scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-08 22:21:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 78

test(router): cover _widest_configured_limit directly for the coverage gate

Browse source
This commit is contained in:
michelligabriele 2026-09-02 14:12:23 +02:00
parent d5270890c4
commit f0f6ff8de4
No known key found for this signature in database
2 changed files with 25 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
litellm/proxy/utils.py
View file

@ -7545,9 +7545,17 @@ def _group_token_limit(candidate_sets: tuple[tuple[ModelInfo, ...], ...], field:
"""The widest limit any deployment behind the listed name declares for ``field``.
A model group is normally one model behind several interchangeable deployments, so
there is a single value to report. When a group genuinely mixes models, reporting the
widest window keeps the listing independent of config order and agreeing with
``/model_group/info``, which aggregates the same way for the Admin UI.
there is a single value to report and the choice of aggregate does not arise.
When a group genuinely mixes models no single number is right, and the widest is the
deliberate pick over the narrowest for two reasons. It is what ``/model_group/info``
has long reported to the Admin UI, so the two surfaces agree; disagreeing is the very
complaint this resolution path exists to fix. And of the two ways to be wrong,
under-advertising is worse: a client that trusts a narrowed window silently refuses
prompts the group would have served, while an over-long prompt that reaches a smaller
deployment comes back as a legible context-length error -- and does not reach one at
all when ``enable_pre_call_checks`` is set, which filters deployments the prompt does
not fit.
"""
limits: Final = tuple(
limit for limit in (_first_token_limit(candidates, field) for candidates in candidate_sets) if limit is not None

14
tests/test_litellm/test_router.py
View file

@ -7350,6 +7350,20 @@ def test_get_model_listing_info_carries_configured_limits():
assert (info.max_input_tokens, info.max_output_tokens) == (32000, 8000)
def test_widest_configured_limit_ignores_absent_and_malformed_values():
model_infos = (
{"max_input_tokens": 32000},
{},
{"max_input_tokens": "not-a-number"},
{"max_input_tokens": "128000"},
{"max_output_tokens": 4096},
)
assert litellm.Router._widest_configured_limit(model_infos, "max_input_tokens") == 128000
assert litellm.Router._widest_configured_limit(model_infos, "max_output_tokens") == 4096
assert litellm.Router._widest_configured_limit((), "max_input_tokens") is None
def test_get_model_listing_info_dedupes_interchangeable_deployments():
"""The ordinary group is N deployments of one model, so it yields exactly one key."""
router = litellm.Router(