## MCP Phase 3 — OAuth 2.1 for Claude Desktop/web & ChatGPT connectors
Phase 1 shipped a read-only MCP server (#689); Phase 2 added write tools
+ the read/read_write token scope (#690). This phase adds **OAuth 2.1
(Authorization Code + PKCE)** so Anthropic's Claude Desktop/web custom
connectors and OpenAI's ChatGPT connectors can authenticate — those
clients sign in with OAuth rather than pasting a static bearer token, so
until now they only saw a "coming soon" note.
It reuses `laravel/mcp`'s built-in OAuth support (inert until Passport
is installed) wired to `laravel/passport ^13`. We do not hand-write the
authorization server, discovery endpoints, DCR endpoint, or the
`WWW-Authenticate` challenge — the package provides all of it.
### What's in it
- **`laravel/passport ^13`** + an `api` (passport) guard alongside the
existing session `web` guard; Passport migrations (UUID user columns),
config, and signing keys.
- **`Mcp::oauthRoutes()`** — RFC 8414/9728 discovery, RFC 7591 DCR
(`oauth/register`), and the `mcp:use` scope.
- **A second MCP endpoint `POST /mcp/oauth`** guarded by `auth:api`. The
existing Sanctum `/mcp` endpoint (Claude Code static PAT) is left 100%
unchanged.
- **On-brand OAuth consent screen** (Blade, light + dark, localized)
naming the connecting client and its redirect host, and stating plainly
what the connection can do (read/analyse + make changes, bank-connected
data excepted).
- **Settings UI**: the "Claude Desktop & ChatGPT" block now shows real
connect instructions (the `/mcp/oauth` URL to add as a custom connector,
no token needed) instead of "coming soon".
## Decision #1 — OAuth connections have read + write access
`laravel/mcp` advertises and uses a single `mcp:use` scope; it has no
read/write granularity, so there is no per-connection scope choice over
OAuth. **OAuth connections get full read + write access**, gated by the
user explicitly approving the connection on the Whisper Money consent
screen. (An earlier revision made them read-only; that restriction has
been lifted per request.)
`WriteTool` (`app/Mcp/Tools/WriteTool.php`) grants writes when the
request resolves through the `api` (Passport) guard **or** carries a
Sanctum `mcp:write` ability; a read-only Sanctum PAT is still rejected.
Bank-connected accounts and their transactions remain read-only for
every caller (only manual data can be created/edited/deleted; any
transaction can still be categorised/labelled). The consent screen and
settings copy state the read + write capability and the bank-connected
exception.
Possible follow-up: a consent-time read-only/read-write toggle, if
per-connection granularity is wanted (not offered by the standard MCP
OAuth flow's single scope).
## Other locked decisions
- **Route topology**: a separate `/mcp/oauth` endpoint rather than
multi-guarding `/mcp`. Keeps the Claude Code path unchanged (its
`abilities:mcp:read` gate would 403 an OAuth `mcp:use` token) and gives
each client type a clean documented URL. The package's nested discovery
`/.well-known/oauth-protected-resource/mcp/oauth` returns `resource =
url('/mcp/oauth')`.
- **Registration**: ship DCR (`oauth/register`). Redirect allowlist
tightened to `https://claude.ai` and `https://chatgpt.com` only — no
wildcard. CIMD is a possible later enhancement; both clients accept DCR.
## Deviation from the original plan — the User model is untouched
The plan proposed aliasing Passport's `HasApiTokens` trait alongside
Sanctum's (with `insteadof`/`as`) and implementing `OAuthenticatable`.
**Both are impossible here and, it turns out, unnecessary:**
- The two `HasApiTokens` traits declare an **incompatible `$accessToken`
property** (Sanctum untyped vs Passport `?ScopeAuthorizable`), which is
a hard PHP fatal that `insteadof` cannot resolve (it only resolves
methods).
- `OAuthenticatable::tokens(): HasMany` is incompatible with Sanctum's
canonical `tokens(): MorphMany`, and the Claude Code PAT suite depends
on Sanctum's `tokens()`. The interface is never enforced at runtime by
Passport (docblock-only).
- Passport's resource guard only calls `$user->withAccessToken()`, which
Sanctum already provides (untyped, so it accepts the Passport
`AccessToken`); and Passport's `AccessToken::can()` makes
`tokenCan('mcp:write')` behave correctly for OAuth tokens. So Sanctum
stays canonical and the Claude Code PAT path is genuinely unchanged.
## Signing keys (deploy note)
Passport signs OAuth tokens with a key pair. This PR provisions it
everywhere it's needed: CI (`passport:keys` before tests), the
production Docker entrypoint (generates into the persisted `storage/`
volume unless provided via `PASSPORT_PRIVATE_KEY`/`PASSPORT_PUBLIC_KEY`
env), `worktree.sh`, and a documented `.env.example` entry. **For a
multi-instance deployment, set `PASSPORT_*` env** so every instance
validates tokens with the same key.
## Tests (`tests/Feature/Mcp/McpOAuthTest.php`)
Discovery metadata (RFC 9728/8414), the mandatory **401 bootstrap**
challenge + `WWW-Authenticate` header, DCR (allowed + rejected redirect
URIs), the full **Authorization Code + PKCE** flow reaching a read tool,
and **write access over OAuth** (an OAuth connection calling
`create_label` succeeds and the row is created). The existing
`McpTokenTest` / `Mcp/*` suites (incl. the read-only Sanctum PAT
guardrail) and `LocalizationTest` still pass unchanged.
## QA
- **Protocol** (curl, over HTTPS): both discovery endpoints return the
exact required JSON; unauthenticated `POST /mcp/oauth` returns `401` +
`WWW-Authenticate: Bearer …
resource_metadata="…/.well-known/oauth-protected-resource/mcp/oauth"`;
DCR accepts `claude.ai`/`chatgpt.com` callbacks and rejects others with
`400 invalid_redirect_uri`.
- **Browser**: consent screen verified in light and dark mode (client
name, signed-in email, redirect host, read + write capability +
bank-connected read-only note, Cancel/Connect); updated settings page
verified. No JS errors.
- Full PKCE token exchange + a write tool call is covered by the green
Pest e2e test.
## Fast-follows (not in this PR)
- **"Connected apps" revoke UI** — `McpTokenController` manages only
Sanctum PATs today, so there's no in-app revoke for OAuth grants yet.
The consent copy says "disconnect from the connected app" for now; a
Passport-grant list + revoke is the top follow-up (more important now
that OAuth grants can write).
- CIMD registration; optional consent-time read-only/read-write toggle.
## Stacking
Was developed stacked on `mcp-write-tools` (#690), itself on #689.
**Both have since merged to `main`**, so this branch was rebased onto
`main` (`git rebase --onto origin/main mcp-write-tools`) and targets
`main` directly.
## What & why
Fixes the Sentry N+1 **PHP-LARAVEL-3V** — `N+1 insert into jobs` on
`POST /transactions`.
### Root cause
Laravel's **event discovery is on by default** (the base
`EventServiceProvider` sets `$shouldDiscoverEvents = true`, and this app
has no subclass to turn it off), so every listener in `app/Listeners` is
already wired to its event by its `handle()` type-hint.
`AppServiceProvider::boot()` was **also** registering six of them with
`Event::listen(...)`, so each ended up registered **twice** — every
queued listener published its job twice per event.
Concretely, creating a transaction dispatched
`AssignTransactionToBudget` and `CategorizeTransactionWithAi` twice each
→ repeated `insert into jobs` in one request. (The same bug made
`PostStripeEventToDiscord` post to Discord twice per webhook,
`ApplyAutomationRules` run twice, etc.)
## Changes
1. **`AppServiceProvider`** — drop the redundant explicit
`Event::listen` calls and rely on discovery, which already wires every
listener exactly once (`ScheduleDripEmailsListener` and
`SyncUserToResendListener` were discovery-only already). Verified with
`php artisan event:list`: each event now has a single listener, and the
synchronous `ApplyAutomationRules` still runs first on
`TransactionCreated`.
2. **`CategorizeTransactionWithAi`** — add `shouldQueue()` so the job
isn't even published when it would immediately no-op (already
categorized by a rule, encrypted, or user not AI-eligible — the default,
since AI is opt-in). The same guard still runs in `handle()` because
state can change while the job waits.
Together these remove the second `insert into jobs` on transaction
creation for the common (non-AI) path.
## Tests
- New `tests/Feature/Ai/CategorizeTransactionWithAiListenerTest.php`:
the AI job is queued **once** for an eligible uncategorized transaction,
and **not at all** when the user has no AI consent or the transaction is
already categorized.
- Full suite: **1828 passing**. The one failure (`DashboardTest` → 409)
is **pre-existing on `main`** (Inertia asset-version mismatch from a
local build manifest) and reproduces with these changes reverted —
unrelated to this PR.
Fixes PHP-LARAVEL-3V
## What
Adds a `DEMO_ENABLED` env var (`config('app.demo.enabled')`, default
`true`) to fully toggle the demo account. Setting `DEMO_ENABLED=false`
in production blocks it without code changes.
When disabled:
- **Login is blocked** — `Fortify::authenticateUsing` rejects the demo
account with a generic credentials error (doesn't reveal the demo is
off). Regular users and 2FA are unaffected.
- **Landing link hidden** — the "Check Demo" button on the landing page
is removed (shared `demoEnabled` prop).
- **No credential prefill** — `demoCredentials` is only shared when
enabled, so `/login?demo=1` no longer autofills.
## Why
The demo account is publicly shared and gets abused (e.g. duplicate
votes on integration requests). This gives us a kill switch.
## Tests
Added to `DemoAccountRestrictionsTest`:
- demo account cannot log in when disabled
- demo account can log in when enabled
- regular user can still log in when demo is disabled
Existing auth + 2FA tests still pass.
## What
Auto-categorizes transactions with AI (Gemini) for **pro +
AI-consented** users when no automation rule already matched. Ships the
full backend **behind a Pennant flag, off by default**, so it's
mergeable and testable in isolation; the UI is a deliberate follow-up.
## Why / cost
Prod check first: ~20k txns/month, **~52% of pro-user transactions are
uncategorized** after rules. At Gemini Flash-Lite rates the cost is a
**rounding error** — ~$0.13–$0.75/month for all pro users, single-digit
dollars even on full Flash. So the model is chosen for accuracy, not
price; the real constraints are trust, accuracy and privacy.
## How it works
**Two tiers** (every transaction is covered, rules are an optimization
on top):
- **Tier 1 – label** — a queued listener runs *after* the synchronous
rules; if still uncategorized and the user is eligible, the model picks
a **leaf** category (referenced by numeric index, never a UUID, so it
can't hallucinate one). Auto-applied only above the **label bar**
(`0.7`); below → left blank, no nag. Tagged `category_source = ai` +
`ai_confidence`, fully reversible.
- **Tier 2 – learn** — above the higher **rule bar** (`0.85`) *and* a
clean merchant key *and* the model flags the merchant unambiguous → the
merchant is appended to a single **ai-owned** automation rule for that
category (OR'd conditions, not rule-sprawl), so future transactions
match for free and consistently. AI rules sit at the lowest priority;
**user-owned rules are never touched**.
**Self-heal + signal** — when a user overrides an AI category, a
`category_correction` is logged (calibration signal, bucketable by
confidence) and the offending merchant condition is dropped from the ai
rule (deleted if empty). User rules and manual categories are untouched.
**Safety** — config kill switch + pro + active consent + gradual Pennant
rollout. Dedicated `ai` queue so Gemini never blocks bank syncs.
Encrypted (client-side) transactions are never sent.
**Backfill** — `ai:categorize-backfill {user}`, explicit opt-in,
batched, learns rules as it goes.
## Data model
- `transactions`: `category_source`, `ai_confidence`,
`categorized_by_rule_id`
- `automation_rules`: `origin` (`user`/`ai`)
- new `category_corrections` table
## Screenshots
<img width="921" height="384" alt="image"
src="https://github.com/user-attachments/assets/f04c2a03-b39e-4a3d-81eb-ecf26eaefb83"
/>
Suggests transaction categorization rules during onboarding.
After a sync or import, it groups the uncategorized transactions, asks
Gemini (via laravel/ai) to map the common merchants to categories, and
shows the results for review. The user edits or drops any and creates
the ones they want. During onboarding the accepted rules also categorize
existing transactions right away.
Off by default: it needs the `AiRuleSuggestions` Pennant flag and a
per-user AI consent. The model and thresholds are config-driven.
`ai:suggest-rules {user}` prints what a user would get.
The settings-page surface and monthly regeneration are a follow-up.
## What
Adds two timestamp columns to `users`:
- **`last_logged_in_at`** — set by an `UpdateLastLoggedInAt` listener on
Laravel's `Login` event. Records each explicit authentication (login
form or remember-me re-auth). Does **not** update on plain session-based
requests.
- **`last_active_at`** — set by a `TrackLastActiveAt` middleware on
authenticated web requests. Records the last moment the user did
anything. Throttled to at most one write per 5 minutes to avoid a DB
write on every request.
## Why
`last_logged_in_at` answers "when did they last authenticate";
`last_active_at` answers "when were they last using the app" (any
screen/activity), which a session-based login does not capture.
## Tests
- Login records `last_logged_in_at`
- Authenticated request records `last_active_at`
- Throttle window respected (no rewrite within 5 min) and refreshed once
it passes
Migrations not yet run on environments.
## What
Adds a private Discord admin feed with two flows, both posting through
one webhook (`DISCORD_WEBHOOK_URL`):
### 1. Daily stats — `stats:daily-report`
Scheduled **09:00 Europe/Madrid**. Posts an embed with:
- New users created **yesterday** (Madrid calendar day, converted to UTC
for the query)
- Total users
- Active/trialing counts + current & projected **MRR / ARR** per
currency
Reuses the #457 Stripe stats logic, extracted into
`SubscriptionStatsCollector` so the existing `stripe:subscription-stats`
command and this report share one source of truth.
### 2. Stripe events — `PostStripeEventToDiscord`
Queued listener on Cashier's `WebhookReceived`. Posts on:
- `customer.subscription.created` / `updated` / `deleted`
- `invoice.payment_succeeded` / `payment_failed`
## Setup
- `DISCORD_WEBHOOK_URL` — added to prod ✅ (set locally to test)
- Stripe dashboard must send the 5 event types above to the existing
Cashier `/stripe/webhook` endpoint
- A queue worker must be running (listener is `ShouldQueue`)
## Tests
13 passing: Discord client (3), daily report (2), Stripe event listener
(4), plus the existing stats command (4) still green after the refactor.
## Summary
- keep Stripe past_due subscriptions active during retry window
- share payment issue state with Inertia and show persistent toast
- send toast action directly to Stripe Billing Portal
- allow canceled users to fall back to free plan, while paid-only bank
connection access remains blocked
- add Spanish translations for new payment issue messages
## Tests
- vendor/bin/pint --dirty --format agent
- php artisan test --compact tests/Feature/SubscriptionTest.php
tests/Feature/InertiaSharedDataTest.php
- php artisan test --compact tests/Feature/LocalizationTest.php
- npm test -- subscription-payment-issue-toast
Note: npm run types still fails on pre-existing unrelated TypeScript
errors.
## Summary
Wires up the launch flow: each waitlist lead gets a per-cohort
invitation email, a personal single-use Stripe promo code matching their
reward, and a signed landing link that unlocks register/install.
## Cohorts (resolved at send-time, by queue rank ASC, ignoring
`position` null/0)
| Cohort | Rule | Reward | Stripe coupon |
|---|---|---|---|
| `founder` | ranks 1–10 | Free forever | `wm_founder_forever` (100%
off, forever) |
| `founder_referrer` | referred any current founder (overrides rank) |
Free forever | `wm_founder_forever` |
| `early_bird` | ranks 11–100 | 2 mo free monthly / 3 mo free yearly
first year | `wm_earlybird_monthly` (100% off, 2 mo, monthly only) +
`wm_earlybird_yearly` (25% off once, yearly only) |
| `waitlist` | ranks 101+ | same as early bird | same coupons |
## What's added
- **DB**: `cohort`, `promo_code_monthly`, `promo_code_yearly`,
`invitation_sent_at` on `user_leads`.
- **Services**: `LeadCohortResolver`, `LeadPromoCodeAllocator`.
- **Commands**:
- `php artisan stripe:ensure-launch-coupons` — idempotent Stripe coupon
setup (run once per env).
- `php artisan leads:send-invitations --limit=N [--cohort=…] [--dry-run]
[--force]` — wave-by-wave delivery, idempotent across runs
(`invitation_sent_at` gate). Lazily generates Stripe promo codes per
lead it touches.
- **Checkout**: `SubscriptionController::checkout` resolves the auth
user's `UserLead` by email and applies the matching promo code
(`monthly`/`yearly`) via Cashier's `withPromotionCode()`.
- **Invite link**:
`LandingAuthOverrideService::generateInvitationUrl($leadId, days: 30)` —
signed lead-bound URL that unlocks auth buttons (existing override
cookie) and stores `invited_lead_id` in session. The register view
prefills the email from the lead.
- **Emails**: 4 cohort markdown templates (`founder`,
`founder-referrer`, `early-bird`, `waitlist`) with per-cohort subject +
body. Locale set from `$lead->preferredLocale()`. 28 Spanish keys added.
## Tests (Pest)
- `LeadCohortResolverTest` — boundaries + founder-referrer override +
null/0 position skip.
- `SendUserLeadInvitationsTest` — batch ordering, idempotent across
runs, ignores null/0, persists cohort.
- `UserLeadInvitationTest` — per-cohort body content, signed lead-bound
signup URL, Spanish locale.
- `LandingAuthOverrideTest` — invitation URL unlocks + stores session
lead.
Full suite green (1262 passed).
## Launch checklist
1. Merge + deploy.
2. `php artisan stripe:ensure-launch-coupons` against staging Stripe →
verify in dashboard → run on prod.
3. Optional preflight: `php artisan leads:send-invitations --limit=10
--dry-run`.
4. Wave-by-wave: `php artisan leads:send-invitations --limit=50` per
day.
5. Confirm `HIDE_AUTH_BUTTONS=true` on prod so only signed invite links
unlock register/install.
## Notes / non-goals
- No `User → UserLead` foreign key — checkout matches by email per
request.
- Existing `FOUNDER` promo flow is untouched and still kicks in if a
user has no lead-specific code.
- `founder_referrer` cohort is empty in current prod data; logic is in
place for when founders start referring.
## Summary
- add signed landing links that unlock auth buttons while
HIDE_AUTH_BUTTONS is enabled
- persist the unlock in a secure cookie so desktop and installed PWA
users can still sign up
- add artisan command to generate signed landing auth links and test
coverage for the flow
## Testing
- php artisan test --compact tests/Feature/LandingAuthOverrideTest.php
tests/Feature/Console/GenerateLandingAuthLinkCommandTest.php
tests/Feature/Auth/RegistrationTest.php
- php artisan test --compact tests/Feature/WelcomeBanksOrderingTest.php
tests/Feature/SubscriptionTest.php
- vendor/bin/pint --dirty --format agent
## Summary
- remove the `real-estate` Pennant flag definition, request gating,
local auto-activation middleware, and frontend shared flag plumbing
- make real-estate account creation and onboarding availability the
default path for all users
- update feature and browser tests to cover default availability instead
of flag enable/disable behavior
## Testing
- vendor/bin/pint --dirty --format agent
- php artisan test --compact tests/Feature/RealEstateTest.php
- php artisan test --compact
tests/Feature/RealEstateAvailabilityTest.php
- php artisan test --compact tests/Browser/RealEstateAccountTest.php
- php artisan test --compact tests/Browser/OnboardingFlowTest.php
- php artisan test --compact --filter=\"can create a real estate account
linked to an existing loan\" tests/Browser/BankAccountsTest.php
## Notes
- `npm run build` completed the client build, but the Sentry sourcemap
upload step failed with an SSL/TLS error from the configured plugin
- deploy follow-up: run `php artisan pennant:purge real-estate` to
remove stale stored flag values
## Summary
- allow `/register?force=1` to bypass the hidden-auth redirect and
render the registration page
- preserve the `force=1` query on form submit so hidden signup still
works end-to-end
- enforce hidden-signup blocking in the Fortify user creation path and
cover the forced/unforced flows with tests
## Summary
- remove the Pennant-based `open-banking` flag and middleware gating so
open banking is always available for authenticated users
- simplify landing, onboarding, settings, and subscription flows to use
always-on open-banking behavior and remove stale frontend/shared flag
plumbing
- update open-banking tests and purge stored `open-banking` Pennant rows
## Testing
- `php artisan test --compact
tests/Feature/OpenBanking/InstitutionControllerTest.php`
- `php artisan test --compact
tests/Feature/OpenBanking/BinanceControllerTest.php`
- `php artisan test --compact
tests/Feature/OpenBanking/IndexaCapitalControllerTest.php`
- `php artisan test --compact
tests/Feature/OpenBanking/BitpandaControllerTest.php`
- `php artisan test --compact
tests/Feature/OpenBanking/AuthorizationControllerTest.php`
- `php artisan test --compact
tests/Feature/OpenBanking/ConnectionControllerTest.php`
- `php artisan test --compact
tests/Feature/OpenBanking/AccountMappingTest.php`
- `php artisan test --compact
tests/Feature/OpenBanking/OpenBankingFeatureFlagTest.php`
- `php artisan test --compact
tests/Feature/OpenBanking/SyncRetryAndLoggingTest.php`
- `php artisan test --compact tests/Feature/SubscriptionTest.php`
- `php artisan test --compact
tests/Feature/WelcomeBanksOrderingTest.php`
- `vendor/bin/pint --dirty --format agent`
## Notes
- `php artisan pennant:purge open-banking` was run to remove stale
stored values
- `php artisan test --compact tests/Browser/OnboardingFlowTest.php`
still has one unrelated real-estate onboarding browser failure (`it
creates a real estate account during onboarding when feature is
enabled`)
## Summary
- Removes the `account-mapping` Pennant feature flag entirely, making
the account mapping flow (pending accounts data + map-accounts page) the
default and only code path
- Removes the old direct-creation branches from all banking controllers
(Authorization, Bitpanda, Binance, IndexaCapital)
- Extracts a shared `CreatesAccountsFromPending` trait for the
onboarding auto-create logic
- Updates all controller tests to reflect the always-on mapping behavior
## Changes
### Backend
- **AppServiceProvider** — removed `account-mapping` flag definition
- **AuthorizationController** — removed flag check +
`createAccountsFromSession()` dead code; always stores
`pending_accounts_data` and redirects to mapping
- **BitpandaController / BinanceController / IndexaCapitalController** —
removed flag checks, old inline account creation, and unused imports
- **HandleInertiaRequests / ActivateDevelopmentFeatures /
ResolvesFeatures** — removed `account-mapping` from flag arrays
- **New `CreatesAccountsFromPending` trait** — shared auto-create logic
for onboarding path (to be consumed next)
### Frontend
- Removed `'account-mapping'` from the TypeScript `Features` interface
### Tests
- Merged flag-specific test variants into single always-on tests
- Removed redundant tests that tested the old disabled-flag code path
- Updated assertions to check `pending_accounts_data` instead of direct
account creation
## Summary
- Adds **real estate** as a new account type (`real_estate`) for
tracking property assets within the existing Accounts page
- Properties store metadata (type, address, purchase price/date, area,
notes) in a dedicated `real_estate_details` table with a one-to-one
relationship to accounts
- Properties can be **linked to a loan account** (mortgage) to
implicitly calculate equity — property value counts as asset (+), linked
loan counts as liability (-)
- Market value is tracked as the account balance and uses "market value"
terminology throughout the UI
## What's included
### Backend
- `PropertyType` enum (Residential, Commercial, Land, Vacation, Other)
- `RealEstateDetail` model, factory, migration, policy
- `StoreRealEstateDetailRequest` and `UpdateRealEstateDetailRequest`
form requests
- `RealEstateDetailController` with `update()` for editing property
details
- Extended `Settings\AccountController@store` to create
`RealEstateDetail` when type is `real_estate`
- Extended `AccountController@show` to load real estate detail, linked
loan with bank info, and available loan accounts
- Extended `AccountController@index` SQL ordering to include
`real_estate`
- Conditional validation rules in `StoreAccountRequest` for real estate
fields
### Frontend
- New `real_estate` type in `account.ts` with `PropertyType`,
`AreaUnit`, `RealEstateDetail` interface, and helper functions
- Conditional real estate fields in `account-form.tsx` (property type,
address, purchase price, purchase date, area, linked loan, notes)
- `PropertyDetailsCard` component in `Accounts/Show.tsx` with view and
inline edit modes
- "Update market value" terminology in balance update buttons for real
estate accounts
- `real_estate` added to account type ordering and groups on the Index
page
- Wayfinder routes regenerated
### Tests
- 22 feature tests covering creation, validation, show page, index
ordering, updating details, IDOR protection, model relationships, and
soft delete behavior
- Unit test updates for `AccountType` enum (`reducesNetWorth`,
`isNonTransactional`)
### Translations
- 32 new Spanish translation strings for all real estate UI
## Design decisions
- Real estate accounts are **non-transactional** (like
investment/retirement) — balance-only tracking for now. Future iteration
will link transactions directly for rental income/expense tracking
- **Single loan per property** via direct FK from
`real_estate_details.linked_loan_account_id`
- No encryption on address/notes fields (opted out per discussion)
- No separate sidebar page — real estate is a grouped section within the
existing Accounts page
## 🚪 Why?
### Problem
PHPStan was running with a baseline of 56 suppressed errors, meaning
static analysis was not enforcing type safety across a significant
portion of the codebase. These errors were real type mismatches,
redundant null-safety operators, and incorrect PHPDoc annotations that
could mask bugs and make the code harder to reason about.
## 🔑 What?
### Changes
- Add `@property` PHPDoc annotations to `Account`, `BankingConnection`,
`ExchangeRate`, and `Transaction` models so Enum casts and typed columns
are visible to PHPStan
- Add `instanceof User` guards in `ScheduleDripEmailsListener`,
`SyncUserToResendListener`, and `FortifyServiceProvider` to properly
narrow `Authenticatable` to `App\Models\User`
- Remove redundant `?? false` and unnecessary nullsafe `?->value` in
`HandleInertiaRequests`
- Fix `SyncBankingConnectionJob`: use `->name` instead of `?->name` on
an always-loaded `bank` relation
- Remove `is_countable()` guard in `BalanceLookup` (parameter is always
`Collection|array`, both countable)
- Remove `?? []` / `?? default` fallbacks on fully-typed array keys
across `BalanceSyncService`, `BinanceBalanceSyncService`,
`BinanceClient`, `BitpandaBalanceSyncService`, `BitpandaClient`,
`IndexaCapitalClient`, `IndexaCapitalBalanceSyncService`, and
`AuthorizationController`
- Fix `BinanceClient::publicClient()` `retry()` call: use `when:` named
argument and `\Throwable` type hint to match `PendingRequest::retry()`
signature
- Update `IndexaCapitalClient::getPerformance()` `@return` to include
`portfolios` and `net_amounts` keys; simplify sync service to remove
dead null checks
- Replace nullsafe chain with ternary in `BudgetPeriodService`
- Replace `match` statement in `SetupMainUser` with `if/else` to
eliminate always-true comparison
- Clear `phpstan-baseline.neon` entirely (was 56 suppressed errors, now
0)
## ✅ Verification
### Tests
- Existing tests pass: PHPStan level 5 reports 0 errors with empty
baseline
## Summary
- Removes the `plaintext-transactions` Pennant feature flag — plaintext
is now the default for all users
- Removes encryption guards and `isPlaintext` conditionals from
transaction create/edit/import flows, keeping only the plaintext code
paths
- Makes `EncryptionKeyButton` conditional — only shown when user has
legacy encrypted accounts or transactions
- Removes encryption onboarding steps (`step-encryption-explained`,
`step-encryption-setup`) and related state/props
- Updates landing page to replace E2E encryption marketing with
privacy-first messaging ("Your Data, Your Rules" section)
- Updates privacy policy to replace E2E encryption claims with accurate
security language (encryption at rest, TLS in transit, no third-party
sharing)
- Cleans up tests to remove feature flag assertions and
`Feature::activate()` calls
**22 files changed, 145 insertions, 730 deletions**
## Test plan
- [x] Create a transaction without encryption key unlocked — should
succeed
- [x] EncryptionKeyButton should not appear in header for users with no
encrypted data
- [x] EncryptionKeyButton should appear for users with legacy encrypted
transactions/accounts
- [x] Landing page has no E2E encryption references, shows new privacy
section
- [x] Onboarding flow has no encryption setup steps
- [x] Privacy policy reflects accurate security language
- [x] Frontend builds successfully (`bun run build`)
- [x] All linting passes (`bun run lint`, `vendor/bin/pint --dirty`)
## Summary
- Remove the `budgets` Pennant feature flag — budgets is now enabled for
all users
- Delete `EnsureBudgetsFeature` middleware and its route guard
- Remove `budgets` from shared Inertia features and the `Features`
TypeScript interface
- Remove all `Feature::for($user)->activate('budgets')` calls from tests
- Delete `BudgetFeatureFlagTest` and feature-disabled test cases from
`BudgetsFeatureNavigationTest`
## Summary
- Adds **EnableBanking** as the first open banking provider, allowing
users to connect real bank accounts and automatically sync transactions
and balances
- Uses a **`BankingProviderInterface`** contract so future providers
(Plaid, GoCardless, etc.) can be added by implementing the same
interface
- Feature-flagged behind the **`open-banking`** Pennant flag (default:
off)
- Connected accounts are **unencrypted** and transactions have `source =
'enablebanking'`
### What's included
**Backend:**
- `BankingProviderInterface` contract + `EnableBankingProvider`
implementation (JWT RS256 auth)
- `BankingConnection` model with full lifecycle (pending →
awaiting_mapping → active → expired/revoked/error)
- `TransactionSyncService` — pagination, deduplication by
`external_transaction_id`, amount/date mapping
- `BalanceSyncService` — preferred balance type selection (CLBD → ITAV
fallback)
- Authorization flow: start auth → bank redirect → callback → session
creation → account mapping → sync
- `SyncBankingConnectionJob` (unique per connection, 3 retries) +
scheduled every 6 hours
- `banking:sync` artisan command
- 5 migrations: `banking_connections` table, account fields, transaction
`external_transaction_id`, `pending_accounts_data`, `linked_at`
**Frontend:**
- Manual vs Connected account choice in the create account dialog
- Multi-step bank connection dialog (country → bank selection →
confirmation → redirect)
- Account mapping page — map discovered bank accounts to existing
accounts, create new ones, or skip
- Settings/Connections page with status badges, sync/disconnect actions
- "Connected" badge on linked accounts in settings
**Tests:**
- 49 tests covering feature flags, controllers, account mapping,
transaction sync, balance sync, deduplication, and pagination
### Feature Flags
This PR introduces **two Pennant feature flags**:
1. **`open-banking`** — Gates the entire open banking feature
(institutions endpoint, authorization flow, connections page). When
disabled, all open banking routes return 404.
2. **`account-mapping`** — Controls whether users see an intermediate
account mapping step after connecting a bank. When **enabled**, users
are redirected to a mapping page where they can choose to create new
accounts, link to existing ones, or skip each discovered bank account.
When **disabled**, all discovered accounts are automatically created
(original behavior). Linked accounts only sync transactions from their
last transaction date and only update the current balance from the
provider (no historical balance calculation or daily balance tracking).
Enable per-user:
```bash
php artisan feature:enable open-banking user@example.com
php artisan feature:enable account-mapping user@example.com
```
Enable for all users:
```bash
php artisan feature:enable open-banking all
php artisan feature:enable account-mapping all
```
## Test plan
- [x] Enable feature flag: `php artisan feature:enable open-banking`
- [x] Verify "Connected" option appears in create account dialog
- [x] Start authorization flow and verify redirect to bank
- [x] With `account-mapping` **disabled**: verify callback creates
accounts directly and dispatches sync
- [x] With `account-mapping` **enabled**: verify callback redirects to
mapping page
- [x] Test mapping page: create new, link to existing, and skip actions
- [x] Verify linked accounts sync only from last transaction date and
only update current balance
- [x] Verify connections page shows "Setup Required" badge for
awaiting_mapping status
- [x] Run `php artisan banking:sync` and verify transactions sync
- [x] Verify connections page shows status, sync, and disconnect actions
- [x] Run full test suite: `php artisan test --compact`
## Summary
- Adds `plaintext-transactions` Pennant feature flag (defaults to
`false` / encryption ON)
- When active, new transactions are stored as plaintext (no client-side
encryption)
- Existing encrypted transactions continue to work — detection is based
on `description_iv` being NULL (plaintext) vs present (encrypted)
- Migration makes `description_iv` nullable on the transactions table
## Changes
**Backend:**
- Feature flag definition in `AppServiceProvider`, shared via
`HandleInertiaRequests`
- `StoreTransactionRequest` / `UpdateTransactionRequest` conditionally
require `description_iv`
- `TransactionFactory` gains a `plaintext()` state
**Frontend:**
- Edit dialog and import drawer skip encryption when flag is active
- `EncryptedTransactionDescription` renders plaintext directly when IV
is null
- All decryption loops handle both encrypted and plaintext transactions
- Rule re-evaluation stores notes as plaintext when flag is active
## Test plan
- [x] Run `php artisan migrate` to apply the migration
- [x] Activate flag: `php artisan feature:enable plaintext-transactions
all`
- [ ] Create a transaction — verify description is stored as plaintext
in DB (`description_iv` is NULL)
- [ ] Deactivate flag: `php artisan feature:disable
plaintext-transactions all`
- [ ] Create a transaction — verify encryption is still required (422
without IV)
- [x] Verify old encrypted transactions still display correctly
- [ ] Run `php artisan test --compact
tests/Feature/PlaintextTransactionsTest.php`
## Summary
- Enable the budgets Pennant feature flag for all users by changing the
default from `false` to `true`
## Test plan
- [x] Existing `BudgetFeatureFlagTest` passes (9 tests, 39 assertions)
## Overview
We're excited to introduce budgeting capabilities to Whisper Money! This
feature helps you take control of your finances by setting spending
limits and tracking your progress over time.
## Screenshots
<img width="1316" height="793" alt="image"
src="https://github.com/user-attachments/assets/ac394d36-cded-4ea4-9883-120785e260f1"
/>
<img width="1315" height="907" alt="image"
src="https://github.com/user-attachments/assets/7c682474-5aa7-4388-b626-29b56f5ebbef"
/>
<img width="1315" height="992" alt="image"
src="https://github.com/user-attachments/assets/21eace45-23c6-472d-9aa0-0feb6db3fba4"
/>
## What's New
### Create Flexible Budgets
- Set budgets for specific categories or labels
- Choose from monthly, weekly, bi-weekly, or custom periods
- Set your own budget start date for better alignment with your pay
schedule
### Track Your Spending
- Visual spending charts show how much you've spent vs. your budget
- See at a glance which budgets are on track and which need attention
- View all transactions that count toward each budget
### Smart Budget Management
- **Carry Over**: Unused budget amounts automatically roll into the next
period
- **Reset**: Unused amounts return to your available money pool
- Edit or delete budgets anytime as your needs change
### Easy Access
- New Budgets section in the main navigation
- Quick overview cards showing budget status
- Detailed budget pages with spending history and transaction lists
## How It Works
1. Create a budget by selecting a category or label and setting your
spending limit
2. Your transactions are automatically matched to relevant budgets
3. Track your progress with visual charts and spending summaries
4. Adjust your budgets as needed to stay on track with your financial
goals
This feature is now available behind a feature flag and can be enabled
for users who want to start budgeting their expenses.
## Summary
This PR implements automatic opening of the encryption key unlock modal
immediately after user login when they visit the dashboard. The modal
will only appear once per login session and will not show up on
subsequent dashboard visits or if the user manually clears their
encryption key.
## Problem
Previously, users had to manually click the encryption key button in the
sidebar after logging in to unlock their encrypted data. This extra step
could be confusing for new users and added friction to the login flow.
## Solution
The encryption key modal now automatically opens when users visit the
dashboard immediately after logging in, but **only if**:
1. The user just completed a login (session flag is set)
2. Their encryption key is not already in browser storage
3. Encrypted challenge data is available
## Implementation Details
### Backend Changes
#### 1. Custom Login Response Classes
Created two new response classes that override Fortify's default login
responses:
**`app/Http/Responses/LoginResponse.php`**
- Implements `LoginResponse` contract
- Sets `show_encryption_prompt` session flash variable after successful
login
- Handles both regular login and JSON API responses
**`app/Http/Responses/TwoFactorLoginResponse.php`**
- Implements `TwoFactorLoginResponse` contract
- Sets the same session flag after successful 2FA authentication
- Ensures the modal appears for 2FA users as well
#### 2. Service Provider Registration
**`app/Providers/FortifyServiceProvider.php`**
- Registered custom response classes as singletons in the container
- Fortify now uses our custom responses instead of defaults
#### 3. Dashboard Controller
**`app/Http/Controllers/DashboardController.php`**
- Passes `showEncryptionPrompt` flag from session to frontend
- Uses `session('show_encryption_prompt', false)` which automatically
consumes the flash data
### Frontend Changes
**`resources/js/pages/dashboard.tsx`**
- Added `DashboardProps` interface extending `SharedData` with
`showEncryptionPrompt` boolean
- Updated `useEffect` hook to check three conditions before auto-opening
modal:
1. `props.showEncryptionPrompt` - User just logged in (from session
flash)
2. `!isKeySet` - Encryption key not in browser storage
3. `encryptedMessageData` - Encrypted challenge data loaded
- Includes `UnlockMessageDialog` component that conditionally renders
## How It Works
### User Flow
1. **User logs in** → Custom `LoginResponse` or `TwoFactorLoginResponse`
sets `show_encryption_prompt` flash session variable
2. **Redirect to dashboard** → `DashboardController` retrieves and
passes the flag to frontend (consuming it)
3. **Dashboard loads** → React component checks all three conditions
4. **Modal appears** → If conditions are met, `UnlockMessageDialog`
opens automatically
5. **Session flag consumed** → Subsequent page loads won't trigger the
modal
### Why Session Flash?
Laravel's session flash data is perfect for this use case because:
- It's automatically removed after being accessed once
- It survives redirects (crucial for post-login flow)
- It's server-side, so it can't be manipulated by client-side code
- No database changes or additional state management needed
### Edge Cases Handled
✅ **User clears encryption key manually** → Modal won't auto-open on
dashboard visit (no session flag)
✅ **User refreshes dashboard** → Modal won't re-appear (flash data
consumed)
✅ **User logs out and back in** → Modal appears again (new session flag)
✅ **2FA enabled users** → Modal appears after successful 2FA challenge
✅ **Key already in browser** → Modal doesn't appear (key check passes)
## Testing
- ✅ All existing dashboard tests pass (2 tests)
- ✅ All authentication tests pass (58 tests)
- ✅ Code formatted with Laravel Pint
- ✅ Code formatted with Prettier
- ✅ ESLint validation passes
## Files Changed
- `app/Http/Responses/LoginResponse.php` (new)
- `app/Http/Responses/TwoFactorLoginResponse.php` (new)
- `app/Providers/FortifyServiceProvider.php` (modified)
- `app/Http/Controllers/DashboardController.php` (modified)
- `resources/js/pages/dashboard.tsx` (modified)
## Breaking Changes
None. This is an additive feature that enhances the existing
authentication flow without breaking any existing functionality.
## Summary
- Implement event-driven drip email campaign system for new user signups
- Add 5 targeted emails based on user journey (welcome, onboarding
reminder, promo code, import help, feedback)
- Configure Laravel Horizon with Redis queue for reliable job processing
- Track sent emails in `user_mail_logs` table to prevent duplicates
## Email Schedule
| Email | Timing | Condition |
|-------|--------|-----------|
| Welcome | 30 min after signup | All users |
| Onboarding Reminder | 1 day after signup | Not onboarded |
| Promo Code (FOUNDER) | 1 day after signup | Onboarded + has
transactions + not subscribed |
| Import Help | 1 day after signup | Onboarded + no transactions + not
subscribed |
| Feedback | 5 days after signup | Not subscribed |
## Architecture
```
User Registers → ScheduleDripEmailsListener
├─> SendWelcomeEmailJob (30 min delay)
├─> SendOnboardingReminderEmailJob (1 day delay)
├─> SendPromoCodeEmailJob (1 day delay)
├─> SendImportHelpEmailJob (1 day delay)
└─> SendFeedbackEmailJob (5 days delay)
```
Each job checks conditions at execution time and either sends the email
+ logs it, or silently completes.
## Test plan
- [x] All 23 drip email tests pass
- [x] Migration creates `user_mail_logs` table
- [x] Jobs dispatch with correct delays
- [x] Emails only sent when conditions are met
- [x] Duplicate emails prevented via UserMailLog check
- [ ] Verify Horizon processes jobs in production
## Summary
Implements a complete user onboarding flow that guides new users through
setting up their account after registration.
## Features
- **Step-by-step wizard UI** with progress indicator and smooth
animations
- **E2E Encryption setup** with password strength indicator and
explanation of how encryption works
- **Account creation** supporting all account types (checking, savings,
credit card, investment, pension)
- **Category customization** with explanation of category types
(expenses, income, transfer)
- **Smart rules explanation** covering why there is no AI
auto-categorization (privacy & E2EE)
- **Transaction/balance import** based on account type
- **Sync integration** to ensure data consistency with backend
## Flow Diagram
```mermaid
flowchart TD
A[User Registration] --> B[Welcome]
B --> E[Encryption Explained]
E --> C{Has encryption key?}
C -->|No|F[Encryption Setup]
C -->|Yes|G{Has Existing Accounts?}
G -->|Yes| H[Show Existing Accounts]
G -->|No| I[Create First Account]
H --> J[Continue]
I --> K{Account Type?}
K -->|Checking/Savings/Credit Card| L[Import Transactions]
K -->|Investment/Pension| M[Import Balances]
J --> N[Category Types Explanation]
L --> N
M --> N
N --> O[Customize Categories]
O --> P[Smart Rules Explanation]
P --> Q[More Accounts?]
Q -->|Add More| I
Q -->|Finish| R[Complete]
R --> S[Redirect to Dashboard]
S --> T{Subscribed?}
T -->|No| U[Subscribe Page]
T -->|Yes| V[Dashboard]
```
## Technical Changes
### Backend
- Added `onboarded_at` field to users table with migration
- Created `EnsureOnboardingComplete` middleware for redirect logic
- Created `OnboardingController` with index and complete actions
- Custom `RegisterResponse` to redirect new users to onboarding
- Updated `AccountController::store` to return JSON for fetch requests
### Frontend
- `OnboardingLayout` - fullscreen layout with step progress
- `useOnboardingState` hook - manages step navigation and state
- 12 step components for each onboarding screen
- Backend sync after account creation and imports
### Tests
- Feature tests for onboarding middleware
- Updated existing tests to use `onboarded()` factory state
- Add `hideAuthButtons` config check in Fortify login view
- Pass `hideAuthButtons` prop to register view from config
- Redirect to login when registration is hidden
- Add early return in register component when registration is disabled
Víctor Falcón