Merge branch 'main' into codex/add-raw-chain-of-thought-in-codex-cli

This commit is contained in:
aibrahim-oai
2025-07-31 21:35:17 -07:00
committed by GitHub
48 changed files with 1587 additions and 864 deletions
+21
View File
@@ -0,0 +1,21 @@
You are a summarization assistant. A conversation follows between a user and a coding-focused AI (Codex). Your task is to generate a clear summary capturing:
• High-level objective or problem being solved
• Key instructions or design decisions given by the user
• Main code actions or behaviors from the AI
• Important variables, functions, modules, or outputs discussed
• Any unresolved questions or next steps
Produce the summary in a structured format like:
**Objective:** …
**User instructions:** … (bulleted)
**AI actions / code behavior:** … (bulleted)
**Important entities:** … (e.g. function names, variables, files)
**Open issues / next steps:** … (if any)
**Summary (concise):** (one or two sentences)
+3
View File
@@ -793,6 +793,7 @@ dependencies = [
"reqwest",
"serde",
"serde_json",
"tempfile",
"tokio",
]
@@ -2642,6 +2643,7 @@ version = "0.0.0"
dependencies = [
"anyhow",
"assert_cmd",
"codex-core",
"codex-mcp-server",
"mcp-types",
"pretty_assertions",
@@ -2649,6 +2651,7 @@ dependencies = [
"shlex",
"tempfile",
"tokio",
"uuid",
"wiremock",
]
+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);
+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;
+304 -76
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;
@@ -76,8 +76,11 @@ 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;
@@ -361,20 +364,32 @@ 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;
}
@@ -386,18 +401,33 @@ 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;
}
@@ -415,6 +445,12 @@ impl Session {
let _ = self.tx_event.send(event).await;
}
/// Build the full turn input by concatenating the current conversation
/// history with additional items for this turn.
pub fn turn_input_with_history(&self, extra: Vec<ResponseItem>) -> Vec<ResponseItem> {
[self.state.lock().unwrap().history.contents(), extra].concat()
}
/// Returns the input if there was no task running to inject into
pub fn inject_input(&self, input: Vec<InputItem>) -> Result<(), Vec<InputItem>> {
let mut state = self.state.lock().unwrap();
@@ -505,6 +541,21 @@ 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>,
@@ -522,6 +573,25 @@ impl AgentTask {
handle,
}
}
fn compact(
sess: Arc<Session>,
sub_id: String,
input: Vec<InputItem>,
compact_instructions: String,
) -> Self {
let handle = tokio::spawn(run_compact_task(
Arc::clone(&sess),
sub_id.clone(),
input,
compact_instructions,
))
.abort_handle();
Self {
sess,
sub_id,
handle,
}
}
fn abort(self) {
if !self.handle.is_finished() {
@@ -843,6 +913,31 @@ async fn submission_loop(
}
});
}
Op::Compact => {
let sess = match sess.as_ref() {
Some(sess) => sess,
None => {
send_no_session_event(sub.id).await;
continue;
}
};
// Create a summarization request as user input
const SUMMARIZATION_PROMPT: &str = include_str!("../../../SUMMARY.md");
// Attempt to inject input into current task
if let Err(items) = sess.inject_input(vec![InputItem::Text {
text: "Start Summarization".to_string(),
}]) {
let task = AgentTask::compact(
sess.clone(),
sub.id,
items,
SUMMARIZATION_PROMPT.to_string(),
);
sess.set_task(task);
}
}
Op::Shutdown => {
info!("Shutting down Codex instance");
@@ -904,7 +999,7 @@ async fn run_task(sess: Arc<Session>, sub_id: String, input: Vec<InputItem>) {
return;
}
let initial_input_for_turn = ResponseInputItem::from(input);
let initial_input_for_turn: ResponseInputItem = ResponseInputItem::from(input);
sess.record_conversation_items(&[initial_input_for_turn.clone().into()])
.await;
@@ -925,8 +1020,7 @@ async fn run_task(sess: Arc<Session>, sub_id: String, input: Vec<InputItem>) {
// conversation history on each turn. The rollout file, however, should
// only record the new items that originated in this turn so that it
// represents an append-only log without duplicates.
let turn_input: Vec<ResponseItem> =
[sess.state.lock().unwrap().history.contents(), pending_input].concat();
let turn_input: Vec<ResponseItem> = sess.turn_input_with_history(pending_input);
let turn_input_messages: Vec<String> = turn_input
.iter()
@@ -1253,6 +1347,88 @@ async fn try_run_turn(
}
}
async fn run_compact_task(
sess: Arc<Session>,
sub_id: String,
input: Vec<InputItem>,
compact_instructions: String,
) {
let start_event = Event {
id: sub_id.clone(),
msg: EventMsg::TaskStarted,
};
if sess.tx_event.send(start_event).await.is_err() {
return;
}
let initial_input_for_turn: ResponseInputItem = ResponseInputItem::from(input);
let turn_input: Vec<ResponseItem> =
sess.turn_input_with_history(vec![initial_input_for_turn.clone().into()]);
let prompt = Prompt {
input: turn_input,
user_instructions: None,
store: !sess.disable_response_storage,
extra_tools: HashMap::new(),
base_instructions_override: Some(compact_instructions.clone()),
};
let max_retries = sess.client.get_provider().stream_max_retries();
let mut retries = 0;
loop {
let attempt_result = drain_to_completed(&sess, &prompt).await;
match attempt_result {
Ok(()) => break,
Err(CodexErr::Interrupted) => return,
Err(e) => {
if retries < max_retries {
retries += 1;
let delay = backoff(retries);
sess.notify_background_event(
&sub_id,
format!(
"stream error: {e}; retrying {retries}/{max_retries} in {delay:?}…"
),
)
.await;
tokio::time::sleep(delay).await;
continue;
} else {
let event = Event {
id: sub_id.clone(),
msg: EventMsg::Error(ErrorEvent {
message: e.to_string(),
}),
};
sess.send_event(event).await;
return;
}
}
}
}
sess.remove_task(&sub_id);
let event = Event {
id: sub_id.clone(),
msg: EventMsg::AgentMessage(AgentMessageEvent {
message: "Compact task completed".to_string(),
}),
};
sess.send_event(event).await;
let event = Event {
id: sub_id.clone(),
msg: EventMsg::TaskComplete(TaskCompleteEvent {
last_agent_message: None,
}),
};
sess.send_event(event).await;
let mut state = sess.state.lock().unwrap();
state.history.keep_last_messages(1);
}
async fn handle_response_item(
sess: &Session,
sub_id: &str,
@@ -1453,35 +1629,39 @@ 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());
@@ -1501,13 +1681,22 @@ 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 = {
@@ -1568,7 +1757,22 @@ 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);
@@ -1590,8 +1794,15 @@ 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(
@@ -1609,16 +1820,7 @@ 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
@@ -1634,14 +1836,17 @@ 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 {
@@ -1671,7 +1876,7 @@ 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;
@@ -1687,8 +1892,7 @@ 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`.
@@ -1710,8 +1914,15 @@ 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(
@@ -1801,3 +2012,20 @@ fn get_last_assistant_message_from_turn(responses: &[ResponseItem]) -> Option<St
}
})
}
async fn drain_to_completed(sess: &Session, prompt: &Prompt) -> CodexResult<()> {
let mut stream = sess.client.clone().stream(prompt).await?;
loop {
let maybe_event = stream.next().await;
let Some(event) = maybe_event else {
return Err(CodexErr::Stream(
"stream closed before response.completed".into(),
));
};
match event {
Ok(ResponseEvent::Completed { .. }) => return Ok(()),
Ok(_) => continue,
Err(e) => return Err(e),
}
}
}
+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,
+28
View File
@@ -30,6 +30,34 @@ impl ConversationHistory {
}
}
}
pub(crate) fn keep_last_messages(&mut self, n: usize) {
if n == 0 {
self.items.clear();
return;
}
// Collect the last N message items (assistant/user), newest to oldest.
let mut kept: Vec<ResponseItem> = Vec::with_capacity(n);
for item in self.items.iter().rev() {
if let ResponseItem::Message { role, content, .. } = item {
kept.push(ResponseItem::Message {
// we need to remove the id or the model will complain that messages are sent without
// their reasonings
id: None,
role: role.clone(),
content: content.clone(),
});
if kept.len() == n {
break;
}
}
}
// Preserve chronological order (oldest to newest) within the kept slice.
kept.reverse();
self.items = kept;
}
}
/// Anything that is not a system message or "reasoning" message is considered
+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(
+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;
+4
View File
@@ -121,6 +121,10 @@ pub enum Op {
/// Request a single history entry identified by `log_id` + `offset`.
GetHistoryEntryRequest { offset: usize, log_id: u64 },
/// Request the agent to summarize the current conversation context.
/// The agent will use its existing context (either conversation history or previous response id)
/// to generate a summary which will be returned as an AgentMessage event.
Compact,
/// Request to shut down codex instance.
Shutdown,
}
+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()
}
+1 -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;
+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()),
}),
)
}
+254
View File
@@ -0,0 +1,254 @@
#![expect(clippy::unwrap_used)]
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_login::CodexAuth;
use core_test_support::load_default_config_for_test;
use core_test_support::wait_for_event;
use serde_json::Value;
use tempfile::TempDir;
use wiremock::Mock;
use wiremock::MockServer;
use wiremock::ResponseTemplate;
use wiremock::matchers::method;
use wiremock::matchers::path;
use pretty_assertions::assert_eq;
// --- Test helpers -----------------------------------------------------------
/// Build an SSE stream body from a list of JSON events.
fn sse(events: Vec<Value>) -> String {
use std::fmt::Write as _;
let mut out = String::new();
for ev in events {
let kind = ev.get("type").and_then(|v| v.as_str()).unwrap();
writeln!(&mut out, "event: {kind}").unwrap();
if !ev.as_object().map(|o| o.len() == 1).unwrap_or(false) {
write!(&mut out, "data: {ev}\n\n").unwrap();
} else {
out.push('\n');
}
}
out
}
/// Convenience: SSE event for a completed response with a specific id.
fn ev_completed(id: &str) -> Value {
serde_json::json!({
"type": "response.completed",
"response": {
"id": id,
"usage": {"input_tokens":0,"input_tokens_details":null,"output_tokens":0,"output_tokens_details":null,"total_tokens":0}
}
})
}
/// Convenience: SSE event for a single assistant message output item.
fn ev_assistant_message(id: &str, text: &str) -> Value {
serde_json::json!({
"type": "response.output_item.done",
"item": {
"type": "message",
"role": "assistant",
"id": id,
"content": [{"type": "output_text", "text": text}]
}
})
}
fn sse_response(body: String) -> ResponseTemplate {
ResponseTemplate::new(200)
.insert_header("content-type", "text/event-stream")
.set_body_raw(body, "text/event-stream")
}
async fn mount_sse_once<M>(server: &MockServer, matcher: M, body: String)
where
M: wiremock::Match + Send + Sync + 'static,
{
Mock::given(method("POST"))
.and(path("/v1/responses"))
.and(matcher)
.respond_with(sse_response(body))
.expect(1)
.mount(server)
.await;
}
const FIRST_REPLY: &str = "FIRST_REPLY";
const SUMMARY_TEXT: &str = "SUMMARY_ONLY_CONTEXT";
const SUMMARIZE_TRIGGER: &str = "Start Summarization";
const THIRD_USER_MSG: &str = "next turn";
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn summarize_context_three_requests_and_instructions() {
if std::env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
println!(
"Skipping test because it cannot execute when network is disabled in a Codex sandbox."
);
return;
}
// Set up a mock server that we can inspect after the run.
let server = MockServer::start().await;
// SSE 1: assistant replies normally so it is recorded in history.
let sse1 = sse(vec![
ev_assistant_message("m1", FIRST_REPLY),
ev_completed("r1"),
]);
// SSE 2: summarizer returns a summary message.
let sse2 = sse(vec![
ev_assistant_message("m2", SUMMARY_TEXT),
ev_completed("r2"),
]);
// SSE 3: minimal completed; we only need to capture the request body.
let sse3 = sse(vec![ev_completed("r3")]);
// Mount three expectations, one per request, matched by body content.
let first_matcher = |req: &wiremock::Request| {
let body = std::str::from_utf8(&req.body).unwrap_or("");
body.contains("\"text\":\"hello world\"")
&& !body.contains(&format!("\"text\":\"{SUMMARIZE_TRIGGER}\""))
};
mount_sse_once(&server, first_matcher, sse1).await;
let second_matcher = |req: &wiremock::Request| {
let body = std::str::from_utf8(&req.body).unwrap_or("");
body.contains(&format!("\"text\":\"{SUMMARIZE_TRIGGER}\""))
};
mount_sse_once(&server, second_matcher, sse2).await;
let third_matcher = |req: &wiremock::Request| {
let body = std::str::from_utf8(&req.body).unwrap_or("");
body.contains(&format!("\"text\":\"{THIRD_USER_MSG}\""))
};
mount_sse_once(&server, third_matcher, sse3).await;
// Build config pointing to the mock server and spawn Codex.
let model_provider = ModelProviderInfo {
base_url: Some(format!("{}/v1", server.uri())),
..built_in_model_providers()["openai"].clone()
};
let home = TempDir::new().unwrap();
let mut config = load_default_config_for_test(&home);
config.model_provider = model_provider;
let ctrl_c = std::sync::Arc::new(tokio::sync::Notify::new());
let CodexSpawnOk { codex, .. } = Codex::spawn(
config,
Some(CodexAuth::from_api_key("dummy".to_string())),
ctrl_c.clone(),
)
.await
.unwrap();
// 1) Normal user input – should hit server once.
codex
.submit(Op::UserInput {
items: vec![InputItem::Text {
text: "hello world".into(),
}],
})
.await
.unwrap();
wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
// 2) Summarize – second hit with summarization instructions.
codex.submit(Op::Compact).await.unwrap();
wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
// 3) Next user input – third hit; history should include only the summary.
codex
.submit(Op::UserInput {
items: vec![InputItem::Text {
text: THIRD_USER_MSG.into(),
}],
})
.await
.unwrap();
wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
// Inspect the three captured requests.
let requests = server.received_requests().await.unwrap();
assert_eq!(requests.len(), 3, "expected exactly three requests");
let req1 = &requests[0];
let req2 = &requests[1];
let req3 = &requests[2];
let body1 = req1.body_json::<serde_json::Value>().unwrap();
let body2 = req2.body_json::<serde_json::Value>().unwrap();
let body3 = req3.body_json::<serde_json::Value>().unwrap();
// System instructions should change for the summarization turn.
let instr1 = body1.get("instructions").and_then(|v| v.as_str()).unwrap();
let instr2 = body2.get("instructions").and_then(|v| v.as_str()).unwrap();
assert_ne!(
instr1, instr2,
"summarization should override base instructions"
);
assert!(
instr2.contains("You are a summarization assistant"),
"summarization instructions not applied"
);
// The summarization request should include the injected user input marker.
let input2 = body2.get("input").and_then(|v| v.as_array()).unwrap();
// The last item is the user message created from the injected input.
let last2 = input2.last().unwrap();
assert_eq!(last2.get("type").unwrap().as_str().unwrap(), "message");
assert_eq!(last2.get("role").unwrap().as_str().unwrap(), "user");
let text2 = last2["content"][0]["text"].as_str().unwrap();
assert!(text2.contains(SUMMARIZE_TRIGGER));
// Third request must contain only the summary from step 2 as prior history plus new user msg.
let input3 = body3.get("input").and_then(|v| v.as_array()).unwrap();
println!("third request body: {body3}");
assert!(
input3.len() >= 2,
"expected summary + new user message in third request"
);
// Collect all (role, text) message tuples.
let mut messages: Vec<(String, String)> = Vec::new();
for item in input3 {
if item["type"].as_str() == Some("message") {
let role = item["role"].as_str().unwrap_or_default().to_string();
let text = item["content"][0]["text"]
.as_str()
.unwrap_or_default()
.to_string();
messages.push((role, text));
}
}
// Exactly one assistant message should remain after compaction and the new user message is present.
let assistant_count = messages.iter().filter(|(r, _)| r == "assistant").count();
assert_eq!(
assistant_count, 1,
"exactly one assistant message should remain after compaction"
);
assert!(
messages
.iter()
.any(|(r, t)| r == "user" && t == THIRD_USER_MSG),
"third request should include the new user message"
);
assert!(
!messages.iter().any(|(_, t)| t.contains("hello world")),
"third request should not include the original user input"
);
assert!(
!messages.iter().any(|(_, t)| t.contains(SUMMARIZE_TRIGGER)),
"third request should not include the summarize trigger"
);
}
+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
@@ -19,7 +19,7 @@ mod codex_tool_config;
mod codex_tool_runner;
mod exec_approval;
mod json_to_toml;
mod mcp_protocol;
pub mod mcp_protocol;
mod message_processor;
mod outgoing_message;
mod patch_approval;
+74 -18
View File
@@ -7,7 +7,10 @@ use serde::Serialize;
use strum_macros::Display;
use uuid::Uuid;
use mcp_types::CallToolResult;
use mcp_types::ContentBlock;
use mcp_types::RequestId;
use mcp_types::TextContent;
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[serde(transparent)]
@@ -118,10 +121,47 @@ pub struct ToolCallResponse {
pub request_id: RequestId,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub is_error: Option<bool>,
#[serde(default, skip_serializing_if = "Option::is_none")]
#[serde(default, skip_serializing_if = "Option::is_none", flatten)]
pub result: Option<ToolCallResponseResult>,
}
impl From<ToolCallResponse> for CallToolResult {
fn from(val: ToolCallResponse) -> Self {
let ToolCallResponse {
request_id: _request_id,
is_error,
result,
} = val;
let (content, structured_content, is_error_out) = match result {
Some(res) => match serde_json::to_value(&res) {
Ok(v) => {
let content = vec![ContentBlock::TextContent(TextContent {
r#type: "text".to_string(),
text: v.to_string(),
annotations: None,
})];
(content, Some(v), is_error)
}
Err(e) => {
let content = vec![ContentBlock::TextContent(TextContent {
r#type: "text".to_string(),
text: format!("Failed to serialize tool result: {e}"),
annotations: None,
})];
(content, None, Some(true))
}
},
None => (vec![], None, is_error),
};
CallToolResult {
content,
is_error: is_error_out,
structured_content,
}
}
}
#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
#[serde(untagged)]
pub enum ToolCallResponseResult {
@@ -141,8 +181,10 @@ pub struct ConversationCreateResult {
pub struct ConversationStreamResult {}
#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
pub struct ConversationSendMessageResult {
pub success: bool,
#[serde(tag = "status", rename_all = "camelCase")]
pub enum ConversationSendMessageResult {
Ok,
Error { message: String },
}
#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
@@ -455,10 +497,13 @@ mod tests {
},
)),
};
let observed = to_val(&env);
let req_id = env.request_id.clone();
let observed = to_val(&CallToolResult::from(env));
let expected = json!({
"requestId": 1,
"result": {
"content": [
{ "type": "text", "text": "{\"conversation_id\":\"d0f6ecbe-84a2-41c1-b23d-b20473b25eab\",\"model\":\"o3\"}" }
],
"structuredContent": {
"conversation_id": "d0f6ecbe-84a2-41c1-b23d-b20473b25eab",
"model": "o3"
}
@@ -467,6 +512,7 @@ mod tests {
observed, expected,
"response (ConversationCreate) must match"
);
assert_eq!(req_id, RequestId::Integer(1));
}
#[test]
@@ -478,15 +524,17 @@ mod tests {
ConversationStreamResult {},
)),
};
let observed = to_val(&env);
let req_id = env.request_id.clone();
let observed = to_val(&CallToolResult::from(env));
let expected = json!({
"requestId": 2,
"result": {}
"content": [ { "type": "text", "text": "{}" } ],
"structuredContent": {}
});
assert_eq!(
observed, expected,
"response (ConversationStream) must have empty object result"
);
assert_eq!(req_id, RequestId::Integer(2));
}
#[test]
@@ -495,18 +543,20 @@ mod tests {
request_id: RequestId::Integer(3),
is_error: None,
result: Some(ToolCallResponseResult::ConversationSendMessage(
ConversationSendMessageResult { success: true },
ConversationSendMessageResult::Ok,
)),
};
let observed = to_val(&env);
let req_id = env.request_id.clone();
let observed = to_val(&CallToolResult::from(env));
let expected = json!({
"requestId": 3,
"result": { "success": true }
"content": [ { "type": "text", "text": "{\"status\":\"ok\"}" } ],
"structuredContent": { "status": "ok" }
});
assert_eq!(
observed, expected,
"response (ConversationSendMessageAccepted) must match"
);
assert_eq!(req_id, RequestId::Integer(3));
}
#[test]
@@ -526,10 +576,13 @@ mod tests {
},
)),
};
let observed = to_val(&env);
let req_id = env.request_id.clone();
let observed = to_val(&CallToolResult::from(env));
let expected = json!({
"requestId": 4,
"result": {
"content": [
{ "type": "text", "text": "{\"conversations\":[{\"conversation_id\":\"67e55044-10b1-426f-9247-bb680e5fe0c8\",\"title\":\"Refactor config loader\"}],\"next_cursor\":\"next123\"}" }
],
"structuredContent": {
"conversations": [
{
"conversation_id": "67e55044-10b1-426f-9247-bb680e5fe0c8",
@@ -543,6 +596,7 @@ mod tests {
observed, expected,
"response (ConversationsList with cursor) must match"
);
assert_eq!(req_id, RequestId::Integer(4));
}
#[test]
@@ -552,15 +606,17 @@ mod tests {
is_error: Some(true),
result: None,
};
let observed = to_val(&env);
let req_id = env.request_id.clone();
let observed = to_val(&CallToolResult::from(env));
let expected = json!({
"requestId": 4,
"content": [],
"isError": true
});
assert_eq!(
observed, expected,
"error response must omit `result` and include `isError`"
);
assert_eq!(req_id, RequestId::Integer(4));
}
// ----- Notifications -----
@@ -6,6 +6,7 @@ use crate::codex_tool_config::CodexToolCallParam;
use crate::codex_tool_config::CodexToolCallReplyParam;
use crate::codex_tool_config::create_tool_for_codex_tool_call_param;
use crate::codex_tool_config::create_tool_for_codex_tool_call_reply_param;
use crate::mcp_protocol::ToolCallRequestParams;
use crate::outgoing_message::OutgoingMessageSender;
use codex_core::Codex;
@@ -300,6 +301,14 @@ impl MessageProcessor {
params: <mcp_types::CallToolRequest as mcp_types::ModelContextProtocolRequest>::Params,
) {
tracing::info!("tools/call -> params: {:?}", params);
// Serialize params into JSON and try to parse as new type
if let Ok(new_params) =
serde_json::to_value(&params).and_then(serde_json::from_value::<ToolCallRequestParams>)
{
// New tool call matched → forward
self.handle_new_tool_calls(id, new_params).await;
return;
}
let CallToolRequestParams { name, arguments } = params;
match name.as_str() {
@@ -323,6 +332,20 @@ impl MessageProcessor {
}
}
}
async fn handle_new_tool_calls(&self, request_id: RequestId, _params: ToolCallRequestParams) {
// TODO: implement the new tool calls
let result = CallToolResult {
content: vec![ContentBlock::TextContent(TextContent {
r#type: "text".to_string(),
text: "Unknown tool".to_string(),
annotations: None,
})],
is_error: Some(true),
structured_content: None,
};
self.send_response::<mcp_types::CallToolRequest>(request_id, result)
.await;
}
async fn handle_tool_call_codex(&self, id: RequestId, arguments: Option<serde_json::Value>) {
let (initial_prompt, config): (String, CodexConfig) = match arguments {
+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;
@@ -10,6 +10,7 @@ path = "lib.rs"
anyhow = "1"
assert_cmd = "2"
codex-mcp-server = { path = "../.." }
codex-core = { path = "../../../core" }
mcp-types = { path = "../../../mcp-types" }
pretty_assertions = "1.4.1"
serde_json = "1"
@@ -22,3 +23,4 @@ tokio = { version = "1", features = [
"rt-multi-thread",
] }
wiremock = "0.6"
uuid = { version = "1", features = ["serde", "v4"] }
@@ -11,8 +11,13 @@ use tokio::process::ChildStdout;
use anyhow::Context;
use assert_cmd::prelude::*;
use codex_core::protocol::InputItem;
use codex_mcp_server::CodexToolCallParam;
use codex_mcp_server::CodexToolCallReplyParam;
use codex_mcp_server::mcp_protocol::ConversationId;
use codex_mcp_server::mcp_protocol::ConversationSendMessageArgs;
use codex_mcp_server::mcp_protocol::ToolCallRequestParams;
use mcp_types::CallToolRequestParams;
use mcp_types::ClientCapabilities;
use mcp_types::Implementation;
@@ -29,6 +34,7 @@ use pretty_assertions::assert_eq;
use serde_json::json;
use std::process::Command as StdCommand;
use tokio::process::Command;
use uuid::Uuid;
pub struct McpProcess {
next_request_id: AtomicI64,
@@ -174,6 +180,26 @@ impl McpProcess {
.await
}
pub async fn send_user_message_tool_call(
&mut self,
message: &str,
session_id: &str,
) -> anyhow::Result<i64> {
let params = ToolCallRequestParams::ConversationSendMessage(ConversationSendMessageArgs {
conversation_id: ConversationId(Uuid::parse_str(session_id)?),
content: vec![InputItem::Text {
text: message.to_string(),
}],
parent_message_id: None,
conversation_overrides: None,
});
self.send_request(
mcp_types::CallToolRequest::METHOD,
Some(serde_json::to_value(params)?),
)
.await
}
async fn send_request(
&mut self,
method: &str,
+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;
+2
View File
@@ -62,6 +62,8 @@ unicode-segmentation = "1.12.0"
unicode-width = "0.1"
uuid = "1"
[dev-dependencies]
insta = "1.43.1"
pretty_assertions = "1"
+75 -9
View File
@@ -11,12 +11,16 @@ use codex_core::config::Config;
use codex_core::protocol::Event;
use codex_core::protocol::EventMsg;
use codex_core::protocol::ExecApprovalRequestEvent;
use codex_core::protocol::Op;
use color_eyre::eyre::Result;
use crossterm::SynchronizedUpdate;
use crossterm::event::KeyCode;
use crossterm::event::KeyEvent;
use crossterm::event::KeyEventKind;
use crossterm::terminal::supports_keyboard_enhancement;
use ratatui::layout::Offset;
use ratatui::prelude::Backend;
use ratatui::text::Line;
use std::path::PathBuf;
use std::sync::Arc;
use std::sync::atomic::AtomicBool;
@@ -55,9 +59,13 @@ pub(crate) struct App<'a> {
/// True when a redraw has been scheduled but not yet executed.
pending_redraw: Arc<AtomicBool>,
pending_history_lines: Vec<Line<'static>>,
/// Stored parameters needed to instantiate the ChatWidget later, e.g.,
/// after dismissing the Git-repo warning.
chat_args: Option<ChatWidgetArgs>,
enhanced_keys_supported: bool,
}
/// Aggregate parameters needed to create a `ChatWidget`, as creation may be
@@ -67,6 +75,7 @@ struct ChatWidgetArgs {
config: Config,
initial_prompt: Option<String>,
initial_images: Vec<PathBuf>,
enhanced_keys_supported: bool,
}
impl App<'_> {
@@ -80,6 +89,8 @@ impl App<'_> {
let app_event_tx = AppEventSender::new(app_event_tx);
let pending_redraw = Arc::new(AtomicBool::new(false));
let enhanced_keys_supported = supports_keyboard_enhancement().unwrap_or(false);
// Spawn a dedicated thread for reading the crossterm event loop and
// re-publishing the events as AppEvents, as appropriate.
{
@@ -132,6 +143,7 @@ impl App<'_> {
config: config.clone(),
initial_prompt,
initial_images,
enhanced_keys_supported,
}),
)
} else {
@@ -140,6 +152,7 @@ impl App<'_> {
app_event_tx.clone(),
initial_prompt,
initial_images,
enhanced_keys_supported,
);
(
AppState::Chat {
@@ -152,12 +165,14 @@ impl App<'_> {
let file_search = FileSearchManager::new(config.cwd.clone(), app_event_tx.clone());
Self {
app_event_tx,
pending_history_lines: Vec::new(),
app_event_rx,
app_state,
config,
file_search,
pending_redraw,
chat_args,
enhanced_keys_supported,
}
}
@@ -197,7 +212,7 @@ impl App<'_> {
while let Ok(event) = self.app_event_rx.recv() {
match event {
AppEvent::InsertHistory(lines) => {
crate::insert_history::insert_history_lines(terminal, lines);
self.pending_history_lines.extend(lines);
self.app_event_tx.send(AppEvent::RequestRedraw);
}
AppEvent::RequestRedraw => {
@@ -211,6 +226,7 @@ impl App<'_> {
KeyEvent {
code: KeyCode::Char('c'),
modifiers: crossterm::event::KeyModifiers::CONTROL,
kind: KeyEventKind::Press,
..
} => {
match &mut self.app_state {
@@ -225,6 +241,7 @@ impl App<'_> {
KeyEvent {
code: KeyCode::Char('d'),
modifiers: crossterm::event::KeyModifiers::CONTROL,
kind: KeyEventKind::Press,
..
} => {
match &mut self.app_state {
@@ -243,9 +260,15 @@ impl App<'_> {
}
}
}
_ => {
KeyEvent {
kind: KeyEventKind::Press | KeyEventKind::Repeat,
..
} => {
self.dispatch_key_event(key_event);
}
_ => {
// Ignore Release key events for now.
}
};
}
AppEvent::Paste(text) => {
@@ -272,10 +295,17 @@ impl App<'_> {
self.app_event_tx.clone(),
None,
Vec::new(),
self.enhanced_keys_supported,
));
self.app_state = AppState::Chat { widget: new_widget };
self.app_event_tx.send(AppEvent::RequestRedraw);
}
SlashCommand::Compact => {
if let AppState::Chat { widget } = &mut self.app_state {
widget.clear_token_usage();
self.app_event_tx.send(AppEvent::CodexOp(Op::Compact));
}
}
SlashCommand::Quit => {
break;
}
@@ -302,14 +332,41 @@ impl App<'_> {
}
#[cfg(debug_assertions)]
SlashCommand::TestApproval => {
use std::collections::HashMap;
use codex_core::protocol::ApplyPatchApprovalRequestEvent;
use codex_core::protocol::FileChange;
self.app_event_tx.send(AppEvent::CodexEvent(Event {
id: "1".to_string(),
msg: EventMsg::ExecApprovalRequest(ExecApprovalRequestEvent {
call_id: "1".to_string(),
command: vec!["git".into(), "apply".into()],
cwd: self.config.cwd.clone(),
reason: Some("test".to_string()),
}),
// msg: EventMsg::ExecApprovalRequest(ExecApprovalRequestEvent {
// call_id: "1".to_string(),
// command: vec!["git".into(), "apply".into()],
// cwd: self.config.cwd.clone(),
// reason: Some("test".to_string()),
// }),
msg: EventMsg::ApplyPatchApprovalRequest(
ApplyPatchApprovalRequestEvent {
call_id: "1".to_string(),
changes: HashMap::from([
(
PathBuf::from("/tmp/test.txt"),
FileChange::Add {
content: "test".to_string(),
},
),
(
PathBuf::from("/tmp/test2.txt"),
FileChange::Update {
unified_diff: "+test\n-test2".to_string(),
move_path: None,
},
),
]),
reason: None,
grant_root: Some(PathBuf::from("/tmp")),
},
),
}));
}
},
@@ -361,8 +418,9 @@ impl App<'_> {
AppState::Chat { widget } => widget.desired_height(size.width),
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
@@ -374,6 +432,13 @@ impl App<'_> {
terminal.clear()?;
terminal.set_viewport_area(area);
}
if !self.pending_history_lines.is_empty() {
crate::insert_history::insert_history_lines(
terminal,
self.pending_history_lines.clone(),
);
self.pending_history_lines.clear();
}
match &mut self.app_state {
AppState::Chat { widget } => {
terminal.draw(|frame| frame.render_widget_ref(&**widget, frame.area()))?;
@@ -405,6 +470,7 @@ impl App<'_> {
self.app_event_tx.clone(),
args.initial_prompt,
args.initial_images,
args.enhanced_keys_supported,
));
self.app_state = AppState::Chat { widget };
self.app_event_tx.send(AppEvent::RequestRedraw);
@@ -99,6 +99,7 @@ mod tests {
let mut pane = BottomPane::new(super::super::BottomPaneParams {
app_event_tx: AppEventSender::new(tx_raw2),
has_input_focus: true,
enhanced_keys_supported: false,
});
assert_eq!(CancellationEvent::Handled, view.on_ctrl_c(&mut pane));
assert!(view.queue.is_empty());
+22 -9
View File
@@ -41,6 +41,7 @@ pub(crate) struct ChatComposer<'a> {
app_event_tx: AppEventSender,
history: ChatComposerHistory,
ctrl_c_quit_hint: bool,
use_shift_enter_hint: bool,
dismissed_file_popup_token: Option<String>,
current_file_query: Option<String>,
pending_pastes: Vec<(String, String)>,
@@ -54,17 +55,24 @@ enum ActivePopup {
}
impl ChatComposer<'_> {
pub fn new(has_input_focus: bool, app_event_tx: AppEventSender) -> Self {
pub fn new(
has_input_focus: bool,
app_event_tx: AppEventSender,
enhanced_keys_supported: bool,
) -> Self {
let mut textarea = TextArea::default();
textarea.set_placeholder_text(BASE_PLACEHOLDER_TEXT);
textarea.set_cursor_line_style(ratatui::style::Style::default());
let use_shift_enter_hint = enhanced_keys_supported;
let mut this = Self {
textarea,
active_popup: ActivePopup::None,
app_event_tx,
history: ChatComposerHistory::new(),
ctrl_c_quit_hint: false,
use_shift_enter_hint,
dismissed_file_popup_token: None,
current_file_query: None,
pending_pastes: Vec::new(),
@@ -712,11 +720,16 @@ impl WidgetRef for &ChatComposer<'_> {
Span::from(" to quit"),
]
} else {
let newline_hint_key = if self.use_shift_enter_hint {
"Shift+⏎"
} else {
"Ctrl+J"
};
vec![
Span::from(" "),
"⏎".set_style(key_hint_style),
Span::from(" send "),
"Shift+⏎".set_style(key_hint_style),
newline_hint_key.set_style(key_hint_style),
Span::from(" newline "),
"Ctrl+C".set_style(key_hint_style),
Span::from(" quit"),
@@ -890,7 +903,7 @@ mod tests {
let (tx, _rx) = std::sync::mpsc::channel();
let sender = AppEventSender::new(tx);
let mut composer = ChatComposer::new(true, sender);
let mut composer = ChatComposer::new(true, sender, false);
let needs_redraw = composer.handle_paste("hello".to_string());
assert!(needs_redraw);
@@ -913,7 +926,7 @@ mod tests {
let (tx, _rx) = std::sync::mpsc::channel();
let sender = AppEventSender::new(tx);
let mut composer = ChatComposer::new(true, sender);
let mut composer = ChatComposer::new(true, sender, false);
let large = "x".repeat(LARGE_PASTE_CHAR_THRESHOLD + 10);
let needs_redraw = composer.handle_paste(large.clone());
@@ -942,7 +955,7 @@ mod tests {
let large = "y".repeat(LARGE_PASTE_CHAR_THRESHOLD + 1);
let (tx, _rx) = std::sync::mpsc::channel();
let sender = AppEventSender::new(tx);
let mut composer = ChatComposer::new(true, sender);
let mut composer = ChatComposer::new(true, sender, false);
composer.handle_paste(large);
assert_eq!(composer.pending_pastes.len(), 1);
@@ -978,7 +991,7 @@ mod tests {
for (name, input) in test_cases {
// Create a fresh composer for each test case
let mut composer = ChatComposer::new(true, sender.clone());
let mut composer = ChatComposer::new(true, sender.clone(), false);
if let Some(text) = input {
composer.handle_paste(text);
@@ -1015,7 +1028,7 @@ mod tests {
let (tx, _rx) = std::sync::mpsc::channel();
let sender = AppEventSender::new(tx);
let mut composer = ChatComposer::new(true, sender);
let mut composer = ChatComposer::new(true, sender, false);
// Define test cases: (paste content, is_large)
let test_cases = [
@@ -1088,7 +1101,7 @@ mod tests {
let (tx, _rx) = std::sync::mpsc::channel();
let sender = AppEventSender::new(tx);
let mut composer = ChatComposer::new(true, sender);
let mut composer = ChatComposer::new(true, sender, false);
// Define test cases: (content, is_large)
let test_cases = [
@@ -1161,7 +1174,7 @@ mod tests {
let (tx, _rx) = std::sync::mpsc::channel();
let sender = AppEventSender::new(tx);
let mut composer = ChatComposer::new(true, sender);
let mut composer = ChatComposer::new(true, sender, false);
// Define test cases: (cursor_position_from_end, expected_pending_count)
let test_cases = [
+8 -1
View File
@@ -50,12 +50,18 @@ pub(crate) struct BottomPane<'a> {
pub(crate) struct BottomPaneParams {
pub(crate) app_event_tx: AppEventSender,
pub(crate) has_input_focus: bool,
pub(crate) enhanced_keys_supported: bool,
}
impl BottomPane<'_> {
pub fn new(params: BottomPaneParams) -> Self {
let enhanced_keys_supported = params.enhanced_keys_supported;
Self {
composer: ChatComposer::new(params.has_input_focus, params.app_event_tx.clone()),
composer: ChatComposer::new(
params.has_input_focus,
params.app_event_tx.clone(),
enhanced_keys_supported,
),
active_view: None,
app_event_tx: params.app_event_tx,
has_input_focus: params.has_input_focus,
@@ -298,6 +304,7 @@ mod tests {
let mut pane = BottomPane::new(BottomPaneParams {
app_event_tx: tx,
has_input_focus: true,
enhanced_keys_supported: false,
});
pane.push_approval_request(exec_request());
assert_eq!(CancellationEvent::Handled, pane.on_ctrl_c());
@@ -11,4 +11,4 @@ expression: terminal.backend()
"▌ "
"▌ "
"▌ "
" ⏎ send Shift+⏎ newline Ctrl+C quit "
" ⏎ send Ctrl+J newline Ctrl+C quit "
@@ -11,4 +11,4 @@ expression: terminal.backend()
"▌ "
"▌ "
"▌ "
" ⏎ send Shift+⏎ newline Ctrl+C quit "
" ⏎ send Ctrl+J newline Ctrl+C quit "
@@ -11,4 +11,4 @@ expression: terminal.backend()
"▌ "
"▌ "
"▌ "
" ⏎ send Shift+⏎ newline Ctrl+C quit "
" ⏎ send Ctrl+J newline Ctrl+C quit "
@@ -11,4 +11,4 @@ expression: terminal.backend()
"▌ "
"▌ "
"▌ "
" ⏎ send Shift+⏎ newline Ctrl+C quit "
" ⏎ send Ctrl+J newline Ctrl+C quit "
@@ -11,4 +11,4 @@ expression: terminal.backend()
"▌ "
"▌ "
"▌ "
" ⏎ send Shift+⏎ newline Ctrl+C quit "
" ⏎ send Ctrl+J newline Ctrl+C quit "
+16 -1
View File
@@ -26,6 +26,7 @@ use codex_core::protocol::PatchApplyBeginEvent;
use codex_core::protocol::TaskCompleteEvent;
use codex_core::protocol::TokenUsage;
use crossterm::event::KeyEvent;
use crossterm::event::KeyEventKind;
use ratatui::buffer::Buffer;
use ratatui::layout::Rect;
use ratatui::widgets::Widget;
@@ -95,6 +96,7 @@ impl ChatWidget<'_> {
app_event_tx: AppEventSender,
initial_prompt: Option<String>,
initial_images: Vec<PathBuf>,
enhanced_keys_supported: bool,
) -> Self {
let (codex_op_tx, mut codex_op_rx) = unbounded_channel::<Op>();
@@ -140,6 +142,7 @@ impl ChatWidget<'_> {
bottom_pane: BottomPane::new(BottomPaneParams {
app_event_tx,
has_input_focus: true,
enhanced_keys_supported,
}),
config,
initial_user_message: create_initial_user_message(
@@ -158,7 +161,9 @@ impl ChatWidget<'_> {
}
pub(crate) fn handle_key_event(&mut self, key_event: KeyEvent) {
self.bottom_pane.clear_ctrl_c_quit_hint();
if key_event.kind == KeyEventKind::Press {
self.bottom_pane.clear_ctrl_c_quit_hint();
}
match self.bottom_pane.handle_key_event(key_event) {
InputResult::Submitted(text) => {
@@ -298,6 +303,10 @@ 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,
@@ -498,6 +507,12 @@ impl ChatWidget<'_> {
pub(crate) fn token_usage(&self) -> &TokenUsage {
&self.token_usage
}
pub(crate) fn clear_token_usage(&mut self) {
self.token_usage = TokenUsage::default();
self.bottom_pane
.set_token_usage(self.token_usage.clone(), self.config.model_context_window);
}
}
impl WidgetRef for &ChatWidget<'_> {
+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
+2 -2
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() {
@@ -226,7 +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) => {
+2
View File
@@ -13,6 +13,7 @@ pub enum SlashCommand {
// DO NOT ALPHA-SORT! Enum order is presentation order in the popup, so
// more frequently used commands should be listed first.
New,
Compact,
Diff,
Quit,
#[cfg(debug_assertions)]
@@ -24,6 +25,7 @@ impl SlashCommand {
pub fn description(self) -> &'static str {
match self {
SlashCommand::New => "Start a new chat.",
SlashCommand::Compact => "Compact the chat history.",
SlashCommand::Quit => "Exit the application.",
SlashCommand::Diff => {
"Show git diff of the working directory (including untracked files)"
+120 -186
View File
@@ -7,23 +7,24 @@
//! driven workflow – a fully‑fledged visual match is not required.
use std::path::PathBuf;
use std::sync::LazyLock;
use codex_core::protocol::Op;
use codex_core::protocol::ReviewDecision;
use crossterm::event::KeyCode;
use crossterm::event::KeyEvent;
use crossterm::event::KeyEventKind;
use ratatui::buffer::Buffer;
use ratatui::layout::Rect;
use ratatui::prelude::*;
use ratatui::text::Line;
use ratatui::text::Span;
use ratatui::widgets::List;
use ratatui::widgets::Block;
use ratatui::widgets::BorderType;
use ratatui::widgets::Borders;
use ratatui::widgets::Paragraph;
use ratatui::widgets::Widget;
use ratatui::widgets::WidgetRef;
use ratatui::widgets::Wrap;
use tui_input::Input;
use tui_input::backend::crossterm::EventHandler;
use crate::app_event::AppEvent;
use crate::app_event_sender::AppEventSender;
@@ -47,68 +48,62 @@ pub(crate) enum ApprovalRequest {
/// Options displayed in the *select* mode.
struct SelectOption {
label: &'static str,
decision: Option<ReviewDecision>,
/// `true` when this option switches the widget to *input* mode.
enters_input_mode: bool,
label: Line<'static>,
description: &'static str,
key: KeyCode,
decision: ReviewDecision,
}
// keep in same order as in the TS implementation
const SELECT_OPTIONS: &[SelectOption] = &[
SelectOption {
label: "Yes (y)",
decision: Some(ReviewDecision::Approved),
static COMMAND_SELECT_OPTIONS: LazyLock<Vec<SelectOption>> = LazyLock::new(|| {
vec![
SelectOption {
label: Line::from(vec!["Y".underlined(), "es".into()]),
description: "Approve and run the command",
key: KeyCode::Char('y'),
decision: ReviewDecision::Approved,
},
SelectOption {
label: Line::from(vec!["A".underlined(), "lways".into()]),
description: "Approve the command for the remainder of this session",
key: KeyCode::Char('a'),
decision: ReviewDecision::ApprovedForSession,
},
SelectOption {
label: Line::from(vec!["N".underlined(), "o".into()]),
description: "Do not run the command",
key: KeyCode::Char('n'),
decision: ReviewDecision::Denied,
},
]
});
enters_input_mode: false,
},
SelectOption {
label: "Yes, always approve this exact command for this session (a)",
decision: Some(ReviewDecision::ApprovedForSession),
enters_input_mode: false,
},
SelectOption {
label: "Edit or give feedback (e)",
decision: None,
enters_input_mode: true,
},
SelectOption {
label: "No, and keep going (n)",
decision: Some(ReviewDecision::Denied),
enters_input_mode: false,
},
SelectOption {
label: "No, and stop for now (esc)",
decision: Some(ReviewDecision::Abort),
enters_input_mode: false,
},
];
/// Internal mode the widget is in – mirrors the TypeScript component.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
enum Mode {
Select,
Input,
}
static PATCH_SELECT_OPTIONS: LazyLock<Vec<SelectOption>> = LazyLock::new(|| {
vec![
SelectOption {
label: Line::from(vec!["Y".underlined(), "es".into()]),
description: "Approve and apply the changes",
key: KeyCode::Char('y'),
decision: ReviewDecision::Approved,
},
SelectOption {
label: Line::from(vec!["N".underlined(), "o".into()]),
description: "Do not apply the changes",
key: KeyCode::Char('n'),
decision: ReviewDecision::Denied,
},
]
});
/// A modal prompting the user to approve or deny the pending request.
pub(crate) struct UserApprovalWidget<'a> {
approval_request: ApprovalRequest,
app_event_tx: AppEventSender,
confirmation_prompt: Paragraph<'a>,
select_options: &'a Vec<SelectOption>,
/// Currently selected index in *select* mode.
selected_option: usize,
/// State for the optional input widget.
input: Input,
/// Current mode.
mode: Mode,
/// Set to `true` once a decision has been sent – the parent view can then
/// remove this widget from its queue.
done: bool,
@@ -116,7 +111,6 @@ pub(crate) struct UserApprovalWidget<'a> {
impl UserApprovalWidget<'_> {
pub(crate) fn new(approval_request: ApprovalRequest, app_event_tx: AppEventSender) -> Self {
let input = Input::default();
let confirmation_prompt = match &approval_request {
ApprovalRequest::Exec {
command,
@@ -132,25 +126,20 @@ impl UserApprovalWidget<'_> {
None => cwd.display().to_string(),
};
let mut contents: Vec<Line> = vec![
Line::from(vec![
Span::from(cwd_str).dim(),
Span::from("$"),
Span::from(format!(" {cmd}")),
]),
Line::from(vec!["codex".bold().magenta(), " wants to run:".into()]),
Line::from(vec![cwd_str.dim(), "$".into(), format!(" {cmd}").into()]),
Line::from(""),
];
if let Some(reason) = reason {
contents.push(Line::from(reason.clone().italic()));
contents.push(Line::from(""));
}
contents.extend(vec![Line::from("Allow command?"), Line::from("")]);
Paragraph::new(contents).wrap(Wrap { trim: false })
}
ApprovalRequest::ApplyPatch {
reason, grant_root, ..
} => {
let mut contents: Vec<Line> =
vec![Line::from("Apply patch".bold()), Line::from("")];
let mut contents: Vec<Line> = vec![];
if let Some(r) = reason {
contents.push(Line::from(r.clone().italic()));
@@ -165,20 +154,19 @@ impl UserApprovalWidget<'_> {
contents.push(Line::from(""));
}
contents.push(Line::from("Allow changes?"));
contents.push(Line::from(""));
Paragraph::new(contents)
Paragraph::new(contents).wrap(Wrap { trim: false })
}
};
Self {
select_options: match &approval_request {
ApprovalRequest::Exec { .. } => &COMMAND_SELECT_OPTIONS,
ApprovalRequest::ApplyPatch { .. } => &PATCH_SELECT_OPTIONS,
},
approval_request,
app_event_tx,
confirmation_prompt,
selected_option: 0,
input,
mode: Mode::Select,
done: false,
}
}
@@ -194,9 +182,8 @@ impl UserApprovalWidget<'_> {
/// captures input while visible, we don’t need to report whether the event
/// was consumed—callers can assume it always is.
pub(crate) fn handle_key_event(&mut self, key: KeyEvent) {
match self.mode {
Mode::Select => self.handle_select_key(key),
Mode::Input => self.handle_input_key(key),
if key.kind == KeyEventKind::Press {
self.handle_select_key(key);
}
}
@@ -208,58 +195,24 @@ impl UserApprovalWidget<'_> {
fn handle_select_key(&mut self, key_event: KeyEvent) {
match key_event.code {
KeyCode::Up => {
if self.selected_option == 0 {
self.selected_option = SELECT_OPTIONS.len() - 1;
} else {
self.selected_option -= 1;
}
KeyCode::Left => {
self.selected_option = (self.selected_option + self.select_options.len() - 1)
% self.select_options.len();
}
KeyCode::Down => {
self.selected_option = (self.selected_option + 1) % SELECT_OPTIONS.len();
}
KeyCode::Char('y') => {
self.send_decision(ReviewDecision::Approved);
}
KeyCode::Char('a') => {
self.send_decision(ReviewDecision::ApprovedForSession);
}
KeyCode::Char('n') => {
self.send_decision(ReviewDecision::Denied);
}
KeyCode::Char('e') => {
self.mode = Mode::Input;
KeyCode::Right => {
self.selected_option = (self.selected_option + 1) % self.select_options.len();
}
KeyCode::Enter => {
let opt = &SELECT_OPTIONS[self.selected_option];
if opt.enters_input_mode {
self.mode = Mode::Input;
} else if let Some(decision) = opt.decision {
self.send_decision(decision);
}
let opt = &self.select_options[self.selected_option];
self.send_decision(opt.decision);
}
KeyCode::Esc => {
self.send_decision(ReviewDecision::Abort);
}
_ => {}
}
}
fn handle_input_key(&mut self, key_event: KeyEvent) {
// Handle special keys first.
match key_event.code {
KeyCode::Enter => {
let feedback = self.input.value().to_string();
self.send_decision_with_feedback(ReviewDecision::Denied, feedback);
}
KeyCode::Esc => {
// Cancel input – treat as deny without feedback.
self.send_decision(ReviewDecision::Denied);
}
_ => {
// Feed into input widget for normal editing.
let ct_event = crossterm::event::Event::Key(key_event);
self.input.handle_event(&ct_event);
other => {
if let Some(opt) = self.select_options.iter().find(|opt| opt.key == other) {
self.send_decision(opt.decision);
}
}
}
}
@@ -312,87 +265,68 @@ impl UserApprovalWidget<'_> {
}
pub(crate) fn desired_height(&self, width: u16) -> u16 {
self.get_confirmation_prompt_height(width - 2) + SELECT_OPTIONS.len() as u16 + 2
self.get_confirmation_prompt_height(width) + self.select_options.len() as u16
}
}
const PLAIN: Style = Style::new();
const BLUE_FG: Style = Style::new().fg(Color::LightCyan);
impl WidgetRef for &UserApprovalWidget<'_> {
fn render_ref(&self, area: Rect, buf: &mut Buffer) {
// Take the area, wrap it in a block with a border, and divide up the
// remaining area into two chunks: one for the confirmation prompt and
// one for the response.
let inner = area.inner(Margin::new(0, 2));
// Determine how many rows we can allocate for the static confirmation
// prompt while *always* keeping enough space for the interactive
// response area (select list or input field). When the full prompt
// would exceed the available height we truncate it so the response
// options never get pushed out of view. This keeps the approval modal
// usable even when the overall bottom viewport is small.
// Full height of the prompt (may be larger than the available area).
let full_prompt_height = self.get_confirmation_prompt_height(inner.width);
// Minimum rows that must remain for the interactive section.
let min_response_rows = match self.mode {
Mode::Select => SELECT_OPTIONS.len() as u16,
// In input mode we need exactly two rows: one for the guidance
// prompt and one for the single-line input field.
Mode::Input => 2,
};
// Clamp prompt height so confirmation + response never exceed the
// available space. `saturating_sub` avoids underflow when the area is
// too small even for the minimal layout – in this unlikely case we
// fall back to zero-height prompt so at least the options are
// visible.
let prompt_height = full_prompt_height.min(inner.height.saturating_sub(min_response_rows));
let chunks = Layout::default()
let prompt_height = self.get_confirmation_prompt_height(area.width);
let [prompt_chunk, response_chunk] = Layout::default()
.direction(Direction::Vertical)
.constraints([Constraint::Length(prompt_height), Constraint::Min(0)])
.split(inner);
let prompt_chunk = chunks[0];
let response_chunk = chunks[1];
.areas(area);
// Build the inner lines based on the mode. Collect them into a List of
// non-wrapping lines rather than a Paragraph for predictable layout.
let lines = match self.mode {
Mode::Select => SELECT_OPTIONS
.iter()
.enumerate()
.map(|(idx, opt)| {
let (prefix, style) = if idx == self.selected_option {
("▶", BLUE_FG)
} else {
(" ", PLAIN)
};
Line::styled(format!(" {prefix} {}", opt.label), style)
})
.collect(),
Mode::Input => {
vec![
Line::from("Give the model feedback on this command:"),
Line::from(self.input.value()),
]
}
let lines: Vec<Line> = self
.select_options
.iter()
.enumerate()
.map(|(idx, opt)| {
let style = if idx == self.selected_option {
Style::new().bg(Color::Cyan).fg(Color::Black)
} else {
Style::new().bg(Color::DarkGray)
};
opt.label.clone().alignment(Alignment::Center).style(style)
})
.collect();
let [title_area, button_area, description_area] = Layout::vertical([
Constraint::Length(1),
Constraint::Length(1),
Constraint::Min(0),
])
.areas(response_chunk.inner(Margin::new(1, 0)));
let title = match &self.approval_request {
ApprovalRequest::Exec { .. } => "Allow command?",
ApprovalRequest::ApplyPatch { .. } => "Apply changes?",
};
let border = ("◢◤")
.repeat((area.width / 2).into())
.fg(Color::LightYellow);
border.render_ref(area, buf);
Paragraph::new(" Execution Request ".bold().black().on_light_yellow())
.alignment(Alignment::Center)
.render_ref(area, buf);
Line::from(title).render(title_area, buf);
self.confirmation_prompt.clone().render(prompt_chunk, buf);
List::new(lines).render_ref(response_chunk, buf);
let areas = Layout::horizontal(
lines
.iter()
.map(|l| Constraint::Length(l.width() as u16 + 2)),
)
.spacing(1)
.split(button_area);
for (idx, area) in areas.iter().enumerate() {
let line = &lines[idx];
line.render(*area, buf);
}
border.render_ref(Rect::new(0, area.y + area.height - 1, area.width, 1), buf);
Line::from(self.select_options[self.selected_option].description)
.style(Style::new().italic().fg(Color::DarkGray))
.render(description_area.inner(Margin::new(1, 0)), buf);
Block::bordered()
.border_type(BorderType::QuadrantOutside)
.border_style(Style::default().fg(Color::Cyan))
.borders(Borders::LEFT)
.render_ref(
Rect::new(0, response_chunk.y, 1, response_chunk.height),
buf,
);
}
}