single source · inference & serving
Assistant output channels
Assistant output channels tag every message the model emits as analysis, commentary, or final.1 The channels separate internal messages, such as tool calls routed to the analysis channel, from user-facing output.2,3
How this definition was written
Summarised by glm-5.3-flash from 1 source; every sentence is checked against the quote it cites.
Valid channels: analysis, commentary, final. Channel must be included for every message
— OpenAI Harmony Response FormatRequests will be made to the analysis channel
— OpenAI Harmony Response FormatThe code will not be shown to the user
— OpenAI Harmony Response Format
Also called channels.
Filed under inference & serving › agentic scaffolding