.env.eval.example

# Example env for running Instance AI workflow evals locally.
#
# This is ONE setup — a local instance that runs the build sandbox directly
# (no hosted proxy). Other setups (proxy-vended sandbox/model, an instance you
# already run) need different vars or none of these. Copy to `.env.eval`
# (gitignored) and fill in real values, then load it alongside your usual env
# however you manage env (a common way is `dotenvx run -f .env.local -f .env.eval`).
#
# See .agents/skills/create-instance-ai-eval/running-evals.md for what each
# piece does and packages/@n8n/instance-ai/evaluations/README.md for the harness.

N8N_LOG_LEVEL=debug

# Enable AI features and the instance-ai module.
N8N_AI_ENABLED=true
N8N_ENABLED_MODULES=instance-ai

# Model key for the builder and the eval helper (mock generation, verifier,
# user-proxy, expectation judge). When the instance runs without the proxy, the
# model client reads ANTHROPIC_API_KEY directly, so export that too if you go
# that route.
N8N_AI_ANTHROPIC_KEY=sk-ant-api03-REPLACE_ME

# Sandbox where the builder executes its workflow-build code.
N8N_INSTANCE_AI_SANDBOX_ENABLED=true
N8N_INSTANCE_AI_SANDBOX_PROVIDER=daytona

# Daytona credentials — used when the instance provisions the sandbox directly
# (rather than through the proxy). Get a key from https://app.daytona.io.
DAYTONA_API_KEY=dtn_REPLACE_ME
DAYTONA_API_URL=https://app.daytona.io/api