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---
Praxis CI
bba99418df