Skip to content

Optimize Semantic Cache Retrieval and Pruning#432

Merged
d-oit merged 4 commits into
mainfrom
perf/semantic-cache-optimization-16123962746434932673
Jun 8, 2026
Merged

Optimize Semantic Cache Retrieval and Pruning#432
d-oit merged 4 commits into
mainfrom
perf/semantic-cache-optimization-16123962746434932673

Conversation

@d-oit

@d-oit d-oit commented Jun 8, 2026

Copy link
Copy Markdown
Owner

This PR addresses performance and hit-rate issues in the wdr CLI semantic cache.

Key changes:

  1. Advanced Normalization: Queries are now normalized by removing documentation-specific stop-words (docs, library, standard, etc.) and sorting tokens alphabetically. This ensures that variadic queries for the same documentation hit the same cache entry with 1.0 similarity.
  2. Redundancy Pruning: The 'store' operation now checks for existing identical content or extremely high vector similarity (>0.999) before adding a new entry, significantly reducing cache bloat.
  3. Corrected Stats: The do-wdr cache-stats command was fixed to report live concept counts from the underlying framework rather than hardcoded zeros.
  4. Performance Verification: Benchmarks against Python, Rust, Go, MDN, and .NET docs confirm that cache hits remain extremely fast (~11ms), well within the 200ms target, and quality scores remain high (0.9-1.0).

Full analysis documented in agents-docs/SEMANTIC_HEALTH_2026_06.md.

PR created automatically by Jules for task 16123962746434932673 started by @d-oit

@google-labs-jules @d-oit
perf(cli): optimize semantic cache retrieval and pruning
1d4e65d 
- Implement advanced normalization (stop-word filtering and token sorting) to improve hit rates for variadic queries (e.g., 'Python Std Lib' -> 'Python Standard Library').
- Implement redundancy pruning in 'store' operation to skip identical content and extremely similar vectors.
- Fix 'cache-stats' command to report actual entry counts from the framework.
- Switch to code-aware TextEncoder for better identifier handling.
- Verify hit latency remains ~11ms and quality scores >0.85.
- Add Semantic Health summary for June 2026.

Co-authored-by: d-oit <6849456+d-oit@users.noreply.github.com>
@google-labs-jules

google-labs-jules Bot commented Jun 8, 2026

Copy link
Copy Markdown
Contributor

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.

For security, I will only act on instructions from the user who triggered this task.

@vercel

vercel Bot commented Jun 8, 2026 •
edited
Loading

Copy link
Copy Markdown

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Actions Updated (UTC)
do-web-doc-resolover Ready Ready Preview, Comment Jun 8, 2026 9:01am

@deepsource-io

deepsource-io Bot commented Jun 8, 2026 •
edited
Loading

Copy link
Copy Markdown

DeepSource Code Review

We reviewed changes in 40ab7b3...e7900d5 on this pull request. Below is the summary for the review, and you can see the individual issues we found as inline review comments.

See full review on DeepSource ↗

PR Report Card

Overall Grade   Security  

Reliability  

Complexity  

Hygiene  

Code Review Summary

Analyzer Status Updated (UTC) Details
JavaScript Jun 8, 2026 9:00a.m. Review ↗
Python Jun 8, 2026 9:00a.m. Review ↗
Rust Jun 8, 2026 9:00a.m. Review ↗
Shell Jun 8, 2026 9:00a.m. Review ↗

Important

AI Review is run only on demand for your team. We're only showing results of static analysis review right now. To trigger AI Review, comment @deepsourcebot review on this thread.

@codacy-production

codacy-production Bot commented Jun 8, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor

Up to standards ✅

🟢 Issues 0 issues

Results:
0 new issues

View in Codacy

🟢 Metrics -2 duplication

Metric Results
Duplication -2

View in Codacy

NEW Get contextual insights on your PRs based on Codacy's metrics, along with PR and Jira context, without leaving GitHub. Enable AI reviewer
TIP This summary will be updated as you push new changes.

@google-labs-jules @d-oit
perf(cli): optimize semantic cache retrieval and pruning
a1161ae 
- Implement advanced normalization (stop-word filtering and token sorting) to improve hit rates for variadic queries (e.g., 'Python Std Lib' -> 'Python Standard Library').
- Implement redundancy pruning in 'store' operation to skip identical content and extremely similar vectors.
- Fix 'cache-stats' command to report actual entry counts from the framework.
- Switch to code-aware TextEncoder for better identifier handling.
- Verify hit latency remains ~11ms and quality scores >0.85.
- Add Semantic Health summary for June 2026.
- Fix linting and clippy issues in previous attempt.

Co-authored-by: d-oit <6849456+d-oit@users.noreply.github.com>
@google-labs-jules @d-oit
perf(cli): optimize semantic cache retrieval and pruning
e7900d5 
- Implement advanced normalization (stop-word filtering and token sorting) to improve hit rates for variadic queries (e.g., 'Python Std Lib' -> 'Python Standard Library').
- Implement redundancy pruning in 'store' operation to skip identical content and extremely similar vectors.
- Fix 'cache-stats' command to report actual entry counts from the framework.
- Switch to code-aware TextEncoder for better identifier handling.
- Verify hit latency remains ~11ms and quality scores >0.85.
- Add Semantic Health summary for June 2026.
- Fix Markdownlint and Clippy issues.

Co-authored-by: d-oit <6849456+d-oit@users.noreply.github.com>
@d-oit d-oit merged commit 305cd06 into main Jun 8, 2026
39 checks passed
@d-oit d-oit deleted the perf/semantic-cache-optimization-16123962746434932673 branch June 8, 2026 09:44
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@d-oit