wehub-resource-sync
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
51 lines
1.4 KiB
YAML
51 lines
1.4 KiB
YAML
# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
|
|
description: Comprehensive test of deep research features
|
|
prompts:
|
|
- |
|
|
Research and provide a brief answer to: {{query}}
|
|
Limit your research to 2-3 sources for efficiency.
|
|
|
|
providers:
|
|
# Test with limited searches
|
|
- id: openai:responses:o4-mini-deep-research
|
|
label: Quick Research (2 searches)
|
|
config:
|
|
max_output_tokens: 5000
|
|
max_tool_calls: 2
|
|
tools:
|
|
- type: web_search_preview
|
|
|
|
# Test with more searches
|
|
- id: openai:responses:o4-mini-deep-research
|
|
label: Detailed Research (5 searches)
|
|
config:
|
|
max_output_tokens: 10000
|
|
max_tool_calls: 5
|
|
tools:
|
|
- type: web_search_preview
|
|
|
|
tests:
|
|
- vars:
|
|
query: What is the current stable version of React.js?
|
|
assert:
|
|
- type: contains-any
|
|
value: [React, version, '18', '19', stable]
|
|
- type: contains
|
|
value: Web Search
|
|
|
|
- vars:
|
|
query: What are the main features of TypeScript 5.0?
|
|
assert:
|
|
- type: contains-any
|
|
value: [TypeScript, '5.0', features, decorators]
|
|
- type: contains
|
|
value: Web Search
|
|
|
|
- vars:
|
|
query: What is the latest Python version and its release date?
|
|
assert:
|
|
- type: contains-any
|
|
value: [Python, version, '3.1', '3.2', release]
|
|
- type: contains
|
|
value: Web Search
|