smart-org/apps/api/tests/test_v2_e2e_smoke.py

"""End-to-end smoke for the v2 seams: wizard, team, manager order, engine task, push, run.

Only the model is fake: ``tests.engine_fakes.ScriptedModel`` answers every call, reached
through ``app.application.container.get_model_provider``. Git is the default fake
workspace (``GIT_WORKSPACE=fake``, the ``container_delivery._fake_workspace`` singleton),
and the sandbox and domain router are the mock defaults. Everything else is the real
code path: the owner grants the default models over HTTP, the manager completes the
wizard over HTTP (which runs the real bootstrap and delivery hooks), the manager opens a
thread over HTTP without a project as the web UI does, the order goes through the real
``ManagerTurns.chat``, and every pass is one real ``AiRuntimeWorker.drain()``.

What it proves is that the seams line up. A fresh organization gets its team, its demo
host and its granted models. A thread made without a project still yields a task in the
organization's project, with a pipeline state. The engine starts the project's sandbox
session on its own. The task walks to ``COMPLETED``, and the merge queues a ``dev``
pipeline run that names the pushed commit. No network, docker or real git.
"""

from __future__ import annotations

from sqlalchemy import select

from app.application.container_delivery import _fake_workspace
from app.application.container_engine import build_scheduler
from app.application.ports.repo_workspace import DiffResult
from app.core.config import settings
from app.domain.workforce.models import RoleKey, TaskStatus
from app.domain.workforce.pipeline import Stage
from app.infrastructure.db.models import (
    AiModelRow,
    OrganizationRow,
    OrgModelGrantRow,
    SandboxSessionRow,
    WorkspaceRow,
)
from app.infrastructure.db.models_delivery import AppRuntimeRow
from app.infrastructure.repositories.delivery import PipelineRunRepository
from app.infrastructure.repositories.engine import PipelineStateRepository
from app.infrastructure.repositories.workforce import EmployeeRepository, TaskRepository
from app.workers.ai_runtime import AiRuntimeWorker
from tests.billing_helpers import fund_org
from tests.conftest import auth_header
from tests.engine_fakes import ScriptedModel, ScriptedReply
from tests.test_org_wizard import _complete, _manager

DEFAULTS = "/api/admin/default-model-grants"

#: The manager's chat reply: one task tag, so the order becomes one task.
ORDER_REPLY = (
    "باشه، یک کار می‌سازم.\n"
    '[[CREATE_TASK title="صفحهٔ ورود" kind="feature"]]'
    "ساخت صفحهٔ ورود با اعتبارسنجی[[/CREATE_TASK]]"
)

#: The replies that drive one task from triage to merge, as in test_engine_flow. The
#: pipeline is ``plan_code_test``: the default for a feature, and the one the ASSIGN reply
#: names. It has no review stage, so no review replies are needed.
PIPELINE_REPLIES = [
    '[[ASSIGN employee="" pipeline="plan_code_test"/]]',
    "[[PLAN_SPEC]]پلان کار[[/PLAN_SPEC]]",
    "[[WORK_REPORT]]پیاده‌سازی شد[[/WORK_REPORT]]",
    "[[TEST_PASS]]سبز است[[/TEST_PASS]]",
    "[[COMPLETE/]]",
]


async def _sandboxes_of(session_factory, organization_id: str, project_id: str) -> list:
    """The sandbox sessions of one organization's project."""
    async with session_factory() as session:
        stmt = (
            select(SandboxSessionRow)
            .join(WorkspaceRow, SandboxSessionRow.workspace_id == WorkspaceRow.id)
            .where(
                WorkspaceRow.organization_id == organization_id,
                WorkspaceRow.project_id == project_id,
            )
        )
        return list((await session.execute(stmt)).scalars().all())


async def test_a_manager_order_ships_through_the_engine(
    client, session_factory, seeded, platform_owner_token, monkeypatch, redirect_error_log
):
    scripted = ScriptedModel(
        [ScriptedReply(content=ORDER_REPLY), *(ScriptedReply(content=r) for r in PIPELINE_REPLIES)]
    )
    monkeypatch.setattr("app.application.container.get_model_provider", lambda: scripted)

    # The platform owner grants one reasoning model and one cheap model to the default set.
    async with session_factory() as session:
        models = list(
            (await session.execute(select(AiModelRow).order_by(AiModelRow.internal_name)))
            .scalars()
            .all()
        )
    strong = next(m for m in models if "reasoning" in m.capabilities)
    cheap = next(m for m in models if "reasoning" not in m.capabilities)
    owner = auth_header(platform_owner_token)
    for model in (strong, cheap):
        granted = await client.put(
            f"{DEFAULTS}/{model.id}", json={"is_active": True}, headers=owner
        )
        assert granted.status_code == 200, granted.text

    # The manager completes the wizard over HTTP: org, project, team, runtime, grants.
    _, headers = await _manager(client)
    body = await _complete(client, headers)
    org_id = body["organization"]["id"]
    slug = body["organization"]["slug"]
    project_id = body["project"]["id"]
    # prepaid: the owner credits a new org before work
    await fund_org(session_factory, org_id, 1000.0)

    async with session_factory() as session:
        roles = {e.role_key for e in await EmployeeRepository(session).list_for_org(org_id)}
        runtime = await session.get(AppRuntimeRow, project_id)
        grants = (
            await session.execute(
                select(OrgModelGrantRow).where(OrgModelGrantRow.organization_id == org_id)
            )
        ).scalars().all()
        owner_user_id = (await session.get(OrganizationRow, org_id)).owner_user_id

    assert {RoleKey.MANAGER, RoleKey.PLANNER, RoleKey.DEVELOPER, RoleKey.TESTER} <= roles
    assert runtime is not None
    assert runtime.demo_host == f"{slug}.{settings.preview_root_domain}"
    assert grants

    # The manager opens a thread the way the web UI does: no project_id.
    created = await client.post(
        f"/api/organizations/{org_id}/threads", json={"title": "گفتگو"}, headers=headers
    )
    assert created.status_code == 201, created.text
    assert created.json()["project_id"] is None
    thread_id = created.json()["id"]

    # A manager order in that thread becomes one task with a pipeline state. The order goes to
    # the engine's manager directly, only to read the reply and the states in this session: the
    # HTTP message route builds its manager with the pipeline states too
    # (test_integration_order_route.py).
    async with session_factory() as session:
        await build_scheduler(session).manager.chat(
            organization_id=org_id,
            thread_id=thread_id,
            content="یک صفحهٔ ورود بساز.",
            user_id=owner_user_id,
        )
        await session.commit()
        tasks = await TaskRepository(session).list_for_org(org_id)
        states = await PipelineStateRepository(session).list_for_org(org_id)

    assert len(tasks) == 1
    assert len(states) == 1
    assert tasks[0].project_id == project_id
    assert states[0].project_id == project_id
    task_id = tasks[0].id

    # Nothing has started the project's sandbox yet; the engine must do it.
    assert await _sandboxes_of(session_factory, org_id, project_id) == []

    # The engine walks the task through its stages. Each pass is one real worker drain (the
    # legacy drain, then one Scheduler.tick()); the merge pushes to dev.
    _fake_workspace.diffs[task_id] = DiffResult(
        changed_files=["app/main.py"], text="--- a\n+++ b\n@@\n+x\n"
    )
    state = None
    for _ in range(10):
        await AiRuntimeWorker().drain()
        async with session_factory() as session:
            state = await PipelineStateRepository(session).get(task_id)
        if state is not None and state.stage is Stage.COMPLETED:
            break

    async with session_factory() as session:
        task = await TaskRepository(session).get(task_id)

    assert state is not None and state.stage is Stage.COMPLETED
    assert task is not None and task.status is TaskStatus.DONE
    # The engine started the project's sandbox session on its own; no API call did.
    assert await _sandboxes_of(session_factory, org_id, project_id)

    pushed_sha = _fake_workspace.heads[(project_id, "dev")]
    async with session_factory() as session:
        runs = await PipelineRunRepository(session).list_for_project(
            organization_id=org_id, project_id=project_id
        )
    assert any(
        run.trigger == "engine" and run.branch == "dev" and run.sha == pushed_sha for run in runs
    )