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
ci(devcontainers): free runner disk before memory-stack validation
chopratejas7020684ce720
diff --git a/.github/workflows/devcontainers.yml b/.github/workflows/devcontainers.ymlindex 1f9bb4e16..4c75c29cc 100644--- a/.github/workflows/devcontainers.yml+++ b/.github/workflows/devcontainers.yml@@ -32,6 +32,30 @@ jobs:steps:- uses: actions/checkout@v4+ # The memory-stack devcontainer brings up Neo4j + Postgres ++ # Redis + Qdrant on top of the Docker base. PR #495 surfaced+ # that the GitHub-hosted runner now ships with too little+ # headroom for that stack: the runner's diagnostic log writer+ # hit "No space left on device" mid-smoke-test, killing the+ # job before `devcontainer exec` could finish. The default+ # devcontainer is light enough to pass on the same image.+ #+ # Reclaim ~14 GB by stripping preinstalled tools none of the+ # devcontainer paths use (Android SDK, .NET, Haskell). Run+ # ONLY on memory-stack — the default validate is fast and+ # benefits from the preinstalled toolcache.+ - name: Free runner disk (memory-stack only)+ if: matrix.name == 'memory-stack'+ uses: jlumbroso/[email protected]+ with:+ tool-cache: true+ android: true+ dotnet: true+ haskell: true+ large-packages: false+ docker-images: false+ swap-storage: false+- name: Set up Nodeuses: actions/setup-node@v4with: