Class GeminiModerationCapabilityImpl

Adapts Gemini moderation responses into ProviderPlaneAI's normalized moderation artifact surface.

Gemini does not expose a dedicated moderation endpoint, so this adapter uses a structured JSON generation prompt and normalizes the parsed result.

Implements

ModerationCapability<ClientModerationRequest, NormalizedModeration[]>

Index

Constructors

Methods

Constructors

constructor

new GeminiModerationCapabilityImpl(
provider: BaseProvider,
client: GoogleGenAI,
): GeminiModerationCapabilityImpl
Creates a new Gemini moderation capability adapter.
Parameters
- provider: BaseProvider
  Owning provider instance used for initialization checks and merged config access.
- client: GoogleGenAI
  Initialized Google GenAI SDK client.
Returns GeminiModerationCapabilityImpl
- Defined in src/providers/gemini/capabilities/GeminiModerationCapabilityImpl.ts:59

Methods

moderation

moderation(
    request: AIRequest<ClientModerationRequest>,
    _executionContext?: MultiModalExecutionContext,
    signal?: AbortSignal,
): Promise<AIResponse<NormalizedModeration[]>>
Executes a Gemini moderation request.

Responsibilities:
- validate moderation input
- resolve merged model/runtime options
- execute one structured moderation request per input string
- parse Gemini JSON output into normalized moderation artifacts
- attach provider/model/request metadata
Parameters
- request: AIRequest<ClientModerationRequest>
  Unified moderation request envelope.
- Optional_executionContext: MultiModalExecutionContext
  Optional execution context. Unused directly in this adapter.
- Optionalsignal: AbortSignal
  Optional cancellation signal.
Returns Promise<AIResponse<NormalizedModeration[]>>
Provider-normalized moderation artifacts.

Throws
When input is invalid or the provider call fails.
Implementation of ModerationCapability.moderation
- Defined in src/providers/gemini/capabilities/GeminiModerationCapabilityImpl.ts:80