codex

Add text element metadata to protocol, app server, and core (#9331 )

The second part of breaking up PR
https://github.com/openai/codex/pull/9116

Summary:

- Add `TextElement` / `ByteRange` to protocol user inputs and user
message events with defaults.
- Thread `text_elements` through app-server v1/v2 request handling and
history rebuild.
- Preserve UI metadata only in user input/events (not `ContentItem`)
while keeping local image attachments in user events for rehydration.

Details:

- Protocol: `UserInput::Text` carries `text_elements`;
`UserMessageEvent` carries `text_elements` + `local_images`.
Serialization includes empty vectors for backward compatibility.
- app-server-protocol: v1 defines `V1TextElement` / `V1ByteRange` in
camelCase with conversions; v2 uses its own camelCase wrapper.
- app-server: v1/v2 input mapping includes `text_elements`; thread
history rebuilds include them.
- Core: user event emission preserves UI metadata while model history
stays clean; history replay round-trips the metadata.

charley-oai · 2026-01-15 17:26:41 -08:00

1fa8350ae7

fix: send non-null content on elicitation Accept (#9196 )

## Summary

- When a user accepts an MCP elicitation request, send `content:
Some(json!({}))` instead of `None`
- MCP servers that use elicitation expect content to be present when
action is Accept
- This matches the expected behavior shown in tests at
`exec-server/tests/common/lib.rs:171`

## Root Cause

In `codex-rs/core/src/codex.rs`, the `resolve_elicitation` function
always sent `content: None`:

```rust
let response = ElicitationResponse {
    action,
    content: None,  // Always None, even for Accept
};
```

## Fix

Send an empty object when accepting:

```rust
let content = match action {
    ElicitationAction::Accept => Some(serde_json::json!({})),
    ElicitationAction::Decline | ElicitationAction::Cancel => None,
};
```

## Test plan

- [x] Code compiles with `cargo check -p codex-core`
- [x] Formatted with `just fmt`
- [ ] Integration test `accept_elicitation_for_prompt_rule` (requires
MCP server binary)

Fixes #9053

Yuvraj Angad Singh · 2026-01-15 14:20:57 -08:00

004a74940a

Revert empty paste image handling (#9318 )

Revert #9049 behavior so empty paste events no longer trigger a
clipboard image read.

Ahmed Ibrahim · 2026-01-15 14:16:09 -08:00

749b58366c

remove needs_follow_up error log (#9272 )

pap-openai · 2026-01-15 21:20:54 +00:00

d886a8646c

[search] allow explicitly disabling web search (#9249 )

moving `web_search` rollout serverside, so need a way to explicitly
disable search + signal eligibility from the client.

- Add `x‑oai‑web‑search‑eligible` header that signifies whether the
request can have web search.
- Only attach the `web_search` tool when the resolved `WebSearchMode` is
`Live` or `Cached`.

sayan-oai · 2026-01-15 11:28:57 -08:00

169201b1b5

Support SKILL.toml file. (#9125 )

We’re introducing a new SKILL.toml to hold skill metadata so Codex can
deliver a richer Skills experience.

Initial focus is the interface block:
```
[interface]
display_name = "Optional user-facing name"
short_description = "Optional user-facing description"
icon_small = "./assets/small-400px.png"
icon_large = "./assets/large-logo.svg"
brand_color = "#3B82F6"
default_prompt = "Optional surrounding prompt to use the skill with"
```

All fields are exposed via the app server API.
display_name and short_description are consumed by the TUI.

xl-openai · 2026-01-15 11:20:04 -08:00

42fa4c237f

Revert recent styling change for input prompt placeholder text (#9307 )

A recent change in commit ccba737d26 modified the styling of the
placeholder text (e.g. "Implement {feature}") in the input box of the
CLI, changing it from non-italic to italic. I think this was likely
unintentional. It results in a bad display appearance on some terminal
emulators, and several users have complained about it.

This change switches back to non-italic styling, restoring the older
behavior.

It addresses #9262

Eric Traut · 2026-01-15 10:58:12 -08:00

5f10548772

nit: clean unified exec background processes (#9304 )

To fix the occurences where the End event is received after the listener
stopped listenning

jif-oai · 2026-01-15 18:34:33 +00:00

da44569fef

chore: better orchestrator prompt (#9301 )

jif-oai · 2026-01-15 18:11:43 +00:00

393a5a0311

revert: remove pre-Landlock bind mounts apply (#9300 )

**Description**

This removes the pre‑Landlock read‑only bind‑mount step from the Linux
sandbox so filesystem restrictions rely solely on Landlock again.
`mounts.rs` is kept in place but left unused. The linux‑sandbox README
is updated to match the new behavior and manual test expectations.

viyatb-oai · 2026-01-15 09:47:57 -08:00

55bda1a0f2

fix(exec): improve stdin prompt decoding (#9151 )

Fixes #8733.

- Read prompt from stdin as raw bytes and decode more helpfully.
- Strip UTF-8 BOM; decode UTF-16LE/UTF-16BE when a BOM is present.
- For other non-UTF8 input, fail with an actionable message (offset +
iconv hint).

Tests: `cargo test -p codex-exec`.

李琼羽 · 2026-01-15 09:29:05 -08:00

b4d240c3ae

Propagate MCP disabled reason (#9207 )

Indicate why MCP servers are disabled when they are disabled by
requirements:

```
➜  codex git:(main) ✗ just codex mcp list
cargo run --bin codex -- "$@"
    Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.27s
     Running `target/debug/codex mcp list`
Name         Command          Args  Env  Cwd  Status                                                                  Auth
docs         docs-mcp         -     -    -    disabled: requirements (MDM com.openai.codex:requirements_toml_base64)  Unsupported
hello_world  hello-world-mcp  -     -    -    disabled: requirements (MDM com.openai.codex:requirements_toml_base64)  Unsupported

➜  codex git:(main) ✗ just c
cargo run --bin codex -- "$@"
    Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.90s
     Running `target/debug/codex`
╭─────────────────────────────────────────────╮
│ >_ OpenAI Codex (v0.0.0)                    │
│                                             │
│ model:     gpt-5.2 xhigh   /model to change │
│ directory: ~/code/codex/codex-rs            │
╰─────────────────────────────────────────────╯

/mcp

🔌  MCP Tools

  • No MCP tools available.

  • docs (disabled)
    • Reason: requirements (MDM com.openai.codex:requirements_toml_base64)

  • hello_world (disabled)
    • Reason: requirements (MDM com.openai.codex:requirements_toml_base64)
```

gt-oai · 2026-01-15 17:24:00 +00:00

f6df1596eb

Changed codex resume --last to honor the current cwd (#9245 )

This PR changes `codex resume --last` to work consistently with `codex
resume`. Namely, it filters based on the cwd when selecting the last
session. It also supports the `--all` modifier as an override.

This addresses #8700

Eric Traut · 2026-01-15 17:05:08 +00:00

ae96a15312

feat: basic tui for event emission (#9209 )

jif-oai · 2026-01-15 15:53:02 +00:00

3fc487e0e0

feat: add interrupt capabilities to send_input (#9276 )

jif-oai · 2026-01-15 14:59:07 +00:00

faeb08c1e1

feat: add agent roles to collab tools (#9275 )

Add `agent_type` parameter to the collab tool `spawn_agent` that
contains a preset to apply on the config when spawning this agent

jif-oai · 2026-01-15 13:33:52 +00:00

05b960671d

feat: collab tools app-server event mapping (#9213 )

jif-oai · 2026-01-15 09:03:26 +00:00

bad4c12b9d

fix: fallback to Landlock-only when user namespaces unavailable and set PR_SET_NO_NEW_PRIVS early (#9250 )

fixes https://github.com/openai/codex/issues/9236

### Motivation
- Prevent sandbox setup from failing when unprivileged user namespaces
are denied so Landlock-only protections can still be applied.
- Ensure `PR_SET_NO_NEW_PRIVS` is set before installing seccomp and
Landlock restrictions to avoid kernel `EPERM`/`LandlockRestrict`
ordering issues.

### Description
- Add `is_permission_denied` helper that detects `EPERM` /
`PermissionDenied` from `CodexErr` to drive fallback logic.
- In `apply_read_only_mounts` skip read-only bind-mount setup and return
`Ok(())` when `unshare_user_and_mount_namespaces()` fails with
permission-denied so Landlock rules can still be installed.
- Add `set_no_new_privs()` and call it from
`apply_sandbox_policy_to_current_thread` before installing seccomp
filters and Landlock rules when disk or network access is restricted.

viyatb-oai · 2026-01-14 22:24:34 -08:00

2259031d64

Add migration_markdown in model_info (#9219 )

Next step would be to clean Model Upgrade in model presets

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: aibrahim-oai <219906144+aibrahim-oai@users.noreply.github.com>

Ahmed Ibrahim · 2026-01-15 01:55:22 +00:00

a09711332a

Add text element metadata to types (#9235 )

Initial type tweaking PR to make the diff of
https://github.com/openai/codex/pull/9116 smaller

This should not change any behavior, just adds some fields to types

charley-oai · 2026-01-14 16:41:50 -08:00

4a9c2bcc5a

fix: increase timeout for release builds from 30 to 60 minutes (#9242 )

Windows builds have been tripping the 30 minute timeout. For sure, we
need to improve this, but as a quick fix, let's just increase the
timeout.

Perhaps we should switch to `lto = "thin"` for release builds, at least
for Windows:


https://github.com/openai/codex/blob/3728db11b87cb8490bcf6bf2cdf0e13dcfb0c28b/codex-rs/Cargo.toml#L288

See https://doc.rust-lang.org/cargo/reference/profiles.html#lto for
details.

Michael Bolin · 2026-01-15 00:38:25 +00:00

2a68b74b9b

fix: eliminate unnecessary clone() for each SSE event (#9238 )

Given how many SSE events we get, seems worth fixing.

Michael Bolin · 2026-01-15 00:06:09 +00:00

3728db11b8

fix: correct linux sandbox uid/gid mapping after unshare (#9234 )

fixes https://github.com/openai/codex/issues/9233
## Summary
- capture effective uid/gid before unshare for user namespace maps
- pass captured ids into uid/gid map writer

## Testing
- just fmt
- just fix -p codex-linux-sandbox
- cargo test -p codex-linux-sandbox

viyatb-oai · 2026-01-14 15:35:53 -08:00

e59e7d163d

upgrade runners in rust-ci.yml to use the larger runners (#9106 )

Upgrades runners in rust-ci.yaml to larger runners

ubuntu-24.04 (x64 and arm64) -> custom 16 core ubuntu 24.04 runners
macos-14 -> mac0s-15-xlarge
[TODO] windows (x64 and arm64) -> custom 16 core windows runners

willwang-openai · 2026-01-14 15:22:59 -08:00

71a2973fd9

Updated issue template to ask for terminal emulator (#9231 )

Co-authored-by: Josh McKinney <joshka@openai.com>

Eric Traut · 2026-01-14 23:00:15 +00:00

24b88890cb

add WebSearchMode enum (#9216 )

### What
Add `WebSearchMode` enum (disabled, cached live, defaults to cached) to
config + V2 protocol. This enum takes precedence over legacy flags:
`web_search_cached`, `web_search_request`, and `tools.web_search`.

Keep `--search` as live.

### Tests
Added tests

sayan-oai · 2026-01-14 12:51:42 -08:00

5e426ac270

fix(tui): disable double-press quit shortcut (#9220 )

Disables the default Ctrl+C/Ctrl+D double-press quit UX (keeps the code
path behind a const) while we rethink the quit/interrupt flow.

Tests:
- just fmt
- cargo clippy --fix --all-features --tests --allow-dirty --allow-no-vcs
-p codex-tui
- cargo test -p codex-tui --lib

Josh McKinney · 2026-01-14 20:28:18 +00:00

27da8a68d3

fix(tui2): align Steer submit keys (#9218 )

- Remove legacy Ctrl+K queuing in tui2; Tab is the queue key.
- Make Enter queue when Steer is disabled and submit immediately when
Steer is enabled.
- Add Steer keybinding docs on both tui and tui2 chat composers.

Josh McKinney · 2026-01-14 19:35:55 +00:00

0471ddbe74

Rename hierarchical_agents to child_agents_md (#9215 )

Clearer name

pakrym-oai · 2026-01-14 19:14:24 +00:00

e6d2ef432d

feat: adding piped process to replace PTY when needed (#8797 )

jif-oai · 2026-01-14 18:44:04 +00:00

577e1fd1b2

s/mcp_server_requirements/mcp_servers (#9212 )

A simple `s/mcp_server_requirements/mcp_servers/g` for an unreleased
feature. @bolinfest correctly pointed out, it's already in
`requirements.toml` so the `_requirements` is redundant.

gt-oai · 2026-01-14 18:41:52 +00:00

fe1e0da102

Log headers in trace mode (#9214 )

To enable:

```
export RUST_LOG="warn,codex_=trace"
```

Sample: 
```
Request completed method=POST url=https://chatgpt.com/backend-api/codex/responses status=200 OK headers={"date": "Wed, 14 Jan 2026 18:21:21 GMT", "transfer-encoding": "chunked", "connection": "keep-alive", "x-codex-plan-type": "business", "x-codex-primary-used-percent": "3", "x-codex-secondary-used-percent": "6", "x-codex-primary-window-minutes": "300", "x-codex-primary-over-secondary-limit-percent": "0", "x-codex-secondary-window-minutes": "10080", "x-codex-primary-reset-after-seconds": "9944", "x-codex-secondary-reset-after-seconds": "171121", "x-codex-primary-reset-at": "1768424824", "x-codex-secondary-reset-at": "1768586001", "x-codex-credits-has-credits": "False", "x-codex-credits-balance": "", "x-codex-credits-unlimited": "False", "x-models-etag": "W/\"7a7ffbc83c159dbd7a2a73aaa9c91b7a\"", "x-oai-request-id": "ffedcd30-6d8a-4c4d-be10-8ebb23c142c8", "x-envoy-upstream-service-time": "417", "x-openai-proxy-wasm": "v0.1", "cf-cache-status": "DYNAMIC", "set-cookie": "__cf_bm=xFKeaMbWNbKO5ZX.K5cJBhj34OA1QvnF_3nkdMThjlA-1768414881-1.0.1.1-uLpsE_BDkUfcmOMaeKVQmv_6_2ytnh_R3lO_il5N5K3YPQEkBo0cOMTdma6bK0Gz.hQYcIesFwKIJht1kZ9JKqAYYnjgB96hF4.sii2U3cE; path=/; expires=Wed, 14-Jan-26 18:51:21 GMT; domain=.chatgpt.com; HttpOnly; Secure; SameSite=None", "report-to": "{\"endpoints\":[{\"url\":\"https:\/\/a.nel.cloudflare.com\/report\/v4?s=4Kc7g4zUhKkIm3xHuB6ba4jyIUqqZ07ETwIPAYQASikRjA8JesbtUKDP9tSrZ5PnzWldaiSz5dZVQFI579LEsCMlMUSelTvmyQ8j4FbFDawi%2FprWZ5iRePiaSalr\"}],\"group\":\"cf-nel\",\"max_age\":604800}", "nel": "{\"success_fraction\":0.01,\"report_to\":\"cf-nel\",\"max_age\":604800}", "strict-transport-security": "max-age=31536000; includeSubDomains; preload", "x-content-type-options": "nosniff", "cross-origin-opener-policy": "same-origin-allow-popups", "referrer-policy": "strict-origin-when-cross-origin", "server": "cloudflare", "cf-ray": "9bdf270adc7aba3a-SEA"} version=HTTP/1.1
```

pakrym-oai · 2026-01-14 18:38:12 +00:00

e958d0337e

Get model on session configured (#9191 )

- Don't try to precompute model unless you know it from `config`
- Block `/model` on session configured
- Queue messages until session configured
- show "loading" in status until session configured

Ahmed Ibrahim · 2026-01-14 10:20:41 -08:00

8e937fbba9

fix: Emit response.completed immediately for Responses SSE (#9170 )

we see windows test failures like this:
https://github.com/openai/codex/actions/runs/20930055601/job/60138344260.

The issue is that SSE connections sometimes remain open after the
completion event esp. for windows. We should emit the completion event
and return immediately. this is consistent with the protocol:

> The Model streams responses back in an SSE, which are collected until
"completed" message and the SSE terminates

from
https://github.com/openai/codex/blob/dev/cc/fix-windows-test/codex-rs/docs/protocol_v1.md#L37.

this helps us achieve parity with responses websocket logic here:
https://github.com/openai/codex/blob/dev/cc/fix-windows-test/codex-rs/codex-api/src/endpoint/responses_websocket.rs#L220-L227.

Celia Chen · 2026-01-14 10:05:00 -08:00

02f67bace8

feat: add collab prompt (#9208 )

Adding a prompt for collab tools. This is only for internal use and the
prompt won't be gated for now as it is not stable yet.

The goal of this PR is to provide the tool required to iterate on the
prompt

jif-oai · 2026-01-14 09:58:15 -08:00

3d322fa9d8

feat: emit events around collab tools (#9095 )

Emit the following events around the collab tools. On the `app-server`
this will be under `item/started` and `item/completed`
```
#[derive(Debug, Clone, Deserialize, Serialize, PartialEq, JsonSchema, TS)]
pub struct CollabAgentSpawnBeginEvent {
    /// Identifier for the collab tool call.
    pub call_id: String,
    /// Thread ID of the sender.
    pub sender_thread_id: ThreadId,
    /// Initial prompt sent to the agent. Can be empty to prevent CoT leaking at the
    /// beginning.
    pub prompt: String,
}

#[derive(Debug, Clone, Deserialize, Serialize, PartialEq, JsonSchema, TS)]
pub struct CollabAgentSpawnEndEvent {
    /// Identifier for the collab tool call.
    pub call_id: String,
    /// Thread ID of the sender.
    pub sender_thread_id: ThreadId,
    /// Thread ID of the newly spawned agent, if it was created.
    pub new_thread_id: Option<ThreadId>,
    /// Initial prompt sent to the agent. Can be empty to prevent CoT leaking at the
    /// beginning.
    pub prompt: String,
    /// Last known status of the new agent reported to the sender agent.
    pub status: AgentStatus,
}

#[derive(Debug, Clone, Deserialize, Serialize, PartialEq, JsonSchema, TS)]
pub struct CollabAgentInteractionBeginEvent {
    /// Identifier for the collab tool call.
    pub call_id: String,
    /// Thread ID of the sender.
    pub sender_thread_id: ThreadId,
    /// Thread ID of the receiver.
    pub receiver_thread_id: ThreadId,
    /// Prompt sent from the sender to the receiver. Can be empty to prevent CoT
    /// leaking at the beginning.
    pub prompt: String,
}

#[derive(Debug, Clone, Deserialize, Serialize, PartialEq, JsonSchema, TS)]
pub struct CollabAgentInteractionEndEvent {
    /// Identifier for the collab tool call.
    pub call_id: String,
    /// Thread ID of the sender.
    pub sender_thread_id: ThreadId,
    /// Thread ID of the receiver.
    pub receiver_thread_id: ThreadId,
    /// Prompt sent from the sender to the receiver. Can be empty to prevent CoT
    /// leaking at the beginning.
    pub prompt: String,
    /// Last known status of the receiver agent reported to the sender agent.
    pub status: AgentStatus,
}

#[derive(Debug, Clone, Deserialize, Serialize, PartialEq, JsonSchema, TS)]
pub struct CollabWaitingBeginEvent {
    /// Thread ID of the sender.
    pub sender_thread_id: ThreadId,
    /// Thread ID of the receiver.
    pub receiver_thread_id: ThreadId,
    /// ID of the waiting call.
    pub call_id: String,
}

#[derive(Debug, Clone, Deserialize, Serialize, PartialEq, JsonSchema, TS)]
pub struct CollabWaitingEndEvent {
    /// Thread ID of the sender.
    pub sender_thread_id: ThreadId,
    /// Thread ID of the receiver.
    pub receiver_thread_id: ThreadId,
    /// ID of the waiting call.
    pub call_id: String,
    /// Last known status of the receiver agent reported to the sender agent.
    pub status: AgentStatus,
}

#[derive(Debug, Clone, Deserialize, Serialize, PartialEq, JsonSchema, TS)]
pub struct CollabCloseBeginEvent {
    /// Identifier for the collab tool call.
    pub call_id: String,
    /// Thread ID of the sender.
    pub sender_thread_id: ThreadId,
    /// Thread ID of the receiver.
    pub receiver_thread_id: ThreadId,
}

#[derive(Debug, Clone, Deserialize, Serialize, PartialEq, JsonSchema, TS)]
pub struct CollabCloseEndEvent {
    /// Identifier for the collab tool call.
    pub call_id: String,
    /// Thread ID of the sender.
    pub sender_thread_id: ThreadId,
    /// Thread ID of the receiver.
    pub receiver_thread_id: ThreadId,
    /// Last known status of the receiver agent reported to the sender agent before
    /// the close.
    pub status: AgentStatus,
}
```

jif-oai · 2026-01-14 17:55:57 +00:00

6a939ed7a4

tui: double-press Ctrl+C/Ctrl+D to quit (#8936 )

## Problem

Codex’s TUI quit behavior has historically been easy to trigger
accidentally and hard to reason
about.

- `Ctrl+C`/`Ctrl+D` could terminate the UI immediately, which is a
common key to press while trying
  to dismiss a modal, cancel a command, or recover from a stuck state.
- “Quit” and “shutdown” were not consistently separated, so some exit
paths could bypass the
  shutdown/cleanup work that should run before the process terminates.

This PR makes quitting both safer (harder to do by accident) and more
uniform across quit
gestures, while keeping the shutdown-first semantics explicit.

## Mental model

After this change, the system treats quitting as a UI request that is
coordinated by the app
layer.

- The UI requests exit via `AppEvent::Exit(ExitMode)`.
- `ExitMode::ShutdownFirst` is the normal user path: the app triggers
`Op::Shutdown`, continues
rendering while shutdown runs, and only ends the UI loop once shutdown
has completed.
- `ExitMode::Immediate` exists as an escape hatch (and as the
post-shutdown “now actually exit”
signal); it bypasses cleanup and should not be the default for
user-triggered quits.

User-facing quit gestures are intentionally “two-step” for safety:

- `Ctrl+C` and `Ctrl+D` no longer exit immediately.
- The first press arms a 1-second window and shows a footer hint (“ctrl
+ <key> again to quit”).
- Pressing the same key again within the window requests a
shutdown-first quit; otherwise the
  hint expires and the next press starts a fresh window.

Key routing remains modal-first:

- A modal/popup gets first chance to consume `Ctrl+C`.
- If a modal handles `Ctrl+C`, any armed quit shortcut is cleared so
dismissing a modal cannot
  prime a subsequent `Ctrl+C` to quit.
- `Ctrl+D` only participates in quitting when the composer is empty and
no modal/popup is active.

The design doc `docs/exit-confirmation-prompt-design.md` captures the
intended routing and the
invariants the UI should maintain.

## Non-goals

- This does not attempt to redesign modal UX or make modals uniformly
dismissible via `Ctrl+C`.
It only ensures modals get priority and that quit arming does not leak
across modal handling.
- This does not introduce a persistent confirmation prompt/menu for
quitting; the goal is to keep
  the exit gesture lightweight and consistent.
- This does not change the semantics of core shutdown itself; it changes
how the UI requests and
  sequences it.

## Tradeoffs

- Quitting via `Ctrl+C`/`Ctrl+D` now requires a deliberate second
keypress, which adds friction for
  users who relied on the old “instant quit” behavior.
- The UI now maintains a small time-bounded state machine for the armed
shortcut, which increases
  complexity and introduces timing-dependent behavior.

This design was chosen over alternatives (a modal confirmation prompt or
a long-lived “are you
sure” state) because it provides an explicit safety barrier while
keeping the flow fast and
keyboard-native.

## Architecture

- `ChatWidget` owns the quit-shortcut state machine and decides when a
quit gesture is allowed
  (idle vs cancellable work, composer state, etc.).
- `BottomPane` owns rendering and local input routing for modals/popups.
It is responsible for
consuming cancellation keys when a view is active and for
showing/expiring the footer hint.
- `App` owns shutdown sequencing: translating
`AppEvent::Exit(ShutdownFirst)` into `Op::Shutdown`
  and only terminating the UI loop when exit is safe.

This keeps “what should happen” decisions (quit vs interrupt vs ignore)
in the chat/widget layer,
while keeping “how it looks and which view gets the key” in the
bottom-pane layer.

## Observability

You can tell this is working by running the TUIs and exercising the quit
gestures:

- While idle: pressing `Ctrl+C` (or `Ctrl+D` with an empty composer and
no modal) shows a footer
hint for ~1 second; pressing again within that window exits via
shutdown-first.
- While streaming/tools/review are active: `Ctrl+C` interrupts work
rather than quitting.
- With a modal/popup open: `Ctrl+C` dismisses/handles the modal (if it
chooses to) and does not
arm a quit shortcut; a subsequent quick `Ctrl+C` should not quit unless
the user re-arms it.

Failure modes are visible as:

- Quits that happen immediately (no hint window) from `Ctrl+C`/`Ctrl+D`.
- Quits that occur while a modal is open and consuming `Ctrl+C`.
- UI termination before shutdown completes (cleanup skipped).

## Tests

- Updated/added unit and snapshot coverage in `codex-tui` and
`codex-tui2` to validate:
  - The quit hint appears and expires on the expected key.
- Double-press within the window triggers a shutdown-first quit request.
- Modal-first routing prevents quit bypass and clears any armed shortcut
when a modal consumes
    `Ctrl+C`.

These tests focus on the UI-level invariants and rendered output; they
do not attempt to validate
real terminal key-repeat timing or end-to-end process shutdown behavior.

---
Screenshot:
<img width="912" height="740" alt="Screenshot 2026-01-13 at 1 05 28 PM"
src="https://github.com/user-attachments/assets/18f3d22e-2557-47f2-a369-ae7a9531f29f"
/>

Josh McKinney · 2026-01-14 17:42:52 +00:00

4283a7432b

Use current model for review (#9179 )

Instead of having a hard-coded default review model, use the current
model for running `/review` unless one is specified in the config.

Also inherit current reasoning effort

pakrym-oai · 2026-01-14 08:59:41 -08:00

92472e7baa

feat: add support for read-only bind mounts in the linux sandbox (#9112 )

### Motivation

- Landlock alone cannot prevent writes to sensitive in-repo files like
`.git/` when the repo root is writable, so explicit mount restrictions
are required for those paths.
- The sandbox must set up any mounts before calling Landlock so Landlock
can still be applied afterwards and the two mechanisms compose
correctly.

### Description

- Add a new `linux-sandbox` helper `apply_read_only_mounts` in
`linux-sandbox/src/mounts.rs` that: unshares namespaces, maps uids/gids
when required, makes mounts private, bind-mounts targets, and remounts
them read-only.
- Wire the mount step into the sandbox flow by calling
`apply_read_only_mounts(...)` before network/seccomp and before applying
Landlock rules in `linux-sandbox/src/landlock.rs`.

viyatb-oai · 2026-01-14 08:30:46 -08:00

e1447c3009

feat: add auto refresh on thread listeners (#9105 )

This PR is in the scope of multi-agent work. 

An agent (=thread) can now spawn other agents. Those other agents are
not attached to any clients. We need a way to make sure that the clients
are aware of the new threads to look at (for approval for example). This
PR adds a channel to the `ThreadManager` that pushes the ID of those
newly created agents such that the client (here the app-server) can also
subscribe to those ones.

jif-oai · 2026-01-14 16:26:01 +00:00

bcd7858ced

chore: clamp min yield time for empty write_stdin (#9156 )

After evals, 0 impact on performance

jif-oai · 2026-01-14 16:25:40 +00:00

32b1795ff4

Render exec output deltas inline (#9194 )

Ahmed Ibrahim · 2026-01-14 08:11:12 -08:00

bdae0035ec

fix: drop double waiting header in TUI (#9145 )

jif-oai · 2026-01-14 09:52:34 +00:00

7532f34699

feat: only source shell snapshot if the file exists (#9197 )

jif-oai · 2026-01-14 01:28:25 -08:00

bc6d9ef6fc

feat: return an error if the image sent by the user is a bad image (#9146 )

## Before
When we detect an `InvalidImageRequest`, we replace the image by a
placeholder and keep going

## Now
In such `InvalidImageRequest`, we check if the image is due to a user
message or a tool call output. For tool call output we still replace it
with a placeholder to avoid breaking the agentic loop bu tif this is
because of a user message, we send an error to the user

jif-oai · 2026-01-14 09:07:45 +00:00

dc3deaa3e7

fix: shell snapshot clean-up (#9155 )

Clean all shell snapshot files corresponding to sessions that have not
been updated in 7 days
Those files should never leak. The only known cases were it can leak are
during non graceful interrupt of the process (`kill -9, `panic`, OS
crash, ...)

jif-oai · 2026-01-14 09:05:46 +00:00

6fbb89e858

feat: add sourcing of rc files to shell snapshot (#9150 )

jif-oai · 2026-01-14 08:58:10 +00:00

258fc4b401

change api default model (#9188 )

Ahmed Ibrahim · 2026-01-13 22:33:34 -08:00

b9ff4ec830

feat: add threadId to MCP server messages (#9192 )

This favors `threadId` instead of `conversationId` so we use the same
terms as https://developers.openai.com/codex/sdk/.

To test the local build:

```
cd codex-rs
cargo build --bin codex
npx -y @modelcontextprotocol/inspector ./target/debug/codex mcp-server
```

I sent:

```json
{
  "method": "tools/call",
  "params": {
    "name": "codex",
    "arguments": {
      "prompt": "favorite ls option?"
    },
    "_meta": {
      "progressToken": 0
    }
  }
}
```

and got:

```json
{
  "content": [
    {
      "type": "text",
      "text": "`ls -lah` (or `ls -alh`) — long listing, includes dotfiles, human-readable sizes."
    }
  ],
  "structuredContent": {
    "threadId": "019bbb20-bff6-7130-83aa-bf45ab33250e"
  }
}
```

and successfully used the `threadId` in the follow-up with the
`codex-reply` tool call:

```json
{
  "method": "tools/call",
  "params": {
    "name": "codex-reply",
    "arguments": {
      "prompt": "what is the long versoin",
      "threadId": "019bbb20-bff6-7130-83aa-bf45ab33250e"
    },
    "_meta": {
      "progressToken": 1
    }
  }
}
```

whose response also has the `threadId`:

```json
{
  "content": [
    {
      "type": "text",
      "text": "Long listing is `ls -l` (adds permissions, owner/group, size, timestamp)."
    }
  ],
  "structuredContent": {
    "threadId": "019bbb20-bff6-7130-83aa-bf45ab33250e"
  }
}
```

Fixes https://github.com/openai/codex/issues/3712.

Michael Bolin · 2026-01-13 22:14:41 -08:00

0c09dc3c03

chore: clarify default shell for unified_exec (#8997 )

The description of the `shell` arg for `exec_command` states the default
is `/bin/bash`, but AFAICT it's the user's default shell.

Default logic
[here](https://github.com/openai/codex/blob/2a06d64bc996e4d848b95285700b195c2852a42f/codex-rs/core/src/tools/handlers/unified_exec.rs#L123).

EDIT: #9004 has an alternative where we inform the model of the default
shell itself.

sayan-oai · 2026-01-13 21:37:41 -08:00

5675af5190

3718 Commits