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: type integration imports explicitly
JerrettDavisd5a33c110021
diff --git a/headroom/integrations/mcp/server.py b/headroom/integrations/mcp/server.pyindex 8bc06fdc3..9fe0b2626 100644--- a/headroom/integrations/mcp/server.py+++ b/headroom/integrations/mcp/server.py@@ -53,8 +53,8 @@ from dataclasses import dataclass, fieldfrom typing import Anyfrom headroom.config import HeadroomConfig, SmartCrusherConfig-from headroom.providers import OpenAIProvider-from headroom.transforms import SmartCrusher+from headroom.providers.openai import OpenAIProvider+from headroom.transforms.smart_crusher import SmartCrusher@dataclassdiff --git a/headroom/integrations/strands/providers.py b/headroom/integrations/strands/providers.pyindex f93609f1c..11979c153 100644--- a/headroom/integrations/strands/providers.py+++ b/headroom/integrations/strands/providers.py@@ -8,12 +8,10 @@ from __future__ import annotationsimport loggingfrom typing import Any-from headroom.providers import (- AnthropicProvider,- GoogleProvider,- OpenAIProvider,-)+from headroom.providers.anthropic import AnthropicProviderfrom headroom.providers.base import Provider+from headroom.providers.google import GoogleProvider+from headroom.providers.openai import OpenAIProviderlogger = logging.getLogger(__name__)