fix: split long Telegram captions (#907) - thanks @jalehman
Co-authored-by: Josh Lehman <josh@martian.engineering>
This commit is contained in:
Peter Steinberger
@@ -9,6 +9,7 @@
|
||||
- Gateway/Dev: ensure `pnpm gateway:dev` always uses the dev profile config + state (`~/.clawdbot-dev`).
|
||||
- macOS: fix cron preview/testing payload to use `channel` key. (#867) — thanks @wes-davis.
|
||||
- Telegram: honor `channels.telegram.timeoutSeconds` for grammY API requests. (#863) — thanks @Snaver.
|
||||
- Telegram: split long captions into media + follow-up text messages. (#907) - thanks @jalehman.
|
||||
|
||||
## 2026.1.13
|
||||
|
||||
|
||||
366
src/telegram/send.caption-split.test.ts
Normal file
366
src/telegram/send.caption-split.test.ts
Normal file
@@ -0,0 +1,366 @@
|
||||
import { beforeEach, describe, expect, it, vi } from "vitest";
|
||||
|
||||
const { botApi, botCtorSpy } = vi.hoisted(() => ({
|
||||
botApi: {
|
||||
sendMessage: vi.fn(),
|
||||
sendPhoto: vi.fn(),
|
||||
},
|
||||
botCtorSpy: vi.fn(),
|
||||
}));
|
||||
|
||||
const { loadWebMedia } = vi.hoisted(() => ({
|
||||
loadWebMedia: vi.fn(),
|
||||
}));
|
||||
|
||||
vi.mock("../web/media.js", () => ({
|
||||
loadWebMedia,
|
||||
}));
|
||||
|
||||
vi.mock("grammy", () => ({
|
||||
Bot: class {
|
||||
api = botApi;
|
||||
constructor(
|
||||
public token: string,
|
||||
public options?: {
|
||||
client?: { fetch?: typeof fetch; timeoutSeconds?: number };
|
||||
},
|
||||
) {
|
||||
botCtorSpy(token, options);
|
||||
}
|
||||
},
|
||||
InputFile: class {},
|
||||
}));
|
||||
|
||||
const { loadConfig } = vi.hoisted(() => ({
|
||||
loadConfig: vi.fn(() => ({})),
|
||||
}));
|
||||
vi.mock("../config/config.js", async (importOriginal) => {
|
||||
const actual = await importOriginal<typeof import("../config/config.js")>();
|
||||
return {
|
||||
...actual,
|
||||
loadConfig,
|
||||
};
|
||||
});
|
||||
|
||||
import { sendMessageTelegram } from "./send.js";
|
||||
|
||||
describe("sendMessageTelegram caption splitting", () => {
|
||||
beforeEach(() => {
|
||||
loadConfig.mockReturnValue({});
|
||||
loadWebMedia.mockReset();
|
||||
botApi.sendMessage.mockReset();
|
||||
botApi.sendPhoto.mockReset();
|
||||
botCtorSpy.mockReset();
|
||||
});
|
||||
|
||||
it("splits long captions into media + text messages when text exceeds 1024 chars", async () => {
|
||||
const chatId = "123";
|
||||
// Generate text longer than 1024 characters
|
||||
const longText = "A".repeat(1100);
|
||||
|
||||
const sendPhoto = vi.fn().mockResolvedValue({
|
||||
message_id: 70,
|
||||
chat: { id: chatId },
|
||||
});
|
||||
const sendMessage = vi.fn().mockResolvedValue({
|
||||
message_id: 71,
|
||||
chat: { id: chatId },
|
||||
});
|
||||
const api = { sendPhoto, sendMessage } as unknown as {
|
||||
sendPhoto: typeof sendPhoto;
|
||||
sendMessage: typeof sendMessage;
|
||||
};
|
||||
|
||||
loadWebMedia.mockResolvedValueOnce({
|
||||
buffer: Buffer.from("fake-image"),
|
||||
contentType: "image/jpeg",
|
||||
fileName: "photo.jpg",
|
||||
});
|
||||
|
||||
const res = await sendMessageTelegram(chatId, longText, {
|
||||
token: "tok",
|
||||
api,
|
||||
mediaUrl: "https://example.com/photo.jpg",
|
||||
});
|
||||
|
||||
// Media should be sent first without caption
|
||||
expect(sendPhoto).toHaveBeenCalledWith(chatId, expect.anything(), {
|
||||
caption: undefined,
|
||||
});
|
||||
// Then text sent as separate message (plain text, matching caption behavior)
|
||||
expect(sendMessage).toHaveBeenCalledWith(chatId, longText);
|
||||
// Returns the text message ID (the "main" content)
|
||||
expect(res.messageId).toBe("71");
|
||||
});
|
||||
|
||||
it("uses caption when text is within 1024 char limit", async () => {
|
||||
const chatId = "123";
|
||||
// Text exactly at 1024 characters should still use caption
|
||||
const shortText = "B".repeat(1024);
|
||||
|
||||
const sendPhoto = vi.fn().mockResolvedValue({
|
||||
message_id: 72,
|
||||
chat: { id: chatId },
|
||||
});
|
||||
const sendMessage = vi.fn();
|
||||
const api = { sendPhoto, sendMessage } as unknown as {
|
||||
sendPhoto: typeof sendPhoto;
|
||||
sendMessage: typeof sendMessage;
|
||||
};
|
||||
|
||||
loadWebMedia.mockResolvedValueOnce({
|
||||
buffer: Buffer.from("fake-image"),
|
||||
contentType: "image/jpeg",
|
||||
fileName: "photo.jpg",
|
||||
});
|
||||
|
||||
const res = await sendMessageTelegram(chatId, shortText, {
|
||||
token: "tok",
|
||||
api,
|
||||
mediaUrl: "https://example.com/photo.jpg",
|
||||
});
|
||||
|
||||
// Caption should be included with media
|
||||
expect(sendPhoto).toHaveBeenCalledWith(chatId, expect.anything(), {
|
||||
caption: shortText,
|
||||
});
|
||||
// No separate text message needed
|
||||
expect(sendMessage).not.toHaveBeenCalled();
|
||||
expect(res.messageId).toBe("72");
|
||||
});
|
||||
|
||||
it("preserves thread params when splitting long captions", async () => {
|
||||
const chatId = "-1001234567890";
|
||||
const longText = "C".repeat(1100);
|
||||
|
||||
const sendPhoto = vi.fn().mockResolvedValue({
|
||||
message_id: 73,
|
||||
chat: { id: chatId },
|
||||
});
|
||||
const sendMessage = vi.fn().mockResolvedValue({
|
||||
message_id: 74,
|
||||
chat: { id: chatId },
|
||||
});
|
||||
const api = { sendPhoto, sendMessage } as unknown as {
|
||||
sendPhoto: typeof sendPhoto;
|
||||
sendMessage: typeof sendMessage;
|
||||
};
|
||||
|
||||
loadWebMedia.mockResolvedValueOnce({
|
||||
buffer: Buffer.from("fake-image"),
|
||||
contentType: "image/jpeg",
|
||||
fileName: "photo.jpg",
|
||||
});
|
||||
|
||||
await sendMessageTelegram(chatId, longText, {
|
||||
token: "tok",
|
||||
api,
|
||||
mediaUrl: "https://example.com/photo.jpg",
|
||||
messageThreadId: 271,
|
||||
replyToMessageId: 500,
|
||||
});
|
||||
|
||||
// Media sent with thread params but no caption
|
||||
expect(sendPhoto).toHaveBeenCalledWith(chatId, expect.anything(), {
|
||||
caption: undefined,
|
||||
message_thread_id: 271,
|
||||
reply_to_message_id: 500,
|
||||
});
|
||||
// Text message also includes thread params (plain text, matching caption behavior)
|
||||
expect(sendMessage).toHaveBeenCalledWith(chatId, longText, {
|
||||
message_thread_id: 271,
|
||||
reply_to_message_id: 500,
|
||||
});
|
||||
});
|
||||
|
||||
it("puts reply_markup only on follow-up text when splitting", async () => {
|
||||
const chatId = "123";
|
||||
const longText = "D".repeat(1100);
|
||||
|
||||
const sendPhoto = vi.fn().mockResolvedValue({
|
||||
message_id: 75,
|
||||
chat: { id: chatId },
|
||||
});
|
||||
const sendMessage = vi.fn().mockResolvedValue({
|
||||
message_id: 76,
|
||||
chat: { id: chatId },
|
||||
});
|
||||
const api = { sendPhoto, sendMessage } as unknown as {
|
||||
sendPhoto: typeof sendPhoto;
|
||||
sendMessage: typeof sendMessage;
|
||||
};
|
||||
|
||||
loadWebMedia.mockResolvedValueOnce({
|
||||
buffer: Buffer.from("fake-image"),
|
||||
contentType: "image/jpeg",
|
||||
fileName: "photo.jpg",
|
||||
});
|
||||
|
||||
await sendMessageTelegram(chatId, longText, {
|
||||
token: "tok",
|
||||
api,
|
||||
mediaUrl: "https://example.com/photo.jpg",
|
||||
buttons: [[{ text: "Click me", callback_data: "action:click" }]],
|
||||
});
|
||||
|
||||
// Media sent WITHOUT reply_markup
|
||||
expect(sendPhoto).toHaveBeenCalledWith(chatId, expect.anything(), {
|
||||
caption: undefined,
|
||||
});
|
||||
// Follow-up text has the reply_markup
|
||||
expect(sendMessage).toHaveBeenCalledWith(chatId, longText, {
|
||||
reply_markup: {
|
||||
inline_keyboard: [[{ text: "Click me", callback_data: "action:click" }]],
|
||||
},
|
||||
});
|
||||
});
|
||||
|
||||
it("includes thread params and reply_markup on follow-up text when splitting", async () => {
|
||||
const chatId = "-1001234567890";
|
||||
const longText = "F".repeat(1100);
|
||||
|
||||
const sendPhoto = vi.fn().mockResolvedValue({
|
||||
message_id: 78,
|
||||
chat: { id: chatId },
|
||||
});
|
||||
const sendMessage = vi.fn().mockResolvedValue({
|
||||
message_id: 79,
|
||||
chat: { id: chatId },
|
||||
});
|
||||
const api = { sendPhoto, sendMessage } as unknown as {
|
||||
sendPhoto: typeof sendPhoto;
|
||||
sendMessage: typeof sendMessage;
|
||||
};
|
||||
|
||||
loadWebMedia.mockResolvedValueOnce({
|
||||
buffer: Buffer.from("fake-image"),
|
||||
contentType: "image/jpeg",
|
||||
fileName: "photo.jpg",
|
||||
});
|
||||
|
||||
await sendMessageTelegram(chatId, longText, {
|
||||
token: "tok",
|
||||
api,
|
||||
mediaUrl: "https://example.com/photo.jpg",
|
||||
messageThreadId: 271,
|
||||
replyToMessageId: 500,
|
||||
buttons: [[{ text: "Click me", callback_data: "action:click" }]],
|
||||
});
|
||||
|
||||
expect(sendPhoto).toHaveBeenCalledWith(chatId, expect.anything(), {
|
||||
caption: undefined,
|
||||
message_thread_id: 271,
|
||||
reply_to_message_id: 500,
|
||||
});
|
||||
expect(sendMessage).toHaveBeenCalledWith(chatId, longText, {
|
||||
message_thread_id: 271,
|
||||
reply_to_message_id: 500,
|
||||
reply_markup: {
|
||||
inline_keyboard: [[{ text: "Click me", callback_data: "action:click" }]],
|
||||
},
|
||||
});
|
||||
});
|
||||
|
||||
it("wraps chat-not-found errors from follow-up message", async () => {
|
||||
const chatId = "123";
|
||||
const longText = "G".repeat(1100);
|
||||
|
||||
const sendPhoto = vi.fn().mockResolvedValue({
|
||||
message_id: 80,
|
||||
chat: { id: chatId },
|
||||
});
|
||||
const sendMessage = vi
|
||||
.fn()
|
||||
.mockRejectedValue(new Error("400: Bad Request: chat not found"));
|
||||
const api = { sendPhoto, sendMessage } as unknown as {
|
||||
sendPhoto: typeof sendPhoto;
|
||||
sendMessage: typeof sendMessage;
|
||||
};
|
||||
|
||||
loadWebMedia.mockResolvedValueOnce({
|
||||
buffer: Buffer.from("fake-image"),
|
||||
contentType: "image/jpeg",
|
||||
fileName: "photo.jpg",
|
||||
});
|
||||
|
||||
await expect(
|
||||
sendMessageTelegram(chatId, longText, {
|
||||
token: "tok",
|
||||
api,
|
||||
mediaUrl: "https://example.com/photo.jpg",
|
||||
}),
|
||||
).rejects.toThrow(
|
||||
/Telegram send failed: chat not found \(chat_id=123\)\./,
|
||||
);
|
||||
});
|
||||
|
||||
it("does not send follow-up text when caption is empty", async () => {
|
||||
const chatId = "123";
|
||||
const emptyText = " ";
|
||||
|
||||
const sendPhoto = vi.fn().mockResolvedValue({
|
||||
message_id: 81,
|
||||
chat: { id: chatId },
|
||||
});
|
||||
const sendMessage = vi.fn();
|
||||
const api = { sendPhoto, sendMessage } as unknown as {
|
||||
sendPhoto: typeof sendPhoto;
|
||||
sendMessage: typeof sendMessage;
|
||||
};
|
||||
|
||||
loadWebMedia.mockResolvedValueOnce({
|
||||
buffer: Buffer.from("fake-image"),
|
||||
contentType: "image/jpeg",
|
||||
fileName: "photo.jpg",
|
||||
});
|
||||
|
||||
const res = await sendMessageTelegram(chatId, emptyText, {
|
||||
token: "tok",
|
||||
api,
|
||||
mediaUrl: "https://example.com/photo.jpg",
|
||||
});
|
||||
|
||||
expect(sendPhoto).toHaveBeenCalledWith(chatId, expect.anything(), {
|
||||
caption: undefined,
|
||||
});
|
||||
expect(sendMessage).not.toHaveBeenCalled();
|
||||
expect(res.messageId).toBe("81");
|
||||
});
|
||||
|
||||
it("keeps reply_markup on media when not splitting", async () => {
|
||||
const chatId = "123";
|
||||
const shortText = "E".repeat(100);
|
||||
|
||||
const sendPhoto = vi.fn().mockResolvedValue({
|
||||
message_id: 77,
|
||||
chat: { id: chatId },
|
||||
});
|
||||
const sendMessage = vi.fn();
|
||||
const api = { sendPhoto, sendMessage } as unknown as {
|
||||
sendPhoto: typeof sendPhoto;
|
||||
sendMessage: typeof sendMessage;
|
||||
};
|
||||
|
||||
loadWebMedia.mockResolvedValueOnce({
|
||||
buffer: Buffer.from("fake-image"),
|
||||
contentType: "image/jpeg",
|
||||
fileName: "photo.jpg",
|
||||
});
|
||||
|
||||
await sendMessageTelegram(chatId, shortText, {
|
||||
token: "tok",
|
||||
api,
|
||||
mediaUrl: "https://example.com/photo.jpg",
|
||||
buttons: [[{ text: "Click me", callback_data: "action:click" }]],
|
||||
});
|
||||
|
||||
// Media sent WITH reply_markup when not splitting
|
||||
expect(sendPhoto).toHaveBeenCalledWith(chatId, expect.anything(), {
|
||||
caption: shortText,
|
||||
reply_markup: {
|
||||
inline_keyboard: [[{ text: "Click me", callback_data: "action:click" }]],
|
||||
},
|
||||
});
|
||||
expect(sendMessage).not.toHaveBeenCalled();
|
||||
});
|
||||
});
|
||||
@@ -54,6 +54,10 @@ type TelegramReactionOpts = {
|
||||
|
||||
const PARSE_ERR_RE = /can't parse entities|parse entities|find end of the entity/i;
|
||||
|
||||
// Telegram limits media captions to 1024 characters.
|
||||
// Text beyond this must be sent as a separate follow-up message.
|
||||
const TELEGRAM_MAX_CAPTION_LENGTH = 1024;
|
||||
|
||||
function resolveToken(explicit: string | undefined, params: { accountId: string; token: string }) {
|
||||
if (explicit?.trim()) return explicit.trim();
|
||||
if (!params.token) {
|
||||
@@ -195,16 +199,22 @@ export async function sendMessageTelegram(
|
||||
});
|
||||
const fileName = media.fileName ?? (isGif ? "animation.gif" : inferFilename(kind)) ?? "file";
|
||||
const file = new InputFile(media.buffer, fileName);
|
||||
const caption = text?.trim() || undefined;
|
||||
const trimmedText = text?.trim() || "";
|
||||
// If text exceeds Telegram's caption limit, send media without caption
|
||||
// then send text as a separate follow-up message.
|
||||
const needsSeparateText = trimmedText.length > TELEGRAM_MAX_CAPTION_LENGTH;
|
||||
const caption = needsSeparateText ? undefined : trimmedText || undefined;
|
||||
// When splitting, put reply_markup only on the follow-up text (the "main" content),
|
||||
// not on the media message.
|
||||
const mediaParams = hasThreadParams
|
||||
? {
|
||||
caption,
|
||||
...threadParams,
|
||||
...(replyMarkup ? { reply_markup: replyMarkup } : {}),
|
||||
...(!needsSeparateText && replyMarkup ? { reply_markup: replyMarkup } : {}),
|
||||
}
|
||||
: {
|
||||
caption,
|
||||
...(replyMarkup ? { reply_markup: replyMarkup } : {}),
|
||||
...(!needsSeparateText && replyMarkup ? { reply_markup: replyMarkup } : {}),
|
||||
};
|
||||
let result:
|
||||
| Awaited<ReturnType<typeof api.sendPhoto>>
|
||||
@@ -258,13 +268,41 @@ export async function sendMessageTelegram(
|
||||
},
|
||||
);
|
||||
}
|
||||
const messageId = String(result?.message_id ?? "unknown");
|
||||
const mediaMessageId = String(result?.message_id ?? "unknown");
|
||||
const resolvedChatId = String(result?.chat?.id ?? chatId);
|
||||
recordChannelActivity({
|
||||
channel: "telegram",
|
||||
accountId: account.accountId,
|
||||
direction: "outbound",
|
||||
});
|
||||
return { messageId, chatId: String(result?.chat?.id ?? chatId) };
|
||||
|
||||
// If text was too long for a caption, send it as a separate follow-up message.
|
||||
// Use plain text to match caption behavior (captions don't use HTML conversion).
|
||||
if (needsSeparateText && trimmedText) {
|
||||
const textParams =
|
||||
hasThreadParams || replyMarkup
|
||||
? {
|
||||
...threadParams,
|
||||
...(replyMarkup ? { reply_markup: replyMarkup } : {}),
|
||||
}
|
||||
: undefined;
|
||||
const textRes = await request(
|
||||
() =>
|
||||
textParams
|
||||
? api.sendMessage(chatId, trimmedText, textParams)
|
||||
: api.sendMessage(chatId, trimmedText),
|
||||
"message",
|
||||
).catch((err) => {
|
||||
throw wrapChatNotFound(err);
|
||||
});
|
||||
// Return the text message ID as the "main" message (it's the actual content).
|
||||
return {
|
||||
messageId: String(textRes?.message_id ?? mediaMessageId),
|
||||
chatId: resolvedChatId,
|
||||
};
|
||||
}
|
||||
|
||||
return { messageId: mediaMessageId, chatId: resolvedChatId };
|
||||
}
|
||||
|
||||
if (!text || !text.trim()) {
|
||||
|
||||
Reference in New Issue
Block a user