From 7b29fb2f51ab2b1816b9dd07bd2be8c6f01e5e08 Mon Sep 17 00:00:00 2001 From: Jonathan M Hsieh Date: Tue, 8 Sep 2026 23:11:20 +0000 Subject: [PATCH] feat(secrets): named Secrets and EnvVarSecret bindings Adds the client half of database-scoped named Secrets: a Secret is a name and an opaque value stored by the service, and a Function binds one to the environment variable its library already reads. - `db.create_secret` / `alter_secret` / `list_secrets` / `describe_secret` / `drop_secret` on sync, async and remote connections, with the pyo3 binding and the Rust client behind them. There is no read API by construction rather than by policy: no code path returns a stored credential, and `describe_secret` answers with metadata only. - `EnvVarSecret(secret=..., env_variable=...)` pairs a Secret with the variable it arrives in. It is a pure local constructor -- it contacts no server, so it cannot fail on a Secret that does not exist -- and it exists so a bare string in that position, which would be a credential, is a TypeError rather than a plausible-looking mistake that reads identically in a diff. - `create_function(..., secrets=[...])` carries the bindings as `secret_bindings`, a map from variable name to Secret name. The value never travels: it is resolved by the service when the Function runs, which is what lets a rotation reach columns pinned to an older FunctionVersion. The UDF body is unchanged and stays portable -- it reads `OPENAI_API_KEY` the way it always did, and the binding is what puts a value there. Squashed: the original three commits were a first design plus a rewrite of it, so their sequence describes an interface that no longer exists. Co-Authored-By: Claude Opus 5 (1M context) Claude-Session: https://claude.ai/code/session_01XE1UwYKsgbb3USBfkqCE6v --- docs/src/python/python.md | 4 + python/python/lancedb/__init__.py | 2 + python/python/lancedb/_lancedb.pyi | 5 + python/python/lancedb/db.py | 172 +++++++++++++++- python/python/lancedb/functions.py | 80 +++++++- python/python/lancedb/remote/db.py | 42 +++- python/python/lancedb/secrets.py | 165 +++++++++++++++ .../tests/test_first_class_function_slice1.py | 36 ++++ .../tests/test_first_class_function_slice2.py | 183 +++++++++++++++++ python/src/connection.rs | 50 +++++ python/uv.lock | 193 +++++++++--------- rust/lancedb/src/connection.rs | 55 ++++- rust/lancedb/src/database.rs | 48 +++++ rust/lancedb/src/function.rs | 22 +- rust/lancedb/src/remote/db.rs | 167 ++++++++++++++- .../tests/first_class_function_slice1.rs | 62 ++++++ .../tests/first_class_function_slice2.rs | 56 +++++ .../v1/remote_function_job.json | 1 + ...secret_registration_request.canonical.json | 1 + ..._function_secret_registration_request.json | 46 +++++ .../v1/remote_function_version.canonical.json | 2 +- 21 files changed, 1274 insertions(+), 118 deletions(-) create mode 100644 python/python/lancedb/secrets.py create mode 100644 rust/lancedb/tests/fixtures/first_class_functions/v1/remote_function_secret_registration_request.canonical.json create mode 100644 rust/lancedb/tests/fixtures/first_class_functions/v1/remote_function_secret_registration_request.json diff --git a/docs/src/python/python.md b/docs/src/python/python.md index 28e774473..b74aaf0c2 100644 --- a/docs/src/python/python.md +++ b/docs/src/python/python.md @@ -125,6 +125,10 @@ listing a storage directory. ::: lancedb.functions.UdfDefinition +::: lancedb.secrets.EnvVarSecret + +::: lancedb.secrets.SecretInfo + ::: lancedb.functions.FunctionRegistrationRequest ::: lancedb.functions.FunctionArtifactRequest diff --git a/python/python/lancedb/__init__.py b/python/python/lancedb/__init__.py index cb9b57be3..51bb39fff 100644 --- a/python/python/lancedb/__init__.py +++ b/python/python/lancedb/__init__.py @@ -37,6 +37,8 @@ from .functions import ( UdfDefinition as UdfDefinition, udf as udf, ) +from .secrets import EnvVarSecret as EnvVarSecret +from .secrets import SecretInfo as SecretInfo from .materialized_view import ( AsyncMaterializedView, MaterializedView, diff --git a/python/python/lancedb/_lancedb.pyi b/python/python/lancedb/_lancedb.pyi index 0f7b110ac..3d84c2423 100644 --- a/python/python/lancedb/_lancedb.pyi +++ b/python/python/lancedb/_lancedb.pyi @@ -153,6 +153,11 @@ class Connection(object): async def get_function(self, name: str, version: str) -> str: ... async def list_functions(self) -> List[str]: ... async def drop_function(self, name: str, version: str) -> bool: ... + async def create_secret(self, name: str, value: str) -> None: ... + async def alter_secret(self, name: str, value: str) -> None: ... + async def list_secrets(self) -> List[str]: ... + async def drop_secret(self, name: str) -> None: ... + async def describe_secret(self, name: str) -> Dict[str, str]: ... async def list_jobs(self) -> List[JobInfo]: ... async def cancel_job(self, job_id: str) -> bool: ... async def execute_query_async( diff --git a/python/python/lancedb/db.py b/python/python/lancedb/db.py index 88718e968..804a98080 100644 --- a/python/python/lancedb/db.py +++ b/python/python/lancedb/db.py @@ -17,6 +17,7 @@ from typing import ( List, Literal, Optional, + Sequence, Union, ) from uuid import UUID @@ -57,6 +58,7 @@ from .materialized_view import ( SelectArg, normalize_select, ) +from .secrets import EnvVarSecret, SecretInfo, validate_secret_name from .table import ( AsyncTable, LanceTable, @@ -692,15 +694,47 @@ class DBConnection(EnforceOverrides): """ raise NotImplementedError("serialize is not supported for this connection type") - def create_function(self, definition: UdfDefinition) -> FunctionVersion: + def create_function( + self, + definition: UdfDefinition, + *, + secrets: Optional[Sequence[EnvVarSecret]] = None, + ) -> FunctionVersion: """Register a scalar Python UDF and wait for its immutable version. This is the blocking counterpart of :meth:`create_function_async`. Local connections raise ``NotImplementedError``. - """ - return self.create_function_async(definition).wait() - def create_function_async(self, definition: UdfDefinition) -> Job[FunctionVersion]: + Parameters + ---------- + definition : UdfDefinition + A callable decorated with [udf][lancedb.udf]. + secrets : sequence of EnvVarSecret, optional + One [EnvVarSecret][lancedb.secrets.EnvVarSecret] per credential the + Function needs, each naming a Secret and the environment variable + its value arrives in. The Function's source is unchanged by this; + it reads the variable the way it already did. + + Examples + -------- + ```python + db.create_secret("openai-prod", os.environ["OPENAI_API_KEY"]) + db.create_function( + analyze_caption, + secrets=[ + EnvVarSecret(secret="openai-prod", env_variable="OPENAI_API_KEY") + ], + ) + ``` + """ + return self.create_function_async(definition, secrets=secrets).wait() + + def create_function_async( + self, + definition: UdfDefinition, + *, + secrets: Optional[Sequence[EnvVarSecret]] = None, + ) -> Job[FunctionVersion]: """Register a scalar Python UDF through the remote Function catalog. Submission returns a typed job. The immutable Function version becomes @@ -745,6 +779,62 @@ class DBConnection(EnforceOverrides): "Function catalog operations are not supported for this connection type" ) + def create_secret(self, name: str, value: str) -> None: + """Create a named Secret in this database. + + Fails if the name is taken, so a create never silently becomes a + rotation. Nothing reads the value back: it is bound to a Function by + name and resolved by the service when that Function runs. Local + connections raise ``NotImplementedError``. + """ + raise NotImplementedError( + "Secret operations are not supported for this connection type" + ) + + def alter_secret(self, name: str, value: str) -> None: + """Replace the credential behind an existing Secret. + + Fails if it does not exist. Every Function bound to the Secret uses the + new value from its next job, and no new Function version is created -- + which is how a rotation reaches columns pinned to a version registered + before it. Local connections raise ``NotImplementedError``. + """ + raise NotImplementedError( + "Secret operations are not supported for this connection type" + ) + + def list_secrets(self) -> List[str]: + """The names of every Secret in this database. + + Names only. No method returns a stored credential, by construction + rather than by policy. Local connections raise ``NotImplementedError``. + """ + raise NotImplementedError( + "Secret operations are not supported for this connection type" + ) + + def drop_secret(self, name: str) -> None: + """Drop a Secret. + + Functions bound to it fail at their next job, naming the Secret; that + is the revocation path. The name becomes free to reuse, and a new + Secret under it is picked up by everything still bound to that name. + Local connections raise ``NotImplementedError``. + """ + raise NotImplementedError( + "Secret operations are not supported for this connection type" + ) + + def describe_secret(self, name: str) -> SecretInfo: + """What this database records about a Secret: name and timestamps. + + Never the value -- there is no code path that could return one. Local + connections raise ``NotImplementedError``. + """ + raise NotImplementedError( + "Secret operations are not supported for this connection type" + ) + def open_job(self, job_id: str) -> Job: """Open a server-side job by id, returning a handle with its record already populated. @@ -1457,8 +1547,13 @@ class LanceDBConnection(DBConnection): return Job(LOOP.run(self._conn.open_job(job_id))) @override - def create_function_async(self, definition: UdfDefinition) -> Job[FunctionVersion]: - job = LOOP.run(self._conn.create_function_async(definition)) + def create_function_async( + self, + definition: UdfDefinition, + *, + secrets: Optional[Sequence[EnvVarSecret]] = None, + ) -> Job[FunctionVersion]: + job = LOOP.run(self._conn.create_function_async(definition, secrets=secrets)) return Job(job) @override @@ -1473,6 +1568,26 @@ class LanceDBConnection(DBConnection): def drop_function(self, name: str, *, version: str) -> bool: return LOOP.run(self._conn.drop_function(name, version=version)) + @override + def create_secret(self, name: str, value: str) -> None: + LOOP.run(self._conn.create_secret(name, value)) + + @override + def alter_secret(self, name: str, value: str) -> None: + LOOP.run(self._conn.alter_secret(name, value)) + + @override + def list_secrets(self) -> List[str]: + return LOOP.run(self._conn.list_secrets()) + + @override + def drop_secret(self, name: str) -> None: + LOOP.run(self._conn.drop_secret(name)) + + @override + def describe_secret(self, name: str) -> SecretInfo: + return LOOP.run(self._conn.describe_secret(name)) + @override def list_jobs(self) -> List[JobInfo]: """List server-side jobs across the database's tables.""" @@ -2265,18 +2380,23 @@ class AsyncConnection(object): return AsyncJob(await self._inner.open_job(job_id)) async def create_function_async( - self, definition: UdfDefinition + self, + definition: UdfDefinition, + *, + secrets: Optional[Sequence[EnvVarSecret]] = None, ) -> AsyncJob[FunctionVersion]: """Register a scalar Python UDF through the remote Function catalog. The returned typed job resolves to the immutable Function version. - Local connections raise ``NotImplementedError``. + ``secrets`` is a sequence of + [EnvVarSecret][lancedb.secrets.EnvVarSecret], each naming a Secret and + the environment variable its value arrives in. Local connections raise + ``NotImplementedError``. """ if not isinstance(definition, UdfDefinition): raise TypeError("create_function_async requires a @udf definition") - inner = await self._inner.create_function_async( - definition.registration_request.to_canonical_json() - ) + request = definition.bind_secrets(secrets) + inner = await self._inner.create_function_async(request.to_canonical_json()) return _typed_job(inner, FunctionVersion.from_json) async def get_function(self, name: str, *, version: str) -> FunctionVersion: @@ -2298,6 +2418,36 @@ class AsyncConnection(object): """Drop one exact immutable Function version from the remote catalog.""" return await self._inner.drop_function(name, version) + async def create_secret(self, name: str, value: str) -> None: + """Create a named Secret in this database. + + Fails if the name is taken, so a create never silently becomes a + rotation. Nothing reads the value back. + """ + await self._inner.create_secret(validate_secret_name(name), value) + + async def alter_secret(self, name: str, value: str) -> None: + """Replace the credential behind an existing Secret. + + Fails if it does not exist. Bound Functions use the new value from + their next job, with no new Function version. + """ + await self._inner.alter_secret(validate_secret_name(name), value) + + async def list_secrets(self) -> List[str]: + """The names of every Secret in this database. Names only.""" + return await self._inner.list_secrets() + + async def drop_secret(self, name: str) -> None: + """Drop a Secret. Bound Functions fail at their next job.""" + await self._inner.drop_secret(validate_secret_name(name)) + + async def describe_secret(self, name: str) -> SecretInfo: + """What this database records about a Secret. Never the value.""" + return SecretInfo.from_json( + await self._inner.describe_secret(validate_secret_name(name)) + ) + async def list_jobs(self) -> List[JobInfo]: """List server-side jobs across the database's tables.""" return await self._inner.list_jobs() diff --git a/python/python/lancedb/functions.py b/python/python/lancedb/functions.py index d3fa6da81..77316dff2 100644 --- a/python/python/lancedb/functions.py +++ b/python/python/lancedb/functions.py @@ -4,7 +4,7 @@ """Canonical Function values exchanged with LanceDB Enterprise services. These immutable models contain client/wire state only. Catalog persistence, -environment bake, and execution are owned by Sophon. +environment bake, secret resolution, and execution are owned by Sophon. ``RefreshColumnResult`` is also the backend-neutral result of a local expression-backed refresh job. """ @@ -25,7 +25,7 @@ import re import sys import textwrap import types -from collections.abc import Mapping +from collections.abc import Mapping, Sequence from datetime import date, datetime from typing import ( Annotated, @@ -50,6 +50,7 @@ from pydantic import ( ) from .schema import is_blob_v2_field as _is_blob_v2_field +from .secrets import EnvVarSecret _Int32 = conint(strict=True, ge=-(2**31), le=2**31 - 1) _UInt32 = conint(strict=True, ge=0, le=2**32 - 1) @@ -309,6 +310,7 @@ class FunctionVersion(_RemoteValue): runtime: PythonRuntimeSpec runtime_digest: str environment_digest: str + secret_bindings: Mapping[str, str] = {} created_at: str def __call__(self, **inputs: Any) -> FunctionApplication: @@ -370,12 +372,18 @@ class FunctionVersion(_RemoteValue): class FunctionRegistrationRequest(_RemoteValue): - """Stable remote registration envelope produced by :func:`udf`.""" + """Stable remote registration envelope produced by :func:`udf`. + + Credential values deliberately have no field here. The only secret-shaped + thing a client sends is ``secret_bindings``: the name of a Secret the + database already holds, which the remote service resolves at execution. + """ name: str artifact: FunctionArtifactRequest signature: FunctionSignature runtime: PythonRuntimeSpec + secret_bindings: Mapping[str, str] = {} class FunctionVersionRef(_OpenRemoteValue): @@ -524,6 +532,14 @@ class RefreshColumnResult(_RemoteValue): _FUNCTION_NAME = re.compile(r"^[A-Za-z_][A-Za-z0-9_.-]*$") +_DECLARED_SECRET = re.compile(r"^[A-Za-z_][A-Za-z0-9_]*$") + +MAX_FUNCTION_SECRET_BINDINGS = 16 +"""A Function binds at most this many Secrets. + +Each bound Secret is one extra read on the launch path of every fragment, so +the count needs a bound for the same reason a credential needs a size limit. +""" _FUNCTION_BLOB_V2_TYPE = "blob_v2" _ARROW_EXTENSION_NAME_KEY = "ARROW:extension:name" _BLOB_V2_EXTENSION_NAME = "lance.blob.v2" @@ -1265,9 +1281,61 @@ class UdfDefinition: @property def registration_request(self) -> FunctionRegistrationRequest: - """The immutable request sent by ``create_function_async``.""" + """The immutable request sent by ``create_function_async``. + + Carries no secret bindings. Binding is a registration-time decision, + so a Function bound to Secrets is registered through :meth:`bind_secrets`, + which is what ``create_function`` calls. + """ return self._request + def bind_secrets( + self, secrets: Optional[Sequence[EnvVarSecret]] + ) -> FunctionRegistrationRequest: + """The registration request for this definition bound to ``secrets``. + + Binding does not change the Function's source: each + [EnvVarSecret][lancedb.secrets.EnvVarSecret] names a Secret and the + environment variable its value should arrive in, and the Function reads + that variable the way it already did. Whether the named Secrets exist is + the server's answer, not this one. + """ + bindings = () if secrets is None else tuple(secrets) + wrong_type = [ + binding for binding in bindings if not isinstance(binding, EnvVarSecret) + ] + if wrong_type: + kinds = sorted({type(binding).__name__ for binding in wrong_type}) + raise TypeError( + f"Function secrets must be EnvVarSecret values, not {kinds!r}; a " + "credential value is never sent to this API" + ) + if len(bindings) > MAX_FUNCTION_SECRET_BINDINGS: + raise ValueError( + f"a Function binds at most {MAX_FUNCTION_SECRET_BINDINGS} secrets, " + f"not {len(bindings)}" + ) + variables = [binding.env_variable for binding in bindings] + duplicates = sorted({name for name in variables if variables.count(name) > 1}) + if duplicates: + raise ValueError( + "a Function binds each environment variable once; duplicated: " + f"{duplicates!r}" + ) + # `env` is ordinary configuration carried in the definition, so a name in + # both would have a value visible in the Function's record and a value + # that is not. Refuse rather than pick. + environment = self._request.runtime.env or {} + overlap = sorted(set(environment) & set(variables)) + if overlap: + raise ValueError( + f"Function env and secret bindings must be disjoint: {overlap!r}" + ) + if not bindings: + return self._request + resolved = {binding.env_variable: binding.secret for binding in bindings} + return self._request._copy(update={"secret_bindings": resolved}) + def __call__(self, *args, **kwargs): return self._function(*args, **kwargs) @@ -1332,7 +1400,9 @@ def udf( conda_channels : sequence of str, optional Conda channels in priority order; requires ``conda``. env : mapping of str to str, optional - Environment variables included in the Function definition. + Environment variables included in the Function definition. Not for + credentials -- these are ordinary configuration, stored with the + Function and visible wherever it is. python_version : str, optional Remote Python major/minor version. Defaults to the client version. gpu : bool, default False diff --git a/python/python/lancedb/remote/db.py b/python/python/lancedb/remote/db.py index 5b6828b04..83e9aacb1 100644 --- a/python/python/lancedb/remote/db.py +++ b/python/python/lancedb/remote/db.py @@ -7,7 +7,16 @@ import json import logging from concurrent.futures import ThreadPoolExecutor import sys -from typing import TYPE_CHECKING, Any, Dict, Iterable, List, Optional, Union +from typing import ( + TYPE_CHECKING, + Any, + Dict, + Iterable, + List, + Optional, + Sequence, + Union, +) from urllib.parse import urlparse from uuid import UUID import warnings @@ -29,6 +38,7 @@ from ..job import AsyncJob, Job from ..sql import Query as SqlQuery from ..sql import QueryDescription from ..materialized_view import MaterializedView, SelectArg +from ..secrets import EnvVarSecret, SecretInfo if TYPE_CHECKING: from .._lancedb import JobInfo @@ -746,8 +756,14 @@ class RemoteDBConnection(DBConnection): return Job(LOOP.run(self._conn.open_job(job_id))) @override - def create_function_async(self, definition: UdfDefinition) -> Job[FunctionVersion]: - return Job(LOOP.run(self._conn.create_function_async(definition))) + def create_function_async( + self, + definition: UdfDefinition, + *, + secrets: Optional[Sequence[EnvVarSecret]] = None, + ) -> Job[FunctionVersion]: + job = LOOP.run(self._conn.create_function_async(definition, secrets=secrets)) + return Job(job) @override def get_function(self, name: str, *, version: str) -> FunctionVersion: @@ -761,6 +777,26 @@ class RemoteDBConnection(DBConnection): def drop_function(self, name: str, *, version: str) -> bool: return LOOP.run(self._conn.drop_function(name, version=version)) + @override + def create_secret(self, name: str, value: str) -> None: + LOOP.run(self._conn.create_secret(name, value)) + + @override + def alter_secret(self, name: str, value: str) -> None: + LOOP.run(self._conn.alter_secret(name, value)) + + @override + def describe_secret(self, name: str) -> SecretInfo: + return LOOP.run(self._conn.describe_secret(name)) + + @override + def list_secrets(self) -> List[str]: + return LOOP.run(self._conn.list_secrets()) + + @override + def drop_secret(self, name: str) -> None: + LOOP.run(self._conn.drop_secret(name)) + @override def list_jobs(self) -> List["JobInfo"]: """List server-side jobs across the database's tables.""" diff --git a/python/python/lancedb/secrets.py b/python/python/lancedb/secrets.py new file mode 100644 index 000000000..b16f32314 --- /dev/null +++ b/python/python/lancedb/secrets.py @@ -0,0 +1,165 @@ +# SPDX-License-Identifier: Apache-2.0 +# SPDX-FileCopyrightText: Copyright The LanceDB Authors + +"""Named Secrets, and the bindings that deliver them to Functions. + +A Secret is a database-scoped named credential. Nothing in this module holds a +value: :class:`EnvVarSecret` names one and says which environment variable it +should arrive in, and the value is resolved by the remote service when a +Function bound to it runs. No API returns a stored credential, by construction +rather than by policy -- there is no code path that could. +""" + +from __future__ import annotations + +import re + +_SECRET_NAME = re.compile(r"^[A-Za-z0-9_-]{1,255}$") +_ENV_VARIABLE = re.compile(r"^[A-Za-z_][A-Za-z0-9_]*$") + + +def validate_secret_name(name: str) -> str: + """Check a Secret name locally and return it unchanged.""" + if not isinstance(name, str): + raise TypeError(f"Secret name must be a string, not {type(name).__name__}") + if not _SECRET_NAME.fullmatch(name): + raise ValueError(f"invalid Secret name: {name!r}") + return name + + +def validate_env_variable(name: str) -> str: + """Check an environment variable name locally and return it unchanged.""" + if not isinstance(name, str): + raise TypeError( + f"environment variable name must be a string, not {type(name).__name__}" + ) + if not _ENV_VARIABLE.fullmatch(name): + raise ValueError(f"invalid environment variable name: {name!r}") + return name + + +class EnvVarSecret: + """A Secret bound to the environment variable a Function's library reads. + + Pass these in the ``secrets`` sequence of + [DBConnection.create_function][lancedb.db.DBConnection.create_function]. The + Function's source is unchanged by binding: it reads ``OPENAI_API_KEY`` the + way it always did, and the binding is what puts a value there. + + This is a local value. Constructing it contacts no server, so it always + succeeds and says nothing about whether the Secret exists; that is checked + at registration, where a mistyped Secret name surfaces as a clear "does not + exist" naming both the Secret and the variable bound to it. A mistyped + *variable* name cannot be caught anywhere -- nothing knows which variables a + Function reads -- so it surfaces on the first rows instead. + + The type exists so a credential cannot be passed by accident. A bare string + in the same position is a plausible-looking mistake with the opposite + meaning, and it reads identically in a diff. + + Parameters + ---------- + secret : str + The Secret's database-scoped name. + env_variable : str + The environment variable the Function reads it from. + + Examples + -------- + >>> from lancedb import EnvVarSecret + >>> binding = EnvVarSecret(secret="openai-prod", env_variable="OPENAI_API_KEY") + >>> binding.secret, binding.env_variable + ('openai-prod', 'OPENAI_API_KEY') + """ + + __slots__ = ("_secret", "_env_variable") + + def __init__(self, secret: str, env_variable: str): + self._secret = validate_secret_name(secret) + self._env_variable = validate_env_variable(env_variable) + + @property + def secret(self) -> str: + """The Secret's database-scoped name.""" + return self._secret + + @property + def env_variable(self) -> str: + """The environment variable the value is delivered in.""" + return self._env_variable + + def __repr__(self) -> str: + return ( + f"EnvVarSecret(secret={self._secret!r}, " + f"env_variable={self._env_variable!r})" + ) + + def __eq__(self, other: object) -> bool: + return ( + isinstance(other, EnvVarSecret) + and other._secret == self._secret + and other._env_variable == self._env_variable + ) + + def __hash__(self) -> int: + return hash((EnvVarSecret, self._secret, self._env_variable)) + + +class SecretInfo: + """What a database records about a Secret. Never its value. + + Returned by + [DBConnection.describe_secret][lancedb.db.DBConnection.describe_secret]. + """ + + __slots__ = ("_name", "_created_at", "_updated_at") + + def __init__(self, name: str, created_at: str, updated_at: str): + self._name = name + self._created_at = created_at + self._updated_at = updated_at + + @property + def name(self) -> str: + """The Secret's database-scoped name.""" + return self._name + + @property + def created_at(self) -> str: + """When the Secret was created, as an RFC 3339 timestamp.""" + return self._created_at + + @property + def updated_at(self) -> str: + """When the Secret's value was last rotated, as an RFC 3339 timestamp.""" + return self._updated_at + + @classmethod + def from_json(cls, value: dict) -> "SecretInfo": + return cls( + name=value["name"], + created_at=value["created_at"], + updated_at=value["updated_at"], + ) + + def __repr__(self) -> str: + return ( + f"SecretInfo(name={self._name!r}, created_at={self._created_at!r}, " + f"updated_at={self._updated_at!r})" + ) + + def __eq__(self, other: object) -> bool: + return ( + isinstance(other, SecretInfo) + and other._name == self._name + and other._created_at == self._created_at + and other._updated_at == self._updated_at + ) + + +__all__ = [ + "EnvVarSecret", + "SecretInfo", + "validate_env_variable", + "validate_secret_name", +] diff --git a/python/python/tests/test_first_class_function_slice1.py b/python/python/tests/test_first_class_function_slice1.py index 89172ba3f..ba1964e6c 100644 --- a/python/python/tests/test_first_class_function_slice1.py +++ b/python/python/tests/test_first_class_function_slice1.py @@ -37,6 +37,22 @@ def job_result(name: str) -> dict: return json.loads(fixture(name))["result"] +def assert_no_secret_values(value): + """No client value models a resolved credential, at any nesting depth.""" + 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() @@ -94,6 +110,7 @@ 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 dict(version.secret_bindings) == {"HF_TOKEN": "hf-prod"} with pytest.raises((TypeError, ValueError)): version.version = "fv_changed" @@ -276,6 +293,25 @@ def test_refresh_result_rejects_non_u64_values(field): RefreshColumnResult.from_json(json.dumps(value)) +def test_canonical_client_values_carry_bindings_and_no_credentials(): + """A binding names a Secret; the credential behind it has no client field.""" + version = FunctionVersion.from_json( + json.dumps(job_result("remote_function_job.json")) + ) + canonical = json.loads(version.to_canonical_json()) + assert canonical["secret_bindings"] == {"HF_TOKEN": "hf-prod"} + assert_no_secret_values(canonical) + + +def test_a_version_without_bindings_keeps_the_original_wire_shape(): + """Every Function registered before Secrets existed serializes unchanged.""" + value = job_result("remote_function_job.json") + del value["secret_bindings"] + version = FunctionVersion.from_json(json.dumps(value)) + assert dict(version.secret_bindings) == {} + assert "secret_bindings" not in json.loads(version.to_canonical_json()) + + class _FunctionDeclarationInner: def __init__(self): self.calls = [] diff --git a/python/python/tests/test_first_class_function_slice2.py b/python/python/tests/test_first_class_function_slice2.py index 4816019d6..4499769a2 100644 --- a/python/python/tests/test_first_class_function_slice2.py +++ b/python/python/tests/test_first_class_function_slice2.py @@ -28,6 +28,7 @@ from lancedb.functions import ( _GRAMMAR_PRIMITIVES, udf, ) +from lancedb.secrets import EnvVarSecret THRESHOLD = 20 _CACHE = None @@ -53,6 +54,15 @@ def normalize_score(value: float) -> float: return value / 100.0 +@udf( + pip=["openai==3.7.0"], + env={"MODE": "test"}, + python_version="3.12", +) +def analyze_caption(caption: str) -> str: + return caption.strip() + + def test_scalar_udf_matches_shared_registration_golden_and_remains_callable(): assert isinstance(normalize_score, UdfDefinition) assert normalize_score(25.0) == 0.25 @@ -69,6 +79,98 @@ def test_scalar_udf_matches_shared_registration_golden_and_remains_callable(): } +def test_secret_bound_udf_matches_its_shared_registration_golden(): + assert analyze_caption(" hello ") == "hello" + bound = analyze_caption.bind_secrets( + [EnvVarSecret(secret="openai-prod", env_variable="OPENAI_API_KEY")] + ) + assert ( + bound.to_canonical_json() + == (FIXTURES / "remote_function_secret_registration_request.canonical.json") + .read_text() + .strip() + ) + + +def test_an_unbound_request_carries_no_binding_at_all(): + """Binding is a registration-time decision, so the definition holds none. + + The decorator declares nothing about secrets, which is what makes the PRD's + claim true: a Function's source and its registration request are identical + whether or not a credential is later bound to it. + """ + unbound = json.loads(analyze_caption.registration_request.to_canonical_json()) + assert "secret_bindings" not in unbound + assert "OPENAI_API_KEY" not in json.dumps(unbound) + + +def test_binding_a_secret_leaves_the_packaged_artifact_untouched(): + """The artifact is source bytes and nothing else, with or without secrets.""" + bound = analyze_caption.bind_secrets( + [EnvVarSecret(secret="openai-prod", env_variable="OPENAI_API_KEY")] + ) + assert bound.artifact == analyze_caption.registration_request.artifact + assert bound.artifact.digest == analyze_caption.registration_request.artifact.digest + + +def test_a_function_declaring_no_secret_is_registered_exactly_as_before(): + """The compatibility claim: nothing about the no-secret path moves.""" + assert ( + normalize_score.bind_secrets(None).to_canonical_json() + == normalize_score.registration_request.to_canonical_json() + ) + assert ( + "secret_bindings" + not in normalize_score.registration_request.to_canonical_json() + ) + + +def test_a_function_binds_each_variable_once(): + with pytest.raises(ValueError, match="binds each environment variable once"): + analyze_caption.bind_secrets( + [ + EnvVarSecret(secret="openai-prod", env_variable="OPENAI_API_KEY"), + EnvVarSecret(secret="openai-staging", env_variable="OPENAI_API_KEY"), + ] + ) + + +def test_bindings_may_not_collide_with_plain_configuration(): + """`env` is stored with the Function; a Secret is not. Refuse, do not pick.""" + with pytest.raises(ValueError, match="must be disjoint"): + analyze_caption.bind_secrets( + [EnvVarSecret(secret="mode-prod", env_variable="MODE")] + ) + + +def test_a_function_binds_at_most_sixteen_secrets(): + bindings = [ + EnvVarSecret(secret=f"secret-{index}", env_variable=f"TOKEN_{index}") + for index in range(17) + ] + with pytest.raises(ValueError, match="at most 16 secrets"): + normalize_score.bind_secrets(bindings) + + +def test_a_credential_value_is_rejected_in_the_binding_position(): + """The one mistake the typed binding exists to stop.""" + with pytest.raises(TypeError, match="EnvVarSecret"): + analyze_caption.bind_secrets(["sk-live-0001"]) + + +@pytest.mark.parametrize( + ("secret", "variable", "message"), + [ + ("openai-prod", "not-a-var", "invalid environment variable name"), + ("openai-prod", "API-TOKEN", "invalid environment variable name"), + ("not a name", "API_TOKEN", "invalid Secret name"), + ], +) +def test_a_binding_validates_both_names_locally(secret, variable, message): + with pytest.raises(ValueError, match=message): + EnvVarSecret(secret=secret, env_variable=variable) + + def _main_udf_source( *, threshold: int = 20, input_annotation: str = "int", comparison: str = ">=" ) -> str: @@ -1230,6 +1332,7 @@ def _mock_remote_function_catalog(): "runtime": body["runtime"], "runtime_digest": "sha256:runtime", "environment_digest": "sha256:environment", + "secret_bindings": body.get("secret_bindings", {}), "created_at": "2026-08-21T00:00:00Z", } response = {"job_id": "job-register"} @@ -1270,6 +1373,21 @@ def _mock_remote_function_catalog(): "version": "fv_exact", } response = {"dropped": True} + elif self.path in ("/v1/secrets/create", "/v1/secrets/alter"): + assert set(body) == {"name", "value"} + response = {} + elif self.path == "/v1/secrets/list": + if "page_token" not in body: + response = { + "secrets": [{"name": "openai-prod"}], + "page_token": "next", + } + else: + assert body["page_token"] == "next" + response = {"secrets": [{"name": "hf-prod"}]} + elif self.path == "/v1/secrets/drop": + assert body == {"name": "openai-prod"} + response = {} else: status = 404 response = {"error": "not found"} @@ -1312,6 +1430,71 @@ def test_remote_registration_job_and_exact_version_reopen_round_trip(): ) +def test_remote_registration_sends_bindings_and_never_a_credential(): + with _mock_remote_function_catalog() as (host, state): + db = lancedb.connect( + "db://dev", + api_key="fake", + host_override=host, + client_config={"retry_config": {"retries": 0}}, + ) + created = db.create_function( + analyze_caption, + secrets=[EnvVarSecret(secret="openai-prod", env_variable="OPENAI_API_KEY")], + ) + + assert dict(created.secret_bindings) == {"OPENAI_API_KEY": "openai-prod"} + path, create_request = state["requests"][0] + assert path == "/v1/functions/create" + assert create_request["secret_bindings"] == {"OPENAI_API_KEY": "openai-prod"} + # The request names a Secret and carries nothing that could be one. + assert create_request == json.loads( + analyze_caption.bind_secrets( + [EnvVarSecret(secret="openai-prod", env_variable="OPENAI_API_KEY")] + ).to_canonical_json() + ) + + +def test_remote_secret_verbs_round_trip(): + with _mock_remote_function_catalog() as (host, state): + db = lancedb.connect( + "db://dev", + api_key="fake", + host_override=host, + client_config={"retry_config": {"retries": 0}}, + ) + assert db.create_secret("openai-prod", "sk-live-0001") is None + assert db.alter_secret("openai-prod", "sk-live-0002") is None + assert db.list_secrets() == ["openai-prod", "hf-prod"] + assert db.drop_secret("openai-prod") is None + + routes = [path for path, _ in state["requests"]] + assert routes == [ + "/v1/secrets/create", + "/v1/secrets/alter", + "/v1/secrets/list", + "/v1/secrets/list", + "/v1/secrets/drop", + ] + assert state["requests"][0][1] == {"name": "openai-prod", "value": "sk-live-0001"} + # The listing returns names, and the client has no way to ask for more. + assert state["requests"][2][1] == {} + + +def test_building_a_binding_contacts_no_server(): + """A binding is a local value: it says nothing about whether the Secret exists. + + Existence is the server's answer at registration, where a mistyped name is a + clear error rather than a client-side check that was already stale. + """ + with _mock_remote_function_catalog() as (_host, state): + binding = EnvVarSecret(secret="openai-prod", env_variable="OPENAI_API_KEY") + assert binding.secret == "openai-prod" + assert binding.env_variable == "OPENAI_API_KEY" + + assert state["requests"] == [] + + def test_blocking_remote_registration_returns_function_version(): with _mock_remote_function_catalog() as (host, state): db = lancedb.connect( diff --git a/python/src/connection.rs b/python/src/connection.rs index 2d613966a..fdb3a2429 100644 --- a/python/src/connection.rs +++ b/python/src/connection.rs @@ -704,6 +704,56 @@ impl Connection { }) } + pub fn create_secret( + self_: PyRef<'_, Self>, + name: String, + value: String, + ) -> PyResult> { + let inner = self_.get_inner()?.clone(); + future_into_py(self_.py(), async move { + inner.create_secret(name, value).await.infer_error() + }) + } + + pub fn alter_secret( + self_: PyRef<'_, Self>, + name: String, + value: String, + ) -> PyResult> { + let inner = self_.get_inner()?.clone(); + future_into_py(self_.py(), async move { + inner.alter_secret(name, value).await.infer_error() + }) + } + + pub fn list_secrets(self_: PyRef<'_, Self>) -> PyResult> { + let inner = self_.get_inner()?.clone(); + future_into_py(self_.py(), async move { + inner.list_secrets().await.infer_error() + }) + } + + pub fn drop_secret(self_: PyRef<'_, Self>, name: String) -> PyResult> { + let inner = self_.get_inner()?.clone(); + future_into_py(self_.py(), async move { + inner.drop_secret(name).await.infer_error() + }) + } + + /// Name and timestamps as a plain mapping. `SecretInfo` carries no value, + /// so there is none to filter out here. + pub fn describe_secret(self_: PyRef<'_, Self>, name: String) -> PyResult> { + let inner = self_.get_inner()?.clone(); + future_into_py(self_.py(), async move { + let info = inner.describe_secret(name).await.infer_error()?; + Ok(HashMap::from([ + ("name".to_string(), info.name), + ("created_at".to_string(), info.created_at), + ("updated_at".to_string(), info.updated_at), + ])) + }) + } + pub fn list_jobs(self_: PyRef<'_, Self>) -> PyResult> { let inner = self_.get_inner()?.clone(); future_into_py(self_.py(), async move { diff --git a/python/uv.lock b/python/uv.lock index c957a4c06..6ea4af9ec 100644 --- a/python/uv.lock +++ b/python/uv.lock @@ -10,6 +10,9 @@ resolution-markers = [ "python_full_version < '3.11'", ] +[options] +prerelease-mode = "allow" + [[package]] name = "accelerate" version = "1.14.0" @@ -799,7 +802,7 @@ name = "cuda-bindings" version = "13.3.1" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "cuda-pathfinder", marker = "(python_full_version < '3.14' and sys_platform == 'emscripten') or (python_full_version < '3.14' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" }, + { name = "cuda-pathfinder" }, ] wheels = [ { url = "https://files.pythonhosted.org/packages/a9/21/8464d133752951c154feafb3b65c297e7d80f301183d220bec4c830f1441/cuda_bindings-13.3.1-cp310-cp310-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:120fcc53d57903df529c3486962c56528cba5b7d6c57c99537320ed9922c8b86", size = 6073403, upload-time = "2026-05-29T23:11:36.22Z" }, @@ -834,37 +837,37 @@ wheels = [ [package.optional-dependencies] cublas = [ - { name = "nvidia-cublas", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" }, + { name = "nvidia-cublas" }, ] cudart = [ - { name = "nvidia-cuda-runtime", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" }, + { name = "nvidia-cuda-runtime" }, ] cufft = [ - { name = "nvidia-cufft", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" }, + { name = "nvidia-cufft" }, ] cufile = [ - { name = "nvidia-cufile", marker = "sys_platform == 'linux'" }, + { name = "nvidia-cufile" }, ] cupti = [ - { name = "nvidia-cuda-cupti", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" }, + { name = "nvidia-cuda-cupti" }, ] curand = [ - { name = "nvidia-curand", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" }, + { name = "nvidia-curand" }, ] cusolver = [ - { name = "nvidia-cusolver", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" }, + { name = "nvidia-cusolver" }, ] cusparse = [ - { name = "nvidia-cusparse", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" }, + { name = "nvidia-cusparse" }, ] nvjitlink = [ - { name = "nvidia-nvjitlink", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" }, + { name = "nvidia-nvjitlink" }, ] nvrtc = [ - { name = "nvidia-cuda-nvrtc", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" }, + { name = "nvidia-cuda-nvrtc" }, ] nvtx = [ - { name = "nvidia-nvtx", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" }, + { name = "nvidia-nvtx" }, ] [[package]] @@ -1023,7 +1026,7 @@ name = "exceptiongroup" version = "1.3.1" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "typing-extensions", marker = "python_full_version < '3.11'" }, + { name = "typing-extensions" }, ] sdist = { url = "https://files.pythonhosted.org/packages/50/79/66800aadf48771f6b62f7eb014e352e5d06856655206165d775e675a02c9/exceptiongroup-1.3.1.tar.gz", hash = "sha256:8b412432c6055b0b7d14c310000ae93352ed6754f70fa8f7c34141f91c4e3219", size = 30371, upload-time = "2025-11-21T23:01:54.787Z" } wheels = [ @@ -1440,16 +1443,16 @@ resolution-markers = [ "python_full_version < '3.11'", ] dependencies = [ - { name = "cachetools", marker = "python_full_version < '3.11'" }, - { name = "certifi", marker = "python_full_version < '3.11'" }, - { name = "httpx", marker = "python_full_version < '3.11'" }, - { name = "ibm-cos-sdk", marker = "python_full_version < '3.11'" }, - { name = "lomond", marker = "python_full_version < '3.11'" }, - { name = "packaging", marker = "python_full_version < '3.11'" }, - { name = "pandas", version = "2.2.3", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" }, - { name = "requests", marker = "python_full_version < '3.11'" }, - { name = "tabulate", marker = "python_full_version < '3.11'" }, - { name = "urllib3", marker = "python_full_version < '3.11'" }, + { name = "cachetools" }, + { name = "certifi" }, + { name = "httpx" }, + { name = "ibm-cos-sdk" }, + { name = "lomond" }, + { name = "packaging" }, + { name = "pandas", version = "2.2.3", source = { registry = "https://pypi.org/simple" } }, + { name = "requests" }, + { name = "tabulate" }, + { name = "urllib3" }, ] sdist = { url = "https://files.pythonhosted.org/packages/c7/56/2e3df38a1f13062095d7bde23c87a92f3898982993a15186b1bfecbd206f/ibm_watsonx_ai-1.3.42.tar.gz", hash = "sha256:ee5be59009004245d957ce97d1227355516df95a2640189749487614fef674ff", size = 688651, upload-time = "2025-10-01T13:35:41.527Z" } wheels = [ @@ -1468,17 +1471,17 @@ resolution-markers = [ "python_full_version == '3.11.*'", ] dependencies = [ - { name = "cachetools", marker = "python_full_version >= '3.11'" }, - { name = "certifi", marker = "python_full_version >= '3.11'" }, - { name = "httpx", marker = "python_full_version >= '3.11'" }, - { name = "ibm-cos-sdk", marker = "python_full_version >= '3.11'" }, - { name = "lomond", marker = "python_full_version >= '3.11'" }, - { name = "packaging", marker = "python_full_version >= '3.11'" }, - { name = "pandas", version = "2.3.3", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.11' and python_full_version < '3.14'" }, + { name = "cachetools" }, + { name = "certifi" }, + { name = "httpx" }, + { name = "ibm-cos-sdk" }, + { name = "lomond" }, + { name = "packaging" }, + { name = "pandas", version = "2.3.3", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.14'" }, { name = "pandas", version = "3.0.3", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.14'" }, - { name = "requests", marker = "python_full_version >= '3.11'" }, - { name = "tabulate", marker = "python_full_version >= '3.11'" }, - { name = "urllib3", marker = "python_full_version >= '3.11'" }, + { name = "requests" }, + { name = "tabulate" }, + { name = "urllib3" }, ] sdist = { url = "https://files.pythonhosted.org/packages/29/a3/c756b534696ab2f3f29882fdb7ca7198b7a5c94e10c0a3a327853d6d6b79/ibm_watsonx_ai-1.5.14.tar.gz", hash = "sha256:a756488bd57e87c0fc51be42dcba871143cfe0ac1e805c497c5047e1e4f13e9d", size = 735804, upload-time = "2026-06-22T12:32:43.85Z" } wheels = [ @@ -1554,17 +1557,17 @@ resolution-markers = [ "python_full_version < '3.11'", ] dependencies = [ - { name = "colorama", marker = "python_full_version < '3.11' and sys_platform == 'win32'" }, - { name = "decorator", marker = "python_full_version < '3.11'" }, - { name = "exceptiongroup", marker = "python_full_version < '3.11'" }, - { name = "jedi", marker = "python_full_version < '3.11'" }, - { name = "matplotlib-inline", marker = "python_full_version < '3.11'" }, - { name = "pexpect", marker = "python_full_version < '3.11' and sys_platform != 'emscripten' and sys_platform != 'win32'" }, - { name = "prompt-toolkit", marker = "python_full_version < '3.11'" }, - { name = "pygments", marker = "python_full_version < '3.11'" }, - { name = "stack-data", marker = "python_full_version < '3.11'" }, - { name = "traitlets", marker = "python_full_version < '3.11'" }, - { name = "typing-extensions", marker = "python_full_version < '3.11'" }, + { name = "colorama", marker = "sys_platform == 'win32'" }, + { name = "decorator" }, + { name = "exceptiongroup" }, + { name = "jedi" }, + { name = "matplotlib-inline" }, + { name = "pexpect", marker = "sys_platform != 'emscripten' and sys_platform != 'win32'" }, + { name = "prompt-toolkit" }, + { name = "pygments" }, + { name = "stack-data" }, + { name = "traitlets" }, + { name = "typing-extensions" }, ] sdist = { url = "https://files.pythonhosted.org/packages/40/18/f8598d287006885e7136451fdea0755af4ebcbfe342836f24deefaed1164/ipython-8.39.0.tar.gz", hash = "sha256:4110ae96012c379b8b6db898a07e186c40a2a1ef5d57a7fa83166047d9da7624", size = 5513971, upload-time = "2026-03-27T10:02:13.94Z" } wheels = [ @@ -1583,18 +1586,18 @@ resolution-markers = [ "python_full_version == '3.11.*'", ] dependencies = [ - { name = "colorama", marker = "python_full_version >= '3.11' and sys_platform == 'win32'" }, - { name = "decorator", marker = "python_full_version >= '3.11'" }, - { name = "ipython-pygments-lexers", marker = "python_full_version >= '3.11'" }, - { name = "jedi", marker = "python_full_version >= '3.11'" }, - { name = "matplotlib-inline", marker = "python_full_version >= '3.11'" }, - { name = "pexpect", marker = "python_full_version >= '3.11' and sys_platform != 'emscripten' and sys_platform != 'win32'" }, - { name = "prompt-toolkit", marker = "python_full_version >= '3.11'" }, - { name = "psutil", marker = "python_full_version >= '3.11' and sys_platform != 'cygwin' and sys_platform != 'emscripten'" }, - { name = "pygments", marker = "python_full_version >= '3.11'" }, - { name = "stack-data", marker = "python_full_version >= '3.11'" }, - { name = "traitlets", marker = "python_full_version >= '3.11'" }, - { name = "typing-extensions", marker = "python_full_version == '3.11.*'" }, + { name = "colorama", marker = "sys_platform == 'win32'" }, + { name = "decorator" }, + { name = "ipython-pygments-lexers" }, + { name = "jedi" }, + { name = "matplotlib-inline" }, + { name = "pexpect", marker = "sys_platform != 'emscripten' and sys_platform != 'win32'" }, + { name = "prompt-toolkit" }, + { name = "psutil", marker = "sys_platform != 'cygwin' and sys_platform != 'emscripten'" }, + { name = "pygments" }, + { name = "stack-data" }, + { name = "traitlets" }, + { name = "typing-extensions", marker = "python_full_version < '3.12'" }, ] sdist = { url = "https://files.pythonhosted.org/packages/53/59/165d3b4d75cc34add3122c4417ecb229085140ac573103c223cd01dde96f/ipython-9.15.0.tar.gz", hash = "sha256:da2819ce2aa83135257df830660b1176d986c3d2876db24df01974fa955b2756", size = 4442580, upload-time = "2026-06-26T11:03:35.913Z" } wheels = [ @@ -1606,7 +1609,7 @@ name = "ipython-pygments-lexers" version = "1.1.1" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "pygments", marker = "python_full_version >= '3.11'" }, + { name = "pygments" }, ] sdist = { url = "https://files.pythonhosted.org/packages/ef/4c/5dd1d8af08107f88c7f741ead7a40854b8ac24ddf9ae850afbcf698aa552/ipython_pygments_lexers-1.1.1.tar.gz", hash = "sha256:09c0138009e56b6854f9535736f4171d855c8c08a563a0dcd8022f78355c7e81", size = 8393, upload-time = "2025-01-17T11:24:34.505Z" } wheels = [ @@ -2858,7 +2861,7 @@ name = "nvidia-cudnn-cu13" version = "9.19.0.56" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "nvidia-cublas", marker = "(python_full_version < '3.14' and sys_platform == 'emscripten') or (python_full_version < '3.14' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" }, + { name = "nvidia-cublas" }, ] wheels = [ { url = "https://files.pythonhosted.org/packages/f1/84/26025437c1e6b61a707442184fa0c03d083b661adf3a3eecfd6d21677740/nvidia_cudnn_cu13-9.19.0.56-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:6ed29ffaee1176c612daf442e4dd6cfeb6a0caa43ddcbeb59da94953030b1be4", size = 433781201, upload-time = "2026-02-03T20:40:53.805Z" }, @@ -2870,7 +2873,7 @@ name = "nvidia-cufft" version = "12.0.0.61" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "nvidia-nvjitlink", marker = "(python_full_version < '3.14' and sys_platform == 'emscripten') or (python_full_version < '3.14' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" }, + { name = "nvidia-nvjitlink" }, ] wheels = [ { url = "https://files.pythonhosted.org/packages/8b/ae/f417a75c0259e85c1d2f83ca4e960289a5f814ed0cea74d18c353d3e989d/nvidia_cufft-12.0.0.61-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:2708c852ef8cd89d1d2068bdbece0aa188813a0c934db3779b9b1faa8442e5f5", size = 214053554, upload-time = "2025-09-04T08:31:38.196Z" }, @@ -2900,9 +2903,9 @@ name = "nvidia-cusolver" version = "12.0.4.66" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "nvidia-cublas", marker = "(python_full_version < '3.14' and sys_platform == 'emscripten') or (python_full_version < '3.14' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" }, - { name = "nvidia-cusparse", marker = "(python_full_version < '3.14' and sys_platform == 'emscripten') or (python_full_version < '3.14' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" }, - { name = "nvidia-nvjitlink", marker = "(python_full_version < '3.14' and sys_platform == 'emscripten') or (python_full_version < '3.14' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" }, + { name = "nvidia-cublas" }, + { name = "nvidia-cusparse" }, + { name = "nvidia-nvjitlink" }, ] wheels = [ { url = "https://files.pythonhosted.org/packages/c8/c3/b30c9e935fc01e3da443ec0116ed1b2a009bb867f5324d3f2d7e533e776b/nvidia_cusolver-12.0.4.66-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:02c2457eaa9e39de20f880f4bd8820e6a1cfb9f9a34f820eb12a155aa5bc92d2", size = 223467760, upload-time = "2025-09-04T08:33:04.222Z" }, @@ -2914,7 +2917,7 @@ name = "nvidia-cusparse" version = "12.6.3.3" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "nvidia-nvjitlink", marker = "(python_full_version < '3.14' and sys_platform == 'emscripten') or (python_full_version < '3.14' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" }, + { name = "nvidia-nvjitlink" }, ] wheels = [ { url = "https://files.pythonhosted.org/packages/f8/94/5c26f33738ae35276672f12615a64bd008ed5be6d1ebcb23579285d960a9/nvidia_cusparse-12.6.3.3-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:80bcc4662f23f1054ee334a15c72b8940402975e0eab63178fc7e670aa59472c", size = 162155568, upload-time = "2025-09-04T08:33:42.864Z" }, @@ -3091,10 +3094,10 @@ resolution-markers = [ "python_full_version < '3.11'", ] dependencies = [ - { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" }, - { name = "python-dateutil", marker = "python_full_version < '3.11'" }, - { name = "pytz", marker = "python_full_version < '3.11'" }, - { name = "tzdata", marker = "python_full_version < '3.11'" }, + { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" } }, + { name = "python-dateutil" }, + { name = "pytz" }, + { name = "tzdata" }, ] sdist = { url = "https://files.pythonhosted.org/packages/9c/d6/9f8431bacc2e19dca897724cd097b1bb224a6ad5433784a44b587c7c13af/pandas-2.2.3.tar.gz", hash = "sha256:4f18ba62b61d7e192368b84517265a99b4d7ee8912f8708660fb4a366cc82667", size = 4399213, upload-time = "2024-09-20T13:10:04.827Z" } wheels = [ @@ -3143,11 +3146,11 @@ resolution-markers = [ "python_full_version == '3.11.*'", ] dependencies = [ - { name = "numpy", version = "2.4.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version == '3.11.*'" }, + { name = "numpy", version = "2.4.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.12' or python_full_version >= '3.14'" }, { name = "numpy", version = "2.5.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.12' and python_full_version < '3.14'" }, - { name = "python-dateutil", marker = "python_full_version >= '3.11' and python_full_version < '3.14'" }, - { name = "pytz", marker = "python_full_version >= '3.11' and python_full_version < '3.14'" }, - { name = "tzdata", marker = "python_full_version >= '3.11' and python_full_version < '3.14'" }, + { name = "python-dateutil" }, + { name = "pytz" }, + { name = "tzdata" }, ] sdist = { url = "https://files.pythonhosted.org/packages/33/01/d40b85317f86cf08d853a4f495195c73815fdf205eef3993821720274518/pandas-2.3.3.tar.gz", hash = "sha256:e05e1af93b977f7eafa636d043f9f94c7ee3ac81af99c13508215942e64c993b", size = 4495223, upload-time = "2025-09-29T23:34:51.853Z" } wheels = [ @@ -3210,9 +3213,9 @@ resolution-markers = [ "python_full_version >= '3.14' and sys_platform != 'emscripten' and sys_platform != 'win32'", ] dependencies = [ - { name = "numpy", version = "2.5.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.14'" }, - { name = "python-dateutil", marker = "python_full_version >= '3.14'" }, - { name = "tzdata", marker = "(python_full_version >= '3.14' and sys_platform == 'emscripten') or (python_full_version >= '3.14' and sys_platform == 'win32')" }, + { name = "numpy", version = "2.5.1", source = { registry = "https://pypi.org/simple" } }, + { name = "python-dateutil" }, + { name = "tzdata", marker = "sys_platform == 'emscripten' or sys_platform == 'win32'" }, ] sdist = { url = "https://files.pythonhosted.org/packages/f8/87/4341c6252d1c47b08768c3d25ac487362bf403f0313ddae4a2a26c9b1b4c/pandas-3.0.3.tar.gz", hash = "sha256:696a4a00a2a2a35d4e5deb3fc946641b96c944f02230e4f76137fe35d806c4fc", size = 4651414, upload-time = "2026-05-11T18:54:29.21Z" } wheels = [ @@ -3320,7 +3323,7 @@ name = "pexpect" version = "4.9.0" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "ptyprocess", marker = "(python_full_version < '3.14' and sys_platform == 'emscripten') or (python_full_version < '3.14' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" }, + { name = "ptyprocess" }, ] sdist = { url = "https://files.pythonhosted.org/packages/42/92/cc564bf6381ff43ce1f4d06852fc19a2f11d180f23dc32d9588bee2f149d/pexpect-4.9.0.tar.gz", hash = "sha256:ee7d41123f3c9911050ea2c2dac107568dc43b2d3b0c7557a33212c398ead30f", size = 166450, upload-time = "2023-11-25T09:07:26.339Z" } wheels = [ @@ -3912,8 +3915,8 @@ crypto = [ [[package]] name = "pylance" -version = "7.0.0" -source = { registry = "https://pypi.org/simple" } +version = "9.0.0rc1" +source = { registry = "https://pypi.fury.io/lance-format/" } dependencies = [ { name = "lance-namespace" }, { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" }, @@ -3922,12 +3925,12 @@ dependencies = [ { name = "pyarrow" }, ] wheels = [ - { url = "https://files.pythonhosted.org/packages/ac/ad/2f64921bf346e7075aef24a72595db44821724a3d89a9a92dd24e79632aa/pylance-7.0.0-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:98422021975be76e72b1572f41b8c9abb3bee5bdc9bfa5e9ce731110a65ed4d1", size = 62134146, upload-time = "2026-05-27T21:59:37.459Z" }, - { url = "https://files.pythonhosted.org/packages/73/1c/c5a01bee0160b55d9a98895cbd33091d038f0a0995b121ab72e629008d02/pylance-7.0.0-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4bec86ee5b6fbd8bfc493e653f0a1fba0303cfe5492b9b46fc25ab908edc7183", size = 65373684, upload-time = "2026-05-27T22:04:01.584Z" }, - { url = "https://files.pythonhosted.org/packages/eb/da/1fe8b8f7dbfe734d76af76acc994fc360a0d0c79a4874ef69f5a72a58fe3/pylance-7.0.0-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:881491432c53184e52f8d1db8d5f872f39a03f36fb104bec77b33d379519d8b5", size = 69458555, upload-time = "2026-05-27T22:16:50.567Z" }, - { url = "https://files.pythonhosted.org/packages/76/f0/dd505cf3fd0226ab9d94759acd713125af1d3bfacfd80bbd52e3b9f89509/pylance-7.0.0-cp39-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:18453999e7fff4f76b16d6b7882c9df0628bd142ff95e2461bd7dd5ee3fe0af3", size = 65394430, upload-time = "2026-05-27T22:05:30.923Z" }, - { url = "https://files.pythonhosted.org/packages/17/ba/2357b81034f28eb00790e258ed140289a6a887a7468ca9df6349fd186b27/pylance-7.0.0-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:04a58051d408c60fe76d41a220dcaf8fea8fb6d1aa0ca78a709b60bc3cc8d19a", size = 69473470, upload-time = "2026-05-27T22:17:18.935Z" }, - { url = "https://files.pythonhosted.org/packages/1f/ec/5c00b6303a67d787f9475141832cbdc513d674ac3dcaeef8a7b169905e65/pylance-7.0.0-cp39-abi3-win_amd64.whl", hash = "sha256:467d4864af047eaab4e1370e2f1e88e2c6f507c079874421116cb41d78bc3629", size = 74792863, upload-time = "2026-05-27T22:19:23.875Z" }, + { url = "https://pypi.fury.io/lance-format/-/ver_vEHBE/pylance-9.0.0rc1-cp310-abi3-macosx_11_0_arm64.whl", hash = "sha256:f0b6b02a1808bb3072ee7fe4e36614cae6f86302513e73ec7f55b2234a963b24" }, + { url = "https://pypi.fury.io/lance-format/-/ver_1Jipm4/pylance-9.0.0rc1-cp310-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:30f0ebf0d88034301819eb964f9236ce555aaa58e7ab89c5975a3e2250bbb405" }, + { url = "https://pypi.fury.io/lance-format/-/ver_IvKxo/pylance-9.0.0rc1-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:44609ea2615ea6e684b85478d1694af2026458f61cf7895ecc75e238bfd17aa8" }, + { url = "https://pypi.fury.io/lance-format/-/ver_2hidj1/pylance-9.0.0rc1-cp310-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:182167a8dba9eeabffbffd53bd5b8548613d4d459b7cd7b34a840dd00cbb806f" }, + { url = "https://pypi.fury.io/lance-format/-/ver_1dFx3r/pylance-9.0.0rc1-cp310-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:8a63b11e814b7eab758bcaf0d6f97eb05ea86203d9fb0af718c462c24c7d6c9c" }, + { url = "https://pypi.fury.io/lance-format/-/ver_2a8dSh/pylance-9.0.0rc1-cp310-abi3-win_amd64.whl", hash = "sha256:2ff8b953ae2b0550490c1a7efd210aa91bc223d200ffac28849056cfd7436d97" }, ] [[package]] @@ -4683,10 +4686,10 @@ resolution-markers = [ "python_full_version < '3.11'", ] dependencies = [ - { name = "joblib", marker = "python_full_version < '3.11'" }, - { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" }, - { name = "scipy", version = "1.15.3", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" }, - { name = "threadpoolctl", marker = "python_full_version < '3.11'" }, + { name = "joblib" }, + { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" } }, + { name = "scipy", version = "1.15.3", source = { registry = "https://pypi.org/simple" } }, + { name = "threadpoolctl" }, ] sdist = { url = "https://files.pythonhosted.org/packages/98/c2/a7855e41c9d285dfe86dc50b250978105dce513d6e459ea66a6aeb0e1e0c/scikit_learn-1.7.2.tar.gz", hash = "sha256:20e9e49ecd130598f1ca38a1d85090e1a600147b9c02fa6f15d69cb53d968fda", size = 7193136, upload-time = "2025-09-09T08:21:29.075Z" } wheels = [ @@ -4734,13 +4737,13 @@ resolution-markers = [ "python_full_version == '3.11.*'", ] dependencies = [ - { name = "joblib", marker = "python_full_version >= '3.11'" }, - { name = "narwhals", marker = "python_full_version >= '3.11'" }, - { name = "numpy", version = "2.4.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version == '3.11.*'" }, + { name = "joblib" }, + { name = "narwhals" }, + { name = "numpy", version = "2.4.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.12'" }, { name = "numpy", version = "2.5.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.12'" }, - { name = "scipy", version = "1.17.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version == '3.11.*'" }, + { name = "scipy", version = "1.17.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.12'" }, { name = "scipy", version = "1.18.0", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.12'" }, - { name = "threadpoolctl", marker = "python_full_version >= '3.11'" }, + { name = "threadpoolctl" }, ] sdist = { url = "https://files.pythonhosted.org/packages/fa/6f/37092bdb25f712817231799fc5674d8e704066a8a70c1d2d40517e18b4ab/scikit_learn-1.9.0.tar.gz", hash = "sha256:8833266989d3a5110178a9fae30783675460724d0e1efb13b14901d2c660c557", size = 7750767, upload-time = "2026-06-02T11:54:32.706Z" } wheels = [ @@ -4784,7 +4787,7 @@ resolution-markers = [ "python_full_version < '3.11'", ] dependencies = [ - { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" }, + { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" } }, ] sdist = { url = "https://files.pythonhosted.org/packages/0f/37/6964b830433e654ec7485e45a00fc9a27cf868d622838f6b6d9c5ec0d532/scipy-1.15.3.tar.gz", hash = "sha256:eae3cf522bc7df64b42cad3925c876e1b0b6c35c1337c93e12c0f366f55b0eaf", size = 59419214, upload-time = "2025-05-08T16:13:05.955Z" } wheels = [ @@ -4843,7 +4846,7 @@ resolution-markers = [ "python_full_version == '3.11.*'", ] dependencies = [ - { name = "numpy", version = "2.4.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version == '3.11.*'" }, + { name = "numpy", version = "2.4.6", source = { registry = "https://pypi.org/simple" } }, ] sdist = { url = "https://files.pythonhosted.org/packages/7a/97/5a3609c4f8d58b039179648e62dd220f89864f56f7357f5d4f45c29eb2cc/scipy-1.17.1.tar.gz", hash = "sha256:95d8e012d8cb8816c226aef832200b1d45109ed4464303e997c5b13122b297c0", size = 30573822, upload-time = "2026-02-23T00:26:24.851Z" } wheels = [ @@ -4920,7 +4923,7 @@ resolution-markers = [ "python_full_version >= '3.12' and python_full_version < '3.14'", ] dependencies = [ - { name = "numpy", version = "2.5.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.12'" }, + { name = "numpy", version = "2.5.1", source = { registry = "https://pypi.org/simple" } }, ] sdist = { url = "https://files.pythonhosted.org/packages/a7/25/c2700dfaf6442b4effaa91af24ebce5dc9d31bb4a69706313aae70d72cd0/scipy-1.18.0.tar.gz", hash = "sha256:67b2ad2ad54c72ca6d04975a9b2df8c3638c34ddd5b28738e94fc2b57929d378", size = 30774447, upload-time = "2026-06-19T15:01:43.456Z" } wheels = [ diff --git a/rust/lancedb/src/connection.rs b/rust/lancedb/src/connection.rs index 6ec4a6ec1..b399d9081 100644 --- a/rust/lancedb/src/connection.rs +++ b/rust/lancedb/src/connection.rs @@ -24,7 +24,7 @@ use crate::data::scannable::Scannable; use crate::database::listing::ListingDatabase; use crate::database::{ CloneTableRequest, Database, DatabaseOptions, JobInfo, OpenTableRequest, ReadConsistency, - TableNamesRequest, + SecretInfo, TableNamesRequest, }; use crate::embeddings::{EmbeddingRegistry, MemoryRegistry}; use crate::error::{Error, Result}; @@ -645,6 +645,59 @@ impl Connection { .await } + /// Create a named Secret in this database. + /// + /// Fails if the name is taken, so a create can never silently become a + /// rotation. There is no API that reads a stored credential back; the only + /// consumer is a Function that binds the Secret by name. Local databases + /// return [`Error::NotSupported`]. + pub async fn create_secret(&self, name: impl AsRef, value: impl AsRef) -> Result<()> { + self.internal + .create_secret(name.as_ref(), value.as_ref()) + .await + } + + /// Replace the credential behind an existing Secret. + /// + /// Fails if it does not exist. Every Function bound to the Secret resolves + /// the new value from its next execution, and no new Function version is + /// minted -- which is what lets a rotation reach columns pinned to a + /// version registered before it. Local databases return + /// [`Error::NotSupported`]. + pub async fn alter_secret(&self, name: impl AsRef, value: impl AsRef) -> Result<()> { + self.internal + .alter_secret(name.as_ref(), value.as_ref()) + .await + } + + /// The names of every Secret in this database. + /// + /// Names only. No path in this API returns a stored credential, by + /// construction rather than by policy. Local databases return + /// [`Error::NotSupported`]. + pub async fn list_secrets(&self) -> Result> { + self.internal.list_secrets().await + } + + /// Drop a Secret. + /// + /// Functions bound to it fail at their next job, naming the Secret; that + /// is the revocation path. The name becomes free to reuse, and a new + /// Secret under it is picked up by everything still bound to that name. + /// Local databases return [`Error::NotSupported`]. + pub async fn drop_secret(&self, name: impl AsRef) -> Result<()> { + self.internal.drop_secret(name.as_ref()).await + } + + /// What this database records about one Secret: its name and timestamps. + /// + /// Never the value. The type it returns has no field for one, so this is a + /// property of the API rather than of what the caller chooses to read. + /// Local databases return [`Error::NotSupported`]. + pub async fn describe_secret(&self, name: impl AsRef) -> Result { + self.internal.describe_secret(name.as_ref()).await + } + /// Rename a table in the database. /// /// This is only supported in LanceDB Cloud. diff --git a/rust/lancedb/src/database.rs b/rust/lancedb/src/database.rs index 843170030..f4988d217 100644 --- a/rust/lancedb/src/database.rs +++ b/rust/lancedb/src/database.rs @@ -249,9 +249,29 @@ fn function_catalog_not_supported() -> Result { }) } +fn secret_catalog_not_supported() -> Result { + Err(crate::error::Error::NotSupported { + message: "Secret operations are not supported by this database".to_string(), + }) +} + /// The `Database` trait defines the interface for database implementations. /// /// A database is responsible for managing tables and their metadata. +/// What a database records about a Secret. Never its value. +/// +/// Returned by [`crate::connection::Connection::describe_secret`]. There is no +/// field for the credential and no method that could produce one. +#[derive(Debug, Clone, PartialEq, Eq, serde::Deserialize)] +pub struct SecretInfo { + /// The Secret's database-scoped name. + pub name: String, + /// When the Secret was created, as an RFC 3339 timestamp. + pub created_at: String, + /// When the Secret's value was last rotated, as an RFC 3339 timestamp. + pub updated_at: String, +} + #[async_trait::async_trait] pub trait Database: Send + Sync + std::any::Any + std::fmt::Debug + std::fmt::Display + 'static @@ -317,6 +337,34 @@ pub trait Database: async fn drop_function(&self, _name: &str, _version: &str) -> Result { function_catalog_not_supported() } + /// Create a named Secret in this database. Fails if the name is taken, so + /// a create can never silently become a rotation. + async fn create_secret(&self, _name: &str, _value: &str) -> Result<()> { + secret_catalog_not_supported() + } + /// Replace the credential behind an existing Secret. Fails if it does not + /// exist. Every Function bound to it resolves the new value from its next + /// execution, with no new Function version. + async fn alter_secret(&self, _name: &str, _value: &str) -> Result<()> { + secret_catalog_not_supported() + } + /// The names of every Secret in this database. + /// + /// Names only. No API path returns a stored credential, by construction + /// rather than by policy. + async fn list_secrets(&self) -> Result> { + secret_catalog_not_supported() + } + /// Drop a Secret. Functions bound to it fail at their next job, which is + /// the revocation path. + async fn drop_secret(&self, _name: &str) -> Result<()> { + secret_catalog_not_supported() + } + /// What the database records about one Secret: its name and timestamps, + /// never its value. + async fn describe_secret(&self, _name: &str) -> Result { + secret_catalog_not_supported() + } /// Open a job by id, returning a handle with its record already /// populated. Fails with [`crate::Error::JobNotFound`] when the server has /// no such job. diff --git a/rust/lancedb/src/function.rs b/rust/lancedb/src/function.rs index e67d763ac..1e75d4202 100644 --- a/rust/lancedb/src/function.rs +++ b/rust/lancedb/src/function.rs @@ -5,7 +5,7 @@ //! backend-neutral terminal result of a computed-column refresh. //! //! This module contains client/wire values only. Catalog persistence, -//! environment bake, and execution are owned by Sophon. +//! environment bake, secret resolution, and execution are owned by Sophon. use std::collections::BTreeMap; @@ -409,6 +409,8 @@ pub struct FunctionVersion { runtime: PythonRuntimeSpec, runtime_digest: String, environment_digest: String, + #[serde(default, skip_serializing_if = "BTreeMap::is_empty")] + secret_bindings: BTreeMap, created_at: String, } @@ -441,6 +443,16 @@ impl FunctionVersion { &self.environment_digest } + /// Declared environment variable name to the Secret each one resolves. + /// + /// Bindings are part of this version's identity; the credentials behind + /// them are not, and resolve at execution. Rotating a bound Secret + /// therefore changes what the same version runs with, and no value has a + /// field in this model. + pub fn secret_bindings(&self) -> &BTreeMap { + &self.secret_bindings + } + pub fn created_at(&self) -> &str { &self.created_at } @@ -482,12 +494,20 @@ pub struct FunctionArtifactRequest { } /// Stable request envelope for remote immutable Function registration. +/// +/// Credential values deliberately have no field here. The only secret-shaped +/// thing a client sends is `secret_bindings`: the name of a Secret the +/// database already holds, which 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, + /// Declared environment variable name to the Secret it binds. Every bound + /// Secret must already exist; registration fails otherwise. + #[serde(default, skip_serializing_if = "BTreeMap::is_empty")] + pub secret_bindings: BTreeMap, } impl_json!(FunctionRegistrationRequest); diff --git a/rust/lancedb/src/remote/db.rs b/rust/lancedb/src/remote/db.rs index 32ace368e..3db66c182 100644 --- a/rust/lancedb/src/remote/db.rs +++ b/rust/lancedb/src/remote/db.rs @@ -21,7 +21,7 @@ use lance_namespace::models::{ use crate::Error; use crate::database::{ CloneTableRequest, CreateTableMode, CreateTableRequest, Database, DatabaseOptions, JobInfo, - OpenTableRequest, ReadConsistency, TableNamesRequest, + OpenTableRequest, ReadConsistency, SecretInfo, TableNamesRequest, }; use crate::error::Result; use crate::function::{FunctionRegistrationRequest, FunctionVersion}; @@ -352,6 +352,20 @@ impl RemoteDatabase { } impl RemoteDatabase { + /// `create` and `alter` differ only in which name state the server + /// requires, so they share one request shape. The value is a request field + /// and never a path segment or query parameter, which keeps it out of + /// access logs and proxy traces. + async fn write_secret(&self, route: &str, name: &str, value: &str) -> Result<()> { + let req = self.client.post(route).json(&serde_json::json!({ + "name": name, + "value": value, + })); + let (request_id, response) = self.client.send(req).await?; + self.client.check_response(&request_id, response).await?; + Ok(()) + } + async fn submit_drop_table( &self, name: &str, @@ -570,6 +584,21 @@ struct RemoteDropFunctionResponse { dropped: bool, } +#[derive(serde::Deserialize)] +struct RemoteListSecretsResponse { + #[serde(default)] + secrets: Vec, + #[serde(default)] + page_token: Option, +} + +/// An object rather than a bare name so a later listing can carry a Secret's +/// type or last-updated time without breaking this one. +#[derive(serde::Deserialize)] +struct RemoteListedSecret { + name: String, +} + /// Bound on `list_jobs` page walking; a warning is logged when the listing /// is truncated at this many pages. const MAX_LIST_JOBS_PAGES: usize = 100; @@ -671,6 +700,66 @@ impl Database for RemoteDatabase { Ok(response.dropped) } + async fn create_secret(&self, name: &str, value: &str) -> Result<()> { + self.write_secret("/v1/secrets/create", name, value).await + } + + async fn alter_secret(&self, name: &str, value: &str) -> Result<()> { + self.write_secret("/v1/secrets/alter", name, value).await + } + + async fn list_secrets(&self) -> Result> { + let mut names = Vec::new(); + let mut page_token: Option = None; + let mut seen_page_tokens = HashSet::new(); + loop { + let mut body = serde_json::json!({}); + if let Some(token) = &page_token { + body["page_token"] = serde_json::Value::String(token.clone()); + } + let req = self.client.post("/v1/secrets/list").json(&body); + let (request_id, response) = self.client.send(req).await?; + let response = self.client.check_response(&request_id, response).await?; + let status = response.status(); + let response: RemoteListSecretsResponse = + response.json().await.err_to_http(request_id.clone())?; + names.extend(response.secrets.into_iter().map(|secret| secret.name)); + let Some(next_page_token) = response.page_token.filter(|token| !token.is_empty()) + else { + break; + }; + if !seen_page_tokens.insert(next_page_token.clone()) { + return Err(Error::Http { + source: "Secret listing response repeated a page_token".into(), + request_id, + status_code: Some(status), + }); + } + page_token = Some(next_page_token); + } + Ok(names) + } + + async fn drop_secret(&self, name: &str) -> Result<()> { + let req = self + .client + .post("/v1/secrets/drop") + .json(&serde_json::json!({ "name": name })); + let (request_id, response) = self.client.send(req).await?; + self.client.check_response(&request_id, response).await?; + Ok(()) + } + + async fn describe_secret(&self, name: &str) -> Result { + let req = self + .client + .post("/v1/secrets/describe") + .json(&serde_json::json!({ "name": name })); + let (request_id, response) = self.client.send(req).await?; + let response = self.client.check_response(&request_id, response).await?; + response.json().await.err_to_http(request_id) + } + async fn open_job(&self, job_id: &str) -> Result { let handle = super::job::RemoteJob::new(self.client.clone(), job_id.to_string()); match crate::job::JobHandle::describe(&handle).await { @@ -2781,6 +2870,82 @@ mod tests { assert_eq!(batches[0].schema(), schema); } + #[tokio::test] + async fn test_create_and_alter_secret_send_the_value_in_the_request_body() { + for (route, call) in [("/v1/secrets/create", true), ("/v1/secrets/alter", false)] { + let conn = Connection::new_with_handler(move |request| { + assert_eq!(request.method(), &reqwest::Method::POST); + assert_eq!(request.url().path(), route); + // Never a path segment or query parameter, which is what keeps + // it out of access logs and proxy traces. + assert!(request.url().query().is_none(), "{:?}", request.url()); + let body: serde_json::Value = + serde_json::from_slice(request.body().unwrap().as_bytes().unwrap()).unwrap(); + assert_eq!(body["name"], "openai-prod"); + assert_eq!(body["value"], "sk-live-0001"); + http::Response::builder().status(200).body("{}").unwrap() + }); + if call { + conn.create_secret("openai-prod", "sk-live-0001") + .await + .unwrap(); + } else { + conn.alter_secret("openai-prod", "sk-live-0001") + .await + .unwrap(); + } + } + } + + #[tokio::test] + async fn test_list_secrets_walks_pages_and_returns_names_only() { + let conn = Connection::new_with_handler(|request| { + assert_eq!(request.url().path(), "/v1/secrets/list"); + let body: serde_json::Value = + serde_json::from_slice(request.body().unwrap().as_bytes().unwrap()).unwrap(); + let page = body.get("page_token").and_then(|token| token.as_str()); + let body = match page { + None => r#"{"secrets":[{"name":"openai-prod"}],"page_token":"p2"}"#, + Some("p2") => r#"{"secrets":[{"name":"hf-prod"}]}"#, + Some(other) => panic!("unexpected page token: {other}"), + }; + http::Response::builder().status(200).body(body).unwrap() + }); + assert_eq!( + conn.list_secrets().await.unwrap(), + vec!["openai-prod".to_string(), "hf-prod".to_string()] + ); + } + + /// A server that keeps handing back the same token would otherwise spin + /// forever. + #[tokio::test] + async fn test_list_secrets_rejects_a_repeated_page_token() { + let conn = Connection::new_with_handler(|_| { + http::Response::builder() + .status(200) + .body(r#"{"secrets":[{"name":"openai-prod"}],"page_token":"same"}"#) + .unwrap() + }); + let error = conn.list_secrets().await.unwrap_err(); + assert!( + error.to_string().contains("repeated a page_token"), + "{error}" + ); + } + + #[tokio::test] + async fn test_drop_secret_posts_the_name_alone() { + let conn = Connection::new_with_handler(|request| { + assert_eq!(request.url().path(), "/v1/secrets/drop"); + let body: serde_json::Value = + serde_json::from_slice(request.body().unwrap().as_bytes().unwrap()).unwrap(); + assert_eq!(body, serde_json::json!({"name": "openai-prod"})); + http::Response::builder().status(200).body("{}").unwrap() + }); + conn.drop_secret("openai-prod").await.unwrap(); + } + #[tokio::test] async fn test_create_function_async_sends_canonical_request_and_decodes_typed_job() { const REQUEST: &str = include_str!( diff --git a/rust/lancedb/tests/first_class_function_slice1.rs b/rust/lancedb/tests/first_class_function_slice1.rs index ce020bd53..92cb9e1ee 100644 --- a/rust/lancedb/tests/first_class_function_slice1.rs +++ b/rust/lancedb/tests/first_class_function_slice1.rs @@ -1,6 +1,7 @@ // SPDX-License-Identifier: Apache-2.0 // SPDX-FileCopyrightText: Copyright The LanceDB Authors +use std::collections::BTreeMap; use std::fs; use std::path::PathBuf; @@ -20,6 +21,26 @@ fn job_result(name: &str) -> Value { serde_json::from_str::(&fixture(name)).expect("remote Job fixture")["result"].clone() } +/// No client value models a resolved credential, at any nesting depth. +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"); @@ -28,6 +49,10 @@ 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.secret_bindings(), + &BTreeMap::from([("HF_TOKEN".to_string(), "hf-prod".to_string())]) + ); assert_eq!( version.to_canonical_json().expect("canonical JSON"), fixture("remote_function_version.canonical.json").trim() @@ -142,3 +167,40 @@ fn floating_point_application_literals_are_rejected_consistently() { .contains("floating-point Function literals") ); } + +#[test] +fn canonical_client_values_carry_bindings_and_no_credentials() { + 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["secret_bindings"], + serde_json::json!({"HF_TOKEN": "hf-prod"}) + ); + assert_no_secret_values(&canonical); +} + +/// Every Function registered before Secrets existed serializes unchanged. +#[test] +fn a_version_without_bindings_keeps_the_original_wire_shape() { + let mut result = job_result("remote_function_job.json"); + result + .as_object_mut() + .expect("Function version object") + .remove("secret_bindings"); + let version = FunctionVersion::from_json(&result.to_string()).expect("FunctionVersion result"); + + assert!(version.secret_bindings().is_empty()); + assert!( + !version + .to_canonical_json() + .expect("canonical FunctionVersion") + .contains("secret_bindings") + ); +} diff --git a/rust/lancedb/tests/first_class_function_slice2.rs b/rust/lancedb/tests/first_class_function_slice2.rs index 6d046d9d1..c1fbb559c 100644 --- a/rust/lancedb/tests/first_class_function_slice2.rs +++ b/rust/lancedb/tests/first_class_function_slice2.rs @@ -6,6 +6,7 @@ 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")) @@ -14,6 +15,26 @@ fn fixture(name: &str) -> String { fs::read_to_string(path).expect("fixture must be readable") } +/// A registration request never models a resolved credential, at any depth. +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( @@ -22,10 +43,45 @@ 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"); + // The unchanged path: a Function that binds nothing serializes today's + // bytes, with no `secret_bindings` key at all. + assert!(request.secret_bindings.is_empty()); 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); +} + +/// The same shared golden as the Python suite builds from `@udf(secrets=...)` +/// plus `bind_secrets`, so both clients agree byte for byte on a bound request. +#[test] +fn secret_bound_registration_request_matches_shared_canonical_golden() { + let request = FunctionRegistrationRequest::from_json(&fixture( + "remote_function_secret_registration_request.json", + )) + .expect("registration request"); + assert_eq!(request.name, "analyze_caption"); + assert_eq!( + request.secret_bindings, + std::collections::BTreeMap::from([( + "OPENAI_API_KEY".to_string(), + "openai-prod".to_string() + )]) + ); + assert_eq!( + request.to_canonical_json().expect("canonical request"), + fixture("remote_function_secret_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] diff --git a/rust/lancedb/tests/fixtures/first_class_functions/v1/remote_function_job.json b/rust/lancedb/tests/fixtures/first_class_functions/v1/remote_function_job.json index 39a279692..b5103ba05 100644 --- a/rust/lancedb/tests/fixtures/first_class_functions/v1/remote_function_job.json +++ b/rust/lancedb/tests/fixtures/first_class_functions/v1/remote_function_job.json @@ -24,6 +24,7 @@ }, "runtime_digest": "sha256:runtime", "environment_digest": "sha256:environment", + "secret_bindings": {"HF_TOKEN": "hf-prod"}, "created_at": "2026-08-21T00:00:00Z" }, "future_job": {"trace_id": "trace-1"} diff --git a/rust/lancedb/tests/fixtures/first_class_functions/v1/remote_function_secret_registration_request.canonical.json b/rust/lancedb/tests/fixtures/first_class_functions/v1/remote_function_secret_registration_request.canonical.json new file mode 100644 index 000000000..7c971de00 --- /dev/null +++ b/rust/lancedb/tests/fixtures/first_class_functions/v1/remote_function_secret_registration_request.canonical.json @@ -0,0 +1 @@ +{"artifact":{"adapter":{"kind":"scalar_to_arrow_batch","version":1},"content":{"data":"ZnJvbSBfX2Z1dHVyZV9fIGltcG9ydCBhbm5vdGF0aW9ucwoKZGVmIGFuYWx5emVfY2FwdGlvbihjYXB0aW9uOiBzdHIpIC0+IHN0cjoKICAgIHJldHVybiBjYXB0aW9uLnN0cmlwKCkK","encoding":"base64"},"digest":"sha256:800462c9ad15151a80f83f85b8912ff149300c1563e07f58448f099afcd0d077","entrypoint":"analyze_caption","kind":"python_callable"},"name":"analyze_caption","runtime":{"env":{"MODE":"test"},"environment":{"kind":"pip","packages":["openai==3.7.0"]},"kind":"python","python_version":"3.12"},"secret_bindings":{"OPENAI_API_KEY":"openai-prod"},"signature":{"inputs":[{"arrow_type":"utf8","name":"caption","nullable":false}],"output":{"arrow_type":"utf8","kind":"scalar","nullable":false}}} diff --git a/rust/lancedb/tests/fixtures/first_class_functions/v1/remote_function_secret_registration_request.json b/rust/lancedb/tests/fixtures/first_class_functions/v1/remote_function_secret_registration_request.json new file mode 100644 index 000000000..679b831a6 --- /dev/null +++ b/rust/lancedb/tests/fixtures/first_class_functions/v1/remote_function_secret_registration_request.json @@ -0,0 +1,46 @@ +{ + "artifact": { + "adapter": { + "kind": "scalar_to_arrow_batch", + "version": 1 + }, + "content": { + "data": "ZnJvbSBfX2Z1dHVyZV9fIGltcG9ydCBhbm5vdGF0aW9ucwoKZGVmIGFuYWx5emVfY2FwdGlvbihjYXB0aW9uOiBzdHIpIC0+IHN0cjoKICAgIHJldHVybiBjYXB0aW9uLnN0cmlwKCkK", + "encoding": "base64" + }, + "digest": "sha256:800462c9ad15151a80f83f85b8912ff149300c1563e07f58448f099afcd0d077", + "entrypoint": "analyze_caption", + "kind": "python_callable" + }, + "name": "analyze_caption", + "runtime": { + "env": { + "MODE": "test" + }, + "environment": { + "kind": "pip", + "packages": [ + "openai==3.7.0" + ] + }, + "kind": "python", + "python_version": "3.12" + }, + "secret_bindings": { + "OPENAI_API_KEY": "openai-prod" + }, + "signature": { + "inputs": [ + { + "arrow_type": "utf8", + "name": "caption", + "nullable": false + } + ], + "output": { + "arrow_type": "utf8", + "kind": "scalar", + "nullable": false + } + } +} diff --git a/rust/lancedb/tests/fixtures/first_class_functions/v1/remote_function_version.canonical.json b/rust/lancedb/tests/fixtures/first_class_functions/v1/remote_function_version.canonical.json index 2670ad0b2..e182bc2af 100644 --- a/rust/lancedb/tests/fixtures/first_class_functions/v1/remote_function_version.canonical.json +++ b/rust/lancedb/tests/fixtures/first_class_functions/v1/remote_function_version.canonical.json @@ -1 +1 @@ -{"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","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","secret_bindings":{"HF_TOKEN":"hf-prod"},"signature":{"inputs":[{"arrow_type":"utf8","name":"text","nullable":true}],"output":{"arrow_type":"list","kind":"scalar","nullable":false}},"version":"fv_01K3EXACT"}