scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-06 08:16:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 78

test: cover clock-skew day prefix in gcs read-back and retry team callback propagation

Browse source
This commit is contained in:
Yucheng Zhu 2026-08-27 11:52:57 -07:00
parent bcc2e71b5d
commit d3ee9f6217
2 changed files with 31 additions and 20 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
tests/e2e/logging/gcs_reader.py
View file

@ -153,7 +153,7 @@ class GcsLogReader:
duplicate-delivery bug, so this never collapses to a single record."""
records: list[GcsLogRecord] = []
window_start = since - _SKEW
for day_offset in (0, 1):
for day_offset in (-1, 0, 1):
day = (since + timedelta(days=day_offset)).strftime("%Y-%m-%d")
for obj in self._list(f"{day}/"):
if obj.name == f"{day}/{response_id}":

49
tests/e2e/logging/test_team_langfuse_callback_e2e.py
View file

@ -62,16 +62,33 @@ class TestTeamLangfuseCallback:
solo_key = client.key_with_alias(solo_alias, models=[CHEAP_ANTHROPIC_MODEL])
resources.defer(lambda: client.delete_key(solo_key))
team_marker = unique_marker()
team_outcome = first_ok(
client,
lambda: client.chat_raw(
team_key, CHEAP_ANTHROPIC_MODEL, f"reply with one word {team_marker}", max_tokens=16
),
)
assert team_outcome.response_cost is not None and team_outcome.response_cost > 0, (
f"the response must report x-litellm-response-cost, got {team_outcome.response_cost!r}"
)
# Enforced behavior, positive half, with one propagation retry: a
# worker still holding the pre-callback team object can serve the
# first call without shipping it, and by the time the first Langfuse
# poll has timed out the team cache TTL has lapsed, so a second call
# must deliver.
team_marker = ""
team_outcome = None
observation = None
for _attempt in range(2):
team_marker = unique_marker()
team_outcome = first_ok(
client,
lambda marker=team_marker: client.chat_raw(
team_key, CHEAP_ANTHROPIC_MODEL, f"reply with one word {marker}", max_tokens=16
),
)
assert team_outcome.response_cost is not None and team_outcome.response_cost > 0, (
f"the response must report x-litellm-response-cost, got {team_outcome.response_cost!r}"
)
observation = client.poll_langfuse_observation(
langfuse_creds,
key_alias=team_alias,
prompt_marker=team_marker,
require_positive_cost=True,
)
if observation is not None:
break
solo_marker = unique_marker()
_ = first_ok(
client,
@ -80,17 +97,11 @@ class TestTeamLangfuseCallback:
),
)
# Enforced behavior, positive half: the team member's call is readable
# back from the real Langfuse project with an agreeing cost.
observation = client.poll_langfuse_observation(
langfuse_creds,
key_alias=team_alias,
prompt_marker=team_marker,
require_positive_cost=True,
)
assert observation is not None, (
f"the team key's call (marker {team_marker}) never reached Langfuse within the deadline"
f"the team key's call (marker {team_marker}) never reached Langfuse within the deadline, "
"even after a fresh call past the team-object cache TTL"
)
assert team_outcome is not None and team_outcome.response_cost is not None
cost = observation_spend(observation)
assert cost is not None and costs_agree(team_outcome.response_cost, cost), (
f"Langfuse calculatedTotalCost {cost!r} must agree with the header cost {team_outcome.response_cost}"