Digest improvements: Exclude meaningless information#611
Digest improvements: Exclude meaningless information#611elie222 merged 1 commit intoelie222:mainfrom
Conversation
|
@edulelis is attempting to deploy a commit to the Inbox Zero OSS Program Team on Vercel. A member of the Team first needs to authorize it. |
WalkthroughA new section, "Content rules for structured classification," was added to the AI system prompt for email summarization. This section instructs the AI to include only human-relevant, human-readable information in structured summaries and to exclude technical identifiers like account IDs or tracking tokens. No other logic or control flow was changed. Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~2 minutes Possibly related PRs
Poem
✨ 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. Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
Documentation and Community
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🔭 Outside diff range comments (1)
apps/web/utils/ai/digest/summarize-email-for-digest.ts (1)
71-72: Avoid logging full prompt ‒ potential PII/PCI exposure
logger.trace("Input", { system, prompt });records the entire e-mail body and rule name verbatim. Digest e-mails can contain personal data, so persisting them in logs risks accidental retention or leakage.Minimal fix: log only metadata or a truncated/hash version of the content.
-logger.trace("Input", { system, prompt }); +logger.trace("Input", { + systemPreview: system.slice(0, 120), + promptPreview: prompt.slice(0, 200), // truncate to avoid PII retention +});
🧹 Nitpick comments (1)
apps/web/utils/ai/digest/summarize-email-for-digest.ts (1)
52-55: Clarify & extend the new “Content rules” to guard against PII leakageNice addition! Consider tightening the guidance further so the model also omits personal identifiers that are human-readable but still sensitive (e-mail addresses, phone numbers, street addresses, credit-card PANs, etc.). This keeps the digest privacy-safe and consistent with GDPR/CCPA expectations.
**Content rules for structured classification:** - Only include human-relevant and human-readable information. - Exclude opaque technical identifiers like account IDs, payment IDs, tracking tokens, or long alphanumeric strings that aren't meaningful to users. + - Exclude or redact sensitive personal data such as e-mail addresses, phone numbers, street addresses, or full credit-card numbers.
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
apps/web/utils/ai/digest/summarize-email-for-digest.ts(1 hunks)
🧰 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/digest/summarize-email-for-digest.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/digest/summarize-email-for-digest.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.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.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.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.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.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.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.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/digest/summarize-email-for-digest.ts
🧠 Learnings (11)
📓 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 : Document complex AI logic with clear comments in LLM-related code.
📚 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.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/digest/summarize-email-for-digest.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.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 : 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/digest/summarize-email-for-digest.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/digest/summarize-email-for-digest.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/digest/summarize-email-for-digest.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.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.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.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: Static Code Analysis Js
- GitHub Check: Jit Security
🔇 Additional comments (1)
apps/web/utils/ai/digest/summarize-email-for-digest.ts (1)
64-69: Consider pre-emptive token/size control for large mails
stringifyEmailSimplemay return very long strings, pushing the request over model context limits or incurring extra cost. A simple guard such astruncateMiddle()(keeping head & tail) before interpolation would improve robustness.No action required if
stringifyEmailSimplealready handles this, but worth verifying.
2 participants
Summary by CodeRabbit