Commit Graph
830 Commits
Author SHA1 Message Date
Ahmed Ibrahim 5c79085dae models 2026-01-05 10:44:23 -08:00
Ahmed Ibrahim d7b0997d32 models 2026-01-05 10:10:32 -08:00
Ahmed Ibrahim 88d090a2b7 models 2026-01-05 10:02:44 -08:00
Ahmed Ibrahim 5f56a2328b models 2026-01-05 09:41:38 -08:00
Ahmed Ibrahim ff5f74b6bf models 2026-01-05 09:22:04 -08:00
Ahmed Ibrahim a944b0ebf1 files 2026-01-05 08:17:34 -08:00
Ahmed Ibrahim c982cbd6e1 files 2026-01-04 14:29:05 -08:00
Ahmed Ibrahim 9cd4d895ba async 2026-01-03 22:12:55 -08:00
Ahmed Ibrahim 2de731490e Remove model family from tui (#8488)
- Remove model family from tui
2026-01-02 11:30:04 -08:00
sayan-oai bf732600ea [chore] add additional_details to StreamErrorEvent + wire through (#8307)
### What

Builds on #8293.

Add `additional_details`, which contains the upstream error message, to
relevant structures used to pass along retryable `StreamError`s.

Uses the new TUI status indicator's `details` field (shows under the
status header) to display the `additional_details` error to the user on
retryable `Reconnecting...` errors. This adds clarity for users for
retryable errors.

Will make corresponding change to VSCode extension to show
`additional_details` as expandable from the `Reconnecting...` cell.

Examples:
<img width="1012" height="326" alt="image"
src="https://github.com/user-attachments/assets/f35e7e6a-8f5e-4a2f-a764-358101776996"
/>

<img width="1526" height="358" alt="image"
src="https://github.com/user-attachments/assets/0029cbc0-f062-4233-8650-cc216c7808f0"
/>
2025-12-24 10:07:38 -08:00
Josh McKinney 96a65ff0ed perf(tui): cap redraw scheduling to 60fps (#8499)
Clamp frame draw notifications in the `FrameRequester` scheduler so we
don't redraw more frequently than a user can perceive.

This applies to both `codex-tui` and `codex-tui2`, and keeps the
draw/dispatch loops simple by centralizing the rate limiting in a small
helper module.

- Add `FrameRateLimiter` (pure, unit-tested) to clamp draw deadlines
- Apply the limiter in the scheduler before emitting `TuiEvent::Draw`
- Use immediate redraw requests for scroll paths (scheduler now
coalesces + clamps)
- Add scheduler tests covering immediate/delayed interactions
2025-12-23 19:10:15 -08:00
Ahmed Ibrahim 40de81e7af Remove reasoning format (#8484)
This isn't very useful parameter. 

logic:
```
if model puts `**` in their reasoning, trim it and visualize the header.
if couldn't trim: don't render
if model doesn't support: don't render
```

We can simplify to:
```
if could trim, visualize header.
if not, don't render
```
2025-12-23 16:01:46 -08:00
Michael Bolin 972b5853a0 fix: fix test that was writing temp file to cwd instead of TMPDIR (#8493)
I am trying to support building with [Buck2](https://buck2.build), which
reports which files have changed between invocations of `buck2 test` and
`tmp_delete_example.txt` came up. This turned out to be the reason.
2025-12-23 15:48:06 -08:00
sayan-oai 53eb2e9f27 [tui] add optional details to TUI status header (#8293)
### What

Add optional `details` field to TUI's status indicator header. `details`
is shown under the header with text wrapping and a max height of 3
lines.

Duplicated changes to `tui2`.

### Why

Groundwork for displaying error details under `Reconnecting...` for
clarity with retryable errors.

Basic examples
<img width="1012" height="326" alt="image"
src="https://github.com/user-attachments/assets/dd751ceb-b179-4fb2-8fd1-e4784d6366fb"
/>

<img width="1526" height="358" alt="image"
src="https://github.com/user-attachments/assets/bbe466fc-faff-4a78-af7f-3073ccdd8e34"
/>

Truncation example
<img width="936" height="189" alt="image"
src="https://github.com/user-attachments/assets/f3f1b5dd-9050-438b-bb07-bd833c03e889"
/>

### Tests
Tested locally, added tests for truncation.
2025-12-23 12:40:40 -08:00
Josh McKinney f6275a5142 chore(tui): include tracing targets in file logs (#8418)
with_target(true) is the default for tracing-subscriber, but we
previously disabled it for file output.

Keep it enabled so we can selectively enable specific targets/events at
runtime via RUST_LOG=..., and then grep by target/module in the log file
during troubleshooting.

before and after:

<img width="629" height="194" alt="image"
src="https://github.com/user-attachments/assets/33f7df3f-0c5d-4d3f-b7b7-80b03d4acd21"
/>
2025-12-22 15:59:30 -08:00
sayan-oai 4673090f73 feat: open prompt in configured external editor (#7606)
Add `ctrl+g` shortcut to enable opening current prompt in configured
editor (`$VISUAL` or `$EDITOR`).


- Prompt is updated with editor's content upon editor close.
- Paste placeholders are automatically expanded when opening the
external editor, and are not "recompressed" on close
- They could be preserved in the editor, but it would be hard to prevent
the user from modifying the placeholder text directly, which would drop
the mapping to the `pending_paste` value
- Image placeholders stay as-is
- `ctrl+g` explanation added to shortcuts menu, snapshot tests updated



https://github.com/user-attachments/assets/4ee05c81-fa49-4e99-8b07-fc9eef0bbfce
2025-12-22 15:12:23 -08:00
jif-oai 45727b9ed3 chore: drop undo from the docs (#8431) 2025-12-22 15:09:48 +00:00
jif-oai 7a8407bbb6 chore: un-ship undo (#8424) 2025-12-22 09:53:03 +01:00
Michael Bolin a6974087e5 chore: enusre the logic that creates ConfigLayerStack has access to cwd (#8353)
`load_config_layers_state()` should load config from a
`.codex/config.toml` in any folder between the `cwd` for a thread and
the project root. Though in order to do that,
`load_config_layers_state()` needs to know what the `cwd` is, so this PR
does the work to thread the `cwd` through for existing callsites.

A notable exception is the `/config` endpoint in app server for which a
`cwd` is not guaranteed to be associated with the query, so the `cwd`
param is `Option<AbsolutePathBuf>` to account for this case.

The logic to make use of the `cwd` will be done in a follow-up PR.
2025-12-19 20:11:27 -08:00
Ahmed Ibrahim f0dc6fd3c7 Rename OpenAI models to models manager (#8346)
# 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.
2025-12-19 16:20:05 -08:00
Michael Bolin dc61fc5f50 feat: support allowed_sandbox_modes in requirements.toml (#8298)
This adds support for `allowed_sandbox_modes` in `requirements.toml` and
provides legacy support for constraining sandbox modes in
`managed_config.toml`. This is converted to `Constrained<SandboxPolicy>`
in `ConfigRequirements` and applied to `Config` such that constraints
are enforced throughout the harness.

Note that, because `managed_config.toml` is deprecated, we do not add
support for the new `external-sandbox` variant recently introduced in
https://github.com/openai/codex/pull/8290. As noted, that variant is not
supported in `config.toml` today, but can be configured programmatically
via app server.
2025-12-19 21:09:20 +00:00
Michael Bolin 7e5c343ef5 feat: make ConstraintError an enum (#8330)
This will make it easier to test for expected errors in unit tests since
we can compare based on the field values rather than the message (which
might change over time). See https://github.com/openai/codex/pull/8298
for an example.

It also ensures more consistency in the way a `ConstraintError` is
constructed.
2025-12-19 19:03:50 +00:00
xl-openai ba835c3c36 Fix tests (#8299)
Fix broken tests.
2025-12-19 02:07:23 +00:00
xl-openai dcc01198e2 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.
2025-12-19 01:16:51 +00:00
jif-oai 6c76d17713 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"
/>
2025-12-18 17:03:43 -08:00
Anton Panasenko 3429de21b3 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>,
            ....
        }
```
2025-12-18 17:02:03 -08:00
Michael Bolin 3d4ced3ff5 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.
2025-12-18 16:12:52 -08:00
xl-openai 358a5baba0 Support skills shortDescription. (#8278)
Allow SKILL.md to specify a more human-readable short description as
skill metadata.
2025-12-18 23:13:18 +00:00
jif-oai 4fb0b547d6 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"
/>
2025-12-18 21:09:06 +00:00
Jeremy Rose be274cbe62 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"
/>
2025-12-18 11:05:26 -08:00
Ahmed Ibrahim 7157421daa 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.
2025-12-18 10:59:53 -08:00
jif-oai aea47b6553 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"
/>
2025-12-18 16:59:46 +00:00
Ahmed Ibrahim f084e5264b caribou (#8265)
Welcome caribou

<img width="1536" height="1024" alt="image"
src="https://github.com/user-attachments/assets/2a67b21f-40cf-4518-aee4-691af331ab50"
/>
2025-12-18 08:58:44 -08:00
Ahmed Ibrahim 374d591311 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.
2025-12-18 08:41:34 -08:00
jif-oai cea76b85af nit: ui background terminals (#8255) 2025-12-18 10:34:10 +00:00
Ethan PhillipsandCopilot e1deeefa0f 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>
2025-12-18 08:35:22 +00:00
Gav Verma 50dafbc31b 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"
/>
2025-12-17 23:41:04 -08:00
Ahmed Ibrahim 6f102e18c4 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.
2025-12-18 02:03:40 +00:00
Michael Bolin a8797019a1 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.
2025-12-17 18:01:17 -08:00
Ahmed Ibrahim 774bd9e432 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.
2025-12-17 16:12:35 -08:00
Ahmed Ibrahim 927a6acbea 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
2025-12-17 14:34:13 -08:00
jif-oai a2cc0032e0 chore: move back stuff out of beta program (#8199) 2025-12-17 17:58:47 +00:00
jif-oai f74e0cda92 feat: unified exec footer (#8117)
# With `unified_exec`
Known tools are correctly casted
<img width="1150" height="312" alt="Screenshot 2025-12-16 at 19 27 28"
src="https://github.com/user-attachments/assets/24150ee5-e88d-461b-a459-483c24784196"
/>
If a session exit the turn, we render it with the "Ran ..."
<img width="1168" height="355" alt="Screenshot 2025-12-16 at 19 27 58"
src="https://github.com/user-attachments/assets/3f00b60c-2d57-4f9d-a201-9cc8388957cb"
/>
If a session does not exit during the turn, it is closed at the end of
the turn but this is not rendered
<img width="642" height="342" alt="Screenshot 2025-12-16 at 19 34 37"
src="https://github.com/user-attachments/assets/c2bd9283-7017-4915-ba73-c52199b0b28e"
/>

# Without `unified_exec`
No changes
<img width="740" height="603" alt="Screenshot 2025-12-16 at 19 31 21"
src="https://github.com/user-attachments/assets/ca5d90fe-a9b2-42ba-bcd7-3e98c4ed22e8"
/>
2025-12-17 17:12:04 +00:00
jif-oai ac6ba286aa feat: experimental menu (#8071)
This will automatically render any `Stage::Beta` features.

The change only gets applied to the *next session*. This started as a
bug but actually this is a good thing to prevent out of distribution
push

<img width="986" height="288" alt="Screenshot 2025-12-15 at 15 38 35"
src="https://github.com/user-attachments/assets/78b7a71d-0e43-4828-a118-91c5237909c7"
/>


<img width="509" height="109" alt="Screenshot 2025-12-15 at 17 35 44"
src="https://github.com/user-attachments/assets/6933de52-9b66-4abf-b58b-a5f26d5747e2"
/>
2025-12-17 17:08:03 +00:00
gt-oai 9352c6b235 feat: Constrain values for approval_policy (#7778)
Constrain `approval_policy` through new `admin_policy` config.

This PR will:
1. Add a `admin_policy` section to config, with a single field (for now)
`allowed_approval_policies`. This list constrains the set of
user-settable `approval_policy`s.
2. Introduce a new `Constrained<T>` type, which combines a current value
and a validator function. The validator function ensures disallowed
values are not set.
3. Change the type of `approval_policy` on `Config` and
`SessionConfiguration` from `AskForApproval` to
`Constrained<AskForApproval>`. The validator function is set by the
values passed into `allowed_approval_policies`.
4. `GenericDisplayRow`: add a `disabled_reason: Option<String>`. When
set, it disables selection of the value and indicates as such in the
menu. This also makes it unselectable with arrow keys or numbers. This
is used in the `/approvals` menu.

Follow ups are:
1. Do the same thing to `sandbox_policy`.
2. Propagate the allowed set of values through app-server for the
extension (though already this should prevent app-server from setting
this values, it's just that we want to disable UI elements that are
unsettable).

Happy to split this PR up if you prefer, into the logical numbered areas
above. Especially if there are parts we want to gavel on separately
(e.g. admin_policy).

Disabled full access:
<img width="1680" height="380" alt="image"
src="https://github.com/user-attachments/assets/1fb61c8c-1fcb-4dc4-8355-2293edb52ba0"
/>

Disabled `--yolo` on startup:
<img width="749" height="76" alt="image"
src="https://github.com/user-attachments/assets/0a1211a0-6eb1-40d6-a1d7-439c41e94ddb"
/>

CODEX-4087
2025-12-17 16:19:27 +00:00
xl-openai 4897efcced Add public skills + improve repo skill discovery and error UX (#8098)
1. Adds SkillScope::Public end-to-end (core + protocol) and loads skills
from the public cache directory
2. Improves repo skill discovery by searching upward for the nearest
.codex/skills within a git repo
3. Deduplicates skills by name with deterministic ordering to avoid
duplicates across sources
4. Fixes garbled “Skill errors” overlay rendering by preventing pending
history lines from being injected during the modal
5. Updates the project docs “Skills” intro wording to avoid hardcoded
paths
2025-12-17 01:35:49 -08:00
jif-oai 2041b72da7 chore: dedup review result duplication (#8057) 2025-12-17 09:10:51 +00:00
Eric Traut 42b8f28ee8 Fixed resume matching to respect case insensitivity when using WSL mount points (#8000)
This fixes #7995
2025-12-16 16:27:38 -08:00
jif-oai b53889aed5 Revert "feat: unified exec footer" (#8109)
Reverts openai/codex#8067
2025-12-16 17:03:19 +00:00
jif-oai 021c9a60e5 feat: unified exec footer (#8067)
<img width="452" height="205" alt="Screenshot 2025-12-15 at 17 54 44"
src="https://github.com/user-attachments/assets/9ece0b1c-8387-4dfc-b883-c6a68ea1b663"
/>
2025-12-16 16:52:36 +00:00