feat: streaming replies, stop/cancel, thinking traces, in-app voice, GPU backend selector#38
Merged
Merged
Conversation
…GPU backend selector - Cloud SSE streaming with reasoning deltas and incremental tool calls; buffered fallback - Cooperative cancellation (Stop) aborting the cloud stream and local generation - Live streaming bubble, typing indicator, collapsible thinking trace - In-app voice: speech_to_text + flutter_tts, composer mic, listening overlay - LiteRT-LM GPU backend with automatic CPU fallback + Settings CPU/GPU toggle
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes #37
Summary
Three related upgrades to the assistant experience.
1. Streaming replies + Stop/cancel + thinking traces
content+reasoningdeltas,incremental tool calls); buffered fallback when streaming isn't used.
AgentCancelToken) — Stop button aborts the HTTPstream and any local generation, committing whatever streamed so far.
(reasoning) panel; ~30fps coalesced repaints.
2. In-app voice
VoiceControllerwithspeech_to_text+flutter_tts: hold-to-dictate andtap-for-conversation, speaks replies.
3. On-device model GPU/CPU selector
Settings toggle lets the user force CPU.
Verification
flutter analyze: clean.LiteRT-LM initialized on GPU backend);streaming + Stop + voice exercised manually.