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.

src/chat/models.ts

@@ -1,7 +1,7 @@
 import { config } from "../config.js";
 import {
   getAgentModelIds,
-  parseAgentModelOptions,
+  getAgentModelOptions,
   type SupportedModel,
 } from "./modelConfig.js";
 
@@ -11,9 +11,7 @@ export {
   type SupportedModel,
 } from "./modelConfig.js";
 
-export const agentModelOptions = parseAgentModelOptions(
-  config.OPENCODE_MODEL_OPTIONS,
-);
+export const agentModelOptions = getAgentModelOptions(config.MODEL_CONFIG);
 
 export const supportedModels = getAgentModelIds(agentModelOptions);