From e5304fde294e9ae5720e121ae0ba96e0d4a7452f Mon Sep 17 00:00:00 2001
From: asepharyana <superaseph@gmail.com>
Date: Wed, 2 Sep 2026 10:12:03 +0700
Subject: [PATCH] feat(gateway): add manual video-watch command for selfbot
 screen-share capture

A selfbot (user token) cannot auto-detect other members' camera/share
(no VOICE_STATE_UPDATE for others, 403 on member fetch). The only
selfbot-viable path to capture another member's SCREEN SHARE is an
operator-initiated STREAM_WATCH (gateway op 20, not gated on bot-vs-user).

Add video:watch / video:unwatch Redis commands routed via the existing
command handler to startStreamWatch/stopStreamWatch, which then does the
DAVE handshake + per-burst MP4 segmentation + DB insert + Tele upload
(already implemented in streamWatchReceiver).

- new VideoHandler (command-handler/video.handler.ts)
- register video:watch / video:unwatch in handler-registry + CommandHandler
- command constants COMMAND_VIDEO_WATCH / COMMAND_VIDEO_UNWATCH
- resolve active voice channel from voice controller + client cache
- 8 unit tests (videoHandler.test.ts)
- biome fixes for pre-existing test import ordering

All green: typecheck, build, lint (174 files), 200 tests.
---
 ...6-09-02_selfbot-manual-video-watch-spec.md |  81 ++++++++++
 .../modules/command-handler/commandHandler.ts |   4 +
 .../command-handler/handler-registry.ts       |  12 ++
 .../modules/command-handler/video.handler.ts  | 145 +++++++++++++++++
 .../src/shared/redis-channels.ts              |   2 +
 .../tests/llmChunkExtraction.test.ts          |   2 +-
 .../tests/videoHandler.test.ts                | 147 ++++++++++++++++++
 .../tests/videoReceiver.test.ts               |   2 +-
 8 files changed, 393 insertions(+), 2 deletions(-)
 create mode 100644 .hermes/plans/2026-09-02_selfbot-manual-video-watch-spec.md
 create mode 100644 services/discord-gateway/src/modules/command-handler/video.handler.ts
 create mode 100644 services/discord-gateway/tests/videoHandler.test.ts

diff --git a/.hermes/plans/2026-09-02_selfbot-manual-video-watch-spec.md b/.hermes/plans/2026-09-02_selfbot-manual-video-watch-spec.md
new file mode 100644
index 00000000..f7efc84f
--- /dev/null
+++ b/.hermes/plans/2026-09-02_selfbot-manual-video-watch-spec.md
@@ -0,0 +1,81 @@
+# Spec: Selfbot-Viable Video Capture — manual screen-share watch command (Phase D)
+
+Status: PLANNED (not yet built)
+Date: 2026-09-02
+Author: Hermes
+Related: `.hermes/plans/2026-08-31_video-receive-phaseC-spec.md` (auto-receive, superseded
+for selfbot), `gmw-ops/references/selfbot-presence-detection-limits.md`,
+`gmw-ops/references/discord-voice-fork-video-receive.md`
+
+## TL;DR — the decisive finding (verified live 2026-09-02)
+
+User insists on keeping the **selfbot** (no bot-token migration). Live diagnostics prove
+a selfbot CANNOT auto-detect other members' camera/share because:
+- It never receives `VOICE_STATE_UPDATE` for other members (only its own).
+- `guild.members.fetch()` → 403, `GET /channels/{id}/voice-states` → 404.
+- No `GUILD_CREATE`, no `READY.broadcaster_user_ids` presence.
+- `scanExistingStreamers` + `handleVoiceStateUpdate` (the only two `startStreamWatch`
+  triggers) are therefore both **dead on a selfbot**.
+- No manual watch command exists today, so even on-demand capture is impossible.
+
+→ The ONE selfbot-viable path is a **manual, operator-initiated STREAM_WATCH** on a
+   member known to be screen-sharing. Gateway op 20 (STREAM_WATCH) is **NOT gated on
+   bot-vs-user**; the DAVE handshake to Ready+MLS was already verified live in earlier
+   sessions. The receive/mux/segment/upload pipeline (`streamWatchReceiver.ts`) is already
+   built and only lacks a real streamer to produce its first `.mp4`.
+
+Camera-of-others is NOT viable on a selfbot even with `unknown-ssrc` fallback:
+`@discordjs/voice` `parsePacket` calls `daveSession.decrypt(packet, userId)` keyed per
+REAL userId (vendor fork dist/index.js:2143), so a fake id selects no MLS decryptor →
+garbage, not H264. (The uncommitted `unknown-ssrc` change was reverted this session.)
+
+Selfbot CAN capture the OWNER's own video (its own VOICE_STATE_UPDATE + fork op12
+videoSSRC are attributable), but `videoRecorder.ts` hard-skips its own id — parameterized
+self-capture is a follow-up, not the default.
+
+## Goal
+
+Add a **manual watch command** so an operator can say "record <member>'s screen share"
+and the gateway `startStreamWatch`s that member → DAVE watch → per-burst `.mp4` segments
+(mirroring voice silence split) → upload → DB `voice_recordings` → dashboard `<video>`.
+
+This is the only form of OTHER-member video capture a selfbot can deliver, and it is
+genuinely buildable with the existing receive pipeline.
+
+## Scope / files
+
+Gateway (`services/discord-gateway`):
+- New command type `VIDEO_WATCH` + handler in `command-handler/` (dedicated
+  `video.handler.ts`), routed via `createHandlerRegistry`.
+- Handler resolves a VoiceChannel (from persisted `voice_auto_reconnect` / active
+  connections) + target memberId from the command payload, calls
+  `startStreamWatch(channel, memberId)` (already exported).
+- Idempotent (startStreamWatch early-returns if a watch exists); a `VIDEO_UNWATCH`
+  command calls `stopStreamWatch(guildId, userId)`.
+- Reply: success/failure via the standard `CommandReply` publish.
+
+Backend (`services/backend`):
+- oRPC procedure (or the existing command bridge) that publishes a `VIDEO_WATCH`
+  command to `backend:command` with `{ guildId, channelId, userId }`. Reuse the same
+  bridge the FE already uses for voice commands.
+
+Frontend (`services/frontend`):
+- A "Video Watch" control: pick a voice member + a "Record screen" button → calls the
+  backend procedure. Shows live status (watching / recording / segments uploaded).
+
+(Each layer optional independently; gateway alone gives a Redis-testable path.)
+
+## Verification
+1. `pnpm typecheck` + `pnpm build` + `biome check src/` green in discord-gateway.
+2. Unit test: handler publishes reply + calls startStreamWatch with the right args
+   (mock the module).
+3. Live: operator invokes `!videorec <member>` while that member screen-shares →
+   journal shows `Sending STREAM_WATCH` → `STREAM_CREATE` → `DAVE watch READY` → `Video
+   burst opened` → `Video muxed to mp4` → a `video-*.mp4` appears under
+   `<recordingsDir>/<uid>/` and a `video-%` row lands in `voice_recordings`.
+4. `Build & Deploy (Nix)` CI green.
+
+## Out of scope (documented dead ends on selfbot)
+- Auto camera/share capture of OTHER members (impossible at detection layer).
+- Camera-of-others via `unknown-ssrc` (DAVE decrypt needs real userId).
+- Bot-token migration (user declined).
diff --git a/services/discord-gateway/src/modules/command-handler/commandHandler.ts b/services/discord-gateway/src/modules/command-handler/commandHandler.ts
index d9d3bbcd..4c03da7c 100644
--- a/services/discord-gateway/src/modules/command-handler/commandHandler.ts
+++ b/services/discord-gateway/src/modules/command-handler/commandHandler.ts
@@ -18,6 +18,7 @@ import {
 import { MediaHandler } from "./media.handler.js";
 import { wireMediaStatusWriter } from "./mediaStatusSink.js";
 import { ModerationHandler } from "./moderation.handler.js";
+import { VideoHandler } from "./video.handler.js";
 import { VoiceHandler } from "./voice.handler.js";
 
 const logger = createChildLogger("command-handler");
@@ -52,6 +53,7 @@ export class CommandHandler {
   private mediaHandler!: MediaHandler;
   private guildHandler!: GuildHandler;
   private moderationHandler!: ModerationHandler;
+  private videoHandler!: VideoHandler;
 
   constructor() {
     // Dedicated Redis connection needed because: Redis requires a dedicated
@@ -86,6 +88,7 @@ export class CommandHandler {
     this.mediaHandler = new MediaHandler();
     this.guildHandler = new GuildHandler(client);
     this.moderationHandler = new ModerationHandler(client);
+    this.videoHandler = new VideoHandler(client, voiceController);
 
     // Wire the media status sink so MediaHandler can persist status on
     // queue advances that happen outside a command (natural track end).
@@ -97,6 +100,7 @@ export class CommandHandler {
       this.mediaHandler,
       this.guildHandler,
       this.moderationHandler,
+      this.videoHandler,
     );
 
     this.redisSub.on("message", (_channel, message) => {
diff --git a/services/discord-gateway/src/modules/command-handler/handler-registry.ts b/services/discord-gateway/src/modules/command-handler/handler-registry.ts
index f4a68401..1923d7bc 100644
--- a/services/discord-gateway/src/modules/command-handler/handler-registry.ts
+++ b/services/discord-gateway/src/modules/command-handler/handler-registry.ts
@@ -7,6 +7,8 @@ import {
   COMMAND_MEDIA_STOP,
   COMMAND_MEDIA_VOLUME,
   COMMAND_MODERATION_ACTION,
+  COMMAND_VIDEO_UNWATCH,
+  COMMAND_VIDEO_WATCH,
   COMMAND_VOICE_CHANNELS,
   COMMAND_VOICE_CONNECT,
   COMMAND_VOICE_DISCONNECT,
@@ -19,6 +21,7 @@ import {
 import type { GuildHandler } from "./guild.handler.js";
 import type { MediaHandler } from "./media.handler.js";
 import type { ModerationHandler } from "./moderation.handler.js";
+import type { VideoHandler } from "./video.handler.js";
 import type { VoiceHandler } from "./voice.handler.js";
 
 // ---------------------------------------------------------------------------
@@ -38,6 +41,7 @@ export function createHandlerRegistry(
   mediaHandler: MediaHandler,
   guildHandler: GuildHandler,
   moderationHandler: ModerationHandler,
+  videoHandler: VideoHandler,
 ): Map<string, CommandHandlerFn> {
   const registry = new Map<string, CommandHandlerFn>();
 
@@ -61,6 +65,14 @@ export function createHandlerRegistry(
     voiceHandler.handleVoiceTransmitStop(cmd),
   );
 
+  // Video watch commands
+  registry.set(COMMAND_VIDEO_WATCH, (cmd) =>
+    videoHandler.handleVideoWatch(cmd),
+  );
+  registry.set(COMMAND_VIDEO_UNWATCH, (cmd) =>
+    videoHandler.handleVideoUnwatch(cmd),
+  );
+
   // Media commands
   registry.set(COMMAND_MEDIA_QUEUE, (cmd) =>
     mediaHandler.handleMediaQueue(cmd),
diff --git a/services/discord-gateway/src/modules/command-handler/video.handler.ts b/services/discord-gateway/src/modules/command-handler/video.handler.ts
new file mode 100644
index 00000000..d00eca19
--- /dev/null
+++ b/services/discord-gateway/src/modules/command-handler/video.handler.ts
@@ -0,0 +1,145 @@
+import type { Client, Guild, VoiceChannel } from "discord.js-selfbot-v13";
+import type { CommandMessage, CommandReply } from "../../shared/index.js";
+import {
+  startStreamWatch,
+  stopStreamWatch,
+} from "../voice-recording/streamWatchReceiver.js";
+import type { VoiceController } from "../voice-recording/voiceController.js";
+
+// ---------------------------------------------------------------------------
+// VideoHandler — manual screen-share / camera watch (selfbot-viable capture)
+// ---------------------------------------------------------------------------
+//
+// On a selfbot (user token) there is NO automatic detection of other members'
+// video (no VOICE_STATE_UPDATE for them, no member list). The only way to
+// capture another member's SCREEN SHARE is an operator-initiated STREAM_WATCH
+// (gateway op 20, NOT gated on bot-vs-user) — which this handler exposes as a
+// backend→gateway Redis command. `streamWatchReceiver` does the DAVE handshake,
+// per-burst `.mp4` segmentation (mirroring voice silence split), DB insert and
+// Tele upload exactly like the audio path.
+//
+// Camera-of-others stays impossible on a selfbot (DAVE decrypt is keyed per real
+// userId and a selfbot cannot learn others' ids), so this command targets SCREEN
+// SHARE. Watching the operator's OWN camera/share is a separate (parameterized)
+// follow-up.
+export class VideoHandler {
+  constructor(
+    private client: Client | null,
+    private voiceController: VoiceController | null,
+  ) {}
+
+  setClient(client: Client): void {
+    this.client = client;
+  }
+
+  setVoiceController(vc: VoiceController): void {
+    this.voiceController = vc;
+  }
+
+  /**
+   * Resolve the active voice channel for a guild from the voice controller.
+   * Prefers the controller's live connection; falls back to the client cache.
+   */
+  private async resolveChannel(
+    guildId: string,
+    requestedChannelId?: string,
+  ): Promise<{ guild: Guild; channel: VoiceChannel } | null> {
+    const client = this.client;
+    if (!client) return null;
+    const guild =
+      client.guilds.cache.get(guildId) ??
+      (await client.guilds.fetch(guildId).catch(() => null));
+    if (!guild) return null;
+
+    // If an explicit channelId was given, use it.
+    const channelId =
+      requestedChannelId || this.voiceController?.getStatus()?.activeChannelId;
+    if (channelId) {
+      const ch = (guild.channels.cache.get(channelId) ??
+        (await guild.channels
+          .fetch(channelId)
+          .catch(() => null))) as VoiceChannel | null;
+      if (ch && ch.type === "GUILD_VOICE") return { guild, channel: ch };
+    }
+    // Fallback: any voice channel the account is currently in.
+    const voiceCh = Array.from(guild.channels.cache.values()).find(
+      (c): c is VoiceChannel =>
+        c.type === "GUILD_VOICE" && c.members?.has(client.user?.id ?? ""),
+    );
+    return voiceCh ? { guild, channel: voiceCh } : null;
+  }
+
+  async handleVideoWatch(cmd: CommandMessage): Promise<CommandReply<unknown>> {
+    if (!this.client) {
+      return {
+        id: cmd.id,
+        success: false,
+        data: null,
+        error: "Gateway not initialized",
+      };
+    }
+    const guildId = String(cmd.payload.guildId ?? "");
+    const userId = String(cmd.payload.userId ?? "");
+    const channelId = String(cmd.payload.channelId ?? "");
+    if (!guildId || !userId) {
+      return {
+        id: cmd.id,
+        success: false,
+        data: null,
+        error: "guildId and userId are required",
+      };
+    }
+
+    const resolved = await this.resolveChannel(guildId, channelId || undefined);
+    if (!resolved) {
+      return {
+        id: cmd.id,
+        success: false,
+        data: null,
+        error: "No active voice channel to watch in this guild",
+      };
+    }
+    if (userId === this.client.user?.id) {
+      // Self-watch is intentionally not enabled by default (see file header).
+      return {
+        id: cmd.id,
+        success: false,
+        data: null,
+        error: "Watching the selfbot's own stream is not enabled",
+      };
+    }
+
+    await startStreamWatch(resolved.channel, userId);
+    return {
+      id: cmd.id,
+      success: true,
+      data: {
+        status: "requested",
+        guildId,
+        channelId: resolved.channel.id,
+        userId,
+      },
+    };
+  }
+
+  async handleVideoUnwatch(
+    cmd: CommandMessage,
+  ): Promise<CommandReply<unknown>> {
+    const guildId = String(cmd.payload.guildId ?? "");
+    const userId = String(cmd.payload.userId ?? "");
+    if (!guildId || !userId) {
+      return {
+        id: cmd.id,
+        success: false,
+        data: null,
+        error: "guildId and userId are required",
+      };
+    }
+    stopStreamWatch(guildId, userId);
+    return {
+      id: cmd.id,
+      success: true,
+      data: { status: "stopped", guildId, userId },
+    };
+  }
+}
diff --git a/services/discord-gateway/src/shared/redis-channels.ts b/services/discord-gateway/src/shared/redis-channels.ts
index 57549642..b778c365 100644
--- a/services/discord-gateway/src/shared/redis-channels.ts
+++ b/services/discord-gateway/src/shared/redis-channels.ts
@@ -57,6 +57,8 @@ export const COMMAND_VOICE_DISCONNECT_GUILD = "voice:disconnect:guild";
 export const COMMAND_VOICE_CHANNELS = "voice:channels";
 export const COMMAND_VOICE_TRANSMIT_START = "voice:transmit:start";
 export const COMMAND_VOICE_TRANSMIT_STOP = "voice:transmit:stop";
+export const COMMAND_VIDEO_WATCH = "video:watch";
+export const COMMAND_VIDEO_UNWATCH = "video:unwatch";
 export const COMMAND_GUILDS_LIST = "guilds:list";
 export const COMMAND_GUILDS_TEXT_CHANNELS = "guilds:text-channels";
 export const COMMAND_MEDIA_QUEUE = "media:queue";
diff --git a/services/discord-gateway/tests/llmChunkExtraction.test.ts b/services/discord-gateway/tests/llmChunkExtraction.test.ts
index 9a56307a..c3c9aacf 100644
--- a/services/discord-gateway/tests/llmChunkExtraction.test.ts
+++ b/services/discord-gateway/tests/llmChunkExtraction.test.ts
@@ -34,7 +34,7 @@ describe("extractChunkText — streaming chunk text extraction", () => {
   });
 
   it('falls back to delta.reasoning — mimo via omniroute streams reasoning there with content:""', () => {
-  // Exact shape seen from omniroute → mimo-v2.5-free (2026-08-11):
+    // Exact shape seen from omniroute → mimo-v2.5-free (2026-08-11):
     // {"choices":[{"delta":{"content":"","reasoning":"The user wants a","role":"assistant"},"finish_reason":null,...}]}
     expect(
       extractChunkText({
diff --git a/services/discord-gateway/tests/videoHandler.test.ts b/services/discord-gateway/tests/videoHandler.test.ts
new file mode 100644
index 00000000..499f2910
--- /dev/null
+++ b/services/discord-gateway/tests/videoHandler.test.ts
@@ -0,0 +1,147 @@
+import { beforeEach, describe, expect, it, vi } from "vitest";
+import { VideoHandler } from "../src/modules/command-handler/video.handler.js";
+import * as streamWatch from "../src/modules/voice-recording/streamWatchReceiver.js";
+
+// ─── mocks ─────────────────────────────────────────────────────────────
+function makeClient({ botId = "bot1", channelType = "GUILD_VOICE" } = {}) {
+  const activeChannel = {
+    id: "c1",
+    name: "Lounge",
+    type: channelType,
+    members: { has: vi.fn(() => false) },
+  };
+  const guild = {
+    id: "g1",
+    channels: {
+      cache: new Map([["c1", activeChannel]]),
+      fetch: vi.fn().mockResolvedValue(new Map()),
+    },
+  };
+  return {
+    user: { id: botId },
+    guilds: {
+      cache: new Map([["g1", guild]]),
+      fetch: vi.fn().mockResolvedValue(guild),
+    },
+  };
+}
+
+function makeVoiceController(activeChannelId = "c1") {
+  return {
+    getStatus: vi.fn().mockReturnValue({ activeChannelId, connected: true }),
+  };
+}
+
+function makeCmd(type: string, payload: Record<string, unknown>) {
+  return { id: "req-1", type, payload, replyChannel: "ch:1" };
+}
+
+beforeEach(() => {
+  vi.restoreAllMocks();
+  vi.spyOn(streamWatch, "startStreamWatch").mockResolvedValue();
+  vi.spyOn(streamWatch, "stopStreamWatch").mockImplementation(() => {});
+});
+
+describe("VideoHandler", () => {
+  it("rejects when gateway not initialized", async () => {
+    const handler = new VideoHandler(null, null);
+    const reply = await handler.handleVideoWatch(makeCmd("video:watch", {}));
+    expect(reply.success).toBe(false);
+    expect(reply.error).toContain("not initialized");
+  });
+
+  it("rejects when guildId/userId missing", async () => {
+    const handler = new VideoHandler(makeClient(), makeVoiceController());
+    const reply = await handler.handleVideoWatch(
+      makeCmd("video:watch", { guildId: "g1" }),
+    );
+    expect(reply.success).toBe(false);
+    expect(reply.error).toContain("guildId and userId are required");
+  });
+
+  it("rejects watching the selfbot's own stream", async () => {
+    const handler = new VideoHandler(
+      makeClient({ botId: "bot1" }),
+      makeVoiceController(),
+    );
+    const reply = await handler.handleVideoWatch(
+      makeCmd("video:watch", { guildId: "g1", userId: "bot1" }),
+    );
+    expect(reply.success).toBe(false);
+    expect(reply.error).toContain("own stream");
+  });
+
+  it("returns error when no active voice channel found", async () => {
+    // Freeze the cache so no channel resolves.
+    const client = makeClient();
+    client.guilds.cache.get("g1").channels.cache.clear();
+    const handler = new VideoHandler(client, makeVoiceController());
+    const reply = await handler.handleVideoWatch(
+      makeCmd("video:watch", { guildId: "g1", userId: "user-x" }),
+    );
+    expect(reply.success).toBe(false);
+    expect(reply.error).toContain("No active voice channel");
+  });
+
+  it("calls startStreamWatch with resolved channel + userId and replies success", async () => {
+    const client = makeClient();
+    const handler = new VideoHandler(client, makeVoiceController("c1"));
+    const reply = await handler.handleVideoWatch(
+      makeCmd("video:watch", { guildId: "g1", userId: "user-x" }),
+    );
+    expect(reply.success).toBe(true);
+    expect(reply.data).toMatchObject({
+      status: "requested",
+      guildId: "g1",
+      channelId: "c1",
+      userId: "user-x",
+    });
+    expect(streamWatch.startStreamWatch).toHaveBeenCalledWith(
+      expect.objectContaining({ id: "c1" }),
+      "user-x",
+    );
+  });
+
+  it("prefers an explicit channelId over the active one", async () => {
+    const client = makeClient();
+    // Add a second voice channel.
+    const guild = client.guilds.cache.get("g1");
+    guild.channels.cache.set("c9", {
+      id: "c9",
+      name: "Other",
+      type: "GUILD_VOICE",
+      members: { has: vi.fn(() => false) },
+    });
+    const handler = new VideoHandler(client, makeVoiceController("c1"));
+    const reply = await handler.handleVideoWatch(
+      makeCmd("video:watch", {
+        guildId: "g1",
+        userId: "user-x",
+        channelId: "c9",
+      }),
+    );
+    expect(reply.success).toBe(true);
+    expect(streamWatch.startStreamWatch).toHaveBeenCalledWith(
+      expect.objectContaining({ id: "c9" }),
+      "user-x",
+    );
+  });
+
+  it("handleVideoUnwatch calls stopStreamWatch", async () => {
+    const handler = new VideoHandler(makeClient(), makeVoiceController());
+    const reply = await handler.handleVideoUnwatch(
+      makeCmd("video:unwatch", { guildId: "g1", userId: "user-x" }),
+    );
+    expect(reply.success).toBe(true);
+    expect(streamWatch.stopStreamWatch).toHaveBeenCalledWith("g1", "user-x");
+  });
+
+  it("handleVideoUnwatch rejects missing args", async () => {
+    const handler = new VideoHandler(makeClient(), makeVoiceController());
+    const reply = await handler.handleVideoUnwatch(
+      makeCmd("video:unwatch", { guildId: "g1" }),
+    );
+    expect(reply.success).toBe(false);
+    expect(reply.error).toContain("guildId and userId are required");
+  });
+});
diff --git a/services/discord-gateway/tests/videoReceiver.test.ts b/services/discord-gateway/tests/videoReceiver.test.ts
index db33fa74..f61c0068 100644
--- a/services/discord-gateway/tests/videoReceiver.test.ts
+++ b/services/discord-gateway/tests/videoReceiver.test.ts
@@ -3,8 +3,8 @@ import { mkdtempSync, rmSync } from "node:fs";
 import { access, stat } from "node:fs/promises";
 import { tmpdir } from "node:os";
 import path from "node:path";
-import { describe, expect, it } from "vitest";
 import { SSRCMap } from "@discordjs/voice";
+import { describe, expect, it } from "vitest";
 import {
   H264Depacketizer,
   muxToMp4,