Praxis CI
f2a12f9fed
v0.4 (Operator Tier — Cohort Dashboard + Auth + Postgres) milestone complete. Phases: ✓ P0 pre-execution (planning) → v0.1.6 ✓ P1 operator foundation (Postgres+auth+VC migration) → v0.1.7 ✓ P2 cohort dashboard + aggregation → v0.1.8 ✓ P3 final review + ship → v0.1.9 (= v0.4 milestone release) Requirements covered (8/8): REQ-MT-01 (Postgres store), REQ-MT-02 (aggregation pipeline), REQ-AUTH-01 (operator auth), REQ-DASH-01 (cohort dashboard), REQ-NFR-AUTH-01 (auth NFRs), REQ-NFR-MT-01 (Postgres-in-LXC), REQ-NFR-DASH-01 (k-anonymity ≥10), REQ-NFR-DASH-02 (freshness ≤24h) Grill MUSTs honored (6/6): G-008, G-011, G-027, G-031, G-038, G-041 Tests: 317 pytest pass, 36 skip (Postgres-requiring), 0 fail; 17/17 vitest pass Review: APPROVE_WITH_NOTES (6/6 personas, 0 P0, 8 P1+ carry-forward) Audit: HEALTHY (reconstruction PASS, 8/8 REQ, 6/6 grill) ---ci--- project: praxis phase: 3 milestone: v0.4 status: complete phase_role: final milestone_complete: true milestone_merged_to_main: true tag: v0.1.9 requirements: covered: [REQ-MT-01, REQ-MT-02, REQ-AUTH-01, REQ-DASH-01, REQ-NFR-AUTH-01, REQ-NFR-MT-01, REQ-NFR-DASH-01, REQ-NFR-DASH-02] partial: [] ---/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.