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): pypi publish skip-existing to unblock idempotent re-runs
chopratejas6a191b405b5c
diff --git a/.github/workflows/release.yml b/.github/workflows/release.ymlindex bce87e910..680fde7e6 100644--- a/.github/workflows/release.yml+++ b/.github/workflows/release.yml@@ -616,6 +616,15 @@ jobs:- name: Publish ${{ env.PYPI_PACKAGE }} to PyPIid: pypi-publishuses: pypa/gh-action-pypi-publish@release/v1+ with:+ # Idempotent re-runs: when a wheel filename for the computed+ # version is already on PyPI (e.g. a previous push to main+ # already published this version, or this run's computed+ # semver hasn't bumped past the last release), treat the+ # existing file as a no-op instead of a hard failure. PyPA's+ # recommended pattern for release workflows that may run+ # multiple times against the same version.+ skip-existing: truepublish-npm:needs: [detect-version, build]