mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-26 01:12:21 +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 Delete eight tests the audit found superseded by stronger ones kept in this move.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>
144 lines
3.5 KiB
Python
144 lines
3.5 KiB
Python
"""Unit tests for litellm.litellm_core_utils.completion_timeout.CompletionTimeout."""
|
|
|
|
import os
|
|
import sys
|
|
|
|
import httpx
|
|
|
|
sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), "../../..")))
|
|
|
|
from litellm.litellm_core_utils.completion_timeout import CompletionTimeout
|
|
from litellm.utils import supports_httpx_timeout
|
|
|
|
|
|
def test_explicit_timeout_wins():
|
|
assert (
|
|
CompletionTimeout.resolve(
|
|
12.5,
|
|
{"timeout": 99.0, "request_timeout": 88.0},
|
|
"openai",
|
|
global_timeout=None,
|
|
supports_httpx_timeout=supports_httpx_timeout,
|
|
)
|
|
== 12.5
|
|
)
|
|
|
|
|
|
def test_kwargs_timeout_when_param_none():
|
|
assert (
|
|
CompletionTimeout.resolve(
|
|
None,
|
|
{"timeout": 21.0},
|
|
"azure_ai",
|
|
global_timeout=None,
|
|
supports_httpx_timeout=supports_httpx_timeout,
|
|
)
|
|
== 21.0
|
|
)
|
|
|
|
|
|
def test_request_timeout_alias_in_kwargs():
|
|
assert (
|
|
CompletionTimeout.resolve(
|
|
None,
|
|
{"request_timeout": 33.0},
|
|
"bedrock",
|
|
global_timeout=None,
|
|
supports_httpx_timeout=supports_httpx_timeout,
|
|
)
|
|
== 33.0
|
|
)
|
|
|
|
|
|
def test_global_timeout_from_litellm_settings():
|
|
assert (
|
|
CompletionTimeout.resolve(
|
|
None,
|
|
{},
|
|
"vertex_ai",
|
|
global_timeout=360.0,
|
|
supports_httpx_timeout=supports_httpx_timeout,
|
|
)
|
|
== 360.0
|
|
)
|
|
|
|
|
|
def test_explicit_global_timeout_6000_is_preserved():
|
|
"""The caller passes the explicitly-configured value (or None); an explicit
|
|
6000 must be honored, not silently coerced to 600."""
|
|
assert (
|
|
CompletionTimeout.resolve(
|
|
None,
|
|
{},
|
|
"openai",
|
|
global_timeout=6000.0,
|
|
supports_httpx_timeout=supports_httpx_timeout,
|
|
)
|
|
== 6000.0
|
|
)
|
|
|
|
|
|
def test_explicit_request_timeout_6000_preserved():
|
|
"""Explicit deployment/request timeout must not be truncated by the package sentinel."""
|
|
assert (
|
|
CompletionTimeout.resolve(
|
|
None,
|
|
{"request_timeout": 6000.0},
|
|
"openai",
|
|
global_timeout=None,
|
|
supports_httpx_timeout=supports_httpx_timeout,
|
|
)
|
|
== 6000.0
|
|
)
|
|
|
|
|
|
def test_explicit_model_timeout_6000_preserved():
|
|
assert (
|
|
CompletionTimeout.resolve(
|
|
6000.0,
|
|
{"timeout": 1.0, "request_timeout": 2.0},
|
|
"openai",
|
|
global_timeout=None,
|
|
supports_httpx_timeout=supports_httpx_timeout,
|
|
)
|
|
== 6000.0
|
|
)
|
|
|
|
|
|
def test_fallback_600_when_no_global_timeout():
|
|
assert (
|
|
CompletionTimeout.resolve(
|
|
None,
|
|
{},
|
|
"azure_ai",
|
|
global_timeout=None,
|
|
supports_httpx_timeout=supports_httpx_timeout,
|
|
)
|
|
== 600.0
|
|
)
|
|
|
|
|
|
def test_httpx_timeout_coerced_for_provider_without_httpx_timeout_support():
|
|
t = httpx.Timeout(50.0, connect=2.0)
|
|
out = CompletionTimeout.resolve(
|
|
t,
|
|
{},
|
|
"azure_ai",
|
|
global_timeout=None,
|
|
supports_httpx_timeout=supports_httpx_timeout,
|
|
)
|
|
assert out == 50.0
|
|
assert not isinstance(out, httpx.Timeout)
|
|
|
|
|
|
def test_httpx_timeout_preserved_for_openai():
|
|
t = httpx.Timeout(40.0, connect=5.0)
|
|
out = CompletionTimeout.resolve(
|
|
t,
|
|
{},
|
|
"openai",
|
|
global_timeout=None,
|
|
supports_httpx_timeout=supports_httpx_timeout,
|
|
)
|
|
assert out is t
|
|
assert isinstance(out, httpx.Timeout)
|