Merged
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
|
Warning Rate limit exceeded
To keep reviews running without waiting, you can enable usage-based add-on for your organization. This allows additional reviews beyond the hourly cap. Account admins can enable it under billing. ⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (5)
📝 WalkthroughWalkthroughSwitches Node crypto usage to Changes
Sequence Diagram(s)sequenceDiagram
participant User
participant Browser
participant FileReader
participant GraphQL_API
participant QueryCache
User->>Browser: choose .zip file in admin upload form
Browser->>FileReader: readAsDataURL(file)
FileReader-->>Browser: base64-encoded ZIP
Browser->>GraphQL_API: UPLOAD_LEXICONS(base64Zip)
GraphQL_API-->>Browser: upload response (count / error)
Browser->>QueryCache: invalidate ["lexicons"]
Browser-->>User: show success/error and reset file input
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
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. Review rate limit: 0/1 reviews remaining, refill in 51 minutes and 17 seconds.Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (2)
client/src/app/docs/page.tsx (1)
71-81:⚠️ Potential issue | 🟡 MinorGuard overlapping tokens to avoid malformed highlight output.
highlightJScan process overlapping tokens (e.g., keyword inside string), which may render duplicate fragments and movelastEndbackward.💡 Suggested fix
- tokens.forEach((token) => { + tokens.forEach((token) => { + if (token.start < lastEnd) { + return; + } if (token.start > lastEnd) { parts.push(<span key={key++}>{line.slice(lastEnd, token.start)}</span>); } if (token.type === "keyword") { parts.push(<span key={key++} className="text-purple-400 font-medium">{token.text}</span>); } else if (token.type === "string") { parts.push(<span key={key++} className="text-amber-300">{token.text}</span>); } - lastEnd = token.end; + lastEnd = Math.max(lastEnd, token.end); });🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@client/src/app/docs/page.tsx` around lines 71 - 81, Tokens may overlap causing lastEnd to move backward and produce duplicate/malformed fragments; in the tokens.forEach loop (tokens.forEach) guard against overlaps by skipping any token where token.end <= lastEnd, compute startPos = Math.max(lastEnd, token.start) before pushing fragments, use the token's substring corresponding to [startPos, token.end] (i.e., token.text.slice(startPos - token.start, token.end - token.start)) when pushing highlighted spans into parts, and finally set lastEnd = Math.max(lastEnd, token.end) so lastEnd never moves backward.client/scripts/generate-jwk.js (1)
11-26:⚠️ Potential issue | 🟡 MinorSet non-zero exit code on error in catch handler
When
generateJWK()rejects, the catch block logs the error but the process still exits with code 0. This can cause CI/build checks to incorrectly pass. Update line 38 to:generateJWK().catch((err) => { console.error(err) process.exitCode = 1 })🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@client/scripts/generate-jwk.js` around lines 11 - 26, The current top-level caller of generateJWK() logs errors but does not set a non-zero exit code on failure; update the promise rejection handler for generateJWK() to set process.exitCode = 1 after logging the error (e.g., in the catch for generateJWK()) so CI sees failures; locate the invocation of generateJWK() and its .catch(...) and change it to log the error then set process.exitCode = 1.
🧹 Nitpick comments (1)
client/scripts/generate-jwk.js (1)
38-38: Script should exit non-zero on failure
generateJWK().catch(console.error)logs the error but doesn’t guarantee a failing exit code. For CI, better to setprocess.exitCode = 1(orprocess.exit(1)).🔧 Proposed fix
-generateJWK().catch(console.error) +generateJWK().catch((err) => { + console.error(err) + process.exitCode = 1 +})🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@client/scripts/generate-jwk.js` at line 38, The current top-level call generateJWK().catch(console.error) only logs failures but leaves process exit code as zero; update the catch handler for generateJWK to both log the error and set a non-zero exit (e.g., set process.exitCode = 1 or call process.exit(1)) so CI sees failures—replace the current trailing call with a catch that logs the error and sets the exit code accordingly.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@client/src/app/lexicons/page.tsx`:
- Around line 374-388: Prevent duplicate submits by guarding handleUpload with
an "in-progress" check and setting/resetting that flag before the FileReader
starts and after it completes/error. Specifically, add a local state like
isUploading (useState) and at the top of handleUpload return early if
uploadMutation.isPending || isUploading; set isUploading = true immediately
before calling reader.readAsDataURL(zipFile), and set isUploading = false in
both reader.onload and reader.onerror (after calling uploadMutation.mutate or
setError/setSuccess). Apply the same pattern to the other upload handler
referenced (the one around the other submit block) and ensure any submit
button/form disabled prop uses uploadMutation.isPending || isUploading.
- Around line 445-453: The textarea using state nsidInput (with onChange calling
setNsidInput) and the other input around lines 483-491 lack programmatic labels;
add either a <label htmlFor="..."> tied to a unique id on each control or add an
aria-label attribute on the textarea and the other input so assistive tech can
identify them (e.g., give the textarea id="nsid-input" and label/aria-label
"NSIDs" and apply a similar id/label/aria-label for the second control
referenced in that block).
- Around line 266-268: Import and use useAdminSession in
client/src/app/lexicons/page.tsx and gate the uploadMutation by the admin flag:
call const { isAdmin } = useAdminSession() and pass enabled: isAdmin to the
useMutation for uploadMutation (or conditionally render/disable the upload UI
when isAdmin is false) so only admins can trigger the UPLOAD_LEXICONS mutation;
ensure references to uploadMutation, UPLOAD_LEXICONS and the upload UI are
updated to respect isAdmin.
---
Outside diff comments:
In `@client/scripts/generate-jwk.js`:
- Around line 11-26: The current top-level caller of generateJWK() logs errors
but does not set a non-zero exit code on failure; update the promise rejection
handler for generateJWK() to set process.exitCode = 1 after logging the error
(e.g., in the catch for generateJWK()) so CI sees failures; locate the
invocation of generateJWK() and its .catch(...) and change it to log the error
then set process.exitCode = 1.
In `@client/src/app/docs/page.tsx`:
- Around line 71-81: Tokens may overlap causing lastEnd to move backward and
produce duplicate/malformed fragments; in the tokens.forEach loop
(tokens.forEach) guard against overlaps by skipping any token where token.end <=
lastEnd, compute startPos = Math.max(lastEnd, token.start) before pushing
fragments, use the token's substring corresponding to [startPos, token.end]
(i.e., token.text.slice(startPos - token.start, token.end - token.start)) when
pushing highlighted spans into parts, and finally set lastEnd =
Math.max(lastEnd, token.end) so lastEnd never moves backward.
---
Nitpick comments:
In `@client/scripts/generate-jwk.js`:
- Line 38: The current top-level call generateJWK().catch(console.error) only
logs failures but leaves process exit code as zero; update the catch handler for
generateJWK to both log the error and set a non-zero exit (e.g., set
process.exitCode = 1 or call process.exit(1)) so CI sees failures—replace the
current trailing call with a catch that logs the error and sets the exit code
accordingly.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: 1b351beb-8073-47aa-9f23-3e7976fee5d9
📒 Files selected for processing (6)
client/scripts/generate-jwk.jsclient/src/app/docs/page.tsxclient/src/app/lexicons/page.tsxclient/src/components/ThemeToggle.tsxclient/src/components/ui/Button.tsxclient/src/components/ui/Card.tsx
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@client/src/proxy.ts`:
- Around line 7-13: The current redirect only matches "localhost:<port>" and is
case-sensitive, so requests where hostname is "localhost" (no port) or
mixed-case like "LocalHost" are missed; update the check to use
hostname.toLowerCase() and match either exactly "localhost" or starting with
"localhost:"; when building the redirectUrl (used with NextResponse.redirect)
derive the port by checking for a colon in the original host (e.g., const port =
newHost.includes(":") ? newHost.split(":")[1] : "3000") so requests without an
explicit port get a sensible default, and then set redirectUrl.hostname =
"127.0.0.1" and redirectUrl.port = port before returning
NextResponse.redirect(redirectUrl, { status: 307 }).
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: 85274036-f2b3-4390-ad89-b2d90d39cdd1
📒 Files selected for processing (4)
client/.env.exampleclient/next.config.tsclient/src/app/lexicons/page.tsxclient/src/proxy.ts
✅ Files skipped from review due to trivial changes (1)
- client/.env.example
🚧 Files skipped from review as they are similar to previous changes (1)
- client/src/app/lexicons/page.tsx
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
uploadLexicons(zipBase64:)admin GraphQL mutation and refreshes the lexicon list after upload.Validation
npm --prefix client run lintnpm --prefix client run testnpm --prefix client run buildnode client/scripts/generate-jwk.jsNotes
Summary by CodeRabbit
New Features
Refactor
Chores