mateo-berri 65d8bbb8ac fix(e2e): wait for every gateway before using a new model and keep the network rerun ... The changed-tests workflow overrode the suite's `--reruns 1` with `--reruns 0`, so a transport blip failed a pass that pytest.ini already scopes to network errors and 5xx responses. Pass 2 of run 33692484803 also went red 15s after a model write with "no healthy deployments": the barrier only polled /v1/models through nginx, which proves one gateway converged, and the next request rolled the other. The stack now exports LITELLM_PROXY_REPLICA_URLS, the barrier polls every replica with the full budget before settling, and up.sh refuses to boot without DD_API_KEY, since the gateway config enables the datadog callback on every run		2026-09-05 16:10:40 -07:00
..
assert_tests_ran.py	ci(e2e): refine changed-test selection and runner lifecycle	2026-09-05 12:03:42 -07:00
down.sh	ci(e2e): run a PR's changed e2e tests three times behind a human-approved environment	2026-09-02 14:53:40 -07:00
secrets_to_env.py	ci(e2e): refine changed-test selection and runner lifecycle	2026-09-05 12:03:42 -07:00
up.sh	fix(e2e): wait for every gateway before using a new model and keep the network rerun	2026-09-05 16:10:40 -07:00