Awesome Reviewers checks + prompts

sources / BerriAI/litellm

BerriAI/litellm

The checks this repository runs, scanned at bd8eeed, and the review prompts derived from its discussions.

24 recognised tools
25 prompts
28310 stars
LLM Serving & Gateways
GitHub

Static analysis

11 tools

ToolKindCommandRuns inFound in
cargo-check Type checking cargo check -p litellm-python-bridge --locked --no-default-features --feature... ci .github/workflows/test-rust.yml
clippy Linting cargo clippy --workspace --all-targets --locked -- -D warnings ci .github/workflows/test-rust.yml
litellm-rust/clippy.toml
codeql Security scanning uses github/codeql-action/analyze ci .github/workflows/codeql.yml
eslint Linting eslint --no-warn-ignored --pass-on-unpruned-suppressions ${eslint_files[@]}
eslint . -f json -o $RUNNER_TEMP/lint-report.json
ci .github/workflows/test-linting.yml
ui/litellm-dashboard/eslint.config.mjs
go-vet Linting go vet ./... ci .github/workflows/test-terraform-provider.yml
pyright Type checking basedpyright tests/e2e tests/e2e_harness
basedpyright --pythonpath .venv/bin/python --project tests/typing/pyrightconf...
ci .github/workflows/test-linting.yml
.github/workflows/test-unit.yml
pyproject.toml
pyrightconfig.json
ruff-check Linting ruff check .
ruff check --config ruff-tests.toml tests
ci .github/workflows/test-linting.yml
pyproject.toml
ruff.toml
semgrep Security scanning semgrep scan --config .semgrep/rules . --error ci .github/workflows/test-linting.yml
tsc Type checking tsc --noEmit ci, local .github/workflows/test-vscode-extension.yml
vscode-extension/package.json
mypy
configured, not run
Type checking pyproject.toml
pylint
configured, not run
Linting pyproject.toml

Testing

10 tools

ToolKindCommandRuns inFound in
cargo-test Unit and integration tests cargo test -p litellm-db --locked -- --include-ignored
cargo nextest run --workspace --locked
cargo test --workspace --doc --locked
ci .github/workflows/test-rust-db.yml
.github/workflows/test-rust.yml
ci-matrix Version and platform matrix analyze (include: 3)
runtime-image (dockerfile: 2)
unit (include: 41)
ci .github/workflows/codeql.yml
.github/workflows/image-scan.yml
.github/workflows/test-unit.yml
go-test Unit and integration tests go test -timeout 120s ./... ci .github/workflows/test-terraform-provider.yml
hypothesis Property-based tests pyproject.toml
mutmut Mutation testing mutmut run 2>&1 ci .github/workflows/mutation-test.yml
pyproject.toml
proptest Property-based tests litellm-rust/Cargo.toml
pytest Unit and integration tests pytest tests/e2e -m replayable --reruns 0 -v --tb=short -rA
pytest --noconftest tests/integration/database/image/test_offline_image_migra...
pytest --noconftest tests/integration/database/image/test_offline_image_migra...
ci .github/workflows/e2e_record_replay.yml
.github/workflows/image-scan.yml
.github/workflows/interactions-spec-canary.yml
.github/workflows/test-e2e-redis-chaos.yml
vitest Unit and integration tests vitest run ci, local .github/workflows/test-vscode-extension.yml
vscode-extension/package.json
ui/litellm-dashboard/vitest.config.ts
vscode-extension/vitest.config.mts
jest
configured, not run
Unit and integration tests package.json
playwright
configured, not run
End-to-end browser tests tests/e2e/ui/playwright.config.ts
ToolKindCommandRuns inFound in
prettier Formatting prettier --check ${prettier_files[@]} ci .github/workflows/test-linting.yml
ui/litellm-dashboard/.prettierrc
rustfmt Formatting cargo fmt --all --check ci .github/workflows/test-rust.yml

Supply chain

1 tool

ToolKindCommandRuns inFound in
uv-lock Lockfile consistency uv lock --check ci .github/workflows/test-linting.yml
.github/workflows/test-mcp-dependency-resolution.yml
103 other commands the scanner could not classify

Commands from CI steps and task runners that look like checks but match no known tool. Some are checks, some are not.

  • Bearer ${LITELLM_MASTER_KEY} --header 'Content-Type: application/json' --data '{model:gpt-4,messages:[{role:sys...
  • bash $GITHUB_WORKSPACE/.github/scripts/select_ui_test_scope.sh)
  • bun test scripts/auto-close-duplicates.test.ts
  • bun test scripts/classify-issue.test.ts scripts/label-issue.test.ts
  • bun test scripts/comment-fixed-issue.test.ts
  • bun test scripts/flag-duplicate-issue.test.ts
  • bun test scripts/sync-issue-labels.test.ts
  • check_deps base/enterprise/pyproject.toml pr/enterprise/pyproject.toml enterprise/pyproject.toml
  • check_deps base/litellm-proxy-extras/pyproject.toml pr/litellm-proxy-extras/pyproject.toml litellm-proxy-extras/pypro...
  • check_deps base/pyproject.toml pr/pyproject.toml pyproject.toml
  • coverage run --rcfile=/dev/null --branch --include=*/scripts/build_core_distribution.py scripts/build_core_distributi...
  • coverage xml --rcfile=/dev/null -o coverage-core.xml
  • diff $$base_ref --unified=0 --no-color -- *.py)
  • diff --name-only $$base_ref -- *.py)
  • diff --name-only --diff-filter=ACMR --merge-base $$base_ref -- litellm/*.py)
  • do eslint_files+=($f)
  • do file=$${range%%:*}
  • done
  • done < $RUNNER_TEMP/eslint_files.txt
  • else echo $$files
  • else echo No changed .py files to check.
  • for spec in data.get(project, {}).get(dependencies, []):
  • for spec in group:
  • ggshield secret scan repo .
  • go run ./tools/endpointaudit -provider-dir ./litellm -spec ${RUNNER_TEMP}/openapi.json -coverage-allowlist ./tools/en...
  • helm plugin install https://github.com/helm-unittest/helm-unittest --version v0.8.2
  • helm plugin list
  • helm unittest -f tests/*.yaml $chart
  • helm unittest -f tests/*.yaml helm/litellm-helm
  • m = pep508.match(spec)
  • node scripts/check-lint-budgets.mjs $RUNNER_TEMP/lint-report.json eslint-budgets.json
  • node tests/e2e/ui/node_modules/@playwright/test/cli.js install chromium
  • node tests/e2e/ui/node_modules/@playwright/test/cli.js install-deps chromium
  • nohup .venv/bin/python tests/_fake_openai_endpoint_server.py --host 0.0.0.0 --port 8190 > ${RUNNER_TEMP}/fake-openai....
  • nothing to check."
  • perl -ne ' if (/^diff --git a\/(.*) b\//) { $$file = $$1
  • print $$file:$$start:1-$$end:999\n
  • python ../tests/documentation_tests/test_circular_imports.py
  • python ./tests/code_coverage_tests/ban_copy_deepcopy_kwargs.py
  • python ./tests/code_coverage_tests/callback_manager_test.py

full scan as JSON

Review prompts

most discussed first

  • BerriAI/litellm Code Style Python llm-infra
    raw open
  • BerriAI/litellm Testing Python llm-infra
    raw open
  • BerriAI/litellm AI Python llm-infra
    raw open
  • BerriAI/litellm AI Json llm-infra
    raw open
  • BerriAI/litellm Null Handling Python llm-infra
    raw open
  • BerriAI/litellm AI Markdown llm-infra
    raw open
  • BerriAI/litellm Naming Conventions Python llm-infra
    raw open
  • BerriAI/litellm Logging Python llm-infra
    raw open
  • BerriAI/litellm Configurations Python llm-infra
    raw open
  • BerriAI/litellm API Python llm-infra
    raw open
  • BerriAI/litellm API Markdown llm-infra
    raw open
  • BerriAI/litellm Performance Optimization Python llm-infra
    raw open
  • BerriAI/litellm Concurrency Python llm-infra
    raw open
  • BerriAI/litellm Error Handling Python llm-infra
    raw open
  • BerriAI/litellm Configurations Toml llm-infra
    raw open
  • BerriAI/litellm Database Python llm-infra
    raw open
  • BerriAI/litellm Observability Markdown llm-infra
    raw open
  • BerriAI/litellm CI/CD Yaml llm-infra
    raw open
  • BerriAI/litellm Configurations Markdown llm-infra
    raw open
  • BerriAI/litellm Security Python llm-infra
    raw open
  • BerriAI/litellm Configurations Txt llm-infra
    raw open
  • BerriAI/litellm Documentation Markdown llm-infra
    raw open
  • BerriAI/litellm Naming Conventions Markdown llm-infra
    raw open
  • BerriAI/litellm Security Yaml llm-infra
    raw open
  • BerriAI/litellm Security Prisma llm-infra
    raw open