refactor: revamp ultrabrain category with deep work mindset

- Add variant: max to ultrabrain's gemini-3-pro fallback entry
- Rename STRATEGIC_CATEGORY_PROMPT_APPEND to ULTRABRAIN_CATEGORY_PROMPT_APPEND
- Keep original strategic advisor prompt content (no micromanagement instructions)
- Update description: use only for genuinely hard tasks, give clear goals only
- Update tests to match renamed constant

src/shared/model-requirements.ts

@@ -90,7 +90,7 @@ export const CATEGORY_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
     fallbackChain: [
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2-codex", variant: "xhigh" },
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5", variant: "max" },
-      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro" },
+      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro", variant: "max" },
     ],
   },
   artistry: {