feat: Implement Study Interview Mode as default study creation method

Study Interview Mode is now the DEFAULT for all study creation requests.
This intelligent Q&A system guides users through optimization setup with:

- 7-phase interview flow: introspection → objectives → constraints → design_variables → validation → review → complete
- Material-aware validation with 12 materials and fuzzy name matching
- Anti-pattern detection for 12 common mistakes (mass-no-constraint, stress-over-yield, etc.)
- Auto extractor mapping E1-E24 based on goal keywords
- State persistence with JSON serialization and backup rotation
- StudyBlueprint generation with full validation

Triggers: "create a study", "new study", "optimize this", any study creation intent
Skip with: "skip interview", "quick setup", "manual config"

Components:
- StudyInterviewEngine: Main orchestrator
- QuestionEngine: Conditional logic evaluation
- EngineeringValidator: MaterialsDatabase + AntiPatternDetector
- InterviewPresenter: Markdown formatting for Claude
- StudyBlueprint: Validated configuration output
- InterviewState: Persistent state management

All 129 tests passing.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

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

knowledge_base/lac/session_insights/failure.jsonl

@@ -6,3 +6,4 @@
 {"timestamp":"2025-12-28T17:30:00","category":"failure","context":"V5 turbo optimization created from scratch instead of copying V4. Multiple critical components were missing or wrong: no license server, wrong extraction keys (filtered_rms_nm vs relative_filtered_rms_nm), wrong mfg_90 key, missing figure_path parameter, incomplete version regex.","insight":"STUDY DERIVATION FAILURE: When creating a new study version (V5 from V4), NEVER rewrite the run_optimization.py from scratch. ALWAYS copy the working version first, then add/modify only the new feature (e.g., L-BFGS polish). Rewriting caused 5 independent bugs: (1) missing LICENSE_SERVER setup, (2) wrong extraction key filtered_rms_nm instead of relative_filtered_rms_nm, (3) wrong mfg_90 key, (4) missing figure_path=None in extractor call, (5) incomplete version regex missing DesigncenterNX pattern. The FEA/extraction pipeline is PROVEN CODE - never rewrite it. Only add new optimization strategies as modules on top.","confidence":1.0,"tags":["study-creation","copy-dont-rewrite","extraction","license-server","v5","critical"],"severity":"critical","rule":"When deriving a new study version, COPY the entire working run_optimization.py first. Add new features as ADDITIONS, not rewrites. The FEA pipeline (license, NXSolver setup, extraction) is proven - never rewrite it."}
 {"timestamp":"2025-12-28T21:30:00","category":"failure","context":"V5 flat back turbo optimization with MLP surrogate + L-BFGS polish. Surrogate predicted WS~280 but actual FEA gave WS~365-377. Error of 85-96 (30%+ relative error). All L-BFGS solutions converged to same fake optimum that didn't exist in reality.","insight":"SURROGATE + L-BFGS FAILURE MODE: Gradient-based optimization on MLP surrogates finds 'fake optima' that don't exist in real FEA. The surrogate has smooth gradients everywhere, but L-BFGS descends to regions OUTSIDE the training distribution where predictions are wildly wrong. V5 results: (1) Best TPE trial: WS=290.18, (2) Best L-BFGS trial: WS=325.27, (3) Worst L-BFGS trials: WS=376.52. The fancy L-BFGS polish made results WORSE than random TPE. Key issues: (a) No uncertainty quantification - can't detect out-of-distribution, (b) No mass constraint in surrogate - L-BFGS finds infeasible designs (122-124kg vs 120kg limit), (c) L-BFGS converges to same bad point from multiple starting locations (trials 31-44 all gave WS=376.52).","confidence":1.0,"tags":["surrogate","mlp","lbfgs","gradient-descent","fake-optima","out-of-distribution","v5","turbo"],"severity":"critical","rule":"NEVER trust gradient descent on surrogates without: (1) Uncertainty quantification to reject OOD predictions, (2) Mass/constraint prediction to enforce feasibility, (3) Trust-region to stay within training distribution. Pure TPE with real FEA often beats surrogate+gradient methods."}
 {"timestamp": "2025-12-29T15:29:55.869508", "category": "failure", "context": "Trial 5 solver error", "insight": "convergence_failure: Convergence failure at iteration 100", "confidence": 0.7, "tags": ["solver", "convergence_failure", "automatic"]}
+{"timestamp": "2026-01-01T21:06:37.877252", "category": "failure", "context": "V13 optimization had 45 FEA failures (34% failure rate)", "insight": "rib_thickness parameter has CAD geometry constraint at ~9mm. All trials with rib_thickness > 9.0 failed. Set max to 9.0 (was 12.0). This is a critical CAD constraint not documented anywhere - the NX model geometry breaks with thicker radial ribs.", "confidence": 0.95, "tags": ["m1_mirror", "cad_constraint", "rib_thickness", "V13", "parameter_bounds"]}