mirror of
https://github.com/BerriAI/litellm.git
synced 2026-08-28 05:25:59 +00:00
ffd6ac52c5
aiohttp 3.14.0 and 3.14.1 re-arm the sock_read timer on a keep-alive connection after it has already been returned to the idle pool. The stray timer stamps a SocketTimeoutError on the pooled connection without closing it, so the pool keeps handing it out and the next request to pick it up fails instantly on an error left behind by an earlier, unrelated request. Because a single pool is shared across providers, the failures appear simultaneously across Vertex AI, Bedrock, Anthropic and OpenAI-compatible deployments as sub-millisecond "Connection timed out" errors. uv.lock resolved aiohttp 3.14.1 and the published images install via `uv sync --frozen`, so every image built from that lock shipped the regression. The wheel's own metadata declared `aiohttp>=3.10,<4.0`, which also left pip consumers free to resolve into the same broken window, so both the runtime floor and the uv constraint move to >=3.14.2. Upstream fixed this in aio-libs/aiohttp#12954, released in aiohttp 3.14.2; the lock now resolves 3.14.3. Raising the floor rather than capping below 3.14 keeps the advisories that the existing 3.14.1 floor cleared, so no osv-scanner ignores are needed. litellm requires Python >=3.10 and aiohttp 3.14.2 requires >=3.10, so no supported interpreter loses support. Both new tests fail on the previous pins and pass on these.
363 lines
12 KiB
TOML
363 lines
12 KiB
TOML
[project]
|
|
name = "litellm"
|
|
version = "1.96.0"
|
|
description = "Library to easily interface with LLM API providers"
|
|
readme = "README.md"
|
|
requires-python = ">=3.10, <3.15"
|
|
license = "MIT"
|
|
license-files = ["LICENSE"]
|
|
authors = [
|
|
{ name = "BerriAI" },
|
|
]
|
|
dependencies = [
|
|
# Ranges (not exact pins) so SDK consumers can coexist with their other
|
|
# deps. Reproducibility for our Docker/CI comes from `uv.lock`.
|
|
# When changing a floor, verify it installs + imports on every supported
|
|
# Python with: `uv pip install --resolution=lowest-direct .`
|
|
"fastuuid>=0.14.0,<1.0",
|
|
"httpx>=0.28.0,<1.0",
|
|
"openai>=2.20.0,<3.0.0",
|
|
"python-dotenv>=1.0.0,<2.0",
|
|
"tiktoken>=0.8.0,<1.0",
|
|
"importlib-metadata>=8.0.0,<9.0",
|
|
"tokenizers>=0.21.0,<1.0",
|
|
"click>=8.0.0,<9.0",
|
|
"jinja2>=3.1.6,<4.0",
|
|
"aiohttp>=3.14.2,<4.0",
|
|
"pydantic>=2.10.0,<3.0.0",
|
|
"jsonschema>=4.0.0,<5.0",
|
|
]
|
|
|
|
[project.urls]
|
|
Homepage = "https://litellm.ai"
|
|
Repository = "https://github.com/BerriAI/litellm"
|
|
Documentation = "https://docs.litellm.ai"
|
|
|
|
# Optional extras use compatible ranges (like the core SDK above) so downstream
|
|
# consumers can coexist with other packages and pick up security patches without
|
|
# forking. Reproducibility for our Docker/CI comes from `uv.lock` (images install
|
|
# via `uv sync --frozen`). A few deps stay exact-pinned: litellm's own
|
|
# sub-packages and the opentelemetry trio move in lockstep, and grpcio is
|
|
# supply-chain-pinned to a vetted, aged release.
|
|
[project.optional-dependencies]
|
|
proxy = [
|
|
"gunicorn>=23.0.0,<24.0",
|
|
"uvicorn>=0.33.0,<1.0",
|
|
"granian>=2.7.4,<3.0",
|
|
"uvloop>=0.21.0,<1.0; sys_platform != 'win32'",
|
|
"fastapi>=0.136.3,<1.0",
|
|
"starlette>=1.0.1,<2.0",
|
|
"backoff>=2.2.1,<3.0",
|
|
"pyyaml>=6.0.3,<7.0",
|
|
"rq>=2.7.0,<3.0",
|
|
"orjson>=3.11.6,<4.0",
|
|
"apscheduler>=3.11.2,<4.0",
|
|
"fastapi-sso>=0.19.0,<1.0",
|
|
"PyJWT>=2.13.0,<3.0",
|
|
"python-multipart>=0.0.27,<1.0",
|
|
"cryptography>=48.0.1,<49.0",
|
|
"pynacl>=1.6.2,<2.0",
|
|
"websockets>=15.0.1,<16.0",
|
|
"boto3>=1.43.1,<2.0",
|
|
"azure-identity>=1.25.2,<2.0",
|
|
"azure-storage-blob>=12.28.0,<13.0",
|
|
"mcp>=1.28.1,<2.0",
|
|
"litellm-proxy-extras==0.4.81",
|
|
"litellm-enterprise==0.1.52",
|
|
"RestrictedPython>=8.1,<9.0",
|
|
"rich>=13.9.4,<14.0",
|
|
"InquirerPy>=0.3.4,<1.0",
|
|
"polars>=1.38.1,<2.0",
|
|
"soundfile>=0.12.1,<1.0",
|
|
"pyroscope-io>=0.8.16,<1.0; sys_platform != 'win32'",
|
|
"pydantic-settings>=2.14.1,<3.0",
|
|
"expression>=5.6.0,<6.0",
|
|
]
|
|
# Thin client install for the `lite` CLI on developer laptops. The CLI's heavy
|
|
# imports (fastapi, cryptography, ...) are all guarded, so it runs on the base
|
|
# SDK plus just these four; none of the server runtime in `proxy` is pulled in.
|
|
cli = [
|
|
"rich>=13.9.4,<14.0",
|
|
"pyyaml>=6.0.3,<7.0",
|
|
"requests>=2.32.0,<3.0",
|
|
"InquirerPy>=0.3.4,<1.0",
|
|
]
|
|
extra_proxy = [
|
|
"prisma>=0.11.0,<1.0",
|
|
"azure-identity>=1.25.2,<2.0",
|
|
"azure-keyvault-secrets>=4.10.0,<5.0",
|
|
# Not in PyPI proxy extra.
|
|
"google-cloud-kms>=2.24.2,<3.0",
|
|
"google-cloud-iam>=2.19.1,<3.0",
|
|
# Not in PyPI proxy extra.
|
|
"resend>=2.23.0,<3.0",
|
|
"redisvl>=0.4.1,<1.0",
|
|
"a2a-sdk>=1.1.0,<2.0",
|
|
]
|
|
utils = [
|
|
# Not in Docker or PyPI proxy extra.
|
|
"numpydoc>=1.8.0,<2.0",
|
|
]
|
|
caching = ["diskcache>=5.6.3,<6.0"]
|
|
# SAML SSO for the admin UI. python3-saml pulls in xmlsec/lxml, whose wheels
|
|
# bundle the native libxmlsec1/libxml2 libraries, so no system packages are
|
|
# required. Kept out of the base `proxy` extra so it stays optional.
|
|
saml = ["python3-saml>=1.16.0,<2.0"]
|
|
semantic-router = [
|
|
"semantic-router>=0.1.15,<1.0; python_version < '3.14'",
|
|
"aurelio-sdk>=0.0.19,<1.0; python_version < '3.14'",
|
|
]
|
|
mlflow = ["mlflow>=3.11.1,<4.0"]
|
|
grpc = [
|
|
# Newest non-yanked release older than the 30-day cutoff.
|
|
"grpcio==1.78.0",
|
|
]
|
|
stt-nvidia-riva = [
|
|
# NVIDIA Riva STT provider (gRPC). These are imported lazily inside the
|
|
# provider handler so litellm core remains usable without them.
|
|
"nvidia-riva-client>=2.15.0",
|
|
"soundfile>=0.12.1",
|
|
"audioread>=3.0.1",
|
|
"numpy>=1.26.0",
|
|
]
|
|
google = ["google-cloud-aiplatform>=1.133.0,<2.0"]
|
|
bedrock-realtime = [
|
|
# Bedrock Nova Sonic realtime (speech-to-speech) uses the
|
|
# InvokeModelWithBidirectionalStream API, which boto3 cannot do. This
|
|
# experimental AWS SDK (with its smithy-* deps, pulled transitively)
|
|
# provides the bidirectional stream; imported lazily in the realtime
|
|
# handler so litellm core stays usable without it.
|
|
"aws-sdk-bedrock-runtime>=0.7.0,<0.8.0; python_version >= '3.12'",
|
|
]
|
|
proxy-runtime = [
|
|
# Historically bundled in the proxy Docker images via requirements.txt.
|
|
# Keep these in a dedicated extra so uv-based images preserve the same
|
|
# feature surface without forcing the base SDK install to grow.
|
|
"google-cloud-aiplatform>=1.133.0,<2.0",
|
|
"google-genai>=1.37.0,<2.0",
|
|
"anthropic[vertex]>=0.84.0,<1.0",
|
|
"grpcio==1.78.0",
|
|
"prometheus-client>=0.20.0,<1.0",
|
|
"langfuse>=2.59.7,<3.0",
|
|
"opentelemetry-api==1.28.0",
|
|
"opentelemetry-sdk==1.28.0",
|
|
"opentelemetry-exporter-otlp==1.28.0",
|
|
"opentelemetry-instrumentation-fastapi==0.49b0",
|
|
"ddtrace>=4.8.2,<5.0",
|
|
"sentry-sdk>=2.21.0,<3.0",
|
|
"mangum>=0.17.0,<1.0",
|
|
"azure-ai-contentsafety>=1.0.0,<2.0",
|
|
"azure-storage-file-datalake>=12.20.0,<13.0",
|
|
"pypdf>=6.12.0,<7.0",
|
|
"llm-sandbox>=0.3.39,<1.0",
|
|
"detect-secrets>=1.5.0,<2.0",
|
|
]
|
|
|
|
[project.scripts]
|
|
litellm = "litellm:run_server"
|
|
lite = "litellm.proxy.client.cli:cli"
|
|
litellm-proxy = "litellm.proxy.client.cli:cli"
|
|
|
|
[dependency-groups]
|
|
dev = [
|
|
"diff-cover==9.7.2",
|
|
"flake8==7.3.0",
|
|
"basedpyright==1.39.7",
|
|
"pytest==9.0.3",
|
|
"pytest-mock==3.15.1",
|
|
"pytest-asyncio==1.3.0",
|
|
"pytest-postgresql==7.0.2",
|
|
# pytest-postgresql imports psycopg v3 during pytest startup. Keep the base
|
|
# package and the binary wheel in the default dev environment so local
|
|
# pytest works without requiring a system libpq install.
|
|
"psycopg==3.3.3",
|
|
"psycopg-binary==3.3.3",
|
|
"pytest-xdist==3.8.0",
|
|
"requests-mock==1.12.1",
|
|
"responses==0.26.0",
|
|
"respx==0.22.0",
|
|
"ruff==0.15.3",
|
|
"types-requests==2.32.4.20260107",
|
|
"types-setuptools==75.8.0.20250225",
|
|
"types-redis==4.6.0.20241004",
|
|
"types-PyYAML==6.0.12.20250915",
|
|
"botocore-stubs==1.43.14",
|
|
"types-boto3[bedrock,bedrock-agent,bedrock-runtime,kms,s3,sagemaker-runtime,sts]==1.43.30",
|
|
"opentelemetry-api==1.28.0",
|
|
"opentelemetry-sdk==1.28.0",
|
|
"opentelemetry-exporter-otlp==1.28.0",
|
|
"opentelemetry-instrumentation-fastapi==0.49b0",
|
|
"langfuse==2.59.7",
|
|
"fastapi-offline==1.7.6",
|
|
"fakeredis==2.34.1",
|
|
"pytest-rerunfailures==15.1",
|
|
"pytest-cov==5.0.0",
|
|
"parameterized==0.9.0",
|
|
"openapi-core==0.22.0",
|
|
"pytest-timeout==2.4.0",
|
|
"vcrpy==8.2.1",
|
|
"pytest-recording==0.13.4",
|
|
]
|
|
e2e-dev = [
|
|
"playwright==1.61.0",
|
|
"websockets>=15.0.1,<16.0",
|
|
"locust==2.45.0",
|
|
"mcp>=1.28.1,<2.0",
|
|
]
|
|
proxy-dev = [
|
|
"prisma==0.11.0",
|
|
"hypercorn==0.17.3",
|
|
"prometheus-client==0.20.0",
|
|
"opentelemetry-api==1.28.0",
|
|
"opentelemetry-sdk==1.28.0",
|
|
"opentelemetry-exporter-otlp==1.28.0",
|
|
"opentelemetry-instrumentation-fastapi==0.49b0",
|
|
"azure-identity==1.25.2",
|
|
"a2a-sdk==1.1.0",
|
|
]
|
|
ci = [
|
|
# These are lazily imported at call sites; keep them out of core deps to
|
|
# avoid bloating the base SDK install (google-generativeai pulls grpcio +
|
|
# protobuf, Pillow is a compiled C extension).
|
|
"tenacity==8.5.0",
|
|
"google-generativeai==0.8.6",
|
|
"Pillow==12.3.0",
|
|
# Azure batch E2E tests still import psycopg2 directly.
|
|
"psycopg2-binary==2.9.11",
|
|
"pytest-codspeed==4.3.0",
|
|
"pytest-retry==1.7.0",
|
|
"pyarrow==23.0.1",
|
|
"langchain==1.3.9",
|
|
"lunary==1.4.36; python_version == '3.10'",
|
|
"lunary==1.4.37; python_version >= '3.11'",
|
|
"logfire==4.6.0",
|
|
"traceloop-sdk==0.33.12",
|
|
"detect-secrets==1.5.0",
|
|
"PyGithub==2.8.1",
|
|
"aiodynamo==24.7",
|
|
"argon2-cffi==25.1.0",
|
|
"assemblyai==0.52.4",
|
|
"jsonlines==4.0.0",
|
|
"anthropic==0.84.0",
|
|
"blockbuster==1.5.26",
|
|
"beautifulsoup4==4.14.3",
|
|
"pylint==4.0.5",
|
|
"langchain-mcp-adapters==0.2.1",
|
|
"langchain-openai==1.1.14",
|
|
"langgraph>=1.2.4,<1.3.0",
|
|
"langgraph-prebuilt>=1.1.0,<1.3.0",
|
|
"claude-agent-sdk==0.1.44",
|
|
]
|
|
healthcheck = [
|
|
"httpx==0.28.1",
|
|
"pyyaml==6.0.3",
|
|
]
|
|
|
|
[build-system]
|
|
requires = ["maturin==1.9.4"]
|
|
build-backend = "maturin"
|
|
|
|
[tool.maturin]
|
|
manifest-path = "litellm-rust/crates/python-bridge/Cargo.toml"
|
|
module-name = "litellm.rust_bridge._native"
|
|
python-source = "."
|
|
bindings = "pyo3"
|
|
include = ["litellm/proxy/_experimental/out/**"]
|
|
exclude = [
|
|
"litellm/proxy/enterprise",
|
|
"litellm/proxy/enterprise/**",
|
|
"**/__pycache__",
|
|
"**/__pycache__/**",
|
|
"**/.pytest_cache",
|
|
"**/.pytest_cache/**",
|
|
"**/.ruff_cache",
|
|
"**/.ruff_cache/**",
|
|
]
|
|
|
|
[tool.uv]
|
|
constraint-dependencies = [
|
|
"tornado>=6.5.6",
|
|
"aiohttp>=3.14.2,<4.0",
|
|
"packaging>=24.0",
|
|
"soupsieve>=2.8.4",
|
|
"httplib2>=0.32.0",
|
|
"setuptools>=83.0.0",
|
|
]
|
|
override-dependencies = [
|
|
# a2a-sdk 1.x requires packaging>=24.0; lunary 1.4.x still caps at <24.0.
|
|
"packaging>=24.0",
|
|
]
|
|
default-groups = ["dev"]
|
|
required-version = ">=0.10.9"
|
|
exclude-newer = "3 days"
|
|
|
|
[tool.uv.sources]
|
|
litellm-proxy-extras = { workspace = true }
|
|
litellm-enterprise = { workspace = true }
|
|
|
|
[tool.uv.workspace]
|
|
members = ["enterprise", "litellm-proxy-extras"]
|
|
|
|
[tool.isort]
|
|
profile = "black"
|
|
|
|
[tool.commitizen]
|
|
version = "1.96.0"
|
|
version_files = [
|
|
"pyproject.toml:^version",
|
|
]
|
|
|
|
[tool.pytest.ini_options]
|
|
asyncio_mode = "auto"
|
|
asyncio_default_fixture_loop_scope = "session"
|
|
markers = [
|
|
"asyncio: mark test as an asyncio test",
|
|
"limit_leaks: mark test with memory limit for leak detection (e.g., '40 MB')",
|
|
"no_parallel: mark test to run sequentially (not in parallel) - typically for memory measurement tests",
|
|
]
|
|
filterwarnings = [
|
|
# Suppress Pydantic serializer warnings from mock server responses (non-critical for memory tests)
|
|
# These occur because the mock server returns a simplified response format
|
|
"ignore:Pydantic serializer warnings:UserWarning",
|
|
"ignore::UserWarning:pydantic.main",
|
|
# Suppress pytest-asyncio event loop deprecation warning (handled automatically by pytest-asyncio)
|
|
"ignore::DeprecationWarning:pytest_asyncio.plugin",
|
|
]
|
|
|
|
[tool.mutmut]
|
|
# Mutation-testing scope. Driven by the manually-triggered workflow at
|
|
# .github/workflows/mutation-test.yml. mutmut is not part of the project's
|
|
# default install; it is pulled in via `uv run --with mutmut==<version>` in CI.
|
|
# `also_copy = ["litellm/"]` is required because mutmut runs in a `mutants/`
|
|
# sandbox and the test conftest imports from across the litellm package.
|
|
paths_to_mutate = [
|
|
"litellm/proxy/management_endpoints/",
|
|
]
|
|
tests_dir = [
|
|
"tests/test_litellm/proxy/management_endpoints/",
|
|
"tests/proxy_behavior/management/",
|
|
]
|
|
also_copy = [
|
|
"litellm/",
|
|
]
|
|
# Run the test suite once before mutation to gather line coverage, then skip
|
|
# mutating lines no test exercises. Those mutants would survive regardless
|
|
# (no test hits the line to kill them), so generating them wastes hours of CI.
|
|
# The score now reads as "mutation score over covered code" — pair with a
|
|
# line-coverage number when reporting.
|
|
mutate_only_covered_lines = true
|
|
# Disable rerun/parallel plugins for mutation runs:
|
|
# - pytest-retry triggers an `INTERNALERROR: no option named 'filtered_exceptions'`
|
|
# when invoked via mutmut's in-process `pytest.main()` call.
|
|
# - rerunning a "failed" test on a mutant would mask which mutants are killed
|
|
# vs. survive, so reruns are wrong for mutation testing regardless.
|
|
# - xdist is unnecessary inside mutmut (mutmut handles its own parallelism).
|
|
pytest_add_cli_args = [
|
|
"-p", "no:retry",
|
|
"-p", "no:rerunfailures",
|
|
"-p", "no:xdist",
|
|
]
|
|
|
|
[tool.coverage.run]
|
|
source = ["litellm"]
|
|
relative_files = true
|