refactor(backend): split into api/ schemas/ services/ clients/ layers

4-phase restructuring of the previously flat backend/ package. Each
phase lands as a single squash commit so future bisects stay readable
per phase if needed.

## Phase 1 — move + shim (location-only, zero behavior change)
* git mv 14 files into api/ schemas/ services/ clients/ subpackages
  (history preserved via RM/R renames)
* New files: api/{admin,auth,dependencies,jupyter,platform,resources,
  scripts,storage}.py + api/schedules/{schedules,runs}.py
* New files: schemas/{auth,common,jupyter,platform,resources,
  schedules,scripts}.py
* New files: clients/{rclone,runtime,scheduler}.py
* Old paths kept as 1-line `from backend.<new> import *` shims so
  tests/main.py/importers kept working untouched
* schemas/__init__.py now re-exports from backend.schemas.<domain>

## Phase 2 — APIRouter prefix consolidation
* Every APIRouter() now carries its prefix (e.g. prefix="/api/v1/auth")
  and decorators are stripped of the redundant path prefix
* URL paths exposed to the frontend are byte-identical to before
* Affected: api/{auth,jupyter,admin,platform,resources,scripts,
  storage}.py + api/schedules/{schedules,runs}.py

## Phase 3 — first service-layer extraction
* backend.services.schedules.validate_dag moved out of api/
  (pure DAG validator, no Request/BackgroundTasks/DB)
* api/schedules/schedules.py now re-exports the symbol so existing
  4 callsites keep working unchanged
* Added backend/tests/test_validate_dag.py: 8 unit tests covering
  DAG_EMPTY, linear chain, diamond, cycle, self-edge, duplicate
  edge, orphan edge, multi-root ordering

## Phase 4 — delete shims + unify test imports
* Removed 14 flat shim files + schemas/__init__.py
* Migrated 5 test files (32 import sites) to new paths:
  backend.scripts.* → backend.api.scripts.*
  backend.resources.* → backend.api.resources.*
  backend.jupyter.* → backend.api.jupyter.*
  backend.runtime_client.* → backend.clients.runtime.*
  backend.schemas.UpdateScriptRequest → backend.schemas.scripts.*
* audit.py kept at backend.audit (main.py references it; not a
  shim, real code)

## Final structure
backend/src/backend/
  main.py, audit.py, __init__.py
  api/            (10 files: routes + 2 subpackage)
  schemas/        (7 files: Pydantic contracts)
  services/       (storage + schedules)
  clients/        (rclone, runtime, scheduler)

## Verification
* uv run python -m compileall backend/src backend/tests — clean
* uv run --package backend pytest backend/tests -q — 122 passed
  (114 → 114 → 122 → 122 across phases)
* grep -r 'from backend\.\(scripts\|resources\|...\)' backend/ — 0 hits
* git blame --follow still traces file origins through the renames

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
tao.chen
2026-08-21 15:32:04 +08:00
co-authored by Claude
parent 5501b26628
commit bca239ed4b
36 changed files with 487 additions and 282 deletions
+11 -11
View File
@@ -13,7 +13,7 @@ import pytest
from fastapi import HTTPException
from sqlalchemy import Column, MetaData, String, Table, create_engine, select
from sqlalchemy.dialects import mysql as mysql_dialect
from backend.resources import (
from backend.api.resources import (
_build_list_resources_descendant_prefix,
can_view,
compute_jupyter_relative_path,
@@ -126,7 +126,7 @@ def _bind_payload():
@pytest.mark.asyncio
async def test_bind_resource_rejects_duplicate_name_in_same_directory() -> None:
"""Same resource_name in the same directory raises 409."""
from backend.resources import bind_resource
from backend.api.resources import bind_resource
existing_rows = [
(
@@ -153,7 +153,7 @@ async def test_bind_resource_rejects_duplicate_name_in_same_directory() -> None:
@pytest.mark.asyncio
async def test_bind_resource_allows_same_name_in_different_directory() -> None:
"""Same resource_name in a different directory binds successfully."""
from backend.resources import bind_resource
from backend.api.resources import bind_resource
existing_rows = [
(
@@ -179,7 +179,7 @@ async def test_bind_resource_allows_same_name_in_different_directory() -> None:
@pytest.mark.asyncio
async def test_bind_resource_allows_same_name_when_workspace_empty() -> None:
"""No same-name rows at all: bind succeeds (root directory)."""
from backend.resources import bind_resource
from backend.api.resources import bind_resource
session = _BindSessionMock(
new_object_key=f"{_BIND_WS}/{_BIND_USER}/data.csv",
@@ -197,7 +197,7 @@ async def test_bind_resource_allows_same_name_when_workspace_empty() -> None:
@pytest.mark.asyncio
async def test_bind_resource_allows_same_name_for_different_owner() -> None:
"""其他用户在同目录下的同名资源不阻塞当前用户的绑定。"""
from backend.resources import bind_resource
from backend.api.resources import bind_resource
other_user = "01USR0000000000000000000B"
existing_rows = [
@@ -223,7 +223,7 @@ async def test_bind_resource_allows_same_name_for_different_owner() -> None:
@pytest.mark.asyncio
async def test_bind_resource_allows_rebinding_same_storage_object() -> None:
"""重新绑定同一 upload_id 应走 idempotent 复用路径,不触发 409。"""
from backend.resources import bind_resource
from backend.api.resources import bind_resource
new_object_key = f"{_BIND_WS}/{_BIND_USER}/data.csv"
existing_resource = _make_resource(_BIND_WS, _BIND_USER)
@@ -251,7 +251,7 @@ async def test_bind_resource_allows_rebinding_same_storage_object() -> None:
@pytest.mark.asyncio
async def test_bind_resource_rejects_non_data_resource_upload() -> None:
"""其他用途(如 working_copy)的 upload session 不能 bind 成数据资源。"""
from backend.resources import bind_resource
from backend.api.resources import bind_resource
session = _BindSessionMock(
new_object_key=f"{_BIND_WS}/{_BIND_USER}/data.csv",
@@ -566,7 +566,7 @@ def _list_resources_capturing_session(captured_sql: list[str]) -> MagicMock:
async def test_list_resources_where_clause_uses_like_prefix_and_excludes_deeper() -> None:
from backend.resources import list_resources
from backend.api.resources import list_resources
captured_sql: list[str] = []
mock_session = _list_resources_capturing_session(captured_sql)
@@ -589,7 +589,7 @@ async def test_list_resources_where_clause_uses_like_prefix_and_excludes_deeper(
async def test_list_resources_where_clause_escapes_underscore() -> None:
"""Regression: parent_path containing ``_`` MUST be escaped in the
compiled LIKE pattern, otherwise sibling-path leak (``fooXbar``) returns."""
from backend.resources import list_resources
from backend.api.resources import list_resources
captured_sql: list[str] = []
mock_session = _list_resources_capturing_session(captured_sql)
@@ -614,7 +614,7 @@ async def test_list_resources_where_clause_escapes_underscore() -> None:
async def test_list_resources_without_parent_path_adds_no_like_clause() -> None:
"""Empty parent_path keeps the legacy workspace-wide behaviour — no
object_key LIKE filter at all."""
from backend.resources import list_resources
from backend.api.resources import list_resources
captured_sql: list[str] = []
mock_session = _list_resources_capturing_session(captured_sql)
@@ -634,7 +634,7 @@ async def test_list_resources_without_parent_path_adds_no_like_clause() -> None:
async def test_list_resources_joins_users_for_display_name() -> None:
"""list_resources must OUTER JOIN users and SELECT users.display_name so
every resource carries owner_display_name (frontend displayName chain)."""
from backend.resources import list_resources
from backend.api.resources import list_resources
captured_sql: list[str] = []
mock_session = _list_resources_capturing_session(captured_sql)