fix: Increase MCP sampling timeout to 5 minutes for slower LLMs

- Increase sampling timeout from 30s to 300s in semantic.py to accommodate
  slower local LLMs like Ollama
- Refactor RAG integration tests to support multiple providers (ollama,
  openai, anthropic, bedrock)
- Remove unnecessary embedding_provider fixture since MCP server handles
  embeddings internally
- Add --provider flag via tests/integration/conftest.py
- Add provider_fixtures.py with factory functions for generation providers

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

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

tests/integration/conftest.py

@@ -0,0 +1,26 @@
+"""Pytest configuration for integration tests.
+
+This conftest.py provides hooks and fixtures specific to integration tests,
+including the --provider flag for RAG tests.
+"""
+
+# Valid provider names
+VALID_PROVIDERS = ["openai", "ollama", "anthropic", "bedrock"]
+
+
+def pytest_addoption(parser):
+    """Add --provider command line option for RAG tests."""
+    parser.addoption(
+        "--provider",
+        action="store",
+        default=None,
+        choices=VALID_PROVIDERS,
+        help="LLM provider for RAG tests: openai, ollama, anthropic, bedrock",
+    )
+
+
+def pytest_configure(config):
+    """Configure custom markers."""
+    config.addinivalue_line(
+        "markers", "rag: mark test as RAG integration test (requires --provider flag)"
+    )