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: stabilize learn write-failure worker test
Tejas Chopra155c0691767d
diff --git a/tests/test_cli_learn.py b/tests/test_cli_learn.pyindex 87125fab4..846385145 100644--- a/tests/test_cli_learn.py+++ b/tests/test_cli_learn.py@@ -153,6 +153,7 @@ def test_learn_project_lookup_and_apply_flow(monkeypatch.setattr("headroom.learn.analyzer._detect_default_model", lambda: "gpt-4o")monkeypatch.setattr("headroom.learn.registry.get_plugin", lambda name: plugin)monkeypatch.setattr("headroom.learn.analyzer.SessionAnalyzer", lambda model=None: analyzer)+ monkeypatch.setattr("os.cpu_count", lambda: 12)result = runner.invoke(main,