mirror of
https://github.com/openai/codex.git
synced 2026-11-07 16:35:32 +00:00
Always use streamed remote compaction for supported providers (#44255)
## What changed - Route manual and automatic remote compaction through the v2 implementation. - Retire the `remote_compaction_v2` feature toggle while continuing to advertise it in the model client beta features header. - Migrate compaction tests from `/responses/compact` to streamed `/responses` requests with `compaction_trigger` items and remove legacy parity coverage. ## Testing Add streamed compaction coverage for tool search output trimming and session base instruction token estimates. Update app-server tests to verify started/completed notifications for both local and streamed remote compaction. GitOrigin-RevId: cea392a6166a9b116ff83708fd9126d5546476e4
This commit is contained in:
1 parent
2617ed2e1c
commit
3dc1e2a584
25 files changed
+675
-5635
No files matched your search
@@ -29,6 +29,10 @@ pub use responses_metadata::CodexResponsesMetadata;
|
||||
pub use turn_metadata::detached_memory_responses_metadata;
|
||||
mod codex_thread;
|
||||
mod compact_model_fallback;
|
||||
#[expect(
|
||||
dead_code,
|
||||
reason = "the unrouted v1 runner is removed in the follow-up"
|
||||
)]
|
||||
mod compact_remote;
|
||||
mod compact_remote_history;
|
||||
mod compact_remote_v2;
|
||||
|
||||
Reference in new issue
Block a user