Unverified50% confidenceFactExact time
In DeepSeek thinking mode, the reasoning_content field stores the model's reasoning process before the final answer, and when the request carries tools, this field in historical assistant messages must be sent back verbatim.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedFactual recall in language models exhibits a layered, sequentially ordered information integration process: first locking in the type framework of the answer, then routing specific entity content to the output position.69% similarUnverifiedThe summarization capability of large language models is essentially the process of identifying key semantic nodes in text through the attention mechanism, compressing long documents into short texts that retain the core arguments.68% similarUnverifiedReasoning tokens refer to the tokens consumed by the internal reasoning content generated by models with chain-of-thought capabilities (such as the OpenAI o series, DeepSeek-R1, etc.) before giving a final answer; they are usually not shown directly to the user but are counted toward billing and context window usage.68% similarUnverifiedAnything entered into a prompt becomes part of the model's context and may be retained in history, written to logs, sent to the hosted model, or summarized into subsequent conversation memory.67% similarUnverifiedAnthropic格式将工具调用结果（tool_result）作为独立消息块处理，并对Thinking模式的推理内容有专门的字段定义66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1067657API
curl https://kongchang.com/api/v1/knowledge/claims/1067657MCP
get_claim(id=1067657)