test: 125 simulated user scenarios for plan + suggestions

Exercises the real code paths with realistic inputs:

- 84 phrase classification scenarios: approval (20), rejection (24),
  refinement (16), qualifier overrides (12), word boundary (12)
- 13 warehouse suggestion configs: 8 warehouse types x indexed/dbt/multi
- 8 progressive disclosure chains: full progression, dedup, interleaved
- 6 revision cap simulations: mixed actions, all rejections, cap behavior
- 5 performance stress: 10k classifications < 500ms, determinism checks
- 10 adversarial: unicode lookalikes, 50KB, SQL injection, null bytes

All 125 pass in 255ms.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: anandgupta42