broker-sync/tests/test_pipeline.py

160 lines
5.1 KiB
Python
Raw Normal View History

Add sync pipeline + trading212 CLI subcommand Context ------- Closes the gap between "Trading212 provider yields Activities" and "activities land in Wealthfolio with dedup". One generic pipeline function works for every provider (Phase 2 IMAP ingest and Phase 3 CSV drop will reuse it). This change ----------- - `broker_sync/pipeline.py` — sync_provider_to_wealthfolio(): ensure accounts exist in Wealthfolio, fetch, dedup against the local SQLite store, batch into Wealthfolio's CSV import at 200 rows each, record successful imports in the dedup store with the returned Wealthfolio activity id. Failed batches don't touch the dedup store so the next run retries. - Notes field stamped with `sync:<provider>:<external_id>` for human auditability — NOT used for dedup (the SQLite store owns that). - `broker_sync/cli.py` — new `trading212` subcommand driven by T212_API_KEYS_JSON + WF_* + BROKER_SYNC_DATA_DIR env vars. Two modes: `steady` fetches last 7 days; `backfill` pulls all history. Exits 0 on clean run, 1 if any batch failed, 2 on config errors. - Pipeline tests with MockTransport: dedup-skip-then-import happy path (verifies imported CSV contains only the unseen rows and all three are recorded after the run); import-rejected path (verifies the failed row is NOT recorded so the next run retries). Test plan --------- ## Automated - poetry run pytest -q → 70 passed - poetry run mypy broker_sync tests → Success: no issues found in 29 source files - poetry run ruff check . → All checks passed! - poetry run broker-sync trading212 --help → shows all env vars + mode flag ## Manual Verification Live smoke test blocked on: 1. Vault secret/broker-sync seeded (wf_base_url, wf_username, wf_password, trading212_api_keys). 2. Terraform stack applied (infra/stacks/broker-sync/ — staged, not yet applied). 3. Image pushed to viktorbarzin/broker-sync on DockerHub via GHA. Once those land: kubectl -n broker-sync create job t212-backfill \ --from=cronjob/broker-sync-trading212 -- \ broker-sync trading212 --mode=backfill
2026-04-17 19:45:43 +00:00
from __future__ import annotations
import json
from collections.abc import AsyncIterator
from datetime import UTC, datetime
from decimal import Decimal
from pathlib import Path
import httpx
from broker_sync.dedup import SyncRecordStore
from broker_sync.models import Account, AccountType, Activity, ActivityType
from broker_sync.pipeline import sync_provider_to_wealthfolio
from broker_sync.sinks.wealthfolio import WealthfolioSink
class _FakeProvider:
name = "fake"
def __init__(self, accounts: list[Account], activities: list[Activity]) -> None:
self._accounts = accounts
self._activities = activities
def accounts(self) -> list[Account]:
return list(self._accounts)
async def fetch(
self,
*,
since: datetime | None = None,
before: datetime | None = None,
) -> AsyncIterator[Activity]:
for a in self._activities:
yield a
def _buy(external_id: str, account_id: str = "fake-isa") -> Activity:
return Activity(
external_id=external_id,
account_id=account_id,
account_type=AccountType.ISA,
date=datetime(2026, 4, 1, tzinfo=UTC),
activity_type=ActivityType.BUY,
symbol="VUAG",
quantity=Decimal("1"),
unit_price=Decimal("100"),
currency="GBP",
)
def _sink(transport: httpx.MockTransport, session_path: Path) -> WealthfolioSink:
session_path.write_text(json.dumps({"cookies": {"wf_token": "fresh"}}))
return WealthfolioSink(
base_url="https://wf.test",
username="x",
password="x",
session_path=session_path,
transport=transport,
)
async def test_pipeline_skips_dedup_then_imports_new(tmp_path: Path) -> None:
account = Account(
id="fake-isa",
name="Fake ISA",
account_type=AccountType.ISA,
currency="GBP",
provider="fake",
)
provider = _FakeProvider([account], [_buy("a"), _buy("b"), _buy("c")])
posted_batches: list[str] = []
async def handler(req: httpx.Request) -> httpx.Response:
if req.method == "GET" and req.url.path == "/api/v1/accounts":
return httpx.Response(200, json=[{"id": "fake-isa"}])
if req.url.path == "/api/v1/activities/import/check":
return httpx.Response(200, json={"ok": True})
if req.url.path == "/api/v1/activities/import":
# The httpx request body is multipart. We don't parse the multipart
# properly — we just scan for our dedup tags to confirm the
# pipeline pushed the rows it should have.
body = req.content.decode()
posted_batches.append(body)
# Echo back external_ids so dedup.record gets the WF activity id.
return httpx.Response(
200,
json=[{
"id": f"wf-{i}",
"external_id": ext
} for i, ext in enumerate(["a", "b", "c"])],
)
return httpx.Response(500)
sink = _sink(httpx.MockTransport(handler), tmp_path / "wf-session.json")
dedup = SyncRecordStore(tmp_path / "sync.db")
# Seed one already-seen to confirm dedup.
dedup.record("fake", "fake-isa", "a", wealthfolio_activity_id="wf-old")
try:
result = await sync_provider_to_wealthfolio(
provider=provider,
sink=sink,
dedup=dedup,
)
finally:
await sink.close()
assert result.fetched == 3
assert result.new_after_dedup == 2
assert result.imported == 2
assert result.failed == 0
assert len(posted_batches) == 1
body = posted_batches[0]
# Only the new rows (b, c) — NOT the already-seen "a".
assert "sync:fake:a" not in body
assert "sync:fake:b" in body
assert "sync:fake:c" in body
# All three external_ids are now in dedup after the run.
assert dedup.has_seen("fake", "fake-isa", "a")
assert dedup.has_seen("fake", "fake-isa", "b")
assert dedup.has_seen("fake", "fake-isa", "c")
async def test_pipeline_records_failure_when_import_rejects(tmp_path: Path) -> None:
account = Account(
id="fake-isa",
name="Fake ISA",
account_type=AccountType.ISA,
currency="GBP",
provider="fake",
)
provider = _FakeProvider([account], [_buy("a")])
async def handler(req: httpx.Request) -> httpx.Response:
if req.method == "GET" and req.url.path == "/api/v1/accounts":
return httpx.Response(200, json=[{"id": "fake-isa"}])
if req.url.path == "/api/v1/activities/import/check":
return httpx.Response(400, json={"errors": ["bad row"]})
return httpx.Response(500)
sink = _sink(httpx.MockTransport(handler), tmp_path / "wf-session.json")
dedup = SyncRecordStore(tmp_path / "sync.db")
try:
result = await sync_provider_to_wealthfolio(
provider=provider,
sink=sink,
dedup=dedup,
)
finally:
await sink.close()
assert result.fetched == 1
assert result.imported == 0
assert result.failed == 1
# NOT recorded in dedup so the next run retries.
assert not dedup.has_seen("fake", "fake-isa", "a")