Fix HF 410: always use router.huggingface.co for all models

api-inference.huggingface.co is deprecated (HTTP 410).
All three services (ai_analyst, ch_ai_trader, dashboard) now
route every model through router.huggingface.co.

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

ai_analyst/ai_analyst.py

@@ -90,10 +90,7 @@ def call_llm(prompt: str) -> str | None:
         if not HF_TOKEN:
             return None
         m = model or HF_MODEL
-        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"
+        url = "https://router.huggingface.co/v1/chat/completions"
         print(f"[AI-Analyst] Calling HF: model={m}")
         for attempt in range(3):
             try:

clearing_house/ch_ai_trader.py

@@ -434,10 +434,7 @@ def _try_groq(prompt: str) -> Optional[str]:
 def _try_hf(prompt: str) -> Optional[str]:
     if not HF_TOKEN:
         return None
-    if HF_MODEL.startswith("RayMelius/"):
-        url = f"https://api-inference.huggingface.co/models/{HF_MODEL}/v1/chat/completions"
-    else:
-        url = "https://router.huggingface.co/v1/chat/completions"
+    url = "https://router.huggingface.co/v1/chat/completions"
     try:
         resp = requests.post(
             url,

dashboard/dashboard.py

@@ -144,11 +144,7 @@ def _call_llm(prompt, force_provider=None, force_model=None):
         if not HF_TOKEN:
             return None, "HuggingFace not configured (HF_TOKEN not set)"
         m = model or HF_MODEL
-        # Use direct inference API for any org/model format; router for bare model names
-        if "/" in m:
-            url = f"https://api-inference.huggingface.co/models/{m}/v1/chat/completions"
-        else:
-            url = HF_URL
+        url = HF_URL
         print(f"[Dashboard/LLM] Calling HF ({m})...")
         for attempt in range(3):
             try: