mirror of
https://github.com/openai/codex.git
synced 2026-05-03 02:46:39 +00:00
feat(tui): pace catch-up stream chunking with hysteresis (#10461)
## Summary - preserve baseline streaming behavior (smooth mode still commits one line per 50ms tick) - extract adaptive chunking policy and commit-tick orchestration from ChatWidget into `streaming/chunking.rs` and `streaming/commit_tick.rs` - add hysteresis-based catch-up behavior with bounded batch draining to reduce queue lag without bursty single-frame jumps - document policy behavior, tuning guidance, and debug flow in rustdoc + docs ## Testing - just fmt - cargo test -p codex-tui
This commit is contained in:
@@ -852,6 +852,7 @@ async fn make_chatwidget_manual(
|
||||
rate_limit_warnings: RateLimitWarningState::default(),
|
||||
rate_limit_switch_prompt: RateLimitSwitchPromptState::default(),
|
||||
rate_limit_poller: None,
|
||||
adaptive_chunking: crate::streaming::chunking::AdaptiveChunkingPolicy::default(),
|
||||
stream_controller: None,
|
||||
plan_stream_controller: None,
|
||||
running_commands: HashMap::new(),
|
||||
|
||||
Reference in New Issue
Block a user