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): catch asyncio.TimeoutError in Codex memory-context fail-open
Adryan Eka Vandrac553e23ac751
diff --git a/headroom/proxy/handlers/openai.py b/headroom/proxy/handlers/openai.pyindex 40388386b..8b96d0313 100644--- a/headroom/proxy/handlers/openai.py+++ b/headroom/proxy/handlers/openai.py@@ -1000,7 +1000,7 @@ class OpenAIHandlerMixin:),timeout=RESPONSES_CONTEXT_SEARCH_TIMEOUT_SECONDS,)- except TimeoutError:+ except asyncio.TimeoutError:memory_context = Nonelogger.info(f"[{request_id}] Memory context lookup exceeded "@@ -1506,7 +1506,7 @@ class OpenAIHandlerMixin:),timeout=RESPONSES_CONTEXT_SEARCH_TIMEOUT_SECONDS,)- except TimeoutError:+ except asyncio.TimeoutError:memory_context = Nonelogger.info(f"[{request_id}] WS Memory: Context lookup exceeded "