convez.ai
MCP ServerAutomaçãoIntermediário
QAInsights

Feather Wand - Agent IA para JMeter

QAInsights/jmeter-ai

Assistente IA integrado ao JMeter com streaming, refatoração e execução de código

Ver no GitHub
BomPluginScore · de 0 a 100

Agent inteligente que integra Claude, OpenAI, Google Gemini e outros modelos de IA diretamente no Apache JMeter. Oferece chat em tempo real, refatoração de código, terminal CLI com Code Execution e comandos contextuais para otimização de testes de performance.

Instalação

$npx convez-ai QAInsights/jmeter-ai

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
67
Forks
29
Acompanhando
4
Saúde
42%
Último commit
há 1 dia
Versão
v4.0.0
Issues abertas
14
Contribuidores
2

Casos de uso

  • Otimizar e refatorar scripts de teste de performance com IA
  • Gerar casos de teste e planos de teste usando comandos contextuais
  • Executar código Claude/OpenAI diretamente no editor JMeter
  • Analisar resultados de testes com suporte a múltiplos modelos de IA

Veredito

Agent robusto e bem pensado que traz automação inteligente ao ecossistema JMeter. A integração multi-modelo e recursos como streaming, refatoração contextual e terminal IA agregam valor real para engenheiros de performance, embora exija JMeter como dependência.

README

A tradução para o português deste README ainda está na fila.

🪶 Feather Wand

AI-powered assistant for Apache JMeter

Release PerfAtlas License Stars

Features · Install · Configure · Commands · Changelog

🪄 Why "Feather Wand"? My kids named it after a Bluey episode, where a simple feather becomes a magical wand that turns the ordinary into something special. That's exactly what this plugin does for your JMeter workflow.


📑 Contents


✨ Features

🤖 Multi-Model ChatTalk to Claude, OpenAI, Google Gemini, DeepSeek, or Ollama — all inside JMeter.
⚡ Real-Time StreamingWatch AI responses appear token-by-token with a Stop button to cancel anytime.
🖥️ AI CLI TerminalRun Claude Code, OpenAI Codex, OpenCode, or Antigravity directly in JMeter.
🧹 Smart RefactoringRight-click in the JSR223 editor to refactor, format, or inject functions with AI.
🔍 Context-Aware Commands@this, @optimize, @lint, @wrap, @code, @usage — each tailored to your test plan.
🔔 Audio ChimeOptional sound notification when AI finishes responding.
🔧 Model FilteringOnly chat-compatible models appear in the dropdown — no audio/TTS clutter.
⚙️ Fully ConfigurableCustomize prompts, temperature, tokens, history, timeouts, and more via JMeter properties.

📥 Installation

Plugins Manager (Recommended)

1. Install JMeter Plugins Manager → https://jmeter-plugins.org/
2. Restart JMeter
3. Open Plugins Manager → Available Plugins
4. Search for "feather wand"
5. Select it → Apply Changes and Restart JMeter

Manual Installation

1. Download the latest JAR from Releases
2. Drop it into JMeter's lib/ext directory
3. Copy jmeter-ai-sample.properties into jmeter.properties (or user.properties)
4. Add your API key(s) and restart JMeter

See Releases for the latest JAR.

⚙️ Configuration

Copy jmeter-ai-sample.properties into your jmeter.properties or user.properties and adjust the values below.

General Settings

PropertyDescriptionDefault
jmeter.ai.streaming.enabledStream AI responses token-by-tokentrue
jmeter.ai.response.chimePlay a chime when AI finishesfalse
jmeter.ai.refactoring.enabledEnable JSR223 editor AI refactoringtrue
jmeter.ai.service.typeDefault AI service for refactoringanthropic

AI Service Settings

PropertyDescriptionDefault
anthropic.api.keyClaude API keyRequired
claude.default.modelDefault modelclaude-sonnet-4-6
claude.temperatureTemperature (0.0-1.0)0.5
claude.max.tokensMax response tokens1024
claude.max.history.sizeConversation history size10
claude.system.promptSystem promptSee sample file
anthropic.log.levelLogging (info/debug)(empty)
PropertyDescriptionDefault
openai.api.keyOpenAI API keyRequired
openai.default.modelDefault modelgpt-4o
openai.temperatureTemperature (0.0-1.0)0.5
openai.max.tokensMax response tokens1024
openai.max.history.sizeConversation history size10
openai.system.promptSystem promptSee sample file
openai.log.levelLogging (INFO/DEBUG)(empty)
PropertyDescriptionDefault
google.api.keyGoogle AI API keyRequired
google.default.modelDefault modelgemini-2.5-flash
google.temperatureTemperature (0.0-1.0)0.7
google.max.tokensMax response tokens4096
google.max.history.sizeConversation history size10
google.system.promptSystem promptSee sample file
PropertyDescriptionDefault
ollama.hostServer hosthttp://localhost
ollama.portServer port11434
ollama.default.modelDefault modeldeepseek-r1:1.5b
ollama.temperatureTemperature (0.0-1.0)0.5
ollama.max.history.sizeConversation history size10
ollama.thinking.modeExtended thinking (ENABLED/DISABLED)DISABLED
ollama.thinking.levelThinking depth (LOW/MEDIUM/HIGH)MEDIUM
ollama.request.timeout.secondsRequest timeout120
ollama.system.promptSystem promptSee sample file

⚠️ If ollama.thinking.mode=ENABLED, raise ollama.request.timeout.seconds to at least 300.

AI CLI Terminal

PropertyDescriptionDefault
jmeter.ai.terminal.claudecode.enabledEnable the embedded terminaltrue
jmeter.ai.terminal.claudecode.pathFull path to claude binary(auto-detect)
jmeter.ai.terminal.copilot.enabledEnable GitHub Copilot CLIfalse
jmeter.ai.terminal.copilot.pathFull path to copilot binary(auto-detect)
jmeter.ai.terminal.antigravity.enabledEnable Antigravity CLIfalse

Prerequisite CLIs

CLIBinaryInstall Guide
Claude CodeclaudeDocs
OpenAI CodexcodexRepo
GitHub CopilotcopilotDocs
OpenCodeopencodeRepo
AntigravityagySite

Custom System Prompts

Each service supports its own *.system.prompt property — tweak them in your properties file to focus the AI on specific JMeter topics or team conventions.

🔍 Special Commands

Type any of these directly in the chat box. All commands are context-aware and work with the currently selected test-plan element.

CommandWhat it doesExample
@thisDescribe the selected element and suggest best practices.How do I configure @this?
@optimizeAnalyze the selected element and suggest performance tweaks.@optimize or optimize this sampler
@lintAuto-rename elements for consistency. Undo/redo supported.@lint rename elements in PascalCase
@wrapGroup HTTP samplers under Transaction Controllers.@wrap (select a Thread Group first)
@codeExtract the last AI code block into the JSR223 editor.@code
@usageShow token-usage stats and recent conversation history.@usage

@lint Tips

  • Run it after importing a recorded test plan to clean up generic names.
  • Use it before sharing plans with your team.
  • Apply custom rules: @lint rename based on the URL.

@wrap Details

@wrap uses pattern matching (not AI) to group related HTTP samplers under Transaction Controllers, preserving child elements and hierarchy. Great for imported or recorded plans.

💨 Streaming AI Responses

All five AI services support real-time streaming out of the box. Responses appear token-by-token as they are generated.

ControlWhat it does
StopAppears next to the Send button during streaming — click to cancel mid-response.

Disable streaming:

jmeter.ai.streaming.enabled=false

🔔 Response Chime

Get an audible cue when the AI finishes responding so you can multitask across windows.

jmeter.ai.response.chime=true

The bundled WAV plays from src/main/resources/org/qainsights/jmeter/ai/sound/jmeter-chime.wav with an MP3 fallback.

💻 Multi-AI CLI Terminal

An embedded interactive terminal (JediTerm) that brings agentic AI CLIs directly into JMeter.

Supported CLIs: Claude Code · OpenAI Codex · OpenCode · Antigravity

How it works

  1. Install one or more CLIs on your PATH.
  2. Feather Wand auto-detects them on startup.
  3. Pick a CLI from the dropdown in the terminal header.
  4. The terminal receives your open .jmx context via an auto-generated CLAUDE.md.
  5. Use natural language to run tests, parse JTL files, refactor scripts, and more.

Buttons

  • Reload — refresh the test plan from disk.
  • Ctx — resend the current test-plan context.

Architecture Built on an Adapter Pattern: AiCliAdapter → BaseCliAdapter → concrete adapters (ClaudeCodeCliAdapter, OpenAiCodexCliAdapter, ...). To add a new CLI, implement AiCliAdapter and register it in detectAvailableClis().

⚠️ Caution: AI CLIs can execute commands and modify files. Review each CLI's documentation before enabling.

🗝️ API Configuration

Quick Setup

ProviderStepsProperty
ClaudeSign up at anthropic.com → create API keyanthropic.api.key
OpenAISign up at platform.openai.com → create API keyopenai.api.key
GeminiSign in at Google AI Studio → Get API Keygoogle.api.key
OllamaInstall from ollama.com → ollama pull llama3.1No key needed

Set jmeter.ai.service.type=ollama to switch to a local model. All other providers work side-by-side; just pick the model from the UI dropdown.

Model Filtering

Feather Wand automatically hides non-chat models so you only see useful options:

  • OpenAI — hides audio, TTS, whisper, davinci, search, realtime, and instruct models.
  • Claude — shows only the latest available models.
  • Gemini — shows only gemini-* and gemma-* chat models.

Default models: claude-sonnet-4-6 · gpt-4o · gemini-2.5-flash · deepseek-chat · deepseek-r1:1.5b


🪲 Report Issues

Found a bug or have an idea? Open an issue.

⛳️ Roadmap

See what's next on the project board.

⚠️ Disclaimer

  • Verify everything — AI can hallucinate. Double-check critical suggestions before production runs.
  • Backup first — Save your .jmx before letting AI refactor it.
  • Test in staging — Validate changes in a safe environment.
  • Watch costs — Token usage adds up. Use @usage to keep an eye on it.
  • No secrets in chat — Never paste credentials or proprietary code into the chat box.

Feather Wand is an assistant, not a replacement for engineering judgment.

Ver o original no GitHub

Bom para

Relacionados