Module prelude

Source

Expand description

Convenience re-exports for common types across all layers.

Re-exports§

pub use crate::a2a::A2AServer;
pub use crate::a2a::AgentRegistry;
pub use crate::a2a::RemoteAgent;
pub use crate::a2a::SkillDeclaration;
pub use crate::compose::Ctx;
pub use crate::compose::A;
pub use crate::compose::C;
pub use crate::compose::E;
pub use crate::compose::G;
pub use crate::compose::M;
pub use crate::compose::P;
pub use crate::compose::S;
pub use crate::compose::T;
pub use crate::live::Live;
pub use crate::builder::*;
pub use crate::live_builders::*;
pub use crate::operators::*;
pub use crate::patterns::*;
pub use crate::testing::*;

Modules§

client: Client → Server message types for the Gemini Live wire protocol.
server: Server → Client message types for the Gemini Live wire protocol.

Structs§

ActivityEnd: Marker for speech activity end.
ActivitySignalMessage: Activity signal for client-side VAD events.
ActivitySignalPayload: Payload for activity signals.
ActivityStart: Marker for speech activity start.
AgentSession: Intercepting wrapper around a SessionWriter.
AudioJitterBuffer: Adaptive jitter buffer for audio playback.
AuthCredential: An authentication credential with optional token, refresh, and metadata.
AutomaticActivityDetection: Automatic activity detection (VAD) settings.
BargeInConfig: Configuration for barge-in behavior.
BargeInDetector: Barge-in detector — checks whether user speech should interrupt model output.
Blob: A blob of inline data (audio, image, etc.) sent to or received from Gemini.
CallbackContext: Rich context for callbacks — provides access to state, artifacts, memory, and event actions for mutation.
Candidate: A single response candidate.
CitationMetadata: Citation metadata for a response.
CitationSource: A single citation source.
Client: Unified Gemini API client.
ClientContentMessage: Client content message for sending text or conversation history.
ClientContentPayload: Payload for client content.
CodeExecutionResult: Result of code execution.
ConnectBuilder: Builder for advanced connection configuration.
Content: A content message containing a role and a sequence of parts.
ContextWindowCompressionConfig: Context window compression configuration for long sessions.
DefaultResultFormatter: Default formatter that wraps results in a status object.
DeferredWriter: A SessionWriter wrapper that flushes pending context before user content.
DispatchTextAgent: Fire-and-forget background task launcher with global task budget.
EventCallbacks: Typed callback registry for Live session events.
ExecutableCode: Executable code returned by the model.
FallbackTextAgent: Tries each child agent in sequence. Returns the first successful result. If all fail, returns the last error.
FieldPromotion: Rule for promoting one raw extraction field into authoritative state.
FileData: Reference to an uploaded file.
FnTextAgent: Zero-cost state transform agent — executes a closure, no LLM call.
FsPersistence: File-system persistence (good for development and single-server deployments).
FunctionCall: A function call request from the model.
FunctionCallingConfig: Configuration for function calling behavior.
FunctionDeclaration: Schema for a single function that the model can call.
FunctionResponse: A function call response sent back to the model.
GeminiLlm: Concrete Gemini LLM implementation using gemini-live Client.
GeminiLlmParams: Parameters for constructing a GeminiLlm.
GenerateContentConfig: Configuration for a generateContent request.
GenerateContentResponse: Top-level response from generateContent.
GenerationConfig: Generation config sent in the setup message.
GoAwayMessage: Server GoAway signal — requesting graceful disconnect.
GoAwayPayload: Payload for GoAway.
GoogleAIAuth: Google AI API key authentication.
GoogleAITokenAuth: Google AI OAuth2 access token authentication.
GoogleSearch: Google Search tool configuration (empty — presence enables the feature).
GoogleSearchRetrieval: Google Search retrieval tool configuration.
GroundingMetadata: Grounding metadata for server content with search results.
HttpClient: HTTP client wrapping reqwest with retry and telemetry.
HttpConfig: Configuration for the HTTP client.
InMemoryCredentialService: In-memory credential service for testing and development.
InMemoryRunner: Runs TextAgents with full service wiring (session, memory, artifacts, plugins).
InputAudioTranscription: Input audio transcription configuration.
JitterConfig: Configuration for the jitter buffer.
JoinTextAgent: Waits for dispatched background tasks and collects their results.
JsonCodec: Default JSON codec — current behavior extracted from connection.rs.
LiveHandle: Handle for interacting with a running Live session.
LiveSessionBuilder: Builder for a callback-driven Live session.
LlmExtractor: LLM-backed turn extractor that sends transcript windows to an OOB LLM with a structured extraction prompt.
LlmRegistry: Registry that maps model name patterns to LLM factory functions.
LlmRequest: Configuration for an LLM generation request.
LlmResponse: The response from an LLM generation request.
LlmTextAgent: Core text agent — calls BaseLlm::generate(), dispatches tools, loops until the model produces a final text response.
LoopTextAgent: Runs a text agent repeatedly until max iterations or a state predicate.
MapOverTextAgent: Iterates a single agent over each item in a state list. Reads state[list_key], runs agent per item (setting state[item_key]), collects results into state[output_key].
MediaChunk: A single chunk of media data (audio). Deprecated — use Blob in audio field.
MemoryPersistence: In-memory persistence (good for tests).
MockTransport: Mock transport for unit testing.
ModalityTokenCount: Token count breakdown by modality (text, audio, image, video).
NeedsFulfillment: Tracks need fulfillment per phase and recommends repair actions.
NoOpSessionWriter: A SessionWriter that discards all writes. Used for isolated agent execution (AgentTool) where no real WebSocket exists.
OutputAudioTranscription: Output audio transcription configuration.
ParallelTextAgent: Runs text agents concurrently. All branches share state. Results are collected and joined with newlines.
PendingContext: Thread-safe buffer for pending context turns awaiting delivery.
PrebuiltVoiceConfig: Prebuilt voice selection.
ProactivityConfig: Proactivity configuration — controls whether the model can initiate responses.
RaceTextAgent: Runs agents concurrently, returns the first to complete. Cancels the rest.
RealtimeInputConfig: Server-side VAD configuration for the setup message.
RealtimeInputMessage: Realtime audio input sent as a stream of chunks.
RealtimeInputPayload: Payload for realtime audio input.
RepairConfig: Configuration for the conversation repair system.
ResumeInfo: Session resumption information from the server.
RouteRule: A routing rule: predicate over state → target agent.
RouteTextAgent: State-driven deterministic branching — evaluates predicates in order, dispatches to the first matching agent. Falls back to default if none match.
RunConfig: Configuration for an agent execution run.
SafetyRating: Per-category safety assessment of generated content.
SafetySetting: Per-category safety configuration for content generation.
SequentialTextAgent: Runs text agents sequentially. Each agent sees state mutations from previous agents. The final agent’s output is the pipeline’s output.
ServerContentMessage: Server content message containing model output.
ServerContentPayload: Payload for server content.
ServerMessageWrapper: Server message wrapper — includes optional usage metadata alongside the message.
SessionConfig: Complete session configuration — the builder entrypoint.
SessionHandle: The public API surface for a Gemini Live session.
SessionResumptionConfig: Session resumption configuration.
SessionResumptionResult: Session resumption result from server.
SessionResumptionUpdateMessage: Session resumption update from server (sent during active session).
SessionResumptionUpdatePayload: Payload for session resumption update.
SessionSnapshot: Serializable snapshot of the control plane state.
SetupCompleteMessage: Server setup complete acknowledgment.
SetupCompletePayload: Payload for setup complete.
SetupMessage: Top-level setup message sent immediately after WebSocket connect.
SetupPayload: Payload of the setup message.
SlidingWindow: Sliding window configuration for context compression.
SoftTurnDetector: Detects proactive silence — user stopped speaking but model didn’t respond.
SpeechConfig: Speech configuration for audio output.
SpscRing: Lock-free single-producer single-consumer ring buffer.
State: A concurrent, type-safe state container that agents read from and write to.
StateKey: A compile-time typed state key that eliminates typo bugs and type mismatches.
StaticToolset: A simple toolset backed by a fixed list of tools.
TapTextAgent: Read-only observation agent. Calls a function with the state but cannot mutate it. Returns empty string. No LLM call.
TaskRegistry: Shared registry for dispatched background tasks.
TelemetryConfig: Telemetry configuration.
ThinkingConfig: Configuration for model thinking/reasoning (Gemini 2.5+).
TimeoutTextAgent: Wraps an agent with a time limit. Returns AgentError::Timeout if exceeded.
Tool: A tool declaration sent in the setup message. Each Tool object can contain one of: function declarations, urlContext, googleSearch, codeExecution, or googleSearchRetrieval.
ToolCallCancellationMessage: Server tool call cancellation message.
ToolCallCancellationPayload: Payload for tool call cancellation.
ToolCallMessage: Server tool call request message.
ToolCallPayload: Payload for tool call.
ToolCodeExecution: Code execution tool configuration (empty — presence enables the feature).
ToolConfig: Controls how and when the model uses tools.
ToolConfirmation: Represents a user’s confirmation decision for a tool call.
ToolContext: Extended context for tool execution — adds function call ID and confirmation.
ToolResponseMessage: Tool response message sent after executing function calls.
ToolResponsePayload: Payload for tool response.
TranscriptBuffer: Accumulates input/output transcripts and segments them by turn boundaries.
TranscriptTurn: A single completed conversation turn with accumulated transcripts.
TranscriptionPayload: Transcription text from server.
TransportConfig: Configuration for the transport layer.
TungsteniteTransport: WebSocket transport using tokio-tungstenite.
TurnDetectionConfig: Configuration for client-side turn detection.
TurnDetector: Client-side turn detector.
UrlContext: URL context tool configuration (empty — presence enables the feature).
UrlContextMetadata: URL context metadata for content sourced from URLs.
UsageMetadata: Usage metadata returned by the server on messages.
VadConfig: VAD configuration parameters.
VertexAIAuth: Vertex AI Bearer token authentication.
VertexConfig: Configuration for connecting through Vertex AI.
VoiceActivityDetector: Voice Activity Detector with adaptive noise floor.
VoiceActivityMessage: Server-side voice activity detection event.
VoiceActivityPayload: Payload for voice activity detection.
VoiceConfig: Voice configuration within speech config.

Enums§

ActivityHandling: Controls how incoming audio interacts with model output.
AgentError: Errors that can occur during agent execution.
ApiEndpoint: API endpoint selector — Google AI (direct), Google AI with OAuth token, or Vertex AI.
AudioFormat: Audio encoding formats supported by the Gemini Live API.
AuthError: Authentication-specific errors.
BargeInAction: Result of a barge-in check.
CallbackMode: Controls how a control-lane callback is executed relative to the event loop.
CodecError: Error during encoding or decoding.
ContextDelivery: When to deliver model-role context turns to the wire.
ExtractionTrigger: Controls WHEN an extractor runs.
FinishReason: Why the model stopped generating.
FunctionCallingBehavior: Whether tool calls block model output or run concurrently.
FunctionCallingMode: How the model should decide when to execute tool calls.
FunctionResponseScheduling: Scheduling mode for non-blocking function responses.
GeminiModel: Gemini models that support the Multimodal Live API.
GenerateError: Errors specific to the Generate API.
HarmBlockThreshold: Blocking threshold for safety settings.
HarmCategory: Categories of potential harm in model output.
HarmProbability: Probability that content is harmful.
HttpError: Errors from HTTP client operations.
InputEvent: Input events broadcast to input-streaming tools. Distinct from SessionCommand — this is observation-only.
LiveEvent: Semantic events emitted by the Live session processor.
MediaResolution: Media resolution for image/video inputs.
MergePolicy: How an extracted field should be merged into authoritative session state.
Modality: Output modalities the model can produce.
Part: A single part of a Content message. Parts are polymorphic — discriminated by field presence, not a type tag.
Platform: Which platform variant to use for the Gemini API.
RepairAction: What action the repair system recommends.
Role: Role in a conversation.
Sensitivity: Voice activity detection sensitivity level.
ServerMessage: Unified server message enum — parsed from incoming WebSocket text frames.
ServiceEndpoint: Identifies which Gemini API service to connect to.
SessionCommand: Commands sent from application code to the session transport.
SessionError: Errors that can occur during a session.
SessionEvent: Events emitted by the session, consumed by application code.
SessionPhase: The lifecycle phase of a Gemini Live session.
SetupError: Errors during the setup handshake phase.
SteeringMode: How the phase machine steers the model’s behavior.
StreamingMode: How the agent communicates with clients.
ToolError: Errors that can occur during tool execution.
ToolExecutionMode: Execution mode for a tool.
TurnCoverage: Controls which input counts toward a user’s conversation turn.
TurnDetectionEvent: Events from the turn detector.
VadEvent: Events emitted by the VAD.
Voice: Available voice presets for Gemini Live audio output.
VoiceActivityType: Type of voice activity event from the server.
WebSocketError: WebSocket-level errors with structured detail.

Traits§

AuthProvider: Provides authentication credentials and URL construction for Gemini API connections.
BaseLlm: Trait for LLM providers — decouples agents from specific models.
Codec: Encodes client commands into wire bytes and decodes server bytes into messages.
CredentialService: Trait for credential persistence — load, save, delete.
ResultFormatter: Formats tool responses for background execution lifecycle.
SessionPersistence: Trait for persisting session state across process restarts.
SessionReader: Read-side of a session — subscribe to events and observe phase.
SessionWriter: Write-side of a session — send commands without owning the full handle.
TextAgent: A text-based agent that runs via BaseLlm::generate() (request/response).
ToolProvider: Declares tools for a Gemini session setup message. Implement this trait to provide tools from any source (runtime ToolDispatcher, etc.).
Toolset: A collection of tools that can be enumerated.
Transport: A bidirectional message transport.
TurnExtractor: Trait for between-turn extraction from transcript windows.

Functions§

bytes_to_i16: Convert raw bytes to i16 PCM samples (zero-copy via bytemuck).
connect: Connect to the Gemini Multimodal Live API and return a session handle.
connect_with: Connect with a custom transport and codec.
i16_to_bytes: Convert a slice of i16 PCM samples to raw bytes (zero-copy via bytemuck).
inject_session_state: Replace {key} placeholders in template with values from state.
into_shared: Wrap raw bytes as a shared Bytes handle for zero-copy fan-out.
quick_connect: Connect to Gemini Live with minimal configuration.
quick_connect_vertex: Connect via Vertex AI with minimal configuration.
recv_event: Receive the next event from a broadcast receiver, handling lag gracefully.

Type Aliases§

ToolDeclaration: Backward-compatible alias for Tool.

Module prelude

Module prelude Copy item path

Re-exports§

Modules§

Structs§

Enums§

Traits§

Functions§

Type Aliases§

Module prelude