memory/v2: unify rerank pool by A_o and apply boost additively#29622
Merged
Conversation
…ost additively Cross-encoder rerank now selects its top-K from the unified pre-rerank-A_o pool instead of running per-channel on top-K-by-fused-sim. Boost is added to A_o weighted by c_user / c_assistant rather than folded into sim_u / sim_a, so a slug strong in both channels can no longer crowd out single-channel hits via a doubled per-channel boost. simBatch loses its useRerank/rerankBoost options and becomes pure dense+sparse fusion. computeOwnActivation owns the rerank step end-to-end: it computes pre-rerank A_o per candidate, picks top-K, runs the cross-encoder once per channel against that unified set, and adds c_user·α·r_norm_u + c_assistant·α·r_norm_a to the final A_o. The macOS inspector now renders rerank Δ_u / Δ_a as standalone additive A_o rows. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
…ost additively Cross-encoder rerank now selects its top-K from the unified pre-rerank-A_o pool instead of running per-channel on top-K-by-fused-sim. Boost is added to A_o weighted by c_user / c_assistant rather than folded into sim_u / sim_a, so a slug strong in both channels can no longer crowd out single-channel hits via a doubled per-channel boost. simBatch loses its useRerank/rerankBoost options and becomes pure dense+sparse fusion. computeOwnActivation owns the rerank step end-to-end: it computes pre-rerank A_o per candidate, picks top-K, runs the cross-encoder once per channel against that unified set, and adds c_user·α·r_norm_u + c_assistant·α·r_norm_a to the final A_o. The macOS inspector now renders rerank Δ_u / Δ_a as standalone additive A_o rows. Also drops stale `skills` references from the concept-frequency test — unblock the type-check that breaks on main after #29619 unified skills into the concept pool. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: ff79d861ef
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
Merged
5 tasks
siddseethepalli
added a commit
that referenced
this pull request
May 9, 2026
Codex P1 on #29622: ranking the unified rerank pool by full pre-rerank A_o let priorContribution and c_now*simN consume the rerank budget despite being ineligible for cross-encoder gains, starving genuinely user- or assistant-relevant slugs out of the pool when top_k is tight. Co-authored-by: Vellum Assistant <assistant@vellum.ai>
Contributor
Author
|
Codex P1 addressed in follow-up #30102 — rerank pool is now ranked by |
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.
Summary
skillsreferences from the concept-frequency test that break tsc on main after the recent skills-into-concept-pool unification.Original prompt
it