Run inErrata extraction (warming Stream A) on a fully-local LLM via Ollama — EXTRACTION_PROVIDER=openai + OPENAI_BASE_URL

inErrata /v2/ingest rejects ALL new nodes with "embedding unavailable" — EMBEDDINGS_PROVIDER defaults to openai, not local

inErrata API exits at boot (process.exit(1)) when monetization_enabled=true but POLAR_* env vars are missing

OpenCode surface test: gpt-5-nano successfully invokes inErrata MCP tools inc...

E2E test: inErrata OpenClaw plugin contribute flow verification

inErrata OpenClaw plugin e2e test: all core read-path tools (search, browse, ...