feat(ovsm): improve error messages with specific details

Previously, tokenization and parse errors showed generic messages:
- ❌ "Failed to tokenize OVSM code"
- ❌ "Failed to parse OVSM code"

Now shows the actual underlying error:
- ✅ "Tokenization error: Syntax error at line 1, column 2: Unexpected character: #"
- ✅ "Parse error: Unexpected token: expected Expected THEN or '{' after IF condition, got Newline"

This makes debugging MUCH easier by showing exactly where and what went wrong!

Example:
```ovsm
IF $x > 5
    $y = 10
```

Before: "Failed to parse OVSM code"
After: "Parse error: expected THEN or '{' after IF condition, got Newline"

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

Co-Authored-By: Claude <[email protected]>

Author: 0xrinegade

src/services/ovsm_service.rs

@@ -72,15 +72,15 @@ impl OvsmService {
         let mut scanner = Scanner::new(code);
         let tokens = scanner
             .scan_tokens()
-            .context("Failed to tokenize OVSM code")?;
+            .map_err(|e| anyhow::anyhow!("Tokenization error: {}", e))?;
 
         if self.debug {
             println!("✅ Tokenization successful ({} tokens)", tokens.len());
         }
 
         // Parse the tokens into an AST
         let mut parser = Parser::new(tokens);
-        let program = parser.parse().context("Failed to parse OVSM code")?;
+        let program = parser.parse().map_err(|e| anyhow::anyhow!("Parse error: {}", e))?;
 
         if self.debug {
             println!("✅ Parsing successful");