feat(llm): batch triage RAG context extended

docs/advanced/ci-cd.mdx

@@ -39,15 +39,15 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v2
-      
+
       - name: Set up Python
         uses: actions/setup-python@v2
         with:
           python-version: '3.9'
-      
+
       - name: Install Refactron
         run: pip install refactron
-      
+
       - name: Analyze Code
         run: refactron analyze . --log-format json
 ```
@@ -131,7 +131,7 @@ repos:
     refactron analyze . --log-format json
     ```
   </Accordion>
-  
+
   <Accordion title="Configure Failure Thresholds">
     Fail builds based on severity:
     ```yaml
@@ -142,7 +142,7 @@ repos:
     max_error_issues: 10
     ```
   </Accordion>
-  
+
   <Accordion title="Cache Dependencies">
     Speed up CI runs by caching pip packages:
     ```yaml
@@ -153,7 +153,7 @@ repos:
         key: ${{ runner.os }}-pip-refactron
     ```
   </Accordion>
-  
+
   <Accordion title="Generate Reports">
     Create HTML reports and save as artifacts:
     ```bash

docs/advanced/monitoring.mdx

@@ -8,7 +8,7 @@ description: 'Production monitoring and telemetry'
 Refactron includes comprehensive logging and monitoring capabilities for production environments:
 
 - **Structured Logging** - JSON-formatted logs for CI/CD
-- **Metrics Collection** - Track analysis time and success rates  
+- **Metrics Collection** - Track analysis time and success rates
 - **Prometheus Integration** - Expose metrics via HTTP endpoint
 - **Opt-in Telemetry** - Anonymous usage analytics
 
@@ -187,15 +187,15 @@ prometheus_port: 9090
   <Step title="Use JSON Logging in CI/CD">
     JSON format integrates easily with log aggregation systems
   </Step>
-  
+
   <Step title="Enable Metrics in Production">
     Track performance and identify bottlenecks
   </Step>
-  
+
   <Step title="Set Up Prometheus Dashboards">
     Visualize Refactron metrics over time
   </Step>
-  
+
   <Step title="Keep Telemetry Optional">
     Respect user privacy with opt-in telemetry
   </Step>

docs/advanced/performance.mdx

@@ -36,20 +36,20 @@ Cache parsed Abstract Syntax Trees to avoid re-parsing.
     - Reduces CPU usage
     - Especially effective for large files
   </Accordion>
-  
+
   <Accordion title="Configuration">
     ```python
     from refactron import Refactron
     from refactron.core.config import RefactronConfig
-    
+
     config = RefactronConfig(
         enable_ast_cache=True,
         max_ast_cache_size_mb=100
     )
     refactron = Refactron(config)
     ```
   </Accordion>
-  
+
   <Accordion title="Cache Statistics">
     ```python
     stats = refactron.get_performance_stats()
@@ -156,13 +156,13 @@ refactron.clear_caches()
     print(f"Hit rate: {stats['ast_cache']['hit_rate']}%")
     ```
   </Accordion>
-  
+
   <Accordion title="High Memory Usage">
     - Reduce cache size: `max_ast_cache_size_mb: 50`
     - Lower parallel workers: `max_parallel_workers: 2`
     - Clear caches periodically: `refactron.clear_caches()`
   </Accordion>
-  
+
   <Accordion title="Parallel Processing Slower">
     Disable for small codebases:
     ```yaml

docs/api-reference/refactron-class.mdx

@@ -80,7 +80,7 @@ def refactor(
 
 <ParamField path="operation_types" type="List[str]" default="None">
   Specific refactoring types to apply. None = all types.
-  
+
   Available types:
   - `extract_constant`
   - `add_docstring`
@@ -316,7 +316,7 @@ for op in result.operations:
     print(f"  File: {op.file_path}:{op.line_number}")
     print(f"  Risk: {op.risk_score}")
     print(f"  Description: {op.description}")
-    
+
     # Record feedback
     refactron.record_feedback(
         operation_id=op.operation_id,

docs/docs.json

@@ -93,4 +93,4 @@
       "vscode"
     ]
   }
-}
+}

docs/essentials/authentication.mdx

@@ -84,17 +84,17 @@ Features that require authentication:
     refactron repo connect my-repo
     ```
   </Accordion>
-  
+
   <Accordion icon="sparkles" title="Cloud AI Features">
     Enhanced AI-powered refactoring with cloud LLM models
   </Accordion>
-  
+
   <Accordion icon="chart-simple" title="Usage Analytics">
     ```bash
     refactron metrics
     ```
   </Accordion>
-  
+
   <Accordion icon="share-nodes" title="Team Pattern Sharing">
     Share learned patterns across your team
   </Accordion>
@@ -120,15 +120,15 @@ Cloud features gracefully degrade when offline.
     2. Paste it into your browser manually
     3. Complete the authentication
   </Accordion>
-  
+
   <Accordion title="Token expired">
     If you see "Token expired" errors:
     ```bash
     refactron auth logout
     refactron login
     ```
   </Accordion>
-  
+
   <Accordion title="API key not working">
     Verify the API key is set correctly:
     ```bash

docs/essentials/configuration.mdx

@@ -67,23 +67,23 @@ pattern_storage_dir: null  # null = auto-detect
   <Accordion icon="shield" title="security">
     Detects security vulnerabilities like SQL injection, code injection, hardcoded secrets, and SSRF
   </Accordion>
-  
+
   <Accordion icon="code" title="code_smell">
     Identifies magic numbers, long functions, excessive parameters, and deep nesting
   </Accordion>
-  
+
   <Accordion icon="chart-line" title="complexity">
     Measures cyclomatic complexity, maintainability index, and nested loops
   </Accordion>
-  
+
   <Accordion icon="file-code" title="type_hint">
     Checks for missing or incomplete type annotations
   </Accordion>
-  
+
   <Accordion icon="trash" title="dead_code">
     Finds unused functions and unreachable code
   </Accordion>
-  
+
   <Accordion icon="link" title="dependency">
     Analyzes circular imports and wildcard imports
   </Accordion>
@@ -95,15 +95,15 @@ pattern_storage_dir: null  # null = auto-detect
   <Accordion title="extract_constant">
     Extract magic numbers into named constants
   </Accordion>
-  
+
   <Accordion title="add_docstring">
     Add missing docstrings to functions and classes
   </Accordion>
-  
+
   <Accordion title="simplify_conditionals">
     Simplify complex conditional statements
   </Accordion>
-  
+
   <Accordion title="reduce_parameters">
     Reduce function parameter count using dataclasses or dictionaries
   </Accordion>

docs/essentials/installation.mdx

@@ -6,7 +6,7 @@ description: 'How to install and set up Refactron'
 ## Requirements
 
 <Info>
-  **Python Version**: 3.8 or higher  
+  **Python Version**: 3.8 or higher
   **Supported Platforms**: macOS, Linux, Windows
 </Info>
 
@@ -71,7 +71,7 @@ Refactron automatically installs these dependencies:
     - **radon** - Complexity metrics
     - **astroid** - AST analysis
   </Accordion>
-  
+
   <Accordion title="AI & RAG Dependencies">
     - **chromadb** - Vector database for RAG
     - **tree-sitter** - Code parsing
@@ -90,7 +90,7 @@ Refactron automatically installs these dependencies:
     pip install --user refactron
     ```
   </Accordion>
-  
+
   <Accordion title="Python Version Issues">
     Ensure you're using Python 3.8+:
     ```bash
@@ -101,7 +101,7 @@ Refactron automatically installs these dependencies:
     python3.10 -m pip install refactron
     ```
   </Accordion>
-  
+
   <Accordion title="SSL Certificate Errors">
     On macOS, you may need to install certificates:
     ```bash

docs/guides/ai-features.mdx

@@ -120,19 +120,19 @@ refactron refactor myfile.py --ai --apply
   <Step title="Analysis">
     Refactron analyzes your code for issues
   </Step>
-  
+
   <Step title="Context Retrieval">
     RAG system retrieves relevant code chunks from your project
   </Step>
-  
+
   <Step title="LLM Generation">
     LLM generates refactoring suggestions with project context
   </Step>
-  
+
   <Step title="Safety Validation">
     Safety gate validates syntax and checks for issues
   </Step>
-  
+
   <Step title="Presentation">
     Suggestions presented with explanations and risk scores
   </Step>
@@ -158,10 +158,10 @@ AI-powered refactoring suggests:
 # AI-suggested refactoring
 def process_users(users):
     """Process and filter users based on eligibility criteria.
-    
+
     Args:
         users: List of user objects to process
-        
+
     Returns:
         List of eligible users (adult, active, verified)
     """
@@ -202,21 +202,21 @@ refactron suggest myfile.py --line 42 --apply
 <AccordionGroup>
   <Accordion title="Groq (Recommended)" icon="bolt">
     Fast, cloud-based LLM provider with free tier
-    
+
     **Models:**
     - `llama3-70b-8192` - Best quality
     - `llama3-8b-8192` - Faster, good quality
     - `mixtral-8x7b-32768` - Long context window
-    
+
     **Setup:**
     ```bash
     export GROQ_API_KEY='your-key'
     ```
   </Accordion>
-  
+
   <Accordion title="Custom Providers" icon="gear">
     Bring your own LLM provider
-    
+
     Configure in `.refactron.yaml`:
     ```yaml
     llm:
@@ -301,19 +301,19 @@ refactron feedback <operation-id> --action rejected --reason "Breaks API contrac
   <Accordion title="Keep Index Updated">
     Re-run `refactron rag index` after significant code changes for accurate context
   </Accordion>
-  
+
   <Accordion title="Use Higher-Parameter Models">
     Models like Llama 3 70B provide better refactoring logic than smaller models
   </Accordion>
-  
+
   <Accordion title="Always Preview AI Suggestions">
     Use `--preview` to review AI-generated code before applying
   </Accordion>
-  
+
   <Accordion title="Provide Feedback">
     Record feedback to improve AI suggestions over time
   </Accordion>
-  
+
   <Accordion title="Test After Applying">
     Run your test suite after applying AI refactorings
   </Accordion>
@@ -329,14 +329,14 @@ refactron feedback <operation-id> --action rejected --reason "Breaks API contrac
     ```
     Export it in your shell profile for persistence
   </Accordion>
-  
+
   <Accordion title="RAG Index Not Found">
     Create index first:
     ```bash
     refactron rag index
     ```
   </Accordion>
-  
+
   <Accordion title="Slow AI Responses">
     - Use smaller models (llama3-8b-8192)
     - Reduce `max_tokens`