Skip to content

// Generated from the feature catalog

Context Window Compression

Picks the Right Brain for the Job · Shipped · workstation, home

Level-of-Detail memory management keeping long conversations from blowing the context ceiling.

As conversations grow, raw token counts can exceed the model’s context window. The compression subsystem applies lingua and semantic compressors to distill earlier turns into denser representations while preserving critical facts and tool outputs.

The lingua compressor removes syntactic filler and redundancy. The semantic compressor identifies and merges duplicate information across turns. Together they maintain a sliding window of full-fidelity recent turns backed by compressed summaries of older context.

Compression never discards tool outputs or system-state observations — only conversational filler and redundant explanations are candidates for reduction.

  • halbert_core/halbert_core/compression/lingua_compressor.py
  • halbert_core/halbert_core/compression/semantic_compressor.py