Fix HF routing: use router for third-party models, not model-specific endpoint

Only RayMelius/ finetuned models need the direct inference endpoint.
All other org/model format models (e.g. mistralai/Mistral-7B-Instruct-v0.3)
must go through router.huggingface.co which supports chat completions for them.

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

ai_analyst/ai_analyst.py

@@ -90,7 +90,7 @@ def call_llm(prompt: str) -> str | None:
         if not HF_TOKEN:
             return None
         m = model or HF_MODEL
-        if m.startswith("RayMelius/") or "/" in m:
+        if m.startswith("RayMelius/"):
             url = f"https://api-inference.huggingface.co/models/{m}/v1/chat/completions"
         else:
             url = "https://router.huggingface.co/v1/chat/completions"