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 learn CLI worker expectation in CI
Tejas Chopra22e750c78f48
diff --git a/tests/test_cli_learn.py b/tests/test_cli_learn.pyindex 846385145..c1a5e499f 100644--- a/tests/test_cli_learn.py+++ b/tests/test_cli_learn.py@@ -1,5 +1,6 @@from __future__ import annotations+import osfrom pathlib import Pathfrom types import SimpleNamespace@@ -246,7 +247,8 @@ def test_learn_analyze_all_continues_when_one_project_write_fails(assert str(blocked.project_path) in result.outputassert "[WROTE]" in result.outputassert str(ok.project_path / "AGENTS.md") in result.output- assert plugin.scan_calls == [(blocked, 8), (ok, 8)]+ expected_workers = min(os.cpu_count() or 4, 8)+ assert plugin.scan_calls == [(blocked, expected_workers), (ok, expected_workers)]def test_learn_handles_empty_sessions_and_no_pattern_outputs(