codex

Fix admin skills. (#8305 )

We were assembling the skill roots in two different places, and the
admin root was missing in one of them. This change centralizes root
selection into a helper so both paths stay in sync.

xl-openai · 2025-12-19 04:10:19 +00:00

339b052d68

Add short descriptions to system skills (#8301 )

Gav Verma · 2025-12-19 02:44:53 +00:00

f4371d2f6c

Support admin scope skills. (#8296 )

a new scope reads from /etc/codex

xl-openai · 2025-12-19 02:28:56 +00:00

8120c8765b

skills feature default on. (#8297 )

skills default on.

xl-openai · 2025-12-18 18:26:46 -08:00

d35337227a

Fix tests (#8299 )

Fix broken tests.

xl-openai · 2025-12-19 02:07:23 +00:00

ba835c3c36

UI tweaks on skills popup. (#8250 )

Only display the skill name (not the folder), and truncate the skill
description to a maximum of two lines.

xl-openai · 2025-12-19 01:16:51 +00:00

dcc01198e2

feat: collapse "waiting" of unified_exec (#8257 )

Screenshots here but check the snapshot files to see it better
<img width="712" height="408" alt="Screenshot 2025-12-18 at 11 58 02"
src="https://github.com/user-attachments/assets/84a2c410-0767-4870-84d1-ae1c0d4c445e"
/>
<img width="523" height="352" alt="Screenshot 2025-12-18 at 11 17 41"
src="https://github.com/user-attachments/assets/d029c7ea-0feb-4493-9dca-af43a0c70c52"
/>

jif-oai · 2025-12-18 17:03:43 -08:00

6c76d17713

feat: introduce ExternalSandbox policy (#8290 )

## Description

Introduced `ExternalSandbox` policy to cover use case when sandbox
defined by outside environment, effectively it translates to
`SandboxMode#DangerFullAccess` for file system (since sandbox configured
on container level) and configurable `network_access` (either Restricted
or Enabled by outside environment).

as example you can configure `ExternalSandbox` policy as part of
`sendUserTurn` v1 app_server API:

```
 {
            "conversationId": <id>,
            "cwd": <cwd>,
            "approvalPolicy": "never",
            "sandboxPolicy": {
                  "type": ""external-sandbox",
                  "network_access": "enabled"/"restricted"
            },
            "model": <model>,
            "effort": <effort>,
            ....
        }
```

Anton Panasenko · 2025-12-18 17:02:03 -08:00

3429de21b3

chore: migrate from Config::load_from_base_config_with_overrides to ConfigBuilder (#8276 )

https://github.com/openai/codex/pull/8235 introduced `ConfigBuilder` and
this PR updates all call non-test call sites to use it instead of
`Config::load_from_base_config_with_overrides()`.

This is important because `load_from_base_config_with_overrides()` uses
an empty `ConfigRequirements`, which is a reasonable default for testing
so the tests are not influenced by the settings on the host. This method
is now guarded by `#[cfg(test)]` so it cannot be used by business logic.

Because `ConfigBuilder::build()` is `async`, many of the test methods
had to be migrated to be `async`, as well. On the bright side, this made
it possible to eliminate a bunch of `block_on_future()` stuff.

Michael Bolin · 2025-12-18 16:12:52 -08:00

3d4ced3ff5

fix: remove duplicate shell_snapshot FeatureSpec (#8274 )

regression: #8199

Signed-off-by: Koichi Shiraishi <zchee.io@gmail.com>

Koichi Shiraishi · 2025-12-18 15:55:47 -08:00

2d9826098e

fix: change codex/sandbox-state/update from a notification to a request (#8142 )

Historically, `accept_elicitation_for_prompt_rule()` was flaky because
we were using a notification to update the sandbox followed by a `shell`
tool request that we expected to be subject to the new sandbox config,
but because [rmcp](https://crates.io/crates/rmcp) MCP servers delegate
each incoming message to a new Tokio task, messages are not guaranteed
to be processed in order, so sometimes the `shell` tool call would run
before the notification was processed.

Prior to this PR, we relied on a generous `sleep()` between the
notification and the request to reduce the change of the test flaking
out.

This PR implements a proper fix, which is to use a _request_ instead of
a notification for the sandbox update so that we can wait for the
response to the sandbox request before sending the request to the
`shell` tool call. Previously, `rmcp` did not support custom requests,
but I fixed that in
https://github.com/modelcontextprotocol/rust-sdk/pull/590, which made it
into the `0.12.0` release (see #8288).

This PR updates `shell-tool-mcp` to expect
`"codex/sandbox-state/update"` as a _request_ instead of a notification
and sends the appropriate ack. Note this behavior is tied to our custom
`codex/sandbox-state` capability, which Codex honors as an MCP client,
which is why `core/src/mcp_connection_manager.rs` had to be updated as
part of this PR, as well.

This PR also updates the docs at `shell-tool-mcp/README.md`.

Michael Bolin · 2025-12-18 15:32:01 -08:00

46baedd7cb

Support skills shortDescription. (#8278 )

Allow SKILL.md to specify a more human-readable short description as
skill metadata.

xl-openai · 2025-12-18 23:13:18 +00:00

358a5baba0

Update system skills bundled with codex-rs (#8253 )

Synced with https://github.com/openai/skills/tree/main/skills/.system

Gav Verma · 2025-12-18 14:30:00 -08:00

1cd1cf17c6

chore: upgrade rmcp crate from 0.10.0 to 0.12.0 (#8288 )

Version `0.12.0` includes
https://github.com/modelcontextprotocol/rust-sdk/pull/590, which I will
use in https://github.com/openai/codex/pull/8142.

Changes:

- `rmcp::model::CustomClientNotification` was renamed to
`rmcp::model::CustomNotification`
- a bunch of types have a `meta` field now, but it is `Option`, so I
added `meta: None` to a bunch of things

Michael Bolin · 2025-12-18 14:28:46 -08:00

53f53173a8

Set exclude to true by default in app server (#8281 )

Andrew Ambrosino · 2025-12-18 14:28:30 -08:00

9fb9ed6cea

model list (#8286 )

<img width="200" alt="7ff2254b-e96f-42fc-8232-b4e76cb26248"
src="https://github.com/user-attachments/assets/1f56799d-e2cd-4b69-9290-854943f7c6b6"
/>

pakrym-oai · 2025-12-18 14:13:49 -08:00

8f0b383621

feat(app-server): add v2 deprecation notice (#8285 )

Add a v2 event for deprecation notices so we can get rid of
`codex/event/deprecation_notice`.

Owen Lin · 2025-12-18 21:45:36 +00:00

d7ae342ff4

feat: add support for /etc/codex/requirements.toml on UNIX (#8277 )

This implements the new config design where config _requirements_ are
loaded separately (and with a special schema) as compared to config
_settings_. In particular, on UNIX, with this PR, you could define
`/etc/codex/requirements.toml` with:

```toml
allowed_approval_policies = ["never", "on-request"]
```

to enforce that `Config.approval_policy` must be one of those two values
when Codex runs.

We plan to expand the set of things that can be restricted by
`/etc/codex/requirements.toml` in short order.

Note that requirements can come from several sources:

- new MDM key on macOS (not implemented yet)
- `/etc/codex/requirements.toml`
- re-interpretation of legacy MDM key on macOS
(`com.openai.codex/config_toml_base64`)
- re-interpretation of legacy `/etc/codex/managed_config.toml`

So our resolution strategy is to load TOML data from those sources, in
order. Later TOMLs are "merged" into previous TOMLs, but any field that
is already set cannot be overwritten. See
`ConfigRequirementsToml::merge_unset_fields()`.

Michael Bolin · 2025-12-18 13:36:55 -08:00

2f048f2063

feat: add /ps (#8279 )

See snapshots for view of edge cases
This is still named `UnifiedExecSessions` for consistency across the
code but should be renamed to `BackgroundTerminals` in a follow-up

Example:
<img width="945" height="687" alt="Screenshot 2025-12-18 at 20 12 53"
src="https://github.com/user-attachments/assets/92f39ff2-243c-4006-b402-e3fa9e93c952"
/>

jif-oai · 2025-12-18 21:09:06 +00:00

4fb0b547d6

fix: flaky tests 5 (#8282 )

jif-oai · 2025-12-18 21:08:43 +00:00

87abf06e78

add a default dacl to restricted token to enable reading of pipes (#8280 )

this fixes sandbox errors (legacy and elevated) for commands that
include pipes, which the model often favors.

iceweasel-oai · 2025-12-18 12:59:52 -08:00

6395430220

Terminal Detection Metadata for Per-Terminal Scroll Scaling (#8252 )

# Terminal Detection Metadata for Per-Terminal Scroll Scaling

## Summary
Expand terminal detection into structured metadata (`TerminalInfo`) with
multiplexer awareness, plus a testable environment shim and
characterization tests.

## Context / Motivation
- TUI2 owns its viewport and scrolling model (see
`codex-rs/tui2/docs/tui_viewport_and_history.md`), so scroll behavior
must be consistent across terminals and independent of terminal
scrollback quirks.
- Prior investigations show mouse wheel scroll deltas vary noticeably by
terminal. To tune scroll scaling (line increments per wheel tick) we
need reliable terminal identification, including when running inside
tmux/zellij.
- tmux is especially tricky because it can mask the underlying terminal;
we now consult `tmux display-message` client termtype/name to attribute
sessions to the actual terminal rather than tmux itself.
- This remains backwards compatible with the existing OpenTelemetry
user-agent token because `user_agent()` is still derived from the same
environment signals (now via `TerminalInfo`).

## Changes
- Introduce `TerminalInfo`, `TerminalName`, and `Multiplexer` with
`TERM_PROGRAM`/`TERM`/multiplexer detection and user-agent formatting in
`codex-rs/core/src/terminal.rs`.
- Add an injectable `Environment` trait + `FakeEnvironment` for testing,
and comprehensive characterization tests covering known terminals, tmux
client termtype/name, and zellij.
- Document module usage and detection order; update `terminal_info()` to
be the primary interface for callers.

## Testing
- `cargo test -p codex-core terminal::tests`
- manually checked ghostty, iTerm2, Terminal.app, vscode, tmux, zellij,
Warp, alacritty, kitty.
```
2025-12-18T07:07:49.191421Z  INFO Detected terminal info terminal=TerminalInfo { name: Iterm2, term_program: Some("iTerm.app"), version: Some("3.6.6"), term: None, multiplexer: None }
2025-12-18T07:07:57.991776Z  INFO Detected terminal info terminal=TerminalInfo { name: AppleTerminal, term_program: Some("Apple_Terminal"), version: Some("455.1"), term: None, multiplexer: None }
2025-12-18T07:08:07.732095Z  INFO Detected terminal info terminal=TerminalInfo { name: WarpTerminal, term_program: Some("WarpTerminal"), version: Some("v0.2025.12.10.08.12.stable_03"), term: None, multiplexer: None }
2025-12-18T07:08:24.860316Z  INFO Detected terminal info terminal=TerminalInfo { name: Kitty, term_program: None, version: None, term: None, multiplexer: None }
2025-12-18T07:08:38.302761Z  INFO Detected terminal info terminal=TerminalInfo { name: Alacritty, term_program: None, version: None, term: None, multiplexer: None }
2025-12-18T07:08:50.887748Z  INFO Detected terminal info terminal=TerminalInfo { name: VsCode, term_program: Some("vscode"), version: Some("1.107.1"), term: None, multiplexer: None }
2025-12-18T07:10:01.309802Z  INFO Detected terminal info terminal=TerminalInfo { name: WezTerm, term_program: Some("WezTerm"), version: Some("20240203-110809-5046fc22"), term: None, multiplexer: None }
2025-12-18T08:05:17.009271Z  INFO Detected terminal info terminal=TerminalInfo { name: Ghostty, term_program: Some("ghostty"), version: Some("1.2.3"), term: None, multiplexer: None }
2025-12-18T08:05:23.819973Z  INFO Detected terminal info terminal=TerminalInfo { name: Ghostty, term_program: Some("ghostty"), version: Some("1.2.3"), term: Some("xterm-ghostty"), multiplexer: Some(Tmux { version: Some("3.6a") }) }
2025-12-18T08:05:35.572853Z  INFO Detected terminal info terminal=TerminalInfo { name: Ghostty, term_program: Some("ghostty"), version: Some("1.2.3"), term: None, multiplexer: Some(Zellij) }
```

## Notes / Follow-ups
- Next step is to wire `TerminalInfo` into TUI2’s scroll scaling
configuration and add a per-terminal tuning table.
- The log output in TUI2 helps validate real-world detection before
applying behavior changes.

Josh McKinney · 2025-12-18 12:50:00 -08:00

df46ea48a2

grant read ACL to exe directory first so we can call the command runner (#8275 )

when granting read access to the sandbox user, grant the
codex/command-runner exe directory first so commands can run before the
entire read ACL process is finished.

iceweasel-oai · 2025-12-18 19:52:32 +00:00

ad41182ee8

tui: improve rendering of search cell (#8273 )

before:

<img width="795" height="150" alt="Screenshot 2025-12-18 at 10 48 01 AM"
src="https://github.com/user-attachments/assets/6f4d8856-b4c2-4e2a-b60a-b86f82b956a0"
/>

after:

<img width="795" height="150" alt="Screenshot 2025-12-18 at 10 48 39 AM"
src="https://github.com/user-attachments/assets/dd0d167a-5d09-4bb7-9d36-95a2eb1aaa83"
/>

Jeremy Rose · 2025-12-18 11:05:26 -08:00

be274cbe62

splash screen (#8270 )

# External (non-OpenAI) Pull Request Requirements

Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md

If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.

Include a link to a bug report or enhancement request.

Ahmed Ibrahim · 2025-12-18 10:59:53 -08:00

7157421daa

feat: migrate to new constraint-based loading strategy (#8251 )

This is a significant change to how layers of configuration are applied.
In particular, the `ConfigLayerStack` now has two important fields:

- `layers: Vec<ConfigLayerEntry>`
- `requirements: ConfigRequirements`

We merge `TomlValue`s across the layers, but they are subject to
`ConfigRequirements` before creating a `Config`.

How I would review this PR:

- start with `codex-rs/app-server-protocol/src/protocol/v2.rs` and note
the new variants added to the `ConfigLayerSource` enum:
`LegacyManagedConfigTomlFromFile` and `LegacyManagedConfigTomlFromMdm`
- note that `ConfigLayerSource` now has a `precedence()` method and
implements `PartialOrd`
- `codex-rs/core/src/config_loader/layer_io.rs` is responsible for
loading "admin" preferences from `/etc/codex/managed_config.toml` and
MDM. Because `/etc/codex/managed_config.toml` is now deprecated in favor
of `/etc/codex/requirements.toml` and `/etc/codex/config.toml`, we now
include some extra information on the `LoadedConfigLayers` returned in
`layer_io.rs`.
- `codex-rs/core/src/config_loader/mod.rs` has major changes to
`load_config_layers_state()`, which is what produces `ConfigLayerStack`.
The docstring has the new specification and describes the various layers
that will be loaded and the precedence order.
- It uses the information from `LoaderOverrides` "twice," both in the
spirit of legacy support:
- We use one instances to derive an instance of `ConfigRequirements`.
Currently, the only field in `managed_config.toml` that contributes to
`ConfigRequirements` is `approval_policy`. This PR introduces
`Constrained::allow_only()` to support this.
- We use a clone of `LoaderOverrides` to derive
`ConfigLayerSource::LegacyManagedConfigTomlFromFile` and
`ConfigLayerSource::LegacyManagedConfigTomlFromMdm` layers, as
appropriate. As before, this ends up being a "best effort" at enterprise
controls, but is enforcement is not guaranteed like it is for
`ConfigRequirements`.
- Now we only create a "user" layer if `$CODEX_HOME/config.toml` exists.
(Previously, a user layer was always created for `ConfigLayerStack`.)
- Similarly, we only add a "session flags" layer if there are CLI
overrides.
- `config_loader/state.rs` contains the updated implementation for
`ConfigLayerStack`. Note the public API is largely the same as before,
but the implementation is quite different. We leverage the fact that
`ConfigLayerSource` is now `PartialOrd` to ensure layers are in the
correct order.
- A `Config` constructed via `ConfigBuilder.build()` will use
`load_config_layers_state()` to create the `ConfigLayerStack` and use
the associated `ConfigRequirements` when constructing the `Config`
object.
- That said, a `Config` constructed via
`Config::load_from_base_config_with_overrides()` does _not_ yet use
`ConfigBuilder`, so it creates a `ConfigRequirements::default()` instead
of loading a proper `ConfigRequirements`. I will fix this in a
subsequent PR.

Then the following files are mostly test changes:

```
codex-rs/app-server/tests/suite/v2/config_rpc.rs
codex-rs/core/src/config/service.rs
codex-rs/core/src/config_loader/tests.rs
```

Again, because we do not always include "user" and "session flags"
layers when the contents are empty, `ConfigLayerStack` sometimes has
fewer layers than before (and the precedence order changed slightly),
which is the main reason integration tests changed.

Michael Bolin · 2025-12-18 10:06:05 -08:00

b903285746

cloud: default to current branch in cloud exec (#7460 )

## Summary
- add a shared git-ref resolver and use it for `codex cloud exec` and
TUI task submission
- expose a new `--branch` flag to override the git ref passed to cloud
tasks
- cover the git-ref resolution behavior with new async unit tests and
supporting dev dependencies

## Testing
- cargo test -p codex-cloud-tasks


------
[Codex
Task](https://chatgpt.com/codex/tasks/task_i_692decc6cbec8332953470ef063e11ab)

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Jeremy Rose <172423086+nornagon-openai@users.noreply.github.com>
Co-authored-by: Jeremy Rose <nornagon@openai.com>

squinlan-oai · 2025-12-18 17:44:38 +00:00

425c8dc372

feat: add name to beta features (#8266 )

Add a name to Beta features

<img width="906" height="153" alt="Screenshot 2025-12-18 at 16 42 49"
src="https://github.com/user-attachments/assets/d56f3519-0613-4d9a-ad4d-38b1a7eb125a"
/>

jif-oai · 2025-12-18 16:59:46 +00:00

aea47b6553

caribou (#8265 )

Welcome caribou

<img width="1536" height="1024" alt="image"
src="https://github.com/user-attachments/assets/2a67b21f-40cf-4518-aee4-691af331ab50"
/>

Ahmed Ibrahim · 2025-12-18 08:58:44 -08:00

f084e5264b

chore: prefer AsRef<Path> to &Path (#8249 )

This is some minor API cleanup that will make it easier to use
`AbsolutePathBuf` in more places in a subsequent PR.

Michael Bolin · 2025-12-18 08:50:13 -08:00

deafead169

chores: clean picker (#8232 )

# External (non-OpenAI) Pull Request Requirements

Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md

If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.

Include a link to a bug report or enhancement request.

Ahmed Ibrahim · 2025-12-18 08:41:34 -08:00

374d591311

chore: simplify loading of Mac-specific logic in config_loader (#8248 )

Over in `config_loader/macos.rs`, we were doing this complicated `mod`
thing to expose one version of `load_managed_admin_config_layer()` for
Mac:


https://github.com/openai/codex/blob/580c59aa9af61cb4bffb5b204bd16a5dcc4bc911/codex-rs/core/src/config_loader/macos.rs#L4-L5

While exposing a trivial implementation for non-Mac:


https://github.com/openai/codex/blob/580c59aa9af61cb4bffb5b204bd16a5dcc4bc911/codex-rs/core/src/config_loader/macos.rs#L110-L117

That was being used like this:


https://github.com/openai/codex/blob/580c59aa9af61cb4bffb5b204bd16a5dcc4bc911/codex-rs/core/src/config_loader/layer_io.rs#L47-L48

This PR simplifies that callsite in `layer_io.rs` to just be:

```rust
    #[cfg(not(target_os = "macos"))]
    let managed_preferences = None;
```

And updates `config_loader/mod.rs` so we only pull in `macos.rs` on Mac:

```rust
#[cfg(target_os = "macos")]
mod macos;
```

This simplifies `macos.rs` considerably, though it looks like a big
change because everything gets unindented and reformatted because we can
drop the whole `mod native` thing now.




---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/8248).
* #8251
* #8249
* __->__ #8248

Michael Bolin · 2025-12-18 07:35:16 -08:00

9bf41e9262

chore: add beta features (#8201 )

jif-oai · 2025-12-18 13:09:12 +00:00

1cfacbf56d

nit: ui background terminals (#8255 )

jif-oai · 2025-12-18 10:34:10 +00:00

cea76b85af

Reintroduce feature flags for skills. (#8244 )

1. Reintroduce feature flags for skills;
2. UI tweaks (truncate descriptions, better validation error display).

xl-openai · 2025-12-18 01:14:11 -08:00

5c8d22138a

Change "Team" to "Buisness" and add Education (#8221 )

This pull request updates the ChatGPT login description in the
onboarding authentication widgets to clarify which plans include usage.
The description now lists "Business" rather than "Team" and adds
"Education" plans in addition to the previously mentioned plans.

I have read the CLA Document and I hereby sign the CLAs.

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

Ethan Phillips · 2025-12-18 08:35:22 +00:00

e1deeefa0f

fix: introduce ConfigBuilder (#8235 )

Introduce `ConfigBuilder` as an alternative to our existing `Config`
constructors.

I noticed that the existing constructors,
`Config::load_with_cli_overrides()` and
`Config::load_with_cli_overrides_and_harness_overrides()`, did not take
`codex_home` as a parameter, which can be a problem.

Historically, when Codex was purely a CLI, we wanted to be extra sure
that the creation of `codex_home` was always done via
`find_codex_home()`, so we did not expose `codex_home` as a parameter
when creating `Config` in business logic. But in integration tests,
`codex_home` nearly always needs to be configured (as a temp directory),
which is why callers would have to go through
`Config::load_from_base_config_with_overrides()` instead.

Now that the Codex harness also functions as an app server, which could
conceivably load multiple threads where `codex_home` is parameterized
differently in each one, I think it makes sense to make this
configurable. Going to a builder pattern makes it more flexible to
ensure an arbitrary permutation of options can be set when constructing
a `Config` while using the appropriate defaults for the options that
aren't set explicitly.

Ultimately, I think this should make it possible for us to make
`Config::load_from_base_config_with_overrides()` private because all
integration tests should be able to leverage `ConfigBuilder` instead.
Though there could be edge cases, so I'll pursue that migration after we
get through the current config overhaul.






---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/8235).
* #8237
* __->__ #8235

Michael Bolin · 2025-12-17 23:45:09 -08:00

580c59aa9a

Make loading malformed skills fail-open (#8243 )

Instead of failing to start Codex, clearly call out that N skills did
not load and provide warnings so that the user may fix them.

<img width="3548" height="874" alt="image"
src="https://github.com/user-attachments/assets/6ce041b2-1373-4007-a6dd-0194e58fafe4"
/>

Gav Verma · 2025-12-17 23:41:04 -08:00

50dafbc31b

Support SYSTEM skills. (#8220 )

1. Remove PUBLIC skills and introduce SYSTEM skills embedded in the
binary and installed into $CODEX_HOME/skills/.system at startup.
2. Skills are now always enabled (feature flag removed).
3. Update skills/list to accept forceReload and plumb it through (not
used by clients yet).

xl-openai · 2025-12-17 18:48:28 -08:00

da3869eeb6

Show migration link (#8228 )

# External (non-OpenAI) Pull Request Requirements

Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md

If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.

Include a link to a bug report or enhancement request.

Ahmed Ibrahim · 2025-12-18 02:03:40 +00:00

6f102e18c4

chore: cleanup Config instantiation codepaths (#8226 )

This PR does various types of cleanup before I can proceed with more
ambitious changes to config loading.

First, I noticed duplicated code across these two methods:


https://github.com/openai/codex/blob/774bd9e432fa2e0f4e059e97648cf92216912e19/codex-rs/core/src/config/mod.rs#L314-L324


https://github.com/openai/codex/blob/774bd9e432fa2e0f4e059e97648cf92216912e19/codex-rs/core/src/config/mod.rs#L334-L344

This has now been consolidated in
`load_config_as_toml_with_cli_overrides()`.

Further, I noticed that `Config::load_with_cli_overrides()` took two
similar arguments:


https://github.com/openai/codex/blob/774bd9e432fa2e0f4e059e97648cf92216912e19/codex-rs/core/src/config/mod.rs#L308-L311

The difference between `cli_overrides` and `overrides` was not
immediately obvious to me. At first glance, it appears that one should
be able to be expressed in terms of the other, but it turns out that
some fields of `ConfigOverrides` (such as `cwd` and
`codex_linux_sandbox_exe`) are, by design, not configurable via a
`.toml` file or a command-line `--config` flag.

That said, I discovered that many callers of
`Config::load_with_cli_overrides()` were passing
`ConfigOverrides::default()` for `overrides`, so I created two separate
methods:

- `Config::load_with_cli_overrides(cli_overrides: Vec<(String,
TomlValue)>)`
- `Config::load_with_cli_overrides_and_harness_overrides(cli_overrides:
Vec<(String, TomlValue)>, harness_overrides: ConfigOverrides)`

The latter has a long name, as it is _not_ what should be used in the
common case, so the extra typing is designed to draw attention to this
fact. I tried to update the existing callsites to use the shorter name,
where possible.

Further, in the cases where `ConfigOverrides` is used, usually only a
limited subset of fields are actually set, so I updated the declarations
to leverage `..Default::default()` where possible.

Michael Bolin · 2025-12-17 18:01:17 -08:00

a8797019a1

feat: model picker (#8209 )

# External (non-OpenAI) Pull Request Requirements

Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md

If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.

Include a link to a bug report or enhancement request.

Ahmed Ibrahim · 2025-12-17 16:12:35 -08:00

774bd9e432

speed and reliability improvements for setting reads ACLs (#8216 )

- Batch read ACL creation for online/offline sandbox user
- creates a new ACL helper process that is long-lived and runs in the
background
- uses a mutex so that only one helper process is running at a time.

iceweasel-oai · 2025-12-17 15:27:52 -08:00

25ecd0c2e4

Load models from static file (#8153 )

- Load models from static file as a fallback
- Make API users use this file directly
- Add tests to make sure updates to the file always serialize

Ahmed Ibrahim · 2025-12-17 14:34:13 -08:00

927a6acbea

feat: make list_models non-blocking (#8198 )

### Summary
* Make `app_server.list_models` to be non-blocking and consumers (i.e.
extension) can manage the flow themselves.
* Force config to use remote models and therefore fetch codex-auto model
list.

Shijie Rao · 2025-12-17 12:13:16 -08:00

df35189366

fix: PathBuf -> AbsolutePathBuf in ConfigToml struct (#8205 )

We should not have any `PathBuf` fields in `ConfigToml` or any of the
transitive structs we include, as we should use `AbsolutePathBuf`
instead so that we do not have to keep track of the file from which
`ConfigToml` was loaded such that we need it to resolve relative paths
later when the values of `ConfigToml` are used.

I only found two instances of this: `experimental_instructions_file` and
`experimental_compact_prompt_file`. Incidentally, when these were
specified as relative paths, they were resolved against `cwd` rather
than `config.toml`'s parent, which seems wrong to me. I changed the
behavior so they are resolved against the parent folder of the
`config.toml` being parsed, which we get "for free" due to the
introduction of `AbsolutePathBufGuard ` in
https://github.com/openai/codex/pull/7796.

While it is not great to change the behavior of a released feature,
these fields are prefixed with `experimental_`, which I interpret to
mean we have the liberty to change the contract.

For reference:

- `experimental_instructions_file` was introduced in
https://github.com/openai/codex/pull/1803
- `experimental_compact_prompt_file` was introduced in
https://github.com/openai/codex/pull/5959

Michael Bolin · 2025-12-17 12:08:18 -08:00

1e9babe178

feat: add config to disable warnings around ghost snapshot (#8178 )

jif-oai · 2025-12-17 18:50:22 +00:00

3d92b443b0

fix: session downgrade (#8196 )

The problem is that the `tokio` task own an `Arc` reference of the
session and that this task only exit with the broadcast channel get
closed. But this never get closed if the session is not dropped. So it's
a snake biting his tail basically

The most notable result was that non of the `Drop` implementation were
triggered (temporary files, shell snapshots, session cleaning etc etc)
when closing the session (through a `/new` for example)

The fix is just to weaken the `Arc` and upgrade it on the fly

jif-oai · 2025-12-17 10:44:39 -08:00

167553f00d

fix: proper skills dir cleanup (#8194 )

jif-oai · 2025-12-17 18:31:03 +00:00

9f28c6251d

chore: update listMcpServerStatus to be non-blocking (#8151 )

### Summary
* Update `listMcpServerStatus` to be non-blocking by wrapping it with
tokio:spawn.

Shijie Rao · 2025-12-17 10:11:02 -08:00

3702793882

1978 Commits