📄️ Test Generation from Execution - Quick Start Guide
0. Before You Start
📄️ Agent mode (Explyt Agent)
The agent can perform an arbitrary task upon request in the chat.
📄️ Agent Modes (Modes)
Mode Selection
📄️ What test type should I choose?
Choosing the most appropriate test type is crucial for accurate test generation.
📄️ Model Context Protocol: What It Is and How to Use It
MCP (Model Context Protocol) is an open standard based on JSON-RPC that defines how LLMs connect to tools, services, and data. With MCP, developers don't need to build custom integrations for every single tool.
📄️ Rules
What is the Rules feature?
📄️ Workflows
What is the Workflows feature?
📄️ Explain Code describes how the code works and outlines what impacts its use
📄️ Analyze for Bugs analyzes the code for possible implementation errors
📄️ Flaky test detection
📄️ Increase test coverage
Scenarios where this feature can be useful
📄️ Repair compilation and runtime errors of any test class
📄️ Inline code generation
You can select a piece of code and change it inside the code editor in all IDEs.
📄️ IDE Run Configurations
IDE Run Configurations
📄️ Extending test class with new test methods
📄️ Symbol Refactoring
The agent can rename symbols — classes, methods, fields, variables, and parameters — using the IDE's refactoring mechanism (analogous to Shift-F6).
📄️ Explain Error in Run Window
📄️ Message Queue in Chat
You can send messages to a queue in the chat without waiting for the agent's previous response to fully complete.
📄️ Plugin Settings
Model Context Size
📄️ Web search & Web fetch Agent Tools
The agent can now fetch web pages and use them in chat.
📄️ Run tests with instrumentation
TBA
📄️ Indexes for fast code search
In our plugin there are two types of search: similar search and exact search.
📄️ Automatic chat compression
If the chat with the agent becomes too large, there's a risk of hitting the context window limit: the model's performance decreases, while its cost and response time increase. We have implemented automatic chat compression that reduces the chat size automatically when it becomes too large. It's triggered automatically and doesn't make additional requests to LLM, so it doesn't waste your time and tokens.
📄️ .readignore/.writeignore
For cybersecurity reasons, it may be useful to prevent the agent from reading or editing certain folders or files in the project. This can be done by creating .readignore and .writeignore files in the .explyt/tools/ folder in the project.
📄️ Images
You can attach an image to the chat. This will be especially useful for frontend development and UI testing.
📄️ Skills
We support the open SKILLs standard (Skills).
📄️ AGENTS.md
AGENTS.md is an open standard for project context for AI tools that helps the agent understand the domain, repository structure, and working rules.
📄️ Auto Review for generated changes
Auto Review starts a separate chat with the Review agent, passing it the task and the changes made by the agent.
📄️ Edit Scope: limit the editing area
Edit Scope limits the agent's editing area to selected files and folders: the agent can propose and apply changes only within the defined scope.
📄️ Commit Message Generation
The agent can generate commit messages directly from the commit window in the IDE.
📄️ Ask/Copy for Selected Text in Chat
When you select a fragment of text in the agent's response, a panel with buttons appears: "Ask" and "Copy".
🗃️ TMS
2 items