iiRecord
Agentic AI Atlas · pi-mono coding-agent output guard
output-guard:pi-coding-agenta5c.ai
II.
OutputGuard overview

output-guard:pi-coding-agent

Reference · live

pi-mono coding-agent output guard overview

Streaming + post-call guard sitting in front of pi-mono's event-bus. Inspects assistant_message_delta chunks and tool_result blocks before they hit the user-facing channel, raising warnings or rewriting per detector. Distinct from the compliance-side ContentPolicy — this is the runtime gate, not the policy declaration.

OutputGuardOutgoing · 0Incoming · 1

Attributes

displayName
pi-mono coding-agent output guard
appliesTo
all
phase
both
detectorKinds
  • refusal-stop-reason
  • secret-leak
  • format-violation
  • custom
onTrigger
emit-system-message
severity
warn
description
Streaming + post-call guard sitting in front of pi-mono's event-bus. Inspects assistant_message_delta chunks and tool_result blocks before they hit the user-facing channel, raising warnings or rewriting per detector. Distinct from the compliance-side ContentPolicy — this is the runtime gate, not the policy declaration.

Outgoing edges

None.

Incoming edges

output_guard_applied_by1