Compare commits

...

5 Commits

Author SHA1 Message Date
Ahmed Ibrahim
472e0f951e review-sandbox 2025-10-29 18:27:35 -07:00
Ahmed Ibrahim
f1527920b3 Merge branch 'main' into review-sandbox 2025-10-29 18:25:06 -07:00
Ahmed Ibrahim
576ec081c4 update sandbox 2025-10-29 18:24:29 -07:00
zhao-oai
b34efde2f3 asdf (#5940)
.
2025-10-30 01:10:41 +00:00
Ahmed Ibrahim
7aa46ab5fc ignore agent message deltas for the review mode (#5937)
The deltas produce the whole json output. ignore them.
2025-10-30 00:47:55 +00:00
10 changed files with 154 additions and 17 deletions

View File

@@ -253,7 +253,7 @@ impl std::fmt::Display for UsageLimitReachedError {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
let message = match self.plan_type.as_ref() {
Some(PlanType::Known(KnownPlan::Plus)) => format!(
"You've hit your usage limit. Upgrade to Pro (https://openai.com/chatgpt/pricing){}",
"You've hit your usage limit. Upgrade to Pro (https://openai.com/chatgpt/pricing), visit chatgpt.com/codex/settings/usage to purchase more credits{}",
retry_suffix_after_or(self.resets_at.as_ref())
),
Some(PlanType::Known(KnownPlan::Team)) | Some(PlanType::Known(KnownPlan::Business)) => {
@@ -266,8 +266,11 @@ impl std::fmt::Display for UsageLimitReachedError {
"You've hit your usage limit. Upgrade to Plus to continue using Codex (https://openai.com/chatgpt/pricing)."
.to_string()
}
Some(PlanType::Known(KnownPlan::Pro))
| Some(PlanType::Known(KnownPlan::Enterprise))
Some(PlanType::Known(KnownPlan::Pro)) => format!(
"You've hit your usage limit. Visit chatgpt.com/codex/settings/usage to purchase more credits{}",
retry_suffix_after_or(self.resets_at.as_ref())
),
Some(PlanType::Known(KnownPlan::Enterprise))
| Some(PlanType::Known(KnownPlan::Edu)) => format!(
"You've hit your usage limit.{}",
retry_suffix(self.resets_at.as_ref())
@@ -467,7 +470,7 @@ mod tests {
};
assert_eq!(
err.to_string(),
"You've hit your usage limit. Upgrade to Pro (https://openai.com/chatgpt/pricing) or try again later."
"You've hit your usage limit. Upgrade to Pro (https://openai.com/chatgpt/pricing), visit chatgpt.com/codex/settings/usage to purchase more credits or try again later."
);
}
@@ -597,7 +600,7 @@ mod tests {
#[test]
fn usage_limit_reached_error_formats_default_for_other_plans() {
let err = UsageLimitReachedError {
plan_type: Some(PlanType::Known(KnownPlan::Pro)),
plan_type: Some(PlanType::Known(KnownPlan::Enterprise)),
resets_at: None,
rate_limits: Some(rate_limit_snapshot()),
};
@@ -607,6 +610,23 @@ mod tests {
);
}
#[test]
fn usage_limit_reached_error_formats_pro_plan_with_reset() {
let base = Utc.with_ymd_and_hms(2024, 1, 1, 0, 0, 0).unwrap();
let resets_at = base + ChronoDuration::hours(1);
with_now_override(base, move || {
let err = UsageLimitReachedError {
plan_type: Some(PlanType::Known(KnownPlan::Pro)),
resets_at: Some(resets_at),
rate_limits: Some(rate_limit_snapshot()),
};
assert_eq!(
err.to_string(),
"You've hit your usage limit. Visit chatgpt.com/codex/settings/usage to purchase more credits or try again in 1 hour."
);
});
}
#[test]
fn usage_limit_reached_includes_minutes_when_available() {
let base = Utc.with_ymd_and_hms(2024, 1, 1, 0, 0, 0).unwrap();
@@ -636,7 +656,7 @@ mod tests {
};
assert_eq!(
err.to_string(),
"You've hit your usage limit. Upgrade to Pro (https://openai.com/chatgpt/pricing) or try again in 3 hours 32 minutes."
"You've hit your usage limit. Upgrade to Pro (https://openai.com/chatgpt/pricing), visit chatgpt.com/codex/settings/usage to purchase more credits or try again in 3 hours 32 minutes."
);
});
}

View File

@@ -4,11 +4,15 @@ use async_trait::async_trait;
use codex_protocol::items::TurnItem;
use codex_protocol::models::ContentItem;
use codex_protocol::models::ResponseItem;
use codex_protocol::protocol::AgentMessageContentDeltaEvent;
use codex_protocol::protocol::AgentMessageDeltaEvent;
use codex_protocol::protocol::AskForApproval;
use codex_protocol::protocol::Event;
use codex_protocol::protocol::EventMsg;
use codex_protocol::protocol::ExitedReviewModeEvent;
use codex_protocol::protocol::ItemCompletedEvent;
use codex_protocol::protocol::ReviewOutputEvent;
use codex_protocol::protocol::SandboxPolicy;
use tokio_util::sync::CancellationToken;
use crate::codex::Session;
@@ -81,6 +85,8 @@ async fn start_review_conversation(
.disable(crate::features::Feature::StreamableShell);
// Set explicit review rubric for the sub-agent
sub_agent_config.base_instructions = Some(crate::REVIEW_PROMPT.to_string());
sub_agent_config.sandbox_policy = SandboxPolicy::ReadOnly;
sub_agent_config.approval_policy = AskForApproval::Never;
(run_codex_conversation_one_shot(
sub_agent_config,
session.auth_manager(),
@@ -111,13 +117,15 @@ async fn process_review_events(
}
prev_agent_message = Some(event);
}
// Suppress ItemCompleted for assistant messages: forwarding it would
// trigger legacy AgentMessage via as_legacy_events(), which this
// Suppress ItemCompleted only for assistant messages: forwarding it
// would trigger legacy AgentMessage via as_legacy_events(), which this
// review flow intentionally hides in favor of structured output.
EventMsg::ItemCompleted(ItemCompletedEvent {
item: TurnItem::AgentMessage(_),
..
}) => {}
})
| EventMsg::AgentMessageDelta(AgentMessageDeltaEvent { .. })
| EventMsg::AgentMessageContentDelta(AgentMessageContentDeltaEvent { .. }) => {}
EventMsg::TaskComplete(task_complete) => {
// Parse review output from the last agent message (if present).
let out = task_complete

View File

@@ -204,6 +204,85 @@ async fn review_op_with_plain_text_emits_review_fallback() {
server.verify().await;
}
/// Ensure review flow suppresses assistant-specific streaming/completion events:
/// - AgentMessageContentDelta
/// - AgentMessageDelta (legacy)
/// - ItemCompleted for TurnItem::AgentMessage
// Windows CI only: bump to 4 workers to prevent SSE/event starvation and test timeouts.
#[cfg_attr(windows, tokio::test(flavor = "multi_thread", worker_threads = 4))]
#[cfg_attr(not(windows), tokio::test(flavor = "multi_thread", worker_threads = 2))]
async fn review_filters_agent_message_related_events() {
skip_if_no_network!();
// Stream simulating a typing assistant message with deltas and finalization.
let sse_raw = r#"[
{"type":"response.output_item.added", "item":{
"type":"message", "role":"assistant", "id":"msg-1",
"content":[{"type":"output_text","text":""}]
}},
{"type":"response.output_text.delta", "delta":"Hi"},
{"type":"response.output_text.delta", "delta":" there"},
{"type":"response.output_item.done", "item":{
"type":"message", "role":"assistant", "id":"msg-1",
"content":[{"type":"output_text","text":"Hi there"}]
}},
{"type":"response.completed", "response": {"id": "__ID__"}}
]"#;
let server = start_responses_server_with_sse(sse_raw, 1).await;
let codex_home = TempDir::new().unwrap();
let codex = new_conversation_for_server(&server, &codex_home, |_| {}).await;
codex
.submit(Op::Review {
review_request: ReviewRequest {
prompt: "Filter streaming events".to_string(),
user_facing_hint: "Filter streaming events".to_string(),
},
})
.await
.unwrap();
let mut saw_entered = false;
let mut saw_exited = false;
// Drain until TaskComplete; assert filtered events never surface.
wait_for_event_with_timeout(
&codex,
|event| match event {
EventMsg::TaskComplete(_) => true,
EventMsg::EnteredReviewMode(_) => {
saw_entered = true;
false
}
EventMsg::ExitedReviewMode(_) => {
saw_exited = true;
false
}
// The following must be filtered by review flow
EventMsg::AgentMessageContentDelta(_) => {
panic!("unexpected AgentMessageContentDelta surfaced during review")
}
EventMsg::AgentMessageDelta(_) => {
panic!("unexpected AgentMessageDelta surfaced during review")
}
EventMsg::ItemCompleted(ev) => match &ev.item {
codex_protocol::items::TurnItem::AgentMessage(_) => {
panic!(
"unexpected ItemCompleted for TurnItem::AgentMessage surfaced during review"
)
}
_ => false,
},
_ => false,
},
tokio::time::Duration::from_secs(5),
)
.await;
assert!(saw_entered && saw_exited, "missing review lifecycle events");
server.verify().await;
}
/// When the model returns structured JSON in a review, ensure no AgentMessage
/// is emitted; the UI consumes the structured result via ExitedReviewMode.
// Windows CI only: bump to 4 workers to prevent SSE/event starvation and test timeouts.

View File

@@ -31,6 +31,8 @@ use super::rate_limits::StatusRateLimitRow;
use super::rate_limits::compose_rate_limit_data;
use super::rate_limits::format_status_limit_summary;
use super::rate_limits::render_status_limit_progress_bar;
use crate::wrapping::RtOptions;
use crate::wrapping::word_wrap_lines;
#[derive(Debug, Clone)]
struct StatusContextWindowData {
@@ -195,13 +197,7 @@ impl StatusHistoryCell {
lines
}
StatusRateLimitData::Missing => {
vec![formatter.line(
"Limits",
vec![
Span::from("visit ").dim(),
"chatgpt.com/codex/settings/usage".cyan().underlined(),
],
)]
vec![formatter.line("Limits", vec![Span::from("data not available yet").dim()])]
}
}
}
@@ -315,6 +311,21 @@ impl HistoryCell for StatusHistoryCell {
let formatter = FieldFormatter::from_labels(labels.iter().map(String::as_str));
let value_width = formatter.value_width(available_inner_width);
let note_first_line = Line::from(vec![
Span::from("Visit ").cyan(),
"chatgpt.com/codex/settings/usage".cyan().underlined(),
Span::from(" for up-to-date").cyan(),
]);
let note_second_line = Line::from(vec![
Span::from("information on rate limits and credits").cyan(),
]);
let note_lines = word_wrap_lines(
[note_first_line, note_second_line],
RtOptions::new(available_inner_width),
);
lines.extend(note_lines);
lines.push(Line::from(Vec::<Span<'static>>::new()));
let mut model_spans = vec![Span::from(self.model_name.clone())];
if !self.model_details.is_empty() {
model_spans.push(Span::from(" (").dim());

View File

@@ -7,6 +7,9 @@ expression: sanitized
╭────────────────────────────────────────────────────────────────────────────╮
│ >_ OpenAI Codex (v0.0.0) │
│ │
│ Visit chatgpt.com/codex/settings/usage for up-to-date │
│ information on rate limits and credits │
│ │
│ Model: gpt-5-codex (reasoning none, summaries auto) │
│ Directory: [[workspace]] │
│ Approval: on-request │

View File

@@ -7,6 +7,9 @@ expression: sanitized
╭─────────────────────────────────────────────────────────────────────╮
│ >_ OpenAI Codex (v0.0.0) │
│ │
│ Visit chatgpt.com/codex/settings/usage for up-to-date │
│ information on rate limits and credits │
│ │
│ Model: gpt-5-codex (reasoning high, summaries detailed) │
│ Directory: [[workspace]] │
│ Approval: on-request │

View File

@@ -7,6 +7,9 @@ expression: sanitized
╭─────────────────────────────────────────────────────────────────╮
│ >_ OpenAI Codex (v0.0.0) │
│ │
│ Visit chatgpt.com/codex/settings/usage for up-to-date │
│ information on rate limits and credits │
│ │
│ Model: gpt-5-codex (reasoning none, summaries auto) │
│ Directory: [[workspace]] │
│ Approval: on-request │

View File

@@ -7,6 +7,9 @@ expression: sanitized
╭─────────────────────────────────────────────────────────────────╮
│ >_ OpenAI Codex (v0.0.0) │
│ │
│ Visit chatgpt.com/codex/settings/usage for up-to-date │
│ information on rate limits and credits │
│ │
│ Model: gpt-5-codex (reasoning none, summaries auto) │
│ Directory: [[workspace]] │
│ Approval: on-request │
@@ -15,5 +18,5 @@ expression: sanitized
│ │
│ Token usage: 750 total (500 input + 250 output) │
│ Context window: 100% left (750 used / 272K) │
│ Limits: visit chatgpt.com/codex/settings/usage
│ Limits: data not available yet
╰─────────────────────────────────────────────────────────────────╯

View File

@@ -7,6 +7,9 @@ expression: sanitized
╭─────────────────────────────────────────────────────────────────────╮
│ >_ OpenAI Codex (v0.0.0) │
│ │
│ Visit chatgpt.com/codex/settings/usage for up-to-date │
│ information on rate limits and credits │
│ │
│ Model: gpt-5-codex (reasoning none, summaries auto) │
│ Directory: [[workspace]] │
│ Approval: on-request │

View File

@@ -7,6 +7,10 @@ expression: sanitized
╭────────────────────────────────────────────╮
│ >_ OpenAI Codex (v0.0.0) │
│ │
│ Visit chatgpt.com/codex/settings/usage for │
│ up-to-date │
│ information on rate limits and credits │
│ │
│ Model: gpt-5-codex (reasoning │
│ Directory: [[workspace]] │
│ Approval: on-request │