telegram

Changed

Notey now summarises long conversations on Discord, Slack, WhatsApp and iMessage too, instead of only reading the last 20 messages. On Telegram, a reply that failed to send is delivered again later, marked as delayed.

Changed

Notey’s answers now stream in as they are written, in the app and in Telegram. Long conversations are summarised instead of cut off, and a model that keeps failing is skipped for a while rather than retried every time. You can tell Notey to forget something it remembered, and scheduling a note that is nearly the same as one already queued asks first.

Added

Voice notes sent to Notey on Telegram are transcribed and answered like text, with spoken replies as an option (off by default). A new Spend card in the AI tab shows this month’s usage and lets you cap what runs on your own key.

Added

Settings can now pair a Telegram, Discord, Slack, WhatsApp or iMessage chat with Notey using a one-time code, list the paired chats and unpair them. The daily digest also reports anything that has stopped running or is stuck, on every channel you get it on.

Added

Connect your own BlueBubbles server in Settings and Notey answers your iMessages, mirrors the daily digest, and lets you approve or dismiss proposals by replying "approve 2" or "dismiss all". It only answers the one number you allow, and ignores group chats.

Added

The Telegram agent no longer only replies to you — it can push messages to your chat on its own and react to your latest message with an emoji (or retract one). message.send sends a proactive note to your own chat (e.g. "digest queued" or "clip render finished") via the agent's Telegram connection; message.react attaches a single emoji reaction to your most recent message (or a specific one by id) via Telegram's setMessageReaction. Both are registry capabilities (message.send / message.react) exposed through the MCP adapter and the telegram-agent TOOL_EXECUTORS, gated on canWrite like other draft-tier tools, and blocked for sub-agents so a detached agent can never message you. The not-connected case returns an honest refusal instead of throwing. Ported from Hermes' MIT send_message_tool.py and react_to_message_tool.py.

Added

Discord joins Telegram as a conversational agent surface (A4 stage 1). Bring your own Discord bot (no OAuth app on our side — same BYOK class as Telegram): connect in Settings, Team, Discord with a bot token + application id, then @ your bot in any channel it can see and it replies via the same Notey engine. Slash-command deferred responses, follow-up message delivery, and the same role-check + connection-verification flow as Telegram. Bot tokens are encrypted at rest; the application id resolves the account from interaction payloads.

Added

Slack joins Telegram and Discord as a conversational agent surface (A4 stage 2). Bring your own Slack bot (no OAuth app on our side): connect in Settings, Team, Slack with a bot token + signing secret + team id (verified via auth.test before saving), then DM or @ your bot and it replies via the same Notey engine. Slack Events API signature verification (X-Slack-Signature HMAC), url_verification challenge handshake, and fire-and-forget deferred generation so retries never race with generation. Bot tokens and signing secrets are encrypted at rest.

Added

WhatsApp joins Telegram, Slack, and Discord as a conversational agent surface (A4 stage 2). Bring your own Meta App with WhatsApp Business API access: connect in Settings, Team, WhatsApp with an access token + phone number id + verify token + phone number (verified via Graph API before saving), then message your business account and it replies via the same Notey engine. Webhook challenge-response verification (verify token is hashed, never stored plain) and fire-and-forget deferred generation so retries never race with generation. Access tokens are encrypted at rest; the phone number id and phone number are stored plain like Discord application ids.

Changed

The bot webhook used a hardcoded if-chain for its single command (/selftest). Everything now goes through a slash-command registry in one file: adding a new command is a registry entry, never another conditional in the route. /help derives from the registry so it always reflects reality, and a mistyped command gets an honest "unknown command" reply instead of wasting a model turn.

Added

Notey could only talk when talked to. Now it can open the conversation: once a day it sends a Telegram digest of what it sees coming — notes scheduled in the next 24 hours, anything that failed to publish, drafts still waiting on you, evergreen pieces that have never gone out, and subscriber counts but only when they’ve actually been measured. When there’s genuinely nothing to report, it says so instead of inventing filler. It reports and suggests — it never queues or publishes anything on its own.

Fixed

Connecting a bot used to accept destinations that could never work: paste your bot’s own numeric id (or its @username) as the chat and the connection saved cleanly — then every scheduled note to it died with “Forbidden: the bot can’t send messages to the bot”, surfacing only as a stuck retrying note. The connect step now catches both forms on the spot and tells you what to use instead.

Fixed

Talking to Notey over Telegram could feel broken: a thoughtful answer sometimes took longer than Telegram was willing to wait, so the message looked like it vanished — or came through twice when the delivery was retried. The heavy thinking now happens after the delivery is acknowledged instead of during it, so every message is received exactly once and the reply lands whenever the answer is ready. Your words are still saved first, before anything else runs.

Changed

Ask "who are you" in the Telegram chat or the in-app Notey panel and the answer used to be whatever raw model name was configured that day. Every conversation now opens from a fixed identity: Notey, NoteSurge's content agent, running on its current AI model (named for transparency, never claimed as self). Works identically on both surfaces because they share one agent loop.

Added

Notey used to live only in Telegram: to ask about your queue or request a draft you left the app and opened a chat there. Now the AI tab has its own chat panel, wired to the very same assistant and the very same conversation history — ask something here and your Telegram bot sees it too; reply from your phone later and it shows up here. Nothing new to set up: if Notey has a model key it works immediately, with or without the Telegram connection.

Added

Notey acts as a member of your workspace, so it should play by the same rules you do. The agent's abilities now follow the role of the person whose workspace it serves: give that seat viewer access and Notey can look things up but not draft; make it a contributor and it drafts freely but never schedules, even with agent publishing switched on. Change the role in the Team tab and Notey's next move already reflects it — no re-setup needed. On top of that, every tool call spends from a per-workspace budget, so a confused or looping request can't hammer your connected accounts.

Added

Ask Notey for something like "turn this essay into a week of content" or "do an archive dive — five fresh Notes from stuff I already wrote," and it now runs the whole play as a named skill instead of improvising call by call. Before anything happens, Notey shows you the plan — every step it's about to take — and only runs it once you're good with it. Three skills ship today: essay-to-week-of-content, winner-to-carousel-and-thread, and archive-dive-fresh-notes.

Added

Notey has been able to look things up and draft for you for a little while now — but the Team activity feed only showed the results, not what Notey actually did to get there. Now every tool Notey runs lands its own line in the feed: "Notey ran notes.list" reads differently from you scheduling a post, because it should. That covers the quiet stuff too — what Notey looked at, and when a call failed — so you can always answer "what has the agent been doing in my workspace?" without guessing.

Added

Your Telegram co-writer can now do more than save drafts. With the new "Allow agent publishing" switch on (Settings > AI, off by default), asking Notey to schedule a post queues it as a Proposal — it lands in your Queue tab with an Approve/Decline pair and goes out only after you tap Approve, one post at a time. Without the switch, Notey simply has no scheduling tool at all; nothing about your existing setup changes.

Added

Message your own Telegram bot and it writes back like a co-writer, not a form. Riff on an idea, ask it to draft a Note in your own voice (it learns that from your last 15 published notes), or let it ask a few sharp questions when you’re stuck and don’t know what you’re trying to say yet.

Every reply has a save button under it that drops the text straight into your Library as an editable idea.

Added

Post straight to a Discord channel through an incoming webhook, or to a Telegram chat through a bot token from @BotFather.

Neither one touches OAuth, neither one goes through Typefully, and neither one needs anybody’s app review.