Pranit b9be2de170 Run libfx agents on Codex with ChatGPT sign-in ...

- Run a libfx agent on Codex with `provider: "codex"`: model requests and the model list go to ChatGPT's Codex endpoints through the host's `fetch` instead of AI Gateway.
- Supply each session's ChatGPT credentials through a `chatgpt` callback. libfx adds them only to Codex requests, so tokens never reach the engine or a saved session.
- Refresh ChatGPT tokens five minutes before they expire and once after a 401, and pass the new tokens to `onChatgptCredentials`.
- Continue a durable Codex session in a new process, which asks `chatgpt` for that session's credentials.
- Sign in with ChatGPT from `libfx/chatgpt` by pasting the callback address, or with device code where the workspace allows it, and refresh tokens from there.

2026-10-10 20:22:57 -04:00

..

build-node-cjs.mjs

Fix libfx loading in Node deployments

2026-09-06 13:18:36 -04:00

bundle-durable.mjs

Accept an app's World, ship types, and bound repeated deadline cut-offs

2026-10-08 22:27:30 -04:00

check-linux-abi.py

Fix libfx loading in Node deployments

2026-09-06 13:18:36 -04:00

package-libfx.mjs

Run libfx agents on Codex with ChatGPT sign-in

2026-10-10 20:22:57 -04:00

package-term-demo.mjs

Fix libfx loading in Node deployments

2026-09-06 13:18:36 -04:00