Module compress 

Context compression for conversation history.

This module implements intelligent compression of conversation history to reduce token usage while preserving important information.

Module Structure

• config: Compression configuration and bias settings
• types: Compression strategy, result, and segment types
• compressor: AI compressor and compression functions

Structs

AiCompressor

AI-based compressor using a Provider.

CompressionBias

Compression bias - controls what to prioritize during compression.

CompressionConfig

Configuration for context compression.

CompressionHistoryEntry

Compression history entry for session metadata.

CompressionResult

Result of a compression operation.

SummarizedSegment

A segment of conversation history that has been summarized.

Enums

CompressionStrategy

Strategy for compressing conversation history.

Constants

DEFAULT_COMPRESSION_THRESHOLD

Compression trigger threshold (percentage of context window). Lowered to 0.5 to compress earlier for long conversations (128K context -> 64K threshold)

DEFAULT_COMPRESSOR_MODEL

Default model for summarization.

DEFAULT_TARGET_RATIO

Target ratio after compression (keep this fraction of tokens).

MIN_MESSAGES_TO_KEEP

Minimum messages to keep after compression. Increased to preserve more recent context for continuity

Traits

Compressor

Compressor trait for different implementations.

Functions

build_summary_prompt

Build a prompt for summarization.

compress_messages

Compress messages synchronously.

compress_with_bias

Compress with bias-based scoring.

estimate_tokens

Estimate token count for a message.

estimate_total_tokens

Estimate total tokens for a message list.

format_tokens

Format token count for display.

should_compress

Check if compression should be triggered.