Member Junction
    Preparing search index...

    Concrete IRealtimeSession backed by a raw AssemblyAI Voice Agent websocket.

    Owns the inbound translation (flat snake_case wire events → Core events) and the outbound translation (Core calls → wire frames). Created by AssemblyAIRealtime.StartSession; never instantiated directly by consumers.

    Provider-behavior notes (the contract deltas a consumer should know):

    • User transcripts have DELTAS, agent transcripts are FINAL-only. The socket emits transcript.user.delta fragments followed by a final transcript.user; agent turns arrive as one final transcript.agent (carrying interrupted: true after a barge-in, in which case the text reflects the truncated turn — already the authoritative record, no ElevenLabs-style correction event follows).
    • Interruption signal is reply.done with status: 'interrupted' — the provider owns turn detection AND tracks its own audio emission, so this is the authoritative "user speech cut off active model output" signal (raw input.speech.started fires on EVERY user utterance and is NOT an interruption per the base contract; the server bridge also cannot see host-side playback, so it defers to the provider's verdict).
    • No usage events — see the driver-level note.
    • RequestSpokenUpdate is NATIVE (reply.create carries per-response instructions — no ElevenLabs-style user-turn emulation, no fidelity caveat), queued behind any in-flight response per the contract's collision rule.
    • SendContextNote is EMULATED via the mutable system_prompt: the protocol has no non-interrupting context channel, but session.update may rewrite the prompt mid-session without triggering generation — notes are appended under a "Background updates" heading and the full prompt is re-sent. Never interrupts; the model sees the notes the next time it speaks.
    • RegisterTools re-declares NATIVELY: tools is a mutable session.update field, so (unlike ElevenLabs) a genuinely different post-start set is applied to the live session; an identical set is a silent no-op per the idempotency rule.

    Hierarchy (View Summary)

    Implements

    Index

    Constructors

    Properties

    callsFromBeforeReseed: Set<string>
    closedByConsumer: boolean
    configuredCallDurationSeconds: number
    configuredReconnectBufferSeconds: number
    configuredSessionMaxSeconds: number
    configuredTrustNativeResumption: boolean
    configuredZeroDataRetention: boolean
    conversationMemory: RealtimeConversationMemory
    pendingToolCallNames: Map<string, string>
    reconnectController: RealtimeReconnectController
    turnOpen: boolean

    Accessors

    • get CallDurationSeconds(): number

      Effective single-connection duration in seconds, resolved via ClampSessionSecondsValue so metadata (configuredCallDurationSeconds) narrows the driver's provider ceiling (DefaultCallDurationSeconds) and any state-dependent RuntimeCallDurationSeconds, never widening it.

      Returns number

    • get ConversationMemory(): RealtimeConversationMemory

      Accessor for the session's provider-neutral conversation memory ledger.

      Returns RealtimeConversationMemory

    • get DefaultCallDurationSeconds(): number

      Static driver default connection duration in seconds when metadata does not specify one.

      Returns number

    • get DefaultTrustsNativeResumption(): boolean

      Driver default for whether native resumption handles are trusted when metadata does not override.

      Returns boolean

    • get IsClosedByConsumer(): boolean

      True once the consumer has closed the session.

      Returns boolean

    • get IsReconnecting(): boolean

      True while an in-place reconnect is currently running.

      Returns boolean

    • get ReconnectBufferSeconds(): number

      Buffer in seconds before CallDurationSeconds at which the framework initiates a reconnect.

      Returns number

    • get RequiresPostTurnResumptionHandle(): boolean

      Whether this session's provider emits a fresh resumable handle shortly after each turnComplete (e.g. Gemini / Vertex AI Live), so a planned move (goAway or soft window) during a turn waits for that post-turn handle (bounded by the deadline timer) rather than resuming from a pre-turn handle.

      Returns boolean

    • get ResumptionHandle(): string

      Latest recorded provider resumption handle, or null if none.

      Returns string

    • get RuntimeCallDurationSeconds(): number

      Dynamic state-dependent duration cap in seconds (for example, returning 120 when uncompressed video is active on Gemini Live, and undefined otherwise). Clamped with configuredCallDurationSeconds via ClampSessionSecondsValue so neither a seeded 600s catalog value nor a tighter custom metadata value (e.g., 45s) is shadowed.

      Returns number

    • get SessionMaxSeconds(): number

      Configured credential/session lifetime in seconds, when distinct from CallDurationSeconds.

      Returns number

    • get TrustsNativeResumption(): boolean

      Whether native resumption is trusted on this session (always false under ZeroDataRetention).

      Returns boolean

    Methods

    • Extracts timing and native-resumption overrides from a session configuration bag.

      Parameters

      • config: Record<string, unknown>

      Returns void

    • Arms (or re-arms) the proactive connection-duration timer for the current connection.

      Returns void

    • Cancels all reconnect and duration timers and abandons any in-flight attempt when closed by the consumer. Tool results held for the attempt are dropped: no new connection will carry them.

      Returns void

    • Surfaces an UNEXPECTED socket close as a fatal error (expected closes — the consumer called Close — are silent). The provider hard-closes at token expiry and when it ends the session itself, so this is also how credential / session death reaches the consumer.

      Parameters

      Returns void

    • Holds a tool result that arrives while a reconnect is moving the session, and returns true when it did. Sent then, the result would reach the connection being replaced after the attempt's seed was built, so the new connection would have the call and never its result. A driver calls this first in SendToolResult and returns when it is true. Once the move lands the result goes through SendToolResult again, after callsFromBeforeReseed is rebuilt, so a reseeded connection gets it as a late-result note; a failed reconnect or a close drops it with a warning. Outside a reconnect it returns false and changes nothing.

      Parameters

      • callID: string
      • output: string
      • OptionaltaskRevision: number

      Returns boolean

    • Clears the recorded resumption handle so subsequent reconnects fall back to history seeding.

      Returns void

    • Handles a provider-initiated connection-ending advisory (goAway / session.going_away). Reconnects immediately if idle and ready, or waits for the turn/handle boundary up to the scaled deadline.

      Parameters

      • OptionaltimeLeftMs: number

      Returns void

    • Notifies the reconnect controller when pending tool calls drain on SendToolResult. When expectsReply is true (default), a queued soft-window or ConnectionEnding move waits for the model's post-tool turn (or a fresh trusted native handle) rather than reconnecting in the gap between SendToolResult and the first model output frame.

      Parameters

      • OptionalexpectsReply: boolean

      Returns void

    • Marks a turn as ended and triggers a queued soft-window or ConnectionEnding reconnect if ready.

      Parameters

      • OptionalkeepPostToolTurnWait: boolean

      Returns void

    • Marks a turn as open so soft-window reconnects wait for the turn boundary.

      Returns void

    • Registers a handler for session errors.

      Fatality semantics mirror the client-side BaseRealtimeClient contract:

      • Fatal: true — the session is unusable (transport/socket failure, credential/token expiry, unexpected connection loss). The consumer should finalize the session (e.g. RealtimeSessionRunner calls Stop()) instead of idling forever on a dead socket.
      • Fatal: false — a provider-reported, recoverable error frame; the session stays open and the consumer should log and continue.

      Parameters

      Returns void

    • Registers a handler for provider-detected interruptions (barge-in).

      True barge-in only: the handler fires ONLY when user speech interrupts ACTIVE model output — NOT on every user utterance. A user simply taking their normal turn while the model is idle is not an interruption, and drivers must not report it as one (e.g. a raw "speech started" frame must be gated on whether a model response is actually in flight).

      Turn detection / VAD is owned by the provider. The agent layer uses this hook to cancel the model's current turn and to fire the cancellationToken of any in-flight delegated agent run — a stale delegated result must never be narrated into a conversation that has moved on.

      Parameters

      • handler: () => void

        Invoked when the provider reports a true barge-in interruption.

      Returns void

    • Hook invoked when a reconnect attempt succeeds.

      Parameters

      • _usedNativeResumption: boolean

      Returns void

    • Records a provider resumption handle or conversation ID.

      Parameters

      • handle: string
      • Optionalresumable: boolean

      Returns void

    • Registers the set of tools the model may call, translating them into the provider's native function-calling format.

      The Core-level RealtimeToolDefinition is intentionally minimal: BaseRealtimeModel lives in the lowest AI layer and cannot depend on the richer tool metadata defined in higher packages (the agent layer) — doing so would create an illegal upward/circular dependency. The agent layer is responsible for mapping its richer tool metadata down to this Core type before calling RegisterTools, and the concrete driver maps this Core type up to the provider's native function-calling schema.

      Note that some providers (e.g. Eleven Labs) bind to a pre-declared tool set on a server-side agent configuration; for those, the driver maps these definitions onto the pre-declared tool names rather than registering arbitrary schemas at session start.

      Idempotency rule: a post-start registration of a set IDENTICAL to the set supplied at connect time (via RealtimeSessionParams.Tools) MUST be a no-op. Providers that bind their tool set at connect time and cannot re-declare schemas on an open session MUST no-op (and may log) rather than degrade the conversation — e.g. by injecting schema text into the conversation as content. A genuinely DIFFERENT post-start set on such a provider is unsupported and should be surfaced as a warning, not silently mangled.

      Parameters

      Returns Promise<void>

    • Parameters

      • instructions: string

      Returns void

      on this provider: reply.create carries one-off per-response instructions. Collision behavior: queue. A reply.create sent mid-reply would collide with the in-flight generation, so the send is deferred until the active reply completes.

    • Sends the initial session.update frame carrying the full server-authored session config (prompt, tools, voice, turn detection). Always the FIRST client frame — the provider drops audio sent before the session is configured and ready.

      Returns void

    • Parameters

      • callID: string
      • output: string

      Returns Promise<void>

      tool.result correlated by call_id. Sent IMMEDIATELY (never queued behind a reply): the provider's own guidance is "send it the moment your tool returns — no buffering, no waiting on reply.done"; it owns the continuation and speaks the result as soon as the floor allows. The one wait is a reconnect: the result is held and sent on the new socket (holdToolResultDuringReconnect). The wire result slot expects a JSON-STRING (not an object), which is exactly the contract's output shape — it passes through verbatim. The reply flag is set eagerly so a queued narration can't slip in before the spoken result.