FIN-17 · Import front door: upload endpoint, CLI, batch review, transactions API

[lbedner]

Milestone: Finance M3 · Depends on: FIN-14, FIN-15, FIN-16.

Goal

One import front door: upload endpoint + CLI + batch review API. After this, a user (or the Flet UI) can throw any supported file at one endpoint and get a precise per-row report.

Implementation

1. POST /api/v1/finance/import — multipart UploadFile + optional account_id + optional profile_id. Mirror the blog import endpoint pattern (app/components/backend/api/blog/router.py:285-321 in downstream; template has the same shape — grep import_posts_endpoint). Dispatch by lowercased extension: .ofx/.qfx→ofx, .qif→qif, .csv→csv_profiles; unknown → 415. Read bytes in memory; hard cap size (e.g. 10 MB → 413).
2. GET /finance/import/batches + GET /finance/import/batches/{id} — list caller's batches; detail includes per-row parsed_status/reason/matched_transaction_id (paginate rows).
3. CLI (app/cli/finance.py.jinja): finance import <file> [--account-id N] [--profile P] → calls the SAME service ingest synchronously, prints the ImportResult as a rich table (mirror the insights CLI backfill commands' style).
4. GET /finance/transactions — the read API the UI needs: filters account_id, from/to date, category_id, q (payee ILIKE), paginated, default excludes deleted_at IS NOT NULL and dedup_status='duplicate' rows.

Acceptance criteria

• curl multipart upload of each M3 fixture (qfx/qif/csv) → 200 with {batch_id, rows_inserted, rows_duplicate, rows_error} matching FIN-14/15/16 expectations.
• Re-upload byte-identical file → short-circuits via file-sha (rows_duplicate == rows_total, no new batch rows parsed).
• GET /finance/transactions?account_id=…&from=… returns imported rows, newest first; duplicate-marked rows absent.
• CLI import of the QIF fixture prints the same counts the API returned.
• Oversized file → 413; unknown extension → 415; wrong-owner account_id → 404.

---

Shared context (read this first — identical in every FIN ticket)

What we're building: a Finance Service for aegis-stack — a personal-finance aggregator (Empower/Quicken class: linked bank/credit/brokerage accounts, Quicken/OFX/CSV import, net-worth-over-time, "wasting money" insights). It is a gated template service like payment/insights: a new include_finance copier flag + a SERVICES["finance"] registry entry. Nothing is bolted into any one generated project.

Authoritative design docs (in this repo):

• docs/plans/finance-service/finance-service-plan.md — the full plan.
• docs/plans/finance-service/finance-schema-canonical.md — THE schema: 33 tables, every column/FK/index/unique/check, dedup contract, ER diagram. Schema tickets inline their slice, but this file is the tiebreaker.
• docs/plans/finance-service/finance-research/ — Plaid/OFX/product research briefs.

The two parallel systems (keep them in sync — this is the #1 thing to understand):

1. Copier template — aegis/templates/copier-aegis-project/{{ project_slug }}/…. Gating = literal {% if include_finance %} blocks in .jinja files + questions in copier.yml (repo root).
2. Python registry — aegis/core/services.py → the SERVICES dict. Single source of truth for: post-gen file pruning (aegis/core/post_gen_tasks.py:139-146 removes every path in a spec's FileManifest.primary when its flag is off), aegis add-service, migrations, aegis update disk-detection (marker_path), and aegis init service listing. Copy the payment spec (services.py:677-763) as the reference.

Migrations are GENERATED, not hand-written. Table definitions live as declarative specs in aegis/core/migration_generator.py: TableSpec / ColumnSpec / IndexSpec(name, columns, unique, where=…) (a where= renders BOTH sqlite_where and postgresql_where — partial uniques work on both engines) / ForeignKeySpec(columns, ref_table, ref_columns, ondelete=…, ref_schema=…) / CheckConstraintSpec(name, sqltext) / AlterTableSpec (for circular FKs; runs in one op.batch_alter_table, SQLite-safe). Revision IDs are auto-assigned at generation time (get_next_revision_id, max+1 zero-padded) — NEVER hardcode a revision number. Which migrations generate is decided by get_services_needing_migrations(context) (migration_generator.py:~1771) — finance gets a block there mirroring payment's (:~1839).

Generated-project conventions (non-negotiable, from the schema doc §conventions):

• int autoincrement PKs (id: int | None = Field(default=None, primary_key=True)) — NO UUIDs.
• Money = int minor units (cents) + a currency code column. NO Decimal/Numeric/float. Fractional share quantities = quantity_e8 (int, ×1e8); prices = int + price_scale; FX = rate_e8.
• Timestamps = naive UTC via a utcnow_naive() helper (datetime.now(UTC).replace(tzinfo=None)).
• Enums we own = String column + CheckConstraint (never native PG enum). Provider taxonomies that grow (Plaid account subtype, PFC categories, security_type) = plain TEXT, no check.
• JSON via sa_column=Column("name", JSON); the attr metadata_ maps to DB column "metadata" (SQLModel reserves metadata).
• Every user-scoped row: owner_user_id FK → user.id (CASCADE, indexed) + nullable organization_id (SET NULL, indexed). These FKs target the auth service's tables — finance declares required_services=["auth"]. Cross-schema FK precedent: payment.payment_customer → auth.user uses ForeignKeySpec(..., ref_schema="auth").
• Every FK indexed. ONE documented exception: currency FKs (low-cardinality) stay unindexed, ON DELETE RESTRICT.
• All finance tables are finance_-prefixed; explicit __tablename__; index names ix_…, uniques uq_…, checks ck_….
• Services: class FinanceService: def __init__(self, db: AsyncSession); queries via sqlmodel.select + await self.db.exec(…); writes self.db.add(…) + await self.db.flush() — services NEVER commit (the request-scoped get_async_db dependency commits).
• Dedup = real UNIQUE constraints + dialect-dispatched idempotent UPSERT (sqlite.insert(...).on_conflict_do_update(...) vs postgresql.insert(...) — pick by db.bind.dialect.name).

Dev workflow / how to validate (all from the aegis-stack repo root):

make check                 # repo's own lint + typecheck + tests — must stay green
make test-template         # generate a project from the template + validate it
make test-stacks-quick     # 3 representative stacks: base, everything, insights
make clean-test-projects   # remove generated test projects

# Generate a throwaway project from your UNCOMMITTED working tree:
uv run aegis init fin-smoke --dev --no-interactive -y \
  -o /tmp/aegis-fin-test \
  -c database,scheduler -s auth,finance
# (…and a second one WITHOUT `finance` in -s to prove pruning.)

Generated-project checks (run inside the generated project): make test, make lint, boot the app, hit endpoints with curl.

Postgres matters: the template supports sqlite AND postgres. FK enforcement, partial-unique behavior, and ON CONFLICT semantics must be validated against postgres too (generate with a postgres database answer, or run the migration against a local postgres). SQLite test sessions don't enforce FKs — don't trust green sqlite tests for constraint behavior.

Ticket codes: FIN-01…FIN-27. Dependencies are cited by code. Do not start a ticket whose dependencies aren't merged.