feat: Dashboard improvements and configuration updates

Dashboard:
- Enhanced terminal components (ClaudeTerminal, GlobalClaudeTerminal)
- Improved MarkdownRenderer for better documentation display
- Updated convergence plots (ConvergencePlot, PlotlyConvergencePlot)
- Refined Home, Analysis, Dashboard, Setup, Results pages
- Added StudyContext improvements
- Updated vite.config for better dev experience

Configuration:
- Updated CLAUDE.md with latest instructions
- Enhanced launch_dashboard.py
- Updated config.py settings

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

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

CLAUDE.md

@@ -18,7 +18,7 @@ On **EVERY new Claude session**, perform these initialization steps:
 1. Read `.claude/ATOMIZER_CONTEXT.md` for unified context (if not already loaded via this file)
 2. This file (CLAUDE.md) provides system instructions
 3. Use `.claude/skills/00_BOOTSTRAP.md` for task routing
-4. Check `knowledge_base/lac/` for relevant prior learnings (see LAC section below)
+4. **MANDATORY: Read `knowledge_base/lac/session_insights/failure.jsonl`** - Contains critical lessons from past sessions. These are hard-won insights about what NOT to do.
 
 ### Step 2: Detect Study Context
 If working directory is inside a study (`studies/*/`):
@@ -27,16 +27,26 @@ If working directory is inside a study (`studies/*/`):
 3. Summarize study state to user in first response
 
 ### Step 3: Route by User Intent
+
+**CRITICAL: Actually READ the protocol file before executing the task. Don't work from memory.**
+
 | User Keywords | Load Protocol | Subagent Type |
 |---------------|---------------|---------------|
-| "create", "new", "set up" | OP_01, SYS_12 | general-purpose |
-| "run", "start", "trials" | OP_02, SYS_15 | - (direct execution) |
+| "create", "new", "set up" | **READ** OP_01 first, then execute | general-purpose |
+| "run", "start", "trials" | **READ** OP_02 first | - (direct execution) |
 | "status", "progress" | OP_03 | - (DB query) |
 | "results", "analyze", "Pareto" | OP_04 | - (analysis) |
 | "neural", "surrogate", "turbo" | SYS_14, SYS_15 | general-purpose |
 | "NX", "model", "expression" | MCP siemens-docs | general-purpose |
 | "error", "fix", "debug" | OP_06 | Explore |
 
+**Protocol Loading Rule**: When a task matches a protocol (e.g., "create study" → OP_01), you MUST:
+1. Read the protocol file (`docs/protocols/operations/OP_01_CREATE_STUDY.md`)
+2. Extract the checklist/required outputs
+3. Add ALL items to TodoWrite
+4. Execute each item
+5. Mark complete ONLY when all checklist items are done
+
 ### Step 4: Proactive Actions
 - If optimization is running: Report progress automatically
 - If no study context: Offer to create one or list available studies