Add AI debug logging and switch from fetch to https module

- Add toggle-able debug logging (AI_DEBUG env var) that logs prompts,
  request metadata, raw responses, parsed output, and full error chains
- Replace Node.js native fetch() with https module for Docker Alpine
  compatibility (fixes "fetch failed" error with large payloads)
- Reduce max_tokens from 16384 to 4096 (qwen3.5 doesn't need thinking
  token budget)
- Strip <think> blocks from model responses
- Add AI_DEBUG to docker-compose.yml and .env.example

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

docker-compose.yml

@@ -25,6 +25,7 @@ services:
       - AI_API_URL=${AI_API_URL}
       - AI_API_KEY=${AI_API_KEY}
       - AI_MODEL=${AI_MODEL}
+      - AI_DEBUG=${AI_DEBUG:-false}
     volumes:
       - ./backend/src:/app/src
       - ./backend/nest-cli.json:/app/nest-cli.json