Skip to content

providers-codex.md

Latest commit

 

History

History
113 lines (85 loc) · 5.06 KB

providers-codex.md

File metadata and controls

113 lines (85 loc) · 5.06 KB
Raw

Codex

For one account, use the default Codex provider with your normal Codex login. Provider setup covers installation, Settings > Providers, and custom binaries or environment variables.

Use multiple accounts

A shared Codex home with a shadow home lets work and personal accounts continue the same threads. The accounts share Codex sessions and configuration while keeping their own login and available models.

Keep your first account in ~/.codex. On the environment's machine, sign the second account into a fresh directory:

mkdir -p ~/.codex_personal
CODEX_HOME=~/.codex_personal codex login

Then add a second Codex instance in Settings > Providers:

Instance CODEX_HOME path Shadow home path
Codex Work ~/.codex Leave empty
Codex Personal ~/.codex ~/.codex_personal

Both instances must use the same CODEX_HOME path. T3 Code prepares the shared state in the shadow directory; do not populate it by copying your whole Codex home.

The shadow account needs its own auth.json file. If Codex uses an OS credential store, configure file storage for this setup. See OpenAI's credential storage guide.

Use a completely separate CODEX_HOME path, with no shadow home, when you want separate Codex sessions and configuration. That instance cannot continue threads from the other home.

Switch accounts in an existing thread

Choose the other account from the thread's model picker. T3 Code offers compatible Codex instances that share the thread's CODEX_HOME path. Changing accounts does not move the conversation into a separate Codex home.

If the account is missing from the picker, compare the home paths in provider settings. If two instances show the same unexpected account or models, check their reported accounts, refresh provider status, and confirm the second instance has its own shadow path and login. A shadow-home conflict usually means the directory contains a copied Codex setup. Use a fresh shadow directory and sign in again.

Answer questions while Codex works

Codex can ask a question and keep working. Answer it in the thread's question panel. The answer becomes a new message: it reaches the active turn, or starts another turn if Codex has finished. Unanswered questions survive reconnects. If you do not want to answer, dismiss the question from its panel. Dismissing closes it without sending anything to Codex. This requires a Codex version that supports async questions.

Approve app access

Codex tools can request access to another app. Respond to the named app's request in the thread on web, desktop, or mobile. Some tools offer access for one request, the current session, or permanently. See Permission modes for command and file approvals.

Codex says I hit a usage limit

When Codex stops on a usage limit, the thread names the window that ran out and when it resets, when Codex reports them. Send the message again after the reset. On a workspace plan the message also says whether your workspace owner needs to add credits or raise the spend limit to continue sooner.

Queue messages from outside T3 Code

codex queue --thread <codex-thread-id> --message <text> stores a message in Codex's own queue. Codex only delivers it once the thread is loaded, and T3 Code unloads idle Codex sessions after about 30 minutes, so a queued message can wait until someone opens the thread and sends something. Wake the thread instead:

curl -X POST "$T3_URL/api/orchestration/threads/wake" \
  -H "Authorization: Bearer $T3_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"providerThreadId":"<codex-thread-id>"}'

The wake reloads the Codex session so Codex delivers what it already queued. It never sends a message itself, so calling it more than once is safe. A settled thread is unsettled by the wake. Issue the bearer token with t3 auth session issue. It carries full admin scopes, so keep it as private as your Codex login.

Send feedback to OpenAI

In an existing Codex thread, send /feedback with an optional description, for example /feedback The agent stopped before finishing the tests. This uploads the conversation and Codex logs to OpenAI. The returned thread ID can be shared with OpenAI support.

Monitor background changes

With Codex 0.153.2 or later, ask Codex to watch a CI job, log, or other changing source and react when something happens. It can leave a watcher running after its response finishes using the built-in monitor_start and monitor_unsubscribe tools. No special prompt syntax is needed. On web and desktop, the thread shows Monitoring between turns and wakes when the watcher reports an event. Ordinary background commands do not wake the agent just because they print output.

Use Stop in the thread to cancel background work and pending monitor events. Watchers belong to the current provider session; after stopping that session or restarting the environment, ask Codex to start the watch again.