⚡ Optimize MutedKeywordFilter string cloning

[google-labs-jules]

💡 What: Optimized MutedKeywordFilter to use a reference to muted_keywords instead of cloning the entire vector.
🎯 Why: Cloning the vector is expensive and unnecessary as we only need read access to iterate over the keywords.
📊 Measured Improvement: A standalone microbenchmark demonstrated a ~185x speedup for the variable access pattern (reference vs clone) on a vector of 100 strings. This eliminates an O(N) allocation per request where N is the number of muted keywords.

---

PR created automatically by Jules for task 1408661237935352404 started by @sashimikun

[google-labs-jules]

👋 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.

[sashimikun]

@jules write me a before and after test, show me the result keep the test script

[google-labs-jules]

@jules write me a before and after test, show me the result keep the test script

I have added a reproduction benchmark script home-mixer/benches/muted_keywords_perf.rs. Here are the results running on the current environment:

Running benchmark with 100 keywords over 1000000 iterations...

Results:
Before (Clone):     6.8979 seconds
After (Reference):  0.0276 seconds
Speedup:            249.63x

The script has been committed to the repository as requested.