Feat/linux pulseaudio audio#152
Open
xingjianll wants to merge 8 commits into
Open
Conversation
On Linux, use parec/paplay subprocess to access PulseAudio/PipeWire virtual devices (e.g. cable_a.monitor, cable_b) that sounddevice can't see through ALSA. Device dropdown lists PulseAudio sources/sinks via pactl. Falls back to sounddevice on macOS/Windows. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Single component replaces separate VAD + ASR pipeline. Streams audio to Deepgram's WebSocket API (nova-3), returns final transcriptions with speaker labels (e.g. "[Speaker 0] hello"). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Removes messages output, adds token/text/tool_calls/eos outputs (same as LLM) - Calls OpenAI Responses API directly with streaming - Recursive _call_llm for tool call → tool result → LLM loop - Accepts ToolDef inputs for function calling - Drains speech/feedback/vision/objects/pose/memory each iteration - Only calls LLM when new user input arrives Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…tchpad tool - AgentLoop calls OpenAI Responses API directly (no external LLM component) - Accepts VideoFrame input, encodes as base64 JPEG for vision - Built-in diary tool for tracking mental state (handled internally) - ScratchpadTool component with read/update tools - Continuous loop with no speech gating — agent is always active - No recursion — flat loop with fresh transient context each iteration - System prompt emphasizes embodiment and vision grounding Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Use ToolResult frame instead of TextFrame for tool_result input - Use result.call_id instead of local tc dict for correct pairing - Add head look heading alongside body heading in pose context - Add debug prints for pose data Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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.
No description provided.