## Summary
Based on our most recent [release
attempt](https://github.com/openai/codex/actions/runs/21980518940/job/63501739210)
we are not building the shell-tool-mcp job correctly. This one is
outside my expertise, but seems mostly reasonable.
## Testing
- [x] We really need dry runs of these
## Summary
CI is broken on main because our CI toolchain is trying to run 1.93.1
while our rust toolchain is locked at 1.93.0. I'm sure it's likely safe
to upgrade, but let's keep things stable for now.
## Testing
- [x] CI should hopefully pass
## Summary
If the model suggests a bad rule, don't show it to the user. This does
not impact the parsing of existing rules, just the ones we show.
## Testing
- [x] Added unit tests
- [x] Ran locally
## Summary
In an effort to start simplifying our sandbox setup, we're announcing
this approval_policy as deprecated. In general, it performs worse than
`on-request`, and we're focusing on making fewer sandbox configurations
perform much better.
## Testing
- [x] Tested locally
- [x] Existing tests pass
## Summary
Preserve the specified model slug when we get a prefix-based match
## Testing
- [x] added unit test
---------
Co-authored-by: Ahmed Ibrahim <aibrahim@openai.com>
## Summary
Consolidate `/status` Permissions lines into a simpler view. It should
only show "Default," "Full Access," or "Custom" (with specifics)
## Testing
- [x] many snapshots updated
## Summary
This should rarely, if ever, happen in practice. But regardless, we
should never provide an empty list of `commands` to ExecPolicy. This PR
is almost entirely adding test around these cases.
## Testing
- [x] Adds a bunch of unit tests for this
## Summary
- keep wiremock MockServer handles alive through async assertions in
remote model suite tests
- assert /models request count in remote_models_hide_picker_only_models
- use a slightly higher parallel timing threshold on aarch64 while
keeping existing x86 threshold
## Validation
- just fmt
- targeted tests:
- cargo test -p codex-core --test all
suite::remote_models::remote_models_merge_replaces_overlapping_model --
--exact
- cargo test -p codex-core --test all
suite::remote_models::remote_models_hide_picker_only_models -- --exact
- cargo test -p codex-core --test all
suite::tool_parallelism::shell_tools_run_in_parallel -- --exact
- soak loop: 40 iterations of all three targeted tests
## Notes
- cargo test -p codex-core has one unrelated local-env failure in
shell_snapshot::tests::try_new_creates_and_deletes_snapshot_file from
exported certificate env content in this workspace.
- local bazel test //codex-rs/core:core-all-test failed to build due
missing rust-objcopy in this host toolchain.
Summary
- add platform-aware defaults for shell command timeouts so Windows
tests get longer waits
- keep medium timeout longer on Windows to ensure flakiness is reduced
Testing
- Not run (not requested)
## Summary
When resuming with a different model, we should also append a developer
message with the model instructions
## Testing
- [x] Added unit tests
## Summary
When switching models, we should append the instructions of the new
model to the conversation as a developer message.
## Test
- [x] Adds a unit test
## Summary
We ideally shouldn't make it to this point in the first place, but if we
do try to append a rule that already exists, we shouldn't append the
same rule twice.
## Testing
- [x] Added unit test for this case
## Summary
We should probably warn users that they have a million rules, and help
clean them up. But for now, we should handle this unbounded case.
Limit rules listed in conversations, with shortest / broadest rules
first.
## Testing
- [x] Updated unit tests
## Summary
Let's dial in this api contract in a bit more with more robust fallback
behavior when model_instructions_template is false.
Switches to a more explicit template / variables structure, with more
fallbacks.
## Testing
- [x] Adding unit tests
- [x] Tested locally
## Summary
Add personality instructions so we can let users try it out, in tandem
with making it an experimental feature
## Testing
- [x] Tested locally
## Summary
Sets up an explicit Feature flag for `/personality`, so users can now
opt in to it via `/experimental`. #10114 also updates the config
## Testing
- [x] Tested locally
## Summary
Move `model_instructions_template` config to the experimental slug while
we iterate on this feature
## Testing
- [x] Tested locally, unit tests still pass
## Summary
Adds /personality selector in the TUI, which leverages the new core
interface in #9644
Notes:
- We are doing some of our own state management for model_info loading
here, but not sure if that's ideal. open to opinions on simpler
approach, but would like to avoid blocking on a larger refactor
- Right now, the `/personality` selector just hides when the model
doesn't support it. we can update this behavior down the line
## Testing
- [x] Tested locally
- [x] Added snapshot tests
### Motivation
Exposes a per-thread / per-turn `personality` override in the v2
app-server API so clients can influence model communication style at
thread/turn start. Ensures the override is passed into the session
configuration resolution so it becomes effective for subsequent turns
and headless runners.
### Testing
- [x] Add an integration-style test
`turn_start_accepts_personality_override_v2` in
`codex-rs/app-server/tests/suite/v2/turn_start.rs` that verifies a
`/personality` override results in a developer update message containing
`<personality_spec>` in the outbound model request.
------
[Codex
Task](https://chatgpt.com/codex/tasks/task_i_6971d646b1c08322a689a54d2649f3fe)
## Summary
Support updating Personality mid-Thread via UserTurn/OverwriteTurn. This
is explicitly unused by the clients so far, to simplify PRs - app-server
and tui implementations will be follow-ups.
## Testing
- [x] added integration tests
## Summary
Adds the `/permissions` command, with a (usually) shorter set of
permissions. `/approvals` still exists, for backwards compatibility.
<img width="863" height="309" alt="Screenshot 2026-01-20 at 4 12 51 PM"
src="https://github.com/user-attachments/assets/c49b5ba5-bc47-46dd-9067-e1a5670328fe"
/>
## Testing
- [x] updated unit tests
- [x] Tested locally
## Summary
#9555 is the start of a rename, so I'm starting to standardize here.
Sets up `model_instructions` templating with a strongly-typed object for
injecting a personality block into the model instructions.
## Testing
- [x] Added tests
- [x] Ran locally
## Summary
When we send multiple assistant messages, reset the timer so "Worked for
2m 36s" is the time since the last time we showed the message, rather
than an ever-increasing number.
We could instead change the copy so it's more clearly a running counter.
## Testing
- [x] ran locally
<img width="903" height="732" alt="Screenshot 2026-01-21 at 1 42 51 AM"
src="https://github.com/user-attachments/assets/bb4d827b-3a0e-48ba-bd6a-d8cd65d8e892"
/>
## Summary
Introduces the concept of a config model_personality. I would consider
this an MVP for testing out the feature. There are a number of
follow-ups to this PR:
- More sophisticated templating with validation
- In-product experience to manage this
## Testing
- [x] Testing locally
## Summary
This PR consolidates base_instructions onto SessionMeta /
SessionConfiguration, so we ensure `base_instructions` is set once per
session and should be (mostly) immutable, unless:
- overridden by config on resume / fork
- sub-agent tasks, like review or collab
In a future PR, we should convert all references to `base_instructions`
to consistently used the typed struct, so it's less likely that we put
other strings there. See #9423. However, this PR is already quite
complex, so I'm deferring that to a follow-up.
## Testing
- [x] Added a resume test to assert that instructions are preserved. In
particular, `resume_switches_models_preserves_base_instructions` fails
against main.
Existing test coverage thats assert base instructions are preserved
across multiple requests in a session:
- Manual compact keeps baseline instructions:
core/tests/suite/compact.rs:199
- Auto-compact keeps baseline instructions:
core/tests/suite/compact.rs:1142
- Prompt caching reuses the same instructions across two requests:
core/tests/suite/prompt_caching.rs:150 and
core/tests/suite/prompt_caching.rs:157
- Prompt caching with explicit expected string across two requests:
core/tests/suite/prompt_caching.rs:213 and
core/tests/suite/prompt_caching.rs:222
- Resume with model switch keeps original instructions:
core/tests/suite/resume.rs:136
- Compact/resume/fork uses request 0 instructions for later expected
payloads: core/tests/suite/compact_resume_fork.rs:215
### Description
- Remove the now-unused `instructions` field from the session metadata
to simplify SessionMeta and stop propagating transient instruction text
through the rollout recorder API. This was only saving
user_instructions, and was never being read.
- Stop passing user instructions into the rollout writer at session
creation so the rollout header only contains canonical session metadata.
### Testing
- Ran `just fmt` which completed successfully.
- Ran `just fix -p codex-protocol`, `just fix -p codex-core`, `just fix
-p codex-app-server`, `just fix -p codex-tui`, and `just fix -p
codex-tui2` which completed (Clippy fixes applied) as part of
verification.
- Ran `cargo test -p codex-protocol` which passed (28 tests).
- Ran `cargo test -p codex-core` which showed failures in a small set of
tests (not caused by the protocol type change directly):
`default_client::tests::test_create_client_sets_default_headers`,
several `models_manager::manager::tests::refresh_available_models_*`,
and `shell_snapshot::tests::linux_sh_snapshot_includes_sections` (these
tests failed in this CI run).
- Ran `cargo test -p codex-app-server` which reported several failing
integration tests (including
`suite::codex_message_processor_flow::test_codex_jsonrpc_conversation_flow`,
`suite::output_schema::send_user_turn_*`, and
`suite::user_agent::get_user_agent_returns_current_codex_user_agent`).
- `cargo test -p codex-tui` and `cargo test -p codex-tui2` were
attempted but aborted due to disk space exhaustion (`No space left on
device`).
------
[Codex
Task](https://chatgpt.com/codex/tasks/task_i_696bd8ce632483228d298cf07c7eb41c)
## Summary
We have a variety of things we refer to as instructions in the code
base: our current canonical terms are:
- base instructions (raw string)
- developer instructions (has a type in protocol)
- user instructions
We also have `instructions` floating around in various places. We should
standardize on the above, and start using types to prevent them from
ending up in the wrong place. There will be additional PRs, but I'm
going to keep these small so we can easily follow them!
## Testing
- [x] Tests pass, this is purely a file move
## Summary
Bumps the windows setup version, to re-trigger windows sandbox setup for
users in the experimental sandbox. We've seen some drift in the ACL
controls, amongst a few other changes. Hopefully this should fix#9062.
## Testing
- [x] Tested locally
## Summary
This PR builds _heavily_ on the work from @occurrent in #8021 - I've
only added a small fix, added additional tests, and propagated the
changes to tui2.
From the original PR:
> On Windows, Codex relies on PasteBurst for paste detection because
bracketed paste is not reliably available via crossterm.
>
> When pasted content starts with non-ASCII characters, input is routed
through handle_non_ascii_char, which bypasses the normal paste burst
logic. This change extends the paste burst window for that path, which
should ensure that Enter is correctly grouped as part of the paste.
## Testing
- [x] tested locally cross-platform
- [x] added regression tests
---------
Co-authored-by: occur <occurring@outlook.com>
## Summary
Adds a FeatureFlag to enforce UTF8 encoding in powershell, particularly
Windows Powershell v5. This should help address issues like #7290.
Notably, this PR does not include the ability to parse `apply_patch`
invocations within UTF8 shell commands (calls to the freeform tool
should not be impacted). I am leaving this out of scope for now. We
should address before this feature becomes Stable, but those cases are
not the default behavior at this time so we're okay for experimentation
phase. We should continue cleaning up the `apply_patch::invocation`
logic and then can handle it more cleanly.
## Testing
- [x] Adds additional testing
## Summary
Adds a unicode scenario, and fills in files on failing scenarios to
ensure directory state is unchanged, for completeness
## Testing
- [x] only changes tests
## Summary:
This PR is a pure copy and paste of tests from lib.rs into
invocation.rs, to colocate logic and tests.
## Testing
- [x] Purely a test refactor
lib.rs has grown quite large, and mixes two responsibilities:
1. executing patch operations
2. parsing apply_patch invocations via a shell command
This PR splits out (2) into its own file, so we can work with it more
easily. We are explicitly NOT moving tests in this PR, to ensure
behavior stays the same and we can avoid losing coverage via merge
conflicts. Tests are moved in a subsequent PR.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/8110).
* #8111
* __->__ #8110
## Summary
This PR is heavily based on #4017, which contains the core logic for the
fix. To reduce the risk, we are first introducing it only on windows. We
can then expand to wsl / other environments as needed, and then tackle
net new files.
## Testing
- [x] added unit tests in apply-patch
- [x] add integration tests to apply_patch_cli.rs
---------
Co-authored-by: Chase Naples <Cnaples79@gmail.com>
## Summary
This PR introduces an End to End test suite for apply-patch, so we can
easily validate behavior against other implementations as well.
## Testing
- [x] These are tests
Closes#3404
## Summary
On windows, ctrl+v does not work for the same reason that cmd+v does not
work on macos. This PR adds alt/option+v detection, which allows windows
users to paste images from the clipboard using.
We could swap between just ctrl on mac and just alt on windows, but this
felt simpler - I don't feel strongly about it.
Note that this will NOT address image pasting in WSL environments, due
to issues with WSL <> Windows clipboards. I'm planning to address that
in a separate PR since it will likely warrant some discussion.
## Testing
- [x] Tested locally on a Mac and Windows laptop
## Summary
When incrementing the minor version, we should reset patch to 0, rather
than keeping it.
## Testing
- [x] tested locally with dry_run and `get_latest_release_version`
mocked out
---------
Co-authored-by: Michael Bolin <mbolin@openai.com>
### Summary
After #7022, we no longer need this warning. We should also clean up the
schema for the notification, but this is a quick fix to just stop the
behavior in the VSCE
## Testing
- [x] Ran locally
## Summary
Setting `/approvals` before the start of a conversation was not updating
the environment_context for a conversation. Not sure exactly when this
problem was introduced, but this should reduce model confusion
dramatically.
## Testing
- [x] Added unit test to reproduce bug, confirmed fix with update
- [x] Tested locally
## Summary
Enables shell_command for windows users, and starts adding some basic
command parsing here, to at least remove powershell prefixes. We'll
follow this up with command parsing but I wanted to land this change
separately with some basic UX.
**NOTE**: This implementation parses bash and powershell on both
platforms. In theory this is possible, since you can use git bash on
windows or powershell on linux. In practice, this may not be worth the
complexity of supporting, so I don't feel strongly about the current
approach vs. platform-specific branching.
## Testing
- [x] Added a bunch of tests
- [x] Ran on both windows and os x
## Summary
Similar to #6545, this PR updates the shell_serialization test suite to
cover the various `shell` tool invocations we have. Note that this does
not cover unified_exec, which has its own suite of tests. This should
provide some test coverage for when we eventually consolidate
serialization logic.
## Testing
- [x] These are tests
## Summary
Consolidates our apply_patch tests into one suite, and ensures each test
case tests the various ways the harness supports apply_patch:
1. Freeform custom tool call
2. JSON function tool
3. Simple shell call
4. Heredoc shell call
There are a few test cases that are specific to a particular variant,
I've left those alone.
## Testing
- [x] This adds a significant number of tests
## Summary
musl 1.2.5 includes [several fixes to DNS over
TCP](https://www.openwall.com/lists/musl/2024/03/01/2), which appears to
be the root cause of #6116.
This approach is a bit janky, but according to codex:
> On the Ubuntu 24.04 runners we use, apt-cache policy musl-tools shows
only the distro build (1.2.4-2ubuntu2)"
We should build with this version and confirm.
## Testing
- [ ] TODO: test and see if this fixes Azure issues
## Summary
Can never have enough tests on this code path - checking that json
inside a shell call is deserialized correctly.
## Tests
- [x] These are tests 😎
## Summary
Duplicates the tests in `apply_patch_cli.rs`, but tests the freeform
apply_patch tool as opposed to the function call path. The good news is
that all the tests pass with zero logical tests, with the exception of
the heredoc, which doesn't really make sense in the freeform tool
context anyway.
@jif-oai since you wrote the original tests in #5557, I'd love your
opinion on the right way to DRY these test cases between the two. Happy
to set up a more sophisticated harness, but didn't want to go down the
rabbit hole until we agreed on the right pattern
## Testing
- [x] These are tests
Dylan HurdandGitHub
