Repository navigation
Enclosing code ranks file lessons by resolved symbol names - #1140
Merged
Merged
Conversation
Signed-off-by: Lareb Zafar <lareb.zafar@clickhouse.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
6 of 7 tasks
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Related: #1139
Changelog category (leave one):
Changelog entry (one or two sentences a user of Loom can read without the diff; the release pull request collects these into the release notes):
Enclosing-code reads use resolved symbol names to rank attached memories. Relevant notes can precede newer unrelated notes about the same file within the shared response budget.
Why
The enclosing-code handler resolves method names, but file-lesson enrichment receives an empty query. It therefore spends its bounded response on listing order even when the resolved names match an older note. Passing those names into the existing ranker retains evidence the code read already produced.
Scope and risk
The shared result wrapper derives one deduplicated query from resolved enclosing symbols, with qualified names when short names are absent. Unresolved locations contribute no terms. Search and grep retain their request queries. The same readable candidates, authorization, timeout, token budget, constraint and pin priority, and supersession filtering apply. No database or model call is added. No extractor or index stage changes.
Compatibility, rollout and rollback
Tests
AI assistance in the code (leave one; writing this description with AI is fine):
AI-generated: Codex implemented the change and regression coverage. Fresh independent agent review checks the pushed head.
I can explain every line of this diff and how it interacts with the rest of Loom.
Checklist