praxis

coreci/praxis

Fork 0

Commit Graph

Author	SHA1	Message	Date
Praxis CI	7b1b296430	feat(P01-02-05,P01-02-06): React client + latency readout client/ — React + Vite + TypeScript scaffolded with the Pipecat client SDK (@pipecat-ai/client-js) and SmallWebRTCTransport (@pipecat-ai/small-webrtc-transport). useVoiceSession.ts hook manages mic permission, WebRTC connect, audio playback, live transcript, and a latency readout (captures the e2e_latency_ms metric the server emits). App.tsx is a minimal one-page session UI: disclaimer, Start/End buttons, status badge, latency readout (within/over 600ms budget), live transcript. vite.config.ts proxies /pipecat + /health to the Python server (port 8789). npm run typecheck + npm run build pass. server/latency.py — LatencyObserver (a Pipecat FrameProcessor) timestamps transcript-ready, LLM-first-token, TTS-first-audio, and playback-start per turn, computes ASR→TTS-first-audio (the v0.1 latency target), and logs it to console with a within/over-budget verdict. Wired into the pipeline between STT/LLM/TTS so it observes without altering the frame stream. 5 unit tests pass (LatencyRecord e2e math + observer construction + reset_turn). Full server suite: 18 passed. ---ci--- phase: 1 milestone: v0.1 plan: 02 task: 02-05,02-06 status: execute persona: frontend-engineer,backend-engineer requirements: covered: [REQ-VOICE-01, REQ-VOICE-02, REQ-VOICE-03, REQ-NFR-LAT-01] ---/ci---	2026-08-01 13:08:42 +00:00
Praxis CI	bba99418df	feat(P01-02-04): Pipecat server pipeline — Silero VAD→Deepgram→Ollama→TTS→WebRTC server/pipeline.py assembles the Pipecat pipeline (D-017): WebRTC audio in → Deepgram Nova-3 STT → LLMContextAggregator(user) → OLLamaLLMService (gemma4:cloud via https://ollama.com/v1 + bearer, R6) → Cartesia/Piper TTS (selected via PRAXIS_TTS) → WebRTC audio out. Interruptibility via allow_interruptions=True (D-008 abort-and-yield). Hardcoded single-turn system prompt (SLICE-03 replaces with scenario YAML). All keys from env; missing keys log a warning and the pipeline still starts (code structure is the deliverable). server/__main__.py exposes a FastAPI app with /health (reports key-provisioning status) and POST /pipecat/webrtc (accepts an SDP offer, starts a pipeline task, returns the answer). Verified: imports succeed, /health returns 200, routes wired. ---ci--- phase: 1 milestone: v0.1 plan: 02 task: 02-04 status: execute persona: backend-engineer requirements: covered: [REQ-VOICE-01, REQ-VOICE-02, REQ-VOICE-04, REQ-ORCH-01] ---/ci---	2026-08-01 13:04:17 +00:00

Author

SHA1

Message

Date

Praxis CI

7b1b296430

feat(P01-02-05,P01-02-06): React client + latency readout

client/ — React + Vite + TypeScript scaffolded with the Pipecat client SDK
(@pipecat-ai/client-js) and SmallWebRTCTransport
(@pipecat-ai/small-webrtc-transport). useVoiceSession.ts hook manages mic
permission, WebRTC connect, audio playback, live transcript, and a latency
readout (captures the e2e_latency_ms metric the server emits). App.tsx is a
minimal one-page session UI: disclaimer, Start/End buttons, status badge,
latency readout (within/over 600ms budget), live transcript. vite.config.ts
proxies /pipecat + /health to the Python server (port 8789). npm run
typecheck + npm run build pass.

server/latency.py — LatencyObserver (a Pipecat FrameProcessor) timestamps
transcript-ready, LLM-first-token, TTS-first-audio, and playback-start per
turn, computes ASR→TTS-first-audio (the v0.1 latency target), and logs it
to console with a within/over-budget verdict. Wired into the pipeline
between STT/LLM/TTS so it observes without altering the frame stream. 5
unit tests pass (LatencyRecord e2e math + observer construction +
reset_turn). Full server suite: 18 passed.

---ci---
phase: 1
milestone: v0.1
plan: 02
task: 02-05,02-06
status: execute
persona: frontend-engineer,backend-engineer
requirements:
  covered: [REQ-VOICE-01, REQ-VOICE-02, REQ-VOICE-03, REQ-NFR-LAT-01]
---/ci---

2026-08-01 13:08:42 +00:00

Praxis CI

bba99418df

feat(P01-02-04): Pipecat server pipeline — Silero VAD→Deepgram→Ollama→TTS→WebRTC

server/pipeline.py assembles the Pipecat pipeline (D-017): WebRTC audio in →
Deepgram Nova-3 STT → LLMContextAggregator(user) → OLLamaLLMService
(gemma4:cloud via https://ollama.com/v1 + bearer, R6) → Cartesia/Piper TTS
(selected via PRAXIS_TTS) → WebRTC audio out. Interruptibility via
allow_interruptions=True (D-008 abort-and-yield). Hardcoded single-turn
system prompt (SLICE-03 replaces with scenario YAML). All keys from env;
missing keys log a warning and the pipeline still starts (code structure is
the deliverable). server/__main__.py exposes a FastAPI app with /health
(reports key-provisioning status) and POST /pipecat/webrtc (accepts an SDP
offer, starts a pipeline task, returns the answer). Verified: imports
succeed, /health returns 200, routes wired.

---ci---
phase: 1
milestone: v0.1
plan: 02
task: 02-04
status: execute
persona: backend-engineer
requirements:
  covered: [REQ-VOICE-01, REQ-VOICE-02, REQ-VOICE-04, REQ-ORCH-01]
---/ci---

2026-08-01 13:04:17 +00:00

2 Commits