Skip to content

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.

fix: preserve lazy proxy backend imports

JerrettDavis364a07228fcd
diff --git a/headroom/proxy/server.py b/headroom/proxy/server.py
index f07ecaa81..cee782ecf 100644
--- a/headroom/proxy/server.py
+++ b/headroom/proxy/server.py
@@ -166,20 +166,6 @@ from headroom.transforms import (
AnyLLMBackend: Any = None
LiteLLMBackend: Any = None
-try:
- from headroom.backends.anyllm import AnyLLMBackend as _AnyLLMBackend
-
- AnyLLMBackend = _AnyLLMBackend
-except ImportError:
- pass
-
-try:
- from headroom.backends.litellm import LiteLLMBackend as _LiteLLMBackend
-
- LiteLLMBackend = _LiteLLMBackend
-except ImportError:
- pass
-
fcntl: Any = None
try:
import fcntl as _fcntl