Praxis CI
be3df525d8
server/scenarios/schema.py defines the typed model: Scenario (id, path, market, language, title, difficulty, failure_mode, persona, setup, success_criteria, common_mistakes, branches[], debrief) + Branch (id, trigger.learner_signals, outcome, failure_mode, debrief_focus) + ScenarioDebrief (model=deepseek-v4-flash:cloud, mode=no_think, D-020). failure_mode field present per D-009. server/scenarios/loader.py loads YAML → Pydantic, validates at load time, raises typed ValidationError on bad input. scenarios/customer_service_refund_ca_v01.yaml — the v0.1 Canada Customer Service scenario (D-010): 'Angry customer requesting refund on a damaged product', one branch point (accept_resolution vs escalate), failure_mode=escalates_unresolved, success criteria, common mistakes, debrief config. Matches the RESEARCH.md example. 5 unit tests pass (valid parse, invalid raises typed error, branch outcome Literal, branch_by_id, real YAML load). load() returns a valid Scenario with both branches. ---ci--- phase: 1 milestone: v0.1 plan: 03 task: 03-01,03-02 status: execute persona: data-engineer requirements: covered: [REQ-SCEN-01, REQ-SCEN-FMT-01] ---/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.