mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-27 01:22:18 +00:00
f6882246d4
* ci: run the unit_selection.sh shard files on every event instead of only fork pull requests Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * ci: rename fork-flag to unit-flag now that it applies on every event * test: move tests/test_litellm root and small trees into tests/unit Pure renames, no content changes. Follow-up commits in this PR fix references, merge the three files that already existed in tests/unit, keep live-provider tests in tests/test_litellm and wire CI. * test: carry tests/test_litellm conftest isolation into tests/unit Callback lists, routing fallbacks, cached HTTP clients, logger state, AWS, proxy-URL and keychain env, and session-end client cleanup now reset for unit tests too. The environment isolation owns its MonkeyPatch so a test's own monkeypatch is undone before the model-cost teardown runs. * test: merge, split and prune the moved root and small-tree tests Merge batches/test_batch_utils.py and the chat_completions and messages dispatch tests into the files that already existed in tests/unit. Keep the live Gemini interactions tests, the async image-fetch format test and the OpenAI embedding scorer test in tests/test_litellm since they need real network or keys. Put test_router.py under tests/unit/test_router so the existing package no longer shadows it. Delete eight tests the audit found superseded by stronger ones kept in this move. * ci: run the moved root and small-tree tests under their legacy flags Add the misc and responses-caching-types flags to unit_selection.sh and CircleCI, extend enterprise-routing and mcp-integration, and point the legacy GHA shards, Makefile, redis-compat workflow, merge smoke manifest and change classifier at the new paths. * test: make the new tests/unit directories packages tests/unit/test_package_layout.py requires every directory to carry an __init__.py, and without one the moved and retained test_litellm_responses_bridge.py modules collide on import. * test: scope the unit socket block to tests/unit in shared sessions The GHA shards collect the legacy test-path and the unit selection in one pytest session. The unit conftest's loopback-only block leaked into legacy modules that reach the network at import. The legacy conftest now lifts the restriction at collect and setup time, and the unit conftest re-applies it when collecting its own modules. * test: give the shard-script tests their own GITHUB_OUTPUT They only passed where the runner set it. The CircleCI unit job's env allowlist drops it, so the script's redirect failed there. * test: point the router and module-deletion checks at tests/unit router_code_coverage and code_qa_check_tests only searched tests/test_litellm, so the moved router tests no longer counted. The two silent-experiment tests the audit deleted were the only direct callers of those methods; they are replaced with tests that assert the forwarded shadow request and the recursion guard. --------- Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
57 lines
2 KiB
Python
57 lines
2 KiB
Python
import json
|
|
from pathlib import Path
|
|
from typing import get_args
|
|
|
|
from typing_extensions import get_type_hints
|
|
|
|
from litellm.types.utils import ModelInfoBase
|
|
|
|
REALTIME_ONLY_GPT_MODELS = (
|
|
"azure/gpt-realtime-2025-08-28",
|
|
"azure/gpt-realtime-1.5-2026-02-23",
|
|
"azure/gpt-realtime-mini",
|
|
"azure/gpt-realtime-mini-2025-10-06",
|
|
"gpt-realtime",
|
|
"gpt-realtime-1.5",
|
|
"gpt-realtime-2",
|
|
"gpt-realtime-2.1",
|
|
"gpt-realtime-2.1-mini",
|
|
"gpt-realtime-mini",
|
|
"gpt-realtime-2025-08-28",
|
|
"gpt-realtime-mini-2025-10-06",
|
|
"gpt-realtime-mini-2025-12-15",
|
|
)
|
|
|
|
REALTIME_ONLY_GPT_MODELS_WITHOUT_ENDPOINTS = (
|
|
"azure/eu/gpt-4o-mini-realtime-preview-2024-12-17",
|
|
"azure/eu/gpt-4o-realtime-preview-2024-10-01",
|
|
"azure/eu/gpt-4o-realtime-preview-2024-12-17",
|
|
"azure/gpt-4o-mini-realtime-preview-2024-12-17",
|
|
"azure/gpt-4o-realtime-preview-2024-10-01",
|
|
"azure/gpt-4o-realtime-preview-2024-12-17",
|
|
"azure/us/gpt-4o-mini-realtime-preview-2024-12-17",
|
|
"azure/us/gpt-4o-realtime-preview-2024-10-01",
|
|
"azure/us/gpt-4o-realtime-preview-2024-12-17",
|
|
"gpt-4o-mini-realtime-preview",
|
|
"gpt-4o-mini-realtime-preview-2024-12-17",
|
|
"gpt-4o-realtime-preview",
|
|
"gpt-4o-realtime-preview-2024-12-17",
|
|
"gpt-4o-realtime-preview-2025-06-03",
|
|
)
|
|
|
|
ALL_REALTIME_ONLY_GPT_MODELS = REALTIME_ONLY_GPT_MODELS + REALTIME_ONLY_GPT_MODELS_WITHOUT_ENDPOINTS
|
|
|
|
|
|
def test_realtime_is_a_valid_mode_literal():
|
|
hints = get_type_hints(ModelInfoBase, include_extras=False)
|
|
assert "realtime" in get_args(hints["mode"])
|
|
|
|
|
|
def test_backup_matches_main_for_realtime_models():
|
|
repo_root = Path(__file__).parents[2]
|
|
with open(repo_root / "model_prices_and_context_window.json") as f:
|
|
main_cost = json.load(f)
|
|
with open(repo_root / "litellm" / "model_prices_and_context_window_backup.json") as f:
|
|
backup_cost = json.load(f)
|
|
for model in ALL_REALTIME_ONLY_GPT_MODELS:
|
|
assert backup_cost.get(model) == main_cost.get(model)
|