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
chore(ci): align the pre-commit mypy hook with CI's mypy 1.20.2 (#3397)
trs-80a37d734352be
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yamlindex 86d88bcd4..826c19188 100644--- a/.pre-commit-config.yaml+++ b/.pre-commit-config.yaml@@ -35,7 +35,7 @@ repos:- id: ruff-formatexclude: ^experiments/- repo: https://github.com/pre-commit/mirrors-mypy- rev: v1.14.1+ rev: v1.20.2hooks:- id: mypyargs: [--ignore-missing-imports]