feat: add support for --sandbox flag (#1476)

On a high-level, we try to design `config.toml` so that you don't have
to "comment out a lot of stuff" when testing different options.

Previously, defining a sandbox policy was somewhat at odds with this
principle because you would define the policy as attributes of
`[sandbox]` like so:

```toml
[sandbox]
mode = "workspace-write"
writable_roots = [ "/tmp" ]
```

but if you wanted to temporarily change to a read-only sandbox, you
might feel compelled to modify your file to be:

```toml
[sandbox]
mode = "read-only"
# mode = "workspace-write"
# writable_roots = [ "/tmp" ]
```

Technically, commenting out `writable_roots` would not be strictly
necessary, as `mode = "read-only"` would ignore `writable_roots`, but
it's still a reasonable thing to do to keep things tidy.

Currently, the various values for `mode` do not support that many
attributes, so this is not that hard to maintain, but one could imagine
this becoming more complex in the future.

In this PR, we change Codex CLI so that it no longer recognizes
`[sandbox]`. Instead, it introduces a top-level option, `sandbox_mode`,
and `[sandbox_workspace_write]` is used to further configure the sandbox
when when `sandbox_mode = "workspace-write"` is used:

```toml
sandbox_mode = "workspace-write"

[sandbox_workspace_write]
writable_roots = [ "/tmp" ]
```

This feels a bit more future-proof in that it is less tedious to
configure different sandboxes:

```toml
sandbox_mode = "workspace-write"

[sandbox_read_only]
# read-only options here...

[sandbox_workspace_write]
writable_roots = [ "/tmp" ]

[sandbox_danger_full_access]
# danger-full-access options here...
```

In this scheme, you never need to comment out the configuration for an
individual sandbox type: you only need to redefine `sandbox_mode`.

Relatedly, previous to this change, a user had to do `-c
sandbox.mode=read-only` to change the mode on the command line. With
this change, things are arguably a bit cleaner because the equivalent
option is `-c sandbox_mode=read-only` (and now `-c
sandbox_workspace_write=...` can be set separately).

Though more importantly, we introduce the `-s/--sandbox` option to the
CLI, which maps directly to `sandbox_mode` in `config.toml`, making
config override behavior easier to reason about. Moreover, as you can
see in the updates to the various Markdown files, it is much easier to
explain how to configure sandboxing when things like `--sandbox
read-only` can be used as an example.

Relatedly, this cleanup also made it straightforward to add support for
a `sandbox` option for Codex when used as an MCP server (see the changes
to `mcp-server/src/codex_tool_config.rs`).

Fixes https://github.com/openai/codex/issues/1248.

codex-rs/exec/src/cli.rs

@@ -14,11 +14,16 @@ pub struct Cli {
     #[arg(long, short = 'm')]
     pub model: Option<String>,
 
+    /// Select the sandbox policy to use when executing model-generated shell
+    /// commands.
+    #[arg(long = "sandbox", short = 's')]
+    pub sandbox_mode: Option<codex_common::SandboxModeCliArg>,
+
     /// Configuration profile from config.toml to specify default options.
     #[arg(long = "profile", short = 'p')]
     pub config_profile: Option<String>,
 
-    /// Convenience alias for low-friction sandboxed automatic execution (-a on-failure, -c sandbox.mode=workspace-write).
+    /// Convenience alias for low-friction sandboxed automatic execution (-a on-failure, --sandbox workspace-write).
     #[arg(long = "full-auto", default_value_t = false)]
     pub full_auto: bool,
 

codex-rs/exec/src/lib.rs

@@ -11,12 +11,12 @@ pub use cli::Cli;
 use codex_core::codex_wrapper;
 use codex_core::config::Config;
 use codex_core::config::ConfigOverrides;
+use codex_core::config_types::SandboxMode;
 use codex_core::protocol::AskForApproval;
 use codex_core::protocol::Event;
 use codex_core::protocol::EventMsg;
 use codex_core::protocol::InputItem;
 use codex_core::protocol::Op;
-use codex_core::protocol::SandboxPolicy;
 use codex_core::protocol::TaskCompleteEvent;
 use codex_core::util::is_inside_git_repo;
 use event_processor::EventProcessor;
@@ -36,6 +36,7 @@ pub async fn run_main(cli: Cli, codex_linux_sandbox_exe: Option<PathBuf>) -> any
         skip_git_repo_check,
         color,
         last_message_file,
+        sandbox_mode: sandbox_mode_cli_arg,
         prompt,
         config_overrides,
     } = cli;
@@ -84,12 +85,12 @@ pub async fn run_main(cli: Cli, codex_linux_sandbox_exe: Option<PathBuf>) -> any
         ),
     };
 
-    let sandbox_policy = if full_auto {
-        Some(SandboxPolicy::new_workspace_write_policy())
+    let sandbox_mode = if full_auto {
+        Some(SandboxMode::WorkspaceWrite)
     } else if dangerously_bypass_approvals_and_sandbox {
-        Some(SandboxPolicy::DangerFullAccess)
+        Some(SandboxMode::DangerFullAccess)
     } else {
-        None
+        sandbox_mode_cli_arg.map(Into::<SandboxMode>::into)
     };
 
     // Load configuration and determine approval policy
@@ -99,7 +100,7 @@ pub async fn run_main(cli: Cli, codex_linux_sandbox_exe: Option<PathBuf>) -> any
         // This CLI is intended to be headless and has no affordances for asking
         // the user for approval.
         approval_policy: Some(AskForApproval::Never),
-        sandbox_policy,
+        sandbox_mode,
         cwd: cwd.map(|p| p.canonicalize().unwrap_or(p)),
         model_provider: None,
         codex_linux_sandbox_exe,