mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-09 03:18:44 +00:00
* build: migrate packaging metadata to uv * ci: move automation and local tooling to uv * docker: migrate image builds and runtime setup to uv * docs: update install and deployment guidance for uv * chore: align auxiliary scripts and tests with uv * test: harden test_litellm isolation * fix: keep release and health check images self-contained * build: pin uv tooling and health check deps * test: isolate bedrock image request formatting from suite state * test: cover sandbox executor requirements flow * ci: fix circleci no-op command steps * ci: fix circleci publish workflow parsing * fix: stabilize remaining uv migration CI checks * ci: increase matrix test timeout headroom * fix: restore published docker and license coverage * fix: restore proxy runtime build parity * fix: restore proxy extras parity and venv migrations * ci: persist uv path across circleci steps * fix: keep psycopg binary in default test env * docker: preserve prisma cache across stages * test: run local proxy checks through uv python * build: restore runtime deps moved into ci * build: refresh uv lock after upstream merge * fix: restore module import in test_check_migration after merge The conflict resolution imported only the function but the test body references check_migration as a module throughout. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: revert dependency promotions, remove nodejs-wheel-binaries, fix Docker layer caching - Move google-generativeai, Pillow, tenacity back to ci group (they are lazily imported and bloat the base SDK install needlessly) - Remove nodejs-wheel-binaries from extra_proxy and proxy-dev (redundant in Docker where system Node.js is already installed via apk) - Remove all nodejs-wheel node replacement and venv npm patching blocks from Dockerfiles since the wheel is no longer installed - Add --no-default-groups to CodSpeed benchmark workflow so the benchmark environment matches the old minimal pip install footprint - Apply standard uv two-phase Docker pattern: copy metadata first, install deps (cached layer), then copy source and install project - Replace CircleCI enterprise no-op with proper uv sync command Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * chore: regenerate uv.lock after removing nodejs-wheel-binaries Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(ci): use cache/restore instead of cache to prevent cache poisoning The old workflow used actions/cache/restore (read-only). The uv migration changed it to actions/cache (read-write), which zizmor flags as a cache poisoning risk. Restore the safer read-only variant. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(ci): disable setup-uv built-in cache to silence cache-poisoning alert The setup-uv action enables caching by default, which zizmor flags as a cache poisoning risk. Disable it since we already use a read-only cache/restore step. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(ci): disable setup-uv cache in publish workflow Silences zizmor cache-poisoning alert. Publishing workflow runs infrequently on protected branches so caching adds no real benefit. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(test): remove duplicate verbose_logger mock in test_check_migration The logger was patched twice — first via mocker.patch() then via mocker.patch.object(autospec=True). The second call fails because autospec cannot inspect an already-mocked attribute. Remove the redundant first patch. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(ci): free disk space before Docker build in test-server-root-path The Dockerfile.non_root build ran out of disk on the CI runner. Remove Android SDK, .NET, Boost, and GHC toolchains (~12GB) to free space. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
108 lines
4 KiB
Python
108 lines
4 KiB
Python
"""
|
|
Test for LITELLM_DISABLE_LAZY_LOADING environment variable.
|
|
|
|
This test verifies that when LITELLM_DISABLE_LAZY_LOADING is set,
|
|
encoding is loaded at import time (pre-#18070 behavior) instead of lazy loading.
|
|
|
|
This addresses issue #18659: VCR cassette creation broken by lazy loading.
|
|
For now, this only affects encoding as it was the only reported issue.
|
|
|
|
Tests that need to clear sys.modules and re-import litellm run in subprocesses
|
|
to avoid contaminating the test process's module graph (which breaks mock.patch
|
|
for all subsequent tests on the same xdist worker).
|
|
"""
|
|
import subprocess
|
|
import sys
|
|
import textwrap
|
|
|
|
import pytest
|
|
|
|
|
|
def _run_python(script: str, env_override: dict | None = None) -> subprocess.CompletedProcess:
|
|
"""Run a Python script in a subprocess and return the result."""
|
|
import os
|
|
|
|
env = os.environ.copy()
|
|
# Remove the var so each test controls it explicitly
|
|
env.pop("LITELLM_DISABLE_LAZY_LOADING", None)
|
|
env.pop("TIKTOKEN_CACHE_DIR", None)
|
|
if env_override:
|
|
env.update(env_override)
|
|
return subprocess.run(
|
|
[sys.executable, "-c", textwrap.dedent(script)],
|
|
capture_output=True,
|
|
text=True,
|
|
env=env,
|
|
# Importing litellm can cold-load tiktoken/tokenizer assets and is
|
|
# occasionally slow on CI runners; these tests validate behavior, not speed.
|
|
timeout=180,
|
|
)
|
|
|
|
|
|
def test_eager_loading_enabled():
|
|
"""Test that encoding is loaded at import time when env var is set"""
|
|
result = _run_python(
|
|
"""
|
|
import litellm
|
|
assert hasattr(litellm, "encoding"), "Encoding should be available when eager loading is enabled"
|
|
encoding = litellm.encoding
|
|
assert encoding is not None, "Encoding should not be None"
|
|
tokens = encoding.encode("Hello, world!")
|
|
assert len(tokens) > 0, "Encoding should work"
|
|
""",
|
|
env_override={"LITELLM_DISABLE_LAZY_LOADING": "1"},
|
|
)
|
|
assert result.returncode == 0, f"Subprocess failed:\nstdout: {result.stdout}\nstderr: {result.stderr}"
|
|
|
|
|
|
def test_eager_loading_env_var_values():
|
|
"""Test that various env var values enable eager loading"""
|
|
values = ["1", "true", "True", "TRUE", "yes", "Yes", "YES", "on", "On", "ON"]
|
|
for value in values:
|
|
result = _run_python(
|
|
"""
|
|
import litellm
|
|
assert hasattr(litellm, "encoding"), "Encoding should be available"
|
|
encoding = litellm.encoding
|
|
tokens = encoding.encode("test")
|
|
assert len(tokens) > 0
|
|
""",
|
|
env_override={"LITELLM_DISABLE_LAZY_LOADING": value},
|
|
)
|
|
assert result.returncode == 0, (
|
|
f"Failed for value {value!r}:\nstdout: {result.stdout}\nstderr: {result.stderr}"
|
|
)
|
|
|
|
|
|
def test_lazy_loading_default():
|
|
"""Test that encoding is lazy loaded by default (when env var is not set)"""
|
|
result = _run_python(
|
|
"""
|
|
import litellm
|
|
# Encoding should be accessible via __getattr__ (lazy loading)
|
|
encoding = litellm.encoding
|
|
tokens = encoding.encode("Hello, world!")
|
|
assert len(tokens) > 0, "Encoding should work"
|
|
""",
|
|
)
|
|
assert result.returncode == 0, f"Subprocess failed:\nstdout: {result.stdout}\nstderr: {result.stderr}"
|
|
|
|
|
|
def test_tiktoken_cache_dir_set_on_lazy_load():
|
|
"""Test that TIKTOKEN_CACHE_DIR is set when encoding is lazy loaded.
|
|
|
|
This ensures the local tiktoken cache is used instead of downloading
|
|
from the internet. Regression test for issue #19768.
|
|
"""
|
|
result = _run_python(
|
|
"""
|
|
import os
|
|
import litellm
|
|
# Access encoding (triggers lazy load)
|
|
_ = litellm.encoding
|
|
assert "TIKTOKEN_CACHE_DIR" in os.environ, "TIKTOKEN_CACHE_DIR should be set after lazy loading encoding"
|
|
cache_dir = os.environ["TIKTOKEN_CACHE_DIR"]
|
|
assert "tokenizers" in cache_dir, f"TIKTOKEN_CACHE_DIR should point to tokenizers directory, got: {cache_dir}"
|
|
""",
|
|
)
|
|
assert result.returncode == 0, f"Subprocess failed:\nstdout: {result.stdout}\nstderr: {result.stderr}"
|