The best way to control Claude Code, Codex and more from any computer or phone
Mirrored from https://github.com/Camo67/t3code.git
Synced Nov 22, 02:00 UTC
fix(codex): explain speed limits on managed connections (#30322)
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
shivam committed
Nov 7, 2026 at 13:24 UTC
0f4a13071090e89c6d7eccdb0eb98b3cde1823ee
3 files changed
+33
-4
apps/mobile/src/features/threads/ChatGptSharingStatus.tsx
+1
@@ -19,6 +19,7 @@ export function ChatGptSharingStatus({ provider }: { provider: ServerProvider |
19
[
20
provider?.auth.email,
21
"Eligible usage uses your ChatGPT plan. Credit settings and limits are managed in ChatGPT.",
22
+ "Fast and Ultrafast are unavailable with this ChatGPT connection. Use an existing Codex CLI login for speed options your account supports.",
23
]
24
.filter(Boolean)
25
.join("\n\n"),
apps/web/src/components/chat/ChatGptSharingControl.tsx
+24
-4
@@ -1,16 +1,36 @@
1
import { usesChatGptSharing } from "@t3tools/shared/usageLimits";
2
import type { ServerProvider } from "@t3tools/contracts";
3
+import { useId } from "react";
4
import { OpenAI } from "../Icons";
5
import { ChatGptUsageButton } from "../settings/ChatGptUsageButton";
6
+import { Tooltip, TooltipPopup, TooltipTrigger } from "../ui/tooltip";
7
+
8
+const speedNotice =
9
+ "Fast and Ultrafast are unavailable with this ChatGPT connection. Use an existing Codex CLI login for speed options your account supports.";
10
11
export function ChatGptSharingControl({ provider }: { provider: ServerProvider | null }) {
12
+ const speedNoticeId = useId();
13
if (!usesChatGptSharing(provider)) return null;
14
return (
15
<div className="flex items-center justify-between gap-4 border-t px-3 py-2">
10
- <span className="flex items-center gap-2 text-xs text-muted-foreground">
11
- <OpenAI className="size-3.5" aria-hidden="true" />
12
- Using ChatGPT plan
13
- </span>
16
+ <Tooltip>
17
+ <TooltipTrigger
18
+ render={
19
+ <span
20
+ aria-describedby={speedNoticeId}
21
+ tabIndex={0}
22
+ className="flex items-center gap-2 rounded-sm text-xs text-muted-foreground outline-none focus-visible:ring-2 focus-visible:ring-inset focus-visible:ring-ring"
23
+ />
24
+ }
25
+ >
26
+ <OpenAI className="size-3.5" aria-hidden="true" />
27
+ Using ChatGPT plan
28
+ </TooltipTrigger>
29
+ <span id={speedNoticeId} className="sr-only">
30
+ {speedNotice}
31
+ </span>
32
+ <TooltipPopup side="top">{speedNotice}</TooltipPopup>
33
+ </Tooltip>
34
<ChatGptUsageButton size="xs" />
35
</div>
36
);
docs/user/providers-codex.md
+8
@@ -12,6 +12,9 @@ Manage shared usage and credits in ChatGPT through **Manage usage** in T3 Code.
12
If a request uses a feature that ChatGPT sharing does not support, use another
13
provider for that request.
14
15
+Fast and Ultrafast speeds are unavailable with this connection. To use the speed
16
+options your account supports, [use an existing Codex login](#use-an-existing-codex-login).
17
+
18
When reconnecting, choose the same account in T3 Code and on OpenAI's sign-in
19
page. Disconnecting stops running threads but keeps their history and lets you
20
reconnect later.
@@ -25,6 +28,11 @@ T3 Code can use your installed Codex and its existing login. Run `codex login`
28
on the environment's machine to sign in. [Provider setup](./install.md#providers)
29
covers installation and custom configuration.
30
31
+Running `codex login` does not change a managed ChatGPT connection. In
32
+**Settings > Providers**, add a Codex instance, choose **Configure manually**,
33
+and complete the wizard. Then select that instance from the thread's model
34
+picker. See [Use multiple accounts](#use-multiple-accounts).
35
+
36
## Use multiple accounts
37
38
Add another ChatGPT account in **Settings → Providers**, then select the account