feat: simplify Discover view into socket cards & backend upgrades

backend/services/caps.py

@@ -115,6 +115,10 @@ def capabilities(name: str = "", cmd: str = "", gguf_path: str = "", hf: dict |
         m = re.search(r"-(?:c|-ctx-size)\s+(\d+)", cmdl)
         ctx = int(m.group(1)) if m else None
 
+    # Cap context length at 131072 for Qwen / Hermes models to prevent reporting scaled RoPE context of 256k+ which might OOM or be unstable.
+    if ctx and ctx > 131072 and ("qwen" in low or "hermes" in low):
+        ctx = 131072
+
     tool_confirmed = "--jinja" in cmdl or "tool_call" in chat_tpl or "<tools>" in chat_tpl
     tool_family = any(fam in low for fam in _TOOL_FAMILIES) or "function-calling" in tags
     tools = "yes" if tool_confirmed else ("likely" if tool_family else "no")