codex

bump(version): 0.1.2504251709 (#660 )

## `0.1.2504251709`

### 🚀 Features

- Add openai model info configuration (#551)
- Added provider to run quiet mode function (#571)
- Create parent directories when creating new files (#552)
- Print bug report URL in terminal instead of opening browser (#510)
(#528)
- Add support for custom provider configuration in the user config
(#537)
- Add support for OpenAI-Organization and OpenAI-Project headers (#626)
- Add specific instructions for creating API keys in error msg (#581)
- Enhance toCodePoints to prevent potential unicode 14 errors (#615)
- More native keyboard navigation in multiline editor (#655)
- Display error on selection of invalid model (#594)

### 🪲 Bug Fixes

- Model selection (#643)
- Nits in apply patch (#640)
- Input keyboard shortcuts (#676)
- `apply_patch` unicode characters (#625)
- Don't clear turn input before retries (#611)
- More loosely match context for apply_patch (#610)
- Update bug report template - there is no --revision flag (#614)
- Remove outdated copy of text input and external editor feature (#670)
- Remove unreachable "disableResponseStorage" logic flow introduced in
#543 (#573)
- Non-openai mode - fix for gemini content: null, fix 429 to throw
before stream (#563)
- Only allow going up in history when not already in history if input is
empty (#654)
- Do not grant "node" user sudo access when using run_in_container.sh
(#627)
- Update scripts/build_container.sh to use pnpm instead of npm (#631)
- Update lint-staged config to use pnpm --filter (#582)
- Non-openai mode - don't default temp and top_p (#572)
- Fix error catching when checking for updates (#597)
- Close stdin when running an exec tool call (#636)

Fouad Matin · 2025-04-25 17:15:40 -07:00

103093f793

fix: input keyboard shortcuts (#676 )

Fixes keyboard shortcuts:
- ctrl+a/e
- opt+arrow keys

Fouad Matin · 2025-04-25 16:58:09 -07:00

3f4762d969

ci: build Rust on Windows as part of CI (#665 )

While we aren't ready to provide Windows binaries of Codex CLI, it seems
like a good idea to ensure we guard platform-specific code
appropriately.

Michael Bolin · 2025-04-25 16:22:16 -07:00

f3ee933a74

fix: remove outdated copy of text input and external editor feature (#670 )

Signed-off-by: Thibault Sottiaux <tibo@openai.com>

Thibault Sottiaux · 2025-04-25 16:11:16 -07:00

44d68f9dbf

fix: handling weird unicode characters in apply_patch (#674 )

I � unicode

Misha Davidov · 2025-04-25 16:01:58 -07:00

15bf5ca971

fix: small fixes so Codex compiles on Windows (#673 )

Small fixes required:

* `ExitStatusExt` differs because UNIX expects exit code to be `i32`
whereas Windows does `u32`
* Marking a file "executable only by owner" is a bit more involved on
Windows. We just do something approximate for now (and add a TODO) to
get things compiling.

I created this PR on my personal Windows machine and `cargo test` and
`cargo clippy` succeed. Once this is in, I'll rebase
https://github.com/openai/codex/pull/665 on top so Windows stays fixed!

Michael Bolin · 2025-04-25 15:58:44 -07:00

c18f1689a9

fix: remove dependency on expanduser crate (#667 )

In putting up https://github.com/openai/codex/pull/665, I discovered
that the `expanduser` crate does not compile on Windows. Looking into
it, we do not seem to need it because we were only using it with a value
that was passed in via a command-line flag, so the shell expands `~` for
us before we see it, anyway. (I changed the type in `Cli` from `String`
to `PathBuf`, to boot.)

If we do need this sort of functionality in the future,
https://docs.rs/shellexpand/latest/shellexpand/fn.tilde.html seems
promising.

Michael Bolin · 2025-04-25 14:20:21 -07:00

ebd2ae4abd

fix: flipped the sense of Prompt.store in #642 (#663 )

I got the sense of this wrong in
https://github.com/openai/codex/pull/642. In that PR, I made
`--disable-response-storage` work, but broke the default case.

With this fix, both cases work and I think the code is a bit cleaner.

Michael Bolin · 2025-04-25 13:41:17 -07:00

9c3ebac3b7

[codex-rs] Improve linux sandbox timeouts (#662 )

* Fixes flaking rust unit test
* Adds explicit sandbox exec timeout handling

Parker Thompson · 2025-04-25 12:56:20 -07:00

7d9de34bc7

[codex-rs] CI performance for rust (#639 )

* Refactors the rust-ci into a matrix build
* Adds directory caching for the build artifacts
* Adds workflow dispatch for manual testing

Parker Thompson · 2025-04-25 12:44:03 -07:00

55e25abf78

feat: add ZDR support to Rust implementation (#642 )

This adds support for the `--disable-response-storage` flag across our
multiple Rust CLIs to support customers who have opted into Zero-Data
Retention (ZDR). The analogous changes to the TypeScript CLI were:

* https://github.com/openai/codex/pull/481
* https://github.com/openai/codex/pull/543

For a client using ZDR, `previous_response_id` will never be available,
so the `input` field of an API request must include the full transcript
of the conversation thus far. As such, this PR changes the type of
`Prompt.input` from `Vec<ResponseInputItem>` to `Vec<ResponseItem>`.

Practically speaking, `ResponseItem` was effectively a "superset" of
`ResponseInputItem` already. The main difference for us is that
`ResponseItem` includes the `FunctionCall` variant that we have to
include as part of the conversation history in the ZDR case.

Another key change in this PR is modifying `try_run_turn()` so that it
returns the `Vec<ResponseItem>` for the turn in addition to the
`Vec<ResponseInputItem>` produced by `try_run_turn()`. This is because
the caller of `run_turn()` needs to record the `Vec<ResponseItem>` when
ZDR is enabled.

To that end, this PR introduces `ZdrTranscript` (and adds
`zdr_transcript: Option<ZdrTranscript>` to `struct State` in `codex.rs`)
to take responsibility for maintaining the conversation transcript in
the ZDR case.

Michael Bolin · 2025-04-25 12:08:18 -07:00

b323d10ea7

feat(tui-rs): add support for mousewheel scrolling (#641 )

It is intuitive to try to scroll the conversation history using the
mouse in the TUI, but prior to this change, we only supported scrolling
via keyboard events.

This PR enables mouse capture upon initialization (and disables it on
exit) such that we get `ScrollUp` and `ScrollDown` events in
`codex-rs/tui/src/app.rs`. I initially mapped each event to scrolling by
one line, but that felt sluggish. I decided to introduce
`ScrollEventHelper` so we could debounce scroll events and measure the
number of scroll events in a 100ms window to determine the "magnitude"
of the scroll event. I put in a basic heuristic to start, but perhaps
someone more motivated can play with it over time.

`ScrollEventHelper` takes care of handling the atomic fields and thread
management to ensure an `AppEvent::Scroll` event is pumped back through
the event loop at the appropriate time with the accumulated delta.

Michael Bolin · 2025-04-25 12:01:52 -07:00

dc7b83666a

[codex-rs] Reliability pass on networking (#658 )

We currently see a behavior that looks like this:
```
2025-04-25T16:52:24.552789Z WARN codex_core::codex: stream disconnected - retrying turn (1/10 in 232ms)...
codex> event: BackgroundEvent { message: "stream error: stream disconnected before completion: Transport error: error decoding response body; retrying 1/10 in 232ms…" }
2025-04-25T16:52:54.789885Z WARN codex_core::codex: stream disconnected - retrying turn (2/10 in 418ms)...
codex> event: BackgroundEvent { message: "stream error: stream disconnected before completion: Transport error: error decoding response body; retrying 2/10 in 418ms…" }
```

This PR contains a few different fixes that attempt to resolve/improve
this:
1. **Remove overall client timeout.** I think
[this](https://github.com/openai/codex/pull/658/files#diff-c39945d3c42f29b506ff54b7fa2be0795b06d7ad97f1bf33956f60e3c6f19c19L173)
is perhaps the big fix -- it looks to me like this was actually timing
out even if events were still coming through, and that was causing a
disconnect right in the middle of a healthy stream.
2. **Cap response sizes.** We were frequently sending MUCH larger
responses than the upstream typescript `codex`, and that was definitely
not helping. [Fix
here](https://github.com/openai/codex/pull/658/files#diff-d792bef59aa3ee8cb0cbad8b176dbfefe451c227ac89919da7c3e536a9d6cdc0R21-R26)
for that one.
3. **Much higher idle timeout.** Our idle timeout value was much lower
than typescript.
4. **Sub-linear backoff.** We were much too aggressively backing off,
[this](https://github.com/openai/codex/pull/658/files#diff-5d5959b95c6239e6188516da5c6b7eb78154cd9cfedfb9f753d30a7b6d6b8b06R30-R33)
makes it sub-exponential but maintains the jitter and such.

I was seeing that `stream error: stream disconnected` behavior
constantly, and anecdotally I can no longer reproduce. It feels much
snappier.

oai-ragona · 2025-04-25 11:44:22 -07:00

d7a40195e6

perf: optimize token streaming with balanced approach (#635 )

- Replace setTimeout(10ms) with queueMicrotask for immediate processing
- Add minimal 3ms setTimeout for rendering to maintain readable UX
- Reduces per-token delay while preserving streaming experience
- Add performance test to verify optimization works correctly

---------

Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Thibault Sottiaux <tibo@openai.com>

Tomas Cupr · 2025-04-25 10:49:38 -07:00

4760aa1eb9

feat: more native keyboard navigation in multiline editor (#655 )

Signed-off-by: Thibault Sottiaux <tibo@openai.com>

Thibault Sottiaux · 2025-04-25 10:35:30 -07:00

d401283a41

feat: Add support for OpenAI-Organization and OpenAI-Project headers (#626 )

Added support for OpenAI-Organization and OpenAI-Project headers for
OpenAI API calls.

This is for #74

rumple · 2025-04-25 09:52:42 -07:00

69ce06d2f8

fix: only allow going up in history when not already in history if input is empty (#654 )

\+ cleanup below input help to be "ctrl+c to exit | "/" to see commands
| enter to send" now that we have command autocompletion
\+ minor other drive-by code cleanups

---------

Signed-off-by: Thibault Sottiaux <tibo@openai.com>

Thibault Sottiaux · 2025-04-25 09:39:24 -07:00

866626347b

fix: model selection (#643 )

fix: pass correct selected model in ModelOverlay

The ModelOverlay component was incorrectly passing the current model
instead of the newly selected model to its onSelect callback. This
prevented model changes from being applied properly.

The fix ensures that when a user selects a new model, the parent
component receives the correct newly selected model value, allowing
model changes to work as intended.

Pulipaka Sai Krishna · 2025-04-25 09:38:05 -07:00

2759ff39da

fix: nits in apply patch (#640 )

## Description

Fix a nit in `apply patch`, potentially improving performance slightly.

Luci · 2025-04-25 07:27:48 -07:00

3fe7e53327

docs: provider config (#653 )

close: #651

Hi! @tibo-openai 👋 Could you share some great examples of
`instructions.md` files? Thanks!

---------

Co-authored-by: Thibault Sottiaux <tibo@openai.com>

Luci · 2025-04-25 07:25:32 -07:00

1ef8e8afd3

chore: upgrade prettier to v3 (#644 )

## Description

This PR addresses the following improvements:

**Unify Prettier Version**: Currently, the Prettier version used in
`/package.json` and `/codex-cli/package.json` are different. In this PR,
we're updating both to use Prettier v3.

- Prettier v3 introduces improved support for JavaScript and TypeScript.
(e.g. the formatting scenario shown in the image below. This is more
aligned with the TypeScript indentation standard).

<img width="1126" alt="image"
src="https://github.com/user-attachments/assets/6e237eb8-4553-4574-b336-ed9561c55370"
/>

**Add Prettier Auto-Formatting in lint-staged**: We've added a step to
automatically run prettier --write on JavaScript and TypeScript files as
part of the lint-staged process, before the ESLint checks.

- This will help ensure that all committed code is properly formatted
according to the project's Prettier configuration.

Luci · 2025-04-25 07:21:50 -07:00

a9ecb2efce

fix: close stdin when running an exec tool call (#636 )

We were already doing this in the TypeScript version, but forgot to
bring this over to Rust:


https://github.com/openai/codex/blob/c38c2a59c72504a72a537123dc4b6026875cdfac/codex-cli/src/utils/agent/sandbox/raw-exec.ts#L76-L78

Michael Bolin · 2025-04-24 18:06:08 -07:00

bfe6fac463

fix: add RUST_BACKTRACE=full when running cargo test in CI (#638 )

This should provide more information in the event of a failure.

Michael Bolin · 2025-04-24 18:05:56 -07:00

6a9c9f4b6c

fix: only run rust-ci.yml on PRs that modify files in codex-rs (#637 )

The `rust-ci.yml` build appears to be a bit flaky (we're looking into
it...), so to save TypeScript contributors some noise, restrict the
`rust-ci.yml` job so that it only runs on PRs that touch files in
`codex-rs/`.

Michael Bolin · 2025-04-24 17:59:35 -07:00

5cdcbfa9b4

fix(utils): save config (#578 )

## Description

When `saveConfig` is called, the project doc is incorrectly saved into
user instructions. This change ensures that only user instructions are
saved to `instructions.md` during saveConfig, preventing data
corruption.

close: #576

---------

Co-authored-by: Thibault Sottiaux <tibo@openai.com>

Luci · 2025-04-24 17:32:33 -07:00

c38c2a59c7

feat: introduce codex_execpolicy crate for defining "safe" commands (#634 )

As described in detail in `codex-rs/execpolicy/README.md` introduced in
this PR, `execpolicy` is a tool that lets you define a set of _patterns_
used to match [`execv(3)`](https://linux.die.net/man/3/execv)
invocations. When a pattern is matched, `execpolicy` returns the parsed
version in a structured form that is amenable to static analysis.

The primary use case is to define patterns match commands that should be
auto-approved by a tool such as Codex. This supports a richer pattern
matching mechanism that the sort of prefix-matching we have done to
date, e.g.:


https://github.com/openai/codex/blob/5e40d9d2211737f46136610497bcd9a8271009e0/codex-cli/src/approvals.ts#L333-L354

Note we are still playing with the API and the `system_path` option in
particular still needs some work.

Michael Bolin · 2025-04-24 17:14:47 -07:00

58f0e5ab74

feat(bug-report): print bug report URL in terminal instead of opening browser (#510 ) (#528 )

Solves #510 
This PR changes the `/bug` command to print the URL into the terminal
(so it works in headless sessions) instead of trying to open a browser.

---------

Co-authored-by: Thibault Sottiaux <tibo@openai.com>

nvp159 · 2025-04-24 17:00:14 -07:00

5e40d9d221

feat: display error on selection of invalid model (#594 )

Up-to-date of #78 

Fixes #32

addressed requested changes @tibo-openai :) made sense to me


though, previous rationale with passing the state up was assuming there
could be a future need to have a shared state with all available models
being available to the parent

sooraj · 2025-04-24 16:56:00 -07:00

36a5a02d5c

fix: update scripts/build_container.sh to use pnpm instead of npm (#631 )

I suspect this is why some contributors kept accidentally including a
new `codex-cli/package-lock.json` in their PRs.

Note the `Dockerfile` still uses `npm` instead of `pnpm`, but that
appears to be fine. (Probably nicer to globally install as few things as
possible in the image.)

Michael Bolin · 2025-04-24 16:38:57 -07:00

bb2d411043

[codex-rs] More fine-grained sandbox flag support on Linux (#632 )

##### What/Why
This PR makes it so that in Linux we actually respect the different
types of `--sandbox` flag, such that users can apply network and
filesystem restrictions in combination (currently the only supported
behavior), or just pick one or the other.

We should add similar support for OSX in a future PR.

##### Testing
From Linux devbox, updated tests to use more specific flags:
```
test linux::tests_linux::sandbox_blocks_ping ... ok
test linux::tests_linux::sandbox_blocks_getent ... ok
test linux::tests_linux::test_root_read ... ok
test linux::tests_linux::test_dev_null_write ... ok
test linux::tests_linux::sandbox_blocks_dev_tcp_redirection ... ok
test linux::tests_linux::sandbox_blocks_ssh ... ok
test linux::tests_linux::test_writable_root ... ok
test linux::tests_linux::sandbox_blocks_curl ... ok
test linux::tests_linux::sandbox_blocks_wget ... ok
test linux::tests_linux::sandbox_blocks_nc ... ok
test linux::tests_linux::test_root_write - should panic ... ok
```

##### Todo
- [ ] Add negative tests (e.g. confirm you can hit the network if you
configure filesystem only restrictions)

oai-ragona · 2025-04-24 15:33:45 -07:00

b34ed2ab83

fix: do not grant "node" user sudo access when using run_in_container.sh (#627 )

This exploration came out of my review of
https://github.com/openai/codex/pull/414.

`run_in_container.sh` runs Codex in a Docker container like so:


https://github.com/openai/codex/blob/bd1c3deed9f4f103e755baa3f3a45e7a1c1a134b/codex-cli/scripts/run_in_container.sh#L51-L58

But then runs `init_firewall.sh` to set up the firewall to restrict
network access.

Previously, we did this by adding `/usr/local/bin/init_firewall.sh` to
the container and adding a special rule in `/etc/sudoers.d` so the
unprivileged user (`node`) could run the privileged `init_firewall.sh`
script to open up the firewall for `api.openai.com`:


https://github.com/openai/codex/blob/31d0d7a305305ad557035a2edcab60b6be5018d8/codex-cli/Dockerfile#L51-L56

Though I believe this is unnecessary, as we can use `docker exec --user
root` from _outside_ the container to run
`/usr/local/bin/init_firewall.sh` as `root` without adding a special
case in `/etc/sudoers.d`.

This appears to work as expected, as I tested it by doing the following:

```
./codex-cli/scripts/build_container.sh
./codex-cli/scripts/run_in_container.sh 'what is the output of `curl https://www.openai.com`'
```

This was a bit funny because in some of my runs, Codex wasn't convinced
it had network access, so I had to convince it to try the `curl`
request:


![image](https://github.com/user-attachments/assets/80bd487c-74e2-4cd3-aa0f-26a6edd8d3f7)

As you can see, when it ran `curl -s https\://www.openai.com`, it a
connection failure, so the network policy appears to be working as
intended.

Note this PR also removes `sudo` from the `apt-get install` list in the
`Dockerfile`.

Michael Bolin · 2025-04-24 14:25:02 -07:00

61805a832d

update: readme (#630 )

- mention support for ZDR
- codex open source fund

Fouad Matin · 2025-04-24 14:05:26 -07:00

bd1c3deed9

feat: initial import of Rust implementation of Codex CLI in codex-rs/ (#629 )

As stated in `codex-rs/README.md`:

Today, Codex CLI is written in TypeScript and requires Node.js 22+ to
run it. For a number of users, this runtime requirement inhibits
adoption: they would be better served by a standalone executable. As
maintainers, we want Codex to run efficiently in a wide range of
environments with minimal overhead. We also want to take advantage of
operating system-specific APIs to provide better sandboxing, where
possible.

To that end, we are moving forward with a Rust implementation of Codex
CLI contained in this folder, which has the following benefits:

- The CLI compiles to small, standalone, platform-specific binaries.
- Can make direct, native calls to
[seccomp](https://man7.org/linux/man-pages/man2/seccomp.2.html) and
[landlock](https://man7.org/linux/man-pages/man7/landlock.7.html) in
order to support sandboxing on Linux.
- No runtime garbage collection, resulting in lower memory consumption
and better, more predictable performance.

Currently, the Rust implementation is materially behind the TypeScript
implementation in functionality, so continue to use the TypeScript
implmentation for the time being. We will publish native executables via
GitHub Releases as soon as we feel the Rust version is usable.

Michael Bolin · 2025-04-24 13:31:40 -07:00

31d0d7a305

fix: apply_patch unicode characters (#625 )

fuzzy-er matching for apply_patch to handle u00A0 and u202F spaces.

Misha Davidov · 2025-04-24 13:04:37 -07:00

acc4acc81e

fix(agent-loop): notify type (#608 )

## Description

The `as AppConfig` type assertion in the constructor may introduce
potential type safety risks. Removing the assertion and making `notify`
an optional parameter could enhance type robustness and prevent
unexpected runtime errors.

close: #605

Luci · 2025-04-24 11:08:52 -07:00

e84fa6793d

feat: update README and config to support custom providers with API k… (#577 )

When using a non-built-in provider with the `--provider` option, users
are prompted:

```
Set the environment variable <provider>_API_KEY and re-run this command.
You can create a <provider>_API_KEY in the <provider> dashboard.
```

However, many users are confused because, even after correctly setting
`<provider>_API_KEY`, authentication may still fail unless
`OPENAI_API_KEY` is _also_ present in the environment. This is not
intuitive and leads to ambiguity about which API key is actually
required and used as a fallback, especially when using custom or
third-party (non-listed) providers.

Furthermore, the original README/documentation did not mention the
requirement to set `<provider>_BASE_URL` for non-built-in providers,
which is necessary for proper client behavior. This omission made the
configuration process more difficult for users trying to integrate with
custom endpoints.

Asa · 2025-04-24 11:08:19 -07:00

d1c0d5e683

feat: enhance toCodePoints to prevent potential unicode 14 errors (#615 )

## Description

`Array.from` may fail when handling certain characters newly added in
Unicode 14. Where possible, it seems better to use `Intl.Segmenter` for
more reliable processing.


![image](https://github.com/user-attachments/assets/2cbd779d-69d3-448e-b76a-d793cb639d96)

Luci · 2025-04-24 10:49:18 -07:00

6d68a90064

fix: update bug report template - there is no --revision flag (#614 )

I think there was a wrong word; --revision seems not to exist in help
and does nothing.

Ilya Kamen · 2025-04-24 10:48:42 -07:00

1008e1b9a0

fix: lint-staged error (#617 )

## Description

In a recent commit, the command `"cd codex-cli && pnpm run typecheck"`
was updated to `"pnpm --filter @openai/codex run typecheck"`.

However, this change introduces an issue: 
when running `pnpm --filter @openai/codex run typecheck`, it executes
`tsc --noEmit somefile.ts` directly, bypassing the `tsconfig.json`
configuration. As a result, numerous type errors are triggered,
preventing successful commits.

Close: #619

Luci · 2025-04-24 10:48:35 -07:00

257167a034

feat: more loosely match context for apply_patch (#610 )

More of a proposal than anything but models seem to struggle with
composing valid patches for `apply_patch` for context matching when
there are unicode look-a-likes involved. This would normalize them.

```
top-level          # ASCII
top-level          # U+2011 NON-BREAKING HYPHEN
top–level          # U+2013 EN DASH
top—level          # U+2014 EM DASH
top‒level          # U+2012 FIGURE DASH
```

thanks unicode.

Misha Davidov · 2025-04-24 09:05:19 -07:00

9b102965b9

feat: add specific instructions for creating API keys in error msg (#581 )

Updates the error message for missing Gemini API keys to reference
"Google AI Studio" instead of the generic "GEMINI dashboard". This
provides users with more accurate information about where to obtain
their Gemini API keys.

This could be extended to other providers as well.

theg1239 · 2025-04-24 06:33:34 -05:00

ad1e39c903

chore: update lint-staged config to use pnpm --filter (#582 )

Replaced directory-specific commands with workspace-aware pnpm commands

theg1239 · 2025-04-24 06:33:13 -05:00

006992b85a

fix: don't clear turn input before retries (#611 )

The current turn input in the agent loop is being discarded before
consuming the stream events which causes the stream reconnect (after
rate limit failure) to not include the inputs. Since the new stream
includes the previous response ID, it triggers a bad request exception
considering the input doesn't match what OpenAI has stored on the server
side and subsequently a very confusing error message of: `No tool output
found for function call call_xyz`.

This should fix https://github.com/openai/codex/issues/586.

## Testing

I have a personal project that I'm working on that runs multiple Codex
CLIs in parallel and often runs into rate limit errors (as seen in the
OpenAI logs). After making this change, I am no longer experiencing
Codex crashing and it was able to retry and handle everything gracefully
until completion (even though I still see rate limiting in the OpenAI
logs).

Connor Christie · 2025-04-24 06:29:36 -05:00

622323a59b

bug: fix error catching when checking for updates (#597 )

This fixes https://github.com/openai/codex/issues/480 where the latest
code was crashing when attempting to be run inside docker since the
update checker attempts to reach out to `npm.antfu.dev` but that DNS is
not allowed in the firewall rules.

I believe the original code was attempting to catch and ignore any
errors when checking for updates but was doing so incorrectly. If you
use await on a promise, you have to use a standard try/catch instead of
`Promise.catch` so this fixes that.

## Testing

### Before

```
$ scripts/run_in_container.sh "explain this project to me"
7d1aa845edf9a36fe4d5b331474b5cb8ba79537b682922b554ea677f14996c6b
Resolving api.openai.com...
Adding 162.159.140.245 for api.openai.com
Adding 172.66.0.243 for api.openai.com
Host network detected as: 172.17.0.0/24
Firewall configuration complete
Verifying firewall rules...
Firewall verification passed - unable to reach https://example.com as expected
Firewall verification passed - able to reach https://api.openai.com as expected
TypeError: fetch failed
    at node:internal/deps/undici/undici:13510:13
    at process.processTicksAndRejections (node:internal/process/task_queues:95:5)
    at async getLatestVersionBatch (file:///usr/local/share/npm-global/lib/node_modules/@openai/codex/dist/cli.js:132669:17)
    at async getLatestVersion (file:///usr/local/share/npm-global/lib/node_modules/@openai/codex/dist/cli.js:132674:19)
    at async getUpdateCheckInfo (file:///usr/local/share/npm-global/lib/node_modules/@openai/codex/dist/cli.js:132748:20)
    at async checkForUpdates (file:///usr/local/share/npm-global/lib/node_modules/@openai/codex/dist/cli.js:132772:23)
    at async file:///usr/local/share/npm-global/lib/node_modules/@openai/codex/dist/cli.js:142027:1 {
  [cause]: AggregateError [ECONNREFUSED]: 
      at internalConnectMultiple (node:net:1122:18)
      at afterConnectMultiple (node:net:1689:7) {
    code: 'ECONNREFUSED',
    [errors]: [ [Error], [Error] ]
  }
}
```

### After

```
$ scripts/run_in_container.sh "explain this project to me"
91aa716e3d3f86c9cf6013dd567be31b2c44eb5d7ab184d55ef498731020bb8d
Resolving api.openai.com...
Adding 162.159.140.245 for api.openai.com
Adding 172.66.0.243 for api.openai.com
Host network detected as: 172.17.0.0/24
Firewall configuration complete
Verifying firewall rules...
Firewall verification passed - unable to reach https://example.com as expected
Firewall verification passed - able to reach https://api.openai.com as expected
╭──────────────────────────────────────────────────────────────╮
│ ● OpenAI Codex (research preview) v0.1.2504221401            │
╰──────────────────────────────────────────────────────────────╯
╭──────────────────────────────────────────────────────────────╮
│ localhost session: 7c782f196ae04503866e39f071e26a69          │
│ ↳ model: o4-mini                                             │
│ ↳ provider: openai                                           │
│ ↳ approval: full-auto                                        │
╰──────────────────────────────────────────────────────────────╯
user
explain this project to me
╭───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│( ●    ) 2s  Thinking                                                                                                                                                                                                                                                  │
╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
  send q or ctrl+c to exit | send "/clear" to reset | send "/help" for commands | press enter to send | shift+enter for new line — 100% context left
```

Connor Christie · 2025-04-23 15:21:00 -07:00

c75cb507f0

feat: add support for custom provider configuration in the user config (#537 )

### What

- Add support for loading and merging custom provider configurations
from a local `providers.json` file.
- Allow users to override or extend default providers with their own
settings.

### Why

This change enables users to flexibly customize and extend provider
endpoints and API keys without modifying the codebase, making the CLI
more adaptable for various LLM backends and enterprise use cases.

### How

- Introduced `loadProvidersFromFile` and `getMergedProviders` in config
logic.
- Added/updated related tests in [tests/config.test.tsx]


### Checklist

- [x] Lint passes for changed files
- [x] Tests pass for all files
- [x] Documentation/comments updated as needed

---------

Co-authored-by: Thibault Sottiaux <tibo@openai.com>

kshern · 2025-04-23 01:45:56 -04:00

146a61b073

feat: added provider to run quiet mode function (#571 )

Adding support to be able to run other models in quiet mode

ie: `codex --approval-mode full-auto -q "explain the current directory"
--provider xai --model grok-3-beta`

Erick · 2025-04-23 01:12:18 -04:00

b428d66f2b

fix: remove unreachable "disableResponseStorage" logic flow introduced in #543 (#573 )

This PR cleans up unreachable code that was added as a result of
https://github.com/openai/codex/pull/543.

The code being removed is already being handled above:

https://github.com/openai/codex/blob/23f0887df3323a2b2a5bd87780c8845776b56bba/codex-cli/src/utils/agent/agent-loop.ts#L535-L539

Connor Christie · 2025-04-23 01:08:52 -04:00

cbeb5c3057

bug: non-openai mode - don't default temp and top_p (#572 )

I haven't seen any actual errors due to this, but it's been bothering me
that I had it defaulted to 1. I think best to leave it undefined and
have each provider do their thing

Daniel Nakov · 2025-04-23 01:07:40 -04:00

4261973467

bug: non-openai mode - fix for gemini content: null, fix 429 to throw before stream (#563 )

Gemini's API is finicky, it 400's without an error when you pass
content: null
Also fixed the rate limiting issues by throwing outside of the iterator.
I think there's a separate issue with the second isRateLimit check in
agent-loop - turnInput is cleared by that time, so it retries without
the last message.

Daniel Nakov · 2025-04-22 20:37:48 -04:00

23f0887df3

feat: create parent directories when creating new files. (#552 )

apply_patch doesn't create parent directories when creating a new file
leading to confusion and flailing by the agent. This will create parent
directories automatically when absent.

---------

Co-authored-by: Thibault Sottiaux <tibo@openai.com>

Misha Davidov · 2025-04-22 19:45:17 -04:00

20b6ef0de8

3718 Commits