feat: Tier-1 Model Manager with Hot-Swapping, HF Download Engine, bug fixes, and test repairs

- Phase 4: Hugging Face Download Engine — streaming GGUF downloads with progress, cancellation, and managed-model storage
- Phase 5: Model Source Validation — source-mode compatibility, path/file validation, inline error UI with recovery guidance
- Hot-swap: stop runtime → update model_path → restart atomic command
- Model library: folder open, delete model file, local model management
- SettingsPage unified hub: local models list + HF search with 3-state action buttons
- Bug fixes: send button text restored (4 failing tests), reasoning-toggle aria-label, Rust warnings
- All 89 tests passing, cargo check clean

vendor/llama-runtime/manifest.json

@@ -0,0 +1,48 @@
+{
+  "release": "b8358",
+  "variants": [
+    {
+      "id": "windows-x64-cpu",
+      "target": "windows-x86_64",
+      "gpu": false,
+      "dll": "llama.dll",
+      "archives": [
+        {
+          "url": "https://github.com/ggml-org/llama.cpp/releases/download/b8358/llama-b8358-bin-win-cpu-x64.zip",
+          "sha256": "bb78ff8d7e9b53c36fe4cc845f8a479017f97bf5fd99a9a047b45c9c36b93810",
+          "size": 37300696
+        }
+      ],
+      "required_files": [
+        "llama.dll",
+        "ggml.dll",
+        "ggml-base.dll"
+      ]
+    },
+    {
+      "id": "windows-x64-cuda-12.4",
+      "target": "windows-x86_64",
+      "gpu": true,
+      "dll": "llama.dll",
+      "archives": [
+        {
+          "url": "https://github.com/ggml-org/llama.cpp/releases/download/b8358/llama-b8358-bin-win-cuda-12.4-x64.zip",
+          "sha256": "92c0c30401e7284fd28836b112ffa752b3beb7d89786e0c87e378f478b973e48",
+          "size": 226836797
+        },
+        {
+          "url": "https://github.com/ggml-org/llama.cpp/releases/download/b8358/cudart-llama-bin-win-cuda-12.4-x64.zip",
+          "sha256": "8c79a9b226de4b3cacfd1f83d24f962d0773be79f1e7b75c6af4ded7e32ae1d6",
+          "size": 391443627
+        }
+      ],
+      "required_files": [
+        "llama.dll",
+        "ggml.dll",
+        "ggml-base.dll",
+        "ggml-cuda.dll",
+        "cudart64_12.dll"
+      ]
+    }
+  ]
+}