fix: rename generation model setting to ollama_llm_model to avoid OLLAMA_MODEL env collision

The deployed container sets OLLAMA_MODEL=nomic-embed-text for embeddings,
which shadowed the generation-model setting and broke Phase 0 keyword
extraction and Phase 4 LLM re-ranking on every request. The setting is now
ollama_llm_model (env: OLLAMA_LLM_MODEL, default gemma4:e2b), startup logs
the resolved generation model, and Phase 0/Phase 4 LLM calls are wrapped in
a 12s asyncio.wait_for with graceful fallback so a hung call cannot gate
retrieval for the full 120s client timeout.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

src/config.py

@@ -66,7 +66,9 @@ class Settings(BaseSettings):
 
     # Ollama Configuration
     ollama_url: str = Field(default="http://ollama:11434", description="Ollama URL")
-    ollama_model: str = Field(default="mistral-nemo-large:latest", description="Ollama LLM model")
+    # Named ollama_llm_model (env: OLLAMA_LLM_MODEL) to avoid collision with the
+    # OLLAMA_MODEL container env var, which is used for the embedding model.
+    ollama_llm_model: str = Field(default="gemma4:e2b", description="Ollama LLM model for generation (keyword extraction, re-ranking, consolidation)")
     ollama_embedding_model: str = Field(default="nomic-embed-text", description="Ollama embedding model")
 
     # HybridRAG Configuration