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(proxy): satisfy rustfmt import ordering (#2158)
JD Davisf00833654f18
diff --git a/crates/headroom-proxy/src/proxy.rs b/crates/headroom-proxy/src/proxy.rsindex 7bccf123b..cb9f1ffb1 100644--- a/crates/headroom-proxy/src/proxy.rs+++ b/crates/headroom-proxy/src/proxy.rs@@ -10,9 +10,9 @@ use axum::http::{HeaderMap, HeaderName, Request, Response, StatusCode, Uri};use axum::response::IntoResponse;use axum::routing::{any, get, post};use axum::Router;-use futures_util::{StreamExt as _, TryStreamExt};#[cfg(test)]use bytes::Bytes;+use futures_util::{StreamExt as _, TryStreamExt};#[cfg(test)]use http_body_util::BodyExt;