mirror of
https://github.com/openai/codex.git
synced 2026-11-17 14:58:36 +00:00
Optimize remote compaction history handling (#34431)
## Why Remote compaction can process large histories. Repeatedly estimating and replacing the full history, and cloning it when tracing is disabled, adds avoidable CPU and memory overhead. ## What changed - Estimate each history item's token count once, update the total as trailing tool outputs are rewritten, and replace history only after all rewrites are selected. - Preserve unclamped token totals while calculating removed tokens so saturated estimates do not hide overflow. - Snapshot compaction input history only when rollout tracing is enabled. - Reuse the v2 request input instead of cloning it before adding the compaction trigger. ## Testing - Cover enabled and disabled compaction trace contexts through `is_enabled()` assertions. GitOrigin-RevId: 8de9c9704ba29532fba05430eb204bbae2e8bf83
This commit is contained in:
1 parent
56c11cf658
commit
fd3c1dc13d
9 files changed
+72
-40
No files matched your search
@@ -142,6 +142,7 @@ fn disabled_thread_context_accepts_trace_calls_without_writing() -> anyhow::Resu
|
||||
"gpt-test",
|
||||
"test-provider",
|
||||
);
|
||||
assert!(!compaction_trace.is_enabled());
|
||||
let compaction_attempt =
|
||||
compaction_trace.start_attempt(&serde_json::json!({ "kind": "compaction" }));
|
||||
compaction_attempt.record_completed(&[]);
|
||||
@@ -175,6 +176,7 @@ fn compaction_contexts_share_identity_across_models() -> anyhow::Result<()> {
|
||||
for model in ["gpt-previous", "gpt-selected"] {
|
||||
let compaction_trace =
|
||||
thread_trace.compaction_trace_context("turn-1", "compaction-1", model, "test-provider");
|
||||
assert!(compaction_trace.is_enabled());
|
||||
compaction_trace
|
||||
.start_attempt(&serde_json::json!({ "model": model }))
|
||||
.record_failed("test failure");
|
||||
|
||||
Reference in new issue
Block a user