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
155 lines
4.5 KiB
YAML
155 lines
4.5 KiB
YAML
# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
|
|
description: Anthropic structured outputs for JSON responses and strict tools
|
|
|
|
prompts:
|
|
# JSON outputs example - extract structured data
|
|
- |
|
|
Extract the key information from this customer support email:
|
|
|
|
Subject: Enterprise Plan Upgrade Request
|
|
From: Sarah Johnson <sarah.johnson@techcorp.com>
|
|
|
|
Hi there,
|
|
|
|
I'm reaching out to inquire about upgrading our team to the Enterprise plan. We currently have 25 users on the Professional plan, and we're interested in the advanced security features and dedicated support that come with Enterprise.
|
|
|
|
Could someone schedule a demo for next Tuesday, March 15th at 2:00 PM EST? We'd like to see the SSO integration and audit logging features in action.
|
|
|
|
Also, what's the pricing for 50 users on the Enterprise plan?
|
|
|
|
Thanks,
|
|
Sarah Johnson
|
|
Director of Engineering, TechCorp
|
|
|
|
providers:
|
|
# JSON outputs - Inline schema
|
|
- id: anthropic:messages:claude-sonnet-4-6
|
|
label: inline-schema
|
|
config:
|
|
max_tokens: 2048
|
|
output_format:
|
|
type: json_schema
|
|
schema:
|
|
type: object
|
|
properties:
|
|
customer_name:
|
|
type: string
|
|
customer_email:
|
|
type: string
|
|
company:
|
|
type: string
|
|
current_plan:
|
|
type: string
|
|
requested_plan:
|
|
type: string
|
|
current_users:
|
|
type: integer
|
|
requested_users:
|
|
type: integer
|
|
demo_requested:
|
|
type: boolean
|
|
demo_datetime:
|
|
type: string
|
|
features_of_interest:
|
|
type: array
|
|
items:
|
|
type: string
|
|
questions:
|
|
type: array
|
|
items:
|
|
type: string
|
|
required:
|
|
- customer_name
|
|
- customer_email
|
|
- current_plan
|
|
- requested_plan
|
|
- demo_requested
|
|
additionalProperties: false
|
|
|
|
# JSON outputs - External file
|
|
- id: anthropic:messages:claude-sonnet-4-6
|
|
label: external-file
|
|
config:
|
|
max_tokens: 2048
|
|
output_format: file://output_format.json
|
|
|
|
# JSON outputs - Nested file reference (format file references schema file)
|
|
- id: anthropic:messages:claude-sonnet-4-6
|
|
label: nested-file-reference
|
|
config:
|
|
max_tokens: 2048
|
|
output_format: file://nested_format.json
|
|
|
|
# Strict tool use - Ensure tool parameters exactly match schema
|
|
- id: anthropic:messages:claude-sonnet-4-6
|
|
config:
|
|
max_tokens: 2048
|
|
tool_choice:
|
|
type: any
|
|
tools:
|
|
- name: book_demo
|
|
description: Book a demo session for a customer
|
|
strict: true
|
|
input_schema:
|
|
type: object
|
|
properties:
|
|
customer_email:
|
|
type: string
|
|
customer_name:
|
|
type: string
|
|
company:
|
|
type: string
|
|
demo_datetime:
|
|
type: string
|
|
description: ISO 8601 datetime string
|
|
features_to_demo:
|
|
type: array
|
|
items:
|
|
type: string
|
|
enum:
|
|
- sso_integration
|
|
- audit_logging
|
|
- advanced_security
|
|
- dedicated_support
|
|
- custom_integrations
|
|
attendees_count:
|
|
type: integer
|
|
enum: [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
|
|
required:
|
|
- customer_email
|
|
- customer_name
|
|
- demo_datetime
|
|
additionalProperties: false
|
|
|
|
- name: get_pricing
|
|
description: Get pricing information for a specific plan and user count
|
|
strict: true
|
|
input_schema:
|
|
type: object
|
|
properties:
|
|
plan:
|
|
type: string
|
|
enum:
|
|
- professional
|
|
- enterprise
|
|
user_count:
|
|
type: integer
|
|
billing_period:
|
|
type: string
|
|
enum:
|
|
- monthly
|
|
- annual
|
|
required:
|
|
- plan
|
|
- user_count
|
|
additionalProperties: false
|
|
|
|
tests:
|
|
# Simple test that works for both providers
|
|
- description: Should extract customer information
|
|
assert:
|
|
- type: contains
|
|
value: Sarah Johnson
|
|
- type: contains
|
|
value: sarah.johnson@techcorp.com
|