perf(codex): skip recall for control-only prompts - #3881
Open
AirHua-byte wants to merge 1 commit into
Open
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Skips automatic recall for strict control-only Codex prompts such as a bare acknowledgement, continue/status request, or fingerprinted approval. Classification is deterministic and happens before any recall HTTP request; prompts carrying task details continue through the existing recall path.
Human Involvement
Related Issue
Part of #3686
Type of Change
Changes Made
Testing
Added focused tests
Targeted tests pass locally
Tested on macOS
node --test scripts/auto-recall.test.mjs— 12 passed.Real-hook A/B, 15 repeats: false-injection rate 0.75 → 0.50; P50 1840 ms → 31 ms; P95 2885 ms → 2114 ms; injected-token P95 3238 → 2934; strict comparison passed.
Checklist
Additional Notes
The classifier intentionally avoids semantic inference. Any prompt with task-specific content falls through to normal recall.