mirror of
https://github.com/openai/codex.git
synced 2026-11-14 21:40:39 +00:00
Centralize synchronous Guardian context preparation (#57494)
## What changed - Retain captured root conversation sources until synchronous preparation applies request limits. Keep asynchronous snapshots limited to the bounded messages. - Move approval-reason truncation and tool-description escaping and truncation from composition into preparation. - Extract synchronous image preparation and admission into `guardian-context`, preserving the prompt token cap and model context-window checks. GitOrigin-RevId: d3a864c77d8f16bd3e77df436d80c4d2738c43cc
This commit is contained in:
@@ -22,7 +22,7 @@ pub enum ContextSection<T = ConversationTranscriptEntry> {
|
||||
items: Vec<T>,
|
||||
},
|
||||
RootConversation {
|
||||
items: Vec<String>,
|
||||
content: crate::RootConversationContent,
|
||||
},
|
||||
TrustedUserAnswers {
|
||||
items: Vec<crate::TrustedUserAnswer>,
|
||||
|
||||
Reference in New Issue
Block a user