Back to Agno

Test Log: reliability

cookbook/09_evals/reliability/TEST_LOG.md

2.6.4706 B
Original Source

Test Log: reliability

Tests not yet run. Run each file and update this log.

db_logging.py

Status: PENDING

Description: Runs reliability evaluation and stores results in PostgreSQL.


reliability_async.py

Status: PENDING

Description: Runs reliability evaluation using arun.


single_tool_calls/calculator.py

Status: PENDING

Description: Validates a single expected factorial tool call.


multiple_tool_calls/calculator.py

Status: PENDING

Description: Validates expected multiply and exponentiate tool calls.


team/ai_news.py

Status: PENDING

Description: Validates team delegation and news-search tool calls.