mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-16 04:29:31 +00:00
2d4472efc1
* fix(vllm): write spend log rows for /vllm passthrough calls to router models The vLLM passthrough config never built a logged response for relayed calls, so stream and non-stream calls through /vllm with a router model wrote no spend row and never charged the key. vLLM now shares the OpenAI-shaped relay logging that Azure already had, moved into an openai_like helper both configs call. * ci: run the vllm passthrough unit tests in the llms-providers shard * fix(proxy): log /vllm text completions and ask router models for stream usage A chat stream relayed to a router model without stream_options now gets include_usage added on the way out, and the usage chunk vLLM appends is removed before the client sees it, so the spend row carries vLLM's own token counts instead of a local estimate. /vllm/completions calls now write a row too, stream and non-stream. * fix(vllm): keep usage, fingerprints, and disconnect rows correct on /vllm streams Inject and strip stream usage on /vllm/completions too, hold every finish frame for the fingerprint when n > 1, pass a forced-usage server's stream through untouched, stop turning continuous_usage_stats alone into per-chunk usage, close the upstream when the client hangs up so the row is written, and assemble text choices with one sort instead of a scan per choice * fix(vllm): keep n>1 stream order when holding finish chunks for the fingerprint A held finish chunk now goes out as soon as any other chunk arrives, so a choice that finishes while another still streams keeps its place. Only the finish chunks right before the usage chunk get vLLM's system_fingerprint. * fix(vllm): keep caller stream_options and log both success handlers Forward a stream_options the proxy cannot read, or a non-boolean include_usage, to vLLM as the caller sent it. Only a false always_include_stream_usage changes the /vllm relay, so clients get the same stream bytes under every setting. Record the passthrough origin when logging starts so the sync and async success handlers both parse the relayed body, hand callbacks a parsed text completion, and read relayed messages and prompt separately so a stray field no longer drops the local count. Add the audit's integration tests for the relay, the settings, and the Azure spend row. * test(vllm): expect the caller's stream under always_include_stream_usage true * fix(vllm): relay long SSE frames in linear time * test(vllm): time the relay's usage and finish_reason prefilter on one large frame --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
1536 lines
60 KiB
YAML
1536 lines
60 KiB
YAML
name: unit
|
|
|
|
on:
|
|
pull_request:
|
|
branches:
|
|
- main
|
|
- "litellm_**"
|
|
push:
|
|
branches:
|
|
- main
|
|
workflow_dispatch:
|
|
|
|
permissions:
|
|
contents: read
|
|
|
|
concurrency:
|
|
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}
|
|
cancel-in-progress: ${{ github.event_name == 'pull_request' }}
|
|
|
|
jobs:
|
|
rust-bridge:
|
|
name: rust-bridge
|
|
permissions:
|
|
contents: read
|
|
pull-requests: read
|
|
outputs:
|
|
artifact: ${{ steps.rust-bridge-artifact.outputs.name }}
|
|
runs-on: ubuntu-latest
|
|
env:
|
|
UV_PYTHON: "3.12"
|
|
steps:
|
|
- uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955
|
|
with:
|
|
persist-credentials: false
|
|
|
|
- name: Detect relevant changes
|
|
id: changes
|
|
timeout-minutes: 2
|
|
uses: ./.github/actions/detect-changes
|
|
|
|
- name: Define editable Rust bridge cache key
|
|
id: rust-bridge-key
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
env:
|
|
RUST_BRIDGE_CACHE_KEY: ${{ runner.os }}-rust-bridge-editable-${{ hashFiles('litellm-rust/Cargo.lock', 'litellm-rust/Cargo.toml', 'litellm-rust/crates/**', 'pyproject.toml') }}
|
|
run: echo "key=$RUST_BRIDGE_CACHE_KEY" >> "$GITHUB_OUTPUT"
|
|
|
|
- name: Set up Python
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
timeout-minutes: 3
|
|
uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065
|
|
with:
|
|
python-version: ${{ env.UV_PYTHON }}
|
|
|
|
- name: Set up uv
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
timeout-minutes: 3
|
|
uses: ./.github/actions/setup-uv-with-retries
|
|
with:
|
|
version: "0.10.9"
|
|
|
|
- name: Restore editable Rust bridge
|
|
id: rust-bridge-cache
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
timeout-minutes: 5
|
|
uses: actions/cache/restore@0057852bfaa89a56745cba8c7296529d2fc39830
|
|
with:
|
|
path: rust-bridge-dist
|
|
key: ${{ steps.rust-bridge-key.outputs.key }}
|
|
|
|
- name: Cache the Rust build
|
|
if: steps.changes.outputs.decision != 'skip' && steps.rust-bridge-cache.outputs.cache-hit != 'true'
|
|
timeout-minutes: 5
|
|
uses: ./.github/actions/cache-cargo-build
|
|
|
|
- name: Build editable Rust bridge
|
|
if: steps.changes.outputs.decision != 'skip' && steps.rust-bridge-cache.outputs.cache-hit != 'true'
|
|
timeout-minutes: 15
|
|
run: |
|
|
mkdir -p rust-bridge-dist
|
|
uv run --no-project --with maturin==1.15.0 python -c 'import maturin; maturin.build_editable("rust-bridge-dist")'
|
|
strip --strip-debug litellm/rust_bridge/_native.abi3.so
|
|
mkdir -p rust-bridge-dist/litellm/rust_bridge
|
|
cp litellm/rust_bridge/_native.abi3.so rust-bridge-dist/litellm/rust_bridge/_native.abi3.so
|
|
|
|
- name: Upload Rust bridge artifact
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
timeout-minutes: 10
|
|
uses: actions/upload-artifact@4cec3d8aa04e39d1a68397de0c4cd6fb9dce8ec1
|
|
with:
|
|
name: rust-bridge-${{ github.run_id }}-${{ github.run_attempt }}
|
|
path: rust-bridge-dist/
|
|
retention-days: 1
|
|
|
|
- name: Save editable Rust bridge
|
|
if: steps.changes.outputs.decision != 'skip' && github.ref == 'refs/heads/main' && steps.rust-bridge-cache.outputs.cache-hit != 'true'
|
|
timeout-minutes: 10
|
|
uses: actions/cache/save@0057852bfaa89a56745cba8c7296529d2fc39830
|
|
with:
|
|
path: rust-bridge-dist
|
|
key: ${{ steps.rust-bridge-key.outputs.key }}
|
|
|
|
- name: Expose the Rust bridge artifact
|
|
id: rust-bridge-artifact
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
timeout-minutes: 1
|
|
env:
|
|
RUN_ID: ${{ github.run_id }}
|
|
RUN_ATTEMPT: ${{ github.run_attempt }}
|
|
run: echo "name=rust-bridge-${RUN_ID}-${RUN_ATTEMPT}" >> "$GITHUB_OUTPUT"
|
|
assert-shard-coverage:
|
|
permissions:
|
|
contents: read
|
|
runs-on: ubuntu-latest
|
|
timeout-minutes: 2
|
|
steps:
|
|
- uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
|
|
with:
|
|
persist-credentials: false
|
|
- name: Assert every test directory and file is claimed by a shard
|
|
run: python3 .github/scripts/assert_ci_coverage.py --shards
|
|
unit:
|
|
name: ${{ matrix.shard }}
|
|
needs: [rust-bridge, assert-shard-coverage]
|
|
if: ${{ !cancelled() }}
|
|
runs-on: ubuntu-latest
|
|
timeout-minutes: ${{ matrix.job-timeout-minutes }}
|
|
permissions:
|
|
contents: read
|
|
pull-requests: read
|
|
env:
|
|
UV_PYTHON: ${{ matrix.python-version }}
|
|
LITELLM_LOCAL_MODEL_COST_MAP: "True"
|
|
strategy:
|
|
fail-fast: false
|
|
matrix:
|
|
include:
|
|
- shard: core-utils
|
|
test-path: |-
|
|
tests/unit/batch_completion
|
|
tests/unit/decisions
|
|
tests/unit/litellm_core_utils
|
|
tests/unit/systemone
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 0
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: enterprise-routing
|
|
test-path: |-
|
|
tests/unit/google_genai
|
|
tests/unit/router_strategy
|
|
tests/unit/router_utils
|
|
tests/unit/proxy/common_utils/test_cache_aware_routing.py
|
|
tests/unit/enterprise/enterprise_callbacks/send_emails
|
|
tests/unit/enterprise/proxy/test_afile_retrieve_returns_unified_id.py
|
|
tests/unit/enterprise/proxy/test_batch_retrieve_input_file_id.py
|
|
tests/unit/enterprise/proxy/test_batch_retrieve_registers_missing_output_file_id.py
|
|
tests/unit/enterprise/proxy/test_batch_retrieve_returns_unified_input_file_id.py
|
|
tests/unit/enterprise/proxy/test_batch_update_db_managed_output_file_id.py
|
|
tests/unit/enterprise/proxy/test_deleted_file_returns_403_not_404.py
|
|
tests/unit/enterprise/proxy/test_enterprise_routes.py
|
|
tests/unit/enterprise/proxy/test_file_deletion_blocking.py
|
|
tests/unit/enterprise/proxy/test_managed_files_access_check.py
|
|
tests/unit/enterprise/proxy/test_managed_files_hook.py
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 2
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: integrations
|
|
test-path: |-
|
|
tests/unit/integrations
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 0
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: llms-vertex-ai
|
|
test-path: >-
|
|
tests/unit/llms/vertex_ai
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 0
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: llms-anthropic
|
|
test-path: >-
|
|
tests/unit/llms/anthropic
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 0
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: llms-bedrock
|
|
test-path: |-
|
|
tests/unit/llms/bedrock
|
|
tests/unit/llms/bedrock_mantle
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 0
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: llms-providers
|
|
test-path: |-
|
|
tests/unit/llms/test_cache_control_and_reasoning.py
|
|
tests/unit/llms/test_custom_llm.py
|
|
tests/unit/llms/test_file_content_block.py
|
|
tests/unit/llms/test_file_search_responses.py
|
|
tests/unit/llms/test_lifecycle_fix.py
|
|
tests/unit/llms/test_oss_decision.py
|
|
tests/unit/llms/test_polling_url_origin_match.py
|
|
tests/unit/llms/test_predibase_transformation.py
|
|
tests/unit/llms/a2a
|
|
tests/unit/llms/aiml
|
|
tests/unit/llms/aiohttp_openai
|
|
tests/unit/llms/apiserpent
|
|
tests/unit/llms/aws_polly
|
|
tests/unit/llms/azure
|
|
tests/unit/llms/azure_ai
|
|
tests/unit/llms/base_llm
|
|
tests/unit/llms/baseten
|
|
tests/unit/llms/black_forest_labs
|
|
tests/unit/llms/brave
|
|
tests/unit/llms/bytez
|
|
tests/unit/llms/cerebras
|
|
tests/unit/llms/chat
|
|
tests/unit/llms/chatgpt
|
|
tests/unit/llms/clarifai
|
|
tests/unit/llms/claude_code
|
|
tests/unit/llms/cloudflare
|
|
tests/unit/llms/codex
|
|
tests/unit/llms/cohere
|
|
tests/unit/llms/cometapi
|
|
tests/unit/llms/compactifai
|
|
tests/unit/llms/crusoe
|
|
tests/unit/llms/custom_httpx
|
|
tests/unit/llms/dashscope
|
|
tests/unit/llms/databricks
|
|
tests/unit/llms/dataforseo
|
|
tests/unit/llms/datarobot
|
|
tests/unit/llms/deepagents
|
|
tests/unit/llms/deepgram
|
|
tests/unit/llms/deepinfra
|
|
tests/unit/llms/deepseek
|
|
tests/unit/llms/docker_model_runner
|
|
tests/unit/llms/duckduckgo
|
|
tests/unit/llms/e2b
|
|
tests/unit/llms/edenai
|
|
tests/unit/llms/elevenlabs
|
|
tests/unit/llms/exa_ai
|
|
tests/unit/llms/fal_ai
|
|
tests/unit/llms/fastcrw
|
|
tests/unit/llms/featherless_ai
|
|
tests/unit/llms/firecrawl
|
|
tests/unit/llms/fireworks_ai
|
|
tests/unit/llms/gdc
|
|
tests/unit/llms/gemini
|
|
tests/unit/llms/gigachat
|
|
tests/unit/llms/google_pse
|
|
tests/unit/llms/github_copilot
|
|
tests/unit/llms/gradient_ai
|
|
tests/unit/llms/groq
|
|
tests/unit/llms/heroku
|
|
tests/unit/llms/hosted_vllm
|
|
tests/unit/llms/huggingface
|
|
tests/unit/llms/hyperbolic
|
|
tests/unit/llms/inception
|
|
tests/unit/llms/infinity
|
|
tests/unit/llms/jina_ai
|
|
tests/unit/llms/lambda_ai
|
|
tests/unit/llms/langflow
|
|
tests/unit/llms/langgraph
|
|
tests/unit/llms/laya
|
|
tests/unit/llms/lemonade
|
|
tests/unit/llms/linkup
|
|
tests/unit/llms/litellm_proxy
|
|
tests/unit/llms/llamafile
|
|
tests/unit/llms/lm_studio
|
|
tests/unit/llms/manus
|
|
tests/unit/llms/meta_llama
|
|
tests/unit/llms/microsoft_365_copilot
|
|
tests/unit/llms/milvus
|
|
tests/unit/llms/minimax
|
|
tests/unit/llms/mistral
|
|
tests/unit/llms/modelscope
|
|
tests/unit/llms/mongodb
|
|
tests/unit/llms/moonshot
|
|
tests/unit/llms/nadir
|
|
tests/unit/llms/nebius
|
|
tests/unit/llms/neosantara
|
|
tests/unit/llms/nimble
|
|
tests/unit/llms/nlp_cloud
|
|
tests/unit/llms/novita
|
|
tests/unit/llms/nscale
|
|
tests/unit/llms/nvidia_nim
|
|
tests/unit/llms/nvidia_riva
|
|
tests/unit/llms/oci
|
|
tests/unit/llms/ocr
|
|
tests/unit/llms/ollama
|
|
tests/unit/llms/oobabooga
|
|
tests/unit/llms/openai_like
|
|
tests/unit/llms/opencode
|
|
tests/unit/llms/opensandbox
|
|
tests/unit/llms/openrouter
|
|
tests/unit/llms/ovhcloud
|
|
tests/unit/llms/parallel_ai
|
|
tests/unit/llms/parasail
|
|
tests/unit/llms/pass_through
|
|
tests/unit/llms/perplexity
|
|
tests/unit/llms/pg_vector
|
|
tests/unit/llms/publicai
|
|
tests/unit/llms/ragflow
|
|
tests/unit/llms/recraft
|
|
tests/unit/llms/reducto
|
|
tests/unit/llms/replicate
|
|
tests/unit/llms/runwayml
|
|
tests/unit/llms/s3_vectors
|
|
tests/unit/llms/sagemaker
|
|
tests/unit/llms/sail
|
|
tests/unit/llms/sambanova
|
|
tests/unit/llms/scaledown
|
|
tests/unit/llms/sap
|
|
tests/unit/llms/scaleway
|
|
tests/unit/llms/searchapi
|
|
tests/unit/llms/searxng
|
|
tests/unit/llms/serper
|
|
tests/unit/llms/snowflake
|
|
tests/unit/llms/soniox
|
|
tests/unit/llms/stability
|
|
tests/unit/llms/strands_decider
|
|
tests/unit/llms/tavily
|
|
tests/unit/llms/tencent
|
|
tests/unit/llms/tinyfish
|
|
tests/unit/llms/together_ai
|
|
tests/unit/llms/tool_loop
|
|
tests/unit/llms/triton
|
|
tests/unit/llms/v0
|
|
tests/unit/llms/valkey
|
|
tests/unit/llms/vercel_ai_gateway
|
|
tests/unit/llms/vllm
|
|
tests/unit/llms/volcengine
|
|
tests/unit/llms/voyage
|
|
tests/unit/llms/wandb
|
|
tests/unit/llms/watsonx
|
|
tests/unit/llms/xai
|
|
tests/unit/llms/xinference
|
|
tests/unit/llms/you_com
|
|
tests/unit/llms/zai
|
|
--ignore=tests/unit/llms/base_llm/batches/base_batches_config_test.py
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 0
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: llms-openai-meta
|
|
test-path: >-
|
|
tests/unit/llms/openai
|
|
tests/unit/llms/meta
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 0
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: root
|
|
test-path: >-
|
|
tests/unit/test_*.py
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 2
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: router
|
|
test-path: >-
|
|
tests/unit/test_router
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 0
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: endpoints
|
|
test-path: >-
|
|
tests/unit/a2a_protocol
|
|
tests/unit/anthropic_interface
|
|
tests/unit/batches
|
|
tests/unit/chat_completions
|
|
tests/unit/completion_extras
|
|
tests/unit/containers
|
|
tests/unit/embeddings
|
|
tests/unit/endpoints
|
|
tests/unit/files
|
|
tests/unit/images
|
|
tests/unit/interactions
|
|
tests/unit/messages
|
|
tests/unit/ocr
|
|
tests/unit/passthrough
|
|
tests/unit/rag
|
|
tests/unit/realtime_api
|
|
tests/unit/rerank_api
|
|
tests/unit/vector_stores
|
|
tests/unit/videos
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 0
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: rust-bridge-harness
|
|
test-path: >-
|
|
tests/unit/compression
|
|
tests/unit/harness
|
|
tests/unit/rust_bridge
|
|
tests/unit/sandbox
|
|
--ignore=tests/unit/rust_bridge/native_route_wheel_test.py
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 0
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: enterprise-repositories-secrets
|
|
test-path: >-
|
|
tests/unit/enterprise/enterprise_callbacks/test_callback_controls.py
|
|
tests/unit/enterprise/enterprise_callbacks/test_llm_guard.py
|
|
tests/unit/enterprise/enterprise_callbacks/test_pagerduty_alerting.py
|
|
tests/unit/enterprise/enterprise_callbacks/test_secret_detection.py
|
|
tests/unit/integration_support
|
|
tests/unit/models
|
|
tests/unit/repositories
|
|
tests/unit/secret_managers
|
|
tests/unit/skills/test_skills_main.py
|
|
tests/unit/telemetry tests/unit/proxy/telemetry
|
|
tests/unit/tracing
|
|
python-version: "3.12"
|
|
workers: 2
|
|
reruns: 0
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: proxy-auth
|
|
test-path: |-
|
|
tests/unit/proxy/auth
|
|
--ignore=tests/unit/proxy/auth/test_auth_checks.py
|
|
--ignore=tests/unit/proxy/auth/test_user_api_key_auth.py
|
|
--ignore=tests/unit/proxy/auth/test_default_end_user_budget_simple.py
|
|
--ignore=tests/unit/proxy/auth/test_jwt.py
|
|
--ignore=tests/unit/proxy/auth/test_models_fallback_endpoint.py
|
|
--ignore=tests/unit/proxy/auth/test_multipart_bypass_repro.py
|
|
--ignore=tests/unit/proxy/auth/test_proxy_routes.py
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 0
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: proxy-hooks-client
|
|
test-path: |-
|
|
tests/unit/proxy/hooks
|
|
tests/unit/proxy/policy_engine
|
|
tests/unit/proxy/client
|
|
--ignore=tests/unit/proxy/hooks/test_banned_keyword_list.py
|
|
--ignore=tests/unit/proxy/hooks/test_unit_test_max_model_budget_limiter.py
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 0
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: proxy-endpoints
|
|
test-path: |-
|
|
tests/unit/proxy/management_endpoints
|
|
tests/unit/proxy/management_helpers
|
|
tests/unit/proxy/list_api
|
|
tests/unit/proxy/analytics_endpoints
|
|
tests/unit/proxy/decisions_endpoints
|
|
tests/unit/proxy/memory
|
|
tests/unit/proxy/agent_endpoints
|
|
tests/unit/proxy/openai_files_endpoint
|
|
tests/unit/proxy/health_endpoints
|
|
tests/unit/proxy/batches_endpoints
|
|
--ignore=tests/unit/proxy/management_endpoints/test_jwt_key_mapping.py
|
|
--ignore=tests/unit/proxy/management_endpoints/test_key_generate_prisma.py
|
|
--ignore=tests/unit/proxy/management_endpoints/test_roi_calculator_endpoints.py
|
|
--ignore=tests/unit/proxy/management_helpers/test_audit_logs_proxy.py
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 0
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: proxy-feature-endpoints
|
|
test-path: |-
|
|
tests/unit/proxy/guardrails
|
|
--ignore=tests/unit/proxy/google_endpoints/test_gemini_agents_endpoints.py
|
|
--ignore=tests/unit/proxy/google_endpoints/test_google_endpoint_routing.py
|
|
--ignore=tests/unit/proxy/google_endpoints/test_google_gemini_proxy_request.py
|
|
--ignore=tests/unit/proxy/public_endpoints/test_blog_posts_endpoint.py
|
|
tests/unit/proxy/anthropic_endpoints
|
|
tests/unit/proxy/google_endpoints
|
|
tests/unit/proxy/container_endpoints
|
|
tests/unit/proxy/fine_tuning_endpoints
|
|
tests/unit/proxy/vector_store_files_endpoints
|
|
tests/unit/proxy/video_endpoints
|
|
tests/unit/proxy/response_api_endpoints
|
|
tests/unit/proxy/image_endpoints
|
|
tests/unit/proxy/ocr_endpoints
|
|
tests/unit/proxy/search_endpoints
|
|
tests/unit/proxy/vector_store_endpoints
|
|
tests/unit/proxy/a2a
|
|
tests/unit/proxy/credential_endpoints
|
|
tests/unit/proxy/discovery_endpoints
|
|
tests/unit/proxy/shutdown
|
|
tests/unit/proxy/public_endpoints
|
|
tests/unit/proxy/prompts
|
|
tests/unit/proxy/rag_endpoints
|
|
tests/unit/proxy/rerank_endpoints
|
|
tests/unit/proxy/realtime_endpoints
|
|
tests/unit/proxy/ui_crud_endpoints
|
|
tests/unit/proxy/config_resolvers
|
|
tests/unit/proxy/utils
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 0
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: proxy-server
|
|
test-path: >-
|
|
tests/unit/proxy/proxy_server
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 0
|
|
timeout-minutes: 60
|
|
job-timeout-minutes: 100
|
|
dist: loadscope
|
|
|
|
- shard: mcp-elicitation
|
|
test-path: |-
|
|
--override-ini=pythonpath=tests
|
|
tests/unit/experimental_mcp_client/test_mcp_client.py
|
|
tests/unit/proxy/_experimental/mcp_server/test_capabilities.py
|
|
tests/unit/proxy/_experimental/mcp_server/test_interactions.py
|
|
tests/unit/proxy/_experimental/mcp_server/test_mcp_elicitation_handler.py
|
|
tests/unit/proxy/_experimental/mcp_server/test_mcp_server_manager.py
|
|
tests/unit/proxy/_experimental/mcp_server/test_mcp_server_tool_calls_and_headers.py
|
|
tests/unit/proxy/_experimental/mcp_server/test_operations.py
|
|
tests/integration/mcp/test_interactions.py
|
|
python-version: "3.12"
|
|
workers: 2
|
|
reruns: 0
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: proxy-infra
|
|
test-path: |-
|
|
tests/unit/proxy/db
|
|
--ignore=tests/unit/proxy/db/db_transaction_queue/test_e2e_pod_lock_manager.py
|
|
--ignore=tests/unit/proxy/db/test_update_daily_tag_spend.py
|
|
tests/unit/proxy/middleware
|
|
--ignore=tests/unit/proxy/middleware/test_request_size_limit_middleware.py
|
|
tests/unit/proxy/spend_tracking
|
|
--ignore=tests/unit/proxy/spend_tracking/test_search_api_logging.py
|
|
tests/unit/proxy/pass_through_endpoints
|
|
tests/unit/proxy/experimental
|
|
tests/unit/proxy/common_utils
|
|
--ignore=tests/unit/proxy/common_utils/test_cache_aware_routing.py
|
|
--ignore=tests/unit/proxy/common_utils/test_check_batch_cost.py
|
|
--ignore=tests/unit/proxy/common_utils/test_check_responses_cost.py
|
|
--ignore=tests/unit/proxy/common_utils/test_proxy_encrypt_decrypt.py
|
|
--ignore=tests/unit/proxy/common_utils/test_realtime_cache.py
|
|
tests/unit/proxy/enterprise_billing
|
|
tests/unit/proxy/types_utils
|
|
tests/unit/proxy/logging_endpoints
|
|
tests/unit/gateway
|
|
tests/unit/proxy/management
|
|
tests/unit/proxy/management_endpoints/test_roi_calculator_endpoints.py
|
|
tests/unit/proxy/roi_calculator
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 0
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: proxy-infra-root
|
|
test-path: |-
|
|
tests/unit/proxy/test_*.py
|
|
--ignore=tests/unit/proxy/test_aproxy_startup.py
|
|
--ignore=tests/unit/proxy/test_credential_slot_registry.py
|
|
--ignore=tests/unit/proxy/test_custom_callback_input.py
|
|
--ignore=tests/unit/proxy/test_custom_logger_s3_gcs.py
|
|
--ignore=tests/unit/proxy/test_custom_tokenizer_bug.py
|
|
--ignore=tests/unit/proxy/test_db_schema_changes.py
|
|
--ignore=tests/unit/proxy/test_deprecated_key_grace_period.py
|
|
--ignore=tests/unit/proxy/test_get_favicon.py
|
|
--ignore=tests/unit/proxy/test_get_image.py
|
|
--ignore=tests/unit/proxy/test_prisma_client_backoff_retry.py
|
|
--ignore=tests/unit/proxy/test_prompt_test_endpoint.py
|
|
--ignore=tests/unit/proxy/test_proxy_config_unit_test.py
|
|
--ignore=tests/unit/proxy/test_proxy_custom_auth.py
|
|
--ignore=tests/unit/proxy/test_proxy_reject_logging.py
|
|
--ignore=tests/unit/proxy/test_proxy_server.py
|
|
--ignore=tests/unit/proxy/test_proxy_setting_guardrails.py
|
|
--ignore=tests/unit/proxy/test_proxy_token_counter.py
|
|
--ignore=tests/unit/proxy/test_proxy_utils.py
|
|
--ignore=tests/unit/proxy/test_reducto_ocr_route.py
|
|
--ignore=tests/unit/proxy/test_response_polling_pre_call_checks.py
|
|
--ignore=tests/unit/proxy/test_server_root_path.py
|
|
--ignore=tests/unit/proxy/test_ui_path_detection.py
|
|
--ignore=tests/unit/proxy/test_unit_test_proxy_hooks.py
|
|
--ignore=tests/unit/proxy/test_update_spend.py
|
|
--ignore=tests/unit/proxy/test_zero_cost_model_budget_bypass.py
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 0
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: caching-local
|
|
test-path: >-
|
|
tests/unit/caching
|
|
python-version: "3.12"
|
|
workers: 2
|
|
reruns: 0
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: proxy-extras
|
|
test-path: >-
|
|
tests/unit/litellm_proxy_extras
|
|
python-version: "3.12"
|
|
workers: 2
|
|
reruns: 0
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: enterprise-package
|
|
test-path: |-
|
|
tests/unit/enterprise/integrations
|
|
tests/unit/enterprise/proxy/auth
|
|
tests/unit/enterprise/proxy/guardrails
|
|
tests/unit/enterprise/proxy/management_endpoints
|
|
tests/unit/enterprise/proxy/test_audit_logging_endpoints.py
|
|
tests/unit/enterprise/proxy/test_liteadmin.py
|
|
tests/unit/enterprise/enterprise_callbacks/test_prometheus_logging_callbacks.py
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 0
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: enterprise-managed-files
|
|
test-path: >-
|
|
tests/unit/enterprise/proxy/hooks
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 0
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: load
|
|
|
|
- shard: responses-caching-types
|
|
test-path: |-
|
|
tests/unit/responses/litellm_completion_transformation
|
|
tests/unit/responses/test_additional_tools.py
|
|
tests/unit/responses/test_custom_tool_call.py
|
|
tests/unit/responses/test_dispatch.py
|
|
tests/unit/responses/test_metadata_codex_callback.py
|
|
tests/unit/responses/test_no_duplicate_spend_logs.py
|
|
tests/unit/responses/test_null_test_fix.py
|
|
tests/unit/responses/test_responses_api_bridge_flag.py
|
|
tests/unit/responses/test_responses_api_lifecycle.py
|
|
tests/unit/responses/test_responses_api_request_body.py
|
|
tests/unit/responses/test_responses_prompt_management.py
|
|
tests/unit/responses/test_responses_router_cooldown.py
|
|
tests/unit/responses/test_responses_streaming_iterator.py
|
|
tests/unit/responses/test_responses_supported_endpoints_passthrough.py
|
|
tests/unit/responses/test_responses_utils.py
|
|
tests/unit/responses/test_responses_websocket_all_providers.py
|
|
tests/unit/responses/test_rust_bridge_websocket.py
|
|
tests/unit/responses/test_sse_output_recovery.py
|
|
tests/unit/responses/test_streaming_iterator.py
|
|
tests/unit/responses/test_streaming_iterator_error_events.py
|
|
tests/unit/responses/test_text_format_conversion.py
|
|
tests/unit/types
|
|
python-version: "3.12"
|
|
workers: 2
|
|
reruns: 0
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: key-generation
|
|
test-path: >-
|
|
tests/unit/proxy/management_endpoints/test_key_generate_prisma.py
|
|
python-version: "3.12"
|
|
workers: 0
|
|
reruns: 2
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: auth-checks
|
|
test-path: |-
|
|
tests/unit/proxy/auth/test_auth_checks.py
|
|
tests/unit/proxy/auth/test_user_api_key_auth.py
|
|
tests/unit/proxy/test_credential_slot_registry.py
|
|
tests/unit/proxy/test_deprecated_key_grace_period.py
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 2
|
|
timeout-minutes: 15
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: jwt-and-keys
|
|
test-path: |-
|
|
tests/unit/proxy/auth/test_jwt.py
|
|
tests/unit/proxy/management_endpoints/test_jwt_key_mapping.py
|
|
tests/unit/proxy/test_proxy_custom_auth.py
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 2
|
|
timeout-minutes: 15
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: proxy-utils
|
|
test-path: >-
|
|
tests/unit/proxy/test_proxy_utils.py
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 2
|
|
timeout-minutes: 15
|
|
job-timeout-minutes: 60
|
|
dist: worksteal
|
|
|
|
- shard: proxy-server-core
|
|
test-path: |-
|
|
tests/unit/proxy/pass_through_endpoints/test_llm_passthrough_endpoints.py
|
|
tests/unit/proxy/test__lazy_features.py
|
|
tests/unit/proxy/test_aproxy_startup.py
|
|
tests/unit/proxy/test_proxy_server.py
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 2
|
|
timeout-minutes: 15
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: proxy-runtime
|
|
test-path: |-
|
|
tests/unit/proxy/auth/test_multipart_bypass_repro.py
|
|
tests/unit/proxy/auth/test_proxy_routes.py
|
|
tests/unit/proxy/middleware/test_request_size_limit_middleware.py
|
|
tests/unit/proxy/test_proxy_config_unit_test.py
|
|
tests/unit/proxy/test_proxy_token_counter.py
|
|
tests/unit/proxy/test_server_root_path.py
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 2
|
|
timeout-minutes: 15
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: mcp-oauth
|
|
test-path: |-
|
|
tests/unit/proxy/_experimental/mcp_server/test_discoverable_endpoints.py
|
|
tests/unit/proxy/_experimental/mcp_server/test_mcp_server_manager.py
|
|
tests/unit/proxy/_experimental/mcp_server/test_db_credentials.py
|
|
tests/unit/proxy/_experimental/mcp_server/test_gateway_dcr_flow.py
|
|
tests/unit/proxy/_experimental/mcp_server/test_mcp_oauth_passthrough_tools.py
|
|
tests/unit/proxy/_experimental/mcp_server/test_mcp_max_concurrent_requests.py
|
|
tests/unit/proxy/_experimental/mcp_server/faults/test_list_outcomes.py
|
|
tests/unit/proxy/_experimental/mcp_server/outbound_credentials
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 2
|
|
timeout-minutes: 15
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: mcp-server
|
|
test-path: |-
|
|
tests/unit/experimental_mcp_client
|
|
tests/unit/proxy/_experimental/mcp_server
|
|
tests/unit/responses/mcp
|
|
--ignore=tests/unit/experimental_mcp_client/test_mcp_client.py
|
|
--ignore=tests/unit/proxy/_experimental/mcp_server/test_capabilities.py
|
|
--ignore=tests/unit/proxy/_experimental/mcp_server/test_interactions.py
|
|
--ignore=tests/unit/proxy/_experimental/mcp_server/test_mcp_elicitation_handler.py
|
|
--ignore=tests/unit/proxy/_experimental/mcp_server/test_mcp_server_manager.py
|
|
--ignore=tests/unit/proxy/_experimental/mcp_server/test_mcp_server_tool_calls_and_headers.py
|
|
--ignore=tests/unit/proxy/_experimental/mcp_server/test_operations.py
|
|
--ignore=tests/unit/proxy/_experimental/mcp_server/test_discoverable_endpoints.py
|
|
--ignore=tests/unit/proxy/_experimental/mcp_server/test_db_credentials.py
|
|
--ignore=tests/unit/proxy/_experimental/mcp_server/outbound_credentials
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 0
|
|
timeout-minutes: 20
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: custom-logging
|
|
test-path: |-
|
|
tests/unit/proxy/test_proxy_server_custom_logger.py
|
|
tests/unit/proxy/test_custom_callback_input.py
|
|
tests/unit/proxy/test_custom_logger_s3_gcs.py
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 2
|
|
timeout-minutes: 15
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: logging-misc
|
|
test-path: |-
|
|
tests/unit/proxy/management_helpers/test_audit_logs_proxy.py
|
|
tests/unit/proxy/spend_tracking/test_search_api_logging.py
|
|
tests/unit/proxy/test_proxy_reject_logging.py
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 2
|
|
timeout-minutes: 15
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: db-and-spend
|
|
test-path: |-
|
|
tests/unit/proxy/common_utils/test_proxy_encrypt_decrypt.py
|
|
tests/unit/proxy/db/db_transaction_queue/test_e2e_pod_lock_manager.py
|
|
tests/unit/proxy/db/test_update_daily_tag_spend.py
|
|
tests/unit/proxy/test_db_schema_changes.py
|
|
tests/unit/proxy/test_prisma_client_backoff_retry.py
|
|
tests/unit/proxy/test_update_spend.py
|
|
tests/unit/skills/test_skills_db.py
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 2
|
|
timeout-minutes: 15
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: guardrails-hooks
|
|
test-path: |-
|
|
tests/unit/proxy/hooks/test_banned_keyword_list.py
|
|
tests/unit/proxy/test_proxy_setting_guardrails.py
|
|
tests/unit/proxy/test_unit_test_proxy_hooks.py
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 2
|
|
timeout-minutes: 15
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: budgets
|
|
test-path: |-
|
|
tests/unit/proxy/auth/test_default_end_user_budget_simple.py
|
|
tests/unit/proxy/hooks/test_unit_test_max_model_budget_limiter.py
|
|
tests/unit/proxy/test_zero_cost_model_budget_bypass.py
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 2
|
|
timeout-minutes: 15
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: endpoints-and-responses
|
|
test-path: |-
|
|
tests/unit/proxy/test_proxy_server_exception_mapping.py
|
|
tests/unit/proxy/lens
|
|
tests/unit/proxy/auth/test_models_fallback_endpoint.py
|
|
tests/unit/proxy/common_utils/test_check_batch_cost.py
|
|
tests/unit/proxy/common_utils/test_check_responses_cost.py
|
|
tests/unit/proxy/common_utils/test_realtime_cache.py
|
|
tests/unit/proxy/google_endpoints/test_gemini_agents_endpoints.py
|
|
tests/unit/proxy/google_endpoints/test_google_endpoint_routing.py
|
|
tests/unit/proxy/google_endpoints/test_google_gemini_proxy_request.py
|
|
tests/unit/proxy/public_endpoints/test_blog_posts_endpoint.py
|
|
tests/unit/proxy/response_polling
|
|
tests/unit/proxy/test_custom_tokenizer_bug.py
|
|
tests/unit/proxy/test_get_favicon.py
|
|
tests/unit/proxy/test_get_image.py
|
|
tests/unit/proxy/test_prompt_test_endpoint.py
|
|
tests/unit/proxy/test_reducto_ocr_route.py
|
|
tests/unit/proxy/test_response_polling_pre_call_checks.py
|
|
tests/unit/proxy/test_ui_path_detection.py
|
|
python-version: "3.12"
|
|
workers: 4
|
|
reruns: 2
|
|
timeout-minutes: 15
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
|
|
- shard: lens-python-310
|
|
test-path: >-
|
|
tests/unit/proxy/lens
|
|
python-version: "3.10"
|
|
workers: 0
|
|
reruns: 0
|
|
timeout-minutes: 5
|
|
job-timeout-minutes: 60
|
|
dist: loadscope
|
|
steps:
|
|
- uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
|
|
timeout-minutes: 3
|
|
with:
|
|
persist-credentials: false
|
|
fetch-depth: ${{ matrix.shard == 'db-and-spend' && '0' || '1' }}
|
|
|
|
- name: Detect relevant changes
|
|
id: changes
|
|
timeout-minutes: 2
|
|
uses: ./.github/actions/detect-changes
|
|
|
|
- name: Set up Python
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
timeout-minutes: 3
|
|
uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
|
|
with:
|
|
python-version: ${{ env.UV_PYTHON }}
|
|
|
|
- name: Set up uv
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
timeout-minutes: 3
|
|
uses: ./.github/actions/setup-uv-with-retries
|
|
with:
|
|
version: "0.10.9"
|
|
|
|
- name: Cache uv dependencies
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
timeout-minutes: 5
|
|
uses: ./.github/actions/cache-uv-downloads
|
|
|
|
- name: Set up the Rust build
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
timeout-minutes: 5
|
|
uses: ./.github/actions/rust-bridge
|
|
with:
|
|
artifact: ${{ needs.rust-bridge.outputs.artifact }}
|
|
|
|
- name: Install dependencies and check schema
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
timeout-minutes: 8
|
|
env:
|
|
RUST_BRIDGE_ARTIFACT: ${{ needs.rust-bridge.outputs.artifact }}
|
|
UNIT_SHARD: ${{ matrix.shard }}
|
|
SCHEMA_BASE_REF: origin/${{ github.event.repository.default_branch }}
|
|
run: |
|
|
diff -u model_prices_and_context_window.json litellm/model_prices_and_context_window_backup.json
|
|
if [ -z "$RUST_BRIDGE_ARTIFACT" ]; then
|
|
.github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router --extra saml --extra caching --extra extra_proxy --extra proxy-runtime --extra utils
|
|
else
|
|
.github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router --extra saml --extra caching --extra extra_proxy --extra proxy-runtime --extra utils --no-install-project
|
|
uv pip install --no-deps --python .venv/bin/python rust-bridge-dist/*.whl
|
|
cp rust-bridge-dist/litellm/rust_bridge/_native.abi3.so litellm/rust_bridge/_native.abi3.so
|
|
uv run --no-sync python -c "import importlib.metadata; import litellm.rust_bridge._native; print(importlib.metadata.version('litellm'))"
|
|
fi
|
|
uv run --no-sync python -c 'import os, sys; print(sys.version); assert f"{sys.version_info.major}.{sys.version_info.minor}" == os.environ["UV_PYTHON"]'
|
|
if [ "$UNIT_SHARD" = "db-and-spend" ]; then
|
|
uv run --no-sync python scripts/check_schema_compatibility.py --base-ref "$SCHEMA_BASE_REF"
|
|
fi
|
|
|
|
- name: Cache Prisma binaries
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
timeout-minutes: 3
|
|
uses: ./.github/actions/cache-prisma-binaries
|
|
|
|
- name: Generate Prisma client
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
timeout-minutes: 3
|
|
run: |
|
|
uv run --no-sync prisma generate --schema litellm/proxy/schema.prisma
|
|
|
|
- name: Run tests
|
|
id: tests
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
timeout-minutes: ${{ matrix.timeout-minutes }}
|
|
env:
|
|
TEST_PATH: ${{ matrix.test-path }}
|
|
MAX_FAILURES: "10"
|
|
WORKERS: ${{ matrix.workers }}
|
|
RERUNS: ${{ matrix.reruns }}
|
|
TEST_TIMEOUT_SECONDS: "120"
|
|
DIST: ${{ matrix.dist }}
|
|
COVERAGE_CORE: sysmon
|
|
run: |
|
|
echo "has-coverage=false" >> "$GITHUB_OUTPUT"
|
|
selection="${TEST_PATH}"
|
|
if [ -z "${selection// /}" ]; then
|
|
echo "shard selection is empty; nothing to run"
|
|
exit 0
|
|
fi
|
|
pytest_args=()
|
|
existing_paths=0
|
|
for token in ${selection}; do
|
|
case "${token}" in
|
|
-*) pytest_args+=("${token}") ;;
|
|
*)
|
|
if [ -e "${token%%::*}" ]; then
|
|
pytest_args+=("${token}")
|
|
existing_paths=$((existing_paths + 1))
|
|
else
|
|
echo "::warning::${token} does not exist; drop it from this shard's test-path"
|
|
fi
|
|
;;
|
|
esac
|
|
done
|
|
if [ "${existing_paths}" -eq 0 ]; then
|
|
echo "No path in the selection exists (${selection}); nothing to run"
|
|
exit 0
|
|
fi
|
|
xdist_args=()
|
|
if [ "${WORKERS}" != "0" ]; then
|
|
xdist_args=(-n "${WORKERS}" --dist="${DIST}")
|
|
fi
|
|
set +e
|
|
uv run --no-sync pytest "${pytest_args[@]}" \
|
|
--tb=short -vv \
|
|
--maxfail="${MAX_FAILURES}" \
|
|
"${xdist_args[@]}" \
|
|
--reruns "${RERUNS}" \
|
|
--reruns-delay 1 \
|
|
--timeout="${TEST_TIMEOUT_SECONDS}" \
|
|
--rerun-except "from pytest-timeout" \
|
|
--durations=20 \
|
|
--cov=./litellm --cov=./enterprise/litellm_enterprise \
|
|
--cov-report=xml:coverage.xml \
|
|
--cov-config=pyproject.toml
|
|
status=$?
|
|
set -e
|
|
if [ -f coverage.xml ]; then
|
|
echo "has-coverage=true" >> "$GITHUB_OUTPUT"
|
|
fi
|
|
if [ "$status" -eq 5 ]; then
|
|
echo "pytest collected no tests from ${selection}; passing"
|
|
exit 0
|
|
fi
|
|
exit "$status"
|
|
|
|
- name: Save coverage report
|
|
if: always() && steps.changes.outputs.decision != 'skip'
|
|
uses: actions/upload-artifact@4cec3d8aa04e39d1a68397de0c4cd6fb9dce8ec1 # v4.6.1
|
|
with:
|
|
name: coverage-${{ matrix.shard }}-${{ github.run_id }}-${{ github.run_attempt }}
|
|
path: coverage.xml
|
|
retention-days: 1
|
|
ui-unit:
|
|
name: ui-unit
|
|
permissions:
|
|
contents: read
|
|
pull-requests: read
|
|
runs-on: ubuntu-latest-16-cores
|
|
timeout-minutes: 20
|
|
defaults:
|
|
run:
|
|
working-directory: ui/litellm-dashboard
|
|
|
|
steps:
|
|
- name: Checkout repository
|
|
uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
|
|
with:
|
|
fetch-depth: 1
|
|
persist-credentials: false
|
|
|
|
- name: Detect relevant changes
|
|
id: changes
|
|
uses: ./.github/actions/detect-changes
|
|
with:
|
|
category: ui
|
|
|
|
- name: Setup Node.js
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
uses: actions/setup-node@a0853c24544627f65ddf259abe73b1d18a591444 # v5.0.0
|
|
with:
|
|
node-version-file: ui/litellm-dashboard/.nvmrc
|
|
cache: "npm"
|
|
cache-dependency-path: ui/litellm-dashboard/package-lock.json
|
|
|
|
- name: Install dependencies
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
run: npm ci
|
|
|
|
- name: Check UI production source types
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
run: npm run typecheck
|
|
|
|
- name: Run UI type tests (Vitest)
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
env:
|
|
CI: "true"
|
|
run: npm run test:types
|
|
|
|
- name: Run UI unit tests (Vitest)
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
env:
|
|
CI: "true"
|
|
GH_TOKEN: ${{ github.token }}
|
|
BASE_SHA: ${{ github.event.pull_request.base.sha }}
|
|
HEAD_SHA: ${{ github.event.pull_request.head.sha }}
|
|
run: |
|
|
full_suite() { npm run test -- --run --pool forks --maxWorkers=14; }
|
|
|
|
if [ -z "$BASE_SHA" ]; then
|
|
echo "Push to $GITHUB_REF_NAME: running the full suite"
|
|
full_suite
|
|
exit 0
|
|
fi
|
|
|
|
merge_base=$(gh api "repos/${{ github.repository }}/compare/${BASE_SHA}...${HEAD_SHA}?per_page=1" --jq '.merge_base_commit.sha')
|
|
test -n "$merge_base"
|
|
git fetch --no-tags --depth=1 origin "$merge_base" "$HEAD_SHA"
|
|
changed_files=()
|
|
while IFS= read -r f; do
|
|
changed_files+=("$f")
|
|
done < <(git diff --name-only --relative "$merge_base" "$HEAD_SHA" -- .)
|
|
if [ ${#changed_files[@]} -eq 0 ]; then
|
|
echo "No UI files changed in this PR; skipping unit tests."
|
|
exit 0
|
|
fi
|
|
|
|
scope=$(printf '%s\n' "${changed_files[@]}" | bash "$GITHUB_WORKSPACE/.github/scripts/select_ui_test_scope.sh")
|
|
if [ "$scope" != related ]; then
|
|
echo "Pull request: ${#changed_files[@]} changed UI files reach outside src/, so related would miss their dependents; running the full suite"
|
|
full_suite
|
|
exit 0
|
|
fi
|
|
|
|
echo "Pull request: running tests related to ${#changed_files[@]} changed UI files"
|
|
npm run test -- related "${changed_files[@]}" --run --passWithNoTests \
|
|
--pool forks --maxWorkers=14
|
|
docs:
|
|
name: docs
|
|
permissions:
|
|
contents: read
|
|
pull-requests: read
|
|
runs-on: ubuntu-latest
|
|
timeout-minutes: 10
|
|
steps:
|
|
- uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
|
|
with:
|
|
persist-credentials: false
|
|
|
|
- name: Detect relevant changes
|
|
id: changes
|
|
uses: ./.github/actions/detect-changes
|
|
|
|
- name: Checkout litellm-docs into docs/my-website (for documentation_tests)
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
|
|
with:
|
|
repository: BerriAI/litellm-docs
|
|
path: docs/my-website
|
|
persist-credentials: false
|
|
|
|
- name: Set up Python
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
|
|
with:
|
|
python-version: "3.12"
|
|
|
|
- name: Set up uv
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
uses: ./.github/actions/setup-uv-with-retries
|
|
with:
|
|
version: "0.10.9"
|
|
|
|
- name: Cache uv dependencies
|
|
if: steps.changes.outputs.decision != 'skip' && github.ref == 'refs/heads/main'
|
|
uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
|
|
with:
|
|
path: |
|
|
~/.cache/uv
|
|
.venv
|
|
key: ${{ runner.os }}-uv-${{ hashFiles('uv.lock') }}
|
|
restore-keys: |
|
|
${{ runner.os }}-uv-
|
|
|
|
- name: Cache uv dependencies
|
|
if: steps.changes.outputs.decision != 'skip' && github.ref != 'refs/heads/main'
|
|
uses: actions/cache/restore@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
|
|
with:
|
|
path: |
|
|
~/.cache/uv
|
|
.venv
|
|
key: ${{ runner.os }}-uv-${{ hashFiles('uv.lock') }}
|
|
restore-keys: |
|
|
${{ runner.os }}-uv-
|
|
|
|
- name: Cache the Rust build
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
uses: ./.github/actions/cache-cargo-build
|
|
|
|
- name: Install dependencies
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
run: |
|
|
.github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router
|
|
|
|
- name: Cache Prisma binaries
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
uses: ./.github/actions/cache-prisma-binaries
|
|
|
|
- name: Generate Prisma client
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
run: |
|
|
uv run --no-sync prisma generate --schema litellm/proxy/schema.prisma
|
|
|
|
- name: Run documentation validation tests
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
run: |
|
|
uv run --no-sync python ./tests/documentation_tests/test_env_keys.py
|
|
uv run --no-sync python ./tests/documentation_tests/test_router_settings.py
|
|
uv run --no-sync python ./tests/documentation_tests/test_api_docs.py
|
|
uv run --no-sync python ./tests/documentation_tests/test_circular_imports.py
|
|
helm:
|
|
name: helm
|
|
permissions:
|
|
contents: read
|
|
runs-on: ubuntu-latest
|
|
timeout-minutes: 10
|
|
steps:
|
|
- name: Checkout
|
|
uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
|
|
with:
|
|
persist-credentials: false
|
|
|
|
- name: Set up Helm 3.11.1
|
|
uses: azure/setup-helm@1a275c3b69536ee54be43f2070a358922e12c8d4 # v4.3.1
|
|
with:
|
|
version: "3.11.1"
|
|
|
|
- name: Download and verify Helm Unit Test Plugin
|
|
run: |
|
|
curl -fsSLo "$RUNNER_TEMP/helm-unittest.tgz" https://github.com/helm-unittest/helm-unittest/releases/download/v0.8.2/helm-unittest-linux-amd64-0.8.2.tgz
|
|
echo "56ab3091e6fa52a7c92ee951def9bed957f295d9ce98483aed404e748d7b3a94 $RUNNER_TEMP/helm-unittest.tgz" | sha256sum -c -
|
|
|
|
- name: Install Helm Unit Test Plugin
|
|
run: |
|
|
PLUGIN_DIR="$(helm env HELM_PLUGINS)/helm-unittest"
|
|
mkdir -p "$PLUGIN_DIR"
|
|
tar -xzf "$RUNNER_TEMP/helm-unittest.tgz" -C "$PLUGIN_DIR"
|
|
helm plugin list
|
|
|
|
- name: Run unit tests
|
|
run: |
|
|
for chart in helm/litellm-helm helm/litellm; do
|
|
declared="$(grep -h '^suite:' "$chart"/tests/*.yaml | wc -l | tr -d '[:space:]')"
|
|
output="$(mktemp)"
|
|
helm unittest -f 'tests/*.yaml' "$chart" | tee "$output"
|
|
executed="$(sed -n 's/^Test Suites:.*[[:space:]]\([0-9][0-9]*\) total$/\1/p' "$output")"
|
|
if [ "$declared" != "$executed" ]; then
|
|
echo "::error::$chart declares $declared test suites but helm-unittest ran $executed. Suites are being skipped silently, so their assertions never execute."
|
|
exit 1
|
|
fi
|
|
echo "$chart: all $declared declared test suites ran"
|
|
done
|
|
openai-sdk-compat:
|
|
name: OpenAI ${{ matrix.openai-version }} compatibility
|
|
permissions:
|
|
contents: read
|
|
pull-requests: read
|
|
runs-on: ubuntu-latest
|
|
timeout-minutes: 20
|
|
strategy:
|
|
fail-fast: false
|
|
matrix:
|
|
openai-version: ["2.20.0", "3.0.0", "3.25.0"]
|
|
env:
|
|
LITELLM_LOCAL_MODEL_COST_MAP: "True"
|
|
PYTHONPATH: ${{ github.workspace }}
|
|
UV_PYTHON: "3.10"
|
|
OPENAI_VERSION: ${{ matrix.openai-version }}
|
|
steps:
|
|
- uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
|
|
with:
|
|
persist-credentials: false
|
|
|
|
- name: Detect relevant changes
|
|
id: changes
|
|
timeout-minutes: 2
|
|
uses: ./.github/actions/detect-changes
|
|
|
|
- name: Set up Python
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
|
|
with:
|
|
python-version: ${{ env.UV_PYTHON }}
|
|
|
|
- name: Set up uv
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
uses: ./.github/actions/setup-uv-with-retries
|
|
with:
|
|
version: "0.10.9"
|
|
|
|
- name: Install dependencies
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
run: |
|
|
.github/scripts/uv_sync_with_retries.sh --frozen --group dev --group proxy-dev --extra proxy --no-install-workspace
|
|
uv pip install "openai==${OPENAI_VERSION:?}" --exclude-newer-package openai=2026-10-07T00:00:00Z
|
|
uv run --no-sync python -c 'import os, openai; assert openai.__version__ == os.environ["OPENAI_VERSION"], openai.__version__'
|
|
|
|
- name: Run OpenAI SDK compatibility tests
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
run: |
|
|
uv run --no-sync pytest \
|
|
tests/unit/llms/openai/test_openai.py \
|
|
tests/unit/llms/openai/test_openai_common_utils.py \
|
|
tests/unit/llms/openai/test_openai_file_content_streaming.py \
|
|
tests/unit/test_openai_embedding_encoding_format_default.py \
|
|
tests/unit/llms/inception/test_inception_completion_transformation.py::test_inception_fim_targets_fim_endpoint \
|
|
tests/unit/llms/inception/test_inception_completion_transformation.py::test_inception_fim_async \
|
|
tests/unit/llms/azure/test_azure_exception_mapping.py \
|
|
tests/unit/test_completion_timeout_resolution.py \
|
|
tests/unit/types/test_router.py \
|
|
tests/unit/test_exception_header_preservation.py \
|
|
tests/unit/integrations/otel/test_otel_v2_sources_of_truth.py::test_speech_binary_response_still_streaming_reports_the_bytes_downloaded_so_far \
|
|
--tb=short -q
|
|
|
|
- name: Run workload identity tests with SDK 3
|
|
if: steps.changes.outputs.decision != 'skip' && startsWith(matrix.openai-version, '3.')
|
|
run: uv run --no-sync pytest tests/unit/llms/openai/test_openai_workload_identity.py --tb=short -q
|
|
|
|
- name: Check consumer types with the installed SDK
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
run: uv run --no-sync basedpyright --pythonpath .venv/bin/python --project tests/typing/pyrightconfig.json
|
|
redis-compat:
|
|
name: redis-py ${{ matrix.redis-py }} compatibility
|
|
needs: rust-bridge
|
|
if: ${{ !cancelled() }}
|
|
permissions:
|
|
contents: read
|
|
id-token: write
|
|
pull-requests: read
|
|
runs-on: ubuntu-latest
|
|
timeout-minutes: 25
|
|
strategy:
|
|
fail-fast: false
|
|
matrix:
|
|
redis-py: ["5.3.1", "6.4.0", "7.4.1", "8.0.1"]
|
|
env:
|
|
UV_PYTHON: "3.12"
|
|
LITELLM_LOCAL_MODEL_COST_MAP: "True"
|
|
REDIS_PY_VERSION: ${{ matrix.redis-py }}
|
|
steps:
|
|
- uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
|
|
timeout-minutes: 3
|
|
with:
|
|
persist-credentials: false
|
|
|
|
- name: Detect relevant changes
|
|
id: changes
|
|
timeout-minutes: 2
|
|
uses: ./.github/actions/detect-changes
|
|
with:
|
|
category: redis-compat
|
|
|
|
- name: Set up Python
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
timeout-minutes: 3
|
|
uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
|
|
with:
|
|
python-version: ${{ env.UV_PYTHON }}
|
|
|
|
- name: Set up uv
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
timeout-minutes: 3
|
|
uses: ./.github/actions/setup-uv-with-retries
|
|
with:
|
|
version: "0.10.9"
|
|
|
|
- name: Cache uv dependencies
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
timeout-minutes: 5
|
|
uses: ./.github/actions/cache-uv-downloads
|
|
|
|
- name: Set up the Rust build
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
timeout-minutes: 5
|
|
uses: ./.github/actions/rust-bridge
|
|
with:
|
|
artifact: ${{ needs.rust-bridge.outputs.artifact }}
|
|
|
|
- name: Install dependencies with redis-py ${{ matrix.redis-py }}
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
timeout-minutes: 8
|
|
env:
|
|
RUST_BRIDGE_ARTIFACT: ${{ needs.rust-bridge.outputs.artifact }}
|
|
run: |
|
|
if [ -z "$RUST_BRIDGE_ARTIFACT" ]; then
|
|
.github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router --extra saml --extra caching --extra extra_proxy --extra proxy-runtime --extra utils
|
|
else
|
|
.github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router --extra saml --extra caching --extra extra_proxy --extra proxy-runtime --extra utils --no-install-project
|
|
uv pip install --no-deps --python .venv/bin/python rust-bridge-dist/*.whl
|
|
cp rust-bridge-dist/litellm/rust_bridge/_native.abi3.so litellm/rust_bridge/_native.abi3.so
|
|
fi
|
|
uv pip install --python .venv/bin/python "redis==${REDIS_PY_VERSION:?}"
|
|
uv run --no-sync python -c 'import os, redis; assert redis.__version__ == os.environ["REDIS_PY_VERSION"], redis.__version__'
|
|
|
|
- name: Install redis-server 7.2.16
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
timeout-minutes: 5
|
|
run: |
|
|
mkdir -p "$RUNNER_TEMP/redis-bin"
|
|
cid="$(docker create redis:7.2.16@sha256:0637954999d01b7c9ce9167db2da50656e2590d3b884f1c600c5f63bb6e6773c)"
|
|
docker cp "${cid}:/usr/local/bin/redis-server" "$RUNNER_TEMP/redis-bin/redis-server"
|
|
docker rm "$cid"
|
|
"$RUNNER_TEMP/redis-bin/redis-server" --version | grep -q 'v=7.2.16'
|
|
echo "$RUNNER_TEMP/redis-bin" >> "$GITHUB_PATH"
|
|
|
|
- name: Run Redis compatibility tests
|
|
if: steps.changes.outputs.decision != 'skip'
|
|
timeout-minutes: 15
|
|
env:
|
|
COVERAGE_CORE: sysmon
|
|
run: |
|
|
uv run --no-sync pytest \
|
|
tests/unit/test_redis.py \
|
|
tests/unit/caching/test_redis_connection_pool.py \
|
|
tests/unit/caching/test_redis_cluster_cache.py \
|
|
tests/unit/caching/test_evicted_client_closer.py \
|
|
tests/integration/sdk/test_redis_cluster_iam_auth.py \
|
|
--tb=short -vv -rs -p no:rerunfailures -p no:pytest-retry --timeout=120 --durations=20 \
|
|
--cov=./litellm --cov-report=xml:coverage.xml
|
|
|
|
- name: Upload redis-py ${{ matrix.redis-py }} coverage to Codecov
|
|
if: always() && steps.changes.outputs.decision != 'skip' && matrix.redis-py == '5.3.1'
|
|
continue-on-error: true
|
|
uses: codecov/codecov-action@0fb7174895f61a3b6b78fc075e0cd60383518dac # v5.5.5
|
|
with:
|
|
use_oidc: true
|
|
files: coverage.xml
|
|
root_dir: ${{ github.workspace }}
|
|
flags: redis-compat
|
|
fail_ci_if_error: false
|
|
coverage:
|
|
name: coverage
|
|
needs: unit
|
|
if: always()
|
|
runs-on: ubuntu-latest
|
|
timeout-minutes: 10
|
|
permissions:
|
|
contents: read
|
|
id-token: write
|
|
pull-requests: write
|
|
|
|
steps:
|
|
- name: Checkout code
|
|
uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
|
|
with:
|
|
persist-credentials: false
|
|
|
|
- name: Download coverage report
|
|
uses: actions/download-artifact@95815c38cf2ff2164869cbab79da8d1f422bc89e # v4.2.1
|
|
with:
|
|
pattern: coverage-*-${{ github.run_id }}-*
|
|
path: coverage-reports
|
|
merge-multiple: false
|
|
|
|
- name: Upload to Codecov
|
|
id: codecov-upload
|
|
continue-on-error: true
|
|
uses: codecov/codecov-action@0fb7174895f61a3b6b78fc075e0cd60383518dac # v5.5.5
|
|
with:
|
|
use_oidc: true
|
|
directory: coverage-reports
|
|
root_dir: ${{ github.workspace }}
|
|
flags: unit
|
|
fail_ci_if_error: false
|
|
|
|
- name: Upload to Codecov (retry)
|
|
if: steps.codecov-upload.outcome == 'failure'
|
|
continue-on-error: true
|
|
uses: codecov/codecov-action@0fb7174895f61a3b6b78fc075e0cd60383518dac # v5.5.5
|
|
with:
|
|
use_oidc: true
|
|
directory: coverage-reports
|
|
root_dir: ${{ github.workspace }}
|
|
flags: unit
|
|
fail_ci_if_error: false
|
|
|
|
- name: Upload MCP server coverage under its own flag
|
|
continue-on-error: true
|
|
uses: codecov/codecov-action@0fb7174895f61a3b6b78fc075e0cd60383518dac # v5.5.5
|
|
with:
|
|
use_oidc: true
|
|
files: coverage-reports/coverage-mcp-server-${{ github.run_id }}-${{ github.run_attempt }}/coverage.xml
|
|
root_dir: ${{ github.workspace }}
|
|
flags: mcp-integration
|
|
fail_ci_if_error: false
|
|
unit-passed:
|
|
name: unit passed
|
|
permissions: {}
|
|
needs: [rust-bridge, assert-shard-coverage, unit, ui-unit, docs, helm, openai-sdk-compat, redis-compat]
|
|
if: always()
|
|
runs-on: ubuntu-latest
|
|
timeout-minutes: 2
|
|
steps:
|
|
- name: Require every unit job to succeed
|
|
env:
|
|
NEEDS: ${{ toJSON(needs) }}
|
|
run: |
|
|
jq -r 'to_entries[] | "\(.key): \(.value.result)"' <<< "$NEEDS"
|
|
jq -e 'all(.[]; .result == "success")' <<< "$NEEDS" > /dev/null
|