1.2 KiB
1.2 KiB
Next Steps — Codex App Server: Embeddable Agent Protocol & BYO Auth
Part of codex-app-server-byo-auth/index
Decisions pending
- Pick the target app shape first: local/desktop (stable, recommended) vs hosted multi-tenant (experimental transport, more work)
- For hosted: decide key placement — user's browser (localStorage) vs your DB vs Codex-managed device-code tokens
- For hosted: contact OpenAI for the known-clients list / compliance assessment before building for enterprise
Build considerations
- Prototype the device-code flow with a minimal app-server client (Node/TS) to validate the no-sign-in UX
- Design the provider adapter interface (Effect Layer):
ApiKeyProvidervsChatGptAuthProvider - Evaluate per-version bindings (
generate-ts/generate-json-schema) for type safety - Consider Codex SDK for any CI/headless automation needs (separate from app-server embedding)
Open questions
- Does OpenAI's BYO-ChatGPT posture change over time? (monitor; Anthropic precedent exists)
- What's the real token-refresh behavior of
chatgptAuthTokensmode in production? - Rate-limit surfacing: which plan limits matter per target user base?