Praxis CI
9108b07de1
server/interruptibility.py — programmatic check that the pipeline task is configured with allow_interruptions=True (D-008 abort-and-yield). The manual test (speaking during AI speech cuts it off) is documented in docs/latency-report.md; the automated test confirms the flag is set. server/scenarios/classifier.py — classify_branch() uses deepseek-v4-flash:cloud no-think (D-020) as LLM-as-judge to classify the learner's turn transcripts into accept_resolution or escalate at session end, OFFLINE from the voice loop (D-P1-05, G-002 post-hoc classification). Parses the LLM's JSON response leniently (code fences, unknown-id fallback, malformed JSON scan). classify_branch_sync_heuristic() is a rule-based fallback for tests/e2e when no API key is present. 11 tests pass (interruptibility flag on/off/missing; classifier accept/escalate scripted transcripts; JSON parse valid/code-fenced/unknown-id/malformed; fake-LLM async classify; offline structural assertion). ---ci--- phase: 1 milestone: v0.1 plan: 03 task: 03-05,03-06 status: execute persona: backend-engineer requirements: covered: [REQ-VOICE-04, REQ-SCEN-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.