{{ message }}
avoid cloning sampling request input#28306
Merged
Merged
Conversation
jif-oai
changed the title
Collaborator
Author
anp-oai
approved these changes
Jun 15, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Why
Every model request cloned the full prepared input just to keep it for the legacy after-agent hook. That copy gets more expensive as the conversation grows.
What
Move the prepared input into the sampling loop and return it with the result. If the request retries, keep the first input so the hook still sees the same data as before.
This removes one
O(n)clone per sampling request, wherenis the size of the prepared input. It savesO(n)copy work andO(n)temporary memory.No behavior change is intended.
Performance
Local rollout traces show turns reaching roughly 260k input tokens. On turns of that size, this removes the only unconditional full prepared-input clone on the happy path. That avoids one request-sized allocation/copy per sampling attempt for large conversations, and the savings scale linearly with request size.
Testing
just test -p codex-core continue_after_stream_errorjust fix -p codex-core