chore: import upstream snapshot with attribution
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

This commit is contained in:
wehub-resource-sync
2026-07-13 13:24:08 +08:00
commit 0d3cb498a3
5438 changed files with 1316560 additions and 0 deletions
@@ -0,0 +1,72 @@
# config-executable-prompts (Executable Prompts)
This example demonstrates how to use executable scripts and binaries as prompt generators in promptfoo.
To initialize and run it:
```bash
npx promptfoo@latest init --example config-executable-prompts
cd config-executable-prompts
promptfoo eval
```
## Prerequisites
- bash/zsh (macOS/Linux) or PowerShell (Windows)
- jq (for the shell example): https://stedolan.github.io/jq/
- Ruby 3.x (for the Ruby example)
- Make scripts executable: `chmod +x prompt-generator.sh template-prompt.rb`
## Overview
Promptfoo supports using any executable (shell scripts, Python scripts, binaries, etc.) to dynamically generate prompts. This is useful when you need to:
- Generate prompts based on external data sources
- Create context-aware prompts dynamically
- Integrate with existing tools and scripts
- Generate prompts in languages other than JavaScript or Python
## How It Works
1. **Script Input**: Your executable receives a JSON context as its first command-line argument containing:
- `vars`: Test variables from your configuration
- `provider`: Information about the current provider
- `config`: Any additional configuration passed to the prompt
2. **Script Output**: Your script should output the generated prompt to stdout
3. **Error Handling**:
- Errors should be written to stderr
- Non-zero exit codes will cause the prompt generation to fail
## Usage Methods
### Method 1: Using `exec:` prefix
```yaml
prompts:
- exec:./my-script.sh
- exec:/usr/bin/custom-prompt-generator
```
### Method 2: Direct file reference (auto-detected)
```yaml
prompts:
- ./my-script.sh # Detected by .sh extension
# Note: Python files (.py) are processed as Python prompt templates by default.
# To run a Python script as an executable prompt, use the exec: prefix:
# - exec:./generator.py
```
### Method 3: With configuration
```yaml
prompts:
- label: 'Custom Prompt'
raw: exec:./generator.sh
config:
temperature: 0.7
style: technical
timeout: 30000 # 30 second timeout (default: 60s)
```
+28
View File
@@ -0,0 +1,28 @@
#!/bin/bash
# This script demonstrates how to create executable prompts for promptfoo
# It receives context as JSON in the first argument
CONTEXT=$1
# Parse some values from the context using jq
VARS=$(echo "$CONTEXT" | jq -r '.vars')
PROVIDER_ID=$(echo "$CONTEXT" | jq -r '.provider.id')
# Extract specific vars if they exist
USER_NAME=$(echo "$CONTEXT" | jq -r '.vars.name // "user"')
TASK=$(echo "$CONTEXT" | jq -r '.vars.task // "help with a task"')
# Generate a dynamic prompt based on the context
cat <<EOF
You are a helpful AI assistant.
Current user: ${USER_NAME}
Task requested: ${TASK}
Please provide a detailed and helpful response to assist the user with their task.
Be professional, accurate, and thorough in your response.
Context variables received:
$CONTEXT
EOF
@@ -0,0 +1,29 @@
# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
# This configuration demonstrates executable scripts as prompt generators
description: 'Testing executable prompts with multiple languages and use cases'
prompts:
# Basic shell script prompt
- label: 'Shell Basic'
raw: exec:./prompt-generator.sh
# Ruby template-based prompt
- label: 'Ruby Template'
raw: exec:./template-prompt.rb
providers:
# This just repeats the prompt back to the user
- echo
# Uncomment to use real providers
# - openai:gpt-4o-mini
# - anthropic:claude-haiku-4-5-20251001
tests:
- vars:
name: Alice
task: 'Help me understand recursion'
- vars:
name: Bob
task: 'Why is the sky blue'
+140
View File
@@ -0,0 +1,140 @@
#!/usr/bin/env ruby
# Ruby executable prompt generator
# Demonstrates template-based prompt generation
require 'json'
require 'erb'
# Parse context from command line
begin
context = JSON.parse(ARGV[0] || '{}')
rescue JSON::ParserError => e
STDERR.puts "Error parsing JSON: #{e.message}"
exit 1
end
vars = context['vars'] || {}
provider = context['provider'] || {}
config = context['config'] || {}
# Define prompt templates using ERB
class PromptGenerator
attr_accessor :vars, :config, :provider
def initialize(vars, config, provider)
@vars = vars
@config = config
@provider = provider
end
def generate
template = if vars['useCase'] == 'customer_service'
customer_service_template
elsif vars['useCase'] == 'data_analysis'
data_analysis_template
elsif vars['useCase'] == 'creative_writing'
creative_writing_template
else
default_template
end
ERB.new(template, trim_mode: '-').result(binding)
end
private
def customer_service_template
<<~TEMPLATE
You are a customer service representative for <%= vars['company'] || 'our company' %>.
Customer Profile:
- Name: <%= vars['customerName'] || 'Valued Customer' %>
- Issue Type: <%= vars['issueType'] || 'General Inquiry' %>
- Priority: <%= vars['priority'] || 'Normal' %>
Guidelines:
- Be empathetic and professional
- Acknowledge the customer's concerns
- Provide clear solutions or next steps
- Follow up appropriately
Customer Message: <%= vars['message'] || 'How can I help you today?' %>
Please respond appropriately to resolve the customer's issue.
TEMPLATE
end
def data_analysis_template
<<~TEMPLATE
You are a data analyst examining <%= vars['dataType'] || 'business data' %>.
Analysis Parameters:
- Dataset: <%= vars['dataset'] || 'general dataset' %>
- Time Period: <%= vars['timePeriod'] || 'last quarter' %>
- Focus Areas: <%= vars['focusAreas'] || 'key metrics' %>
Required Analysis:
1. Identify trends and patterns
2. Highlight anomalies or outliers
3. Provide actionable insights
4. Suggest areas for further investigation
<% if vars['specificQuestions'] %>
Specific Questions to Address:
<%= vars['specificQuestions'] %>
<% end %>
Provide a comprehensive analysis with visualizations where appropriate.
TEMPLATE
end
def creative_writing_template
<<~TEMPLATE
You are a creative writer working on <%= vars['genre'] || 'general fiction' %>.
Writing Parameters:
- Style: <%= vars['style'] || 'contemporary' %>
- Tone: <%= vars['tone'] || 'engaging' %>
- Target Audience: <%= vars['audience'] || 'general readers' %>
- Length: <%= vars['length'] || 'medium' %>
<% if vars['prompt'] %>
Writing Prompt: <%= vars['prompt'] %>
<% end %>
<% if vars['characters'] %>
Characters: <%= vars['characters'] %>
<% end %>
<% if vars['setting'] %>
Setting: <%= vars['setting'] %>
<% end %>
Create an original, compelling piece that captures the reader's attention.
TEMPLATE
end
def default_template
<<~TEMPLATE
You are a helpful AI assistant.
Context Information:
- Provider: <%= provider['id'] || 'default' %>
- Task: <%= vars['task'] || 'assist the user' %>
- User: <%= vars['userName'] || 'User' %>
<% if config['temperature'] %>
Response Style: <%= config['temperature'] > 0.7 ? 'Creative' : 'Focused' %>
<% end %>
User Request: <%= vars['request'] || 'Please help me with my task.' %>
Please provide a helpful and appropriate response.
TEMPLATE
end
end
# Generate and output the prompt
generator = PromptGenerator.new(vars, config, provider)
puts generator.generate