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/runtime/opencode2-config.ts

@@ -1,22 +1,24 @@
 import { readFileSync } from "node:fs";
 import { resolve } from "node:path";
 import { normalizeMcpConfig } from "./mcp-config.js";
+import { compileOpencodeModels, loadAgentModelConfig, type AgentModelConfig } from "../chat/modelConfig.js";
 
 // A conversation Location can be outside the checkout. Load only the trusted
 // service assets explicitly, rather than relying on its current directory.
-export function serviceOpencodeConfig(input: Record<string, unknown>) {
+export function serviceOpencodeConfig(input: Record<string, unknown>, models: AgentModelConfig = loadAgentModelConfig()) {
   const agents = (input.agents ?? {}) as Record<string, unknown>;
   const instruction = (agents.instruction ?? {}) as Record<string, unknown>;
   const system = readFileSync(resolve(".opencode/agents/instruction.md"), "utf8")
     .replace(/^---\s*\n[\s\S]*?\n---\s*\n/, "");
   return {
     ...input,
+    ...compileOpencodeModels(models),
     snapshots: false,
     mcp: normalizeMcpConfig(input.mcp),
     plugins: ["*", ...((input.plugins ?? []) as unknown[]), resolve(".opencode/tjwater-plugin")],
     skills: [resolve(process.env.OPENCODE_SKILLS_ROOT_DIR ?? ".opencode/skills")],
     agents: { ...agents, instruction: {
-      description: "TJWater structured data and UI agent", mode: "primary", ...instruction, system,
+      description: "TJWater structured data and UI agent", mode: "primary", ...instruction, model: models.default_model, system,
     } },
   };
 }