feat(models): add langchain-ollama for native Ollama thinking support (#2062)

Add langchain-ollama as an optional dependency and provide ChatOllama
config examples, enabling proper thinking/reasoning content preservation
for local Ollama models.

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

backend/packages/harness/pyproject.toml

@@ -36,6 +36,7 @@ dependencies = [
 ]
 
 [project.optional-dependencies]
+ollama = ["langchain-ollama>=0.3.0"]
 pymupdf = ["pymupdf4llm>=0.0.17"]
 
 [build-system]