This PR adds a central `AuthManager` struct that manages the auth
information used across conversations and the MCP server. Prior to this,
each conversation and the MCP server got their own private snapshots of
the auth information, and changes to one (such as a logout or token
refresh) were not seen by others.
This is especially problematic when multiple instances of the CLI are
run. For example, consider the case where you start CLI 1 and log in to
ChatGPT account X and then start CLI 2 and log out and then log in to
ChatGPT account Y. The conversation in CLI 1 is still using account X,
but if you create a new conversation, it will suddenly (and
unexpectedly) switch to account Y.
With the `AuthManager`, auth information is read from disk at the time
the `ConversationManager` is constructed, and it is cached in memory.
All new conversations use this same auth information, as do any token
refreshes.
The `AuthManager` is also used by the MCP server's GetAuthStatus
command, which now returns the auth method currently used by the MCP
server.
This PR also includes an enhancement to the GetAuthStatus command. It
now accepts two new (optional) input parameters: `include_token` and
`refresh_token`. Callers can use this to request the in-use auth token
and can optionally request to refresh the token.
The PR also adds tests for the login and auth APIs that I recently added
to the MCP server.
## Summary
Before we land #2243, let's start printing environment_context in our
preferred format. This struct will evolve over time with new
information, xml gives us a balance of human readable without too much
parsing, llm readable, and extensible.
Also moves us over to an Option-based struct, so we can easily provide
diffs to the model.
## Testing
- [x] Updated tests to reflect new format
## What? Why? How?
- When running on Windows, codex often tries to invoke bash commands,
which commonly fail (unless WSL is installed)
- Fix: Detect if powershell is available and, if so, route commands to
it
- Also add a shell_name property to environmental context for codex to
default to powershell commands when running in that environment
## Testing
- Tested within WSL and powershell (e.g. get top 5 largest files within
a folder and validated that commands generated were powershell commands)
- Tested within Zsh
- Updated unit tests
---------
Co-authored-by: Eddy Escardo <eddy@openai.com>
Codex created this PR from the following prompt:
> upgrade this entire repo to Rust 1.89. Note that this requires
updating codex-rs/rust-toolchain.toml as well as the workflows in
.github/. Make sure that things are "clippy clean" as this change will
likely uncover new Clippy errors. `just fmt` and `cargo clippy --tests`
are sufficient to check for correctness
Note this modifies a lot of lines because it folds nested `if`
statements using `&&`.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/2465).
* #2467
* __->__ #2465
## Summary
Adds a `/mcp` command to list active tools. We can extend this command
to allow configuration of MCP tools, but for now a simple list command
will help debug if your config.toml and your tools are working as
expected.
Introduces `EventMsg::TurnAborted` that should be sent in response to
`Op::Interrupt`.
In the MCP server, updates the handling of a
`ClientRequest::InterruptConversation` request such that it sends the
`Op::Interrupt` but does not respond to the request until it sees an
`EventMsg::TurnAborted`.
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 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
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
#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
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>
This PR does two things because after I got deep into the first one I
started pulling on the thread to the second:
- Makes `ConversationManager` the place where all in-memory
conversations are created and stored. Previously, `MessageProcessor` in
the `codex-mcp-server` crate was doing this via its `session_map`, but
this is something that should be done in `codex-core`.
- It unwinds the `ctrl_c: tokio::sync::Notify` that was threaded
throughout our code. I think this made sense at one time, but now that
we handle Ctrl-C within the TUI and have a proper `Op::Interrupt` event,
I don't think this was quite right, so I removed it. For `codex exec`
and `codex proto`, we now use `tokio::signal::ctrl_c()` directly, but we
no longer make `Notify` a field of `Codex` or `CodexConversation`.
Changes of note:
- Adds the files `conversation_manager.rs` and `codex_conversation.rs`
to `codex-core`.
- `Codex` and `CodexSpawnOk` are no longer exported from `codex-core`:
other crates must use `CodexConversation` instead (which is created via
`ConversationManager`).
- `core/src/codex_wrapper.rs` has been deleted in favor of
`ConversationManager`.
- `ConversationManager::new_conversation()` returns `NewConversation`,
which is in line with the `new_conversation` tool we want to add to the
MCP server. Note `NewConversation` includes `SessionConfiguredEvent`, so
we eliminate checks in cases like `codex-rs/core/tests/client.rs` to
verify `SessionConfiguredEvent` is the first event because that is now
internal to `ConversationManager`.
- Quite a bit of code was deleted from
`codex-rs/mcp-server/src/message_processor.rs` since it no longer has to
manage multiple conversations itself: it goes through
`ConversationManager` instead.
- `core/tests/live_agent.rs` has been deleted because I had to update a
bunch of tests and all the tests in here were ignored, and I don't think
anyone ever ran them, so this was just technical debt, at this point.
- Removed `notify_on_sigint()` from `util.rs` (and in a follow-up, I
hope to refactor the blandly-named `util.rs` into more descriptive
files).
- In general, I started replacing local variables named `codex` as
`conversation`, where appropriate, though admittedly I didn't do it
through all the integration tests because that would have added a lot of
noise to this PR.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/2240).
* #2264
* #2263
* __->__ #2240
Wait for newlines, then render markdown on a line by line basis. Word wrap it for the current terminal size and then spit it out line by line into the UI. Also adds tests and fixes some UI regressions.
# Note for reviewers
The bulk of this PR is in in the new file, `parse_command.rs`. This file
is designed to be written TDD and implemented with Codex. Do not worry
about reviewing the code, just review the unit tests (if you want). If
any cases are missing, we'll add more tests and have Codex fix them.
I think the best approach will be to land and iterate. I have some
follow-ups I want to do after this lands. The next PR after this will
let us merge (and dedupe) multiple sequential cells of the same such as
multiple read commands. The deduping will also be important because the
model often reads the same file multiple times in a row in chunks
===
This PR formats common commands like reading, formatting, testing, etc
more nicely:
It tries to extract things like file names, tests and falls back to the
cmd if it doesn't. It also only shows stdout/err if the command failed.
<img width="770" height="238" alt="CleanShot 2025-08-09 at 16 05 15"
src="https://github.com/user-attachments/assets/0ead179a-8910-486b-aa3d-7d26264d751e"
/>
<img width="348" height="158" alt="CleanShot 2025-08-09 at 16 05 32"
src="https://github.com/user-attachments/assets/4302681b-5e87-4ff3-85b4-0252c6c485a9"
/>
<img width="834" height="324" alt="CleanShot 2025-08-09 at 16 05 56 2"
src="https://github.com/user-attachments/assets/09fb3517-7bd6-40f6-a126-4172106b700f"
/>
Part 2: https://github.com/openai/codex/pull/2097
Part 3: https://github.com/openai/codex/pull/2110
## Summary
Allow tui conversations to resume after the client fails out of retries.
I tested this with exec / mocked api failures as well, and it appears to
be fine. But happy to add an exec integration test as well!
## Testing
- [x] Added integration test
- [x] Tested locally
## Summary
Forgot to remove this in #1869 last night! Too much of a performance hit
on the main thread. We can bring it back via an async thread on startup.
## Summary
Includes a new user message in the api payload which provides useful
environment context for the model, so it knows about things like the
current working directory and the sandbox.
## Testing
Updated unit tests
## Summary
A split-up PR of #1763 , stacked on top of a tools refactor #1858 to
make the change clearer. From the previous summary:
> Let's try something new: tell the model about the sandbox, and let it
decide when it will need to break the sandbox. Some local testing
suggests that it works pretty well with zero iteration on the prompt!
## Testing
- [x] Added unit tests
- [x] Tested locally and it appears to work smoothly!
## Summary
In an effort to make tools easier to work with and more configurable,
I'm introducing `ToolConfig` and updating `Prompt` to take in a general
list of Tools. I think this is simpler and better for a few reasons:
- We can easily assemble tools from various sources (our own harness,
mcp servers, etc.) and we can consolidate the logic for constructing the
logic in one place that is separate from serialization.
- client.rs no longer needs arbitrary config values, it just takes in a
list of tools to serialize
A hefty portion of the PR is now updating our conversion of
`mcp_types::Tool` to `OpenAITool`, but considering that @bolinfest
accurately called this out as a TODO long ago, I think it's time we
tackled it.
## Testing
- [x] Experimented locally, no changes, as expected
- [x] Added additional unit tests
- [x] Responded to rust-review
## Summary
Escalating out of sandbox is (almost always) not going to fix
long-running commands timing out - therefore we should just pass the
failure back to the model instead of asking the user to re-run a command
that took a long time anyway.
## Testing
- [x] Ran locally with a timeout and confirmed this worked as expected
https://github.com/openai/codex/pull/1835 has some messed up history.
This adds support for streaming chat completions, which is useful for ollama. We should probably take a very skeptical eye to the code introduced in this PR.
---------
Co-authored-by: Ahmed Ibrahim <aibrahim@openai.com>
Stream models thoughts and responses instead of waiting for the whole
thing to come through. Very rough right now, but I'm making the risk call to push through.
This lets us show an accumulating diff across all patches in a turn.
Refer to the docs for TurnDiffTracker for implementation details.
There are multiple ways this could have been done and this felt like the
right tradeoff between reliability and completeness:
*Pros*
* It will pick up all changes to files that the model touched including
if they prettier or another command that updates them.
* It will not pick up changes made by the user or other agents to files
it didn't modify.
*Cons*
* It will pick up changes that the user made to a file that the model
also touched
* It will not pick up changes to codegen or files that were not modified
with apply_patch
## Summary
- stream command stdout as `ExecCommandStdout` events
- forward streamed stdout to clients and ignore in human output
processor
- adjust call sites for new streaming API
- Add operation to summarize the context so far.
- The operation runs a compact task that summarizes the context.
- The operation clear the previous context to free the context window
- The operation didn't use `run_task` to avoid corrupting the session
- Add /compact in the tui
https://github.com/user-attachments/assets/e06c24e5-dcfb-4806-934a-564d425a919c
This is a follow-up to https://github.com/openai/codex/pull/1705, as
that PR inadvertently lost the logic where `PatchApplyBeginEvent` and
`PatchApplyEndEvent` events were sent when patches were auto-approved.
Though as part of this fix, I believe this also makes an important
safety fix to `assess_patch_safety()`, as there was a case that returned
`SandboxType::None`, which arguably is the thing we were trying to avoid
in #1705.
On a high level, we want there to be only one codepath where
`apply_patch` happens, which should be unified with the patch to run
`exec`, in general, so that sandboxing is applied consistently for both
cases.
Prior to this change, `apply_patch()` in `core` would either:
* exit early, delegating to `exec()` to shell out to `apply_patch` using
the appropriate sandbox
* proceed to run the logic for `apply_patch` in memory
549846b29a/codex-rs/core/src/apply_patch.rs (L61-L63)
In this implementation, only the latter would dispatch
`PatchApplyBeginEvent` and `PatchApplyEndEvent`, though the former would
dispatch `ExecCommandBeginEvent` and `ExecCommandEndEvent` for the
`apply_patch` call (or, more specifically, the `codex
--codex-run-as-apply-patch PATCH` call).
To unify things in this PR, we:
* Eliminate the back half of the `apply_patch()` function, and instead
have it also return with `DelegateToExec`, though we add an extra field
to the return value, `user_explicitly_approved_this_action`.
* In `codex.rs` where we process `DelegateToExec`, we use
`SandboxType::None` when `user_explicitly_approved_this_action` is
`true`. This means **we no longer run the apply_patch logic in memory**,
as we always `exec()`. (Note this is what allowed us to delete so much
code in `apply_patch.rs`.)
* In `codex.rs`, we further update `notify_exec_command_begin()` and
`notify_exec_command_end()` to take additional fields to determine what
type of notification to send: `ExecCommand` or `PatchApply`.
Admittedly, this PR also drops some of the functionality about giving
the user the opportunity to expand the set of writable roots as part of
approving the `apply_patch` command. I'm not sure how much that was
used, and we should probably rethink how that works as we are currently
tidying up the protocol to the TUI, in general.
Building on the work of https://github.com/openai/codex/pull/1702, this
changes how a shell call to `apply_patch` is handled.
Previously, a shell call to `apply_patch` was always handled in-process,
never leveraging a sandbox. To determine whether the `apply_patch`
operation could be auto-approved, the
`is_write_patch_constrained_to_writable_paths()` function would check if
all the paths listed in the paths were writable. If so, the agent would
apply the changes listed in the patch.
Unfortunately, this approach afforded a loophole: symlinks!
* For a soft link, we could fix this issue by tracing the link and
checking whether the target is in the set of writable paths, however...
* ...For a hard link, things are not as simple. We can run `stat FILE`
to see if the number of links is greater than 1, but then we would have
to do something potentially expensive like `find . -inum <inode_number>`
to find the other paths for `FILE`. Further, even if this worked, this
approach runs the risk of a
[TOCTOU](https://en.wikipedia.org/wiki/Time-of-check_to_time-of-use)
race condition, so it is not robust.
The solution, implemented in this PR, is to take the virtual execution
of the `apply_patch` CLI into an _actual_ execution using `codex
--codex-run-as-apply-patch PATCH`, which we can run under the sandbox
the user specified, just like any other `shell` call.
This, of course, assumes that the sandbox prevents writing through
symlinks as a mechanism to write to folders that are not in the writable
set configured by the sandbox. I verified this by testing the following
on both Mac and Linux:
```shell
#!/usr/bin/env bash
set -euo pipefail
# Can running a command in SANDBOX_DIR write a file in EXPLOIT_DIR?
# Codex is run in SANDBOX_DIR, so writes should be constrianed to this directory.
SANDBOX_DIR=$(mktemp -d -p "$HOME" sandboxtesttemp.XXXXXX)
# EXPLOIT_DIR is outside of SANDBOX_DIR, so let's see if we can write to it.
EXPLOIT_DIR=$(mktemp -d -p "$HOME" sandboxtesttemp.XXXXXX)
echo "SANDBOX_DIR: $SANDBOX_DIR"
echo "EXPLOIT_DIR: $EXPLOIT_DIR"
cleanup() {
# Only remove if it looks sane and still exists
[[ -n "${SANDBOX_DIR:-}" && -d "$SANDBOX_DIR" ]] && rm -rf -- "$SANDBOX_DIR"
[[ -n "${EXPLOIT_DIR:-}" && -d "$EXPLOIT_DIR" ]] && rm -rf -- "$EXPLOIT_DIR"
}
trap cleanup EXIT
echo "I am the original content" > "${EXPLOIT_DIR}/original.txt"
# Drop the -s to test hard links.
ln -s "${EXPLOIT_DIR}/original.txt" "${SANDBOX_DIR}/link-to-original.txt"
cat "${SANDBOX_DIR}/link-to-original.txt"
if [[ "$(uname)" == "Linux" ]]; then
SANDBOX_SUBCOMMAND=landlock
else
SANDBOX_SUBCOMMAND=seatbelt
fi
# Attempt the exploit
cd "${SANDBOX_DIR}"
codex debug "${SANDBOX_SUBCOMMAND}" bash -lc "echo pwned > ./link-to-original.txt" || true
cat "${EXPLOIT_DIR}/original.txt"
```
Admittedly, this change merits a proper integration test, but I think I
will have to do that in a follow-up PR.
