codex

Freeform unified exec output formatting (#6233 )

pakrym-oai · 2025-11-06 22:14:27 +00:00

b5349202e9

Fixes intermittent test failures in CI (#6282 )

I'm seeing two tests fail intermittently in CI. This PR attempts to
address (or at least mitigate) the flakiness.

* summarize_context_three_requests_and_instructions - The test snapshots
server.received_requests() immediately after observing TaskComplete.
Because the OpenAI /v1/responses call is streamed, the HTTP request can
still be draining when that event fires, so wiremock occasionally
reports only two captured requests. Fix is to wait for async activity to
complete.
* archive_conversation_moves_rollout_into_archived_directory - times out
on a slow CI run. Mitigation is to increase timeout value from 10s to
20s.

Eric Traut · 2025-11-05 13:12:25 -08:00

d7953aed74

[app-server] feat: v2 Thread APIs (#6214 )

Implements:
```
thread/list
thread/start
thread/resume
thread/archive
```

along with their integration tests. These are relatively light wrappers
around the existing core logic, and changes to core logic are minimal.

However, an improvement made for developer ergonomics:
- `thread/start` and `thread/resume` automatically attaches a
conversation listener internally, so clients don't have to make a
separate `AddConversationListener` call like they do today.

For consistency, also updated `model/list` and `feedback/upload` (naming
conventions, list API params).

Owen Lin · 2025-11-05 20:28:43 +00:00

2ab1650d4d

Improved token refresh handling to address "Re-connecting" behavior (#6231 )

Currently, when the access token expires, we attempt to use the refresh
token to acquire a new access token. This works most of the time.
However, there are situations where the refresh token is expired,
exhausted (already used to perform a refresh), or revoked. In those
cases, the current logic treats the error as transient and attempts to
retry it repeatedly.

This PR changes the token refresh logic to differentiate between
permanent and transient errors. It also changes callers to treat the
permanent errors as fatal rather than retrying them. And it provides
better error messages to users so they understand how to address the
problem. These error messages should also help us further understand why
we're seeing examples of refresh token exhaustion.

Here is the error message in the CLI. The same text appears within the
extension.

<img width="863" height="38" alt="image"
src="https://github.com/user-attachments/assets/7ffc0d08-ebf0-4900-b9a9-265064202f4f"
/>

I also correct the spelling of "Re-connecting", which shouldn't have a
hyphen in it.

Testing: I manually tested these code paths by adding temporary code to
programmatically cause my refresh token to be exhausted (by calling the
token refresh endpoint in a tight loop more than 50 times). I then
simulated an access token expiration, which caused the token refresh
logic to be invoked. I confirmed that the updated logic properly handled
the error condition.

Note: We earlier discussed the idea of forcefully logging out the user
at the point where token refresh failed. I made several attempts to do
this, and all of them resulted in a bad UX. It's important to surface
this error to users in a way that explains the problem and tells them
that they need to log in again. We also previously discussed deleting
the auth.json file when this condition is detected. That also creates
problems because it effectively changes the auth status from logged in
to logged out, and this causes odd failures and inconsistent UX. I think
it's therefore better not to delete auth.json in this case. If the user
closes the CLI or VSCE and starts it again, we properly detect that the
access token is expired and the refresh token is "dead", and we force
the user to go through the login flow at that time.

This should address aspects of #6191, #5679, and #5505

Eric Traut · 2025-11-05 10:51:57 -08:00

c4ebe4b078

fix: Update the deprecation message to link to the docs (#6211 )

The deprecation message is currently a bit confusing. Users may not
understand what is `[features].x`. I updated the docs and the
deprecation message for more guidance.

---------

Co-authored-by: Gabriel Peal <gpeal@users.noreply.github.com>

Ahmed Ibrahim · 2025-11-04 21:02:27 +00:00

d40a6b7f73

ignore deltas in codex_delegate (#6208 )

ignore legacy deltas in codex-delegate to avoid this
[issue](https://github.com/openai/codex/pull/6202).

Ahmed Ibrahim · 2025-11-04 19:21:35 +00:00

fe54c216a3

[App-server] v2 for account/updated and account/logout (#6175 )

V2 for `account/updated` and `account/logout` for app server. correspond
to old `authStatusChange` and `LogoutChatGpt` respectively. Followup PRs
will make other v2 endpoints call `account/updated` instead of
`authStatusChange` too.

Celia Chen · 2025-11-03 22:01:33 -08:00

d3187dbc17

Fixed notify handler so it passes correct input_messages details (#6143 )

This fixes bug #6121. 

The `input_messages` field passed to the notify handler is currently
empty because the logic is incorrectly including the OutputText rather
than InputText. I've fixed that and added proper filtering to remove
messages associated with AGENTS.md and other context injected by the
harness.

Testing: I wrote a notify handler and verified that the user prompt is
correctly passed through to the handler.

Eric Traut · 2025-11-03 14:23:04 -08:00

1e0e553304

feat: add the time after aborting (#5996 )

Tell the model how much time passed after the user aborted the call.

Ahmed Ibrahim · 2025-11-03 11:44:06 -08:00

6ee7fbcfff

feat: compactor 2 (#6027 )

Co-authored-by: pakrym-oai <pakrym@openai.com>

jif-oai · 2025-10-31 14:27:08 -07:00

611e00c862

Add warning on compact (#6052 )

This PR introduces the ability for `core` to send `warnings` as it can
send `errors. It also sends a warning on compaction.

<img width="811" height="187" alt="image"
src="https://github.com/user-attachments/assets/0947a42d-b720-420d-b7fd-115f8a65a46a"
/>

Ahmed Ibrahim · 2025-10-31 13:27:33 -07:00

c8ebb2a0dc

chore: Add shell serialization tests for json (#6043 )

## 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 😎

Dylan Hurd · 2025-10-31 11:01:58 -07:00

88e083a9d0

Truncate total tool calls text (#5979 )

Put a cap on the aggregate output of text content on tool calls.

---------

Co-authored-by: Gabriel Peal <gpeal@users.noreply.github.com>

Ahmed Ibrahim · 2025-10-31 10:30:36 -07:00

1c8507b32a

test: undo (#6034 )

jif-oai · 2025-10-31 14:46:24 +00:00

0508823075

Update user instruction message format (#6010 )

pakrym-oai · 2025-10-30 18:44:02 -07:00

2371d771cc

Remove last turn reasoning filtering (#5986 )

Ahmed Ibrahim · 2025-10-30 23:20:32 +00:00

a3d3719481

fix: Update seatbelt policy for java on macOS (#3987 )

# Summary

This PR is related to the Issue #3978 and contains a fix to the seatbelt
profile for macOS that allows to run java/jdk tooling from the sandbox.
I have found that the included change is the minimum change to make it
run on my machine.

There is a unit test added by codex when making this fix. I wonder if it
is useful since you need java installed on the target machine for it to
be relevant. I can remove it it is better.

Fixes #3978

Bernard Niset · 2025-10-30 14:25:04 -07:00

ff6d4cec6b

[codex] add developer instructions (#5897 )

we are using developer instructions for code reviews, we need to pass
them in cli as well.

Anton Panasenko · 2025-10-30 11:18:31 -07:00

9572cfc782

chore: testing on freeform apply_patch (#5952 )

## 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 Hurd · 2025-10-30 10:40:48 -07:00

4a55646a02

feat: compaction prompt configurable (#5959 )

```
 codex -c compact_prompt="Summarize in bullet points"
 ```

jif-oai · 2025-10-30 14:24:24 +00:00

f4f9695978

chore: unify config crates (#5958 )

jif-oai · 2025-10-30 10:28:32 +00:00

aa76003e28

Send delegate header (#5942 )

Send delegate type header

Ahmed Ibrahim · 2025-10-30 09:49:40 +00:00

fac548e430

ignore agent message deltas for the review mode (#5937 )

The deltas produce the whole json output. ignore them.

Ahmed Ibrahim · 2025-10-30 00:47:55 +00:00

7aa46ab5fc

Add item streaming events (#5546 )

Adds AgentMessageContentDelta, ReasoningContentDelta,
ReasoningRawContentDelta item streaming events while maintaining
compatibility for old events.

---------

Co-authored-by: Owen Lin <owen@openai.com>

pakrym-oai · 2025-10-29 22:33:57 +00:00

3429e82e45

Delegate review to codex instance (#5572 )

In this PR, I am exploring migrating task kind to an invocation of
Codex. The main reason would be getting rid off multiple
`ConversationHistory` state and streamlining our context/history
management.

This approach depends on opening a channel between the sub-codex and
codex. This channel is responsible for forwarding `interactive`
(`approvals`) and `non-interactive` events. The `task` is responsible
for handling those events.

This opens the door for implementing `codex as a tool`, replacing
`compact` and `review`, and potentially subagents.

One consideration is this code is very similar to `app-server` specially
in the approval part. If in the future we wanted an interactive
`sub-codex` we should consider using `codex-mcp`

Ahmed Ibrahim · 2025-10-29 21:04:25 +00:00

13e1d0362d

feat: add output even in sandbox denied (#5908 )

jif-oai · 2025-10-29 18:21:18 +00:00

3183935bd7

feat: deprecation warning (#5825 )

<img width="955" height="311" alt="Screenshot 2025-10-28 at 14 26 25"
src="https://github.com/user-attachments/assets/99729b3d-3bc9-4503-aab3-8dc919220ab4"
/>

jif-oai · 2025-10-29 12:29:28 +00:00

060637b4d4

feature: Add "!cmd" user shell execution (#2471 )

feature: Add "!cmd" user shell execution

This change lets users run local shell commands directly from the TUI by
prefixing their input with ! (e.g. !ls). Output is truncated to keep the
exec cell usable, and Ctrl-C cleanly
  interrupts long-running commands (e.g. !sleep 10000).

**Summary of changes**

- Route Op::RunUserShellCommand through a dedicated UserShellCommandTask
(core/src/tasks/user_shell.rs), keeping the task logic out of codex.rs.
- Reuse the existing tool router: the task constructs a ToolCall for the
local_shell tool and relies on ShellHandler, so no manual MCP tool
lookup is required.
- Emit exec lifecycle events (ExecCommandBegin/ExecCommandEnd) so the
TUI can show command metadata, live output, and exit status.

**End-to-end flow**

  **TUI handling**

1. ChatWidget::submit_user_message (TUI) intercepts messages starting
with !.
2. Non-empty commands dispatch Op::RunUserShellCommand { command };
empty commands surface a help hint.
3. No UserInput items are created, so nothing is enqueued for the model.

  **Core submission loop**
4. The submission loop routes the op to handlers::run_user_shell_command
(core/src/codex.rs).
5. A fresh TurnContext is created and Session::spawn_user_shell_command
enqueues UserShellCommandTask.

  **Task execution**
6. UserShellCommandTask::run emits TaskStartedEvent, formats the
command, and prepares a ToolCall targeting local_shell.
  7. ToolCallRuntime::handle_tool_call dispatches to ShellHandler.

  **Shell tool runtime**
8. ShellHandler::run_exec_like launches the process via the unified exec
runtime, honoring sandbox and shell policies, and emits
ExecCommandBegin/End.
9. Stdout/stderr are captured for the UI, but the task does not turn the
resulting ToolOutput into a model response.

  **Completion**
10. After ExecCommandEnd, the task finishes without an assistant
message; the session marks it complete and the exec cell displays the
final output.

  **Conversation context**

- The command and its output never enter the conversation history or the
model prompt; the flow is local-only.
  - Only exec/task events are emitted for UI rendering.

**Demo video**


https://github.com/user-attachments/assets/fcd114b0-4304-4448-a367-a04c43e0b996

Abhishek Bhardwaj · 2025-10-29 00:31:20 -07:00

89591e4246

verify mime type of images (#5888 )

solves: https://github.com/openai/codex/issues/5675

Block non-image uploads in the view_image workflow. We now confirm the
file’s MIME is image/* before building the data URL; otherwise we emit a
“unsupported MIME type” error to the model. This stops the agent from
sending application/json blobs that the Responses API rejects with 400s.

<img width="409" height="556" alt="Screenshot 2025-10-28 at 1 15 10 PM"
src="https://github.com/user-attachments/assets/a92199e8-2769-4b1d-8e33-92d9238c90fe"
/>

zhao-oai · 2025-10-28 14:52:51 -07:00

36113509f2

Filter out reasoning items from previous turns (#5857 )

Reduces request size and prevents 400 errors when switching between API
orgs.

Based on Responses API behavior described in
https://cookbook.openai.com/examples/responses_api/reasoning_items#caching

pakrym-oai · 2025-10-28 11:39:34 -07:00

1b8f2543ac

chore: speed-up pipeline (#5812 )

Speed-up pipeline by:
* Decoupling tests and clippy
* Use pre-built binary in tests
* `sccache` for caching of the builds

jif-oai · 2025-10-28 14:08:52 +00:00

7ff142d93f

[Auth] Choose which auth storage to use based on config (#5792 )

This PR is a follow-up to #5591. It allows users to choose which auth
storage mode they want by using the new
`cli_auth_credentials_store_mode` config.

Celia Chen · 2025-10-27 19:41:49 -07:00

4a42c4e142

[MCP] Render MCP tool call result images to the model (#5600 )

It's pretty amazing we have gotten here without the ability for the
model to see image content from MCP tool calls.

This PR builds off of 4391 and fixes #4819. I would like @KKcorps to get
adequete credit here but I also want to get this fix in ASAP so I gave
him a week to update it and haven't gotten a response so I'm going to
take it across the finish line.


This test highlights how absured the current situation is. I asked the
model to read this image using the Chrome MCP
<img width="2378" height="674" alt="image"
src="https://github.com/user-attachments/assets/9ef52608-72a2-4423-9f5e-7ae36b2b56e0"
/>

After this change, it correctly outputs:
> Captured the page: image dhows a dark terminal-style UI labeled
`OpenAI Codex (v0.0.0)` with prompt `model: gpt-5-codex medium` and
working directory `/codex/codex-rs`
(and more)  

Before this change, it said:
> Took the full-page screenshot you asked for. It shows a long,
horizontally repeating pattern of stylized people in orange, light-blue,
and mustard clothing, holding hands in alternating poses against a white
background. No text or other graphics-just rows of flat illustration
stretching off to the right.

Without this change, the Figma, Playwright, Chrome, and other visual MCP
servers are pretty much entirely useless.

I tested this change with the openai respones api as well as a third
party completions api

Gabriel Peal · 2025-10-27 17:55:57 -04:00

b0bdc04c30

Centralize truncation in conversation history (#5652 )

move the truncation logic to conversation history to use on any tool
output. This will help us in avoiding edge cases while truncating the
tool calls and mcp calls.

Ahmed Ibrahim · 2025-10-27 14:05:35 -07:00

7226365397

[Auth] Introduce New Auth Storage Abstraction for Codex CLI (#5569 )

This PR introduces a new `Auth Storage` abstraction layer that takes
care of read, write, and load of auth tokens based on the
AuthCredentialsStoreMode. It is similar to how we handle MCP client
oauth
[here](https://github.com/openai/codex/blob/main/codex-rs/rmcp-client/src/oauth.rs).
Instead of reading and writing directly from disk for auth tokens, Codex
CLI workflows now should instead use this auth storage using the public
helper functions.

This PR is just a refactor of the current code so the behavior stays the
same. We will add support for keyring and hybrid mode in follow-up PRs.

I have read the CLA Document and I hereby sign the CLA

Celia Chen · 2025-10-27 11:01:14 -07:00

eb5b1b627f

feat: image resizing (#5446 )

Add image resizing on the client side to reduce load on the API

jif-oai · 2025-10-27 16:58:10 +00:00

aea7610c76

fix: test yield time (#5811 )

jif-oai · 2025-10-27 11:57:29 +00:00

81be54b229

feat: async ghost commit (#5618 )

jif-oai · 2025-10-27 10:09:10 +00:00

e92c4f6561

feat: annotate conversations with model_provider for filtering (#5658 )

Because conversations that use the Responses API can have encrypted
reasoning messages, trying to resume a conversation with a different
provider could lead to confusing "failed to decrypt" errors. (This is
reproducible by starting a conversation using ChatGPT login and resuming
it as a conversation that uses OpenAI models via Azure.)

This changes `ListConversationsParams` to take a `model_providers:
Option<Vec<String>>` and adds `model_provider` on each
`ConversationSummary` it returns so these cases can be disambiguated.

Note this ended up making changes to
`codex-rs/core/src/rollout/tests.rs` because it had a number of cases
where it expected `Some` for the value of `next_cursor`, but the list of
rollouts was complete, so according to this docstring:


https://github.com/openai/codex/blob/bcd64c7e7231d6316a2377d1525a0fa74f21b783/codex-rs/app-server-protocol/src/protocol.rs#L334-L337

If there are no more items to return, then `next_cursor` should be
`None`. This PR updates that logic.






---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/5658).
* #5803
* #5793
* __->__ #5658

Michael Bolin · 2025-10-27 02:03:30 -07:00

5907422d65

Add feedback upload request handling (#5682 )

Ahmed Ibrahim · 2025-10-27 05:53:39 +00:00

f178805252

fix: flaky tests (#5625 )

jif-oai · 2025-10-24 13:56:41 +01:00

80783a7bb9

feat: end events on unified exec (#5551 )

jif-oai · 2025-10-23 18:51:34 +01:00

a6b9471548

fix: resume lookup for gitignored CODEX_HOME (#5311 )

Walk the sessions tree instead of using file_search so gitignored
CODEX_HOME directories can resume sessions. Add a regression test that
covers a .gitignore'd sessions directory.

Fixes #5247
Fixes #5412

---------

Co-authored-by: Owen Lin <owen@openai.com>

Thibault Sottiaux · 2025-10-23 17:04:40 +00:00

3059373e06

chore: testing on apply_path (#5557 )

jif-oai · 2025-10-23 17:00:48 +01:00

6745b12427

Handle cancelling/aborting while processing a turn (#5543 )

Currently we collect all all turn items in a vector, then we add it to
the history on success. This result in losing those items on errors
including aborting `ctrl+c`.

This PR:
- Adds the ability for the tool call to handle cancellation
- bubble the turn items up to where we are recording this info

Admittedly, this logic is an ad-hoc logic that doesn't handle a lot of
error edge cases. The right thing to do is recording to the history on
the spot as `items`/`tool calls output` come. However, this isn't
possible because of having different `task_kind` that has different
`conversation_histories`. The `try_run_turn` has no idea what thread are
we using. We cannot also pass an `arc` to the `conversation_histories`
because it's a private element of `state`.

That's said, `abort` is the most common case and we should cover it
until we remove `task kind`

Ahmed Ibrahim · 2025-10-23 08:47:10 -07:00

f59978ed3d

Move changing turn input functionalities to ConversationHistory (#5473 )

We are doing some ad-hoc logic while dealing with conversation history.
Ideally, we shouldn't mutate `vec[responseitem]` manually at all and
should depend on `ConversationHistory` for those changes.

Those changes are:
- Adding input to the history
- Removing items from the history
- Correcting history

I am also adding some `error` logs for cases we shouldn't ideally face.
For example, we shouldn't be missing `toolcalls` or `outputs`. We
shouldn't hit `ContextWindowExceeded` while performing `compact`

This refactor will give us granular control over our context management.

Ahmed Ibrahim · 2025-10-22 13:08:46 -07:00

273819aaae

Add new thread items and rewire event parsing to use them (#5418 )

1. Adds AgentMessage,  Reasoning,  WebSearch items.
2. Switches the ResponseItem parsing to use new items and then also emit
3. Removes user-item kind and filters out "special" (environment) user
items when returning to clients.

pakrym-oai · 2025-10-22 10:14:50 -07:00

3c90728a29

chore: align unified_exec (#5442 )

Align `unified_exec` with b implementation

jif-oai · 2025-10-22 11:50:18 +01:00

00b1e130b3

feat: add experimental_bearer_token option to model provider definition (#5467 )

While we do not want to encourage users to hardcode secrets in their
`config.toml` file, it should be possible to pass an API key
programmatically. For example, when using `codex app-server`, it is
possible to pass a "bag of configuration" as part of the
`NewConversationParams`:

https://github.com/openai/codex/blob/682d05512f2992dd0657f1078d4146f15c744d7a/codex-rs/app-server-protocol/src/protocol.rs#L248-L251

When using `codex app-server`, it's not practical to change env vars of
the `codex app-server` process on the fly (which is how we usually read
API key values), so this helps with that.

Michael Bolin · 2025-10-21 14:02:56 -07:00

404cae7d40

Add a baseline test for resume initial messages (#5466 )

pakrym-oai · 2025-10-21 11:45:01 -07:00

5cd8803998

653 Commits