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_stiffness_optimization/2_results/optimization_summary.json

@@ -0,0 +1,41 @@
+{
+  "study_name": "bracket_stiffness_optimization",
+  "optimizer": "Protocol 10 - Intelligent Multi-Strategy",
+  "n_trials": 30,
+  "completed_trials": 30,
+  "feasible_trials": 18,
+  "infeasible_trials": 12,
+  "pruned_trials": 0,
+  "failed_trials": 0,
+  "elapsed_seconds": 0.462249,
+  "pareto_front_all": 16,
+  "pareto_front_feasible": 14,
+  "best_solution": {
+    "best_params": {
+      "support_angle": 65.24559155460827,
+      "tip_thickness": 27.09745933355004
+    },
+    "best_value": [
+      -14910.194937824257,
+      0.11645991891270796
+    ],
+    "best_trial": 10,
+    "is_multi_objective": true,
+    "pareto_front_size": 16,
+    "total_trials": 30,
+    "final_strategy": "random",
+    "landscape_analysis": null,
+    "strategy_recommendation": {
+      "confidence": 1.0,
+      "reasoning": "Insufficient data (30 trials) - using random exploration for landscape characterization",
+      "sampler_config": {
+        "type": "RandomSampler",
+        "params": {}
+      }
+    },
+    "transition_history": [],
+    "strategy_performance": {},
+    "protocol_used": "Protocol 10: Intelligent Multi-Strategy Optimization"
+  },
+  "timestamp": "2025-11-21T14:51:42.557284"
+}