Files

26 lines
1013 B
Bash

# Copy to evals/.env and fill in. Both files are gitignored.
#
# REQUIRED: API key for both the agent (system under test) and the rubric
# grader unless you switch the grader to a non-Anthropic provider via
# RUBRIC_MODEL below.
# Request access via #ask-app-eng to get an API key.
ANTHROPIC_API_KEY=
# OPTIONAL: the system-under-test model. Stays on Claude because that's what
# real users will run skills against. Defaults to claude-sonnet-4-6 if unset.
# AGENT_MODEL=claude-sonnet-4-6
# REQUIRED: the rubric grader for `llm-rubric` assertions. Wired into
# shared/defaults.yaml as defaultTest.options.provider. Pick a cheaper model
# than AGENT_MODEL since this only judges agent output and runs once per
# rubric assertion.
#
# Examples:
# anthropic:messages:claude-haiku-4-5-20251001
# openai:gpt-4.1-mini
RUBRIC_MODEL=anthropic:messages:claude-haiku-4-5-20251001
# OPTIONAL: only needed if RUBRIC_MODEL points at an OpenAI model.
# Get yours at https://platform.openai.com/api-keys
# OPENAI_API_KEY=