Merge branch 'codelion:main' into main

Author: maisyhoang

.github/workflows/claude-code-review.yml

@@ -0,0 +1,78 @@
+name: Claude Code Review
+
+on:
+  pull_request:
+    types: [opened, synchronize]
+    # Optional: Only run on specific file changes
+    # paths:
+    #   - "src/**/*.ts"
+    #   - "src/**/*.tsx"
+    #   - "src/**/*.js"
+    #   - "src/**/*.jsx"
+
+jobs:
+  claude-review:
+    # Optional: Filter by PR author
+    # if: |
+    #   github.event.pull_request.user.login == 'external-contributor' ||
+    #   github.event.pull_request.user.login == 'new-developer' ||
+    #   github.event.pull_request.author_association == 'FIRST_TIME_CONTRIBUTOR'
+    
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: read
+      issues: read
+      id-token: write
+    
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Run Claude Code Review
+        id: claude-review
+        uses: anthropics/claude-code-action@beta
+        with:
+          claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
+
+          # Optional: Specify model (defaults to Claude Sonnet 4, uncomment for Claude Opus 4)
+          # model: "claude-opus-4-20250514"
+          
+          # Direct prompt for automated review (no @claude mention needed)
+          direct_prompt: |
+            Please review this pull request and provide feedback on:
+            - Code quality and best practices
+            - Potential bugs or issues
+            - Performance considerations
+            - Security concerns
+            - Test coverage
+            
+            Be constructive and helpful in your feedback.
+
+          # Optional: Use sticky comments to make Claude reuse the same comment on subsequent pushes to the same PR
+          # use_sticky_comment: true
+          
+          # Optional: Customize review based on file types
+          # direct_prompt: |
+          #   Review this PR focusing on:
+          #   - For TypeScript files: Type safety and proper interface usage
+          #   - For API endpoints: Security, input validation, and error handling
+          #   - For React components: Performance, accessibility, and best practices
+          #   - For tests: Coverage, edge cases, and test quality
+          
+          # Optional: Different prompts for different authors
+          # direct_prompt: |
+          #   ${{ github.event.pull_request.author_association == 'FIRST_TIME_CONTRIBUTOR' && 
+          #   'Welcome! Please review this PR from a first-time contributor. Be encouraging and provide detailed explanations for any suggestions.' ||
+          #   'Please provide a thorough code review focusing on our coding standards and best practices.' }}
+          
+          # Optional: Add specific tools for running tests or linting
+          # allowed_tools: "Bash(npm run test),Bash(npm run lint),Bash(npm run typecheck)"
+          
+          # Optional: Skip review for certain conditions
+          # if: |
+          #   !contains(github.event.pull_request.title, '[skip-review]') &&
+          #   !contains(github.event.pull_request.title, '[WIP]')
+

.github/workflows/claude.yml

@@ -0,0 +1,64 @@
+name: Claude Code
+
+on:
+  issue_comment:
+    types: [created]
+  pull_request_review_comment:
+    types: [created]
+  issues:
+    types: [opened, assigned]
+  pull_request_review:
+    types: [submitted]
+
+jobs:
+  claude:
+    if: |
+      (github.event_name == 'issue_comment' && contains(github.event.comment.body, '@claude')) ||
+      (github.event_name == 'pull_request_review_comment' && contains(github.event.comment.body, '@claude')) ||
+      (github.event_name == 'pull_request_review' && contains(github.event.review.body, '@claude')) ||
+      (github.event_name == 'issues' && (contains(github.event.issue.body, '@claude') || contains(github.event.issue.title, '@claude')))
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: read
+      issues: read
+      id-token: write
+      actions: read # Required for Claude to read CI results on PRs
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Run Claude Code
+        id: claude
+        uses: anthropics/claude-code-action@beta
+        with:
+          claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
+
+          # This is an optional setting that allows Claude to read CI results on PRs
+          additional_permissions: |
+            actions: read
+          
+          # Optional: Specify model (defaults to Claude Sonnet 4, uncomment for Claude Opus 4)
+          # model: "claude-opus-4-20250514"
+          
+          # Optional: Customize the trigger phrase (default: @claude)
+          # trigger_phrase: "/claude"
+          
+          # Optional: Trigger when specific user is assigned to an issue
+          # assignee_trigger: "claude-bot"
+          
+          # Optional: Allow Claude to run specific commands
+          # allowed_tools: "Bash(npm install),Bash(npm run build),Bash(npm run test:*),Bash(npm run lint:*)"
+          
+          # Optional: Add custom instructions for Claude to customize its behavior for your project
+          # custom_instructions: |
+          #   Follow our coding standards
+          #   Ensure all new code has tests
+          #   Use TypeScript for new files
+          
+          # Optional: Custom environment variables for Claude
+          # claude_env: |
+          #   NODE_ENV: test
+

examples/rust_adaptive_sort/config.yaml

@@ -49,9 +49,5 @@ evaluator:
   timeout: 60  # Rust compilation can take time
   parallel_evaluations: 3
 
-  # Use cascade evaluation for performance testing
-  cascade_evaluation: true
-  cascade_thresholds:
-    - 0.5  # Compilation success and basic correctness
-    - 0.7  # Good performance
-    - 0.85 # Excellent adaptability
+  # Direct evaluation - evaluator doesn't implement cascade functions
+  cascade_evaluation: false

openevolve/config.py

@@ -32,7 +32,7 @@ class LLMModelConfig:
     timeout: int = None
     retries: int = None
     retry_delay: int = None
-    
+
     # Reproducibility
     random_seed: Optional[int] = None
 
@@ -56,10 +56,12 @@ class LLMConfig(LLMModelConfig):
     retry_delay: int = 5
 
     # n-model configuration for evolution LLM ensemble
-    models: List[LLMModelConfig] = field(default_factory=lambda: [
-        LLMModelConfig(name="gpt-4o-mini", weight=0.8),
-        LLMModelConfig(name="gpt-4o", weight=0.2)
-    ])
+    models: List[LLMModelConfig] = field(
+        default_factory=lambda: [
+            LLMModelConfig(name="gpt-4o-mini", weight=0.8),
+            LLMModelConfig(name="gpt-4o", weight=0.2),
+        ]
+    )
 
     # n-model configuration for evaluator LLM ensemble
     evaluator_models: List[LLMModelConfig] = field(default_factory=lambda: [])
@@ -264,7 +266,7 @@ def from_dict(cls, config_dict: Dict[str, Any]) -> "Config":
             config.prompt = PromptConfig(**config_dict["prompt"])
         if "database" in config_dict:
             config.database = DatabaseConfig(**config_dict["database"])
-        
+
         # Ensure database inherits the random seed if not explicitly set
         if config.database.random_seed is None and config.random_seed is not None:
             config.database.random_seed = config.random_seed
@@ -365,4 +367,4 @@ def load_config(config_path: Optional[Union[str, Path]] = None) -> Config:
     # Make the system message available to the individual models, in case it is not provided from the prompt sampler
     config.llm.update_model_params({"system_message": config.prompt.system_message})
 
-    return config
+    return config

openevolve/controller.py

@@ -104,20 +104,20 @@ def __init__(
             # Set global random seeds
             random.seed(self.config.random_seed)
             np.random.seed(self.config.random_seed)
-            
+
             # Create hash-based seeds for different components
-            base_seed = str(self.config.random_seed).encode('utf-8')
-            llm_seed = int(hashlib.md5(base_seed + b'llm').hexdigest()[:8], 16) % (2**31)
-            
+            base_seed = str(self.config.random_seed).encode("utf-8")
+            llm_seed = int(hashlib.md5(base_seed + b"llm").hexdigest()[:8], 16) % (2**31)
+
             # Propagate seed to LLM configurations
             self.config.llm.random_seed = llm_seed
             for model_cfg in self.config.llm.models:
-                if not hasattr(model_cfg, 'random_seed') or model_cfg.random_seed is None:
+                if not hasattr(model_cfg, "random_seed") or model_cfg.random_seed is None:
                     model_cfg.random_seed = llm_seed
             for model_cfg in self.config.llm.evaluator_models:
-                if not hasattr(model_cfg, 'random_seed') or model_cfg.random_seed is None:
+                if not hasattr(model_cfg, "random_seed") or model_cfg.random_seed is None:
                     model_cfg.random_seed = llm_seed
-            
+
             logger.info(f"Set random seed to {self.config.random_seed} for reproducibility")
             logger.debug(f"Generated LLM seed: {llm_seed}")
 
@@ -161,7 +161,7 @@ def __init__(
         self.evaluation_file = evaluation_file
 
         logger.info(f"Initialized OpenEvolve with {initial_program_path}")
-        
+
         # Initialize improved parallel processing components
         self.parallel_controller = None
 
@@ -212,7 +212,7 @@ async def run(
             Best program found
         """
         max_iterations = iterations or self.config.max_iterations
-        
+
         # Determine starting iteration
         start_iteration = 0
         if checkpoint_path and os.path.exists(checkpoint_path):
@@ -260,30 +260,31 @@ async def run(
             self.parallel_controller = ImprovedParallelController(
                 self.config, self.evaluation_file, self.database
             )
-            
+
             # Set up signal handlers for graceful shutdown
             def signal_handler(signum, frame):
                 logger.info(f"Received signal {signum}, initiating graceful shutdown...")
                 self.parallel_controller.request_shutdown()
-                
+
                 # Set up a secondary handler for immediate exit if user presses Ctrl+C again
                 def force_exit_handler(signum, frame):
                     logger.info("Force exit requested - terminating immediately")
                     import sys
+
                     sys.exit(0)
-                
+
                 signal.signal(signal.SIGINT, force_exit_handler)
-            
+
             signal.signal(signal.SIGINT, signal_handler)
             signal.signal(signal.SIGTERM, signal_handler)
-            
+
             self.parallel_controller.start()
-            
+
             # Run evolution with improved parallel processing and checkpoint callback
             await self._run_evolution_with_checkpoints(
                 start_iteration, max_iterations, target_score
             )
-            
+
         finally:
             # Clean up parallel processing resources
             if self.parallel_controller:
@@ -420,31 +421,28 @@ def _load_checkpoint(self, checkpoint_path: str) -> None:
         """Load state from a checkpoint directory"""
         if not os.path.exists(checkpoint_path):
             raise FileNotFoundError(f"Checkpoint directory {checkpoint_path} not found")
-        
+
         logger.info(f"Loading checkpoint from {checkpoint_path}")
         self.database.load(checkpoint_path)
-        logger.info(
-            f"Checkpoint loaded successfully (iteration {self.database.last_iteration})"
-        )
+        logger.info(f"Checkpoint loaded successfully (iteration {self.database.last_iteration})")
 
     async def _run_evolution_with_checkpoints(
         self, start_iteration: int, max_iterations: int, target_score: Optional[float]
     ) -> None:
         """Run evolution with checkpoint saving support"""
         logger.info(f"Using island-based evolution with {self.config.database.num_islands} islands")
         self.database.log_island_status()
-        
+
         # Run the evolution process with checkpoint callback
         await self.parallel_controller.run_evolution(
-            start_iteration, max_iterations, target_score,
-            checkpoint_callback=self._save_checkpoint
+            start_iteration, max_iterations, target_score, checkpoint_callback=self._save_checkpoint
         )
-        
+
         # Check if shutdown was requested
         if self.parallel_controller.shutdown_flag.is_set():
             logger.info("Evolution stopped due to shutdown request")
             return
-        
+
         # Save final checkpoint if needed
         final_iteration = start_iteration + max_iterations - 1
         if final_iteration > 0 and final_iteration % self.config.checkpoint_interval == 0:
@@ -499,4 +497,4 @@ def _save_best_program(self, program: Optional[Program] = None) -> None:
                 indent=2,
             )
 
-        logger.info(f"Saved best program to {code_path} with program info to {info_path}")
+        logger.info(f"Saved best program to {code_path} with program info to {info_path}")