Adds earning at payment time (docs/prd-point-coin.md F3, PC-203).
An order becomes fully paid through UpdateOrder, CreatePayment and both
kinds of split bill. All of them now go through one OrderProcessorImpl
hook, onOrderPaid, called after the payment has committed; for
CreatePayment that is after its transaction, not from updateOrderStatus
inside it. The hook runs detached from the caller's transaction and from
the request being cancelled, and it runs synchronously so the order
response can show what was earned.
EarningProcessor.EarnForOrder skips orders that are not paid, are void,
have no customer, or whose customer is the walk-in customer or inactive.
It computes the earning with CalculateEarning, subtracting any part paid
with EnakPoint (none until phase 3), and credits each currency through the
wallet engine as EARN with key earn:{order_id}:{currency} and the settings
snapshot in metadata. A repeat, even concurrent, credits nothing more.
OnOrderPaid never fails the payment: errors and panics are logged.
EarningBackfillJob is the safety net: every 30 minutes it earns for orders
paid in the last three days that have no EARN row. It only looks at
outlets with earning switched on and pages by (updated_at, id), so orders
that correctly earned nothing cannot starve the ones that were missed.
Lots from earning never expire until the expiry model is decided (F12,
note N4). Adds the point payment method type constant, not yet accepted as
a payment method.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Adds CalculateEarning (docs/prd-point-coin.md F1, Q1, Q10, PC-202), a pure
function returning, per currency, the amount an order earns and the
settings that produced it, plus the basis:
basis = subtotal − discount − paid with EnakPoint (never negative)
amount = 0 below min_order_amount, else
floor(basis / earn_per_amount) × earn_value, capped by max_per_order
Tax and anything added on top of the subtotal are not part of the basis,
and the part paid with EnakPoint earns nothing. Money is handled in whole
cents: in float64 some baskets divide to 4956.999… and a naive floor would
lose a point, which a test reproduces. Metadata() gives the snapshot the
EARN row will freeze.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Adds GET and PUT /outlets/:id/loyalty-settings (docs/prd-point-coin.md F1,
PC-201) on top of the typed settings processor.
The response shows every setting with its default when unset, the
organization's point value, and the effective EnakPoint cashback
(earn_value × point_value / earn_per_amount), so an owner cannot misread
the scale. PUT applies the body on top of the current settings: fields left
out keep their value, null clears an optional limit, and unknown fields are
refused so a typo cannot be ignored silently. The read-only fields of the
GET response are accepted and ignored, so a client can send back what it
received. It returns the keys that changed. Values outside the F1 bounds
answer 400, and an outlet of another organization 404.
RequireAdminOrManager also lets the purchasing role through, so loyalty
settings and the manual wallet adjustment from PC-107 now use a stricter
RequireLoyaltyManager (superadmin, admin, manager, owner).
Adds a test that registers every route, since gin panics at startup when
two routes name the same path parameter differently.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Adds LoyaltySettingsProcessor (docs/prd-point-coin.md F1, F2, F12, PC-109).
Reading returns typed settings for an outlet (earning per currency, paying
with EnakPoint) and for an organization (point value, exchange rate,
transfers, and the expiry settings awaiting note N4). A key that was never
set takes the PRD default. A stored value that is unusable, such as an
earn_per_amount of 0 that would divide by zero, also falls back to the
default and is logged, so a bad row never reaches a calculation.
Writing takes the whole settings struct, validates every rule in the PRD
before touching the database, and stores and records in
loyalty_setting_changes only the keys whose effective value changes: old
value (NULL while it was on its default), new value, and who changed it.
Clearing a limit deletes the stored value. Each save runs in one
transaction under an advisory lock per outlet or organization, so two saves
at once cannot both compute their change from the same old value. The
outlet must belong to the caller's organization.
Every key is described once (key, default, valid range, bound field), and
reading, validating and diffing all use that description.
GET /customer/wallet now reads the point value through this processor; the
minimal organization settings repository from PC-106 is removed.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Adds the reconciliation of docs/prd-point-coin.md §7.5 (PC-108). One
aggregate query per check, across every wallet:
- wallet balance = SUM(ledger), per currency, including customers with
ledger rows but no wallet row
- wallet balance = SUM(lot remaining)
- lot original - SUM(allocations) = remaining
- SUM(allocations) = |amount| for every deduction
- lots created = amount for every addition, which the engine keeps and the
other checks rely on
The check on payments.points_used waits for that column (PC-305).
WalletReconciliationJob runs the checks at startup and every six hours,
alongside the omset scheduler. It is silent while the data is consistent.
Each discrepancy is logged with its check, customer, object and the
expected and actual values, and the organization's admins, owners and
managers get a high-priority notification. An organization is notified
again only when its set of discrepancies changes. Nothing is corrected
automatically. At most 50 discrepancies per check are reported.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Adds the dashboard side of a customer's wallet (docs/prd-point-coin.md F7,
PC-107), under /marketing for admins and managers:
- GET /marketing/customers/:id/wallet returns the customer, the ledger and
spendable balances, every lot that still holds something (flagged when
expired), and a page of history. Unlike the customer's own view, each row
carries the real names behind it: the transfer counterparty, the admin or
cashier, and the outlet, plus the reason and metadata.
- POST /marketing/customers/:id/wallet/adjust takes a signed amount and a
required reason. It writes an ADJUSTMENT pointing at the admin through the
wallet engine, refuses to take more than the customer can spend, and
accepts an optional idempotency key so a retried request adjusts once.
Reasons describing a cash-out are refused (K7).
The customer must belong to the caller's organization; otherwise both
endpoints answer 404. Positive adjustments create non-expiring lots until
the expiry model is decided (F12, note N4).
The mapping from ledger rows to what the apps show is now shared between the
customer and dashboard views.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
GET /customer/wallet now reads the EnakPoint & EnakCoin wallet
(docs/prd-point-coin.md F6, PC-106): spendable point and coin balances, the
rupiah value of one EnakPoint and of the balance, the nearest day each
currency loses balance (grouped by Asia/Jakarta day), and recent ledger
rows. The fields of the pre-wallet response stay, filled from the wallet, so
app versions that read them keep working.
Adds GET /customer/wallet/transactions with pagination and filters for
currency, one or more types, and an inclusive date range. Each row shows
where the value came from (additions) or went to (deductions) as in §8.1,
and additions list their lots and earliest expiry. The counterparty id, the
admin and the metadata are left out; the description already carries the
masked name. A malformed query answers 400, a missing customer 404.
/customer/points and /customer/tokens keep their shape and now read the
wallet too, so customer_points_repository is no longer used for balances.
Balances are what the customer can spend: lots that have expired but that
the expiry job has not processed are not counted. The point value is read
from organization_settings (loyalty.point.value, default 1) through a small
repository that the typed settings reader in PC-109 will build on.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Adds cmd/wallet-migrate (make wallet-migrate, args=-dry-run to only report),
which moves customer_points and customer_tokens into the wallet
(docs/prd-point-coin.md §10, PC-105). Each customer gets a MIGRATION ledger
row and a non-expiring lot per currency, written through WalletProcessor in
one transaction per customer. EnakCoin is the sum of every token type (Q6),
with the legacy rows listed in the row's metadata.
It credits the difference between the legacy balance and what earlier runs
migrated, so running it again never doubles a balance and picks up only
what the old code added since. A legacy balance that shrank after being
migrated is reported and left alone, since only an admin adjustment may
take balance away, and the command then exits non-zero. It ends with a
legacy / migrated / wallet total per currency.
Migration 000092 renames TOKENS to COINS in campaigns.type and
campaign_rules.reward_type. The campaign API now validates COINS; it still
accepts TOKENS, including as a list filter, and stores it as COINS so older
dashboards keep working while they are updated.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
GetTransactionByIdempotencyKey used First, so every wallet operation with a
key not seen before, which is the normal case, logged a "record not found"
error. It now uses Find with a limit and returns nil when nothing matches.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
WalletProcessor writes the balance, the ledger row and the lots or
allocations together, which keeps SUM(ledger) = balance = SUM(lot
remaining) (docs/prd-point-coin.md §7.5, PC-104).
- Credit writes the ledger row and creates lots, each with its own expiry
and origin lot.
- Debit draws from the preferred lots first (a reversal's own lots, or the
lot being expired), then from unexpired lots in K9 order, and returns the
allocations with their expiry so CarryOver can give the receiving side of
a transfer or exchange the same expiry.
- DebitUpTo takes what the wallet has and reports the shortfall (F10, Q3).
- An idempotency key returns the first result; reusing it for a different
operation is an error.
- §8.1 is checked in code from one rule table, ahead of the database
constraints, so callers get a readable error.
Each method locks the wallet itself, after validating the input and before
checking the idempotency key, so correctness does not depend on the caller.
Operations on two wallets still call LockWallets first to keep lock order.
Unit tests run on an in-memory repository and check the §7.5 invariants
after every scenario; one more test runs the engine against Postgres when
TEST_DATABASE_URL is set.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Entities for the four wallet tables and a WalletRepository that the wallet
processor will build on (PC-103).
Every method goes through the caller's transaction, and writes and locks
refuse to run without one: outside a transaction a lock is released as soon
as it is taken and a balance could move without its ledger row.
- LockWallet creates the wallet on first use, taking the organization from
the customer, then locks it with SELECT ... FOR UPDATE.
- LockWallets always locks in customer_id order so opposite transfers
cannot deadlock.
- AddBalance and ConsumeLot are conditional updates that return an error
when they would overdraw, instead of tripping the CHECK constraint.
- ListActiveLots returns unexpired lots with balance in K9 spending order.
The tests need a real Postgres and run only when TEST_DATABASE_URL points at
a migrated database. Both the lock and the lock ordering were checked by
removing them and watching the tests fail (lost update, deadlock detected).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A weight-based line is one weighing, so order_items.quantity is pinned to 1
while unit_price and unit_cost are per unit of weight. Analytics SQL was
multiplying and dividing per-unit rates by the raw quantity, costing a 4.2 ons
fish as a single ons: standard_hpp_total and moving_average_hpp_total came out
far too low across all four product reports, overstating gross profit, and
average_price and fifo_hpp_per_unit read per weighing while
standard_hpp_per_unit read per unit, so the three HPP figures in one row could
not be compared.
Adds billableQty and billableQtyNet as the single place that decides the
multiplier, mirroring entities.OrderItem.BillableQuantity.
quantity_sold and total_items stay as weighing counts; weight_sold already
carries the amount. revenue and fifo_hpp_total were already correct via
total_price/total_cost.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
CreateOrderContractToModel and AddToOrderContractToModel copied every order
item field except Weight, so a weight sent by the client never reached the
processor and every weight-based line failed with "product ... is sold by
weight and requires a weight".
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
A product sold by weight with no unit produces order lines with nothing to
print: the receipt would read "4,2" with no idea of what. Until now nothing
stopped that — the mistake only surfaced at the cashier.
Enforce it in two places, because neither alone sees the whole picture. On
create, the validator has everything it needs. On update, the request may
omit unit_id for a product that already has one, so the check runs in the
processor against the merged product: what is rejected is the end state, a
product sold by weight with no unit.
Also fixes two things this uncovered:
The struct tags on the product contracts are decorative — this validator is
hand-written and never calls validator.Struct — so `oneof=unit weight` was
never enforced, and an unknown sell_by was silently rewritten to "unit" by
the mapper. It is now rejected with a message that names the valid values.
The update validator's "at least one field" guard did not list unit_id,
sell_by or print_to_checker, so an update carrying only one of those was
turned away as an empty request.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Products like fish are sold per weighing (4.2 ons, 5.6 ons), which the
order line could not represent: quantity is INTEGER and prices are always
computed as quantity * unit_price.
Model one weighing as one order line. quantity stays INTEGER and keeps
meaning "how many items"; the measured amount goes into a new nullable
order_items.weight, and the line is priced weight * unit_price. Two
weighings of the same product are two lines, never merged into one.
Keeping quantity integral avoids float comparisons in void, refund and
split bill, where accumulated rounding error would silently misbehave —
"1.4 + 1.4 + 1.4" is not 4.2 in float64, which would leave a fully paid
split-bill item marked unpaid.
BillableQuantity() is now the single place that decides between weight
and count; every price and cost calculation goes through it. Missing one
would bill a 4.2 ons fish as a single ons — wrong money, no error.
Two database constraints back the design: a weighed line always carries a
positive weight, and its quantity is pinned to 1. The latter also makes
void all-or-nothing for weighed lines, so the row-splitting branch can
never produce a zero-weight remainder row.
Also wires product.unit_id through the API, which was previously not
settable at all, and corrects the misleading comment on the request's
unit_price field — that value has never been used; price always comes
from the database.
Design notes and the audit of every price multiplication site are in
docs/rfc-weight-based-products.md.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
efrilmandClaude Opus 5.5
aefril
ryan