fix(hwfit): filter non-GGUF models on Windows (#2530)

Odysseus only supports llama.cpp on Windows (vLLM/SGLang are
explicitly blocked). llama.cpp requires GGUF, so AWQ/GPTQ/FP8
safetensors models without a GGUF alternate should not be
recommended in the Cookbook on Windows hosts.

Changes:
- hardware.py: add 'platform': 'windows' to _detect_windows()
  so downstream logic can identify Windows hosts.
- fit.py: include is_windows in the existing GGUF-only filter
  alongside apple_silicon and consumer_amd.
- tests: add test_hwfit_windows.py with regression tests.

Fixes #122, #614 (root cause: unservable models recommended).

services/hwfit/hardware.py

@@ -539,6 +539,7 @@ def _detect_windows():
             "backend": d.get("gpu_backend", "cpu_x86"),
             "homogeneous": True,
             "gpu_error": None,
+            "platform": "windows",
         }
         # PowerShell only reports aggregate GPU info, not per-card detail, so we
         # can't tell a mixed box from a uniform one here — assume one homogeneous