Praxis CI
de2020eee1
TASK-10-01 (G-041 binding): server/__main__.py — SpaStaticFiles custom subclass that returns index.html for non-file paths (NOT a catch-all route). G-041 OVERRIDES the plan's catch-all approach — a catch-all before StaticFiles would shadow asset serving. The subclass serves assets normally + falls back to index.html for client-side routes. Mounted at / AFTER all API routes so they take precedence. TASK-10-02: server/__main__.py — mount operator API routers (cohort, mastery, failure_patterns, credentials) before SPA fallback. Start NightlyScheduler in lifespan (03:00 CT), cancel on shutdown. TASK-10-03: tests/test_p2_aggregation_integration.py — e2e aggregation→ endpoint (12 learners non-suppressed, 5 suppressed), nightly reconcile refreshes last_updated, freshness ≤ 24h. G-038 differencing-attack at API layer. Requires Postgres (skips if no DSN). TASK-10-04: tests/test_p2_spa_fallback.py — 9 assertions: / → voice UI, /operator/* → index.html, API routes → JSON, /assets/* → StaticFiles. R-DASH-03/05 verified. Deviation: GET to POST-only /pipecat/webrtc falls through to SPA fallback (not 405) — acceptable, the POST route is the real entrypoint; a GET is a client-side navigation attempt. TASK-10-05: .ciagent/VERIFY-P2.md — REQ-ID → test mapping for all 4 P2 REQ-IDs + G-038 + G-041 + R-DASH-05. ---ci--- project: praxis phase: 2 milestone: v0.4 status: execute persona: backend-engineer task: 10-01..10-05 requirements: covered: [REQ-DASH-01, REQ-NFR-DASH-01, REQ-NFR-DASH-02, REQ-MT-02] ---/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.