Repository navigation
feat(agent): add LiveLlmProvider abstraction and Gemini Live WebSocket provider - #69
Open
juliantoledo wants to merge 2 commits into
Open
juliantoledo wants to merge 2 commits into
juliantoledo wants to merge 2 commits into
Conversation
juliantoledo
force-pushed
the
feat/live-llm-provider
branch
from
November 1, 2026 21:23
d2c1af9 to
e52f370
Compare
mingweiliao
requested changes
Nov 2, 2026
…ider and GeminiLiveProviderImpl
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Part 2 of 5 in the Gemini Live voice assistant series (following #65):
LiveLlmProviderabstraction +GeminiLiveProviderImpl)LiveAudioSession+GeminiLiveAudioHelper)LiveAgentOrchestrator)VoiceInteractionServiceand Live UI integrationChanges in this PR
LiveLlmProvider/LiveLlmSession/LiveLlmEvent: Introduce a provider-agnostic bidirectional streaming abstraction returningLiveLlmSession(withclose()and awithSessionlifecycle extension), supporting configurable input/output sample rates, input/output transcriptions, turn completion, interruption events, tool call requests/responses, andLiveLlmEvent.Error.LlmProviderFactory/LlmProviderFactoryImpl: Extend the provider factory withgetLiveProvider(name: LlmProviderName): LiveLlmProvider.GeminiLiveProviderImpl&GeminiLiveVoice: Implement Gemini Live over theBidiGenerateContentWebSocket endpoint (models/gemini-3.8-live) using KtorWebSockets(withpingIntervalMillisconfigured inDataModule), supporting prebuilt studio voice selection (GeminiLiveVoicepersisted inSettingsRepository), realtime PCM audio streaming, input/output audio transcriptions, and tool call/response frames.GeminiLiveToolConverter&ToolConverter/JsonExtensions: AddGeminiLiveToolConverter(normalizing OpenAPI schema fields forBidiGenerateContent), provider-agnosticselectDistinctTools,findToolByName, andresolveToolNameextensions onToolConverter, and sharedtoPrimitive()/toArgumentsMap()JSON helpers indomain/JsonExtensions.kt.GeminiLiveProviderImplTest,GeminiLiveToolConverterTest,ToolConverterTest, andSettingsRepositoryTest.Test Plan
./gradlew spotlessCheck testStandardDebugUnitTest testRetailDebugUnitTest compileStandardDebugAndroidTestKotlin compileStandardDebugScreenshotTestKotlin