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
46 lines
1.2 KiB
YAML
46 lines
1.2 KiB
YAML
# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
|
|
description: 'Claude Agent SDK with structured JSON output'
|
|
|
|
prompts:
|
|
- |
|
|
Analyze the following code snippet and provide your assessment:
|
|
|
|
```python
|
|
def calculate_discount(price, discount_percent):
|
|
return price - (price * discount_percent)
|
|
```
|
|
|
|
providers:
|
|
- id: anthropic:claude-agent-sdk
|
|
config:
|
|
output_format:
|
|
type: json_schema
|
|
schema:
|
|
type: object
|
|
properties:
|
|
has_bugs:
|
|
type: boolean
|
|
description: Whether the code has bugs
|
|
bug_description:
|
|
type: string
|
|
description: Description of the bug if found
|
|
severity:
|
|
type: string
|
|
enum: [low, medium, high, critical]
|
|
description: Severity of the bug
|
|
suggested_fix:
|
|
type: string
|
|
description: How to fix the bug
|
|
required: [has_bugs, severity]
|
|
|
|
tests:
|
|
- vars: {}
|
|
assert:
|
|
- type: is-json
|
|
- type: javascript
|
|
value: output.has_bugs === true
|
|
- type: javascript
|
|
value: output.severity === 'medium' || output.severity === 'high'
|
|
- type: contains
|
|
value: '100'
|