616 B
616 B
DEPRECATED
This framework is kept for backward compatibility but is scheduled for removal.
Why It's Deprecated
- Narrow scope: Tests diff schema compliance, not general model capability
- Better alternatives:
cline-benchprovides real-world task evaluation - Maintenance burden: Requires manual test case generation from conversations
If You're Using This
Contact @ara or @robin before this gets removed. We can help migrate your use case to the smoke tests or cline-bench framework.
Removal Timeline
Target: Q2 2026 (or when cline-bench is fully operational for model comparison)