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: prevent stat inflation in compute_frozen_count, fix token estimate

chopratejas87fec30c0843
diff --git a/headroom/cache/compression_cache.py b/headroom/cache/compression_cache.py
index 3659ef8c4..9aa7b80d0 100644
--- a/headroom/cache/compression_cache.py
+++ b/headroom/cache/compression_cache.py
@@ -151,7 +151,7 @@ class CompressionCache:
content = _extract_tool_result_content(msg)
if content is not None:
h = self.content_hash(content)
- if self.get_compressed(h) is None:
+ if h not in self._cache:
break
else:
# tool_result with non-string content; treat as unstable
@@ -202,5 +202,5 @@ class CompressionCache:
if orig_content == comp_content:
continue
h = self.content_hash(orig_content)
- tokens_saved = len(orig_content) - len(comp_content)
+ tokens_saved = len(orig_content) // 4 - len(comp_content) // 4
self.store_compressed(h, comp_content, tokens_saved=max(tokens_saved, 0))