mirror of https://github.com/openai/codex.git synced 2026-05-04 21:32:21 +03:00

Files

Michael Bolin 7fa9d9ae35 feat: include sandbox config with escalation request (#12839 )

## Why

Before this change, an escalation approval could say that a command
should be rerun, but it could not carry the sandbox configuration that
should still apply when the escalated command is actually spawned.

That left an unsafe gap in the `zsh-fork` skill path: skill scripts
under `scripts/` that did not declare permissions could be escalated
without a sandbox, and scripts that did declare permissions could lose
their bounded sandbox on rerun or cached session approval.

This PR extends the escalation protocol so approvals can optionally
carry sandbox configuration all the way through execution. That lets the
shell runtime preserve the intended sandbox instead of silently widening
access.

We likely want a single permissions type for this codepath eventually,
probably centered on `Permissions`. For now, the protocol needs to
represent both the existing `PermissionProfile` form and the fuller
`Permissions` form, so this introduces a temporary disjoint union,
`EscalationPermissions`, to carry either one.

Further, this means that today, a skill either:

- does not declare any permissions, in which case it is run using the
default sandbox for the turn
- specifies permissions, in which case the skill is run using that exact
sandbox, which might be more restrictive than the default sandbox for
the turn

We will likely change the skill's permissions to be additive to the
existing permissions for the turn.

## What Changed

- Added `EscalationPermissions` to `codex-protocol` so escalation
requests can carry either a `PermissionProfile` or a full `Permissions`
payload.
- Added an explicit `EscalationExecution` mode to the shell escalation
protocol so reruns distinguish between `Unsandboxed`, `TurnDefault`, and
`Permissions(...)` instead of overloading `None`.
- Updated `zsh-fork` shell reruns to resolve `TurnDefault` at execution
time, which keeps ordinary `UseDefault` commands on the turn sandbox and
preserves turn-level macOS seatbelt profile extensions.
- Updated the `zsh-fork` skill path so a skill with no declared
permissions inherits the conversation's effective sandbox instead of
escalating unsandboxed.
- Updated the `zsh-fork` skill path so a skill with declared permissions
reruns with exactly those permissions, including when a cached session
approval is reused.

## Testing

- Added unit coverage in
`core/src/tools/runtimes/shell/unix_escalation.rs` for the explicit
`UseDefault` / `RequireEscalated` / `WithAdditionalPermissions`
execution mapping.
- Added unit coverage in
`core/src/tools/runtimes/shell/unix_escalation.rs` for macOS seatbelt
extension preservation in both the `TurnDefault` and
explicit-permissions rerun paths.
- Added integration coverage in `core/tests/suite/skill_approval.rs` for
permissionless skills inheriting the turn sandbox and explicit skill
permissions remaining bounded across cached approval reuse.

2026-02-26 12:00:18 -08:00

src

feat: include sandbox config with escalation request (#12839 )

2026-02-26 12:00:18 -08:00

templates

…

tests

feat: include sandbox config with escalation request (#12839 )

2026-02-26 12:00:18 -08:00

BUILD.bazel

…

Cargo.toml

…

config.schema.json

…

gpt_5_1_prompt.md

…

gpt_5_2_prompt.md

…

gpt_5_codex_prompt.md

…

gpt-5.1-codex-max_prompt.md

…

gpt-5.2-codex_prompt.md

…

hierarchical_agents_message.md

…

models.json

…

prompt_with_apply_patch_instructions.md

…

prompt.md

…

README.md

…

review_prompt.md

…

README.md

codex-core

This crate implements the business logic for Codex. It is designed to be used by the various Codex UIs written in Rust.

Dependencies

Note that codex-core makes some assumptions about certain helper utilities being available in the environment. Currently, this support matrix is:

macOS

Expects /usr/bin/sandbox-exec to be present.

When using the workspace-write sandbox policy, the Seatbelt profile allows writes under the configured writable roots while keeping .git (directory or pointer file), the resolved gitdir: target, and .codex read-only.

Network access and filesystem read/write roots are controlled by SandboxPolicy. Seatbelt consumes the resolved policy and enforces it.

Seatbelt also supports macOS permission-profile extensions layered on top of SandboxPolicy:

no extension profile provided: keeps legacy default preferences read access (user-preference-read).
extension profile provided with no macos_preferences grant: does not add preferences access clauses.
macos_preferences = "readonly": enables cfprefs read clauses and user-preference-read.
macos_preferences = "readwrite": includes readonly clauses plus user-preference-write and cfprefs shm write clauses.
macos_automation = true: enables broad Apple Events send permissions.
macos_automation = ["com.apple.Notes", ...]: enables Apple Events send only to listed bundle IDs.
macos_accessibility = true: enables com.apple.axserver mach lookup.
macos_calendar = true: enables com.apple.CalendarAgent mach lookup.

Linux

Expects the binary containing codex-core to run the equivalent of codex sandbox linux (legacy alias: codex debug landlock) when arg0 is codex-linux-sandbox. See the codex-arg0 crate for details.

All Platforms

Expects the binary containing codex-core to simulate the virtual apply_patch CLI when arg1 is --codex-run-as-apply-patch. See the codex-arg0 crate for details.