Release Notes: Adaptive Token Compressor#
Version 2026.3.0#
Release Date: November, 2026
Summary:
Adds an experimental third compressor type for conversation context, and supports a small reranker model in the tool compressor for faster tool selection.
New:
Experimental:
ContextCompressor("context"compressor type) optimizes long, tool-heavy conversation histories through turn-aware policies and selective compression, using tool-interaction boundaries to retain recent turns and process older content while preserving call-result associations. It replaces eligible oversized historical results with recovery-guided stubs, and can preserve reads of files later changed in the conversation. Remaining eligible content can be routed through Claw Compactor or Compress Server.Small-model tool selection with
Qwen/Qwen3-Reranker-0.6B(predictor_backend="reranker"): about 10x lower predictor latency than the defaultQwen/Qwen3.6-35B-A3Bconfiguration, at a lower tool-token savingNew
ToolCompressorparameterstop_k,tool_count_level,predictor_max_output_tokens, andpredictor_max_input_tokensMulti-key metrics aggregation in
CompressionManager: declaremetrics_keyswhen registering a compressor (for example,["provider", "user"]) and passmetrics_valuestocompress()to aggregate metrics independently by each key’s values; retrieve results withsnapshot(key=..., value=...)orsnapshot_by_keys().
Upgrade Notes:
Avg*PerRequestmetrics now divide by the unique requests that went through the metric’s ownsources, instead of all requests seen by theCompressionManager. Requests that did not call any of the metric’s compressors no longer lower its average, andsnapshot()andsnapshot(source=...)return the same value for the same metric. Values change only when some requests skip some compressors. Withoutreq_idfrom the metric’s sources, theset_per_anchor()call count is still the denominator.CompressionManager.snapshot(source=...)now selects metrics by the compressor they track instead of by metric name: it returns the metrics registered withsourcesset to the given compressor’s registered name, whatever the metric names are. Metrics named<name>.<metric>that track only that compressor are returned as before. Metrics that track several compressors, andRequestCountmetrics, are no longer returned even if their names start with<name>.; read them withsnapshot().
Version 2026.2.0#
Release Date: September, 2026
Summary:
Initial release of the Adaptive Token Compressor — a pluggable compression library purpose-built for LLM agent systems. Using a single unified interface, it compresses system prompts, context, and tool schemas across an LLM agent pipeline to reduce token usage and improve inference efficiency.
Features:
Unified compressor API with two compression types: conversation messages (harness) and tool descriptions (tool)
Factory-based construction for drop-in integration as a plugin in other projects
LLMLingua-backed text compression for local Lingua Server backends (PyTorch/OpenVINO)
LLM-based tool selection through a configurable predictor endpoint
Hybrid rule-based and model-based compression to balance compression ratio and content fidelity
Configurable tool-injection placements to flexibly trade off token savings against prefix-cache hit rate
Per-compressor telemetry for tokens, savings, compression ratio, and latency, with cross-compressor aggregation through
CompressionManager