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: capture Zone 1 + Zone 2 savings in token_headroom stats
chopratejasaa73c7bbe18d
diff --git a/headroom/proxy/server.py b/headroom/proxy/server.pyindex ebf70ed97..3373527a5 100644--- a/headroom/proxy/server.py+++ b/headroom/proxy/server.py@@ -2243,7 +2243,9 @@ class HeadroomProxy:optimized_messages = result.messagestransforms_applied = result.transforms_appliedpipeline_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_afterelse:result = self.anthropic_pipeline.apply(@@ -4802,7 +4804,8 @@ class HeadroomProxy:optimized_messages = result.messagestransforms_applied = result.transforms_appliedpipeline_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_afterelse:result = self.openai_pipeline.apply(