implementation detail · filed under inference & serving
Preserve thinking
A setting or capability for retaining thinking blocks in conversation history, rather than omitting them.
Also called Preserve thinking blocks.
- sources
- 2
- model
- 1
- lab adopt it
- 1
- strongest
- optional
How sources treat it
One count per evidence span, weakest treatment to strongest.
optional 2
Documented in
Evidence
2 spans quoted from the sources, strongest treatment first.
This capability is particularly beneficial for agent scenarios, where maintaining full reasoning context can enhance decision consistency and, in many cases, reduce overall token consumption by minimizing redundant reasoning.
optionalinference servingin Qwen3.6-27BQwen
model, please use"preserve_thinking": Trueinsteadof"chat_template_kwargs": {"preserve_thinking": False}.
optionalinference servingin Qwen3.6-35B-A3BQwen
Filed alongside
Other methods under inference & serving :: context management.
Discard-all context managementPreserved thinking history modeExcluding prior thinking from conversation historyContext compactionContext foldingDiscard-75%Thinking context management for tool useTrajectory summarization and rollout re-initiationContext management methodContext management strategyDiscarding tool-call historyHierarchical context managementKeep-recent-kMemory compressionModality-specific deploymentSummary-based context compressionTest-time context management for extending token budgets