[NoQA][AI Reviewer] Fix file content exceeds maximum allowed tokens

[kacper-mikolajczak]

Explanation of Change

Fixes handling of too large files for AI reviewer. For more see summary in comment below.

Fixed Issues

$ #72802
PROPOSAL: #72802 (comment)

Tests

Create or find a PR that modifies src/CONST/index.ts and verify:

• Agent completes successfully
• Agent uses gh pr diff first
• Agent uses Grep instead of Read for large files
• Inline comments are still created correctly

Offline tests

QA Steps

// TODO: These must be filled out, or the issue title must include "[No QA]."

• Verify that no errors appear in the JS console

PR Author Checklist

• I linked the correct issue in the ### Fixed Issues section above
• I wrote clear testing steps that cover the changes made in this PR
  • I added steps for local testing in the Tests section
  • I added steps for the expected offline behavior in the Offline steps section
  • I added steps for Staging and/or Production testing in the QA steps section
  • I added steps to cover 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 tested this PR with a High Traffic account against the staging or production API to ensure there are no regressions (e.g. long loading states that impact usability).
• I included screenshots or videos for tests on all platforms
• I ran the tests on all platforms & verified they passed on:
  • Android: Native
  • Android: mWeb Chrome
  • iOS: Native
  • iOS: mWeb Safari
  • MacOS: Chrome / Safari
  • MacOS: Desktop
• I verified there are no console errors (if there's a console error not related to the PR, report it or open an issue for it to be fixed)
• I verified there are no new alerts related to the canBeMissing param for useOnyx
• I followed proper code patterns (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
    • If any non-english text was added/modified, I used JaimeGPT to get English > Spanish translation. I then posted it in #expensify-open-source and it was approved by an internal Expensify engineer. Link to Slack message:
  • 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 followed the guidelines as stated in the Review Guidelines
• I tested other components that can be impacted by my changes (i.e. if the PR modifies a shared library or component like Avatar, I verified the components using Avatar are working as expected)
• 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
• I verified that if a function's arguments changed that all usages have also been updated correctly
• 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 new assets were added or existing ones were modified, I verified that:
  • The assets are optimized and compressed (for SVG files, run npm run compress-svg)
  • The assets load correctly across all supported platforms.
• 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.
• I added unit tests for any new feature or bug fix in this PR to help automatically prevent regressions in this user 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.

Screenshots/Videos

Android: Native

Android: mWeb Chrome

iOS: Native

iOS: mWeb Safari

MacOS: Chrome / Safari

MacOS: Desktop

[kacper-mikolajczak]

Fix Summary: AI Reviewer Token Limit Errors

Problem

The AI reviewer agents were failing with token limit errors when trying to review PRs that modified large files:

File content (89479 tokens) exceeds maximum allowed tokens (25000).

From the error report:

• 13 occurrences of this error
• Affected files: src/CONST/index.ts (89k tokens), src/libs/actions/Policy/Policy.ts (70k tokens), and others
• Root cause: Agents were trying to read entire files, exceeding the 25k token read limit

Solution

1. Updated Code Inline Reviewer Agent

File: .claude/agents/code-inline-reviewer.md

Changes:

• ✅ Added instruction to start with gh pr diff to see only changed lines
• ✅ Added strategy for handling large files (>5000 lines) using Grep instead of Read
• ✅ Added fallback mechanism: if Read fails, switch to Grep immediately
• ✅ Added specific grep patterns for each performance rule (PERF-1 through PERF-6)

Key Instructions Added:

2. **For analyzing changed files:**
   - **For large files (>5000 lines):** Use the Grep tool instead of reading entire file
   - **For smaller files:** You may read the full file using the Read tool
   - **If a Read fails with token limit error:** Immediately switch to Grep

3. **Search strategy for large files:**
   - PERF-1: Search for `renderItem` and `...` patterns
   - PERF-2: Search for `.every(`, `.some(`, `.find(`, `.filter(`
   - PERF-3: Search for `useOnyx` within renderItem components
   - PERF-4: Search for `useMemo`, `useCallback` patterns
   - PERF-5: Search for `React.memo` and `deepEqual`
   - PERF-6: Search for hook dependency arrays

2. Updated HelpDot Inline Reviewer Agent

File: .claude/agents/helpdot-inline-reviewer.md

Changes:

• ✅ Added similar protections for large documentation files
• ✅ Added instruction to use gh pr diff first
• ✅ Added grep-based search for terminology violations
• ✅ Added fallback to chunked reading if needed

How It Works Now

Before (Failed)

1. Get list of changed files
2. For each file:
   - Read entire file (FAILS for large files >25k tokens)
   - Check for violations
   - Create inline comments

After (Fixed)

1. Get PR diff to see only changed lines
2. For each file:
   - If small file: Read entire file
   - If large file: Use Grep to search for specific patterns
   - If Read fails: Immediately fall back to Grep
   - Check for violations in changed areas only
   - Create inline comments

Expected Impact

Immediate Benefits

• ✅ Zero token limit errors - Agents will no longer try to read files that exceed limits
• ✅ Faster reviews - Only analyzing changed code, not entire files
• ✅ More reliable - Automatic fallback if Read operations fail
• ✅ Better resource usage - Using Grep instead of reading massive files

Error Rate Reduction

From your error report:

• Before: 13 token limit errors out of 164 total errors (7.9%)
• Expected After: 0 token limit errors (0%)

Affected Files That Will Now Work

These large files will no longer cause failures:

• src/CONST/index.ts (89,479 tokens)
• src/libs/actions/Policy/Policy.ts (70,347 tokens)
• Other large CONST and action files (25k-46k tokens)

Testing Recommendations

1. Test with a Known Large File PR

Create or find a PR that modifies src/CONST/index.ts and verify:

• Agent completes successfully
• Agent uses gh pr diff first
• Agent uses Grep instead of Read for large files
• Inline comments are still created correctly

2. Monitor Next 10 PR Reviews

Watch for:

• Zero token limit errors in job_error_report.md
• Successful completion rate
• Quality of inline comments (should be unchanged)

3. Check Agent Execution Time

Large file PRs should now be:

• Faster (not reading entire 89k token files)
• More efficient (grep is faster than full reads)

[melvin-bot]

@eh2077 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]

[eh2077]

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

NA

Android: mWeb Chrome

NA

iOS: HybridApp

NA

iOS: mWeb Safari

NA

MacOS: Chrome / Safari

NA

MacOS: Desktop

NA

[kacper-mikolajczak]

@mountiny, PR is ready to be merged and further tested 🚀

[mountiny]

Thanks!

[OSBotify]

✋ 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]

🚀 Deployed to staging by https://github.com/mountiny in version: 9.2.41-0 🚀

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

[OSBotify]

🚀 Deployed to production by https://github.com/puneetlath in version: 9.2.41-6 🚀

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