Fix entity extraction parsing to handle brackets and quotes

CRITICAL FIX: Entity extraction was returning empty results

Issue: New comprehensive prompt returns lists with brackets like:
DRUGS: [Ianalumab, VAY736, ...]
But old parser expected: DRUGS: Ianalumab, VAY736

Fix:
- Strip brackets: drugs.strip('[]')
- Strip quotes: .strip('"\'')
- Filter empty values: if d.strip()
- Handle missing SEARCH_TERMS with fallback

This fixes the bug where "Ianalumab for Sjogren's" returned 0 entities
and searched irrelevant trials (vaping, HIV, etc.)

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

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

foundation_engine.py

@@ -1118,22 +1118,29 @@ Be expansive - more synonyms mean better trial matching."""
             line = line.strip()
             if line.startswith('DRUGS:'):
                 drugs = line.replace('DRUGS:', '').strip()
-                if drugs.lower() != 'none':
-                    result['drugs'] = [d.strip() for d in drugs.split(',')]
+                # Remove brackets if present: [item1, item2] → item1, item2
+                drugs = drugs.strip('[]')
+                if drugs and drugs.lower() != 'none':
+                    result['drugs'] = [d.strip().strip('"\'') for d in drugs.split(',') if d.strip()]
             elif line.startswith('DISEASES:'):
                 diseases = line.replace('DISEASES:', '').strip()
-                if diseases.lower() != 'none':
-                    result['diseases'] = [d.strip() for d in diseases.split(',')]
+                diseases = diseases.strip('[]')
+                if diseases and diseases.lower() != 'none':
+                    result['diseases'] = [d.strip().strip('"\'') for d in diseases.split(',') if d.strip()]
             elif line.startswith('COMPANIES:'):
                 companies = line.replace('COMPANIES:', '').strip()
-                if companies.lower() != 'none':
-                    result['companies'] = [c.strip() for c in companies.split(',')]
+                companies = companies.strip('[]')
+                if companies and companies.lower() != 'none':
+                    result['companies'] = [c.strip().strip('"\'') for c in companies.split(',') if c.strip()]
             elif line.startswith('ENDPOINTS:'):
                 endpoints = line.replace('ENDPOINTS:', '').strip()
-                if endpoints.lower() != 'none':
-                    result['endpoints'] = [e.strip() for e in endpoints.split(',')]
+                endpoints = endpoints.strip('[]')
+                if endpoints and endpoints.lower() != 'none':
+                    result['endpoints'] = [e.strip().strip('"\'') for e in endpoints.split(',') if e.strip()]
             elif line.startswith('SEARCH_TERMS:'):
-                result['search_terms'] = line.replace('SEARCH_TERMS:', '').strip()
+                terms = line.replace('SEARCH_TERMS:', '').strip()
+                terms = terms.strip('[]')
+                result['search_terms'] = terms if terms else query
 
         logger.info(f"[QUERY PARSER] ✓ Drugs: {result['drugs']}, Diseases: {result['diseases']}, Companies: {result['companies']}")
         return result