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: retry workflow validation dry-runs
JerrettDavis297f499e3737
diff --git a/scripts/validate-workflows.sh b/scripts/validate-workflows.shindex c6a59b93d..b6083ccf0 100644--- a/scripts/validate-workflows.sh+++ b/scripts/validate-workflows.sh@@ -3,6 +3,27 @@ set -euo pipefailactionlint .github/workflows/*.yml-act workflow_dispatch -W .github/workflows/release.yml -e .github/act/dry-run.json -n-act push -W .github/workflows/release.yml -e .github/act/push-feat.json -n-act workflow_dispatch -W .github/workflows/docker.yml -e .github/act/docker-version.json -n+run_act() {+ local attempt=1+ local max_attempts=3+ local delay_seconds=5++ while true; do+ if "$@"; then+ return 0+ fi++ if (( attempt >= max_attempts )); then+ return 1+ fi++ echo "act dry-run failed on attempt ${attempt}/${max_attempts}; retrying in ${delay_seconds}s..." >&2+ sleep "${delay_seconds}"+ attempt=$((attempt + 1))+ delay_seconds=$((delay_seconds * 2))+ done+}++run_act act workflow_dispatch -W .github/workflows/release.yml -e .github/act/dry-run.json -n+run_act act push -W .github/workflows/release.yml -e .github/act/push-feat.json -n+run_act act workflow_dispatch -W .github/workflows/docker.yml -e .github/act/docker-version.json -n