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): check out repo in PR Governance label job (#1021)
Eyal Mizrachi4558bc2465e5
diff --git a/.github/workflows/pr-health.yml b/.github/workflows/pr-health.ymlindex 1b266e05c..ad41fddcb 100644--- a/.github/workflows/pr-health.yml+++ b/.github/workflows/pr-health.yml@@ -144,6 +144,10 @@ jobs:GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}REPO: ${{ github.repository }}steps:+ - uses: actions/checkout@v6+ with:+ ref: ${{ github.event.pull_request.base.sha }}+- name: Ensure maintenance labels existrun: |set -euo pipefail@@ -189,7 +193,7 @@ jobs:--json isDraft,labels,mergeStateStatus,statusCheckRollup)"merge_state="$(jq -r '.mergeStateStatus // "UNKNOWN"' <<<"$data")"- check_state="$(python3 .github/scripts/pr-health-labels.py --state-json "$data")"+ check_state="$(python3 .github/scripts/pr-health-labels.py --state-json "$data")"is_draft="$(jq -r '.isDraft' <<<"$data")"if [[ "$merge_state" == "BEHIND" ]]; then