Fix pre-run skills refresh timing out after catalog updates - #93
Merged
Merged
Conversation
lukebuehler
enabled auto-merge (squash)
September 12, 2026 16:59
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
When a skill catalog changes before a run, Lightspeed retains the previous catalog version under the same context key for prompt caching. The gateway waiter selected that older entry, so a successfully committed refresh still timed out after 90 seconds and prevented the new input from starting a run.
Use the engine’s current-entry lookup when acknowledging context updates. Add a regression test with retained catalog history that verifies the latest update is acknowledged, superseded content is rejected, and a missing key remains pending.
Validation: gateway service unit tests;
cargo fmt --all --check;git diff --check.