feat(tenant): add tenant_domains allowlist and /v1/domains management API

Why:
- Domain values are denormalized into every Qdrant point payload. Without
  validation, an unregistered or typo'd domain (e.g. "fier" for "fire")
  silently creates a new partition that retrieval never queries — the file
  ends up invisible rather than rejected. Tenants also need independently
  sized domain sets (one may run 14 insurance lines, another 6), which rules
  out an enum.

Changes:
- tenant_domains table (migration 41335d162de8) + repository, unique on
  (tenant_id, domain).
- src/application/domains/: ensure_domain_allowed() is the strict-allowlist
  check now run inside upload_source_file()'s first transaction, before any
  MinIO object, job row, or Qdrant point is written.
- /v1/domains (list/create/patch/disable/enable) gated on its own
  domains:read/domains:write scopes, deliberately separate from files:write
  so an upload key cannot create partitions. domain itself is immutable
  (denormalized into every point payload); only display_name is editable.
  Disable blocks new uploads without touching already-indexed points.

Impact:
- BREAKING: POST /v1/files now rejects any domain without an active
  tenant_domains row (400, unknown_domain). A domain must be created via
  POST /v1/domains before the first upload to it.
This commit is contained in:
Ali Zarinkolah
2026-08-20 18:20:24 +03:30
parent fa933b08ff
commit e9e83b3a26
21 changed files with 1102 additions and 12 deletions

View File

@@ -16,6 +16,7 @@ from src.application.auth.errors import (
MissingScopeError,
TenantInactiveError,
)
from src.application.domains.errors import DomainAlreadyExistsError, UnknownDomainError
from src.application.files.errors import FileTooLargeError, InvalidUploadError
from src.application.ingestion.errors import (
ChunkLimitExceededError,
@@ -40,6 +41,8 @@ _MAPPING: tuple[tuple[type[Exception], int, str], ...] = (
(TenantInactiveError, status.HTTP_401_UNAUTHORIZED, "tenant_not_found"),
(MissingScopeError, status.HTTP_403_FORBIDDEN, "missing_scope"),
(InvalidUploadError, status.HTTP_400_BAD_REQUEST, "validation_error"),
(UnknownDomainError, status.HTTP_400_BAD_REQUEST, "unknown_domain"),
(DomainAlreadyExistsError, status.HTTP_409_CONFLICT, "conflict"),
(DocumentParseError, status.HTTP_400_BAD_REQUEST, "validation_error"),
(UnsupportedSourceTypeError, status.HTTP_415_UNSUPPORTED_MEDIA_TYPE, "unsupported_media_type"),
(FileTooLargeError, status.HTTP_413_CONTENT_TOO_LARGE, "payload_too_large"),

View File

@@ -1,6 +1,8 @@
from fastapi import APIRouter
from src.api.routers.domains import router as domains_router
from src.api.routers.files import router as files_router
router = APIRouter()
router.include_router(domains_router)
router.include_router(files_router)

110
src/api/routers/domains.py Normal file
View File

@@ -0,0 +1,110 @@
"""`/v1/domains` (ADR-0008, ADR-0009).
The management surface for a tenant's domain allowlist, used by the calling
backend rather than by an operator with a psql prompt.
Gated on `domains:read`/`domains:write`, deliberately **not** on `files:write`:
if an upload key could create domains, the allowlist would no longer prevent a
typo'd `domain` from creating a Qdrant partition, which is its only purpose.
"""
from typing import Annotated
from fastapi import APIRouter, Depends, status
from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker
from src.api.dependencies.auth import require_scope
from src.api.schemas.domains import (
CreateDomainRequest,
DomainListResponse,
DomainResponse,
UpdateDomainRequest,
)
from src.application.auth.context import AuthContext
from src.application.domains import (
create_domain,
list_domains,
set_domain_status,
update_domain,
)
from src.bootstrap.dependencies import get_sessionmaker
router = APIRouter(prefix="/domains", tags=["domains"])
_RequireDomainsRead = Annotated[AuthContext, Depends(require_scope("domains:read"))]
_RequireDomainsWrite = Annotated[AuthContext, Depends(require_scope("domains:write"))]
_SessionmakerDep = Annotated[async_sessionmaker[AsyncSession], Depends(get_sessionmaker)]
@router.get("")
async def list_tenant_domains(
auth: _RequireDomainsRead,
sessionmaker: _SessionmakerDep,
include_disabled: bool = False,
) -> DomainListResponse:
results = await list_domains(
sessionmaker, tenant_id=auth.tenant_id, include_disabled=include_disabled
)
return DomainListResponse(domains=[DomainResponse.from_result(item) for item in results])
@router.post("", status_code=status.HTTP_201_CREATED)
async def create_tenant_domain(
request: CreateDomainRequest,
auth: _RequireDomainsWrite,
sessionmaker: _SessionmakerDep,
) -> DomainResponse:
result = await create_domain(
sessionmaker,
tenant_id=auth.tenant_id,
domain=request.domain,
display_name=request.display_name,
metadata=request.metadata,
)
return DomainResponse.from_result(result)
@router.patch("/{domain}")
async def update_tenant_domain(
domain: str,
request: UpdateDomainRequest,
auth: _RequireDomainsWrite,
sessionmaker: _SessionmakerDep,
) -> DomainResponse:
result = await update_domain(
sessionmaker,
tenant_id=auth.tenant_id,
domain=domain,
display_name=request.display_name,
)
return DomainResponse.from_result(result)
@router.delete("/{domain}")
async def disable_tenant_domain(
domain: str,
auth: _RequireDomainsWrite,
sessionmaker: _SessionmakerDep,
) -> DomainResponse:
"""Disable, not delete.
Blocks new uploads and drops the domain from pickers while leaving the
points already indexed under it intact and retrievable. Actually removing
them needs the tenant-erasure workflow plan 001 defers.
"""
result = await set_domain_status(
sessionmaker, tenant_id=auth.tenant_id, domain=domain, status="disabled"
)
return DomainResponse.from_result(result)
@router.post("/{domain}/enable")
async def enable_tenant_domain(
domain: str,
auth: _RequireDomainsWrite,
sessionmaker: _SessionmakerDep,
) -> DomainResponse:
result = await set_domain_status(
sessionmaker, tenant_id=auth.tenant_id, domain=domain, status="active"
)
return DomainResponse.from_result(result)

View File

@@ -0,0 +1,63 @@
"""Public request/response models for `/v1/domains` (ADR-0008, ADR-0009).
`tenant_id` appears in none of these: it comes from the authenticated key, and
accepting it from a body would break the isolation boundary (ADR-0002).
"""
import uuid
from datetime import datetime
from pydantic import BaseModel, Field, field_validator
from src.application.domains.models import DomainResult
# Lowercase alphanumerics plus - and _; the key is embedded in every Qdrant
# payload and filtered on as a keyword, so it stays boring on purpose.
_DOMAIN_PATTERN = r"^[a-z0-9][a-z0-9_-]*$"
class DomainResponse(BaseModel):
id: uuid.UUID
domain: str
display_name: str
status: str
metadata: dict[str, object]
created_at: datetime
updated_at: datetime
@classmethod
def from_result(cls, result: DomainResult) -> "DomainResponse":
return cls(
id=result.id,
domain=result.domain,
display_name=result.display_name,
status=result.status,
metadata=result.metadata,
created_at=result.created_at,
updated_at=result.updated_at,
)
class DomainListResponse(BaseModel):
domains: list[DomainResponse]
class CreateDomainRequest(BaseModel):
domain: str = Field(min_length=1, max_length=80, pattern=_DOMAIN_PATTERN)
display_name: str = Field(min_length=1, max_length=200)
metadata: dict[str, object] = Field(default_factory=dict)
@field_validator("domain")
@classmethod
def _normalize(cls, value: str) -> str:
return value.strip()
class UpdateDomainRequest(BaseModel):
"""`domain` is absent by design — the key is immutable.
It is denormalized into every point payload and into `source_files`, so
renaming it is a migration rather than an edit (ADR-0009).
"""
display_name: str = Field(min_length=1, max_length=200)