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: satisfy cross-platform mypy for copilot auth
JerrettDavise5cad5ed920b
diff --git a/headroom/copilot_auth.py b/headroom/copilot_auth.pyindex a4540bd00..4f8c8a577 100644--- a/headroom/copilot_auth.py+++ b/headroom/copilot_auth.py@@ -148,7 +148,11 @@ def _read_windows_copilot_cli_oauth_token() -> str | None:cred_ptr = ctypes.POINTER(CREDENTIAL)credentials = ctypes.POINTER(cred_ptr)()count = wintypes.DWORD()- advapi32 = ctypes.WinDLL("Advapi32.dll")+ win_dll = getattr(ctypes, "WinDLL", None)+ if win_dll is None:+ return None++ advapi32 = win_dll("Advapi32.dll")advapi32.CredEnumerateW.argtypes = [wintypes.LPCWSTR,wintypes.DWORD,