feat: backfill missing PnL for submitted alphas

backend/tests/test_pnl_backfill.py

@@ -0,0 +1,103 @@
+"""Submitted PnL backfill covers the local library and preserves existing caches."""
+
+import pytest
+from sqlalchemy import func, select
+
+from app.alphas import upsert_alpha
+from app.models import Pnl
+from app.worldquant import WqError
+from tests.conftest import alpha
+from tests.test_jobs import ready_runner, result
+
+URL = "/api/v1/sync-jobs"
+
+
+async def start(client):
+    response = await client.post(URL, json={"kind": "pnl_backfill"})
+    assert response.status_code == 202
+    return response.json()
+
+
+async def test_backfill_all_submitted_beyond_page_limit_and_deduplicates(app, logged_in):
+    runner = await ready_runner(app)
+    async with runner.sessions() as db:
+        for i in range(105):
+            await upsert_alpha(db, alpha(
+                f"ref{i:03}", status="DECOMMISSIONED" if i % 2 else "ACTIVE",
+                hidden=bool(i % 2), settings={"region": "EUR" if i % 2 else "USA"},
+            ))
+        for raw in [alpha("pending"), alpha("unknown", status=None), alpha("cached", status="ACTIVE")]:
+            await upsert_alpha(db, raw)
+        db.add(Pnl(alpha_id="cached", raw={"original": True}, points=[]))
+        await db.commit()
+    first = await start(logged_in)
+    assert first["total"] == 105
+    assert first["payload"]["alpha_ids"] == [f"ref{i:03}" for i in range(105)]
+    # Another task can populate an item after this snapshot was fixed.
+    async with runner.sessions() as db:
+        db.add(Pnl(alpha_id="ref000", raw={"original": True}, points=[]))
+        await db.commit()
+    assert (await start(logged_in))["id"] == first["id"]
+    calls = []
+    original_pnl = runner.client.pnl
+
+    async def pnl(alpha_id):
+        calls.append(alpha_id)
+        return await original_pnl(alpha_id)
+
+    runner.client.pnl = pnl
+    await runner.execute(first["id"])
+    finished = await result(runner, first["id"])
+    assert (finished.status, finished.processed, finished.failed) == ("completed", 105, 0)
+    assert calls == [f"ref{i:03}" for i in range(1, 105)]
+    async with runner.sessions() as db:
+        assert await db.scalar(select(func.count()).select_from(Pnl)) == 106
+        assert (await db.get(Pnl, "cached")).raw == {"original": True}
+        assert (await db.get(Pnl, "ref000")).raw == {"original": True}
+    empty = await start(logged_in)
+    assert empty["status"] == "completed" and empty["total"] == 0
+    assert empty["payload"]["alpha_ids"] == []
+
+
+async def test_backfill_keeps_progress_and_retries_only_unfinished_items(app, logged_in):
+    runner = await ready_runner(app)
+    async with runner.sessions() as db:
+        for name in ("a", "b", "c"):
+            await upsert_alpha(db, alpha(name, status="ACTIVE"))
+        await db.commit()
+    calls = []
+    blocked = True
+    original_pnl = runner.client.pnl
+
+    async def pnl(alpha_id):
+        calls.append(alpha_id)
+        if blocked and alpha_id == "b":
+            raise WqError("无权访问", "access_denied")
+        if blocked and alpha_id == "c":
+            raise WqError("平台数据仍在准备，请稍后重试", "pending")
+        return await original_pnl(alpha_id)
+
+    runner.client.pnl = pnl
+    job = await start(logged_in)
+    await runner.execute(job["id"])
+    failed = await result(runner, job["id"])
+    assert (failed.status, failed.processed, failed.failed) == ("failed", 1, 1)
+    assert failed.checkpoint["alpha_id"] == "c"
+    async with runner.sessions() as db:
+        assert await db.get(Pnl, "a") is not None
+        assert await db.get(Pnl, "b") is None
+        assert await db.get(Pnl, "c") is None
+    blocked = False
+    assert (await logged_in.post(f"{URL}/{job['id']}/retry")).status_code == 200
+    await runner.execute(job["id"])
+    finished = await result(runner, job["id"])
+    assert (finished.status, finished.processed, finished.failed) == ("completed", 3, 0)
+    assert calls == ["a", "b", "c", "b", "c"]
+
+
+@pytest.mark.parametrize("extra", [
+    {"alpha_ids": ["a"]}, {"submission": "UNSUBMITTED"}, {"date_from": "2025-01-01"},
+])
+async def test_backfill_rejects_client_scope(logged_in, extra):
+    response = await logged_in.post(URL, json={"kind": "pnl_backfill", **extra})
+    assert response.status_code == 422