Unverified50% confidenceSolutionExact time
A complete user Prompt structure typically contains the current Harness rules, Git-retrieved knowledge, the current task state, session conversation history, Memory-related content, and the user's current input.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedToolContext不仅能获取自定义元数据，还能访问当前的聊天记录State，包含用户提示词、大模型响应、工具调用参数等完整对话上下文信息75% similarUnverifiedCoze provides a persistent memory feature that can store user preference settings, frequently asked questions, and language habits over the long term.71% similarUnverifiedA session's complete Context Window includes all user instructions, model responses, tool call records, and file read/write history70% similarUnverifiedTaking LLMs as an example, context includes the system prompt, user query, externally retrieved information, historical interaction records, and additional system outputs.70% similarUnverified该工具提供Token用量查看功能，用户需自行配置对话模型和生图模型70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/902543API
curl https://kongchang.com/api/v1/knowledge/claims/902543MCP
get_claim(id=902543)