Agent Harnesses and the Architecture of Software

说明与用途

示例展示了代理 harness 如何协调 REA 工具调用，以分析 JavaScript 应用程序，并在步骤之间保留证据和上下文。

问题

How can an AI agent orchestrate tool calls to perform reverse‑engineering tasks while preserving evidence and context across multiple steps?

结果

The example demonstrates that an agent harness can coordinate tool calls to a reverse‑engineering toolkit, preserving evidence across steps and enabling iterative investigation of application features.

工作流

• 1. Model receives user request to investigate search functionality.
• 2. Agent harness proposes tool call analyze_javascript_application to REA.
• 3. REA performs static analysis and returns a summary with a reference to retained evidence.
• 4. Model requests a paged view of modules via inspect_analysis_view using the evidence ID.
• 5. Model identifies module search.js and calls trace_application_feature with the same evidence ID and module seed.
• 6. REA returns a feature trace, possibly revealing HTTP requests or local indices.
• 7. Model evaluates trace, may request dynamic execution evidence if needed.
• 8. Agent harness logs all messages, tool calls, and results for persistence and recovery.

证据

The model receives the request and the available tool descriptions. It might propose analyze_javascript_application. The surrounding agent runtime dispatches that call to REA.

来源

The model can then ask to see a page of modules: …

来源

The trace might lead toward a local index, or toward code that sends an HTTP request. Those clues would lead to different follow‑up work.

来源