0d3cb498a3
CI / Shell Format Check (push) Has been cancelled
CI / Check Ruby (3.4) (push) Has been cancelled
CI / CI Config (push) Has been cancelled
CI / Test on Node ${{ matrix.node }} and ${{ matrix.os }}${{ matrix.shard && format(' (shard {0}/3)', matrix.shard) || '' }} (push) Has been cancelled
CI / Build on Node ${{ matrix.node }} (push) Has been cancelled
CI / Style Check (push) Has been cancelled
CI / Generate Assets (push) Has been cancelled
CI / Check Python (3.14) (push) Has been cancelled
CI / Check Python (3.9) (push) Has been cancelled
CI / Build Docs (push) Has been cancelled
CI / Code Scan Action (push) Has been cancelled
CI / Site tests (push) Has been cancelled
CI / webui tests (push) Has been cancelled
CI / Run Integration Tests (push) Has been cancelled
CI / Run Smoke Tests (push) Has been cancelled
CI / Go Tests (push) Has been cancelled
CI / Share Test (push) Has been cancelled
CI / Redteam (Production API) (push) Has been cancelled
CI / Redteam (Staging API) (push) Has been cancelled
CI / GitHub Actions Lint (push) Has been cancelled
CI / Check Ruby (3.0) (push) Has been cancelled
release-please / release-please (push) Has been cancelled
release-please / build (push) Has been cancelled
release-please / publish-npm (push) Has been cancelled
release-please / publish-npm-backfill (push) Has been cancelled
release-please / docker (push) Has been cancelled
release-please / publish-code-scan-action (push) Has been cancelled
release-please / attest-code-scan-action (push) Has been cancelled
Deploy local.promptfoo.app / Deploy to Cloudflare Pages (push) Has been cancelled
Test and Publish Multi-arch Docker Image / test (push) Has been cancelled
Test and Publish Multi-arch Docker Image / build-docker-and-push-digests (map[digest-suffix:linux-amd64 platform:linux/amd64 runner:ubuntu-latest]) (push) Has been cancelled
Test and Publish Multi-arch Docker Image / build-docker-and-push-digests (map[digest-suffix:linux-arm64 platform:linux/arm64 runner:ubuntu-24.04-arm]) (push) Has been cancelled
Test and Publish Multi-arch Docker Image / merge-docker-digests (push) Has been cancelled
Test and Publish Multi-arch Docker Image / Attest Multi-arch Image (push) Has been cancelled
Validate Renovate Config / Validate Renovate Configuration (push) Has been cancelled
44 lines
1.1 KiB
YAML
44 lines
1.1 KiB
YAML
# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
|
|
description: 'n8n AI agent evaluation'
|
|
|
|
prompts:
|
|
- '{{query}}'
|
|
|
|
providers:
|
|
- id: n8n:https://your-n8n-instance.com/webhook/your-agent-id
|
|
config:
|
|
headers:
|
|
Authorization: 'Bearer {{env.N8N_API_KEY}}'
|
|
body:
|
|
message: '{{prompt}}'
|
|
userId: '{{userId}}'
|
|
|
|
tests:
|
|
- vars:
|
|
query: What are your business hours?
|
|
userId: test-user-1
|
|
assert:
|
|
- type: contains-any
|
|
value:
|
|
- hours
|
|
- open
|
|
- available
|
|
|
|
- vars:
|
|
query: What's the status of my order #12345?
|
|
userId: test-user-2
|
|
assert:
|
|
- type: javascript
|
|
value: |
|
|
const toolCalls = context.providerResponse?.metadata?.toolCalls || [];
|
|
return toolCalls.some(tc => tc.name === 'order_lookup');
|
|
- type: contains
|
|
value: '12345'
|
|
|
|
- vars:
|
|
query: I need help resetting my password
|
|
userId: test-user-3
|
|
assert:
|
|
- type: llm-rubric
|
|
value: The response should acknowledge the request and provide clear next steps
|