Unverified50% confidenceFactExact time
During 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.
1
Sources
50%
Confidence
Long-term
Relevance
9/24/2026
First Seen
Sources
Related Entities
Related Claims
Unverified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76% similarVerifiedThe context window determines how much content the model can remember within a single conversation.75% similarUnverified自定义工具（Custom Tool）可以将重复流程封装起来实现一键复用，绕过重复推理75% similarUnverifiedMid-conversation tool changes allow different tool lists to be passed in across different turns of the same session, enabling agents to load specialized toolkits on demand, thereby reducing token consumption and improving tool call precision.74% similarUnverifiedSaved Skills appear in the conversation list and can be invoked at any time, enabling a build-once, reuse-many-times workflow.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/948058API
curl https://kongchang.com/api/v1/knowledge/claims/948058MCP
get_claim(id=948058)