Improve compact (#6692)

This PR does the following:
- Add compact prefix to the summary
- Change the compaction prompt
- Allow multiple compaction for long running tasks
- Filter out summary messages on the following compaction

Considerations:
- Filtering out the summary message isn't the most clean
- Theoretically, we can end up in infinite compaction loop if the user
messages > compaction limit . However, that's not possible in today's
code because we have hard cap on user messages.
- We need to address having multiple user messages because it confuses
the model.

Testing:
- Making sure that after compact we always end up with one user message
(task) and one summary, even on multiple compaction.
This commit is contained in:
Ahmed Ibrahim
2025-11-15 07:17:51 +00:00
committed by GitHub
parent 94dfb211af
commit 0b28e72b66
5 changed files with 610 additions and 184 deletions
+1 -17
View File
@@ -1819,7 +1819,6 @@ pub(crate) async fn run_task(
// Although from the perspective of codex.rs, TurnDiffTracker has the lifecycle of a Task which contains
// many turns, from the perspective of the user, it is a single turn.
let turn_diff_tracker = Arc::new(tokio::sync::Mutex::new(TurnDiffTracker::new()));
let mut auto_compact_recently_attempted = false;
loop {
// Note that pending_input would be something like a message the user
@@ -1874,27 +1873,12 @@ pub(crate) async fn run_task(
let (responses, items_to_record_in_conversation_history) =
process_items(processed_items, &sess, &turn_context).await;
// as long as compaction works well in getting us way below the token limit, we shouldn't worry about being in an infinite loop.
if token_limit_reached {
if auto_compact_recently_attempted {
let limit_str = limit.to_string();
let current_tokens = total_usage_tokens
.map(|tokens| tokens.to_string())
.unwrap_or_else(|| "unknown".to_string());
let event = EventMsg::Error(ErrorEvent {
message: format!(
"Conversation is still above the token limit after automatic summarization (limit {limit_str}, current {current_tokens}). Please start a new session or trim your input."
),
});
sess.send_event(&turn_context, event).await;
break;
}
auto_compact_recently_attempted = true;
compact::run_inline_auto_compact_task(sess.clone(), turn_context.clone()).await;
continue;
}
auto_compact_recently_attempted = false;
if responses.is_empty() {
last_agent_message = get_last_assistant_message_from_turn(
&items_to_record_in_conversation_history,
+15 -2
View File
@@ -26,6 +26,7 @@ use futures::prelude::*;
use tracing::error;
pub const SUMMARIZATION_PROMPT: &str = include_str!("../templates/compact/prompt.md");
pub const SUMMARY_PREFIX: &str = include_str!("../templates/compact/summary_prefix.md");
const COMPACT_USER_MESSAGE_MAX_TOKENS: usize = 20_000;
pub(crate) async fn run_inline_auto_compact_task(
@@ -140,7 +141,9 @@ async fn run_compact_task_inner(
}
let history_snapshot = sess.clone_history().await.get_history();
let summary_text = get_last_assistant_message_from_turn(&history_snapshot).unwrap_or_default();
let summary_suffix =
get_last_assistant_message_from_turn(&history_snapshot).unwrap_or_default();
let summary_text = format!("{SUMMARY_PREFIX}\n{summary_suffix}");
let user_messages = collect_user_messages(&history_snapshot);
let initial_context = sess.build_initial_context(turn_context.as_ref());
@@ -201,12 +204,22 @@ 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)) => Some(user.message()),
Some(TurnItem::UserMessage(user)) => {
if is_summary_message(&user.message()) {
None
} else {
Some(user.message())
}
}
_ => None,
})
.collect()
}
pub(crate) fn is_summary_message(message: &str) -> bool {
message.starts_with(format!("{SUMMARY_PREFIX}\n").as_str())
}
pub(crate) fn build_compacted_history(
initial_context: Vec<ResponseItem>,
user_messages: &[String],