OptionalCanWhether delegation mode can be reconfigured mid-session.
Whether the session can change its turn-taking / auto-response mode on a live socket (no
reconnect) via IRealtimeSession.Reconfigure. true for providers with a runtime-mutable
session config (OpenAI session.update); false where it's fixed at connect (Gemini Live).
OptionalEmitsWhether the provider emits a discrete signal when model generation is cut off.
OptionalEmitsWhether the provider emits a response-complete signal when a turn ends.
OptionalEmitsWhether the provider emits a discrete user-interruption signal when user barge-in occurs.
OptionalMaxMaximum number of concurrent delegations supported by the provider, or undefined if unbounded.
OptionalProvidesWhether this driver provides speech-to-text transcript events for user audio input.
OptionalProvidesWhether this driver provides text transcript events for model audio output.
OptionalSupportedWhich reasoning planes this driver supports (e.g. ['local'], ['remote'], or ['local', 'remote']).
OptionalSupportsWhether this driver supports dynamic, multi-tool sets projected into the realtime session (e.g. direct action invocation on realtime co-agents).
When true, allowed target agent actions can be registered as direct tools on the realtime model.
When absent or false, only single/co-agent delegation tools (invoke-target-agent) are registered.
OptionalSupportsWhether the provider supports receiving multiple parallel tool calls and batched results (gpt-live-1.md §4.2).
OptionalUsageThe units this provider uses to measure and bill usage: tokens, seconds, or both.
Static capability flags of a live IRealtimeSession, for container introspection (the realtime- session analogue of
IBridgeProviderFeatures). Grow this as providers gain runtime abilities — each new flag defaults to "unsupported" for any driver that hasn't declared it, so the container stays safe.