puregram-stream
Skill3 starsChanged 5 months agoNo licenceView on GitHub
use when working with `@puregram/stream` in puregram v3 — bridge any `AsyncIterable<string>` or LLM SDK stream to telegram via animated `sendMessageDraft` previews and a terminal `sendMessage`. covers `.extend(stream())`, `update.stream(source, opts?)` / `tg.stream({ chat_id, source, ... })`, the eight built-in adapters (`fromOpenAI` / `fromAnthropic` / `fromVercelAI` / `fromOllama` / `fromLangChain` / `fromTextStream` / `fromBytes` / `fromEventEmitter`) plus duck-typed auto-detect, `parseMode: 'MarkdownV2' | 'HTML'` integration with `@puregram/markup`, `editIntervalMs` / `maxEditBackoff` / `thinkingPlaceholder` pacing, `signal` aborts, the user-facing stop button (`canStop` / `keepOnStop` / `result.stopped`), the 4096-char rollover, rich-message streaming via `rich` (`sendRichMessageDraft` + `sendRichMessage`, 32768-char limit), and the `StreamResult` return shape. private-chat-only.
- Reads credentials
In this repository24 other files it gives its agents.
- puregram-callback-dataSkill
- puregram-file-idSkill
- puregram-flowSkill
- puregram-inline-message-idSkill
- puregram-markupSkill
- puregram-media-cacherSkill
- puregram-rate-limitSkill
- puregram-richSkill
- puregram-scenesSkill
- puregram-sessionSkill
- puregram-storageSkill
- puregram-testingSkill
- puregram-throttlerSkill
- puregram-utilsSkill
- rich-message-authoringSkill
- telegram-bot-apiSkill
- telegram-business-botsSkill
- telegram-ephemeral-messagesSkill
- telegram-groupsSkill
- telegram-guest-modeSkill
- telegram-inline-modeSkill
- telegram-rich-messagesSkill
- telegram-streaming-repliesSkill
- using-puregramSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.