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/routes/chatStream.ts

@@ -4,6 +4,7 @@ import { createBusinessStageTracker } from "./chatBusinessStages.js";
 
 import { writeLlmRequestAuditLog } from "../audit/llmRequestAudit.js";
 import { type SupportedModel } from "../chat/models.js";
+import { toRuntimeModel } from "../chat/modelConfig.js";
 import { config } from "../config.js";
 import { executionPlanSchema } from "./executionPlan.js";
 import { logger } from "../logger.js";
@@ -104,20 +105,6 @@ const getPermissionTarget = (metadata: unknown) => {
   return undefined;
 };
 
-const toRuntimeModel = (model?: SupportedModel) => {
-  if (!model) {
-    return undefined;
-  }
-  const [providerID, modelID] = model.split("/");
-  if (!providerID || !modelID) {
-    return undefined;
-  }
-  return {
-    providerID,
-    modelID,
-  };
-};
-
 const parseToolOutput = (output: unknown): unknown => {
   if (typeof output !== "string") return output;
   try {