feat(app-server): support external auth mode (#10012)

This enables a new use case where `codex app-server` is embedded into a
parent application that will directly own the user's ChatGPT auth
lifecycle, which means it owns the user’s auth tokens and refreshes it
when necessary. The parent application would just want a way to pass in
the auth tokens for codex to use directly.

The idea is that we are introducing a new "auth mode" currently only
exposed via app server: **`chatgptAuthTokens`** which consist of the
`id_token` (stores account metadata) and `access_token` (the bearer
token used directly for backend API calls). These auth tokens are only
stored in-memory. This new mode is in addition to the existing `apiKey`
and `chatgpt` auth modes.

This PR reuses the shape of our existing app-server account APIs as much
as possible:
- Update `account/login/start` with a new `chatgptAuthTokens` variant,
which will allow the client to pass in the tokens and have codex
app-server use them directly. Upon success, the server emits
`account/login/completed` and `account/updated` notifications.
- A new server->client request called
`account/chatgptAuthTokens/refresh` which the server can use whenever
the access token previously passed in has expired and it needs a new one
from the parent application.

I leveraged the core 401 retry loop which typically triggers auth token
refreshes automatically, but made it pluggable:
- **chatgpt** mode refreshes internally, as usual.
- **chatgptAuthTokens** mode calls the client via
`account/chatgptAuthTokens/refresh`, the client responds with updated
tokens, codex updates its in-memory auth, then retries. This RPC has a
10s timeout and handles JSON-RPC errors from the client.

Also some additional things:
- chatgpt logins are blocked while external auth is active (have to log
out first. typically clients will pick one OR the other, not support
both)
- `account/logout` clears external auth in memory
- Ensures that if `forced_chatgpt_workspace_id` is set via the user's
config, we respect it in both:
- `account/login/start` with `chatgptAuthTokens` (returns a JSON-RPC
error back to the client)
- `account/chatgptAuthTokens/refresh` (fails the turn, and on next
request app-server will send another `account/chatgptAuthTokens/refresh`
request to the client).
This commit is contained in:
Owen Lin
2026-01-29 15:46:04 -08:00
committed by GitHub
parent b79bf69af6
commit 81a17bb2c1
25 changed files with 1577 additions and 79 deletions

View File

@@ -29,11 +29,13 @@ use codex_app_server_protocol::GetAuthStatusParams;
use codex_app_server_protocol::InitializeParams;
use codex_app_server_protocol::InterruptConversationParams;
use codex_app_server_protocol::JSONRPCError;
use codex_app_server_protocol::JSONRPCErrorError;
use codex_app_server_protocol::JSONRPCMessage;
use codex_app_server_protocol::JSONRPCNotification;
use codex_app_server_protocol::JSONRPCRequest;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::ListConversationsParams;
use codex_app_server_protocol::LoginAccountParams;
use codex_app_server_protocol::LoginApiKeyParams;
use codex_app_server_protocol::ModelListParams;
use codex_app_server_protocol::NewConversationParams;
@@ -298,6 +300,20 @@ impl McpProcess {
self.send_request("account/read", params).await
}
/// Send an `account/login/start` JSON-RPC request with ChatGPT auth tokens.
pub async fn send_chatgpt_auth_tokens_login_request(
&mut self,
id_token: String,
access_token: String,
) -> anyhow::Result<i64> {
let params = LoginAccountParams::ChatgptAuthTokens {
id_token,
access_token,
};
let params = Some(serde_json::to_value(params)?);
self.send_request("account/login/start", params).await
}
/// Send a `feedback/upload` JSON-RPC request.
pub async fn send_feedback_upload_request(
&mut self,
@@ -608,6 +624,15 @@ impl McpProcess {
.await
}
pub async fn send_error(
&mut self,
id: RequestId,
error: JSONRPCErrorError,
) -> anyhow::Result<()> {
self.send_jsonrpc_message(JSONRPCMessage::Error(JSONRPCError { id, error }))
.await
}
pub async fn send_notification(
&mut self,
notification: ClientNotification,