feat: run zsh fork shell tool via shell-escalation (#12649)

## Why

This PR switches the `shell_command` zsh-fork path over to
`codex-shell-escalation` so the new shell tool can use the shared
exec-wrapper/escalation protocol instead of the `zsh_exec_bridge`
implementation that was introduced in
https://github.com/openai/codex/pull/12052. `zsh_exec_bridge` relied on
UNIX domain sockets, which is not as tamper-proof as the FD-based
approach in `codex-shell-escalation`.

## What Changed

- Added a Unix zsh-fork runtime adapter in `core`
(`core/src/tools/runtimes/shell/unix_escalation.rs`) that:
- runs zsh-fork commands through
`codex_shell_escalation::run_escalate_server`
  - bridges exec-policy / approval decisions into `ShellActionProvider`
- executes escalated commands via a `ShellCommandExecutor` that calls
`process_exec_tool_call`
- Updated `ShellRuntime` / `ShellCommandHandler` / tool spec wiring to
select a `shell_command` backend (`classic` vs `zsh-fork`) while leaving
the generic `shell` tool path unchanged.
- Removed the `zsh_exec_bridge`-based session service and deleted
`core/src/zsh_exec_bridge/mod.rs`.
- Moved exec-wrapper entrypoint dispatch to `arg0` by handling the
`codex-execve-wrapper` arg0 alias there, and removed the old
`codex_core::maybe_run_zsh_exec_wrapper_mode()` hooks from `cli` and
`app-server` mains.
- Added the needed `codex-shell-escalation` dependencies for `core` and
`arg0`.

## Tests

- `cargo test -p codex-core
shell_zsh_fork_prefers_shell_command_over_unified_exec`
- `cargo test -p codex-app-server turn_start_shell_zsh_fork --
--nocapture`
- verifies zsh-fork command execution and approval flows through the new
backend
- includes subcommand approve/decline coverage using the shared zsh
DotSlash fixture in `app-server/tests/suite/zsh`
- To test manually, I added the following to `~/.codex/config.toml`:

```toml
zsh_path = "/Users/mbolin/code/codex3/codex-rs/app-server/tests/suite/zsh"

[features]
shell_zsh_fork = true
```

Then I ran `just c` to run the dev build of Codex with these changes and
sent it the message:

```
run `echo $0`
```

And it replied with:

```
  echo $0 printed:

  /Users/mbolin/code/codex3/codex-rs/app-server/tests/suite/zsh

  In this tool context, $0 reflects the script path used to invoke the shell, not just zsh.
```

so the tool appears to be wired up correctly.

## Notes

- The zsh subcommand-decline integration test now uses `rm` under a
`WorkspaceWrite` sandbox. The previous `/usr/bin/true` scenario is
auto-allowed by the new `shell-escalation` policy path, which no longer
produces subcommand approval prompts.
This commit is contained in:
Michael Bolin
2026-02-24 10:31:08 -08:00
committed by GitHub
parent 8d3d58f992
commit 3ca0e7673b
24 changed files with 706 additions and 723 deletions

View File

@@ -109,7 +109,6 @@ pub mod terminal;
mod tools;
pub mod turn_diff_tracker;
mod turn_metadata;
mod zsh_exec_bridge;
pub use rollout::ARCHIVED_SESSIONS_SUBDIR;
pub use rollout::INTERACTIVE_SESSION_SOURCES;
pub use rollout::RolloutRecorder;
@@ -144,7 +143,17 @@ pub(crate) use codex_shell_command::is_safe_command;
pub(crate) use codex_shell_command::parse_command;
pub(crate) use codex_shell_command::powershell;
pub use client::ModelClient;
pub use client::ModelClientSession;
pub use client::ResponsesWebsocketVersion;
pub use client::X_CODEX_TURN_METADATA_HEADER;
pub use client::ws_version_from_features;
pub use client_common::Prompt;
pub use client_common::REVIEW_PROMPT;
pub use client_common::ResponseEvent;
pub use client_common::ResponseStream;
pub use compact::content_items_to_text;
pub use event_mapping::parse_turn_item;
pub use exec_policy::ExecPolicyError;
pub use exec_policy::check_execpolicy_for_warnings;
pub use exec_policy::format_exec_policy_error_with_source;
@@ -153,18 +162,6 @@ pub use file_watcher::FileWatcherEvent;
pub use safety::get_platform_sandbox;
pub use tools::spec::parse_tool_input_schema;
pub use turn_metadata::build_turn_metadata_header;
pub use zsh_exec_bridge::maybe_run_zsh_exec_wrapper_mode;
pub use client::ModelClient;
pub use client::ModelClientSession;
pub use client::ResponsesWebsocketVersion;
pub use client::ws_version_from_features;
pub use client_common::Prompt;
pub use client_common::REVIEW_PROMPT;
pub use client_common::ResponseEvent;
pub use client_common::ResponseStream;
pub use compact::content_items_to_text;
pub use event_mapping::parse_turn_item;
pub mod compact;
pub mod memory_trace;
pub mod otel_init;