Commit Graph
610 Commits
Author SHA1 Message Date
Dylan Hurd c9c5d694c9 OnceLock 2025-11-03 21:04:18 -08:00
Dylan Hurd 86d636cf33 core: exclude OS from env_context diffs; update tests for Windows/WSL OS block 2025-11-03 21:04:17 -08:00
Dylan Hurd 9f7097160d feat: Better OS Detection, starting with windows 2025-11-03 20:56:27 -08:00
Vinh Nguyen a1ee10b438 fix: improve usage URLs in status card and snapshots (#6111)
Hi OpenAI Codex team, currently "Visit chatgpt.com/codex/settings/usage
for up-to-date information on rate limits and credits" message in status
card and error messages. For now, without the "https://" prefix, the
link cannot be clicked directly from most terminals or chat interfaces.

<img width="636" height="127" alt="Screenshot 2025-11-02 at 22 47 06"
src="https://github.com/user-attachments/assets/5ea11e8b-fb74-451c-85dc-f4d492b2678b"
/>

---

The fix is intent to improve this issue:

- It makes the link clickable in terminals that support it, hence better
accessibility
- It follows standard URL formatting practices
- It maintains consistency with other links in the application (like the
existing "https://openai.com/chatgpt/pricing" links)

Thank you!
2025-11-02 21:44:59 -08:00
Eric Traut 0c7efa0cfd Fix incorrect "deprecated" message about experimental config key (#6131)
When I enable `experimental_sandbox_command_assessment`, I get an
incorrect deprecation warning: "experimental_sandbox_command_assessment
is deprecated. Use experimental_sandbox_command_assessment instead."

This PR fixes this error.
2025-11-02 16:33:09 -08:00
Eric Traut d5853d9c47 Changes to sandbox command assessment feature based on initial experiment feedback (#6091)
* Removed sandbox risk categories; feedback indicates that these are not
that useful and "less is more"
* Tweaked the assessment prompt to generate terser answers
* Fixed bug in orchestrator that prevents this feature from being
exposed in the extension
2025-11-01 14:52:23 -07:00
Thomas Stokes d9118c04bf Parse the Azure OpenAI rate limit message (#5956)
Fixes #4161

Currently Codex uses a regex to parse the "Please try again in 1.898s"
OpenAI-style rate limit message, so that it can wait the correct
duration before retrying. Azure OpenAI returns a different error that
looks like "Rate limit exceeded. Try again in 35 seconds."

This PR extends the regex and parsing code to match in a more fuzzy
manner, handling anything matching the pattern "try again in
\<duration>\<unit>".
2025-11-01 09:33:13 -07:00
jif-oaiandpakrym-oai 611e00c862 feat: compactor 2 (#6027)
Co-authored-by: pakrym-oai <pakrym@openai.com>
2025-10-31 14:27:08 -07:00
Ahmed Ibrahim c8ebb2a0dc Add warning on compact (#6052)
This PR introduces the ability for `core` to send `warnings` as it can
send `errors. It also sends a warning on compaction.

<img width="811" height="187" alt="image"
src="https://github.com/user-attachments/assets/0947a42d-b720-420d-b7fd-115f8a65a46a"
/>
2025-10-31 13:27:33 -07:00
Ahmed IbrahimandGabriel Peal 1c8507b32a Truncate total tool calls text (#5979)
Put a cap on the aggregate output of text content on tool calls.

---------

Co-authored-by: Gabriel Peal <gpeal@users.noreply.github.com>
2025-10-31 10:30:36 -07:00
pakrym-oai 2371d771cc Update user instruction message format (#6010) 2025-10-30 18:44:02 -07:00
Ahmed Ibrahim dc2aeac21f override verbosity for gpt-5-codex (#6007)
we are seeing [reports](https://github.com/openai/codex/issues/6004) of
users having verbosity in their config.toml and facing issues.
gpt-5-codex doesn't accept other values rather than medium for
verbosity.
2025-10-31 00:45:05 +00:00
zhao-oai dcf73970d2 rate limit errors now provide absolute time (#6000) 2025-10-30 20:33:25 -04:00
Ahmed Ibrahim a3d3719481 Remove last turn reasoning filtering (#5986) 2025-10-30 23:20:32 +00:00
iceweasel-oai 87cce88f48 Windows Sandbox - Alpha version (#4905)
- Added the new codex-windows-sandbox crate that builds both a library
entry point (run_windows_sandbox_capture) and a CLI executable to launch
commands inside a Windows restricted-token sandbox, including ACL
management, capability SID provisioning, network lockdown, and output
capture
(windows-sandbox-rs/src/lib.rs:167, windows-sandbox-rs/src/main.rs:54).
- Introduced the experimental WindowsSandbox feature flag and wiring so
Windows builds can opt into the sandbox:
SandboxType::WindowsRestrictedToken, the in-process execution path, and
platform sandbox selection now honor the flag (core/src/features.rs:47,
core/src/config.rs:1224, core/src/safety.rs:19,
core/src/sandboxing/mod.rs:69, core/src/exec.rs:79,
core/src/exec.rs:172).
- Updated workspace metadata to include the new crate and its
Windows-specific dependencies so the core crate can link against it
(codex-rs/
    Cargo.toml:91, core/Cargo.toml:86).
- Added a PowerShell bootstrap script that installs the Windows
toolchain, required CLI utilities, and builds the workspace to ease
development
    on the platform (scripts/setup-windows.ps1:1).
- Landed a Python smoke-test suite that exercises
read-only/workspace-write policies, ACL behavior, and network denial for
the Windows sandbox
    binary (windows-sandbox-rs/sandbox_smoketests.py:1).
2025-10-30 15:51:57 -07:00
Bernard Niset ff6d4cec6b fix: Update seatbelt policy for java on macOS (#3987)
# Summary

This PR is related to the Issue #3978 and contains a fix to the seatbelt
profile for macOS that allows to run java/jdk tooling from the sandbox.
I have found that the included change is the minimum change to make it
run on my machine.

There is a unit test added by codex when making this fix. I wonder if it
is useful since you need java installed on the target machine for it to
be relevant. I can remove it it is better.

Fixes #3978
2025-10-30 14:25:04 -07:00
Celia Chen 6ef658a9f9 [Hygiene] Remove include_view_image_tool config (#5976)
There's still some debate about whether we want to expose
`tools.view_image` or `feature.view_image` so those are left unchanged
for now, but this old `include_view_image_tool` config is good-to-go.
Also updated the doc to reflect that `view_image` tool is now by default
true.
2025-10-30 13:23:24 -07:00
Anton Panasenko 9572cfc782 [codex] add developer instructions (#5897)
we are using developer instructions for code reviews, we need to pass
them in cli as well.
2025-10-30 11:18:31 -07:00
jif-oai f4f9695978 feat: compaction prompt configurable (#5959)
```
 codex -c compact_prompt="Summarize in bullet points"
 ```
2025-10-30 14:24:24 +00:00
Ahmed Ibrahim 5fcc380bd9 Pass initial history as an optional to codex delegate (#5950)
This will give us more freedom on controlling the delegation. i.e we can
fork our history and run `compact`.
2025-10-30 07:22:42 -07:00
jif-oai aa76003e28 chore: unify config crates (#5958) 2025-10-30 10:28:32 +00:00
Ahmed Ibrahim fac548e430 Send delegate header (#5942)
Send delegate type header
2025-10-30 09:49:40 +00:00
zhao-oai b34efde2f3 asdf (#5940)
.
2025-10-30 01:10:41 +00:00
Ahmed Ibrahim 7aa46ab5fc ignore agent message deltas for the review mode (#5937)
The deltas produce the whole json output. ignore them.
2025-10-30 00:47:55 +00:00
pakrym-oaiandOwen Lin 3429e82e45 Add item streaming events (#5546)
Adds AgentMessageContentDelta, ReasoningContentDelta,
ReasoningRawContentDelta item streaming events while maintaining
compatibility for old events.

---------

Co-authored-by: Owen Lin <owen@openai.com>
2025-10-29 22:33:57 +00:00
Ahmed Ibrahim 13e1d0362d Delegate review to codex instance (#5572)
In this PR, I am exploring migrating task kind to an invocation of
Codex. The main reason would be getting rid off multiple
`ConversationHistory` state and streamlining our context/history
management.

This approach depends on opening a channel between the sub-codex and
codex. This channel is responsible for forwarding `interactive`
(`approvals`) and `non-interactive` events. The `task` is responsible
for handling those events.

This opens the door for implementing `codex as a tool`, replacing
`compact` and `review`, and potentially subagents.

One consideration is this code is very similar to `app-server` specially
in the approval part. If in the future we wanted an interactive
`sub-codex` we should consider using `codex-mcp`
2025-10-29 21:04:25 +00:00
jif-oai db31f6966d chore: config editor (#5878)
The goal is to have a single place where we actually write files

In a follow-up PR, will move everything config related in a dedicated
module and move the helpers in a dedicated file
2025-10-29 20:52:46 +00:00
Rasmus Rygaard 39e09c289d Add a wrapper around raw response items (#5923)
We currently have nested enums when sending raw response items in the
app-server protocol. This makes downstream schemas confusing because we
need to embed `type`-discriminated enums within each other.

This PR adds a small wrapper around the response item so we can keep the
schemas separate
2025-10-29 20:32:40 +00:00
jif-oai 3183935bd7 feat: add output even in sandbox denied (#5908) 2025-10-29 18:21:18 +00:00
jif-oai 060637b4d4 feat: deprecation warning (#5825)
<img width="955" height="311" alt="Screenshot 2025-10-28 at 14 26 25"
src="https://github.com/user-attachments/assets/99729b3d-3bc9-4503-aab3-8dc919220ab4"
/>
2025-10-29 12:29:28 +00:00
jif-oai fa92cd92fa chore: merge git crates (#5909)
Merge `git-apply` and `git-tooling` into `utils/`
2025-10-29 12:11:44 +00:00
Abhishek Bhardwaj 89591e4246 feature: Add "!cmd" user shell execution (#2471)
feature: Add "!cmd" user shell execution

This change lets users run local shell commands directly from the TUI by
prefixing their input with ! (e.g. !ls). Output is truncated to keep the
exec cell usable, and Ctrl-C cleanly
  interrupts long-running commands (e.g. !sleep 10000).

**Summary of changes**

- Route Op::RunUserShellCommand through a dedicated UserShellCommandTask
(core/src/tasks/user_shell.rs), keeping the task logic out of codex.rs.
- Reuse the existing tool router: the task constructs a ToolCall for the
local_shell tool and relies on ShellHandler, so no manual MCP tool
lookup is required.
- Emit exec lifecycle events (ExecCommandBegin/ExecCommandEnd) so the
TUI can show command metadata, live output, and exit status.

**End-to-end flow**

  **TUI handling**

1. ChatWidget::submit_user_message (TUI) intercepts messages starting
with !.
2. Non-empty commands dispatch Op::RunUserShellCommand { command };
empty commands surface a help hint.
3. No UserInput items are created, so nothing is enqueued for the model.

  **Core submission loop**
4. The submission loop routes the op to handlers::run_user_shell_command
(core/src/codex.rs).
5. A fresh TurnContext is created and Session::spawn_user_shell_command
enqueues UserShellCommandTask.

  **Task execution**
6. UserShellCommandTask::run emits TaskStartedEvent, formats the
command, and prepares a ToolCall targeting local_shell.
  7. ToolCallRuntime::handle_tool_call dispatches to ShellHandler.

  **Shell tool runtime**
8. ShellHandler::run_exec_like launches the process via the unified exec
runtime, honoring sandbox and shell policies, and emits
ExecCommandBegin/End.
9. Stdout/stderr are captured for the UI, but the task does not turn the
resulting ToolOutput into a model response.

  **Completion**
10. After ExecCommandEnd, the task finishes without an assistant
message; the session marks it complete and the exec cell displays the
final output.

  **Conversation context**

- The command and its output never enter the conversation history or the
model prompt; the flow is local-only.
  - Only exec/task events are emitted for UI rendering.

**Demo video**


https://github.com/user-attachments/assets/fcd114b0-4304-4448-a367-a04c43e0b996
2025-10-29 00:31:20 -07:00
Axojhf 802d2440b4 Fix bash detection failure in VS Code Codex extension on Windows under certain conditions (#3421)
Found that the VS Code Codex extension throws “Error starting
conversation” when initializing a conversation with Git for Windows’
bash on PATH.
Debugging showed the bash-detection logic did not return as expected;
this change makes it reliable in that scenario.
Possibly related to issue #2841.
2025-10-28 21:29:16 -07:00
pakrym-oai ef3e075ad6 Refresh tokens more often and log a better message when both auth and token refresh fails (#5655)
<img width="784" height="153" alt="image"
src="https://github.com/user-attachments/assets/c44b0eb2-d65c-4fc2-8b54-b34f7e1c4d95"
/>
2025-10-28 18:55:53 -07:00
Anton Panasenko 149e198ce8 [codex][app-server] resume conversation from history (#5893) 2025-10-28 18:18:03 -07:00
Ahmed Ibrahim ef55992ab0 remove beta experimental header (#5892) 2025-10-28 21:28:56 +00:00
pakrym-oai 1b8f2543ac Filter out reasoning items from previous turns (#5857)
Reduces request size and prevents 400 errors when switching between API
orgs.

Based on Responses API behavior described in
https://cookbook.openai.com/examples/responses_api/reasoning_items#caching
2025-10-28 11:39:34 -07:00
Jeremy Rose 65107d24a2 Fix handling of non-main default branches for cloud task submissions (#5069)
## Summary
- detect the repository's default branch before submitting a cloud task
- expose a helper in `codex_core::git_info` for retrieving the default
branch name

Fixes #4888


------
https://chatgpt.com/codex/tasks/task_i_68e96093cf28832ca0c9c73fc618a309
2025-10-28 11:02:25 -07:00
jif-oai 5ba2a17576 chore: decompose submission loop (#5854) 2025-10-28 15:23:46 +00:00
jif-oai be4bdfec93 chore: drop useless shell stuff (#5848) 2025-10-28 14:52:52 +00:00
Celia Chen 4a42c4e142 [Auth] Choose which auth storage to use based on config (#5792)
This PR is a follow-up to #5591. It allows users to choose which auth
storage mode they want by using the new
`cli_auth_credentials_store_mode` config.
2025-10-27 19:41:49 -07:00
Josh McKinney 66a4b89822 feat(tui): clarify Windows auto mode requirements (#5568)
## Summary
- Coerce Windows `workspace-write` configs back to read-only, surface
the forced downgrade in the approvals popup,
  and funnel users toward WSL or Full Access.
- Add WSL installation instructions to the Auto preset on Windows while
keeping the preset available for other
  platforms.
- Skip the trust-on-first-run prompt on native Windows so new folders
remain read-only without additional
  confirmation.
- Expose a structured sandbox policy resolution from config to flag
Windows downgrades and adjust tests (core,
exec, TUI) to reflect the new behavior; provide a Windows-only approvals
snapshot.

  ## Testing
  - cargo fmt
- cargo test -p codex-core
config::tests::add_dir_override_extends_workspace_writable_roots
- cargo test -p codex-exec
suite::resume::exec_resume_preserves_cli_configuration_overrides
- cargo test -p codex-tui
chatwidget::tests::approvals_selection_popup_snapshot
- cargo test -p codex-tui
approvals_popup_includes_wsl_note_for_auto_mode
  - cargo test -p codex-tui windows_skips_trust_prompt
  - just fix -p codex-core
  - just fix -p codex-tui
2025-10-28 01:19:32 +00:00
Ahmed Ibrahim d7b333be97 Truncate the content-item for mcp tools (#5835)
This PR truncates the text output of MCP tool
2025-10-28 00:39:35 +00:00
Gabriel Peal b0bdc04c30 [MCP] Render MCP tool call result images to the model (#5600)
It's pretty amazing we have gotten here without the ability for the
model to see image content from MCP tool calls.

This PR builds off of 4391 and fixes #4819. I would like @KKcorps to get
adequete credit here but I also want to get this fix in ASAP so I gave
him a week to update it and haven't gotten a response so I'm going to
take it across the finish line.


This test highlights how absured the current situation is. I asked the
model to read this image using the Chrome MCP
<img width="2378" height="674" alt="image"
src="https://github.com/user-attachments/assets/9ef52608-72a2-4423-9f5e-7ae36b2b56e0"
/>

After this change, it correctly outputs:
> Captured the page: image dhows a dark terminal-style UI labeled
`OpenAI Codex (v0.0.0)` with prompt `model: gpt-5-codex medium` and
working directory `/codex/codex-rs`
(and more)  

Before this change, it said:
> Took the full-page screenshot you asked for. It shows a long,
horizontally repeating pattern of stylized people in orange, light-blue,
and mustard clothing, holding hands in alternating poses against a white
background. No text or other graphics-just rows of flat illustration
stretching off to the right.

Without this change, the Figma, Playwright, Chrome, and other visual MCP
servers are pretty much entirely useless.

I tested this change with the openai respones api as well as a third
party completions api
2025-10-27 17:55:57 -04:00
Ahmed Ibrahim 7226365397 Centralize truncation in conversation history (#5652)
move the truncation logic to conversation history to use on any tool
output. This will help us in avoiding edge cases while truncating the
tool calls and mcp calls.
2025-10-27 14:05:35 -07:00
Celia Chen 0fc295d958 [Auth] Add keyring support for Codex CLI (#5591)
Follow-up PR to #5569. Add Keyring Support for Auth Storage in Codex CLI
as well as a hybrid mode (default to persisting in keychain but fall
back to file when unavailable.)

It also refactors out the keyringstore implementation from rmcp-client
[here](https://github.com/openai/codex/blob/main/codex-rs/rmcp-client/src/oauth.rs)
to a new keyring-store crate.

There will be a follow-up that picks the right credential mode depending
on the config, instead of hardcoding `AuthCredentialsStoreMode::File`.
2025-10-27 12:10:11 -07:00
jif-oai 3e50f94d76 feat: support verbosity in model_family (#5821) 2025-10-27 18:46:30 +00:00
Celia Chen eb5b1b627f [Auth] Introduce New Auth Storage Abstraction for Codex CLI (#5569)
This PR introduces a new `Auth Storage` abstraction layer that takes
care of read, write, and load of auth tokens based on the
AuthCredentialsStoreMode. It is similar to how we handle MCP client
oauth
[here](https://github.com/openai/codex/blob/main/codex-rs/rmcp-client/src/oauth.rs).
Instead of reading and writing directly from disk for auth tokens, Codex
CLI workflows now should instead use this auth storage using the public
helper functions.

This PR is just a refactor of the current code so the behavior stays the
same. We will add support for keyring and hybrid mode in follow-up PRs.

I have read the CLA Document and I hereby sign the CLA
2025-10-27 11:01:14 -07:00
Eric Traut 0c1ff1d3fd Made token refresh code resilient to missing id_token (#5782)
This PR does the following:
1. Changes `try_refresh_token` to handle the case where the endpoint
returns a response without an `id_token`. The OpenID spec indicates that
this field is optional and clients should not assume it's present.
2. Changes the `attempt_stream_responses` to propagate token refresh
errors rather than silently ignoring them.
3. Fixes a typo in a couple of error messages (unrelated to the above,
but something I noticed in passing) - "reconnect" should be spelled
without a hyphen.

This PR does not implement the additional suggestion from @pakrym-oai
that we should sign out when receiving `refresh_token_expired` from the
refresh endpoint. Leaving this as a follow-on because I'm undecided on
whether this should be implemented in `try_refresh_token` or its
callers.
2025-10-27 10:09:53 -07:00
jif-oai 775fbba6e0 feat: return an error if unknown enabled/disabled feature (#5817) 2025-10-27 16:53:00 +00:00