progress 235b

pyinfra/framework/compose/homepage/services.yaml

@@ -10,9 +10,21 @@
         description: Local model server (Qwen3-Coder-30B and friends)
         server: localhost-docker
         container: ollama
+        # Built-in `type: ollama` widget is missing on the installed
+        # Homepage version. customapi against /api/ps gives a better
+        # signal anyway: actually-loaded model + its VRAM footprint.
+        # When no model is loaded the models array is empty and fields
+        # render as N/A — that itself is useful state.
         widget:
-          type: ollama
-          url: http://framework:11434
+          type: customapi
+          url: http://host.docker.internal:11434/api/ps
+          refreshInterval: 30000
+          mappings:
+            - field: models.0.name
+              label: Loaded
+            - field: models.0.size_vram
+              label: VRAM
+              format: bytes
 
     - llama.cpp:
         icon: si-llama
@@ -23,18 +35,50 @@
         # No native widget; a ping check confirms liveness.
         widget:
           type: customapi
-          url: http://framework:8080/health
+          url: http://host.docker.internal:8080/health
           refreshInterval: 30000
           mappings:
             - field: status
               label: Status
 
-    - vLLM:
+    - vLLM (Kimi-Linear):
         icon: mdi-server-network
         href: http://framework:8000
-        description: Batched OpenAI-compatible serving (ROCm)
+        description: Batched OpenAI-compatible serving — Kimi-Linear-48B-A3B (long-context)
         server: localhost-docker
-        container: vllm
+        # Actual vLLM container is `kimi-linear` (compose/kimi-linear.yml).
+        # The legacy `vllm` container in compose/vllm.yml is an unused stub.
+        container: kimi-linear
+        widget:
+          type: customapi
+          url: http://host.docker.internal:8000/v1/models
+          refreshInterval: 30000
+          mappings:
+            - field: data.0.id
+              label: Served
+            - field: data.0.max_model_len
+              label: Context
+              format: number
+
+    - ComfyUI:
+        icon: mdi-image-edit
+        href: http://framework:8188
+        description: Image generation (Flux.1-Dev via kyuz0 gfx1151 toolbox)
+        server: localhost-docker
+        container: comfyui
+        # ComfyUI's /system_stats returns nested {system, devices[0]}.
+        # Surfacing version + free VRAM gives a quick "is it healthy
+        # and does it have memory" read at a glance.
+        widget:
+          type: customapi
+          url: http://host.docker.internal:8188/system_stats
+          refreshInterval: 30000
+          mappings:
+            - field: system.comfyui_version
+              label: Version
+            - field: devices.0.vram_free
+              label: VRAM Free
+              format: bytes
 
 - Agent UIs:
     - OpenWebUI: