Conversation
- Deleted the following test files as they are no longer needed: - `src/mastra/tools/tests/serpapi-news-trends.tool.test.ts` - `src/mastra/tools/tests/serpapi-search.tool.test.ts` - `src/mastra/tools/tests/serpapi-shopping.tool.test.ts` - `src/mastra/tools/tests/weather-tool.test.ts` - `src/mastra/tools/tests/web-scraper-tool.test.ts` - Added a new task documentation file `memory-bank/tasks/TASK001-update-2025-12-14.md` detailing updates made to align tools with the streaming and progress convention: - Replaced `data-tool-agent` messages with `data-tool-progress` in various tools. - Normalized nested-agent streaming patterns across tools. - Updated financial chart tools to use the new streaming pattern. - Updated client-side parsers to handle legacy `data-tool-agent` parts. - Documented changes in `src/mastra/tools/AGENTS.md`. - Noted that tests will be added to verify progress events and streaming behavior.
- Updated access control enforcement in tools and workflows to use `RequestContext` and agent-specific runtime context types. - Added optional fields `userId` and `researchPhase` to `ResearchRuntimeContext` for improved context handling. - Imported new agents: `calendarAgent`, `bgColorAgent`, and `danePackagePublisher` into the main index. - Implemented a new tool `colorChangeTool` to change the background color with a defined input schema.
Learn moreAll Green is an AI agent that automatically: ✅ Addresses code review comments ✅ Fixes failing CI checks ✅ Resolves merge conflicts |
![sourcery-ai[bot]](https://avatars.githubusercontent.com/in/48477?s=60&v=4){kind=small}
Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings. WalkthroughThis PR refactors tool progress event handling across the Mastra framework. It normalizes legacy event data into standardized progress events, adds streaming support to multiple tools with proper progress tracking, registers new agents, updates provider contexts to normalize legacy events, and removes legacy test files. Documentation and ESLint configurations are updated to align with new streaming conventions. Changes
Sequence DiagramsequenceDiagram
actor User
participant ToolRuntime as Tool Runtime
participant Agent as Agent<br/>(runtime or imported)
participant Writer as Writer/<br/>Progress Events
participant Client as Client UI
User->>ToolRuntime: Execute tool with input
ToolRuntime->>ToolRuntime: Emit progress event<br/>(start)
ToolRuntime->>Agent: Resolve agent<br/>(mastra.getAgent ∣∣ fallback)
alt Agent has stream()
ToolRuntime->>Agent: Invoke agent.stream(prompt)
Agent-->>ToolRuntime: MastraModelOutput
ToolRuntime->>Writer: Pipe textStream/fullStream
Writer-->>Client: Stream chunks to UI
ToolRuntime->>ToolRuntime: Extract text/object<br/>from stream
else Agent has generate() only
ToolRuntime->>Agent: Invoke agent.generate(prompt)
Agent-->>ToolRuntime: Response
ToolRuntime->>ToolRuntime: Parse response.object<br/>or response.text
end
ToolRuntime->>ToolRuntime: Emit progress event<br/>(in-progress/done)
ToolRuntime->>Writer: Custom event with<br/>status, message, stage
Writer-->>Client: Progress update to UI
ToolRuntime-->>User: Return structured result
Estimated Code Review Effort🎯 3 (Moderate) | ⏱️ ~25 minutes Areas requiring extra attention:
Possibly Related PRs
Poem
Pre-merge checks and finishing touches❌ Failed checks (3 warnings)
✨ 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. Comment |
|
🤖 Hi @ssdeanx, I've received your request, and I'm working on it now! You can track my progress in the logs for more details. |
|
🤖 I'm sorry @ssdeanx, but I was unable to process your request. Please see the logs for more details. |
Summary of ChangesHello @ssdeanx, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request introduces significant architectural improvements to the agent and tool ecosystem, focusing on standardizing how agents stream information and report progress. It refines core functionalities like document processing and context management, making the system more robust and extensible. The changes also reflect an updated approach to development guidelines and potentially testing practices. Highlights
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request introduces a significant and valuable refactoring to standardize tool streaming and progress events across the application. The changes improve consistency and align with modern agent interaction patterns. The code quality is high, with many tools being updated to a more robust and readable standard. However, there is a critical issue that must be addressed: a large number of test files have been removed. Given the scale of the refactoring, this introduces significant risk. The tests must be restored or rewritten to ensure the stability and correctness of the new implementations before this PR can be merged. I have also included a few minor suggestions to improve code readability in some of the more complex new logic.
I am having trouble creating individual review comments. Click here to see my feedback.
app/chat/providers/chat-context.tsx (324)
The files parameter is declared but never used within the sendMessage function. The recent ESLint configuration change will now flag this as a warning. If this parameter is not intended to be used, it should be removed to keep the function signature clean.
(text: string) => {
app/networks/providers/network-context.tsx (304-308)
This long chain of ternary operators to determine the msg value is difficult to read and maintain. Consider refactoring this logic into a helper function or a series of if statements to improve clarity. This would make it easier to understand the priority of fields (dataObj.text, dataObj.message, etc.) and to modify the logic in the future.
app/networks/providers/network-context.tsx (310)
Similar to the msg variable, this nested ternary for determining the stage is complex and reduces readability. Refactoring this into a more straightforward conditional structure would make the code easier to follow.
app/workflows/providers/workflow-context.tsx (327)
This chain of ternary operators for assigning the msg variable is complex and hard to read. To improve maintainability and clarity, please consider refactoring this into a small helper function or a series of if/else statements. This would make the logic for selecting the message source more explicit.
src/mastra/index.ts (483-488)
The checks authHeader !== null && authHeader !== '' and userId !== null && userId !== '' are slightly redundant. Since authHeader is initialized with ?? '', it will never be null. A simple truthiness check would be more concise and achieve the same result.
if (!userId && authHeader?.startsWith('Bearer ')) {
const token = authHeader.slice('Bearer '.length)
const exec = /user:([^;\s]+)/.exec(token)
if (exec) { userId = exec[1] }
}
if (userId) { requestContext.set('userId', userId) }
src/mastra/tools/AGENTS.md (105)
There appears to be a typo in the example code block. The line ends with ....,`, which includes an extra comma and backtick.
message: "Descriptive progress message ${inputData.context}....",
src/mastra/tools/document-chunking.tool.ts (341-347)
The duplicated span.end() call and its comment have been removed. This is a good cleanup. However, it's even better to ensure span.end() is called in all circumstances by using a finally block. I see this has been correctly implemented later in the file (lines 409-411), which is excellent practice!
src/mastra/tools/document-chunking.tool.ts (886)
This expression to safely access the text from metadata is a bit complex. It can be simplified to be more readable while achieving the same goal of providing an empty string as a fallback.
text: String(result.metadata?.text ?? ''),
src/mastra/tools/financial-chart-tools.ts (338)
The use of the nullish coalescing operator (??) here is more concise and idiomatic than the previous !== undefined check. This is a good improvement for code readability.
Greptile OverviewGreptile SummaryThis PR implements a comprehensive refactoring of the agent tool streaming architecture and adds new middleware for request context management. Key Changes
Issues Found
The refactoring follows Mastra's nested-agent-streaming pattern consistently and aligns with the project's AGENTS.md guidelines. Confidence Score: 4/5
Important Files ChangedFile Analysis
Sequence DiagramsequenceDiagram
participant Client as Frontend UI
participant Mastra as Mastra Runtime
participant Tool as Agent Tool
participant Agent as Nested Agent
participant Writer as Stream Writer
Client->>Mastra: POST /chat with message
Mastra->>Mastra: Apply middleware (extract user context from headers)
Note over Mastra: Extract userId, user-tier, language, temperature-unit
Mastra->>Tool: Execute tool (e.g. copywriterTool)
Tool->>Writer: Emit progress: "in-progress" - Starting agent
Tool->>Mastra: Get agent instance via context.mastra.getAgent()
Mastra-->>Tool: Return agent or fallback to import
Tool->>Agent: Call agent.stream(prompt)
Agent-->>Tool: Return MastraModelOutput stream
Tool->>Writer: Emit progress: "in-progress" - Streaming from agent
Tool->>Writer: Pipe stream.textStream or stream.fullStream
Writer->>Client: Stream nested agent chunks (text-delta, reasoning-delta)
Agent-->>Tool: Stream completes with text/object
Tool->>Tool: Parse response (JSON or text)
Tool->>Writer: Emit progress: "done" - Operation complete
Tool-->>Mastra: Return tool result
Mastra->>Client: Stream complete with final result
Note over Client,Writer: Legacy Event Normalization
Client->>Client: Normalize data-tool-agent → data-tool-progress
Client->>Client: Display progress events in UI
|
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
| return { | ||
| strategy: 'html' as const, | ||
| ...baseParams, |
There was a problem hiding this comment.
syntax: mismatch in property name: headers should be used instead of sections for markdown strategy
| return { | |
| strategy: 'html' as const, | |
| ...baseParams, | |
| headers: [ | |
| ['#', 'title'], | |
| ['##', 'section'], |
Prompt To Fix With AI
This is a comment left during a code review.
Path: src/mastra/tools/document-chunking.tool.ts
Line: 528:530
Comment:
**syntax:** mismatch in property name: `headers` should be used instead of `sections` for markdown strategy
```suggestion
headers: [
['#', 'title'],
['##', 'section'],
```
How can I resolve this? If you propose a fix, please make it concise.| await writer?.custom({ type: 'data-tool-progress', data: { status: 'in-progress', message: '🤖 Generating insights with learning agent', stage: 'extract-learnings' }, id: 'extract-learnings' }); | ||
|
|
||
| const truncatedContent = (result?.content ?? '').slice(0, 8000); | ||
| const contentWithTruncation = (result?.content ?? '').length > 8000 ? truncatedContent + 'AAAA...' : truncatedContent; |
There was a problem hiding this comment.
style: typo in truncation marker - should be three dots or ellipsis
| const contentWithTruncation = (result?.content ?? '').length > 8000 ? truncatedContent + 'AAAA...' : truncatedContent; | |
| const contentWithTruncation = (result?.content ?? '').length > 8000 ? truncatedContent + '...' : truncatedContent; |
Prompt To Fix With AI
This is a comment left during a code review.
Path: src/mastra/tools/extractLearningsTool.ts
Line: 55:55
Comment:
**style:** typo in truncation marker - should be three dots or ellipsis
```suggestion
const contentWithTruncation = (result?.content ?? '').length > 8000 ? truncatedContent + '...' : truncatedContent;
```
How can I resolve this? If you propose a fix, please make it concise.| } | ||
| if (userId !== null && userId !== '') { requestContext.set('userId', userId) } | ||
|
|
There was a problem hiding this comment.
logic: regex on untrusted bearer tokens without length validation could cause performance issues - add token length check before regex execution
Prompt To Fix With AI
This is a comment left during a code review.
Path: src/mastra/index.ts
Line: 487:489
Comment:
**logic:** regex on untrusted bearer tokens without length validation could cause performance issues - add token length check before regex execution
How can I resolve this? If you propose a fix, please make it concise.![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 32
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (7)
app/workflows/providers/workflow-context.tsx (1)
322-340: Consider refactoring complex message extraction logic.The normalization of legacy
data-tool-agentevents works correctly and provides good backward compatibility. However, the message extraction logic on line 327 is quite complex with multiple fallbacks and type assertions, making it difficult to read and maintain.Consider extracting this into a helper function for clarity:
// Helper function at the top of the file or in a utils module function extractAgentMessage(eventData: Record<string, unknown> | undefined): string { if (!eventData) { return 'Agent executing tool' } const dataObj = eventData.data as Record<string, unknown> | undefined // Check nested data object first if (typeof dataObj?.text === 'string') { return dataObj.text } if (typeof dataObj?.message === 'string') { return dataObj.message } // Fallback to top-level message if (typeof eventData.message === 'string') { return eventData.message } return 'Agent executing tool' } function extractStage(eventData: Record<string, unknown> | undefined): string { return typeof eventData?.stage === 'string' ? eventData.stage : 'tool agent' }Then simplify the usage:
// Handle legacy tool agent events (data-tool-agent) by normalizing into progress events if (part.type === "data-tool-agent") { const agentPart = part as { data?: AgentDataPart } const eventData = agentPart.data as Record<string, unknown> | undefined - const dataObj = eventData?.data as Record<string, unknown> | undefined - const msg = typeof dataObj?.text === 'string' ? dataObj.text : (typeof dataObj?.message === 'string' ? dataObj.message : (typeof eventData?.message === 'string' ? eventData.message : `Agent executing tool`)) - const stage = typeof eventData?.stage === 'string' ? eventData.stage : 'tool agent' + const msg = extractAgentMessage(eventData) + const stage = extractStage(eventData) if (msg && msg.trim().length > 0) {This improves readability while maintaining the same functionality and defensive checks.
app/chat/providers/chat-context.tsx (1)
323-330: Implementation signature doesn't match interface definition—use underscore prefix to align with ChatContext.The
sendMessageimplementation (line 324) declaresfiles?: File[], but the ChatContext interface (line 95) declares_files?: File[]. This mismatch will cause type errors. Since the parameter is unused, align the implementation with the interface:const sendMessage = useCallback( - (text: string, files?: File[]) => { + (text: string, _files?: File[]) => { if (!text.trim() || isLoading) {return} setChatError(null) aiSendMessage({ text: text.trim() }) },src/mastra/tools/editor-agent-tool.ts (1)
8-164: Missing TSDoc documentation for the tool.Per coding guidelines, public APIs should have TSDoc comments including parameter descriptions, return types, and examples. Consider adding documentation for
editorTool./** * Editor tool that calls the editor agent to improve content across multiple formats. * Supports streaming responses and emits progress events during execution. * * @example * ```typescript * const result = await editorTool.execute({ * content: "Draft blog post...", * contentType: "blog", * tone: "professional" * }, context); * ``` */ export const editorTool = createTool({src/mastra/tools/financial-chart-tools.ts (2)
16-206: Missing TSDoc documentation for chartSupervisorTool.Per coding guidelines, tools should have TSDoc comments. The existing JSDoc comment on line 12-15 is minimal. Consider expanding with
@param,@returns, and@exampletags.
84-205: chartSupervisorTool should explicitly orchestrate chartDataProcessorTool before chart generation.The tool currently delegates the entire pipeline to chartSupervisorAgent, which has chartDataProcessorTool available but doesn't mandate its use. Per coding guidelines, financial chart tools must explicitly orchestrate data processing through dedicated processors. Consider refactoring the execute function to explicitly call chartDataProcessorTool first to transform the fetched financial data into Recharts-compatible format, then pass the processed data to chartSupervisorAgent or chartGeneratorTool for component generation.
src/mastra/tools/copywriter-agent-tool.ts (1)
180-182: Critical: 'general' contentType throws error despite being a valid input option.The
generalcontent type is defined as a valid option in theinputSchema(line 27) and documented as the default, but the switch statement throwsError('Not implemented yet: "general" case'). This will break the tool for any user selecting or defaulting to 'general'.Either implement the 'general' case or remove it from the enum:
case 'general': { - throw new Error('Not implemented yet: "general" case') + prompt += '\n\nCreate clear, well-organized content appropriate for the topic and audience.' + break }src/mastra/tools/document-chunking.tool.ts (1)
916-920: Complex nested fallback logic for text extraction.This output formatting code has deeply nested ternary operators with type assertions, making it difficult to understand and maintain. This is related to the text extraction complexity on line 886.
Using the
extractTexthelper suggested earlier, create another helper for the rerank result:/** * Extract text from a rerank result with proper fallback chain */ function extractRerankText(r: RerankResult): string { // Try result.document first (if it's a string) if (typeof r.result?.document === 'string') { return r.result.document } // Try result.text const resultWithText = r.result as { text?: unknown } if (typeof resultWithText?.text === 'string') { return resultWithText.text } // Try result.metadata.text return extractText(r.result?.metadata) }Then simplify the output formatting:
const rerankedDocuments = rerankedResults.map((r, index) => ({ id: r.result?.id ?? `rerank_${index}`, - text: - (typeof r.result?.document === 'string' ? r.result.document : undefined) ?? - (typeof (r.result as { text?: unknown })?.text === 'string' ? (r.result as unknown as { text: string }).text : undefined) ?? - (r.result?.metadata?.text as string) ?? - '', + text: extractRerankText(r), metadata: r.result?.metadata ?? {}, relevanceScore: r.score, rank: index + 1, }))
📜 Review details
Configuration used: CodeRabbit UI
Review profile: ASSERTIVE
Plan: Pro
📒 Files selected for processing (34)
app/chat/providers/chat-context.tsx(1 hunks)app/networks/providers/network-context.tsx(2 hunks)app/workflows/providers/workflow-context.tsx(1 hunks)eslint.config.js(1 hunks)memory-bank/copilot-rules.md(1 hunks)memory-bank/memory-bank-instructions.md(1 hunks)memory-bank/tasks/TASK001-tool-streaming.md(1 hunks)memory-bank/tasks/TASK001-update-2025-12-14.md(1 hunks)src/mastra/AGENTS.md(1 hunks)src/mastra/agents/researchAgent.ts(3 hunks)src/mastra/index.ts(4 hunks)src/mastra/tools/AGENTS.md(4 hunks)src/mastra/tools/color-change-tool.ts(1 hunks)src/mastra/tools/copywriter-agent-tool.ts(3 hunks)src/mastra/tools/document-chunking.tool.ts(16 hunks)src/mastra/tools/editor-agent-tool.ts(4 hunks)src/mastra/tools/evaluateResultTool.ts(3 hunks)src/mastra/tools/extractLearningsTool.ts(3 hunks)src/mastra/tools/financial-chart-tools.ts(10 hunks)src/mastra/tools/tests/copywriter-agent-tool.test.ts(0 hunks)src/mastra/tools/tests/csv-to-json.tool.test.ts(0 hunks)src/mastra/tools/tests/data-file-manager.test.ts(0 hunks)src/mastra/tools/tests/data-validator.tool.test.ts(0 hunks)src/mastra/tools/tests/document-chunking.tool.test.ts(0 hunks)src/mastra/tools/tests/editor-agent-tool.test.ts(0 hunks)src/mastra/tools/tests/evaluateResultTool.test.ts(0 hunks)src/mastra/tools/tests/extractLearningsTool.test.ts(0 hunks)src/mastra/tools/tests/json-to-csv.tool.test.ts(0 hunks)src/mastra/tools/tests/serpapi-academic-local.tool.test.ts(0 hunks)src/mastra/tools/tests/serpapi-news-trends.tool.test.ts(0 hunks)src/mastra/tools/tests/serpapi-search.tool.test.ts(0 hunks)src/mastra/tools/tests/serpapi-shopping.tool.test.ts(0 hunks)src/mastra/tools/tests/weather-tool.test.ts(0 hunks)src/mastra/tools/tests/web-scraper-tool.test.ts(0 hunks)
💤 Files with no reviewable changes (15)
- src/mastra/tools/tests/serpapi-news-trends.tool.test.ts
- src/mastra/tools/tests/serpapi-academic-local.tool.test.ts
- src/mastra/tools/tests/document-chunking.tool.test.ts
- src/mastra/tools/tests/web-scraper-tool.test.ts
- src/mastra/tools/tests/serpapi-search.tool.test.ts
- src/mastra/tools/tests/copywriter-agent-tool.test.ts
- src/mastra/tools/tests/csv-to-json.tool.test.ts
- src/mastra/tools/tests/evaluateResultTool.test.ts
- src/mastra/tools/tests/serpapi-shopping.tool.test.ts
- src/mastra/tools/tests/data-validator.tool.test.ts
- src/mastra/tools/tests/editor-agent-tool.test.ts
- src/mastra/tools/tests/weather-tool.test.ts
- src/mastra/tools/tests/json-to-csv.tool.test.ts
- src/mastra/tools/tests/data-file-manager.test.ts
- src/mastra/tools/tests/extractLearningsTool.test.ts
🧰 Additional context used
📓 Path-based instructions (25)
**/*.md
📄 CodeRabbit inference engine (.github/instructions/markdown.instructions.md)
**/*.md: Use appropriate heading levels (H2, H3, etc.) to structure markdown content. Do not use H1 headings, as these will be generated from the title. Use##for H2 and###for H3 in a hierarchical manner. Recommend restructuring if content includes H4 or higher levels.
Use bullet points (with-) or numbered lists (with1.) for lists in markdown. Indent nested lists with two spaces and ensure proper indentation and spacing.
Use fenced code blocks (triple backticks) for code snippets in markdown. Specify the language after the opening backticks for syntax highlighting (e.g.,csharp).
Use proper markdown syntax for links:[link text](URL). Ensure that link text is descriptive and URLs are valid and accessible.
Use proper markdown syntax for images:. Include a brief description of the image in the alt text for accessibility.
Use markdown tables (with|delimiters) for tabular data. Ensure proper formatting, alignment, and inclusion of headers.
Limit line length to 80 characters in markdown for readability. Use soft line breaks for long paragraphs.
Use appropriate whitespace in markdown to separate sections and improve readability. Use blank lines between sections and avoid excessive whitespace.
Include YAML front matter at the beginning of markdown files with required metadata fields:post_title,author1,post_slug,microsoft_alias,featured_image,categories(from /categories.txt),tags,ai_note,summary, andpost_date.
Files:
src/mastra/AGENTS.mdmemory-bank/tasks/TASK001-update-2025-12-14.mdsrc/mastra/tools/AGENTS.mdmemory-bank/memory-bank-instructions.mdmemory-bank/tasks/TASK001-tool-streaming.mdmemory-bank/copilot-rules.md
src/mastra/**/*
📄 CodeRabbit inference engine (src/AGENTS.md)
mastramodules can import fromutils, but must not import fromapporcli(excepttypes)
Files:
src/mastra/AGENTS.mdsrc/mastra/index.tssrc/mastra/tools/evaluateResultTool.tssrc/mastra/tools/financial-chart-tools.tssrc/mastra/agents/researchAgent.tssrc/mastra/tools/color-change-tool.tssrc/mastra/tools/AGENTS.mdsrc/mastra/tools/extractLearningsTool.tssrc/mastra/tools/copywriter-agent-tool.tssrc/mastra/tools/document-chunking.tool.tssrc/mastra/tools/editor-agent-tool.ts
**/*.{js,jsx,ts,tsx}
📄 CodeRabbit inference engine (.github/instructions/next-js.instructions.md)
**/*.{js,jsx,ts,tsx}: Usenext/dynamicfor dynamic imports to load components only when needed, improving initial load time.
Usenext/imagecomponent for automatic image optimization, including lazy loading and responsive images.
Use React.memo to prevent unnecessary re-renders of components.
Use the<Link prefetch>tag to prefetch pages that are likely to be visited.
Use getServerSideProps, getStaticProps, or server components for fetching data on the server-side.
Use SWR or React Query for client-side data fetching and caching.
Use CSS Modules, Styled Components, or Tailwind CSS for component-level styling. Prefer Tailwind CSS for rapid development.
Use React Context, Zustand, Jotai, or Recoil for managing global state. Avoid Redux unless necessary.
Usereact-hook-formfor managing forms and validation.
Only fetch the data that is needed by the component to avoid over-fetching.
Avoid long-running synchronous operations in the main thread to prevent blocking.
Always usesetStateor hooks to update state instead of mutating state directly.
Include a complete dependency array inuseEffecthooks to prevent unexpected behavior.
Avoid writing server-side code in client components to prevent exposing secrets or causing unexpected behavior.
Usetry...catchblocks for handling errors in asynchronous operations.
Implement error boundary components usinggetDerivedStateFromErrororcomponentDidCatchlifecycle methods.
Sanitize user input to prevent Cross-Site Scripting (XSS) attacks. Be especially careful when rendering HTML directly from user input.
Store authentication tokens in HTTP-only cookies or local storage securely.
Implement role-based access control to restrict access to sensitive resources.
Clean up event listeners and timers inuseEffecthooks to avoid memory leaks.
Only update state when necessary to reduce the number of re-renders and improve performance.
Use immutable data structures and avoid mutating data directly to prevent unexpected...
Files:
src/mastra/index.tsapp/chat/providers/chat-context.tsxsrc/mastra/tools/evaluateResultTool.tsapp/workflows/providers/workflow-context.tsxapp/networks/providers/network-context.tsxsrc/mastra/tools/financial-chart-tools.tssrc/mastra/agents/researchAgent.tssrc/mastra/tools/color-change-tool.tssrc/mastra/tools/extractLearningsTool.tssrc/mastra/tools/copywriter-agent-tool.tseslint.config.jssrc/mastra/tools/document-chunking.tool.tssrc/mastra/tools/editor-agent-tool.ts
**/*.{js,ts}
📄 CodeRabbit inference engine (.github/instructions/next-js.instructions.md)
Use parameterized queries or an ORM to prevent SQL injection attacks.
Files:
src/mastra/index.tssrc/mastra/tools/evaluateResultTool.tssrc/mastra/tools/financial-chart-tools.tssrc/mastra/agents/researchAgent.tssrc/mastra/tools/color-change-tool.tssrc/mastra/tools/extractLearningsTool.tssrc/mastra/tools/copywriter-agent-tool.tseslint.config.jssrc/mastra/tools/document-chunking.tool.tssrc/mastra/tools/editor-agent-tool.ts
**/*.{ts,tsx,js,jsx,py,java,cs,rb,go,rs,cpp,c,h,hpp,swift,kotlin,php,scala,clj,groovy,lua,sh,bash}
📄 CodeRabbit inference engine (.github/instructions/self-explanatory-code-commenting.instructions.md)
**/*.{ts,tsx,js,jsx,py,java,cs,rb,go,rs,cpp,c,h,hpp,swift,kotlin,php,scala,clj,groovy,lua,sh,bash}: Write code that speaks for itself. Comment only when necessary to explain WHY, not WHAT. Avoid obvious comments that state what the code literally does.
Avoid redundant comments that simply repeat what the code is doing
Keep comments accurate and up-to-date with code changes. Remove or update outdated comments that no longer match the implementation.
Write comments for complex business logic that explain the WHY behind specific calculations or business rules
Document non-obvious algorithms with comments explaining the algorithm choice and its reasoning
Add comments explaining what regex patterns match, especially for complex patterns
Document API constraints, rate limits, gotchas, and external dependencies with explanatory comments
Avoid commenting out dead code. Use version control instead of maintaining commented code blocks.
Do not maintain code change history or modification logs as comments. Rely on git history and commit messages instead.
Avoid decorative divider comments (e.g., lines of equals signs or asterisks) for section separation
Ensure comments are placed appropriately above or adjacent to the code they describe
Write comments using proper grammar, spelling, and professional language
Prefer self-documenting code with clear variable/function names over adding comments to explain unclear code
Files:
src/mastra/index.tsapp/chat/providers/chat-context.tsxsrc/mastra/tools/evaluateResultTool.tsapp/workflows/providers/workflow-context.tsxapp/networks/providers/network-context.tsxsrc/mastra/tools/financial-chart-tools.tssrc/mastra/agents/researchAgent.tssrc/mastra/tools/color-change-tool.tssrc/mastra/tools/extractLearningsTool.tssrc/mastra/tools/copywriter-agent-tool.tseslint.config.jssrc/mastra/tools/document-chunking.tool.tssrc/mastra/tools/editor-agent-tool.ts
**/*.{ts,tsx,js,jsx}
📄 CodeRabbit inference engine (.github/instructions/self-explanatory-code-commenting.instructions.md)
**/*.{ts,tsx,js,jsx}: Document public APIs with TSDoc/JSDoc comments including parameter descriptions, return types, examples, and thrown exceptions
Add TSDoc comments to configuration constants and environment variables explaining their source, reasoning, or constraints
Use TSDoc annotation tags (TODO, FIXME, HACK, NOTE, WARNING, PERF, SECURITY, BUG, REFACTOR, DEPRECATED) to mark special comments
Include file headers with @fileoverview, @author, @copyright, and @license tags to document file purpose and ownership
Document function parameters with @param tags, return values with @returns tags, and exceptions with @throws tags in TSDoc comments
Use @see tags in TSDoc comments to reference related functions, methods, or documentation
Include @example tags in public API documentation with code examples showing typical usage
**/*.{ts,tsx,js,jsx}: Use Mastra mcp tools (#mastradocs,#mastraChanges,#mastraexamples,#mastraBlog) for Mastra framework development to stay updated with latest features and best practices
When working with Next.js projects, always utilize thenext-devtools-mcpserver for all Next.js related queries
Files:
src/mastra/index.tsapp/chat/providers/chat-context.tsxsrc/mastra/tools/evaluateResultTool.tsapp/workflows/providers/workflow-context.tsxapp/networks/providers/network-context.tsxsrc/mastra/tools/financial-chart-tools.tssrc/mastra/agents/researchAgent.tssrc/mastra/tools/color-change-tool.tssrc/mastra/tools/extractLearningsTool.tssrc/mastra/tools/copywriter-agent-tool.tseslint.config.jssrc/mastra/tools/document-chunking.tool.tssrc/mastra/tools/editor-agent-tool.ts
**/*.{ts,tsx}
📄 CodeRabbit inference engine (.github/instructions/self-explanatory-code-commenting.instructions.md)
**/*.{ts,tsx}: Document interface and type definitions with TSDoc comments explaining their purpose and usage context
Document interface properties with /** */ comments explaining each field's purpose and constraints
Document generic type parameters with @template tags explaining what each type parameter represents
Use type guards with comments explaining the runtime validation logic being performed
Document advanced/complex TypeScript types with explanatory comments about their purpose and use cases
Files:
src/mastra/index.tsapp/chat/providers/chat-context.tsxsrc/mastra/tools/evaluateResultTool.tsapp/workflows/providers/workflow-context.tsxapp/networks/providers/network-context.tsxsrc/mastra/tools/financial-chart-tools.tssrc/mastra/agents/researchAgent.tssrc/mastra/tools/color-change-tool.tssrc/mastra/tools/extractLearningsTool.tssrc/mastra/tools/copywriter-agent-tool.tssrc/mastra/tools/document-chunking.tool.tssrc/mastra/tools/editor-agent-tool.ts
src/mastra/index.ts
📄 CodeRabbit inference engine (src/AGENTS.md)
Enforce registration pattern in
mastra/index.tsfor AI orchestration modules composition
Files:
src/mastra/index.ts
**/*.{css,tsx,ts}
📄 CodeRabbit inference engine (AGENTS.md)
Use Tailwind CSS 4 with oklch color variables for styling
Files:
src/mastra/index.tsapp/chat/providers/chat-context.tsxsrc/mastra/tools/evaluateResultTool.tsapp/workflows/providers/workflow-context.tsxapp/networks/providers/network-context.tsxsrc/mastra/tools/financial-chart-tools.tssrc/mastra/agents/researchAgent.tssrc/mastra/tools/color-change-tool.tssrc/mastra/tools/extractLearningsTool.tssrc/mastra/tools/copywriter-agent-tool.tssrc/mastra/tools/document-chunking.tool.tssrc/mastra/tools/editor-agent-tool.ts
**/app/**
📄 CodeRabbit inference engine (.github/instructions/next-js.instructions.md)
Use the
app/directory structure for route handlers, server components, and client components (Next.js 13+). Prefer this over thepages/directory for new projects.
Files:
app/chat/providers/chat-context.tsxapp/workflows/providers/workflow-context.tsxapp/networks/providers/network-context.tsx
app/**/*.{tsx,ts}
📄 CodeRabbit inference engine (app/AGENTS.md)
app/**/*.{tsx,ts}: Use Tailwind CSS 4 with oklch color variables for styling in Next.js App Router pages and layouts
Use React 19 latest features in component implementations within the app directory
Files:
app/chat/providers/chat-context.tsxapp/workflows/providers/workflow-context.tsxapp/networks/providers/network-context.tsx
app/chat/providers/chat-context.tsx
📄 CodeRabbit inference engine (app/chat/AGENTS.md)
app/chat/providers/chat-context.tsx: Use ChatContext provider with AI SDK v5 types in chat-context.tsx to manage chat state, agent selection, and streaming messages across the application
Use DefaultChatTransport from @ai-sdk/react with the Mastra /chat route endpoint, configure prepareSendMessagesRequest to include resourceId and agentId in the request body for proper agent routing
Files:
app/chat/providers/chat-context.tsx
app/**/*.{ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
Frontend uses Next.js 16 App Router with React 19; use shadcn/ui base components (34 components) from ui/ directory
Files:
app/chat/providers/chat-context.tsxapp/workflows/providers/workflow-context.tsxapp/networks/providers/network-context.tsx
app/**/*.tsx
📄 CodeRabbit inference engine (AGENTS.md)
Use @ai-sdk/react for streaming and AI interactions in React components
Files:
app/chat/providers/chat-context.tsxapp/workflows/providers/workflow-context.tsxapp/networks/providers/network-context.tsx
src/mastra/tools/**/*.ts
📄 CodeRabbit inference engine (src/mastra/AGENTS.md)
src/mastra/tools/**/*.ts: Use thecreateToolpattern with Zod schemas when adding new tools undersrc/mastra/tools
Use explicit Zod schemas for every tool input/outputImplement tools using createTool({ id, inputSchema, outputSchema, execute }) pattern with strict Zod schemas
Files:
src/mastra/tools/evaluateResultTool.tssrc/mastra/tools/financial-chart-tools.tssrc/mastra/tools/color-change-tool.tssrc/mastra/tools/extractLearningsTool.tssrc/mastra/tools/copywriter-agent-tool.tssrc/mastra/tools/document-chunking.tool.tssrc/mastra/tools/editor-agent-tool.ts
src/mastra/{tools,workflows}/**/*.ts
📄 CodeRabbit inference engine (src/mastra/AGENTS.md)
Use
RuntimeContextto enforce access control in tools and workflows
Files:
src/mastra/tools/evaluateResultTool.tssrc/mastra/tools/financial-chart-tools.tssrc/mastra/tools/color-change-tool.tssrc/mastra/tools/extractLearningsTool.tssrc/mastra/tools/copywriter-agent-tool.tssrc/mastra/tools/document-chunking.tool.tssrc/mastra/tools/editor-agent-tool.ts
src/mastra/{tools,agents,workflows}/**/*.ts
📄 CodeRabbit inference engine (AGENTS.md)
Use Zod schemas for strict input/output validation in tools, agents, and workflows
Files:
src/mastra/tools/evaluateResultTool.tssrc/mastra/tools/financial-chart-tools.tssrc/mastra/agents/researchAgent.tssrc/mastra/tools/color-change-tool.tssrc/mastra/tools/extractLearningsTool.tssrc/mastra/tools/copywriter-agent-tool.tssrc/mastra/tools/document-chunking.tool.tssrc/mastra/tools/editor-agent-tool.ts
src/mastra/tools/**/*.{ts,tool.ts}
📄 CodeRabbit inference engine (src/mastra/tools/AGENTS.md)
All tool exports must be named exports matching the pattern {descriptiveName}Tool and must include Zod input/output schemas
Files:
src/mastra/tools/evaluateResultTool.tssrc/mastra/tools/financial-chart-tools.tssrc/mastra/tools/color-change-tool.tssrc/mastra/tools/extractLearningsTool.tssrc/mastra/tools/copywriter-agent-tool.tssrc/mastra/tools/document-chunking.tool.tssrc/mastra/tools/editor-agent-tool.ts
app/workflows/providers/workflow-context.tsx
📄 CodeRabbit inference engine (app/workflows/AGENTS.md)
app/workflows/providers/workflow-context.tsx: State management in workflow-context.tsx should use useChat hook from @ai-sdk/react with DefaultChatTransport for real-time streaming
Workflow-context.tsx should provide WorkflowContextValue interface with state management for selectedWorkflow, workflowStatus, currentRun, activeStepIndex, and streaming data
Files:
app/workflows/providers/workflow-context.tsx
app/networks/**/*.tsx
📄 CodeRabbit inference engine (app/networks/AGENTS.md)
app/networks/**/*.tsx: UseuseChatfrom@ai-sdk/reactwithDefaultChatTransportfor streaming responses from the/networkroute in the networks feature
Support real-time streaming with stop/cancel functionality, reasoning visualization for chain-of-thought models, and tool invocation display showing agent tool calls
Provide a responsive layout with collapsible sidebar on mobile for the networks feature
Files:
app/networks/providers/network-context.tsx
app/networks/providers/network-context.tsx
📄 CodeRabbit inference engine (app/networks/AGENTS.md)
Implement state management using
useNetworkContext()hook that provides selectedNetwork, networkConfig, networkStatus, messages, streamingOutput, routingSteps, and control functions (sendMessage, stopExecution, clearHistory)
Files:
app/networks/providers/network-context.tsx
src/mastra/tools/*financial-chart*.ts
📄 CodeRabbit inference engine (src/mastra/tools/AGENTS.md)
Financial chart tools must orchestrate data processing through dedicated processors before chart generation
Files:
src/mastra/tools/financial-chart-tools.ts
src/mastra/agents/**/*.ts
📄 CodeRabbit inference engine (src/mastra/AGENTS.md)
Add new agent definitions under
src/mastra/agentsthat wire tools together into higher-level behaviorsAgents must compose tools into specialized behaviors and be located in src/mastra/agents
Files:
src/mastra/agents/researchAgent.ts
src/mastra/agents/*.ts
📄 CodeRabbit inference engine (src/mastra/agents/AGENTS.md)
src/mastra/agents/*.ts: Agent file naming convention: Create agent files using kebab-case with.tsextension in/src/mastra/agents/directory (e.g.,your-agent-name.ts)
Each agent must follow the pattern: export agent asconst yourAgent = new Agent({ id: 'your-agent-id', name: 'Your Agent Name', description: '...' })
Files:
src/mastra/agents/researchAgent.ts
src/mastra/tools/**/*.tool.ts
📄 CodeRabbit inference engine (src/mastra/tools/AGENTS.md)
src/mastra/tools/**/*.tool.ts: All tools must emit progress events with type 'data-tool-progress' containing status ('in-progress' or 'done'), message, and stage fields, with id placed outside the data object
Data validation in tools must use Zod schemas for runtime validation
Files:
src/mastra/tools/document-chunking.tool.ts
🧬 Code graph analysis (5)
src/mastra/tools/evaluateResultTool.ts (3)
src/mastra/agents/evaluationAgent.ts (1)
evaluationAgent(18-140)src/mastra/services/VectorQueryService.ts (1)
query(419-442)src/mastra/config/logger.ts (1)
log(14-18)
src/mastra/tools/financial-chart-tools.ts (1)
src/mastra/agents/recharts.ts (4)
chartSupervisorAgent(378-539)chartGeneratorAgent(237-372)chartDataProcessorAgent(131-231)chartTypeAdvisorAgent(44-125)
src/mastra/tools/copywriter-agent-tool.ts (2)
src/mastra/index.ts (1)
mastra(99-523)src/mastra/agents/copywriterAgent.ts (1)
copywriterAgent(27-148)
src/mastra/tools/document-chunking.tool.ts (2)
src/mastra/config/logger.ts (3)
logStepStart(72-88)logError(153-174)log(14-18)src/mastra/config/pg-storage.ts (1)
pgVector(77-84)
src/mastra/tools/editor-agent-tool.ts (1)
src/mastra/agents/editorAgent.ts (1)
editorAgent(18-133)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (6)
- GitHub Check: CodeQL analysis (javascript-typescript)
- GitHub Check: Agent
- GitHub Check: Codacy Security Scan
- GitHub Check: Analyze (javascript-typescript)
- GitHub Check: Codacy Security Scan
- GitHub Check: Analyze (javascript-typescript)
🔇 Additional comments (28)
src/mastra/AGENTS.md (1)
48-48: LGTM! Improved context guidance.The updated guidance to use
RequestContextor agent-specific runtime context types provides clearer direction for developers implementing access control. This aligns with the middleware patterns introduced elsewhere in the codebase.app/chat/providers/chat-context.tsx (1)
95-95: Public API parameter name changed.The parameter name changed from
_filestofilesin the public interface. While this doesn't affect consumers (parameter names in interfaces are for documentation), be aware this parameter remains unused in the implementation (see line 324).src/mastra/tools/AGENTS.md (1)
135-136: LGTM! Documentation properly updated.The documentation updates correctly reference the TASK001 tracking, update timestamps, and add appropriate changelog entries for the streaming and progress event changes.
Also applies to: 151-151, 163-163
src/mastra/agents/researchAgent.ts (3)
37-39: LGTM! Well-designed runtime context extensions.The new
userIdandresearchPhasefields enable user-aware and phase-specific research behavior. The union type forresearchPhase('initial' | 'followup' | 'validation' | string) provides good flexibility while documenting common phases.
52-53: LGTM! Proper context field integration.The new runtime context fields are correctly read with sensible defaults ('anonymous', 'initial') and integrated into the system prompt. This enables the research agent to adapt its behavior based on user identity and research phase.
Also applies to: 62-63
171-172: Lines 169 and 175 use non-existentgoogle.chat()method that will fail at runtime.Line 172 (pro tier) returns a valid string format
'google/gemini-2.5-flash-preview-09-2025'. However, lines 169 and 175 callgoogle.chat()which does not exist in the@ai-sdk/googlelibrary. This pattern is used identically inscriptWriterAgent.tsandeditorAgent.ts.Align all tiers with the working pattern used in most other agents (e.g.,
stockAnalysisAgent.ts,weather-agent.ts):model: ({ requestContext }: { requestContext: RequestContext<ResearchRuntimeContext> }) => { const userTier = requestContext.get('user-tier') ?? 'free' if (userTier === 'enterprise') { // higher quality (chat style) for enterprise - return google.chat('gemini-3-pro-preview') + return googleAIPro } else if (userTier === 'pro') { // cheaper/faster model for pro tier - return 'google/gemini-2.5-flash-preview-09-2025' + return googleAI } // cheaper/faster model for free tier - return google.chat('gemini-2.5-flash-preview-09-2025') + return googleAIFlashLite },Likely an incorrect or invalid review comment.
memory-bank/memory-bank-instructions.md (1)
40-40: LGTM! Helpful cross-reference to streaming conventions.The addition of the TASK001-tool-streaming.md reference provides developers with clear guidance on implementing standardized streaming and progress events. This helps maintain consistency across tool implementations.
app/networks/providers/network-context.tsx (2)
298-323: LGTM - Robust legacy event normalization.The defensive extraction of message text from multiple possible fields (
dataObj?.text,dataObj?.message,eventData?.message,eventData?.text) with proper type guards handles varying legacy event formats well. The stage derivation fallback and agentId extraction are appropriately guarded.
331-341: The condition correctly filters for the actual status values emitted by tools. All tools in the codebase emit onlystatus: "in-progress"orstatus: "done"; error conditions are indicated via thestagefield (e.g.,status: "done", stage: "error"), not through a"error"status value. The"error"status defined in theProgressEventtype is never created by any tool implementation and appears to be unused in the current codebase.However, the
ProgressEventtype definition includes"error"as a valid status value, creating a mismatch between the type and actual usage. Consider either removing"error"from the type definition or implementing support for error progress events if they're intended for future use.memory-bank/copilot-rules.md (1)
155-179: LGTM - Clear streaming convention documentation.The guidance provides actionable patterns for:
- Runtime agent resolution with fallback
- Stream API usage with
textStream/fullStreampiping- Structured progress event emission
This aligns well with the implementation changes in
evaluateResultTool.tsand other tools in this PR.src/mastra/index.ts (3)
54-56: LGTM - New agent imports.The new agent imports for
calendarAgent,bgColorAgent, anddanePackagePublisherfollow the established pattern.
147-151: LGTM - Agent registration follows established pattern.New agents are properly registered in the Mastra agent registry with descriptive comments.
484-497: Token parsing is basic pattern matching - verify this is intentional.The userId and userTier extraction from Bearer tokens uses simple string pattern matching (
/user:([^;\s]+)/,token.includes('enterprise')), not cryptographic JWT validation. This appears to be development/convenience logic.Ensure this approach is intentional and that proper authentication is handled elsewhere (e.g., API gateway, separate auth middleware). Based on coding guidelines, authentication tokens should be handled securely.
src/mastra/tools/evaluateResultTool.ts (4)
5-5: LGTM - Type import for streaming support.Adding
MastraModelOutputtype import aligns with the streaming pattern documented incopilot-rules.md.
54-55: LGTM - Runtime agent resolution with fallback.Follows the TASK001 streaming convention: prefer runtime agent via
context.mastra.getAgent(), fallback to local import.
90-93: LGTM - Generate fallback path with defensive parsing.The fallback to
agent.generate()when streaming is unavailable, with defensive JSON parsing using an IIFE, handles both structured and text responses appropriately.
64-72: The code correctly implements the official Mastra nested-agent streaming pattern. After callingpipeTo()onstream.textStreamorstream.fullStream, awaitingstream.textworks as intended becauseMastraModelOutputmaintains a separate internal buffer for the.textproperty independent of stream consumption. This pattern is documented in the project's memory bank and consistently used across all agent-calling tools without issues.Likely an incorrect or invalid review comment.
src/mastra/tools/editor-agent-tool.ts (4)
38-51: LGTM - Progress event initialization.The progress event structure follows the standardized
data-tool-progresspattern with appropriate status, message, and stage fields.
115-121: Good error handling in streaming block.The error handling correctly records exceptions on the span, sets error status, and rethrows. This ensures observability while preserving the error for the outer catch block.
91-92: The type assertionas MastraModelOutput | undefineditself lacks runtime validation, but the code already implements comprehensive defensive checks that prevent the claimed issues. Property accesses use optional chaining (stream?.textStream,stream?.fullStream,stream?.text), and fallback values are provided via the null coalescing operator (?? ''). The if-else-if structure on lines 97–110 handles all cases: textStream, fullStream, or fallback toagent.generate(). This is the documented standard pattern in your codebase (permemory-bank/copilot-rules.md) for agent streaming, and the try-catch block (lines 90–121) provides additional error handling.Likely an incorrect or invalid review comment.
97-106: This implementation follows the documented Mastra tool streaming pattern referenced in the official docs. The code already includes runtime guards checking forwriterexistence before callingpipeTo(), preventing the runtime errors this comment suggests. The unsafe cast is an intentional design of Mastra's tool context to support different runtime environments, and this pattern is consistently implemented across all agent-based tools in the codebase. No changes are needed.src/mastra/tools/financial-chart-tools.ts (1)
108-117: Agent capability check validates correctly.The check
typeof agent.generate !== 'function' && typeof agent.stream !== 'function'correctly validates that the agent has at least one invocation method before proceeding. This is a good defensive pattern.src/mastra/tools/copywriter-agent-tool.ts (1)
108-130: Good defensive validation for agent availability.The check for agent invocation methods and graceful fallback with a user-friendly message is well implemented.
src/mastra/tools/extractLearningsTool.ts (1)
76-92: Good streaming implementation with proper fallback.The streaming logic correctly checks for
streamfunction availability, usesMastraModelOutputtyping, and falls back togeneratewhen streaming is unavailable.src/mastra/tools/document-chunking.tool.ts (4)
409-411: LGTM! Proper span cleanup in finally block.Adding
finallyblocks to ensurespan.end()is called prevents OpenTelemetry span leaks and follows tracing best practices. This pattern is correctly applied across all three tools in this file.
841-847: LGTM! Proper weight normalization with informative logging.The weight normalization ensures valid input to the reranker and provides helpful debugging information when user-supplied weights don't sum to 1. The floating-point comparison threshold is appropriate.
199-199: LGTM! Progress events follow coding guidelines.The tool progress events are properly structured with
type: 'data-tool-progress', include required fields (status,message,stage), and place theidoutside thedataobject as required by the coding guidelines. This pattern is consistently applied across all three tools.Based on coding guidelines: "All tools must emit progress events with type 'data-tool-progress' containing status ('in-progress' or 'done'), message, and stage fields, with id placed outside the data object."
46-56: Remove unnecessary export ofnormalizeWeightsfunction.The function is only used internally within
document-chunking.tool.ts(line 842) and has no external usages. Remove theexportkeyword to keep the module's public API focused and prevent accidental external dependencies.Likely an incorrect or invalid review comment.
| 'no-unused-vars': ['warn', { }], | ||
| '@typescript-eslint/no-unused-vars': ['warn', {}], |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
# First, let's examine the eslint.config.js file around lines 65-66
cat -n eslint.config.js | sed -n '50,80p'Repository: ssdeanx/AgentStack
Length of output: 1444
🏁 Script executed:
# Check git history to see what the previous config looked like
git log --oneline -n 20 eslint.config.jsRepository: ssdeanx/AgentStack
Length of output: 121
🏁 Script executed:
# Search for underscore-prefixed parameters in the codebase
rg -nP '\(_[a-zA-Z]' --type=ts --type=tsx --type=js --type=jsx -g '!node_modules' -g '!.next' | head -50Repository: ssdeanx/AgentStack
Length of output: 89
🏁 Script executed:
# Specific check for the chat-context.tsx file mentioned in the review
cat -n app/chat/providers/chat-context.tsx | sed -n '320,330p'Repository: ssdeanx/AgentStack
Length of output: 393
🏁 Script executed:
# Let's try a different approach to find underscore-prefixed variables
rg '(_[a-zA-Z])' --type=ts --type=js -g '!node_modules' -g '!.next' | grep -E '\(.*_[a-zA-Z]|=.*_[a-zA-Z]' | head -30Repository: ssdeanx/AgentStack
Length of output: 6576
🏁 Script executed:
# Let's also search more directly for function parameters starting with underscore
rg '\([^)]*_[a-zA-Z][a-zA-Z0-9]*[^)]*\)' -g '!node_modules' -g '!.next' | head -40Repository: ssdeanx/AgentStack
Length of output: 48439
🏁 Script executed:
# Check if there's a git diff showing what changed
git diff HEAD~1 eslint.config.js 2>/dev/null || echo "No previous commit available"Repository: ssdeanx/AgentStack
Length of output: 90
🏁 Script executed:
# Get more context about the PR/commit
git show --stat 2>/dev/null | head -30Repository: ssdeanx/AgentStack
Length of output: 1882
🏁 Script executed:
# Search for function parameters starting with underscore more carefully
rg '(\(|,)\s*_[a-zA-Z]' -g '!node_modules' -g '!.next' --context=2 | head -80Repository: ssdeanx/AgentStack
Length of output: 50375
🏁 Script executed:
# Check specifically for any existing underscore usage that would now fail linting
find . -name '*.ts' -o -name '*.tsx' -o -name '*.js' -o -name '*.jsx' | grep -v node_modules | grep -v .next | xargs grep -l '(_[a-zA-Z]' 2>/dev/null | head -20Repository: ssdeanx/AgentStack
Length of output: 751
🏁 Script executed:
# Let's verify the exact change by looking at git diff of eslint.config.js
git diff HEAD~1 eslint.config.js 2>/dev/null || echo "Can't get diff, showing current lines 60-70"
cat eslint.config.js | sed -n '60,70p'Repository: ssdeanx/AgentStack
Length of output: 490
Verify impact of stricter ESLint unused-vars rules causing new lint warnings.
The removal of argsIgnorePattern and varsIgnorePattern from both no-unused-vars rules has already been applied in the current configuration. This change makes the linting rules stricter and will flag unused variables that start with underscores, which developers commonly use to indicate intentionally unused parameters.
The codebase contains at least two existing instances of underscore-prefixed unused parameters that will now trigger warnings:
src/mastra/tools/web-scraper-tool.tsline with(_i, element) => {...}src/mastra/tools/execa-tool.tswithtransform(chunk, _encoding, callback)
Additionally, the unused files parameter in app/chat/providers/chat-context.tsx line 324 will trigger a warning regardless of underscore convention.
🤖 Prompt for AI Agents
In eslint.config.js around lines 65-66, removing
argsIgnorePattern/varsIgnorePattern made unused-vars rules flag
underscore-prefixed parameters and other unused params; restore the original
ignore patterns (e.g., argsIgnorePattern and varsIgnorePattern matching ^_) to
exempt intentionally unused underscore-prefixed variables, and/or fix the
reported sites by either removing the unused parameter, renaming it to a clearly
ignored name (e.g., _unused) or adding a targeted eslint-disable-next-line
comment; specifically address src/mastra/tools/web-scraper-tool.ts (_i
parameter), src/mastra/tools/execa-tool.ts (transform's _encoding), and
app/chat/providers/chat-context.tsx (remove or use the unused files parameter)
so no new warnings remain.
| # TASK001 - Update Log (2025-12-14) | ||
|
|
||
| Summary of changes performed to align tools with the streaming + progress convention: | ||
|
|
||
| - Replaced `data-tool-agent` messages with `data-tool-progress` (standard in-progress/done events) in: | ||
| - `src/mastra/tools/evaluateResultTool.ts` | ||
| - `src/mastra/tools/extractLearningsTool.ts` | ||
| - `src/mastra/tools/editor-agent-tool.ts` | ||
| - `src/mastra/tools/copywriter-agent-tool.ts` | ||
|
|
||
| - Normalized nested-agent streaming pattern in tools to: | ||
| - Prefer `context.mastra.getAgent()` runtime instance if available, otherwise fall back to local agent import | ||
| - Use `agent.stream(prompt)` returning `MastraModelOutput` when available | ||
| - Pipe `textStream` / `fullStream` to `context.writer` | ||
| - Parse `stream.object` or JSON text safely for structured output | ||
|
|
||
| - Updated `src/mastra/tools/financial-chart-tools.ts` to use the same streaming pattern and to validate agent capability (check for `generate` or `stream`). | ||
|
|
||
| - Updated client-side parsers to normalize legacy `data-tool-agent` parts into `data-tool-progress` events: | ||
| - `app/networks/providers/network-context.tsx` | ||
| - `app/workflows/providers/workflow-context.tsx` | ||
|
|
||
| - Updated `src/mastra/tools/AGENTS.md` with a note referencing this task and the progress convention. | ||
|
|
||
| Notes: | ||
| - Tests will be added next to verify that progress events and streaming behavior are emitted consistently. (Pending) | ||
| - If you'd like, I can add/restore unit tests and run the test suite now. |
There was a problem hiding this comment.
🧹 Nitpick | 🔵 Trivial
Missing YAML front matter.
Per coding guidelines, markdown files should include YAML front matter with required metadata fields (post_title, author1, post_slug, etc.). Consider adding front matter if this document is intended for publication or documentation systems.
🤖 Prompt for AI Agents
In memory-bank/tasks/TASK001-update-2025-12-14.md around lines 1 to 27, this
markdown lacks the required YAML front matter; add a top-of-file YAML block
delimited by --- that includes at minimum post_title, author1, post_slug and
date (e.g., date: 2025-12-14) and any other project-required fields (tags,
summary) ensuring keys use valid YAML syntax and values are properly quoted if
needed; place the block before any content so tooling/publishers recognize the
metadata.
| @@ -0,0 +1,27 @@ | |||
| # TASK001 - Update Log (2025-12-14) | |||
There was a problem hiding this comment.
🧹 Nitpick | 🔵 Trivial
Use H2 instead of H1 for the document heading.
Per coding guidelines, H1 headings should not be used as they are generated from the title. Replace # with ##.
-# TASK001 - Update Log (2025-12-14)
+## TASK001 - Update Log (2025-12-14)📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| # TASK001 - Update Log (2025-12-14) | |
| ## TASK001 - Update Log (2025-12-14) |
🤖 Prompt for AI Agents
In memory-bank/tasks/TASK001-update-2025-12-14.md around lines 1 to 1, the
document uses an H1 heading ("# TASK001 - Update (2025-12-14)") but coding
guidelines require H2 headings; change the leading "#" to "##" so the file
starts with "## TASK001 - Update (2025-12-14)" to comply with the guideline that
H1 is reserved for the generated title.
| - Tests will be added next to verify that progress events and streaming behavior are emitted consistently. (Pending) | ||
| - If you'd like, I can add/restore unit tests and run the test suite now. |
There was a problem hiding this comment.
🧹 Nitpick | 🔵 Trivial
Remove conversational tone from documentation.
Line 27 contains conversational language ("If you'd like, I can...") which is inappropriate for task documentation. Consider rephrasing to be more declarative.
-- If you'd like, I can add/restore unit tests and run the test suite now.
+- Unit tests should be added/restored and the test suite run to verify changes.📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| - Tests will be added next to verify that progress events and streaming behavior are emitted consistently. (Pending) | |
| - If you'd like, I can add/restore unit tests and run the test suite now. | |
| - Tests will be added next to verify that progress events and streaming behavior are emitted consistently. (Pending) | |
| - Unit tests should be added/restored and the test suite run to verify changes. |
🤖 Prompt for AI Agents
In memory-bank/tasks/TASK001-update-2025-12-14.md around lines 26-27, replace
the conversational sentence "If you'd like, I can add/restore unit tests and run
the test suite now." with a declarative statement that describes the planned
action (for example, state that unit tests will be added or restored and the
test suite will be run), removing first‑person/offering phrasing and keeping it
concise and factual.
| if (!userId && authHeader !== null && authHeader !== '' && authHeader.startsWith('Bearer ')) { | ||
| const token = authHeader.slice('Bearer '.length) | ||
| const exec = /user:([^;\s]+)/.exec(token) | ||
| if (exec) { userId = exec[1] } | ||
| } | ||
| if (userId !== null && userId !== '') { requestContext.set('userId', userId) } | ||
|
|
||
| // user-tier: prefer explicit header, otherwise derive from token hints | ||
| let userTier = headerUserTier | ||
| if (!userTier && authHeader !== null && authHeader !== '' && authHeader.startsWith('Bearer ')) { | ||
| const token = authHeader.slice('Bearer '.length) | ||
| if (token.includes('enterprise')) { userTier = 'enterprise' } | ||
| else if (token.includes('pro')) { userTier = 'pro' } | ||
| else { userTier = 'free' } | ||
| } | ||
| if (userTier !== null && userTier !== '') { requestContext.set('user-tier', userTier) } |
There was a problem hiding this comment.
🧹 Nitpick | 🔵 Trivial
Simplify redundant null checks.
Since authHeader is defaulted to '' on line 469, the !== null checks are redundant. Similarly, userId and userTier can only be string | undefined, not null.
- if (!userId && authHeader !== null && authHeader !== '' && authHeader.startsWith('Bearer ')) {
+ if (!userId && authHeader.startsWith('Bearer ')) {
const token = authHeader.slice('Bearer '.length)
const exec = /user:([^;\s]+)/.exec(token)
if (exec) { userId = exec[1] }
}
- if (userId !== null && userId !== '') { requestContext.set('userId', userId) }
+ if (userId) { requestContext.set('userId', userId) }
// user-tier: prefer explicit header, otherwise derive from token hints
let userTier = headerUserTier
- if (!userTier && authHeader !== null && authHeader !== '' && authHeader.startsWith('Bearer ')) {
+ if (!userTier && authHeader.startsWith('Bearer ')) {
const token = authHeader.slice('Bearer '.length)
if (token.includes('enterprise')) { userTier = 'enterprise' }
else if (token.includes('pro')) { userTier = 'pro' }
else { userTier = 'free' }
}
- if (userTier !== null && userTier !== '') { requestContext.set('user-tier', userTier) }
+ if (userTier) { requestContext.set('user-tier', userTier) }🤖 Prompt for AI Agents
In src/mastra/index.ts around lines 483 to 498, remove redundant `!== null`
checks and simplify truthiness checks: since `authHeader` is defaulted to '' and
`userId`/`userTier` are `string | undefined`, use concise conditions like `if
(!userId && authHeader.startsWith('Bearer '))` and `if (!userTier &&
authHeader.startsWith('Bearer '))`, and when setting the context use `if
(userId)` / `if (userTier)` or `if (userId !== '')` to avoid null checks; ensure
behavior is unchanged while eliminating unnecessary null comparisons.
|
|
||
| if (stream) { | ||
| const text = (await stream.text) ?? ''; | ||
| try { responseObject = stream.object ?? (text ? JSON.parse(text) : {}) } catch { responseObject = {} } |
There was a problem hiding this comment.
🧹 Nitpick | 🔵 Trivial
Complex one-liner JSON parsing is hard to maintain.
The nested try/catch with ternary in one line reduces readability:
- try { responseObject = stream.object ?? (text ? JSON.parse(text) : {}) } catch { responseObject = {} }
+ try {
+ responseObject = stream.object ?? (text ? JSON.parse(text) : {});
+ } catch {
+ responseObject = {};
+ }🤖 Prompt for AI Agents
In src/mastra/tools/extractLearningsTool.ts around line 85, the complex one-line
that attempts to set responseObject with a nested ternary and try/catch is hard
to read and swallows errors; refactor into a few clear statements: first compute
a fallback (e.g., const raw = stream.object ?? text), then if raw is a string
attempt JSON.parse inside a try/catch that only handles parsing and sets
responseObject = parsed or {} on failure, otherwise assign responseObject = raw,
and optionally log parse errors instead of silently ignoring them.
| const learningLength = parsed.data.learning.length ?? 0; | ||
| const followUpQuestionsCount = parsed.data.followUpQuestions?.length ?? 0; |
There was a problem hiding this comment.
🧹 Nitpick | 🔵 Trivial
Unnecessary nullish coalescing on string .length.
parsed.data.learning.length is always a number (string always has length property). The ?? 0 is redundant:
- const learningLength = parsed.data.learning.length ?? 0;
- const followUpQuestionsCount = parsed.data.followUpQuestions?.length ?? 0;
+ const learningLength = parsed.data.learning.length;
+ const followUpQuestionsCount = parsed.data.followUpQuestions.length;Note: followUpQuestions is defined as z.array(z.string()) in the schema, so after successful parse it's guaranteed to be an array with a .length property.
📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| const learningLength = parsed.data.learning.length ?? 0; | |
| const followUpQuestionsCount = parsed.data.followUpQuestions?.length ?? 0; | |
| const learningLength = parsed.data.learning.length; | |
| const followUpQuestionsCount = parsed.data.followUpQuestions.length; |
🤖 Prompt for AI Agents
In src/mastra/tools/extractLearningsTool.ts around lines 129-130, remove the
unnecessary nullish coalescing on .length: parsed.data.learning.length and
parsed.data.followUpQuestions.length are guaranteed numbers after schema
validation, so delete the "?? 0" fallbacks and use the .length values directly;
adjust any related variable typings if needed to reflect they will always be
numbers.
| if (typeof agent.stream === 'function') { | ||
| const stream = await agent.stream(prompt) as MastraModelOutput | undefined | ||
| if (stream?.fullStream) { | ||
| await stream.fullStream.pipeTo(writer as unknown as WritableStream) | ||
| } else if (stream.textStream) { | ||
| } else if (stream?.textStream) { | ||
| await stream.textStream.pipeTo(writer as unknown as WritableStream) | ||
| } | ||
| resultText = (await stream.text) ?? '' | ||
| const text = stream?.text ? await stream.text : undefined | ||
| resultText = text ?? '' | ||
| } else { | ||
| const result = await agentWithStream.generate(prompt) | ||
| const result = await agent.generate(prompt) | ||
| resultText = result.text | ||
| } |
There was a problem hiding this comment.
🛠️ Refactor suggestion | 🟠 Major
Consider extracting duplicated streaming logic into a helper function.
The streaming pattern (check for stream function, call agent.stream(), pipe fullStream or textStream, extract text) is repeated across all four chart tools. This violates DRY principles and increases maintenance burden.
// Suggested helper in a shared utility file
async function executeAgentWithStreaming(
agent: { stream?: Function; generate: Function },
prompt: string,
writer?: unknown
): Promise<string> {
if (typeof agent.stream === 'function') {
const stream = await agent.stream(prompt) as MastraModelOutput | undefined;
if (stream?.fullStream && writer) {
await stream.fullStream.pipeTo(writer as unknown as WritableStream);
} else if (stream?.textStream && writer) {
await stream.textStream.pipeTo(writer as unknown as WritableStream);
}
return stream?.text ? await stream.text : '';
}
const result = await agent.generate(prompt);
return result.text;
}🤖 Prompt for AI Agents
In src/mastra/tools/financial-chart-tools.ts around lines 140 to 152, the
streaming and fallback logic for calling agent.stream() or agent.generate() is
duplicated; extract that block into a shared helper function (e.g., in a
utilities module) that accepts the agent, prompt, and optional writer, performs
the typeof agent.stream check, awaits agent.stream(prompt) when available, pipes
fullStream or textStream to the writer when present, awaits and returns
stream.text (or ''), and otherwise calls agent.generate(prompt) and returns
result.text; replace the repeated blocks in all four chart tools with calls to
this helper.
| if (stream?.fullStream) { | ||
| await stream.fullStream.pipeTo(writer as unknown as WritableStream) |
There was a problem hiding this comment.
Same unsafe WritableStream cast as in editor-agent-tool.
This cast pattern writer as unknown as WritableStream is repeated across all chart tools. If the writer is not a valid WritableStream, this will fail at runtime. See earlier comment on editor-agent-tool for suggested fix.
🤖 Prompt for AI Agents
In src/mastra/tools/financial-chart-tools.ts around lines 142-143 the code
unsafely casts writer as unknown as WritableStream before calling
stream.fullStream.pipeTo(writer), which can throw at runtime if writer is not a
web WritableStream; replace the blind cast with a safe conversion/guard: detect
the writer type at runtime (e.g., if it already implements WritableStream-like
pipeTo/abort/closed methods, or if it's a Node.js Writable stream) and either
convert Node writable to a web WritableStream (or wrap the web stream around
Node writer) or call an appropriate pipe method for that writer; factor this
logic into a small helper (e.g., ensureWritableStream(writer): WritableStream)
and use it here so pipeTo is only invoked on a verified WritableStream, and
throw a clear error if conversion is not possible.
| const text = stream?.text ? await stream.text : undefined | ||
| resultText = text ?? '' |
There was a problem hiding this comment.
🧹 Nitpick | 🔵 Trivial
Potential issue with conditional await on stream.text.
The pattern stream?.text ? await stream.text : undefined is correct if stream.text is a Promise. However, if stream.text is already resolved (synchronous), the conditional check stream?.text would be truthy and await would work fine. The pattern is safe but could be simplified:
- const text = stream?.text ? await stream.text : undefined
- resultText = text ?? ''
+ resultText = (await stream?.text) ?? ''📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| const text = stream?.text ? await stream.text : undefined | |
| resultText = text ?? '' | |
| resultText = (await stream?.text) ?? '' |
🤖 Prompt for AI Agents
In src/mastra/tools/financial-chart-tools.ts around lines 147-148, simplify the
conditional await: replace the two-line pattern that reads stream?.text ? await
stream.text : undefined and then sets resultText to text ?? '' with a single
expression that awaits stream.text if present and defaults to empty string (use
parentheses so await applies to the optional property), then assign that value
to resultText.
There was a problem hiding this comment.
Pull request overview
This pull request removes test files and implements streaming improvements across multiple tools, focusing on standardizing progress events and nested agent streaming patterns. The changes update 11 test files, several tool implementations, agent configurations, and related infrastructure.
- Test file cleanup: Deletion of 11 test files across various tool suites
- Tool streaming pattern standardization: Adoption of
MastraModelOutputanddata-tool-progressevents - Agent improvements: Addition of new agents and runtime context enhancements
Reviewed changes
Copilot reviewed 33 out of 34 changed files in this pull request and generated 5 comments.
Show a summary per file
| File | Description |
|---|---|
| src/mastra/tools/tests/*.test.ts | Multiple test files deleted, removing test coverage |
| src/mastra/tools/financial-chart-tools.ts | Standardized agent streaming pattern with fallback logic |
| src/mastra/tools/extractLearningsTool.ts | Improved error handling and streaming with safe parsing |
| src/mastra/tools/evaluateResultTool.ts | Added streaming support and consistent progress events |
| src/mastra/tools/editor-agent-tool.ts | Implemented nested agent streaming with writer piping |
| src/mastra/tools/document-chunking.tool.ts | Enhanced chunking with metadata sanitization and batch embedding |
| src/mastra/tools/copywriter-agent-tool.ts | Standardized streaming pattern and progress events |
| src/mastra/tools/color-change-tool.ts | New tool for background color changes |
| src/mastra/tools/AGENTS.md | Documentation updates for progress event format |
| src/mastra/index.ts | Added new agents and comprehensive middleware |
| src/mastra/agents/researchAgent.ts | Added runtime context fields for userId and researchPhase |
| eslint.config.js | Removed pattern matching from unused vars rule |
| app/workflows/providers/workflow-context.tsx | Normalized legacy events into progress events |
| app/networks/providers/network-context.tsx | Improved event parsing with type safety |
| app/chat/providers/chat-context.tsx | Fixed unused parameter warning |
| memory-bank/* | Added task tracking documentation |
Comments suppressed due to low confidence (2)
src/mastra/tools/tests/web-scraper-tool.test.ts:1
- This test file for web-scraper-tool has been removed. Given that other similar tool files have comprehensive test coverage, this removal significantly reduces test coverage for the web scraping functionality, which includes critical components like HtmlProcessor, ValidationUtils, and multiple scraping tools (webScraperTool, batchWebScraperTool, etc.).
src/mastra/tools/tests/weather-tool.test.ts:1 - Removal of weather-tool tests eliminates coverage for temperature unit handling, location resolution, API error handling, and tracing context. This tool handles external API calls and various edge cases that should be tested.
| await writer?.custom({ type: 'data-tool-progress', data: { status: 'in-progress', message: '🤖 Generating insights with learning agent', stage: 'extract-learnings' }, id: 'extract-learnings' }); | ||
|
|
||
| const truncatedContent = (result?.content ?? '').slice(0, 8000); | ||
| const contentWithTruncation = (result?.content ?? '').length > 8000 ? truncatedContent + 'AAAA...' : truncatedContent; |
There was a problem hiding this comment.
The truncation marker 'AAAA...' appears to be a debug placeholder instead of a meaningful ellipsis. This should be changed to a standard ellipsis '...' or a more descriptive truncation indicator.
| const contentWithTruncation = (result?.content ?? '').length > 8000 ? truncatedContent + 'AAAA...' : truncatedContent; | |
| const contentWithTruncation = (result?.content ?? '').length > 8000 ? truncatedContent + '...' : truncatedContent; |
| chunkOverlap: inputData.chunkOverlap, | ||
| }, | ||
| id: `chunk_${Date.now()}_${index}`, | ||
| id: chunk.metadata?.id ?? `chunk_${Date.now()}_${randomUUID()}`, |
There was a problem hiding this comment.
Using Date.now() in the ID generation for every chunk may create collisions if multiple chunks are processed in the same millisecond. Consider using only randomUUID() or a sequential counter combined with a session UUID for better uniqueness guarantees.
| id: chunk.metadata?.id ?? `chunk_${Date.now()}_${randomUUID()}`, | |
| id: chunk.metadata?.id ?? `chunk_${index}_${randomUUID()}`, |
|
|
||
| // userId: prefer explicit header, otherwise try to parse from a bearer token (format: "Bearer user:<id>") | ||
| let userId = headerUserId | ||
| if (!userId && authHeader !== null && authHeader !== '' && authHeader.startsWith('Bearer ')) { |
There was a problem hiding this comment.
The condition checks for both !== null and !== '' separately before calling startsWith(). Since empty string is falsy, these conditions can be simplified to if (!userId && authHeader && authHeader.startsWith('Bearer ')) for better readability.
| 'no-unused-vars': ['warn', { }], | ||
| '@typescript-eslint/no-unused-vars': ['warn', {}], |
There was a problem hiding this comment.
Removing the argsIgnorePattern and varsIgnorePattern options means variables/parameters prefixed with underscore will now trigger warnings. This breaks a common convention for explicitly unused variables. Consider restoring these patterns to allow intentional unused parameters marked with underscore.
| 'no-unused-vars': ['warn', { }], | |
| '@typescript-eslint/no-unused-vars': ['warn', {}], | |
| 'no-unused-vars': [ | |
| 'warn', | |
| { | |
| argsIgnorePattern: '^_', | |
| varsIgnorePattern: '^_', | |
| }, | |
| ], | |
| '@typescript-eslint/no-unused-vars': [ | |
| 'warn', | |
| { | |
| argsIgnorePattern: '^_', | |
| varsIgnorePattern: '^_', | |
| }, | |
| ], |
|
|
||
| const sendMessage = useCallback( | ||
| (text: string, _files?: File[]) => { | ||
| (text: string, files?: File[]) => { |
There was a problem hiding this comment.
The files parameter was renamed from _files (explicitly unused) to files, but it's still not used in the function body. This will now trigger an unused variable warning. Either use the parameter or revert to _files to indicate intentional non-use.
1 participant
No description provided.