Merge pull request #1835 from codeflash-ai/update-claude-md

update claude.md

Author: misrasaurabh1

CLAUDE.md

@@ -2,7 +2,7 @@
 
 ## Project Overview
 
-CodeFlash is an AI-powered code optimizer that automatically improves performance while maintaining correctness. It supports Python, JavaScript, and TypeScript, with more languages planned. It uses LLMs to generate optimization candidates, verifies correctness through test execution, and benchmarks performance improvements.
+CodeFlash is an AI-powered code optimizer that automatically improves performance while maintaining correctness. It supports Python, JavaScript, TypeScript, Java with more languages planned. It uses LLMs to generate optimization candidates, verifies correctness through test execution, and benchmarks performance improvements.
 
 ## Optimization Pipeline
 
@@ -18,19 +18,9 @@ Discovery → Ranking → Context Extraction → Test Gen + Optimization → Bas
 6. **Benchmarking** (`benchmarking/`): Measure performance, select best candidate by speedup
 7. **Result** (`result/`, `github/`): Create PR with winning optimization
 
-## Domain Glossary
-
-- **Optimization candidate**: A generated code variant that might be faster (`OptimizedCandidate`)
-- **Function context**: All code needed for optimization — split into read-writable (modifiable) and read-only (reference)
-- **Addressable time**: Time a function spends that could be optimized (own time + callee time / call count)
-- **Candidate forest**: DAG of candidates where refinements/repairs build on previous candidates
-- **Replay test**: Test generated from recorded benchmark data to reproduce real workloads
-- **Tracer**: Profiling system that records function call trees and timings (`tracing/`, `tracer.py`)
-- **Worktree mode**: Git worktree-based parallel optimization (`--worktree` flag)
-
-## PR Reviews
-
-- GitHub PR comments and review feedback can be stale — they may reference issues already fixed by a later commit. Before acting on review feedback, verify it still applies to the current code. If the issue no longer exists, resolve the conversation in the GitHub UI.
+# Instructions
+- When I report a bug, don't start by trying to fix it. Instead, start by writing a test that reproduces the bug. Then, have subagents try to fix the bug and prove it with a passing test.
+- Everything that can be tested should have tests.
 
 <!-- Section below is auto-generated by `tessl install` - do not edit manually -->