litellm/tests/unit/test_daybreak_model_metadata.py
yuneng-jiang f6882246d4
test: move tests/test_litellm root and small trees into tests/unit (#43186)
* 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found superseded by stronger ones kept in this move.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>
2026-09-25 11:30:43 -07:00

61 lines
1.9 KiB
Python

import json
from pathlib import Path
import pytest
REPO_ROOT = Path(__file__).parents[2]
MAIN_PATH = REPO_ROOT / "model_prices_and_context_window.json"
BACKUP_PATH = REPO_ROOT / "litellm" / "model_prices_and_context_window_backup.json"
DAYBREAK_MODELS = (
"gpt-5.6-cyber",
"daybreak-red-latest",
"daybreak-blue-latest",
)
BLUE_ALIAS = "daybreak-blue-latest"
BLUE_SNAPSHOT = "gpt-5.6-sol"
OFFICIAL_ALIAS_SNAPSHOTS = (
("gpt-daybreak-blue-latest", "gpt-5.6-sol"),
("gpt-daybreak-red-latest", "gpt-5.6-cyber"),
)
PRICE_FIELDS = (
"input_cost_per_token",
"output_cost_per_token",
"cache_read_input_token_cost",
"input_cost_per_token_above_272k_tokens",
"output_cost_per_token_above_272k_tokens",
)
def _load(path):
with open(path) as f:
return json.load(f)
def test_blue_alias_matches_its_snapshot_computer_use():
cost_map = _load(MAIN_PATH)
assert cost_map[BLUE_ALIAS]["supports_computer_use"] is True
assert cost_map[BLUE_SNAPSHOT]["supports_computer_use"] is True
@pytest.mark.parametrize(("alias", "snapshot"), OFFICIAL_ALIAS_SNAPSHOTS)
def test_official_alias_tracks_snapshot(alias, snapshot):
cost_map = _load(MAIN_PATH)
alias_info = cost_map[alias]
snapshot_info = cost_map[snapshot]
assert alias_info["supported_endpoints"] == ["/v1/responses"]
assert alias_info["mode"] == "responses"
assert {field: alias_info.get(field) for field in PRICE_FIELDS} == {
field: snapshot_info.get(field) for field in PRICE_FIELDS
}
assert alias_info["max_output_tokens"] == snapshot_info["max_output_tokens"]
@pytest.mark.parametrize("model", (*DAYBREAK_MODELS, BLUE_SNAPSHOT, *(alias for alias, _ in OFFICIAL_ALIAS_SNAPSHOTS)))
def test_backup_matches_main(model):
main_cost = _load(MAIN_PATH)
backup_cost = _load(BACKUP_PATH)
assert backup_cost.get(model) == main_cost.get(model), f"{model} differs between main and backup model cost maps"