Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Python agentaianthropicclaude-codecompressioncontext-engineeringcontext-windowcursorfastapilangchainllmmcpopenaiprompt-engineeringproxypythonragtoken-optimizationtokenstypescript
chore: satisfy release version lint
JerrettDavis8ac100aa7ac6
diff --git a/headroom/release_version.py b/headroom/release_version.pyindex 21c9a38d5..00dccadf7 100644--- a/headroom/release_version.py+++ b/headroom/release_version.py@@ -5,11 +5,12 @@ from __future__ import annotationsimport osimport reimport subprocess-import tomllibfrom collections.abc import Sequencefrom dataclasses import dataclass, replacefrom pathlib import Path+import tomllib+SEMVER_RE = re.compile(r"^(\d+)\.(\d+)\.(\d+)$")RELEASE_TAG_RE = re.compile(r"^v(\d+)\.(\d+)\.(\d+)(?:\.(\d+))?$")