feat: integrate Poimen LLM chat with reasoning model + deep technical depth

- Terminal: hook to api.riotpiao.com reasoning model with streaming
- Add markdown rendering via react-markdown + typography plugin
- Show thinking spinner (⠋⠙⠹⠸⠼⠴⠦⠧⠇⠏) + V100 32GB context during reasoning
- Interview-style help: cert rotation, Talos, SQS failover, vLLM, exactly-once, deploy root cause, K8s CRD
- Chat route: ultra-compressed caveman prompt (60% token reduction)
  - K8s deep expertise: CRDs, operators, reconciliation, Talos, Cilium
  - Cert management: cert-manager, 30d renewal, SOPS, Git audit trail
  - Multi-region queues: SQS FIFO, exactly-once, QueueTask CRD
  - AWS: CDK, CloudFormation, CloudWatch across 57+ regions
- Remove dark mode toggle button (system preference only)
- Update hire-me.png (dark/light auto-switch)
- Add tailwind typography for prose styling

tailwind.config.ts

@@ -1,4 +1,5 @@
 import type { Config } from 'tailwindcss'
+import typography from '@tailwindcss/typography'
 
 export default {
   content: [
@@ -29,5 +30,5 @@ export default {
       },
     },
   },
-  plugins: [],
+  plugins: [typography],
 } satisfies Config