codex

Revert "Ensure shell command skills trigger approval (#12697 )" (#12721 )

This reverts commit daf0f03ac8.

# 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.

Celia Chen · 2026-02-25 22:49:53 +00:00

b6d20748e0

Ensure shell command skills trigger approval (#12697 )

Summary
- detect skill-invoking shell commands based on the original command
string, request approvals when needed, and cache positive decisions per
session
- keep implicit skill invocation emitted after approval and keep skill
approval decline messaging centralized to the shell handler
- expand and adjust skill approval tests to cover shell-based skill
scripts while matching the new detection expectations

Testing
- Not run (not requested)

pakrym-oai · 2026-02-24 12:13:20 -08:00

daf0f03ac8

feat(linux-sandbox): implement proxy-only egress via TCP-UDS-TCP bridge (#11293 )

## Summary
- Implement Linux proxy-only routing in `codex-rs/linux-sandbox` with a
two-stage bridge: host namespace `loopback TCP proxy endpoint -> UDS`,
then bwrap netns `loopback TCP listener -> host UDS`.
- Add hidden `--proxy-route-spec` plumbing for outer-to-inner stage
handoff.
- Fail closed in proxy mode when no valid loopback proxy endpoints can
be routed.
- Introduce explicit network seccomp modes: `Restricted` (legacy
restricted networking) and `ProxyRouted` (allow INET/INET6 for routed
proxy access, deny `AF_UNIX` and `socketpair`).
- Enforce that proxy bridge/routing is bwrap-only by validating
`--apply-seccomp-then-exec` requires `--use-bwrap-sandbox`.
- Keep landlock-only flows unchanged (no proxy bridge behavior outside
bwrap).

---------

Co-authored-by: Codex <199175422+chatgpt-codex-connector[bot]@users.noreply.github.com>

viyatb-oai · 2026-02-21 18:16:34 +00:00

b3202cbd58

chore: remove codex-core public protocol/shell re-exports (#12432 )

## Why

`codex-rs/core/src/lib.rs` re-exported a broad set of types and modules
from `codex-protocol` and `codex-shell-command`. That made it easy for
workspace crates to import those APIs through `codex-core`, which in
turn hides dependency edges and makes it harder to reduce compile-time
coupling over time.

This change removes those public re-exports so call sites must import
from the source crates directly. Even when a crate still depends on
`codex-core` today, this makes dependency boundaries explicit and
unblocks future work to drop `codex-core` dependencies where possible.

## What Changed

- Removed public re-exports from `codex-rs/core/src/lib.rs` for:
- `codex_protocol::protocol` and related protocol/model types (including
`InitialHistory`)
  - `codex_protocol::config_types` (`protocol_config_types`)
- `codex_shell_command::{bash, is_dangerous_command, is_safe_command,
parse_command, powershell}`
- Migrated workspace Rust call sites to import directly from:
  - `codex_protocol::protocol`
  - `codex_protocol::config_types`
  - `codex_protocol::models`
  - `codex_shell_command`
- Added explicit `Cargo.toml` dependencies (`codex-protocol` /
`codex-shell-command`) in crates that now import those crates directly.
- Kept `codex-core` internal modules compiling by using `pub(crate)`
aliases in `core/src/lib.rs` (internal-only, not part of the public
API).
- Updated the two utility crates that can already drop a `codex-core`
dependency edge entirely:
  - `codex-utils-approval-presets`
  - `codex-utils-cli`

## Verification

- `cargo test -p codex-utils-approval-presets`
- `cargo test -p codex-utils-cli`
- `cargo check --workspace --all-targets`
- `just clippy`

Michael Bolin · 2026-02-20 23:45:35 -08:00

1af2a37ada

Refactor network approvals to host/protocol/port scope (#12140 )

## Summary
Simplify network approvals by removing per-attempt proxy correlation and
moving to session-level approval dedupe keyed by (host, protocol, port).
Instead of encoding attempt IDs into proxy credentials/URLs, we now
treat approvals as a destination policy decision.

- Concurrent calls to the same destination share one approval prompt.
- Different destinations (or same host on different ports) get separate
prompts.
- Allow once approves the current queued request group only.
- Allow for session caches that (host, protocol, port) and auto-allows
future matching requests.
- Never policy continues to deny without prompting.

Example:
- 3 calls: 
  - a.com (line 443)
  - b.com (line 443)
  - a.com (line 443)
=> 2 prompts total (a, b), second a waits on the first decision.
- a.com:80 is treated separately from a.com line 443

## Testing
- `just fmt` (in `codex-rs`)
- `cargo test -p codex-core tools::network_approval::tests`
- `cargo test -p codex-core` (unit tests pass; existing
integration-suite failures remain in this environment)

viyatb-oai · 2026-02-20 10:39:55 -08:00

e8afaed502

fix(linux-sandbox): mount /dev in bwrap sandbox (#12081 )

## Summary
- Updates the Linux bubblewrap sandbox args to mount a minimal `/dev`
using `--dev /dev` instead of only binding `/dev/null`. tools needing
entropy (git, crypto libs, etc.) can fail.

- Changed mount order so `--dev /dev` is added before writable-root
`--bind` mounts, preserving writable `/dev/*` submounts like `/dev/shm`

## Why
Fixes sandboxed command failures when reading `/dev/urandom` (and
similar standard device-node access).


Fixes https://github.com/openai/codex/issues/12056

viyatb-oai · 2026-02-18 23:27:32 -08:00

4fe99b086f

feat(core): add structured network approval plumbing and policy decision model (#11672 )

### Description
#### Summary
Introduces the core plumbing required for structured network approvals

#### What changed
- Added structured network policy decision modeling in core.
- Added approval payload/context types needed for network approval
semantics.
- Wired shell/unified-exec runtime plumbing to consume structured
decisions.
- Updated related core error/event surfaces for structured handling.
- Updated protocol plumbing used by core approval flow.
- Included small CLI debug sandbox compatibility updates needed by this
layer.

#### Why
establishes the minimal backend foundation for network approvals without
yet changing high-level orchestration or TUI behavior.

#### Notes
- Behavior remains constrained by existing requirements/config gating.
- Follow-up PRs in the stack handle orchestration, UX, and app-server
integration.

---------

Co-authored-by: Codex <199175422+chatgpt-codex-connector[bot]@users.noreply.github.com>

viyatb-oai · 2026-02-14 04:18:12 +00:00

b527ee2890

feat: make sandbox read access configurable with ReadOnlyAccess (#11387 )

`SandboxPolicy::ReadOnly` previously implied broad read access and could
not express a narrower read surface.
This change introduces an explicit read-access model so we can support
user-configurable read restrictions in follow-up work, while preserving
current behavior today.

It also ensures unsupported backends fail closed for restricted-read
policies instead of silently granting broader access than intended.

## What

- Added `ReadOnlyAccess` in protocol with:
  - `Restricted { include_platform_defaults, readable_roots }`
  - `FullAccess`
- Updated `SandboxPolicy` to carry read-access configuration:
  - `ReadOnly { access: ReadOnlyAccess }`
  - `WorkspaceWrite { ..., read_only_access: ReadOnlyAccess }`
- Preserved existing behavior by defaulting current construction paths
to `ReadOnlyAccess::FullAccess`.
- Threaded the new fields through sandbox policy consumers and call
sites across `core`, `tui`, `linux-sandbox`, `windows-sandbox`, and
related tests.
- Updated Seatbelt policy generation to honor restricted read roots by
emitting scoped read rules when full read access is not granted.
- Added fail-closed behavior on Linux and Windows backends when
restricted read access is requested but not yet implemented there
(`UnsupportedOperation`).
- Regenerated app-server protocol schema and TypeScript artifacts,
including `ReadOnlyAccess`.

## Compatibility / rollout

- Runtime behavior remains unchanged by default (`FullAccess`).
- API/schema changes are in place so future config wiring can enable
restricted read access without another policy-shape migration.

Michael Bolin · 2026-02-11 18:31:14 -08:00

abbd74e2be

deflake linux-sandbox NoNewPrivs timeout (#11245 )

Deflake `codex-linux-sandbox::all
suite::landlock::test_no_new_privs_is_enabled`.

CI has intermittently failed with `Sandbox(Timeout)` (exit 124) because
the sandboxed
`grep '^NoNewPrivs:' /proc/self/status` can run close to the short
timeout budget.

This updates only this test to use `LONG_TIMEOUT_MS`, which removes the
near-threshold timeout
behavior while keeping the rest of the suite unchanged.

Refs (previous failures):
- PR:
https://github.com/openai/codex/actions/runs/21836764823/job/63009902779
- PR:
https://github.com/openai/codex/actions/runs/21837427251/job/63012470353
- main:
https://github.com/openai/codex/actions/runs/21830746538/job/62988079964

Validation:
- Local: `cd codex-rs && cargo test -p codex-linux-sandbox` (non-Linux
runs 0 tests)

Josh McKinney · 2026-02-10 03:03:58 +00:00

34c88d10ea

feat: include NetworkConfig through ExecParams (#11105 )

This PR adds the following field to `Config`:

```rust
pub network: Option<NetworkProxy>,
```

Though for the moment, it will always be initialized as `None` (this
will be addressed in a subsequent PR).

This PR does the work to thread `network` through to `execute_exec_env()`, `process_exec_tool_call()`, and `UnifiedExecRuntime.run()` to ensure it is available whenever we span a process.

Michael Bolin · 2026-02-09 03:32:17 +00:00

383b45279e

feat(linux-sandbox): add bwrap support (#9938 )

## Summary
This PR introduces a gated Bubblewrap (bwrap) Linux sandbox path. The
curent Linux sandbox path relies on in-process restrictions (including
Landlock). Bubblewrap gives us a more uniform filesystem isolation
model, especially explicit writable roots with the option to make some
directories read-only and granular network controls.

This is behind a feature flag so we can validate behavior safely before
making it the default.

- Added temporary rollout flag:
  - `features.use_linux_sandbox_bwrap`
- Preserved existing default path when the flag is off.
- In Bubblewrap mode:
- Added internal retry without /proc when /proc mount is not permitted
by the host/container.

viyatb-oai · 2026-02-04 11:13:17 -08:00

ae4de43ccc

Inject CODEX_THREAD_ID into the terminal environment (#10096 )

Inject CODEX_THREAD_ID (when applicable) into the terminal environment
so that the agent (and skills) can refer to the current thread / session
ID.

Discussion:
https://openai.slack.com/archives/C095U48JNL9/p1769542492067109

Max Johnson · 2026-02-03 11:31:12 -08:00

66b196a725

remove sandbox globals. (#9797 )

Threads sandbox updates through OverrideTurnContext for active turn
Passes computed sandbox type into safety/exec

iceweasel-oai · 2026-01-27 11:04:23 -08:00

c40ad65bd8

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: 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

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

fix: introduce AbsolutePathBuf as part of sandbox config (#7856 )

Changes the `writable_roots` field of the `WorkspaceWrite` variant of
the `SandboxPolicy` enum from `Vec<PathBuf>` to `Vec<AbsolutePathBuf>`.
This is helpful because now callers can be sure the value is an absolute
path rather than a relative one. (Though when using an absolute path in
a Seatbelt config policy, we still have to _canonicalize_ it first.)

Because `writable_roots` can be read from a config file, it is important
that we are able to resolve relative paths properly using the parent
folder of the config file as the base path.

Michael Bolin · 2025-12-12 15:25:22 -08:00

642b7566df

refactoring with_escalated_permissions to use SandboxPermissions instead (#7750 )

helpful in the future if we want more granularity for requesting
escalated permissions:
e.g when running in readonly sandbox, model can request to escalate to a
sandbox that allows writes

zhao-oai · 2025-12-10 17:18:48 +00:00

e0fb3ca1db

refactor: inline sandbox type lookup in process_exec_tool_call (#7122 )

`process_exec_tool_call()` was taking `SandboxType` as a param, but in
practice, the only place it was constructed was in
`codex_message_processor.rs` where it was derived from the other
`sandbox_policy` param, so this PR inlines the logic that decides the
`SandboxType` into `process_exec_tool_call()`.



---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/7122).
* #7112
* __->__ #7122

Michael Bolin · 2025-11-21 22:53:05 +00:00

67975ed33a

feat: update process_exec_tool_call() to take a cancellation token (#6972 )

This updates `ExecParams` so that instead of taking `timeout_ms:
Option<u64>`, it now takes a more general cancellation mechanism,
`ExecExpiration`, which is an enum that includes a
`Cancellation(tokio_util::sync::CancellationToken)` variant.

If the cancellation token is fired, then `process_exec_tool_call()`
returns in the same way as if a timeout was exceeded.

This is necessary so that in #6973, we can manage the timeout logic
external to the `process_exec_tool_call()` because we want to "suspend"
the timeout when an elicitation from a human user is pending.








---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/6972).
* #7005
* #6973
* __->__ #6972

Michael Bolin · 2025-11-20 16:29:57 -08:00

f56d1dc8fc

chore: unify config crates (#5958 )

jif-oai · 2025-10-30 10:28:32 +00:00

aa76003e28

chore: rework tools execution workflow (#5278 )

Re-work the tool execution flow. Read `orchestrator.rs` to understand
the structure

jif-oai · 2025-10-20 20:57:37 +01:00

5e4f3bbb0b

chore: clippy on redundant closure (#4058 )

Add redundant closure clippy rules and let Codex fix it by minimising
FQP

jif-oai · 2025-09-22 19:30:16 +00:00

be366a31ab

fix: ensure cwd for conversation and sandbox are separate concerns (#3874 )

Previous to this PR, both of these functions take a single `cwd`:


https://github.com/openai/codex/blob/71038381aa0f51aa62e1a2bcc7cbf26a05b141f3/codex-rs/core/src/seatbelt.rs#L19-L25


https://github.com/openai/codex/blob/71038381aa0f51aa62e1a2bcc7cbf26a05b141f3/codex-rs/core/src/landlock.rs#L16-L23

whereas `cwd` and `sandbox_cwd` should be set independently (fixed in
this PR).

Added `sandbox_distinguishes_command_and_policy_cwds()` to
`codex-rs/exec/tests/suite/sandbox.rs` to verify this.

Michael Bolin · 2025-09-18 14:37:06 -07:00

8595237505

Include command output when sending timeout to model (#3576 )

Being able to see the output helps the model decide how to handle the
timeout.

pakrym-oai · 2025-09-14 14:38:26 -07:00

863d9c237e

test: faster test execution in codex-core (#2633 )

this dramatically improves time to run `cargo test -p codex-core` (~25x
speedup).

before:
```
cargo test -p codex-core  35.96s user 68.63s system 19% cpu 8:49.80 total
```

after:
```
cargo test -p codex-core  5.51s user 8.16s system 63% cpu 21.407 total
```

both tests measured "hot", i.e. on a 2nd run with no filesystem changes,
to exclude compile times.

approach inspired by [Delete Cargo Integration
Tests](https://matklad.github.io/2021/02/27/delete-cargo-integration-tests.html),
we move all test cases in tests/ into a single suite in order to have a
single binary, as there is significant overhead for each test binary
executed, and because test execution is only parallelized with a single
binary.

Jeremy Rose · 2025-08-24 11:10:53 -07:00

32bbbbad61

26 Commits