Fix leading colon in tag value and false tag violations for non-required levels by wildan-m · Pull Request #87198 · Expensify/App

wildan-m · 2026-04-07T01:50:58Z

Explanation of Change

When transactionTags is an empty string, getTagArrayFromName splits it into [""] (one empty element) instead of []. Setting a tag at index > 0 then produces a leading colon (e.g. ":Alpha" instead of "Alpha"), which triggers false "tag no longer valid" violations.

This fix adds an empty-string guard so that splitting an empty transactionTags returns [] instead of [""], and fills any sparse array slots when tagIndex exceeds the current array length.

Additionally, getTagViolationsForDependentTags blindly flagged any empty tag level via tags.includes('') and a length mismatch check, without considering whether each level is actually required. This caused false ALL_TAG_LEVELS_REQUIRED violations when users only filled some tag levels that were not required. The fix now checks each tag level's required property before flagging.

Fixed Issues

$ #81881
PROPOSAL: #81881 (comment)

Tests

Sample CSV for multi-level tag import (tags-multilevel.csv):

Department,Project
Engineering,Alpha
Engineering,Beta
Marketing,Gamma
Marketing,Delta

tags-multilevel.csv

Import the CSV above into a workspace's multi-level tags:
1. Go to Settings > Workspaces > [Your workspace] > More features and enable Tags
2. Go to Tags, click Import, and select Multi-level tags
3. Upload the CSV file above
4. On the import settings screen, turn "These are independent tags" OFF, and click Import
5. For each tag level (Department, Project), tap on it and toggle off Required so both levels are not required
Create an expense — fill only Merchant and Category, do not select any tags
Submit the expense
Turn off your network connection (go offline)
Find the submitted expense
Edit the expense and select only Department (first level tag, e.g. "Engineering")
Verify the tag does not have a leading colon (should be "Alpha", not ":Alpha")
Verify the false "all tag levels required" violation is cleared

Verify that no errors appear in the JS console

Offline tests

The tag validation logic runs locally on cached data, so behavior is unchanged offline.

QA Steps

Same as tests above.

Verify that no errors appear in the JS console

PR Author Checklist

Screenshots/Videos

Android: Native

Kapture.2026-04-08.at.06.04.54.mp4

Android: mWeb Chrome

Kapture.2026-04-08.at.06.09.47.mp4

iOS: Native

Kapture.2026-04-08.at.06.22.44.mp4

iOS: mWeb Safari

Kapture.2026-04-08.at.06.25.32.mp4

MacOS: Chrome / Safari

Kapture.2026-04-08.at.05.35.40.mp4

…ionTagsString When transactionTags is an empty string, getTagArrayFromName splits it into [""] (one empty element) instead of []. Setting a tag at index > 0 then produces a leading colon (e.g. ":Alpha" instead of "Alpha"), which triggers false "tag no longer valid" violations. This adds the same empty-string guard already used in IOURequestStepTag.tsx.

The violation check in getTagViolationsForDependentTags blindly flagged any empty tag level via tags.includes('') and a length mismatch check, without considering whether each level is actually required. This caused false ALL_TAG_LEVELS_REQUIRED violations when users only filled some tag levels that were not required. Also fill sparse array slots in insertTagIntoTransactionTagsString when tagIndex exceeds the current array length, preventing undefined entries.

…ag violations

codecov · 2026-04-07T02:08:06Z

Codecov Report

✅ Changes either increased or maintained existing code coverage, great job!

Files with missing lines	Coverage Δ
src/libs/IOUUtils.ts	`74.00% <100.00%> (+0.39%)`	⬆️
src/libs/Violations/ViolationsUtils.ts	`77.07% <100.00%> (+1.11%)`	⬆️
... and 11 files with indirect coverage changes

…ading-colon-tag

melvin-bot · 2026-04-07T23:30:38Z

@situchan Please copy/paste the Reviewer Checklist from here into a new comment on this PR and complete it. If you have the K2 extension, you can simply click: [this button]

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: b15af95663

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

…olicy

JmillsExpensify

Wild one, glad we caught it. LGTM

situchan · 2026-04-14T19:18:45Z

@wildan-m please merge main

situchan · 2026-04-14T19:19:07Z

Reviewer Checklist

I have verified the author checklist is complete (all boxes are checked off).
I verified the correct issue is linked in the ### Fixed Issues section above
I verified testing steps are clear and they cover the changes made in this PR
- I verified the steps for local testing are in the Tests section
- I verified the steps for Staging and/or Production testing are in the QA steps section
- I verified the steps cover any possible failure scenarios (i.e. verify an input displays the correct error message if the entered data is not correct)
- I turned off my network connection and tested it while offline to ensure it matches the expected behavior (i.e. verify the default avatar icon is displayed if app is offline)
I checked that screenshots or videos are included for tests on all platforms
I included screenshots or videos for tests on all platforms
I verified that the composer does not automatically focus or open the keyboard on mobile unless explicitly intended. This includes checking that returning the app from the background does not unexpectedly open the keyboard.
I verified tests pass on all platforms & I tested again on:
- Android: HybridApp
- Android: mWeb Chrome
- iOS: HybridApp
- iOS: mWeb Safari
- MacOS: Chrome / Safari
- MacOS: Desktop
If there are any errors in the console that are unrelated to this PR, I either fixed them (preferred) or linked to where I reported them in Slack
I verified there are no new alerts related to the canBeMissing param for useOnyx
I verified proper code patterns were followed (see Reviewing the code)
- I verified that any callback methods that were added or modified are named for what the method does and never what callback they handle (i.e. toggleReport and not onIconClick).
- I verified that comments were added to code that is not self explanatory
- I verified that any new or modified comments were clear, correct English, and explained "why" the code was doing something instead of only explaining "what" the code was doing.
- I verified any copy / text shown in the product is localized by adding it to src/languages/* files and using the translation method
- I verified all numbers, amounts, dates and phone numbers shown in the product are using the localization methods
- I verified any copy / text that was added to the app is grammatically correct in English. It adheres to proper capitalization guidelines (note: only the first word of header/labels should be capitalized), and is either coming verbatim from figma or has been approved by marketing (in order to get marketing approval, ask the Bug Zero team member to add the Waiting for copy label to the issue)
- I verified proper file naming conventions were followed for any new files or renamed files. All non-platform specific files are named after what they export and are not named "index.js". All platform-specific files are named for the platform the code supports as outlined in the README.
- I verified the JSDocs style guidelines (in STYLE.md) were followed
If a new code pattern is added I verified it was agreed to be used by multiple Expensify engineers
I verified that this PR follows the guidelines as stated in the Review Guidelines
I verified other components that can be impacted by these changes have been tested, and I retested again (i.e. if the PR modifies a shared library or component like Avatar, I verified the components using Avatar have been tested & I retested again)
I verified all code is DRY (the PR doesn't include any logic written more than once, with the exception of tests)
I verified any variables that can be defined as constants (ie. in CONST.ts or at the top of the file that uses the constant) are defined as such
If a new component is created I verified that:
- A similar component doesn't exist in the codebase
- All props are defined accurately and each prop has a /** comment above it */
- The file is named correctly
- The component has a clear name that is non-ambiguous and the purpose of the component can be inferred from the name alone
- The only data being stored in the state is data necessary for rendering and nothing else
- For Class Components, any internal methods passed to components event handlers are bound to this properly so there are no scoping issues (i.e. for onClick={this.submit} the method this.submit should be bound to this in the constructor)
- Any internal methods bound to this are necessary to be bound (i.e. avoid this.submit = this.submit.bind(this); if this.submit is never passed to a component event handler like onClick)
- All JSX used for rendering exists in the render method
- The component has the minimum amount of code necessary for its purpose, and it is broken down into smaller components in order to separate concerns and functions
If any new file was added I verified that:
- The file has a description of what it does and/or why is needed at the top of the file if the code is not self explanatory
If a new CSS style is added I verified that:
- A similar style doesn't already exist
- The style can't be created with an existing StyleUtils function (i.e. StyleUtils.getBackgroundAndBorderStyle(theme.componentBG)
If the PR modifies code that runs when editing or sending messages, I tested and verified there is no unexpected behavior for all supported markdown - URLs, single line code, code blocks, quotes, headings, bold, strikethrough, and italic.
If the PR modifies a generic component, I tested and verified that those changes do not break usages of that component in the rest of the App (i.e. if a shared library or component like Avatar is modified, I verified that Avatar is working as expected in all cases)
If the PR modifies a component related to any of the existing Storybook stories, I tested and verified all stories for that component are still working as expected.
If the PR modifies a component or page that can be accessed by a direct deeplink, I verified that the code functions as expected when the deeplink is used - from a logged in and logged out account.
If the PR modifies the UI (e.g. new buttons, new UI components, changing the padding/spacing/sizing, moving components, etc) or modifies the form input styles:
- I verified that all the inputs inside a form are aligned with each other.
- I added Design label and/or tagged @Expensify/design so the design team can review the changes.
If a new page is added, I verified it's using the ScrollView component to make it scrollable when more elements are added to the page.
For any bug fix or new feature in this PR, I verified that sufficient unit tests are included to prevent regressions in this flow.
If the main branch was merged into this PR after a review, I tested again and verified the outcome was still expected according to the Test steps.
I have checked off every checkbox in the PR reviewer checklist, including those that don't apply to this PR.

Screenshots/Videos

Android: HybridApp

Android: mWeb Chrome

iOS: HybridApp

ios.mov

iOS: mWeb Safari

MacOS: Chrome / Safari

web.mov

MelvinBot · 2026-04-14T19:22:00Z

Code Review — LGTM with one minor nit

Both fixes are correct and well-tested.

IOUUtils.ts — The empty-string guard (transactionTags ? ... : []) correctly avoids ''.split(':') producing ['']. The sparse-slot fill loop is sound: Array.prototype.at() returns undefined for holes, which gets filled with '' before .join().

ViolationsUtils.ts — The new hasEmptyRequiredLevel logic correctly iterates sorted policy tag keys and only flags ALL_TAG_LEVELS_REQUIRED when a required level is empty. The ?? true fallback is a safe defensive default (the required field is typed as non-optional boolean, so it only fires if the key is missing from policyTagList). The retained tags.length > policyTagKeys.length condition properly catches stale/malformed tag strings.

Tests cover the key scenarios: empty transactionTags at index > 0, sparse slots, required vs non-required dependent tag levels.

Minor nit (non-blocking)

The test name at tests/unit/IOUUtilsTest.ts:310:

"Should not produce a leading colon when transactionTags is empty and tagIndex > 0"

…expects ':Alpha', which does have a leading colon. The colon is correct (it separates the empty first-level slot from the second-level value), but the test name is misleading. Something like "Should correctly insert tag at index > 0 when transactionTags is empty" would be clearer.

situchan · 2026-04-14T19:42:21Z

+            const tagValue = tags.at(index) ?? '';
+            return tagValue === '' && (policyTagList[key]?.required ?? true);
+        });
+        if (hasEmptyRequiredLevel || tags.length > policyTagKeys.length) {


Is this condition correct?

tags.length > policyTagKeys.length

Shouldn't this be tags.length < policyTagKeys.length? Actually, this condition is not needed at all.

@MelvinBot

situchan is correct — this condition can be removed.

Why < is not needed: hasEmptyRequiredLevel already iterates over all policyTagKeys. When tags.length < policyTagKeys.length, tags.at(index) returns undefined for the missing indices, which coalesces to ''. If those levels are required, hasEmptyRequiredLevel will already be true.

Why > is not needed: Having more tags than policy levels is a stale-data edge case, and flagging it as ALL_TAG_LEVELS_REQUIRED is semantically wrong — that violation means required levels are unfilled, not that there are extra levels. The extra tags are harmless and would be trimmed on next edit.

The hasEmptyRequiredLevel check alone is sufficient.

You are right, reverted in 59f84f1. Also merged main as requested.

…s than policy" This reverts commit 1e24236.

…ading-colon-tag

MelvinBot · 2026-04-15T03:13:04Z

Re-review — LGTM ✅

The code is unchanged since my previous review. All CI checks pass, and situchan has approved. My prior assessment still holds:

IOUUtils.ts — Empty-string guard and sparse-slot fill are correct.
ViolationsUtils.ts — hasEmptyRequiredLevel properly respects each tag level's required property.
Tests — Cover the key scenarios (empty tags at index > 0, sparse slots, required vs non-required levels).

No new concerns. Ready to merge.

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 4f7de5a044

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

github-actions · 2026-04-15T22:30:27Z

🚧 @Julesssss has triggered a test Expensify/App build. You can view the workflow run here.

github-actions · 2026-04-15T22:35:34Z

🧪🧪 Use the links below to test this adhoc build on Android, iOS, and Web. Happy testing! 🧪🧪
Built from App PR #87198.

Android 🤖	iOS 🍎
https://ad-hoc-expensify-cash.s3.us-east-1.amazonaws.com/rock-artifacts/ad-hoc/rock-android-Adhoc-b497a8c-d10f585-c93741b5a4bfb4ee02b2108f4a2eb8fc8324df01/index.html	https://ad-hoc-expensify-cash.s3.us-east-1.amazonaws.com/rock-artifacts/ad-hoc/rock-ios-device-AdHoc-b497a8c-d10f585-6865eb9ec6cbeed9cfc3fc3b5e9c55bd71e155a7/index.html

Web 🕸️
https://87198.pr-testing.expensify.com

👀 View the workflow run that generated this build 👀

OSBotify · 2026-04-15T22:39:41Z

✋ This PR was not deployed to staging yet because QA is ongoing. It will be automatically deployed to staging after the next production release.

OSBotify · 2026-04-16T03:56:41Z

🚀 Deployed to staging by https://github.com/Julesssss in version: 9.3.60-0 🚀

platform	result
🕸 web 🕸	success ✅
🤖 android 🤖	success ✅
🍎 iOS 🍎	success ✅

Bundle Size Analysis (Sentry):

Android
iOS

MelvinBot · 2026-04-16T03:58:13Z

No help site changes required.

This PR is a bug fix to internal tag validation logic — it corrects two issues:

A leading colon appearing in tag values when transactionTags is empty (e.g. ":Alpha" instead of "Alpha")
False ALL_TAG_LEVELS_REQUIRED violations firing for non-required tag levels

These are code-level fixes that don't change any user-facing features, workflows, or UI labels. The relevant help articles (Create and Manage Expense Tags, Require Tags and Categories) describe how to set up and require tags — they don't reference the internal tag string format or specific violation behavior that was fixed here.

OSBotify · 2026-04-21T11:10:36Z

🚀 Deployed to production by https://github.com/mountiny in version: 9.3.60-22 🚀

platform	result
🕸 web 🕸	success ✅
🤖 android 🤖	success ✅
🍎 iOS 🍎	success ✅

wildan-m added 2 commits April 7, 2026 08:49

melvin-bot Bot assigned wildan-m Apr 7, 2026

Add unit tests for insertTagIntoTransactionTagsString and dependent t…

0a8dfbf

…ag violations

wildan-m added 2 commits April 8, 2026 04:29

Merge remote-tracking branch 'upstream/main' into wildan/81881-fix-le…

b15af95

…ading-colon-tag

Merge remote-tracking branch 'upstream/main' into wildan/81881-fix-le…

0ae0255

…ading-colon-tag

wildan-m marked this pull request as ready for review April 7, 2026 23:30

wildan-m requested review from a team as code owners April 7, 2026 23:30

melvin-bot Bot requested a review from situchan April 7, 2026 23:30

melvin-bot Bot requested review from JmillsExpensify and removed request for a team April 7, 2026 23:30

wildan-m mentioned this pull request Apr 7, 2026

[Due for payment 2026-04-28] Tag Becomes Invalid After Saving — Leading “:” Added to Tag Value #81881

Open

7 tasks

chatgpt-codex-connector Bot reviewed Apr 7, 2026

View reviewed changes

Comment thread src/libs/Violations/ViolationsUtils.ts

Flag allTagLevelsRequired when transaction has more tag levels than p…

1e24236

…olicy

JmillsExpensify previously approved these changes Apr 8, 2026

View reviewed changes

situchan reviewed Apr 14, 2026

View reviewed changes

wildan-m added 2 commits April 15, 2026 07:09

Revert "Flag allTagLevelsRequired when transaction has more tag level…

d5df579

…s than policy" This reverts commit 1e24236.

Merge remote-tracking branch 'upstream/main' into wildan/81881-fix-le…

59f84f1

…ading-colon-tag

wildan-m dismissed JmillsExpensify’s stale review via 59f84f1 April 15, 2026 00:11

Merge remote-tracking branch 'upstream/main' into wildan/81881-fix-le…

4f7de5a

…ading-colon-tag

situchan approved these changes Apr 15, 2026

View reviewed changes

melvin-bot Bot requested a review from Julesssss April 15, 2026 03:11

chatgpt-codex-connector Bot reviewed Apr 15, 2026

View reviewed changes

Comment thread src/libs/Violations/ViolationsUtils.ts

Julesssss approved these changes Apr 15, 2026

View reviewed changes

Julesssss merged commit b497a8c into Expensify:main Apr 15, 2026
38 checks passed

OSBotify mentioned this pull request Apr 16, 2026

Deploy Checklist: New Expensify 2026-04-16 #88022

Closed

Conversation

wildan-m commented Apr 7, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Explanation of Change

Fixed Issues

Tests

Offline tests

QA Steps

PR Author Checklist

Screenshots/Videos

Uh oh!

codecov Bot commented Apr 7, 2026 • edited by github-actions Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Codecov Report

Uh oh!

melvin-bot Bot commented Apr 7, 2026

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

Uh oh!

JmillsExpensify left a comment

Choose a reason for hiding this comment

Uh oh!

situchan commented Apr 14, 2026

Uh oh!

situchan commented Apr 14, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Reviewer Checklist

Screenshots/Videos

Uh oh!

MelvinBot commented Apr 14, 2026

Uh oh!

situchan Apr 14, 2026

Choose a reason for hiding this comment

Uh oh!

MelvinBot Apr 14, 2026

Choose a reason for hiding this comment

Uh oh!

wildan-m Apr 15, 2026

Choose a reason for hiding this comment

Uh oh!

MelvinBot commented Apr 15, 2026

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

Uh oh!

Uh oh!

github-actions Bot commented Apr 15, 2026

Uh oh!

github-actions Bot commented Apr 15, 2026

Uh oh!

OSBotify commented Apr 15, 2026

Uh oh!

OSBotify commented Apr 16, 2026

Uh oh!

MelvinBot commented Apr 16, 2026

Uh oh!

OSBotify commented Apr 21, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

6 participants

wildan-m commented Apr 7, 2026 •

edited

Loading

codecov Bot commented Apr 7, 2026 •

edited by github-actions Bot

Loading

situchan commented Apr 14, 2026 •

edited

Loading