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
fix: avoid proxy registry import cycle
JerrettDavis7c86fa6b22e7
diff --git a/headroom/providers/registry.py b/headroom/providers/registry.pyindex 15bdcb1b0..7204dd39f 100644--- a/headroom/providers/registry.py+++ b/headroom/providers/registry.py@@ -11,7 +11,6 @@ from typing import TYPE_CHECKING, Any, castfrom headroom.providers.claude import DEFAULT_API_URL as DEFAULT_ANTHROPIC_API_URLfrom headroom.providers.codex import DEFAULT_API_URL as DEFAULT_OPENAI_API_URLfrom headroom.providers.gemini import DEFAULT_API_URL as DEFAULT_GEMINI_API_URL-from headroom.proxy.helpers import is_anthropic_authDEFAULT_CLOUDCODE_API_URL = "https://cloudcode-pa.googleapis.com"@@ -310,4 +309,9 @@ _CLIENT_TRANSPORTS: dict[str, _ClientTransport] = {def _is_anthropic_auth(headers: Mapping[str, str]) -> bool:- return is_anthropic_auth(dict(headers))+ authorization = headers.get("authorization") or headers.get("Authorization") or ""+ return bool(+ headers.get("x-api-key")+ or headers.get("anthropic-version")+ or authorization.startswith("Bearer sk-ant-")+ )