fix: rewrite title generator to only use user messages; bump background model to qwen2.5:3b

2026-04-07 12:53:33 -04:00
parent b3cf42863a
commit 39e554d938
3 changed files with 31 additions and 20 deletions
@@ -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", "qwen2.5:0.5b")
+    OLLAMA_BACKGROUND_MODEL: str = os.environ.get("OLLAMA_BACKGROUND_MODEL", "qwen2.5:3b")
    # KV cache context window for generation. Keep this as small as practical —
    # a larger context forces more KV cache into CPU RAM, drastically slowing prefill.
    # 16384 covers ~30+ message conversations with our system prompt comfortably.