What does provenance-aware priority handling do?

It prevents untrusted RAG, tool, and assistant content from gaining protected priority solely through imperative or safety-critical wording.

Does LLMSlim prevent prompt injection?

No. It mitigates compression-induced instruction elevation and applications still need defense in depth.

Does LLMSlim require remote calls?

The default extractive strategy runs locally. Rewrite and hybrid strategies use a caller-supplied provider.

All documentation

Core Concepts 5 min readUpdated August 2026

Provenance and ContextRole

Assign the trust semantics of the content you are compressing.

Roles

SYSTEM and DEVELOPER are trusted. USER is semi-trusted. ASSISTANT, TOOL, and RAG are untrusted: wording and preservation-pattern matches cannot move them above Tier 2 or make them must_keep. GENERAL is the legacy default.

Trust boundary

LLMSlim trusts caller-provided role labels and cannot authenticate provenance.

roles.py

from llmslim import ContextRole, compress

result = compress(retrieved_text, context_role=ContextRole.RAG)

Frequently asked questions

Does ContextRole prevent prompt injection?

No. It mitigates compression-induced instruction elevation. Applications still need defense in depth.

Can LLMSlim authenticate a role label?

No. The caller is responsible for accurate provenance.