fix: preserve Responses cache salt#96
Merged
Merged
Conversation
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This was referenced Jul 13, 2026
franciscojavierarceo
marked this pull request as ready for review
July 16, 2026 14:25
franciscojavierarceo
requested review from
bbrowning,
jiahuei,
leseb,
maralbahari,
noobHappylife,
qandrew and
tjtanaa
as code owners
July 16, 2026 14:25
maralbahari
approved these changes
Jul 16, 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 join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
cache_saltwhen parsingRequestPayloadand serializing the normalized request sent upstream.RequestPayload::to_upstream_request.Why
The gateway previously accepted JSON containing
cache_saltbut silently discarded the unknown field during deserialization. In a KV-aware llm-d deployment, llm-d folds the salt into its first canonical request key and vLLM includes it in APC block identity. Dropping the field weakens tenant isolation and prevents llm-d's salted request keys from matching vLLM's salted KV events.This implementation is intentionally separate from the ADR and benchmark evidence in #65.
Test Plan
cargo test -p agentic-server-core request_payload_forwards_cache_salt_upstream -- --nocapturecargo testcargo clippy --all-targets -- -D warningscargo fmt --all -- --checkuvx pre-commit run --all-files