fix(llm): switch default background model to gemma3:4b

qwen2.5:3b produced broken auto-summaries (misspellings, token repetition,
hallucinated topics) — its synthesis ceiling is too low for free-form
summarization. Gemma 3 4B is stronger on summarization at similar size
and still fits comfortably alongside the main chat model in VRAM, so it
preserves the KV-cache-separation strategy that keeps chat TTFT fast.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

src/fabledassistant/config.py

@@ -27,7 +27,7 @@ class Config:
     # Lightweight model for background tasks (title generation, tag suggestions,
     # project summaries, RSS classification). Using a separate model keeps the
     # main model's KV cache intact between user messages, enabling prefix cache hits.
-    OLLAMA_BACKGROUND_MODEL: str = os.environ.get("OLLAMA_BACKGROUND_MODEL", "qwen2.5:3b")
+    OLLAMA_BACKGROUND_MODEL: str = os.environ.get("OLLAMA_BACKGROUND_MODEL", "gemma3:4b")
     # Ollama keep_alive — how long a model stays resident in VRAM after its last
     # request. Main model gets a longer window since it's used interactively;
     # the background model is called sporadically and doesn't need to camp VRAM.