fix: Change Ollama default URL to host.docker.internal for Docker compatibility

- Changed default Ollama URL from localhost:11434 to host.docker.internal:11434
- This allows Docker containers to connect to Ollama running on the host machine
- Updated in backend services, frontend components, migration scripts, and documentation
- Most users run Archon in Docker but Ollama as a local binary, making this a better default

python/src/server/services/credential_service.py

@@ -475,7 +475,7 @@ class CredentialService:
     def _get_provider_base_url(self, provider: str, rag_settings: dict) -> str | None:
         """Get base URL for provider."""
         if provider == "ollama":
-            return rag_settings.get("LLM_BASE_URL", "http://localhost:11434/v1")
+            return rag_settings.get("LLM_BASE_URL", "http://host.docker.internal:11434/v1")
         elif provider == "google":
             return "https://generativelanguage.googleapis.com/v1beta/openai/"
         return None  # Use default for OpenAI

python/src/server/services/llm_provider_service.py

@@ -203,7 +203,7 @@ async def _get_optimal_ollama_instance(instance_type: str | None = None,
                 return embedding_url if embedding_url.endswith('/v1') else f"{embedding_url}/v1"
 
         # Default to LLM base URL for chat operations
-        fallback_url = rag_settings.get("LLM_BASE_URL", "http://localhost:11434")
+        fallback_url = rag_settings.get("LLM_BASE_URL", "http://host.docker.internal:11434")
         return fallback_url if fallback_url.endswith('/v1') else f"{fallback_url}/v1"
 
     except Exception as e:
@@ -211,11 +211,11 @@ async def _get_optimal_ollama_instance(instance_type: str | None = None,
         # Final fallback to localhost only if we can't get RAG settings
         try:
             rag_settings = await credential_service.get_credentials_by_category("rag_strategy")
-            fallback_url = rag_settings.get("LLM_BASE_URL", "http://localhost:11434")
+            fallback_url = rag_settings.get("LLM_BASE_URL", "http://host.docker.internal:11434")
             return fallback_url if fallback_url.endswith('/v1') else f"{fallback_url}/v1"
         except Exception as fallback_error:
             logger.error(f"Could not retrieve fallback configuration: {fallback_error}")
-            return "http://localhost:11434/v1"
+            return "http://host.docker.internal:11434/v1"
 
 
 async def get_embedding_model(provider: str | None = None) -> str:

python/src/server/services/provider_discovery_service.py

@@ -23,7 +23,7 @@ _provider_cache: dict[str, tuple[Any, float]] = {}
 _CACHE_TTL_SECONDS = 300  # 5 minutes
 
 # Default Ollama instance URL (configurable via environment/settings)
-DEFAULT_OLLAMA_URL = "http://localhost:11434"
+DEFAULT_OLLAMA_URL = "http://host.docker.internal:11434"
 
 # Model pattern detection for dynamic capabilities (no hardcoded model names)
 CHAT_MODEL_PATTERNS = ["llama", "qwen", "mistral", "codellama", "phi", "gemma", "vicuna", "orca"]