Conversation
WalkthroughImplements email deduplication in multi-account form defaults and in Stripe seat syncing. Expands Prisma user selection to include email and emailAccounts count. Updates totalSeats to count unique pending invites plus connected users’ emailAccounts. Bumps version from v2.8.10 to v2.8.11. Changes
Sequence Diagram(s)sequenceDiagram
autonumber
participant UI as UI (Settings Form)
participant Billing as BillingService (syncSeats)
participant DB as Prisma (Premium + Users)
participant Stripe as Stripe API
rect rgba(230,245,255,0.6)
note over UI: Initialization
UI->>UI: Build set from emailAddresses
UI->>UI: Filter pendingInvites not in set
UI->>UI: Combine originals + unique invites
end
rect rgba(240,255,240,0.6)
note over Billing,DB: Seat Sync
Billing->>DB: Fetch premium { pendingInvites, users{ email, _count.emailAccounts } }
DB-->>Billing: premium data
Billing->>Billing: connectedEmails := set(users.email)
Billing->>Billing: uniqueInvites := pendingInvites \ connectedEmails
Billing->>Billing: totalSeats := sum(users._count.emailAccounts) + len(uniqueInvites)
Billing->>Stripe: Update subscription item with totalSeats
Stripe-->>Billing: Acknowledgement
end
note over Billing: Types updated to include user.email and _count.emailAccounts
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related PRs
Poem
✨ Finishing Touches
🧪 Generate unit tests
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR/Issue comments)Type Other keywords and placeholders
Status, Documentation and Community
|
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (3)
apps/web/app/(app)/[emailAccountId]/settings/MultiAccountSection.tsx(1 hunks)apps/web/ee/billing/stripe/sync-stripe.ts(2 hunks)version.txt(1 hunks)
🧰 Additional context used
📓 Path-based instructions (15)
!{.cursor/rules/*.mdc}
📄 CodeRabbit inference engine (.cursor/rules/cursor-rules.mdc)
Never place rule files in the project root, in subdirectories outside .cursor/rules, or in any other location
Files:
version.txtapps/web/app/(app)/[emailAccountId]/settings/MultiAccountSection.tsxapps/web/ee/billing/stripe/sync-stripe.ts
!pages/_document.{js,jsx,ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/ultracite.mdc)
!pages/_document.{js,jsx,ts,tsx}: Don't import next/document outside of pages/_document.jsx in Next.js projects.
Don't import next/document outside of pages/_document.jsx in Next.js projects.
Files:
version.txtapps/web/app/(app)/[emailAccountId]/settings/MultiAccountSection.tsxapps/web/ee/billing/stripe/sync-stripe.ts
apps/web/**/*.{ts,tsx}
📄 CodeRabbit inference engine (apps/web/CLAUDE.md)
apps/web/**/*.{ts,tsx}: Use TypeScript with strict null checks
Path aliases: Use@/for imports from project root
Use proper error handling with try/catch blocks
Format code with Prettier
Leverage TypeScript inference for better DX
Files:
apps/web/app/(app)/[emailAccountId]/settings/MultiAccountSection.tsxapps/web/ee/billing/stripe/sync-stripe.ts
apps/web/app/**
📄 CodeRabbit inference engine (apps/web/CLAUDE.md)
NextJS app router structure with (app) directory
Files:
apps/web/app/(app)/[emailAccountId]/settings/MultiAccountSection.tsx
apps/web/**/*.tsx
📄 CodeRabbit inference engine (apps/web/CLAUDE.md)
apps/web/**/*.tsx: Follow tailwindcss patterns with prettier-plugin-tailwindcss
Prefer functional components with hooks
Use shadcn/ui components when available
Ensure responsive design with mobile-first approach
Follow consistent naming conventions (PascalCase for components)
Use LoadingContent component for async data
Useresult?.serverErrorwithtoastErrorandtoastSuccess
UseLoadingContentcomponent to handle loading and error states consistently
Passloading,error, and children props toLoadingContent
Files:
apps/web/app/(app)/[emailAccountId]/settings/MultiAccountSection.tsx
**/*.tsx
📄 CodeRabbit inference engine (.cursor/rules/form-handling.mdc)
**/*.tsx: Use React Hook Form with Zod for validation
Validate form inputs before submission
Show validation errors inline next to form fields
Files:
apps/web/app/(app)/[emailAccountId]/settings/MultiAccountSection.tsx
**/*.{ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/logging.mdc)
**/*.{ts,tsx}: UsecreateScopedLoggerfor logging in backend TypeScript files
Typically add the logger initialization at the top of the file when usingcreateScopedLogger
Only use.with()on a logger instance within a specific function, not for a global loggerImport Prisma in the project using
import prisma from "@/utils/prisma";
**/*.{ts,tsx}: Don't use TypeScript enums.
Don't use TypeScript const enum.
Don't use the TypeScript directive @ts-ignore.
Don't use primitive type aliases or misleading types.
Don't use empty type parameters in type aliases and interfaces.
Don't use any or unknown as type constraints.
Don't use implicit any type on variable declarations.
Don't let variables evolve into any type through reassignments.
Don't use non-null assertions with the ! postfix operator.
Don't misuse the non-null assertion operator (!) in TypeScript files.
Don't use user-defined types.
Use as const instead of literal types and type annotations.
Use export type for types.
Use import type for types.
Don't declare empty interfaces.
Don't merge interfaces and classes unsafely.
Don't use overload signatures that aren't next to each other.
Use the namespace keyword instead of the module keyword to declare TypeScript namespaces.
Don't use TypeScript namespaces.
Don't export imported variables.
Don't add type annotations to variables, parameters, and class properties that are initialized with literal expressions.
Don't use parameter properties in class constructors.
Use either T[] or Array consistently.
Initialize each enum member value explicitly.
Make sure all enum members are literal values.
Files:
apps/web/app/(app)/[emailAccountId]/settings/MultiAccountSection.tsxapps/web/ee/billing/stripe/sync-stripe.ts
apps/web/app/(app)/*/**
📄 CodeRabbit inference engine (.cursor/rules/page-structure.mdc)
Components for the page are either put in page.tsx, or in the apps/web/app/(app)/PAGE_NAME folder
Files:
apps/web/app/(app)/[emailAccountId]/settings/MultiAccountSection.tsx
apps/web/app/(app)/*/**/*.tsx
📄 CodeRabbit inference engine (.cursor/rules/page-structure.mdc)
If you need to use onClick in a component, that component is a client component and file must start with 'use client'
Files:
apps/web/app/(app)/[emailAccountId]/settings/MultiAccountSection.tsx
apps/web/app/(app)/*/**/**/*.tsx
📄 CodeRabbit inference engine (.cursor/rules/page-structure.mdc)
If we're in a deeply nested component we will use swr to fetch via API
Files:
apps/web/app/(app)/[emailAccountId]/settings/MultiAccountSection.tsx
apps/web/app/**/*.tsx
📄 CodeRabbit inference engine (.cursor/rules/project-structure.mdc)
Components with
onClickmust be client components withuse clientdirective
Files:
apps/web/app/(app)/[emailAccountId]/settings/MultiAccountSection.tsx
**/*.{js,jsx,ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/ultracite.mdc)
**/*.{js,jsx,ts,tsx}: Don't useelements in Next.js projects.
Don't use elements in Next.js projects.
Don't use namespace imports.
Don't access namespace imports dynamically.
Don't use global eval().
Don't use console.
Don't use debugger.
Don't use var.
Don't use with statements in non-strict contexts.
Don't use the arguments object.
Don't use consecutive spaces in regular expression literals.
Don't use the comma operator.
Don't use unnecessary boolean casts.
Don't use unnecessary callbacks with flatMap.
Use for...of statements instead of Array.forEach.
Don't create classes that only have static members (like a static namespace).
Don't use this and super in static contexts.
Don't use unnecessary catch clauses.
Don't use unnecessary constructors.
Don't use unnecessary continue statements.
Don't export empty modules that don't change anything.
Don't use unnecessary escape sequences in regular expression literals.
Don't use unnecessary labels.
Don't use unnecessary nested block statements.
Don't rename imports, exports, and destructured assignments to the same name.
Don't use unnecessary string or template literal concatenation.
Don't use String.raw in template literals when there are no escape sequences.
Don't use useless case statements in switch statements.
Don't use ternary operators when simpler alternatives exist.
Don't use useless this aliasing.
Don't initialize variables to undefined.
Don't use the void operators (they're not familiar).
Use arrow functions instead of function expressions.
Use Date.now() to get milliseconds since the Unix Epoch.
Use .flatMap() instead of map().flat() when possible.
Use literal property access instead of computed property access.
Don't use parseInt() or Number.parseInt() when binary, octal, or hexadecimal literals work.
Use concise optional chaining instead of chained logical expressions.
Use regular expression literals instead of the RegExp constructor when possible.
Don't use number literal object member names th...
Files:
apps/web/app/(app)/[emailAccountId]/settings/MultiAccountSection.tsxapps/web/ee/billing/stripe/sync-stripe.ts
**/*.{jsx,tsx}
📄 CodeRabbit inference engine (.cursor/rules/ultracite.mdc)
**/*.{jsx,tsx}: Don't destructure props inside JSX components in Solid projects.
Don't use both children and dangerouslySetInnerHTML props on the same element.
Don't use Array index in keys.
Don't assign to React component props.
Don't define React components inside other components.
Don't use event handlers on non-interactive elements.
Don't assign JSX properties multiple times.
Don't add extra closing tags for components without children.
Use <>...</> instead of ....
Don't insert comments as text nodes.
Don't use the return value of React.render.
Make sure all dependencies are correctly specified in React hooks.
Make sure all React hooks are called from the top level of component functions.
Don't use unnecessary fragments.
Don't pass children as props.
Use semantic elements instead of role attributes in JSX.
Files:
apps/web/app/(app)/[emailAccountId]/settings/MultiAccountSection.tsx
**/*.{html,jsx,tsx}
📄 CodeRabbit inference engine (.cursor/rules/ultracite.mdc)
**/*.{html,jsx,tsx}: Don't use or elements.
Don't use accessKey attribute on any HTML element.
Don't set aria-hidden="true" on focusable elements.
Don't add ARIA roles, states, and properties to elements that don't support them.
Only use the scope prop on elements.
Don't assign non-interactive ARIA roles to interactive HTML elements.
Make sure label elements have text content and are associated with an input.
Don't assign interactive ARIA roles to non-interactive HTML elements.
Don't assign tabIndex to non-interactive HTML elements.
Don't use positive integers for tabIndex property.
Don't include "image", "picture", or "photo" in img alt prop.
Don't use explicit role property that's the same as the implicit/default role.
Make static elements with click handlers use a valid role attribute.
Always include a title element for SVG elements.
Give all elements requiring alt text meaningful information for screen readers.
Make sure anchors have content that's accessible to screen readers.
Assign tabIndex to non-interactive HTML elements with aria-activedescendant.
Include all required ARIA attributes for elements with ARIA roles.
Make sure ARIA properties are valid for the element's supported roles.
Always include a type attribute for button elements.
Make elements with interactive roles and handlers focusable.
Give heading elements content that's accessible to screen readers (not hidden with aria-hidden).
Always include a lang attribute on the html element.
Always include a title attribute for iframe elements.
Accompany onClick with at least one of: onKeyUp, onKeyDown, or onKeyPress.
Accompany onMouseOver/onMouseOut with onFocus/onBlur.
Include caption tracks for audio and video elements.
Make sure all anchors are valid and navigable.
Ensure all ARIA properties (aria-*) are valid.
Use valid, non-abstract ARIA roles for elements with ARIA roles.
Use valid ARIA state and property values.
Use valid values for the autocomplete attribute on input eleme...Files:
apps/web/app/(app)/[emailAccountId]/settings/MultiAccountSection.tsx**/*.ts
📄 CodeRabbit inference engine (.cursor/rules/form-handling.mdc)
**/*.ts: The same validation should be done in the server action too
Define validation schemas using ZodFiles:
apps/web/ee/billing/stripe/sync-stripe.ts🔇 Additional comments (3)
version.txt (1)
1-1: Version bump looks good.
No concerns.apps/web/ee/billing/stripe/sync-stripe.ts (2)
125-127: Selecting email for users is necessary and correct.
This enables invite/connection dedup downstream.
153-155: Type shape update matches the new select.
Keeps Prisma types aligned; good.
| ? (() => { | ||
| // Deduplicate to prevent showing the same email twice | ||
| const existingEmails = new Set(emailAddresses.map((e) => e.email)); | ||
| const uniquePendingInvites = pendingInvites.filter( | ||
| (email) => !existingEmails.has(email), | ||
| ); | ||
| return [ | ||
| ...emailAddresses, | ||
| ...uniquePendingInvites.map((email) => ({ email })), | ||
| ]; | ||
| })() |
There was a problem hiding this comment.
💡 Verification agent
❓ Verification inconclusive
Don’t drop pendingInvites when there are 0 connected users; also dedup invites themselves (case-insensitive).
Current gating on emailAddresses?.length hides pending invites for brand‑new orgs, and duplicates inside pendingInvites can still surface. Normalize to lowercase for comparison, keep original casing for existing users, and only fallback to an empty row if the combined list is empty.
Apply:
- emailAddresses: emailAddresses?.length
- ? (() => {
- // Deduplicate to prevent showing the same email twice
- const existingEmails = new Set(emailAddresses.map((e) => e.email));
- const uniquePendingInvites = pendingInvites.filter(
- (email) => !existingEmails.has(email),
- );
- return [
- ...emailAddresses,
- ...uniquePendingInvites.map((email) => ({ email })),
- ];
- })()
- : [{ email: "" }],
+ emailAddresses: (() => {
+ const existingLc = new Set(
+ (emailAddresses || [])
+ .map((e) => e.email?.toLowerCase())
+ .filter(Boolean) as string[],
+ );
+ const uniquePendingLc = Array.from(
+ new Set(
+ (pendingInvites || [])
+ .map((e) => e?.toLowerCase())
+ .filter(Boolean) as string[],
+ ),
+ ).filter((email) => !existingLc.has(email));
+ const combined = [
+ ...emailAddresses,
+ ...uniquePendingLc.map((email) => ({ email })),
+ ];
+ return combined.length ? combined : [{ email: "" }];
+ })(),If invites are already normalized at write-time, confirm and we can simplify the lowercasing here.
Always merge pendingInvites & existing users unconditionally
Replace the emailAddresses?.length ? … : [{ email: "" }] branch with an unconditional merge that
- normalizes only for comparison (case-insensitive dedupe of both existing emails and invites),
- preserves original casing for both lists,
- falls back to
[{ email: "" }]only if the combined array is empty.
emailAddresses: (() => {
const existingLc = new Set(
(emailAddresses || []).map(e => e.email.toLowerCase())
);
const uniqueInvites = (pendingInvites || [])
// remove invites already in existingEmails (case-insensitive)
.filter(inv => !existingLc.has(inv.toLowerCase()))
// dedupe invites themselves (case-insensitive), preserving first‐seen casing
.filter((inv, i, arr) =>
arr.findIndex(x => x.toLowerCase() === inv.toLowerCase()) === i
);
const combined = [
...(emailAddresses || []),
...uniqueInvites.map(email => ({ email })),
];
return combined.length ? combined : [{ email: "" }];
})(),Confirm whether pendingInvites values are already normalized upstream to simplify/remove the toLowerCase() calls.
🤖 Prompt for AI Agents
In apps/web/app/(app)/[emailAccountId]/settings/MultiAccountSection.tsx around
lines 146–156, replace the conditional branch that only merges pendingInvites
when emailAddresses exists with an unconditional merge: build a set of existing
emails lowercased for comparison, filter pendingInvites (or empty array) to
remove any invites that match existing emails case-insensitively, dedupe
pendingInvites themselves case-insensitively while preserving first-seen casing,
then concatenate the original emailAddresses (or empty array) with the unique
invites mapped to { email } and finally return that combined array or [{ email:
"" }] if it ends up empty; also confirm whether pendingInvites are already
normalized upstream so you can remove the toLowerCase() calls.
| // Get all connected user emails | ||
| const connectedUserEmails = new Set(premium.users.map((u) => u.email)); | ||
|
|
||
| // Filter out pending invites that are already connected users to avoid double counting | ||
| const uniquePendingInvites = (premium.pendingInvites || []).filter( | ||
| (email) => !connectedUserEmails.has(email), | ||
| ); | ||
|
|
||
| // total seats = premium users + unique pending invites (excluding duplicates) | ||
| const totalSeats = | ||
| sumBy(premium.users, (u) => u._count.emailAccounts) + | ||
| (premium.pendingInvites?.length || 0); | ||
| uniquePendingInvites.length; | ||
|
|
There was a problem hiding this comment.
💡 Verification agent
🧩 Analysis chain
Still double-counts duplicate pending invites; compare and dedup case-insensitively to avoid overbilling.
Currently only excludes emails already connected; duplicates within pendingInvites are still counted. This can inflate totalSeats.
Apply:
- // Get all connected user emails
- const connectedUserEmails = new Set(premium.users.map((u) => u.email));
-
- // Filter out pending invites that are already connected users to avoid double counting
- const uniquePendingInvites = (premium.pendingInvites || []).filter(
- (email) => !connectedUserEmails.has(email),
- );
+ // Build lowercase sets for robust comparison
+ const connectedUserEmails = new Set(
+ premium.users
+ .map((u) => u.email?.toLowerCase())
+ .filter(Boolean) as string[],
+ );
+ // Unique pending invites (case-insensitive), excluding already-connected
+ const uniquePendingInvites = Array.from(
+ new Set(
+ (premium.pendingInvites || [])
+ .map((e) => e?.toLowerCase())
+ .filter(Boolean) as string[],
+ ),
+ ).filter((email) => !connectedUserEmails.has(email));Optional: if emails are normalized to lowercase at creation time, confirm via a quick repo search and we can drop the lowercasing here for perf.
🏁 Script executed:
#!/bin/bash
# Display lines around the pendingInvites logic for context
sed -n '140,180p' apps/web/ee/billing/stripe/sync-stripe.ts
# Locate all references to the type or origin of `pendingInvites`
rg -n "pendingInvites" -g 'apps/web/**/*.ts'Length of output: 2242
🏁 Script executed:
#!/bin/bash
# List all Prisma schema files to locate the Premium model definition
find . -type f -name '*.prisma'Length of output: 65
🏁 Script executed:
#!/bin/bash
# Extract the Premium model definition from Prisma schema
sed -n '/model Premium {/,/}/p' apps/web/prisma/schema.prisma
# Inspect pendingInvites normalization logic in premium actions
sed -n '180,250p' apps/web/utils/actions/premium.tsLength of output: 4740
🏁 Script executed:
#!/bin/bash
# Inspect how uniqueEmails is derived and normalized before setting pendingInvites
sed -n '1,200p' apps/web/utils/actions/premium.tsLength of output: 6567
Deduplicate pendingInvites case-insensitively before counting
Normalize both connected user emails and pending invites to lowercase, use a Set to remove duplicates, then exclude any already-connected emails prior to computing totalSeats.
Apply in apps/web/ee/billing/stripe/sync-stripe.ts (around lines 162–174):
- // Get all connected user emails
- const connectedUserEmails = new Set(premium.users.map((u) => u.email));
-
- // Filter out pending invites that are already connected users to avoid double counting
- const uniquePendingInvites = (premium.pendingInvites || []).filter(
- (email) => !connectedUserEmails.has(email),
- );
+ // Build lowercase sets for robust comparison
+ const connectedUserEmails = new Set(
+ premium.users
+ .map((u) => u.email?.toLowerCase())
+ .filter(Boolean) as string[],
+ );
+ // Dedupe and exclude already-connected invites
+ const uniquePendingInvites = Array.from(
+ new Set(
+ (premium.pendingInvites || [])
+ .map((e) => e?.toLowerCase())
+ .filter(Boolean) as string[],
+ ),
+ ).filter((email) => !connectedUserEmails.has(email));📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| // Get all connected user emails | |
| const connectedUserEmails = new Set(premium.users.map((u) => u.email)); | |
| // Filter out pending invites that are already connected users to avoid double counting | |
| const uniquePendingInvites = (premium.pendingInvites || []).filter( | |
| (email) => !connectedUserEmails.has(email), | |
| ); | |
| // total seats = premium users + unique pending invites (excluding duplicates) | |
| const totalSeats = | |
| sumBy(premium.users, (u) => u._count.emailAccounts) + | |
| (premium.pendingInvites?.length || 0); | |
| uniquePendingInvites.length; | |
| // Build lowercase sets for robust comparison | |
| const connectedUserEmails = new Set( | |
| premium.users | |
| .map((u) => u.email?.toLowerCase()) | |
| .filter(Boolean) as string[], | |
| ); | |
| // Dedupe and exclude already-connected invites | |
| const uniquePendingInvites = Array.from( | |
| new Set( | |
| (premium.pendingInvites || []) | |
| .map((e) => e?.toLowerCase()) | |
| .filter(Boolean) as string[], | |
| ), | |
| ).filter((email) => !connectedUserEmails.has(email)); | |
| // total seats = premium users + unique pending invites (excluding duplicates) | |
| const totalSeats = | |
| sumBy(premium.users, (u) => u._count.emailAccounts) + | |
| uniquePendingInvites.length; |
🤖 Prompt for AI Agents
In apps/web/ee/billing/stripe/sync-stripe.ts around lines 162 to 174,
pendingInvites are not deduplicated case-insensitively before counting and may
double-count invites differing only by case; normalize connected user emails and
pending invites to lowercase, build a Set of lowercased pendingInvites to remove
duplicates, remove any entries that exist in the lowercased connected user email
set, then use the size of that filtered Set as the uniquePendingInvites count
(guarding for null/undefined pendingInvites) and compute totalSeats as
sumBy(premium.users, u => u._count.emailAccounts) + uniquePendingInvitesCount.
1 participant
Summary by CodeRabbit
Bug Fixes
Chores