specific method · filed under inference & serving
Assistant output channels
Channel labels separate user-facing assistant responses from internal messages.
Also called channels.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- core
How sources treat it
One count per evidence span, weakest treatment to strongest.
core 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
Assistant messages can be output in three different “channels”. These are being used to separate between user-facing responses and internal facing messages.
coreinference servingin gpt-ossOpenAI
Filed alongside
Other methods under inference & serving :: agentic scaffolding.
Advisor strategyAutomatic tool choicePython toolFunction callingHarmony formatBrowser toolGeneric tool-call parserMCP tool configurationMulti-agent collaborationRole-based instruction hierarchyThinking with toolsVisual Search ToolXML-based tool-call schema with DSML tokenAgent Team modeAgentENVAgentic searchAgentic tool callingApp-server mode with adapted tool schemasAppArmor and eBPF sandbox policiesAsynchronous teammate spawningBash commands for context retrievalBash computer-use agentBrowsing tool with domain filteringChain-of-thought in the analysis channel