Use these tools to interact with AI Dev Runtime:
- - aidevruntimecommand: Slash command —
/ai-dev-runtime <task> runs full dev task (plan → edit → test → fix) - aidevruntimeinvoke: Low-level tool calls — readfile, search, edit, editmulti, applypatch, findreferences, callhierarchy, runterminal, runtests
- aidevruntimeruntask: Batch task execution (multi-step coding)
- aidevruntimefixbug: Bug-fix workflow (analyze → patch → verify)
- aidevruntimeanalyze: Codebase analysis (semantic + keyword search, learning memory)
For higher accuracy: Before calling aidevruntimefixbug or aidevruntimeruntask, use memorysearch to find similar past fixes (e.g. "login bug", "500 error", "pytest"). Pass the snippets as priormemory so Runtime can use them.
Set AIDEVRUNTIMEURL (default http://localhost:8000) and optionally AIDEVRUNTIMEAPI_KEY. Ensure AiDevRuntime HTTP server is running.
技能名称: ai-dev-runtime
详细描述:
使用这些工具与AI开发运行时交互:
- - aidevruntimecommand: 斜杠命令 — /ai-dev-runtime <任务> 执行完整开发任务(规划→编辑→测试→修复)
- aidevruntimeinvoke: 底层工具调用 — 读取文件、搜索、编辑、批量编辑、应用补丁、查找引用、调用层次、运行终端、运行测试
- aidevruntimeruntask: 批量任务执行(多步骤编码)
- aidevruntimefixbug: 缺陷修复工作流(分析→补丁→验证)
- aidevruntime_analyze: 代码库分析(语义+关键词搜索,学习记忆)
为获得更高准确性:在调用aidevruntimefixbug或aidevruntimeruntask之前,使用memorysearch查找相似的过往修复记录(例如登录缺陷、500错误、pytest)。将代码片段作为priormemory传递,以便运行时使用。
设置AIDEVRUNTIMEURL(默认http://localhost:8000)以及可选的AIDEVRUNTIMEAPI_KEY。确保AiDevRuntime HTTP服务器正在运行。