### What version of Codex CLI is running? 0.101.0 ### What subscription do you have? Pro ### Which model were you using? gpt-5.3-codex xhigh ### What platform is your computer? Darwin 25.2.0 arm64 arm ### What terminal emulator and version are you using (if applicable)? JetBrains ### What issue are you seeing? I'm using the following prompt: ``` --- allowed-
### What feature would you like to see? Switching the global provider should not make previous chat sessions disappear from the Codex app sidebar. ### Current behavior - I create sessions with one provider. - I switch the global provider. - Older sessions no longer appear in the sidebar. ### Expected behavior Previous sessions should remain visible and acces
### What variant of Codex are you using? App ### What feature would you like to see? I find the autoscroll during the Codex response to be visually uncomfortable - especially for longer messages. This is, I think, my preferred behavior: - a space is afforded for a short response that requires no scrolling (~10 lines) - if the output goes beyond that space, t
### What version of the Codex App are you using (From “About Codex” dialog)? 26.715.61943 (released July 21, 2026) ### What subscription do you have? ChatGPT Plus ### What platform is your computer? Microsoft Windows NT 10.0.22631.0 x64 ### What issue are you seeing? When I try to create a Work chat inside an existing ChatGPT Project, I immediately receive e
## Summary On Windows, Codex Desktop continuously writes high-frequency `TRACE` logs into `~/.codex/logs_2.sqlite`, mainly from websocket/tungstenite internals, even though `RUST_LOG=warn` and analytics/OTel export are disabled in `~/.codex/config.toml`. This causes persistent SQLite/WAL writes and database growth. ## Environment - OS: Windows - Codex app pa
### What version of Codex CLI is running? 0.144.0 ### What subscription do you have? Plus ### Which model were you using? gpt-5.6-sol ### What platform is your computer? Linux 7.1.3-arch1-1 x86_64 unknown ### What terminal emulator and version are you using (if applicable)? st ### Codex doctor report ```json { "schemaVersion": 1, "generatedAt": "1783631946s
## Summary During intentional Ultra and multi-agent work, Codex Desktop repeatedly re-entered the model merely to wait for agents or poll terminal status. In a corrected reset-to-49%-usage window, model turns whose only tool action was wait/status polling accounted for **19.8% of raw local token volume**. Ultra and multi-agent use were intentional. The suspe
### What problem are you trying to solve? In Codex App, turns currently only show a brief blinking `Thinking` state and then the final answer. Even with reasoning-related config enabled, I do not see an expandable reasoning summary, progress trace, or `Thought`-style section while the turn is running or after it completes. This makes it harder to understand
Codex reports Chrome extension is not installed when connected in Brave # Bug report: Codex reports Chrome extension is not installed even though the extension is connected in Brave ## Summary Codex reports that the browser extension is not installed, but the Codex Chrome Extension is installed and connected in Brave. The extension-backed browser connection
## Summary In the Codex app, completed or closed subagents can appear to remain visible/stuck in the UI for a long time even after the supported close/readback path reports that there is no live agent handle left. ## Component Codex app / Desktop on macOS. I do not know the exact app version from the UI at the time of filing. ## What happened A workflow used
# MCP stdio servers leak pipe fds + orphan child processes → cumulative EMFILE ("Too many open files", os error 24) ### What version of Codex CLI is running? codex-cli 0.137.0 (also reproduced symptom on long-running 0.12x sessions) ### What subscription do you have? Pro ### Which model were you using? n/a (process/transport bug, model-independent) ### What
### What version of the Codex App are you using (From “About Codex” dialog)? v0.147.0 ### What subscription do you have? Custom litellm provider ### What platform is your computer? AlmaLinux 10.2 (Lavender Lion) ### What issue are you seeing? After upgrading Codex from `v0.146.0` to `v0.147.0`, all requests made through our LiteLLM-backed custom provider fai
## Summary A long-running `/goal` workflow can create a rollout JSONL that Codex Desktop can no longer safely resume or list, even though the workflow is behaving as designed. In this case, the thread was running normally under Codex Desktop with WSL enabled. The user paused the active goal to install a new Desktop update, then the updated app could not reco
## Summary In Codex Desktop, opening a large existing conversation/thread can cause the Codex main process to stay at 100%+ CPU. Switching away to another conversation does not recover CPU usage; only fully restarting Codex clears it. ## Version - Codex Desktop version: `26.527.31326 (3390)` - Platform: macOS ## Reproduction 1. Start Codex Desktop. 2. Open a
## Summary Codex Desktop on Windows repeatedly starts duplicate stdio MCP process pools under `codex.exe app-server --analytics-default-enabled`. The duplicate `cmd -> npx/npx.cmd -> node.exe` trees are not consistently reaped, causing large memory growth. This appears related to: - #28361 - #30408 - #30753 - #29079 I am filing a separate report because this
### What version of Codex is running? - Codex Desktop: `26.707.72221` - Embedded CLI: `codex-cli 0.144.2` - Platform: macOS 26.3 (Build 25D125), Apple Silicon - Model: `gpt-5.6-sol` ### What issue are you seeing? A long-running, image-heavy Codex Desktop thread enters a repeated auto-compaction cycle. After a compaction completes, the resulting history remai
### What version of the Codex App are you using (From “About Codex” dialog)? - Codex desktop version: 26.803.41515 - Computer Use service version: 26.804.1000633 ### What subscription do you have? pro 20x ### What platform is your computer? macOS 26.6 ### What issue are you seeing? Environment: - macOS - Codex desktop version: 26.803.41515 - Computer Use ser
### What version of the Codex App are you using (From "About Codex" dialog)? Version 26.429.30905 ### What subscription do you have? API key auth mode. ChatGPT login is not available for this account/device because phone verification cannot be completed. ### What platform is your computer? macOS / Darwin arm64 ### What issue are you seeing? Codex Desktop dic
### What version of Codex CLI is running? codex-cli 0.132.0 ### What subscription do you have? Plus ### Which model were you using? gpt-5.5 ### What platform is your computer? Microsoft Windows NT 10.0.26100.0 x64 ### What terminal emulator and version are you using (if applicable)? VS Code integrated terminal (PowerShell), codex running via openai.chatgpt V
### Summary After updating/restarting Codex Desktop, the `codex app-server` process grew to tens of GB on a 16 GB macOS machine, causing extreme swap usage and memory pressure. Local evidence points to a pathological persisted rollout/session history interacting with app-server thread listing/resume/read paths. This report is intentionally sanitized: I am no
### What version of the Codex App are you using (From “About Codex” dialog)? 1.2026.190.0 (MSIX OpenAI.ChatGPT-Desktop_1.2026.190.0_x64__2p2nqsd0c76g0) ### What subscription do you have? Pro $100 ### What platform is your computer? Microsoft Windows NT 10.0.26100.0 x64 (Windows 11 Home Single Language) ### What issue are you seeing? `~/.codex/logs_2.sqlite`
### What version of the Codex App are you using (From “About Codex” dialog)? 无 ### What subscription do you have? 无 ### What platform is your computer? macos12 ### What issue are you seeing? <img width="540" height="484" alt="Image" src="https://github.com/user-attachments/assets/8ef1f21d-e583-4d86-8526-167d74fdd948" /> 我电脑是macbook pro 2020 intel系统是macos12今天
### What version of Codex CLI is running? codex-cli 0.147.0 ### What platform is your computer? Linux 5.15.120 x86_64 (also reproducible on other platforms — the bug is in the TUI prompt-edit/backtrack logic, not platform-specific) ### What issue are you seeing? When editing an earlier prompt (Esc-Esc backtrack → select a prompt → Enter), the TUI forks the t
### What version of the Codex App are you using (From “About Codex” dialog)? Unknown — the app is blocked on the "Finish Windows setup" screen and I cannot reach the About dialog. ### What subscription do you have? Plus ### What platform is your computer? "$([Environment]::OSVersion | ForEach-Object VersionString) $(if ([Environment]::Is64BitOperatingSystem)
### What issue are you seeing? A long-running Codex Desktop conversation using Ultra reasoning and multi-agent V2 produced approximately 110 GiB of local session data under `$CODEX_HOME/sessions`. The growth appears multiplicative rather than being caused by subagents producing unusually large outputs: 1. Context compaction persists `Compacted` rollout recor
### What version of Codex CLI is running? codex-cli 0.145.0 ### What subscription do you have? Pro 20x ### Which model were you using? gpt-5.6-luna ### What platform is your computer? Linux 6.18.33.2-microsoft-standard-WSL2 x86_64 x86_64 ### What terminal emulator and version are you using (if applicable)? Windows Terminal ### Codex doctor report ```json { "
## Environment - OS: Windows - Codex IDE extension: 26.715.31925 - Also observed in: 26.707.91948 and 26.715.61943 - IDEs tested: Visual Studio Code and Devin - GPT-5.6 is available in newer extension builds, but IDE Context is broken ## Problem IDE Context does not work in recent Codex extension versions. The extension logs: ~~~text [Composer] failed to fet
## Summary `0.147.0-alpha.4` still cannot deliver a MultiAgentV2 task from an OpenAI parent to a correctly selected non-OpenAI child, despite the plaintext collaboration support merged in #35845. The OpenAI parent returns a `collaboration.spawn_agent` call whose `message` is actual ciphertext and whose `encrypted_function_args` field is `null`. Codex therefo
## Bug Description Codex search/grep tools (launched by `codex app-server --listen unix://` in code_mode_host mode) can run **indefinitely** with **no timeout and no automatic kill** — orphaned `rg` processes keep burning CPU/network I/O for 1+ hours on large projects (observed 46 min and 87 min). On a cluster where the project lives on a **network filesyste
# Bug: Tool-call envelope leaks into assistant text (+ occasional off-topic injection like lottery/ads) ## What version of Codex CLI is running? `@openai/codex` dependency in app: `^0.106.0` ## Which model were you using? `gpt-5.3-codex` (observed in local leak logs) ## What platform is your computer? macOS (Apple Silicon) ## What issue are you seeing? In GU
### What variant of Codex are you using? Codex desktop app ### What feature would you like to see? ## Summary Codex already has official thread lifecycle primitives (`thread/start`, `thread/resume`, `thread/fork`, `thread/read`, `thread/list`, `thread/archive`) plus per-turn overrides on `turn/start`. Subagents solve delegation **inside** a parent thread, bu
## 1. Feedback ID 019e4c10-cadb-7e70-8bf8-38245507bc2f ## 2. Product Codex Desktop App / Remote Control / app-server `thread/start` dynamic tool provisioning. ## 3. Environment - Host: always-on Mac Mini running Codex Desktop - Client: MacBook Pro using the Codex remote workflow against the Mac Mini host - Host project path: `~/Documents/Codex/projects/busin
### What version of the Codex App are you using (From “About Codex” dialog)? Versión 26.527.31326 (3390) ### What subscription do you have? Plus Plan ### What platform is your computer? Darwin 25.5.0 arm64 arm ### What issue are you seeing? ### Summary In a long-running Codex desktop session that uses many subagents, the app appears to accumulate stale subag
### What issue are you seeing? This appears to be a regression or an incomplete fix for #29385, which was closed as completed on 2026-07-14. On the latest Codex/ChatGPT Desktop build, both the in-app Browser and the Chrome extension can eventually navigate to a normal webpage, but the browser-control operation still takes about 30.5–30.7 seconds. During the
## Summary Opening the Codex desktop app on Windows 11 causes sustained CPU usage from **WMI Provider Host** and **Windows Management Instrumentation**, even when Codex is idle and no project, workspace, or agent task has been opened. I rely heavily on Codex for day-to-day development and university work, so this regression has a direct impact on my ability
### What version of the Codex App are you using (From “About Codex” dialog)? Version 26.715.52143 ### What subscription do you have? Pro ### What platform is your computer? Microsoft Windows NT 10.0.26200.0 x64 ### What issue are you seeing? Codex App's git-root resolution retries **without any backoff, circuit breaker, or negative-result cache**. When a sin
### What version of the IDE extension are you using? Affected version: 26.715.61943. The same faulty IDE-context request construction was also found in 26.715.31925 and 26.707.91948. Version 26.5609.30741 works as a rollback. ### What subscription do you have? ChatGPT Plus ### Which IDE are you using? Visual Studio Code 1.129.1 ### What platform is your comp
### What version of the Codex App are you using (From “About Codex” dialog)? 26.721.31836 ### What subscription do you have? Plus ### What platform is your computer? Microsoft Windows NT 10.0.26200.0 x64 ### What issue are you seeing? The Codex desktop app does not load the home page correctly on one of my Windows PCs. The app recognizes that I am signed in,
### What version of the Codex App are you using (From “About Codex” dialog)? OpenAI.Codex 26.803.5235.0 (Computer Use plugin 26.803.41515; bundled Codex CLI 0.147.0-alpha.6.5; @oai/sky 0.6.2) ### What subscription do you have? Unknown / not displayed in the Codex App ### What platform is your computer? Windows 11 Pro 25H2, build 26200.8973, x64; Codex instal
### What variant of Codex are you using? Codex Desktop / app-server multi-agent workflows. The design should also apply to CLI and IDE subagents. Observed on: - Codex App `26.803.10989.0` - Windows 11 x64, build `26200` - `multi_agent = true` - `max_concurrent_threads_per_session = 128` ### What feature would you like to see? Treat MCP access as a **leased c
## Summary On Windows Codex Desktop, newly created threads can persist as `approvalPolicy = on-request` / `sandboxPolicy.type = workspaceWrite` even when the user workflow appears to be operating in a Full Access-like mode. This is reproducible with: - ordinary fresh test threads - handoff-created threads and does **not** require Goal auto-continuation. ## E
## Summary Browser Use / Node REPL does not work in the Codex Windows Desktop app when the agent is configured to run in WSL and the project lives on the WSL filesystem. The Desktop app auto-generates a `node_repl` MCP server that runs a Windows `node_repl.exe`, but tool calls send a Linux/WSL `sandboxCwd` URI (`file:///home/...`). The Windows-side Node REPL
### What version of the Codex App are you using? Codex App 26.707.51957 ### What platform is your computer? macOS arm64 ### What feature would you like? Allow users to define the presets shown in the Codex App's Advanced model picker / power slider. The app already persists related desktop settings in `~/.codex/config.toml`, for example: ```toml [desktop] en
### What version of the Codex App are you using? Affected version: `26.730.61309`. The issue appeared after today's update from `26.727.51351`. ### What subscription do you have? Pro ### What platform is your computer? Windows 11 x64 (`10.0.26200`). The affected task uses a WSL2 workspace. ### What issue are you seeing? After today's update, selecting a Code
## Summary Every build from 26.730.61639 onward crash-loops on launch on one of my Macs, while the identical builds run fine on another. 26.727.51351 is the last build that works on the affected machine. - **26.730.61639 (Sparkle 6234):** crashes ~6 s after launch — V8 "JavaScript heap out of memory", faulting thread CrBrowserMain. - **26.803.41515 (Sparkle
### What version of the Codex App are you using (From “About Codex” dialog)? Desktop app 26.803.41515 ### What subscription do you have? chatgpt pro ### What platform is your computer? windows ### What issue are you seeing? Since the 26.803.41515 build (released Aug 7, 2026) arrived on this machine, the Windows desktop app has become unusable for Work/projec
### What version of the Codex App are you using (From “About Codex” dialog)? 26.803.10989.0 ### What subscription do you have? ChatGPT Pro ### What platform is your computer? Microsoft Windows NT 10.0.26200.0 x64 ### What issue are you seeing? ## Summary Codex Desktop `26.803.10989.0` on Windows becomes unreliable when sending messages to an SSH remote. Ther
### What version of the IDE extension are you using? openai.chatgpt version 26.803.41515 (latest) ### What subscription do you have? plus ### Which IDE are you using? vs code ### What platform is your computer? Microsoft Windows NT 10.0.26200.0 x64 ### What issue are you seeing? The Codex sidebar webview fails to start whenever a system HTTP proxy is running
### What version of the Codex App are you using (From “About Codex” dialog)? 26.803.41515 ### What subscription do you have? ChatGPT Pro 20x ### What platform is your computer? arm64 ### What issue are you seeing? The Codex Renderer processes are consuming an excessive amount of memory. This may be related to conversations becoming very large over time. A lo
### What version of the Codex App are you using? `OpenAI.Codex 26.803.10989.0` from the Microsoft Store (installed/updated on 2026-08-12). ### What subscription do you have? Paid ChatGPT plan with additional Codex credits enabled. ### What platform is your computer? - Windows 11 Pro x64, build 26100 - NVIDIA GeForce RTX 3050, driver 32.0.15.8157 - Display: 2