Agentic AI Atlasby a5c.ai
/
GitHubDocsDiscord
iiRecord
Agentic AI Atlas · Babysitter task outputSchema guard
output-guard:babysitter-task-output-schemaa5c.ai
II.
OutputGuard overview

output-guard:babysitter-task-output-schema

Reference · live

Babysitter task outputSchema guard overview

Per-task structural guard. The babysitter SDK accepts an `outputSchema` on agent task definitions (see packages/babysitter-sdk/src/tasks/types.ts:46 and packages/babysitter-sdk/src/prompts/templates/task-kinds.md). At result-posting time the SDK validates the task result against the per-task JSON schema and rejects shape-mismatched results, surfacing a structured error on the journal as part of EFFECT_RESOLVED with status=error. Distinct from `output-guard:claude-code-aup-refusal` (post-call refusal-rewrite over assistant text) — this guard is structural over tool/effect results, not safety/AUP over assistant content.

OutputGuardOutgoing · 0Incoming · 1

Attributes

displayName
Babysitter task outputSchema guard
appliesTo
tool-result
phase
post-call
detectorKinds
  • format-violation
onTrigger
block
severity
block-call
description
Per-task structural guard. The babysitter SDK accepts an `outputSchema` on agent task definitions (see packages/babysitter-sdk/src/tasks/types.ts:46 and packages/babysitter-sdk/src/prompts/templates/task-kinds.md). At result-posting time the SDK validates the task result against the per-task JSON schema and rejects shape-mismatched results, surfacing a structured error on the journal as part of EFFECT_RESOLVED with status=error. Distinct from `output-guard:claude-code-aup-refusal` (post-call refusal-rewrite over assistant text) — this guard is structural over tool/effect results, not safety/AUP over assistant content.

Outgoing edges

None.

Incoming edges

output_guard_applied_by1