-
released this
2026-09-11 15:40:30 +00:00 | 69 commits to main since this releaseNextcraft v0.1.2 — v0.2 Phase 1
apps/ai-servicestands up: a Python FastAPI application hosting the AI tutor agents behind a provider-agnostic LLM layer.Delivered (REQ-2-001, REQ-2-002, REQ-2-003)
- FastAPI app — lifespan-managed httpx pool (10s connect / 300s read for cloud TTFT), localhost-only CORS,
/health - Provider-agnostic LLM layer —
LLMProviderprotocol;OpenAICompatProvider(ollama-cloud + local endpoints, raw httpx, no SDK); deterministicMockProvider(failure injection, abort recording); factory selection - SSE chat streaming —
POST /v1/chat/streamwith the D-016 envelope:metaevent → content deltas →done→[DONE]; in-banderrorevents on failure - Monorepo integration — zero-dep package shim, turbo passthrough tasks, root
pnpm ai:dev/ai:test/ai:lint/ai:bootstrap - Quality gates — ruff clean, 20/20 pytest green (mock provider only, mechanically enforced cloud-free guard), live smoke verified meta→delta→done→[DONE]
Next
Phase 2: agent framework (BaseAgent, session store, registry, structured outputs).
Downloads
- FastAPI app — lifespan-managed httpx pool (10s connect / 300s read for cloud TTFT), localhost-only CORS,