Merge branch 'main' into initial-context-tool

This commit is contained in:
pap-openai
2025-08-01 00:19:54 +01:00
committed by GitHub
30 changed files with 793 additions and 635 deletions
+1
View File
@@ -793,6 +793,7 @@ dependencies = [
"reqwest",
"serde",
"serde_json",
"tempfile",
"tokio",
]
+1 -1
View File
@@ -18,7 +18,7 @@ pub fn set_chatgpt_token_data(value: TokenData) {
/// Initialize the ChatGPT token from auth.json file
pub async fn init_chatgpt_token_from_auth(codex_home: &Path) -> std::io::Result<()> {
let auth = codex_login::load_auth(codex_home)?;
let auth = codex_login::load_auth(codex_home, true)?;
if let Some(auth) = auth {
let token_data = auth.get_token_data().await?;
set_chatgpt_token_data(token_data);
@@ -10,8 +10,13 @@ use tokio::process::Command;
async fn create_temp_git_repo() -> anyhow::Result<TempDir> {
let temp_dir = TempDir::new()?;
let repo_path = temp_dir.path();
let envs = vec![
("GIT_CONFIG_GLOBAL", "/dev/null"),
("GIT_CONFIG_NOSYSTEM", "1"),
];
let output = Command::new("git")
.envs(envs.clone())
.args(["init"])
.current_dir(repo_path)
.output()
@@ -25,12 +30,14 @@ async fn create_temp_git_repo() -> anyhow::Result<TempDir> {
}
Command::new("git")
.envs(envs.clone())
.args(["config", "user.email", "test@example.com"])
.current_dir(repo_path)
.output()
.await?;
Command::new("git")
.envs(envs.clone())
.args(["config", "user.name", "Test User"])
.current_dir(repo_path)
.output()
@@ -39,12 +46,14 @@ async fn create_temp_git_repo() -> anyhow::Result<TempDir> {
std::fs::write(repo_path.join("README.md"), "# Test Repo\n")?;
Command::new("git")
.envs(envs.clone())
.args(["add", "README.md"])
.current_dir(repo_path)
.output()
.await?;
let output = Command::new("git")
.envs(envs.clone())
.args(["commit", "-m", "Initial commit"])
.current_dir(repo_path)
.output()
+2 -2
View File
@@ -4,10 +4,10 @@ use codex_common::CliConfigOverrides;
use codex_core::config::Config;
use codex_core::config::ConfigOverrides;
use codex_core::config_types::SandboxMode;
use codex_core::exec::StdioPolicy;
use codex_core::exec::spawn_command_under_linux_sandbox;
use codex_core::exec::spawn_command_under_seatbelt;
use codex_core::exec_env::create_env;
use codex_core::seatbelt::spawn_command_under_seatbelt;
use codex_core::spawn::StdioPolicy;
use crate::LandlockCommand;
use crate::SeatbeltCommand;
+31 -1
View File
@@ -1,8 +1,12 @@
use std::env;
use codex_common::CliConfigOverrides;
use codex_core::config::Config;
use codex_core::config::ConfigOverrides;
use codex_login::AuthMode;
use codex_login::OPENAI_API_KEY_ENV_VAR;
use codex_login::load_auth;
use codex_login::login_with_api_key;
use codex_login::login_with_chatgpt;
pub async fn run_login_with_chatgpt(cli_config_overrides: CliConfigOverrides) -> ! {
@@ -21,14 +25,40 @@ pub async fn run_login_with_chatgpt(cli_config_overrides: CliConfigOverrides) ->
}
}
pub async fn run_login_with_api_key(
cli_config_overrides: CliConfigOverrides,
api_key: String,
) -> ! {
let config = load_config_or_exit(cli_config_overrides);
match login_with_api_key(&config.codex_home, &api_key) {
Ok(_) => {
eprintln!("Successfully logged in");
std::process::exit(0);
}
Err(e) => {
eprintln!("Error logging in: {e}");
std::process::exit(1);
}
}
}
pub async fn run_login_status(cli_config_overrides: CliConfigOverrides) -> ! {
let config = load_config_or_exit(cli_config_overrides);
match load_auth(&config.codex_home) {
match load_auth(&config.codex_home, true) {
Ok(Some(auth)) => match auth.mode {
AuthMode::ApiKey => {
if let Some(api_key) = auth.api_key.as_deref() {
eprintln!("Logged in using an API key - {}", safe_format_key(api_key));
if let Ok(env_api_key) = env::var(OPENAI_API_KEY_ENV_VAR) {
if env_api_key == api_key {
eprintln!(
" API loaded from OPENAI_API_KEY environment variable or .env file"
);
}
}
} else {
eprintln!("Logged in using an API key");
}
+9 -1
View File
@@ -8,6 +8,7 @@ use codex_chatgpt::apply_command::run_apply_command;
use codex_cli::LandlockCommand;
use codex_cli::SeatbeltCommand;
use codex_cli::login::run_login_status;
use codex_cli::login::run_login_with_api_key;
use codex_cli::login::run_login_with_chatgpt;
use codex_cli::proto;
use codex_common::CliConfigOverrides;
@@ -92,6 +93,9 @@ struct LoginCommand {
#[clap(skip)]
config_overrides: CliConfigOverrides,
#[arg(long = "api-key", value_name = "API_KEY")]
api_key: Option<String>,
#[command(subcommand)]
action: Option<LoginSubcommand>,
}
@@ -133,7 +137,11 @@ async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()
run_login_status(login_cli.config_overrides).await;
}
None => {
run_login_with_chatgpt(login_cli.config_overrides).await;
if let Some(api_key) = login_cli.api_key {
run_login_with_api_key(login_cli.config_overrides, api_key).await;
} else {
run_login_with_chatgpt(login_cli.config_overrides).await;
}
}
}
}
+1 -1
View File
@@ -36,7 +36,7 @@ pub async fn run_main(opts: ProtoCli) -> anyhow::Result<()> {
.map_err(anyhow::Error::msg)?;
let config = Config::load_with_cli_overrides(overrides_vec, ConfigOverrides::default())?;
let auth = load_auth(&config.codex_home)?;
let auth = load_auth(&config.codex_home, true)?;
let ctrl_c = notify_on_sigint();
let CodexSpawnOk { codex, .. } = Codex::spawn(config, auth, ctrl_c.clone()).await?;
let codex = Arc::new(codex);
+9
View File
@@ -96,3 +96,12 @@ You can invoke apply_patch like:
```
shell {"command":["apply_patch","*** Begin Patch\n*** Add File: hello.txt\n+Hello, world!\n*** End Patch\n"]}
```
Plan updates
A tool named `update_plan` is available. Use it to keep an up‑to‑date, step‑by‑step plan for the task so you can follow your progress. When making your plans, keep in mind that you are a deployed coding agent - `update_plan` calls should not involve doing anything that you aren't capable of doing. For example, `update_plan` calls should NEVER contain tasks to merge your own pull requests. Only stop to ask the user if you genuinely need their feedback on a change.
- At the start of the task, call `update_plan` with an initial plan: a short list of 1‑sentence steps with a `status` for each step (`pending`, `in_progress`, or `completed`). There should always be exactly one `in_progress` step until everything is done.
- Whenever you finish a step, call `update_plan` again, marking the finished step as `completed` and the next step as `in_progress`.
- If your plan needs to change, call `update_plan` with the revised steps and include an `explanation` describing the change.
- When all steps are complete, make a final `update_plan` call with all steps marked `completed`.
+33 -310
View File
@@ -1,19 +1,12 @@
use crate::codex::Session;
use crate::models::FunctionCallOutputPayload;
use crate::models::ResponseInputItem;
use crate::protocol::Event;
use crate::protocol::EventMsg;
use crate::protocol::FileChange;
use crate::protocol::PatchApplyBeginEvent;
use crate::protocol::PatchApplyEndEvent;
use crate::protocol::ReviewDecision;
use crate::safety::SafetyCheck;
use crate::safety::assess_patch_safety;
use anyhow::Context;
use codex_apply_patch::AffectedPaths;
use codex_apply_patch::ApplyPatchAction;
use codex_apply_patch::ApplyPatchFileChange;
use codex_apply_patch::print_summary;
use std::collections::HashMap;
use std::path::Path;
use std::path::PathBuf;
@@ -26,12 +19,18 @@ pub(crate) enum InternalApplyPatchInvocation {
/// result to use with the `shell` function call that contained `apply_patch`.
Output(ResponseInputItem),
/// The `apply_patch` call was auto-approved, which means that, on the
/// surface, it appears to be safe, but it should be run in a sandbox if the
/// user has configured one because a path being written could be a hard
/// link to a file outside the writable folders, so only the sandbox can
/// faithfully prevent the write in that case.
DelegateToExec(ApplyPatchAction),
/// The `apply_patch` call was approved, either automatically because it
/// appears that it should be allowed based on the user's sandbox policy
/// *or* because the user explicitly approved it. In either case, we use
/// exec with [`CODEX_APPLY_PATCH_ARG1`] to realize the `apply_patch` call,
/// but [`ApplyPatchExec::auto_approved`] is used to determine the sandbox
/// used with the `exec()`.
DelegateToExec(ApplyPatchExec),
}
pub(crate) struct ApplyPatchExec {
pub(crate) action: ApplyPatchAction,
pub(crate) user_explicitly_approved_this_action: bool,
}
impl From<ResponseInputItem> for InternalApplyPatchInvocation {
@@ -52,254 +51,57 @@ pub(crate) async fn apply_patch(
guard.clone()
};
let auto_approved = match assess_patch_safety(
match assess_patch_safety(
&action,
sess.approval_policy,
&writable_roots_snapshot,
&sess.cwd,
) {
SafetyCheck::AutoApprove { .. } => {
return InternalApplyPatchInvocation::DelegateToExec(action);
InternalApplyPatchInvocation::DelegateToExec(ApplyPatchExec {
action,
user_explicitly_approved_this_action: false,
})
}
SafetyCheck::AskUser => {
// Compute a readable summary of path changes to include in the
// approval request so the user can make an informed decision.
//
// Note that it might be worth expanding this approval request to
// give the user the option to expand the set of writable roots so
// that similar patches can be auto-approved in the future during
// this session.
let rx_approve = sess
.request_patch_approval(sub_id.to_owned(), call_id.to_owned(), &action, None, None)
.await;
match rx_approve.await.unwrap_or_default() {
ReviewDecision::Approved | ReviewDecision::ApprovedForSession => false,
ReviewDecision::Approved | ReviewDecision::ApprovedForSession => {
InternalApplyPatchInvocation::DelegateToExec(ApplyPatchExec {
action,
user_explicitly_approved_this_action: true,
})
}
ReviewDecision::Denied | ReviewDecision::Abort => {
return ResponseInputItem::FunctionCallOutput {
ResponseInputItem::FunctionCallOutput {
call_id: call_id.to_owned(),
output: FunctionCallOutputPayload {
content: "patch rejected by user".to_string(),
success: Some(false),
},
}
.into();
.into()
}
}
}
SafetyCheck::Reject { reason } => {
return ResponseInputItem::FunctionCallOutput {
call_id: call_id.to_owned(),
output: FunctionCallOutputPayload {
content: format!("patch rejected: {reason}"),
success: Some(false),
},
}
.into();
}
};
// Verify write permissions before touching the filesystem.
let writable_snapshot = {
#[allow(clippy::unwrap_used)]
sess.writable_roots.lock().unwrap().clone()
};
if let Some(offending) = first_offending_path(&action, &writable_snapshot, &sess.cwd) {
let root = offending.parent().unwrap_or(&offending).to_path_buf();
let reason = Some(format!(
"grant write access to {} for this session",
root.display()
));
let rx = sess
.request_patch_approval(
sub_id.to_owned(),
call_id.to_owned(),
&action,
reason.clone(),
Some(root.clone()),
)
.await;
if !matches!(
rx.await.unwrap_or_default(),
ReviewDecision::Approved | ReviewDecision::ApprovedForSession
) {
return ResponseInputItem::FunctionCallOutput {
call_id: call_id.to_owned(),
output: FunctionCallOutputPayload {
content: "patch rejected by user".to_string(),
success: Some(false),
},
}
.into();
}
// user approved, extend writable roots for this session
#[allow(clippy::unwrap_used)]
sess.writable_roots.lock().unwrap().push(root);
}
let _ = sess
.tx_event
.send(Event {
id: sub_id.to_owned(),
msg: EventMsg::PatchApplyBegin(PatchApplyBeginEvent {
call_id: call_id.to_owned(),
auto_approved,
changes: convert_apply_patch_to_protocol(&action),
}),
})
.await;
let mut stdout = Vec::new();
let mut stderr = Vec::new();
// Enforce writable roots. If a write is blocked, collect offending root
// and prompt the user to extend permissions.
let mut result = apply_changes_from_apply_patch_and_report(&action, &mut stdout, &mut stderr);
if let Err(err) = &result {
if err.kind() == std::io::ErrorKind::PermissionDenied {
// Determine first offending path.
let offending_opt = action
.changes()
.iter()
.flat_map(|(path, change)| match change {
ApplyPatchFileChange::Add { .. } => vec![path.as_ref()],
ApplyPatchFileChange::Delete => vec![path.as_ref()],
ApplyPatchFileChange::Update {
move_path: Some(move_path),
..
} => {
vec![path.as_ref(), move_path.as_ref()]
}
ApplyPatchFileChange::Update {
move_path: None, ..
} => vec![path.as_ref()],
})
.find_map(|path: &Path| {
// ApplyPatchAction promises to guarantee absolute paths.
if !path.is_absolute() {
panic!("apply_patch invariant failed: path is not absolute: {path:?}");
}
let writable = {
#[allow(clippy::unwrap_used)]
let roots = sess.writable_roots.lock().unwrap();
roots.iter().any(|root| path.starts_with(root))
};
if writable {
None
} else {
Some(path.to_path_buf())
}
});
if let Some(offending) = offending_opt {
let root = offending.parent().unwrap_or(&offending).to_path_buf();
let reason = Some(format!(
"grant write access to {} for this session",
root.display()
));
let rx = sess
.request_patch_approval(
sub_id.to_owned(),
call_id.to_owned(),
&action,
reason.clone(),
Some(root.clone()),
)
.await;
if matches!(
rx.await.unwrap_or_default(),
ReviewDecision::Approved | ReviewDecision::ApprovedForSession
) {
// Extend writable roots.
#[allow(clippy::unwrap_used)]
sess.writable_roots.lock().unwrap().push(root);
stdout.clear();
stderr.clear();
result = apply_changes_from_apply_patch_and_report(
&action,
&mut stdout,
&mut stderr,
);
}
}
}
}
// Emit PatchApplyEnd event.
let success_flag = result.is_ok();
let _ = sess
.tx_event
.send(Event {
id: sub_id.to_owned(),
msg: EventMsg::PatchApplyEnd(PatchApplyEndEvent {
call_id: call_id.to_owned(),
stdout: String::from_utf8_lossy(&stdout).to_string(),
stderr: String::from_utf8_lossy(&stderr).to_string(),
success: success_flag,
}),
})
.await;
let item = match result {
Ok(_) => ResponseInputItem::FunctionCallOutput {
SafetyCheck::Reject { reason } => ResponseInputItem::FunctionCallOutput {
call_id: call_id.to_owned(),
output: FunctionCallOutputPayload {
content: String::from_utf8_lossy(&stdout).to_string(),
success: None,
},
},
Err(e) => ResponseInputItem::FunctionCallOutput {
call_id: call_id.to_owned(),
output: FunctionCallOutputPayload {
content: format!("error: {e:#}, stderr: {}", String::from_utf8_lossy(&stderr)),
content: format!("patch rejected: {reason}"),
success: Some(false),
},
},
};
InternalApplyPatchInvocation::Output(item)
}
/// Return the first path in `hunks` that is NOT under any of the
/// `writable_roots` (after normalising). If all paths are acceptable,
/// returns None.
fn first_offending_path(
action: &ApplyPatchAction,
writable_roots: &[PathBuf],
cwd: &Path,
) -> Option<PathBuf> {
let changes = action.changes();
for (path, change) in changes {
let candidate = match change {
ApplyPatchFileChange::Add { .. } => path,
ApplyPatchFileChange::Delete => path,
ApplyPatchFileChange::Update { move_path, .. } => move_path.as_ref().unwrap_or(path),
};
let abs = if candidate.is_absolute() {
candidate.clone()
} else {
cwd.join(candidate)
};
let mut allowed = false;
for root in writable_roots {
let root_abs = if root.is_absolute() {
root.clone()
} else {
cwd.join(root)
};
if abs.starts_with(&root_abs) {
allowed = true;
break;
}
}
if !allowed {
return Some(candidate.clone());
}
.into(),
}
None
}
pub(crate) fn convert_apply_patch_to_protocol(
@@ -327,85 +129,6 @@ pub(crate) fn convert_apply_patch_to_protocol(
result
}
fn apply_changes_from_apply_patch_and_report(
action: &ApplyPatchAction,
stdout: &mut impl std::io::Write,
stderr: &mut impl std::io::Write,
) -> std::io::Result<()> {
match apply_changes_from_apply_patch(action) {
Ok(affected_paths) => {
print_summary(&affected_paths, stdout)?;
}
Err(err) => {
writeln!(stderr, "{err:?}")?;
}
}
Ok(())
}
fn apply_changes_from_apply_patch(action: &ApplyPatchAction) -> anyhow::Result<AffectedPaths> {
let mut added: Vec<PathBuf> = Vec::new();
let mut modified: Vec<PathBuf> = Vec::new();
let mut deleted: Vec<PathBuf> = Vec::new();
let changes = action.changes();
for (path, change) in changes {
match change {
ApplyPatchFileChange::Add { content } => {
if let Some(parent) = path.parent() {
if !parent.as_os_str().is_empty() {
std::fs::create_dir_all(parent).with_context(|| {
format!("Failed to create parent directories for {}", path.display())
})?;
}
}
std::fs::write(path, content)
.with_context(|| format!("Failed to write file {}", path.display()))?;
added.push(path.clone());
}
ApplyPatchFileChange::Delete => {
std::fs::remove_file(path)
.with_context(|| format!("Failed to delete file {}", path.display()))?;
deleted.push(path.clone());
}
ApplyPatchFileChange::Update {
unified_diff: _unified_diff,
move_path,
new_content,
} => {
if let Some(move_path) = move_path {
if let Some(parent) = move_path.parent() {
if !parent.as_os_str().is_empty() {
std::fs::create_dir_all(parent).with_context(|| {
format!(
"Failed to create parent directories for {}",
move_path.display()
)
})?;
}
}
std::fs::rename(path, move_path)
.with_context(|| format!("Failed to rename file {}", path.display()))?;
std::fs::write(move_path, new_content)?;
modified.push(move_path.clone());
deleted.push(path.clone());
} else {
std::fs::write(path, new_content)?;
modified.push(path.clone());
}
}
}
}
Ok(AffectedPaths {
added,
modified,
deleted,
})
}
pub(crate) fn get_writable_roots(cwd: &Path) -> Vec<PathBuf> {
let mut writable_roots = Vec::new();
if cfg!(target_os = "macos") {
+7 -1
View File
@@ -192,7 +192,7 @@ impl ModelClient {
loop {
attempt += 1;
let req_builder = self
let mut req_builder = self
.client
.post(format!("{base_url}/responses"))
.header("OpenAI-Beta", "responses=experimental")
@@ -201,6 +201,12 @@ impl ModelClient {
.header(reqwest::header::ACCEPT, "text/event-stream")
.json(&payload);
if auth.mode == AuthMode::ChatGPT {
if let Some(account_id) = auth.get_account_id().await {
req_builder = req_builder.header("chatgpt-account-id", account_id);
}
}
let req_builder = self.provider.apply_http_headers(req_builder);
let res = req_builder.send().await;
+153 -73
View File
@@ -4,7 +4,6 @@
use std::borrow::Cow;
use std::collections::HashMap;
use std::collections::HashSet;
use std::path::Path;
use std::path::PathBuf;
use std::sync::Arc;
use std::sync::Mutex;
@@ -31,6 +30,7 @@ use tracing::trace;
use tracing::warn;
use uuid::Uuid;
use crate::apply_patch::ApplyPatchExec;
use crate::apply_patch::CODEX_APPLY_PATCH_ARG1;
use crate::apply_patch::InternalApplyPatchInvocation;
use crate::apply_patch::convert_apply_patch_to_protocol;
@@ -74,8 +74,11 @@ use crate::protocol::EventMsg;
use crate::protocol::ExecApprovalRequestEvent;
use crate::protocol::ExecCommandBeginEvent;
use crate::protocol::ExecCommandEndEvent;
use crate::protocol::FileChange;
use crate::protocol::InputItem;
use crate::protocol::Op;
use crate::protocol::PatchApplyBeginEvent;
use crate::protocol::PatchApplyEndEvent;
use crate::protocol::ReviewDecision;
use crate::protocol::SandboxPolicy;
use crate::protocol::SessionConfiguredEvent;
@@ -359,20 +362,32 @@ impl Session {
}
}
async fn notify_exec_command_begin(
&self,
sub_id: &str,
call_id: &str,
command_for_display: Vec<String>,
command_cwd: &Path,
) {
async fn notify_exec_command_begin(&self, exec_command_context: ExecCommandContext) {
let ExecCommandContext {
sub_id,
call_id,
command_for_display,
cwd,
apply_patch,
} = exec_command_context;
let msg = match apply_patch {
Some(ApplyPatchCommandContext {
user_explicitly_approved_this_action,
changes,
}) => EventMsg::PatchApplyBegin(PatchApplyBeginEvent {
call_id,
auto_approved: !user_explicitly_approved_this_action,
changes,
}),
None => EventMsg::ExecCommandBegin(ExecCommandBeginEvent {
call_id,
command: command_for_display.clone(),
cwd,
}),
};
let event = Event {
id: sub_id.to_string(),
msg: EventMsg::ExecCommandBegin(ExecCommandBeginEvent {
call_id: call_id.to_string(),
command: command_for_display,
cwd: command_cwd.to_path_buf(),
}),
msg,
};
let _ = self.tx_event.send(event).await;
}
@@ -384,18 +399,33 @@ impl Session {
stdout: &str,
stderr: &str,
exit_code: i32,
is_apply_patch: bool,
) {
// Because stdout and stderr could each be up to 100 KiB, we send
// truncated versions.
const MAX_STREAM_OUTPUT: usize = 5 * 1024; // 5KiB
let stdout = stdout.chars().take(MAX_STREAM_OUTPUT).collect();
let stderr = stderr.chars().take(MAX_STREAM_OUTPUT).collect();
let msg = if is_apply_patch {
EventMsg::PatchApplyEnd(PatchApplyEndEvent {
call_id: call_id.to_string(),
stdout,
stderr,
success: exit_code == 0,
})
} else {
EventMsg::ExecCommandEnd(ExecCommandEndEvent {
call_id: call_id.to_string(),
stdout,
stderr,
exit_code,
})
};
let event = Event {
id: sub_id.to_string(),
// Because stdout and stderr could each be up to 100 KiB, we send
// truncated versions.
msg: EventMsg::ExecCommandEnd(ExecCommandEndEvent {
call_id: call_id.to_string(),
stdout: stdout.chars().take(MAX_STREAM_OUTPUT).collect(),
stderr: stderr.chars().take(MAX_STREAM_OUTPUT).collect(),
exit_code,
}),
msg,
};
let _ = self.tx_event.send(event).await;
}
@@ -503,6 +533,21 @@ impl State {
}
}
#[derive(Clone, Debug)]
pub(crate) struct ExecCommandContext {
pub(crate) sub_id: String,
pub(crate) call_id: String,
pub(crate) command_for_display: Vec<String>,
pub(crate) cwd: PathBuf,
pub(crate) apply_patch: Option<ApplyPatchCommandContext>,
}
#[derive(Clone, Debug)]
pub(crate) struct ApplyPatchCommandContext {
pub(crate) user_explicitly_approved_this_action: bool,
pub(crate) changes: HashMap<PathBuf, FileChange>,
}
/// A series of Turns in response to user input.
pub(crate) struct AgentTask {
sess: Arc<Session>,
@@ -1567,35 +1612,39 @@ async fn handle_container_exec_with_params(
call_id: String,
) -> ResponseInputItem {
// check if this was a patch, and apply it if so
let apply_patch_action_for_exec =
match maybe_parse_apply_patch_verified(&params.command, &params.cwd) {
MaybeApplyPatchVerified::Body(changes) => {
match apply_patch::apply_patch(sess, &sub_id, &call_id, changes).await {
InternalApplyPatchInvocation::Output(item) => return item,
InternalApplyPatchInvocation::DelegateToExec(action) => Some(action),
let apply_patch_exec = match maybe_parse_apply_patch_verified(&params.command, &params.cwd) {
MaybeApplyPatchVerified::Body(changes) => {
match apply_patch::apply_patch(sess, &sub_id, &call_id, changes).await {
InternalApplyPatchInvocation::Output(item) => return item,
InternalApplyPatchInvocation::DelegateToExec(apply_patch_exec) => {
Some(apply_patch_exec)
}
}
MaybeApplyPatchVerified::CorrectnessError(parse_error) => {
// It looks like an invocation of `apply_patch`, but we
// could not resolve it into a patch that would apply
// cleanly. Return to model for resample.
return ResponseInputItem::FunctionCallOutput {
call_id,
output: FunctionCallOutputPayload {
content: format!("error: {parse_error:#}"),
success: None,
},
};
}
MaybeApplyPatchVerified::ShellParseError(error) => {
trace!("Failed to parse shell command, {error:?}");
None
}
MaybeApplyPatchVerified::NotApplyPatch => None,
};
}
MaybeApplyPatchVerified::CorrectnessError(parse_error) => {
// It looks like an invocation of `apply_patch`, but we
// could not resolve it into a patch that would apply
// cleanly. Return to model for resample.
return ResponseInputItem::FunctionCallOutput {
call_id,
output: FunctionCallOutputPayload {
content: format!("error: {parse_error:#}"),
success: None,
},
};
}
MaybeApplyPatchVerified::ShellParseError(error) => {
trace!("Failed to parse shell command, {error:?}");
None
}
MaybeApplyPatchVerified::NotApplyPatch => None,
};
let (params, safety, command_for_display) = match apply_patch_action_for_exec {
Some(ApplyPatchAction { patch, cwd, .. }) => {
let (params, safety, command_for_display) = match &apply_patch_exec {
Some(ApplyPatchExec {
action: ApplyPatchAction { patch, cwd, .. },
user_explicitly_approved_this_action,
}) => {
let path_to_codex = std::env::current_exe()
.ok()
.map(|p| p.to_string_lossy().to_string());
@@ -1615,13 +1664,22 @@ async fn handle_container_exec_with_params(
CODEX_APPLY_PATCH_ARG1.to_string(),
patch.clone(),
],
cwd,
cwd: cwd.clone(),
timeout_ms: params.timeout_ms,
env: HashMap::new(),
};
let safety =
assess_safety_for_untrusted_command(sess.approval_policy, &sess.sandbox_policy);
(params, safety, vec!["apply_patch".to_string(), patch])
let safety = if *user_explicitly_approved_this_action {
SafetyCheck::AutoApprove {
sandbox_type: SandboxType::None,
}
} else {
assess_safety_for_untrusted_command(sess.approval_policy, &sess.sandbox_policy)
};
(
params,
safety,
vec!["apply_patch".to_string(), patch.clone()],
)
}
None => {
let safety = {
@@ -1682,7 +1740,22 @@ async fn handle_container_exec_with_params(
}
};
sess.notify_exec_command_begin(&sub_id, &call_id, command_for_display.clone(), &params.cwd)
let exec_command_context = ExecCommandContext {
sub_id: sub_id.clone(),
call_id: call_id.clone(),
command_for_display: command_for_display.clone(),
cwd: params.cwd.clone(),
apply_patch: apply_patch_exec.map(
|ApplyPatchExec {
action,
user_explicitly_approved_this_action,
}| ApplyPatchCommandContext {
user_explicitly_approved_this_action,
changes: convert_apply_patch_to_protocol(&action),
},
),
};
sess.notify_exec_command_begin(exec_command_context.clone())
.await;
let params = maybe_run_with_user_profile(params, sess);
@@ -1704,8 +1777,15 @@ async fn handle_container_exec_with_params(
duration,
} = output;
sess.notify_exec_command_end(&sub_id, &call_id, &stdout, &stderr, exit_code)
.await;
sess.notify_exec_command_end(
&sub_id,
&call_id,
&stdout,
&stderr,
exit_code,
exec_command_context.apply_patch.is_some(),
)
.await;
let is_success = exit_code == 0;
let content = format_exec_output(
@@ -1723,16 +1803,7 @@ async fn handle_container_exec_with_params(
}
}
Err(CodexErr::Sandbox(error)) => {
handle_sandbox_error(
error,
sandbox_type,
params,
command_for_display,
sess,
sub_id,
call_id,
)
.await
handle_sandbox_error(params, exec_command_context, error, sandbox_type, sess).await
}
Err(e) => {
// Handle non-sandbox errors
@@ -1748,14 +1819,17 @@ async fn handle_container_exec_with_params(
}
async fn handle_sandbox_error(
params: ExecParams,
exec_command_context: ExecCommandContext,
error: SandboxErr,
sandbox_type: SandboxType,
params: ExecParams,
command_for_display: Vec<String>,
sess: &Session,
sub_id: String,
call_id: String,
) -> ResponseInputItem {
let call_id = exec_command_context.call_id.clone();
let sub_id = exec_command_context.sub_id.clone();
let cwd = exec_command_context.cwd.clone();
let is_apply_patch = exec_command_context.apply_patch.is_some();
// Early out if the user never wants to be asked for approval; just return to the model immediately
if sess.approval_policy == AskForApproval::Never {
return ResponseInputItem::FunctionCallOutput {
@@ -1785,7 +1859,7 @@ async fn handle_sandbox_error(
sub_id.clone(),
call_id.clone(),
params.command.clone(),
params.cwd.clone(),
cwd.clone(),
Some("command failed; retry without sandbox?".to_string()),
)
.await;
@@ -1801,8 +1875,7 @@ async fn handle_sandbox_error(
sess.notify_background_event(&sub_id, "retrying command without sandbox")
.await;
sess.notify_exec_command_begin(&sub_id, &call_id, command_for_display, &params.cwd)
.await;
sess.notify_exec_command_begin(exec_command_context).await;
// This is an escalated retry; the policy will not be
// examined and the sandbox has been set to `None`.
@@ -1824,8 +1897,15 @@ async fn handle_sandbox_error(
duration,
} = retry_output;
sess.notify_exec_command_end(&sub_id, &call_id, &stdout, &stderr, exit_code)
.await;
sess.notify_exec_command_end(
&sub_id,
&call_id,
&stdout,
&stderr,
exit_code,
is_apply_patch,
)
.await;
let is_success = exit_code == 0;
let content = format_exec_output(
+1 -1
View File
@@ -26,7 +26,7 @@ pub struct CodexConversation {
/// that callers can surface the information to the UI.
pub async fn init_codex(config: Config) -> anyhow::Result<CodexConversation> {
let ctrl_c = notify_on_sigint();
let auth = load_auth(&config.codex_home)?;
let auth = load_auth(&config.codex_home, true)?;
let CodexSpawnOk {
codex,
init_id,
+3 -185
View File
@@ -6,7 +6,6 @@ use std::io;
use std::path::Path;
use std::path::PathBuf;
use std::process::ExitStatus;
use std::process::Stdio;
use std::sync::Arc;
use std::time::Duration;
use std::time::Instant;
@@ -15,14 +14,15 @@ use tokio::io::AsyncRead;
use tokio::io::AsyncReadExt;
use tokio::io::BufReader;
use tokio::process::Child;
use tokio::process::Command;
use tokio::sync::Notify;
use tracing::trace;
use crate::error::CodexErr;
use crate::error::Result;
use crate::error::SandboxErr;
use crate::protocol::SandboxPolicy;
use crate::seatbelt::spawn_command_under_seatbelt;
use crate::spawn::StdioPolicy;
use crate::spawn::spawn_child_async;
// Maximum we send for each stream, which is either:
// - 10KiB OR
@@ -37,24 +37,6 @@ const DEFAULT_TIMEOUT_MS: u64 = 10_000;
const SIGKILL_CODE: i32 = 9;
const TIMEOUT_CODE: i32 = 64;
const MACOS_SEATBELT_BASE_POLICY: &str = include_str!("seatbelt_base_policy.sbpl");
/// When working with `sandbox-exec`, only consider `sandbox-exec` in `/usr/bin`
/// to defend against an attacker trying to inject a malicious version on the
/// PATH. If /usr/bin/sandbox-exec has been tampered with, then the attacker
/// already has root access.
const MACOS_PATH_TO_SEATBELT_EXECUTABLE: &str = "/usr/bin/sandbox-exec";
/// Experimental environment variable that will be set to some non-empty value
/// if both of the following are true:
///
/// 1. The process was spawned by Codex as part of a shell tool call.
/// 2. SandboxPolicy.has_full_network_access() was false for the tool call.
///
/// We may try to have just one environment variable for all sandboxing
/// attributes, so this may change in the future.
pub const CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR: &str = "CODEX_SANDBOX_NETWORK_DISABLED";
#[derive(Debug, Clone)]
pub struct ExecParams {
pub command: Vec<String>,
@@ -168,27 +150,6 @@ pub async fn process_exec_tool_call(
}
}
pub async fn spawn_command_under_seatbelt(
command: Vec<String>,
sandbox_policy: &SandboxPolicy,
cwd: PathBuf,
stdio_policy: StdioPolicy,
env: HashMap<String, String>,
) -> std::io::Result<Child> {
let args = create_seatbelt_command_args(command, sandbox_policy, &cwd);
let arg0 = None;
spawn_child_async(
PathBuf::from(MACOS_PATH_TO_SEATBELT_EXECUTABLE),
args,
arg0,
cwd,
sandbox_policy,
stdio_policy,
env,
)
.await
}
/// Spawn a shell tool command under the Linux Landlock+seccomp sandbox helper
/// (codex-linux-sandbox).
///
@@ -248,65 +209,6 @@ fn create_linux_sandbox_command_args(
linux_cmd
}
fn create_seatbelt_command_args(
command: Vec<String>,
sandbox_policy: &SandboxPolicy,
cwd: &Path,
) -> Vec<String> {
let (file_write_policy, extra_cli_args) = {
if sandbox_policy.has_full_disk_write_access() {
// Allegedly, this is more permissive than `(allow file-write*)`.
(
r#"(allow file-write* (regex #"^/"))"#.to_string(),
Vec::<String>::new(),
)
} else {
let writable_roots = sandbox_policy.get_writable_roots_with_cwd(cwd);
let (writable_folder_policies, cli_args): (Vec<String>, Vec<String>) = writable_roots
.iter()
.enumerate()
.map(|(index, root)| {
let param_name = format!("WRITABLE_ROOT_{index}");
let policy: String = format!("(subpath (param \"{param_name}\"))");
let cli_arg = format!("-D{param_name}={}", root.to_string_lossy());
(policy, cli_arg)
})
.unzip();
if writable_folder_policies.is_empty() {
("".to_string(), Vec::<String>::new())
} else {
let file_write_policy = format!(
"(allow file-write*\n{}\n)",
writable_folder_policies.join(" ")
);
(file_write_policy, cli_args)
}
}
};
let file_read_policy = if sandbox_policy.has_full_disk_read_access() {
"; allow read-only file operations\n(allow file-read*)"
} else {
""
};
// TODO(mbolin): apply_patch calls must also honor the SandboxPolicy.
let network_policy = if sandbox_policy.has_full_network_access() {
"(allow network-outbound)\n(allow network-inbound)\n(allow system-socket)"
} else {
""
};
let full_policy = format!(
"{MACOS_SEATBELT_BASE_POLICY}\n{file_read_policy}\n{file_write_policy}\n{network_policy}"
);
let mut seatbelt_args: Vec<String> = vec!["-p".to_string(), full_policy];
seatbelt_args.extend(extra_cli_args);
seatbelt_args.push("--".to_string());
seatbelt_args.extend(command);
seatbelt_args
}
#[derive(Debug)]
pub struct RawExecToolCallOutput {
pub exit_status: ExitStatus,
@@ -352,90 +254,6 @@ async fn exec(
consume_truncated_output(child, ctrl_c, timeout_ms).await
}
#[derive(Debug, Clone, Copy)]
pub enum StdioPolicy {
RedirectForShellTool,
Inherit,
}
/// Spawns the appropriate child process for the ExecParams and SandboxPolicy,
/// ensuring the args and environment variables used to create the `Command`
/// (and `Child`) honor the configuration.
///
/// For now, we take `SandboxPolicy` as a parameter to spawn_child() because
/// we need to determine whether to set the
/// `CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR` environment variable.
async fn spawn_child_async(
program: PathBuf,
args: Vec<String>,
#[cfg_attr(not(unix), allow(unused_variables))] arg0: Option<&str>,
cwd: PathBuf,
sandbox_policy: &SandboxPolicy,
stdio_policy: StdioPolicy,
env: HashMap<String, String>,
) -> std::io::Result<Child> {
trace!(
"spawn_child_async: {program:?} {args:?} {arg0:?} {cwd:?} {sandbox_policy:?} {stdio_policy:?} {env:?}"
);
let mut cmd = Command::new(&program);
#[cfg(unix)]
cmd.arg0(arg0.map_or_else(|| program.to_string_lossy().to_string(), String::from));
cmd.args(args);
cmd.current_dir(cwd);
cmd.env_clear();
cmd.envs(env);
if !sandbox_policy.has_full_network_access() {
cmd.env(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR, "1");
}
// If this Codex process dies (including being killed via SIGKILL), we want
// any child processes that were spawned as part of a `"shell"` tool call
// to also be terminated.
// This relies on prctl(2), so it only works on Linux.
#[cfg(target_os = "linux")]
unsafe {
cmd.pre_exec(|| {
// This prctl call effectively requests, "deliver SIGTERM when my
// current parent dies."
if libc::prctl(libc::PR_SET_PDEATHSIG, libc::SIGTERM) == -1 {
return Err(io::Error::last_os_error());
}
// Though if there was a race condition and this pre_exec() block is
// run _after_ the parent (i.e., the Codex process) has already
// exited, then the parent is the _init_ process (which will never
// die), so we should just terminate the child process now.
if libc::getppid() == 1 {
libc::raise(libc::SIGTERM);
}
Ok(())
});
}
match stdio_policy {
StdioPolicy::RedirectForShellTool => {
// Do not create a file descriptor for stdin because otherwise some
// commands may hang forever waiting for input. For example, ripgrep has
// a heuristic where it may try to read from stdin as explained here:
// https://github.com/BurntSushi/ripgrep/blob/e2362d4d5185d02fa857bf381e7bd52e66fafc73/crates/core/flags/hiargs.rs#L1101-L1103
cmd.stdin(Stdio::null());
cmd.stdout(Stdio::piped()).stderr(Stdio::piped());
}
StdioPolicy::Inherit => {
// Inherit stdin, stdout, and stderr from the parent process.
cmd.stdin(Stdio::inherit())
.stdout(Stdio::inherit())
.stderr(Stdio::inherit());
}
}
cmd.kill_on_drop(true).spawn()
}
/// Consumes the output of a child process, truncating it so it is suitable for
/// use as the output of a `shell` tool call. Also enforces specified timeout.
pub(crate) async fn consume_truncated_output(
+9
View File
@@ -111,9 +111,14 @@ mod tests {
// Helper function to create a test git repository
async fn create_test_git_repo(temp_dir: &TempDir) -> PathBuf {
let repo_path = temp_dir.path().to_path_buf();
let envs = vec![
("GIT_CONFIG_GLOBAL", "/dev/null"),
("GIT_CONFIG_NOSYSTEM", "1"),
];
// Initialize git repo
Command::new("git")
.envs(envs.clone())
.args(["init"])
.current_dir(&repo_path)
.output()
@@ -122,6 +127,7 @@ mod tests {
// Configure git user (required for commits)
Command::new("git")
.envs(envs.clone())
.args(["config", "user.name", "Test User"])
.current_dir(&repo_path)
.output()
@@ -129,6 +135,7 @@ mod tests {
.expect("Failed to set git user name");
Command::new("git")
.envs(envs.clone())
.args(["config", "user.email", "test@example.com"])
.current_dir(&repo_path)
.output()
@@ -140,6 +147,7 @@ mod tests {
fs::write(&test_file, "test content").expect("Failed to write test file");
Command::new("git")
.envs(envs.clone())
.args(["add", "."])
.current_dir(&repo_path)
.output()
@@ -147,6 +155,7 @@ mod tests {
.expect("Failed to add files");
Command::new("git")
.envs(envs.clone())
.args(["commit", "-m", "Initial commit"])
.current_dir(&repo_path)
.output()
+2
View File
@@ -39,7 +39,9 @@ mod project_doc;
pub mod protocol;
mod rollout;
mod safety;
pub mod seatbelt;
pub mod shell;
pub mod spawn;
mod user_notification;
pub mod util;
+7 -5
View File
@@ -41,11 +41,13 @@ pub fn assess_patch_safety(
}
}
if is_write_patch_constrained_to_writable_paths(action, writable_roots, cwd) {
SafetyCheck::AutoApprove {
sandbox_type: SandboxType::None,
}
} else if policy == AskForApproval::OnFailure {
// Even though the patch *appears* to be constrained to writable paths, it
// is possible that paths in the patch are hard links to files outside the
// writable roots, so we should still run `apply_patch` in a sandbox in that
// case.
if is_write_patch_constrained_to_writable_paths(action, writable_roots, cwd)
|| policy == AskForApproval::OnFailure
{
// Only auto‑approve when we can actually enforce a sandbox. Otherwise
// fall back to asking the user because the patch may touch arbitrary
// paths outside the project.
+96
View File
@@ -0,0 +1,96 @@
use std::collections::HashMap;
use std::path::Path;
use std::path::PathBuf;
use tokio::process::Child;
use crate::protocol::SandboxPolicy;
use crate::spawn::StdioPolicy;
use crate::spawn::spawn_child_async;
const MACOS_SEATBELT_BASE_POLICY: &str = include_str!("seatbelt_base_policy.sbpl");
/// When working with `sandbox-exec`, only consider `sandbox-exec` in `/usr/bin`
/// to defend against an attacker trying to inject a malicious version on the
/// PATH. If /usr/bin/sandbox-exec has been tampered with, then the attacker
/// already has root access.
const MACOS_PATH_TO_SEATBELT_EXECUTABLE: &str = "/usr/bin/sandbox-exec";
pub async fn spawn_command_under_seatbelt(
command: Vec<String>,
sandbox_policy: &SandboxPolicy,
cwd: PathBuf,
stdio_policy: StdioPolicy,
env: HashMap<String, String>,
) -> std::io::Result<Child> {
let args = create_seatbelt_command_args(command, sandbox_policy, &cwd);
let arg0 = None;
spawn_child_async(
PathBuf::from(MACOS_PATH_TO_SEATBELT_EXECUTABLE),
args,
arg0,
cwd,
sandbox_policy,
stdio_policy,
env,
)
.await
}
fn create_seatbelt_command_args(
command: Vec<String>,
sandbox_policy: &SandboxPolicy,
cwd: &Path,
) -> Vec<String> {
let (file_write_policy, extra_cli_args) = {
if sandbox_policy.has_full_disk_write_access() {
// Allegedly, this is more permissive than `(allow file-write*)`.
(
r#"(allow file-write* (regex #"^/"))"#.to_string(),
Vec::<String>::new(),
)
} else {
let writable_roots = sandbox_policy.get_writable_roots_with_cwd(cwd);
let (writable_folder_policies, cli_args): (Vec<String>, Vec<String>) = writable_roots
.iter()
.enumerate()
.map(|(index, root)| {
let param_name = format!("WRITABLE_ROOT_{index}");
let policy: String = format!("(subpath (param \"{param_name}\"))");
let cli_arg = format!("-D{param_name}={}", root.to_string_lossy());
(policy, cli_arg)
})
.unzip();
if writable_folder_policies.is_empty() {
("".to_string(), Vec::<String>::new())
} else {
let file_write_policy = format!(
"(allow file-write*\n{}\n)",
writable_folder_policies.join(" ")
);
(file_write_policy, cli_args)
}
}
};
let file_read_policy = if sandbox_policy.has_full_disk_read_access() {
"; allow read-only file operations\n(allow file-read*)"
} else {
""
};
// TODO(mbolin): apply_patch calls must also honor the SandboxPolicy.
let network_policy = if sandbox_policy.has_full_network_access() {
"(allow network-outbound)\n(allow network-inbound)\n(allow system-socket)"
} else {
""
};
let full_policy = format!(
"{MACOS_SEATBELT_BASE_POLICY}\n{file_read_policy}\n{file_write_policy}\n{network_policy}"
);
let mut seatbelt_args: Vec<String> = vec!["-p".to_string(), full_policy];
seatbelt_args.extend(extra_cli_args);
seatbelt_args.push("--".to_string());
seatbelt_args.extend(command);
seatbelt_args
}
+102
View File
@@ -0,0 +1,102 @@
use std::collections::HashMap;
use std::path::PathBuf;
use std::process::Stdio;
use tokio::process::Child;
use tokio::process::Command;
use tracing::trace;
use crate::protocol::SandboxPolicy;
/// Experimental environment variable that will be set to some non-empty value
/// if both of the following are true:
///
/// 1. The process was spawned by Codex as part of a shell tool call.
/// 2. SandboxPolicy.has_full_network_access() was false for the tool call.
///
/// We may try to have just one environment variable for all sandboxing
/// attributes, so this may change in the future.
pub const CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR: &str = "CODEX_SANDBOX_NETWORK_DISABLED";
#[derive(Debug, Clone, Copy)]
pub enum StdioPolicy {
RedirectForShellTool,
Inherit,
}
/// Spawns the appropriate child process for the ExecParams and SandboxPolicy,
/// ensuring the args and environment variables used to create the `Command`
/// (and `Child`) honor the configuration.
///
/// For now, we take `SandboxPolicy` as a parameter to spawn_child() because
/// we need to determine whether to set the
/// `CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR` environment variable.
pub(crate) async fn spawn_child_async(
program: PathBuf,
args: Vec<String>,
#[cfg_attr(not(unix), allow(unused_variables))] arg0: Option<&str>,
cwd: PathBuf,
sandbox_policy: &SandboxPolicy,
stdio_policy: StdioPolicy,
env: HashMap<String, String>,
) -> std::io::Result<Child> {
trace!(
"spawn_child_async: {program:?} {args:?} {arg0:?} {cwd:?} {sandbox_policy:?} {stdio_policy:?} {env:?}"
);
let mut cmd = Command::new(&program);
#[cfg(unix)]
cmd.arg0(arg0.map_or_else(|| program.to_string_lossy().to_string(), String::from));
cmd.args(args);
cmd.current_dir(cwd);
cmd.env_clear();
cmd.envs(env);
if !sandbox_policy.has_full_network_access() {
cmd.env(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR, "1");
}
// If this Codex process dies (including being killed via SIGKILL), we want
// any child processes that were spawned as part of a `"shell"` tool call
// to also be terminated.
// This relies on prctl(2), so it only works on Linux.
#[cfg(target_os = "linux")]
unsafe {
cmd.pre_exec(|| {
// This prctl call effectively requests, "deliver SIGTERM when my
// current parent dies."
if libc::prctl(libc::PR_SET_PDEATHSIG, libc::SIGTERM) == -1 {
return Err(std::io::Error::last_os_error());
}
// Though if there was a race condition and this pre_exec() block is
// run _after_ the parent (i.e., the Codex process) has already
// exited, then the parent is the _init_ process (which will never
// die), so we should just terminate the child process now.
if libc::getppid() == 1 {
libc::raise(libc::SIGTERM);
}
Ok(())
});
}
match stdio_policy {
StdioPolicy::RedirectForShellTool => {
// Do not create a file descriptor for stdin because otherwise some
// commands may hang forever waiting for input. For example, ripgrep has
// a heuristic where it may try to read from stdin as explained here:
// https://github.com/BurntSushi/ripgrep/blob/e2362d4d5185d02fa857bf381e7bd52e66fafc73/crates/core/flags/hiargs.rs#L1101-L1103
cmd.stdin(Stdio::null());
cmd.stdout(Stdio::piped()).stderr(Stdio::piped());
}
StdioPolicy::Inherit => {
// Inherit stdin, stdout, and stderr from the parent process.
cmd.stdin(Stdio::inherit())
.stdout(Stdio::inherit())
.stderr(Stdio::inherit());
}
}
cmd.kill_on_drop(true).spawn()
}
+12 -1
View File
@@ -1,7 +1,7 @@
#![expect(clippy::unwrap_used)]
use assert_cmd::Command as AssertCommand;
use codex_core::exec::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
use codex_core::spawn::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
use std::time::Duration;
use std::time::Instant;
use tempfile::TempDir;
@@ -460,9 +460,14 @@ async fn integration_git_info_unit_test() {
// 1. Create temp directory for git repo
let temp_dir = TempDir::new().unwrap();
let git_repo = temp_dir.path().to_path_buf();
let envs = vec![
("GIT_CONFIG_GLOBAL", "/dev/null"),
("GIT_CONFIG_NOSYSTEM", "1"),
];
// 2. Initialize a git repository with some content
let init_output = std::process::Command::new("git")
.envs(envs.clone())
.args(["init"])
.current_dir(&git_repo)
.output()
@@ -471,12 +476,14 @@ async fn integration_git_info_unit_test() {
// Configure git user (required for commits)
std::process::Command::new("git")
.envs(envs.clone())
.args(["config", "user.name", "Integration Test"])
.current_dir(&git_repo)
.output()
.unwrap();
std::process::Command::new("git")
.envs(envs.clone())
.args(["config", "user.email", "test@example.com"])
.current_dir(&git_repo)
.output()
@@ -487,12 +494,14 @@ async fn integration_git_info_unit_test() {
std::fs::write(&test_file, "integration test content").unwrap();
std::process::Command::new("git")
.envs(envs.clone())
.args(["add", "."])
.current_dir(&git_repo)
.output()
.unwrap();
let commit_output = std::process::Command::new("git")
.envs(envs.clone())
.args(["commit", "-m", "Integration test commit"])
.current_dir(&git_repo)
.output()
@@ -501,6 +510,7 @@ async fn integration_git_info_unit_test() {
// Create a branch to test branch detection
std::process::Command::new("git")
.envs(envs.clone())
.args(["checkout", "-b", "integration-test-branch"])
.current_dir(&git_repo)
.output()
@@ -508,6 +518,7 @@ async fn integration_git_info_unit_test() {
// Add a remote to test repository URL detection
std::process::Command::new("git")
.envs(envs.clone())
.args([
"remote",
"add",
+8 -6
View File
@@ -5,11 +5,11 @@ use codex_core::Codex;
use codex_core::CodexSpawnOk;
use codex_core::ModelProviderInfo;
use codex_core::built_in_model_providers;
use codex_core::exec::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
use codex_core::protocol::EventMsg;
use codex_core::protocol::InputItem;
use codex_core::protocol::Op;
use codex_core::protocol::SessionConfiguredEvent;
use codex_core::spawn::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
use codex_login::AuthDotJson;
use codex_login::AuthMode;
use codex_login::CodexAuth;
@@ -237,6 +237,7 @@ async fn chatgpt_auth_sends_correct_request() {
let request_session_id = request.headers.get("session_id").unwrap();
let request_originator = request.headers.get("originator").unwrap();
let request_authorization = request.headers.get("authorization").unwrap();
let request_chatgpt_account_id = request.headers.get("chatgpt-account-id").unwrap();
let request_body = request.body_json::<serde_json::Value>().unwrap();
assert!(current_session_id.is_some());
@@ -249,6 +250,7 @@ async fn chatgpt_auth_sends_correct_request() {
request_authorization.to_str().unwrap(),
"Bearer Access Token"
);
assert_eq!(request_chatgpt_account_id.to_str().unwrap(), "account_id");
assert!(!request_body["store"].as_bool().unwrap());
assert!(request_body["stream"].as_bool().unwrap());
assert_eq!(
@@ -327,14 +329,14 @@ fn auth_from_token(id_token: String) -> CodexAuth {
AuthMode::ChatGPT,
PathBuf::new(),
Some(AuthDotJson {
tokens: TokenData {
openai_api_key: None,
tokens: Some(TokenData {
id_token,
access_token: "Access Token".to_string(),
refresh_token: "test".to_string(),
account_id: None,
},
last_refresh: Utc::now(),
openai_api_key: None,
account_id: Some("account_id".to_string()),
}),
last_refresh: Some(Utc::now()),
}),
)
}
+1 -1
View File
@@ -6,10 +6,10 @@ use std::time::Duration;
use codex_core::Codex;
use codex_core::CodexSpawnOk;
use codex_core::ModelProviderInfo;
use codex_core::exec::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
use codex_core::protocol::EventMsg;
use codex_core::protocol::InputItem;
use codex_core::protocol::Op;
use codex_core::spawn::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
use codex_login::CodexAuth;
use core_test_support::load_default_config_for_test;
use core_test_support::load_sse_fixture;
+3
View File
@@ -18,3 +18,6 @@ tokio = { version = "1", features = [
"rt-multi-thread",
"signal",
] }
[dev-dependencies]
tempfile = "3"
+177 -36
View File
@@ -20,7 +20,7 @@ use tokio::process::Command;
const SOURCE_FOR_PYTHON_SERVER: &str = include_str!("./login_with_chatgpt.py");
const CLIENT_ID: &str = "app_EMoamEEZ73f0CkXaXp7hrann";
const OPENAI_API_KEY_ENV_VAR: &str = "OPENAI_API_KEY";
pub const OPENAI_API_KEY_ENV_VAR: &str = "OPENAI_API_KEY";
#[derive(Clone, Debug, PartialEq)]
pub enum AuthMode {
@@ -70,13 +70,16 @@ impl CodexAuth {
pub async fn get_token_data(&self) -> Result<TokenData, std::io::Error> {
#[expect(clippy::unwrap_used)]
let auth_dot_json = self.auth_dot_json.lock().unwrap().clone();
match auth_dot_json {
Some(auth_dot_json) => {
if auth_dot_json.last_refresh < Utc::now() - chrono::Duration::days(28) {
Some(AuthDotJson {
tokens: Some(mut tokens),
last_refresh: Some(last_refresh),
..
}) => {
if last_refresh < Utc::now() - chrono::Duration::days(28) {
let refresh_response = tokio::time::timeout(
Duration::from_secs(60),
try_refresh_token(auth_dot_json.tokens.refresh_token.clone()),
try_refresh_token(tokens.refresh_token.clone()),
)
.await
.map_err(|_| {
@@ -92,13 +95,21 @@ impl CodexAuth {
)
.await?;
tokens = updated_auth_dot_json
.tokens
.clone()
.ok_or(std::io::Error::other(
"Token data is not available after refresh.",
))?;
#[expect(clippy::unwrap_used)]
let mut auth_dot_json = self.auth_dot_json.lock().unwrap();
*auth_dot_json = Some(updated_auth_dot_json);
let mut auth_lock = self.auth_dot_json.lock().unwrap();
*auth_lock = Some(updated_auth_dot_json);
}
Ok(auth_dot_json.tokens.clone())
Ok(tokens)
}
None => Err(std::io::Error::other("Token data is not available.")),
_ => Err(std::io::Error::other("Token data is not available.")),
}
}
@@ -112,11 +123,22 @@ impl CodexAuth {
}
}
}
pub async fn get_account_id(&self) -> Option<String> {
match self.mode {
AuthMode::ApiKey => None,
AuthMode::ChatGPT => {
let token_data = self.get_token_data().await.ok()?;
token_data.account_id.clone()
}
}
}
}
// Loads the available auth information from the auth.json or OPENAI_API_KEY environment variable.
pub fn load_auth(codex_home: &Path) -> std::io::Result<Option<CodexAuth>> {
let auth_file = codex_home.join("auth.json");
pub fn load_auth(codex_home: &Path, include_env_var: bool) -> std::io::Result<Option<CodexAuth>> {
let auth_file = get_auth_file(codex_home);
let auth_dot_json = try_read_auth_json(&auth_file).ok();
@@ -125,12 +147,21 @@ pub fn load_auth(codex_home: &Path) -> std::io::Result<Option<CodexAuth>> {
.and_then(|a| a.openai_api_key.clone())
.filter(|s| !s.is_empty());
let openai_api_key = env::var(OPENAI_API_KEY_ENV_VAR)
.ok()
.filter(|s| !s.is_empty())
.or(auth_json_api_key);
let openai_api_key = if include_env_var {
env::var(OPENAI_API_KEY_ENV_VAR)
.ok()
.filter(|s| !s.is_empty())
.or(auth_json_api_key)
} else {
auth_json_api_key
};
if openai_api_key.is_none() && auth_dot_json.is_none() {
let has_tokens = auth_dot_json
.as_ref()
.and_then(|a| a.tokens.as_ref())
.is_some();
if openai_api_key.is_none() && !has_tokens {
return Ok(None);
}
@@ -148,6 +179,10 @@ pub fn load_auth(codex_home: &Path) -> std::io::Result<Option<CodexAuth>> {
}))
}
fn get_auth_file(codex_home: &Path) -> PathBuf {
codex_home.join("auth.json")
}
/// Run `python3 -c {{SOURCE_FOR_PYTHON_SERVER}}` with the CODEX_HOME
/// environment variable set to the provided `codex_home` path. If the
/// subprocess exits 0, read the OPENAI_API_KEY property out of
@@ -187,6 +222,15 @@ pub async fn login_with_chatgpt(codex_home: &Path, capture_output: bool) -> std:
}
}
pub fn login_with_api_key(codex_home: &Path, api_key: &str) -> std::io::Result<()> {
let auth_dot_json = AuthDotJson {
openai_api_key: Some(api_key.to_string()),
tokens: None,
last_refresh: None,
};
write_auth_json(&get_auth_file(codex_home), &auth_dot_json)
}
/// Attempt to read and refresh the `auth.json` file in the given `CODEX_HOME` directory.
/// Returns the full AuthDotJson structure after refreshing if necessary.
pub fn try_read_auth_json(auth_file: &Path) -> std::io::Result<AuthDotJson> {
@@ -198,35 +242,38 @@ pub fn try_read_auth_json(auth_file: &Path) -> std::io::Result<AuthDotJson> {
Ok(auth_dot_json)
}
async fn update_tokens(
auth_file: &Path,
id_token: String,
access_token: Option<String>,
refresh_token: Option<String>,
) -> std::io::Result<AuthDotJson> {
fn write_auth_json(auth_file: &Path, auth_dot_json: &AuthDotJson) -> std::io::Result<()> {
let json_data = serde_json::to_string_pretty(auth_dot_json)?;
let mut options = OpenOptions::new();
options.truncate(true).write(true).create(true);
#[cfg(unix)]
{
options.mode(0o600);
}
let mut file = options.open(auth_file)?;
file.write_all(json_data.as_bytes())?;
file.flush()?;
Ok(())
}
async fn update_tokens(
auth_file: &Path,
id_token: String,
access_token: Option<String>,
refresh_token: Option<String>,
) -> std::io::Result<AuthDotJson> {
let mut auth_dot_json = try_read_auth_json(auth_file)?;
auth_dot_json.tokens.id_token = id_token.to_string();
let tokens = auth_dot_json.tokens.get_or_insert_with(TokenData::default);
tokens.id_token = id_token.to_string();
if let Some(access_token) = access_token {
auth_dot_json.tokens.access_token = access_token.to_string();
tokens.access_token = access_token.to_string();
}
if let Some(refresh_token) = refresh_token {
auth_dot_json.tokens.refresh_token = refresh_token.to_string();
}
auth_dot_json.last_refresh = Utc::now();
let json_data = serde_json::to_string_pretty(&auth_dot_json)?;
{
let mut file = options.open(auth_file)?;
file.write_all(json_data.as_bytes())?;
file.flush()?;
tokens.refresh_token = refresh_token.to_string();
}
auth_dot_json.last_refresh = Some(Utc::now());
write_auth_json(auth_file, &auth_dot_json)?;
Ok(auth_dot_json)
}
@@ -282,12 +329,14 @@ pub struct AuthDotJson {
#[serde(rename = "OPENAI_API_KEY")]
pub openai_api_key: Option<String>,
pub tokens: TokenData,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub tokens: Option<TokenData>,
pub last_refresh: DateTime<Utc>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub last_refresh: Option<DateTime<Utc>>,
}
#[derive(Deserialize, Serialize, Clone, Debug, PartialEq)]
#[derive(Deserialize, Serialize, Clone, Debug, PartialEq, Default)]
pub struct TokenData {
/// This is a JWT.
pub id_token: String,
@@ -299,3 +348,95 @@ pub struct TokenData {
pub account_id: Option<String>,
}
#[cfg(test)]
mod tests {
use super::*;
use tempfile::tempdir;
#[test]
#[expect(clippy::unwrap_used)]
fn writes_api_key_and_loads_auth() {
let dir = tempdir().unwrap();
login_with_api_key(dir.path(), "sk-test-key").unwrap();
let auth = load_auth(dir.path(), false).unwrap().unwrap();
assert_eq!(auth.mode, AuthMode::ApiKey);
assert_eq!(auth.api_key.as_deref(), Some("sk-test-key"));
}
#[test]
#[expect(clippy::unwrap_used)]
fn loads_from_env_var_if_env_var_exists() {
let dir = tempdir().unwrap();
let env_var = std::env::var(OPENAI_API_KEY_ENV_VAR);
if let Ok(env_var) = env_var {
let auth = load_auth(dir.path(), true).unwrap().unwrap();
assert_eq!(auth.mode, AuthMode::ApiKey);
assert_eq!(auth.api_key, Some(env_var));
}
}
#[tokio::test]
#[expect(clippy::unwrap_used)]
async fn loads_token_data_from_auth_json() {
let dir = tempdir().unwrap();
let auth_file = dir.path().join("auth.json");
std::fs::write(
auth_file,
format!(
r#"
{{
"OPENAI_API_KEY": null,
"tokens": {{
"id_token": "test-id-token",
"access_token": "test-access-token",
"refresh_token": "test-refresh-token"
}},
"last_refresh": "{}"
}}
"#,
Utc::now().to_rfc3339()
),
)
.unwrap();
let auth = load_auth(dir.path(), false).unwrap().unwrap();
assert_eq!(auth.mode, AuthMode::ChatGPT);
assert_eq!(auth.api_key, None);
assert_eq!(
auth.get_token_data().await.unwrap(),
TokenData {
id_token: "test-id-token".to_string(),
access_token: "test-access-token".to_string(),
refresh_token: "test-refresh-token".to_string(),
account_id: None,
}
);
}
#[tokio::test]
#[expect(clippy::unwrap_used)]
async fn loads_api_key_from_auth_json() {
let dir = tempdir().unwrap();
let auth_file = dir.path().join("auth.json");
std::fs::write(
auth_file,
r#"
{
"OPENAI_API_KEY": "sk-test-key",
"tokens": null,
"last_refresh": null
}
"#,
)
.unwrap();
let auth = load_auth(dir.path(), false).unwrap().unwrap();
assert_eq!(auth.mode, AuthMode::ApiKey);
assert_eq!(auth.api_key, Some("sk-test-key".to_string()));
assert!(auth.get_token_data().await.is_err());
}
}
+1 -1
View File
@@ -3,9 +3,9 @@ use std::env;
use std::path::Path;
use std::path::PathBuf;
use codex_core::exec::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
use codex_core::protocol::FileChange;
use codex_core::protocol::ReviewDecision;
use codex_core::spawn::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
use codex_mcp_server::CodexToolCallParam;
use codex_mcp_server::ExecApprovalElicitRequestParams;
use codex_mcp_server::ExecApprovalResponse;
+1 -1
View File
@@ -3,7 +3,7 @@
use std::path::Path;
use codex_core::exec::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
use codex_core::spawn::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
use codex_mcp_server::CodexToolCallParam;
use mcp_types::JSONRPCResponse;
use mcp_types::RequestId;
+4 -2
View File
@@ -96,7 +96,9 @@ impl App<'_> {
if let Ok(event) = crossterm::event::read() {
match event {
crossterm::event::Event::Key(key_event) => {
app_event_tx.send(AppEvent::KeyEvent(key_event));
if key_event.kind == crossterm::event::KeyEventKind::Press {
app_event_tx.send(AppEvent::KeyEvent(key_event));
}
}
crossterm::event::Event::Resize(_, _) => {
app_event_tx.send(AppEvent::RequestRedraw);
@@ -362,7 +364,7 @@ impl App<'_> {
AppState::GitWarning { .. } => 10,
};
let mut area = terminal.viewport_area;
area.height = desired_height;
area.height = desired_height.min(size.height);
area.width = size.width;
if area.bottom() > size.height {
terminal
+4
View File
@@ -293,6 +293,10 @@ impl ChatWidget<'_> {
self.add_to_history(HistoryCell::new_error_event(message.clone()));
self.bottom_pane.set_task_running(false);
}
EventMsg::PlanUpdate(update) => {
self.add_to_history(HistoryCell::new_plan_update(update));
self.request_redraw();
}
EventMsg::ExecApprovalRequest(ExecApprovalRequestEvent {
call_id: _,
command,
+96
View File
@@ -9,6 +9,9 @@ use codex_common::summarize_sandbox_policy;
use codex_core::WireApi;
use codex_core::config::Config;
use codex_core::model_supports_reasoning_summaries;
use codex_core::plan_tool::PlanItemArg;
use codex_core::plan_tool::StepStatus;
use codex_core::plan_tool::UpdatePlanArgs;
use codex_core::protocol::FileChange;
use codex_core::protocol::McpInvocation;
use codex_core::protocol::SessionConfiguredEvent;
@@ -109,6 +112,10 @@ pub(crate) enum HistoryCell {
/// behaviour of `ActiveExecCommand` so the user sees *what* patch the
/// model wants to apply before being prompted to approve or deny it.
PendingPatch { view: TextBlock },
/// A human‑friendly rendering of the model's current plan and step
/// statuses provided via the `update_plan` tool.
PlanUpdate { view: TextBlock },
}
const TOOL_CALL_MAX_LINES: usize = 5;
@@ -130,6 +137,7 @@ impl HistoryCell {
| HistoryCell::CompletedExecCommand { view }
| HistoryCell::CompletedMcpToolCall { view }
| HistoryCell::PendingPatch { view }
| HistoryCell::PlanUpdate { view }
| HistoryCell::ActiveExecCommand { view, .. }
| HistoryCell::ActiveMcpToolCall { view, .. } => {
view.lines.iter().map(line_to_static).collect()
@@ -477,6 +485,94 @@ impl HistoryCell {
}
}
/// Render a user‑friendly plan update with colourful status icons and a
/// simple progress indicator so users can follow along.
pub(crate) fn new_plan_update(update: UpdatePlanArgs) -> Self {
let UpdatePlanArgs { explanation, plan } = update;
let mut lines: Vec<Line<'static>> = Vec::new();
// Title
lines.push(Line::from("plan".magenta().bold()));
if !plan.is_empty() {
// Progress bar – show completed/total with a visual bar
let total = plan.len();
let completed = plan
.iter()
.filter(|p| matches!(p.status, StepStatus::Completed))
.count();
let width: usize = 20;
let filled = (completed * width + total / 2) / total;
let empty = width.saturating_sub(filled);
let mut bar_spans: Vec<Span> = Vec::new();
if filled > 0 {
bar_spans.push(Span::styled(
"█".repeat(filled),
Style::default().fg(Color::Green),
));
}
if empty > 0 {
bar_spans.push(Span::styled(
"░".repeat(empty),
Style::default().fg(Color::Gray),
));
}
let progress_prefix = Span::raw("progress [");
let progress_suffix = Span::raw("] ");
let fraction = Span::raw(format!("{completed}/{total}"));
let mut progress_line_spans = vec![progress_prefix];
progress_line_spans.extend(bar_spans);
progress_line_spans.push(progress_suffix);
progress_line_spans.push(fraction);
lines.push(Line::from(progress_line_spans));
}
// Optional explanation/note from the model
if let Some(expl) = explanation.and_then(|s| {
let t = s.trim().to_string();
if t.is_empty() { None } else { Some(t) }
}) {
lines.push(Line::from("note".gray().italic()));
for l in expl.lines() {
lines.push(Line::from(l.to_string()).gray());
}
}
// Steps (1‑based numbering) with fun, readable status icons
if plan.is_empty() {
lines.push(Line::from("(no steps provided)".gray().italic()));
} else {
for (idx, PlanItemArg { step, status }) in plan.into_iter().enumerate() {
let num = idx + 1;
let (icon, style): (&str, Style) = match status {
StepStatus::Completed => ("✓", Style::default().fg(Color::Green)),
StepStatus::InProgress => (
"▶",
Style::default()
.fg(Color::Yellow)
.add_modifier(Modifier::BOLD),
),
StepStatus::Pending => ("○", Style::default().fg(Color::Gray)),
};
let prefix = vec![
Span::raw(format!("{num:>2}. [")),
Span::styled(icon.to_string(), style),
Span::raw("] "),
];
let mut spans = prefix;
spans.push(Span::raw(step));
lines.push(Line::from(spans));
}
}
lines.push(Line::from(""));
HistoryCell::PlanUpdate {
view: TextBlock::new(lines),
}
}
/// Create a new `PendingPatch` cell that lists the file‑level summary of
/// a proposed patch. The summary lines should already be formatted (e.g.
/// "A path/to/file.rs").
+2 -2
View File
@@ -36,12 +36,12 @@ pub(crate) fn insert_history_lines(terminal: &mut tui::Tui, lines: Vec<Line>) {
.backend_mut()
.scroll_region_down(area.top()..screen_size.height, scroll_amount)
.ok();
let cursor_top = area.top() - 1;
let cursor_top = area.top().saturating_sub(1);
area.y += scroll_amount;
terminal.set_viewport_area(area);
cursor_top
} else {
area.top() - 1
area.top().saturating_sub(1)
};
// Limit the scroll region to the lines from the top of the screen to the
+8 -4
View File
@@ -75,7 +75,7 @@ pub async fn run_main(
config_profile: cli.config_profile.clone(),
codex_linux_sandbox_exe,
base_instructions: None,
include_plan_tool: None,
include_plan_tool: Some(true),
};
// Parse `-c` overrides from the CLI.
let cli_kv_overrides = match cli.config_overrides.parse_overrides() {
@@ -176,9 +176,13 @@ fn run_ratatui_app(
color_eyre::install()?;
// Forward panic reports through tracing so they appear in the UI status
// line instead of interleaving raw panic output with the interface.
std::panic::set_hook(Box::new(|info| {
// line, but do not swallow the default/color-eyre panic handler.
// Chain to the previous hook so users still get a rich panic report
// (including backtraces) after we restore the terminal.
let prev_hook = std::panic::take_hook();
std::panic::set_hook(Box::new(move |info| {
tracing::error!("panic: {info}");
prev_hook(info);
}));
let mut terminal = tui::init(&config)?;
terminal.clear()?;
@@ -222,7 +226,7 @@ fn should_show_login_screen(config: &Config) -> bool {
// Reading the OpenAI API key is an async operation because it may need
// to refresh the token. Block on it.
let codex_home = config.codex_home.clone();
match load_auth(&codex_home) {
match load_auth(&codex_home, true) {
Ok(Some(_)) => false,
Ok(None) => true,
Err(err) => {