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/persona/linkedin/linkedin_persona_service.py

@@ -1,12 +1,13 @@
 """
 LinkedIn Persona Service
 Handles LinkedIn-specific persona generation and optimization.
+Uses provider-agnostic llm_text_gen for LLM access.
 """
 
 from typing import Dict, Any, Optional
 from loguru import logger
 
-from services.llm_providers.gemini_provider import gemini_structured_json_response
+from services.llm_providers.main_text_generation import llm_text_gen
 from .linkedin_persona_prompts import LinkedInPersonaPrompts
 from .linkedin_persona_schemas import LinkedInPersonaSchemas
 
@@ -57,14 +58,15 @@ class LinkedInPersonaService:
             # Extract user_id for tracking
             user_id = onboarding_data.get("session_info", {}).get("user_id")
             
-            # Generate structured response using Gemini with optimized prompts
-            response = gemini_structured_json_response(
+            # Generate structured response using provider-agnostic gateway
+            response = llm_text_gen(
                 prompt=prompt,
-                schema=schema,
-                temperature=0.2,
-                max_tokens=4096,
+                json_struct=schema,
                 system_prompt=system_prompt,
-                user_id=user_id
+                user_id=user_id,
+                flow_type="linkedin_persona_generation",
+                max_tokens=4096,
+                temperature=0.2
             )
             
             if "error" in response: