Conversation
|
Caution Review failedThe pull request is closed. WalkthroughThis change refactors multiple AI utility modules to replace calls to Changes
Sequence Diagram(s)sequenceDiagram
participant Caller
participant ModelConfig (getModel)
participant AI (generateObject)
participant UsageTracker (saveAiUsage)
Caller->>ModelConfig: getModel(user, options)
ModelConfig-->>Caller: {provider, model, llmModel, providerOptions}
Caller->>AI: generateObject(model, prompts, schema, providerOptions)
AI-->>Caller: {result, usage?}
alt usage present
Caller->>UsageTracker: saveAiUsage(email, usage, provider, model, label)
end
Caller-->>Caller: process result
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~18 minutes Possibly related PRs
Poem
📜 Recent review detailsConfiguration used: .coderabbit.yaml 📒 Files selected for processing (1)
✨ Finishing Touches
🧪 Generate unit tests
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. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
Documentation and Community
|
|
Claude finished @elie222's task —— View job PR Review: AI Model Integration MigrationI've completed a comprehensive review of this PR which migrates AI utility functions from a custom Todo List:
📋 SummaryThis PR implements a migration from a custom LLM wrapper (
|
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (4)
apps/web/utils/ai/categorize-sender/ai-categorize-single-sender.ts (1)
62-69: Consider removing commented code after refactor validation.The commented
chatCompletionObjectcall should be removed once the new implementation is validated to keep the codebase clean.apps/web/utils/cold-email/is-cold-email.ts (1)
208-219: Consider removing commented code for cleaner maintenance.The commented
chatCompletionObjectimplementation should be removed after validating the new approach to avoid code bloat.apps/web/utils/ai/choose-rule/ai-choose-rule.ts (1)
84-112: Remove extensive commented code block for cleaner maintenance.This large commented code block should be removed after the refactor is validated. The extensive commented implementation details significantly increase file size without providing value.
apps/web/utils/ai/knowledge/extract-from-email-history.ts (1)
102-110: Consider removing commented code after validation.The commented
chatCompletionObjectimplementation should be removed once the new approach is validated to maintain code cleanliness.
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (14)
apps/web/utils/ai/categorize-sender/ai-categorize-senders.ts(2 hunks)apps/web/utils/ai/categorize-sender/ai-categorize-single-sender.ts(2 hunks)apps/web/utils/ai/choose-rule/ai-choose-rule.ts(2 hunks)apps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.ts(2 hunks)apps/web/utils/ai/choose-rule/choose-args.ts(1 hunks)apps/web/utils/ai/clean/ai-clean-select-labels.ts(2 hunks)apps/web/utils/ai/digest/summarize-email-for-digest.ts(2 hunks)apps/web/utils/ai/knowledge/extract-from-email-history.ts(2 hunks)apps/web/utils/ai/knowledge/extract.ts(2 hunks)apps/web/utils/ai/reply/draft-with-knowledge.ts(2 hunks)apps/web/utils/ai/rule/generate-prompt-on-delete-rule.ts(2 hunks)apps/web/utils/ai/rule/generate-prompt-on-update-rule.ts(2 hunks)apps/web/utils/cold-email/is-cold-email.ts(2 hunks)version.txt(1 hunks)
🧰 Additional context used
📓 Path-based instructions (10)
!{.cursor/rules/*.mdc}
📄 CodeRabbit Inference Engine (.cursor/rules/cursor-rules.mdc)
Never place rule files in the project root, in subdirectories outside .cursor/rules, or in any other location
Files:
version.txtapps/web/utils/ai/digest/summarize-email-for-digest.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.tsapps/web/utils/ai/knowledge/extract.tsapps/web/utils/ai/knowledge/extract-from-email-history.tsapps/web/utils/ai/categorize-sender/ai-categorize-single-sender.tsapps/web/utils/ai/rule/generate-prompt-on-delete-rule.tsapps/web/utils/ai/reply/draft-with-knowledge.tsapps/web/utils/ai/rule/generate-prompt-on-update-rule.tsapps/web/utils/cold-email/is-cold-email.tsapps/web/utils/ai/choose-rule/choose-args.tsapps/web/utils/ai/categorize-sender/ai-categorize-senders.tsapps/web/utils/ai/choose-rule/ai-choose-rule.ts
!pages/_document.{js,jsx,ts,tsx}
📄 CodeRabbit Inference Engine (.cursor/rules/ultracite.mdc)
!pages/_document.{js,jsx,ts,tsx}: Don't import next/document outside of pages/_document.jsx in Next.js projects.
Don't import next/document outside of pages/_document.jsx in Next.js projects.
Files:
version.txtapps/web/utils/ai/digest/summarize-email-for-digest.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.tsapps/web/utils/ai/knowledge/extract.tsapps/web/utils/ai/knowledge/extract-from-email-history.tsapps/web/utils/ai/categorize-sender/ai-categorize-single-sender.tsapps/web/utils/ai/rule/generate-prompt-on-delete-rule.tsapps/web/utils/ai/reply/draft-with-knowledge.tsapps/web/utils/ai/rule/generate-prompt-on-update-rule.tsapps/web/utils/cold-email/is-cold-email.tsapps/web/utils/ai/choose-rule/choose-args.tsapps/web/utils/ai/categorize-sender/ai-categorize-senders.tsapps/web/utils/ai/choose-rule/ai-choose-rule.ts
apps/web/**/*.{ts,tsx}
📄 CodeRabbit Inference Engine (apps/web/CLAUDE.md)
apps/web/**/*.{ts,tsx}: Use TypeScript with strict null checks
Path aliases: Use@/for imports from project root
Use proper error handling with try/catch blocks
Format code with Prettier
Leverage TypeScript inference for better DX
Files:
apps/web/utils/ai/digest/summarize-email-for-digest.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.tsapps/web/utils/ai/knowledge/extract.tsapps/web/utils/ai/knowledge/extract-from-email-history.tsapps/web/utils/ai/categorize-sender/ai-categorize-single-sender.tsapps/web/utils/ai/rule/generate-prompt-on-delete-rule.tsapps/web/utils/ai/reply/draft-with-knowledge.tsapps/web/utils/ai/rule/generate-prompt-on-update-rule.tsapps/web/utils/cold-email/is-cold-email.tsapps/web/utils/ai/choose-rule/choose-args.tsapps/web/utils/ai/categorize-sender/ai-categorize-senders.tsapps/web/utils/ai/choose-rule/ai-choose-rule.ts
**/*.ts
📄 CodeRabbit Inference Engine (.cursor/rules/form-handling.mdc)
**/*.ts: The same validation should be done in the server action too
Define validation schemas using Zod
Files:
apps/web/utils/ai/digest/summarize-email-for-digest.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.tsapps/web/utils/ai/knowledge/extract.tsapps/web/utils/ai/knowledge/extract-from-email-history.tsapps/web/utils/ai/categorize-sender/ai-categorize-single-sender.tsapps/web/utils/ai/rule/generate-prompt-on-delete-rule.tsapps/web/utils/ai/reply/draft-with-knowledge.tsapps/web/utils/ai/rule/generate-prompt-on-update-rule.tsapps/web/utils/cold-email/is-cold-email.tsapps/web/utils/ai/choose-rule/choose-args.tsapps/web/utils/ai/categorize-sender/ai-categorize-senders.tsapps/web/utils/ai/choose-rule/ai-choose-rule.ts
apps/web/utils/{ai,llms}/**/*
📄 CodeRabbit Inference Engine (.cursor/rules/llm.mdc)
apps/web/utils/{ai,llms}/**/*: LLM-related code must be organized in the directories: apps/web/utils/ai/, apps/web/utils/llms/, and apps/web/tests/ for LLM-specific tests.
Keep related AI functions in the same file or directory.
Files:
apps/web/utils/ai/digest/summarize-email-for-digest.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.tsapps/web/utils/ai/knowledge/extract.tsapps/web/utils/ai/knowledge/extract-from-email-history.tsapps/web/utils/ai/categorize-sender/ai-categorize-single-sender.tsapps/web/utils/ai/rule/generate-prompt-on-delete-rule.tsapps/web/utils/ai/reply/draft-with-knowledge.tsapps/web/utils/ai/rule/generate-prompt-on-update-rule.tsapps/web/utils/ai/choose-rule/choose-args.tsapps/web/utils/ai/categorize-sender/ai-categorize-senders.tsapps/web/utils/ai/choose-rule/ai-choose-rule.ts
apps/web/utils/{ai,llms}/**/*.ts
📄 CodeRabbit Inference Engine (.cursor/rules/llm.mdc)
apps/web/utils/{ai,llms}/**/*.ts: Follow the standard structure for LLM-related functions: use a scoped logger, define a Zod schema for output, validate inputs early, separate system and user prompts, log inputs and outputs, call chatCompletionObject with proper configuration, and return validated results.
Keep system prompts and user prompts separate in LLM-related code.
System prompt should define the LLM's role and task specifications.
User prompt should contain the actual data and context.
Always define a Zod schema for response validation in LLM-related functions.
Make Zod schemas as specific as possible to guide the LLM output.
Use descriptive scoped loggers for each LLM feature.
Log inputs and outputs with appropriate log levels in LLM-related functions.
Include relevant context in log messages for LLM-related code.
Implement early returns for invalid inputs in LLM-related functions.
Use proper error types and logging in LLM-related code.
Implement fallbacks for AI failures in LLM-related functions.
Add retry logic for transient failures using withRetry in LLM-related code.
Use XML-like tags to structure data in LLM prompts.
Remove excessive whitespace and truncate long inputs in LLM prompts.
Format data consistently across similar LLM-related functions.
Use TypeScript types for all parameters and return values in LLM-related code.
Define clear interfaces for complex input/output structures in LLM-related code.
Extract common patterns into utility functions in LLM-related code.
Document complex AI logic with clear comments in LLM-related code.
Files:
apps/web/utils/ai/digest/summarize-email-for-digest.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.tsapps/web/utils/ai/knowledge/extract.tsapps/web/utils/ai/knowledge/extract-from-email-history.tsapps/web/utils/ai/categorize-sender/ai-categorize-single-sender.tsapps/web/utils/ai/rule/generate-prompt-on-delete-rule.tsapps/web/utils/ai/reply/draft-with-knowledge.tsapps/web/utils/ai/rule/generate-prompt-on-update-rule.tsapps/web/utils/ai/choose-rule/choose-args.tsapps/web/utils/ai/categorize-sender/ai-categorize-senders.tsapps/web/utils/ai/choose-rule/ai-choose-rule.ts
**/*.{ts,tsx}
📄 CodeRabbit Inference Engine (.cursor/rules/logging.mdc)
**/*.{ts,tsx}: UsecreateScopedLoggerfor logging in backend TypeScript files
Typically add the logger initialization at the top of the file when usingcreateScopedLogger
Only use.with()on a logger instance within a specific function, not for a global loggerImport Prisma in the project using
import prisma from "@/utils/prisma";
**/*.{ts,tsx}: Don't use TypeScript enums.
Don't use TypeScript const enum.
Don't use the TypeScript directive @ts-ignore.
Don't use primitive type aliases or misleading types.
Don't use empty type parameters in type aliases and interfaces.
Don't use any or unknown as type constraints.
Don't use implicit any type on variable declarations.
Don't let variables evolve into any type through reassignments.
Don't use non-null assertions with the ! postfix operator.
Don't misuse the non-null assertion operator (!) in TypeScript files.
Don't use user-defined types.
Use as const instead of literal types and type annotations.
Use export type for types.
Use import type for types.
Don't declare empty interfaces.
Don't merge interfaces and classes unsafely.
Don't use overload signatures that aren't next to each other.
Use the namespace keyword instead of the module keyword to declare TypeScript namespaces.
Don't use TypeScript namespaces.
Don't export imported variables.
Don't add type annotations to variables, parameters, and class properties that are initialized with literal expressions.
Don't use parameter properties in class constructors.
Use either T[] or Array consistently.
Initialize each enum member value explicitly.
Make sure all enum members are literal values.
Files:
apps/web/utils/ai/digest/summarize-email-for-digest.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.tsapps/web/utils/ai/knowledge/extract.tsapps/web/utils/ai/knowledge/extract-from-email-history.tsapps/web/utils/ai/categorize-sender/ai-categorize-single-sender.tsapps/web/utils/ai/rule/generate-prompt-on-delete-rule.tsapps/web/utils/ai/reply/draft-with-knowledge.tsapps/web/utils/ai/rule/generate-prompt-on-update-rule.tsapps/web/utils/cold-email/is-cold-email.tsapps/web/utils/ai/choose-rule/choose-args.tsapps/web/utils/ai/categorize-sender/ai-categorize-senders.tsapps/web/utils/ai/choose-rule/ai-choose-rule.ts
apps/web/utils/**
📄 CodeRabbit Inference Engine (.cursor/rules/project-structure.mdc)
Create utility functions in
utils/folder for reusable logic
Files:
apps/web/utils/ai/digest/summarize-email-for-digest.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.tsapps/web/utils/ai/knowledge/extract.tsapps/web/utils/ai/knowledge/extract-from-email-history.tsapps/web/utils/ai/categorize-sender/ai-categorize-single-sender.tsapps/web/utils/ai/rule/generate-prompt-on-delete-rule.tsapps/web/utils/ai/reply/draft-with-knowledge.tsapps/web/utils/ai/rule/generate-prompt-on-update-rule.tsapps/web/utils/cold-email/is-cold-email.tsapps/web/utils/ai/choose-rule/choose-args.tsapps/web/utils/ai/categorize-sender/ai-categorize-senders.tsapps/web/utils/ai/choose-rule/ai-choose-rule.ts
apps/web/utils/**/*.ts
📄 CodeRabbit Inference Engine (.cursor/rules/project-structure.mdc)
apps/web/utils/**/*.ts: Use lodash utilities for common operations (arrays, objects, strings)
Import specific lodash functions to minimize bundle size
Files:
apps/web/utils/ai/digest/summarize-email-for-digest.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.tsapps/web/utils/ai/knowledge/extract.tsapps/web/utils/ai/knowledge/extract-from-email-history.tsapps/web/utils/ai/categorize-sender/ai-categorize-single-sender.tsapps/web/utils/ai/rule/generate-prompt-on-delete-rule.tsapps/web/utils/ai/reply/draft-with-knowledge.tsapps/web/utils/ai/rule/generate-prompt-on-update-rule.tsapps/web/utils/cold-email/is-cold-email.tsapps/web/utils/ai/choose-rule/choose-args.tsapps/web/utils/ai/categorize-sender/ai-categorize-senders.tsapps/web/utils/ai/choose-rule/ai-choose-rule.ts
**/*.{js,jsx,ts,tsx}
📄 CodeRabbit Inference Engine (.cursor/rules/ultracite.mdc)
**/*.{js,jsx,ts,tsx}: Don't useelements in Next.js projects.
Don't use elements in Next.js projects.
Don't use namespace imports.
Don't access namespace imports dynamically.
Don't use global eval().
Don't use console.
Don't use debugger.
Don't use var.
Don't use with statements in non-strict contexts.
Don't use the arguments object.
Don't use consecutive spaces in regular expression literals.
Don't use the comma operator.
Don't use unnecessary boolean casts.
Don't use unnecessary callbacks with flatMap.
Use for...of statements instead of Array.forEach.
Don't create classes that only have static members (like a static namespace).
Don't use this and super in static contexts.
Don't use unnecessary catch clauses.
Don't use unnecessary constructors.
Don't use unnecessary continue statements.
Don't export empty modules that don't change anything.
Don't use unnecessary escape sequences in regular expression literals.
Don't use unnecessary labels.
Don't use unnecessary nested block statements.
Don't rename imports, exports, and destructured assignments to the same name.
Don't use unnecessary string or template literal concatenation.
Don't use String.raw in template literals when there are no escape sequences.
Don't use useless case statements in switch statements.
Don't use ternary operators when simpler alternatives exist.
Don't use useless this aliasing.
Don't initialize variables to undefined.
Don't use the void operators (they're not familiar).
Use arrow functions instead of function expressions.
Use Date.now() to get milliseconds since the Unix Epoch.
Use .flatMap() instead of map().flat() when possible.
Use literal property access instead of computed property access.
Don't use parseInt() or Number.parseInt() when binary, octal, or hexadecimal literals work.
Use concise optional chaining instead of chained logical expressions.
Use regular expression literals instead of the RegExp constructor when possible.
Don't use number literal object member names th...
Files:
apps/web/utils/ai/digest/summarize-email-for-digest.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.tsapps/web/utils/ai/knowledge/extract.tsapps/web/utils/ai/knowledge/extract-from-email-history.tsapps/web/utils/ai/categorize-sender/ai-categorize-single-sender.tsapps/web/utils/ai/rule/generate-prompt-on-delete-rule.tsapps/web/utils/ai/reply/draft-with-knowledge.tsapps/web/utils/ai/rule/generate-prompt-on-update-rule.tsapps/web/utils/cold-email/is-cold-email.tsapps/web/utils/ai/choose-rule/choose-args.tsapps/web/utils/ai/categorize-sender/ai-categorize-senders.tsapps/web/utils/ai/choose-rule/ai-choose-rule.ts
🧠 Learnings (33)
📓 Common learnings
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Follow the standard structure for LLM-related functions: use a scoped logger, define a Zod schema for output, validate inputs early, separate system and user prompts, log inputs and outputs, call chatCompletionObject with proper configuration, and return validated results.
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Implement fallbacks for AI failures in LLM-related functions.
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/* : Keep related AI functions in the same file or directory.
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Document complex AI logic with clear comments in LLM-related code.
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Extract common patterns into utility functions in LLM-related code.
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Define clear interfaces for complex input/output structures in LLM-related code.
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Format data consistently across similar LLM-related functions.
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Make Zod schemas as specific as possible to guide the LLM output.
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Use TypeScript types for all parameters and return values in LLM-related code.
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : implement fallbacks for ai failures in llm-related fun...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Implement fallbacks for AI failures in LLM-related functions.
Applied to files:
apps/web/utils/ai/digest/summarize-email-for-digest.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.tsapps/web/utils/ai/knowledge/extract.tsapps/web/utils/ai/knowledge/extract-from-email-history.tsapps/web/utils/ai/categorize-sender/ai-categorize-single-sender.tsapps/web/utils/ai/rule/generate-prompt-on-delete-rule.tsapps/web/utils/ai/reply/draft-with-knowledge.tsapps/web/utils/ai/rule/generate-prompt-on-update-rule.tsapps/web/utils/cold-email/is-cold-email.tsapps/web/utils/ai/choose-rule/choose-args.tsapps/web/utils/ai/categorize-sender/ai-categorize-senders.tsapps/web/utils/ai/choose-rule/ai-choose-rule.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : document complex ai logic with clear comments in llm-r...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Document complex AI logic with clear comments in LLM-related code.
Applied to files:
apps/web/utils/ai/digest/summarize-email-for-digest.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.tsapps/web/utils/ai/knowledge/extract.tsapps/web/utils/ai/knowledge/extract-from-email-history.tsapps/web/utils/ai/categorize-sender/ai-categorize-single-sender.tsapps/web/utils/ai/rule/generate-prompt-on-delete-rule.tsapps/web/utils/ai/reply/draft-with-knowledge.tsapps/web/utils/ai/rule/generate-prompt-on-update-rule.tsapps/web/utils/cold-email/is-cold-email.tsapps/web/utils/ai/choose-rule/choose-args.tsapps/web/utils/ai/categorize-sender/ai-categorize-senders.tsapps/web/utils/ai/choose-rule/ai-choose-rule.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : follow the standard structure for llm-related function...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Follow the standard structure for LLM-related functions: use a scoped logger, define a Zod schema for output, validate inputs early, separate system and user prompts, log inputs and outputs, call chatCompletionObject with proper configuration, and return validated results.
Applied to files:
apps/web/utils/ai/digest/summarize-email-for-digest.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.tsapps/web/utils/ai/knowledge/extract.tsapps/web/utils/ai/knowledge/extract-from-email-history.tsapps/web/utils/ai/categorize-sender/ai-categorize-single-sender.tsapps/web/utils/ai/rule/generate-prompt-on-delete-rule.tsapps/web/utils/ai/reply/draft-with-knowledge.tsapps/web/utils/ai/rule/generate-prompt-on-update-rule.tsapps/web/utils/cold-email/is-cold-email.tsapps/web/utils/ai/categorize-sender/ai-categorize-senders.tsapps/web/utils/ai/choose-rule/ai-choose-rule.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : include relevant context in log messages for llm-relat...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Include relevant context in log messages for LLM-related code.
Applied to files:
apps/web/utils/ai/digest/summarize-email-for-digest.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/knowledge/extract.tsapps/web/utils/ai/knowledge/extract-from-email-history.tsapps/web/utils/ai/categorize-sender/ai-categorize-single-sender.tsapps/web/utils/ai/reply/draft-with-knowledge.tsapps/web/utils/cold-email/is-cold-email.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : format data consistently across similar llm-related fu...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Format data consistently across similar LLM-related functions.
Applied to files:
apps/web/utils/ai/digest/summarize-email-for-digest.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.tsapps/web/utils/ai/knowledge/extract.tsapps/web/utils/ai/knowledge/extract-from-email-history.tsapps/web/utils/ai/categorize-sender/ai-categorize-single-sender.tsapps/web/utils/ai/reply/draft-with-knowledge.tsapps/web/utils/ai/rule/generate-prompt-on-update-rule.tsapps/web/utils/cold-email/is-cold-email.tsapps/web/utils/ai/choose-rule/choose-args.tsapps/web/utils/ai/categorize-sender/ai-categorize-senders.tsapps/web/utils/ai/choose-rule/ai-choose-rule.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : extract common patterns into utility functions in llm-...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Extract common patterns into utility functions in LLM-related code.
Applied to files:
apps/web/utils/ai/digest/summarize-email-for-digest.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.tsapps/web/utils/ai/knowledge/extract.tsapps/web/utils/ai/knowledge/extract-from-email-history.tsapps/web/utils/ai/categorize-sender/ai-categorize-single-sender.tsapps/web/utils/ai/reply/draft-with-knowledge.tsapps/web/utils/cold-email/is-cold-email.tsapps/web/utils/ai/categorize-sender/ai-categorize-senders.tsapps/web/utils/ai/choose-rule/ai-choose-rule.ts
📚 Learning: in packages/resend/emails/digest.tsx, the digestemailprops type uses `[key: string]: digestitem[] | ...
Learnt from: edulelis
PR: elie222/inbox-zero#576
File: packages/resend/emails/digest.tsx:78-83
Timestamp: 2025-07-17T04:19:57.099Z
Learning: In packages/resend/emails/digest.tsx, the DigestEmailProps type uses `[key: string]: DigestItem[] | undefined | string | Date | undefined` instead of intersection types like `& Record<string, DigestItem[] | undefined>` due to implementation constraints. This was the initial implementation approach and cannot be changed to more restrictive typing.
Applied to files:
apps/web/utils/ai/digest/summarize-email-for-digest.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : define clear interfaces for complex input/output struc...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Define clear interfaces for complex input/output structures in LLM-related code.
Applied to files:
apps/web/utils/ai/digest/summarize-email-for-digest.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.tsapps/web/utils/ai/knowledge/extract.tsapps/web/utils/ai/knowledge/extract-from-email-history.tsapps/web/utils/ai/categorize-sender/ai-categorize-single-sender.tsapps/web/utils/ai/rule/generate-prompt-on-delete-rule.tsapps/web/utils/ai/reply/draft-with-knowledge.tsapps/web/utils/ai/rule/generate-prompt-on-update-rule.tsapps/web/utils/cold-email/is-cold-email.tsapps/web/utils/ai/categorize-sender/ai-categorize-senders.tsapps/web/utils/ai/choose-rule/ai-choose-rule.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : remove excessive whitespace and truncate long inputs i...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Remove excessive whitespace and truncate long inputs in LLM prompts.
Applied to files:
apps/web/utils/ai/digest/summarize-email-for-digest.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/rule/generate-prompt-on-delete-rule.tsapps/web/utils/ai/rule/generate-prompt-on-update-rule.ts
📚 Learning: applies to apps/web/__tests__/**/*.test.ts : test both ai and non-ai paths in llm-related tests...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm-test.mdc:0-0
Timestamp: 2025-07-18T15:06:10.570Z
Learning: Applies to apps/web/__tests__/**/*.test.ts : Test both AI and non-AI paths in LLM-related tests
Applied to files:
apps/web/utils/ai/digest/summarize-email-for-digest.tsapps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.tsapps/web/utils/ai/choose-rule/choose-args.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : always define a zod schema for response validation in ...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Always define a Zod schema for response validation in LLM-related functions.
Applied to files:
apps/web/utils/ai/digest/summarize-email-for-digest.tsapps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.tsapps/web/utils/ai/categorize-sender/ai-categorize-single-sender.tsapps/web/utils/ai/rule/generate-prompt-on-delete-rule.tsapps/web/utils/ai/rule/generate-prompt-on-update-rule.tsapps/web/utils/cold-email/is-cold-email.tsapps/web/utils/ai/categorize-sender/ai-categorize-senders.tsapps/web/utils/ai/choose-rule/ai-choose-rule.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : make zod schemas as specific as possible to guide the ...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Make Zod schemas as specific as possible to guide the LLM output.
Applied to files:
apps/web/utils/ai/digest/summarize-email-for-digest.tsapps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.tsapps/web/utils/ai/knowledge/extract.tsapps/web/utils/ai/categorize-sender/ai-categorize-single-sender.tsapps/web/utils/ai/rule/generate-prompt-on-delete-rule.tsapps/web/utils/ai/reply/draft-with-knowledge.tsapps/web/utils/ai/rule/generate-prompt-on-update-rule.tsapps/web/utils/cold-email/is-cold-email.tsapps/web/utils/ai/choose-rule/choose-args.tsapps/web/utils/ai/categorize-sender/ai-categorize-senders.tsapps/web/utils/ai/choose-rule/ai-choose-rule.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : use descriptive scoped loggers for each llm feature....
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Use descriptive scoped loggers for each LLM feature.
Applied to files:
apps/web/utils/ai/digest/summarize-email-for-digest.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.tsapps/web/utils/ai/knowledge/extract-from-email-history.tsapps/web/utils/ai/categorize-sender/ai-categorize-single-sender.tsapps/web/utils/ai/reply/draft-with-knowledge.tsapps/web/utils/cold-email/is-cold-email.tsapps/web/utils/ai/categorize-sender/ai-categorize-senders.tsapps/web/utils/ai/choose-rule/ai-choose-rule.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : use proper error types and logging in llm-related code...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Use proper error types and logging in LLM-related code.
Applied to files:
apps/web/utils/ai/digest/summarize-email-for-digest.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.tsapps/web/utils/ai/knowledge/extract.tsapps/web/utils/ai/knowledge/extract-from-email-history.tsapps/web/utils/ai/categorize-sender/ai-categorize-single-sender.tsapps/web/utils/ai/reply/draft-with-knowledge.tsapps/web/utils/cold-email/is-cold-email.tsapps/web/utils/ai/choose-rule/choose-args.tsapps/web/utils/ai/categorize-sender/ai-categorize-senders.tsapps/web/utils/ai/choose-rule/ai-choose-rule.ts
📚 Learning: applies to apps/web/utils/llms/model.ts : model definitions and configurations must be placed in uti...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/llms/model.ts : Model definitions and configurations must be placed in utils/llms/model.ts.
Applied to files:
apps/web/utils/ai/digest/summarize-email-for-digest.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : use typescript types for all parameters and return val...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Use TypeScript types for all parameters and return values in LLM-related code.
Applied to files:
apps/web/utils/ai/digest/summarize-email-for-digest.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.tsapps/web/utils/ai/knowledge/extract.tsapps/web/utils/ai/knowledge/extract-from-email-history.tsapps/web/utils/ai/categorize-sender/ai-categorize-single-sender.tsapps/web/utils/ai/rule/generate-prompt-on-delete-rule.tsapps/web/utils/ai/reply/draft-with-knowledge.tsapps/web/utils/cold-email/is-cold-email.tsapps/web/utils/ai/choose-rule/choose-args.tsapps/web/utils/ai/categorize-sender/ai-categorize-senders.tsapps/web/utils/ai/choose-rule/ai-choose-rule.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : keep system prompts and user prompts separate in llm-r...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Keep system prompts and user prompts separate in LLM-related code.
Applied to files:
apps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.tsapps/web/utils/ai/knowledge/extract.tsapps/web/utils/ai/knowledge/extract-from-email-history.tsapps/web/utils/ai/categorize-sender/ai-categorize-single-sender.tsapps/web/utils/ai/rule/generate-prompt-on-delete-rule.tsapps/web/utils/ai/reply/draft-with-knowledge.tsapps/web/utils/ai/rule/generate-prompt-on-update-rule.tsapps/web/utils/cold-email/is-cold-email.tsapps/web/utils/ai/categorize-sender/ai-categorize-senders.tsapps/web/utils/ai/choose-rule/ai-choose-rule.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : log inputs and outputs with appropriate log levels in ...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Log inputs and outputs with appropriate log levels in LLM-related functions.
Applied to files:
apps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/knowledge/extract-from-email-history.tsapps/web/utils/cold-email/is-cold-email.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : system prompt should define the llm's role and task sp...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : System prompt should define the LLM's role and task specifications.
Applied to files:
apps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.tsapps/web/utils/ai/knowledge/extract.tsapps/web/utils/ai/knowledge/extract-from-email-history.tsapps/web/utils/ai/rule/generate-prompt-on-delete-rule.tsapps/web/utils/ai/reply/draft-with-knowledge.tsapps/web/utils/ai/rule/generate-prompt-on-update-rule.tsapps/web/utils/cold-email/is-cold-email.tsapps/web/utils/ai/choose-rule/ai-choose-rule.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : user prompt should contain the actual data and context...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : User prompt should contain the actual data and context.
Applied to files:
apps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.tsapps/web/utils/ai/knowledge/extract.tsapps/web/utils/ai/rule/generate-prompt-on-delete-rule.tsapps/web/utils/ai/reply/draft-with-knowledge.tsapps/web/utils/ai/rule/generate-prompt-on-update-rule.tsapps/web/utils/cold-email/is-cold-email.tsapps/web/utils/ai/choose-rule/ai-choose-rule.ts
📚 Learning: in this project, prisma should be imported using 'import prisma from "@/utils/prisma";' in typescrip...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/prisma.mdc:0-0
Timestamp: 2025-06-23T12:26:53.882Z
Learning: In this project, Prisma should be imported using 'import prisma from "@/utils/prisma";' in TypeScript files.
Applied to files:
apps/web/utils/ai/knowledge/extract.ts
📚 Learning: the `utils` folder also contains core app logic such as next.js server actions and gmail api request...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/utilities.mdc:0-0
Timestamp: 2025-07-19T17:50:28.270Z
Learning: The `utils` folder also contains core app logic such as Next.js Server Actions and Gmail API requests.
Applied to files:
apps/web/utils/ai/knowledge/extract-from-email-history.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/* : keep related ai functions in the same file or directory....
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/* : Keep related AI functions in the same file or directory.
Applied to files:
apps/web/utils/ai/categorize-sender/ai-categorize-single-sender.tsapps/web/utils/ai/categorize-sender/ai-categorize-senders.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : use xml-like tags to structure data in llm prompts....
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Use XML-like tags to structure data in LLM prompts.
Applied to files:
apps/web/utils/ai/rule/generate-prompt-on-delete-rule.tsapps/web/utils/ai/rule/generate-prompt-on-update-rule.tsapps/web/utils/ai/choose-rule/ai-choose-rule.ts
📚 Learning: applies to apps/web/utils/actions/**/*.ts : use zod schemas for validation on both client and server...
Learnt from: CR
PR: elie222/inbox-zero#0
File: apps/web/CLAUDE.md:0-0
Timestamp: 2025-07-18T15:04:30.467Z
Learning: Applies to apps/web/utils/actions/**/*.ts : Use Zod schemas for validation on both client and server
Applied to files:
apps/web/utils/cold-email/is-cold-email.ts
📚 Learning: applies to apps/web/utils/actions/*.validation.ts : define zod schemas for validation in dedicated f...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/fullstack-workflow.mdc:0-0
Timestamp: 2025-07-18T15:05:16.146Z
Learning: Applies to apps/web/utils/actions/*.validation.ts : Define Zod schemas for validation in dedicated files and use them for both client and server validation.
Applied to files:
apps/web/utils/cold-email/is-cold-email.ts
📚 Learning: applies to apps/web/utils/actions/*.validation.ts : define input validation schemas using zod in the...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/server-actions.mdc:0-0
Timestamp: 2025-07-18T17:27:58.249Z
Learning: Applies to apps/web/utils/actions/*.validation.ts : Define input validation schemas using Zod in the corresponding `.validation.ts` file. These schemas are used by `next-safe-action` (`.schema()`) and can also be reused on the client for form validation.
Applied to files:
apps/web/utils/cold-email/is-cold-email.ts
📚 Learning: applies to apps/web/components/**/*.tsx : use react hook form with zod validation for form handling...
Learnt from: CR
PR: elie222/inbox-zero#0
File: apps/web/CLAUDE.md:0-0
Timestamp: 2025-07-18T15:04:30.467Z
Learning: Applies to apps/web/components/**/*.tsx : Use React Hook Form with Zod validation for form handling
Applied to files:
apps/web/utils/cold-email/is-cold-email.ts
📚 Learning: form handling using react hook form and zod...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/index.mdc:0-0
Timestamp: 2025-07-18T15:05:56.644Z
Learning: Form handling using React Hook Form and Zod
Applied to files:
apps/web/utils/cold-email/is-cold-email.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : implement early returns for invalid inputs in llm-rela...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Implement early returns for invalid inputs in LLM-related functions.
Applied to files:
apps/web/utils/ai/choose-rule/choose-args.ts
📚 Learning: applies to apps/web/utils/actions/**/*.ts : use server actions (with `next-safe-action`) for all mut...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/fullstack-workflow.mdc:0-0
Timestamp: 2025-07-18T15:05:16.146Z
Learning: Applies to apps/web/utils/actions/**/*.ts : Use server actions (with `next-safe-action`) for all mutations (create/update/delete operations); do NOT use POST API routes for mutations.
Applied to files:
apps/web/utils/ai/choose-rule/choose-args.ts
📚 Learning: applies to apps/web/utils/actions/**/*.ts : use server actions for all mutations (create/update/dele...
Learnt from: CR
PR: elie222/inbox-zero#0
File: apps/web/CLAUDE.md:0-0
Timestamp: 2025-07-18T15:04:30.467Z
Learning: Applies to apps/web/utils/actions/**/*.ts : Use server actions for all mutations (create/update/delete operations)
Applied to files:
apps/web/utils/ai/choose-rule/choose-args.ts
🧬 Code Graph Analysis (2)
apps/web/utils/ai/clean/ai-clean-select-labels.ts (2)
apps/web/utils/llms/model.ts (1)
getModel(18-32)apps/web/utils/usage.ts (1)
saveAiUsage(8-41)
apps/web/utils/ai/choose-rule/ai-choose-rule.ts (2)
apps/web/utils/llms/model.ts (1)
getModel(18-32)apps/web/utils/usage.ts (1)
saveAiUsage(8-41)
⏰ 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). (4)
- GitHub Check: Static Code Analysis Js
- GitHub Check: Jit Security
- GitHub Check: claude-review
- GitHub Check: Analyze (javascript-typescript)
🔇 Additional comments (22)
version.txt (1)
1-1: LGTM! Appropriate version bump for internal refactoring.The version increment properly reflects the comprehensive internal refactoring of AI utility functions without breaking public APIs.
apps/web/utils/ai/choose-rule/choose-args.ts (1)
73-77: LGTM! Explicit type casting improves type safety.The explicit cast to
ActionArgResponseensures type safety when working with the AI response structure from the refactored AI interaction pattern.apps/web/utils/ai/digest/summarize-email-for-digest.ts (2)
7-9: LGTM! Proper imports for the new AI interaction pattern.The new imports support the refactored AI interaction using
getModel,generateObject, andsaveAiUsagewhich aligns with the established LLM code structure.
79-109: LGTM! Excellent refactoring to the new AI interaction pattern.The refactoring properly implements the new AI interaction pattern:
- Model configuration: Uses
getModelto retrieve provider and model details- AI generation: Calls
generateObjectwith the resolved model and provider options- Usage tracking: Conditionally saves usage data with detailed metadata
- Consistency: Maintains existing logging, error handling, and system/user prompt separation
This follows the established LLM code structure from the retrieved learnings and maintains all required elements for robust AI interaction.
apps/web/utils/ai/clean/ai-clean-select-labels.ts (2)
5-7: LGTM! Correct imports for the refactored AI interaction.The imports properly support the new AI interaction pattern using
getModelfor configuration,generateObjectfor AI calls, andsaveAiUsagefor tracking.
37-66: LGTM! Well-implemented AI interaction refactoring.The refactoring excellently implements the new AI pattern:
- Model resolution: Properly uses
getModelto retrieve configuration based on user context- AI generation: Calls
generateObjectwith resolved model, prompts, schema, and provider options- Usage tracking: Conditionally saves detailed usage metadata including provider, model, and label
- Structure preservation: Maintains system/user prompt separation, logging, and error handling
This follows the established LLM function structure from the coding guidelines and retrieved learnings.
apps/web/utils/ai/choose-rule/ai-detect-recurring-pattern.ts (2)
6-8: LGTM! Proper imports for the AI interaction refactoring.The new imports correctly support the refactored AI interaction pattern with
getModelfor configuration,generateObjectfor AI calls, andsaveAiUsagefor usage tracking.
103-132: LGTM! Excellent implementation of the new AI interaction pattern.The refactoring demonstrates excellent adherence to established LLM code structure:
- Model configuration: Properly retrieves model details via
getModelwith user context- AI generation: Uses
generateObjectwith resolved model, system prompt, user prompt, schema, and provider options- Usage tracking: Conditionally saves comprehensive usage metadata
- Quality preservation: Maintains all existing quality aspects:
- Detailed system prompt with clear role and task specifications
- Proper error handling with try/catch blocks
- Trace logging for inputs and outputs
- Zod schema validation for response structure
This follows all the coding guidelines and retrieved learnings for LLM-related functions while successfully migrating to the new AI interaction pattern.
apps/web/utils/ai/knowledge/extract.ts (2)
127-135: LGTM! Proper usage tracking implementation.The conditional
saveAiUsagecall correctly tracks AI usage with all required parameters including email, usage metrics, provider, model, and label.
114-117: Missing modelType parameter in getModel call.The original
chatCompletionObjectcall usedmodelType: "economy"but the newgetModelcall doesn't specify this parameter. This could result in using a different model tier than intended.Apply this diff to maintain the original model type:
- const { provider, model, llmModel, providerOptions } = getModel( - emailAccount.user, - ); + const { provider, model, llmModel, providerOptions } = getModel( + emailAccount.user, + "economy", + );⛔ Skipped due to learnings
Learnt from: CR PR: elie222/inbox-zero#0 File: .cursor/rules/llm.mdc:0-0 Timestamp: 2025-07-18T15:06:40.272Z Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Document complex AI logic with clear comments in LLM-related code.Learnt from: CR PR: elie222/inbox-zero#0 File: .cursor/rules/llm.mdc:0-0 Timestamp: 2025-07-18T15:06:40.272Z Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Implement fallbacks for AI failures in LLM-related functions.Learnt from: CR PR: elie222/inbox-zero#0 File: .cursor/rules/llm.mdc:0-0 Timestamp: 2025-07-18T15:06:40.272Z Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Follow the standard structure for LLM-related functions: use a scoped logger, define a Zod schema for output, validate inputs early, separate system and user prompts, log inputs and outputs, call chatCompletionObject with proper configuration, and return validated results.Learnt from: CR PR: elie222/inbox-zero#0 File: .cursor/rules/llm.mdc:0-0 Timestamp: 2025-07-18T15:06:40.272Z Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Extract common patterns into utility functions in LLM-related code.Learnt from: CR PR: elie222/inbox-zero#0 File: .cursor/rules/llm.mdc:0-0 Timestamp: 2025-07-18T15:06:40.272Z Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Use proper error types and logging in LLM-related code.Learnt from: CR PR: elie222/inbox-zero#0 File: .cursor/rules/llm.mdc:0-0 Timestamp: 2025-07-18T15:06:40.272Z Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Use TypeScript types for all parameters and return values in LLM-related code.Learnt from: CR PR: elie222/inbox-zero#0 File: .cursor/rules/llm.mdc:0-0 Timestamp: 2025-07-18T15:06:40.272Z Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : System prompt should define the LLM's role and task specifications.Learnt from: CR PR: elie222/inbox-zero#0 File: .cursor/rules/llm.mdc:0-0 Timestamp: 2025-07-18T15:06:40.272Z Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Format data consistently across similar LLM-related functions.Learnt from: CR PR: elie222/inbox-zero#0 File: .cursor/rules/llm.mdc:0-0 Timestamp: 2025-07-18T15:06:40.272Z Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Keep system prompts and user prompts separate in LLM-related code.Learnt from: CR PR: elie222/inbox-zero#0 File: .cursor/rules/llm-test.mdc:0-0 Timestamp: 2025-07-18T15:06:10.570Z Learning: Applies to apps/web/__tests__/**/*.test.ts : Test both AI and non-AI paths in LLM-related testsapps/web/utils/ai/rule/generate-prompt-on-update-rule.ts (1)
71-91: LGTM! Consistent refactor implementation.The refactor correctly follows the new AI pattern:
- Model configuration retrieved via
getModelgenerateObjectcalled with proper parameters- Usage tracking implemented conditionally
- Original behavior preserved
apps/web/utils/ai/rule/generate-prompt-on-delete-rule.ts (1)
66-86: LGTM! Proper implementation of the new AI pattern.The refactor maintains consistency with the original behavior while implementing the standardized AI interaction pattern correctly.
apps/web/utils/ai/reply/draft-with-knowledge.ts (1)
145-165: LGTM! Clean refactor with preserved error handling.The implementation correctly follows the new AI pattern while maintaining the existing error handling structure. The conditional usage tracking is properly implemented.
apps/web/utils/ai/categorize-sender/ai-categorize-senders.ts (1)
103-123: LGTM! Consistent implementation across the codebase.The refactor correctly implements the standardized AI interaction pattern, maintaining all original functionality while adding proper usage tracking.
apps/web/utils/ai/categorize-sender/ai-categorize-single-sender.ts (2)
1-1: LGTM! New imports align with the standardized AI interaction pattern.The imports for
generateObject,getModel, andsaveAiUsageproperly support the refactor fromchatCompletionObjectto the new AI interaction approach.Also applies to: 7-8
71-91: Excellent implementation following LLM coding standards.The refactor correctly implements the new AI interaction pattern:
- Properly retrieves model configuration via
getModel- Uses
generateObjectwith appropriate parameters- Conditionally saves usage data with
saveAiUsage- Maintains existing schema validation and logging
This aligns perfectly with the established LLM-related function structure from the coding guidelines.
apps/web/utils/cold-email/is-cold-email.ts (2)
15-17: LGTM! Imports properly support the AI interaction refactor.The new imports for
getModel,generateObject, andsaveAiUsageare correctly added to support the standardized AI interaction pattern.
221-245: Excellent refactor implementation following established patterns.The new AI interaction logic properly:
- Retrieves model configuration via
getModelwith optionalmodelTypeparameter- Uses
generateObjectwith the resolved model and provider options- Maintains existing schema validation for response structure
- Conditionally saves usage data with proper labeling
- Preserves input/output logging for debugging
This follows the LLM coding guidelines perfectly and maintains backward compatibility.
apps/web/utils/ai/choose-rule/ai-choose-rule.ts (2)
6-8: LGTM! Imports align with the standardized AI refactor pattern.The new imports for
getModel,generateObject, andsaveAiUsageproperly support the refactored AI interaction approach.
130-138: LGTM! Usage tracking properly implemented.The conditional usage saving correctly follows the established pattern with proper parameter mapping.
apps/web/utils/ai/knowledge/extract-from-email-history.ts (2)
9-11: LGTM! Imports properly support the AI interaction refactor.The new imports for
getModel,generateObject, andsaveAiUsageare correctly added and align with the standardized pattern.
112-133: Excellent implementation with proper model type handling.The refactor correctly:
- Passes the "economy" model type to
getModelfor cost-effective processing- Uses
generateObjectwith appropriate parameters and provider options- Maintains existing schema validation and error handling
- Conditionally saves usage data with proper labeling
This exemplifies the standardized LLM interaction pattern perfectly.
| const { provider, model, llmModel, providerOptions } = getModel( | ||
| emailAccount.user, | ||
| ); | ||
|
|
||
| const aiResponse = await generateObject({ | ||
| model: llmModel, | ||
| system, | ||
| prompt, | ||
| schema: z.object({ | ||
| reason: z.string(), | ||
| ruleName: z.string().nullish(), | ||
| noMatchFound: z.boolean().nullish(), | ||
| }), | ||
| userEmail: emailAccount.email, | ||
| usageLabel: "Choose rule", | ||
| providerOptions, | ||
| }); |
There was a problem hiding this comment.
Pass modelType parameter to getModel call.
The modelType parameter (defaulted to "default" on line 23) should be passed to the getModel call to ensure the correct model type is used.
Apply this fix:
const { provider, model, llmModel, providerOptions } = getModel(
emailAccount.user,
+ modelType,
);📝 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 { provider, model, llmModel, providerOptions } = getModel( | |
| emailAccount.user, | |
| ); | |
| const aiResponse = await generateObject({ | |
| model: llmModel, | |
| system, | |
| prompt, | |
| schema: z.object({ | |
| reason: z.string(), | |
| ruleName: z.string().nullish(), | |
| noMatchFound: z.boolean().nullish(), | |
| }), | |
| userEmail: emailAccount.email, | |
| usageLabel: "Choose rule", | |
| providerOptions, | |
| }); | |
| const { provider, model, llmModel, providerOptions } = getModel( | |
| emailAccount.user, | |
| modelType, | |
| ); | |
| const aiResponse = await generateObject({ | |
| model: llmModel, | |
| system, | |
| prompt, | |
| schema: z.object({ | |
| reason: z.string(), | |
| ruleName: z.string().nullish(), | |
| noMatchFound: z.boolean().nullish(), | |
| }), | |
| providerOptions, | |
| }); |
🤖 Prompt for AI Agents
In apps/web/utils/ai/choose-rule/ai-choose-rule.ts around lines 114 to 128, the
call to getModel is missing the modelType parameter, which defaults to "default"
on line 23. Update the getModel call to include the modelType argument to ensure
the correct model type is used when retrieving the model, provider, llmModel,
and providerOptions.
|
Claude finished @elie222's task —— View job PR Review: AI Model Integration MigrationI've completed a comprehensive review of this PR which migrates AI utility functions from a custom Todo List:
📋 SummaryThis PR implements a migration from a custom LLM wrapper (
|
There was a problem hiding this comment.
Actionable comments posted: 3
🧹 Nitpick comments (1)
apps/web/utils/ai/rule/create-rule.ts (1)
58-58: Consider safer type assertion for the return value.The type assertion
as CreateOrUpdateRuleSchemaWithCategoriesassumes the AI response matches the expected type, but this might not always be true if the schema validation fails silently.Consider using the validated result directly:
- return result as CreateOrUpdateRuleSchemaWithCategories; + return result;The schema validation in
generateObjectshould ensure type safety, making the explicit cast unnecessary.
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (6)
apps/web/utils/ai/clean/ai-clean-select-labels.ts(2 hunks)apps/web/utils/ai/clean/ai-clean.ts(2 hunks)apps/web/utils/ai/digest/summarize-email-for-digest.ts(2 hunks)apps/web/utils/ai/knowledge/extract-from-email-history.ts(2 hunks)apps/web/utils/ai/knowledge/extract.ts(2 hunks)apps/web/utils/ai/rule/create-rule.ts(2 hunks)
🚧 Files skipped from review as they are similar to previous changes (3)
- apps/web/utils/ai/digest/summarize-email-for-digest.ts
- apps/web/utils/ai/knowledge/extract.ts
- apps/web/utils/ai/knowledge/extract-from-email-history.ts
🧰 Additional context used
📓 Path-based instructions (10)
apps/web/**/*.{ts,tsx}
📄 CodeRabbit Inference Engine (apps/web/CLAUDE.md)
apps/web/**/*.{ts,tsx}: Use TypeScript with strict null checks
Path aliases: Use@/for imports from project root
Use proper error handling with try/catch blocks
Format code with Prettier
Leverage TypeScript inference for better DX
Files:
apps/web/utils/ai/rule/create-rule.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/clean/ai-clean.ts
!{.cursor/rules/*.mdc}
📄 CodeRabbit Inference Engine (.cursor/rules/cursor-rules.mdc)
Never place rule files in the project root, in subdirectories outside .cursor/rules, or in any other location
Files:
apps/web/utils/ai/rule/create-rule.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/clean/ai-clean.ts
**/*.ts
📄 CodeRabbit Inference Engine (.cursor/rules/form-handling.mdc)
**/*.ts: The same validation should be done in the server action too
Define validation schemas using Zod
Files:
apps/web/utils/ai/rule/create-rule.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/clean/ai-clean.ts
apps/web/utils/{ai,llms}/**/*
📄 CodeRabbit Inference Engine (.cursor/rules/llm.mdc)
apps/web/utils/{ai,llms}/**/*: LLM-related code must be organized in the directories: apps/web/utils/ai/, apps/web/utils/llms/, and apps/web/tests/ for LLM-specific tests.
Keep related AI functions in the same file or directory.
Files:
apps/web/utils/ai/rule/create-rule.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/clean/ai-clean.ts
apps/web/utils/{ai,llms}/**/*.ts
📄 CodeRabbit Inference Engine (.cursor/rules/llm.mdc)
apps/web/utils/{ai,llms}/**/*.ts: Follow the standard structure for LLM-related functions: use a scoped logger, define a Zod schema for output, validate inputs early, separate system and user prompts, log inputs and outputs, call chatCompletionObject with proper configuration, and return validated results.
Keep system prompts and user prompts separate in LLM-related code.
System prompt should define the LLM's role and task specifications.
User prompt should contain the actual data and context.
Always define a Zod schema for response validation in LLM-related functions.
Make Zod schemas as specific as possible to guide the LLM output.
Use descriptive scoped loggers for each LLM feature.
Log inputs and outputs with appropriate log levels in LLM-related functions.
Include relevant context in log messages for LLM-related code.
Implement early returns for invalid inputs in LLM-related functions.
Use proper error types and logging in LLM-related code.
Implement fallbacks for AI failures in LLM-related functions.
Add retry logic for transient failures using withRetry in LLM-related code.
Use XML-like tags to structure data in LLM prompts.
Remove excessive whitespace and truncate long inputs in LLM prompts.
Format data consistently across similar LLM-related functions.
Use TypeScript types for all parameters and return values in LLM-related code.
Define clear interfaces for complex input/output structures in LLM-related code.
Extract common patterns into utility functions in LLM-related code.
Document complex AI logic with clear comments in LLM-related code.
Files:
apps/web/utils/ai/rule/create-rule.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/clean/ai-clean.ts
**/*.{ts,tsx}
📄 CodeRabbit Inference Engine (.cursor/rules/logging.mdc)
**/*.{ts,tsx}: UsecreateScopedLoggerfor logging in backend TypeScript files
Typically add the logger initialization at the top of the file when usingcreateScopedLogger
Only use.with()on a logger instance within a specific function, not for a global loggerImport Prisma in the project using
import prisma from "@/utils/prisma";
**/*.{ts,tsx}: Don't use TypeScript enums.
Don't use TypeScript const enum.
Don't use the TypeScript directive @ts-ignore.
Don't use primitive type aliases or misleading types.
Don't use empty type parameters in type aliases and interfaces.
Don't use any or unknown as type constraints.
Don't use implicit any type on variable declarations.
Don't let variables evolve into any type through reassignments.
Don't use non-null assertions with the ! postfix operator.
Don't misuse the non-null assertion operator (!) in TypeScript files.
Don't use user-defined types.
Use as const instead of literal types and type annotations.
Use export type for types.
Use import type for types.
Don't declare empty interfaces.
Don't merge interfaces and classes unsafely.
Don't use overload signatures that aren't next to each other.
Use the namespace keyword instead of the module keyword to declare TypeScript namespaces.
Don't use TypeScript namespaces.
Don't export imported variables.
Don't add type annotations to variables, parameters, and class properties that are initialized with literal expressions.
Don't use parameter properties in class constructors.
Use either T[] or Array consistently.
Initialize each enum member value explicitly.
Make sure all enum members are literal values.
Files:
apps/web/utils/ai/rule/create-rule.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/clean/ai-clean.ts
apps/web/utils/**
📄 CodeRabbit Inference Engine (.cursor/rules/project-structure.mdc)
Create utility functions in
utils/folder for reusable logic
Files:
apps/web/utils/ai/rule/create-rule.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/clean/ai-clean.ts
apps/web/utils/**/*.ts
📄 CodeRabbit Inference Engine (.cursor/rules/project-structure.mdc)
apps/web/utils/**/*.ts: Use lodash utilities for common operations (arrays, objects, strings)
Import specific lodash functions to minimize bundle size
Files:
apps/web/utils/ai/rule/create-rule.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/clean/ai-clean.ts
**/*.{js,jsx,ts,tsx}
📄 CodeRabbit Inference Engine (.cursor/rules/ultracite.mdc)
**/*.{js,jsx,ts,tsx}: Don't useelements in Next.js projects.
Don't use elements in Next.js projects.
Don't use namespace imports.
Don't access namespace imports dynamically.
Don't use global eval().
Don't use console.
Don't use debugger.
Don't use var.
Don't use with statements in non-strict contexts.
Don't use the arguments object.
Don't use consecutive spaces in regular expression literals.
Don't use the comma operator.
Don't use unnecessary boolean casts.
Don't use unnecessary callbacks with flatMap.
Use for...of statements instead of Array.forEach.
Don't create classes that only have static members (like a static namespace).
Don't use this and super in static contexts.
Don't use unnecessary catch clauses.
Don't use unnecessary constructors.
Don't use unnecessary continue statements.
Don't export empty modules that don't change anything.
Don't use unnecessary escape sequences in regular expression literals.
Don't use unnecessary labels.
Don't use unnecessary nested block statements.
Don't rename imports, exports, and destructured assignments to the same name.
Don't use unnecessary string or template literal concatenation.
Don't use String.raw in template literals when there are no escape sequences.
Don't use useless case statements in switch statements.
Don't use ternary operators when simpler alternatives exist.
Don't use useless this aliasing.
Don't initialize variables to undefined.
Don't use the void operators (they're not familiar).
Use arrow functions instead of function expressions.
Use Date.now() to get milliseconds since the Unix Epoch.
Use .flatMap() instead of map().flat() when possible.
Use literal property access instead of computed property access.
Don't use parseInt() or Number.parseInt() when binary, octal, or hexadecimal literals work.
Use concise optional chaining instead of chained logical expressions.
Use regular expression literals instead of the RegExp constructor when possible.
Don't use number literal object member names th...
Files:
apps/web/utils/ai/rule/create-rule.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/clean/ai-clean.ts
!pages/_document.{js,jsx,ts,tsx}
📄 CodeRabbit Inference Engine (.cursor/rules/ultracite.mdc)
!pages/_document.{js,jsx,ts,tsx}: Don't import next/document outside of pages/_document.jsx in Next.js projects.
Don't import next/document outside of pages/_document.jsx in Next.js projects.
Files:
apps/web/utils/ai/rule/create-rule.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/clean/ai-clean.ts
🧠 Learnings (16)
📓 Common learnings
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Follow the standard structure for LLM-related functions: use a scoped logger, define a Zod schema for output, validate inputs early, separate system and user prompts, log inputs and outputs, call chatCompletionObject with proper configuration, and return validated results.
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Implement fallbacks for AI failures in LLM-related functions.
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/* : Keep related AI functions in the same file or directory.
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Document complex AI logic with clear comments in LLM-related code.
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Extract common patterns into utility functions in LLM-related code.
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Define clear interfaces for complex input/output structures in LLM-related code.
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Format data consistently across similar LLM-related functions.
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Make Zod schemas as specific as possible to guide the LLM output.
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Use TypeScript types for all parameters and return values in LLM-related code.
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : follow the standard structure for llm-related function...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Follow the standard structure for LLM-related functions: use a scoped logger, define a Zod schema for output, validate inputs early, separate system and user prompts, log inputs and outputs, call chatCompletionObject with proper configuration, and return validated results.
Applied to files:
apps/web/utils/ai/rule/create-rule.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/clean/ai-clean.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : document complex ai logic with clear comments in llm-r...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Document complex AI logic with clear comments in LLM-related code.
Applied to files:
apps/web/utils/ai/rule/create-rule.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/clean/ai-clean.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : implement fallbacks for ai failures in llm-related fun...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Implement fallbacks for AI failures in LLM-related functions.
Applied to files:
apps/web/utils/ai/rule/create-rule.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/clean/ai-clean.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : make zod schemas as specific as possible to guide the ...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Make Zod schemas as specific as possible to guide the LLM output.
Applied to files:
apps/web/utils/ai/rule/create-rule.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/clean/ai-clean.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : keep system prompts and user prompts separate in llm-r...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Keep system prompts and user prompts separate in LLM-related code.
Applied to files:
apps/web/utils/ai/rule/create-rule.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/clean/ai-clean.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : use typescript types for all parameters and return val...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Use TypeScript types for all parameters and return values in LLM-related code.
Applied to files:
apps/web/utils/ai/rule/create-rule.tsapps/web/utils/ai/clean/ai-clean-select-labels.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : system prompt should define the llm's role and task sp...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : System prompt should define the LLM's role and task specifications.
Applied to files:
apps/web/utils/ai/rule/create-rule.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/clean/ai-clean.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : user prompt should contain the actual data and context...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : User prompt should contain the actual data and context.
Applied to files:
apps/web/utils/ai/rule/create-rule.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/clean/ai-clean.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : use proper error types and logging in llm-related code...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Use proper error types and logging in LLM-related code.
Applied to files:
apps/web/utils/ai/rule/create-rule.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/clean/ai-clean.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : format data consistently across similar llm-related fu...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Format data consistently across similar LLM-related functions.
Applied to files:
apps/web/utils/ai/rule/create-rule.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/clean/ai-clean.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : extract common patterns into utility functions in llm-...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Extract common patterns into utility functions in LLM-related code.
Applied to files:
apps/web/utils/ai/rule/create-rule.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/clean/ai-clean.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : define clear interfaces for complex input/output struc...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Define clear interfaces for complex input/output structures in LLM-related code.
Applied to files:
apps/web/utils/ai/rule/create-rule.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/clean/ai-clean.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : always define a zod schema for response validation in ...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Always define a Zod schema for response validation in LLM-related functions.
Applied to files:
apps/web/utils/ai/rule/create-rule.tsapps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/clean/ai-clean.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : remove excessive whitespace and truncate long inputs i...
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Remove excessive whitespace and truncate long inputs in LLM prompts.
Applied to files:
apps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/clean/ai-clean.ts
📚 Learning: applies to apps/web/utils/{ai,llms}/**/*.ts : use descriptive scoped loggers for each llm feature....
Learnt from: CR
PR: elie222/inbox-zero#0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-07-18T15:06:40.272Z
Learning: Applies to apps/web/utils/{ai,llms}/**/*.ts : Use descriptive scoped loggers for each LLM feature.
Applied to files:
apps/web/utils/ai/clean/ai-clean-select-labels.tsapps/web/utils/ai/clean/ai-clean.ts
⏰ 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). (2)
- GitHub Check: claude-review
- GitHub Check: Analyze (javascript-typescript)
🔇 Additional comments (6)
apps/web/utils/ai/clean/ai-clean-select-labels.ts (2)
4-6: LGTM: Proper imports for the refactored AI pattern.The new imports correctly support the transition from
chatCompletionObjectto the standardizedgetModel+generateObject+saveAiUsagepattern.
57-65: LGTM: Proper usage tracking implementation.The conditional usage tracking follows the established pattern correctly, saving usage data when available with appropriate metadata.
apps/web/utils/ai/clean/ai-clean.ts (2)
2-2: LGTM: Correct imports for the refactored AI pattern.The imports properly support the new
generateObjectapproach with model resolution and usage tracking.Also applies to: 9-10
118-126: LGTM: Proper usage tracking implementation.The usage tracking correctly saves AI usage data with appropriate metadata including email, provider, model, and usage label.
apps/web/utils/ai/rule/create-rule.ts (2)
7-9: LGTM: Proper imports for the refactored AI pattern.The new imports correctly support the transition to the standardized AI generation approach.
44-52: LGTM: Consistent usage tracking implementation.The usage tracking properly saves AI usage data with correct metadata following the established pattern.
| const { provider, model, llmModel, providerOptions } = getModel( | ||
| emailAccount.user, | ||
| ); | ||
|
|
||
| const aiResponse = await generateObject({ | ||
| model: llmModel, | ||
| system, | ||
| prompt, | ||
| schema, | ||
| userEmail: emailAccount.email, | ||
| usageLabel: "Clean - Select Labels", | ||
| providerOptions, | ||
| }); |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Implement error handling for AI generation failures.
The refactored code lacks fallback mechanisms for AI failures, which is a requirement per the coding guidelines for LLM-related functions.
Consider adding error handling:
+ try {
const aiResponse = await generateObject({
model: llmModel,
system,
prompt,
schema,
providerOptions,
});
+ } catch (error) {
+ logger.error("AI generation failed", { error });
+ // Return empty array as fallback for labels
+ return [];
+ }📝 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 { provider, model, llmModel, providerOptions } = getModel( | |
| emailAccount.user, | |
| ); | |
| const aiResponse = await generateObject({ | |
| model: llmModel, | |
| system, | |
| prompt, | |
| schema, | |
| userEmail: emailAccount.email, | |
| usageLabel: "Clean - Select Labels", | |
| providerOptions, | |
| }); | |
| const { provider, model, llmModel, providerOptions } = getModel( | |
| emailAccount.user, | |
| ); | |
| try { | |
| const aiResponse = await generateObject({ | |
| model: llmModel, | |
| system, | |
| prompt, | |
| schema, | |
| providerOptions, | |
| }); | |
| } catch (error) { | |
| logger.error("AI generation failed", { error }); | |
| // Return empty array as fallback for labels | |
| return []; | |
| } |
🤖 Prompt for AI Agents
In apps/web/utils/ai/clean/ai-clean-select-labels.ts around lines 45 to 55, the
code calls generateObject without error handling, which risks unhandled failures
during AI generation. Wrap the generateObject call in a try-catch block to catch
any errors, and implement a fallback mechanism or return a default value in the
catch block to ensure graceful failure handling as per coding guidelines.
| const { provider, model, llmModel, providerOptions } = getModel( | ||
| emailAccount.user, | ||
| ); | ||
|
|
||
| const aiResponse = await generateObject({ | ||
| model: llmModel, | ||
| system, | ||
| prompt, | ||
| schema, | ||
| userEmail: emailAccount.email, | ||
| usageLabel: "Clean", | ||
| providerOptions, | ||
| }); |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Add error handling and fallback for AI generation failures.
The function lacks error handling for AI generation failures, which could cause the entire email processing to fail. Given this function makes critical decisions about archiving emails, a fallback strategy is essential.
Add comprehensive error handling:
+ try {
const aiResponse = await generateObject({
model: llmModel,
system,
prompt,
schema,
providerOptions,
});
+ } catch (error) {
+ logger.error("AI generation failed for email archiving", {
+ error,
+ messageId,
+ emailAccount: emailAccount.email
+ });
+ // Fallback: don't archive when AI fails (safer default)
+ return { archive: false };
+ }📝 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 { provider, model, llmModel, providerOptions } = getModel( | |
| emailAccount.user, | |
| ); | |
| const aiResponse = await generateObject({ | |
| model: llmModel, | |
| system, | |
| prompt, | |
| schema, | |
| userEmail: emailAccount.email, | |
| usageLabel: "Clean", | |
| providerOptions, | |
| }); | |
| const { provider, model, llmModel, providerOptions } = getModel( | |
| emailAccount.user, | |
| ); | |
| try { | |
| const aiResponse = await generateObject({ | |
| model: llmModel, | |
| system, | |
| prompt, | |
| schema, | |
| providerOptions, | |
| }); | |
| } catch (error) { | |
| logger.error("AI generation failed for email archiving", { | |
| error, | |
| messageId, | |
| emailAccount: emailAccount.email, | |
| }); | |
| // Fallback: don't archive when AI fails (safer default) | |
| return { archive: false }; | |
| } |
🤖 Prompt for AI Agents
In apps/web/utils/ai/clean/ai-clean.ts around lines 106 to 116, the call to
generateObject lacks error handling, risking failure of the entire email
processing if AI generation fails. Wrap the generateObject call in a try-catch
block to catch any errors, log or handle the error appropriately, and implement
a fallback strategy such as returning a default response or skipping AI-based
decisions to ensure the function continues safely.
| const { provider, model, llmModel, providerOptions } = getModel( | ||
| emailAccount.user, | ||
| ); | ||
|
|
||
| const aiResponse = await generateObject({ | ||
| model: llmModel, | ||
| system, | ||
| schemaName: "Generate rule", | ||
| schemaDescription: "Generate a rule to handle the email", | ||
| prompt, | ||
| schema: createRuleSchema, | ||
| userEmail: emailAccount.email, | ||
| usageLabel: "Categorize rule", | ||
| providerOptions, | ||
| }); |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Implement error handling for rule generation failures.
Rule generation is a critical function that should have robust error handling. The current implementation could fail silently or throw unhandled errors.
Add proper error handling with fallbacks:
+ try {
const aiResponse = await generateObject({
model: llmModel,
system,
prompt,
schema: createRuleSchema,
providerOptions,
});
+ } catch (error) {
+ logger.error("AI rule generation failed", {
+ error,
+ instructions,
+ emailAccount: emailAccount.email
+ });
+ throw new Error(`Failed to generate rule: ${error.message}`);
+ }Committable suggestion skipped: line range outside the PR's diff.
🤖 Prompt for AI Agents
In apps/web/utils/ai/rule/create-rule.ts around lines 32 to 42, the code calls
generateObject to create a rule but lacks error handling, risking unhandled
exceptions or silent failures. Wrap the generateObject call in a try-catch block
to catch any errors during rule generation. In the catch block, log the error
appropriately and implement a fallback mechanism or return a default value to
ensure the function handles failures gracefully without crashing.
|
Claude finished @elie222's task —— View job PR Review: AI Model Integration MigrationI've completed a comprehensive review of this PR which migrates AI utility functions from a custom Todo List:
📋 SummaryThis PR implements a migration from a custom LLM wrapper (
|
elie222
deleted the
cursor/switch-to-chat-model-for-user-actions-4934
branch
1 participant
Summary by CodeRabbit