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: capture Zone 1 + Zone 2 savings in token_headroom stats

chopratejasaa73c7bbe18d
diff --git a/headroom/proxy/server.py b/headroom/proxy/server.py
index ebf70ed97..3373527a5 100644
--- a/headroom/proxy/server.py
+++ b/headroom/proxy/server.py
@@ -2243,7 +2243,9 @@ class HeadroomProxy:
optimized_messages = result.messages
transforms_applied = result.transforms_applied
pipeline_timing = result.timing
- original_tokens = result.tokens_before
+ # Keep original_tokens as the REAL original (pre-Zone-1-swap)
+ # so tokens_saved captures both Zone 1 + Zone 2 savings.
+ # original_tokens was set at line ~2183 from uncompressed messages.
optimized_tokens = result.tokens_after
else:
result = self.anthropic_pipeline.apply(
@@ -4802,7 +4804,8 @@ class HeadroomProxy:
optimized_messages = result.messages
transforms_applied = result.transforms_applied
pipeline_timing = result.timing
- original_tokens = result.tokens_before
+ # Keep original_tokens as the REAL original (pre-Zone-1-swap)
+ # so tokens_saved captures both Zone 1 + Zone 2 savings.
optimized_tokens = result.tokens_after
else:
result = self.openai_pipeline.apply(