codex

Fix status usage ratio (#4584 )

1. Removes "Token usage" line for chatgpt sub users
2. Adds the word "used" to the context window line

dedrisian-oai · 2025-10-02 10:27:10 -07:00

b07aafa5f5

fix: handle JSON Schema in additionalProperties for MCP tools (#4454 )

Fixes #4176

Some common tools provide a schema (even if just an empty object schema)
as the value for `additionalProperties`. The parsing as it currently
stands fails when it encounters this. This PR updates the schema to
accept a schema object in addition to a boolean value, per the JSON
Schema spec.

Marcus Griep · 2025-10-02 13:05:51 -04:00

b727d3f98a

Support CODEX_API_KEY for codex exec (#4615 )

Allows to set API key per invocation of `codex exec`

pakrym-oai · 2025-10-02 09:59:45 -07:00

2f6fb37d72

fix: update the gpt-5-codex prompt to be more explicit that it should always used fenced code blocks info tags (#4569 )

We get spurrious reports that the model writes fenced code blocks
without an info tag which then causes auto-language detection in the
extension to incorrectly highlight the code and show the wrong language.
The model should really always include a tag when it can.

Gabriel Peal · 2025-10-01 22:41:56 -07:00

35c76ad47d

Store settings on the thread instead of turn (#4579 )

It's much more common to keep the same settings for the entire
conversation, we can add per-turn overrides later.

pakrym-oai · 2025-10-02 00:31:13 +00:00

c07fb71186

Include request ID in the error message (#4572 )

To help with issue debugging
<img width="1414" height="253" alt="image"
src="https://github.com/user-attachments/assets/254732df-44ac-4252-997a-6c5e0927355b"
/>

pakrym-oai · 2025-10-01 15:36:04 -07:00

e899ae7d8a

canonicalize display of Agents.md paths on Windows. (#4577 )

Canonicalize path on Windows to 
- remove unattractive path prefixes such as `\\?\`
- simplify it (`../AGENTS.md` vs
`C:\Users\iceweasel\code\coded\Agents.md`)
before: <img width="1110" height="45" alt="Screenshot 2025-10-01 123520"
src="https://github.com/user-attachments/assets/48920ae6-d89c-41b8-b4ea-df5c18fb5fad"
/>

after: 
<img width="585" height="46" alt="Screenshot 2025-10-01 123612"
src="https://github.com/user-attachments/assets/70a1761a-9d97-4836-b14c-670b6f13e608"
/>

iceweasel-oai · 2025-10-01 14:33:19 -07:00

6f97ec4990

rework patch/exec approval UI (#4573 )

| Scenario | Screenshot |
| ---------------------- |
----------------------------------------------------------------------------------------------------------------------------------------------------
|
| short patch | <img width="1096" height="533" alt="short patch"
src="https://github.com/user-attachments/assets/8a883429-0965-4c0b-9002-217b3759b557"
/> |
| short command | <img width="1096" height="533" alt="short command"
src="https://github.com/user-attachments/assets/901abde8-2494-4e86-b98a-7cabaf87ca9c"
/> |
| long patch | <img width="1129" height="892" alt="long patch"
src="https://github.com/user-attachments/assets/fa799a29-a0d6-48e6-b2ef-10302a7916d3"
/> |
| long command | <img width="1096" height="892" alt="long command"
src="https://github.com/user-attachments/assets/11ddf79b-98cb-4b60-ac22-49dfa7779343"
/> |
| viewing complete patch | <img width="1129" height="892" alt="viewing
complete patch"
src="https://github.com/user-attachments/assets/81666958-af94-420e-aa66-b60d0a42b9db"
/> |

Jeremy Rose · 2025-10-01 14:29:05 -07:00

07c1db351a

Add initial set of doc comments to the SDK (#4513 )

Also perform minor code cleanup.

pakrym-oai · 2025-10-01 13:12:59 -07:00

31102af54b

Revert "chore: prompt update to enforce good usage of apply_patch" (#4576 )

Reverts openai/codex#3846

Thibault Sottiaux · 2025-10-01 20:11:36 +00:00

5d78c1edd3

Explicit node imports (#4567 )

To help with compatibility

pakrym-oai · 2025-10-01 12:39:04 -07:00

170c685882

Fix hang on second oauth login attempt (#4568 )

This PR fixes a bug that results in a hang in the oauth login flow if a
user logs in, then logs out, then logs in again without first closing
the browser window.

Root cause of problem: We use a local web server for the oauth flow, and
it's implemented using the `tiny_http` rust crate. During the first
login, a socket is created between the browser and the server. The
`tiny_http` library creates worker threads that persist for as long as
this socket remains open. Currently, there's no way to close the
connection on the server side — the library provides no API to do this.
The library also filters all "Connect: close" headers, which makes it
difficult to tell the client browser to close the connection. On the
second login attempt, the browser uses the existing connection rather
than creating a new one. Since that connection is associated with a
server instance that no longer exists, it is effectively ignored.

I considered switching from `tiny_http` to a different web server
library, but that would have been a big change with significant
regression risk. This PR includes a more surgical fix that works around
the limitation of `tiny_http` and sends a "Connect: close" header on the
last "success" page of the oauth flow.

Eric Traut · 2025-10-01 12:26:28 -07:00

609f75acec

fix: use number instead of bigint for the generated TS for RequestId (#4575 )

Before this PR:

```typescript
export type RequestId = string | bigint;
```

After:

```typescript
export type RequestId = string | number;
```

`bigint` introduces headaches in TypeScript without providing any real
value.

Michael Bolin · 2025-10-01 12:10:20 -07:00

eabe18714f

fix ctr-n hint (#4566 )

don't show or enable ctr-n to choose best of n while not in the composer

easong-openai · 2025-10-01 18:42:04 +00:00

ceaba36c7f

feat: add --emergency-version-override option to create_github_release script (#4556 )

I just had to use this like so:

```
./codex-rs/scripts/create_github_release --publish-alpha --emergency-version-override 0.43.0-alpha.10
```

because the build for `0.43.0-alpha.9` failed:

https://github.com/openai/codex/actions/runs/18167317356

Michael Bolin · 2025-10-01 11:40:04 -07:00

d94e8bad8b

SDK: support working directory and skipGitRepoCheck options (#4563 )

Make options not required, add support for working directory and
skipGitRepoCheck options on the turn

pakrym-oai · 2025-10-01 11:26:49 -07:00

8a367ef6bf

Fall back to configured instruction files if AGENTS.md isn't available (#4544 )

Allow users to configure an agents.md alternative to consume, but warn
the user it may degrade model performance.

Fixes #4376

easong-openai · 2025-10-01 18:19:59 +00:00

400a5a90bf

Show context window usage while tasks run (#4536 )

## Summary
- show the remaining context window percentage in `/status` alongside
existing token usage details
- replace the composer shortcut prompt with the context window
percentage (or an unavailable message) while a task is running
- update TUI snapshots to reflect the new context window line

## Testing
- cargo test -p codex-tui

------
https://chatgpt.com/codex/tasks/task_i_68dc6e7397ac8321909d7daff25a396c

Ahmed Ibrahim · 2025-10-01 18:03:05 +00:00

2f370e946d

Show placeholder for commands with no output (#4509 )

## Summary
- show a dim “(no output)” placeholder when an executed command produces
no stdout or stderr so empty runs are visible
- update TUI snapshots to include the new placeholder in history
renderings

## Testing
- cargo test -p codex-tui


------
https://chatgpt.com/codex/tasks/task_i_68dc056c1d5883218fe8d9929e9b1657

Ahmed Ibrahim · 2025-10-01 10:42:30 -07:00

751b3b50ac

Add Updated at time in resume picker (#4468 )

<img width="639" height="281" alt="image"
src="https://github.com/user-attachments/assets/92b2ad2b-9e18-4485-9b8d-d7056eb98651"
/>

Ahmed Ibrahim · 2025-10-01 10:40:43 -07:00

d78d0764aa

Handle trailing backslash properly (#4559 )

**Summary**

This PR fixes an issue in the device code login flow where trailing
slashes in the issuer URL could cause malformed URLs during codex token
exchange step


**Test**


Before the changes

`Error logging in with device code: device code exchange failed: error
decoding response body`

After the changes

`Successfully logged in`

rakesh-oai · 2025-10-01 10:32:09 -07:00

699c121606

implement command safety for PowerShell commands (#4269 )

Implement command safety for PowerShell commands on Windows

This change adds a new Windows-specific command-safety module under
`codex-rs/core/src/command_safety/windows_safe_commands.rs` to strictly
sanitise PowerShell invocations. Key points:

- Introduce `is_safe_command_windows()` to only allow explicitly
read-only PowerShell calls.
- Parse and split PowerShell invocations (including inline `-Command`
scripts and pipelines).
- Block unsafe switches (`-File`, `-EncodedCommand`, `-ExecutionPolicy`,
unknown flags, call operators, redirections, separators).
- Whitelist only read-only cmdlets (`Get-ChildItem`, `Get-Content`,
`Select-Object`, etc.), safe Git subcommands (`status`, `log`, `show`,
`diff`, `cat-file`), and ripgrep without unsafe options.
- Add comprehensive unit tests covering allowed and rejected command
patterns (nested calls, side effects, chaining, redirections).

This ensures Codex on Windows can safely execute discover-only
PowerShell workflows without risking destructive operations.

iceweasel-oai · 2025-10-01 09:56:48 -07:00

dde615f482

fix: pnpm/action-setup@v4 should run before actions/setup-node@v5 (#4555 )

`rust-release.yml` just failed:

https://github.com/openai/codex/actions/runs/18167317356/job/51714366768

The error is:

> Error: Unable to locate executable file: pnpm. Please verify either
the file path exists or the file can be found within a directory
specified by the PATH environment variable. Also check the file mode to
verify the file is executable.

We need to install `pnpm` first like we do in `ci.yml`:


https://github.com/openai/codex/blob/f815157dd9d02377f827c0b6cd1cd1d0386461f8/.github/workflows/ci.yml#L17-L25

Michael Bolin · 2025-10-01 09:04:14 -07:00

325fad1d92

chore: introduce publishing logic for @openai/codex-sdk (#4543 )

There was a bit of copypasta I put up with when were publishing two
packages to npm, but now that it's three, I created some more scripts to
consolidate things.

With this change, I ran:

```shell
./scripts/stage_npm_packages.py --release-version 0.43.0-alpha.8 --package codex --package codex-responses-api-proxy --package codex-sdk
```

Indeed when it finished, I ended up with:

```shell
$ tree dist
dist
└── npm
    ├── codex-npm-0.43.0-alpha.8.tgz
    ├── codex-responses-api-proxy-npm-0.43.0-alpha.8.tgz
    └── codex-sdk-npm-0.43.0-alpha.8.tgz
$ tar tzvf dist/npm/codex-sdk-npm-0.43.0-alpha.8.tgz
-rwxr-xr-x  0 0      0    25476720 Oct 26  1985 package/vendor/aarch64-apple-darwin/codex/codex
-rwxr-xr-x  0 0      0    29871400 Oct 26  1985 package/vendor/aarch64-unknown-linux-musl/codex/codex
-rwxr-xr-x  0 0      0    28368096 Oct 26  1985 package/vendor/x86_64-apple-darwin/codex/codex
-rwxr-xr-x  0 0      0    36029472 Oct 26  1985 package/vendor/x86_64-unknown-linux-musl/codex/codex
-rw-r--r--  0 0      0       10926 Oct 26  1985 package/LICENSE
-rw-r--r--  0 0      0    30187520 Oct 26  1985 package/vendor/aarch64-pc-windows-msvc/codex/codex.exe
-rw-r--r--  0 0      0    35277824 Oct 26  1985 package/vendor/x86_64-pc-windows-msvc/codex/codex.exe
-rw-r--r--  0 0      0        4842 Oct 26  1985 package/dist/index.js
-rw-r--r--  0 0      0        1347 Oct 26  1985 package/package.json
-rw-r--r--  0 0      0        9867 Oct 26  1985 package/dist/index.js.map
-rw-r--r--  0 0      0          12 Oct 26  1985 package/README.md
-rw-r--r--  0 0      0        4287 Oct 26  1985 package/dist/index.d.ts
```

Michael Bolin · 2025-10-01 08:29:59 -07:00

f815157dd9

chore: sanbox extraction (#4286 )

# Extract and Centralize Sandboxing
- Goal: Improve safety and clarity by centralizing sandbox planning and
execution.
  - Approach:
- Add planner (ExecPlan) and backend registry (Direct/Seatbelt/Linux)
with run_with_plan.
- Refactor codex.rs to plan-then-execute; handle failures/escalation via
the plan.
- Delegate apply_patch to the codex binary and run it with an empty env
for determinism.

jif-oai · 2025-10-01 12:05:12 +01:00

b8195a17e5

Fix Callback URL for staging and prod environments (#4533 )

# 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.

rakesh-oai · 2025-10-01 02:57:37 +00:00

349ef7edc6

fix: remove mcp-types from app server protocol (#4537 )

We continue the separation between `codex app-server` and `codex
mcp-server`.

In particular, we introduce a new crate, `codex-app-server-protocol`,
and migrate `codex-rs/protocol/src/mcp_protocol.rs` into it, renaming it
`codex-rs/app-server-protocol/src/protocol.rs`.

Because `ConversationId` was defined in `mcp_protocol.rs`, we move it
into its own file, `codex-rs/protocol/src/conversation_id.rs`, and
because it is referenced in a ton of places, we have to touch a lot of
files as part of this PR.

We also decide to get away from proper JSON-RPC 2.0 semantics, so we
also introduce `codex-rs/app-server-protocol/src/jsonrpc_lite.rs`, which
is basically the same `JSONRPCMessage` type defined in `mcp-types`
except with all of the `"jsonrpc": "2.0"` removed.

Getting rid of `"jsonrpc": "2.0"` makes our serialization logic
considerably simpler, as we can lean heavier on serde to serialize
directly into the wire format that we use now.

Michael Bolin · 2025-10-01 02:16:26 +00:00

5881c0d6d4

Add executable detection and export Codex from the SDK (#4532 )

Executable detection uses the same rules as the codex wrapper.

pakrym-oai · 2025-09-30 18:06:16 -07:00

8dd771d217

fix: use macros to ensure request/response symmetry (#4529 )

Manually curating `protocol-ts/src/lib.rs` was error-prone, as expected.
I finally asked Codex to write some Rust macros so we can ensure that:

- For every variant of `ClientRequest` and `ServerRequest`, there is an
associated `params` and `response` type.
- All response types are included automatically in the output of `codex
generate-ts`.

Michael Bolin · 2025-09-30 18:06:05 -07:00

32853ecbc5

Remove legacy codex exec --json format (#4525 )

`codex exec --json` now maps to the behavior of `codex exec
--experimental-json` with new event and item shapes.

Thread events:
- thread.started
- turn.started
- turn.completed
- turn.failed
- item.started
- item.updated
- item.completed

Item types: 
- assistant_message
- reasoning
- command_execution
- file_change
- mcp_tool_call
- web_search
- todo_list
- error

Sample output:

<details>
`codex exec "list my assigned github issues"  --json | jq`

```
{
  "type": "thread.started",
  "thread_id": "01999ce5-f229-7661-8570-53312bd47ea3"
}
{
  "type": "turn.started"
}
{
  "type": "item.completed",
  "item": {
    "id": "item_0",
    "item_type": "reasoning",
    "text": "**Planning to list assigned GitHub issues**"
  }
}
{
  "type": "item.started",
  "item": {
    "id": "item_1",
    "item_type": "mcp_tool_call",
    "server": "github",
    "tool": "search_issues",
    "status": "in_progress"
  }
}
{
  "type": "item.completed",
  "item": {
    "id": "item_1",
    "item_type": "mcp_tool_call",
    "server": "github",
    "tool": "search_issues",
    "status": "completed"
  }
}
{
  "type": "item.completed",
  "item": {
    "id": "item_2",
    "item_type": "reasoning",
    "text": "**Organizing final message structure**"
  }
}
{
  "type": "item.completed",
  "item": {
    "id": "item_3",
    "item_type": "assistant_message",
    "text": "**Assigned Issues**\n- openai/codex#3267 – “stream error: stream disconnected before completion…” (bug) – last update 2025-09-08\n- openai/codex#3257 – “You've hit your usage limit. Try again in 4 days 20 hours 9 minutes.” – last update 2025-09-23\n- openai/codex#3054 – “reqwest SSL panic (library has no ciphers)” (bug) – last update 2025-09-03\n- openai/codex#3051 – “thread 'main' panicked at linux-sandbox/src/linux_run_main.rs:53:5:” (bug) – last update 2025-09-10\n- openai/codex#3004 – “Auto-compact when approaching context limit” (enhancement) – last update 2025-09-26\n- openai/codex#2916 – “Feature request: Add OpenAI service tier support for cost optimization” – last update 2025-09-12\n- openai/codex#1581 – “stream error: stream disconnected before completion: stream closed before response.complete; retrying...” (bug) – last update 2025-09-17"
  }
}
{
  "type": "turn.completed",
  "usage": {
    "input_tokens": 34785,
    "cached_input_tokens": 12544,
    "output_tokens": 560
  }
}
```

</details>

pakrym-oai · 2025-09-30 17:21:37 -07:00

7fc3edf8a7

wrap markdown at render time (#4506 )

This results in correctly indenting list items with long lines.

<img width="1006" height="251" alt="Screenshot 2025-09-30 at 10 00
48 AM"
src="https://github.com/user-attachments/assets/0a076cf6-ca3c-4efb-b3af-dc07617cdb6f"
/>

Jeremy Rose · 2025-09-30 23:13:55 +00:00

01e6503672

Delete codex proto (#4520 )

pakrym-oai · 2025-09-30 22:33:28 +00:00

9c259737d3

fix: enable process hardening in Codex CLI for release builds (#4521 )

I don't believe there is any upside in making process hardening opt-in
for Codex CLI releases. If you want to tinker with Codex CLI, then build
from source (or run as `root`)?

Michael Bolin · 2025-09-30 14:34:35 -07:00

b8e1fe60c5

fix: clean up TypeScript exports (#4518 )

Fixes:

- Removed overdeclaration of types that were unnecessary because they
were already included by induction.
- Reordered list of response types to match the enum order, making it
easier to identify what was missing.
- Added `ExecArbitraryCommandResponse` because it was missing.
- Leveraged `use codex_protocol::mcp_protocol::*;` to make the file more
readable.
- Removed crate dependency on `mcp-types` now that we have separate the
app server from the MCP server:
https://github.com/openai/codex/pull/4471

My next move is to come up with some scheme that ensures request types
always have a response type and that the response type is automatically
included with the output of `codex generate-ts`.

Michael Bolin · 2025-09-30 14:08:43 -07:00

ddfb7eb548

fix: ensure every variant of ClientRequest has a params field (#4512 )

This ensures changes the generated TypeScript type for `ClientRequest`
so that instead of this:

```typescript
/**
 * Request from the client to the server.
 */
export type ClientRequest =
  | { method: "initialize"; id: RequestId; params: InitializeParams }
  | { method: "newConversation"; id: RequestId; params: NewConversationParams }
  // ...
  | { method: "getUserAgent"; id: RequestId }
  | { method: "userInfo"; id: RequestId }
  // ...
```

we have this:

```typescript
/**
 * Request from the client to the server.
 */
export type ClientRequest =
  | { method: "initialize"; id: RequestId; params: InitializeParams }
  | { method: "newConversation"; id: RequestId; params: NewConversationParams }
  // ...
  | { method: "getUserAgent"; id: RequestId; params: undefined }
  | { method: "userInfo"; id: RequestId; params: undefined }
  // ...
```

which makes TypeScript happier when it comes to destructuring instances
of `ClientRequest` because it does not complain about `params` not being
guaranteed to exist anymore.

Michael Bolin · 2025-09-30 12:03:32 -07:00

6910be3224

Wire up web search item (#4511 )

Add handling for web search events.

pakrym-oai · 2025-09-30 12:01:17 -07:00

a534356fe1

[SDK] Test that a tread can be continued with extra params (#4508 )

pakrym-oai · 2025-09-30 17:22:14 +00:00

c89b0e1235

chore: prompt update to enforce good usage of apply_patch (#3846 )

Update prompt to prevent codex to use Python script or fancy commands to
edit files.

## Testing:
3 scenarios have been considered:
1. Rename codex to meca_code. Proceed to the whole refactor file by
file. Don't ask for approval at each step
2. Add a description to every single function you can find in the repo
3. Rewrite codex.rs in a more idiomatic way. Make sure to touch ONLY
this file and that clippy does not complain at the end

Before this update, 22% (estimation as it's sometimes hard to find all
the creative way the model find to edit files) of the file editions
where made using something else than a raw `apply_patch`

After this update, not a single edition without `apply_patch` was found

[EDIT]
I managed to have a few `["bash", "-lc", "apply_path"]` when reaching <
10% context left

jif-oai · 2025-09-30 10:18:59 -07:00

f6a152848a

Named args for custom prompts (#4474 )

Here's the logic:

1. If text is empty and selector is open:
- Enter on a prompt without args should autosubmit the prompt
- Enter on a prompt with numeric args should add `/prompts:name ` to the
text input
- Enter on a prompt with named args should add `/prompts:name ARG1=""
ARG2=""` to the text input
2. If text is not empty but no args are passed:
- For prompts with numeric args -> we allow it to submit (params are
optional)
- For prompts with named args -> we throw an error (all params should
have values)

<img width="454" height="246" alt="Screenshot 2025-09-23 at 2 23 21 PM"
src="https://github.com/user-attachments/assets/fd180a1b-7d17-42ec-b231-8da48828b811"
/>

dedrisian-oai · 2025-09-30 10:06:41 -07:00

3592ecb23c

Support model and sandbox mode in the sdk (#4503 )

pakrym-oai · 2025-09-30 09:00:39 -07:00

516acc030b

Add cloud tasks (#3197 )

Adds a TUI for managing, applying, and creating cloud tasks

easong-openai · 2025-09-30 10:10:33 +00:00

5b038135de

fix: separate codex mcp into codex mcp-server and codex app-server (#4471 )

This is a very large PR with some non-backwards-compatible changes.

Historically, `codex mcp` (or `codex mcp serve`) started a JSON-RPC-ish
server that had two overlapping responsibilities:

- Running an MCP server, providing some basic tool calls.
- Running the app server used to power experiences such as the VS Code
extension.

This PR aims to separate these into distinct concepts:

- `codex mcp-server` for the MCP server
- `codex app-server` for the "application server"

Note `codex mcp` still exists because it already has its own subcommands
for MCP management (`list`, `add`, etc.)

The MCP logic continues to live in `codex-rs/mcp-server` whereas the
refactored app server logic is in the new `codex-rs/app-server` folder.
Note that most of the existing integration tests in
`codex-rs/mcp-server/tests/suite` were actually for the app server, so
all the tests have been moved with the exception of
`codex-rs/mcp-server/tests/suite/mod.rs`.

Because this is already a large diff, I tried not to change more than I
had to, so `codex-rs/app-server/tests/common/mcp_process.rs` still uses
the name `McpProcess` for now, but I will do some mechanical renamings
to things like `AppServer` in subsequent PRs.

While `mcp-server` and `app-server` share some overlapping functionality
(like reading streams of JSONL and dispatching based on message types)
and some differences (completely different message types), I ended up
doing a bit of copypasta between the two crates, as both have somewhat
similar `message_processor.rs` and `outgoing_message.rs` files for now,
though I expect them to diverge more in the near future.

One material change is that of the initialize handshake for `codex
app-server`, as we no longer use the MCP types for that handshake.
Instead, we update `codex-rs/protocol/src/mcp_protocol.rs` to add an
`Initialize` variant to `ClientRequest`, which takes the `ClientInfo`
object we need to update the `USER_AGENT_SUFFIX` in
`codex-rs/app-server/src/message_processor.rs`.

One other material change is in
`codex-rs/app-server/src/codex_message_processor.rs` where I eliminated
a use of the `send_event_as_notification()` method I am generally trying
to deprecate (because it blindly maps an `EventMsg` into a
`JSONNotification`) in favor of `send_server_notification()`, which
takes a `ServerNotification`, as that is intended to be a custom enum of
all notification types supported by the app server. So to make this
update, I had to introduce a new variant of `ServerNotification`,
`SessionConfigured`, which is a non-backwards compatible change with the
old `codex mcp`, and clients will have to be updated after the next
release that contains this PR. Note that
`codex-rs/app-server/tests/suite/list_resume.rs` also had to be update
to reflect this change.

I introduced `codex-rs/utils/json-to-toml/src/lib.rs` as a small utility
crate to avoid some of the copying between `mcp-server` and
`app-server`.

Michael Bolin · 2025-09-30 07:06:18 +00:00

d9dbf48828

Update MCP docs to reference experimental RMCP client (#4422 )

Gabriel Peal · 2025-09-30 02:44:16 -04:00

2e95e5602d

Move PR-style review to top (#4486 )

<img width="469" height="330" alt="Screenshot 2025-09-29 at 10 31 22 PM"
src="https://github.com/user-attachments/assets/b5e20a08-85b4-4095-8a7f-0f58d1195b7e"
/>

dedrisian-oai · 2025-09-30 06:03:37 +00:00

87a654cf6b

SDK CI (#4483 )

Build debug codex in SDK configuration

pakrym-oai · 2025-09-29 21:15:02 -07:00

27c6c5d7a7

Set originator for codex exec (#4485 )

Distinct from the main CLI.

pakrym-oai · 2025-09-29 20:59:19 -07:00

c09e131653

Rename conversation to thread in codex exec (#4482 )

pakrym-oai · 2025-09-29 20:18:30 -07:00

ea82f86662

Add MCP tool call item to codex exec (#4481 )

No arguments/results for now.
```
{
  "type": "item.started",
  "item": {
    "id": "item_1",
    "item_type": "mcp_tool_call",
    "server": "github",
    "tool": "search_issues",
    "status": "in_progress"
  }
}
{
  "type": "item.completed",
  "item": {
    "id": "item_1",
    "item_type": "mcp_tool_call",
    "server": "github",
    "tool": "search_issues",
    "status": "completed"
  }
}
```

pakrym-oai · 2025-09-29 19:45:11 -07:00

a8edc57740

Add some types and a basic test to the SDK (#4472 )

pakrym-oai · 2025-09-29 19:40:08 -07:00

52e591ce60

Rakesh/support device auth (#3531 )

# 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.

# test

```
codex-rs % export CODEX_DEVICE_AUTH_BASE_URL=http://localhost:3007
codex-rs % cargo run --bin codex login --experimental_use-device-code
   Compiling codex-login v0.0.0 (/Users/rakesh/code/codex/codex-rs/login)
   Compiling codex-mcp-server v0.0.0 (/Users/rakesh/code/codex/codex-rs/mcp-server)
   Compiling codex-tui v0.0.0 (/Users/rakesh/code/codex/codex-rs/tui)
   Compiling codex-cli v0.0.0 (/Users/rakesh/code/codex/codex-rs/cli)
    Finished `dev` profile [unoptimized + debuginfo] target(s) in 2.90s
     Running `target/debug/codex login --experimental_use-device-code`
To authenticate, enter this code when prompted: 6Q27-KBVRF with interval 5
^C

```

The error in the last line is since the poll endpoint is not yet
implemented

rakesh-oai · 2025-09-30 02:34:57 +00:00

079303091f

1436 Commits