## Summary
- Show a temporary Working on diff state in the bottom pan
- Add `DiffResult` app event and dispatch git diff asynchronously
## Testing
- `just fmt`
- `just fix` *(fails: `let` expressions in this position are unstable)*
- `cargo test --all-features` *(fails: `let` expressions in this
position are unstable)*
------
https://chatgpt.com/codex/tasks/task_i_689a839f32b88321840a893551d5fbef
This pull request resolves#2296; I've confirmed if it works by:
1. Add settings to ~/.codex/config.toml:
```toml
model_reasoning_effort = "minimal"
```
2. Run the CLI:
```
cd codex-rs
cargo build && RUST_LOG=trace cargo run --bin codex
/status
tail -f ~/.codex/log/codex-tui.log
```
Co-authored-by: pakrym-oai <pakrym@openai.com>
This adds a new request type, `SendUserTurn`, that makes it possible to
submit a `Op::UserTurn` operation (introduced in #2329) to a
conversation. This PR also adds a new integration test that verifies
that changing from `AskForApproval::UnlessTrusted` to
`AskForApproval::Never` mid-conversation ensures that an elicitation is
no longer sent for running `python3 -c print(42)`.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/2345).
* __->__ #2345
* #2329
* #2343
* #2340
* #2338
This introduces `Op::UserTurn`, which makes it possible to override many
of the fields that were set when the `Session` was originally created
when creating a new conversation turn. This is one way we could support
changing things like `model` or `cwd` in the middle of the conversation,
though we may want to consider making each field optional, or
alternatively having a separate `Op` that mutates the `TurnContext`
associated with a `submission_loop()`.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/2329).
* #2345
* __->__ #2329
* #2343
* #2340
* #2338
This PR introduces `TurnContext`, which is designed to hold a set of
fields that should be constant for a turn of a conversation. Note that
the fields of `TurnContext` were previously governed by `Session`.
Ultimately, we want to enable users to change these values between turns
(changing model, approval policy, etc.), though in the current
implementation, the `TurnContext` is constant for the entire
conversation.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/2345).
* #2345
* #2329
* __->__ #2343
* #2340
* #2338
I still see flakiness in
`test_shell_command_approval_triggers_elicitation()` on occasion where
`MockServer` claims it has not received all of its expected requests.
I recently introduced a similar type of test in #2264,
`test_codex_jsonrpc_conversation_flow()`, which I have not seen flake
(yet!), so this PR pulls over two things I did in that test:
- increased `worker_threads` from `2` to `4`
- added an assertion to make sure the `task_complete` notification is
received
Honestly, I'm still not sure why `MockServer` claims it sometimes does
not receive all its expected requests given that we assert that the
final `JSONRPCResponse` is read on the stream, but let's give this a
shot.
Assuming this fixes things, my hypothesis is that the increase in
`worker_threads` helps because perhaps there are async tasks in
`MockServer` that do not reliably complete fully when there are not
enough threads available? If that is correct, it seems like the test
would still be flaky, though perhaps with lower frequency?
I was looking at the implementation of `Session::get_writable_roots()`,
which did not seem right, as it was a copy of writable roots, which is
not guaranteed to be in sync with the `sandbox_policy` field.
I looked at who was calling `get_writable_roots()` and its only call
site was `apply_patch()` in `codex-rs/core/src/apply_patch.rs`, which
took the roots and forwarded them to `assess_patch_safety()` in
`safety.rs`. I updated `assess_patch_safety()` to take `sandbox_policy:
&SandboxPolicy` instead of `writable_roots: &[PathBuf]` (and replaced
`Session::get_writable_roots()` with `Session::get_sandbox_policy()`).
Within `safety.rs`, it was fairly easy to update
`is_write_patch_constrained_to_writable_paths()` to work with
`SandboxPolicy`, and in particular, it is far more accurate because, for
better or worse, `SandboxPolicy::get_writable_roots_with_cwd()` _returns
an empty vec_ for `SandboxPolicy::DangerFullAccess`, suggesting that
_nothing_ is writable when in reality _everything_ is writable. With
this PR, `is_write_patch_constrained_to_writable_paths()` now does the
right thing for each variant of `SandboxPolicy`.
I thought this would be the end of the story, but it turned out that
`test_writable_roots_constraint()` in `safety.rs` needed to be updated,
as well. In particular, the test was writing to
`std::env::current_dir()` instead of a `TempDir`, which I suspect was a
holdover from earlier when `SandboxPolicy::WorkspaceWrite` would always
make `TMPDIR` writable on macOS, which made it hard to write tests to
verify `SandboxPolicy` in `TMPDIR`. Fortunately, we now have
`exclude_tmpdir_env_var` as an option on
`SandboxPolicy::WorkspaceWrite`, so I was able to update the test to
preserve the existing behavior, but to no longer write to
`std::env::current_dir()`.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/2338).
* #2345
* #2329
* #2343
* #2340
* __->__ #2338
## Summary
We've been seeing a number of issues and reports with our synthetic
`apply_patch` tool, e.g. #802. Let's make this a real tool - in my
anecdotal testing, it's critical for GPT-OSS models, but I'd like to
make it the standard across GPT-5 and codex models as well.
## Testing
- [x] Tested locally
- [x] Integration test
Add env var to show the raw, unparsed command line under parsed
commands. When we have transcript mode we should show the full command
there, but this is useful for debugging.
This PR:
* Added the clippy.toml to configure allowable expect / unwrap usage in
tests
* Removed as many expect/allow lines as possible from tests
* moved a bunch of allows to expects where possible
Note: in integration tests, non `#[test]` helper functions are not
covered by this so we had to leave a few lingering `expect(expect_used`
checks around
It turns out that https://github.com/openai/codex/pull/2324 did not
quite work as intended. Chat's new idea is to have this catch-all "CI
results" job and update our branch protection rules to require this
instead.
When using codex-tui on a linux system I was unable to run `cargo
clippy` inside of codex due to:
```
[pid 3548377] socketpair(AF_UNIX, SOCK_SEQPACKET|SOCK_CLOEXEC, 0, <unfinished ...>
[pid 3548370] close(8 <unfinished ...>
[pid 3548377] <... socketpair resumed>0x7ffb97f4ed60) = -1 EPERM (Operation not permitted)
```
And
```
3611300 <... recvfrom resumed>0x708b8b5cffe0, 8, 0, NULL, NULL) = -1 EPERM (Operation not permitted)
```
This PR:
* Fixes a bug that disallowed AF_UNIX to allow it on `socket()`
* Adds recvfrom() to the syscall allow list, this should be fine since
we disable opening new sockets. But we should validate there is not a
open socket inheritance issue.
* Allow socketpair to be called for AF_UNIX
* Adds tests for AF_UNIX components
* All of which allows running `cargo clippy` within the sandbox on
linux, and possibly other tooling using a fork server model + AF_UNIX
comms.
we have a very unclear lifecycle for the chatwidget—this should only
have to be added in one place! but this fixes the "hanging commands"
issue where the active_exec_cell wasn't correctly cleared when commands
finished.
To repro w/o this PR:
1. prompt "run sleep 10"
2. once the command starts running, press <kbd>Esc</kbd>
3. prompt "run echo hi"
Expected:
```
✓ Completed
└ ⌨️ echo hi
codex
hi
```
Actual:
```
⚙︎ Working
└ ⌨️ echo hi
▌ Ask Codex to do anything
```
i.e. the "Working" never changes to "Completed".
The bug is fixed with this PR.
Our existing path filters for `rust-ci.yml`:
235987843c/.github/workflows/rust-ci.yml (L1-L11)
made it so that PRs that touch only `README.md` would not trigger those
builds, which is a problem because our branch protection rules are set
as follows:
<img width="1569" height="1883" alt="Screenshot 2025-08-14 at 4 45
59 PM"
src="https://github.com/user-attachments/assets/5a61f8cc-cdaf-4341-abda-7faa7b46dbd4"
/>
With the existing setup, a change to `README.md` would get stuck in
limbo because not all the CI jobs required to merge would get run. It
turns out that we need to "run" all the jobs, but make them no-ops when
the `codex-rs` and `.github` folders are untouched to get the best of
both worlds.
I asked chat how to fix this, as we want CI to be fast for
documentation-only changes. It had two suggestions:
- Use https://github.com/dorny/paths-filter or some other third-party
action.
- Write an inline Bash script to avoid a third-party dependency.
This PR takes the latter approach so that we are clear about what we're
running in CI.
The high-order bit on this PR is that it makes it so `sandbox.rs` tests
both Mac and Linux, as we introduce a general
`spawn_command_under_sandbox()` function with platform-specific
implementations for testing.
An important, and interesting, discovery in porting the test to Linux is
that (for reasons cited in the code comments), `/dev/shm` has to be
added to `writable_roots` on Linux in order for `multiprocessing.Lock`
to work there. Granting write access to `/dev/shm` comes with some
degree of risk, so we do not make this the default for Codex CLI.
Piggybacking on top of #2317, this moves the
`python_multiprocessing_lock_works` test yet again, moving
`codex-rs/core/tests/sandbox.rs` to `codex-rs/exec/tests/sandbox.rs`
because in `codex-rs/exec/tests` we can use `cargo_bin()` like so:
```
let codex_linux_sandbox_exe = assert_cmd::cargo::cargo_bin("codex-exec");
```
which is necessary so we can use `codex_linux_sandbox_exe` and therefore
`spawn_command_under_linux_sandbox` in an integration test.
This also moves `spawn_command_under_linux_sandbox()` out of `exec.rs`
and into `landlock.rs`, which makes things more consistent with
`seatbelt.rs` in `codex-core`.
For reference, https://github.com/openai/codex/pull/1808 is the PR that
made the change to Seatbelt to get this test to pass on Mac.
Previous to this PR, `codex-rs/core/tests/sandbox.rs` contained
integration tests that were specific to Seatbelt. This PR moves those
tests to `codex-rs/core/src/seatbelt.rs` and designates
`codex-rs/core/tests/sandbox.rs` to be used as the home for
cross-platform (well, Mac and Linux...) sandbox tests.
To start, this migrates
`python_multiprocessing_lock_works_under_seatbelt()` from #1823 to the
new `sandbox.rs` because this is the type of thing that should work on
both Mac _and_ Linux, though I still need to do some work to clean up
the test so it works on both platforms.
## Summary
- add a unit test to ensure the macOS seatbelt policy allows POSIX
semaphores
- add a macOS-only test that runs a Python multiprocessing Lock under
Seatbelt
## Testing
- `cargo test -p codex_core seatbelt_base_policy_allows_ipc_posix_sem
--no-fail-fast` (failed: failed to download from
`https://static.crates.io/crates/tokio-stream/0.1.17/download`)
- `cargo test -p codex_core seatbelt_base_policy_allows_ipc_posix_sem
--no-fail-fast --offline` (failed: attempting to make an HTTP request,
but --offline was specified)
- `cargo test --all-features --no-fail-fast --offline` (failed:
attempting to make an HTTP request, but --offline was specified)
- `just fmt` (failed: command not found: just)
- `just fix` (failed: command not found: just)
Ran tests locally to confirm it passes on master and failed before my
previous change
------
https://chatgpt.com/codex/tasks/task_i_6890f221e0a4833381cfb53e11499bcc
The "display format" of commands was sometimes producing incorrect
quoting like `echo foo '>' bar`, which is importantly different from the
actual command that was being run. This refactors ParsedCommand to have
a string in `cmd` instead of a vec, as a `vec` can't accurately capture
a full command.
instead of each shimmer needing to have its own animation thread, have
render_ref schedule a new frame if it wants one and coalesce to the
earliest next frame. this also makes the animations
frame-timing-independent, based on start time instead of frame count.
This improves handling of pasted content in the textarea. It's no longer
possible to partially delete a placeholder (e.g. by ^W or ^D), nor is it
possible to place the cursor inside a placeholder. Also, we now render
placeholders in a different color to make them more clearly
differentiated.
https://github.com/user-attachments/assets/2051b3c3-963d-4781-a610-3afee522ae29
#2291 made it so that `Session::new()` is on the critical path to
`Codex::spawn()`, which means it is on the hot path to CLI startup. This
refactors `Session::new()` to run a number of async tasks in parallel
that were previously run serially to try to reduce latency.
## Summary
Currently, we use request-time logic to determine the user_instructions
and environment_context messages. This means that neither of these
values can change over time as conversations go on. We want to add in
additional details here, so we're migrating these to save these messages
to the rollout file instead. This is simpler for the client, and allows
us to append additional environment_context messages to each turn if we
want
## Testing
- [x] Integration test coverage
- [x] Tested locally with a few turns, confirmed model could reference
environment context and cached token metrics were reasonably high
refactors HistoryCell to be a trait instead of an enum. Also collapse
the many "degenerate" HistoryCell enums which were just a store of lines
into a single PlainHistoryCell type.
The goal here is to allow more ways of rendering history cells (e.g.
expanded/collapsed/"live"), and I expect we will return to more varied
types of HistoryCell as we develop this area.
Historically, `Codex::spawn()` would create the instance of `Codex` and
enforce, by construction, that `Op::ConfigureSession` was the first `Op`
submitted via `submit()`. Then over in `submission_loop()`, it would
handle the case for taking the parameters of `Op::ConfigureSession` and
turning it into a `Session`.
This approach has two challenges from a state management perspective:
f968a1327a/codex-rs/core/src/codex.rs (L718)
- The local `sess` variable in `submission_loop()` has to be `mut` and
`Option<Arc<Session>>` because it is not invariant that a `Session` is
present for the lifetime of the loop, so there is a lot of logic to deal
with the case where `sess` is `None` (e.g., the `send_no_session_event`
function and all of its callsites).
- `submission_loop()` is written in such a way that
`Op::ConfigureSession` could be observed multiple times, but in
practice, it is only observed exactly once at the start of the loop.
In this PR, we try to simplify the state management by _removing_ the
`Op::ConfigureSession` enum variant and constructing the `Session` as
part of `Codex::spawn()` so that it can be passed to `submission_loop()`
as `Arc<Session>`. The original logic from the `Op::ConfigureSession`
has largely been moved to the new `Session::new()` constructor.
---
Incidentally, I also noticed that the handling of `Op::ConfigureSession`
can result in events being dispatched in addition to
`EventMsg::SessionConfigured`, as an `EventMsg::Error` is created for
every MCP initialization error, so it is important to preserve that
behavior:
f968a1327a/codex-rs/core/src/codex.rs (L901-L916)
Though admittedly, I believe this does not play nice with #2264, as
these error messages will likely be dispatched before the client has a
chance to call `addConversationListener`, so we likely need to make it
so `newConversation` automatically creates the subscription, but we must
also guarantee that the "ack" from `newConversation` is returned before
any other conversation-related notifications are sent so the client
knows what `conversation_id` to match on.
As `Session` needs a bit of work, it will make things easier to move
around if we can start by reducing the extent of its public API. This
makes all the fields private, though adds three `pub(crate)` getters.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/2285).
* #2287
* #2286
* __->__ #2285
Sometimes COT is returns as text content instead of `ReasoningText`. We
should parse it but not serialize back on requests.
---------
Co-authored-by: Ahmed Ibrahim <aibrahim@openai.com>
