docs: update performance benchmarks

[carlos-alm]

Summary

• Update performance benchmarks in generated/BENCHMARKS.md
• Update benchmark badge/stats in README.md

Test plan

• No code changes — docs only

[claude]

Claude finished @carlos-alm's task —— View job

---

PR Review: docs: update performance benchmarks

Review Tasks:

• Phase 1: Root Cause Analysis
• Phase 2: Configuration Change Detection
• Phase 3: Test Integrity
• Phase 4: Code Quality Assessment
• Examine changed files in detail
• Provide final assessment and rating

Root Cause Analysis

Problem Being Solved: This PR updates performance benchmark data from version 2.0.0 to 2.1.0, reflecting actual improvements in the codegraph tool's performance. The changes show:

• Native engine speed improved from 2.5ms/file to 1.9ms/file (24% faster)
• WASM engine slowed from 5ms/file to 6.6ms/file (32% slower)
• Overall estimated 50k file build time improved from 125s to 95s
• Edge count significantly reduced (~47% decrease) suggesting graph optimization

Why This Approach: This is a legitimate documentation update reflecting real performance measurements from CI. The data includes proper historical tracking and percentage comparisons.

Risk Assessment: LOW - Pure documentation update with no code changes.

Critical Concerns

None. This is a straightforward performance benchmark update.

Detailed Analysis

Phase 2: Configuration Changes ✅

No configuration files modified. Only documentation updates.

Phase 3: Test Integrity ✅

No test files modified. Test plan correctly states "No code changes — docs only".

Phase 4: Code Quality ✅

The benchmark updates appear legitimate and well-formatted:

1. README.md changes (lines 381-387):

   • Updated native speed: 2.5 → 1.9 ms/file ✅
   • Updated WASM speed: 5.0 → 6.6 ms/file ✅
   • Updated 50k estimate: 125.0s → 95.0s ✅
   • Numbers are consistent with detailed benchmarks

2. generated/BENCHMARKS.md changes:

   • Added complete v2.1.0 benchmark data ✅
   • Proper percentage change calculations ✅
   • Updated raw totals section ✅
   • Updated extrapolated performance estimates ✅
   • Maintained JSON data structure ✅

Verification

The performance improvements in the native engine (24% faster) and the WASM regression (32% slower) suggest legitimate architectural changes between v2.0.0 and v2.1.0. The significant edge count reduction (~47%) indicates meaningful graph optimization work.

The data is internally consistent:

• 92 files vs 89 in previous version ✅
• Native build time: 172ms / 92 files = 1.87ms/file ≈ 1.9ms/file ✅
• WASM build time: 609ms / 92 files = 6.62ms/file ≈ 6.6ms/file ✅

Final Recommendation

• Rating: ⭐⭐⭐⭐☆ (4/5)
• Action: APPROVE
• Reasoning: This is a clean, legitimate documentation update reflecting actual performance improvements. No code changes, no configuration relaxations, no test integrity issues. The benchmark data is well-formatted, internally consistent, and properly tracks performance trends. The only reason it's not 5 stars is that it's routine documentation maintenance rather than exceptional work.

---

[greptile-apps]

Greptile Summary

Updated performance benchmarks for v2.1.0, showing 24% improvement in native build speed (2.5 → 1.9 ms/file) but 32% regression in WASM performance (5 → 6.6 ms/file).

• All calculations are mathematically correct and consistent between files
• 50k file estimate updated accordingly (125s → 95s for native)
• No issues found

Confidence Score: 5/5

• This PR is safe to merge with no risk
• Documentation-only changes with accurate benchmark data updates, all calculations verified correct, no code changes
• No files require special attention

Important Files Changed

Filename	Overview
README.md	Updated performance metrics table with v2.1.0 benchmark data showing improved native build speed
generated/BENCHMARKS.md	Added v2.1.0 benchmark entries with updated raw totals and 50k file estimates

_{Last reviewed commit: aa6561b}

[greptile-apps]

_{2 files reviewed, no comments}

_{Edit Code Review Agent Settings | Greptile}