martmull
c2ca90c255
<img width="948" height="593" alt="image" src="https://github.com/user-attachments/assets/d990fa98-3cfd-469d-ab7f-0b2d4ccf3afc" /> <img width="1361" height="802" alt="image" src="https://github.com/user-attachments/assets/1091f598-49f3-4c16-92ea-1e1c200181e2" /> ## Add `runAgent()` to the Logic Function SDK Lets an app's logic function run one of its own AI agents server-side and get the result back synchronously — reusing the existing agent executor instead of a new bespoke transport. ### Backend - New **`runAgent` GraphQL mutation** (metadata schema) in `ai-agent-execution`, wrapping the existing `AgentAsyncExecutorService.executeAgent`. Scopes the agent lookup to the calling application and runs it under an application auth context. - New `@AuthApplication()` param decorator (mirrors `@AuthWorkspace()`) — first GraphQL resolver authenticated by an **application access token**. - Guarded by `WorkspaceAuthGuard` + `SettingsPermissionGuard(PermissionFlagType.AI)`: the app's role must grant the `AI` permission flag. ### SDK - `runAgent({ agentUniversalIdentifier, prompt })` posts the mutation to `/metadata` with the app token via a new runtime GraphQL transport. Returns `{ result, hasNoMoreAvailableCredits }`. - Refactored the connections helpers onto a shared `postAppEndpoint` util (removes duplicated transport logic). ### Frontend - App install permission modal now shows an explicit consent line — _"Run AI agents and bill AI credits to your workspace"_ — when the app's role requests the `AI` flag. ### Docs - Documented `runAgent` and its `AI` permission-flag requirement in _Skills & Agents_. - Fixed outdated role-permission examples in _Roles & Permissions_ (`permissionFlags` → `permissionFlagUniversalIdentifiers`, `PermissionFlag` → `SystemPermissionFlag`). ### Test plan - [x] SDK unit tests (`run-agent.spec.ts`) — request shape, GraphQL/HTTP error handling, missing env vars - [x] `twenty-server`, `twenty-front`, `twenty-shared` typecheck + lint - [ ] Manual: install an app granting the `AI` flag, call `runAgent()` from a logic function, confirm the agent runs and credits are billed --------- Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
Twenty SDK
A CLI and SDK to develop, build, and publish applications that extend Twenty CRM.
Quick start
The recommended way to start is with create-twenty-app:
npx create-twenty-app@latest my-twenty-app
cd my-twenty-app
yarn twenty dev
Documentation
Full documentation is available at docs.twenty.com/developers/extend/apps:
- Getting Started — scaffolding, local server, authentication, dev mode
- Building Apps — entity definitions, API clients, testing, CLI reference
- Publishing — deploy, npm publish, marketplace
Manual installation
If you are adding twenty-sdk to an existing project instead of using create-twenty-app:
yarn add twenty-sdk twenty-client-sdk
Then add a twenty script to your package.json:
{
"scripts": {
"twenty": "twenty"
}
}
Run yarn twenty help to see all available commands.
Configuration
The CLI stores credentials per remote in ~/.twenty/config.json. Run yarn twenty remote:add to configure a remote, or yarn twenty remote:list to see existing ones.
Troubleshooting
- Auth errors: run
yarn twenty remote:addto re-authenticate. - Typings out of date: restart
yarn twenty devto refresh the client and types. - Not seeing changes in dev: make sure dev mode is running (
yarn twenty dev).
Contributing
Development setup
git clone https://github.com/twentyhq/twenty.git
cd twenty
yarn install
Development mode
npx nx run twenty-sdk:dev
Production build
npx nx run twenty-sdk:build
Running the CLI locally
npx nx run twenty-sdk:start -- <command>