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 e2e cleanup: ignore errors from OpenClaw leftover files
chopratejasc9ac5f62704c
diff --git a/e2e/wrap/run.py b/e2e/wrap/run.pyindex 2a6c93544..99dd50e4b 100644--- a/e2e/wrap/run.py+++ b/e2e/wrap/run.py@@ -621,7 +621,9 @@ def verify_openclaw_wrap(def main() -> None:verify_installs()- with tempfile.TemporaryDirectory(prefix="headroom-wrap-e2e-") as tmp_dir_str:+ with tempfile.TemporaryDirectory(+ prefix="headroom-wrap-e2e-", ignore_cleanup_errors=True+ ) as tmp_dir_str:tmp_dir = Path(tmp_dir_str)home_dir = tmp_dir / "home"project_dir = tmp_dir / "project"