Removed Engine Setup

This page used to describe a settings tab that has been removed

Pre-2026-04 versions of Ishvana shipped a Settings tab for external credentials, tier assignment, per-agent routing overrides, and context-compression weights. That tab no longer exists. The Divinity Engine replaced that setup surface with bundled local handlers, so there’s nothing to configure.

If you arrived from an older link, here’s what’s true now:

• No API keys to enter. Every analysis Ishvana runs is local. No request goes to a cloud inference service.
• No engine tiers to assign. There aren’t multiple chat engines. The Divinity Engine ships bundled local intelligence assets, including multilingual e5 embeddings, mDeBERTa NLI, and an optional Deep Analysis Pack that adds spaCy + FastCoref on demand.
• No per-agent overrides. Each agent maps to a fixed set of Divinity Engine handlers documented in Etherforce overview → Handler registry.
• No costs to track. Zero usage billing because every handler runs locally.

Settings overview What's actually configurable in Ishvana today — and what isn't.

Etherforce overview The dispatch layer that replaced the removed routing layer.

Engine overview How the Divinity Engine fits together.

This page keeps a current explanation for older screenshots, support notes, and links that referenced the removed setup surface.