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
..
_builder_unit_tests
_driver_unit_tests
_probe_unit_tests
basic_messaging_non_streaming
basic_messaging_streaming
count_tokens
cron_vm
long_context_1m
passthrough
pdf_input
prompt_caching_1h
prompt_caching_5m
structured_outputs
thinking
thinking_with_tool_use
tool_search
tool_use
tool_use_streaming
vision
web_search
__init__.py
_basic_messaging.py
_compat_models.py
_env.py	fix(e2e): wait for every gateway before using a new model and keep the network rerun	2026-09-05 16:10:40 -07:00
_gpt_cells.py
_passthrough.py
cli_driver.py
conftest.py	fix(e2e): wait for every gateway before using a new model and keep the network rerun	2026-09-05 16:10:40 -07:00
http_probe.py
manifest.yaml
matrix_builder.py
pr_gate_version_resolver.py
rate_limiter.py
run_compat.sh
sample_compatibility-matrix.json
test_config.yaml