Lifecycle
Output policy
Control whether intermediate SubAgent narration becomes public.
Output policy changes which model messages Harnest publishes. It does not change prompts or model responses.
Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
Control whether intermediate SubAgent narration becomes public.
| Value | Behavior |
|---|---|
suppress | Hide provisional SubAgent narration; the default |
include | Publish that narration to neutral transports and the playground |
from harnest.lifecycle import lifecycle
from harnest.output import OutputPolicy
@lifecycle.output_policy
def output_policy():
return OutputPolicy(subagent_messages="include")
| Event | suppress | include |
|---|---|---|
| Root-agent messages | Yes | Yes |
| Tool calls and results | Yes | Yes |
| Final answer | Yes | Yes |
| Intermediate SubAgent narration | No | Yes |
| Hidden model reasoning | No | No |
include only when your product deliberately presents progress.| Property | Rule |
|---|---|
| Factory | Synchronous and zero-argument |
| Allowed | Zero or one per root agent |
| Frameworks | Managed and advanced roots through neutral routes |
| Native routes | Framework-owned |
| Tests | Does not change authored fixtures |