mirror of
https://github.com/openai/codex.git
synced 2026-10-27 18:48:37 +00:00
Channing Conger
ee6257ae1c
Add experimental app-server support for connection-owned dynamic tool providers over both `stdio` and websocket.
Clients can now:
- register a tool with `toolProvider/register`
- unregister it with `toolProvider/unregister`
Registered tools are stored in an app-server registry, mapped back to the owning connection, and routed through the existing dynamic tool call flow. Tools with `injectIntoContext: true` are exposed to the model; tools with `injectIntoContext: false` remain callable only from `js_repl` via `codex.tool(...)`.
This also extends dynamic tool call events with `thread_id` so provider-owned tools can be invoked from newly created or resumed threads.
```mermaid
sequenceDiagram
participant Client as Provider Client
participant AppServer as App Server
participant ThreadClient as Thread Client
participant Core as Core Thread
Client->>AppServer: toolProvider/register(tool)
AppServer->>AppServer: store tool -> owning connection
ThreadClient->>AppServer: thread/start
AppServer->>Core: load thread + sync registered tools
ThreadClient->>AppServer: turn/start
AppServer->>Core: submit user input
Core-->>AppServer: DynamicToolCallRequest(thread_id, tool, args, provider_owned=true)
AppServer->>Client: item/tool/call
Client-->>AppServer: DynamicToolCallResponse
AppServer->>Core: submit dynamic tool response
Core-->>AppServer: continue turn
npm i -g @openai/codex
or brew install --cask codex
Codex CLI is a coding agent from OpenAI that runs locally on your computer.
If you want Codex in your code editor (VS Code, Cursor, Windsurf), install in your IDE.
If you want the desktop app experience, run
codex app or visit the Codex App page.
If you are looking for the cloud-based agent from OpenAI, Codex Web, go to chatgpt.com/codex.
Quickstart
Installing and running Codex CLI
Install globally with your preferred package manager:
# Install using npm
npm install -g @openai/codex
# Install using Homebrew
brew install --cask codex
Then simply run codex to get started.
You can also go to the latest GitHub Release and download the appropriate binary for your platform.
Each GitHub Release contains many executables, but in practice, you likely want one of these:
- macOS
- Apple Silicon/arm64:
codex-aarch64-apple-darwin.tar.gz - x86_64 (older Mac hardware):
codex-x86_64-apple-darwin.tar.gz
- Apple Silicon/arm64:
- Linux
- x86_64:
codex-x86_64-unknown-linux-musl.tar.gz - arm64:
codex-aarch64-unknown-linux-musl.tar.gz
- x86_64:
Each archive contains a single entry with the platform baked into the name (e.g., codex-x86_64-unknown-linux-musl), so you likely want to rename it to codex after extracting it.
Using Codex with your ChatGPT plan
Run codex and select Sign in with ChatGPT. We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Team, Edu, or Enterprise plan. Learn more about what's included in your ChatGPT plan.
You can also use Codex with an API key, but this requires additional setup.
Docs
This repository is licensed under the Apache-2.0 License.