Skip to content

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.

ci: run relevance tests offline so fastembed doesn't 429 on cache HEAD

Tejas Chopra2ea548a86dc2
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 1cde45243..a2767c556 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -233,6 +233,11 @@ jobs:
done
echo "::error::could not fetch fastembed model from HuggingFace"; exit 1
- name: Run relevance tests
+ # Offline so fastembed reads the cache the prefetch step just warmed,
+ # without an unauthenticated cache-validation HEAD that could 429.
+ env:
+ HF_HUB_OFFLINE: "1"
+ TRANSFORMERS_OFFLINE: "1"
run: pytest tests/test_relevance.py -v
test-agno: