Add comprehensive tests for tokenizer, performance benchmarks, and TreeSitter parser functionality

- Implemented unit tests for the Tokenizer class, covering various text inputs, edge cases, and fallback mechanisms.
- Created performance benchmarks comparing tiktoken and pure Python implementations for token counting.
- Developed extensive tests for TreeSitterSymbolParser across Python, JavaScript, and TypeScript, ensuring accurate symbol extraction and parsing.
- Added configuration documentation for MCP integration and custom prompts, enhancing usability and flexibility.
- Introduced a refactor script for GraphAnalyzer to streamline future improvements.

ccw/src/templates/dashboard-css/04-lite-tasks.css

@@ -1022,6 +1022,16 @@
   overflow: hidden;
 }
 
+.diagnosis-card .collapsible-content {
+  display: block;
+  padding: 1rem;
+  background: hsl(var(--card));
+}
+
+.diagnosis-card .collapsible-content.collapsed {
+  display: none;
+}
+
 .diagnosis-header {
   background: hsl(var(--muted) / 0.3);
 }