### What version of Codex CLI is running? `codex-cli 0.104.0` ### What subscription do you have? ChatGPT Plus ### Which model were you using? Primarily `gpt-5.3-codex` ### What platform is your computer? Linux x86_64 (`Ubuntu 25.10`, kernel `6.17.0-14-generic`) ### What terminal emulator and version are you using (if applicable)? zsh terminal on Linux ### Wh
### What version of Codex CLI is running? `codex-cli 0.133.0`. The original affected session metadata includes `codex-cli 0.130.0`, but the WebSocket fallback was reproduced from a copied session using the current Codex CLI/App around `0.133.0`. ### What subscription do you have? ChatGPT Pro 20x. ### Which model were you using? `gpt-5.5` with `reasoning_effo
### What version of the Codex App are you using? Codex Desktop `26.609.41114` on macOS. The app-server version reported after recovery was: ```text currentVersion=0.140.0-alpha.2 ``` ### What subscription do you have? ChatGPT Pro. ### What platform is your computer? macOS 15.6.1 (`darwin`), Apple Silicon. ### What issue are you seeing? Codex Desktop can get
### What version of Codex CLI is running? `codex-cli 0.140.0` Installed with the standalone Windows installer. > **Update (2026-08-13):** Current `main` still has two different Windows Desktop launch paths: `codex app` opens the registered `codex://` protocol, while TUI `/app` directly starts the packaged executable. The current-source comparison and validat
### What variant of Codex are you using? Codex CLI / TUI, especially on headless Linux, SSH, and remote development machines. ### What feature would you like to see? ## Summary Add a first-class, persistent **monitor workflow** to Codex CLI that can return to the same thread at a future time or when a background event occurs, inspect progress, and perform a
### What variant of Codex are you using? IDE Extension ### What feature would you like to see? ## Summary When Codex encounters an OpenAI TPM (Tokens Per Minute) rate limit during a long-running streaming task, it performs a fixed number of reconnect attempts (currently 5) and then terminates the agent. For large repositories and long-running coding sessions
### What version of Codex CLI is running? v0.146.1 ### What subscription do you have? Pro ### Which model were you using? gpt-5.6-sol high ### What platform is your computer? Linux 7.0.0-28-generic x86_64 x86_64 ### What terminal emulator and version are you using (if applicable)? _No response_ ### Codex doctor report ```json { "schemaVersion": 1, "generated
### What happened? Multiple active ChatGPT Pro accounts still show the paid Pro (20x) subscription, and the official Codex usage API continues to identify them as `plan_type: "pro"`. However, their effective Codex usage allowance now behaves like the much smaller Pro 5x tier. The issue is therefore not the displayed subscription name or the `plan_type` field
### What feature would you like to see? The Codex app currently makes provider selection and subagent provider behavior hard to control and hard to understand in the UI. I would like three related improvements: 1. Add an easy provider picker in the Codex app UI for chat threads. - This should make it possible to switch a thread from one provider to another w
## Summary Codex Desktop Browser Use appears unable to connect to either the in-app browser (`iab`) or the Chrome extension backend. Both paths time out at the browser-client connection/listing stage. This looks like a Browser Use/native pipe runtime issue rather than a Chrome extension installation issue. ## Environment - OS: macOS - Chrome: 147.0.7727.139
Summary After updating Codex Desktop, commands that require sandbox escalation no longer run. The escalation reviewer times out before approving the command. As a result, tools such as lark-cli cannot access macOS Keychain from Codex, even though the same commands work successfully in the user's normal terminal. Impact This blocks Codex from using locally co
## Summary After a Codex Windows desktop app update, **Browser**, **Chrome**, and **Computer Use** could all become globally unavailable in Settings. Restarting the app did not repair the state. The failure was caused by several pieces of old and new state being mixed across the bundled marketplace snapshot, version cache, Chrome native host, and `cua_node`
## Summary Codex Desktop stopped showing the file tree / review pane entry points / current branch UI for local Git projects. This appears to be a Desktop UI regression: Git, GitHub auth, the Codex CLI, and the Codex app backend all still detect the repositories correctly. The issue started recently, within the last couple of days. It affects all Codex Deskt
### What version of Codex CLI is running? codex-cli 0.142.5 ### What subscription do you have? Enterprise ### Which model were you using? gpt-5.5 ### What platform is your computer? Microsoft Windows NT 10.0.28000.0 x64 ### What terminal emulator and version are you using (if applicable)? _No response_ ### Codex doctor report ```json { "schemaVersion": 1, "g
### What version of the Codex App are you using (From “About Codex” dialog)? 26.707.6957.0 ### What subscription do you have? pro 20x ### What platform is your computer? Windows 11 x64 ### What issue are you seeing? After today's update, Codex now crashes with the following error which stops all threads, which is highly nonideal given the relatively non-seve
## Summary In Codex Desktop on macOS, switching a task from **Local** to **Cloud** in the side-panel environment selector can leave the task stuck in Cloud. The selector no longer lets me switch the task back to Local. At the same time, the side panel displays **"Summary panel couldn't render."** This blocks returning the task to the local workspace. ## Step
### What version of the Codex App are you using (From “About Codex” dialog)? Version 26.721.81911 ### What subscription do you have? chatgpt pro ### What platform is your computer? _No response_ ### What issue are you seeing? <img width="900" height="270" alt="Image" src="https://github.com/user-attachments/assets/8b627add-697f-4dbb-be1c-79c2fcca7465" /> cli
### What variant of Codex are you using? Codex App (desktop) ### What feature would you like to see? Please give the desktop app its own app-managed config overlay, for example `$CODEX_HOME/config-desktop.toml` (defaulting to `~/.codex/config-desktop.toml`), instead of writing desktop state into the user-managed `$CODEX_HOME/config.toml`. For desktop session
### What version of Codex is running? codex-cli 0.84.0 ### What subscription do you have? Pro ### Which model were you using? 5.2-high (happens on all) ### What platform is your computer? Linux 6.18.3-arch1-1 x86_64 ### What terminal emulator and version are you using (if applicable)? Ghostty ### What issue are you seeing? Trying to do a git push dry run fro
## Summary GPT-5.4 via the Codex CLI occasionally emits corrupted output containing internal ChatGPT tool-calling formats (`multi_tool_use.parallel` with `recipient_name`) mixed with memorized Chinese gambling SEO spam, instead of making proper Responses API tool calls. ## Reproduction - **Model:** gpt-5.4 - **Mode:** Default collaboration, reasoning effort
### What version of Codex CLI is running? codex-cli 0.120.0 ### What subscription do you have? Pro ### Which model were you using? gpt-5.4 ### What platform is your computer? Linux 6.12.0-124.47.1.el10_1.x86_64 x86_64 unknown ### What terminal emulator and version are you using (if applicable)? VSCode ### What issue are you seeing? After reopening Codex, an
### What variant of Codex are you using? App ### What feature would you like to see? I would like Codex to provide a local secret management feature for sensitive information such as server usernames, passwords, API keys, SSH credentials, database passwords, and deployment tokens. In many real-world workflows, Codex may need to execute commands that require
## What version of Codex CLI is running? `codex-cli 0.130.0` ## What subscription do you have? Pro ## Which model were you using? ChatGPT 5.5 ## What platform is your computer? `Darwin 25.4.0 arm64 arm (MacBook Pro, M4 Max, MacOS Tahoe 26.4.1)` ## What terminal emulator and version are you using (if applicable)? `WarpTerminal v0.2026.05.13.09.15.stable_01` #
### What version of the Codex App are you using (From "About Codex" dialog)? Observed on a Windows desktop install whose shipped frontend bundle is: - `openai.chatgpt-26.325.31654-win32-x64` Affected local bundle paths: - `C:\Users\q1371\.antigravity\extensions\openai.chatgpt-26.325.31654-win32-x64\webview\assets\app-server-manager-hooks-XL0eRatK.js` - `C:\U
This bug report was written by Codex. ## Summary Codex Desktop appears to ignore a trusted project's `.codex/config.toml` `model_catalog_json` setting when creating a fresh project thread, while the CLI/debug path from the same cwd respects it. This prevents project-local custom model catalogs from working in Desktop, including per-model `base_instructions`
### What variant of Codex are you using? CLI ### What feature would you like to see? Please add a way for Linux users to view and redeem banked Codex rate-limit resets, either from Codex CLI or from a Codex web usage/settings page. ### Additional information Banked resets currently appear to be exposed through the Codex app UI, but the Codex desktop app is n
### What issue are you seeing? Sessions don't stay in sync when used across cli/desktop/mobile. ### What steps can reproduce the bug? 1. Start cli, launch some subagents 2. While running/once finished, send followup/steer from mobile (android) remotely connected to your host 3. Check cli and see no update made to the session 4. Check codex desktop && vscode
### What variant of Codex are you using? Codex App on Windows / Windows-to-Windows usage ### What feature would you like to see? Please add first-class support for connecting two Codex desktop apps on Windows, so one Windows machine can act as the Codex host and another Windows machine can control it through the official Codex App experience. Desired behavio
## Summary Please support first-class multi-account and multi-machine connections for Codex mobile Remote Control. Right now, Codex mobile Remote Control appears to work best when there is a single active desktop host / enrollment. In real development setups, users often have multiple ChatGPT accounts or workspaces and multiple machines, and the current mode
## Summary `codex exec` with `gpt-5.6-sol` can report that shell/code-mode tools are unavailable, while the same prompt works with `gpt-5.5`. The issue appears to be the Responses Lite request shape: for `use_responses_lite=true` models, Codex currently moves client tool schemas into an `input[0]` item of type `additional_tools` and omits top-level `tools`.
### What version of Codex CLI is running? `codex-cli 0.144.0-alpha.4` ### What version of Codex Desktop is installed? `OpenAI.Codex 26.707.3748.0` from the Microsoft Store / AppX package. ### Platform - Microsoft Windows 11 Pro - Version `10.0.26200`, build `26200` - 64-bit ### What issue are you seeing? On Windows, `codex app <workspace>` reports that Codex
### What variant of Codex are you using? Codex Desktop app ### What feature would you like to see? When the sidebar contains many projects and tasks, it becomes difficult to find a task that is still running—especially when several tasks are active across different projects at the same time. Today, active tasks are mixed into the normal project/thread hierar
### What version of the Codex App are you using (From “About Codex” dialog)? 26.721.4979.0 ### What subscription do you have? ChatGPT Plus ### What platform is your computer? Microsoft Windows NT 10.0.26200.0 x64 / Windows 11 Pro ### What issue are you seeing? Codex Desktop cannot reliably access projects located on a normal authenticated SMB share through U
### What version of Codex CLI is running? Observed on `0.146.0-alpha.10.1`. The affected source paths remain unchanged in `rust-v0.146.0-alpha.14`. ### What platform is your computer? Linux x86_64. ### What issue are you seeing? Paginated rollout history has inconsistent `RolloutLine` decoding. Some readers deserialize JSON directly into `RolloutLine`, while
(not duplicate of https://github.com/openai/codex/issues/36112) ### What version of Codex CLI is running? codex-cli 0.146.0 ### What subscription do you have? Plus ### Which model were you using? gpt-5.6-luna low ### What platform is your computer? Microsoft Windows NT 10.0.26200.0 x64 ### What terminal emulator and version are you using (if applicable)? WSL
### Subscription ChatGPT Pro ### Models used - `gpt-5.6-sol` - `gpt-5.5` ### Issue Immediately after the global Codex usage reset announced by Tibo on **August 1, 2026**, my weekly Pro allowance began draining much faster than it did before the reset. On August 1, a total of **75,250,381 tokens** consumed approximately **26% of the weekly Pro allowance**, le
### What version of the Codex App are you using (From “About Codex” dialog)? ChatGPT desktop app `26.730.61639` (build `6234`, bundle identifier `com.openai.codex`). The bundled `chrome@openai-bundled` plugin is also version `26.730.61639`. ### What subscription do you have? ChatGPT Pro ### What platform is your computer? ~~~text Darwin 25.5.0 arm64 arm Goog
### What variant of Codex are you using? CLI ### What feature would you like to see? I'd like it to be possible to use `request_user_input` in Default mode without the question automatically resolving after a timeout. I have `request_user_input` explicitly enabled in Default mode using the `default_mode_request_user_input` feature. After updating to 0.147.0:
### What version of Codex is running? - Codex CLI 0.146.0: Qonto MCP works - Codex CLI 0.147.0: Qonto MCP initialization fails - Codex Desktop client version observed in logs: 26.803.41515 (internal traces reference client version 0.147.0) ### What operating system are you using? macOS 26.5.2 (25F84) ### What is the issue? Qonto MCP tools are missing in Code
### Summary A Codex Security diff scan completed discovery, validation, attack-path analysis, and canonical draft generation, but finalization rejected an empty `scan.target.snapshotDigest`. After repairing the digest in a fresh turn, completion could not be retried because the first validation error had already moved the scan into the terminal `failed` stat
### What version of Codex CLI is running? codex-cli 0.147.0 ### What subscription do you have? pro $100 ### Which model were you using? gpt-5.6-sol max ### What platform is your computer? Linux 7.0.11-76070011-generic x86_64 x86_64 ### What terminal emulator and version are you using (if applicable)? https://github.com/pop-os/cosmic-term (alacritty based) ##
### What version of Codex CLI is running? `0.148.0-alpha.5` ### What subscription do you have? Not applicable (local rollout migration). ### Which model were you using? Not applicable (local rollout migration). ### What platform is your computer? macOS / Darwin 27.0.0 / arm64 ### What terminal are you using? zsh ### Codex doctor report Not included: this is
### Summary A ChatGPT Chronicle/background run deletes the canonical **system Skill Creator** from the shared Codex system-Skills installation. The Chronicle worker starts the bundled Codex runtime with `skills.bundled.enabled=false`. The resulting cleanup appears to remove the shared `$CODEX_HOME/skills/.system` directory instead of merely disabling bundled
### What version of the Codex App are you using (From “About Codex” dialog)? 26.721.41059 ### What subscription do you have? Free ### What platform is your computer? Darwin 25.5.0 arm64 arm ### What issue are you seeing? On macOS Apple Silicon, long responses in the Codex/ChatGPT desktop app repeatedly jump/scroll upward while I am reading them. The bottom o
### What version of the IDE extension are you using? 26.803.61601 ### What subscription do you have? PRO 5X ### Which IDE are you using? VS CODE ### What platform is your computer? Windows ### What issue are you seeing? Unknown model gpt-5.6-luna when summoning it as a subagent. ### What steps can reproduce the bug? .codex adds luna, use sol to summon it. Us
### What version of the Codex App are you using (From “About Codex” dialog)? 26.803.61601 (build 6396); bundled codex-cli 0.147.0-alpha.6.5 ### What subscription do you have? ChatGPT subscription (exact tier is not displayed in the Codex App) ### What platform is your computer? macOS 26.5.1 (Build 25F80), Apple Silicon arm64; Darwin 25.5.0 ### What issue are
# [Windows app regression] Subagent threads lose direct visibility/control and Spark is missing from spawn overrides ### What version of the Codex App are you using (From “About Codex” dialog)? MSIX package version `26.803.10989.0` (Microsoft Store package, status OK). ### What subscription do you have? Not collected. The report is about the locally advertis
### What version of Codex CLI is running? codex-cli 0.147.0 ### What subscription do you have? Pro ### Which model were you using? gpt-5.6-sol ### What platform is your computer? Linux 5.15.167.4-microsoft-standard-WSL2 x86_64 x86_64 ### What terminal emulator and version are you using (if applicable)? WSL ### Codex doctor report ```json { "schemaVersion": 1
### What version of the Codex App are you using (From “About Codex” dialog)? Version 26.803.81509 ### What subscription do you have? Business ### What platform is your computer? Microsoft Windows NT 10.0.26200.0 x64 ### What issue are you seeing? When using voice dictation in the Codex Windows desktop app, an ongoing or recently completed voice input can be