II.
OutputGuard overview
Reference · liveoutput-guard:gemini-response-mime-type-json
Gemini responseMimeType=application/json guard overview
Google Gemini API generationConfig accepts `responseMimeType: "application/json"` and an optional `responseSchema`. The server constrains output to valid JSON matching the schema and rejects malformed candidates, returning structural error metadata. Doc: ai.google.dev/gemini-api/docs/structured-output.
Attributes
displayName
Gemini responseMimeType=application/json guard
appliesTo
tool-result
phase
post-call
detectorKinds
- format-violation
onTrigger
block
severity
block-call
description
Google Gemini API generationConfig accepts
`responseMimeType: "application/json"` and an optional `responseSchema`.
The server constrains output to valid JSON matching the schema and
rejects malformed candidates, returning structural error metadata.
Doc: ai.google.dev/gemini-api/docs/structured-output.
Outgoing edges
None.
Incoming edges
output_guard_applied_by1
- agent-core-impl:gemini-cli.core@current·AgentCoreImplGemini CLI Core (current)