feat: unify text encoder selection across H3 variants (#2340)

examples/server/recipes/minimax-h3-fl2va.json

@@ -3,7 +3,7 @@
   "id": "minimax-h3-fl2va",
   "name": "MiniMax H3 FL2VA",
   "size_multiple": 32,
-  "description": "Generate video and audio, optionally with start/end images. Supports full and pruned FL2VA weights. Audio VAE is optional for silent video.",
+  "description": "Generate video and audio, optionally with start/end images. Supports full and pruned FL2VA weights with either the MiniMax-H3 Qwen3-VL-32B text encoder or Qwen3-VL-4B with the P-H3 text connector. Audio VAE is optional for silent video.",
   "model_url": "https://huggingface.co/MiniMaxAI/MiniMax-H3",
   "slots": [
     {
@@ -13,7 +13,17 @@
     {
       "id": "llm",
       "required": true,
-      "label": "MiniMax-H3 Qwen 3 VL 32B Text Encoder"
+      "label": "MiniMax-H3 Qwen 3 VL 32B or P-H3 Qwen 3 VL 4B Text Encoder"
+    },
+    {
+      "id": "llm_vision",
+      "required": false,
+      "label": "Vision tower (when not included in the text encoder)"
+    },
+    {
+      "id": "embeddings_connectors",
+      "required": false,
+      "label": "P-H3 Text Connector (for Qwen 3 VL 4B, when not included in the text encoder)"
     },
     {
       "id": "vae",