Unverified50% confidenceFactExact time
Each conversation in ToolTurns begins with an initial request that is deliberately incomplete in information, followed by two context-dependent follow-up queries.
1
Sources
50%
Confidence
Long-term
Relevance
11/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedToolTurns comes with an open-source user simulator that progressively reveals hidden context through dialogue and generates follow-up queries.69% similarUnverifiedTool definitions are repeatedly sent as a fixed prefix in every request, so even if the current conversation does not need a particular tool at all, it still occupies input tokens.69% similarUnverifiedDuring multi-turn tool calls, each tool execution result is appended to the conversation history as a new tool_result message, and the model reads the outputs of previous steps from the conversation context rather than retaining intermediate values in internal memory.68% similarUnverifiedThe Tool Calls events within Messages capture the tool-call intent in the AIMessage, whereas the standalone Tool Calls events capture the ToolMessage results after the tool has actually executed.68% similarUnverified当模型输出工具调用语法后会停止响应,Harness执行工具并将输出追加到对话历史末尾,然后向同一模型重新发起请求68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1165447API
curl https://kongchang.com/api/v1/knowledge/claims/1165447MCP
get_claim(id=1165447)