This commit is contained in:
jimmyfraiture
2025-09-29 10:30:24 +01:00
parent cd7e37c6b0
commit 491ba05f71
25 changed files with 1875 additions and 1805 deletions
+12
View File
@@ -578,10 +578,22 @@ name = "codex-agent"
version = "0.0.0"
dependencies = [
"anyhow",
"async-trait",
"base64",
"codex-protocol",
"core_test_support",
"libc",
"mcp-types",
"portable-pty",
"serde",
"serde_json",
"sha1",
"shlex",
"similar",
"thiserror 2.0.16",
"tokio",
"uuid",
"which",
"wildmatch",
]
+16 -2
View File
@@ -5,11 +5,25 @@ edition.workspace = true
[dependencies]
anyhow = { workspace = true }
portable-pty = { workspace = true }
tokio = { workspace = true, features = ["macros", "rt-multi-thread", "sync", "time"] }
async-trait = { workspace = true }
codex-protocol = { workspace = true }
mcp-types = { workspace = true }
base64 = { workspace = true }
serde_json = { workspace = true }
libc = { workspace = true }
portable-pty = { workspace = true }
serde = { workspace = true, features = ["derive"] }
sha1 = { workspace = true }
shlex = { workspace = true }
similar = { workspace = true }
thiserror = { workspace = true }
tokio = { workspace = true, features = ["macros", "process", "rt-multi-thread", "sync", "time"] }
uuid = { workspace = true, features = ["serde", "v4"] }
which = { workspace = true }
wildmatch = { workspace = true }
[dev-dependencies]
core_test_support = { workspace = true }
[lints]
workspace = true
@@ -0,0 +1,7 @@
use thiserror::Error;
#[derive(Debug, Error, PartialEq)]
pub enum FunctionCallError {
#[error("{0}")]
RespondToModel(String),
}
+14
View File
@@ -1,5 +1,19 @@
pub mod config_types;
pub mod exec_command;
pub mod function_tool;
pub mod notifications;
pub mod services;
pub mod shell;
pub mod token_data;
pub mod truncate;
pub mod turn_diff_tracker;
pub mod unified_exec;
pub use config_types::*;
pub use function_tool::*;
pub use notifications::*;
pub use services::*;
pub use shell::*;
pub use token_data::*;
pub use turn_diff_tracker::*;
pub use unified_exec::*;
+15
View File
@@ -0,0 +1,15 @@
use serde::Serialize;
/// Cross-host notification payloads emitted by the agent runtime.
#[derive(Debug, Clone, PartialEq, Serialize)]
#[serde(tag = "type", rename_all = "kebab-case")]
pub enum UserNotification {
#[serde(rename_all = "kebab-case")]
AgentTurnComplete {
turn_id: String,
/// Messages submitted by the user to start the turn.
input_messages: Vec<String>,
/// Final assistant message emitted at turn completion.
last_assistant_message: Option<String>,
},
}
+92
View File
@@ -0,0 +1,92 @@
use std::collections::HashMap;
use std::path::PathBuf;
use async_trait::async_trait;
use codex_protocol::mcp_protocol::AuthMode;
use codex_protocol::protocol::RolloutItem;
use mcp_types::Tool;
use serde_json::Value;
use crate::exec_command::ExecCommandOutput;
use crate::exec_command::ExecCommandParams;
use crate::exec_command::WriteStdinParams;
use crate::notifications::UserNotification;
use crate::token_data::PlanType;
use crate::unified_exec::UnifiedExecError;
use crate::unified_exec::UnifiedExecRequest;
use crate::unified_exec::UnifiedExecResult;
/// Authentication context made available to the provider layer.
#[async_trait]
pub trait ProviderAuth: Send + Sync {
fn mode(&self) -> AuthMode;
async fn access_token(&self) -> std::io::Result<String>;
fn account_id(&self) -> Option<String>;
fn plan_type(&self) -> Option<PlanType>;
}
/// Provides access to credentials required when talking to model providers.
#[async_trait]
pub trait CredentialsProvider: Send + Sync {
fn auth(&self) -> Option<std::sync::Arc<dyn ProviderAuth>>;
async fn refresh_token(&self) -> std::io::Result<Option<String>>;
}
/// Emits user-facing notifications for turn completion or other events.
pub trait Notifier: Send + Sync {
fn notify(&self, notification: &UserNotification);
}
/// Aggregates and dispatches MCP tool calls across configured servers.
#[async_trait]
pub trait McpInterface: Send + Sync {
fn list_all_tools(&self) -> HashMap<String, Tool>;
fn parse_tool_name(&self, tool_name: &str) -> Option<(String, String)>;
async fn call_tool(
&self,
server: &str,
tool: &str,
arguments: Option<Value>,
) -> anyhow::Result<mcp_types::CallToolResult>;
}
/// Persists rollout events for later inspection or replay.
#[async_trait]
pub trait RolloutSink: Send + Sync {
async fn record_items(&self, items: &[RolloutItem]) -> std::io::Result<()>;
async fn flush(&self) -> std::io::Result<()>;
async fn shutdown(&self) -> std::io::Result<()>;
fn get_rollout_path(&self) -> PathBuf;
}
/// Handles sandboxed exec orchestration, including long-running sessions.
#[async_trait]
pub trait SandboxManager: Send + Sync {
async fn handle_exec_command_request(
&self,
params: ExecCommandParams,
) -> Result<ExecCommandOutput, String>;
async fn handle_write_stdin_request(
&self,
params: WriteStdinParams,
) -> Result<ExecCommandOutput, String>;
async fn handle_unified_exec_request(
&self,
request: UnifiedExecRequest<'_>,
) -> Result<UnifiedExecResult, UnifiedExecError>;
fn codex_linux_sandbox_exe(&self) -> &Option<PathBuf>;
fn user_shell(&self) -> &crate::shell::Shell;
}
+571
View File
@@ -0,0 +1,571 @@
use serde::Deserialize;
use serde::Serialize;
use shlex;
use std::path::PathBuf;
#[derive(Debug, PartialEq, Eq, Clone, Serialize, Deserialize)]
pub struct ZshShell {
pub(crate) shell_path: String,
pub(crate) zshrc_path: String,
}
#[derive(Debug, PartialEq, Eq, Clone, Serialize, Deserialize)]
pub struct BashShell {
pub(crate) shell_path: String,
pub(crate) bashrc_path: String,
}
#[derive(Debug, PartialEq, Eq, Clone, Serialize, Deserialize)]
pub struct PowerShellConfig {
pub(crate) exe: String, // Executable name or path, e.g. "pwsh" or "powershell.exe".
pub(crate) bash_exe_fallback: Option<PathBuf>, // In case the model generates a bash command.
}
#[derive(Debug, PartialEq, Eq, Clone, Serialize, Deserialize)]
pub enum Shell {
Zsh(ZshShell),
Bash(BashShell),
PowerShell(PowerShellConfig),
Unknown,
}
impl Shell {
pub fn format_default_shell_invocation(&self, command: Vec<String>) -> Option<Vec<String>> {
match self {
Shell::Zsh(zsh) => format_shell_invocation_with_rc(
command.as_slice(),
&zsh.shell_path,
&zsh.zshrc_path,
),
Shell::Bash(bash) => format_shell_invocation_with_rc(
command.as_slice(),
&bash.shell_path,
&bash.bashrc_path,
),
Shell::PowerShell(ps) => {
// If model generated a bash command, prefer a detected bash fallback
if let Some(script) = strip_bash_lc(command.as_slice()) {
return match &ps.bash_exe_fallback {
Some(bash) => Some(vec![
bash.to_string_lossy().to_string(),
"-lc".to_string(),
script,
]),
// No bash fallback → run the script under PowerShell.
// It will likely fail (except for some simple commands), but the error
// should give a clue to the model to fix upon retry that it's running under PowerShell.
None => Some(vec![
ps.exe.clone(),
"-NoProfile".to_string(),
"-Command".to_string(),
script,
]),
};
}
// Not a bash command. If model did not generate a PowerShell command,
// turn it into a PowerShell command.
let first = command.first().map(String::as_str);
if first != Some(ps.exe.as_str()) {
// TODO (CODEX_2900): Handle escaping newlines.
if command.iter().any(|a| a.contains('\n') || a.contains('\r')) {
return Some(command);
}
let joined = shlex::try_join(command.iter().map(String::as_str)).ok();
return joined.map(|arg| {
vec![
ps.exe.clone(),
"-NoProfile".to_string(),
"-Command".to_string(),
arg,
]
});
}
// Model generated a PowerShell command. Run it.
Some(command)
}
Shell::Unknown => None,
}
}
pub fn name(&self) -> Option<String> {
match self {
Shell::Zsh(zsh) => std::path::Path::new(&zsh.shell_path)
.file_name()
.map(|s| s.to_string_lossy().to_string()),
Shell::Bash(bash) => std::path::Path::new(&bash.shell_path)
.file_name()
.map(|s| s.to_string_lossy().to_string()),
Shell::PowerShell(ps) => Some(ps.exe.clone()),
Shell::Unknown => None,
}
}
}
fn format_shell_invocation_with_rc(
command: &[String],
shell_path: &str,
rc_path: &str,
) -> Option<Vec<String>> {
let joined = strip_bash_lc(command)
.or_else(|| shlex::try_join(command.iter().map(String::as_str)).ok())?;
let rc_command = if std::path::Path::new(rc_path).exists() {
format!("source {rc_path} && ({joined})")
} else {
joined
};
Some(vec![shell_path.to_string(), "-lc".to_string(), rc_command])
}
fn strip_bash_lc(command: &[String]) -> Option<String> {
match command {
// exactly three items
[first, second, third]
// first two must be "bash", "-lc"
if first == "bash" && second == "-lc" =>
{
Some(third.clone())
}
_ => None,
}
}
#[cfg(unix)]
fn detect_default_user_shell() -> Shell {
use libc::getpwuid;
use libc::getuid;
use std::ffi::CStr;
unsafe {
let uid = getuid();
let pw = getpwuid(uid);
if !pw.is_null() {
let shell_path = CStr::from_ptr((*pw).pw_shell)
.to_string_lossy()
.into_owned();
let home_path = CStr::from_ptr((*pw).pw_dir).to_string_lossy().into_owned();
if shell_path.ends_with("/zsh") {
return Shell::Zsh(ZshShell {
shell_path,
zshrc_path: format!("{home_path}/.zshrc"),
});
}
if shell_path.ends_with("/bash") {
return Shell::Bash(BashShell {
shell_path,
bashrc_path: format!("{home_path}/.bashrc"),
});
}
}
}
Shell::Unknown
}
#[cfg(unix)]
pub async fn default_user_shell() -> Shell {
detect_default_user_shell()
}
#[cfg(target_os = "windows")]
pub async fn default_user_shell() -> Shell {
use tokio::process::Command;
// Prefer PowerShell 7+ (`pwsh`) if available, otherwise fall back to Windows PowerShell.
let has_pwsh = Command::new("pwsh")
.arg("-NoLogo")
.arg("-NoProfile")
.arg("-Command")
.arg("$PSVersionTable.PSVersion.Major")
.output()
.await
.map(|o| o.status.success())
.unwrap_or(false);
let bash_exe = if Command::new("bash.exe")
.arg("--version")
.output()
.await
.ok()
.map(|o| o.status.success())
.unwrap_or(false)
{
which::which("bash.exe").ok()
} else {
None
};
if has_pwsh {
Shell::PowerShell(PowerShellConfig {
exe: "pwsh.exe".to_string(),
bash_exe_fallback: bash_exe,
})
} else {
Shell::PowerShell(PowerShellConfig {
exe: "powershell.exe".to_string(),
bash_exe_fallback: bash_exe,
})
}
}
#[cfg(all(not(target_os = "windows"), not(unix)))]
pub async fn default_user_shell() -> Shell {
Shell::Unknown
}
#[cfg(test)]
#[cfg(unix)]
mod tests {
use super::*;
use std::process::Command;
use std::string::ToString;
#[tokio::test]
async fn test_current_shell_detects_zsh() {
let shell = Command::new("sh")
.arg("-c")
.arg("echo $SHELL")
.output()
.unwrap();
let home = std::env::var("HOME").unwrap();
let shell_path = String::from_utf8_lossy(&shell.stdout).trim().to_string();
if shell_path.ends_with("/zsh") {
assert_eq!(
default_user_shell().await,
Shell::Zsh(ZshShell {
shell_path: shell_path.to_string(),
zshrc_path: format!("{home}/.zshrc",),
})
);
}
}
#[tokio::test]
async fn test_run_with_profile_zshrc_not_exists() {
let shell = Shell::Zsh(ZshShell {
shell_path: "/bin/zsh".to_string(),
zshrc_path: "/does/not/exist/.zshrc".to_string(),
});
let actual_cmd = shell.format_default_shell_invocation(vec!["myecho".to_string()]);
assert_eq!(
actual_cmd,
Some(vec![
"/bin/zsh".to_string(),
"-lc".to_string(),
"myecho".to_string()
])
);
}
#[tokio::test]
async fn test_run_with_profile_bashrc_not_exists() {
let shell = Shell::Bash(BashShell {
shell_path: "/bin/bash".to_string(),
bashrc_path: "/does/not/exist/.bashrc".to_string(),
});
let actual_cmd = shell.format_default_shell_invocation(vec!["myecho".to_string()]);
assert_eq!(
actual_cmd,
Some(vec![
"/bin/bash".to_string(),
"-lc".to_string(),
"myecho".to_string()
])
);
}
#[tokio::test]
async fn test_run_with_profile_bash_escaping_and_execution() {
let shell_path = "/bin/bash";
let cases = vec![
(
vec!["myecho"],
vec![shell_path, "-lc", "source BASHRC_PATH && (myecho)"],
Some("It works!\n"),
),
(
vec!["bash", "-lc", "echo 'single' \"double\""],
vec![
shell_path,
"-lc",
"source BASHRC_PATH && (echo 'single' \"double\")",
],
Some("single double\n"),
),
];
for (input, expected_cmd, expected_output) in cases {
use std::collections::HashMap;
use crate::exec::ExecParams;
use crate::exec::SandboxType;
use crate::exec::process_exec_tool_call;
use crate::protocol::SandboxPolicy;
let temp_home = tempfile::tempdir().unwrap();
let bashrc_path = temp_home.path().join(".bashrc");
std::fs::write(
&bashrc_path,
r#"
set -x
function myecho {
echo 'It works!'
}
"#,
)
.unwrap();
let shell = Shell::Bash(BashShell {
shell_path: shell_path.to_string(),
bashrc_path: bashrc_path.to_str().unwrap().to_string(),
});
let actual_cmd = shell
.format_default_shell_invocation(input.iter().map(ToString::to_string).collect());
let expected_cmd = expected_cmd
.iter()
.map(|s| s.replace("BASHRC_PATH", bashrc_path.to_str().unwrap()))
.collect();
assert_eq!(actual_cmd, Some(expected_cmd));
let output = process_exec_tool_call(
ExecParams {
command: actual_cmd.unwrap(),
cwd: PathBuf::from(temp_home.path()),
timeout_ms: None,
env: HashMap::from([(
"HOME".to_string(),
temp_home.path().to_str().unwrap().to_string(),
)]),
with_escalated_permissions: None,
justification: None,
},
SandboxType::None,
&SandboxPolicy::DangerFullAccess,
temp_home.path(),
&None,
None,
)
.await
.unwrap();
assert_eq!(output.exit_code, 0, "input: {input:?} output: {output:?}");
if let Some(expected) = expected_output {
assert_eq!(
output.stdout.text, expected,
"input: {input:?} output: {output:?}"
);
}
}
}
}
#[cfg(test)]
#[cfg(target_os = "macos")]
mod macos_tests {
use super::*;
use std::string::ToString;
#[tokio::test]
async fn test_run_with_profile_escaping_and_execution() {
let shell_path = "/bin/zsh";
let cases = vec![
(
vec!["myecho"],
vec![shell_path, "-lc", "source ZSHRC_PATH && (myecho)"],
Some("It works!\n"),
),
(
vec!["myecho"],
vec![shell_path, "-lc", "source ZSHRC_PATH && (myecho)"],
Some("It works!\n"),
),
(
vec!["bash", "-c", "echo 'single' \"double\""],
vec![
shell_path,
"-lc",
"source ZSHRC_PATH && (bash -c \"echo 'single' \\\"double\\\"\")",
],
Some("single double\n"),
),
(
vec!["bash", "-lc", "echo 'single' \"double\""],
vec![
shell_path,
"-lc",
"source ZSHRC_PATH && (echo 'single' \"double\")",
],
Some("single double\n"),
),
];
for (input, expected_cmd, expected_output) in cases {
use std::collections::HashMap;
use std::path::PathBuf;
use crate::exec::ExecParams;
use crate::exec::SandboxType;
use crate::exec::process_exec_tool_call;
use crate::protocol::SandboxPolicy;
// create a temp directory with a zshrc file in it
let temp_home = tempfile::tempdir().unwrap();
let zshrc_path = temp_home.path().join(".zshrc");
std::fs::write(
&zshrc_path,
r#"
set -x
function myecho {
echo 'It works!'
}
"#,
)
.unwrap();
let shell = Shell::Zsh(ZshShell {
shell_path: shell_path.to_string(),
zshrc_path: zshrc_path.to_str().unwrap().to_string(),
});
let actual_cmd = shell
.format_default_shell_invocation(input.iter().map(ToString::to_string).collect());
let expected_cmd = expected_cmd
.iter()
.map(|s| s.replace("ZSHRC_PATH", zshrc_path.to_str().unwrap()))
.collect();
assert_eq!(actual_cmd, Some(expected_cmd));
// Actually run the command and check output/exit code
let output = process_exec_tool_call(
ExecParams {
command: actual_cmd.unwrap(),
cwd: PathBuf::from(temp_home.path()),
timeout_ms: None,
env: HashMap::from([(
"HOME".to_string(),
temp_home.path().to_str().unwrap().to_string(),
)]),
with_escalated_permissions: None,
justification: None,
},
SandboxType::None,
&SandboxPolicy::DangerFullAccess,
temp_home.path(),
&None,
None,
)
.await
.unwrap();
assert_eq!(output.exit_code, 0, "input: {input:?} output: {output:?}");
if let Some(expected) = expected_output {
assert_eq!(
output.stdout.text, expected,
"input: {input:?} output: {output:?}"
);
}
}
}
}
#[cfg(test)]
#[cfg(target_os = "windows")]
mod tests_windows {
use super::*;
#[test]
fn test_format_default_shell_invocation_powershell() {
let cases = vec![
(
Shell::PowerShell(PowerShellConfig {
exe: "pwsh.exe".to_string(),
bash_exe_fallback: None,
}),
vec!["bash", "-lc", "echo hello"],
vec!["pwsh.exe", "-NoProfile", "-Command", "echo hello"],
),
(
Shell::PowerShell(PowerShellConfig {
exe: "powershell.exe".to_string(),
bash_exe_fallback: None,
}),
vec!["bash", "-lc", "echo hello"],
vec!["powershell.exe", "-NoProfile", "-Command", "echo hello"],
),
(
Shell::PowerShell(PowerShellConfig {
exe: "pwsh.exe".to_string(),
bash_exe_fallback: Some(PathBuf::from("bash.exe")),
}),
vec!["bash", "-lc", "echo hello"],
vec!["bash.exe", "-lc", "echo hello"],
),
(
Shell::PowerShell(PowerShellConfig {
exe: "pwsh.exe".to_string(),
bash_exe_fallback: Some(PathBuf::from("bash.exe")),
}),
vec![
"bash",
"-lc",
"apply_patch <<'EOF'\n*** Begin Patch\n*** Update File: destination_file.txt\n-original content\n+modified content\n*** End Patch\nEOF",
],
vec![
"bash.exe",
"-lc",
"apply_patch <<'EOF'\n*** Begin Patch\n*** Update File: destination_file.txt\n-original content\n+modified content\n*** End Patch\nEOF",
],
),
(
Shell::PowerShell(PowerShellConfig {
exe: "pwsh.exe".to_string(),
bash_exe_fallback: Some(PathBuf::from("bash.exe")),
}),
vec!["echo", "hello"],
vec!["pwsh.exe", "-NoProfile", "-Command", "echo hello"],
),
(
Shell::PowerShell(PowerShellConfig {
exe: "pwsh.exe".to_string(),
bash_exe_fallback: Some(PathBuf::from("bash.exe")),
}),
vec!["pwsh.exe", "-NoProfile", "-Command", "echo hello"],
vec!["pwsh.exe", "-NoProfile", "-Command", "echo hello"],
),
(
// TODO (CODEX_2900): Handle escaping newlines for powershell invocation.
Shell::PowerShell(PowerShellConfig {
exe: "powershell.exe".to_string(),
bash_exe_fallback: Some(PathBuf::from("bash.exe")),
}),
vec![
"codex-mcp-server.exe",
"--codex-run-as-apply-patch",
"*** Begin Patch\n*** Update File: C:\\Users\\person\\destination_file.txt\n-original content\n+modified content\n*** End Patch",
],
vec![
"codex-mcp-server.exe",
"--codex-run-as-apply-patch",
"*** Begin Patch\n*** Update File: C:\\Users\\person\\destination_file.txt\n-original content\n+modified content\n*** End Patch",
],
),
];
for (shell, input, expected_cmd) in cases {
let actual_cmd = shell
.format_default_shell_invocation(input.iter().map(|s| (*s).to_string()).collect());
assert_eq!(
actual_cmd,
Some(expected_cmd.iter().map(|s| (*s).to_string()).collect())
);
}
}
}
+182
View File
@@ -0,0 +1,182 @@
use base64::Engine;
use serde::Deserialize;
use serde::Serialize;
use thiserror::Error;
#[derive(Deserialize, Serialize, Clone, Debug, PartialEq, Default)]
pub struct TokenData {
/// Flat info parsed from the JWT in auth.json.
#[serde(
deserialize_with = "deserialize_id_token",
serialize_with = "serialize_id_token"
)]
pub id_token: IdTokenInfo,
/// This is a JWT.
pub access_token: String,
pub refresh_token: String,
pub account_id: Option<String>,
}
/// Flat subset of useful claims in id_token from auth.json.
#[derive(Debug, Clone, PartialEq, Eq, Default, Serialize, Deserialize)]
pub struct IdTokenInfo {
pub email: Option<String>,
/// The ChatGPT subscription plan type
/// (e.g., "free", "plus", "pro", "business", "enterprise", "edu").
/// (Note: values may vary by backend.)
pub chatgpt_plan_type: Option<PlanType>,
pub raw_jwt: String,
}
impl IdTokenInfo {
pub fn get_chatgpt_plan_type(&self) -> Option<String> {
self.chatgpt_plan_type.as_ref().map(|t| match t {
PlanType::Known(plan) => format!("{plan:?}"),
PlanType::Unknown(s) => s.clone(),
})
}
}
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
#[serde(untagged)]
pub enum PlanType {
Known(KnownPlan),
Unknown(String),
}
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "lowercase")]
pub enum KnownPlan {
Free,
Plus,
Pro,
Team,
Business,
Enterprise,
Edu,
}
#[derive(Deserialize)]
struct IdClaims {
#[serde(default)]
email: Option<String>,
#[serde(rename = "https://api.openai.com/auth", default)]
auth: Option<AuthClaims>,
}
#[derive(Deserialize)]
struct AuthClaims {
#[serde(default)]
chatgpt_plan_type: Option<PlanType>,
}
#[derive(Debug, Error)]
pub enum IdTokenInfoError {
#[error("invalid ID token format")]
InvalidFormat,
#[error(transparent)]
Base64(#[from] base64::DecodeError),
#[error(transparent)]
Json(#[from] serde_json::Error),
}
pub fn parse_id_token(id_token: &str) -> Result<IdTokenInfo, IdTokenInfoError> {
// JWT format: header.payload.signature
let mut parts = id_token.split('.');
let (_header_b64, payload_b64, _sig_b64) = match (parts.next(), parts.next(), parts.next()) {
(Some(h), Some(p), Some(s)) if !h.is_empty() && !p.is_empty() && !s.is_empty() => (h, p, s),
_ => return Err(IdTokenInfoError::InvalidFormat),
};
let payload_bytes = base64::engine::general_purpose::URL_SAFE_NO_PAD.decode(payload_b64)?;
let claims: IdClaims = serde_json::from_slice(&payload_bytes)?;
Ok(IdTokenInfo {
email: claims.email,
chatgpt_plan_type: claims.auth.and_then(|a| a.chatgpt_plan_type),
raw_jwt: id_token.to_string(),
})
}
fn deserialize_id_token<'de, D>(deserializer: D) -> Result<IdTokenInfo, D::Error>
where
D: serde::Deserializer<'de>,
{
let s = String::deserialize(deserializer)?;
parse_id_token(&s).map_err(serde::de::Error::custom)
}
fn serialize_id_token<S>(id_token: &IdTokenInfo, serializer: S) -> Result<S::Ok, S::Error>
where
S: serde::Serializer,
{
serializer.serialize_str(&id_token.raw_jwt)
}
#[cfg(test)]
mod tests {
use super::*;
use serde::Serialize;
#[test]
fn id_token_info_parses_email_and_plan() {
#[derive(Serialize)]
struct Header {
alg: &'static str,
typ: &'static str,
}
let header = Header {
alg: "none",
typ: "JWT",
};
let payload = serde_json::json!({
"email": "user@example.com",
"https://api.openai.com/auth": {
"chatgpt_plan_type": "pro"
}
});
fn b64url_no_pad(bytes: &[u8]) -> String {
base64::engine::general_purpose::URL_SAFE_NO_PAD.encode(bytes)
}
let header_b64 = b64url_no_pad(&serde_json::to_vec(&header).unwrap());
let payload_b64 = b64url_no_pad(&serde_json::to_vec(&payload).unwrap());
let signature_b64 = b64url_no_pad(b"sig");
let fake_jwt = format!("{header_b64}.{payload_b64}.{signature_b64}");
let info = parse_id_token(&fake_jwt).expect("should parse");
assert_eq!(info.email.as_deref(), Some("user@example.com"));
assert_eq!(info.get_chatgpt_plan_type().as_deref(), Some("Pro"));
}
#[test]
fn id_token_info_handles_missing_fields() {
#[derive(Serialize)]
struct Header {
alg: &'static str,
typ: &'static str,
}
let header = Header {
alg: "none",
typ: "JWT",
};
let payload = serde_json::json!({ "sub": "123" });
fn b64url_no_pad(bytes: &[u8]) -> String {
base64::engine::general_purpose::URL_SAFE_NO_PAD.encode(bytes)
}
let header_b64 = b64url_no_pad(&serde_json::to_vec(&header).unwrap());
let payload_b64 = b64url_no_pad(&serde_json::to_vec(&payload).unwrap());
let signature_b64 = b64url_no_pad(b"sig");
let fake_jwt = format!("{header_b64}.{payload_b64}.{signature_b64}");
let info = parse_id_token(&fake_jwt).expect("should parse");
assert!(info.email.is_none());
assert!(info.get_chatgpt_plan_type().is_none());
}
}
@@ -0,0 +1,896 @@
use std::collections::HashMap;
use std::fs;
use std::path::Path;
use std::path::PathBuf;
use std::process::Command;
use anyhow::Context;
use anyhow::Result;
use anyhow::anyhow;
use sha1::digest::Output;
use uuid::Uuid;
use codex_protocol::protocol::FileChange;
const ZERO_OID: &str = "0000000000000000000000000000000000000000";
const DEV_NULL: &str = "/dev/null";
struct BaselineFileInfo {
path: PathBuf,
content: Vec<u8>,
mode: FileMode,
oid: String,
}
/// Tracks sets of changes to files and exposes the overall unified diff.
/// Internally, the way this works is now:
/// 1. Maintain an in-memory baseline snapshot of files when they are first seen.
/// For new additions, do not create a baseline so that diffs are shown as proper additions (using /dev/null).
/// 2. Keep a stable internal filename (uuid) per external path for rename tracking.
/// 3. To compute the aggregated unified diff, compare each baseline snapshot to the current file on disk entirely in-memory
/// using the `similar` crate and emit unified diffs with rewritten external paths.
#[derive(Default)]
pub struct TurnDiffTracker {
/// Map external path -> internal filename (uuid).
external_to_temp_name: HashMap<PathBuf, String>,
/// Internal filename -> baseline file info.
baseline_file_info: HashMap<String, BaselineFileInfo>,
/// Internal filename -> external path as of current accumulated state (after applying all changes).
/// This is where renames are tracked.
temp_name_to_current_path: HashMap<String, PathBuf>,
/// Cache of known git worktree roots to avoid repeated filesystem walks.
git_root_cache: Vec<PathBuf>,
}
impl TurnDiffTracker {
pub fn new() -> Self {
Self::default()
}
/// Front-run apply patch calls to track the starting contents of any modified files.
/// - Creates an in-memory baseline snapshot for files that already exist on disk when first seen.
/// - For additions, we intentionally do not create a baseline snapshot so that diffs are proper additions.
/// - Also updates internal mappings for move/rename events.
pub fn on_patch_begin(&mut self, changes: &HashMap<PathBuf, FileChange>) {
for (path, change) in changes.iter() {
// Ensure a stable internal filename exists for this external path.
if !self.external_to_temp_name.contains_key(path.as_path()) {
let internal = Uuid::new_v4().to_string();
self.external_to_temp_name
.insert(path.clone(), internal.clone());
self.temp_name_to_current_path
.insert(internal.clone(), path.clone());
// If the file exists on disk now, snapshot as baseline; else leave missing to represent /dev/null.
let baseline_file_info = if path.exists() {
let mode = file_mode_for_path(path);
let mode_val = mode.unwrap_or(FileMode::Regular);
let content = blob_bytes(path, mode_val).unwrap_or_default();
let oid = if mode == Some(FileMode::Symlink) {
format!("{:x}", git_blob_sha1_hex_bytes(&content))
} else {
self.git_blob_oid_for_path(path)
.unwrap_or_else(|| format!("{:x}", git_blob_sha1_hex_bytes(&content)))
};
Some(BaselineFileInfo {
path: path.clone(),
content,
mode: mode_val,
oid,
})
} else {
Some(BaselineFileInfo {
path: path.clone(),
content: vec![],
mode: FileMode::Regular,
oid: ZERO_OID.to_string(),
})
};
if let Some(baseline_file_info) = baseline_file_info {
self.baseline_file_info
.insert(internal.clone(), baseline_file_info);
}
}
// Track rename/move in current mapping if provided in an Update.
if let FileChange::Update {
move_path: Some(dest),
..
} = change
{
let uuid_filename = match self.external_to_temp_name.get(path.as_path()) {
Some(i) => i.clone(),
None => {
// This should be rare, but if we haven't mapped the source, create it with no baseline.
let i = Uuid::new_v4().to_string();
self.baseline_file_info.insert(
i.clone(),
BaselineFileInfo {
path: path.clone(),
content: vec![],
mode: FileMode::Regular,
oid: ZERO_OID.to_string(),
},
);
i
}
};
// Update current external mapping for temp file name.
self.temp_name_to_current_path
.insert(uuid_filename.clone(), dest.clone());
// Update forward file_mapping: external current -> internal name.
self.external_to_temp_name.remove(path);
self.external_to_temp_name
.insert(dest.clone(), uuid_filename);
};
}
}
fn get_path_for_internal(&self, internal: &str) -> Option<PathBuf> {
self.temp_name_to_current_path
.get(internal)
.cloned()
.or_else(|| {
self.baseline_file_info
.get(internal)
.map(|info| info.path.clone())
})
}
/// Find the git worktree root for a file/directory by walking up to the first ancestor containing a `.git` entry.
/// Uses a simple cache of known roots and avoids negative-result caching for simplicity.
fn find_git_root_cached(&mut self, start: &Path) -> Option<PathBuf> {
let dir = if start.is_dir() {
start
} else {
start.parent()?
};
// Fast path: if any cached root is an ancestor of this path, use it.
if let Some(root) = self
.git_root_cache
.iter()
.find(|r| dir.starts_with(r))
.cloned()
{
return Some(root);
}
// Walk up to find a `.git` marker.
let mut cur = dir.to_path_buf();
loop {
let git_marker = cur.join(".git");
if git_marker.is_dir() || git_marker.is_file() {
if !self.git_root_cache.iter().any(|r| r == &cur) {
self.git_root_cache.push(cur.clone());
}
return Some(cur);
}
// On Windows, avoid walking above the drive or UNC share root.
#[cfg(windows)]
{
if is_windows_drive_or_unc_root(&cur) {
return None;
}
}
if let Some(parent) = cur.parent() {
cur = parent.to_path_buf();
} else {
return None;
}
}
}
/// Return a display string for `path` relative to its git root if found, else absolute.
fn relative_to_git_root_str(&mut self, path: &Path) -> String {
let s = if let Some(root) = self.find_git_root_cached(path) {
if let Ok(rel) = path.strip_prefix(&root) {
rel.display().to_string()
} else {
path.display().to_string()
}
} else {
path.display().to_string()
};
s.replace('\\', "/")
}
/// Ask git to compute the blob SHA-1 for the file at `path` within its repository.
/// Returns None if no repository is found or git invocation fails.
fn git_blob_oid_for_path(&mut self, path: &Path) -> Option<String> {
let root = self.find_git_root_cached(path)?;
// Compute a path relative to the repo root for better portability across platforms.
let rel = path.strip_prefix(&root).unwrap_or(path);
let output = Command::new("git")
.arg("-C")
.arg(&root)
.arg("hash-object")
.arg("--")
.arg(rel)
.output()
.ok()?;
if !output.status.success() {
return None;
}
let s = String::from_utf8_lossy(&output.stdout).trim().to_string();
if s.len() == 40 { Some(s) } else { None }
}
/// Recompute the aggregated unified diff by comparing all of the in-memory snapshots that were
/// collected before the first time they were touched by apply_patch during this turn with
/// the current repo state.
pub fn get_unified_diff(&mut self) -> Result<Option<String>> {
let mut aggregated = String::new();
// Compute diffs per tracked internal file in a stable order by external path.
let mut baseline_file_names: Vec<String> =
self.baseline_file_info.keys().cloned().collect();
// Sort lexicographically by full repo-relative path to match git behavior.
baseline_file_names.sort_by_key(|internal| {
self.get_path_for_internal(internal)
.map(|p| self.relative_to_git_root_str(&p))
.unwrap_or_default()
});
for internal in baseline_file_names {
aggregated.push_str(self.get_file_diff(&internal).as_str());
if !aggregated.ends_with('\n') {
aggregated.push('\n');
}
}
if aggregated.trim().is_empty() {
Ok(None)
} else {
Ok(Some(aggregated))
}
}
fn get_file_diff(&mut self, internal_file_name: &str) -> String {
let mut aggregated = String::new();
// Snapshot lightweight fields only.
let (baseline_external_path, baseline_mode, left_oid) = {
if let Some(info) = self.baseline_file_info.get(internal_file_name) {
(info.path.clone(), info.mode, info.oid.clone())
} else {
(PathBuf::new(), FileMode::Regular, ZERO_OID.to_string())
}
};
let current_external_path = match self.get_path_for_internal(internal_file_name) {
Some(p) => p,
None => return aggregated,
};
let current_mode = file_mode_for_path(&current_external_path).unwrap_or(FileMode::Regular);
let right_bytes = blob_bytes(&current_external_path, current_mode);
// Compute displays with &mut self before borrowing any baseline content.
let left_display = self.relative_to_git_root_str(&baseline_external_path);
let right_display = self.relative_to_git_root_str(&current_external_path);
// Compute right oid before borrowing baseline content.
let right_oid = if let Some(b) = right_bytes.as_ref() {
if current_mode == FileMode::Symlink {
format!("{:x}", git_blob_sha1_hex_bytes(b))
} else {
self.git_blob_oid_for_path(&current_external_path)
.unwrap_or_else(|| format!("{:x}", git_blob_sha1_hex_bytes(b)))
}
} else {
ZERO_OID.to_string()
};
// Borrow baseline content only after all &mut self uses are done.
let left_present = left_oid.as_str() != ZERO_OID;
let left_bytes: Option<&[u8]> = if left_present {
self.baseline_file_info
.get(internal_file_name)
.map(|i| i.content.as_slice())
} else {
None
};
// Fast path: identical bytes or both missing.
if left_bytes == right_bytes.as_deref() {
return aggregated;
}
aggregated.push_str(&format!("diff --git a/{left_display} b/{right_display}\n"));
let is_add = !left_present && right_bytes.is_some();
let is_delete = left_present && right_bytes.is_none();
if is_add {
aggregated.push_str(&format!("new file mode {current_mode}\n"));
} else if is_delete {
aggregated.push_str(&format!("deleted file mode {baseline_mode}\n"));
} else if baseline_mode != current_mode {
aggregated.push_str(&format!("old mode {baseline_mode}\n"));
aggregated.push_str(&format!("new mode {current_mode}\n"));
}
let left_text = left_bytes.and_then(|b| std::str::from_utf8(b).ok());
let right_text = right_bytes
.as_deref()
.and_then(|b| std::str::from_utf8(b).ok());
let can_text_diff = matches!(
(left_text, right_text, is_add, is_delete),
(Some(_), Some(_), _, _) | (_, Some(_), true, _) | (Some(_), _, _, true)
);
if can_text_diff {
let l = left_text.unwrap_or("");
let r = right_text.unwrap_or("");
aggregated.push_str(&format!("index {left_oid}..{right_oid}\n"));
let old_header = if left_present {
format!("a/{left_display}")
} else {
DEV_NULL.to_string()
};
let new_header = if right_bytes.is_some() {
format!("b/{right_display}")
} else {
DEV_NULL.to_string()
};
let diff = similar::TextDiff::from_lines(l, r);
let unified = diff
.unified_diff()
.context_radius(3)
.header(&old_header, &new_header)
.to_string();
aggregated.push_str(&unified);
} else {
aggregated.push_str(&format!("index {left_oid}..{right_oid}\n"));
let old_header = if left_present {
format!("a/{left_display}")
} else {
DEV_NULL.to_string()
};
let new_header = if right_bytes.is_some() {
format!("b/{right_display}")
} else {
DEV_NULL.to_string()
};
aggregated.push_str(&format!("--- {old_header}\n"));
aggregated.push_str(&format!("+++ {new_header}\n"));
aggregated.push_str("Binary files differ\n");
}
aggregated
}
}
/// Compute the Git SHA-1 blob object ID for the given content (bytes).
fn git_blob_sha1_hex_bytes(data: &[u8]) -> Output<sha1::Sha1> {
// Git blob hash is sha1 of: "blob <len>\0<data>"
let header = format!("blob {}\0", data.len());
use sha1::Digest;
let mut hasher = sha1::Sha1::new();
hasher.update(header.as_bytes());
hasher.update(data);
hasher.finalize()
}
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
enum FileMode {
Regular,
#[cfg(unix)]
Executable,
Symlink,
}
impl FileMode {
fn as_str(self) -> &'static str {
match self {
FileMode::Regular => "100644",
#[cfg(unix)]
FileMode::Executable => "100755",
FileMode::Symlink => "120000",
}
}
}
impl std::fmt::Display for FileMode {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
f.write_str(self.as_str())
}
}
#[cfg(unix)]
fn file_mode_for_path(path: &Path) -> Option<FileMode> {
use std::os::unix::fs::PermissionsExt;
let meta = fs::symlink_metadata(path).ok()?;
let ft = meta.file_type();
if ft.is_symlink() {
return Some(FileMode::Symlink);
}
let mode = meta.permissions().mode();
let is_exec = (mode & 0o111) != 0;
Some(if is_exec {
FileMode::Executable
} else {
FileMode::Regular
})
}
#[cfg(not(unix))]
fn file_mode_for_path(_path: &Path) -> Option<FileMode> {
// Default to non-executable on non-unix.
Some(FileMode::Regular)
}
fn blob_bytes(path: &Path, mode: FileMode) -> Option<Vec<u8>> {
if path.exists() {
let contents = if mode == FileMode::Symlink {
symlink_blob_bytes(path)
.ok_or_else(|| anyhow!("failed to read symlink target for {}", path.display()))
} else {
fs::read(path)
.with_context(|| format!("failed to read current file for diff {}", path.display()))
};
contents.ok()
} else {
None
}
}
#[cfg(unix)]
fn symlink_blob_bytes(path: &Path) -> Option<Vec<u8>> {
use std::os::unix::ffi::OsStrExt;
let target = std::fs::read_link(path).ok()?;
Some(target.as_os_str().as_bytes().to_vec())
}
#[cfg(not(unix))]
fn symlink_blob_bytes(_path: &Path) -> Option<Vec<u8>> {
None
}
#[cfg(windows)]
fn is_windows_drive_or_unc_root(p: &std::path::Path) -> bool {
use std::path::Component;
let mut comps = p.components();
matches!(
(comps.next(), comps.next(), comps.next()),
(Some(Component::Prefix(_)), Some(Component::RootDir), None)
)
}
#[cfg(test)]
mod tests {
use super::*;
use pretty_assertions::assert_eq;
use tempfile::tempdir;
/// Compute the Git SHA-1 blob object ID for the given content (string).
/// This delegates to the bytes version to avoid UTF-8 lossy conversions here.
fn git_blob_sha1_hex(data: &str) -> String {
format!("{:x}", git_blob_sha1_hex_bytes(data.as_bytes()))
}
fn normalize_diff_for_test(input: &str, root: &Path) -> String {
let root_str = root.display().to_string().replace('\\', "/");
let replaced = input.replace(&root_str, "<TMP>");
// Split into blocks on lines starting with "diff --git ", sort blocks for determinism, and rejoin
let mut blocks: Vec<String> = Vec::new();
let mut current = String::new();
for line in replaced.lines() {
if line.starts_with("diff --git ") && !current.is_empty() {
blocks.push(current);
current = String::new();
}
if !current.is_empty() {
current.push('\n');
}
current.push_str(line);
}
if !current.is_empty() {
blocks.push(current);
}
blocks.sort();
let mut out = blocks.join("\n");
if !out.ends_with('\n') {
out.push('\n');
}
out
}
#[test]
fn accumulates_add_and_update() {
let mut acc = TurnDiffTracker::new();
let dir = tempdir().unwrap();
let file = dir.path().join("a.txt");
// First patch: add file (baseline should be /dev/null).
let add_changes = HashMap::from([(
file.clone(),
FileChange::Add {
content: "foo\n".to_string(),
},
)]);
acc.on_patch_begin(&add_changes);
// Simulate apply: create the file on disk.
fs::write(&file, "foo\n").unwrap();
let first = acc.get_unified_diff().unwrap().unwrap();
let first = normalize_diff_for_test(&first, dir.path());
let expected_first = {
let mode = file_mode_for_path(&file).unwrap_or(FileMode::Regular);
let right_oid = git_blob_sha1_hex("foo\n");
format!(
r#"diff --git a/<TMP>/a.txt b/<TMP>/a.txt
new file mode {mode}
index {ZERO_OID}..{right_oid}
--- {DEV_NULL}
+++ b/<TMP>/a.txt
@@ -0,0 +1 @@
+foo
"#,
)
};
assert_eq!(first, expected_first);
// Second patch: update the file on disk.
let update_changes = HashMap::from([(
file.clone(),
FileChange::Update {
unified_diff: "".to_owned(),
move_path: None,
},
)]);
acc.on_patch_begin(&update_changes);
// Simulate apply: append a new line.
fs::write(&file, "foo\nbar\n").unwrap();
let combined = acc.get_unified_diff().unwrap().unwrap();
let combined = normalize_diff_for_test(&combined, dir.path());
let expected_combined = {
let mode = file_mode_for_path(&file).unwrap_or(FileMode::Regular);
let right_oid = git_blob_sha1_hex("foo\nbar\n");
format!(
r#"diff --git a/<TMP>/a.txt b/<TMP>/a.txt
new file mode {mode}
index {ZERO_OID}..{right_oid}
--- {DEV_NULL}
+++ b/<TMP>/a.txt
@@ -0,0 +1,2 @@
+foo
+bar
"#,
)
};
assert_eq!(combined, expected_combined);
}
#[test]
fn accumulates_delete() {
let dir = tempdir().unwrap();
let file = dir.path().join("b.txt");
fs::write(&file, "x\n").unwrap();
let mut acc = TurnDiffTracker::new();
let del_changes = HashMap::from([(
file.clone(),
FileChange::Delete {
content: "x\n".to_string(),
},
)]);
acc.on_patch_begin(&del_changes);
// Simulate apply: delete the file from disk.
let baseline_mode = file_mode_for_path(&file).unwrap_or(FileMode::Regular);
fs::remove_file(&file).unwrap();
let diff = acc.get_unified_diff().unwrap().unwrap();
let diff = normalize_diff_for_test(&diff, dir.path());
let expected = {
let left_oid = git_blob_sha1_hex("x\n");
format!(
r#"diff --git a/<TMP>/b.txt b/<TMP>/b.txt
deleted file mode {baseline_mode}
index {left_oid}..{ZERO_OID}
--- a/<TMP>/b.txt
+++ {DEV_NULL}
@@ -1 +0,0 @@
-x
"#,
)
};
assert_eq!(diff, expected);
}
#[test]
fn accumulates_move_and_update() {
let dir = tempdir().unwrap();
let src = dir.path().join("src.txt");
let dest = dir.path().join("dst.txt");
fs::write(&src, "line\n").unwrap();
let mut acc = TurnDiffTracker::new();
let mv_changes = HashMap::from([(
src.clone(),
FileChange::Update {
unified_diff: "".to_owned(),
move_path: Some(dest.clone()),
},
)]);
acc.on_patch_begin(&mv_changes);
// Simulate apply: move and update content.
fs::rename(&src, &dest).unwrap();
fs::write(&dest, "line2\n").unwrap();
let out = acc.get_unified_diff().unwrap().unwrap();
let out = normalize_diff_for_test(&out, dir.path());
let expected = {
let left_oid = git_blob_sha1_hex("line\n");
let right_oid = git_blob_sha1_hex("line2\n");
format!(
r#"diff --git a/<TMP>/src.txt b/<TMP>/dst.txt
index {left_oid}..{right_oid}
--- a/<TMP>/src.txt
+++ b/<TMP>/dst.txt
@@ -1 +1 @@
-line
+line2
"#
)
};
assert_eq!(out, expected);
}
#[test]
fn move_without_1change_yields_no_diff() {
let dir = tempdir().unwrap();
let src = dir.path().join("moved.txt");
let dest = dir.path().join("renamed.txt");
fs::write(&src, "same\n").unwrap();
let mut acc = TurnDiffTracker::new();
let mv_changes = HashMap::from([(
src.clone(),
FileChange::Update {
unified_diff: "".to_owned(),
move_path: Some(dest.clone()),
},
)]);
acc.on_patch_begin(&mv_changes);
// Simulate apply: move only, no content change.
fs::rename(&src, &dest).unwrap();
let diff = acc.get_unified_diff().unwrap();
assert_eq!(diff, None);
}
#[test]
fn move_declared_but_file_only_appears_at_dest_is_add() {
let dir = tempdir().unwrap();
let src = dir.path().join("src.txt");
let dest = dir.path().join("dest.txt");
let mut acc = TurnDiffTracker::new();
let mv = HashMap::from([(
src,
FileChange::Update {
unified_diff: "".into(),
move_path: Some(dest.clone()),
},
)]);
acc.on_patch_begin(&mv);
// No file existed initially; create only dest
fs::write(&dest, "hello\n").unwrap();
let diff = acc.get_unified_diff().unwrap().unwrap();
let diff = normalize_diff_for_test(&diff, dir.path());
let expected = {
let mode = file_mode_for_path(&dest).unwrap_or(FileMode::Regular);
let right_oid = git_blob_sha1_hex("hello\n");
format!(
r#"diff --git a/<TMP>/src.txt b/<TMP>/dest.txt
new file mode {mode}
index {ZERO_OID}..{right_oid}
--- {DEV_NULL}
+++ b/<TMP>/dest.txt
@@ -0,0 +1 @@
+hello
"#,
)
};
assert_eq!(diff, expected);
}
#[test]
fn update_persists_across_new_baseline_for_new_file() {
let dir = tempdir().unwrap();
let a = dir.path().join("a.txt");
let b = dir.path().join("b.txt");
fs::write(&a, "foo\n").unwrap();
fs::write(&b, "z\n").unwrap();
let mut acc = TurnDiffTracker::new();
// First: update existing a.txt (baseline snapshot is created for a).
let update_a = HashMap::from([(
a.clone(),
FileChange::Update {
unified_diff: "".to_owned(),
move_path: None,
},
)]);
acc.on_patch_begin(&update_a);
// Simulate apply: modify a.txt on disk.
fs::write(&a, "foo\nbar\n").unwrap();
let first = acc.get_unified_diff().unwrap().unwrap();
let first = normalize_diff_for_test(&first, dir.path());
let expected_first = {
let left_oid = git_blob_sha1_hex("foo\n");
let right_oid = git_blob_sha1_hex("foo\nbar\n");
format!(
r#"diff --git a/<TMP>/a.txt b/<TMP>/a.txt
index {left_oid}..{right_oid}
--- a/<TMP>/a.txt
+++ b/<TMP>/a.txt
@@ -1 +1,2 @@
foo
+bar
"#
)
};
assert_eq!(first, expected_first);
// Next: introduce a brand-new path b.txt into baseline snapshots via a delete change.
let del_b = HashMap::from([(
b.clone(),
FileChange::Delete {
content: "z\n".to_string(),
},
)]);
acc.on_patch_begin(&del_b);
// Simulate apply: delete b.txt.
let baseline_mode = file_mode_for_path(&b).unwrap_or(FileMode::Regular);
fs::remove_file(&b).unwrap();
let combined = acc.get_unified_diff().unwrap().unwrap();
let combined = normalize_diff_for_test(&combined, dir.path());
let expected = {
let left_oid_a = git_blob_sha1_hex("foo\n");
let right_oid_a = git_blob_sha1_hex("foo\nbar\n");
let left_oid_b = git_blob_sha1_hex("z\n");
format!(
r#"diff --git a/<TMP>/a.txt b/<TMP>/a.txt
index {left_oid_a}..{right_oid_a}
--- a/<TMP>/a.txt
+++ b/<TMP>/a.txt
@@ -1 +1,2 @@
foo
+bar
diff --git a/<TMP>/b.txt b/<TMP>/b.txt
deleted file mode {baseline_mode}
index {left_oid_b}..{ZERO_OID}
--- a/<TMP>/b.txt
+++ {DEV_NULL}
@@ -1 +0,0 @@
-z
"#,
)
};
assert_eq!(combined, expected);
}
#[test]
fn binary_files_differ_update() {
let dir = tempdir().unwrap();
let file = dir.path().join("bin.dat");
// Initial non-UTF8 bytes
let left_bytes: Vec<u8> = vec![0xff, 0xfe, 0xfd, 0x00];
// Updated non-UTF8 bytes
let right_bytes: Vec<u8> = vec![0x01, 0x02, 0x03, 0x00];
fs::write(&file, &left_bytes).unwrap();
let mut acc = TurnDiffTracker::new();
let update_changes = HashMap::from([(
file.clone(),
FileChange::Update {
unified_diff: "".to_owned(),
move_path: None,
},
)]);
acc.on_patch_begin(&update_changes);
// Apply update on disk
fs::write(&file, &right_bytes).unwrap();
let diff = acc.get_unified_diff().unwrap().unwrap();
let diff = normalize_diff_for_test(&diff, dir.path());
let expected = {
let left_oid = format!("{:x}", git_blob_sha1_hex_bytes(&left_bytes));
let right_oid = format!("{:x}", git_blob_sha1_hex_bytes(&right_bytes));
format!(
r#"diff --git a/<TMP>/bin.dat b/<TMP>/bin.dat
index {left_oid}..{right_oid}
--- a/<TMP>/bin.dat
+++ b/<TMP>/bin.dat
Binary files differ
"#
)
};
assert_eq!(diff, expected);
}
#[test]
fn filenames_with_spaces_add_and_update() {
let mut acc = TurnDiffTracker::new();
let dir = tempdir().unwrap();
let file = dir.path().join("name with spaces.txt");
// First patch: add file (baseline should be /dev/null).
let add_changes = HashMap::from([(
file.clone(),
FileChange::Add {
content: "foo\n".to_string(),
},
)]);
acc.on_patch_begin(&add_changes);
// Simulate apply: create the file on disk.
fs::write(&file, "foo\n").unwrap();
let first = acc.get_unified_diff().unwrap().unwrap();
let first = normalize_diff_for_test(&first, dir.path());
let expected_first = {
let mode = file_mode_for_path(&file).unwrap_or(FileMode::Regular);
let right_oid = git_blob_sha1_hex("foo\n");
format!(
r#"diff --git a/<TMP>/name with spaces.txt b/<TMP>/name with spaces.txt
new file mode {mode}
index {ZERO_OID}..{right_oid}
--- {DEV_NULL}
+++ b/<TMP>/name with spaces.txt
@@ -0,0 +1 @@
+foo
"#,
)
};
assert_eq!(first, expected_first);
// Second patch: update the file on disk.
let update_changes = HashMap::from([(
file.clone(),
FileChange::Update {
unified_diff: "".to_owned(),
move_path: None,
},
)]);
acc.on_patch_begin(&update_changes);
// Simulate apply: append a new line with a space.
fs::write(&file, "foo\nbar baz\n").unwrap();
let combined = acc.get_unified_diff().unwrap().unwrap();
let combined = normalize_diff_for_test(&combined, dir.path());
let expected_combined = {
let mode = file_mode_for_path(&file).unwrap_or(FileMode::Regular);
let right_oid = git_blob_sha1_hex("foo\nbar baz\n");
format!(
r#"diff --git a/<TMP>/name with spaces.txt b/<TMP>/name with spaces.txt
new file mode {mode}
index {ZERO_OID}..{right_oid}
--- {DEV_NULL}
+++ b/<TMP>/name with spaces.txt
@@ -0,0 +1,2 @@
+foo
+bar baz
"#,
)
};
assert_eq!(combined, expected_combined);
}
}
+30 -67
View File
@@ -1,10 +1,21 @@
use std::collections::HashMap;
use std::path::PathBuf;
use std::sync::Arc;
use anyhow::Result;
use async_trait::async_trait;
use codex_agent::notifications::UserNotification;
use codex_agent::services::CredentialsProvider;
use codex_agent::services::McpInterface;
use codex_agent::services::Notifier;
use codex_agent::services::ProviderAuth;
use codex_agent::services::RolloutSink;
use codex_agent::services::SandboxManager;
use codex_agent::token_data::PlanType;
use codex_protocol::mcp_protocol::AuthMode;
use mcp_types::CallToolResult;
use mcp_types::Tool;
use serde_json::Value;
use std::collections::HashMap;
use std::path::PathBuf;
use crate::auth::AuthManager;
use crate::auth::CodexAuth;
@@ -18,21 +29,31 @@ use crate::unified_exec::UnifiedExecError;
use crate::unified_exec::UnifiedExecRequest;
use crate::unified_exec::UnifiedExecResult;
use crate::unified_exec::UnifiedExecSessionManager;
use crate::user_notification::UserNotification;
use crate::user_notification::UserNotifier;
/// Provides access to credentials required when talking to model providers.
#[async_trait]
pub trait CredentialsProvider: Send + Sync {
fn auth(&self) -> Option<CodexAuth>;
impl ProviderAuth for CodexAuth {
fn mode(&self) -> AuthMode {
self.mode
}
async fn refresh_token(&self) -> std::io::Result<Option<String>>;
async fn access_token(&self) -> std::io::Result<String> {
self.get_token().await
}
fn account_id(&self) -> Option<String> {
self.get_account_id()
}
fn plan_type(&self) -> Option<PlanType> {
self.get_plan_type()
}
}
#[async_trait]
impl CredentialsProvider for AuthManager {
fn auth(&self) -> Option<CodexAuth> {
AuthManager::auth(self)
fn auth(&self) -> Option<Arc<dyn ProviderAuth>> {
AuthManager::auth(self).map(|auth| Arc::new(auth) as Arc<dyn ProviderAuth>)
}
async fn refresh_token(&self) -> std::io::Result<Option<String>> {
@@ -40,32 +61,12 @@ impl CredentialsProvider for AuthManager {
}
}
/// Emits user-facing notifications for turn completion or other events.
pub trait Notifier: Send + Sync {
fn notify(&self, notification: &UserNotification);
}
impl Notifier for UserNotifier {
fn notify(&self, notification: &UserNotification) {
UserNotifier::notify(self, notification);
}
}
/// Aggregates and dispatches MCP tool calls across configured servers.
#[async_trait]
pub trait McpInterface: Send + Sync {
fn list_all_tools(&self) -> HashMap<String, Tool>;
fn parse_tool_name(&self, tool_name: &str) -> Option<(String, String)>;
async fn call_tool(
&self,
server: &str,
tool: &str,
arguments: Option<Value>,
) -> Result<CallToolResult>;
}
#[async_trait]
impl McpInterface for McpConnectionManager {
fn list_all_tools(&self) -> HashMap<String, Tool> {
@@ -86,21 +87,6 @@ impl McpInterface for McpConnectionManager {
}
}
/// Persists rollout events for later inspection or replay.
#[async_trait]
pub trait RolloutSink: Send + Sync {
async fn record_items(
&self,
items: &[codex_protocol::protocol::RolloutItem],
) -> std::io::Result<()>;
async fn flush(&self) -> std::io::Result<()>;
async fn shutdown(&self) -> std::io::Result<()>;
fn get_rollout_path(&self) -> PathBuf;
}
#[async_trait]
impl RolloutSink for RolloutRecorder {
async fn record_items(
@@ -123,29 +109,6 @@ impl RolloutSink for RolloutRecorder {
}
}
/// Handles sandboxed exec orchestration, including long-running sessions.
#[async_trait]
pub trait SandboxManager: Send + Sync {
async fn handle_exec_command_request(
&self,
params: ExecCommandParams,
) -> Result<ExecCommandOutput, String>;
async fn handle_write_stdin_request(
&self,
params: WriteStdinParams,
) -> Result<ExecCommandOutput, String>;
async fn handle_unified_exec_request(
&self,
request: UnifiedExecRequest<'_>,
) -> Result<UnifiedExecResult, UnifiedExecError>;
fn codex_linux_sandbox_exe(&self) -> &Option<PathBuf>;
fn user_shell(&self) -> &crate::shell::Shell;
}
/// Default [`SandboxManager`] used by the CLI runtime. Wraps the existing exec
/// session managers and exposes their functionality via the trait-based
/// interface so other hosts can substitute different implementations.
+1 -1
View File
@@ -135,7 +135,7 @@ impl CodexAuth {
self.get_current_token_data().and_then(|t| t.account_id)
}
pub(crate) fn get_plan_type(&self) -> Option<PlanType> {
pub fn get_plan_type(&self) -> Option<PlanType> {
self.get_current_token_data()
.and_then(|t| t.id_token.chatgpt_plan_type)
}
+4 -5
View File
@@ -4,8 +4,7 @@ use std::path::Path;
use std::sync::OnceLock;
use std::time::Duration;
use crate::agent_services::CredentialsProvider;
use crate::auth::CodexAuth;
use crate::CredentialsProvider;
use bytes::Bytes;
use codex_protocol::mcp_protocol::AuthMode;
use codex_protocol::mcp_protocol::ConversationId;
@@ -298,8 +297,8 @@ impl ModelClient {
.json(payload_json);
if let Some(auth) = auth.as_ref()
&& auth.mode == AuthMode::ChatGPT
&& let Some(account_id) = auth.get_account_id()
&& auth.mode() == AuthMode::ChatGPT
&& let Some(account_id) = auth.account_id()
{
req_builder = req_builder.header("chatgpt-account-id", account_id);
}
@@ -385,7 +384,7 @@ impl ModelClient {
// token.
let plan_type = error
.plan_type
.or_else(|| auth.as_ref().and_then(CodexAuth::get_plan_type));
.or_else(|| auth.as_ref().and_then(|a| a.plan_type()));
let resets_in_seconds = error.resets_in_seconds;
let codex_err = CodexErr::UsageLimitReached(UsageLimitReachedError {
plan_type,
+5 -5
View File
@@ -39,14 +39,14 @@ use tracing::info;
use tracing::trace;
use tracing::warn;
use crate::CredentialsProvider;
use crate::McpInterface;
use crate::ModelProviderInfo;
use crate::Notifier;
use crate::RolloutSink;
use crate::SandboxManager;
use crate::agent_config::AgentConfig;
use crate::agent_services::CredentialsProvider;
use crate::agent_services::DefaultSandboxManager;
use crate::agent_services::McpInterface;
use crate::agent_services::Notifier;
use crate::agent_services::RolloutSink;
use crate::agent_services::SandboxManager;
use crate::apply_patch;
use crate::apply_patch::ApplyPatchExec;
use crate::apply_patch::InternalApplyPatchInvocation;
-1
View File
@@ -5,7 +5,6 @@ use crate::openai_tools::ResponsesApiTool;
pub use codex_agent::exec_command::ExecCommandOutput;
pub use codex_agent::exec_command::ExecCommandParams;
pub use codex_agent::exec_command::ExecCommandSession;
pub use codex_agent::exec_command::ExecSessionManager;
pub use codex_agent::exec_command::WriteStdinParams;
+1 -7
View File
@@ -1,7 +1 @@
use thiserror::Error;
#[derive(Debug, Error, PartialEq)]
pub enum FunctionCallError {
#[error("{0}")]
RespondToModel(String),
}
pub use codex_agent::function_tool::*;
+6 -5
View File
@@ -95,12 +95,7 @@ pub use codex_protocol::protocol;
pub use codex_protocol::config_types as protocol_config_types;
pub use agent_config::AgentConfig;
pub use agent_services::CredentialsProvider;
pub use agent_services::DefaultSandboxManager;
pub use agent_services::McpInterface;
pub use agent_services::Notifier;
pub use agent_services::RolloutSink;
pub use agent_services::SandboxManager;
pub use client::ModelClient;
pub use client_common::Prompt;
pub use client_common::REVIEW_PROMPT;
@@ -108,6 +103,12 @@ pub use client_common::ResponseEvent;
pub use client_common::ResponseStream;
pub use codex::compact::content_items_to_text;
pub use codex::compact::is_session_prefix_message;
pub use codex_agent::services::CredentialsProvider;
pub use codex_agent::services::McpInterface;
pub use codex_agent::services::Notifier;
pub use codex_agent::services::ProviderAuth;
pub use codex_agent::services::RolloutSink;
pub use codex_agent::services::SandboxManager;
pub use codex_protocol::models::ContentItem;
pub use codex_protocol::models::LocalShellAction;
pub use codex_protocol::models::LocalShellExecAction;
+11 -15
View File
@@ -6,11 +6,13 @@
//! key. These override or extend the defaults at runtime.
use crate::CodexAuth;
use crate::ProviderAuth;
use codex_protocol::mcp_protocol::AuthMode;
use serde::Deserialize;
use serde::Serialize;
use std::collections::HashMap;
use std::env::VarError;
use std::sync::Arc;
use std::time::Duration;
use crate::error::EnvVarError;
@@ -97,13 +99,13 @@ impl ModelProviderInfo {
///
/// If the provider declares an `env_key` but the variable is missing/empty, returns an [`Err`] identical to the
/// one produced by [`ModelProviderInfo::api_key`].
pub async fn create_request_builder<'a>(
&'a self,
client: &'a reqwest::Client,
auth: &Option<CodexAuth>,
pub async fn create_request_builder(
&self,
client: &reqwest::Client,
auth: &Option<Arc<dyn ProviderAuth>>,
) -> crate::error::Result<reqwest::RequestBuilder> {
let effective_auth = match self.api_key() {
Ok(Some(key)) => Some(CodexAuth::from_api_key(&key)),
let effective_auth: Option<Arc<dyn ProviderAuth>> = match self.api_key() {
Ok(Some(key)) => Some(Arc::new(CodexAuth::from_api_key(&key))),
Ok(None) => auth.clone(),
Err(err) => {
if auth.is_some() {
@@ -119,7 +121,7 @@ impl ModelProviderInfo {
let mut builder = client.post(url);
if let Some(auth) = effective_auth.as_ref() {
builder = builder.bearer_auth(auth.get_token().await?);
builder = builder.bearer_auth(auth.access_token().await?);
}
Ok(self.apply_http_headers(builder))
@@ -138,14 +140,8 @@ impl ModelProviderInfo {
})
}
pub(crate) fn get_full_url(&self, auth: &Option<CodexAuth>) -> String {
let default_base_url = if matches!(
auth,
Some(CodexAuth {
mode: AuthMode::ChatGPT,
..
})
) {
pub(crate) fn get_full_url(&self, auth: &Option<Arc<dyn ProviderAuth>>) -> String {
let default_base_url = if auth.as_ref().map(|a| a.mode()) == Some(AuthMode::ChatGPT) {
"https://chatgpt.com/backend-api/codex"
} else {
"https://api.openai.com/v1"
+1 -571
View File
@@ -1,571 +1 @@
use serde::Deserialize;
use serde::Serialize;
use shlex;
use std::path::PathBuf;
#[derive(Debug, PartialEq, Eq, Clone, Serialize, Deserialize)]
pub struct ZshShell {
pub(crate) shell_path: String,
pub(crate) zshrc_path: String,
}
#[derive(Debug, PartialEq, Eq, Clone, Serialize, Deserialize)]
pub struct BashShell {
pub(crate) shell_path: String,
pub(crate) bashrc_path: String,
}
#[derive(Debug, PartialEq, Eq, Clone, Serialize, Deserialize)]
pub struct PowerShellConfig {
pub(crate) exe: String, // Executable name or path, e.g. "pwsh" or "powershell.exe".
pub(crate) bash_exe_fallback: Option<PathBuf>, // In case the model generates a bash command.
}
#[derive(Debug, PartialEq, Eq, Clone, Serialize, Deserialize)]
pub enum Shell {
Zsh(ZshShell),
Bash(BashShell),
PowerShell(PowerShellConfig),
Unknown,
}
impl Shell {
pub fn format_default_shell_invocation(&self, command: Vec<String>) -> Option<Vec<String>> {
match self {
Shell::Zsh(zsh) => format_shell_invocation_with_rc(
command.as_slice(),
&zsh.shell_path,
&zsh.zshrc_path,
),
Shell::Bash(bash) => format_shell_invocation_with_rc(
command.as_slice(),
&bash.shell_path,
&bash.bashrc_path,
),
Shell::PowerShell(ps) => {
// If model generated a bash command, prefer a detected bash fallback
if let Some(script) = strip_bash_lc(command.as_slice()) {
return match &ps.bash_exe_fallback {
Some(bash) => Some(vec![
bash.to_string_lossy().to_string(),
"-lc".to_string(),
script,
]),
// No bash fallback → run the script under PowerShell.
// It will likely fail (except for some simple commands), but the error
// should give a clue to the model to fix upon retry that it's running under PowerShell.
None => Some(vec![
ps.exe.clone(),
"-NoProfile".to_string(),
"-Command".to_string(),
script,
]),
};
}
// Not a bash command. If model did not generate a PowerShell command,
// turn it into a PowerShell command.
let first = command.first().map(String::as_str);
if first != Some(ps.exe.as_str()) {
// TODO (CODEX_2900): Handle escaping newlines.
if command.iter().any(|a| a.contains('\n') || a.contains('\r')) {
return Some(command);
}
let joined = shlex::try_join(command.iter().map(String::as_str)).ok();
return joined.map(|arg| {
vec![
ps.exe.clone(),
"-NoProfile".to_string(),
"-Command".to_string(),
arg,
]
});
}
// Model generated a PowerShell command. Run it.
Some(command)
}
Shell::Unknown => None,
}
}
pub fn name(&self) -> Option<String> {
match self {
Shell::Zsh(zsh) => std::path::Path::new(&zsh.shell_path)
.file_name()
.map(|s| s.to_string_lossy().to_string()),
Shell::Bash(bash) => std::path::Path::new(&bash.shell_path)
.file_name()
.map(|s| s.to_string_lossy().to_string()),
Shell::PowerShell(ps) => Some(ps.exe.clone()),
Shell::Unknown => None,
}
}
}
fn format_shell_invocation_with_rc(
command: &[String],
shell_path: &str,
rc_path: &str,
) -> Option<Vec<String>> {
let joined = strip_bash_lc(command)
.or_else(|| shlex::try_join(command.iter().map(String::as_str)).ok())?;
let rc_command = if std::path::Path::new(rc_path).exists() {
format!("source {rc_path} && ({joined})")
} else {
joined
};
Some(vec![shell_path.to_string(), "-lc".to_string(), rc_command])
}
fn strip_bash_lc(command: &[String]) -> Option<String> {
match command {
// exactly three items
[first, second, third]
// first two must be "bash", "-lc"
if first == "bash" && second == "-lc" =>
{
Some(third.clone())
}
_ => None,
}
}
#[cfg(unix)]
fn detect_default_user_shell() -> Shell {
use libc::getpwuid;
use libc::getuid;
use std::ffi::CStr;
unsafe {
let uid = getuid();
let pw = getpwuid(uid);
if !pw.is_null() {
let shell_path = CStr::from_ptr((*pw).pw_shell)
.to_string_lossy()
.into_owned();
let home_path = CStr::from_ptr((*pw).pw_dir).to_string_lossy().into_owned();
if shell_path.ends_with("/zsh") {
return Shell::Zsh(ZshShell {
shell_path,
zshrc_path: format!("{home_path}/.zshrc"),
});
}
if shell_path.ends_with("/bash") {
return Shell::Bash(BashShell {
shell_path,
bashrc_path: format!("{home_path}/.bashrc"),
});
}
}
}
Shell::Unknown
}
#[cfg(unix)]
pub async fn default_user_shell() -> Shell {
detect_default_user_shell()
}
#[cfg(target_os = "windows")]
pub async fn default_user_shell() -> Shell {
use tokio::process::Command;
// Prefer PowerShell 7+ (`pwsh`) if available, otherwise fall back to Windows PowerShell.
let has_pwsh = Command::new("pwsh")
.arg("-NoLogo")
.arg("-NoProfile")
.arg("-Command")
.arg("$PSVersionTable.PSVersion.Major")
.output()
.await
.map(|o| o.status.success())
.unwrap_or(false);
let bash_exe = if Command::new("bash.exe")
.arg("--version")
.output()
.await
.ok()
.map(|o| o.status.success())
.unwrap_or(false)
{
which::which("bash.exe").ok()
} else {
None
};
if has_pwsh {
Shell::PowerShell(PowerShellConfig {
exe: "pwsh.exe".to_string(),
bash_exe_fallback: bash_exe,
})
} else {
Shell::PowerShell(PowerShellConfig {
exe: "powershell.exe".to_string(),
bash_exe_fallback: bash_exe,
})
}
}
#[cfg(all(not(target_os = "windows"), not(unix)))]
pub async fn default_user_shell() -> Shell {
Shell::Unknown
}
#[cfg(test)]
#[cfg(unix)]
mod tests {
use super::*;
use std::process::Command;
use std::string::ToString;
#[tokio::test]
async fn test_current_shell_detects_zsh() {
let shell = Command::new("sh")
.arg("-c")
.arg("echo $SHELL")
.output()
.unwrap();
let home = std::env::var("HOME").unwrap();
let shell_path = String::from_utf8_lossy(&shell.stdout).trim().to_string();
if shell_path.ends_with("/zsh") {
assert_eq!(
default_user_shell().await,
Shell::Zsh(ZshShell {
shell_path: shell_path.to_string(),
zshrc_path: format!("{home}/.zshrc",),
})
);
}
}
#[tokio::test]
async fn test_run_with_profile_zshrc_not_exists() {
let shell = Shell::Zsh(ZshShell {
shell_path: "/bin/zsh".to_string(),
zshrc_path: "/does/not/exist/.zshrc".to_string(),
});
let actual_cmd = shell.format_default_shell_invocation(vec!["myecho".to_string()]);
assert_eq!(
actual_cmd,
Some(vec![
"/bin/zsh".to_string(),
"-lc".to_string(),
"myecho".to_string()
])
);
}
#[tokio::test]
async fn test_run_with_profile_bashrc_not_exists() {
let shell = Shell::Bash(BashShell {
shell_path: "/bin/bash".to_string(),
bashrc_path: "/does/not/exist/.bashrc".to_string(),
});
let actual_cmd = shell.format_default_shell_invocation(vec!["myecho".to_string()]);
assert_eq!(
actual_cmd,
Some(vec![
"/bin/bash".to_string(),
"-lc".to_string(),
"myecho".to_string()
])
);
}
#[tokio::test]
async fn test_run_with_profile_bash_escaping_and_execution() {
let shell_path = "/bin/bash";
let cases = vec![
(
vec!["myecho"],
vec![shell_path, "-lc", "source BASHRC_PATH && (myecho)"],
Some("It works!\n"),
),
(
vec!["bash", "-lc", "echo 'single' \"double\""],
vec![
shell_path,
"-lc",
"source BASHRC_PATH && (echo 'single' \"double\")",
],
Some("single double\n"),
),
];
for (input, expected_cmd, expected_output) in cases {
use std::collections::HashMap;
use crate::exec::ExecParams;
use crate::exec::SandboxType;
use crate::exec::process_exec_tool_call;
use crate::protocol::SandboxPolicy;
let temp_home = tempfile::tempdir().unwrap();
let bashrc_path = temp_home.path().join(".bashrc");
std::fs::write(
&bashrc_path,
r#"
set -x
function myecho {
echo 'It works!'
}
"#,
)
.unwrap();
let shell = Shell::Bash(BashShell {
shell_path: shell_path.to_string(),
bashrc_path: bashrc_path.to_str().unwrap().to_string(),
});
let actual_cmd = shell
.format_default_shell_invocation(input.iter().map(ToString::to_string).collect());
let expected_cmd = expected_cmd
.iter()
.map(|s| s.replace("BASHRC_PATH", bashrc_path.to_str().unwrap()))
.collect();
assert_eq!(actual_cmd, Some(expected_cmd));
let output = process_exec_tool_call(
ExecParams {
command: actual_cmd.unwrap(),
cwd: PathBuf::from(temp_home.path()),
timeout_ms: None,
env: HashMap::from([(
"HOME".to_string(),
temp_home.path().to_str().unwrap().to_string(),
)]),
with_escalated_permissions: None,
justification: None,
},
SandboxType::None,
&SandboxPolicy::DangerFullAccess,
temp_home.path(),
&None,
None,
)
.await
.unwrap();
assert_eq!(output.exit_code, 0, "input: {input:?} output: {output:?}");
if let Some(expected) = expected_output {
assert_eq!(
output.stdout.text, expected,
"input: {input:?} output: {output:?}"
);
}
}
}
}
#[cfg(test)]
#[cfg(target_os = "macos")]
mod macos_tests {
use super::*;
use std::string::ToString;
#[tokio::test]
async fn test_run_with_profile_escaping_and_execution() {
let shell_path = "/bin/zsh";
let cases = vec![
(
vec!["myecho"],
vec![shell_path, "-lc", "source ZSHRC_PATH && (myecho)"],
Some("It works!\n"),
),
(
vec!["myecho"],
vec![shell_path, "-lc", "source ZSHRC_PATH && (myecho)"],
Some("It works!\n"),
),
(
vec!["bash", "-c", "echo 'single' \"double\""],
vec![
shell_path,
"-lc",
"source ZSHRC_PATH && (bash -c \"echo 'single' \\\"double\\\"\")",
],
Some("single double\n"),
),
(
vec!["bash", "-lc", "echo 'single' \"double\""],
vec![
shell_path,
"-lc",
"source ZSHRC_PATH && (echo 'single' \"double\")",
],
Some("single double\n"),
),
];
for (input, expected_cmd, expected_output) in cases {
use std::collections::HashMap;
use std::path::PathBuf;
use crate::exec::ExecParams;
use crate::exec::SandboxType;
use crate::exec::process_exec_tool_call;
use crate::protocol::SandboxPolicy;
// create a temp directory with a zshrc file in it
let temp_home = tempfile::tempdir().unwrap();
let zshrc_path = temp_home.path().join(".zshrc");
std::fs::write(
&zshrc_path,
r#"
set -x
function myecho {
echo 'It works!'
}
"#,
)
.unwrap();
let shell = Shell::Zsh(ZshShell {
shell_path: shell_path.to_string(),
zshrc_path: zshrc_path.to_str().unwrap().to_string(),
});
let actual_cmd = shell
.format_default_shell_invocation(input.iter().map(ToString::to_string).collect());
let expected_cmd = expected_cmd
.iter()
.map(|s| s.replace("ZSHRC_PATH", zshrc_path.to_str().unwrap()))
.collect();
assert_eq!(actual_cmd, Some(expected_cmd));
// Actually run the command and check output/exit code
let output = process_exec_tool_call(
ExecParams {
command: actual_cmd.unwrap(),
cwd: PathBuf::from(temp_home.path()),
timeout_ms: None,
env: HashMap::from([(
"HOME".to_string(),
temp_home.path().to_str().unwrap().to_string(),
)]),
with_escalated_permissions: None,
justification: None,
},
SandboxType::None,
&SandboxPolicy::DangerFullAccess,
temp_home.path(),
&None,
None,
)
.await
.unwrap();
assert_eq!(output.exit_code, 0, "input: {input:?} output: {output:?}");
if let Some(expected) = expected_output {
assert_eq!(
output.stdout.text, expected,
"input: {input:?} output: {output:?}"
);
}
}
}
}
#[cfg(test)]
#[cfg(target_os = "windows")]
mod tests_windows {
use super::*;
#[test]
fn test_format_default_shell_invocation_powershell() {
let cases = vec![
(
Shell::PowerShell(PowerShellConfig {
exe: "pwsh.exe".to_string(),
bash_exe_fallback: None,
}),
vec!["bash", "-lc", "echo hello"],
vec!["pwsh.exe", "-NoProfile", "-Command", "echo hello"],
),
(
Shell::PowerShell(PowerShellConfig {
exe: "powershell.exe".to_string(),
bash_exe_fallback: None,
}),
vec!["bash", "-lc", "echo hello"],
vec!["powershell.exe", "-NoProfile", "-Command", "echo hello"],
),
(
Shell::PowerShell(PowerShellConfig {
exe: "pwsh.exe".to_string(),
bash_exe_fallback: Some(PathBuf::from("bash.exe")),
}),
vec!["bash", "-lc", "echo hello"],
vec!["bash.exe", "-lc", "echo hello"],
),
(
Shell::PowerShell(PowerShellConfig {
exe: "pwsh.exe".to_string(),
bash_exe_fallback: Some(PathBuf::from("bash.exe")),
}),
vec![
"bash",
"-lc",
"apply_patch <<'EOF'\n*** Begin Patch\n*** Update File: destination_file.txt\n-original content\n+modified content\n*** End Patch\nEOF",
],
vec![
"bash.exe",
"-lc",
"apply_patch <<'EOF'\n*** Begin Patch\n*** Update File: destination_file.txt\n-original content\n+modified content\n*** End Patch\nEOF",
],
),
(
Shell::PowerShell(PowerShellConfig {
exe: "pwsh.exe".to_string(),
bash_exe_fallback: Some(PathBuf::from("bash.exe")),
}),
vec!["echo", "hello"],
vec!["pwsh.exe", "-NoProfile", "-Command", "echo hello"],
),
(
Shell::PowerShell(PowerShellConfig {
exe: "pwsh.exe".to_string(),
bash_exe_fallback: Some(PathBuf::from("bash.exe")),
}),
vec!["pwsh.exe", "-NoProfile", "-Command", "echo hello"],
vec!["pwsh.exe", "-NoProfile", "-Command", "echo hello"],
),
(
// TODO (CODEX_2900): Handle escaping newlines for powershell invocation.
Shell::PowerShell(PowerShellConfig {
exe: "powershell.exe".to_string(),
bash_exe_fallback: Some(PathBuf::from("bash.exe")),
}),
vec![
"codex-mcp-server.exe",
"--codex-run-as-apply-patch",
"*** Begin Patch\n*** Update File: C:\\Users\\person\\destination_file.txt\n-original content\n+modified content\n*** End Patch",
],
vec![
"codex-mcp-server.exe",
"--codex-run-as-apply-patch",
"*** Begin Patch\n*** Update File: C:\\Users\\person\\destination_file.txt\n-original content\n+modified content\n*** End Patch",
],
),
];
for (shell, input, expected_cmd) in cases {
let actual_cmd = shell
.format_default_shell_invocation(input.iter().map(|s| (*s).to_string()).collect());
assert_eq!(
actual_cmd,
Some(expected_cmd.iter().map(|s| (*s).to_string()).collect())
);
}
}
}
pub use codex_agent::shell::*;
+4 -4
View File
@@ -1,7 +1,7 @@
use crate::agent_services::McpInterface;
use crate::agent_services::Notifier;
use crate::agent_services::RolloutSink;
use crate::agent_services::SandboxManager;
use crate::McpInterface;
use crate::Notifier;
use crate::RolloutSink;
use crate::SandboxManager;
use std::sync::Arc;
use tokio::sync::Mutex;
+1 -182
View File
@@ -1,182 +1 @@
use base64::Engine;
use serde::Deserialize;
use serde::Serialize;
use thiserror::Error;
#[derive(Deserialize, Serialize, Clone, Debug, PartialEq, Default)]
pub struct TokenData {
/// Flat info parsed from the JWT in auth.json.
#[serde(
deserialize_with = "deserialize_id_token",
serialize_with = "serialize_id_token"
)]
pub id_token: IdTokenInfo,
/// This is a JWT.
pub access_token: String,
pub refresh_token: String,
pub account_id: Option<String>,
}
/// Flat subset of useful claims in id_token from auth.json.
#[derive(Debug, Clone, PartialEq, Eq, Default, Serialize, Deserialize)]
pub struct IdTokenInfo {
pub email: Option<String>,
/// The ChatGPT subscription plan type
/// (e.g., "free", "plus", "pro", "business", "enterprise", "edu").
/// (Note: values may vary by backend.)
pub(crate) chatgpt_plan_type: Option<PlanType>,
pub raw_jwt: String,
}
impl IdTokenInfo {
pub fn get_chatgpt_plan_type(&self) -> Option<String> {
self.chatgpt_plan_type.as_ref().map(|t| match t {
PlanType::Known(plan) => format!("{plan:?}"),
PlanType::Unknown(s) => s.clone(),
})
}
}
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
#[serde(untagged)]
pub(crate) enum PlanType {
Known(KnownPlan),
Unknown(String),
}
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "lowercase")]
pub(crate) enum KnownPlan {
Free,
Plus,
Pro,
Team,
Business,
Enterprise,
Edu,
}
#[derive(Deserialize)]
struct IdClaims {
#[serde(default)]
email: Option<String>,
#[serde(rename = "https://api.openai.com/auth", default)]
auth: Option<AuthClaims>,
}
#[derive(Deserialize)]
struct AuthClaims {
#[serde(default)]
chatgpt_plan_type: Option<PlanType>,
}
#[derive(Debug, Error)]
pub enum IdTokenInfoError {
#[error("invalid ID token format")]
InvalidFormat,
#[error(transparent)]
Base64(#[from] base64::DecodeError),
#[error(transparent)]
Json(#[from] serde_json::Error),
}
pub fn parse_id_token(id_token: &str) -> Result<IdTokenInfo, IdTokenInfoError> {
// JWT format: header.payload.signature
let mut parts = id_token.split('.');
let (_header_b64, payload_b64, _sig_b64) = match (parts.next(), parts.next(), parts.next()) {
(Some(h), Some(p), Some(s)) if !h.is_empty() && !p.is_empty() && !s.is_empty() => (h, p, s),
_ => return Err(IdTokenInfoError::InvalidFormat),
};
let payload_bytes = base64::engine::general_purpose::URL_SAFE_NO_PAD.decode(payload_b64)?;
let claims: IdClaims = serde_json::from_slice(&payload_bytes)?;
Ok(IdTokenInfo {
email: claims.email,
chatgpt_plan_type: claims.auth.and_then(|a| a.chatgpt_plan_type),
raw_jwt: id_token.to_string(),
})
}
fn deserialize_id_token<'de, D>(deserializer: D) -> Result<IdTokenInfo, D::Error>
where
D: serde::Deserializer<'de>,
{
let s = String::deserialize(deserializer)?;
parse_id_token(&s).map_err(serde::de::Error::custom)
}
fn serialize_id_token<S>(id_token: &IdTokenInfo, serializer: S) -> Result<S::Ok, S::Error>
where
S: serde::Serializer,
{
serializer.serialize_str(&id_token.raw_jwt)
}
#[cfg(test)]
mod tests {
use super::*;
use serde::Serialize;
#[test]
fn id_token_info_parses_email_and_plan() {
#[derive(Serialize)]
struct Header {
alg: &'static str,
typ: &'static str,
}
let header = Header {
alg: "none",
typ: "JWT",
};
let payload = serde_json::json!({
"email": "user@example.com",
"https://api.openai.com/auth": {
"chatgpt_plan_type": "pro"
}
});
fn b64url_no_pad(bytes: &[u8]) -> String {
base64::engine::general_purpose::URL_SAFE_NO_PAD.encode(bytes)
}
let header_b64 = b64url_no_pad(&serde_json::to_vec(&header).unwrap());
let payload_b64 = b64url_no_pad(&serde_json::to_vec(&payload).unwrap());
let signature_b64 = b64url_no_pad(b"sig");
let fake_jwt = format!("{header_b64}.{payload_b64}.{signature_b64}");
let info = parse_id_token(&fake_jwt).expect("should parse");
assert_eq!(info.email.as_deref(), Some("user@example.com"));
assert_eq!(info.get_chatgpt_plan_type().as_deref(), Some("Pro"));
}
#[test]
fn id_token_info_handles_missing_fields() {
#[derive(Serialize)]
struct Header {
alg: &'static str,
typ: &'static str,
}
let header = Header {
alg: "none",
typ: "JWT",
};
let payload = serde_json::json!({ "sub": "123" });
fn b64url_no_pad(bytes: &[u8]) -> String {
base64::engine::general_purpose::URL_SAFE_NO_PAD.encode(bytes)
}
let header_b64 = b64url_no_pad(&serde_json::to_vec(&header).unwrap());
let payload_b64 = b64url_no_pad(&serde_json::to_vec(&payload).unwrap());
let signature_b64 = b64url_no_pad(b"sig");
let fake_jwt = format!("{header_b64}.{payload_b64}.{signature_b64}");
let info = parse_id_token(&fake_jwt).expect("should parse");
assert!(info.email.is_none());
assert!(info.get_chatgpt_plan_type().is_none());
}
}
pub use codex_agent::token_data::*;
+1 -896
View File
@@ -1,896 +1 @@
use std::collections::HashMap;
use std::fs;
use std::path::Path;
use std::path::PathBuf;
use std::process::Command;
use anyhow::Context;
use anyhow::Result;
use anyhow::anyhow;
use sha1::digest::Output;
use uuid::Uuid;
use crate::protocol::FileChange;
const ZERO_OID: &str = "0000000000000000000000000000000000000000";
const DEV_NULL: &str = "/dev/null";
struct BaselineFileInfo {
path: PathBuf,
content: Vec<u8>,
mode: FileMode,
oid: String,
}
/// Tracks sets of changes to files and exposes the overall unified diff.
/// Internally, the way this works is now:
/// 1. Maintain an in-memory baseline snapshot of files when they are first seen.
/// For new additions, do not create a baseline so that diffs are shown as proper additions (using /dev/null).
/// 2. Keep a stable internal filename (uuid) per external path for rename tracking.
/// 3. To compute the aggregated unified diff, compare each baseline snapshot to the current file on disk entirely in-memory
/// using the `similar` crate and emit unified diffs with rewritten external paths.
#[derive(Default)]
pub struct TurnDiffTracker {
/// Map external path -> internal filename (uuid).
external_to_temp_name: HashMap<PathBuf, String>,
/// Internal filename -> baseline file info.
baseline_file_info: HashMap<String, BaselineFileInfo>,
/// Internal filename -> external path as of current accumulated state (after applying all changes).
/// This is where renames are tracked.
temp_name_to_current_path: HashMap<String, PathBuf>,
/// Cache of known git worktree roots to avoid repeated filesystem walks.
git_root_cache: Vec<PathBuf>,
}
impl TurnDiffTracker {
pub fn new() -> Self {
Self::default()
}
/// Front-run apply patch calls to track the starting contents of any modified files.
/// - Creates an in-memory baseline snapshot for files that already exist on disk when first seen.
/// - For additions, we intentionally do not create a baseline snapshot so that diffs are proper additions.
/// - Also updates internal mappings for move/rename events.
pub fn on_patch_begin(&mut self, changes: &HashMap<PathBuf, FileChange>) {
for (path, change) in changes.iter() {
// Ensure a stable internal filename exists for this external path.
if !self.external_to_temp_name.contains_key(path) {
let internal = Uuid::new_v4().to_string();
self.external_to_temp_name
.insert(path.clone(), internal.clone());
self.temp_name_to_current_path
.insert(internal.clone(), path.clone());
// If the file exists on disk now, snapshot as baseline; else leave missing to represent /dev/null.
let baseline_file_info = if path.exists() {
let mode = file_mode_for_path(path);
let mode_val = mode.unwrap_or(FileMode::Regular);
let content = blob_bytes(path, mode_val).unwrap_or_default();
let oid = if mode == Some(FileMode::Symlink) {
format!("{:x}", git_blob_sha1_hex_bytes(&content))
} else {
self.git_blob_oid_for_path(path)
.unwrap_or_else(|| format!("{:x}", git_blob_sha1_hex_bytes(&content)))
};
Some(BaselineFileInfo {
path: path.clone(),
content,
mode: mode_val,
oid,
})
} else {
Some(BaselineFileInfo {
path: path.clone(),
content: vec![],
mode: FileMode::Regular,
oid: ZERO_OID.to_string(),
})
};
if let Some(baseline_file_info) = baseline_file_info {
self.baseline_file_info
.insert(internal.clone(), baseline_file_info);
}
}
// Track rename/move in current mapping if provided in an Update.
if let FileChange::Update {
move_path: Some(dest),
..
} = change
{
let uuid_filename = match self.external_to_temp_name.get(path) {
Some(i) => i.clone(),
None => {
// This should be rare, but if we haven't mapped the source, create it with no baseline.
let i = Uuid::new_v4().to_string();
self.baseline_file_info.insert(
i.clone(),
BaselineFileInfo {
path: path.clone(),
content: vec![],
mode: FileMode::Regular,
oid: ZERO_OID.to_string(),
},
);
i
}
};
// Update current external mapping for temp file name.
self.temp_name_to_current_path
.insert(uuid_filename.clone(), dest.clone());
// Update forward file_mapping: external current -> internal name.
self.external_to_temp_name.remove(path);
self.external_to_temp_name
.insert(dest.clone(), uuid_filename);
};
}
}
fn get_path_for_internal(&self, internal: &str) -> Option<PathBuf> {
self.temp_name_to_current_path
.get(internal)
.cloned()
.or_else(|| {
self.baseline_file_info
.get(internal)
.map(|info| info.path.clone())
})
}
/// Find the git worktree root for a file/directory by walking up to the first ancestor containing a `.git` entry.
/// Uses a simple cache of known roots and avoids negative-result caching for simplicity.
fn find_git_root_cached(&mut self, start: &Path) -> Option<PathBuf> {
let dir = if start.is_dir() {
start
} else {
start.parent()?
};
// Fast path: if any cached root is an ancestor of this path, use it.
if let Some(root) = self
.git_root_cache
.iter()
.find(|r| dir.starts_with(r))
.cloned()
{
return Some(root);
}
// Walk up to find a `.git` marker.
let mut cur = dir.to_path_buf();
loop {
let git_marker = cur.join(".git");
if git_marker.is_dir() || git_marker.is_file() {
if !self.git_root_cache.iter().any(|r| r == &cur) {
self.git_root_cache.push(cur.clone());
}
return Some(cur);
}
// On Windows, avoid walking above the drive or UNC share root.
#[cfg(windows)]
{
if is_windows_drive_or_unc_root(&cur) {
return None;
}
}
if let Some(parent) = cur.parent() {
cur = parent.to_path_buf();
} else {
return None;
}
}
}
/// Return a display string for `path` relative to its git root if found, else absolute.
fn relative_to_git_root_str(&mut self, path: &Path) -> String {
let s = if let Some(root) = self.find_git_root_cached(path) {
if let Ok(rel) = path.strip_prefix(&root) {
rel.display().to_string()
} else {
path.display().to_string()
}
} else {
path.display().to_string()
};
s.replace('\\', "/")
}
/// Ask git to compute the blob SHA-1 for the file at `path` within its repository.
/// Returns None if no repository is found or git invocation fails.
fn git_blob_oid_for_path(&mut self, path: &Path) -> Option<String> {
let root = self.find_git_root_cached(path)?;
// Compute a path relative to the repo root for better portability across platforms.
let rel = path.strip_prefix(&root).unwrap_or(path);
let output = Command::new("git")
.arg("-C")
.arg(&root)
.arg("hash-object")
.arg("--")
.arg(rel)
.output()
.ok()?;
if !output.status.success() {
return None;
}
let s = String::from_utf8_lossy(&output.stdout).trim().to_string();
if s.len() == 40 { Some(s) } else { None }
}
/// Recompute the aggregated unified diff by comparing all of the in-memory snapshots that were
/// collected before the first time they were touched by apply_patch during this turn with
/// the current repo state.
pub fn get_unified_diff(&mut self) -> Result<Option<String>> {
let mut aggregated = String::new();
// Compute diffs per tracked internal file in a stable order by external path.
let mut baseline_file_names: Vec<String> =
self.baseline_file_info.keys().cloned().collect();
// Sort lexicographically by full repo-relative path to match git behavior.
baseline_file_names.sort_by_key(|internal| {
self.get_path_for_internal(internal)
.map(|p| self.relative_to_git_root_str(&p))
.unwrap_or_default()
});
for internal in baseline_file_names {
aggregated.push_str(self.get_file_diff(&internal).as_str());
if !aggregated.ends_with('\n') {
aggregated.push('\n');
}
}
if aggregated.trim().is_empty() {
Ok(None)
} else {
Ok(Some(aggregated))
}
}
fn get_file_diff(&mut self, internal_file_name: &str) -> String {
let mut aggregated = String::new();
// Snapshot lightweight fields only.
let (baseline_external_path, baseline_mode, left_oid) = {
if let Some(info) = self.baseline_file_info.get(internal_file_name) {
(info.path.clone(), info.mode, info.oid.clone())
} else {
(PathBuf::new(), FileMode::Regular, ZERO_OID.to_string())
}
};
let current_external_path = match self.get_path_for_internal(internal_file_name) {
Some(p) => p,
None => return aggregated,
};
let current_mode = file_mode_for_path(&current_external_path).unwrap_or(FileMode::Regular);
let right_bytes = blob_bytes(&current_external_path, current_mode);
// Compute displays with &mut self before borrowing any baseline content.
let left_display = self.relative_to_git_root_str(&baseline_external_path);
let right_display = self.relative_to_git_root_str(&current_external_path);
// Compute right oid before borrowing baseline content.
let right_oid = if let Some(b) = right_bytes.as_ref() {
if current_mode == FileMode::Symlink {
format!("{:x}", git_blob_sha1_hex_bytes(b))
} else {
self.git_blob_oid_for_path(&current_external_path)
.unwrap_or_else(|| format!("{:x}", git_blob_sha1_hex_bytes(b)))
}
} else {
ZERO_OID.to_string()
};
// Borrow baseline content only after all &mut self uses are done.
let left_present = left_oid.as_str() != ZERO_OID;
let left_bytes: Option<&[u8]> = if left_present {
self.baseline_file_info
.get(internal_file_name)
.map(|i| i.content.as_slice())
} else {
None
};
// Fast path: identical bytes or both missing.
if left_bytes == right_bytes.as_deref() {
return aggregated;
}
aggregated.push_str(&format!("diff --git a/{left_display} b/{right_display}\n"));
let is_add = !left_present && right_bytes.is_some();
let is_delete = left_present && right_bytes.is_none();
if is_add {
aggregated.push_str(&format!("new file mode {current_mode}\n"));
} else if is_delete {
aggregated.push_str(&format!("deleted file mode {baseline_mode}\n"));
} else if baseline_mode != current_mode {
aggregated.push_str(&format!("old mode {baseline_mode}\n"));
aggregated.push_str(&format!("new mode {current_mode}\n"));
}
let left_text = left_bytes.and_then(|b| std::str::from_utf8(b).ok());
let right_text = right_bytes
.as_deref()
.and_then(|b| std::str::from_utf8(b).ok());
let can_text_diff = matches!(
(left_text, right_text, is_add, is_delete),
(Some(_), Some(_), _, _) | (_, Some(_), true, _) | (Some(_), _, _, true)
);
if can_text_diff {
let l = left_text.unwrap_or("");
let r = right_text.unwrap_or("");
aggregated.push_str(&format!("index {left_oid}..{right_oid}\n"));
let old_header = if left_present {
format!("a/{left_display}")
} else {
DEV_NULL.to_string()
};
let new_header = if right_bytes.is_some() {
format!("b/{right_display}")
} else {
DEV_NULL.to_string()
};
let diff = similar::TextDiff::from_lines(l, r);
let unified = diff
.unified_diff()
.context_radius(3)
.header(&old_header, &new_header)
.to_string();
aggregated.push_str(&unified);
} else {
aggregated.push_str(&format!("index {left_oid}..{right_oid}\n"));
let old_header = if left_present {
format!("a/{left_display}")
} else {
DEV_NULL.to_string()
};
let new_header = if right_bytes.is_some() {
format!("b/{right_display}")
} else {
DEV_NULL.to_string()
};
aggregated.push_str(&format!("--- {old_header}\n"));
aggregated.push_str(&format!("+++ {new_header}\n"));
aggregated.push_str("Binary files differ\n");
}
aggregated
}
}
/// Compute the Git SHA-1 blob object ID for the given content (bytes).
fn git_blob_sha1_hex_bytes(data: &[u8]) -> Output<sha1::Sha1> {
// Git blob hash is sha1 of: "blob <len>\0<data>"
let header = format!("blob {}\0", data.len());
use sha1::Digest;
let mut hasher = sha1::Sha1::new();
hasher.update(header.as_bytes());
hasher.update(data);
hasher.finalize()
}
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
enum FileMode {
Regular,
#[cfg(unix)]
Executable,
Symlink,
}
impl FileMode {
fn as_str(self) -> &'static str {
match self {
FileMode::Regular => "100644",
#[cfg(unix)]
FileMode::Executable => "100755",
FileMode::Symlink => "120000",
}
}
}
impl std::fmt::Display for FileMode {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
f.write_str(self.as_str())
}
}
#[cfg(unix)]
fn file_mode_for_path(path: &Path) -> Option<FileMode> {
use std::os::unix::fs::PermissionsExt;
let meta = fs::symlink_metadata(path).ok()?;
let ft = meta.file_type();
if ft.is_symlink() {
return Some(FileMode::Symlink);
}
let mode = meta.permissions().mode();
let is_exec = (mode & 0o111) != 0;
Some(if is_exec {
FileMode::Executable
} else {
FileMode::Regular
})
}
#[cfg(not(unix))]
fn file_mode_for_path(_path: &Path) -> Option<FileMode> {
// Default to non-executable on non-unix.
Some(FileMode::Regular)
}
fn blob_bytes(path: &Path, mode: FileMode) -> Option<Vec<u8>> {
if path.exists() {
let contents = if mode == FileMode::Symlink {
symlink_blob_bytes(path)
.ok_or_else(|| anyhow!("failed to read symlink target for {}", path.display()))
} else {
fs::read(path)
.with_context(|| format!("failed to read current file for diff {}", path.display()))
};
contents.ok()
} else {
None
}
}
#[cfg(unix)]
fn symlink_blob_bytes(path: &Path) -> Option<Vec<u8>> {
use std::os::unix::ffi::OsStrExt;
let target = std::fs::read_link(path).ok()?;
Some(target.as_os_str().as_bytes().to_vec())
}
#[cfg(not(unix))]
fn symlink_blob_bytes(_path: &Path) -> Option<Vec<u8>> {
None
}
#[cfg(windows)]
fn is_windows_drive_or_unc_root(p: &std::path::Path) -> bool {
use std::path::Component;
let mut comps = p.components();
matches!(
(comps.next(), comps.next(), comps.next()),
(Some(Component::Prefix(_)), Some(Component::RootDir), None)
)
}
#[cfg(test)]
mod tests {
use super::*;
use pretty_assertions::assert_eq;
use tempfile::tempdir;
/// Compute the Git SHA-1 blob object ID for the given content (string).
/// This delegates to the bytes version to avoid UTF-8 lossy conversions here.
fn git_blob_sha1_hex(data: &str) -> String {
format!("{:x}", git_blob_sha1_hex_bytes(data.as_bytes()))
}
fn normalize_diff_for_test(input: &str, root: &Path) -> String {
let root_str = root.display().to_string().replace('\\', "/");
let replaced = input.replace(&root_str, "<TMP>");
// Split into blocks on lines starting with "diff --git ", sort blocks for determinism, and rejoin
let mut blocks: Vec<String> = Vec::new();
let mut current = String::new();
for line in replaced.lines() {
if line.starts_with("diff --git ") && !current.is_empty() {
blocks.push(current);
current = String::new();
}
if !current.is_empty() {
current.push('\n');
}
current.push_str(line);
}
if !current.is_empty() {
blocks.push(current);
}
blocks.sort();
let mut out = blocks.join("\n");
if !out.ends_with('\n') {
out.push('\n');
}
out
}
#[test]
fn accumulates_add_and_update() {
let mut acc = TurnDiffTracker::new();
let dir = tempdir().unwrap();
let file = dir.path().join("a.txt");
// First patch: add file (baseline should be /dev/null).
let add_changes = HashMap::from([(
file.clone(),
FileChange::Add {
content: "foo\n".to_string(),
},
)]);
acc.on_patch_begin(&add_changes);
// Simulate apply: create the file on disk.
fs::write(&file, "foo\n").unwrap();
let first = acc.get_unified_diff().unwrap().unwrap();
let first = normalize_diff_for_test(&first, dir.path());
let expected_first = {
let mode = file_mode_for_path(&file).unwrap_or(FileMode::Regular);
let right_oid = git_blob_sha1_hex("foo\n");
format!(
r#"diff --git a/<TMP>/a.txt b/<TMP>/a.txt
new file mode {mode}
index {ZERO_OID}..{right_oid}
--- {DEV_NULL}
+++ b/<TMP>/a.txt
@@ -0,0 +1 @@
+foo
"#,
)
};
assert_eq!(first, expected_first);
// Second patch: update the file on disk.
let update_changes = HashMap::from([(
file.clone(),
FileChange::Update {
unified_diff: "".to_owned(),
move_path: None,
},
)]);
acc.on_patch_begin(&update_changes);
// Simulate apply: append a new line.
fs::write(&file, "foo\nbar\n").unwrap();
let combined = acc.get_unified_diff().unwrap().unwrap();
let combined = normalize_diff_for_test(&combined, dir.path());
let expected_combined = {
let mode = file_mode_for_path(&file).unwrap_or(FileMode::Regular);
let right_oid = git_blob_sha1_hex("foo\nbar\n");
format!(
r#"diff --git a/<TMP>/a.txt b/<TMP>/a.txt
new file mode {mode}
index {ZERO_OID}..{right_oid}
--- {DEV_NULL}
+++ b/<TMP>/a.txt
@@ -0,0 +1,2 @@
+foo
+bar
"#,
)
};
assert_eq!(combined, expected_combined);
}
#[test]
fn accumulates_delete() {
let dir = tempdir().unwrap();
let file = dir.path().join("b.txt");
fs::write(&file, "x\n").unwrap();
let mut acc = TurnDiffTracker::new();
let del_changes = HashMap::from([(
file.clone(),
FileChange::Delete {
content: "x\n".to_string(),
},
)]);
acc.on_patch_begin(&del_changes);
// Simulate apply: delete the file from disk.
let baseline_mode = file_mode_for_path(&file).unwrap_or(FileMode::Regular);
fs::remove_file(&file).unwrap();
let diff = acc.get_unified_diff().unwrap().unwrap();
let diff = normalize_diff_for_test(&diff, dir.path());
let expected = {
let left_oid = git_blob_sha1_hex("x\n");
format!(
r#"diff --git a/<TMP>/b.txt b/<TMP>/b.txt
deleted file mode {baseline_mode}
index {left_oid}..{ZERO_OID}
--- a/<TMP>/b.txt
+++ {DEV_NULL}
@@ -1 +0,0 @@
-x
"#,
)
};
assert_eq!(diff, expected);
}
#[test]
fn accumulates_move_and_update() {
let dir = tempdir().unwrap();
let src = dir.path().join("src.txt");
let dest = dir.path().join("dst.txt");
fs::write(&src, "line\n").unwrap();
let mut acc = TurnDiffTracker::new();
let mv_changes = HashMap::from([(
src.clone(),
FileChange::Update {
unified_diff: "".to_owned(),
move_path: Some(dest.clone()),
},
)]);
acc.on_patch_begin(&mv_changes);
// Simulate apply: move and update content.
fs::rename(&src, &dest).unwrap();
fs::write(&dest, "line2\n").unwrap();
let out = acc.get_unified_diff().unwrap().unwrap();
let out = normalize_diff_for_test(&out, dir.path());
let expected = {
let left_oid = git_blob_sha1_hex("line\n");
let right_oid = git_blob_sha1_hex("line2\n");
format!(
r#"diff --git a/<TMP>/src.txt b/<TMP>/dst.txt
index {left_oid}..{right_oid}
--- a/<TMP>/src.txt
+++ b/<TMP>/dst.txt
@@ -1 +1 @@
-line
+line2
"#
)
};
assert_eq!(out, expected);
}
#[test]
fn move_without_1change_yields_no_diff() {
let dir = tempdir().unwrap();
let src = dir.path().join("moved.txt");
let dest = dir.path().join("renamed.txt");
fs::write(&src, "same\n").unwrap();
let mut acc = TurnDiffTracker::new();
let mv_changes = HashMap::from([(
src.clone(),
FileChange::Update {
unified_diff: "".to_owned(),
move_path: Some(dest.clone()),
},
)]);
acc.on_patch_begin(&mv_changes);
// Simulate apply: move only, no content change.
fs::rename(&src, &dest).unwrap();
let diff = acc.get_unified_diff().unwrap();
assert_eq!(diff, None);
}
#[test]
fn move_declared_but_file_only_appears_at_dest_is_add() {
let dir = tempdir().unwrap();
let src = dir.path().join("src.txt");
let dest = dir.path().join("dest.txt");
let mut acc = TurnDiffTracker::new();
let mv = HashMap::from([(
src,
FileChange::Update {
unified_diff: "".into(),
move_path: Some(dest.clone()),
},
)]);
acc.on_patch_begin(&mv);
// No file existed initially; create only dest
fs::write(&dest, "hello\n").unwrap();
let diff = acc.get_unified_diff().unwrap().unwrap();
let diff = normalize_diff_for_test(&diff, dir.path());
let expected = {
let mode = file_mode_for_path(&dest).unwrap_or(FileMode::Regular);
let right_oid = git_blob_sha1_hex("hello\n");
format!(
r#"diff --git a/<TMP>/src.txt b/<TMP>/dest.txt
new file mode {mode}
index {ZERO_OID}..{right_oid}
--- {DEV_NULL}
+++ b/<TMP>/dest.txt
@@ -0,0 +1 @@
+hello
"#,
)
};
assert_eq!(diff, expected);
}
#[test]
fn update_persists_across_new_baseline_for_new_file() {
let dir = tempdir().unwrap();
let a = dir.path().join("a.txt");
let b = dir.path().join("b.txt");
fs::write(&a, "foo\n").unwrap();
fs::write(&b, "z\n").unwrap();
let mut acc = TurnDiffTracker::new();
// First: update existing a.txt (baseline snapshot is created for a).
let update_a = HashMap::from([(
a.clone(),
FileChange::Update {
unified_diff: "".to_owned(),
move_path: None,
},
)]);
acc.on_patch_begin(&update_a);
// Simulate apply: modify a.txt on disk.
fs::write(&a, "foo\nbar\n").unwrap();
let first = acc.get_unified_diff().unwrap().unwrap();
let first = normalize_diff_for_test(&first, dir.path());
let expected_first = {
let left_oid = git_blob_sha1_hex("foo\n");
let right_oid = git_blob_sha1_hex("foo\nbar\n");
format!(
r#"diff --git a/<TMP>/a.txt b/<TMP>/a.txt
index {left_oid}..{right_oid}
--- a/<TMP>/a.txt
+++ b/<TMP>/a.txt
@@ -1 +1,2 @@
foo
+bar
"#
)
};
assert_eq!(first, expected_first);
// Next: introduce a brand-new path b.txt into baseline snapshots via a delete change.
let del_b = HashMap::from([(
b.clone(),
FileChange::Delete {
content: "z\n".to_string(),
},
)]);
acc.on_patch_begin(&del_b);
// Simulate apply: delete b.txt.
let baseline_mode = file_mode_for_path(&b).unwrap_or(FileMode::Regular);
fs::remove_file(&b).unwrap();
let combined = acc.get_unified_diff().unwrap().unwrap();
let combined = normalize_diff_for_test(&combined, dir.path());
let expected = {
let left_oid_a = git_blob_sha1_hex("foo\n");
let right_oid_a = git_blob_sha1_hex("foo\nbar\n");
let left_oid_b = git_blob_sha1_hex("z\n");
format!(
r#"diff --git a/<TMP>/a.txt b/<TMP>/a.txt
index {left_oid_a}..{right_oid_a}
--- a/<TMP>/a.txt
+++ b/<TMP>/a.txt
@@ -1 +1,2 @@
foo
+bar
diff --git a/<TMP>/b.txt b/<TMP>/b.txt
deleted file mode {baseline_mode}
index {left_oid_b}..{ZERO_OID}
--- a/<TMP>/b.txt
+++ {DEV_NULL}
@@ -1 +0,0 @@
-z
"#,
)
};
assert_eq!(combined, expected);
}
#[test]
fn binary_files_differ_update() {
let dir = tempdir().unwrap();
let file = dir.path().join("bin.dat");
// Initial non-UTF8 bytes
let left_bytes: Vec<u8> = vec![0xff, 0xfe, 0xfd, 0x00];
// Updated non-UTF8 bytes
let right_bytes: Vec<u8> = vec![0x01, 0x02, 0x03, 0x00];
fs::write(&file, &left_bytes).unwrap();
let mut acc = TurnDiffTracker::new();
let update_changes = HashMap::from([(
file.clone(),
FileChange::Update {
unified_diff: "".to_owned(),
move_path: None,
},
)]);
acc.on_patch_begin(&update_changes);
// Apply update on disk
fs::write(&file, &right_bytes).unwrap();
let diff = acc.get_unified_diff().unwrap().unwrap();
let diff = normalize_diff_for_test(&diff, dir.path());
let expected = {
let left_oid = format!("{:x}", git_blob_sha1_hex_bytes(&left_bytes));
let right_oid = format!("{:x}", git_blob_sha1_hex_bytes(&right_bytes));
format!(
r#"diff --git a/<TMP>/bin.dat b/<TMP>/bin.dat
index {left_oid}..{right_oid}
--- a/<TMP>/bin.dat
+++ b/<TMP>/bin.dat
Binary files differ
"#
)
};
assert_eq!(diff, expected);
}
#[test]
fn filenames_with_spaces_add_and_update() {
let mut acc = TurnDiffTracker::new();
let dir = tempdir().unwrap();
let file = dir.path().join("name with spaces.txt");
// First patch: add file (baseline should be /dev/null).
let add_changes = HashMap::from([(
file.clone(),
FileChange::Add {
content: "foo\n".to_string(),
},
)]);
acc.on_patch_begin(&add_changes);
// Simulate apply: create the file on disk.
fs::write(&file, "foo\n").unwrap();
let first = acc.get_unified_diff().unwrap().unwrap();
let first = normalize_diff_for_test(&first, dir.path());
let expected_first = {
let mode = file_mode_for_path(&file).unwrap_or(FileMode::Regular);
let right_oid = git_blob_sha1_hex("foo\n");
format!(
r#"diff --git a/<TMP>/name with spaces.txt b/<TMP>/name with spaces.txt
new file mode {mode}
index {ZERO_OID}..{right_oid}
--- {DEV_NULL}
+++ b/<TMP>/name with spaces.txt
@@ -0,0 +1 @@
+foo
"#,
)
};
assert_eq!(first, expected_first);
// Second patch: update the file on disk.
let update_changes = HashMap::from([(
file.clone(),
FileChange::Update {
unified_diff: "".to_owned(),
move_path: None,
},
)]);
acc.on_patch_begin(&update_changes);
// Simulate apply: append a new line with a space.
fs::write(&file, "foo\nbar baz\n").unwrap();
let combined = acc.get_unified_diff().unwrap().unwrap();
let combined = normalize_diff_for_test(&combined, dir.path());
let expected_combined = {
let mode = file_mode_for_path(&file).unwrap_or(FileMode::Regular);
let right_oid = git_blob_sha1_hex("foo\nbar baz\n");
format!(
r#"diff --git a/<TMP>/name with spaces.txt b/<TMP>/name with spaces.txt
new file mode {mode}
index {ZERO_OID}..{right_oid}
--- {DEV_NULL}
+++ b/<TMP>/name with spaces.txt
@@ -0,0 +1,2 @@
+foo
+bar baz
"#,
)
};
assert_eq!(combined, expected_combined);
}
}
pub use codex_agent::turn_diff_tracker::*;
+1
View File
@@ -0,0 +1 @@
pub use codex_agent::unified_exec::*;
+4 -44
View File
@@ -1,7 +1,9 @@
use serde::Serialize;
use serde_json::to_string;
use tracing::error;
use tracing::warn;
pub use codex_agent::notifications::UserNotification;
#[derive(Debug, Default)]
pub(crate) struct UserNotifier {
notify_command: Option<Vec<String>>,
@@ -17,7 +19,7 @@ impl UserNotifier {
}
fn invoke_notify(&self, notify_command: &[String], notification: &UserNotification) {
let Ok(json) = serde_json::to_string(&notification) else {
let Ok(json) = to_string(notification) else {
error!("failed to serialise notification payload");
return;
};
@@ -28,7 +30,6 @@ impl UserNotifier {
}
command.arg(json);
// Fire-and-forget – we do not wait for completion.
if let Err(e) = command.spawn() {
warn!("failed to spawn notifier '{}': {e}", notify_command[0]);
}
@@ -40,44 +41,3 @@ impl UserNotifier {
}
}
}
/// User can configure a program that will receive notifications. Each
/// notification is serialized as JSON and passed as an argument to the
/// program.
#[derive(Debug, Clone, PartialEq, Serialize)]
#[serde(tag = "type", rename_all = "kebab-case")]
pub enum UserNotification {
#[serde(rename_all = "kebab-case")]
AgentTurnComplete {
turn_id: String,
/// Messages that the user sent to the agent to initiate the turn.
input_messages: Vec<String>,
/// The last message sent by the assistant in the turn.
last_assistant_message: Option<String>,
},
}
#[cfg(test)]
mod tests {
use super::*;
use anyhow::Result;
#[test]
fn test_user_notification() -> Result<()> {
let notification = UserNotification::AgentTurnComplete {
turn_id: "12345".to_string(),
input_messages: vec!["Rename `foo` to `bar` and update the callsites.".to_string()],
last_assistant_message: Some(
"Rename complete and verified `cargo build` succeeds.".to_string(),
),
};
let serialized = serde_json::to_string(&notification)?;
assert_eq!(
serialized,
r#"{"type":"agent-turn-complete","turn-id":"12345","input-messages":["Rename `foo` to `bar` and update the callsites."],"last-assistant-message":"Rename complete and verified `cargo build` succeeds."}"#
);
Ok(())
}
}