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: suppress '[transformers] PyTorch was not found' startup warning (#1066)
r00t5208e32d64dc
diff --git a/headroom/memory/adapters/embedders.py b/headroom/memory/adapters/embedders.pyindex dba028b11..fce7bea3f 100644--- a/headroom/memory/adapters/embedders.py+++ b/headroom/memory/adapters/embedders.py@@ -31,6 +31,7 @@ if TYPE_CHECKING:# We operate in an authenticated-optional mode; warnings are not actionable.os.environ.setdefault("HF_HUB_DISABLE_PROGRESS_BARS", "1")os.environ.setdefault("HF_HUB_DISABLE_IMPLICIT_TOKEN", "1")+os.environ.setdefault("TRANSFORMERS_VERBOSITY", "error")warnings.filterwarnings("ignore", category=UserWarning, module="huggingface_hub")# Also silence the huggingface_hub logger which emits rate-limit advisory messages.logging.getLogger("huggingface_hub").setLevel(logging.ERROR)diff --git a/headroom/proxy/server.py b/headroom/proxy/server.pyindex f64a4c87d..07b343c38 100644--- a/headroom/proxy/server.py+++ b/headroom/proxy/server.py@@ -424,6 +424,11 @@ def _build_agent_usage_summary(}+# Suppress "[transformers] PyTorch was not found" warning emitted when+# transformers is imported for availability checks (e.g. kompress ONNX probe).+# PyTorch is optional in headroom; the warning is not actionable for operators.+os.environ.setdefault("TRANSFORMERS_VERBOSITY", "error")+logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(name)s - %(levelname)s - %(message)s")