Unverified50% confidenceFactExact time
jev-tools currently provides six tools: jev_ask, jev_ask_files, jev_find_files, jev_locate_in_file, jev_check_diff, and jev_select_tests.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/18/2026
First Seen
Valid until: 1/16/2027
Sources
Related Entities
Related Claims
UnverifiedTool Retrieval uses vector search to first filter out the 3–5 most relevant tools before providing them to the model.68% similarUnverifiedfind命令拥有超过50个参数选项，涵盖按名称、大小、时间戳、权限等多维度的文件检索能力64% similarUnverifiedThe vector-retrieval-based tool search approach stores all tool metadata in a vector database, performs semantic search using the user prompt, and sends only the relevant tool information to the LLM.63% similarUnverified系统的五维并行搜索借鉴了信息检索领域的多路召回（Multi-path Retrieval）架构，同时启动产品类型匹配、样式推荐、配色方案、落地页模式、字体配对五个搜索维度63% similarUnverifiedThe intent router classifies user requests into one of four execution paths: vector_search, entity_lookup, path_synthesis, or general.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1062492API
curl https://kongchang.com/api/v1/knowledge/claims/1062492MCP
get_claim(id=1062492)