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
Merge pull request #411 from manorit2001/wip
Tejas Chopra2f982ade0ecb
diff --cc headroom/cli/proxy.pyindex 93ee7d1e8,c38a0762f..3222e7c7c--- a/headroom/cli/proxy.py+++ b/headroom/cli/proxy.py@@@ -543,19 -530,9 +559,20 @@@ def proxylog_full_messages=log_messagesor os.environ.get("HEADROOM_LOG_MESSAGES", "").lower() in ("true", "1", "yes", "on"),budget_limit_usd=budget,+ # Code-aware compression resolution:+ # 1. Explicit --code-aware / --no-code-aware always wins.+ # 2. Otherwise read HEADROOM_CODE_AWARE_ENABLED (truthy = on).+ # 3. Otherwise default off — matches the prior cli/proxy.py behavior so+ # existing users see no change unless they opt in.+ code_aware_enabled=(+ bool(code_aware_flag)+ if code_aware_flag is not None+ else os.environ.get("HEADROOM_CODE_AWARE_ENABLED", "").strip().lower()+ in ("true", "1", "yes", "on")+ ),# Code graph: live file watcher for incremental reindexingcode_graph_watcher=code_graph,+ code_aware_enabled=code_aware or _get_env_bool("HEADROOM_CODE_AWARE_ENABLED", False),# Read lifecycle: ON by default (use --no-read-lifecycle to disable)read_lifecycle=not no_read_lifecycle,# Memory System (Multi-Provider with auto-detection)