refactor: make Agent.step()
multi-step
#72
Annotations
5 errors
Test first message contains expected function call and inner monologue
Process completed with exit code 1.
|
Test model can edit core memories
Process completed with exit code 1.
|
Summarize test results
Process completed with exit code 78.
|
Test model uses 'archival_memory_search' to find secret
Process completed with exit code 1.
|
Test model uses external tool correctly
Process completed with exit code 1.
|
Loading