feat: keyword-match ranking in get_relevant_experience#3
Merged
Mola-maker merged 1 commit intomainfrom Apr 20, 2026
Merged
Conversation
Previously returned the most recent N experience entries. Now ranks by
keyword-match score (substring hits against problem/model_type/body),
ties broken by recency. Query source priority:
1. explicit 'query=' argument
2. auto-derived from context.json (competition.keywords +
selected_problem + problem_type + modeling.model_type)
3. none -> falls back to old recency-first behavior
When a query yields zero matches across all entries, falls back to
recency instead of suppressing history, so a noisy query never makes
the injection worse than before.
Backward-compatible: existing callers that don't pass 'query' now
benefit from context-derived matching when keywords are available,
and get identical output to the old code when they aren't.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Previously returned the most recent N experience entries. Now ranks by keyword-match score (substring hits against problem/model_type/body), ties broken by recency. Query source priority:
When a query yields zero matches across all entries, falls back to recency instead of suppressing history, so a noisy query never makes the injection worse than before.
Backward-compatible: existing callers that don't pass 'query' now benefit from context-derived matching when keywords are available, and get identical output to the old code when they aren't.