caffeinelabs

MANDATORY recipe for every Caffeine build that calls an LLM, chatbot, GPT, or ChatGPT **on Caffeine Inference** (no user-pasted OpenAI key). The ONLY supported path is the `caffeineai-inference-client` mops package with `Config.fromEnv<system>()`, which hands…

MANDATORY recipe for every Caffeine build that calls OpenAI (ChatGPT, GPT-4o, an LLM, a chatbot, embeddings). The ONLY supported path is the `openai-client` mops package with a canister-side API-key bearer. Hand-rolling `ic.http_request` to…

EXPERIMENTAL, UNTESTED recipe for posting messages to a Slack workspace from a Caffeine canister via the `slack-client` mops package (Slack Web API). Use it when the user wants their app to send a message to a Slack channel — "post to Slack", "notify a…

Authorization system with role-based access control. Must-have for all apps that manage personal or access-restricted data.

Core infrastructure providing backend connection configuration, storage client, and React app entry point.

Make a canister's data queryable by the Caffeine Data Intelligence agent. Use whenever an app stores structured data (Maps/Lists/arrays of records) that should be answerable in natural language — "top customers", "revenue by region", "active projects". Adds a…

Quick reference for the Caffeine Data Intelligence agent to query an OQL-exposing canister (schema() + execute()) through the `icp` CLI against the project's `backend` canister: read the schema, form JSON queries (filter / order / paginate / aggregate /…

Motoko language reference, architecture patterns, and dependency tooling (mops). Load when writing or modifying backend .mo files.

List, inspect, and clean up Caffeine projects, and read their draft and live deployment state. Use when someone asks what they have, what a project's status is, or wants one removed.

Send a change to an existing Caffeine project's agent, answer its questions, and verify the result deployed. Use when modifying an app that already exists.

Download a Caffeine project's Motoko and frontend source, edit it in this workspace, validate it, and upload it back. Use when someone wants to work on the code directly instead of prompting the Caffeine agent.

Start a new Caffeine app from a plain-language brief and hand back the draft and chat links. Use when someone wants to spin up a fresh project.

Manage Motoko projects with the mops CLI — toolchain pinning, dependency management, type-checking, building, and linting. Use when working with mops.toml, mops.lock, running mops commands, adding/removing packages, pinning moc or lintoko versions, checking…

Test frontend changes end-to-end and deploy to staging for verification. Use when testing frontend PRs, verifying frontend migrations, testing UI changes, or when the user asks to test the frontend before production. Covers automated checks, local dev server…

Build the Motoko compiler (moc) and run tests in the motoko repo. Use when the user asks to build, compile, rebuild, run tests, run test-runner, or verify changes to OCaml source files.

Write and debug lintoko lint rules for Motoko using TOML and tree-sitter queries. Use when creating, editing, or reviewing lintoko rule files, when the user mentions lintoko rules or Motoko linting rules, or when writing tree-sitter queries for Motoko code…

Use the `twilio-client` mops package for any request involving Twilio messaging — sending SMS / MMS, configuring a Messaging Service, A2P 10DLC brand registration / campaigns, toll-free verification, alpha / channel senders, short codes, link shortening,…

Use the `spotify-client` mops package whenever the user asks the canister to look up music catalog data on Spotify (albums, artists, tracks, playlists, search, new releases, genres, markets) or to drive a user's Spotify account (their library,…