di Discord adalah ekspresi/emosi umum, bukan konten ofensif.]`
);
}
@@ -0,0 +1,241 @@
import { createHash } from "node:crypto";
import { executeAll, executeGet } from "../../shared/database/drizzle.js";
import { createChildLogger } from "../../shared/logger/logger.js";
const logger = createChildLogger("text-cache-store");
export interface TextCacheEntry {
text: string;
flags: string[];
source: "local" | "nvidia" | "primary_ai" | "groq" | "vision_llm";
analyzed_at: number;
expires_at: number;
hit_count: number;
}
/**
* Lookup cached analysis result for a normalized text string.
* Returns null if not found or expired.
*/
export async function getCachedText(
text: string,
): Promise<TextCacheEntry | null> {
try {
const row = await executeGet(
`SELECT text, flags, source, analyzed_at, expires_at, hit_count
FROM text_analysis_cache
WHERE text = $1 AND expires_at > $2`,
[text, Date.now()],
);
if (!row) return null;
return {
text: row.text,
flags: JSON.parse(row.flags),
source: row.source,
analyzed_at: row.analyzed_at,
expires_at: row.expires_at,
hit_count: row.hit_count,
};
} catch (error) {
logger.error(
{ error: error instanceof Error ? error.message : String(error) },
"Failed to get cached text",
);
return null;
}
}
/**
* Insert or update a text analysis cache entry.
*/
export async function upsertCachedText(
text: string,
flags: string[],
source: "local" | "nvidia" | "primary_ai" | "groq" | "vision_llm",
expiresAt: number,
): Promise<void> {
const now = Date.now();
try {
await executeAll(
`INSERT INTO text_analysis_cache (text, flags, source, analyzed_at, expires_at, hit_count)
VALUES ($1, $2, $3, $4, $5, 0)
ON CONFLICT (text) DO UPDATE SET
flags = EXCLUDED.flags,
source = EXCLUDED.source,
analyzed_at = EXCLUDED.analyzed_at,
expires_at = EXCLUDED.expires_at`,
[text, JSON.stringify(flags), source, now, expiresAt],
);
} catch (error) {
logger.error(
{ error: error instanceof Error ? error.message : String(error) },
"Failed to upsert cached text",
);
}
}
/**
* Increment hit count for a cached text entry (called on cache hit).
*/
export async function incrementTextCacheHit(text: string): Promise<void> {
try {
await executeAll(
`UPDATE text_analysis_cache SET hit_count = hit_count + 1 WHERE text = $1`,
[text],
);
} catch (error) {
// Silent fail — this is just a counter, not critical
}
}
/**
* Delete expired cache entries. Run periodically to keep the table clean.
*/
export async function pruneExpiredTexts(): Promise<number> {
try {
const result = await executeAll(
`DELETE FROM text_analysis_cache WHERE expires_at < $1`,
[Date.now()],
);
return (result as any).rowCount ?? 0;
} catch (error) {
logger.error(
{ error: error instanceof Error ? error.message : String(error) },
"Failed to prune expired texts",
);
return 0;
}
}
/**
* Get cache statistics for observability.
*/
export async function getTextCacheStats(): Promise<{
total: number;
expired: number;
bySource: Record<string, number>;
}> {
try {
const now = Date.now();
const [totalRow, expiredRow, sourceRows] = await Promise.all([
executeAll(`SELECT count(*) as cnt FROM text_analysis_cache`),
executeAll(
`SELECT count(*) as cnt FROM text_analysis_cache WHERE expires_at < $1`,
[now],
),
executeAll(
`SELECT source, count(*) as cnt FROM text_analysis_cache GROUP BY source`,
),
]);
const bySource: Record<string, number> = {};
for (const row of sourceRows) {
bySource[row.source] = row.cnt;
}
return {
total: totalRow[0]?.cnt ?? 0,
expired: expiredRow[0]?.cnt ?? 0,
bySource,
};
} catch (error) {
logger.error(
{ error: error instanceof Error ? error.message : String(error) },
"Failed to get text cache stats",
);
return { total: 0, expired: 0, bySource: {} };
}
}
// ---------------------------------------------------------------------------
// Media / Vision analysis cache helpers (reuses text_analysis_cache table)
// ---------------------------------------------------------------------------
/**
* Generate a deterministic cache key for a sticker.
* Same sticker name → same key across sessions and servers.
*/
export function makeStickerCacheKey(stickerName: string): string {
return `sticker:${stickerName}`;
}
/**
* Generate a deterministic cache key for a custom emoji by its Discord ID.
*/
export function makeCustomEmojiCacheKey(emojiId: string): string {
return `emoji:${emojiId}`;
}
/**
* Generate a deterministic cache key for an image data URL.
* Hashes the first 128 chars of the data URL (enough to identify the image
* without storing the full base64 string as the key).
*/
export function makeImageCacheKey(dataUrl: string): string {
const prefix = dataUrl.slice(0, 128);
const hash = createHash("sha256").update(prefix).digest("hex").slice(0, 16);
return `image:${hash}`;
}
/**
* Lookup a cached media analysis result.
* Returns the full cached text (the analysis summary string) or null.
*/
export async function getCachedMediaAnalysis(
cacheKey: string,
): Promise<string | null> {
try {
const row = await executeGet(
`SELECT flags, hit_count
FROM text_analysis_cache
WHERE text = $1 AND expires_at > $2`,
[cacheKey, Date.now()],
);
if (!row) return null;
// flags stores the analysis result for media entries
const result = JSON.parse(row.flags) as string;
return result || null;
} catch (error) {
logger.error(
{ error: error instanceof Error ? error.message : String(error) },
"Failed to get cached media analysis",
);
return null;
}
}
/**
* Store a media analysis result in the cache.
*/
export async function upsertCachedMediaAnalysis(
cacheKey: string,
analysisResult: string,
source: "vision_llm",
expiresAt: number,
): Promise<void> {
const now = Date.now();
try {
await executeAll(
`INSERT INTO text_analysis_cache (text, flags, source, analyzed_at, expires_at, hit_count)
VALUES ($1, $2, $3, $4, $5, 0)
ON CONFLICT (text) DO UPDATE SET
flags = EXCLUDED.flags,
source = EXCLUDED.source,
analyzed_at = EXCLUDED.analyzed_at,
expires_at = EXCLUDED.expires_at`,
[cacheKey, JSON.stringify(analysisResult), source, now, expiresAt],
);
} catch (error) {
logger.error(
{ error: error instanceof Error ? error.message : String(error) },
"Failed to upsert cached media analysis",
);
}
}
@@ -0,0 +1,209 @@
import { resolve } from "node:dns/promises";
import { isIP } from "node:net";
import { createChildLogger } from "../../shared/logger/logger.js";
const log = createChildLogger("urlFetcher");
export interface FetchedUrlContext {
url: string;
type: "image" | "text" | "error";
data?: Buffer;
mimeType?: string;
textContent?: string;
error?: string;
}
const MAX_FETCH_SIZE = 5 * 1024 * 1024; // 5 MB
const FETCH_TIMEOUT_MS = 8000;
const URL_REGEX = /https?:\/\/[^\s<]+[^<.,:;"')\]\s]/gi;
/**
* Basic SSRF protection.
* Note: A sophisticated attacker could still use DNS rebinding.
*/
async function isSafeUrl(urlStr: string): Promise<boolean> {
try {
const parsed = new URL(urlStr);
const host = parsed.hostname;
// Block obvious local IPs/hostnames
if (
host === "localhost" ||
host === "127.0.0.1" ||
host === "::1" ||
host.startsWith("192.168.") ||
host.startsWith("10.") ||
/^172\.(1[6-9]|2[0-9]|3[0-1])\./.test(host)
) {
return false;
}
// Try resolving to check if it resolves to a local IP
if (!isIP(host)) {
try {
const addresses = await resolve(host);
for (const ip of addresses) {
if (
ip === "127.0.0.1" ||
ip.startsWith("192.168.") ||
ip.startsWith("10.") ||
/^172\.(1[6-9]|2[0-9]|3[0-1])\./.test(ip)
) {
return false;
}
}
} catch (err) {
// If DNS fails, we can't fetch it anyway
return false;
}
}
return true;
} catch (err) {
return false;
}
}
function extractOgImage(html: string): string | null {
// Look for <meta ... property="og:image" ... content="..."> or <meta ... name="twitter:image" ... content="...">
const ogRegex =
/<meta[^>]*(?:property|name)=["'](?:og:image|twitter:image)["'][^>]*content=["']([^"']+)["']/i;
const match = html.match(ogRegex);
if (match && match[1]) {
// Unescape basic HTML entities
return match[1].replace(/&amp;/g, "&").replace(/&quot;/g, '"');
}
// Try reversed attribute order: <meta ... content="..." ... property="og:image">
const ogRegexRev =
/<meta[^>]*content=["']([^"']+)["'][^>]*(?:property|name)=["'](?:og:image|twitter:image)["']/i;
const matchRev = html.match(ogRegexRev);
if (matchRev && matchRev[1]) {
return matchRev[1].replace(/&amp;/g, "&").replace(/&quot;/g, '"');
}
return null;
}
function truncateAndCleanHtml(html: string, maxLen = 1000): string {
// Strip <script> and <style> entirely
let text = html.replace(
/<script\b[^<]*(?:(?!<\/script>)<[^<]*)*<\/script>/gi,
" ",
);
text = text.replace(/<style\b[^<]*(?:(?!<\/style>)<[^<]*)*<\/style>/gi, " ");
// Strip all other HTML tags
text = text.replace(/<[^>]+>/g, " ");
// Replace multiple spaces/newlines
text = text.replace(/\s+/g, " ").trim();
return text.substring(0, maxLen);
}
export async function fetchUrlSafely(
url: string,
depth = 0,
): Promise<FetchedUrlContext> {
if (depth > 1) {
return { url, type: "error", error: "Max redirect/meta depth reached" };
}
if (!(await isSafeUrl(url))) {
return { url, type: "error", error: "Unsafe URL blocked" };
}
const controller = new AbortController();
const timeoutId = setTimeout(() => controller.abort(), FETCH_TIMEOUT_MS);
try {
const response = await fetch(url, {
signal: controller.signal,
headers: {
"User-Agent":
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36 DiscordBot/2.0",
Accept: "image/webp,image/apng,image/*,*/*;q=0.8",
},
// Do not follow more than a few redirects natively, fetch handles up to 20 by default
});
if (!response.ok) {
return { url, type: "error", error: `HTTP ${response.status}` };
}
const contentType = response.headers.get("content-type") || "";
const contentLength = parseInt(
response.headers.get("content-length") || "0",
10,
);
if (contentLength > MAX_FETCH_SIZE) {
return { url, type: "error", error: "Content too large" };
}
const buffer = await response.arrayBuffer();
if (buffer.byteLength > MAX_FETCH_SIZE) {
return { url, type: "error", error: "Downloaded content too large" };
}
if (contentType.startsWith("image/")) {
return {
url,
type: "image",
data: Buffer.from(buffer),
mimeType: contentType,
};
}
if (
contentType.startsWith("text/html") ||
contentType.startsWith("text/plain")
) {
const text = Buffer.from(buffer).toString("utf-8");
// If it's HTML, try to find an og:image first (for Tenor/Giphy etc)
if (contentType.startsWith("text/html")) {
const ogImage = extractOgImage(text);
if (ogImage && ogImage.startsWith("http")) {
// Fetch the og:image instead
return fetchUrlSafely(ogImage, depth + 1);
}
}
// Fallback to text content
const cleaned = truncateAndCleanHtml(text, 1000);
return {
url,
type: "text",
textContent: cleaned,
};
}
return {
url,
type: "error",
error: `Unsupported content type: ${contentType}`,
};
} catch (err) {
return {
url,
type: "error",
error: err instanceof Error ? err.message : String(err),
};
} finally {
clearTimeout(timeoutId);
}
}
export function extractUrlsFromText(text: string): string[] {
const matches = text.match(URL_REGEX);
if (!matches) return [];
// Deduplicate and filter out things that obviously aren't valid
return Array.from(new Set(matches)).filter((url) => {
try {
new URL(url);
return true;
} catch {
return false;
}
});
}
@@ -0,0 +1,133 @@
import { config } from "../../shared/config/config.js";
import { createChildLogger } from "../../shared/logger/logger.js";
import { uploadToTele } from "./teleUpload.js";
import {
updateAttachmentAsFailedUpload,
updateAttachmentAsUploaded,
updateAttachmentDiscordUrl,
} from "../message-capture/messageStore.js";
const logger = createChildLogger("attachment-uploader");
class AttachmentDownloadError extends Error {
constructor(
message: string,
readonly status: number,
) {
super(message);
this.name = "AttachmentDownloadError";
}
}
export type RefreshDiscordAttachmentUrl = () => Promise<string | null>;
function toErrorMessage(error: unknown): string {
return error instanceof Error ? error.message : String(error);
}
function shouldRefreshDiscordUrl(error: unknown): boolean {
return (
error instanceof AttachmentDownloadError &&
(error.status === 403 || error.status === 404)
);
}
export async function uploadAttachmentToTele(
fileBuffer: Buffer,
filename: string,
contentType = "application/octet-stream",
): Promise<string> {
try {
const result = await uploadToTele({
buffer: fileBuffer,
filename,
contentType,
uploadUrl: config.TELE_UPLOAD_URL,
timeoutMs: config.ATTACHMENT_UPLOAD_TIMEOUT_MS,
retries: config.ATTACHMENT_RETRY_ATTEMPTS,
logger,
});
return result.url;
} catch (error) {
logger.error(
{
filename,
error: toErrorMessage(error),
},
"Failed to upload attachment",
);
throw error;
}
}
export async function downloadDiscordAttachment(url: string): Promise<Buffer> {
try {
const response = await fetch(url, {
signal: AbortSignal.timeout(config.ATTACHMENT_UPLOAD_TIMEOUT_MS),
});
if (!response.ok) {
throw new AttachmentDownloadError(
`Download failed with status ${response.status}`,
response.status,
);
}
const buffer = await response.arrayBuffer();
return Buffer.from(buffer);
} catch (error) {
logger.error(
{ url, error: toErrorMessage(error) },
"Failed to download Discord attachment",
);
throw error;
}
}
export async function processAttachmentUpload(
attachmentId: string,
discordUrl: string,
filename: string,
options: {
refreshDiscordUrl?: RefreshDiscordAttachmentUrl;
contentType?: string;
} = {},
): Promise<void> {
try {
let currentDiscordUrl = discordUrl;
let buffer: Buffer;
try {
buffer = await downloadDiscordAttachment(currentDiscordUrl);
} catch (error) {
if (!options.refreshDiscordUrl || !shouldRefreshDiscordUrl(error)) {
throw error;
}
const freshUrl = await options.refreshDiscordUrl();
if (!freshUrl) throw error;
currentDiscordUrl = freshUrl;
await updateAttachmentDiscordUrl(attachmentId, freshUrl);
buffer = await downloadDiscordAttachment(currentDiscordUrl);
}
const sizeMb = buffer.length / (1024 * 1024);
if (sizeMb > config.ATTACHMENT_MAX_SIZE_MB) {
throw new Error(
`File size ${sizeMb.toFixed(2)}MB exceeds limit of ${config.ATTACHMENT_MAX_SIZE_MB}MB`,
);
}
const uploadedUrl = await uploadAttachmentToTele(
buffer,
filename,
options.contentType,
);
await updateAttachmentAsUploaded(attachmentId, uploadedUrl, Date.now());
} catch (error) {
const errorMsg = toErrorMessage(error);
await updateAttachmentAsFailedUpload(attachmentId, errorMsg);
logger.error({ attachmentId, error: errorMsg }, "Attachment upload failed");
}
}
@@ -0,0 +1,58 @@
import sharp from "sharp";
import { createChildLogger } from "../../shared/logger/logger.js";
const log = createChildLogger("imageResizer");
/**
* Resize an image buffer for optimal vision LLM analysis.
*
* - Resizes to maxDim x maxDim maintaining aspect ratio
* - Converts to JPEG at quality 85 for size reduction
* - Falls back to original buffer if sharp fails
*
* @param buf - Raw image buffer
* @param maxDim - Maximum dimension in pixels (default 1024)
* @returns Resized buffer with detected MIME type
*/
export async function resizeImageForVision(
buf: Buffer,
maxDim = 1024,
): Promise<{ data: Buffer; mimeType: string }> {
try {
const metadata = await sharp(buf).metadata();
const inputFormat = metadata.format ?? "jpeg";
// Skip resize if already smaller than maxDim
if ((metadata.width ?? 0) <= maxDim && (metadata.height ?? 0) <= maxDim) {
return { data: buf, mimeType: `image/${inputFormat}` };
}
const resized = await sharp(buf)
.resize(maxDim, maxDim, {
fit: "inside",
withoutEnlargement: true,
})
.jpeg({ quality: 85 })
.toBuffer();
log.debug(
{
originalSize: buf.length,
resizedSize: resized.length,
reductionPct: Math.round(
((buf.length - resized.length) / buf.length) * 100,
),
},
"Image resized for vision analysis",
);
return { data: resized, mimeType: "image/jpeg" };
} catch (error) {
log.warn(
{ error: error instanceof Error ? error.message : String(error) },
"Image resize failed — using original buffer",
);
// Fallback: return original buffer with best-effort MIME type
return { data: buf, mimeType: "image/jpeg" };
}
}
@@ -0,0 +1,2 @@
export { processAttachmentUpload } from "./attachmentUploader.js";
export { resizeImageForVision as resizeImage } from "./imageResizer.js";
@@ -0,0 +1,85 @@
import type { CustomLogger } from "../../shared/logger/logger.js";
import { retryWithBackoff } from "../../shared/utils/retry.js";
export interface TeleUploadResponse {
download_url: string;
public_id?: string;
file_name?: string;
size_bytes?: number;
}
export interface TeleUploadResult {
url: string;
publicId?: string;
filename?: string;
sizeBytes?: number;
}
export function parseTeleUploadResponse(
response: TeleUploadResponse,
): TeleUploadResult {
if (!response.download_url) {
throw new Error("Missing download_url in response");
}
return {
url: response.download_url,
publicId: response.public_id,
filename: response.file_name,
sizeBytes: response.size_bytes,
};
}
export async function uploadToTele(input: {
buffer: Buffer;
filename: string;
contentType: string;
uploadUrl: string;
timeoutMs?: number;
retries: number;
logger: CustomLogger;
}): Promise<TeleUploadResult> {
const {
buffer,
filename,
contentType,
uploadUrl,
timeoutMs,
retries,
logger,
} = input;
const response = await retryWithBackoff(
async () => {
const fileBlob = new Blob([new Uint8Array(buffer)], {
type: contentType,
});
const formData = new FormData();
formData.append("file", fileBlob, filename);
formData.append("fileName", filename);
const res = await fetch(uploadUrl, {
method: "POST",
headers: {
accept: "application/json",
},
body: formData,
...(timeoutMs ? { signal: AbortSignal.timeout(timeoutMs) } : {}),
});
if (!res.ok) {
throw new Error(`Upload failed: Status ${res.status}`);
}
return (await res.json()) as TeleUploadResponse;
},
{
retries,
minTimeout: 1000,
maxTimeout: 5000,
logger,
},
);
return parseTeleUploadResponse(response);
}
@@ -0,0 +1,146 @@
import Redis from "ioredis";
import type { CustomLogger } from "../../shared/logger/logger.js";
export interface DiscordGatewayEvent {
type: string;
data: unknown;
timestamp: number;
source: string;
}
export class RedisEventPublisher {
private redis: Redis;
private logger: CustomLogger;
constructor(redisUrl: string, logger: CustomLogger) {
this.redis = new Redis(redisUrl);
this.logger = logger;
this.redis.on("error", (err) => {
this.logger.error({ error: err }, "Redis connection error");
});
this.redis.on("connect", () => {
this.logger.info("Redis connected");
});
}
async publish(channel: string, event: DiscordGatewayEvent): Promise<void> {
try {
await this.redis.publish(channel, JSON.stringify(event));
} catch (error) {
this.logger.error(
{ error, channel, eventType: event.type },
"Failed to publish event",
);
}
}
async close(): Promise<void> {
await this.redis.quit();
}
}
export class EventBroadcaster {
private publisher: RedisEventPublisher;
private logger: CustomLogger;
constructor(publisher: RedisEventPublisher, logger: CustomLogger) {
this.publisher = publisher;
this.logger = logger;
}
async messageCreated(data: unknown): Promise<void> {
await this.publisher.publish("discord:message:created", {
type: "message_created",
data,
timestamp: Date.now(),
source: "discord-gateway",
});
}
async messageUpdated(data: unknown): Promise<void> {
await this.publisher.publish("discord:message:updated", {
type: "message_updated",
data,
timestamp: Date.now(),
source: "discord-gateway",
});
}
async messageDeleted(data: unknown): Promise<void> {
await this.publisher.publish("discord:message:deleted", {
type: "message_deleted",
data,
timestamp: Date.now(),
source: "discord-gateway",
});
}
async messageAnalyzed(data: unknown): Promise<void> {
await this.publisher.publish("discord:message:analyzed", {
type: "message_analyzed",
data,
timestamp: Date.now(),
source: "discord-gateway",
});
}
async attachmentCreated(data: unknown): Promise<void> {
await this.publisher.publish("discord:attachment:created", {
type: "attachment_created",
data,
timestamp: Date.now(),
source: "discord-gateway",
});
}
async attachmentUploaded(data: unknown): Promise<void> {
await this.publisher.publish("discord:attachment:uploaded", {
type: "attachment_uploaded",
data,
timestamp: Date.now(),
source: "discord-gateway",
});
}
async voiceRecordingStarted(data: unknown): Promise<void> {
await this.publisher.publish("discord:voice:started", {
type: "voice_recording_started",
data,
timestamp: Date.now(),
source: "discord-gateway",
});
}
async voiceRecordingStopped(data: unknown): Promise<void> {
await this.publisher.publish("discord:voice:stopped", {
type: "voice_recording_stopped",
data,
timestamp: Date.now(),
source: "discord-gateway",
});
}
async voiceRecordingUploaded(data: unknown): Promise<void> {
await this.publisher.publish("discord:voice:uploaded", {
type: "voice_recording_uploaded",
data,
timestamp: Date.now(),
source: "discord-gateway",
});
}
async analysisQueueStatus(data: unknown): Promise<void> {
await this.publisher.publish("discord:analysis:queue_status", {
type: "analysis_queue_status",
data,
timestamp: Date.now(),
source: "discord-gateway",
});
}
async close(): Promise<void> {
await this.publisher.close();
}
}
@@ -0,0 +1,22 @@
export interface DiscordGatewayEvent {
type: string;
data: unknown;
timestamp: number;
source: string;
}
export const EventChannels = {
MESSAGE_CREATED: "discord:message:created",
MESSAGE_UPDATED: "discord:message:updated",
MESSAGE_DELETED: "discord:message:deleted",
MESSAGE_ANALYZED: "discord:message:analyzed",
ATTACHMENT_CREATED: "discord:attachment:created",
ATTACHMENT_UPLOADED: "discord:attachment:uploaded",
VOICE_STARTED: "discord:voice:started",
VOICE_STOPPED: "discord:voice:stopped",
VOICE_UPLOADED: "discord:voice:uploaded",
ANALYSIS_QUEUE_STATUS: "discord:analysis:queue_status",
} as const;
export type EventChannelType =
(typeof EventChannels)[keyof typeof EventChannels];
@@ -0,0 +1,6 @@
export { EventBroadcaster, RedisEventPublisher } from "./eventBroadcaster.js";
export {
type DiscordGatewayEvent,
EventChannels,
type EventChannelType,
} from "./eventTypes.js";
@@ -0,0 +1,929 @@
import { executeAll, executeGet } from "../../shared/database/drizzle.js";
import { createChildLogger } from "../../shared/logger/logger.js";
import type { MessageRecord } from "./types.js";
const logger = createChildLogger("analytics-store");
// ── Types ──────────────────────────────────────────────────────────────
export interface HourlyBucket {
hour: string;
count: number;
clean: number;
warned: number;
flagged: number;
error: number;
}
export interface TopicTrend {
topic: string;
count: number;
score: number;
}
export interface UserStat {
user_id: string;
username: string;
avatar_url: string | null;
message_count: number;
edited_count: number;
deleted_count: number;
flagged_count: number;
last_active: number;
}
export interface ModerationBreakdown {
total: number;
clean: number;
warned: number;
flagged: number;
error: number;
pending: number;
average_score: number;
}
export interface AnalyticsOverview {
period: { start: number; end: number };
messages: ModerationBreakdown;
hourly: HourlyBucket[];
topics: TopicTrend[];
top_users: UserStat[];
active_users_count: number;
total_channels: number;
}
// ══════════════════════════════════════════════════════════════════════════
// GENERIC QUERY CACHE (reduces duplicate DB calls from 5s auto-refresh)
// ══════════════════════════════════════════════════════════════════════════
interface CacheEntry<T> {
data: T;
expiresAt: number;
}
const queryCache = new Map<string, CacheEntry<any>>();
/** Default TTL for aggregate queries — 10s is long enough to prevent redundant
* calls from the 5s auto-refresh but short enough to feel real-time. */
const AGGREGATE_CACHE_TTL_MS = 10_000;
/** Topic extraction is expensive (JSON parsing). Cache longer. */
const TOPIC_CACHE_TTL_MS = 120_000;
function makeCacheKey(prefix: string, params: Record<string, any>): string {
return `${prefix}:${JSON.stringify(params)}`;
}
function getCached<T>(key: string): T | undefined {
const entry = queryCache.get(key);
if (entry && entry.expiresAt > Date.now()) return entry.data;
if (entry) queryCache.delete(key); // expired
return undefined;
}
function setCache<T>(key: string, data: T, ttl: number): void {
queryCache.set(key, { data, expiresAt: Date.now() + ttl });
// Prune old entries if cache grows too large (>200 entries)
if (queryCache.size > 200) {
const now = Date.now();
for (const [k, v] of queryCache) {
if (v.expiresAt <= now) queryCache.delete(k);
}
}
}
// ── Hourly Message Stats ───────────────────────────────────────────────
export async function getHourlyStats(input: {
guildId: string;
channelId?: string;
hours?: number;
}): Promise<HourlyBucket[]> {
const { guildId, channelId, hours = 24 } = input;
const cacheKey = makeCacheKey("hourly", { guildId, channelId, hours });
const cached = getCached<HourlyBucket[]>(cacheKey);
if (cached) return cached;
try {
const since = Date.now() - hours * 3600_000;
const hourExpr = `to_char(to_timestamp((created_at / 3600000) * 3600), 'YYYY-MM-DD HH24:MI:SS') as hour`;
const rows = await executeAll(
`
SELECT
${hourExpr},
count(*) as count,
count(case when ai_status = 'clean' then 1 end) as clean,
count(case when ai_status = 'warn' then 1 end) as warned,
count(case when ai_status = 'flagged' then 1 end) as flagged,
count(case when ai_status = 'error' then 1 end) as error
FROM messages
WHERE guild_id = ?
AND created_at >= ?
AND deleted_at IS NULL
${channelId ? `AND (channel_id = ? OR thread_id = ?)` : ""}
GROUP BY (created_at / 3600000)
ORDER BY hour ASC
`,
channelId ? [guildId, since, channelId, channelId] : [guildId, since],
);
// Initialize all hour buckets (fill gaps with zeros)
const buckets = new Map<
string,
{
count: number;
clean: number;
warned: number;
flagged: number;
error: number;
}
>();
for (let h = 0; h < hours; h++) {
const ts = new Date(since + h * 3600_000);
ts.setMinutes(0, 0, 0);
const key = ts.toISOString().slice(0, 13) + ":00:00Z";
buckets.set(key, { count: 0, clean: 0, warned: 0, flagged: 0, error: 0 });
}
for (const row of rows) {
const d = new Date(row.hour.replace(" ", "T") + "Z");
const key = d.toISOString().slice(0, 13) + ":00:00Z";
const bucket = buckets.get(key);
if (!bucket) continue;
bucket.count = row.count;
bucket.clean = row.clean;
bucket.warned = row.warned;
bucket.flagged = row.flagged;
bucket.error = row.error;
}
const result = Array.from(buckets.entries())
.sort(([a], [b]) => a.localeCompare(b))
.map(([hour, data]) => ({ hour, ...data }));
setCache(cacheKey, result, AGGREGATE_CACHE_TTL_MS);
return result;
} catch (error) {
logger.error(
{ error: error instanceof Error ? error.message : String(error) },
"Failed to get hourly stats",
);
return [];
}
}
// ── Topic Trends ───────────────────────────────────────────────────────
const STOP_WORDS = new Set([
"yang",
"dan",
"itu",
"ini",
"dengan",
"akan",
"pada",
"dari",
"di",
"ke",
"untuk",
"tidak",
"ada",
"juga",
"sudah",
"saya",
"kamu",
"dia",
"mereka",
"kami",
"aku",
"lo",
"lu",
"gua",
"gue",
"org",
"orang",
"aja",
"sama",
"kalo",
"kalau",
"bisa",
"karena",
"gak",
"nggak",
"ga",
"tak",
"belum",
"udah",
"dah",
"lah",
"kah",
"pun",
"nih",
"tuh",
"deh",
"dong",
"si",
"nya",
"kan",
"ya",
"yah",
"yuk",
"kok",
"loh",
"nah",
"wow",
"eh",
"the",
"a",
"an",
"is",
"are",
"was",
"were",
"be",
"been",
"being",
"have",
"has",
"had",
"having",
"do",
"does",
"did",
"doing",
"will",
"would",
"could",
"should",
"may",
"might",
"must",
"shall",
"i",
"you",
"he",
"she",
"it",
"we",
"they",
"me",
"him",
"her",
"us",
"them",
"my",
"your",
"his",
"its",
"our",
"their",
"and",
"but",
"or",
"nor",
"not",
"so",
"yet",
"for",
"if",
"to",
"of",
"in",
"on",
"at",
"by",
"as",
"with",
"about",
"just",
"then",
"now",
"here",
"there",
"when",
"where",
"why",
"how",
"all",
"both",
"each",
"few",
"more",
"most",
"other",
"some",
"such",
"only",
"own",
"same",
"too",
"very",
"can",
"go",
"ok",
"okay",
"yeah",
"yes",
"no",
]);
function extractTopics(messages: MessageRecord[], topN = 15): TopicTrend[] {
const topicScores = new Map<string, { count: number; score: number }>();
const wordFreq = new Map<string, number>();
const flaggedWordFreq = new Map<string, number>();
for (const msg of messages) {
if (msg.ai_analysis) {
try {
const analysis = JSON.parse(msg.ai_analysis);
const topics = analysis.topics;
if (topics && Array.isArray(topics)) {
for (const topic of topics) {
const key =
typeof topic === "string" ? topic : topic.name || topic.topic;
if (!key) continue;
const k = key.toLowerCase();
const score = msg.ai_moderation_score || 0;
const existing = topicScores.get(k);
if (existing) {
existing.count++;
existing.score += score;
} else {
topicScores.set(k, { count: 1, score });
}
}
}
if (analysis.category) {
const cat = String(analysis.category).toLowerCase();
const existing = topicScores.get(cat);
if (existing) {
existing.count++;
existing.score += msg.ai_moderation_score || 0;
} else {
topicScores.set(cat, {
count: 1,
score: msg.ai_moderation_score || 0,
});
}
}
} catch {
/* not valid JSON */
}
}
if (msg.content) {
const words = msg.content
.toLowerCase()
.replace(/[^\w\s]/g, " ")
.split(/\s+/)
.filter((w) => w.length > 2 && !STOP_WORDS.has(w));
for (const word of words) {
wordFreq.set(word, (wordFreq.get(word) || 0) + 1);
if (msg.ai_status === "flagged" || msg.ai_status === "warn") {
flaggedWordFreq.set(word, (flaggedWordFreq.get(word) || 0) + 1);
}
}
}
}
const results: TopicTrend[] = [];
for (const [topic, data] of topicScores) {
results.push({ topic, count: data.count, score: data.score });
}
const sortedWords = Array.from(wordFreq.entries())
.sort(([, a], [, b]) => b - a)
.slice(0, topN);
for (const [word, count] of sortedWords) {
if (!topicScores.has(word)) {
results.push({
topic: word,
count,
score: flaggedWordFreq.get(word) || 0,
});
}
}
return results.sort((a, b) => b.count - a.count).slice(0, topN);
}
export async function getTopicTrends(input: {
guildId: string;
channelId?: string;
hours?: number;
}): Promise<TopicTrend[]> {
const { guildId, channelId, hours = 24 } = input;
const cacheKey = makeCacheKey("topics", { guildId, channelId, hours });
const cached = getCached<TopicTrend[]>(cacheKey);
if (cached) return cached;
try {
const since = Date.now() - hours * 3600_000;
// Fetch all analyzed messages within the time window (no hard row cap).
// Messages without ai_analysis are excluded which naturally limits rows.
const rows = (await executeAll(
`
SELECT
id, content, ai_status, ai_analysis, ai_moderation_score,
ai_moderation_flags, created_at
FROM messages
WHERE guild_id = ?
AND created_at >= ?
AND deleted_at IS NULL
AND ai_analysis IS NOT NULL
${channelId ? `AND (channel_id = ? OR thread_id = ?)` : ""}
ORDER BY created_at DESC
`,
channelId ? [guildId, since, channelId, channelId] : [guildId, since],
)) as MessageRecord[];
const result = extractTopics(rows);
setCache(cacheKey, result, TOPIC_CACHE_TTL_MS);
return result;
} catch (error) {
logger.error(
{ error: error instanceof Error ? error.message : String(error) },
"Failed to get topic trends",
);
return [];
}
}
// ── User Leaderboard ────────────────────────────────────────────────────
export async function getUserLeaderboard(input: {
guildId: string;
channelId?: string;
hours?: number;
limit?: number;
}): Promise<UserStat[]> {
const { guildId, channelId, hours = 24, limit = 20 } = input;
const cacheKey = makeCacheKey("leaderboard", {
guildId,
channelId,
hours,
limit,
});
const cached = getCached<UserStat[]>(cacheKey);
if (cached) return cached;
try {
const since = Date.now() - hours * 3600_000;
const rows = await executeAll(
`
SELECT
user_id,
username,
avatar_url,
count(*) as message_count,
count(case when type = 'edited' then 1 end) as edited_count,
count(case when type = 'deleted' then 1 end) as deleted_count,
count(case when ai_status = 'flagged' then 1 end) as flagged_count,
max(created_at) as last_active
FROM messages
WHERE guild_id = ?
AND created_at >= ?
AND deleted_at IS NULL
${channelId ? `AND (channel_id = ? OR thread_id = ?)` : ""}
GROUP BY user_id, username, avatar_url
ORDER BY message_count DESC
LIMIT ?
`,
channelId
? [guildId, since, channelId, channelId, limit]
: [guildId, since, limit],
);
const result = rows as UserStat[];
setCache(cacheKey, result, AGGREGATE_CACHE_TTL_MS);
return result;
} catch (error) {
logger.error(
{ error: error instanceof Error ? error.message : String(error) },
"Failed to get user leaderboard",
);
return [];
}
}
// ── Moderation Stats ───────────────────────────────────────────────────
export async function getModerationStats(input: {
guildId: string;
channelId?: string;
hours?: number;
}): Promise<ModerationBreakdown> {
const { guildId, channelId, hours = 24 } = input;
const cacheKey = makeCacheKey("modstats", { guildId, channelId, hours });
const cached = getCached<ModerationBreakdown>(cacheKey);
if (cached) return cached;
try {
const since = Date.now() - hours * 3600_000;
const avgScoreExpr = `round(avg(ai_moderation_score)::numeric, 2)`;
const row = await executeGet(
`
SELECT
count(*) as total,
count(case when ai_status = 'clean' then 1 end) as clean,
count(case when ai_status = 'warn' then 1 end) as warned,
count(case when ai_status = 'flagged' then 1 end) as flagged,
count(case when ai_status = 'error' then 1 end) as error,
count(case when ai_status = 'pending' or ai_status IS NULL then 1 end) as pending,
${avgScoreExpr} as average_score
FROM messages
WHERE guild_id = ?
AND created_at >= ?
AND deleted_at IS NULL
${channelId ? `AND (channel_id = ? OR thread_id = ?)` : ""}
`,
channelId ? [guildId, since, channelId, channelId] : [guildId, since],
);
const result: ModerationBreakdown = row
? {
total: row.total ?? 0,
clean: row.clean ?? 0,
warned: row.warned ?? 0,
flagged: row.flagged ?? 0,
error: row.error ?? 0,
pending: row.pending ?? 0,
average_score: row.average_score ?? 0,
}
: {
total: 0,
clean: 0,
warned: 0,
flagged: 0,
error: 0,
pending: 0,
average_score: 0,
};
setCache(cacheKey, result, AGGREGATE_CACHE_TTL_MS);
return result;
} catch (error) {
logger.error(
{ error: error instanceof Error ? error.message : String(error) },
"Failed to get moderation stats",
);
return {
total: 0,
clean: 0,
warned: 0,
flagged: 0,
error: 0,
pending: 0,
average_score: 0,
};
}
}
// ── Active Channels Count ──────────────────────────────────────────────
export async function getActiveChannelCount(input: {
guildId: string;
hours?: number;
}): Promise<number> {
const { guildId, hours = 24 } = input;
const cacheKey = makeCacheKey("channels", { guildId, hours });
const cached = getCached<number>(cacheKey);
if (cached !== undefined) return cached;
try {
const since = Date.now() - hours * 3600_000;
const row = await executeGet(
`
SELECT count(DISTINCT channel_id) as cnt
FROM messages
WHERE guild_id = ?
AND created_at >= ?
AND deleted_at IS NULL
`,
[guildId, since],
);
const result = row?.cnt ?? 0;
setCache(cacheKey, result, AGGREGATE_CACHE_TTL_MS);
return result;
} catch (error) {
logger.error(
{ error: error instanceof Error ? error.message : String(error) },
"Failed to get active channel count",
);
return 0;
}
}
// ── Top Violators ─────────────────────────────────────────────────────
export interface ViolatorStat {
user_id: string;
username: string;
avatar_url: string | null;
total_messages: number;
flagged_count: number;
warned_count: number;
violation_score: number;
worst_flags: string[];
last_violation: number;
}
export async function getTopViolators(input: {
guildId: string;
channelId?: string;
hours?: number;
limit?: number;
}): Promise<ViolatorStat[]> {
const { guildId, channelId, hours = 24, limit = 20 } = input;
const cacheKey = makeCacheKey("violators", {
guildId,
channelId,
hours,
limit,
});
const cached = getCached<ViolatorStat[]>(cacheKey);
if (cached) return cached;
try {
const since = Date.now() - hours * 3600_000;
const rows = await executeAll(
`
SELECT
user_id,
username,
avatar_url,
count(*) as total_messages,
count(case when ai_status = 'flagged' then 1 end) as flagged_count,
count(case when ai_status = 'warn' then 1 end) as warned_count,
max(case when ai_status in ('flagged', 'warn') then created_at else 0 end) as last_violation
FROM messages
WHERE guild_id = ?
AND created_at >= ?
AND deleted_at IS NULL
${channelId ? `AND (channel_id = ? OR thread_id = ?)` : ""}
GROUP BY user_id, username, avatar_url
HAVING count(case when ai_status = 'flagged' then 1 end) > 0
OR count(case when ai_status = 'warn' then 1 end) > 0
ORDER BY (
count(case when ai_status = 'flagged' then 1 end) * 3
+ count(case when ai_status = 'warn' then 1 end)
) DESC
LIMIT ?
`,
channelId
? [guildId, since, channelId, channelId, limit]
: [guildId, since, limit],
);
const violators: ViolatorStat[] = rows.map((row: any) => {
const flaggedCount = Number(row.flagged_count ?? 0);
const warnedCount = Number(row.warned_count ?? 0);
return {
user_id: row.user_id,
username: row.username,
avatar_url: row.avatar_url,
total_messages: Number(row.total_messages ?? 0),
flagged_count: flaggedCount,
warned_count: warnedCount,
violation_score: flaggedCount * 3 + warnedCount,
worst_flags: [],
last_violation: Number(row.last_violation ?? 0),
};
});
setCache(cacheKey, violators, AGGREGATE_CACHE_TTL_MS);
return violators;
} catch (error) {
logger.error(
{ error: error instanceof Error ? error.message : String(error) },
"Failed to get top violators",
);
return [];
}
}
// ── Daily Trend (for multi-day line chart) ────────────────────────────
export interface TrendBucket {
date: string;
count: number;
clean: number;
warned: number;
flagged: number;
error: number;
}
export async function getDailyTrend(input: {
guildId: string;
channelId?: string;
hours?: number;
}): Promise<TrendBucket[]> {
const { guildId, channelId, hours = 168 } = input;
const cacheKey = makeCacheKey("daily_trend", { guildId, channelId, hours });
const cached = getCached<TrendBucket[]>(cacheKey);
if (cached) return cached;
try {
const since = Date.now() - hours * 3600_000;
const dateExpr = `to_char(date_trunc('day', to_timestamp(created_at / 1000)), 'YYYY-MM-DD') as date`;
const rows = await executeAll(
`
SELECT
${dateExpr},
count(*) as count,
count(case when ai_status = 'clean' then 1 end) as clean,
count(case when ai_status = 'warn' then 1 end) as warned,
count(case when ai_status = 'flagged' then 1 end) as flagged,
count(case when ai_status = 'error' then 1 end) as error
FROM messages
WHERE guild_id = ?
AND created_at >= ?
AND deleted_at IS NULL
${channelId ? `AND (channel_id = ? OR thread_id = ?)` : ""}
GROUP BY 1
ORDER BY 1 ASC
`,
channelId ? [guildId, since, channelId, channelId] : [guildId, since],
);
// Initialize all day buckets (fill gaps with zeros)
const buckets = new Map<
string,
{
count: number;
clean: number;
warned: number;
flagged: number;
error: number;
}
>();
const msPerDay = 86400_000;
const startDay = Math.floor(since / msPerDay) * msPerDay;
const endDay = Math.floor(Date.now() / msPerDay) * msPerDay;
for (let d = startDay; d <= endDay; d += msPerDay) {
const key = new Date(d).toISOString().slice(0, 10);
buckets.set(key, { count: 0, clean: 0, warned: 0, flagged: 0, error: 0 });
}
for (const row of rows) {
const bucket = buckets.get(row.date);
if (!bucket) continue;
bucket.count = row.count;
bucket.clean = row.clean;
bucket.warned = row.warned;
bucket.flagged = row.flagged;
bucket.error = row.error;
}
const result = Array.from(buckets.entries())
.sort(([a], [b]) => a.localeCompare(b))
.map(([date, data]) => ({ date, ...data }));
setCache(cacheKey, result, AGGREGATE_CACHE_TTL_MS);
return result;
} catch (error) {
logger.error(
{ error: error instanceof Error ? error.message : String(error) },
"Failed to get daily trend",
);
return [];
}
}
// ── Activity Heatmap (day-of-week × hour-of-day) ──────────────────────
export interface HeatmapCell {
dayOfWeek: number; // 0=Senin, 6=Minggu
hour: number; // 0-23
count: number;
clean: number;
warned: number;
flagged: number;
}
export async function getActivityHeatmap(input: {
guildId: string;
channelId?: string;
hours?: number;
}): Promise<HeatmapCell[]> {
const { guildId, channelId, hours = 168 } = input;
const cacheKey = makeCacheKey("heatmap", { guildId, channelId, hours });
const cached = getCached<HeatmapCell[]>(cacheKey);
if (cached) return cached;
try {
const since = Date.now() - hours * 3600_000;
const dayExpr = `(extract(isodow from to_timestamp(created_at / 1000)) % 7)::int as day_of_week`;
const hourExpr = `extract(hour from to_timestamp(created_at / 1000))::int as hour`;
const rows = await executeAll(
`
SELECT
${dayExpr},
${hourExpr},
count(*) as count,
count(case when ai_status = 'clean' then 1 end) as clean,
count(case when ai_status = 'warn' then 1 end) as warned,
count(case when ai_status = 'flagged' then 1 end) as flagged
FROM messages
WHERE guild_id = ?
AND created_at >= ?
AND deleted_at IS NULL
${channelId ? `AND (channel_id = ? OR thread_id = ?)` : ""}
GROUP BY day_of_week, hour
ORDER BY day_of_week, hour
`,
channelId ? [guildId, since, channelId, channelId] : [guildId, since],
);
// Initialize all 7×24 cells with zeros
const cells = new Map<
string,
{ count: number; clean: number; warned: number; flagged: number }
>();
for (let d = 0; d < 7; d++) {
for (let h = 0; h < 24; h++) {
cells.set(`${d}-${h}`, { count: 0, clean: 0, warned: 0, flagged: 0 });
}
}
for (const row of rows) {
const key = `${row.day_of_week}-${row.hour}`;
const cell = cells.get(key);
if (!cell) continue;
cell.count = row.count;
cell.clean = row.clean;
cell.warned = row.warned;
cell.flagged = row.flagged;
}
const result = Array.from(cells.entries())
.map(([key, data]) => {
const [dayOfWeek, hour] = key.split("-").map(Number);
return { dayOfWeek, hour, ...data };
})
.sort((a, b) => a.dayOfWeek - b.dayOfWeek || a.hour - b.hour);
setCache(cacheKey, result, AGGREGATE_CACHE_TTL_MS);
return result;
} catch (error) {
logger.error(
{ error: error instanceof Error ? error.message : String(error) },
"Failed to get activity heatmap",
);
return [];
}
}
// ── Cache Invalidation (called when new messages arrive) ───────────────
export function invalidateAnalyticsCache(guildId: string): void {
const now = Date.now();
const needle = `"${guildId}"`;
for (const [key, entry] of queryCache) {
if (key.includes(needle) && entry.expiresAt > now) {
entry.expiresAt = 0; // expire immediately
}
}
}
// ── Combined Overview ──────────────────────────────────────────────────
export async function getAnalyticsOverview(input: {
guildId: string;
channelId?: string;
hours?: number;
}): Promise<AnalyticsOverview> {
const { guildId, hours = 24 } = input;
const now = Date.now();
const since = now - hours * 3600_000;
const [messages, hourly, topics, topUsers, totalChannels] = await Promise.all(
[
getModerationStats(input),
getHourlyStats(input),
getTopicTrends(input),
getUserLeaderboard(input),
getActiveChannelCount({ guildId, hours }),
],
);
return {
period: { start: since, end: now },
messages,
hourly,
topics,
top_users: topUsers,
active_users_count: topUsers.length,
total_channels: totalChannels,
};
}
@@ -0,0 +1,82 @@
import type { WebSocket } from "ws";
import { createChildLogger } from "../../shared/logger/logger.js";
import type {
AnalysisQueueStatus,
AttachmentRecord,
MediaState,
MessageRecord,
ModerationWsEvent,
} from "../message-capture/types.js";
export type BroadcasterClient = Pick<WebSocket, "readyState" | "send">;
const log = createChildLogger("broadcaster");
function sendJson(
clients: Set<BroadcasterClient>,
event: ModerationWsEvent,
): void {
const payload = JSON.stringify({ ...event, timestamp: Date.now() });
for (const client of clients) {
if (client.readyState === 1) {
try {
client.send(payload);
} catch (error) {
log.warn(
{ error, eventType: event.type },
"Failed to send event to client",
);
}
}
}
}
export function createBroadcaster() {
const clients = new Set<BroadcasterClient>();
return {
addClient(client: BroadcasterClient) {
clients.add(client);
log.debug({ clientCount: clients.size }, "Client added");
},
removeClient(client: BroadcasterClient) {
clients.delete(client);
log.debug({ clientCount: clients.size }, "Client removed");
},
clientCount() {
return clients.size;
},
getClients() {
return Array.from(clients);
},
uiState(state: unknown) {
sendJson(clients, { type: "ui_state", state });
},
userState(users: unknown[]) {
sendJson(clients, { type: "user_state", users });
},
messageCreated(data: MessageRecord) {
sendJson(clients, { type: "message_created", data });
},
messageUpdated(data: Partial<MessageRecord> & { id: string }) {
sendJson(clients, { type: "message_updated", data });
},
messageDeleted(data: { id: string; deleted_at: number }) {
sendJson(clients, { type: "message_deleted", data });
},
messageAnalyzed(data: MessageRecord) {
sendJson(clients, { type: "message_analyzed", data });
},
attachmentCreated(data: AttachmentRecord) {
sendJson(clients, { type: "attachment_created", data });
},
analysisQueueStatus(data: AnalysisQueueStatus) {
sendJson(clients, { type: "analysis_queue_status", data });
},
mediaState(state: MediaState) {
sendJson(clients, { type: "media_state", state });
},
};
}
export type ModerationBroadcaster = ReturnType<typeof createBroadcaster>;
@@ -0,0 +1,21 @@
export { registerMessageCapture } from "./messageCapture.js";
export {
getDisplayContent,
getMessageLocation,
getMessageMetadata,
} from "../message-capture/messageMetadata.js";
export {
getMessageById,
insertAttachment,
updateMessageAsDeleted,
updateMessageAsEdited,
upsertMessageForCapture,
} from "../message-capture/messageStore.js";
export type {
AIRecommendedAction,
AISeverity,
AIStatus,
AttachmentRecord,
MessageRecord,
VoiceSegmentRecord,
} from "../message-capture/types.js";
@@ -0,0 +1,302 @@
import type { Client, Message } from "discord.js-selfbot-v13";
import { config } from "../../shared/config/config.js";
import { createChildLogger } from "../../shared/logger/logger.js";
import { queueMessageAnalysis } from "../ai-moderation/aiAnalyzer.js";
import { processAttachmentUpload } from "../attachment-upload/attachmentUploader.js";
import type { EventBroadcaster } from "../event-broadcaster/eventBroadcaster.js";
import {
getDisplayContent,
getMessageLocation,
getMessageMetadata,
} from "../message-capture/messageMetadata.js";
import {
getMessageById,
insertAttachment,
updateMessageAsDeleted,
updateMessageAsEdited,
upsertMessageForCapture,
} from "../message-capture/messageStore.js";
import type { AttachmentRecord, MessageRecord } from "../message-capture/types.js";
const logger = createChildLogger("message-capture");
let _eventBroadcaster: EventBroadcaster | undefined;
export function setEventBroadcaster(broadcaster: EventBroadcaster | undefined) {
_eventBroadcaster = broadcaster;
}
export interface TextCaptureTarget {
guildId?: string;
channelId?: string;
}
export interface MessageLocationInput {
guildId?: string | null;
channelId?: string | null;
}
export function shouldCaptureMessageLocation(
message: MessageLocationInput,
target: TextCaptureTarget,
): boolean {
if (
message.channelId === "1310988070996414494" ||
message.channelId === "1265679542144467035" ||
message.channelId === "1310867899745046558"
)
return false;
if (!message.guildId || message.guildId !== target.guildId) return false;
if (target.channelId && message.channelId !== target.channelId) return false;
return true;
}
function getTextCaptureTarget(): TextCaptureTarget {
return {
guildId: config.EFFECTIVE_TEXT_GUILD_ID,
channelId: config.TEXT_CHANNEL_ID,
};
}
function requireMessageGuildId(message: Message): string {
if (!message.guildId) {
throw new Error(`Message ${message.id} is missing guildId`);
}
return message.guildId;
}
function buildMessageRecord(
message: Message,
type: "text" | "edited" | "deleted",
): MessageRecord {
const location = getMessageLocation(message);
const metadata = getMessageMetadata(message);
const guildId = requireMessageGuildId(message);
return {
id: message.id,
guild_id: guildId,
channel_id: location.channelId,
thread_id: location.threadId,
user_id: message.author?.id,
username: message.author?.username,
avatar_url: message.author?.avatarURL() || null,
content: getDisplayContent(message),
edited_content: null,
created_at: message.createdTimestamp,
edited_at: null,
deleted_at: null,
type,
metadata: JSON.stringify(metadata),
};
}
function buildAttachmentRecord(
message: Message,
location: ReturnType<typeof getMessageLocation>,
attachment: {
id: string;
name: string | null;
size: number;
contentType: string | null;
url: string;
},
): AttachmentRecord {
const guildId = requireMessageGuildId(message);
return {
id: attachment.id,
message_id: message.id,
guild_id: guildId,
channel_id: location.channelId,
thread_id: location.threadId,
user_id: message.author?.id,
filename: attachment.name || "unknown",
size: attachment.size,
type: attachment.contentType || "application/octet-stream",
discord_url: attachment.url,
uploaded_url: null,
upload_status: "pending",
upload_error: null,
created_at: Date.now(),
uploaded_at: null,
};
}
export async function captureMessage(
message: Message,
type: "text" | "edited" | "deleted",
options: { source?: "live" | "backlog" } = {},
): Promise<void> {
const location = getMessageLocation(message);
const messageRecord = buildMessageRecord(message, type);
const inserted = await upsertMessageForCapture(messageRecord);
if (!inserted) {
return;
}
const isBacklog = options.source === "backlog";
if (_eventBroadcaster && !isBacklog) {
_eventBroadcaster.messageCreated(messageRecord);
}
const attachmentUploadTasks: Promise<void>[] = [];
if (message.attachments.size > 0) {
for (const [, attachment] of message.attachments) {
const attachmentRecord = buildAttachmentRecord(message, location, {
id: attachment.id,
name: attachment.name,
size: attachment.size,
contentType: attachment.contentType,
url: attachment.url,
});
await insertAttachment(attachmentRecord);
if (!isBacklog) {
attachmentUploadTasks.push(
processAttachmentUpload(
attachment.id,
attachment.url,
attachment.name || "unknown",
{
contentType: attachment.contentType ?? undefined,
refreshDiscordUrl: async () => {
const freshMessage = await message.channel.messages.fetch(
message.id,
);
const freshAttachment = freshMessage.attachments.get(
attachment.id,
);
return freshAttachment?.url ?? null;
},
},
).catch((err: unknown) => {
logger.error(
{ attachmentId: attachment.id, error: err },
"Failed to initiate attachment upload",
);
}),
);
}
if (_eventBroadcaster) {
_eventBroadcaster.attachmentCreated(attachmentRecord);
}
}
}
if (!isBacklog) {
if (attachmentUploadTasks.length > 0) {
let analysisQueued = false;
let fallbackTimer: NodeJS.Timeout | null = null;
const queueAnalysisOnce = () => {
if (analysisQueued) return;
analysisQueued = true;
if (fallbackTimer) {
clearTimeout(fallbackTimer);
fallbackTimer = null;
}
queueMessageAnalysis(message.id);
};
fallbackTimer = setTimeout(queueAnalysisOnce, 30000);
Promise.allSettled(attachmentUploadTasks)
.then(queueAnalysisOnce)
.catch((err: unknown) => {
logger.error(
{ messageId: message.id, error: err },
"Failed to queue message analysis after attachment upload",
);
queueAnalysisOnce();
});
} else {
queueMessageAnalysis(message.id);
}
}
}
export function registerMessageCapture(client: Client): void {
client.on("messageCreate", async (message) => {
if (!shouldCaptureMessageLocation(message, getTextCaptureTarget())) return;
if (message.author?.bot) return;
try {
await captureMessage(message, "text");
} catch (error) {
logger.error(
{
messageId: message.id,
error: error instanceof Error ? error.message : String(error),
},
"Failed to capture message",
);
}
});
client.on("messageUpdate", async (_oldMessage, newMessage) => {
if (!shouldCaptureMessageLocation(newMessage, getTextCaptureTarget()))
return;
if (newMessage.author?.bot) return;
try {
const existing = await getMessageById(newMessage.id);
if (existing) {
const editedAt = Date.now();
await updateMessageAsEdited(
newMessage.id,
getDisplayContent(newMessage as Message),
editedAt,
);
queueMessageAnalysis(newMessage.id);
if (_eventBroadcaster) {
_eventBroadcaster.messageUpdated({
id: newMessage.id,
edited_content: getDisplayContent(newMessage as Message),
edited_at: editedAt,
});
}
} else if (newMessage.author) {
await captureMessage(newMessage as Message, "text");
}
} catch (error) {
logger.error(
{
messageId: newMessage.id,
error: error instanceof Error ? error.message : String(error),
},
"Failed to capture message update",
);
}
});
client.on("messageDelete", async (message) => {
if (!shouldCaptureMessageLocation(message, getTextCaptureTarget())) return;
if (!message.author) return;
try {
const deletedAt = Date.now();
await updateMessageAsDeleted(message.id, deletedAt);
if (_eventBroadcaster) {
_eventBroadcaster.messageDeleted({
id: message.id,
deleted_at: deletedAt,
});
}
} catch (error) {
logger.error(
{
messageId: message.id,
error: error instanceof Error ? error.message : String(error),
},
"Failed to capture message deletion",
);
}
});
}
@@ -0,0 +1,375 @@
import type {
Message,
TextChannel,
ThreadChannel,
} from "discord.js-selfbot-v13";
export interface MessageLocation {
channelId: string;
threadId: string | null;
threadName: string | null;
channelName: string | null;
nsfw?: boolean;
nsfwLevel?: string | null;
ageRestricted?: boolean;
}
export interface StickerEvidence {
id: string;
name: string;
url: string;
format: string | null;
}
export interface CustomEmojiEvidence {
id: string;
name: string;
animated: boolean;
url: string;
}
export interface EmbedEvidence {
title: string | null;
description: string | null;
url: string | null;
color: number | null;
image: string | null;
thumbnail: string | null;
author: {
name: string | null;
url: string | null;
iconURL: string | null;
} | null;
footer: { text: string | null; iconURL: string | null } | null;
fields: Array<{ name: string; value: string; inline: boolean }>;
}
export interface AttachmentEvidence {
id: string;
name: string;
url: string;
contentType: string | null;
size: number;
}
export interface MessageMediaEvidence {
stickers: StickerEvidence[];
embeds: EmbedEvidence[];
attachments: AttachmentEvidence[];
customEmojis: CustomEmojiEvidence[];
}
export interface RichMessageMetadata {
stickers: Array<StickerEvidence>;
embeds: Array<EmbedEvidence>;
attachments: Array<AttachmentEvidence>;
customEmojis: Array<CustomEmojiEvidence>;
author: {
id: string;
username: string;
tag: string | null;
avatarURL: string | null;
bot: boolean;
};
member: {
displayName: string | null;
roles: Array<{ id: string; name: string }>;
joinedTimestamp: number | null;
} | null;
channel: MessageLocation;
reference: {
messageId: string | null;
channelId: string | null;
guildId: string | null;
} | null;
}
export function getMessageLocation(message: Message): MessageLocation {
const channel = message.channel as TextChannel | ThreadChannel;
const safetyChannel = channel as TextChannel & {
nsfw?: boolean;
nsfwLevel?: string | null;
};
if (!channel.isThread?.()) {
return {
channelId: message.channelId,
threadId: null,
threadName: null,
channelName: "name" in channel ? channel.name : null,
nsfw:
typeof safetyChannel.nsfw === "boolean"
? safetyChannel.nsfw
: undefined,
nsfwLevel:
typeof safetyChannel.nsfwLevel === "string"
? safetyChannel.nsfwLevel
: null,
ageRestricted:
typeof safetyChannel.nsfw === "boolean"
? safetyChannel.nsfw
: undefined,
};
}
return {
channelId: channel.parentId ?? message.channelId,
threadId: channel.id,
threadName: channel.name,
channelName: channel.parent?.name ?? null,
nsfw:
typeof safetyChannel.nsfw === "boolean" ? safetyChannel.nsfw : undefined,
nsfwLevel:
typeof safetyChannel.nsfwLevel === "string"
? safetyChannel.nsfwLevel
: null,
ageRestricted:
typeof safetyChannel.nsfw === "boolean" ? safetyChannel.nsfw : undefined,
};
}
export function getStickerMetadata(
message: Message,
): RichMessageMetadata["stickers"] {
return Array.from(message.stickers.values()).map((sticker) => ({
id: sticker.id,
name: sticker.name,
url: sticker.url,
format: sticker.format ?? null,
}));
}
/**
* Extract custom emoji references from message content.
* Builds Discord CDN URLs for each emoji so they can be downloaded
* and sent to the vision model for analysis.
*/
export function getCustomEmojiMetadata(
message: Message,
): RichMessageMetadata["customEmojis"] {
const CUSTOM_EMOJI_PATTERN = /<(a)?:([a-zA-Z0-9_]+):(\d+)>/g;
const emojis: CustomEmojiEvidence[] = [];
let match;
while ((match = CUSTOM_EMOJI_PATTERN.exec(message.content)) !== null) {
const [, animated, name, id] = match;
const ext = animated ? "gif" : "png";
emojis.push({
id,
name,
animated: animated === "a",
url: `https://cdn.discordapp.com/emojis/${id}.${ext}?size=128`,
});
}
return emojis;
}
export function getAttachmentMetadata(
message: Message,
): RichMessageMetadata["attachments"] {
return Array.from(message.attachments.values()).map((attachment) => ({
id: attachment.id,
name: attachment.name || "unknown",
url: attachment.url,
contentType: attachment.contentType ?? null,
size: attachment.size,
}));
}
export function getEmbedMetadata(
message: Message,
): RichMessageMetadata["embeds"] {
return message.embeds.map((embed) => ({
title: embed.title ?? null,
description: embed.description ?? null,
url: embed.url ?? null,
color: embed.color ?? null,
image: embed.image?.url ?? null,
thumbnail: embed.thumbnail?.url ?? null,
author: embed.author
? {
name: embed.author.name ?? null,
url: embed.author.url ?? null,
iconURL: embed.author.iconURL ?? null,
}
: null,
footer: embed.footer
? {
text: embed.footer.text ?? null,
iconURL: embed.footer.iconURL ?? null,
}
: null,
fields: embed.fields.map((field) => ({
name: field.name,
value: field.value,
inline: Boolean(field.inline),
})),
}));
}
export function getMessageMetadata(message: Message): RichMessageMetadata {
const member = message.member;
return {
stickers: getStickerMetadata(message),
embeds: getEmbedMetadata(message),
attachments: getAttachmentMetadata(message),
customEmojis: getCustomEmojiMetadata(message),
author: {
id: message.author.id,
username: message.author.username,
tag: "tag" in message.author ? message.author.tag : null,
avatarURL: message.author.avatarURL() ?? null,
bot: Boolean(message.author.bot),
},
member: member
? {
displayName: member.displayName ?? null,
roles: member.roles.cache.map((role) => ({
id: role.id,
name: role.name,
})),
joinedTimestamp: member.joinedTimestamp ?? null,
}
: null,
channel: getMessageLocation(message),
reference: message.reference
? {
messageId: message.reference.messageId ?? null,
channelId: message.reference.channelId ?? null,
guildId: message.reference.guildId ?? null,
}
: null,
};
}
export function parseRichMessageMetadata(
metadata: string | null | undefined,
): RichMessageMetadata | null {
if (!metadata) return null;
try {
const parsed = JSON.parse(metadata) as Partial<RichMessageMetadata>;
return {
stickers: Array.isArray(parsed.stickers) ? parsed.stickers : [],
embeds: Array.isArray(parsed.embeds) ? parsed.embeds : [],
attachments: Array.isArray(parsed.attachments) ? parsed.attachments : [],
customEmojis: Array.isArray(parsed.customEmojis)
? parsed.customEmojis
: [],
author: parsed.author as RichMessageMetadata["author"],
member: (parsed.member ?? null) as RichMessageMetadata["member"],
channel: parsed.channel as RichMessageMetadata["channel"],
reference: (parsed.reference ?? null) as RichMessageMetadata["reference"],
};
} catch {
return null;
}
}
export function isAgeRestrictedMetadata(
metadata: string | null | undefined,
): boolean {
const parsed = parseRichMessageMetadata(metadata);
if (!parsed) return false;
const nsfwLevel = parsed.channel.nsfwLevel?.toUpperCase();
return Boolean(
parsed.channel.nsfw ||
parsed.channel.ageRestricted ||
nsfwLevel === "AGE_RESTRICTED",
);
}
export function extractMessageMediaEvidence(
metadata: string | null | undefined,
): MessageMediaEvidence {
const parsed = parseRichMessageMetadata(metadata);
return {
stickers: parsed?.stickers ?? [],
embeds: parsed?.embeds ?? [],
attachments: parsed?.attachments ?? [],
customEmojis: parsed?.customEmojis ?? [],
};
}
export function formatMediaEvidenceForPrompt(
metadata: string | null | undefined,
): string {
const evidence = extractMessageMediaEvidence(metadata);
const parts: string[] = [];
if (evidence.stickers.length > 0) {
parts.push(
`[stickers: ${evidence.stickers
.map((sticker) =>
[`name=${sticker.name}`, sticker.url ? `url=${sticker.url}` : null]
.filter(Boolean)
.join(", "),
)
.join(" | ")}]`,
);
}
if (evidence.embeds.length > 0) {
parts.push(
`[embeds: ${evidence.embeds
.map((embed) =>
[
embed.title ? `title=${embed.title}` : null,
embed.description ? `description=${embed.description}` : null,
embed.url ? `url=${embed.url}` : null,
embed.image ? `image=${embed.image}` : null,
embed.thumbnail ? `thumbnail=${embed.thumbnail}` : null,
embed.fields.length > 0
? `fields=${embed.fields.map((field) => `${field.name}: ${field.value}`).join("; ")}`
: null,
]
.filter(Boolean)
.join(", "),
)
.join(" | ")}]`,
);
}
if (evidence.attachments.length > 0) {
parts.push(
`[attachments: ${evidence.attachments
.map((attachment) =>
[
`name=${attachment.name}`,
attachment.contentType ? `type=${attachment.contentType}` : null,
`size=${attachment.size}`,
attachment.url ? `url=${attachment.url}` : null,
]
.filter(Boolean)
.join(", "),
)
.join(" | ")}]`,
);
}
return parts.join(" ");
}
export function getDisplayContent(message: Message): string {
if (message.content.trim().length > 0) return message.content;
const stickers = getStickerMetadata(message);
if (stickers.length > 0) {
return stickers.map((sticker) => `[Sticker: ${sticker.name}]`).join(" ");
}
const attachments = getAttachmentMetadata(message);
if (attachments.length > 0) {
return attachments
.map((attachment) => `[Attachment: ${attachment.name}]`)
.join(" ");
}
const embeds = getEmbedMetadata(message);
if (embeds.length > 0) {
return embeds
.map((embed) => embed.title || embed.description || "[Embed]")
.join(" ");
}
return "";
}
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,21 @@
export interface CursorData {
created_at: number;
id: string;
}
export function encodeCursor(data: CursorData): string {
return Buffer.from(JSON.stringify(data)).toString("base64");
}
export function decodeCursor(cursor?: string): CursorData | null {
if (!cursor) return null;
try {
const data = JSON.parse(Buffer.from(cursor, "base64").toString("utf-8"));
if (typeof data.created_at === "number" && typeof data.id === "string") {
return data;
}
return null;
} catch {
return null;
}
}
@@ -0,0 +1,267 @@
import type fs from "node:fs";
import type prism from "prism-media";
export type AIStatus = "pending" | "clean" | "warn" | "flagged" | "error";
export type AISeverity = "none" | "low" | "medium" | "high" | "critical";
export type AIRecommendedAction =
| "none"
| "monitor"
| "warn"
| "review"
| "delete"
| "escalate";
export interface BroadcasterClient {
messageCreated: (data: unknown) => void;
messageUpdated: (data: unknown) => void;
messageDeleted: (data: unknown) => void;
messageAnalyzed: (data: unknown) => void;
attachmentCreated: (data: unknown) => void;
attachmentUploaded: (data: unknown) => void;
voiceRecordingStarted: (data: unknown) => void;
voiceRecordingStopped: (data: unknown) => void;
voiceRecordingUploaded: (data: unknown) => void;
analysisQueueStatus: (data: unknown) => void;
}
export type ModerationBroadcaster = BroadcasterClient;
export interface RoleMetadata {
id: string;
name: string;
position: number;
}
export interface UserMetadata {
userId: string;
username: string;
tag: string;
displayName: string;
avatarUrl: string;
bot: boolean;
roles: RoleMetadata[];
highestRole: RoleMetadata | null;
joinedTimestamp: number | null;
}
export interface SegmentState {
index: number;
startTime: number;
endTime: number | null;
filename: string;
jsonFilename: string;
oggStream: prism.opus.OggLogicalBitstream;
out: fs.WriteStream;
}
export interface SegmentMetadata extends UserMetadata {
recordingSessionId: string;
sessionId: string;
sessionStartTime: number;
segmentIndex: number;
segmentMs: number;
startTime: number;
endTime: number;
durationMs: number;
filename: string;
}
export interface PcmBroadcaster {
broadcastPcmToWeb?: (chunk: Buffer, userId: string) => void;
updateActiveUser?: (
userId: string,
data: { username: string; avatar: string; speaking: boolean },
) => void;
}
export interface MessageRecord {
id: string;
guild_id: string;
channel_id: string;
thread_id: string | null;
user_id: string;
username: string;
avatar_url: string | null;
content: string;
edited_content: string | null;
created_at: number;
edited_at: number | null;
deleted_at: number | null;
type: "text" | "edited" | "deleted";
metadata: string | null;
ai_status?: AIStatus | null;
ai_moderation_flags?: string | null;
ai_moderation_score?: number | null;
ai_analysis?: string | null;
ai_categories?: string | null;
ai_severity?: AISeverity | null;
ai_confidence?: number | null;
ai_recommended_action?: AIRecommendedAction | null;
ai_analyzed_at?: number | null;
ai_error?: string | null;
}
export interface AttachmentRecord {
id: string;
message_id: string;
guild_id: string;
channel_id: string;
thread_id: string | null;
user_id: string;
filename: string;
size: number;
type: string;
discord_url: string;
uploaded_url: string | null;
upload_status: "pending" | "uploaded" | "failed";
upload_error: string | null;
created_at: number;
uploaded_at: number | null;
}
export interface VoiceSegmentRecord {
id: string;
user_id: string;
session_id: string;
guild_id: string;
channel_id: string;
filename: string;
duration_ms: number;
created_at: number;
}
export interface DashboardMessage {
id: string;
channel_id: string;
user_id: string;
username: string;
avatar_url: string | null;
content: string;
created_at: number;
type: "text" | "image" | "voice";
}
export interface MessageQuery {
guildId?: string;
channelId?: string;
threadId?: string;
status?: AIStatus[];
userId?: string;
q?: string;
cursor?: string;
limit: number;
}
export interface PageResult<T> {
data: T[];
nextCursor: string | null;
}
export interface AnalysisResult {
messageId: string;
status: Exclude<AIStatus, "pending">;
flags: string[];
score: number;
analysis: string;
categories?: string[];
severity?: AISeverity;
confidence?: number;
recommendedAction?: AIRecommendedAction;
policyVersion?: string;
evidence?: string[];
}
export type MediaMode = "music" | "screen";
export type MediaSourceKind =
| "url"
| "local"
| "youtube"
| "spotify"
| "search";
export type MediaQueueItemStatus = "queued" | "playing" | "failed";
export interface MediaQueueItem {
id: string;
mode: MediaMode;
source: string;
title: string;
kind: MediaSourceKind;
requestedBy: string;
addedAt: number;
status: MediaQueueItemStatus;
}
export interface MediaState {
playing: boolean;
musicVolume: number;
current: MediaQueueItem | null;
queue: MediaQueueItem[];
}
export type ModerationWsEvent =
| { type: "ui_state"; state: unknown }
| { type: "user_state"; users: unknown[] }
| { type: "message_created"; data: MessageRecord }
| { type: "message_updated"; data: Partial<MessageRecord> & { id: string } }
| { type: "message_deleted"; data: { id: string; deleted_at: number } }
| { type: "message_analyzed"; data: MessageRecord }
| { type: "attachment_created"; data: AttachmentRecord }
| { type: "analysis_queue_status"; data: AnalysisQueueStatus }
| { type: "media_state"; state: MediaState }
| { type: "voice_recording_uploaded"; data: any };
export interface AnalysisQueueStatus {
queuedConversations: number;
activeRequests: number;
activeIndividualRequests: number;
individualInFlightCount: number;
individualCircuitBreakerActive: boolean;
lastError: string | null;
}
export type ReviewStatus = "pending" | "approved" | "rejected" | "escalated";
export interface MessageReview {
id: string;
message_id: string;
guild_id: string;
channel_id: string;
reviewer_id: string | null;
status: ReviewStatus;
notes: string | null;
created_at: number;
reviewed_at: number | null;
}
export type ModerationActionType =
| "delete_message"
| "mute_user"
| "warn_user"
| "kick_user"
| "ban_user";
export interface ModerationAction {
id: string;
message_id: string | null;
user_id: string | null;
guild_id: string;
action_type: ModerationActionType;
reason: string | null;
executed_by: string | null;
status: "pending" | "executed" | "failed";
error: string | null;
created_at: number;
executed_at: number | null;
}
export interface RetentionPolicy {
id: string;
guild_id: string;
channel_id: string | null;
retention_days: number;
apply_to_media: boolean;
apply_to_voice: boolean;
enabled: boolean;
created_at: number;
updated_at: number;
}
@@ -0,0 +1,61 @@
import { spawn } from "child_process";
export interface MuxFfmpegArgsOptions {
inputs: string[];
filter: string;
output: string;
codec: string;
audioFrequency?: number;
audioChannels?: number;
}
/**
* Builds ffmpeg argument array for muxing audio clips.
*/
export function buildMuxFfmpegArgs(options: MuxFfmpegArgsOptions): string[] {
const args: string[] = ["-y"];
for (const input of options.inputs) {
args.push("-i", input);
}
args.push("-filter_complex", options.filter);
args.push("-map", "[out]");
args.push("-codec:a", options.codec);
if (options.audioFrequency !== undefined) {
args.push("-ar", String(options.audioFrequency));
}
if (options.audioChannels !== undefined) {
args.push("-ac", String(options.audioChannels));
}
args.push(options.output);
return args;
}
/**
* Runs ffmpeg with the given arguments.
* Resolves on successful (code 0) exit, rejects on error or non-zero exit.
*/
export function runFfmpeg(args: string[]): Promise<void> {
return new Promise((resolve, reject) => {
const proc = spawn("ffmpeg", args, {
stdio: ["ignore", "inherit", "inherit"],
});
proc.on("close", (code) => {
if (code === 0) {
resolve();
} else {
reject(new Error(`ffmpeg exited with code ${code}`));
}
});
proc.on("error", (err) => {
reject(err);
});
});
}
@@ -0,0 +1,4 @@
export { OpusDecoder } from "./recorder/decoder.js";
export { SegmentManager } from "./recorder/segment.js";
export { startRecording, stopRecording } from "./recorder.js";
export { VoiceController } from "./voiceController.js";
@@ -0,0 +1,80 @@
import type { Readable } from "node:stream";
import type { StreamType } from "@discordjs/voice";
export type MediaMode = "music" | "screen";
export type MediaSourceKind =
| "url"
| "local"
| "youtube"
| "spotify"
| "search";
export type MediaQueueItemStatus = "queued" | "playing" | "failed";
export interface ResolvedMediaSource {
source: string;
title: string;
kind: MediaSourceKind;
}
export interface MediaQueueItem extends ResolvedMediaSource {
id: string;
mode: MediaMode;
requestedBy: string;
addedAt: number;
status: MediaQueueItemStatus;
}
export interface MediaState {
playing: boolean;
activeMode: MediaMode | null;
musicVolume: number;
current: MediaQueueItem | null;
queue: MediaQueueItem[];
}
export interface QueueMediaOptions {
mode?: MediaMode;
requestedBy?: string;
}
export interface MusicPlayback {
done: Promise<void>;
stop(): void;
}
export interface MusicPlayer {
play(source: ResolvedMediaSource): MusicPlayback;
}
export interface ScreenSharePlayback {
done: Promise<void>;
stop(): void;
}
export interface ScreenShareController {
isActive(): boolean;
start(source: string): Promise<ScreenSharePlayback>;
}
export type DiscordPlayerOwner = "none" | "browser-bridge" | "music" | "screen";
export interface DiscordPlayOptions {
inputType?: StreamType;
inlineVolume?: boolean;
volume?: number;
}
export interface DiscordAudioPlayer {
getOwner(): DiscordPlayerOwner;
isConnected(): boolean;
playStream(
stream: Readable,
owner: DiscordPlayerOwner,
options?: DiscordPlayOptions,
): void;
pause(owner?: DiscordPlayerOwner): void;
unpause(owner?: DiscordPlayerOwner): boolean;
stop(owner?: DiscordPlayerOwner): void;
getMusicVolume(): number;
setMusicVolume(volume: number): void;
}
@@ -0,0 +1 @@
export { buildMuxFfmpegArgs, runFfmpeg } from "./ffmpegProcess.js";
@@ -0,0 +1,41 @@
import { Transform, TransformCallback } from "node:stream";
/**
* Transform stream untuk memfilter audio packets yang terlalu kecil
* Packet yang terlalu kecil kemungkinan gagal didekripsi oleh Discord
*/
export class PacketFilter extends Transform {
private minPacketSize: number;
private filteredCount: number = 0;
private totalCount: number = 0;
constructor(minPacketSize: number = 10) {
super();
this.minPacketSize = minPacketSize;
}
_transform(
chunk: Buffer,
encoding: string,
callback: TransformCallback,
): void {
this.totalCount++;
// Filter packet yang terlalu kecil
if (chunk.length >= this.minPacketSize) {
this.push(chunk);
} else {
this.filteredCount++;
if (this.filteredCount % 10 === 0) {
// console.log(`[packet-filter] Filtered ${this.filteredCount} small packets (size < ${this.minPacketSize} bytes)`);
}
}
callback();
}
_flush(callback: TransformCallback): void {
// console.log(`[packet-filter] Total packets: ${this.totalCount}, filtered: ${this.filteredCount}, passed: ${this.totalCount - this.filteredCount}`);
callback();
}
}
@@ -0,0 +1,137 @@
import { Readable } from "node:stream";
import {
AudioPlayer,
AudioPlayerStatus,
type AudioResource,
createAudioPlayer,
createAudioResource,
StreamType,
VoiceConnection,
} from "@discordjs/voice";
import type {
DiscordPlayerOwner,
DiscordPlayOptions,
} from "./mediaTypes.js";
export class DiscordPlayer {
private player: AudioPlayer;
private connection: VoiceConnection | null = null;
private owner: DiscordPlayerOwner = "none";
private resource: AudioResource | null = null;
private musicVolume = 1;
constructor() {
this.player = createAudioPlayer();
this.player.on(AudioPlayerStatus.Playing, () => {
console.log("[player] Audio player is now playing!");
});
this.player.on("error", (error) => {
console.error(`[player] Error: ${error.message}`);
this.owner = "none";
this.resource = null;
});
}
public setConnection(connection: VoiceConnection) {
this.connection = connection;
this.connection.subscribe(this.player);
}
public getOwner(): DiscordPlayerOwner {
return this.owner;
}
public isConnected(): boolean {
return this.connection !== null;
}
public playStream(
stream: Readable,
owner: DiscordPlayerOwner,
options: DiscordPlayOptions = {},
) {
if (owner === "none") {
throw new Error("Discord audio player owner is required");
}
this.assertOwnerAvailable(owner);
const resource = createAudioResource(stream, {
inputType: options.inputType ?? StreamType.OggOpus,
inlineVolume: options.inlineVolume ?? false,
});
if (this.owner === owner) {
this.player.stop();
}
this.resource = resource;
this.owner = owner;
if (owner === "music") {
const nextVolume =
options.volume !== undefined
? this.normalizeVolume(options.volume)
: this.musicVolume;
this.musicVolume = nextVolume;
this.setResourceVolume(nextVolume);
}
this.player.play(resource);
this.unpause(owner);
this.connection?.subscribe(this.player);
}
public getStatus(): AudioPlayerStatus {
return this.player.state.status;
}
public pause(owner?: DiscordPlayerOwner) {
if (!this.canControl(owner)) return;
this.player.pause(true);
}
public unpause(owner?: DiscordPlayerOwner): boolean {
if (!this.canControl(owner)) return false;
return this.player.unpause();
}
public stop(owner?: DiscordPlayerOwner) {
if (!this.canControl(owner)) return;
this.player.stop();
this.owner = "none";
this.resource = null;
}
public getMusicVolume(): number {
return this.musicVolume;
}
public setMusicVolume(volume: number): void {
const nextVolume = this.normalizeVolume(volume);
this.musicVolume = nextVolume;
if (this.owner === "music") {
this.setResourceVolume(nextVolume);
}
}
private assertOwnerAvailable(owner: DiscordPlayerOwner): void {
if (this.owner !== "none" && this.owner !== owner) {
throw new Error(`Discord audio player is owned by ${this.owner}`);
}
}
private canControl(owner?: DiscordPlayerOwner): boolean {
return !owner || this.owner === "none" || this.owner === owner;
}
private normalizeVolume(volume: number): number {
if (!Number.isFinite(volume)) return this.musicVolume;
return Math.max(0, Math.min(1, volume));
}
private setResourceVolume(volume: number): void {
if (!this.resource?.volume) return;
this.resource.volume.setVolume(volume);
}
}
export const discordPlayer = new DiscordPlayer();
@@ -0,0 +1,328 @@
import fs from "node:fs";
import path from "node:path";
import {
type DiscordGatewayAdapterCreator,
EndBehaviorType,
entersState,
getVoiceConnection,
joinVoiceChannel,
type VoiceConnection,
VoiceConnectionStatus,
} from "@discordjs/voice";
import type { Client, VoiceChannel } from "discord.js-selfbot-v13";
import { config } from "../../shared/config/config.js";
import { createChildLogger } from "../../shared/logger/logger.js";
import { PacketFilter } from "./packetFilter.js";
import { subscribeToAudioStream } from "./recorder/audioStream.js";
import { OpusDecoder } from "./recorder/decoder.js";
import {
collectUserMetadata,
createSegmentMetadata,
} from "./recorder/metadata.js";
import { SegmentManager } from "./recorder/segment.js";
import {
createRecordingSession,
finalizeRecordingSession,
type RecordingSession,
} from "./recorder/sessionRecording.js";
import { uploadRecordingSegment } from "./recorder/uploader.js";
import { retryWithBackoff } from "../../shared/utils/retry.js";
import type { PcmBroadcaster } from "../message-capture/types.js";
const logger = createChildLogger("recorder");
const recordingsDir = config.RECORDINGS_DIR;
// Pastikan folder recordings ada
if (!fs.existsSync(recordingsDir)) {
fs.mkdirSync(recordingsDir, { recursive: true });
}
const activeSessions = new Map<string, RecordingSession>();
export function resetActiveSessions(): void {
activeSessions.clear();
}
function finalizeActiveRecordingSession(guildId: string): void {
const session = activeSessions.get(guildId);
if (!session) return;
activeSessions.delete(guildId);
finalizeRecordingSession(session).catch((error: unknown) => {
logger.error({ error }, "Failed to finalize recording session");
});
}
/**
* Join ke voice channel dan mulai merekam semua user yang bicara.
*/
export async function startRecording(
client: Client,
channel: VoiceChannel,
): Promise<VoiceConnection | null> {
const connection = joinVoiceChannel({
channelId: channel.id,
guildId: channel.guild.id,
adapterCreator: channel.guild
.voiceAdapterCreator as DiscordGatewayAdapterCreator,
selfDeaf: false,
selfMute: false,
debug: true,
});
logger.info({ channelName: channel.name }, "Joining voice channel");
connection.on("debug", (msg) => {
if (config.VERBOSE) {
logger.debug({ message: msg }, "Voice debug");
}
});
connection.on("error", (err) => {
logger.error({ error: err }, "Voice connection error");
});
// Tunggu sampai benar-benar terhubung dengan retry logic
try {
await retryWithBackoff(
() =>
entersState(
connection,
VoiceConnectionStatus.Ready,
config.VOICE_CONNECTION_TIMEOUT_MS,
),
{
retries: 3,
minTimeout: 1000,
maxTimeout: 5000,
logger,
},
);
logger.info("Connected to voice channel. Recording started");
// Create recording session after connection is ready
const sessionStartTime = Date.now();
const session = createRecordingSession({
guildId: channel.guild.id,
channelId: channel.id,
channelName: channel.name,
startTime: sessionStartTime,
recordingsDir,
});
activeSessions.set(channel.guild.id, session);
} catch (err) {
logger.error({ error: err }, "Failed to connect to voice channel");
connection.destroy();
return null;
}
const receiver = connection.receiver;
const broadcaster = globalThis as typeof globalThis & PcmBroadcaster;
// Dengarkan siapapun yang mulai bicara
receiver.speaking.on("start", async (userId) => {
if (userId === client.user?.id) return;
const userMetadata = await collectUserMetadata(client, userId, channel);
if (userMetadata.bot) return;
logger.debug(
{ userId, username: userMetadata.username },
"Voice activity detected",
);
// Notify webserver
broadcaster.updateActiveUser?.(userId, {
username: userMetadata.username,
avatar: userMetadata.avatarUrl,
speaking: true,
});
// Jangan record kalau sudah ada stream aktif untuk user ini
if (receiver.subscriptions.has(userId)) return;
const userDir = path.join(recordingsDir, userId);
if (!fs.existsSync(userDir)) {
fs.mkdirSync(userDir, { recursive: true });
}
try {
// --- OGG file recording with segment rotation ---
const packetFilterForOgg = new PacketFilter(
config.PACKET_FILTER_MIN_SIZE,
);
const audioStream = receiver.subscribe(userId, {
end: {
behavior: EndBehaviorType.AfterSilence,
duration: config.AUDIO_STREAM_SILENCE_DURATION_MS,
},
});
const oggPacketStream = audioStream.pipe(packetFilterForOgg);
const segmentManager = new SegmentManager(
userDir,
config.RECORDING_SEGMENT_MS,
);
// --- Web broadcast: prism decoder with safe restart and cooldown ---
const decoder = new OpusDecoder({
cooldownMs: config.DECODER_COOLDOWN_MS,
rotateMs: config.DECODER_ROTATE_MS,
onData: (pcm) => {
if (!broadcaster.broadcastPcmToWeb) return;
// Downsample 48kHz stereo → 24kHz mono (left channel, every 2nd sample)
const outBuf = Buffer.alloc(pcm.length / 4);
for (let i = 0; i < outBuf.length / 2; i++) {
outBuf.writeInt16LE(pcm.readInt16LE(i * 8), i * 2);
}
broadcaster.broadcastPcmToWeb(outBuf, userId);
},
});
const activeSession = activeSessions.get(channel.guild.id);
let currentSegment = segmentManager.open(oggPacketStream);
currentSegment.out.on("finish", () => {
if (config.VERBOSE) {
logger.info({ filename: currentSegment.filename }, "Segment saved");
}
const endTime = currentSegment.endTime ?? Date.now();
if (activeSession) {
activeSession.registerSegment({
user: userMetadata,
oggPath: currentSegment.filename,
jsonPath: currentSegment.jsonFilename,
startTime: currentSegment.startTime,
endTime,
});
}
const metadata = createSegmentMetadata(
userMetadata,
currentSegment,
activeSession?.sessionId ?? `${userId}-0`,
activeSession?.sessionId ?? `${channel.guild.id}-${channel.id}-0`,
activeSession?.startTime ?? 0,
config.RECORDING_SEGMENT_MS,
);
fs.writeFileSync(
currentSegment.jsonFilename,
JSON.stringify(metadata, null, 2),
);
if (config.VERBOSE) {
logger.info(
{ jsonFile: currentSegment.jsonFilename },
"Metadata saved",
);
}
// Trigger async voice segment upload
const segmentId = `${userId}-${currentSegment.startTime}`;
uploadRecordingSegment({
id: segmentId,
oggPath: currentSegment.filename,
userId: userMetadata.userId,
username: userMetadata.username,
avatarUrl: userMetadata.avatarUrl,
guildId: channel.guild.id,
channelId: channel.id,
channelName: channel.name,
}).catch((err: unknown) => {
const msg = err instanceof Error ? err.message : String(err);
logger.error(
{ segmentId, error: msg },
"Upload segment trigger failed",
);
});
});
currentSegment.out.on("error", (err: unknown) => {
const msg = err instanceof Error ? err.message : String(err);
logger.error({ userId, error: msg }, "File write error");
});
// Feed Opus packets one-by-one
subscribeToAudioStream(receiver, userId, {
onPacket: (chunk) => {
if (chunk.length < 8) return;
segmentManager.rotateIfNeeded(oggPacketStream);
if (!broadcaster.broadcastPcmToWeb) return;
decoder.rotateIfNeeded();
decoder.write(chunk);
},
onEnd: () => {
segmentManager.close(oggPacketStream);
decoder.destroy();
broadcaster.updateActiveUser?.(userId, {
username: userMetadata.username,
avatar: userMetadata.avatarUrl,
speaking: false,
});
},
onError: (error) => {
segmentManager.close(oggPacketStream);
decoder.destroy();
logger.error({ userId, error: error.message }, "Audio stream error");
},
});
packetFilterForOgg.on("error", (err) => {
segmentManager.close(oggPacketStream);
logger.error({ userId, error: err.message }, "PacketFilter error");
});
} catch (e) {
logger.error(
{ userId, error: e instanceof Error ? e.message : String(e) },
"Failed to create stream",
);
}
});
// Handle disconnect yang tidak disengaja
connection.on(VoiceConnectionStatus.Disconnected, async () => {
if (config.VERBOSE) {
logger.warn("Disconnected from voice channel. Reconnecting...");
}
try {
await Promise.race([
entersState(
connection,
VoiceConnectionStatus.Signalling,
config.RECONNECT_TIMEOUT_MS,
),
entersState(
connection,
VoiceConnectionStatus.Connecting,
config.RECONNECT_TIMEOUT_MS,
),
]);
// Berhasil reconnect
} catch {
logger.error("Could not reconnect. Destroying connection");
connection.destroy();
}
});
connection.on(VoiceConnectionStatus.Destroyed, () => {
finalizeActiveRecordingSession(channel.guild.id);
if (config.VERBOSE) {
logger.info("Voice connection destroyed");
}
});
return connection;
}
/**
* Hentikan recording dan disconnect dari voice channel.
*/
export function stopRecording(guildId: string): void {
const connection = getVoiceConnection(guildId);
if (connection) {
connection.destroy();
if (config.VERBOSE) {
logger.info("Recording stopped and disconnected");
}
} else {
logger.warn("No active connection to stop");
}
finalizeActiveRecordingSession(guildId);
}
@@ -0,0 +1,27 @@
import { EndBehaviorType, type VoiceReceiver } from "@discordjs/voice";
import { config } from "../../../shared/config/config.js";
export interface AudioStreamHandlers {
onPacket: (chunk: Buffer) => void;
onEnd: () => void;
onError: (error: Error) => void;
}
export function subscribeToAudioStream(
receiver: VoiceReceiver,
userId: string,
handlers: AudioStreamHandlers,
): NodeJS.ReadableStream {
const audioStream = receiver.subscribe(userId, {
end: {
behavior: EndBehaviorType.AfterSilence,
duration: config.AUDIO_STREAM_SILENCE_DURATION_MS,
},
});
audioStream.on("data", handlers.onPacket);
audioStream.on("end", handlers.onEnd);
audioStream.on("error", handlers.onError);
return audioStream;
}
@@ -0,0 +1,127 @@
import { createRequire } from "node:module";
import * as prism from "prism-media";
import { config } from "../../../shared/config/config.js";
const require = createRequire(import.meta.url);
interface OpusDecoderRuntime {
isBun: boolean;
canLoadNativeOpus: boolean;
}
export function shouldEnableDefaultOpusDecoder(
runtime: OpusDecoderRuntime,
): boolean {
return !runtime.isBun || runtime.canLoadNativeOpus;
}
function canLoadNativeOpus(): boolean {
try {
require("@discordjs/opus");
return true;
} catch {
return false;
}
}
const defaultDecoderEnabled = shouldEnableDefaultOpusDecoder({
isBun: Boolean(process.versions.bun),
canLoadNativeOpus: canLoadNativeOpus(),
});
export interface OpusDecoderOptions {
cooldownMs: number;
rotateMs: number;
createDecoder?: () => prism.opus.Decoder;
onData: (pcm: Buffer) => void;
}
export class OpusDecoder {
private decoder: prism.opus.Decoder | null = null;
private disabledUntil = 0;
private createdAt = 0;
private readonly cooldownMs: number;
private readonly rotateMs: number;
private readonly createDecoderFn: () => prism.opus.Decoder;
private readonly onData: (pcm: Buffer) => void;
constructor(options: OpusDecoderOptions) {
this.cooldownMs = options.cooldownMs;
this.rotateMs = options.rotateMs;
this.onData = options.onData;
this.createDecoderFn =
options.createDecoder ??
(() => {
if (!defaultDecoderEnabled) {
throw new Error(
"Native @discordjs/opus is unavailable under Bun; web PCM decode disabled to avoid opusscript aborts",
);
}
return new prism.opus.Decoder({
frameSize: config.OPUS_FRAME_SIZE,
channels: config.AUDIO_CHANNELS as 1 | 2,
rate: config.AUDIO_SAMPLE_RATE as
| 8000
| 12000
| 16000
| 24000
| 48000,
});
});
}
rotateIfNeeded(): void {
if (!this.decoder || this.rotateMs <= 0) return;
if (Date.now() - this.createdAt < this.rotateMs) return;
this.destroy();
this.ensureDecoder();
}
write(chunk: Buffer): void {
const decoder = this.ensureDecoder();
if (!decoder) return;
try {
decoder.write(chunk);
} catch (error) {
console.warn(
"[recorder] Opus decoder write failed, cooling down:",
error,
);
this.coolDown();
}
}
destroy(): void {
if (!this.decoder) return;
this.decoder.removeAllListeners();
this.decoder.destroy();
this.decoder = null;
this.createdAt = 0;
}
private ensureDecoder(): prism.opus.Decoder | null {
if (this.decoder) return this.decoder;
if (Date.now() < this.disabledUntil) return null;
try {
const decoder = this.createDecoderFn();
decoder.on("data", this.onData);
decoder.on("error", (error) => {
console.warn("[recorder] Opus decoder error, cooling down:", error);
this.coolDown();
});
this.decoder = decoder;
this.createdAt = Date.now();
return decoder;
} catch (error) {
console.warn("[recorder] Opus decoder init failed, cooling down:", error);
this.disabledUntil = Date.now() + this.cooldownMs;
return null;
}
}
private coolDown(): void {
this.disabledUntil = Date.now() + this.cooldownMs;
this.destroy();
}
}
@@ -0,0 +1,75 @@
import path from "node:path";
import type { Client, VoiceChannel } from "discord.js-selfbot-v13";
import { config } from "../../../shared/config/config.js";
import type { SegmentMetadata, SegmentState, UserMetadata } from "../../message-capture/types.js";
export async function collectUserMetadata(
client: Client,
userId: string,
channel: VoiceChannel,
): Promise<UserMetadata> {
const user =
client.users.cache.get(userId) ||
(await client.users.fetch(userId).catch(() => null));
const member =
channel.guild.members.cache.get(userId) ||
(await channel.guild.members.fetch(userId).catch(() => null));
const username = user?.username ?? "Unknown User";
const roles =
member?.roles.cache
.filter((role) => role.id !== channel.guild.id)
.sort((a, b) => b.position - a.position)
.map((role) => ({
id: role.id,
name: role.name,
position: role.position,
})) ?? [];
return {
userId,
username,
tag: user?.tag ?? "Unknown#0000",
displayName: member?.displayName ?? username,
avatarUrl:
user?.displayAvatarURL({
format: "png",
size: config.AVATAR_SIZE as
| 16
| 32
| 64
| 128
| 256
| 512
| 1024
| 2048
| 4096,
}) ?? "https://cdn.discordapp.com/embed/avatars/0.png",
bot: user?.bot ?? false,
roles,
highestRole: roles[0] ?? null,
joinedTimestamp: member?.joinedTimestamp ?? null,
};
}
export function createSegmentMetadata(
user: UserMetadata,
segment: SegmentState,
sessionId: string,
recordingSessionId: string,
sessionStartTime: number,
recordingSegmentMs: number,
): SegmentMetadata {
const endTime = segment.endTime ?? Date.now();
return {
...user,
sessionId,
recordingSessionId,
sessionStartTime,
segmentIndex: segment.index,
segmentMs: recordingSegmentMs,
startTime: segment.startTime,
endTime,
durationMs: endTime - segment.startTime,
filename: path.basename(segment.filename),
};
}
@@ -0,0 +1,87 @@
import fs from "node:fs";
import path from "node:path";
import * as prism from "prism-media";
import type { SegmentState } from "../../message-capture/types.js";
export function buildSegmentPaths(
userDir: string,
startTime: number,
): { filename: string; jsonFilename: string } {
return {
filename: path.join(userDir, `${startTime}.ogg`),
jsonFilename: path.join(userDir, `${startTime}.json`),
};
}
export function shouldRotateSegment(
startTime: number,
now: number,
recordingSegmentMs: number,
): boolean {
return recordingSegmentMs > 0 && now - startTime >= recordingSegmentMs;
}
export class SegmentManager {
private currentSegment: SegmentState | null = null;
private segmentIndex = 0;
constructor(
private readonly userDir: string,
private readonly recordingSegmentMs: number,
) {}
open(oggPacketStream: NodeJS.ReadableStream): SegmentState {
const index = this.segmentIndex++;
const startTime = Date.now();
const { filename, jsonFilename } = buildSegmentPaths(
this.userDir,
startTime,
);
const oggStream = new prism.opus.OggLogicalBitstream({
opusHead: new prism.opus.OpusHead({ channelCount: 2, sampleRate: 48000 }),
pageSizeControl: { maxPackets: 10 },
crc: true,
});
const out = fs.createWriteStream(filename);
oggPacketStream.pipe(oggStream).pipe(out);
this.currentSegment = {
index,
startTime,
endTime: null,
filename,
jsonFilename,
oggStream,
out,
};
return this.currentSegment;
}
close(oggPacketStream: NodeJS.ReadableStream): SegmentState | null {
if (!this.currentSegment) return null;
const segment = this.currentSegment;
segment.endTime = Date.now();
oggPacketStream.unpipe(segment.oggStream);
segment.oggStream.end();
this.currentSegment = null;
return segment;
}
rotateIfNeeded(oggPacketStream: NodeJS.ReadableStream): SegmentState | null {
if (!this.currentSegment) return null;
if (
!shouldRotateSegment(
this.currentSegment.startTime,
Date.now(),
this.recordingSegmentMs,
)
)
return null;
this.close(oggPacketStream);
return this.open(oggPacketStream);
}
getCurrent(): SegmentState | null {
return this.currentSegment;
}
}
@@ -0,0 +1,192 @@
import fs from "node:fs";
import path from "node:path";
import {
buildMuxFfmpegArgs,
runFfmpeg as defaultRunFfmpeg,
} from "../ffmpegProcess.js";
import type { UserMetadata } from "../../message-capture/types.js";
export type SessionRecordingStatus =
| "pending"
| "completed"
| "failed"
| "empty";
export interface RecordingSessionOptions {
guildId: string;
channelId: string;
channelName: string;
startTime: number;
recordingsDir: string;
}
export interface SessionSegmentInput {
user: UserMetadata;
oggPath: string;
jsonPath: string;
startTime: number;
endTime: number;
}
export interface SessionParticipant {
userId: string;
username: string;
tag: string;
displayName: string;
avatarUrl: string;
}
export interface SessionSegmentRef {
userId: string;
oggPath: string;
jsonPath: string;
startTime: number;
endTime: number;
durationMs: number;
offsetMs: number;
}
export interface SessionRecordingMetadata {
sessionId: string;
guildId: string;
channelId: string;
channelName: string;
startTime: number;
endTime: number;
durationMs: number;
status: SessionRecordingStatus;
outputFile: string | null;
participants: SessionParticipant[];
segments: SessionSegmentRef[];
error?: string;
}
export interface RecordingSession {
readonly sessionId: string;
readonly recordingsDir: string;
readonly startTime: number;
registerSegment(input: SessionSegmentInput): void;
snapshot(endTime: number): SessionRecordingMetadata;
}
export interface FinalizeRecordingSessionDependencies {
endTime?: number;
mkdir?: (dir: string) => void;
writeJson?: (file: string, metadata: SessionRecordingMetadata) => void;
runFfmpeg?: (args: string[]) => Promise<void>;
}
export function createRecordingSession(
options: RecordingSessionOptions,
): RecordingSession {
const sessionId = `${options.guildId}-${options.channelId}-${options.startTime}`;
const participants = new Map<string, SessionParticipant>();
const segments: SessionSegmentRef[] = [];
return {
sessionId,
recordingsDir: options.recordingsDir,
startTime: options.startTime,
registerSegment(input: SessionSegmentInput): void {
participants.set(input.user.userId, {
userId: input.user.userId,
username: input.user.username,
tag: input.user.tag,
displayName: input.user.displayName,
avatarUrl: input.user.avatarUrl,
});
segments.push({
userId: input.user.userId,
oggPath: input.oggPath,
jsonPath: input.jsonPath,
startTime: input.startTime,
endTime: input.endTime,
durationMs: input.endTime - input.startTime,
offsetMs: input.startTime - options.startTime,
});
},
snapshot(endTime: number): SessionRecordingMetadata {
return {
sessionId,
guildId: options.guildId,
channelId: options.channelId,
channelName: options.channelName,
startTime: options.startTime,
endTime,
durationMs: endTime - options.startTime,
status: "pending",
outputFile: null,
participants: Array.from(participants.values()),
segments: [...segments],
};
},
};
}
export function buildSessionMuxFilter(
segments: Array<{ startTime: number }>,
sessionStartTime: number,
): string {
const filters = segments.map((segment, index) => {
const delayMs = Math.max(0, segment.startTime - sessionStartTime);
return `[${index}:a]adelay=${delayMs}|${delayMs}[pad${index}]`;
});
const inputs = segments.map((_, index) => `[pad${index}]`).join("");
filters.push(
`${inputs}amix=inputs=${segments.length}:dropout_transition=0[out]`,
);
return filters.join(";");
}
export async function finalizeRecordingSession(
session: RecordingSession,
dependencies: FinalizeRecordingSessionDependencies = {},
): Promise<void> {
const endTime = dependencies.endTime ?? Date.now();
const sessionDir = path.join(
session.recordingsDir,
"sessions",
session.sessionId,
);
const outputFile = path.join(sessionDir, "full.ogg");
const metadataFile = path.join(sessionDir, "session.json");
const mkdir =
dependencies.mkdir ?? ((dir) => fs.mkdirSync(dir, { recursive: true }));
const writeJson =
dependencies.writeJson ??
((file, metadata) =>
fs.writeFileSync(file, JSON.stringify(metadata, null, 2)));
const runFfmpeg = dependencies.runFfmpeg ?? defaultRunFfmpeg;
mkdir(sessionDir);
const metadata = session.snapshot(endTime);
if (metadata.segments.length === 0) {
writeJson(metadataFile, { ...metadata, status: "empty" });
return;
}
try {
await runFfmpeg(
buildMuxFfmpegArgs({
inputs: metadata.segments.map((segment) => segment.oggPath),
filter: buildSessionMuxFilter(metadata.segments, metadata.startTime),
output: outputFile,
codec: "libopus",
}),
);
writeJson(metadataFile, {
...metadata,
status: "completed",
outputFile,
});
} catch (error) {
writeJson(metadataFile, {
...metadata,
status: "failed",
error: error instanceof Error ? error.message : String(error),
});
}
}
@@ -0,0 +1,115 @@
import fs from "node:fs";
import path from "node:path";
import { config } from "../../../shared/config/config.js";
import {
insertVoiceRecording,
updateVoiceRecordingAsFailed,
updateVoiceRecordingAsUploaded,
} from "../../../shared/database/voiceRecordingRepo.js";
import { createChildLogger } from "../../../shared/logger/logger.js";
import { uploadToTele } from "../teleUpload.js";
const logger = createChildLogger("recording-uploader");
/**
* Uploads a recorded segment OGG file to external server and registers in database
*/
export async function uploadRecordingSegment(input: {
id: string;
oggPath: string;
userId: string;
username: string;
avatarUrl: string | null;
guildId: string | null;
channelId: string | null;
channelName: string | null;
}): Promise<void> {
const {
id,
oggPath,
userId,
username,
avatarUrl,
guildId,
channelId,
channelName,
} = input;
const fileName = path.basename(oggPath);
try {
// 1. Get file size and insert initial pending state to DB
const stats = await fs.promises.stat(oggPath);
await insertVoiceRecording({
id,
user_id: userId,
username,
avatar_url: avatarUrl,
guild_id: guildId,
channel_id: channelId,
channel_name: channelName,
filename: fileName,
size_bytes: stats.size,
upload_status: "pending",
created_at: Date.now(),
});
// 2. Perform async upload with retry logic
const fileBuffer = await fs.promises.readFile(oggPath);
const uploadResult = await uploadToTele({
buffer: fileBuffer,
filename: fileName,
contentType: "audio/ogg",
uploadUrl: config.TELE_UPLOAD_URL,
retries: 3,
logger,
});
const downloadUrl = uploadResult.url;
// 3. Update DB to uploaded state
await updateVoiceRecordingAsUploaded(id, downloadUrl, Date.now());
logger.info({ id, downloadUrl }, "Recording segment uploaded successfully");
// 4. Broadcast via WebSocket if broadcaster exists globally
const broadcaster = (globalThis as any).moderationBroadcaster;
if (broadcaster) {
const payload = JSON.stringify({
type: "voice_recording_uploaded",
data: {
id,
user_id: userId,
username,
avatar_url: avatarUrl,
guild_id: guildId,
channel_id: channelId,
channel_name: channelName,
filename: fileName,
size_bytes: stats.size,
download_url: downloadUrl,
upload_status: "uploaded",
created_at: Date.now(),
uploaded_at: Date.now(),
},
timestamp: Date.now(),
});
broadcaster.getClients().forEach((client: any) => {
if (client.readyState === 1) {
try {
client.send(payload);
} catch (err) {
logger.warn(
{ err },
"Failed to send recording upload event to client",
);
}
}
});
}
} catch (error) {
const errorMsg = error instanceof Error ? error.message : String(error);
logger.error({ id, error: errorMsg }, "Failed to upload voice recording");
await updateVoiceRecordingAsFailed(id, errorMsg).catch((err: unknown) => {
logger.error({ id, err }, "Failed to write failure state to DB");
});
}
}
@@ -0,0 +1,85 @@
import type { CustomLogger } from "../../shared/logger/logger.js";
import { retryWithBackoff } from "../../shared/utils/retry.js";
export interface TeleUploadResponse {
download_url: string;
public_id?: string;
file_name?: string;
size_bytes?: number;
}
export interface TeleUploadResult {
url: string;
publicId?: string;
filename?: string;
sizeBytes?: number;
}
export function parseTeleUploadResponse(
response: TeleUploadResponse,
): TeleUploadResult {
if (!response.download_url) {
throw new Error("Missing download_url in response");
}
return {
url: response.download_url,
publicId: response.public_id,
filename: response.file_name,
sizeBytes: response.size_bytes,
};
}
export async function uploadToTele(input: {
buffer: Buffer;
filename: string;
contentType: string;
uploadUrl: string;
timeoutMs?: number;
retries: number;
logger: CustomLogger;
}): Promise<TeleUploadResult> {
const {
buffer,
filename,
contentType,
uploadUrl,
timeoutMs,
retries,
logger,
} = input;
const response = await retryWithBackoff(
async () => {
const fileBlob = new Blob([new Uint8Array(buffer)], {
type: contentType,
});
const formData = new FormData();
formData.append("file", fileBlob, filename);
formData.append("fileName", filename);
const res = await fetch(uploadUrl, {
method: "POST",
headers: {
accept: "application/json",
},
body: formData,
...(timeoutMs ? { signal: AbortSignal.timeout(timeoutMs) } : {}),
});
if (!res.ok) {
throw new Error(`Upload failed: Status ${res.status}`);
}
return (await res.json()) as TeleUploadResponse;
},
{
retries,
minTimeout: 1000,
maxTimeout: 5000,
logger,
},
);
return parseTeleUploadResponse(response);
}
@@ -0,0 +1,179 @@
import { getVoiceConnection, type VoiceConnection } from "@discordjs/voice";
import type { Client, Guild, VoiceChannel } from "discord.js-selfbot-v13";
import { AppError } from "../../shared/errors/errors.js";
import { createChildLogger } from "../../shared/logger/logger.js";
import { discordPlayer } from "./player.js";
import { startRecording, stopRecording } from "./recorder.js";
const logger = createChildLogger("voice-controller");
export interface VoiceStatus {
ready: boolean;
connected: boolean;
activeGuildId: string | null;
activeChannelId: string | null;
activeChannelName: string | null;
}
export interface GuildSummary {
id: string;
name: string;
}
export interface VoiceChannelSummary {
id: string;
name: string;
}
export interface ChannelSummary {
id: string;
name: string;
type: string;
}
export class VoiceController {
private activeGuildId: string | null = null;
private activeChannelId: string | null = null;
private activeChannelName: string | null = null;
private connecting = false;
constructor(private readonly client: Client) {}
getStatus(): VoiceStatus {
const connection = this.activeGuildId
? getVoiceConnection(this.activeGuildId)
: undefined;
return {
ready: this.client.isReady(),
connected: Boolean(connection),
activeGuildId: this.activeGuildId,
activeChannelId: this.activeChannelId,
activeChannelName: this.activeChannelName,
};
}
listGuilds(): GuildSummary[] {
return this.client.guilds.cache
.map((guild) => ({ id: guild.id, name: guild.name }))
.sort((a, b) => a.name.localeCompare(b.name));
}
async listVoiceChannels(guildId: string): Promise<VoiceChannelSummary[]> {
const guild = this.getGuild(guildId);
await guild.channels.fetch().catch(() => null);
return guild.channels.cache
.filter((channel) => channel.type === "GUILD_VOICE")
.map((channel) => ({ id: channel.id, name: channel.name }))
.sort((a, b) => a.name.localeCompare(b.name));
}
async listWatchableChannels(guildId: string): Promise<ChannelSummary[]> {
const guild = this.getGuild(guildId);
await guild.channels.fetch().catch(() => null);
return guild.channels.cache
.filter((channel) => channel.type === "GUILD_TEXT")
.map((channel) => ({
id: channel.id,
name: channel.name,
type: channel.type,
}))
.sort((a, b) => a.name.localeCompare(b.name));
}
async connect(guildId: string, channelId: string): Promise<VoiceStatus> {
if (!this.client.isReady()) {
throw new AppError(
"Discord client is not ready",
"CLIENT_NOT_READY",
409,
);
}
if (this.connecting) {
throw new AppError(
"Voice connection is already in progress",
"CONNECT_IN_PROGRESS",
409,
);
}
this.connecting = true;
try {
await this.disconnect();
const guild = this.getGuild(guildId);
const channel =
guild.channels.cache.get(channelId) ??
(await guild.channels.fetch(channelId).catch(() => null));
if (!channel) {
throw new AppError(
"Voice channel not found",
"VOICE_CHANNEL_NOT_FOUND",
404,
);
}
if (channel.type !== "GUILD_VOICE") {
throw new AppError(
"Selected channel is not a voice channel",
"INVALID_CHANNEL_TYPE",
400,
);
}
const connection = await startRecording(
this.client,
channel as VoiceChannel,
);
if (!connection) {
throw new AppError(
"Failed to connect to voice channel",
"VOICE_CONNECT_FAILED",
500,
);
}
discordPlayer.setConnection(connection as VoiceConnection);
this.activeGuildId = guildId;
this.activeChannelId = channelId;
this.activeChannelName = channel.name;
logger.info(
{ guildId, channelId, channelName: channel.name },
"Voice connected",
);
return this.getStatus();
} finally {
this.connecting = false;
}
}
async disconnect(): Promise<VoiceStatus> {
if (this.activeGuildId) {
stopRecording(this.activeGuildId);
}
discordPlayer.stop();
this.activeGuildId = null;
this.activeChannelId = null;
this.activeChannelName = null;
return this.getStatus();
}
private getGuild(guildId: string): Guild {
const guild = this.client.guilds.cache.get(guildId);
if (!guild) {
throw new AppError("Guild not found", "GUILD_NOT_FOUND", 404);
}
return guild;
}
}