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(ci): pin checkout in release notification smoke workflow (#4399)
Anupam Mediratta70273db0af39
diff --git a/.github/act/release-slack-notification.yml b/.github/act/release-slack-notification.ymlindex bcc9854e8..2118f0605 100644--- a/.github/act/release-slack-notification.yml+++ b/.github/act/release-slack-notification.yml@@ -7,7 +7,7 @@ jobs:smoke:runs-on: ubuntu-lateststeps:- - uses: actions/checkout@v7+ - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7- name: Exercise production notification componentuses: ./.github/actions/release-slack-notificationwith: