mirror of
https://github.com/lancedb/lancedb.git
synced 2026-08-26 07:58:31 +00:00
fix: remove unsupported Function secrets contract (#4047)
## Problem The unreleased First-Class Function authoring API exposed `secrets=[...]` and serialized `required_secrets`, promising runtime resolution and injection that Sophon does not implement. ## Behavior Remove the secrets dimension from the public Python decorator, Python and Rust registration/version models, and shared wire fixtures. Existing successfully registered Functions retain stable identity: the field could only be empty and empty values were already omitted from canonical serialization. A stable LanceDB release has not shipped this Function API, so this contracts the surface before it becomes a published compatibility commitment. ## Validation gap The Rust shared-golden Function suites and Python formatting/lint checks pass locally. Python pytest was not run because the local environment lacks its runtime dependencies and the frozen native editable build did not complete in practical time.
This commit is contained in:
@@ -4,7 +4,7 @@
|
||||
"""Canonical Function values exchanged with LanceDB Enterprise services.
|
||||
|
||||
These immutable models contain client/wire state only. Catalog persistence,
|
||||
environment bake, secret resolution, and execution are owned by Sophon.
|
||||
environment bake, and execution are owned by Sophon.
|
||||
``RefreshColumnResult`` is also the backend-neutral result of a local
|
||||
expression-backed refresh job.
|
||||
"""
|
||||
@@ -228,7 +228,7 @@ class PythonEnvironmentSpec(_RemoteValue):
|
||||
|
||||
|
||||
class PythonRuntimeSpec(_RemoteValue):
|
||||
"""Remote runtime definition with non-secret environment values.
|
||||
"""Remote runtime definition with environment values.
|
||||
|
||||
V1 supports ``kind="python"``. Newer runtime kinds remain readable, while
|
||||
their unknown payload fields are intentionally not retained by the client.
|
||||
@@ -267,7 +267,6 @@ class FunctionVersion(_RemoteValue):
|
||||
runtime: PythonRuntimeSpec
|
||||
runtime_digest: str
|
||||
environment_digest: str
|
||||
required_secrets: tuple[str, ...] = ()
|
||||
created_at: str
|
||||
|
||||
def __call__(self, **inputs: Any) -> FunctionApplication:
|
||||
@@ -329,17 +328,12 @@ class FunctionVersion(_RemoteValue):
|
||||
|
||||
|
||||
class FunctionRegistrationRequest(_RemoteValue):
|
||||
"""Stable remote registration envelope produced by :func:`udf`.
|
||||
|
||||
Only secret names are represented. Secret values are resolved inside the
|
||||
remote service and have no client request field.
|
||||
"""
|
||||
"""Stable remote registration envelope produced by :func:`udf`."""
|
||||
|
||||
name: str
|
||||
artifact: FunctionArtifactRequest
|
||||
signature: FunctionSignature
|
||||
runtime: PythonRuntimeSpec
|
||||
required_secrets: tuple[str, ...] = ()
|
||||
|
||||
|
||||
class FunctionVersionRef(_OpenRemoteValue):
|
||||
@@ -484,7 +478,6 @@ class RefreshColumnResult(_RemoteValue):
|
||||
|
||||
|
||||
_FUNCTION_NAME = re.compile(r"^[A-Za-z_][A-Za-z0-9_.-]*$")
|
||||
_SECRET_NAME = re.compile(r"^[A-Za-z_][A-Za-z0-9_]*$")
|
||||
|
||||
|
||||
_GRAMMAR_PRIMITIVES = (
|
||||
@@ -915,7 +908,6 @@ class UdfDefinition:
|
||||
output_schema: Optional[pa.DataType | pa.Field | pa.Schema],
|
||||
pip: tuple[str, ...],
|
||||
env: Mapping[str, str],
|
||||
secrets: tuple[str, ...],
|
||||
python_version: Optional[str],
|
||||
):
|
||||
function_name = name or function.__name__
|
||||
@@ -930,18 +922,6 @@ class UdfDefinition:
|
||||
for key, value in environment.items()
|
||||
):
|
||||
raise TypeError("Function env keys and values must be strings")
|
||||
required_secrets = tuple(sorted(set(secrets)))
|
||||
invalid_secrets = [
|
||||
secret for secret in required_secrets if not _SECRET_NAME.fullmatch(secret)
|
||||
]
|
||||
if invalid_secrets:
|
||||
raise ValueError(f"invalid Function secret names: {invalid_secrets!r}")
|
||||
overlap = set(environment) & set(required_secrets)
|
||||
if overlap:
|
||||
raise ValueError(
|
||||
f"Function env and secret names must be disjoint: {sorted(overlap)!r}"
|
||||
)
|
||||
|
||||
signature = _infer_signature(function, input_schema, output_schema)
|
||||
source = _package_source(function)
|
||||
digest = f"sha256:{hashlib.sha256(source).hexdigest()}"
|
||||
@@ -970,7 +950,6 @@ class UdfDefinition:
|
||||
),
|
||||
signature=signature,
|
||||
runtime=runtime,
|
||||
required_secrets=required_secrets,
|
||||
)
|
||||
functools.update_wrapper(self, function)
|
||||
|
||||
@@ -996,7 +975,6 @@ def udf(
|
||||
output_schema: Optional[pa.DataType | pa.Field | pa.Schema] = None,
|
||||
pip: tuple[str, ...] | list[str] = (),
|
||||
env: Optional[Mapping[str, str]] = None,
|
||||
secrets: tuple[str, ...] | list[str] = (),
|
||||
python_version: Optional[str] = None,
|
||||
) -> Callable[[Callable[..., Any]], UdfDefinition]: ...
|
||||
|
||||
@@ -1009,7 +987,6 @@ def udf(
|
||||
output_schema: Optional[pa.DataType | pa.Field | pa.Schema] = None,
|
||||
pip: tuple[str, ...] | list[str] = (),
|
||||
env: Optional[Mapping[str, str]] = None,
|
||||
secrets: tuple[str, ...] | list[str] = (),
|
||||
python_version: Optional[str] = None,
|
||||
):
|
||||
"""Prepare a scalar Python callable for remote Function registration.
|
||||
@@ -1034,10 +1011,7 @@ def udf(
|
||||
pip : sequence of str, optional
|
||||
Pip requirements for the remote environment.
|
||||
env : mapping of str to str, optional
|
||||
Non-secret environment variables. Use ``secrets`` for credentials.
|
||||
secrets : sequence of str, optional
|
||||
Names of secrets resolved by the remote service. Secret values are not
|
||||
accepted by this API or included in the registration request.
|
||||
Environment variables included in the Function definition.
|
||||
python_version : str, optional
|
||||
Remote Python major/minor version. Defaults to the client version.
|
||||
|
||||
@@ -1059,7 +1033,7 @@ def udf(
|
||||
Examples
|
||||
--------
|
||||
>>> from lancedb import udf
|
||||
>>> @udf(pip=["numpy==2.2.0"], secrets=["MODEL_TOKEN"])
|
||||
>>> @udf(pip=["numpy==2.2.0"])
|
||||
... def score(value: float) -> float:
|
||||
... return value * 2
|
||||
>>> score(1.5)
|
||||
@@ -1074,7 +1048,6 @@ def udf(
|
||||
output_schema=output_schema,
|
||||
pip=tuple(pip),
|
||||
env={} if env is None else env,
|
||||
secrets=tuple(secrets),
|
||||
python_version=python_version,
|
||||
)
|
||||
|
||||
|
||||
@@ -37,21 +37,6 @@ def job_result(name: str) -> dict:
|
||||
return json.loads(fixture(name))["result"]
|
||||
|
||||
|
||||
def assert_no_secret_values(value):
|
||||
if isinstance(value, dict):
|
||||
for key, child in value.items():
|
||||
assert key not in {
|
||||
"secret_value",
|
||||
"secret_values",
|
||||
"resolved_secret",
|
||||
"resolved_secrets",
|
||||
}
|
||||
assert_no_secret_values(child)
|
||||
elif isinstance(value, list):
|
||||
for child in value:
|
||||
assert_no_secret_values(child)
|
||||
|
||||
|
||||
def test_public_function_values_are_in_api_reference():
|
||||
docs = Path(__file__).parents[3] / "docs" / "src" / "python" / "python.md"
|
||||
rendered = docs.read_text()
|
||||
@@ -109,7 +94,6 @@ def test_function_version_identity_is_immutable_and_exact():
|
||||
version = FunctionVersion.from_json(json.dumps(value))
|
||||
assert version.name == "embed"
|
||||
assert version.version == "fv_01K3EXACT"
|
||||
assert version.required_secrets == ("HF_TOKEN",)
|
||||
|
||||
with pytest.raises((TypeError, ValueError)):
|
||||
version.version = "fv_changed"
|
||||
@@ -292,15 +276,6 @@ def test_refresh_result_rejects_non_u64_values(field):
|
||||
RefreshColumnResult.from_json(json.dumps(value))
|
||||
|
||||
|
||||
def test_canonical_client_values_contain_secret_names_only():
|
||||
version = FunctionVersion.from_json(
|
||||
json.dumps(job_result("remote_function_job.json"))
|
||||
)
|
||||
canonical = json.loads(version.to_canonical_json())
|
||||
assert canonical["required_secrets"] == ["HF_TOKEN"]
|
||||
assert_no_secret_values(canonical)
|
||||
|
||||
|
||||
class _FunctionDeclarationInner:
|
||||
def __init__(self):
|
||||
self.calls = []
|
||||
|
||||
@@ -39,28 +39,12 @@ FIXTURES = (
|
||||
@udf(
|
||||
pip=["numpy>=2"],
|
||||
env={"MODE": "test"},
|
||||
secrets=["API_TOKEN"],
|
||||
python_version="3.12",
|
||||
)
|
||||
def normalize_score(value: float) -> float:
|
||||
return value / 100.0
|
||||
|
||||
|
||||
def _assert_no_secret_values(value):
|
||||
if isinstance(value, dict):
|
||||
for key, child in value.items():
|
||||
assert key not in {
|
||||
"secret_value",
|
||||
"secret_values",
|
||||
"resolved_secret",
|
||||
"resolved_secrets",
|
||||
}
|
||||
_assert_no_secret_values(child)
|
||||
elif isinstance(value, list):
|
||||
for child in value:
|
||||
_assert_no_secret_values(child)
|
||||
|
||||
|
||||
def test_scalar_udf_matches_shared_registration_golden_and_remains_callable():
|
||||
assert isinstance(normalize_score, UdfDefinition)
|
||||
assert normalize_score(25.0) == 0.25
|
||||
@@ -75,8 +59,6 @@ def test_scalar_udf_matches_shared_registration_golden_and_remains_callable():
|
||||
"kind": "scalar_to_arrow_batch",
|
||||
"version": 1,
|
||||
}
|
||||
assert request["required_secrets"] == ["API_TOKEN"]
|
||||
_assert_no_secret_values(request)
|
||||
|
||||
|
||||
def _run_packaged(definition, *args):
|
||||
@@ -370,7 +352,6 @@ def test_udf_recursion_versus_a_rebound_module_name(tmp_path):
|
||||
output_schema=None,
|
||||
pip=(),
|
||||
env={},
|
||||
secrets=(),
|
||||
python_version=None,
|
||||
)
|
||||
with pytest.raises(ValueError, match="binds that name to another value"):
|
||||
@@ -525,14 +506,6 @@ def test_annotation_and_explicit_schema_validation_fail_closed():
|
||||
return value
|
||||
|
||||
|
||||
def test_environment_rejects_secret_value_overlap():
|
||||
with pytest.raises(ValueError, match="must be disjoint"):
|
||||
|
||||
@udf(env={"TOKEN": "plaintext"}, secrets=["TOKEN"])
|
||||
def overlapping(value: int) -> int:
|
||||
return value
|
||||
|
||||
|
||||
def test_local_function_catalog_operations_are_not_supported(tmp_path):
|
||||
db = lancedb.connect(tmp_path)
|
||||
message = "Function catalog operations are not supported by this database"
|
||||
@@ -569,7 +542,6 @@ def _mock_remote_function_catalog():
|
||||
"runtime": body["runtime"],
|
||||
"runtime_digest": "sha256:runtime",
|
||||
"environment_digest": "sha256:environment",
|
||||
"required_secrets": body.get("required_secrets", []),
|
||||
"created_at": "2026-08-21T00:00:00Z",
|
||||
}
|
||||
response = {"job_id": "job-register"}
|
||||
@@ -628,7 +600,6 @@ def test_remote_registration_job_and_exact_version_reopen_round_trip():
|
||||
assert create_request == json.loads(
|
||||
normalize_score.registration_request.to_canonical_json()
|
||||
)
|
||||
_assert_no_secret_values(create_request)
|
||||
|
||||
|
||||
def test_blocking_remote_registration_returns_function_version():
|
||||
|
||||
@@ -5,7 +5,7 @@
|
||||
//! backend-neutral terminal result of a computed-column refresh.
|
||||
//!
|
||||
//! This module contains client/wire values only. Catalog persistence,
|
||||
//! environment bake, secret resolution, and execution are owned by Sophon.
|
||||
//! environment bake, and execution are owned by Sophon.
|
||||
|
||||
use std::collections::BTreeMap;
|
||||
|
||||
@@ -195,9 +195,6 @@ pub struct PythonEnvironmentSpec {
|
||||
}
|
||||
|
||||
/// Reproducible Python runtime definition understood by Sophon.
|
||||
///
|
||||
/// `env` contains non-secret values. Secret values have no client model;
|
||||
/// [`FunctionVersion::required_secrets`] contains names only.
|
||||
#[derive(Debug, Clone, PartialEq, Eq)]
|
||||
#[non_exhaustive]
|
||||
pub enum PythonRuntimeSpec {
|
||||
@@ -239,7 +236,7 @@ impl PythonRuntimeSpec {
|
||||
}
|
||||
}
|
||||
|
||||
/// Non-secret environment variables, or `None` for an unknown kind.
|
||||
/// Environment variables, or `None` for an unknown kind.
|
||||
pub fn env(&self) -> Option<&BTreeMap<String, String>> {
|
||||
match self {
|
||||
Self::Python { env, .. } => Some(env),
|
||||
@@ -324,8 +321,6 @@ pub struct FunctionVersion {
|
||||
runtime: PythonRuntimeSpec,
|
||||
runtime_digest: String,
|
||||
environment_digest: String,
|
||||
#[serde(default, skip_serializing_if = "Vec::is_empty")]
|
||||
required_secrets: Vec<String>,
|
||||
created_at: String,
|
||||
}
|
||||
|
||||
@@ -358,11 +353,6 @@ impl FunctionVersion {
|
||||
&self.environment_digest
|
||||
}
|
||||
|
||||
/// Required secret names. Resolved values exist only inside Sophon.
|
||||
pub fn required_secrets(&self) -> &[String] {
|
||||
&self.required_secrets
|
||||
}
|
||||
|
||||
pub fn created_at(&self) -> &str {
|
||||
&self.created_at
|
||||
}
|
||||
@@ -404,18 +394,12 @@ pub struct FunctionArtifactRequest {
|
||||
}
|
||||
|
||||
/// Stable request envelope for remote immutable Function registration.
|
||||
///
|
||||
/// Secret values deliberately have no field in this model. The only secret
|
||||
/// material the client may send is the ordered set of names Sophon resolves
|
||||
/// inside the remote runtime.
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
pub struct FunctionRegistrationRequest {
|
||||
pub name: String,
|
||||
pub artifact: FunctionArtifactRequest,
|
||||
pub signature: FunctionSignature,
|
||||
pub runtime: PythonRuntimeSpec,
|
||||
#[serde(default, skip_serializing_if = "Vec::is_empty")]
|
||||
pub required_secrets: Vec<String>,
|
||||
}
|
||||
|
||||
impl_json!(FunctionRegistrationRequest);
|
||||
|
||||
@@ -20,25 +20,6 @@ fn job_result(name: &str) -> Value {
|
||||
serde_json::from_str::<Value>(&fixture(name)).expect("remote Job fixture")["result"].clone()
|
||||
}
|
||||
|
||||
fn assert_no_secret_values(value: &Value) {
|
||||
match value {
|
||||
Value::Object(values) => {
|
||||
for (key, value) in values {
|
||||
assert!(
|
||||
!matches!(
|
||||
key.as_str(),
|
||||
"secret_value" | "secret_values" | "resolved_secret" | "resolved_secrets"
|
||||
),
|
||||
"client canonical value must not model resolved secret material"
|
||||
);
|
||||
assert_no_secret_values(value);
|
||||
}
|
||||
}
|
||||
Value::Array(values) => values.iter().for_each(assert_no_secret_values),
|
||||
_ => {}
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn function_version_job_result_matches_shared_canonical_golden() {
|
||||
let result = job_result("remote_function_job.json");
|
||||
@@ -47,7 +28,6 @@ fn function_version_job_result_matches_shared_canonical_golden() {
|
||||
assert_eq!(version.name(), "embed");
|
||||
assert_eq!(version.version(), "fv_01K3EXACT");
|
||||
assert_eq!(version.runtime_digest(), "sha256:runtime");
|
||||
assert_eq!(version.required_secrets(), &["HF_TOKEN"]);
|
||||
assert_eq!(
|
||||
version.to_canonical_json().expect("canonical JSON"),
|
||||
fixture("remote_function_version.canonical.json").trim()
|
||||
@@ -162,21 +142,3 @@ fn floating_point_application_literals_are_rejected_consistently() {
|
||||
.contains("floating-point Function literals")
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn canonical_client_values_contain_secret_names_only() {
|
||||
let result = job_result("remote_function_job.json");
|
||||
let version = FunctionVersion::from_json(&result.to_string()).expect("FunctionVersion result");
|
||||
let canonical: Value = serde_json::from_str(
|
||||
&version
|
||||
.to_canonical_json()
|
||||
.expect("canonical FunctionVersion"),
|
||||
)
|
||||
.expect("canonical JSON");
|
||||
|
||||
assert_eq!(
|
||||
canonical["required_secrets"],
|
||||
serde_json::json!(["HF_TOKEN"])
|
||||
);
|
||||
assert_no_secret_values(&canonical);
|
||||
}
|
||||
|
||||
@@ -6,7 +6,6 @@ use std::path::PathBuf;
|
||||
|
||||
use lancedb::Error;
|
||||
use lancedb::function::FunctionRegistrationRequest;
|
||||
use serde_json::Value;
|
||||
|
||||
fn fixture(name: &str) -> String {
|
||||
let path = PathBuf::from(env!("CARGO_MANIFEST_DIR"))
|
||||
@@ -15,25 +14,6 @@ fn fixture(name: &str) -> String {
|
||||
fs::read_to_string(path).expect("fixture must be readable")
|
||||
}
|
||||
|
||||
fn assert_no_secret_values(value: &Value) {
|
||||
match value {
|
||||
Value::Object(values) => {
|
||||
for (key, value) in values {
|
||||
assert!(
|
||||
!matches!(
|
||||
key.as_str(),
|
||||
"secret_value" | "secret_values" | "resolved_secret" | "resolved_secrets"
|
||||
),
|
||||
"registration requests must not model resolved secret material"
|
||||
);
|
||||
assert_no_secret_values(value);
|
||||
}
|
||||
}
|
||||
Value::Array(values) => values.iter().for_each(assert_no_secret_values),
|
||||
_ => {}
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn registration_request_matches_shared_canonical_golden() {
|
||||
let request = FunctionRegistrationRequest::from_json(&fixture(
|
||||
@@ -42,16 +22,10 @@ fn registration_request_matches_shared_canonical_golden() {
|
||||
.expect("registration request");
|
||||
assert_eq!(request.name, "normalize_score");
|
||||
assert_eq!(request.artifact.adapter.kind, "scalar_to_arrow_batch");
|
||||
assert_eq!(request.required_secrets, ["API_TOKEN"]);
|
||||
assert_eq!(
|
||||
request.to_canonical_json().expect("canonical request"),
|
||||
fixture("remote_function_registration_request.canonical.json").trim()
|
||||
);
|
||||
|
||||
let value: Value =
|
||||
serde_json::from_str(&request.to_canonical_json().expect("canonical request"))
|
||||
.expect("request JSON");
|
||||
assert_no_secret_values(&value);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
|
||||
@@ -24,7 +24,6 @@
|
||||
},
|
||||
"runtime_digest": "sha256:runtime",
|
||||
"environment_digest": "sha256:environment",
|
||||
"required_secrets": ["HF_TOKEN"],
|
||||
"created_at": "2026-08-21T00:00:00Z"
|
||||
},
|
||||
"future_job": {"trace_id": "trace-1"}
|
||||
|
||||
+1
-1
@@ -1 +1 @@
|
||||
{"artifact":{"adapter":{"kind":"scalar_to_arrow_batch","version":1},"content":{"data":"ZnJvbSBfX2Z1dHVyZV9fIGltcG9ydCBhbm5vdGF0aW9ucwoKZGVmIG5vcm1hbGl6ZV9zY29yZSh2YWx1ZTogZmxvYXQpIC0+IGZsb2F0OgogICAgcmV0dXJuIHZhbHVlIC8gMTAwLjAK","encoding":"base64"},"digest":"sha256:760784bdcef57b802f389b97804cc0b618aae39e86044733451bcd0b13089a7f","entrypoint":"normalize_score","kind":"python_callable"},"name":"normalize_score","required_secrets":["API_TOKEN"],"runtime":{"env":{"MODE":"test"},"environment":{"kind":"pip","packages":["numpy>=2"]},"kind":"python","python_version":"3.12"},"signature":{"inputs":[{"arrow_type":"float64","name":"value","nullable":false}],"output":{"arrow_type":"float64","kind":"scalar","nullable":false}}}
|
||||
{"artifact":{"adapter":{"kind":"scalar_to_arrow_batch","version":1},"content":{"data":"ZnJvbSBfX2Z1dHVyZV9fIGltcG9ydCBhbm5vdGF0aW9ucwoKZGVmIG5vcm1hbGl6ZV9zY29yZSh2YWx1ZTogZmxvYXQpIC0+IGZsb2F0OgogICAgcmV0dXJuIHZhbHVlIC8gMTAwLjAK","encoding":"base64"},"digest":"sha256:760784bdcef57b802f389b97804cc0b618aae39e86044733451bcd0b13089a7f","entrypoint":"normalize_score","kind":"python_callable"},"name":"normalize_score","runtime":{"env":{"MODE":"test"},"environment":{"kind":"pip","packages":["numpy>=2"]},"kind":"python","python_version":"3.12"},"signature":{"inputs":[{"arrow_type":"float64","name":"value","nullable":false}],"output":{"arrow_type":"float64","kind":"scalar","nullable":false}}}
|
||||
|
||||
Vendored
+1
-4
@@ -39,8 +39,5 @@
|
||||
"env": {
|
||||
"MODE": "test"
|
||||
}
|
||||
},
|
||||
"required_secrets": [
|
||||
"API_TOKEN"
|
||||
]
|
||||
}
|
||||
}
|
||||
|
||||
Vendored
+1
-1
@@ -1 +1 @@
|
||||
{"artifact":{"digest":"sha256:code","entrypoint":"embed","kind":"python_callable"},"created_at":"2026-08-21T00:00:00Z","environment_digest":"sha256:environment","name":"embed","required_secrets":["HF_TOKEN"],"runtime":{"env":{"TOKENIZERS_PARALLELISM":"false"},"environment":{"kind":"pip","packages":["sentence-transformers>=3"]},"kind":"python","python_version":"3.12"},"runtime_digest":"sha256:runtime","signature":{"inputs":[{"arrow_type":"utf8","name":"text","nullable":true}],"output":{"arrow_type":"list<float32>","kind":"scalar","nullable":false}},"version":"fv_01K3EXACT"}
|
||||
{"artifact":{"digest":"sha256:code","entrypoint":"embed","kind":"python_callable"},"created_at":"2026-08-21T00:00:00Z","environment_digest":"sha256:environment","name":"embed","runtime":{"env":{"TOKENIZERS_PARALLELISM":"false"},"environment":{"kind":"pip","packages":["sentence-transformers>=3"]},"kind":"python","python_version":"3.12"},"runtime_digest":"sha256:runtime","signature":{"inputs":[{"arrow_type":"utf8","name":"text","nullable":true}],"output":{"arrow_type":"list<float32>","kind":"scalar","nullable":false}},"version":"fv_01K3EXACT"}
|
||||
|
||||
Reference in New Issue
Block a user