[No QA] Refactor Claude code reviewer to use structured JSON output by kacper-mikolajczak · Pull Request #83226 · Expensify/App

kacper-mikolajczak · 2026-02-23T16:55:12Z

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

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

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.

melvin-bot · 2026-02-23T16:55:19Z

@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 · 2026-02-23T16:59:22Z

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

kacper-mikolajczak · 2026-02-23T17:02:02Z

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

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

.github/workflows/claude-review.yml

.claude/commands/review-code-pr.md

.github/workflows/claude-review.yml

Julesssss

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

Julesssss · 2026-02-23T23:53:40Z

@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

kacper-mikolajczak · 2026-02-25T09:59:51Z

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.

Julesssss · 2026-02-25T20:40:54Z

Local test successful, though I see one less violation captured than the last local run:

28 violations detected across 3 files, covering all rule categories:
    - TestCrossFileViolations.tsx: 1 violation (PERF-6)
    - TestMultiViolationsSameRule.tsx: 2 violations (PERF-6 x2)
    - TestRuleViolations.tsx: 25 violations

Julesssss · 2026-02-25T20:45:41Z

PERF-3 was missed

kacper-mikolajczak · 2026-02-25T20:48:40Z

Hmm, that's interesting. We'd need to check the agent logs to see what has happened that PERF-3 was missed. Do you have access to those locally @Julesssss?

Julesssss · 2026-02-25T20:51:45Z

Hmm, that's interesting. We'd need to check the agent logs to see what has happened that PERF-3 was missed. Do you have access to those locally @Julesssss?

It seems just a bit flakey, as it worked on 2nd run 🤷 I think that's okay.

Julesssss · 2026-02-25T20:53:01Z

@kacper-mikolajczak lets just keep an eye on new runs once merged. Overall seems a good improvement

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: cad72bdf6d

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".

chatgpt-codex-connector · 2026-02-25T20:57:40Z

.github/workflows/claude-review.yml

+              PATH_ARG=$(echo "$v" | jq -r '.path')
+              BODY_ARG=$(echo "$v" | jq -r '.body')
+              LINE_ARG=$(echo "$v" | jq -r '.line')
+              createInlineComment.sh "$PATH_ARG" "$BODY_ARG" "$LINE_ARG" || true


Stop swallowing inline comment posting failures

The createInlineComment.sh call is wrapped with || true, so any failure to post a violation (for example an invalid line/path from the model output or a rule validation rejection) is silently ignored. In that case the workflow still succeeds, and because COUNT > 0 it also skips the +1 reaction path, leaving the PR with neither inline comments nor a success signal even though violations were detected.

Useful? React with 👍 / 👎.

That's a valid remark. However it is more of a dispute about how strict the reviewer check should be - initially it was defined as an auxiliary tool, which should not impact the CI process directly.

We started the discussion about it with Jules already - let's keep it intact for this PR and address it if needed on its own.

kacper-mikolajczak · 2026-02-25T21:17:03Z

Prettier is failing on schema file we've added .claude/schemas/code-review-output.json. It could be simply failing on a new file.

kacper-mikolajczak · 2026-02-25T21:40:10Z

Prettier issues finally resolved @Julesssss 🚀

Julesssss · 2026-02-25T21:49:58Z

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
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 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: mWeb Safari

MacOS: Chrome / Safari

kacper-mikolajczak · 2026-02-25T21:53:28Z

And it lifted off! Let's see how it performs in the wild :)

OSBotify · 2026-02-25T21:59:35Z

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

kacper-mikolajczak · 2026-02-25T22:26:00Z

It is failing due to:

gh: To use GitHub CLI in a GitHub Actions workflow, set the GH_TOKEN environment variable. Example:
  env:
    GH_TOKEN: ${{ github.token }}

I am working on fixing that.

OSBotify · 2026-02-27T15:26:56Z

🚀 Deployed to staging by https://github.com/Julesssss in version: 9.3.27-0 🚀

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

OSBotify · 2026-03-02T22:18:16Z

🚀 Deployed to production by https://github.com/blimpich in version: 9.3.27-8 🚀

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

kacper-mikolajczak requested a review from a team as a code owner February 23, 2026 16:55

melvin-bot bot assigned kacper-mikolajczak Feb 23, 2026

melvin-bot bot requested review from ShridharGoel and removed request for a team February 23, 2026 16:55

kacper-mikolajczak mentioned this pull request Feb 23, 2026

[Due for payment 2026-03-09] Refactor Claude code reviewer to use structured JSON output #83224

Closed

kacper-mikolajczak marked this pull request as draft February 23, 2026 16:58