feat: use the arg0 trick with apply_patch (#2646)

Historically, Codex CLI has treated `apply_patch` (and its sometimes
misspelling, `applypatch`) as a "virtual CLI," intercepting it when it
appears as the first arg to `command` for the `"container.exec",
`"shell"`, or `"local_shell"` tools.

This approach has a known limitation where if, say, the model created a
Python script that runs `apply_patch` and then tried to run the Python
script, we have no insight as to what the model is trying to do and the
Python Script would fail because `apply_patch` was never really on the
`PATH`.

One way to solve this problem is to require users to install an
`apply_patch` executable alongside the `codex` executable (or at least
put it someplace where Codex can discover it). Though to keep Codex CLI
as a standalone executable, we exploit "the arg0 trick" where we create
a temporary directory with an entry named `apply_patch` and prepend that
directory to the `PATH` for the duration of the invocation of Codex.

- On UNIX, `apply_patch` is a symlink to `codex`, which now changes its
behavior to behave like `apply_patch` if arg0 is `apply_patch` (or
`applypatch`)
- On Windows, `apply_patch.bat` is a batch script that runs `codex
--codex-run-as-apply-patch %*`, as Codex also changes its behavior if
the first argument is `--codex-run-as-apply-patch`.

codex-rs/apply-patch/Cargo.toml

@@ -7,6 +7,10 @@ version = { workspace = true }
 name = "codex_apply_patch"
 path = "src/lib.rs"
 
+[[bin]]
+name = "apply_patch"
+path = "src/main.rs"
+
 [lints]
 workspace = true
 
@@ -18,5 +22,6 @@ tree-sitter = "0.25.8"
 tree-sitter-bash = "0.25.0"
 
 [dev-dependencies]
+assert_cmd = "2"
 pretty_assertions = "1.4.1"
 tempfile = "3.13.0"

codex-rs/apply-patch/src/lib.rs

@@ -1,5 +1,6 @@
 mod parser;
 mod seek_sequence;
+mod standalone_executable;
 
 use std::collections::HashMap;
 use std::path::Path;
@@ -19,6 +20,8 @@ use tree_sitter::LanguageError;
 use tree_sitter::Parser;
 use tree_sitter_bash::LANGUAGE as BASH;
 
+pub use standalone_executable::main;
+
 /// Detailed instructions for gpt-4.1 on how to use the `apply_patch` tool.
 pub const APPLY_PATCH_TOOL_INSTRUCTIONS: &str = include_str!("../apply_patch_tool_instructions.md");
 

codex-rs/apply-patch/src/main.rs

@@ -0,0 +1,3 @@
+pub fn main() -> ! {
+    codex_apply_patch::main()
+}

codex-rs/apply-patch/src/standalone_executable.rs

@@ -0,0 +1,59 @@
+use std::io::Read;
+use std::io::Write;
+
+pub fn main() -> ! {
+    let exit_code = run_main();
+    std::process::exit(exit_code);
+}
+
+/// We would prefer to return `std::process::ExitCode`, but its `exit_process()`
+/// method is still a nightly API and we want main() to return !.
+pub fn run_main() -> i32 {
+    // Expect either one argument (the full apply_patch payload) or read it from stdin.
+    let mut args = std::env::args_os();
+    let _argv0 = args.next();
+
+    let patch_arg = match args.next() {
+        Some(arg) => match arg.into_string() {
+            Ok(s) => s,
+            Err(_) => {
+                eprintln!("Error: apply_patch requires a UTF-8 PATCH argument.");
+                return 1;
+            }
+        },
+        None => {
+            // No argument provided; attempt to read the patch from stdin.
+            let mut buf = String::new();
+            match std::io::stdin().read_to_string(&mut buf) {
+                Ok(_) => {
+                    if buf.is_empty() {
+                        eprintln!("Usage: apply_patch 'PATCH'\n       echo 'PATCH' | apply-patch");
+                        return 2;
+                    }
+                    buf
+                }
+                Err(err) => {
+                    eprintln!("Error: Failed to read PATCH from stdin.\n{err}");
+                    return 1;
+                }
+            }
+        }
+    };
+
+    // Refuse extra args to avoid ambiguity.
+    if args.next().is_some() {
+        eprintln!("Error: apply_patch accepts exactly one argument.");
+        return 2;
+    }
+
+    let mut stdout = std::io::stdout();
+    let mut stderr = std::io::stderr();
+    match crate::apply_patch(&patch_arg, &mut stdout, &mut stderr) {
+        Ok(()) => {
+            // Flush to ensure output ordering when used in pipelines.
+            let _ = stdout.flush();
+            0
+        }
+        Err(_) => 1,
+    }
+}

codex-rs/apply-patch/tests/all.rs

@@ -0,0 +1,3 @@
+// Single integration test binary that aggregates all test modules.
+// The submodules live in `tests/suite/`.
+mod suite;

codex-rs/apply-patch/tests/suite/cli.rs

@@ -0,0 +1,90 @@
+use assert_cmd::prelude::*;
+use std::fs;
+use std::process::Command;
+use tempfile::tempdir;
+
+#[test]
+fn test_apply_patch_cli_add_and_update() -> anyhow::Result<()> {
+    let tmp = tempdir()?;
+    let file = "cli_test.txt";
+    let absolute_path = tmp.path().join(file);
+
+    // 1) Add a file
+    let add_patch = format!(
+        r#"*** Begin Patch
+*** Add File: {file}
++hello
+*** End Patch"#
+    );
+    Command::cargo_bin("apply_patch")
+        .expect("should find apply_patch binary")
+        .arg(add_patch)
+        .current_dir(tmp.path())
+        .assert()
+        .success()
+        .stdout(format!("Success. Updated the following files:\nA {file}\n"));
+    assert_eq!(fs::read_to_string(&absolute_path)?, "hello\n");
+
+    // 2) Update the file
+    let update_patch = format!(
+        r#"*** Begin Patch
+*** Update File: {file}
+@@
+-hello
++world
+*** End Patch"#
+    );
+    Command::cargo_bin("apply_patch")
+        .expect("should find apply_patch binary")
+        .arg(update_patch)
+        .current_dir(tmp.path())
+        .assert()
+        .success()
+        .stdout(format!("Success. Updated the following files:\nM {file}\n"));
+    assert_eq!(fs::read_to_string(&absolute_path)?, "world\n");
+
+    Ok(())
+}
+
+#[test]
+fn test_apply_patch_cli_stdin_add_and_update() -> anyhow::Result<()> {
+    let tmp = tempdir()?;
+    let file = "cli_test_stdin.txt";
+    let absolute_path = tmp.path().join(file);
+
+    // 1) Add a file via stdin
+    let add_patch = format!(
+        r#"*** Begin Patch
+*** Add File: {file}
++hello
+*** End Patch"#
+    );
+    let mut cmd =
+        assert_cmd::Command::cargo_bin("apply_patch").expect("should find apply_patch binary");
+    cmd.current_dir(tmp.path());
+    cmd.write_stdin(add_patch)
+        .assert()
+        .success()
+        .stdout(format!("Success. Updated the following files:\nA {file}\n"));
+    assert_eq!(fs::read_to_string(&absolute_path)?, "hello\n");
+
+    // 2) Update the file via stdin
+    let update_patch = format!(
+        r#"*** Begin Patch
+*** Update File: {file}
+@@
+-hello
++world
+*** End Patch"#
+    );
+    let mut cmd =
+        assert_cmd::Command::cargo_bin("apply_patch").expect("should find apply_patch binary");
+    cmd.current_dir(tmp.path());
+    cmd.write_stdin(update_patch)
+        .assert()
+        .success()
+        .stdout(format!("Success. Updated the following files:\nM {file}\n"));
+    assert_eq!(fs::read_to_string(&absolute_path)?, "world\n");
+
+    Ok(())
+}

codex-rs/apply-patch/tests/suite/mod.rs

@@ -0,0 +1 @@
+mod cli;