Skip to content

Comments

[No QA] Refactor Claude code reviewer to use structured JSON output#83226

Draft
kacper-mikolajczak wants to merge 4 commits intoExpensify:mainfrom
callstack-internal:refactor/claude-reviewer-structured-output
Draft

[No QA] Refactor Claude code reviewer to use structured JSON output#83226
kacper-mikolajczak wants to merge 4 commits intoExpensify:mainfrom
callstack-internal:refactor/claude-reviewer-structured-output

Conversation

@kacper-mikolajczak
Copy link
Contributor

@kacper-mikolajczak kacper-mikolajczak commented Feb 23, 2026 •
edited
Loading

Explanation of Change

Replace the Claude code reviewer's direct shell script calls (createInlineComment.sh, addPrReaction.sh) with structured JSON output enforced by claude-code-action's --json-schema flag. The agent now returns a validated { violations: [...] } object, and a separate workflow step handles posting inline comments or adding a PR reaction.

This separates infrastructure/usage logic from the reviewer's core analysis work, making it easier to extend capabilities or change the use-case without touching the reviewer agent itself.

Fixed Issues

$ #83224

Tests

  • Verify that no errors appear in the JS console
  • Open a PR with a code violation (e.g. spread in renderItem) and verify the workflow posts an inline comment
  • Open a clean PR and verify the workflow adds a +1 reaction

Offline tests

N/A - CI workflow only

QA Steps

// [No QA] - CI/tooling change only, no user-facing impact

  • 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
  • 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

N/A - CI/tooling change only

Android: mWeb Chrome

N/A - CI/tooling change only

iOS: Native

N/A - CI/tooling change only

iOS: mWeb Safari

N/A - CI/tooling change only

MacOS: Chrome / Safari

N/A - CI/tooling change only

@kacper-mikolajczak
refactor: use structured JSON output for Claude code reviewer
1f90dbb 
Leverage claude-code-action's --json-schema flag to enforce validated
JSON output from the reviewer agent instead of having the agent call
shell scripts directly. Comment posting and PR reactions are now handled
in a dedicated workflow step that consumes the structured_output.
@kacper-mikolajczak kacper-mikolajczak requested a review from a team as a code owner February 23, 2026 16:55
@melvin-bot melvin-bot bot requested review from ShridharGoel and removed request for a team February 23, 2026 16:55
@melvin-bot
Copy link

melvin-bot bot commented Feb 23, 2026

@ShridharGoel 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]

@kacper-mikolajczak kacper-mikolajczak mentioned this pull request Feb 23, 2026
Open
@kacper-mikolajczak kacper-mikolajczak marked this pull request as draft February 23, 2026 16:58
@kacper-mikolajczak
Copy link
Contributor Author

kacper-mikolajczak commented Feb 23, 2026

Hi @ShridharGoel! It was premature undrafting - there is no need for review for now. Sorry about that ❤️

@kacper-mikolajczak
Copy link
Contributor Author

kacper-mikolajczak commented Feb 23, 2026

@Julesssss could I ask you to run this improvement against #82206 in order to check its correctness? Thanks! ❤️

Julesssss
Julesssss reviewed Feb 23, 2026
View reviewed changes
.claude/agents/code-inline-reviewer.md
name: code-inline-reviewer
description: Reviews code and creates inline comments for specific rule violations.
tools: Glob, Grep, Read, TodoWrite, Bash, BashOutput, KillBash
tools: Glob, Grep, Read, Bash, BashOutput
Copy link
Contributor

@Julesssss Julesssss Feb 23, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Recently I improved MelvinBot by passing the Repo's settings.json file into the GitHub action confirg, this sets the file to Claude's user level settings. Preventing the need for manual tool definition for subagents.

Seems like something we could apply to the AI reviewer too perhaps?

Copy link
Contributor

@Julesssss Julesssss Feb 23, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

As a follow up

Copy link
Contributor Author

@kacper-mikolajczak kacper-mikolajczak Feb 25, 2026 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Great improvement! As you said, let's have it as a follow-up.

Julesssss
Julesssss reviewed Feb 23, 2026
View reviewed changes
Julesssss
Julesssss reviewed Feb 23, 2026
View reviewed changes
Julesssss
Julesssss reviewed Feb 23, 2026
View reviewed changes
Julesssss
Julesssss reviewed Feb 23, 2026
View reviewed changes
Copy link
Contributor

@Julesssss Julesssss left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looking good, conflicts and a couple of improvements. @kacper-mikolajczak I'll merge this one first tomorrow to avoid another conflict

@Julesssss
Copy link
Contributor

Julesssss commented Feb 23, 2026

@Julesssss could I ask you to run this improvement against #82206 in order to check its correctness? Thanks! ❤️

Sure, I did this locally again. Seems that the JSON improvement worked well. Reviewed the PR again

Screenshot 2026-02-23 at 15 40 16

@kacper-mikolajczak
Copy link
Contributor Author

kacper-mikolajczak commented Feb 25, 2026

Thanks for the review @Julesssss! All the comments were addressed. As those changes touch critical parts of the reviewer pipeline, I'd suggest we test it once again before merging.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@Julesssss Julesssss Julesssss left review comments

@ShridharGoel ShridharGoel Awaiting requested review from ShridharGoel

At least 1 approving review is required to merge this pull request.

Assignees

@kacper-mikolajczak kacper-mikolajczak

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@kacper-mikolajczak @Julesssss