feat: add min_score filter to search_code

[iamvirul]

Summary

• Adds min_score: float = 0.35 parameter to search_code to filter out low-relevance results before returning them
• Values below the threshold (default 0.35 cosine similarity) are dropped as noise, reducing token usage without affecting result quality
• get_index_status now shows the default threshold so users know filtering is active
• min_score is clamped to [0.0, 1.0]; set to 0.0 to disable filtering entirely

Closes #35

Test plan

• test_min_score_filters_low_scoring_results — high score passes, low score is dropped
• test_min_score_zero_disables_filtering — min_score=0.0 passes everything through
• test_min_score_clamped_above_one — values > 1.0 are clamped to 1.0
• test_min_score_all_filtered_returns_no_results — returns "No results found" when all results are below threshold
• test_returns_expected_fields — get_index_status output includes Min score

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!

[iamvirul]

@PairReviewer Review this

[PairReviewer]

This PR adds a min_score parameter to the search_code function, enabling filtering of low-relevance results and surfacing the threshold in get_index_status. The implementation clamps min_score to [0.0, 1.0], handles edge cases, and is well-covered by tests. No bugs, security issues, or missing error handling were found; the code is production-ready.