refactor: Convert Tanzu provider to declarative JSON config (#7124)

Signed-off-by: Nick Kuhn <nick.kuhn@broadcom.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

crates/goose/src/providers/declarative/tanzu.json

@@ -0,0 +1,21 @@
+{
+  "name": "tanzu_ai",
+  "engine": "openai",
+  "display_name": "Tanzu AI Services",
+  "description": "Enterprise-managed LLM access through VMware Tanzu Platform AI Services",
+  "api_key_env": "TANZU_AI_API_KEY",
+  "base_url": "${TANZU_AI_ENDPOINT}/openai/v1/chat/completions",
+  "env_vars": [
+    {
+      "name": "TANZU_AI_ENDPOINT",
+      "required": true,
+      "secret": false,
+      "description": "Your Tanzu AI Services endpoint URL"
+    }
+  ],
+  "dynamic_models": true,
+  "models": [
+    { "name": "openai/gpt-oss-120b", "context_limit": 131072 }
+  ],
+  "supports_streaming": false
+}