feat: Add dashboard chat integration and MCP server

Major changes:
- Dashboard: WebSocket-based chat with session management
- Dashboard: New chat components (ChatPane, ChatInput, ModeToggle)
- Dashboard: Enhanced UI with parallel coordinates chart
- MCP Server: New atomizer-tools server for Claude integration
- Extractors: Enhanced Zernike OPD extractor
- Reports: Improved report generator

New studies (configs and scripts only):
- M1 Mirror: Cost reduction campaign studies
- Simple Beam, Simple Bracket, UAV Arm studies

Note: Large iteration data (2_iterations/, best_design_archive/)
excluded via .gitignore - kept on local Gitea only.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

studies/Simple_Bracket/bracket_pareto_3obj/STUDY_REPORT.md

@@ -0,0 +1,60 @@
+# Study Report: bracket_pareto_3obj
+
+**Status**: Not Started
+**Created**: 2025-12-06 14:43
+**Last Updated**: 2025-12-06 14:43
+
+---
+
+## 1. Optimization Progress
+
+| Metric | Value |
+|--------|-------|
+| Total Trials | 0 |
+| Successful Trials | 0 |
+| Best Objective | - |
+| Duration | - |
+
+---
+
+## 2. Best Solutions
+
+*No optimization runs completed yet.*
+
+---
+
+## 3. Pareto Front (if multi-objective)
+
+*No Pareto front generated yet.*
+
+---
+
+## 4. Design Variable Sensitivity
+
+*Analysis pending optimization runs.*
+
+---
+
+## 5. Constraint Satisfaction
+
+*Analysis pending optimization runs.*
+
+---
+
+## 6. Recommendations
+
+*Recommendations will be added after optimization runs.*
+
+---
+
+## 7. Next Steps
+
+1. [ ] Run `python run_optimization.py --discover`
+2. [ ] Run `python run_optimization.py --validate`
+3. [ ] Run `python run_optimization.py --test`
+4. [ ] Run `python run_optimization.py --run --trials 100`
+5. [ ] Analyze results and update this report
+
+---
+
+*Generated by StudyWizard*