Model techniques map
Techniquesinference & servingcontext management

specific method · filed under inference & serving

Excluding prior thinking from conversation history

A multi-turn history policy that omits prior assistant thinking and retains the final response, with an exception for tool-call turns in some descriptions.

Also called No Thinking Content in History.

sources
6
models
3
labs adopt it
3
strongest
default

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 3default 3

Documented in

Evidence

6 spans quoted from the sources, strongest treatment first.

In multi-turn conversations, the historical model output should only include the final output part and does not need to include the thinking content.

defaultinference servingin Qwen3.5-122B-A10BQwen

In multi-turn conversations, the historical model output should only include the final output part and does not need to include the thinking content.

defaultinference servingin Qwen3.5-35B-A3BQwen

Thoughts from previous model turns must not be added before the next user turn begins, with the exception of tool call turns where thinking content should be preserved.

defaultinference servingin Gemma 4Google DeepMind

In multi-turn conversations, the historical model output should only include the final output part and does not need to include the thinking content.

usedsoftware implementationin Qwen3.5-397B-A17BQwen

In general, you should drop any previous CoT content on subsequent sampling if the responses by the assistant ended in a message to the final channel.

usedinference servingin gpt-ossOpenAI

In multi-turn conversations, the historical model output should only include the final response. Thoughts from previous model turns must not be added before the next user turn begins, with the exception of tool call turns where thinking content should be preserved.

usedinference servingin Gemma 4Google DeepMind

Filed alongside

Other methods under inference & serving :: context management.