scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-07 02:59:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

Merge branch 'litellm_internal_staging' into litellm_model_update_null_clear

Browse source
This commit is contained in:
yuneng-jiang 2026-09-07 09:37:10 -07:00 • committed by GitHub
commit 6f48d92ba5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 63 additions and 271 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

129
.github/workflows/report-rust-release-wheel.yml vendored
View file

@ -1,129 +0,0 @@
name: Report LiteLLM Rust release wheel
on: # zizmor: ignore[dangerous-triggers] reporter executes no PR code and consumes no PR artifacts or outputs
workflow_run:
workflows:
- LiteLLM Rust
types:
- completed
permissions: {}
concurrency:
group: ${{ github.workflow }}-${{ github.event.workflow_run.pull_requests[0].number || github.event.workflow_run.id }}
cancel-in-progress: false
jobs:
report-release-wheel:
name: report release wheel
if: >-
github.event.workflow_run.event == 'pull_request' &&
github.event.workflow_run.path == '.github/workflows/test-rust.yml' &&
github.event.workflow_run.head_repository.full_name == github.repository &&
github.event.workflow_run.pull_requests[0].number != null
runs-on: ubuntu-latest
timeout-minutes: 5
permissions:
pull-requests: write
steps:
- name: Link release wheel report on PR
uses: actions/github-script@f28e40c7f34bde8b3046d885e986cb6290c5673b # v7.1.0
env:
COMMENT_MARKER: "<!-- litellm-release-wheel-size -->"
with:
script: |
const marker = process.env.COMMENT_MARKER;
const workflowRun = context.payload.workflow_run;
const allowedConclusions = new Set([
"action_required",
"cancelled",
"failure",
"neutral",
"skipped",
"stale",
"startup_failure",
"success",
"timed_out",
]);
if (
!allowedConclusions.has(workflowRun.conclusion) ||
workflowRun.event !== "pull_request" ||
workflowRun.path !== ".github/workflows/test-rust.yml" ||
workflowRun.head_repository?.full_name !==
`${context.repo.owner}/${context.repo.repo}` ||
workflowRun.pull_requests?.length !== 1
) {
throw new Error("unexpected source workflow");
}
const pullRequest = workflowRun.pull_requests[0];
const pullRequestNumber = pullRequest.number;
const headSha = workflowRun.head_sha;
const runId = workflowRun.id;
if (
!Number.isSafeInteger(pullRequestNumber) ||
pullRequestNumber <= 0 ||
!Number.isSafeInteger(runId) ||
runId <= 0 ||
!/^[0-9a-f]{40}$/.test(headSha) ||
pullRequest.head?.sha !== headSha
) {
throw new Error("invalid source workflow metadata");
}
const runUrl =
`${context.serverUrl}/${context.repo.owner}/${context.repo.repo}` +
`/actions/runs/${runId}`;
const result =
workflowRun.conclusion === "success"
? "successfully"
: `with \`${workflowRun.conclusion}\``;
const body = [
marker,
"## LiteLLM Rust workflow",
"",
`Workflow completed ${result} for \`${headSha}\``,
"",
`[View workflow run](${runUrl})`,
].join("\n");
const comments = await github.paginate(github.rest.issues.listComments, {
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: pullRequestNumber,
per_page: 100,
});
const existing = comments.find(
(comment) =>
comment.user?.login === "github-actions[bot]" &&
comment.body?.startsWith(marker),
);
const currentPullRequest = (
await github.rest.pulls.get({
owner: context.repo.owner,
repo: context.repo.repo,
pull_number: pullRequestNumber,
})
).data;
if (
currentPullRequest.state !== "open" ||
currentPullRequest.head.repo?.full_name !==
`${context.repo.owner}/${context.repo.repo}` ||
currentPullRequest.head.sha !== headSha
) {
core.info("source workflow no longer matches the current pull request head");
return;
}
if (existing) {
await github.rest.issues.updateComment({
owner: context.repo.owner,
repo: context.repo.repo,
comment_id: existing.id,
body,
});
} else {
await github.rest.issues.createComment({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: pullRequestNumber,
body,
});
}

111
.github/workflows/test-rust.yml vendored
View file

@ -7,6 +7,7 @@ on:
- ".cargo/**"
- "pyproject.toml"
- "rust-toolchain.toml"
- ".github/actions/setup-uv-with-retries/**"
- ".github/scripts/smoke_test_native_wheel.py"
- ".github/scripts/verify_linux_native_wheel.py"
- "tests/test_litellm/rust_bridge/native_route_wheel_test.py"
@ -22,6 +23,7 @@ on:
- ".cargo/**"
- "pyproject.toml"
- "rust-toolchain.toml"
- ".github/actions/setup-uv-with-retries/**"
- ".github/scripts/smoke_test_native_wheel.py"
- ".github/scripts/verify_linux_native_wheel.py"
- "tests/test_litellm/rust_bridge/native_route_wheel_test.py"
@ -34,102 +36,89 @@ concurrency:
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: true
env:
CARGO_TERM_COLOR: always
jobs:
rust-checks:
name: rustfmt, clippy, test
rust-lint:
runs-on: ubuntu-latest
timeout-minutes: 10
defaults:
run:
working-directory: litellm-rust
env:
CARGO_TERM_COLOR: always
steps:
- name: Checkout repository
uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
- uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
with:
persist-credentials: false
- name: Set up Rust
run: rustup toolchain install
- run: rustup toolchain install --no-self-update
- name: Cache Cargo registry and target
uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
- run: cargo fmt --check
- uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
with:
path: |
~/.cargo/registry
~/.cargo/git
litellm-rust/target
key: ${{ runner.os }}-cargo-${{ hashFiles('rust-toolchain.toml', 'litellm-rust/Cargo.lock') }}
key: ${{ runner.os }}-cargo-${{ github.job }}-${{ hashFiles('rust-toolchain.toml', '.cargo/**', 'litellm-rust/Cargo.lock') }}
restore-keys: |
${{ runner.os }}-cargo-
${{ runner.os }}-cargo-${{ github.job }}-
- name: Check Rust formatting
run: cargo fmt --check
- run: cargo clippy --workspace --all-targets --locked -- -D warnings
- name: Run Clippy
run: cargo clippy --workspace --all-targets --locked -- -D warnings
- run: cargo clippy -p litellm-core --all-targets --features bedrock-auth --locked -- -D warnings
- name: Run Clippy with Bedrock auth
run: cargo clippy -p litellm-core --all-targets --features bedrock-auth --locked -- -D warnings
- run: cargo clippy -p litellm-ai-gateway --all-targets --all-features --locked -- -D warnings
- name: Run Clippy with all gateway features
run: cargo clippy -p litellm-ai-gateway --all-targets --all-features --locked -- -D warnings
- name: Run Rust tests
run: cargo test --workspace --locked
- name: Run core tests with Bedrock auth
run: cargo test -p litellm-core --features bedrock-auth --locked
# Not --all-features: python-config links libpython, which this job does not install.
- name: Run gateway tests with the server feature
run: cargo test -p litellm-ai-gateway --features server --locked
release-wheel:
name: release wheel
rust-test:
runs-on: ubuntu-latest
timeout-minutes: 20
permissions:
contents: read
env:
CARGO_TERM_COLOR: always
timeout-minutes: 30
steps:
- name: Checkout repository
uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
- uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
with:
persist-credentials: false
- name: Set up Python
uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
- uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
with:
python-version: "3.12"
- name: Set up uv
uses: ./.github/actions/setup-uv-with-retries
- uses: ./.github/actions/setup-uv-with-retries
with:
version: "0.10.9"
- name: Set up Rust
run: rustup toolchain install
- run: rustup toolchain install --no-self-update
- name: Build release wheel
run: uv build --wheel --out-dir dist
- uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
with:
path: |
~/.cargo/registry
~/.cargo/git
litellm-rust/target
key: ${{ runner.os }}-cargo-${{ github.job }}-${{ hashFiles('rust-toolchain.toml', '.cargo/**', 'litellm-rust/Cargo.lock') }}
restore-keys: |
${{ runner.os }}-cargo-${{ github.job }}-
- name: Build panic contract wheel
run: >-
- run: cargo test --workspace --locked
working-directory: litellm-rust
- run: cargo test -p litellm-core --features bedrock-auth --locked
working-directory: litellm-rust
- run: cargo test -p litellm-ai-gateway --features server --locked
working-directory: litellm-rust
- run: uv build --wheel --out-dir dist
- run: python .github/scripts/verify_linux_native_wheel.py dist/*.whl
env:
RELEASE_WHEEL_COMMIT_SHA: ${{ github.event.pull_request.head.sha || github.sha }}
- run: python tests/test_litellm/rust_bridge/native_route_wheel_test.py dist/*.whl
- run: >-
uv build --wheel --out-dir panic-dist
--config-setting "maturin.build-args=--features panic-test,extension-module"
- name: Smoke-test native panic unwinding
run: python .github/scripts/smoke_test_native_wheel.py panic-dist/*.whl
- name: Verify stripped native extension
env:
RELEASE_WHEEL_COMMIT_SHA: ${{ github.event.pull_request.head.sha || github.sha }}
run: python .github/scripts/verify_linux_native_wheel.py dist/*.whl
- name: Test native route wheel
run: python tests/test_litellm/rust_bridge/native_route_wheel_test.py dist/*.whl
- run: python .github/scripts/smoke_test_native_wheel.py panic-dist/*.whl

2
CLAUDE.md
View file

@ -52,7 +52,7 @@ Don't hesitate to use values in .env to get needed API keys and other secrets, a
Python max line length is 120, not 88
When you fix violations gated by `ruff-strict-budget.json`, `type-discipline-budget.json`, or `basedpyright-code-budget.json`, run `make lint-budget-update` and commit the lowered limits so the ceilings ratchet down instead of leaving stale headroom. It measures the working tree, so it must contain exactly the fixes you're committing
Never edit or commit `ruff-strict-budget.json`, `type-discipline-budget.json`, `basedpyright-code-budget.json`, or `test-quality-budget.json` on a PR branch, and don't run `make lint-budget-update` there. A scheduled Devin automation lowers the limits on `litellm_internal_staging` in its own PR by exactly what landed since the last ratchet, so concurrent PRs don't fight over the same `"limit"` lines. If your branch already carries a budget edit, drop it before opening the PR
`make check` (f.k.a. `make pre-commit`, which still works identically as an alias) saves its complete output to a log file in .git (overwriting previous logs) and prints that path as its first and last output lines. To inspect a run, read or grep that log instead of re-running the multi-minute checks just to see a different slice

59
scripts/test_quality_gate.py
View file

@ -10,17 +10,12 @@ base.
Every rule is seeded at exactly its count on the day the gate landed, so the
suite's existing debt is grandfathered and any net-new violation trips the gate
immediately. ``--update`` ratchets a limit down by the violations this branch
fixed relative to its branch point (the merge-base), so the ceilings only ever
fall. Base counts are measured with the *current* checker, so a rule introduced
on this branch is counted at the base too and ratchets like every other one.
Only ever falling is not the same as always falling, so the gate enforces the
second half: a branch that clears violations and leaves the ceiling above its
new count fails, naming the rules and telling the author to run
``make lint-budget-update``. Without that, a removed violation could come back
later under a ceiling nobody lowered. Drift already in the base is never
blamed, so this fires only on the branch that did the clearing.
immediately. ``--update`` ratchets a limit down by the violations fixed relative
to ``--base``, so the ceilings only ever fall. Base counts are measured with the
*current* checker, so a rule introduced on this branch is counted at the base too
and ratchets like every other one. The ratchet runs as a scheduled automation
against litellm_internal_staging, not on PR branches, so concurrent PRs never
race to edit the same limit.
The deliberate difference from its sibling: this gate has no headroom anywhere.
Type discipline seeded LIT010/LIT011 at 1.5x to leave room for an in-flight
@ -144,21 +139,6 @@ def over_ceiling(head: Mapping[str, int], budget: Mapping[str, Mapping[str, int]
)
def unratcheted(
head: Mapping[str, int],
base: Mapping[str, int],
budget: Mapping[str, Mapping[str, int]],
) -> tuple[Breach, ...]:
"""Rules this branch cleared without lowering the ceiling behind them. Requires
both `head < base`, so drift already in the base is never blamed on this change,
and `head < limit`, so a ceiling already at the count is left alone."""
return tuple(sorted(
Breach(rule, head.get(rule, 0), spec["limit"], head.get(rule, 0) - base.get(rule, 0))
for rule, spec in budget.items()
if head.get(rule, 0) < base.get(rule, 0) and head.get(rule, 0) < spec["limit"]
))
def evaluate(
head: Mapping[str, int],
base: Mapping[str, int],
@ -198,38 +178,15 @@ def introduced(
return tuple(v for v in violations if v.line in changed.get(v.file, frozenset()))
def touches_measured_tree(base_point: str) -> bool:
"""Whether this branch changed anything that can move a count. A branch that
touches neither the test tree nor the checker cannot have cleared a violation,
so the base scan is skipped and the gate stays cheap on the common change."""
changed: Final = _run(
["git", "diff", "--name-only", base_point, "--", TARGET, str(CHECKER.relative_to(REPO_ROOT))]
)
return bool(changed.strip())
def cmd_check(base: str) -> None:
budget: Final = json.loads(BUDGET_PATH.read_text())
head: Final = head_violations()
head_counts: Final = count_by_rule(head)
base_point: Final = resolve_base_point(base)
if not over_ceiling(head_counts, budget) and not touches_measured_tree(base_point):
if not over_ceiling(head_counts, budget):
print(f"OK: every TQ rule is within its test-suite ceiling (base {base})")
return
base_point: Final = resolve_base_point(base)
base_at_point: Final = base_counts(base_point)
stale: Final = unratcheted(head_counts, base_at_point, budget)
if stale:
print(f"FAIL: TQ-rule limits were left above the count this branch reached (base {base}):")
for breach in stale:
print(
f" {breach.rule}: this branch cleared {-breach.added} down to {breach.total}, "
f"but the limit is still {breach.cap}"
)
print(
"Run `make lint-budget-update` and commit the lowered limits, so the "
"violations you cleared cannot come back under a ceiling nobody moved."
)
raise SystemExit(1)
breaches: Final = evaluate(head_counts, base_at_point, budget)
if not breaches:
print(f"OK: every TQ rule is within its test-suite ceiling (base {base})")

33
tests/test_litellm/test_test_quality_gate.py
View file

@ -1,11 +1,9 @@
"""Tests for scripts/test_quality_gate.py.
The gate's whole value is that it blames a change only for what it adds, that a limit
can never rise, and that a limit cannot stay above a count the branch pushed below it.
All three live in pure functions, so they are tested directly: `evaluate` for the blame
rule, `ratcheted_budget` for the one-way ratchet, `unratcheted` for the ceiling a branch
left behind, and `parse_changed_lines` for the diff scan that turns a breach into
file:line.
The gate's whole value is that it blames a change only for what it adds and that a
limit can never rise. Both live in pure functions, so they are tested directly:
`evaluate` for the blame rule, `ratcheted_budget` for the one-way ratchet, and
`parse_changed_lines` for the diff scan that turns a breach into file:line.
"""
import importlib.util
@ -73,29 +71,6 @@ def test_ratchet_lowers_a_rule_introduced_on_this_branch_like_any_other():
assert updated["TQ001"]["limit"] == 4
def test_a_branch_that_cleared_violations_must_lower_the_ceiling():
stale = gate.unratcheted({"TQ001": 6}, {"TQ001": 10}, _BUDGET)
assert [(b.rule, b.total, b.cap, b.added) for b in stale] == [("TQ001", 6, 10, -4)]
def test_headroom_already_in_the_base_is_not_blamed_on_this_branch():
assert gate.unratcheted({"TQ001": 6}, {"TQ001": 6}, _BUDGET) == ()
def test_a_branch_that_cleared_down_to_the_ceiling_exactly_is_clean():
assert gate.unratcheted({"TQ001": 10}, {"TQ001": 12}, _BUDGET) == ()
def test_a_branch_that_added_violations_is_not_a_ratchet_finding():
assert gate.unratcheted({"TQ001": 14}, {"TQ001": 10}, _BUDGET) == ()
def test_the_ratchet_finding_survives_the_update_that_answers_it():
cleared = {"TQ001": 6}
updated = gate.ratcheted_budget(_BUDGET, cleared, {"TQ001": 10})
assert gate.unratcheted(cleared, {"TQ001": 10}, updated) == ()
def test_parse_changed_lines_groups_hunks_under_their_own_file():
diff = (
"diff --git a/tests/a.py b/tests/a.py\n"