codex

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

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

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

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

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

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

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

Add turn.failed and rename session created to thread started (#4478 )

Don't produce completed when turn failed.

pakrym-oai · 2025-09-29 18:38:04 -07:00

4a80059b1b

Custom prompts begin with /prompts: (#4476 )

<img width="608" height="354" alt="Screenshot 2025-09-29 at 4 41 08 PM"
src="https://github.com/user-attachments/assets/162508eb-c1ac-4bc0-95f2-5e23cb4ae428"
/>

dedrisian-oai · 2025-09-29 17:58:16 -07:00

bf76258cdc

Fixes (#4458 )

Fixing the "? for shortcuts"

- Only show the hint when composer is empty
- Don't reset footer on new task updates
- Reorder the elements
- Align the "?" and "/" with overlay on and off

Based on #4364

Ahmed Ibrahim · 2025-09-30 00:10:04 +00:00

c64da4ff71

reintroduce "? for shortcuts" (#4364 )

Reverts openai/codex#4362

Ahmed Ibrahim · 2025-09-29 23:35:47 +00:00

98efd352ae

Custom prompt args (numeric) (#4470 )

[Cherry picked from /pull/3565]

Adds $1, $2, $3, $ARGUMENTS param parsing for custom prompts.

dedrisian-oai · 2025-09-29 16:14:37 -07:00

80ccec6530

no background for /command or @file popup (#4469 )

before:

<img width="855" height="270" alt="Screenshot 2025-09-29 at 3 42 53 PM"
src="https://github.com/user-attachments/assets/eb247e1f-0947-4830-93c4-d4ecb2992b32"
/>


after:

<img width="855" height="270" alt="Screenshot 2025-09-29 at 3 43 04 PM"
src="https://github.com/user-attachments/assets/46717844-6066-47a4-a34a-1a75508ea2c3"
/>

Jeremy Rose · 2025-09-29 22:58:15 +00:00

c81baaabda

render • as dim (#4467 )

<img width="988" height="686" alt="Screenshot 2025-09-29 at 3 28 30 PM"
src="https://github.com/user-attachments/assets/634a6e6f-cdc0-49af-97c1-096e871414bb"
/>

Jeremy Rose · 2025-09-29 15:46:47 -07:00

55b74c95e2

[Core]: add tail in the rollout data (#4461 )

This will help us show the conversation tail and last updated timestamp.

Ahmed Ibrahim · 2025-09-29 14:32:26 -07:00

16057e76b0

Parse out frontmatter for custom prompts (#4456 )

[Cherry picked from https://github.com/openai/codex/pull/3565]

Removes the frontmatter description/args from custom prompt files and
only includes body.

dedrisian-oai · 2025-09-29 13:06:08 -07:00

83a4d4d8ed

[mcp-server] Expose fuzzy file search in MCP (#2677 )

## Summary
Expose a simple fuzzy file search implementation for mcp clients to work
with

## Testing
- [x] Tested locally

Dylan · 2025-09-29 12:19:09 -07:00

197f45a3be

OpenTelemetry events (#2103 )

### Title

## otel

Codex can emit [OpenTelemetry](https://opentelemetry.io/) **log events**
that
describe each run: outbound API requests, streamed responses, user
input,
tool-approval decisions, and the result of every tool invocation. Export
is
**disabled by default** so local runs remain self-contained. Opt in by
adding an
`[otel]` table and choosing an exporter.

```toml
[otel]
environment = "staging"   # defaults to "dev"
exporter = "none"          # defaults to "none"; set to otlp-http or otlp-grpc to send events
log_user_prompt = false    # defaults to false; redact prompt text unless explicitly enabled
```

Codex tags every exported event with `service.name = "codex-cli"`, the
CLI
version, and an `env` attribute so downstream collectors can distinguish
dev/staging/prod traffic. Only telemetry produced inside the
`codex_otel`
crate—the events listed below—is forwarded to the exporter.

### Event catalog

Every event shares a common set of metadata fields: `event.timestamp`,
`conversation.id`, `app.version`, `auth_mode` (when available),
`user.account_id` (when available), `terminal.type`, `model`, and
`slug`.

With OTEL enabled Codex emits the following event types (in addition to
the
metadata above):

- `codex.api_request`
  - `cf_ray` (optional)
  - `attempt`
  - `duration_ms`
  - `http.response.status_code` (optional)
  - `error.message` (failures)
- `codex.sse_event`
  - `event.kind`
  - `duration_ms`
  - `error.message` (failures)
  - `input_token_count` (completion only)
  - `output_token_count` (completion only)
  - `cached_token_count` (completion only, optional)
  - `reasoning_token_count` (completion only, optional)
  - `tool_token_count` (completion only)
- `codex.user_prompt`
  - `prompt_length`
  - `prompt` (redacted unless `log_user_prompt = true`)
- `codex.tool_decision`
  - `tool_name`
  - `call_id`
- `decision` (`approved`, `approved_for_session`, `denied`, or `abort`)
  - `source` (`config` or `user`)
- `codex.tool_result`
  - `tool_name`
  - `call_id`
  - `arguments`
  - `duration_ms` (execution time for the tool)
  - `success` (`"true"` or `"false"`)
  - `output`

### Choosing an exporter

Set `otel.exporter` to control where events go:

- `none` – leaves instrumentation active but skips exporting. This is
the
  default.
- `otlp-http` – posts OTLP log records to an OTLP/HTTP collector.
Specify the
  endpoint, protocol, and headers your collector expects:

  ```toml
  [otel]
  exporter = { otlp-http = {
    endpoint = "https://otel.example.com/v1/logs",
    protocol = "binary",
    headers = { "x-otlp-api-key" = "${OTLP_TOKEN}" }
  }}
  ```

- `otlp-grpc` – streams OTLP log records over gRPC. Provide the endpoint
and any
  metadata headers:

  ```toml
  [otel]
  exporter = { otlp-grpc = {
    endpoint = "https://otel.example.com:4317",
    headers = { "x-otlp-meta" = "abc123" }
  }}
  ```

If the exporter is `none` nothing is written anywhere; otherwise you
must run or point to your
own collector. All exporters run on a background batch worker that is
flushed on
shutdown.

If you build Codex from source the OTEL crate is still behind an `otel`
feature
flag; the official prebuilt binaries ship with the feature enabled. When
the
feature is disabled the telemetry hooks become no-ops so the CLI
continues to
function without the extra dependencies.

---------

Co-authored-by: Anton Panasenko <apanasenko@openai.com>

vishnu-oai · 2025-09-29 11:30:55 -07:00

04c1782e52

fix clear-to-end being emitted at the end of a row (#4447 )

This was causing glitchy behavior when a line in the input was the exact
width of the terminal.

Jeremy Rose · 2025-09-29 16:52:35 +00:00

d15253415a

[CODEX-3595] Remove period when copying highlighted text in iTerm (#4419 )

Ed Bayes · 2025-09-28 20:50:04 -07:00

c4120a265b

feat: introduce npm module for codex-responses-api-proxy (#4417 )

This PR expands `.github/workflows/rust-release.yml` so that it also
builds and publishes the `npm` module for
`@openai/codex-responses-api-proxy` in addition to `@openai/codex`. Note
both `npm` modules are similar, in that they each contain a single `.js`
file that is a thin launcher around the appropriate native executable.
(Since we have a minimal dependency on Node.js, I also lowered the
minimum version from 20 to 16 and verified that works on my machine.)

As part of this change, we tighten up some of the docs around
`codex-responses-api-proxy` and ensure the details regarding protecting
the `OPENAI_API_KEY` in memory match the implementation.

To test the `npm` build process, I ran:

```
./codex-cli/scripts/build_npm_package.py --package codex-responses-api-proxy --version 0.43.0-alpha.3
```

which stages the `npm` module for `@openai/codex-responses-api-proxy` in
a temp directory, using the binary artifacts from
https://github.com/openai/codex/releases/tag/rust-v0.43.0-alpha.3.

Michael Bolin · 2025-09-28 19:34:06 -07:00

618a42adf5

Add /review to main commands (#4416 )

<img width="517" height="249" alt="Screenshot 2025-09-28 at 4 33 26 PM"
src="https://github.com/user-attachments/assets/6d34734e-fe3c-4b88-8239-a6436bcb9fa5"
/>

dedrisian-oai · 2025-09-28 16:59:39 -07:00

a9d54b9e92

chore: remove responses-api-proxy from the multitool (#4404 )

This removes the `codex responses-api-proxy` subcommand in favor of
running it as a standalone CLI.

As part of this change, we:

- remove the dependency on `tokio`/`async/await` as well as `codex_arg0`
- introduce the use of `pre_main_hardening()` so `CODEX_SECURE_MODE=1`
is not required

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/4404).
* #4406
* __->__ #4404
* #4403

Michael Bolin · 2025-09-28 15:22:27 -07:00

99841332e2

chore: lower logging level from error to info for MCP startup (#4412 )

Michael Bolin · 2025-09-28 15:13:44 -07:00

7407469791

chore: move pre_main_hardening() utility into its own crate (#4403 )

Michael Bolin · 2025-09-28 14:35:14 -07:00

43615becf0

Improve update nudge (#4405 )

Makes the update nudge larger and adds a link to see latest release:

<img width="542" height="337" alt="Screenshot 2025-09-28 at 11 19 05 AM"
src="https://github.com/user-attachments/assets/1facce96-72f0-4a97-910a-df8b5b8b07af"
/>

dedrisian-oai · 2025-09-28 11:46:15 -07:00

9ee6e6f342

chore: remove model upgrade popup (#4332 )

Thibault Sottiaux · 2025-09-27 13:25:09 -07:00

d7286e9829

fix(tui): make ? work again (#4362 )

Revert #4330 #4316

Fouad Matin · 2025-09-27 12:18:33 -07:00

bcf2bc0aa5

fix: remove default timeout of 30s in the proxy (#4336 )

This is likely the reason that I saw some conversations "freeze up" when
using the proxy.

Note the client in `core` does not specify a timeout when making
requests to the Responses API, so the proxy should not, either.

Michael Bolin · 2025-09-27 07:54:32 -07:00

68765214b3

Edit the spacing in shortcuts (#4330 )

<img width="739" height="132" alt="image"
src="https://github.com/user-attachments/assets/e8d40abb-ac41-49a2-abc4-ddc6decef989"
/>

Ahmed Ibrahim · 2025-09-26 22:54:38 -07:00

5c67dc3af1

tui: separator above final agent message (#4324 )

Adds a separator line before the final agent message

<img width="1011" height="884" alt="Screenshot 2025-09-26 at 4 55 01 PM"
src="https://github.com/user-attachments/assets/7c91adbf-6035-4578-8b88-a6921f11bcbc"
/>

Jeremy Rose · 2025-09-26 22:49:59 -07:00

c0960c0f49

fix: set gpt-5-codex medium preset reasoning (#4335 )

Otherwise it shows up as none, see
https://github.com/openai/codex/issues/4321

Thibault Sottiaux · 2025-09-26 22:31:39 -07:00

90c3a5650c

docs: refresh README under codex-rs (#4333 )

Thibault Sottiaux · 2025-09-26 21:45:46 -07:00

a3254696c8

Add "? for shortcuts" (#4316 )

https://github.com/user-attachments/assets/9e61b197-024b-4cbc-b40d-c446b448e759

Ahmed Ibrahim · 2025-09-26 18:24:26 -07:00

2719fdd12a

[MCP] Add experimental support for streamable HTTP MCP servers (#4317 )

This PR adds support for streamable HTTP MCP servers when the
`experimental_use_rmcp_client` is enabled.

To set one up, simply add a new mcp server config with the url:
```
[mcp_servers.figma]
url = "http://127.0.0.1:3845/mcp"
```

It also supports an optional `bearer_token` which will be provided in an
authorization header. The full oauth flow is not supported yet.

The config parsing will throw if it detects that the user mixed and
matched config fields (like command + bearer token or url + env).

The best way to review it is to review `core/src` and then
`rmcp-client/src/rmcp_client.rs` first. The rest is tests and
propagating the `Transport` struct around the codebase.

Example with the Figma MCP:
<img width="5084" height="1614" alt="CleanShot 2025-09-26 at 13 35 40"
src="https://github.com/user-attachments/assets/eaf2771e-df3e-4300-816b-184d7dec5a28"
/>

Gabriel Peal · 2025-09-26 21:24:01 -04:00

3a1be084f9

update composer + user message styling (#4240 )

Changes:

- the composer and user messages now have a colored background that
stretches the entire width of the terminal.
- the prompt character was changed from a cyan `▌` to a bold `›`.
- the "working" shimmer now follows the "dark gray" color of the
terminal, better matching the terminal's color scheme

| Terminal + Background        | Screenshot |
|------------------------------|------------|
| iTerm with dark bg | <img width="810" height="641" alt="Screenshot
2025-09-25 at 11 44 52 AM"
src="https://github.com/user-attachments/assets/1317e579-64a9-4785-93e6-98b0258f5d92"
/> |
| iTerm with light bg | <img width="845" height="540" alt="Screenshot
2025-09-25 at 11 46 29 AM"
src="https://github.com/user-attachments/assets/e671d490-c747-4460-af0b-3f8d7f7a6b8e"
/> |
| iTerm with color bg | <img width="825" height="564" alt="Screenshot
2025-09-25 at 11 47 12 AM"
src="https://github.com/user-attachments/assets/141cda1b-1164-41d5-87da-3be11e6a3063"
/> |
| Terminal.app with dark bg | <img width="577" height="367"
alt="Screenshot 2025-09-25 at 11 45 22 AM"
src="https://github.com/user-attachments/assets/93fc4781-99f7-4ee7-9c8e-3db3cd854fe5"
/> |
| Terminal.app with light bg | <img width="577" height="367"
alt="Screenshot 2025-09-25 at 11 46 04 AM"
src="https://github.com/user-attachments/assets/19bf6a3c-91e0-447b-9667-b8033f512219"
/> |
| Terminal.app with color bg | <img width="577" height="367"
alt="Screenshot 2025-09-25 at 11 45 50 AM"
src="https://github.com/user-attachments/assets/dd7c4b5b-342e-4028-8140-f4e65752bd0b"
/> |

Jeremy Rose · 2025-09-26 16:35:56 -07:00

43b63ccae8

Add turn started/completed events and correct exit code on error (#4309 )

Adds new event for session completed that includes usage. Also ensures
we return 1 on failures.
```
{
  "type": "session.created",
  "session_id": "019987a7-93e7-7b20-9e05-e90060e411ea"
}
{
  "type": "turn.started"
}
...
{
  "type": "turn.completed",
  "usage": {
    "input_tokens": 78913,
    "cached_input_tokens": 65280,
    "output_tokens": 1099
  }
}
```

pakrym-oai · 2025-09-26 16:21:50 -07:00

cc1b21e47f

1013 Commits