Praxis CI
6cf63cb064
Verification layers: Structural: PASS (all scripts executable, syntax clean, Dockerfile valid) Behavioral: PASS (121 bats, 77 pytest, docker build succeeds, compose valid) Security: PASS (no secrets committed, .dockerignore excludes .env*, env_file pattern) Quality: PASS (coreci patterns followed, no coreci refs, G-104/G-105/G-106 verified) P0 issues found and auto-fixed: 1. docker-compose.yml: removed invalid restart_policy key, fixed env_file syntax 2. pyproject.toml: added fastapi + uvicorn deps (v0.1 gap exposed by Dockerfile) 3. timing.sh: renamed coreci_deploy_timing → praxis_deploy_timing (TASK-03-07) 4. firstboot-hook.sh: fixed idempotency check (/opt/praxis/.git not /usr/local/bin/praxis-deploy) P1+ issues: 8 (1 fixed: lxc-config.sh default alignment, 7 noted for post-hoc review) REQ coverage: 18/20 covered, 2 deferred (live first-boot timing + live E2E require cluster) Must-haves: 25/28 pass, 2 partial (comment-only diffs, no Makefile), 1 deferred ---ci--- project: praxis phase: 1 milestone: v0.2 status: verify ---/ci---
Praxis — v0.1 Foundation
Voice-first AI apprenticeship platform. v0.1 is a tech-validation harness (per G-008) for the minimal viable voice loop: a single learner speaks to an AI tutor playing a Customer Service role-play scenario, hears a <600ms-latency response, receives an end-of-session coaching debrief, and has the session logged to SQLite.
Status
Phase 1 (minimal viable voice loop) — code-complete, pending live API keys for runtime verification.
Stack
- Orchestration: Pipecat (D-017) with Silero VAD + interruptibility
- ASR: Deepgram Nova-3 streaming (D-013)
- LLM: Ollama Cloud direct API (D-020) —
gemma4:cloud(role-play) +deepseek-v4-flash:cloudno-think (debrief) - TTS: Cartesia Sonic (primary, D-014) / Piper (self-hosted, R4 mitigation) — behind an interface
- Client: React + Vite + WebRTC (Pipecat client SDK, D-015)
- State: SQLite
praxis.db(D-007, single hardcoded learner, no auth)
Layout
server/ Pipecat pipeline, services (TTS/LLM/Guardrail interfaces), scenario runtime, adapters
client/ React + Vite + WebRTC learner surface
scenarios/ YAML scenario definitions (D-018)
db/ SQLite schema, migrations, async store
scripts/ Latency probes (R1-R4), e2e smoke
tests/ Unit + e2e
docs/ Latency report, debrief templates
Quickstart
- Copy
.env.example→.env, fill inDEEPGRAM_API_KEY,CARTESIA_API_KEY,OLLAMA_API_KEY. - Install server deps:
pip install -e ".[dev]" - Install client deps:
cd client && npm install - Run probes:
python scripts/probe_deepgram.py(etc.) - Run server:
python -m server - Run client:
cd client && npm run dev
See docs/latency-report.md for the R1-R4 spike status and TTS decision.