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
docs(proxy): document --protect-tool-results side effect on protect_recent_reads_fraction (#2054)
GUOHAO LIU8322677ddd8a
diff --git a/headroom/cli/proxy.py b/headroom/cli/proxy.pyindex 5d0c8aeb5..0c60c5da4 100644--- a/headroom/cli/proxy.py+++ b/headroom/cli/proxy.py@@ -285,6 +285,10 @@ def dashboard(port: int, no_open: bool) -> None:help=("Comma-separated tool names whose results are never lossy-compressed, ""merged with the built-in defaults (e.g. Bash,WebFetch). "+ "In token mode, this also resets protect_recent_reads_fraction "+ "from 0.3 (only recent ~30% of results protected) to 0.0 (all "+ "results protected indefinitely), which prevents older Read/Glob/"+ "Grep/Write/Edit tool results from being silently compressed. ""Env: HEADROOM_PROTECT_TOOL_RESULTS."),)diff --git a/headroom/proxy/server.py b/headroom/proxy/server.pyindex e8d929bcd..275915947 100644--- a/headroom/proxy/server.py+++ b/headroom/proxy/server.py@@ -761,6 +761,11 @@ class HeadroomProxy(if is_token_mode(config.mode):router_config.protect_recent_reads_fraction = 0.3router_config.search_group_by_file = True+ # Note: protect_tool_results runs AFTER token mode (ordering matters).+ # It resets protect_recent_reads_fraction from 0.3→0.0, restoring+ # full protection for ALL excluded-tool results regardless of age.+ # This means naming any tool with --protect-tool-results also+ # protects Read/Glob/Grep/Write/Edit results indefinitely.if config.protect_tool_results:router_config.protect_recent_reads_fraction = 0.0# `--compress-user-messages` flips the router's default skip rule.