contribution/compass
openai/codex

Codex

501 signals · 497 observation events

Open repository ↗

Lightweight coding agent that runs in your terminal

105.7K stars16.0K forksRustApache-2.0keyword: OpenAI Codex
PROJECT NEWS

Release, roadmap, and discussion

All news →
openai/codex

Codex

Coding-Agent Infrastructure
Latest stable

0.147.0

rust-v0.147.0
  • New Features
  • Install portable Agent Plugins and search across local, personal, workspace, and remote plugin catalogs. (#36544, #36409, #36919, #36796)
  • Organize conversations into persistent, manually ordered sections and browse long transcripts incrementally. (#35722, #36007, #36380, #36948, #36950)
  • Enable automatically reviewed approvals with the new --approve-for-me CLI flag. (#36373)
  • Import Cursor-managed skills and synchronize changes to imported Claude and Cursor conversations without creating duplicates. (#36361, #36356, #35623)
Original release notes ↗

Publicly indicated next

Prereleases and milestones indicate public plans; they are not delivery commitments.

Observation trail

  1. discoveredinitial snapshot
  2. discoveredinitial snapshot
  3. discoveredinitial snapshot
  4. discoveredinitial snapshot
  5. discoveredinitial snapshot
  6. changedmetrics
  7. discoveredinitial snapshot
  8. discoveredinitial snapshot
  9. discoveredinitial snapshot
  10. changedupdatedAt, metrics
  11. changedupdatedAt, metrics, state
  12. discoveredinitial snapshot
  13. discoveredinitial snapshot
  14. discoveredinitial snapshot
  15. discoveredinitial snapshot
  16. discoveredinitial snapshot
  17. changedupdatedAt, metrics
  18. discoveredinitial snapshot
  19. discoveredinitial snapshot
  20. discoveredinitial snapshot
  21. discoveredinitial snapshot
  22. discoveredinitial snapshot
  23. changedupdatedAt, metrics
  24. discoveredinitial snapshot
  25. changedupdatedAt, metrics
  26. discoveredinitial snapshot
  27. discoveredinitial snapshot
  28. discoveredinitial snapshot
  29. discoveredinitial snapshot
  30. changedupdatedAt, metrics
50 shown
issue

Codex for Windows: Luna cannot be used as a sub-agent when Sol is selected as the main model

### What version of the Codex App are you using (From “About Codex” dialog)? 26.715.72028 ### What subscription do you have? On the Windows version of Codex, when **Sol** is selected as the main model, **Luna cannot be used as a sub-agent**. I would expect Sol to be able to delegate tasks to Luna as a sub-agent, but Luna either does not appear as an availabl

importance 4@nothing-betterclosedbugwindows-osappsubagentOriginal evidence ↗
issue

Sub-agent launcher rejects configured gpt-5.6-luna while direct Codex Luna run succeeds

## Summary The Codex multi-agent sub-agent launcher rejects `gpt-5.6-luna` as an unknown model even though Luna is configured for the Builder role and a direct Codex Luna Max run succeeds on the same machine and ChatGPT account. ## Environment - macOS 26.5.1, arm64 - Codex desktop-bundled CLI: `0.147.0-alpha.6.5` - Authentication: ChatGPT - Global config: `m

importance 4@mcline-lucey-altopenbugappsubagentOriginal evidence ↗
issue

Codex Windows App failed to start after switching to WSL mode

### What version of the Codex App are you using (From “About Codex” dialog)? 26.803.10989.0 ### What subscription do you have? Plus ### What platform is your computer? Microsoft Windows NT 10.0.26200.0 x64 ### What issue are you seeing? Codex Desktop fails to start when WSL is selected as the execution environment. <img width="344" height="135" alt="Image" s

importance 4@bizukiopenbugwindows-osappapp-serverOriginal evidence ↗
issue

Shared project not showing in Desktop app

Feedback session ID: 019ff564-1d6b-72c1-87e3-87e48b4120fc. desktop build 26.803.10989.0. ChatGPT Business projects visible on chatgpt.com are missing from the Windows desktop app. Account: Devin McGarvey (@devin594646) Workspace: Sift Fire Investigations Desktop build: OpenAI.Codex 26.803.10989.0 Affected project: Sift Technical Writer The account and Busine

importance 4@wanabnerdyopenbugwindows-osappOriginal evidence ↗
issue

Windows elevated sandbox fails on session-scoped mapped-drive cwd with error 267

### What version of Codex are you using? Codex Desktop package `26.803.10989.0`; source reproduction and candidate fix were made from `openai/codex` main at `b1373b74a27d1d9b65074a873202683355cae772`. ### What platform are you using? Windows 11 x64, elevated Windows sandbox, workspace on a session-scoped mapped drive. ### What issue are you seeing? The eleva

importance 4@webby888openbugwindows-ossandboxOriginal evidence ↗
issue

[macOS] Computer Use captures Stage Manager thumbnail, poisons ScreenCaptureKit stream (-3811/-3812)

## Summary With macOS Stage Manager enabled, Codex Computer Use can select an inactive app's Stage Manager thumbnail instead of its real window. The thumbnail has off-screen/negative window coordinates, so ScreenCaptureKit fails its display lookup. That failed capture can then poison the shared capture service: subsequent captures of unrelated, valid on-scre

importance 4@AryanRGopenbugappcomputer-useOriginal evidence ↗
issue

[Bug] Recurring scheduled tasks disable themselves after successful runs without user authorization

### What issue are you seeing? Recurring Scheduled tasks in ChatGPT Work on the web are sometimes changing from enabled to paused after a scheduled run, without any user request to pause, disable, delete, or reschedule them. In the latest occurrence, four unrelated recurring tasks were found disabled shortly after their runs. Other recurring tasks remained e

importance 4@montaoopenbugcodex-webautomationsOriginal evidence ↗
issue

GitHub @codex work task gets no tool to push back to existing PR despite write access

### Product Codex Cloud / GitHub `@codex` mention workflow ### Summary A non-review `@codex` mention on an existing pull request started the expected Codex Cloud work task, checked out the correct repository and PR branch, edited and tested the code, and made a local commit. The task was not given any GitHub publishing tool, so it could not push the commit b

importance 4@toumix-agentsopenbugcodex-webtool-callsOriginal evidence ↗
issue

Responses Lite turns custom base-instruction overrides into additive developer messages

## What issue are you seeing? A custom base-instruction override supplied through `model_instructions_file` replaces the model's bundled Codex base instructions in standard Responses mode, but becomes additive in Responses Lite. With Responses Lite enabled, the model sees both: - the service-provided Codex base identity (beginning with `You are Codex`), and

importance 4@Krual-TopenbugCLIconfigOriginal evidence ↗
issue

[Windows] Codex Desktop 26.803.10989.0: "Error: write EOF" main-process modal keeps appearing (with log evidence and my analysis)

# [Windows] Codex Desktop 26.803.10989.0: "Error: write EOF" main-process modal keeps appearing (with log evidence and my analysis) ## The problem Ever since I updated the Codex Windows desktop app, this modal keeps popping up. It shows on nearly every startup, and then again at random points while I'm working: ``` A JavaScript error occurred in the main pro

importance 4@Nver-thelessopenbugwindows-osappbrowserOriginal evidence ↗
issue

Support reliable cross-provider session handoff with normalized tool history

### What variant of Codex are you using? CLI ### What feature would you like to see? ### Feature request Codex should support handing off a long-running session from one model provider to another while preserving its working context. Example: - Continue a long GPT session with a custom Responses-compatible provider when the GPT quota is exhausted. - Later ha

importance 4@haochengyuanopenenhancementCLIcustom-modeltool-callssessionOriginal evidence ↗
issue

Request too large for gpt-5.6-luna in organization org

### What version of Codex CLI is running? codex-cli 0.146.1 ### What subscription do you have? ? ### Which model were you using? gpt 5.6 luna ### What platform is your computer? cachyos ### What terminal emulator and version are you using (if applicable)? Konsole ### Codex doctor report ```json ~/_newmodel> codex doctor Codex Doctor v0.146.1 · linux-x86_64 N

importance 4@Ultimatoriusopenbugrate-limitsCLIcontextOriginal evidence ↗
issue

Windows Browser Use blocks raw JSON and CSV with ERR_BLOCKED_BY_CLIENT while HTML works

### What version of the Codex App are you using (From “About Codex” dialog)? 26.803.81509 ### What subscription do you have? ChatGPT Plus ### What platform is your computer? Microsoft Windows NT 10.0.26200.0 x64 ### What issue are you seeing? Browser Use in the Codex Windows desktop app blocks raw JSON and CSV responses with `ERR_BLOCKED_BY_CLIENT`, while or

importance 4@evdmolenopenbugwindows-osappbrowserautomationsOriginal evidence ↗
issue

App-server: add safe thread-scoped registration for host-provided hooks

### What variant of Codex are you using? App Server ### What feature would you like to see? ## Summary ### What we are trying to achieve Context: The `microsoft/vscode` team is integrating the Codex App Server into VS Code's agent host (see our [docs 1](https://code.visualstudio.com/docs/agents/run/agent-harnesses?agent-harness=codex#_use-an-agent-harness) a

importance 4@Giuspepeopenenhancementhooksapp-serverOriginal evidence ↗
issue

Collapsing a parent folder hides its child folders one by one

### What version of the Codex App are you using (From “About Codex” dialog)? 26.803.81509 ### What subscription do you have? Plus ### What platform is your computer? Linux 7.1.8-100.fc43.x86_64 x86_64 ### What issue are you seeing? When trying to collapse a top-level folder, such as apps, the folder does not collapse immediately. Instead, each click collapse

importance 4@rafaselfopenbugappOriginal evidence ↗
issue

Safety rejection incorrectly ends turn as "aborted by user" without explanation

## Description A long-running Codex Desktop turn was forcibly interrupted while I was asleep. I did not press Stop or provide any input. The local session transcript shows three automated safety rejections of proposed file changes. Immediately after the third rejection, Codex recorded: - Tool result: `aborted by user after 4.2s` - Turn status: `turn_aborted`

importance 4@fortynovaopenbugappsafety-checkOriginal evidence ↗
issue

[App] Popout Window run-location click hides the window and breaks the hotkey until restart; cloud projects cannot start new chats from the desktop app

### What version of the Codex App are you using (From “About Codex” dialog)? 26.803.10989.0 (Windows; embedded CLI version 0.147.0-alpha.6.6) ### What subscription do you have? ChatGPT Plus ### What platform is your computer? Microsoft Windows NT 10.0.26200.0 x64 ### What issue are you seeing? Two reproducible issues in the Codex App desktop UI: 1. **Popout

importance 4@Hzzz7openbugwindows-osappOriginal evidence ↗
issue

[Windows Desktop][26.803.10989.0] Six stuck app-server requests freeze every window and remove Fast mode

### What version of the Codex App are you using (from the About dialog)? OpenAI Codex Windows package `26.803.10989.0` (x64), bundled backend `codex-cli 0.147.0-alpha.6.6`. ### What subscription do you have? ChatGPT sign-in. Exact plan is omitted because the failure occurs in the local Desktop/app-server transport before a model turn starts. ### What platfor

importance 4@keepyourpolicy-labopenbugwindows-osappsubagentapp-serverOriginal evidence ↗
issue

apply_patch "Update"/"Delete" always fails on Windows Desktop: fs sandbox helper stack overflow (0xC0000005 in essctl.dll); "Add" works

apply_patch "Update"/"Delete" always fails on Windows Desktop: fs sandbox helper stack overflow (0xC0000005 in essctl.dll); "Add" works ## Describe the bug On Codex Desktop for Windows (version 26.803.10989.0), `apply_patch` operations that modify or delete an existing file fail deterministically before applying anything. The tool reports that the filesystem

importance 4@siqian233openbugwindows-ossandboxtool-callsappOriginal evidence ↗
issue

Terminal links open in external browser instead of in-app

### What version of the Codex App are you using (From “About Codex” dialog)? 26.803.81509 ### What subscription do you have? Plus ### What platform is your computer? Linux 7.1.8-100.fc43.x86_64 x86_64 ### What issue are you seeing? Links opened from the integrated terminal in the ChatGPT Codex app for Linux are being launched in the system's external browser

importance 4@rafaselfopenappOriginal evidence ↗
issue

Add shortcut to toggle line comments

### What variant of Codex are you using? App ### What feature would you like to see? Add a keyboard shortcut to quickly comment and uncomment selected lines in the editor, similar to the behavior available in editors such as VS Code. Currently, there does not appear to be a shortcut for toggling line comments in the Codex app editor. This makes a very common

importance 4@rafaselfopenenhancementappOriginal evidence ↗
issue

VS Code extension: controls for edited-file expansion and hover previews

### What variant of Codex are you using? IDE Extension (openai.chatgpt@26.5803.61601) in VS Code 1.133.0 on Linux. ### What feature would you like to see? Please add two independent display controls for edited-file cards: - **Expand edited-file diffs by default** - **Show diff preview when hovering edited-file cards** Both behaviors should be independently c

importance 4@c0ldn3s5openenhancementextensionOriginal evidence ↗
issue

macOS app returned content from an unrelated conversation and showed inconsistent thread state

### What version of the Codex App are you using (From “About Codex” dialog)? 26.803.61601 ### What subscription do you have? ChatGPT Plus ### What platform is your computer? macOS, Apple Silicon (arm64) ### What issue are you seeing? On August 13, 2026, the macOS app returned content apparently belonging to a separate conversation. In an independent non-proj

importance 4@rds-msallcopenbugappsessionOriginal evidence ↗
issue

Codex Desktop WSL agent still creates projectless workspaces under /mnt/c instead of the WSL home

### What version of the Codex App are you using (From “About Codex” dialog)? OpenAI.Codex MSIX `26.803.10989.0` ### What subscription do you have? Not relevant to this local filesystem behavior. ### What platform is your computer? - Windows, x64 - Codex Desktop agent mode: WSL - WSL2 distribution: Ubuntu 26.04 - WSL kernel: `6.18.33.2-microsoft-standard-WSL2

importance 4@aim9souropenbugwindows-osappOriginal evidence ↗
issue

TUI: Quickly interrupting a submitted prompt drops it from rollout history

### What version of Codex CLI is running? `codex-cli 0.147.0` (reported as current/latest by `codex doctor --json`) ### What subscription do you have? ChatGPT authentication (the exact subscription tier is not exposed by the CLI) ### Which model were you using? `gpt-5.6-sol`, max reasoning, fast mode ### What platform is your computer? `Linux 7.0.0-28-generi

importance 4@zengjian513fopenbugTUICLIsessionOriginal evidence ↗
issue

Accessibility: “Choose project” is not announced by NVDA in New chat on Windows

### What version of the Codex App are you using (From “About Codex” dialog)? OpenAI.Codex MSIX `26.803.10989.0` ### What subscription do you have? ChatGPT Plus ### What platform is your computer? Windows, x64 ### What issue are you seeing? In Codex Desktop on Windows, the **Choose project** control on the **New chat** screen is visible on screen but is not a

importance 4@aim9souropenbugwindows-osappOriginal evidence ↗
issue

Desktop: periodically auto-update plugin marketplaces without requiring a restart

### Feature request Codex Desktop currently starts the configured Git marketplace auto-upgrade as an app-server startup task. When the Desktop app stays open for days, marketplace and plugin updates are not checked again unless the app server is restarted or the user manually requests an upgrade. Current implementation references: - The marketplace auto-upgr

importance 4@YunKuiLuopenenhancementappskillsapp-serverOriginal evidence ↗
issue

Codex CLI 0.147.0 fails behind TUN proxy on Windows with os error 10061, MCP failure, and HTTPS fallback failure

### What version of Codex CLI is running? 0.147.0 ### What subscription do you have? ChatGPT Plus ### Which model were you using? gpt-5.6-sol ### What platform is your computer? Microsoft Windows NT 10.0.26200.0 x64 ### What terminal emulator and version are you using (if applicable)? Windows Terminal with Windows PowerShell 5.1 ### Codex doctor report ```js

importance 4@cleo7221openbugwindows-osmcpCLIconnectivityOriginal evidence ↗
issue

GitHub review connector quota failure leaves required exact-head review blocked without retry guidance

### Problem The GitHub-hosted Codex reviewer can reject a requested security review with only: > You have reached your Codex usage limits for security reviews. Please try again later. Example: https://github.com/autumngarage/touchstone/pull/827#issuecomment-5283708031 (2026-08-13). The PR is public and the review was requested against exact head `e9780c11116

importance 4@henrymodisettopenenhancementcode-reviewcodex-webrate-limitsOriginal evidence ↗
issue

Closed at reporter request

This issue was closed and its original details removed at the reporter's request. The problem will be reported through private OpenAI support channels instead.

importance 4@patrickmklineclosedbugwindows-osappbrowserOriginal evidence ↗
pull request

Fuse recent and lexical skills in shadow selection

Fuse recent and lexical skills in shadow selection ## What changed - Add the `lru_plus_lexical_v1` selector, combining the 50 most recent skills with weighted lexical matches through reciprocal rank fusion. - Include the combined selector in the shadow-selection experiment and propagate query and candidate truncation metadata from both inputs. - Generalize t

importance 4@copyberry[bot]closedOriginal evidence ↗
pull request

fix: harden symlinked project config writes

## Summary - Explicitly protect `.codex/config.toml` as a read-only leaf in split filesystem policies. - Preserve intentional pre-existing project config symlinks. - In bubblewrap, first remount `.codex/` read-only to prevent retargeting, then remount the config symlink's stable target read-only. - Fail closed for dangling config symlinks or targets that tra

importance 2@viyatb-oaiclosedcode-reviewedOriginal evidence ↗
pull request

Add conservative restriction helpers for tool policies

Add conservative restriction helpers for tool policies ## What changed - Add `restrict_to` helpers that combine parent and requested `WebSearchMode` and `AppToolApproval` values without granting access beyond either policy. - Treat `Auto` and `Writes` approval modes as incomparable, falling back to `Prompt` when they are combined. ## Testing - Cover every pa

importance 2@copyberry[bot]Original evidence ↗
pull request

Run search tool integration tests on Windows

Run search tool integration tests on Windows ## Why The search tool integration test suite was disabled entirely on Windows. ## What changed - Remove the suite-wide Windows exclusion and build test fixtures with automatic environment selection. - Configure stdio MCP fixtures with environment-aware server paths and environment IDs for local and remote runs. -

importance 2@copyberry[bot]Original evidence ↗
pull request

Run plugin app-server tests in automatic environments

Run plugin app-server tests in automatic environments ## What changed - Use the standard automatic test environment for plugin list, install, and uninstall app-server tests. - Keep the bundled stdio MCP test host-local because its fixture is a local executable. - Strengthen that test to verify the bundled server initializes and exposes its `echo` tool. <!--

importance 2@copyberry[bot]Original evidence ↗
pull request

Add an LRU baseline to skill shadow selection

Add an LRU baseline to skill shadow selection ## What changed - Track the 50 most recently invoked skills for each thread and evaluate them as the `lru_v1` shadow-selection method. - Filter stale and duplicate entries while preserving recency order. - Increase the shadow result limit to 50 and add a `21_50` rank bucket. ## Testing - Add unit coverage for rec

importance 2@copyberry[bot]closedOriginal evidence ↗
pull request

Enforce non-interactive approval policy for Codex delegates

Enforce non-interactive approval policy for Codex delegates ## What changed - Require delegated Codex sessions to use the `never` approval policy and reject delegate creation with any prompt-capable policy. - Stop forwarding delegate approval and permission requests to the parent session. Approval-requiring commands and MCP tool calls are denied within the d

importance 2@copyberry[bot]closedOriginal evidence ↗
pull request

Avoid allocations when sanitizing TUI user text

Avoid allocations when sanitizing TUI user text ## Why Sanitizing user messages and pasted text always allocated a new string, even when the input contained no terminal control characters. ## What changed - Return a `Cow<str>` from `sanitize_user_text` so clean borrowed input remains borrowed. - Reuse owned input buffers when sanitization leaves the text int

importance 2@copyberry[bot]closedOriginal evidence ↗
pull request

Add a flag to retain client developer messages

Add a flag to retain client developer messages ## What changed - Register `retain_client_developer_messages` as an under-development feature that is disabled by default. - Expose the feature in the configuration schema. <!-- copyberry-projection-id: 29b030fa11a45d0b8aefa5cbf378976407e2b239d74721bf86efdbd641812823 -->

importance 2@copyberry[bot]closedOriginal evidence ↗
pull request

Add manifest-defined metrics for trusted plugin scripts

Add manifest-defined metrics for trusted plugin scripts ## What changed - Load version 1 `analytics.yaml` manifests from trusted plugin roots and map declared operations, measurements, and enum dimensions to exact script paths. - Expose resolution types and bind a declared operation to the plugin identity returned by fresh command attribution. - Reject malfo

importance 2@copyberry[bot]closedOriginal evidence ↗
pull request

Add bounded plugin measurement analytics

Add bounded plugin measurement analytics ## What changed - Add `PluginMeasurementsInput` and `PluginMeasurementRow`, plus an analytics client method for recording batches and checking whether analytics are enabled. - Emit each valid row as a `codex_plugin_measurement_event` with thread, turn, item, plugin, execution, and operation context. - Bound batches at

importance 2@copyberry[bot]closedOriginal evidence ↗
pull request

Cache stable active-cell layout measurements

Cache stable active-cell layout measurements ## What changed - Reuse desired and rendered heights for active transcript cells that report a stable height. - Invalidate the cached layout when the cell identity, revision, width, render mode, or syntax theme changes, and when the active cell is removed. - Continue rebuilding display lines on every frame so anim

importance 2@copyberry[bot]closedOriginal evidence ↗
pull request

Add per-thread usage queries to the backend client

Add per-thread usage queries to the backend client ## What changed - Add `Client::get_thread_usage` for querying authoritative estimated credit and dollar usage for a thread across both supported backend path styles. - Expose usage totals and optional model, reasoning effort, speed, and token breakdowns through `ThreadUsage` and `ThreadUsageBreakdownGroup`.

importance 2@copyberry[bot]closedOriginal evidence ↗
pull request

Represent persisted world state as JSON objects

Represent persisted world state as JSON objects ## Why World-state snapshots and merge patches are keyed collections of sections. Allowing their persisted `state` field to contain any JSON value required replay code to handle shapes that cannot represent world state. ## What changed - Type `WorldStateItem.state` and snapshot patches as JSON object maps. - Re

importance 2@copyberry[bot]closedOriginal evidence ↗
pull request

Use protobuf's built-in Bazel proto rule

Use protobuf's built-in Bazel proto rule ## What changed - Load `proto_library` for the code-mode protocol directly from the `com_google_protobuf` repository. - Remove the now-unneeded direct `rules_proto` module dependency. <!-- copyberry-projection-id: e6b84803e28824c3b7e0593badf3b7920e0c913bb09709b7f2b30475558c485f -->

importance 2@copyberry[bot]closedOriginal evidence ↗
pull request

Move `codex-execpolicy` to protocol dev dependencies

Move `codex-execpolicy` to protocol dev dependencies ## What changed Declare `codex-execpolicy` as a dev dependency of `codex-protocol`, matching its use exclusively by tests. <!-- copyberry-projection-id: 81f7b680437dc90a9e7f763db2b620f05f2154c43e5cab3aeaaef43e73e9a9e1 -->

importance 2@copyberry[bot]closedOriginal evidence ↗
pull request

Remove unused apply_patch prompt fallback

Remove unused apply_patch prompt fallback ## What changed - Delete the unused standalone `apply_patch` instruction template and its `codex-prompts` export. - Simplify prompt-caching coverage to assert that requests use the model's base instructions. <!-- copyberry-projection-id: 3d9409b8d9b35e31e06739a14b824035904bc928b371dae2c258b7f4e97b3083 -->

importance 2@copyberry[bot]closedOriginal evidence ↗
pull request

Add Guardian V2 extension scaffold

Add Guardian V2 extension scaffold ## What changed - Add the `codex-guardian-v2` crate with an extension install entry point that does not register contributors yet. - Register the crate in the Cargo workspace and add its Bazel target. <!-- copyberry-projection-id: c87cd1228d948473717d12eeada1529d3653abc088ae33010ff77f15cf03ff09 -->

importance 2@copyberry[bot]closedOriginal evidence ↗
pull request

Optimize orphan output normalization

Optimize orphan output normalization ## What changed - Collect borrowed call IDs in a single pass instead of cloning IDs across separate sets. - Record orphan positions and compact the history only when orphan outputs are present, while preserving the existing matching and error behavior. <!-- copyberry-projection-id: af969a7d4fa2b7defb08f3a5c0daa10c15b712bd

importance 2@copyberry[bot]closedOriginal evidence ↗