feat: LinkedIn LLM alignment - Phase 1-3 complete

Phase 1: Dead Code Cleanup
- Remove GeminiGroundedProvider import and property from linkedin_service.py
- Remove fallback_provider property (gemini_provider imports)
- Fix routers/linkedin.py edit endpoint to use llm_text_gen
- Delete dead LinkedInImageEditor class
- Remove dead _transform_gemini_sources from content_generator.py

Phase 2: Research Infrastructure Alignment
- Add user_id to _conduct_research() for pre-flight validation
- Add validate_exa_research_operations() before Exa/Tavily calls
- Pass user_id to provider.simple_search() for usage tracking
- Inject research content into LLM prompts via _build_research_context()
- Fix Google engine path to fallback to Exa
- Add Exa → Tavily fallback on research failure

Phase 3: Cosmetic Cleanup
- Rename _generate_prompts_with_gemini → _generate_prompts_with_llm
- Rename _build_gemini_prompt → _build_image_prompt
- Rename _parse_gemini_response → _parse_llm_response
- Remove all Gemini references from LinkedIn code (0 remaining)
- Update docstrings and log messages

Additional:
- Research caching using existing ResearchCache
- Shared ExaContentResearchProvider in services/research/
- Persona service uses llm_text_gen instead of gemini_structured_json_response
- LinkedInWriter.tsx ChatMessage → ChatMsg type mapping fix
- RegisterLinkedInActionsEnhanced.tsx content_format_rules typing fix

backend/services/research/__init__.py

@@ -7,6 +7,7 @@ replacing mock research with real-time industry information.
 Available Services:
 - GoogleSearchService: Real-time industry research using Google Custom Search API
 - ExaService: Competitor discovery and analysis using Exa API
+- ExaContentResearchProvider: Shared content research provider for LinkedIn/Blog
 - TavilyService: AI-powered web search with real-time information
 - Source ranking and credibility assessment
 - Content extraction and insight generation
@@ -17,12 +18,13 @@ Core Module (v2.0):
 - ParameterOptimizer: AI-driven parameter optimization
 
 Author: ALwrity Team
-Version: 2.0
-Last Updated: December 2025
+Version: 2.1
+Last Updated: June 2026
 """
 
 from .google_search_service import GoogleSearchService
 from .exa_service import ExaService
+from .exa_content_research import ExaContentResearchProvider, get_exa_content_provider
 from .tavily_service import TavilyService
 
 # Core Research Engine (v2.0)
@@ -43,6 +45,10 @@ __all__ = [
     "ExaService",
     "TavilyService",
     
+    # Shared content research provider
+    "ExaContentResearchProvider",
+    "get_exa_content_provider",
+    
     # Core Research Engine (v2.0)
     "ResearchEngine",
     "ResearchContext",