feat(agent): unify models and validate OpenCode providers

Generate chat, task and learning models from agent-models.json.
Use WaterNetwork fast/expert models with 272k context and validate
upstream names before readiness. Add an isolated model check command
with signal-safe cleanup and plugin, Skill and MCP management docs.

Verified in isolation: type checks, 26 focused tests and both model
catalog checks; no model inference requests.

agent-models.json

@@ -0,0 +1,30 @@
+{
+  "default_model": "waternetwork/gpt-6-luna",
+  "task_model": "waternetwork/gpt-6-luna",
+  "learning_gate_model": "waternetwork/gpt-6-luna",
+  "providers": {
+    "waternetwork": {
+      "name": "WaterNetwork",
+      "api_url": "https://llm.waternetwork.cn/v1",
+      "api_key": "{env:WATERNETWORK_API_KEY}",
+      "models": {
+        "gpt-6-luna": {
+          "name": "快速",
+          "description": "快速回答和日常任务处理",
+          "icon": "bolt",
+          "limit": {
+            "context": 272000
+          }
+        },
+        "gpt-6.1-sol": {
+          "name": "专家",
+          "description": "深入分析和复杂任务处理",
+          "icon": "sparkle",
+          "limit": {
+            "context": 272000
+          }
+        }
+      }
+    }
+  }
+}