Unverified50% confidenceFactExact time
When a single-turn model receives input containing assistant replies or tool call history, LLM will raise an `llm.ConversationNotSupported` exception, and the `llm chat` command will also reject such models before the session begins.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/23/2026
First Seen
Valid until: 12/22/2026
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73% similarUnverifiedMulti-turn conversation models accept a `messages` array containing a list of historical messages, with full context carried in each request; some specialized models' APIs only accept a single `prompt` input and do not process historical context.71% similarUnverifiedLLM 工具内置对话历史管理功能71% similarUnverifiedLLM交互模型中输入分为系统提示、用户消息和助手回复三个层次，系统提示处于最高优先级并在整个对话中持续生效71% similarUnverified在本地模型场景下 Chatbox 本身不加载运行模型，而是连接正在运行的 Ollama、LM Studio 或其他模型服务，负责对话展示、会话管理、提示词管理和多供应商切换71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/942270API
curl https://kongchang.com/api/v1/knowledge/claims/942270MCP
get_claim(id=942270)