general family · filed under inference & serving
Harmony format
The conversation format required for gpt-oss to work correctly.
Also called harmony response format.
- sources
- 3
- model
- 1
- lab adopt it
- 1
- strongest
- core
How sources treat it
One count per evidence span, weakest treatment to strongest.
core 3
Documented in
Evidence
3 spans quoted from the sources, strongest treatment first.
gpt-oss should not be used without using the harmony format, as it will not work correctly.
coreinference servingin gpt-ossOpenAI
Both models were trained on our harmony response format and should only be used with the harmony format as it will not work correctly otherwise.
coreunclearin gpt-oss-120bOpenAI
should only be used with this format; otherwise, they will not work correctly.
coreinference servingin gpt-ossOpenAI
Filed alongside
Other methods under inference & serving :: agentic scaffolding.
Advisor strategyAutomatic tool choicePython toolFunction callingBrowser 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 policiesAssistant output channelsAsynchronous teammate spawningBash commands for context retrievalBash computer-use agentBrowsing tool with domain filteringChain-of-thought in the analysis channel