Refactor llm config

modules/pi/agent/models.work.json

@@ -0,0 +1,51 @@
+{
+  "providers": {
+    "sparkl": {
+      "baseUrl": "http://192.168.10.111:8000/v1",
+      "api": "openai-completions",
+      "apiKey": "vllm",
+      "compat": {
+        "supportsDeveloperRole": false,
+        "supportsReasoningEffort": false
+      },
+      "models": [
+        {
+          "id": "Qwen/Qwen3-30B-A3B",
+          "name": "Qwen3 30B A3B (local vLLM)",
+          "reasoning": true,
+          "input": ["text"],
+          "contextWindow": 16384,
+          "maxTokens": 8192,
+          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
+          "compat": {
+            "thinkingFormat": "qwen-chat-template",
+            "maxTokensField": "max_tokens"
+          }
+        }
+      ]
+    },
+    "sparkr": {
+      "baseUrl": "http://192.168.10.110:8000/v1",
+      "api": "openai-completions",
+      "apiKey": "vllm",
+      "compat": {
+        "supportsDeveloperRole": false,
+        "supportsReasoningEffort": false
+      },
+      "models": [
+        {
+          "id": "Qwen/Qwen3-Coder-Next-FP8",
+          "name": "Qwen3 Coder Next FP8 (local vLLM)",
+          "reasoning": false,
+          "input": ["text"],
+          "contextWindow": 262144,
+          "maxTokens": 8192,
+          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
+          "compat": {
+            "maxTokensField": "max_tokens"
+          }
+        }
+      ]
+    }
+  }
+}