Unverified50% confidenceFactExact time
The actual number of tokens consumed by a single user request includes the entire input context (including conversation history, system prompts, tool definitions, etc.) as well as the response content generated by the model.
1
Sources
50%
Confidence
Long-term
Relevance
9/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn multi-turn conversations, the System message sets the behavioral tone and constraints, the user message represents user input, and the assistant message is the model's historical replies.79% similarUnverifiedA 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.78% 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77% similarUnverifiedTaking LLMs as an example, context includes the system prompt, user query, externally retrieved information, historical interaction records, and additional system outputs.75% similarUnverifiedToolContext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% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/923598API
curl https://kongchang.com/api/v1/knowledge/claims/923598MCP
get_claim(id=923598)