scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-11-11 08:38:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 280
litellm/pyproject.toml
joshua-berri de0b389205
feat(router): add the Switchyard stage router as an auto router strategy (#50407) 
* feat(router): add Switchyard Stage Router strategy

* feat(router): decision-model classifier and safer fallbacks for the Switchyard stage router

Moves to nemo-switchyard 0.4.0a1, which adds decision-model classifiers and makes
ModelCall.respond and fail async. The classifier is now a tagged union of an LLM
judge and a decision model, and decision calls go through the router's adecisions
so any decisions provider works. Algorithm misbehavior and library errors route to
the capable model instead of failing the request, and the session id plus client
session headers are always passed so capable holds apply without a classifier

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* fix(router): keep the Switchyard router inside the type-check gate

The gate's environment did not install the optional switchyard extra, so every
libsy symbol counted as Unknown. nemo-switchyard joins proxy-dev like the other
optional runtime packages, and imports go through switchyard_rust.libsy, which
ships py.typed. Step handling moves into helpers so no Final is rebound in the
loop, and the dashboard API types are regenerated for the new routing fields

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* fix(router): route Switchyard on every endpoint and reject unsafe router saves

The router now passes each request's call type to routing strategies, and
Switchyard converts the request to chat messages with the existing converter for
that call type before translating it. /v1/messages turns with tool or thinking
blocks used to fall back to the capable model, and now route on their signals.
The Anthropic converter can keep tool_result.is_error on an analysis copy, so
Switchyard sees tool failures there, while requests sent to models never carry it

Saves of a strategy router that lists itself now fail with a 400 instead of a
500 with a dead row, the capable and efficient models must differ, judge and
decision calls are not retried before failing open, the Switchyard routing
fields are classified for redaction, and the edit dialog returns the saved
router instead of the stale one

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* fix(router): catch self-routing on patch and rename, and trim Switchyard tests

The self-routing check now reads the stored params through the decrypting
helper and runs when a patch carries no litellm_params, so a PATCH that points
a router at itself or renames it onto one of its targets returns 400 instead of
a 500 with a dead row. The Switchyard tests share one transcript builder and
router fixture, and reformatting noise in unrelated test files is reverted

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* refactor(ui): make Switchyard a strategy in the existing auto router form

Switchyard is now a card in the existing strategy picker. Picking it swaps the
tier and classifier fields for the Switchyard fields, and the shared name, team
and save button create it through one submit branch, the same flow as the other
strategies. The separate add form, the extracted picker and the hidden-form
swap are gone, and the edit dialog keeps its own Switchyard form

The judge's session_affinity and message_hash_fallback settings are removed,
since Switchyard rejects both for the stage router

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* fix(ui): accept partial tool semantics and show server errors on model edit

The Switchyard tool semantics field rejected mappings that list only some
categories, although the server accepts them. Model PATCH errors were
reduced to a generic message, so it now goes through the shared API client
like model create and surfaces the server text

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* feat(ui): show the routing strategy picker up front in the auto router form

Every strategy was hidden behind an Advanced configuration link, so the
quick setup read as the only option and never said it creates a heuristic
router. The picker now always shows with Heuristics as the labelled
default, the quick setup sits under it, and picking another strategy opens
that strategy prefilled with the chosen models

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* fix(ui): show the server's reason when a model settings or API key update fails

Both screens replaced the rejection with a fixed message, so a 400 such as
a router routing to itself read only as a generic failure

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* feat(router): route Switchyard on the Rust router core

main replaced the Python router core with the Rust one, which left
Switchyard routers registered nowhere. Register them with the other
pre-routing strategies, hand each strategy the endpoint the request came
through, and evict Switchyard routers on reload and delete like the rest

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* fix(router): scope Switchyard sessions per API key and fix review gaps in the Switchyard form

Switchyard session state is keyed by a hash of the caller's key hash and session id, and client
session headers no longer reach Switchyard unscoped. The add form carries the quick setup models
into Switchyard, sends the team and access groups, clears a stale tool semantics error, and the
schema reads API-saved configs with nulls and structured decision instructions

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* test(router): make the Switchyard test folder a package

* fix(router): read the Switchyard session key hash only from the proxy's own metadata

* fix(proxy): keep nested nulls as null when masking deployment params

* fix(router): send Switchyard judge calls with the caller's own metadata bucket so tag routing applies

* fix(router): put Switchyard judge metadata in the bucket the judge endpoint reads

---------

Co-authored-by: Joshua Valluru <326636767+joshua-berri@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 12:07:57 -08:00

481 lines
17 KiB
TOML
Raw Permalink Blame History

[project]
name = "litellm"
version = "1.110.0"
description = "Library to easily interface with LLM API providers"
readme = "README.md"
requires-python = ">=3.10, <3.16"
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; python_version < '3.15'",
"filelock>=3.16.1,<5",
"httpx[http2]>=0.28.0,<1.0",
"openai>=2.20.0,<4.0.0",
"python-dotenv>=1.0.0,<2.0",
"pyyaml>=6.0.3,<7.0",
"packaging>=24.0",
"importlib-metadata>=8.0.0,<9.0",
"tiktoken>=0.8.0,<1.0; python_version < '3.14'",
"tiktoken>=0.12.0,<1.0; python_version == '3.14'",
"tiktoken>=0.14.0,<1.0; python_version >= '3.15'",
"tokenizers>=0.21.0,<1.0",
"huggingface-hub>=0.34.0,<3.0",
"click>=8.0.0,<9.0",
"jinja2>=3.1.6,<4.0",
"aiohttp>=3.14.2,<4.0",
"anyio>=4.14.0,<5.0",
"async-timeout>=4.0.3,<6.0; python_version < '3.11'",
"pydantic>=2.11.0,<3.0.0; python_version < '3.14'",
"pydantic>=2.12.0,<3.0.0; python_version == '3.14'",
"pydantic>=2.14.0,<3.0.0; python_version >= '3.15'",
"pydantic-settings>=2.14.1,<3.0",
"jsonschema>=4.0.0,<5.0",
"boto3>=1.43.117,<2.0",
"certifi>=2026.10.19",
"typing-extensions>=4.13.0,<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]
switchyard = ["nemo-switchyard==0.4.0a1"]
proxy = [
"gunicorn>=23.0.0,<24.0",
"uvicorn>=0.33.0,<1.0",
"granian>=2.7.4,<3.0; python_version < '3.15'",
"granian>=2.8.0,<3.0; python_version >= '3.15'",
"uvloop>=0.22.1,<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; python_version < '3.15'",
"orjson>=3.12.0,<4.0; python_version >= '3.15'",
# redis-py's C response parser. It arrives with redis (via rq) either way; naming
# it here is what makes redis-py select _HiredisParser instead of the Python one.
"hiredis>=3.0.0,<4.0; python_version < '3.15'",
"hiredis>=3.5.0,<4.0; python_version >= '3.15'",
"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>=49.0.0,<51.0",
"pynacl>=1.6.2,<2.0",
"websockets>=15.0.1,<16.0",
"boto3>=1.43.117,<2.0",
"azure-identity>=1.25.2,<2.0",
"azure-storage-blob>=12.28.0,<13.0",
"mcp>=2.3.0,<3",
"httpx2>=2.10.0,<3",
"pydantic>=2.12.0,<3",
"litellm-proxy-extras==0.4.114",
"litellm-enterprise==0.1.83",
"RestrictedPython>=8.5,<9.0",
"rich>=13.9.4,<14.0",
"InquirerPy>=0.3.4,<1.0",
"tomlkit>=0.13.3,<1.0",
"polars>=1.38.1,<2.0",
"soundfile>=0.12.1,<1.0",
"pyroscope-io>=0.8.16,<1.0; sys_platform != 'win32'",
"expression>=5.6.0,<6.0",
"backports-zstd>=1.0.0,<2.0; python_version < '3.14'",
"semver>=3.0.4,<4",
]
# Thin client install for the `lite` CLI on developer laptops. The CLI's heavy
# imports are all guarded, so it runs on the base SDK plus these packages, and
# none of the server runtime in `proxy` is pulled in. On Linux,
# keyring reaches the Secret Service through secretstorage, which brings
# cryptography with it.
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",
"keyring>=25.6.0,<26.0",
"tomlkit>=0.13.3,<1.0",
]
extra_proxy = [
"prisma>=0.11.0,<1.0",
# Used by ProxyExtrasDBManager.spend_logs_is_partitioned() to detect a
# partitioned LiteLLM_SpendLogs and keep schema reconciliation from
# fighting its composite primary key.
"psycopg>=3.2,<4.0",
"psycopg-binary>=3.2,<4.0",
"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",
]
mcp = ["mcp>=2.3.0,<3", "httpx2>=2.10.0,<3", "pydantic>=2.12.0,<3"]
# Driver for the MongoDB Atlas vector store; Atlas Vector Search has no HTTP query API.
# The floor is 4.9 because that is the release AsyncMongoClient landed in.
# 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>=3.17.2,<4.0"]
grpc = [
# First release whose bundled roots.pem drops the compromised eMudhra roots, ahead of the 30-day cutoff
"grpcio==1.84.1",
]
stt-vertex-chirp = [
# Google Cloud Speech-to-Text v2 streaming (gRPC) for Chirp models on
# /v1/realtime. Imported lazily inside the backend so litellm core stays
# usable without it.
"google-cloud-speech>=2.40.0,<3.0",
]
stt-nvidia-riva = [
# NVIDIA Riva STT provider (gRPC). These are imported lazily inside the
# provider handler so litellm core remains usable without them.
"grpcio>=1.67.1,<2.0",
"protobuf>=5.26.1,<7.0",
"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. The awscrt extra is
# required: the SDK's default aiohttp transport has no duplex streaming.
"aws-sdk-bedrock-runtime[awscrt]>=0.10.0,<0.12.0; 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-cloud-speech>=2.40.0,<3.0",
"google-genai>=1.37.0,<2.0",
"anthropic[vertex]>=0.84.0,<1.0",
"grpcio==1.84.1",
"prometheus-client>=0.20.0,<1.0",
"langfuse>=4.7,<5.0",
"opentelemetry-api==1.45.1",
"opentelemetry-sdk==1.45.1",
"opentelemetry-exporter-otlp==1.45.1",
"opentelemetry-instrumentation-fastapi==0.66b1",
"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>=6.21.2,<7.0",
"llm-sandbox>=0.3.39,<1.0",
"detect-secrets>=1.5.0,<2.0",
]
[project.scripts]
litellm = "litellm_cli.main:proxy_server"
lite = "litellm_cli.main:cli"
litellm-proxy = "litellm_cli.main:litellm_proxy_cli"
[dependency-groups]
dev = [
"numpy>=1.26.0,<3.0",
"diff-cover==9.7.2",
"hypothesis==6.165.10",
"reportlab==5.0.1",
"basedpyright==1.39.7",
"mypy==1.20.1",
"keyring==25.7.0",
"pytest==9.0.3",
"pytest-socket==0.8.1",
"tomli==2.4.1; python_version < '3.11'",
"pytest-mock==3.15.1",
"pytest-asyncio==1.3.0",
"psycopg==3.3.6",
"psycopg-binary==3.3.6",
"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==1.45.1",
"opentelemetry-sdk==1.45.1",
"opentelemetry-exporter-otlp==1.45.1",
"opentelemetry-instrumentation-fastapi==0.66b1",
"langfuse>=4.7,<5.0",
"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",
"nvidia-riva-client==2.16.0",
]
e2e-dev = [
"playwright==1.61.0",
"websockets>=15.0.1,<16.0",
"locust==2.45.0",
"anthropic==0.84.0",
"psutil==7.2.2",
"mcp>=2.3.0,<3",
]
admin-mcp = [
"litellm-admin-mcp @ https://github.com/BerriAI/liteadmin-mcp/archive/31fb096904ae05684c0779110a93b135b5601182.tar.gz#sha256=5803a20a00a18177f4591706956f31be311879543049b8b38143ad90bb1cb0a6 ; python_version >= '3.12'",
]
proxy-dev = [
{ include-group = "admin-mcp" },
"prisma==0.11.0",
"hypercorn==0.17.3",
"prometheus-client==0.20.0",
"sentry-sdk==2.21.0",
"opentelemetry-api==1.45.1",
"opentelemetry-sdk==1.45.1",
"opentelemetry-exporter-otlp==1.45.1",
"opentelemetry-instrumentation-fastapi==0.66b1",
"azure-identity==1.25.2",
"a2a-sdk==1.1.0",
"nemo-switchyard==0.4.0a1",
"backports-zstd==1.8.0; python_version < '3.14'",
"httptools>=0.7.1,<0.8",
"semver>=3.0.4,<4",
]
ci = [
"psutil==7.2.2",
# 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",
# The Riva tests serve NVIDIA's own message definitions, which checks
# LiteLLM's hand-written copy of them on every run.
"nvidia-riva-client==2.16.0",
"Pillow==12.3.0; python_version == '3.10'",
"Pillow==13.0.0; python_version >= '3.11'",
# 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==5.2.0",
"traceloop-sdk==0.34.0",
"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==4.0.9",
"langchain-openai==1.1.14",
"langgraph>=1.2.4,<1.3.0",
"langgraph-prebuilt>=1.1.0,<1.3.0",
"claude-agent-sdk==0.2.165",
"google-cloud-speech==2.40.0",
]
healthcheck = [
"httpx==0.28.1",
"pyyaml==6.0.3",
]
benchmarks = [
"pytest==9.0.3",
"pytest-codspeed==4.3.0",
"mcp>=2.3.0,<3",
"a2a-sdk==1.1.0",
"pypdf>=6.21.2,<7.0",
]
[build-system]
requires = ["maturin==1.15.0"]
build-backend = "maturin"
[tool.maturin]
manifest-path = "litellm-rust/crates/python-bridge/Cargo.toml"
module-name = "litellm.rust_bridge._native"
python-source = "."
python-packages = ["litellm_cli"]
bindings = "pyo3"
features = ["extension-module"]
profile = "release"
editable-profile = "dev"
include = [
"litellm/proxy/_experimental/out/**",
"litellm/router_strategy/complexity_router/artifacts/*.json",
"litellm/router_strategy/complexity_router/fuse_presets.json",
"litellm/proxy/model_insights_tasks.json",
"litellm/proxy/public_endpoints/whats_new.json",
"litellm/proxy/common_utils/codex_base_instructions.md",
"litellm/proxy/common_utils/codex_bundled_models_0.166.0.json",
{ path = "model_prices_and_context_window.json", format = "sdist" },
]
exclude = [
"litellm/proxy/enterprise",
"litellm/proxy/enterprise/**",
"litellm/proxy/guardrails/guardrail_hooks/litellm_content_filter/guardrail_benchmarks",
"litellm/proxy/guardrails/guardrail_hooks/litellm_content_filter/guardrail_benchmarks/**",
"**/__pycache__",
"**/__pycache__/**",
"**/.pytest_cache",
"**/.pytest_cache/**",
"**/.ruff_cache",
"**/.ruff_cache/**",
]
[tool.uv]
concurrent-builds = 1
cache-keys = [
{ file = "pyproject.toml" },
{ file = "rust-toolchain.toml" },
{ file = ".cargo/config.toml" },
{ file = "litellm-rust/Cargo.lock" },
{ file = "litellm-rust/Cargo.toml" },
{ file = "litellm-rust/crates/**/*" },
{ file = "model_prices_and_context_window.json" },
]
constraint-dependencies = [
"tornado>=6.5.8",
"tornado>=6.6; python_version >= '3.11'",
"aiohttp>=3.14.2,<4.0",
"packaging>=24.0",
"soupsieve>=2.8.4",
"httplib2>=0.32.0",
"setuptools>=84.1.0",
"dnspython>=2.9.0; python_version >= '3.11'",
"filelock<3.20.4; python_version < '3.11'",
"filelock>=4.2.1; python_version >= '3.11'",
]
override-dependencies = [
# a2a-sdk 1.x requires packaging>=24.0; lunary 1.4.x still caps at <24.0.
"packaging>=24.0",
"cryptography>=50.0.0,<51.0",
"mcp>=2.3.0,<3",
]
default-groups = ["dev"]
required-version = ">=0.10.9"
exclude-newer = "3 days"
[tool.uv.exclude-newer-package]
# TODO: remove after 2026-10-25, once brotli 1.2.1 (CVE-2026-111497) clears the 3-day window
brotli = "2026-10-22T14:01:00Z"
# TODO: remove after 2026-10-31, once pypdf 6.21.4 clears the 3-day window
pypdf = "2026-10-28T17:01:00Z"
[tool.uv.sources]
litellm-proxy = { workspace = true }
litellm-proxy-extras = { workspace = true }
litellm-enterprise = { workspace = true }
[tool.uv.workspace]
members = ["enterprise", "litellm-proxy-extras", "packaging/litellm-proxy"]
[tool.commitizen]
version = "1.110.0"
version_files = [
"pyproject.toml:^version",
]
[tool.pytest.ini_options]
pythonpath = ["scripts"]
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",
"requires_rust_extension: public Python contract tests that run against the release-built wheel",
]
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/",
]
# Only the unit tier that maps to paths_to_mutate. mutmut times and
# coverage-maps this whole set once before mutating, so a tier that needs a
# seeded database (tests/proxy_behavior/) kills the run before it starts, and
# a mutation score is only meaningful against the tests that claim to cover
# the mutated code anyway.
tests_dir = [
"tests/unit/proxy/management_endpoints/",
]
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).
# test_saml_sso.py cannot run inside mutmut's mutants/ sandbox: the copied tree
# re-imports cryptography's hash classes under a second identity, so x509 .sign()
# rejects the SHA256 instance the fixture builds with "Algorithm must be a
# registered hash algorithm". Nothing to do with mutation coverage, and one
# erroring test is enough to end the stats phase before any mutant runs.
pytest_add_cli_args = [
"-p", "no:pytest-retry",
"-p", "no:rerunfailures",
"-p", "no:xdist",
"--ignore=tests/unit/proxy/management_endpoints/test_saml_sso.py",
]
[tool.coverage.run]
source = ["litellm"]
relative_files = true
Reference in a new issue View git blame Copy permalink