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 +1,250 @@
import "dotenv/config";
import { z } from "zod";
import { ConfigError } from "../errors/errors.js";
const configSchema = z
.object({
DISCORD_TOKEN: z
.string()
.min(1, "DISCORD_TOKEN is required")
.transform((value) => value.replace(/^("|')|(?:("|'))$/g, "")),
VOICE_CHANNEL_ID: z.string().min(1).optional(),
GUILD_ID: z.string().min(1).optional(),
TEXT_GUILD_ID: z.string().min(1).optional(),
TEXT_CHANNEL_ID: z.string().min(1).optional(),
VOICE_GUILD_ID: z.string().min(1).optional(),
VERBOSE: z
.string()
.optional()
.transform((v) => v === "true")
.default(false),
RECORDINGS_DIR: z.string().default("./recordings"),
RECORDING_SEGMENT_MS: z.coerce.number().positive().default(5000),
DECODER_ROTATE_MS: z.coerce.number().positive().default(5000),
DECODER_COOLDOWN_MS: z.coerce.number().positive().default(30000),
WEBSERVER_PORT: z.coerce.number().positive().default(3000),
VOICE_CONNECTION_TIMEOUT_MS: z.coerce.number().positive().default(15000),
RECONNECT_TIMEOUT_MS: z.coerce.number().positive().default(5000),
AUDIO_STREAM_SILENCE_DURATION_MS: z.coerce
.number()
.positive()
.default(3000),
PACKET_FILTER_MIN_SIZE: z.coerce.number().positive().default(8),
OPUS_FRAME_SIZE: z.coerce.number().positive().default(960),
AUDIO_SAMPLE_RATE: z.coerce.number().positive().default(48000),
AUDIO_CHANNELS: z.coerce.number().positive().default(2),
AVATAR_SIZE: z.coerce.number().positive().default(64),
LOG_LEVEL: z
.enum(["error", "warn", "info", "http", "verbose", "debug", "silly"])
.default("info"),
NODE_ENV: z
.enum(["development", "production", "test"])
.default("development"),
MONITOR_GUILD_ID: z.string().min(1).optional(),
TELE_UPLOAD_URL: z
.string()
.url()
.default("https://upload.asepharyana.tech/api/upload"),
ATTACHMENT_UPLOAD_TIMEOUT_MS: z.coerce.number().positive().default(30000),
ATTACHMENT_MAX_SIZE_MB: z.coerce.number().positive().default(100),
ATTACHMENT_RETRY_ATTEMPTS: z.coerce.number().positive().default(3),
BACKLOG_SYNC_HOURS: z.coerce.number().positive().default(24),
BACKLOG_SYNC_BATCH_SIZE: z.coerce
.number()
.int()
.positive()
.max(100)
.default(100),
AI_ANALYSIS_ENABLED: z
.string()
.optional()
.transform((v) => v === "true")
.default(false),
OPENAI_MODERATION_API_KEY: z.string().optional(),
OPENAI_MODERATION_BASE_URL: z
.string()
.url()
.default("https://api.openai.com/v1"),
OPENAI_MODERATION_MODEL: z.string().default("omni-moderation-latest"),
AI_LLM_API_KEY: z.string().optional(),
AI_LLM_BASE_URL: z
.string()
.url()
.default("https://9router.asepharyana.my.id/v1"),
/** Model used for text-only moderation (messages, badword analysis). */
AI_LLM_MODEL: z.string().default("text"),
/** Model used for image/video moderation (vision-capable model). */
AI_LLM_VISION_MODEL: z.string().optional(),
/** Max concurrent LLM API calls (default: 5). */
AI_LLM_MAX_CONCURRENT: z.coerce.number().int().positive().default(5),
/** Maximum image dimension in pixels before resize for vision API (default: 1024). */
AI_LLM_IMAGE_MAX_DIMENSION: z.coerce
.number()
.int()
.positive()
.default(1024),
/** Maximum messages per text-only moderation batch (default: 20). */
AI_LLM_TEXT_BATCH_SIZE: z.coerce.number().int().positive().default(20),
/** Timeout in ms for individual media analysis calls (default: 60000). */
AI_LLM_MEDIA_ANALYSIS_TIMEOUT_MS: z.coerce
.number()
.int()
.positive()
.default(60000),
AI_ANALYSIS_DEBOUNCE_MS: z.coerce.number().positive().default(500),
AI_ANALYSIS_RECOVERY_INTERVAL_MS: z.coerce
.number()
.positive()
.default(15000),
AI_ANALYSIS_ERROR_COOLDOWN_MS: z.coerce.number().positive().default(30000),
/** Max messages fetched per conversation batch (token budget is the real constraint). */
AI_ANALYSIS_MAX_BATCH_SIZE: z.coerce.number().int().positive().default(200),
AI_ANALYSIS_MAX_CONTEXT_TOKENS: z.coerce.number().positive().default(8000),
/** Token budget for target messages specifically (separate from context window). */
AI_ANALYSIS_MAX_TARGET_TOKENS: z.coerce.number().positive().default(4000),
AI_ANALYSIS_CONTEXT_MESSAGE_LIMIT: z.coerce
.number()
.int()
.positive()
.default(20),
/**
* How long a conversation is considered locked while being processed.
* Must exceed (LLM timeout × max retries) + network overhead.
* LLM client timeout=30s, retries=3 → minimum safe value ≈ 100s.
*/
AI_ANALYSIS_PROCESSING_TIMEOUT_MS: z.coerce
.number()
.positive()
.default(120000),
/** Max concurrent individual-fallback LLM calls (effectively unlimited). */
AI_ANALYSIS_INDIVIDUAL_MAX_CONCURRENT: z.coerce
.number()
.int()
.positive()
.default(1000),
/**
* How many consecutive individual-fallback errors trigger the individual
* circuit breaker (separate from the batch circuit breaker).
*/
AI_ANALYSIS_INDIVIDUAL_CB_THRESHOLD: z.coerce
.number()
.int()
.positive()
.default(50),
/** NVIDIA Nemotron-3 Content Safety API key for badword detection. */
NVIDIA_NEMOTRON_API_KEY: z.string().optional(),
/** NVIDIA Nemotron model identifier. */
NVIDIA_NEMOTRON_MODEL: z
.string()
.default("nvidia/nemotron-3-content-safety"),
/** NVIDIA Nemotron API base URL. */
NVIDIA_NEMOTRON_BASE_URL: z
.string()
.url()
.default("https://integrate.api.nvidia.com/v1/chat/completions"),
/** Groq API key for Llama Prompt Guard moderation fallback. */
GROQ_API_KEY: z.string().optional(),
/** Groq moderation model identifier. */
GROQ_MODERATION_MODEL: z
.string()
.default("meta-llama/llama-prompt-guard-2-86m"),
/** Groq API base URL. */
GROQ_MODERATION_BASE_URL: z
.string()
.url()
.default("https://api.groq.com/openai/v1/chat/completions"),
AUTO_DELETE_FLAGGED_ENABLED: z
.string()
.optional()
.transform((v) => v === "true")
.default(true),
AUTO_DELETE_FLAGGED_DELAY_MS: z.coerce.number().min(0).default(0),
AUTO_DELETE_FLAGGED_DRY_RUN: z
.string()
.optional()
.transform((v) => v === "true")
.default(false),
AUTO_DELETE_MIN_CONFIDENCE: z.coerce.number().min(0).max(1).default(0.5),
AUTO_DELETE_ALLOWED_SEVERITIES: z
.string()
.default("critical,high,medium,low"),
AUTO_DELETE_ALLOWED_CATEGORIES: z.string().default(""),
AUTO_DELETE_EXCLUDED_CHANNEL_IDS: z.string().default(""),
AUTO_DELETE_EXCLUDED_USER_IDS: z.string().default(""),
STICKER_CACHE_DIR: z.string().default("./sticker-cache"),
STICKER_CACHE_MAX_SIZE_MB: z.coerce.number().int().positive().default(100),
RETENTION_MESSAGES_DAYS: z.coerce.number().int().min(0).default(0),
RETENTION_ATTACHMENTS_DAYS: z.coerce.number().int().min(0).default(0),
RETENTION_VOICE_DAYS: z.coerce.number().int().min(0).default(0),
RETENTION_CLEANUP_INTERVAL_MS: z.coerce
.number()
.positive()
.default(24 * 60 * 60 * 1000),
RETENTION_DRY_RUN: z
.string()
.optional()
.transform((v) => v === "true")
.default(true),
AUTO_MIGRATE_ON_STARTUP: z
.string()
.optional()
.transform((v) => v === "true")
.default(true),
DATABASE_URL: z.string().optional(),
POSTGRES_HOST: z.string().default("localhost"),
POSTGRES_PORT: z.coerce.number().int().positive().default(5432),
POSTGRES_USER: z.string().optional(),
POSTGRES_PASSWORD: z.string().optional(),
POSTGRES_DB: z.string().optional(),
POSTGRES_POOL_MIN: z.coerce.number().int().positive().default(2),
POSTGRES_POOL_MAX: z.coerce.number().int().positive().default(10),
ADMIN_PASSWORD: z.string().default("admin123"),
REDIS_URL: z.string().min(1).default("redis://localhost:6379"),
})
.superRefine((value, ctx) => {
if (!value.AI_ANALYSIS_ENABLED) {
// Continue to database validationa
} else if (!value.AI_LLM_API_KEY) {
ctx.addIssue({
code: z.ZodIssueCode.custom,
path: ["AI_LLM_API_KEY"],
message: "AI_LLM_API_KEY is required when AI_ANALYSIS_ENABLED=true",
});
}
// Validate PostgreSQL configuration
if (!value.DATABASE_URL && !value.POSTGRES_HOST) {
ctx.addIssue({
code: z.ZodIssueCode.custom,
path: ["DATABASE_URL"],
message: "Either DATABASE_URL or POSTGRES_HOST must be provided",
});
}
});
export type AppConfig = z.infer<typeof configSchema> & {
EFFECTIVE_TEXT_GUILD_ID?: string;
EFFECTIVE_VOICE_GUILD_ID?: string;
};
export function loadConfig(env: NodeJS.ProcessEnv = process.env): AppConfig {
try {
const parsed = configSchema.parse(env);
return {
...parsed,
// AI text capture and analytics are pinned to the monitor guild.
EFFECTIVE_TEXT_GUILD_ID: parsed.MONITOR_GUILD_ID,
EFFECTIVE_VOICE_GUILD_ID: parsed.VOICE_GUILD_ID ?? parsed.GUILD_ID,
};
} catch (error) {
if (error instanceof z.ZodError) {
const messages = error.issues
.map((e) => `${e.path.join(".")}: ${e.message}`)
.join("\n");
throw new ConfigError(`Configuration validation failed:\n${messages}`);
}
throw error;
}
}
export const config = loadConfig();
@@ -0,0 +1,129 @@
import { drizzle as drizzlePostgres } from "drizzle-orm/node-postgres";
import type { PoolClient } from "pg";
import { Pool } from "pg";
import { config } from "../../shared/config/config.js";
import { createChildLogger } from "../../shared/logger/logger.js";
import * as schema from "./schema.js";
const logger = createChildLogger("drizzle");
let db: ReturnType<typeof drizzlePostgres> | null = null;
let rawPool: Pool | null = null;
/**
* Initialize the PostgreSQL database connection.
*/
export async function initializeDatabase() {
if (db !== null) {
return db;
}
let pool: Pool;
if (config.DATABASE_URL) {
pool = new Pool({
connectionString: config.DATABASE_URL,
min: config.POSTGRES_POOL_MIN,
max: config.POSTGRES_POOL_MAX,
});
} else {
pool = new Pool({
host: config.POSTGRES_HOST,
port: config.POSTGRES_PORT,
user: config.POSTGRES_USER,
password: config.POSTGRES_PASSWORD,
database: config.POSTGRES_DB,
min: config.POSTGRES_POOL_MIN,
max: config.POSTGRES_POOL_MAX,
});
}
rawPool = pool;
db = drizzlePostgres(pool, { schema });
try {
(db as { run?: (sql: string) => Promise<unknown> }).run = (sql: string) =>
pool.query(sql);
} catch {
// ignore
}
logger.info("PostgreSQL database initialized");
return db;
}
/**
* Get the initialized database instance.
* Throws if database has not been initialized.
*/
export function getDatabase() {
if (db === null) {
throw new Error(
"Database not initialized. Call initializeDatabase() first.",
);
}
return db;
}
function convertPlaceholdersForPostgres(sql: string) {
let i = 0;
return sql.replace(/\?/g, () => `$${++i}`);
}
export async function executeAll(sql: string, params?: unknown[]) {
if (!rawPool) {
throw new Error(
"Database not initialized. Call initializeDatabase() first.",
);
}
const query = convertPlaceholdersForPostgres(sql);
const result = await rawPool.query(query, params || []);
return result.rows;
}
export async function executeGet(sql: string, params?: unknown[]) {
if (!rawPool) {
throw new Error(
"Database not initialized. Call initializeDatabase() first.",
);
}
const query = convertPlaceholdersForPostgres(sql);
const result = await rawPool.query(query, params || []);
return result.rows[0] ?? null;
}
/**
* Run a function with a dedicated PostgreSQL client from the shared pool.
* Use this for session-scoped operations such as advisory locks.
*/
export async function withDatabaseClient<T>(
callback: (client: PoolClient) => Promise<T>,
): Promise<T> {
if (!rawPool) {
throw new Error(
"Database not initialized. Call initializeDatabase() first.",
);
}
const client = await rawPool.connect();
try {
return await callback(client);
} finally {
client.release();
}
}
/**
* Close the PostgreSQL connection pool.
*/
export async function closeDatabase() {
if (rawPool !== null) {
await rawPool.end();
}
rawPool = null;
db = null;
logger.info("PostgreSQL database closed");
}
@@ -0,0 +1,54 @@
import "dotenv/config";
import { drizzle as drizzlePostgres } from "drizzle-orm/node-postgres";
import { migrate as migratePostgres } from "drizzle-orm/node-postgres/migrator";
import { config } from "../../shared/config/config.js";
import { createChildLogger } from "../../shared/logger/logger.js";
import {
closeDatabase,
initializeDatabase,
withDatabaseClient,
} from "./drizzle.js";
import * as schema from "./schema.js";
const logger = createChildLogger("migrate");
const MIGRATION_LOCK_KEY_1 = 2026;
const MIGRATION_LOCK_KEY_2 = 531;
export async function runMigrations(): Promise<void> {
try {
logger.info("Starting PostgreSQL migrations");
await initializeDatabase();
try {
await withDatabaseClient(async (client) => {
const db = drizzlePostgres(client, { schema });
await client.query("SELECT pg_advisory_lock($1, $2)", [
MIGRATION_LOCK_KEY_1,
MIGRATION_LOCK_KEY_2,
]);
try {
await migratePostgres(db, {
migrationsFolder: "./drizzle/migrations",
});
} finally {
await client.query("SELECT pg_advisory_unlock($1, $2)", [
MIGRATION_LOCK_KEY_1,
MIGRATION_LOCK_KEY_2,
]);
}
});
} finally {
await closeDatabase();
}
logger.info("PostgreSQL migrations completed successfully");
} catch (error) {
logger.error(
{ error: error instanceof Error ? error.message : String(error) },
"Migration failed",
);
throw error;
}
}
@@ -0,0 +1,14 @@
import { createChildLogger } from "../../shared/logger/logger.js";
import { runMigrations } from "./migrate.js";
const logger = createChildLogger("migrate-cli");
runMigrations()
.then(() => {
logger.info("Migrations completed");
process.exit(0);
})
.catch((error: unknown) => {
logger.error({ error }, "Migration failed");
process.exit(1);
});
@@ -0,0 +1,10 @@
-- Migration: 001_drop_unused_ai_columns.sql
-- Date: 2026-05-30
-- Description: Drop columns that are written but never read from messages table
-- - ai_moderation_raw: raw LLM response, never consumed
-- - ai_policy_version: hardcoded string, never used for decisions
-- - ai_evidence: JSON evidence array, never read after write
ALTER TABLE messages DROP COLUMN IF EXISTS ai_moderation_raw;
ALTER TABLE messages DROP COLUMN IF EXISTS ai_policy_version;
ALTER TABLE messages DROP COLUMN IF EXISTS ai_evidence;
@@ -0,0 +1,433 @@
import {
bigint as pgBigint,
boolean as pgBoolean,
foreignKey as pgForeignKey,
index as pgIndex,
integer as pgInteger,
real as pgReal,
pgTable,
text as pgText,
} from "drizzle-orm/pg-core";
// PostgreSQL Schema
// ==================
/**
* Muxer Jobs Table (PostgreSQL)
* Tracks audio post-processing jobs with status and retry logic
*/
export const pgMuxerJobsTable = pgTable(
"muxer_jobs",
{
id: pgText("id").primaryKey(),
data: pgText("data").notNull(),
status: pgText("status", {
enum: ["pending", "processing", "completed", "failed"],
})
.notNull()
.default("pending"),
attempts: pgInteger("attempts").notNull().default(0),
maxAttempts: pgInteger("maxAttempts").notNull().default(3),
createdAt: pgBigint("createdAt", { mode: "number" }).notNull(),
updatedAt: pgBigint("updatedAt", { mode: "number" }).notNull(),
error: pgText("error"),
},
(table) => ({
statusIdx: pgIndex("idx_muxer_jobs_status").on(table.status),
createdAtIdx: pgIndex("idx_muxer_jobs_createdAt").on(table.createdAt),
}),
);
/**
* Messages Table (PostgreSQL)
* Stores text messages with AI moderation analysis
*/
export const pgMessagesTable = pgTable(
"messages",
{
id: pgText("id").primaryKey(),
guild_id: pgText("guild_id").notNull(),
channel_id: pgText("channel_id").notNull(),
thread_id: pgText("thread_id"),
user_id: pgText("user_id").notNull(),
username: pgText("username").notNull(),
avatar_url: pgText("avatar_url"),
content: pgText("content").notNull(),
edited_content: pgText("edited_content"),
created_at: pgBigint("created_at", { mode: "number" }).notNull(),
edited_at: pgBigint("edited_at", { mode: "number" }),
deleted_at: pgBigint("deleted_at", { mode: "number" }),
type: pgText("type", { enum: ["text", "edited", "deleted"] })
.notNull()
.default("text"),
metadata: pgText("metadata"),
ai_status: pgText("ai_status", {
enum: ["pending", "clean", "warn", "flagged", "error"],
})
.notNull()
.default("pending"),
ai_moderation_flags: pgText("ai_moderation_flags"),
ai_moderation_score: pgReal("ai_moderation_score"),
ai_analysis: pgText("ai_analysis"),
ai_categories: pgText("ai_categories"),
ai_severity: pgText("ai_severity", {
enum: ["none", "low", "medium", "high", "critical"],
}),
ai_confidence: pgReal("ai_confidence"),
ai_recommended_action: pgText("ai_recommended_action", {
enum: ["none", "monitor", "warn", "review", "delete", "escalate"],
}),
ai_analyzed_at: pgBigint("ai_analyzed_at", { mode: "number" }),
ai_error: pgText("ai_error"),
},
(table) => ({
channelIdx: pgIndex("idx_messages_channel").on(table.channel_id),
userIdx: pgIndex("idx_messages_user").on(table.user_id),
createdIdx: pgIndex("idx_messages_created").on(table.created_at),
threadIdx: pgIndex("idx_messages_thread").on(table.thread_id),
channelCreatedIdx: pgIndex("idx_messages_channel_created").on(
table.channel_id,
table.created_at,
table.id,
),
threadCreatedIdx: pgIndex("idx_messages_thread_created").on(
table.thread_id,
table.created_at,
table.id,
),
aiStatusCreatedIdx: pgIndex("idx_messages_ai_status_created").on(
table.ai_status,
table.created_at,
table.id,
),
guildAiStatusCreatedIdx: pgIndex("idx_messages_guild_ai_status_created").on(
table.guild_id,
table.ai_status,
table.created_at,
table.id,
),
guildCreatedDeletedIdx: pgIndex("idx_messages_guild_created_deleted").on(
table.guild_id,
table.created_at,
table.deleted_at,
table.id,
),
channelAiStatusCreatedIdx: pgIndex(
"idx_messages_channel_ai_status_created",
).on(table.channel_id, table.ai_status, table.created_at, table.id),
threadAiStatusCreatedIdx: pgIndex(
"idx_messages_thread_ai_status_created",
).on(table.thread_id, table.ai_status, table.created_at, table.id),
}),
);
/**
* Attachments Table (PostgreSQL)
* Stores attachment metadata with upload status tracking
*/
export const pgAttachmentsTable = pgTable(
"attachments",
{
id: pgText("id").primaryKey(),
message_id: pgText("message_id").notNull(),
guild_id: pgText("guild_id").notNull(),
channel_id: pgText("channel_id").notNull(),
thread_id: pgText("thread_id"),
user_id: pgText("user_id").notNull(),
filename: pgText("filename").notNull(),
size: pgInteger("size").notNull(),
type: pgText("type").notNull(),
discord_url: pgText("discord_url").notNull(),
uploaded_url: pgText("uploaded_url"),
upload_status: pgText("upload_status", {
enum: ["pending", "uploaded", "failed"],
})
.notNull()
.default("pending"),
upload_error: pgText("upload_error"),
created_at: pgBigint("created_at", { mode: "number" }).notNull(),
uploaded_at: pgBigint("uploaded_at", { mode: "number" }),
},
(table) => ({
channelIdx: pgIndex("idx_attachments_channel").on(table.channel_id),
messageIdx: pgIndex("idx_attachments_message").on(table.message_id),
statusIdx: pgIndex("idx_attachments_status").on(table.upload_status),
channelCreatedIdx: pgIndex("idx_attachments_channel_created").on(
table.channel_id,
table.created_at,
table.id,
),
threadCreatedIdx: pgIndex("idx_attachments_thread_created").on(
table.thread_id,
table.created_at,
table.id,
),
messageFk: pgForeignKey({
columns: [table.message_id],
foreignColumns: [pgMessagesTable.id],
name: "fk_attachments_message_id",
}).onDelete("cascade"),
}),
);
/**
* UI State Table (PostgreSQL)
* Stores persistent UI state (e.g., selected channel, filter preferences)
*/
export const pgUIStateTable = pgTable("ui_state", {
key: pgText("key").primaryKey(),
value: pgText("value").notNull(),
updated_at: pgBigint("updated_at", { mode: "number" }).notNull(),
});
/**
* AI Analysis Runs Table (PostgreSQL)
* Tracks AI analysis batch runs for conversation-level moderation
*/
export const pgAIAnalysisRunsTable = pgTable(
"ai_analysis_runs",
{
id: pgText("id").primaryKey(),
conversation_key: pgText("conversation_key").notNull(),
target_message_ids: pgText("target_message_ids").notNull(), // JSON array
model: pgText("model").notNull(),
request_tokens_estimate: pgInteger("request_tokens_estimate"),
response_raw: pgText("response_raw"),
status: pgText("status", {
enum: ["pending", "processing", "completed", "failed"],
})
.notNull()
.default("pending"),
error: pgText("error"),
created_at: pgBigint("created_at", { mode: "number" }).notNull(),
completed_at: pgBigint("completed_at", { mode: "number" }),
},
(table) => ({
conversationKeyIdx: pgIndex("idx_ai_analysis_runs_conversation_key").on(
table.conversation_key,
),
statusIdx: pgIndex("idx_ai_analysis_runs_status").on(table.status),
createdAtIdx: pgIndex("idx_ai_analysis_runs_created_at").on(
table.created_at,
),
}),
);
/**
* Voice Recordings Table (PostgreSQL)
* Stores voice recording segment metadata and upload status
*/
export const pgVoiceRecordingsTable = pgTable(
"voice_recordings",
{
id: pgText("id").primaryKey(),
user_id: pgText("user_id").notNull(),
username: pgText("username").notNull(),
avatar_url: pgText("avatar_url"),
guild_id: pgText("guild_id"),
channel_id: pgText("channel_id"),
channel_name: pgText("channel_name"),
filename: pgText("filename").notNull(),
size_bytes: pgInteger("size_bytes").notNull(),
download_url: pgText("download_url"),
upload_status: pgText("upload_status", {
enum: ["pending", "uploaded", "failed"],
})
.notNull()
.default("pending"),
upload_error: pgText("upload_error"),
created_at: pgBigint("created_at", { mode: "number" }).notNull(),
uploaded_at: pgBigint("uploaded_at", { mode: "number" }),
},
(table) => ({
userIdIdx: pgIndex("idx_voice_recordings_user_id").on(table.user_id),
channelIdIdx: pgIndex("idx_voice_recordings_channel_id").on(
table.channel_id,
),
createdIdx: pgIndex("idx_voice_recordings_created_at").on(table.created_at),
}),
);
/**
* Message Reviews Table (PostgreSQL)
* Tracks manual reviews of messages flagged by AI moderation
*/
export const pgMessageReviewsTable = pgTable(
"message_reviews",
{
id: pgText("id").primaryKey(),
message_id: pgText("message_id").notNull(),
guild_id: pgText("guild_id").notNull(),
channel_id: pgText("channel_id").notNull(),
reviewer_id: pgText("reviewer_id"),
status: pgText("status", {
enum: ["pending", "approved", "rejected", "escalated"],
})
.notNull()
.default("pending"),
notes: pgText("notes"),
created_at: pgBigint("created_at", { mode: "number" }).notNull(),
reviewed_at: pgBigint("reviewed_at", { mode: "number" }),
},
(table) => ({
messageIdIdx: pgIndex("idx_message_reviews_message_id").on(
table.message_id,
),
statusIdx: pgIndex("idx_message_reviews_status").on(table.status),
createdAtIdx: pgIndex("idx_message_reviews_created_at").on(
table.created_at,
),
guildStatusIdx: pgIndex("idx_message_reviews_guild_status").on(
table.guild_id,
table.status,
table.created_at,
),
}),
);
/**
* Moderation Actions Table (PostgreSQL)
* Tracks actions taken on messages (delete, mute, etc.)
*/
export const pgModerationActionsTable = pgTable(
"moderation_actions",
{
id: pgText("id").primaryKey(),
message_id: pgText("message_id"),
user_id: pgText("user_id"),
guild_id: pgText("guild_id").notNull(),
action_type: pgText("action_type", {
enum: [
"delete_message",
"mute_user",
"warn_user",
"kick_user",
"ban_user",
],
}).notNull(),
reason: pgText("reason"),
executed_by: pgText("executed_by"),
status: pgText("status", {
enum: ["pending", "executed", "failed"],
})
.notNull()
.default("pending"),
error: pgText("error"),
created_at: pgBigint("created_at", { mode: "number" }).notNull(),
executed_at: pgBigint("executed_at", { mode: "number" }),
},
(table) => ({
messageIdIdx: pgIndex("idx_moderation_actions_message_id").on(
table.message_id,
),
userIdIdx: pgIndex("idx_moderation_actions_user_id").on(table.user_id),
statusIdx: pgIndex("idx_moderation_actions_status").on(table.status),
guildStatusIdx: pgIndex("idx_moderation_actions_guild_status").on(
table.guild_id,
table.status,
table.created_at,
),
}),
);
/**
* Retention Policies Table (PostgreSQL)
* Defines data retention rules per guild/channel
*/
export const pgRetentionPoliciesTable = pgTable(
"retention_policies",
{
id: pgText("id").primaryKey(),
guild_id: pgText("guild_id").notNull(),
channel_id: pgText("channel_id"),
retention_days: pgInteger("retention_days").notNull().default(90),
apply_to_media: pgBoolean("apply_to_media").notNull().default(true),
apply_to_voice: pgBoolean("apply_to_voice").notNull().default(true),
enabled: pgBoolean("enabled").notNull().default(true),
created_at: pgBigint("created_at", { mode: "number" }).notNull(),
updated_at: pgBigint("updated_at", { mode: "number" }).notNull(),
},
(table) => ({
guildIdIdx: pgIndex("idx_retention_policies_guild_id").on(table.guild_id),
enabledIdx: pgIndex("idx_retention_policies_enabled").on(table.enabled),
}),
);
/**
* Text Analysis Cache Table (PostgreSQL)
* Caches per-normalized-text moderation analysis results so repeated
* phrases reuse previously computed API / fallback results instead of
* re-calling expensive LLM or external moderation APIs.
*
* Uses the FULL normalized text (not per-word) because context matters:
* "kau" alone is clean, but "awas kau" can be a threat.
*/
export const pgTextAnalysisCacheTable = pgTable(
"text_analysis_cache",
{
/** Normalized text (lowercase, whitespace-collapsed) — primary key. */
text: pgText("text").primaryKey(),
/** JSON array of moderation flags detected for this text (e.g. ["vulgar_language","harassment"]). */
flags: pgText("flags").notNull().default("[]"),
/** Which source produced this result: "local" | "nvidia" | "primary_ai" | "groq" | "vision_llm". */
source: pgText("source", {
enum: ["local", "nvidia", "primary_ai", "groq", "vision_llm"],
})
.notNull()
.default("local"),
/** Epoch millis when the analysis was stored. */
analyzed_at: pgBigint("analyzed_at", { mode: "number" }).notNull(),
/** Epoch millis when this cache entry expires. */
expires_at: pgBigint("expires_at", { mode: "number" }).notNull(),
/** How many times this cached text has been reused. */
hit_count: pgInteger("hit_count").notNull().default(0),
},
(table) => ({
expiresAtIdx: pgIndex("idx_text_analysis_cache_expires_at").on(
table.expires_at,
),
sourceIdx: pgIndex("idx_text_analysis_cache_source").on(table.source),
}),
);
// Runtime table exports
// =====================
export const muxerJobsTable = pgMuxerJobsTable;
export const messagesTable = pgMessagesTable;
export const attachmentsTable = pgAttachmentsTable;
export const uiStateTable = pgUIStateTable;
export const aiAnalysisRunsTable = pgAIAnalysisRunsTable;
export const voiceRecordingsTable = pgVoiceRecordingsTable;
export const messageReviewsTable = pgMessageReviewsTable;
export const moderationActionsTable = pgModerationActionsTable;
export const retentionPoliciesTable = pgRetentionPoliciesTable;
export const textAnalysisCacheTable = pgTextAnalysisCacheTable;
// Export table types for use in queries
export type MuxerJob = typeof muxerJobsTable.$inferSelect;
export type MuxerJobInsert = typeof muxerJobsTable.$inferInsert;
export type Message = typeof messagesTable.$inferSelect;
export type MessageInsert = typeof messagesTable.$inferInsert;
export type Attachment = typeof attachmentsTable.$inferSelect;
export type AttachmentInsert = typeof attachmentsTable.$inferInsert;
export type UIState = typeof uiStateTable.$inferSelect;
export type UIStateInsert = typeof uiStateTable.$inferInsert;
export type AIAnalysisRun = typeof aiAnalysisRunsTable.$inferSelect;
export type AIAnalysisRunInsert = typeof aiAnalysisRunsTable.$inferInsert;
export type VoiceRecording = typeof voiceRecordingsTable.$inferSelect;
export type VoiceRecordingInsert = typeof voiceRecordingsTable.$inferInsert;
export type MessageReview = typeof messageReviewsTable.$inferSelect;
export type MessageReviewInsert = typeof messageReviewsTable.$inferInsert;
export type ModerationAction = typeof moderationActionsTable.$inferSelect;
export type ModerationActionInsert = typeof moderationActionsTable.$inferInsert;
export type RetentionPolicy = typeof retentionPoliciesTable.$inferSelect;
export type RetentionPolicyInsert = typeof retentionPoliciesTable.$inferInsert;
@@ -0,0 +1,115 @@
import { desc, eq } from "drizzle-orm";
import { createChildLogger } from "../../shared/logger/logger.js";
import { getDatabase } from "./drizzle.js";
import {
type VoiceRecording,
type VoiceRecordingInsert,
voiceRecordingsTable,
} from "./schema.js";
const logger = createChildLogger("voice-recording-repo");
interface QueryBuilder<T = unknown> extends PromiseLike<T> {
from(...args: unknown[]): QueryBuilder<T>;
where(...args: unknown[]): QueryBuilder<T>;
orderBy(...args: unknown[]): QueryBuilder<T>;
limit(...args: unknown[]): QueryBuilder<T>;
offset(...args: unknown[]): QueryBuilder<T>;
values(...args: unknown[]): QueryBuilder<T>;
onConflictDoNothing(...args: unknown[]): QueryBuilder<T>;
returning(...args: unknown[]): QueryBuilder<T>;
set(...args: unknown[]): QueryBuilder<T>;
}
interface RecordingDatabase {
select<T = unknown[]>(...args: unknown[]): QueryBuilder<T>;
insert<T = unknown>(...args: unknown[]): QueryBuilder<T>;
update(...args: unknown[]): QueryBuilder<unknown>;
}
function db(): RecordingDatabase {
return getDatabase() as unknown as RecordingDatabase;
}
export async function insertVoiceRecording(
recording: VoiceRecordingInsert,
): Promise<void> {
try {
await db()
.insert(voiceRecordingsTable)
.values(recording)
.onConflictDoNothing();
} catch (error) {
logger.error(
{
id: recording.id,
error: error instanceof Error ? error.message : String(error),
},
"Failed to insert voice recording",
);
throw error;
}
}
export async function updateVoiceRecordingAsUploaded(
id: string,
downloadUrl: string,
uploadedAt: number,
): Promise<void> {
try {
await db()
.update(voiceRecordingsTable)
.set({
download_url: downloadUrl,
upload_status: "uploaded",
uploaded_at: uploadedAt,
})
.where(eq(voiceRecordingsTable.id, id));
} catch (error) {
logger.error(
{ id, error: error instanceof Error ? error.message : String(error) },
"Failed to update voice recording status to uploaded",
);
throw error;
}
}
export async function updateVoiceRecordingAsFailed(
id: string,
error: string,
): Promise<void> {
try {
await db()
.update(voiceRecordingsTable)
.set({
upload_status: "failed",
upload_error: error,
})
.where(eq(voiceRecordingsTable.id, id));
} catch (error) {
logger.error(
{ id, error: error instanceof Error ? error.message : String(error) },
"Failed to update voice recording status to failed",
);
throw error;
}
}
export async function listVoiceRecordings(
limit = 100,
): Promise<VoiceRecording[]> {
try {
const rows = await db()
.select()
.from(voiceRecordingsTable)
.orderBy(desc(voiceRecordingsTable.created_at))
.limit(limit);
return rows as VoiceRecording[];
} catch (error) {
logger.error(
{ error: error instanceof Error ? error.message : String(error) },
"Failed to list voice recordings",
);
throw error;
}
}
@@ -0,0 +1,21 @@
import { type ClientOptions, Options } from "discord.js-selfbot-v13";
export function createDiscordClientOptions(): ClientOptions {
return {
makeCache: Options.cacheWithLimits({
...Options.defaultMakeCacheSettings,
MessageManager: 25,
ReactionManager: 0,
ReactionUserManager: 0,
PresenceManager: 0,
}),
partials: ["USER", "CHANNEL", "GUILD_MEMBER", "MESSAGE"],
sweepers: {
messages: { interval: 300, lifetime: 600 },
threads: { interval: 3600, lifetime: 14400 },
},
restRequestTimeout: 15_000,
retryLimit: 2,
restGlobalRateLimit: 45,
};
}
@@ -0,0 +1,43 @@
export class AppError extends Error {
public code: string;
public statusCode: number;
constructor(message: string, code: string, statusCode: number = 500) {
super(message);
this.code = code;
this.statusCode = statusCode;
this.name = "AppError";
Error.captureStackTrace(this, this.constructor);
}
}
export class ConfigError extends AppError {
constructor(message: string) {
super(message, "CONFIG_ERROR", 500);
this.name = "ConfigError";
}
}
export class AudioError extends AppError {
constructor(message: string) {
super(message, "AUDIO_ERROR", 500);
this.name = "AudioError";
}
}
export class VoiceConnectionError extends AppError {
constructor(message: string) {
super(message, "VOICE_CONNECTION_ERROR", 500);
this.name = "VoiceConnectionError";
}
}
export class ValidationError extends AppError {
public details?: Record<string, string[]>;
constructor(message: string, details?: Record<string, string[]>) {
super(message, "VALIDATION_ERROR", 400);
this.details = details;
this.name = "ValidationError";
}
}
@@ -0,0 +1,132 @@
import fs from "node:fs";
import path from "node:path";
import winston from "winston";
import { formatLogMetadata, serializeLogValue } from "./serialization.js";
const isDev = process.env.NODE_ENV !== "production";
const logLevel = process.env.LOG_LEVEL || (isDev ? "debug" : "info");
const logsDir = path.resolve(process.cwd(), "logs");
fs.mkdirSync(logsDir, { recursive: true });
const metadataFormat = winston.format((info) => {
const {
level: _level,
message: _message,
timestamp: _timestamp,
...metadata
} = info;
for (const key of Object.keys(metadata)) {
delete info[key];
}
Object.assign(info, formatLogMetadata(metadata));
return info;
});
const consoleFormat = winston.format.printf((info) => {
const { level, message, timestamp, context, ...metadata } = info;
const contextLabel = context ? ` [${String(context)}]` : "";
const metadataText = Object.keys(metadata).length
? ` ${JSON.stringify(formatLogMetadata(metadata))}`
: "";
return `${timestamp} ${level}${contextLabel}: ${message}${metadataText}`;
});
export interface CustomLogger {
error: (msgOrObj: any, msgOrArgs?: any, ...args: any[]) => void;
warn: (msgOrObj: any, msgOrArgs?: any, ...args: any[]) => void;
info: (msgOrObj: any, msgOrArgs?: any, ...args: any[]) => void;
debug: (msgOrObj: any, msgOrArgs?: any, ...args: any[]) => void;
trace: (msgOrObj: any, msgOrArgs?: any, ...args: any[]) => void;
fatal: (msgOrObj: any, msgOrArgs?: any, ...args: any[]) => void;
silent: (msgOrObj: any, msgOrArgs?: any, ...args: any[]) => void;
child(options: { context: string } & Record<string, any>): CustomLogger;
[key: string]: any;
}
const winstonLogger = winston.createLogger({
level: logLevel,
levels: winston.config.npm.levels,
format: winston.format.combine(
winston.format.timestamp(),
winston.format.errors({ stack: true }),
metadataFormat(),
),
transports: [
new winston.transports.Console({
format: winston.format.combine(
winston.format.colorize(),
winston.format.timestamp(),
metadataFormat(),
consoleFormat,
),
}),
new winston.transports.File({
filename: path.join(logsDir, "app.log"),
format: winston.format.json(),
}),
new winston.transports.File({
filename: path.join(logsDir, "error.log"),
level: "error",
format: winston.format.json(),
}),
],
});
function wrapLogger(wLogger: winston.Logger): CustomLogger {
const logAtLevel = (level: string) => {
return (arg1: any, arg2?: any) => {
if (arg1 instanceof Error) {
wLogger.log(level, arg1.message, { error: arg1 });
} else if (typeof arg1 === "object" && arg1 !== null) {
const message = typeof arg2 === "string" ? arg2 : "";
wLogger.log(level, message, { ...arg1 });
} else {
const message = typeof arg1 === "string" ? arg1 : String(arg1);
const metadata = typeof arg2 === "object" && arg2 !== null ? arg2 : {};
wLogger.log(level, message, metadata);
}
};
};
const wrapped: CustomLogger = {
error: logAtLevel("error"),
warn: logAtLevel("warn"),
info: logAtLevel("info"),
debug: logAtLevel("debug"),
trace: logAtLevel("debug"),
fatal: logAtLevel("error"),
silent: () => {},
child: (options: any) => {
const childWinston = wLogger.child(options);
return wrapLogger(childWinston);
},
};
const proxy = new Proxy(wrapped, {
get(target, prop) {
if (prop in target) {
return (target as any)[prop];
}
const val = (wLogger as any)[prop];
if (typeof val === "function") {
return val.bind(wLogger);
}
return val;
},
});
return proxy;
}
export const logger: CustomLogger = wrapLogger(winstonLogger);
export const createChildLogger = (context: string): CustomLogger => {
return logger.child({ context });
};
export const serializeLogValueForTest = serializeLogValue;
export const formatLogMetadataForTest = formatLogMetadata;
@@ -0,0 +1,109 @@
export type LogMetadata = Record<string, unknown>;
type SerializedError = {
name: string;
message: string;
stack?: string;
code?: unknown;
statusCode?: unknown;
} & Record<string, unknown>;
const serializeError = (error: Error): SerializedError => {
const serialized: SerializedError = {
name: error.name,
message: error.message,
};
if (error.stack) {
serialized.stack = error.stack;
}
const errorWithFields = error as Error & {
code?: unknown;
statusCode?: unknown;
[key: string]: unknown;
};
if (errorWithFields.code !== undefined) {
serialized.code = errorWithFields.code;
}
if (errorWithFields.statusCode !== undefined) {
serialized.statusCode = errorWithFields.statusCode;
}
for (const [key, value] of Object.entries(errorWithFields)) {
if (serialized[key] === undefined) {
serialized[key] = value;
}
}
return serialized;
};
const isPlainObject = (value: unknown): value is Record<string, unknown> => {
if (!value || typeof value !== "object") {
return false;
}
const prototype = Object.getPrototypeOf(value);
return prototype === Object.prototype || prototype === null;
};
export const serializeLogValue = (
value: unknown,
_seen: WeakSet<object> = new WeakSet(),
): unknown => {
if (value === null || value === undefined) return value;
if (value instanceof Error) {
return serializeError(value);
}
if (value instanceof Date) {
return value.toISOString();
}
if (value instanceof RegExp) {
return value.toString();
}
if (typeof value === "object") {
if (_seen.has(value as object)) {
return "[Circular]";
}
_seen.add(value as object);
}
if (Array.isArray(value)) {
return value.map((item) => serializeLogValue(item, _seen));
}
if (isPlainObject(value)) {
return Object.fromEntries(
Object.entries(value).map(([key, nestedValue]) => [
key,
serializeLogValue(nestedValue, _seen),
]),
);
}
if (typeof value === "object") {
try {
return `[Object ${(value as any)?.constructor?.name ?? "unknown"}]`;
} catch {
return "[Object]";
}
}
return value;
};
export const formatLogMetadata = (metadata: LogMetadata): LogMetadata => {
return Object.fromEntries(
Object.entries(metadata).map(([key, value]) => [
key,
serializeLogValue(value),
]),
);
};
@@ -0,0 +1,42 @@
import pRetry from "p-retry";
import type { CustomLogger } from "../../shared/logger/logger.js";
export interface RetryOptions {
retries?: number;
minTimeout?: number;
maxTimeout?: number;
factor?: number;
logger?: CustomLogger;
}
export async function retryWithBackoff<T>(
fn: () => Promise<T>,
options: RetryOptions = {},
): Promise<T> {
const {
retries = 3,
minTimeout = 1000,
maxTimeout = 30000,
factor = 2,
logger,
} = options;
return pRetry(fn, {
retries,
minTimeout,
maxTimeout,
factor,
onFailedAttempt: (error) => {
if (logger) {
logger.warn(
{
attempt: error.attemptNumber,
retriesLeft: error.retriesLeft,
error: error.error,
},
"Retry attempt",
);
}
},
});
}