feat: Complete Phase 2.5-2.7 - Intelligent LLM-Powered Workflow Analysis

This commit implements three major architectural improvements to transform
Atomizer from static pattern matching to intelligent AI-powered analysis.

## Phase 2.5: Intelligent Codebase-Aware Gap Detection ✅

Created intelligent system that understands existing capabilities before
requesting examples:

**New Files:**
- optimization_engine/codebase_analyzer.py (379 lines)
  Scans Atomizer codebase for existing FEA/CAE capabilities

- optimization_engine/workflow_decomposer.py (507 lines, v0.2.0)
  Breaks user requests into atomic workflow steps
  Complete rewrite with multi-objective, constraints, subcase targeting

- optimization_engine/capability_matcher.py (312 lines)
  Matches workflow steps to existing code implementations

- optimization_engine/targeted_research_planner.py (259 lines)
  Creates focused research plans for only missing capabilities

**Results:**
- 80-90% coverage on complex optimization requests
- 87-93% confidence in capability matching
- Fixed expression reading misclassification (geometry vs result_extraction)

## Phase 2.6: Intelligent Step Classification ✅

Distinguishes engineering features from simple math operations:

**New Files:**
- optimization_engine/step_classifier.py (335 lines)

**Classification Types:**
1. Engineering Features - Complex FEA/CAE needing research
2. Inline Calculations - Simple math to auto-generate
3. Post-Processing Hooks - Middleware between FEA steps

## Phase 2.7: LLM-Powered Workflow Intelligence ✅

Replaces static regex patterns with Claude AI analysis:

**New Files:**
- optimization_engine/llm_workflow_analyzer.py (395 lines)
  Uses Claude API for intelligent request analysis
  Supports both Claude Code (dev) and API (production) modes

- .claude/skills/analyze-workflow.md
  Skill template for LLM workflow analysis integration

**Key Breakthrough:**
- Detects ALL intermediate steps (avg, min, normalization, etc.)
- Understands engineering context (CBUSH vs CBAR, directions, metrics)
- Distinguishes OP2 extraction from part expression reading
- Expected 95%+ accuracy with full nuance detection

## Test Coverage

**New Test Files:**
- tests/test_phase_2_5_intelligent_gap_detection.py (335 lines)
- tests/test_complex_multiobj_request.py (130 lines)
- tests/test_cbush_optimization.py (130 lines)
- tests/test_cbar_genetic_algorithm.py (150 lines)
- tests/test_step_classifier.py (140 lines)
- tests/test_llm_complex_request.py (387 lines)

All tests include:
- UTF-8 encoding for Windows console
- atomizer environment (not test_env)
- Comprehensive validation checks

## Documentation

**New Documentation:**
- docs/PHASE_2_5_INTELLIGENT_GAP_DETECTION.md (254 lines)
- docs/PHASE_2_7_LLM_INTEGRATION.md (227 lines)
- docs/SESSION_SUMMARY_PHASE_2_5_TO_2_7.md (252 lines)

**Updated:**
- README.md - Added Phase 2.5-2.7 completion status
- DEVELOPMENT_ROADMAP.md - Updated phase progress

## Critical Fixes

1. **Expression Reading Misclassification** (lines cited in session summary)
   - Updated codebase_analyzer.py pattern detection
   - Fixed workflow_decomposer.py domain classification
   - Added capability_matcher.py read_expression mapping

2. **Environment Standardization**
   - All code now uses 'atomizer' conda environment
   - Removed test_env references throughout

3. **Multi-Objective Support**
   - WorkflowDecomposer v0.2.0 handles multiple objectives
   - Constraint extraction and validation
   - Subcase and direction targeting

## Architecture Evolution

**Before (Static & Dumb):**
User Request → Regex Patterns → Hardcoded Rules → Missed Steps ❌

**After (LLM-Powered & Intelligent):**
User Request → Claude AI Analysis → Structured JSON →
├─ Engineering (research needed)
├─ Inline (auto-generate Python)
├─ Hooks (middleware scripts)
└─ Optimization (config) ✅

## LLM Integration Strategy

**Development Mode (Current):**
- Use Claude Code directly for interactive analysis
- No API consumption or costs
- Perfect for iterative development

**Production Mode (Future):**
- Optional Anthropic API integration
- Falls back to heuristics if no API key
- For standalone batch processing

## Next Steps

- Phase 2.8: Inline Code Generation
- Phase 2.9: Post-Processing Hook Generation
- Phase 3: MCP Integration for automated documentation research

🚀 Generated with Claude Code

Co-Authored-By: Claude <noreply@anthropic.com>

optimization_engine/plugins/post_extraction/log_results.py

@@ -0,0 +1,74 @@
+"""
+Post-Extraction Logger Plugin
+
+Appends extracted results and final trial status to the log.
+"""
+
+from typing import Dict, Any, Optional
+from pathlib import Path
+from datetime import datetime
+import logging
+
+logger = logging.getLogger(__name__)
+
+
+def log_extracted_results(context: Dict[str, Any]) -> Optional[Dict[str, Any]]:
+    """
+    Log extracted results to the trial log file.
+
+    Args:
+        context: Hook context containing:
+            - trial_number: Current trial number
+            - design_variables: Dict of variable values
+            - extracted_results: Dict of all extracted objectives and constraints
+            - result_path: Path to result file
+            - working_dir: Current working directory
+    """
+    trial_num = context.get('trial_number', '?')
+    extracted_results = context.get('extracted_results', {})
+    result_path = context.get('result_path', '')
+
+    # Get the output directory from context (passed by runner)
+    output_dir = Path(context.get('output_dir', 'optimization_results'))
+    log_dir = output_dir / 'trial_logs'
+    if not log_dir.exists():
+        logger.warning(f"Log directory not found: {log_dir}")
+        return None
+
+    # Find trial log file
+    log_files = list(log_dir.glob(f'trial_{trial_num:03d}_*.log'))
+    if not log_files:
+        logger.warning(f"No log file found for trial {trial_num}")
+        return None
+
+    # Use most recent log file
+    log_file = sorted(log_files)[-1]
+
+    with open(log_file, 'a') as f:
+        f.write(f"[{datetime.now().strftime('%H:%M:%S')}] POST_EXTRACTION: Results extracted\n")
+        f.write("\n")
+
+        f.write("-" * 80 + "\n")
+        f.write("EXTRACTED RESULTS\n")
+        f.write("-" * 80 + "\n")
+
+        for result_name, result_value in extracted_results.items():
+            f.write(f"  {result_name:30s} = {result_value:12.4f}\n")
+
+        f.write("\n")
+        f.write(f"[{datetime.now().strftime('%H:%M:%S')}] Evaluating constraints...\n")
+        f.write(f"[{datetime.now().strftime('%H:%M:%S')}] Calculating total objective...\n")
+        f.write("\n")
+
+    return {'logged': True}
+
+
+def register_hooks(hook_manager):
+    """Register this plugin's hooks with the manager."""
+    hook_manager.register_hook(
+        hook_point='post_extraction',
+        function=log_extracted_results,
+        description='Log extracted results to trial log',
+        name='log_extracted_results',
+        priority=10
+    )

optimization_engine/plugins/post_extraction/optimization_logger_results.py

@@ -0,0 +1,78 @@
+"""
+Optimization-Level Logger Hook - Results
+
+Appends trial results to the high-level optimization.log file.
+
+Hook Point: post_extraction
+"""
+
+from pathlib import Path
+from datetime import datetime
+from typing import Dict, Any, Optional
+import logging
+
+logger = logging.getLogger(__name__)
+
+
+def log_optimization_results(context: Dict[str, Any]) -> Optional[Dict[str, Any]]:
+    """
+    Append trial results to the main optimization.log file.
+
+    This hook completes the trial entry in the high-level log with:
+    - Objective values
+    - Constraint evaluations
+    - Trial outcome (feasible/infeasible)
+
+    Args:
+        context: Hook context containing:
+            - trial_number: Current trial number
+            - extracted_results: Dict of all extracted objectives and constraints
+            - result_path: Path to result file
+
+    Returns:
+        None (logging only)
+    """
+    trial_num = context.get('trial_number', '?')
+    extracted_results = context.get('extracted_results', {})
+    result_path = context.get('result_path', '')
+
+    # Get the output directory from context (passed by runner)
+    output_dir = Path(context.get('output_dir', 'optimization_results'))
+    log_file = output_dir / 'optimization.log'
+
+    if not log_file.exists():
+        logger.warning(f"Optimization log file not found: {log_file}")
+        return None
+
+    # Find the last line for this trial and append results
+    with open(log_file, 'a') as f:
+        timestamp = datetime.now().strftime('%H:%M:%S')
+
+        # Extract objective and constraint values
+        results_str = " | ".join([f"{name}={value:.3f}" for name, value in extracted_results.items()])
+
+        f.write(f"[{timestamp}] Trial {trial_num:3d} COMPLETE | {results_str}\n")
+
+    return None
+
+
+def register_hooks(hook_manager):
+    """
+    Register this plugin's hooks with the manager.
+
+    This function is called automatically when the plugin is loaded.
+    """
+    hook_manager.register_hook(
+        hook_point='post_extraction',
+        function=log_optimization_results,
+        description='Append trial results to optimization.log',
+        name='optimization_logger_results',
+        priority=100
+    )
+
+
+# Hook metadata
+HOOK_NAME = "optimization_logger_results"
+HOOK_POINT = "post_extraction"
+ENABLED = True
+PRIORITY = 100