Unverified50% confidenceFactExact time
In the example, the agent generates the app by calling tools such as app_create and app_render, and the chat history on the left keeps a collapsed record of each tool call and version entry points (View app, Edit).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/4/2026
First Seen
Valid until: 2/2/2027
Sources
Related Entities
Related Claims
UnverifiedOpenAI Agents SDK使用to_input_list()方法将上一次的运行结果转换为可重新输入的格式，以实现对话历史的手动管理72% similarUnverifiedCaching for Agent applications usually needs a layered design, including prefix caching of system prompts and tool descriptions, result caching with TTL for tool call results, and caching of embedding results in vector retrieval scenarios.70% similarUnverifiedThe Agent accesses memory through the two tools read_memory and append_memory, which, like the scratchpad and the to-do list, run in-process.70% similarUnverifiedWhen a browser extension handles multi-AI submission, the generated conversations naturally enter each platform's history and project spaces because the logged-in session is used.68% similarUnverified在Agent Scratchpad中，LLM生成的工具调用作为AI Message存储，工具返回的结果作为Tool Message存储，两者通过tool_call_id进行关联68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1136724API
curl https://kongchang.com/api/v1/knowledge/claims/1136724MCP
get_claim(id=1136724)