## Notes
Skills are behind the experimental `skills` feature flag (disabled by
default), but the skills guide didn't explain how to turn them on.
- Add an explicit enable section to `docs/skills.md` (config +
`--enable`)
- Add the skills flag to `docs/config.md` and `docs/example-config.md`
- Document the `/skills` slash command
refactor the way we load and manage skills:
1. Move skill discovery/caching into SkillsManager and reuse it across
sessions.
2. Add the skills/list API (Op::ListSkills/SkillsListResponse) to fetch
skills for one or more cwds. Also update app-server for VSCE/App;
3. Trigger skills/list during session startup so UIs preload skills and
handle errors immediately.
The existing version of `shell-tool-mcp/README.md` was not written in a
way that was meant to be consumed by end-users. This is now fixed.
Added `codex-rs/exec-server/README.md` for the more technical bits.
Codex identified this as the cause of a reported hang:
https://github.com/openai/codex/issues/7822. Apparently, the wrapping
algorithm we're using has known issues and bad worst-case behaviors when
OptimalFit is used on certain strings. It recommended switching to
FirstFit instead.
Drop the AGENTS.md rule that forbids unsigned ints. The blanket guidance
causes unnecessary complexity in cases where values are naturally
unsigned, leading to extra clamping/conversion code instead of using
checked or saturating arithmetic where needed.
Changes the `writable_roots` field of the `WorkspaceWrite` variant of
the `SandboxPolicy` enum from `Vec<PathBuf>` to `Vec<AbsolutePathBuf>`.
This is helpful because now callers can be sure the value is an absolute
path rather than a relative one. (Though when using an absolute path in
a Seatbelt config policy, we still have to _canonicalize_ it first.)
Because `writable_roots` can be read from a config file, it is important
that we are able to resolve relative paths properly using the parent
folder of the config file as the base path.
## Problem
The introduction of `notify_sandbox_state_change()` in #7112 caused a
regression where the blocking call in `Session::new()` waits for all MCP
servers to fully initialize before returning. This prevents the TUI
event loop from starting, resulting in `McpStartupUpdateEvent` messages
being emitted but never consumed or displayed. As a result, the app
appears to hang during startup, and users do not see the expected
"Booting MCP server: {name}" status line.
Issue: [#7827](https://github.com/openai/codex/issues/7827)
## Solution
This change moves sandbox state notification into each MCP server's
background initialization task. The notification is sent immediately
after the server transitions to the Ready state. This approach:
- Avoids blocking `Session::new()`, allowing the TUI event loop to start
promptly.
- Ensures each MCP server receives its sandbox state before handling any
tool calls.
- Restores the display of "Booting MCP server" status lines during
startup.
## Key Changes
- Added `ManagedClient::notify_sandbox_state()` method.
- Passed sandbox_state to `McpConnectionManager::initialize()`.
- Sends sandbox state notification in the background task after the
server reaches Ready status.
- Removed blocking notify_sandbox_state_change() methods.
- Added a chatwidget snapshot test for the "Booting MCP server" status
line.
## Regression Details
Regression was bisected to #7112, which introduced the blocking
behavior.
---------
Co-authored-by: Michael Bolin <[email protected]>
Co-authored-by: Michael Bolin <[email protected]>
# 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.
The elevated sandbox ships two exes
* one for elevated setup of the sandbox
* one to actually run commands under the sandbox user.
This PR adds them to the windows signing step
Previous to this PR, we used a hand-rolled PowerShell parser in
`windows_safe_commands.rs` to take a `&str` of PowerShell script see if
it is equivalent to a list of `execvp(3)` invocations, and if so, we
then test each using `is_safe_powershell_command()` to determine if the
overall command is safe:
https://github.com/openai/codex/blob/5c12b6c0717d63b83ea3aba3685e2496c28e7f7b/codex-rs/core/src/command_safety/windows_safe_commands.rs#L89-L98
Unfortunately, our PowerShell parser did not recognize `@(...)` as a
special construct, so it was treated as an ordinary token. This meant
that the following would erroneously be considered "safe:"
```powershell
ls @(calc.exe)
```
The fix introduced in this PR is to do something comparable what we do
for Bash/Zsh, which is to use a "proper" parser to derive the list of
`execvp(3)` calls. For Bash/Zsh, we rely on
https://crates.io/crates/tree-sitter-bash, but there does not appear to
be a crate of comparable quality for parsing PowerShell statically
(https://github.com/airbus-cert/tree-sitter-powershell/ is the best
thing I found).
Instead, in this PR, we use a PowerShell script to parse the input
PowerShell program to produce the AST.
This PR changes the length validation for SKILL.md `name` and
`description` fields so they use character counts rather than byte
counts. Aligned character limits to other harnesses.
This addresses #7730.
I am trying to tighten up some of our logic around PowerShell over in
https://github.com/openai/codex/pull/7607 and it would be helpful to be
more precise about `pwsh.exe` versus `powershell.exe`, as they do not
accept the exact same input language.
To that end, this PR introduces utilities for detecting each on the
system. I think we also want to update `get_user_shell_path()` to return
PowerShell instead of `None` on Windows, but we'll consider that in a
separate PR since it may require more testing.
## Changes
- Update config docs and example config comments to state that "xhigh"
is supported on gpt-5.2 as well as gpt-5.1-codex-max
- Adjust the FAQ model-support section to reflect broader xhigh
availability
# 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.
We decided that `*.rules` is a more fitting (and concise) file extension
than `*.codexpolicy`, so we are changing the file extension for the
"execpolicy" effort. We are also changing the subfolder of `$CODEX_HOME`
from `policy` to `rules` to match.
This PR updates the in-repo docs and we will update the public docs once
the next CLI release goes out.
Locally, I created `~/.codex/rules/default.rules` with the following
contents:
```
prefix_rule(pattern=["gh", "pr", "view"])
```
And then I asked Codex to run:
```
gh pr view 7888 --json title,body,comments
```
and it was able to!
## Summary
- update CLI OAuth guidance to reference `features.rmcp_client` instead
of the deprecated experimental flag
- keep login/logout help text consistent with the new feature flag
## Testing
- `cargo test -p codex-cli`
------
[Codex
Task](https://chatgpt.com/codex/tasks/task_i_693b3e0bf27c832cb66d585847a552ab)
### What
Don't treat `q` as a special quit character on the API key paste page in
the onboarding flow.
This addresses #7413, where pasting API keys with `q` would cause codex
to quit on Windows.
### Test Plan
Tested on Windows and MacOS.
