Add Opencode config. This was mostly done with big pickle but when I ran out of tokens, I switched to Qwen3.5 35B

opencode.json

@@ -0,0 +1,25 @@
+{
+  "$schema": "https://opencode.ai/config.json",
+  
+  "provider": {
+    "ollama": {
+      "npm": "@ai-sdk/openai-compatible",
+      "name": "Local Llama-server",
+      "options": {
+          "baseURL": "http://llamaserver:8080/v1"
+      },
+      "models": {
+        "Qwen3.5-35B-A3B": {
+          "name": "Qwen3.5 35B-A3B"
+        }
+      }
+    },
+    "aws": {
+      "options": {
+        "accessKeyId": "{env:AWS_ACCESS_KEY_ID}",
+        "secretAccessKey": "{env:AWS_SECRET_ACCESS_KEY}",
+        "region": "us-east-1"
+      }
+    }
+  }
+}