Skip to content

Revert "[codex] Harden overflow auto-compaction recovery" #22170

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
aibrahim-oai merged 1 commit into from
May 11, 2026
Merged

Revert "[codex] Harden overflow auto-compaction recovery" #22170

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
62 changes: 16 additions & 46 deletions codex-rs/core/src/compact.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -386,15 +386,15 @@ pub fn content_items_to_text(content: &[ContentItem]) -> Option<String> {
}
}

pub(crate) fn collect_user_messages(items: &[ResponseItem]) -> Vec<Vec<UserInput>> {
pub(crate) fn collect_user_messages(items: &[ResponseItem]) -> Vec<String> {
items
.iter()
.filter_map(|item| match crate::event_mapping::parse_turn_item(item) {
Some(TurnItem::UserMessage(user)) => {
if is_summary_message(&user.message()) {
None
} else {
Some(user.content)
Some(user.message())
}
}
_ => None,
Expand Down Expand Up @@ -465,7 +465,7 @@ pub(crate) fn insert_initial_context_before_last_real_user_or_summary(

pub(crate) fn build_compacted_history(
initial_context: Vec<ResponseItem>,
user_messages: &[Vec<UserInput>],
user_messages: &[String],
summary_text: &str,
) -> Vec<ResponseItem> {
build_compacted_history_with_limit(
Expand All @@ -478,33 +478,39 @@ pub(crate) fn build_compacted_history(

fn build_compacted_history_with_limit(
mut history: Vec<ResponseItem>,
user_messages: &[Vec<UserInput>],
user_messages: &[String],
summary_text: &str,
max_tokens: usize,
) -> Vec<ResponseItem> {
let mut selected_messages: Vec<Vec<UserInput>> = Vec::new();
let mut selected_messages: Vec<String> = Vec::new();
if max_tokens > 0 {
let mut remaining = max_tokens;
for message in user_messages.iter().rev() {
if remaining == 0 {
break;
}
let message_text = user_message_text(message);
let tokens = approx_token_count(&message_text);
let tokens = approx_token_count(message);
if tokens <= remaining {
selected_messages.push(message.clone());
remaining = remaining.saturating_sub(tokens);
} else {
let truncated = truncate_user_message(message, remaining);
let truncated = truncate_text(message, TruncationPolicy::Tokens(remaining));
selected_messages.push(truncated);
break;
}
}
selected_messages.reverse();
}

for message in selected_messages {
history.push(ResponseItem::from(ResponseInputItem::from(message)));
for message in &selected_messages {
history.push(ResponseItem::Message {
id: None,
role: "user".to_string(),
content: vec![ContentItem::InputText {
text: message.clone(),
}],
phase: None,
});
}

let summary_text = if summary_text.is_empty() {
Expand All @@ -523,42 +529,6 @@ fn build_compacted_history_with_limit(
history
}

pub(crate) fn user_message_text(message: &[UserInput]) -> String {
message
.iter()
.filter_map(|item| match item {
UserInput::Text { text, .. } => Some(text.as_str()),
_ => None,
})
.collect::<Vec<_>>()
.join("")
}

fn truncate_user_message(message: &[UserInput], remaining_tokens: usize) -> Vec<UserInput> {
let mut remaining_tokens = remaining_tokens;
let mut truncated = Vec::with_capacity(message.len());
for item in message {
match item {
UserInput::Text { text, .. } if remaining_tokens > 0 => {
let token_count = approx_token_count(text);
if token_count <= remaining_tokens {
truncated.push(item.clone());
remaining_tokens = remaining_tokens.saturating_sub(token_count);
} else {
truncated.push(UserInput::Text {
text: truncate_text(text, TruncationPolicy::Tokens(remaining_tokens)),
text_elements: Vec::new(),
});
remaining_tokens = 0;
}
}
UserInput::Text { .. } => {}
_ => truncated.push(item.clone()),
}
}
truncated
}

async fn drain_to_completed(
sess: &Session,
turn_context: &TurnContext,
Expand Down
90 changes: 8 additions & 82 deletions codex-rs/core/src/compact_tests.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,7 +55,7 @@ fn content_items_to_text_ignores_image_only_content() {
}

#[test]
fn collect_user_messages_preserves_user_content() {
fn collect_user_messages_extracts_user_text_only() {
let items = vec![
ResponseItem::Message {
id: Some("assistant".to_string()),
Expand All @@ -68,34 +68,17 @@ fn collect_user_messages_preserves_user_content() {
ResponseItem::Message {
id: Some("user".to_string()),
role: "user".to_string(),
content: vec![
ContentItem::InputImage {
image_url: "file://image.png".to_string(),
detail: Some(DEFAULT_IMAGE_DETAIL),
},
ContentItem::InputText {
text: "first".to_string(),
},
],
content: vec![ContentItem::InputText {
text: "first".to_string(),
}],
phase: None,
},
ResponseItem::Other,
];

let collected = collect_user_messages(&items);

assert_eq!(
vec![vec![
UserInput::Image {
image_url: "file://image.png".to_string(),
},
UserInput::Text {
text: "first".to_string(),
text_elements: Vec::new(),
},
]],
collected
);
assert_eq!(vec!["first".to_string()], collected);
}

#[test]
Expand Down Expand Up @@ -134,13 +117,7 @@ do things

let collected = collect_user_messages(&items);

assert_eq!(
vec![vec![UserInput::Text {
text: "real user message".to_string(),
text_elements: Vec::new(),
}]],
collected
);
assert_eq!(vec!["real user message".to_string()], collected);
}

#[test]
Expand All @@ -149,13 +126,9 @@ fn build_token_limited_compacted_history_truncates_overlong_user_messages() {
// that oversized user content is truncated.
let max_tokens = 16;
let big = "word ".repeat(200);
let user_message = vec![UserInput::Text {
text: big.clone(),
text_elements: Vec::new(),
}];
let history = super::build_compacted_history_with_limit(
Vec::new(),
std::slice::from_ref(&user_message),
std::slice::from_ref(&big),
"SUMMARY",
max_tokens,
);
Expand Down Expand Up @@ -189,57 +162,10 @@ fn build_token_limited_compacted_history_truncates_overlong_user_messages() {
assert_eq!(summary_text, "SUMMARY");
}

#[test]
fn truncate_user_message_preserves_text_segment_order_around_images() {
let before_image = "before ".repeat(8);
let after_image = "after ".repeat(200);
let before_image_tokens = approx_token_count(&before_image);
let after_image_token_budget = 16;
let remaining_tokens = before_image_tokens + after_image_token_budget;
let user_message = vec![
UserInput::Text {
text: before_image.clone(),
text_elements: Vec::new(),
},
UserInput::Image {
image_url: "file://image.png".to_string(),
},
UserInput::Text {
text: after_image.clone(),
text_elements: Vec::new(),
},
];

let truncated = super::truncate_user_message(&user_message, remaining_tokens);

assert_eq!(
vec![
UserInput::Text {
text: before_image,
text_elements: Vec::new(),
},
UserInput::Image {
image_url: "file://image.png".to_string(),
},
UserInput::Text {
text: truncate_text(
&after_image,
TruncationPolicy::Tokens(after_image_token_budget)
),
text_elements: Vec::new(),
},
],
truncated
);
}

#[test]
fn build_token_limited_compacted_history_appends_summary_message() {
let initial_context: Vec<ResponseItem> = Vec::new();
let user_messages = vec![vec![UserInput::Text {
text: "first user message".to_string(),
text_elements: Vec::new(),
}]];
let user_messages = vec!["first user message".to_string()];
let summary_text = "summary text";

let history = build_compacted_history(initial_context, &user_messages, summary_text);
Expand Down
33 changes: 4 additions & 29 deletions codex-rs/core/src/session/turn.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,6 @@ use crate::compact::InitialContextInjection;
use crate::compact::collect_user_messages;
use crate::compact::run_inline_auto_compact_task;
use crate::compact::should_use_remote_compact_task;
use crate::compact::user_message_text;
use crate::compact_remote::run_inline_remote_auto_compact_task;
use crate::compact_remote_v2::run_inline_remote_auto_compact_task as run_inline_remote_auto_compact_task_v2;
use crate::connectors;
Expand Down Expand Up @@ -311,7 +310,7 @@ pub(crate) async fn run_turn(
Vec::new()
} else {
let initial_input_for_turn: ResponseInputItem = ResponseInputItem::from(input.clone());
let response_item: ResponseItem = initial_input_for_turn.into();
let response_item: ResponseItem = initial_input_for_turn.clone().into();
let user_prompt_submit_outcome = run_user_prompt_submit_hooks(
&sess,
&turn_context,
Expand Down Expand Up @@ -919,11 +918,7 @@ pub(super) fn filter_connectors_for_input(
return Vec::new();
}

let user_message_texts = user_messages
.iter()
.map(|message| user_message_text(message))
.collect::<Vec<_>>();
let mentions = collect_tool_mentions_from_messages(&user_message_texts);
let mentions = collect_tool_mentions_from_messages(&user_messages);
let mention_names_lower = mentions
.plain_names
.iter()
Expand Down Expand Up @@ -1046,7 +1041,6 @@ async fn run_sampling_request(
Arc::clone(&turn_diff_tracker),
)
.await;
let max_retries = turn_context.provider.info().stream_max_retries();
let mut retries = 0;
let mut initial_input = Some(input);
loop {
Expand Down Expand Up @@ -1080,27 +1074,7 @@ async fn run_sampling_request(
}
Err(CodexErr::ContextWindowExceeded) => {
sess.set_total_tokens_full(&turn_context).await;
if retries >= max_retries {
return Err(CodexErr::ContextWindowExceeded);
}
retries += 1;
let reset_client_session = match run_auto_compact(
&sess,
&turn_context,
client_session,
InitialContextInjection::BeforeLastUserMessage,
CompactionReason::ContextLimit,
CompactionPhase::MidTurn,
)
.await
{
Ok(reset_client_session) => reset_client_session,
Err(_) => return Err(CodexErr::TurnAborted),
};
if reset_client_session {
client_session.reset_websocket_session();
}
continue;
return Err(CodexErr::ContextWindowExceeded);
Comment on lines 1075 to +1077
Copy link
Copy Markdown
Contributor

@chatgpt-codex-connector chatgpt-codex-connector Bot May 11, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Restore overflow compaction before returning context errors

Returning immediately on ContextWindowExceeded prevents the overflow recovery path from running. If the provider rejects a sampling request for input size before the pre/post token thresholds trigger, long threads now surface an error instead of compacting and retrying, so the next user turn remains stuck over the context window.

Useful? React with 👍 / 👎.

}
Err(CodexErr::UsageLimitReached(e)) => {
let rate_limits = e.rate_limits.clone();
Expand All @@ -1117,6 +1091,7 @@ async fn run_sampling_request(
}

// Use the configured provider-specific stream retry budget.
let max_retries = turn_context.provider.info().stream_max_retries();
if retries >= max_retries
&& client_session.try_switch_fallback_transport(
&turn_context.session_telemetry,
Expand Down
Loading
Loading