Open Models Almanac
Methodsinference & servingcontext management

specific method · filed under inference & serving

Tool-use reasoning-context persistence and selective deletion

Thinking Context Management is a context-management rule for tool-calling conversations that decides when the model's reasoning content is kept or discarded.1,2 It retains reasoning across tool-related messages, unlike the DeepSeek-R1 strategy of discarding it at the second message round, which forces the model to redundantly re-reason for each tool call.3,4

Trade-off Preserving reasoning avoids redundant re-reasoning and its token inefficiency, but agent frameworks that simulate tools via user messages may not benefit.5,6

How this definition was written

Summarised by glm-5.3-flash from 2 sources; every sentence is checked against the quote it cites.

  1. we developed a context management strictly tailored for tool-calling scenarios — paper
  2. Historical reasoning content is discarded only when a newuser messageis introduced — paper
  3. If only tool-related messages (e.g., tool outputs) are appended, the reasoning content isretainedthroughout the interaction — paper
  4. discarding reasoning content upon the arrival of the second round of messages—results in significant token inefficiency — paper
  5. forces the model to redundantly re-reason through the entire problem for each subsequent tool call — paper
  6. These frameworks may not fully benefit from our enhanced reasoning persistence — DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Also called Thinking Context Management.

sources
2
model
1
lab adopt it
1
strongest
used

Documented in

Evidence

2 quotes from 2 sources, one card per model, each opening with its strongest.

How sources treat it
used 2

DeepSeek-V3.2

DeepSeekadopted2 sources

Historical reasoning content is discarded only when a new user message is introduced to the conversation. If only tool-related messages ... are appended, the reasoning content is retained throughout the interaction.

usedinference servingin DeepSeek-V3.2DeepSeek
1 more from this model

Historical reasoning content is discarded only when a new user message is introduced to the conversation.

usedinference servingin DeepSeek-V3.2DeepSeek
↑