## Summary
- Reduced repeated approvals for equivalent wrapper commands and fixed
execpolicy matching for heredoc-style shell invocations, with minimal
behavior change and fail-closed defaults.
## Fixes
1. Canonicalized approval matching for wrappers so equivalent commands
map to the same approval intent.
2. Added heredoc-aware prefix extraction for execpolicy so commands like
`python3 <<'PY' ... PY` match rules such as `prefix_rule(["python3"],
...)`.
3. Kept fallback behavior conservative: if parsing is ambiguous,
existing prompt behavior is preserved.
## Edge Cases Covered
- Wrapper path/name differences: `/bin/bash` vs `bash`, `/bin/zsh` vs
`zsh`.
- Shell modes: `-c` and `-lc`.
- Heredoc forms: quoted delimiter (`<<'PY'`) and unquoted delimiter (`<<
PY`).
- Multi-command heredoc scripts are rejected by the fallback
- Non-heredoc redirections (`>`, etc.) are not treated as heredoc prefix
matches.
- Complex scripts still fall back to prior behavior rather than
expanding permissions.
---------
Co-authored-by: Dylan Hurd <dylan.hurd@openai.com>
- Replace image blocks in MCP tool results with a text placeholder when
the active model does not accept image input.
- Add an e2e rmcp test to verify sanitized tool output is what gets sent
back to the model.
- Keep `view_image` in the advertised tool list for all models.
- Return a clear error when the current model does not support image
inputs, and cover it with a unit test.
The `TODO` in `core/src/seatbelt.rs` claimed that `apply_patch` still needed to honor `SandboxPolicy`. That was true when the comment was added, but it is no longer true.
Analysis:
- The TODO was introduced in #1762, when seatbelt code was split out of `exec.rs`.
- `apply_patch` sandboxing was later implemented in #1705.
- Today, `apply_patch` calls are routed through the tool orchestrator and delegated to `ApplyPatchRuntime`, which executes via `execute_env()` using the active sandbox attempt policy.
- On macOS, the sandbox transform path for that execution still builds seatbelt args with `create_seatbelt_command_args(command, policy, sandbox_policy_cwd)`, so the same `SandboxPolicy` gates `apply_patch` writes and network behavior.
Because this behavior is already enforced, the TODO is stale and removing it avoids implying missing sandbox coverage where none exists.
No functional behavior change; comment-only cleanup.
## Summary
- keep wiremock MockServer handles alive through async assertions in
remote model suite tests
- assert /models request count in remote_models_hide_picker_only_models
- use a slightly higher parallel timing threshold on aarch64 while
keeping existing x86 threshold
## Validation
- just fmt
- targeted tests:
- cargo test -p codex-core --test all
suite::remote_models::remote_models_merge_replaces_overlapping_model --
--exact
- cargo test -p codex-core --test all
suite::remote_models::remote_models_hide_picker_only_models -- --exact
- cargo test -p codex-core --test all
suite::tool_parallelism::shell_tools_run_in_parallel -- --exact
- soak loop: 40 iterations of all three targeted tests
## Notes
- cargo test -p codex-core has one unrelated local-env failure in
shell_snapshot::tests::try_new_creates_and_deletes_snapshot_file from
exported certificate env content in this workspace.
- local bazel test //codex-rs/core:core-all-test failed to build due
missing rust-objcopy in this host toolchain.
https://github.com/openai/codex/pull/11318 introduced logic to publish
platform artifacts as separate npm packages (for example,
`@openai/codex-darwin-arm64`, `@openai/codex-linux-x64`, etc.). That
requires provisioning and maintaining multiple package entries in npm,
which we want to avoid.
We still need to keep the package-size mitigation (platform-specific
payloads), but we want that layout to live under a single npm package
namespace (`@openai/codex`) using dist-tags.
We also need to preserve pre-release workflows where users install
`@openai/codex@alpha` and get platform-appropriate binaries.
Additionally, we want GitHub Release assets to group Codex npm tarballs
together, so platform tarballs should follow the same `codex-npm-*`
filename prefix as the main Codex tarball.
## Release Strategy (New Scheme)
We publish **one npm package name for Codex binaries** (`@openai/codex`)
and use **dist-tags** to select platform-specific payloads. This avoids
creating separate platform package names while keeping the package size
split by platform.
### What gets published
#### Mainline release (`x.y.z`)
- `@openai/codex@latest` (meta package)
- `@openai/codex@darwin-arm64`
- `@openai/codex@darwin-x64`
- `@openai/codex@linux-arm64`
- `@openai/codex@linux-x64`
- `@openai/codex@win32-arm64`
- `@openai/codex@win32-x64`
- `@openai/codex-responses-api-proxy@latest`
- `@openai/codex-sdk@latest`
#### Alpha release (`x.y.z-alpha.N`)
- `@openai/codex@alpha` (meta package)
- `@openai/codex@alpha-darwin-arm64`
- `@openai/codex@alpha-darwin-x64`
- `@openai/codex@alpha-linux-arm64`
- `@openai/codex@alpha-linux-x64`
- `@openai/codex@alpha-win32-arm64`
- `@openai/codex@alpha-win32-x64`
- `@openai/codex-responses-api-proxy@alpha`
- `@openai/codex-sdk@alpha`
As an example, the `package.json` for `@openai/codex@alpha` (using
`0.99.0-alpha.17` as the `version`) would be:
```
{
"name": "@openai/codex",
"version": "0.99.0-alpha.17",
"license": "Apache-2.0",
"bin": {
"codex": "bin/codex.js"
},
"type": "module",
"engines": {
"node": ">=16"
},
"files": [
"bin"
],
"repository": {
"type": "git",
"url": "git+https://github.com/openai/codex.git",
"directory": "codex-cli"
},
"packageManager": "pnpm@10.28.2+sha512.41872f037ad22f7348e3b1debbaf7e867cfd448f2726d9cf74c08f19507c31d2c8e7a11525b983febc2df640b5438dee6023ebb1f84ed43cc2d654d2bc326264",
"optionalDependencies": {
"@openai/codex-linux-x64": "npm:@openai/codex@0.99.0-alpha.17-linux-x64",
"@openai/codex-linux-arm64": "npm:@openai/codex@0.99.0-alpha.17-linux-arm64",
"@openai/codex-darwin-x64": "npm:@openai/codex@0.99.0-alpha.17-darwin-x64",
"@openai/codex-darwin-arm64": "npm:@openai/codex@0.99.0-alpha.17-darwin-arm64",
"@openai/codex-win32-x64": "npm:@openai/codex@0.99.0-alpha.17-win32-x64",
"@openai/codex-win32-arm64": "npm:@openai/codex@0.99.0-alpha.17-win32-arm64"
}
}
```
Note that the keys in `optionalDependencies` have "clean" names, but the
values have the tag embedded.
### Important note
**Note:** Because we never created the new platform package names on npm
(for example,
`@openai/codex-darwin-arm64`) since #11318 landed, there are no extra
npm packages to clean up.
## What changed
### 1. Stage platform tarballs as `@openai/codex` with platform-specific
versions
File: `codex-cli/scripts/build_npm_package.py`
- Added `CODEX_NPM_NAME = "@openai/codex"` and platform metadata
`npm_tag` values:
- `darwin-arm64`, `darwin-x64`, `linux-arm64`, `linux-x64`,
`win32-arm64`, `win32-x64`
- For platform package staging (`codex-<platform>` inputs), switched
generated `package.json` from:
- `name = @openai/codex-<platform>`
to:
- `name = @openai/codex`
- Added `compute_platform_package_version(version, platform_tag)` so
platform tarballs have unique
versions (`<release-version>-<platform-tag>`), which is required because
npm forbids re-publishing
the same `name@version`.
### 2. Point meta package optional dependencies at dist-tags on
`@openai/codex`
File: `codex-cli/scripts/build_npm_package.py`
- Updated `optionalDependencies` generation for the main `codex` package
to use npm alias syntax:
- key remains alias package name (for example,
`@openai/codex-darwin-arm64`) so runtime lookup behavior is unchanged
- value now resolves to `@openai/codex` by dist-tag
- Stable releases emit tags like `npm:@openai/codex@darwin-arm64`.
- Alpha releases (`x.y.z-alpha.N`) emit tags like
`npm:@openai/codex@alpha-darwin-arm64`.
### 3. Publish with per-tarball dist-tags in release CI
File: `.github/workflows/rust-release.yml`
- Reworked npm publish logic to derive the publish tag per tarball
filename:
- platform tarballs publish with `<platform>` tags for stable releases
- platform tarballs publish with `alpha-<platform>` tags for alpha
releases
- top-level tarballs (`codex`, `codex-responses-api-proxy`, `codex-sdk`)
continue using
the existing channel tag policy (`latest` implicit for stable, `alpha`
for alpha)
- Added fail-fast behavior for unexpected tarball names to avoid silent
mispublishes.
### 4. Normalize Codex platform tarball filenames for GitHub Release
grouping
Files: `scripts/stage_npm_packages.py`,
`.github/workflows/rust-release.yml`
- Renamed staged platform tarball filenames from:
- `codex-linux-<arch>-npm-<version>.tgz`
- `codex-darwin-<arch>-npm-<version>.tgz`
- `codex-win32-<arch>-npm-<version>.tgz`
- To:
- `codex-npm-linux-<arch>-<version>.tgz`
- `codex-npm-darwin-<arch>-<version>.tgz`
- `codex-npm-win32-<arch>-<version>.tgz`
This keeps all Codex npm artifacts grouped under a common `codex-npm-`
prefix in GitHub Releases.
### 5. Documentation update
File: `codex-cli/scripts/README.md`
- Updated staging docs to clarify that platform-native variants are
published as dist-tagged
`@openai/codex` artifacts rather than separate npm package names.
## Resulting behavior
- Mainline release:
- `@openai/codex@latest` resolves the meta package
- meta package optional dependencies resolve
`@openai/codex@<platform-tag>`
- Alpha release:
- users can continue installing `@openai/codex@alpha`
- alpha meta package optional dependencies resolve
`@openai/codex@alpha-<platform-tag>`
- Release assets:
- Codex npm tarballs share `codex-npm-` prefix for cleaner grouping in
GitHub Releases
This preserves platform-specific payload distribution while avoiding
separate npm package names and
improves release-asset discoverability.
## Validation notes
- Verified staged `package.json` output for stable and alpha meta
packages includes expected alias targets.
- Verified staged platform package manifests are `name=@openai/codex`
with unique platform-suffixed versions.
- Verified publish tag derivation maps renamed platform tarballs to
expected stable and alpha dist-tags.
During thread/fork, the new rollout includes the fork’s own session_meta
plus copied history that can contain older session_meta entries from the
source thread. thread/list was overwriting metadata on later
session_meta lines, so a fork could be reported with the source thread’s
thread_id. This fix only uses the first session_meta, so the fork keeps
its own ID.
This removes overly directed language about how the model should behave
when it's in `approval_policy=never` mode.
---------
Co-authored-by: Dylan Hurd <dylan.hurd@openai.com>
## Summary
- keep cursor at end-of-line after Up/Down history recall
- allow continued history navigation when recalled text cursor is at
start or end boundary
- add regression tests and document the history cursor contract in
composer docs
## Testing
- just fmt
- cargo test -p codex-tui --lib
history_navigation_leaves_cursor_at_end_of_line
- cargo test -p codex-tui --lib
should_handle_navigation_when_cursor_is_at_line_boundaries
- cargo test -p codex-tui *(fails in existing integration test
`suite::no_panic_on_startup::malformed_rules_should_not_panic` because
`target/debug/codex` is not present in this environment)*
## Summary
- remove redundant user message wait that could time out and cause
flakiness
- rely on the existing turn-complete wait to ensure the follow-up
request is observed
## Testing
- Not run (not requested)
Summary
- move `core/src/hooks` implementation into a new `codex-hooks` crate
with its own manifest
- update `codex-rs` workspace and `codex-core` crate to depend on the
extracted `hooks` crate and wire up the shared APIs
- ensure references, modules, and lockfile reflect the new crate layout
Testing
- Not run (not requested)
## Align with the new phase-1 design
Basically we know run phase 1 in parallel by considering:
* Max 64 rollouts
* Max 1 month old
* Consider the most recent first
This PR also adds stronger parallelization capabilities by detecting
stale jobs, retry policies, ownership of computation to prevent double
computations etc etc
As of this PR, `SessionServices` retains a
`Option<StartedNetworkProxy>`, if appropriate.
Now the `network` field on `Config` is `Option<NetworkProxySpec>`
instead of `Option<NetworkProxy>`.
Over in `Session::new()`, we invoke `NetworkProxySpec::start_proxy()` to
create the `StartedNetworkProxy`, which is a new struct that retains the
`NetworkProxy` as well as the `NetworkProxyHandle`. (Note that `Drop` is
implemented for `NetworkProxyHandle` to ensure the proxies are shutdown
when it is dropped.)
The `NetworkProxy` from the `StartedNetworkProxy` is threaded through to
the appropriate places.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/11207).
* #11285
* __->__ #11207
Codex may run many per-thread proxy instances, so hardcoded proxy ports
are brittle and conflict-prone. The previous "ephemeral" approach still
had a race: `build()` read `local_addr()` from temporary listeners and
dropped them before `run()` rebound the ports. That left a
[TOCTOU](https://en.wikipedia.org/wiki/Time-of-check_to_time-of-use)
window where the OS (or another process) could reuse the same port,
causing intermittent `EADDRINUSE` and partial proxy startup.
Change the managed proxy path to reserve real listener sockets up front
and keep them alive until startup:
- add `ReservedListeners` on `NetworkProxy` to hold HTTP/SOCKS/admin std
listeners allocated during `build()`
- in managed mode, bind `127.0.0.1:0` for each listener and carry those
bound sockets into `run()` instead of rebinding by address later
- add `run_*_with_std_listener` entry points for HTTP, SOCKS5, and admin
servers so `run()` can start services from already-reserved sockets
- keep static/configured ports only when `managed_by_codex(false)`,
including explicit `socks_addr` override support
- remove fallback synthetic port allocation and add tests for managed
ephemeral loopback binding and unmanaged configured-port behavior
This makes managed startup deterministic, avoids port collisions, and
preserves the intended distinction between Codex-managed ephemeral ports
and externally managed fixed ports.
The dynamic model refresh feature (`https://api.openai.com/v1/models`
endpoint) is currently gated on a runtime check for an auth method other
than API Key. It should be gated on a check specifically for ChatGPT
Auth because some custom model providers (e.g. for local models) use no
auth mechanism. A call to `self.auth_manager.auth_mode()` will return
`None` in this case.
Addresses #11213
Bumps [regex](https://github.com/rust-lang/regex) from 1.12.2 to 1.12.3.
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/rust-lang/regex/blob/master/CHANGELOG.md">regex's
changelog</a>.</em></p>
<blockquote>
<h1>1.12.3 (2025-02-03)</h1>
<p>This release excludes some unnecessary things from the archive
published to
crates.io. Specifically, fuzzing data and various shell scripts are now
excluded. If you run into problems, please file an issue.</p>
<p>Improvements:</p>
<ul>
<li><a
href="https://redirect.github.com/rust-lang/regex/pull/1319">#1319</a>:
Switch from a Cargo <code>exclude</code> list to an <code>include</code>
list, and exclude some
unnecessary stuff.</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="b028e4f40e"><code>b028e4f</code></a>
1.12.3</li>
<li><a
href="5e195de266"><code>5e195de</code></a>
regex-automata-0.4.14</li>
<li><a
href="a3433f6918"><code>a3433f6</code></a>
regex-syntax-0.8.9</li>
<li><a
href="0c07fae444"><code>0c07fae</code></a>
regex-lite-0.1.9</li>
<li><a
href="6a810068f0"><code>6a81006</code></a>
cargo: exclude development scripts and fuzzing data</li>
<li><a
href="4733e28ba4"><code>4733e28</code></a>
automata: fix <code>onepass::DFA::try_search_slots</code> panic when too
many slots are ...</li>
<li>See full diff in <a
href="https://github.com/rust-lang/regex/compare/1.12.2...1.12.3">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Bumps [anyhow](https://github.com/dtolnay/anyhow) from 1.0.100 to
1.0.101.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/dtolnay/anyhow/releases">anyhow's
releases</a>.</em></p>
<blockquote>
<h2>1.0.101</h2>
<ul>
<li>Add #[inline] to anyhow::Ok helper (<a
href="https://redirect.github.com/dtolnay/anyhow/issues/437">#437</a>,
thanks <a
href="https://github.com/Ibitier"><code>@Ibitier</code></a>)</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="80bfe291b1"><code>80bfe29</code></a>
Release 1.0.101</li>
<li><a
href="dff8c432f9"><code>dff8c43</code></a>
Merge pull request <a
href="https://redirect.github.com/dtolnay/anyhow/issues/437">#437</a>
from Ibitier/inline-ok-helper</li>
<li><a
href="85d9ea9a1c"><code>85d9ea9</code></a>
Add #[inline] to anyhow::Ok helper</li>
<li><a
href="54036cc289"><code>54036cc</code></a>
Update ui test suite to nightly-2026-01-21</li>
<li><a
href="cce0579d85"><code>cce0579</code></a>
Update actions/upload-artifact@v5 -> v6</li>
<li><a
href="f2c598ca0e"><code>f2c598c</code></a>
Update actions/upload-artifact@v4 -> v5</li>
<li><a
href="2c0bda4ce9"><code>2c0bda4</code></a>
Update to 2021 edition</li>
<li><a
href="0d82268129"><code>0d82268</code></a>
Remove rustc version requirement from readme</li>
<li><a
href="67df01216d"><code>67df012</code></a>
Merge pull request <a
href="https://redirect.github.com/dtolnay/anyhow/issues/436">#436</a>
from dtolnay/up</li>
<li><a
href="c8984880a8"><code>c898488</code></a>
Raise required compiler to Rust 1.68</li>
<li>Additional commits viewable in <a
href="https://github.com/dtolnay/anyhow/compare/1.0.100...1.0.101">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
…ount_id and chatgpt_plan_type
### Summary
Following up on external auth mode which was introduced here:
https://github.com/openai/codex/pull/10012
Turns out some clients have a differently shaped ID token and don't have
a chosen workspace (aka chatgpt_account_id) encoded in their ID token.
So, let's replace `id_token` param with `chatgpt_account_id` and
`chatgpt_plan_type` (optional) when initializing the external ChatGPT
auth mode (`account/login/start` with `chatgptAuthTokens`).
The client was able to test end-to-end with a Codex build from this
branch and verified it worked!
Summary
- add platform-aware defaults for shell command timeouts so Windows
tests get longer waits
- keep medium timeout longer on Windows to ensure flakiness is reduced
Testing
- Not run (not requested)
## Summary
- add deterministic child-process cleanup to both test `McpProcess`
helpers
- keep Tokio `kill_on_drop(true)` but also reap via bounded `try_wait()`
polling in `Drop`
- document the failure mode and why this avoids nondeterministic `LEAK`
flakes
## Why
`cargo nextest` leak detection can intermittently report `LEAK` when a
spawned server outlives test teardown, making CI flaky.
## Testing
- `just fmt`
- `cargo test -p codex-app-server`
- `cargo test -p codex-mcp-server`
## Failing CI Reference
- Original failing job:
https://github.com/openai/codex/actions/runs/21845226299/job/63039443593?pr=11245
Automated update of models.json.
---------
Co-authored-by: aibrahim-oai <219906144+aibrahim-oai@users.noreply.github.com>
Co-authored-by: Ahmed Ibrahim <aibrahim@openai.com>
# 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.
Include a link to a bug report or enhancement request.
When steer mode is enabled, Tab used to only queue while a task was
running and otherwise did nothing. Treat Tab as an immediate submit when
no task is running so input isn't dropped when the inflight turn ends
mid-typing.
Adds a regression test and updates docs/tooltips.
Fixes#11020
I do think think `nix build` should run in CI, I had multiple issues
trying to build the flake in the past, as it's continuously out of sync
with the rest of the repo. (like a few days ago I didn't need the
updated outputHashes, just the missing packages).
Co-authored-by: Eric Traut <etraut@openai.com>
