meeting-briefing: Agentic approach with research tools#1162
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
|
Note Other AI code review bot(s) detectedCodeRabbit has detected other AI code review bot(s) in this pull request and will avoid duplicating their findings in the review comments. This may lead to a less comprehensive review. 📝 WalkthroughWalkthroughRefactors meeting-briefing generation to an agentic, tool-driven flow (with finalize tool and web-search/perplexity tooling), removes per-guest AI research from context gathering, renames/expands research cache APIs, threads a logger into generation, adds many tests, and early-exits when no external guests. Changes
Sequence DiagramsequenceDiagram
participant Client
participant Generator as aiGenerateMeetingBriefing
participant Agent as Agentic AI Flow
participant Cache as Research Cache
participant WebSearch as WebSearch Tool
Client->>Generator: aiGenerateMeetingBriefing(briefingData, emailAccount, logger)
Generator->>Cache: getCachedResearch(source?, user, guest)
alt cache hit
Cache-->>Generator: cached research
Generator->>Agent: start agent with cached context & toolsNote
else cache miss
Generator->>Agent: start agent with AGENTIC_SYSTEM_PROMPT & tools
loop Agentic steps (<= MAX_AGENT_STEPS)
Agent->>WebSearch: optional web search request
WebSearch-->>Agent: search results
Agent->>Cache: setCachedResearch(source, user, guest, content)
end
Agent->>Agent: call finalizeBriefing tool
Agent-->>Generator: finalized BriefingContent
end
Generator-->>Client: BriefingContent (guests with per-guest bullets)
Estimated code review effort🎯 4 (Complex) | ⏱️ ~45 minutes Possibly related PRs
Suggested reviewers
Poem
Pre-merge checks and finishing touches❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✨ Finishing touches
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Update meeting briefing agent to attempt agentic generation without search tools in generate-briefing.tsAdjust 📍Where to StartStart with Macroscope summarized 81613e1. |
![cubic-dev-ai[bot]](https://avatars.githubusercontent.com/in/1082092?s=60&v=4){kind=small}
There was a problem hiding this comment.
1 issue found across 4 files
Prompt for AI agents (all issues)
Check if these issues are valid — if so, understand the root cause of each and fix them.
<file name="apps/web/__tests__/ai-meeting-briefing.test.ts">
<violation number="1" location="apps/web/__tests__/ai-meeting-briefing.test.ts:80">
P2: Test assertion `expect(prompt).toContain("new contact")` passes for the wrong reason - it matches template text, not the guest's name "New Contact". Consider changing to `"New Contact"` to actually verify the guest's name is included in the prompt.</violation>
</file>
Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.
![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 (1)
apps/web/utils/ai/meeting-briefs/generate-briefing.ts (1)
86-106: Add error handling to the research tool.The
researchGuesttool callsresearchGuestWithPerplexitywithout error handling. If the research call throws an exception, it could break the entire briefing generation flow.🔎 Proposed enhancement
execute: async ({ email, name }) => { logger.info("Researching guest", { email, name }); - const research = await researchGuestWithPerplexity({ - email, - name, - event: briefingData.event, - emailAccount, - logger, - }); - if (!research) { - return { found: false, message: "No research results available" }; - } - return { found: true, research }; + try { + const research = await researchGuestWithPerplexity({ + email, + name, + event: briefingData.event, + emailAccount, + logger, + }); + if (!research) { + return { found: false, message: "No research results available" }; + } + return { found: true, research }; + } catch (error) { + logger.error("Research failed for guest", { email, name, error }); + return { found: false, message: "Research failed" }; + } },As per coding guidelines, implement proper error handling and fallbacks for AI failures.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (4)
apps/web/__tests__/ai-meeting-briefing.test.tsapps/web/utils/ai/meeting-briefs/generate-briefing.tsapps/web/utils/meeting-briefs/gather-context.tsapps/web/utils/meeting-briefs/process.ts
🧰 Additional context used
📓 Path-based instructions (22)
**/*.{ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/data-fetching.mdc)
**/*.{ts,tsx}: For API GET requests to server, use theswrpackage
Useresult?.serverErrorwithtoastErrorfrom@/components/Toastfor error handling in async operations
**/*.{ts,tsx}: Use wrapper functions for Gmail message operations (get, list, batch, etc.) from @/utils/gmail/message.ts instead of direct API calls
Use wrapper functions for Gmail thread operations from @/utils/gmail/thread.ts instead of direct API calls
Use wrapper functions for Gmail label operations from @/utils/gmail/label.ts instead of direct API calls
**/*.{ts,tsx}: For early access feature flags, create hooks using the naming conventionuse[FeatureName]Enabledthat return a boolean fromuseFeatureFlagEnabled("flag-key")
For A/B test variant flags, create hooks using the naming conventionuse[FeatureName]Variantthat define variant types, useuseFeatureFlagVariantKey()with type casting, and provide a default "control" fallback
Use kebab-case for PostHog feature flag keys (e.g.,inbox-cleaner,pricing-options-2)
Always define types for A/B test variant flags (e.g.,type PricingVariant = "control" | "variant-a" | "variant-b") and provide type safety through type casting
**/*.{ts,tsx}: Don't use primitive type aliases or misleading types
Don't use empty type parameters in type aliases and interfaces
Don't use this and super in static contexts
Don't use any or unknown as type constraints
Don't use the TypeScript directive @ts-ignore
Don't use TypeScript enums
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 TypeScript namespaces
Don't use non-null assertions with the!postfix operator
Don't use parameter properties in class constructors
Don't use user-defined types
Useas constinstead of literal types and type annotations
Use eitherT[]orArray<T>consistently
Initialize each enum member value explicitly
Useexport typefor types
Use `impo...
Files:
apps/web/__tests__/ai-meeting-briefing.test.tsapps/web/utils/meeting-briefs/gather-context.tsapps/web/utils/meeting-briefs/process.tsapps/web/utils/ai/meeting-briefs/generate-briefing.ts
apps/web/__tests__/**/*.test.ts
📄 CodeRabbit inference engine (.cursor/rules/llm-test.mdc)
apps/web/__tests__/**/*.test.ts: Place all LLM-related tests inapps/web/__tests__/directory
Use vitest imports (describe,expect,test,vi,beforeEach) in LLM test files
Mock 'server-only' module with empty object in LLM test files:vi.mock("server-only", () => ({}))
Set timeout constantconst TIMEOUT = 15_000;for LLM tests
Usedescribe.runIf(isAiTest)with environment variableRUN_AI_TESTS === "true"to conditionally run LLM tests
Useconsole.debug()for outputting generated LLM content in tests, e.g.,console.debug("Generated content:\n", result.content);
Prefer using existing helpers from@/__tests__/helpers.ts(getEmailAccount,getEmail,getRule,getMockMessage,getMockExecutedRule) instead of creating custom test data helpers
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
apps/web/{utils/ai,utils/llms,__tests__}/**/*.ts
📄 CodeRabbit inference engine (.cursor/rules/llm.mdc)
LLM-related code must be organized in specific directories:
apps/web/utils/ai/for main implementations,apps/web/utils/llms/for core utilities and configurations, andapps/web/__tests__/for LLM-specific tests
Files:
apps/web/__tests__/ai-meeting-briefing.test.tsapps/web/utils/ai/meeting-briefs/generate-briefing.ts
**/*.{ts,tsx,js,jsx}
📄 CodeRabbit inference engine (.cursor/rules/prisma-enum-imports.mdc)
Always import Prisma enums from
@/generated/prisma/enumsinstead of@/generated/prisma/clientto avoid Next.js bundling errors in client componentsImport Prisma using the project's centralized utility:
import prisma from '@/utils/prisma'
Files:
apps/web/__tests__/ai-meeting-briefing.test.tsapps/web/utils/meeting-briefs/gather-context.tsapps/web/utils/meeting-briefs/process.tsapps/web/utils/ai/meeting-briefs/generate-briefing.ts
apps/web/**/*.{ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/project-structure.mdc)
Import specific lodash functions rather than entire lodash library to minimize bundle size (e.g.,
import groupBy from 'lodash/groupBy')
apps/web/**/*.{ts,tsx}: Use TypeScript with strict null checks
Do not export types/interfaces that are only used within the same file. Export later if needed
Files:
apps/web/__tests__/ai-meeting-briefing.test.tsapps/web/utils/meeting-briefs/gather-context.tsapps/web/utils/meeting-briefs/process.tsapps/web/utils/ai/meeting-briefs/generate-briefing.ts
**/*.ts
📄 CodeRabbit inference engine (.cursor/rules/security.mdc)
**/*.ts: ALL database queries MUST be scoped to the authenticated user/account by including user/account filtering in WHERE clauses to prevent unauthorized data access
Always validate that resources belong to the authenticated user before performing operations, using ownership checks in WHERE clauses or relationships
Always validate all input parameters for type, format, and length before using them in database queries
Use SafeError for error responses to prevent information disclosure. Generic error messages should not reveal internal IDs, logic, or resource ownership details
Only return necessary fields in API responses using Prisma'sselectoption. Never expose sensitive data such as password hashes, private keys, or system flags
Prevent Insecure Direct Object References (IDOR) by validating resource ownership before operations. AllfindUnique/findFirstcalls MUST include ownership filters
Prevent mass assignment vulnerabilities by explicitly whitelisting allowed fields in update operations instead of accepting all user-provided data
Prevent privilege escalation by never allowing users to modify system fields, ownership fields, or admin-only attributes through user input
AllfindManyqueries MUST be scoped to the user's data by including appropriate WHERE filters to prevent returning data from other users
Use Prisma relationships for access control by leveraging nested where clauses (e.g.,emailAccount: { id: emailAccountId }) to validate ownership
Files:
apps/web/__tests__/ai-meeting-briefing.test.tsapps/web/utils/meeting-briefs/gather-context.tsapps/web/utils/meeting-briefs/process.tsapps/web/utils/ai/meeting-briefs/generate-briefing.ts
**/*.{tsx,ts}
📄 CodeRabbit inference engine (.cursor/rules/ui-components.mdc)
**/*.{tsx,ts}: Use Shadcn UI and Tailwind for components and styling
Usenext/imagepackage for images
For API GET requests to server, use theswrpackage with hooks likeuseSWRto fetch data
For text inputs, use theInputcomponent withregisterPropsfor form integration and error handling
Files:
apps/web/__tests__/ai-meeting-briefing.test.tsapps/web/utils/meeting-briefs/gather-context.tsapps/web/utils/meeting-briefs/process.tsapps/web/utils/ai/meeting-briefs/generate-briefing.ts
**/*.{tsx,ts,css}
📄 CodeRabbit inference engine (.cursor/rules/ui-components.mdc)
Implement responsive design with Tailwind CSS using a mobile-first approach
Files:
apps/web/__tests__/ai-meeting-briefing.test.tsapps/web/utils/meeting-briefs/gather-context.tsapps/web/utils/meeting-briefs/process.tsapps/web/utils/ai/meeting-briefs/generate-briefing.ts
**/*.{js,jsx,ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/ultracite.mdc)
**/*.{js,jsx,ts,tsx}: Don't useaccessKeyattribute on any HTML element
Don't setaria-hidden="true"on focusable elements
Don't add ARIA roles, states, and properties to elements that don't support them
Don't use distracting elements like<marquee>or<blink>
Only use thescopeprop on<th>elements
Don't assign non-interactive ARIA roles to interactive HTML elements
Make sure label elements have text content and are associated with an input
Don't assign interactive ARIA roles to non-interactive HTML elements
Don't assigntabIndexto non-interactive HTML elements
Don't use positive integers fortabIndexproperty
Don't include "image", "picture", or "photo" in img alt prop
Don't use explicit role property that's the same as the implicit/default role
Make static elements with click handlers use a valid role attribute
Always include atitleelement for SVG elements
Give all elements requiring alt text meaningful information for screen readers
Make sure anchors have content that's accessible to screen readers
AssigntabIndexto non-interactive HTML elements witharia-activedescendant
Include all required ARIA attributes for elements with ARIA roles
Make sure ARIA properties are valid for the element's supported roles
Always include atypeattribute for button elements
Make elements with interactive roles and handlers focusable
Give heading elements content that's accessible to screen readers (not hidden witharia-hidden)
Always include alangattribute on the html element
Always include atitleattribute for iframe elements
AccompanyonClickwith at least one of:onKeyUp,onKeyDown, oronKeyPress
AccompanyonMouseOver/onMouseOutwithonFocus/onBlur
Include caption tracks for audio and video elements
Use semantic elements instead of role attributes in JSX
Make sure all anchors are valid and navigable
Ensure all ARIA properties (aria-*) are valid
Use valid, non-abstract ARIA roles for elements with ARIA roles
Use valid AR...
Files:
apps/web/__tests__/ai-meeting-briefing.test.tsapps/web/utils/meeting-briefs/gather-context.tsapps/web/utils/meeting-briefs/process.tsapps/web/utils/ai/meeting-briefs/generate-briefing.ts
**/*.{test,spec}.{js,jsx,ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/ultracite.mdc)
**/*.{test,spec}.{js,jsx,ts,tsx}: Don't nest describe() blocks too deeply in test files
Don't use callbacks in asynchronous tests and hooks
Don't have duplicate hooks in describe blocks
Don't use export or module.exports in test files
Don't use focused tests
Make sure the assertion function, like expect, is placed inside an it() function call
Don't use disabled tests
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
!(pages/_document).{jsx,tsx}
📄 CodeRabbit inference engine (.cursor/rules/ultracite.mdc)
Don't use the next/head module in pages/_document.js on Next.js projects
Files:
apps/web/__tests__/ai-meeting-briefing.test.tsapps/web/utils/meeting-briefs/gather-context.tsapps/web/utils/meeting-briefs/process.tsapps/web/utils/ai/meeting-briefs/generate-briefing.ts
**/*.{js,ts,jsx,tsx}
📄 CodeRabbit inference engine (.cursor/rules/utilities.mdc)
**/*.{js,ts,jsx,tsx}: Use lodash utilities for common operations (arrays, objects, strings)
Import specific lodash functions to minimize bundle size (e.g.,import groupBy from 'lodash/groupBy')
Files:
apps/web/__tests__/ai-meeting-briefing.test.tsapps/web/utils/meeting-briefs/gather-context.tsapps/web/utils/meeting-briefs/process.tsapps/web/utils/ai/meeting-briefs/generate-briefing.ts
**/{scripts,tests,__tests__}/**/*.{ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/logging.mdc)
Use createScopedLogger only for code that doesn't run within a middleware chain, such as standalone scripts or tests
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
apps/web/**/*.{ts,tsx,js,jsx}
📄 CodeRabbit inference engine (apps/web/CLAUDE.md)
apps/web/**/*.{ts,tsx,js,jsx}: Use@/path aliases for imports from project root
Prefer self-documenting code over comments; use descriptive variable and function names instead of explaining intent with comments
Add helper functions to the bottom of files, not the top
All imports go at the top of files, no mid-file dynamic imports
Files:
apps/web/__tests__/ai-meeting-briefing.test.tsapps/web/utils/meeting-briefs/gather-context.tsapps/web/utils/meeting-briefs/process.tsapps/web/utils/ai/meeting-briefs/generate-briefing.ts
apps/web/**/*.{ts,tsx,js,jsx,json,css}
📄 CodeRabbit inference engine (apps/web/CLAUDE.md)
Format code with Prettier
Files:
apps/web/__tests__/ai-meeting-briefing.test.tsapps/web/utils/meeting-briefs/gather-context.tsapps/web/utils/meeting-briefs/process.tsapps/web/utils/ai/meeting-briefs/generate-briefing.ts
apps/web/**/*.test.{ts,tsx}
📄 CodeRabbit inference engine (apps/web/CLAUDE.md)
Co-locate test files next to source files (e.g.,
utils/example.test.ts). Only E2E and AI tests go in__tests__/
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
apps/web/**/*.{example,ts,json}
📄 CodeRabbit inference engine (apps/web/CLAUDE.md)
Add environment variables to
.env.example,env.ts, andturbo.json
Files:
apps/web/__tests__/ai-meeting-briefing.test.tsapps/web/utils/meeting-briefs/gather-context.tsapps/web/utils/meeting-briefs/process.tsapps/web/utils/ai/meeting-briefs/generate-briefing.ts
**/*.test.{js,jsx,ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/notes.mdc)
Co-locate test files next to source files (e.g.,
utils/example.test.ts). Only E2E and AI tests go in__tests__/
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
**/*.test.{ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/testing.mdc)
**/*.test.{ts,tsx}: Usevitestas the testing framework
Colocate test files next to the tested file with.test.tsor.test.tsxnaming convention (e.g.,dir/format.tsanddir/format.test.ts)
Mockserver-onlyusingvi.mock("server-only", () => ({}))
Mock Prisma usingvi.mock("@/utils/prisma")and the provided mock from@/utils/__mocks__/prisma
Use test helper functionsgetEmail,getEmailAccount, andgetRulefrom@/__tests__/helpersfor creating mock data
Clear all mocks between tests usingbeforeEach(() => { vi.clearAllMocks(); })
Use descriptive test names that clearly indicate what is being tested
Do not mock the Logger in tests
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
**/__tests__/**/*.{ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/testing.mdc)
Place AI tests in the
__tests__directory and do not run them by default as they use a real LLM
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
**/{utils,helpers,lib}/**/*.{ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/logging.mdc)
Logger should be passed as a parameter to helper functions instead of creating their own logger instances
Files:
apps/web/utils/meeting-briefs/gather-context.tsapps/web/utils/meeting-briefs/process.tsapps/web/utils/ai/meeting-briefs/generate-briefing.ts
apps/web/utils/ai/**/*.ts
📄 CodeRabbit inference engine (.cursor/rules/llm.mdc)
apps/web/utils/ai/**/*.ts: LLM feature functions must import fromzodfor schema validation, usecreateScopedLoggerfrom@/utils/logger,chatCompletionObjectandcreateGenerateObjectfrom@/utils/llms, and importEmailAccountWithAItype from@/utils/llms/types
LLM feature functions must follow a standard structure: accept options withinputDataandemailAccountparameters, implement input validation with early returns, define separate system and user prompts, create a Zod schema for response validation, and usecreateGenerateObjectto execute the LLM call
System prompts must define the LLM's role and task specifications
User prompts must contain the actual data and context, and should be kept separate from system prompts
Always define a Zod schema for LLM response validation and make 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, and include relevant context in log messages
Implement early returns for invalid LLM inputs, use proper error types and logging, implement fallbacks for AI failures, and add retry logic for transient failures usingwithRetry
Use XML-like tags to structure data in prompts, remove excessive whitespace and truncate long inputs, and format data consistently across similar LLM functions
Use TypeScript types for all LLM function parameters and return values, and define clear interfaces for complex input/output structures
Keep related AI functions in the same file or directory, extract common patterns into utility functions, and document complex AI logic with clear comments
Files:
apps/web/utils/ai/meeting-briefs/generate-briefing.ts
🧠 Learnings (17)
📚 Learning: 2026-01-01T10:42:29.767Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/testing.mdc:0-0
Timestamp: 2026-01-01T10:42:29.767Z
Learning: Applies to **/__tests__/**/*.{ts,tsx} : Place AI tests in the `__tests__` directory and do not run them by default as they use a real LLM
Applied to files:
apps/web/__tests__/ai-meeting-briefing.test.ts
📚 Learning: 2025-11-25T14:37:56.430Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm-test.mdc:0-0
Timestamp: 2025-11-25T14:37:56.430Z
Learning: Applies to apps/web/__tests__/**/*.test.ts : Use `describe.runIf(isAiTest)` with environment variable `RUN_AI_TESTS === "true"` to conditionally run LLM tests
Applied to files:
apps/web/__tests__/ai-meeting-briefing.test.ts
📚 Learning: 2025-11-25T14:38:07.606Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-11-25T14:38:07.606Z
Learning: Applies to apps/web/utils/ai/**/*.ts : Keep related AI functions in the same file or directory, extract common patterns into utility functions, and document complex AI logic with clear comments
Applied to files:
apps/web/__tests__/ai-meeting-briefing.test.tsapps/web/utils/meeting-briefs/gather-context.ts
📚 Learning: 2025-11-25T14:38:07.606Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-11-25T14:38:07.606Z
Learning: Applies to apps/web/utils/ai/**/*.ts : Implement early returns for invalid LLM inputs, use proper error types and logging, implement fallbacks for AI failures, and add retry logic for transient failures using `withRetry`
Applied to files:
apps/web/__tests__/ai-meeting-briefing.test.ts
📚 Learning: 2025-12-21T12:21:37.794Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: apps/web/CLAUDE.md:0-0
Timestamp: 2025-12-21T12:21:37.794Z
Learning: Applies to apps/web/**/*.test.{ts,tsx} : Co-locate test files next to source files (e.g., `utils/example.test.ts`). Only E2E and AI tests go in `__tests__/`
Applied to files:
apps/web/__tests__/ai-meeting-briefing.test.ts
📚 Learning: 2025-11-25T14:38:07.606Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-11-25T14:38:07.606Z
Learning: Applies to apps/web/utils/ai/**/*.ts : Use XML-like tags to structure data in prompts, remove excessive whitespace and truncate long inputs, and format data consistently across similar LLM functions
Applied to files:
apps/web/__tests__/ai-meeting-briefing.test.tsapps/web/utils/ai/meeting-briefs/generate-briefing.ts
📚 Learning: 2025-11-25T14:38:07.606Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-11-25T14:38:07.606Z
Learning: Applies to apps/web/utils/ai/**/*.ts : LLM feature functions must import from `zod` for schema validation, use `createScopedLogger` from `@/utils/logger`, `chatCompletionObject` and `createGenerateObject` from `@/utils/llms`, and import `EmailAccountWithAI` type from `@/utils/llms/types`
Applied to files:
apps/web/__tests__/ai-meeting-briefing.test.tsapps/web/utils/meeting-briefs/gather-context.tsapps/web/utils/meeting-briefs/process.tsapps/web/utils/ai/meeting-briefs/generate-briefing.ts
📚 Learning: 2025-11-25T14:37:56.430Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm-test.mdc:0-0
Timestamp: 2025-11-25T14:37:56.430Z
Learning: Applies to apps/web/__tests__/**/*.test.ts : Use vitest imports (`describe`, `expect`, `test`, `vi`, `beforeEach`) in LLM test files
Applied to files:
apps/web/__tests__/ai-meeting-briefing.test.ts
📚 Learning: 2026-01-01T10:42:29.767Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/testing.mdc:0-0
Timestamp: 2026-01-01T10:42:29.767Z
Learning: Applies to **/*.test.{ts,tsx} : Use descriptive test names that clearly indicate what is being tested
Applied to files:
apps/web/__tests__/ai-meeting-briefing.test.ts
📚 Learning: 2025-11-25T14:37:56.430Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm-test.mdc:0-0
Timestamp: 2025-11-25T14:37:56.430Z
Learning: Applies to apps/web/__tests__/**/*.test.ts : Use `console.debug()` for outputting generated LLM content in tests, e.g., `console.debug("Generated content:\n", result.content);`
Applied to files:
apps/web/__tests__/ai-meeting-briefing.test.ts
📚 Learning: 2025-11-25T14:37:22.660Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/gmail-api.mdc:0-0
Timestamp: 2025-11-25T14:37:22.660Z
Learning: Applies to **/*.{ts,tsx} : Use wrapper functions for Gmail thread operations from @/utils/gmail/thread.ts instead of direct API calls
Applied to files:
apps/web/utils/meeting-briefs/gather-context.ts
📚 Learning: 2025-11-25T14:38:07.606Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-11-25T14:38:07.606Z
Learning: Applies to apps/web/utils/ai/**/*.ts : Use descriptive scoped loggers for each LLM feature, log inputs and outputs with appropriate log levels, and include relevant context in log messages
Applied to files:
apps/web/utils/meeting-briefs/process.ts
📚 Learning: 2025-12-18T16:37:47.972Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/logging.mdc:0-0
Timestamp: 2025-12-18T16:37:47.972Z
Learning: Applies to **/{utils,helpers,lib}/**/*.{ts,tsx} : Logger should be passed as a parameter to helper functions instead of creating their own logger instances
Applied to files:
apps/web/utils/meeting-briefs/process.ts
📚 Learning: 2025-11-25T14:38:07.606Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-11-25T14:38:07.606Z
Learning: Applies to apps/web/utils/ai/**/*.ts : LLM feature functions must follow a standard structure: accept options with `inputData` and `emailAccount` parameters, implement input validation with early returns, define separate system and user prompts, create a Zod schema for response validation, and use `createGenerateObject` to execute the LLM call
Applied to files:
apps/web/utils/ai/meeting-briefs/generate-briefing.ts
📚 Learning: 2025-11-25T14:38:07.606Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-11-25T14:38:07.606Z
Learning: Applies to apps/web/utils/ai/**/*.ts : System prompts must define the LLM's role and task specifications
Applied to files:
apps/web/utils/ai/meeting-briefs/generate-briefing.ts
📚 Learning: 2025-11-25T14:38:07.606Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-11-25T14:38:07.606Z
Learning: Applies to apps/web/utils/ai/**/*.ts : Always define a Zod schema for LLM response validation and make schemas as specific as possible to guide the LLM output
Applied to files:
apps/web/utils/ai/meeting-briefs/generate-briefing.ts
📚 Learning: 2025-11-25T14:38:07.606Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-11-25T14:38:07.606Z
Learning: Applies to apps/web/utils/ai/**/*.ts : User prompts must contain the actual data and context, and should be kept separate from system prompts
Applied to files:
apps/web/utils/ai/meeting-briefs/generate-briefing.ts
🧬 Code graph analysis (1)
apps/web/__tests__/ai-meeting-briefing.test.ts (4)
apps/web/utils/logger.ts (1)
createScopedLogger(18-82)apps/web/utils/meeting-briefs/gather-context.ts (2)
CalendarEvent(19-19)MeetingBriefingData(26-31)apps/web/utils/ai/meeting-briefs/generate-briefing.ts (4)
buildPrompt(132-167)formatMeetingForContext(271-282)aiGenerateMeetingBriefing(53-129)BriefingContent(28-28)apps/web/__tests__/helpers.ts (2)
getMockMessage(139-179)getEmailAccount(26-46)
⏰ 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). (3)
- GitHub Check: Baz Reviewer
- GitHub Check: cubic · AI code reviewer
- GitHub Check: test
🔇 Additional comments (7)
apps/web/utils/meeting-briefs/process.ts (1)
203-207: LGTM! Logger parameter correctly passed.The addition of the logger parameter to
aiGenerateMeetingBriefingcorrectly follows the guideline that helper functions should receive the logger as a parameter rather than creating their own instances.Based on learnings, logger should be passed as a parameter to helper functions.
apps/web/utils/meeting-briefs/gather-context.ts (1)
88-96: LGTM! Clean simplification of data structure.The removal of the
aiResearchfield from the external guests mapping aligns with the PR's refactoring goal to move guest research into the AI generation phase as a tool-based workflow.apps/web/__tests__/ai-meeting-briefing.test.ts (1)
1-21: Well-structured LLM test file.The test setup correctly follows LLM testing guidelines:
- Uses
describe.runIf(isAiTest)with environment variable check- Mocks
server-onlymodule- Uses proper vitest imports
- Creates a scoped logger for tests
- Sets appropriate timeout for agentic flow (60 seconds)
As per coding guidelines, LLM tests should be conditionally run and properly configured.
apps/web/utils/ai/meeting-briefs/generate-briefing.ts (4)
53-64: LGTM! Proper function signature and early return.The function correctly:
- Accepts
loggeras a parameter (following the guideline that helpers should receive logger rather than create their own)- Implements early return when there are no external guests
- Accepts
briefingDataandemailAccountparameters as per LLM function structureBased on learnings, logger should be passed as a parameter to helper functions.
30-51: Well-structured system prompt with clear workflow.The
AGENTIC_SYSTEM_PROMPTproperly:
- Defines the AI's role and task specifications
- Provides clear workflow steps
- Documents available tools
- Sets concise briefing guidelines
- Emphasizes the requirement to call
finalizeBriefingThis follows LLM guidelines for separating system prompts (role/task) from user prompts (data/context).
As per coding guidelines, system prompts must define the LLM's role and task specifications.
123-128: Good fallback handling for missing result.The code properly handles the edge case where
finalizeBriefingis never called by:
- Checking if result is null
- Logging a warning
- Returning an empty briefing structure
This prevents the function from returning
nullor throwing an error.As per coding guidelines, implement fallbacks for AI failures.
150-167: Clean prompt construction with XML tags.The
buildPromptfunction properly:
- Uses XML-like tags to structure data (
<upcoming_meeting>,<guest_context>)- Separates meeting details from guest context
- Provides clear instructions for the AI workflow
- Keeps the user prompt focused on data and context
This follows the guideline to use XML-like tags for structuring data in prompts and to keep user prompts separate from system prompts.
As per coding guidelines, use XML-like tags to structure data in prompts.
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
apps/web/__tests__/ai-meeting-briefing.test.ts (1)
23-50: Consider moving helper functions to the bottom of the file.For consistency with project guidelines, helper functions should be placed at the bottom of files. While test data builders are commonly placed at the top in test files, the
prettyPrintBriefinghelper at line 474 follows the guideline. Consider movinggetCalendarEventandgetMeetingBriefingDatato the bottom as well for consistency.As per coding guidelines, helper functions should be at the bottom of files.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
apps/web/__tests__/ai-meeting-briefing.test.ts
🧰 Additional context used
📓 Path-based instructions (20)
**/*.{ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/data-fetching.mdc)
**/*.{ts,tsx}: For API GET requests to server, use theswrpackage
Useresult?.serverErrorwithtoastErrorfrom@/components/Toastfor error handling in async operations
**/*.{ts,tsx}: Use wrapper functions for Gmail message operations (get, list, batch, etc.) from @/utils/gmail/message.ts instead of direct API calls
Use wrapper functions for Gmail thread operations from @/utils/gmail/thread.ts instead of direct API calls
Use wrapper functions for Gmail label operations from @/utils/gmail/label.ts instead of direct API calls
**/*.{ts,tsx}: For early access feature flags, create hooks using the naming conventionuse[FeatureName]Enabledthat return a boolean fromuseFeatureFlagEnabled("flag-key")
For A/B test variant flags, create hooks using the naming conventionuse[FeatureName]Variantthat define variant types, useuseFeatureFlagVariantKey()with type casting, and provide a default "control" fallback
Use kebab-case for PostHog feature flag keys (e.g.,inbox-cleaner,pricing-options-2)
Always define types for A/B test variant flags (e.g.,type PricingVariant = "control" | "variant-a" | "variant-b") and provide type safety through type casting
**/*.{ts,tsx}: Don't use primitive type aliases or misleading types
Don't use empty type parameters in type aliases and interfaces
Don't use this and super in static contexts
Don't use any or unknown as type constraints
Don't use the TypeScript directive @ts-ignore
Don't use TypeScript enums
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 TypeScript namespaces
Don't use non-null assertions with the!postfix operator
Don't use parameter properties in class constructors
Don't use user-defined types
Useas constinstead of literal types and type annotations
Use eitherT[]orArray<T>consistently
Initialize each enum member value explicitly
Useexport typefor types
Use `impo...
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
apps/web/__tests__/**/*.test.ts
📄 CodeRabbit inference engine (.cursor/rules/llm-test.mdc)
apps/web/__tests__/**/*.test.ts: Place all LLM-related tests inapps/web/__tests__/directory
Use vitest imports (describe,expect,test,vi,beforeEach) in LLM test files
Mock 'server-only' module with empty object in LLM test files:vi.mock("server-only", () => ({}))
Set timeout constantconst TIMEOUT = 15_000;for LLM tests
Usedescribe.runIf(isAiTest)with environment variableRUN_AI_TESTS === "true"to conditionally run LLM tests
Useconsole.debug()for outputting generated LLM content in tests, e.g.,console.debug("Generated content:\n", result.content);
Prefer using existing helpers from@/__tests__/helpers.ts(getEmailAccount,getEmail,getRule,getMockMessage,getMockExecutedRule) instead of creating custom test data helpers
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
apps/web/{utils/ai,utils/llms,__tests__}/**/*.ts
📄 CodeRabbit inference engine (.cursor/rules/llm.mdc)
LLM-related code must be organized in specific directories:
apps/web/utils/ai/for main implementations,apps/web/utils/llms/for core utilities and configurations, andapps/web/__tests__/for LLM-specific tests
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
**/*.{ts,tsx,js,jsx}
📄 CodeRabbit inference engine (.cursor/rules/prisma-enum-imports.mdc)
Always import Prisma enums from
@/generated/prisma/enumsinstead of@/generated/prisma/clientto avoid Next.js bundling errors in client componentsImport Prisma using the project's centralized utility:
import prisma from '@/utils/prisma'
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
apps/web/**/*.{ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/project-structure.mdc)
Import specific lodash functions rather than entire lodash library to minimize bundle size (e.g.,
import groupBy from 'lodash/groupBy')
apps/web/**/*.{ts,tsx}: Use TypeScript with strict null checks
Do not export types/interfaces that are only used within the same file. Export later if needed
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
**/*.ts
📄 CodeRabbit inference engine (.cursor/rules/security.mdc)
**/*.ts: ALL database queries MUST be scoped to the authenticated user/account by including user/account filtering in WHERE clauses to prevent unauthorized data access
Always validate that resources belong to the authenticated user before performing operations, using ownership checks in WHERE clauses or relationships
Always validate all input parameters for type, format, and length before using them in database queries
Use SafeError for error responses to prevent information disclosure. Generic error messages should not reveal internal IDs, logic, or resource ownership details
Only return necessary fields in API responses using Prisma'sselectoption. Never expose sensitive data such as password hashes, private keys, or system flags
Prevent Insecure Direct Object References (IDOR) by validating resource ownership before operations. AllfindUnique/findFirstcalls MUST include ownership filters
Prevent mass assignment vulnerabilities by explicitly whitelisting allowed fields in update operations instead of accepting all user-provided data
Prevent privilege escalation by never allowing users to modify system fields, ownership fields, or admin-only attributes through user input
AllfindManyqueries MUST be scoped to the user's data by including appropriate WHERE filters to prevent returning data from other users
Use Prisma relationships for access control by leveraging nested where clauses (e.g.,emailAccount: { id: emailAccountId }) to validate ownership
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
**/*.{tsx,ts}
📄 CodeRabbit inference engine (.cursor/rules/ui-components.mdc)
**/*.{tsx,ts}: Use Shadcn UI and Tailwind for components and styling
Usenext/imagepackage for images
For API GET requests to server, use theswrpackage with hooks likeuseSWRto fetch data
For text inputs, use theInputcomponent withregisterPropsfor form integration and error handling
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
**/*.{tsx,ts,css}
📄 CodeRabbit inference engine (.cursor/rules/ui-components.mdc)
Implement responsive design with Tailwind CSS using a mobile-first approach
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
**/*.{js,jsx,ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/ultracite.mdc)
**/*.{js,jsx,ts,tsx}: Don't useaccessKeyattribute on any HTML element
Don't setaria-hidden="true"on focusable elements
Don't add ARIA roles, states, and properties to elements that don't support them
Don't use distracting elements like<marquee>or<blink>
Only use thescopeprop on<th>elements
Don't assign non-interactive ARIA roles to interactive HTML elements
Make sure label elements have text content and are associated with an input
Don't assign interactive ARIA roles to non-interactive HTML elements
Don't assigntabIndexto non-interactive HTML elements
Don't use positive integers fortabIndexproperty
Don't include "image", "picture", or "photo" in img alt prop
Don't use explicit role property that's the same as the implicit/default role
Make static elements with click handlers use a valid role attribute
Always include atitleelement for SVG elements
Give all elements requiring alt text meaningful information for screen readers
Make sure anchors have content that's accessible to screen readers
AssigntabIndexto non-interactive HTML elements witharia-activedescendant
Include all required ARIA attributes for elements with ARIA roles
Make sure ARIA properties are valid for the element's supported roles
Always include atypeattribute for button elements
Make elements with interactive roles and handlers focusable
Give heading elements content that's accessible to screen readers (not hidden witharia-hidden)
Always include alangattribute on the html element
Always include atitleattribute for iframe elements
AccompanyonClickwith at least one of:onKeyUp,onKeyDown, oronKeyPress
AccompanyonMouseOver/onMouseOutwithonFocus/onBlur
Include caption tracks for audio and video elements
Use semantic elements instead of role attributes in JSX
Make sure all anchors are valid and navigable
Ensure all ARIA properties (aria-*) are valid
Use valid, non-abstract ARIA roles for elements with ARIA roles
Use valid AR...
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
**/*.{test,spec}.{js,jsx,ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/ultracite.mdc)
**/*.{test,spec}.{js,jsx,ts,tsx}: Don't nest describe() blocks too deeply in test files
Don't use callbacks in asynchronous tests and hooks
Don't have duplicate hooks in describe blocks
Don't use export or module.exports in test files
Don't use focused tests
Make sure the assertion function, like expect, is placed inside an it() function call
Don't use disabled tests
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
!(pages/_document).{jsx,tsx}
📄 CodeRabbit inference engine (.cursor/rules/ultracite.mdc)
Don't use the next/head module in pages/_document.js on Next.js projects
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
**/*.{js,ts,jsx,tsx}
📄 CodeRabbit inference engine (.cursor/rules/utilities.mdc)
**/*.{js,ts,jsx,tsx}: Use lodash utilities for common operations (arrays, objects, strings)
Import specific lodash functions to minimize bundle size (e.g.,import groupBy from 'lodash/groupBy')
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
**/{scripts,tests,__tests__}/**/*.{ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/logging.mdc)
Use createScopedLogger only for code that doesn't run within a middleware chain, such as standalone scripts or tests
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
apps/web/**/*.{ts,tsx,js,jsx}
📄 CodeRabbit inference engine (apps/web/CLAUDE.md)
apps/web/**/*.{ts,tsx,js,jsx}: Use@/path aliases for imports from project root
Prefer self-documenting code over comments; use descriptive variable and function names instead of explaining intent with comments
Add helper functions to the bottom of files, not the top
All imports go at the top of files, no mid-file dynamic imports
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
apps/web/**/*.{ts,tsx,js,jsx,json,css}
📄 CodeRabbit inference engine (apps/web/CLAUDE.md)
Format code with Prettier
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
apps/web/**/*.test.{ts,tsx}
📄 CodeRabbit inference engine (apps/web/CLAUDE.md)
Co-locate test files next to source files (e.g.,
utils/example.test.ts). Only E2E and AI tests go in__tests__/
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
apps/web/**/*.{example,ts,json}
📄 CodeRabbit inference engine (apps/web/CLAUDE.md)
Add environment variables to
.env.example,env.ts, andturbo.json
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
**/*.test.{js,jsx,ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/notes.mdc)
Co-locate test files next to source files (e.g.,
utils/example.test.ts). Only E2E and AI tests go in__tests__/
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
**/*.test.{ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/testing.mdc)
**/*.test.{ts,tsx}: Usevitestas the testing framework
Colocate test files next to the tested file with.test.tsor.test.tsxnaming convention (e.g.,dir/format.tsanddir/format.test.ts)
Mockserver-onlyusingvi.mock("server-only", () => ({}))
Mock Prisma usingvi.mock("@/utils/prisma")and the provided mock from@/utils/__mocks__/prisma
Use test helper functionsgetEmail,getEmailAccount, andgetRulefrom@/__tests__/helpersfor creating mock data
Clear all mocks between tests usingbeforeEach(() => { vi.clearAllMocks(); })
Use descriptive test names that clearly indicate what is being tested
Do not mock the Logger in tests
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
**/__tests__/**/*.{ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/testing.mdc)
Place AI tests in the
__tests__directory and do not run them by default as they use a real LLM
Files:
apps/web/__tests__/ai-meeting-briefing.test.ts
🧠 Learnings (15)
📚 Learning: 2026-01-01T10:42:29.767Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/testing.mdc:0-0
Timestamp: 2026-01-01T10:42:29.767Z
Learning: Applies to **/__tests__/**/*.{ts,tsx} : Place AI tests in the `__tests__` directory and do not run them by default as they use a real LLM
Applied to files:
apps/web/__tests__/ai-meeting-briefing.test.ts
📚 Learning: 2025-11-25T14:37:56.430Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm-test.mdc:0-0
Timestamp: 2025-11-25T14:37:56.430Z
Learning: Applies to apps/web/__tests__/**/*.test.ts : Use `describe.runIf(isAiTest)` with environment variable `RUN_AI_TESTS === "true"` to conditionally run LLM tests
Applied to files:
apps/web/__tests__/ai-meeting-briefing.test.ts
📚 Learning: 2025-11-25T14:38:07.606Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-11-25T14:38:07.606Z
Learning: Applies to apps/web/utils/ai/**/*.ts : Keep related AI functions in the same file or directory, extract common patterns into utility functions, and document complex AI logic with clear comments
Applied to files:
apps/web/__tests__/ai-meeting-briefing.test.ts
📚 Learning: 2025-12-21T12:21:37.794Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: apps/web/CLAUDE.md:0-0
Timestamp: 2025-12-21T12:21:37.794Z
Learning: Applies to apps/web/**/*.test.{ts,tsx} : Co-locate test files next to source files (e.g., `utils/example.test.ts`). Only E2E and AI tests go in `__tests__/`
Applied to files:
apps/web/__tests__/ai-meeting-briefing.test.ts
📚 Learning: 2025-11-25T14:38:07.606Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-11-25T14:38:07.606Z
Learning: Applies to apps/web/utils/ai/**/*.ts : Implement early returns for invalid LLM inputs, use proper error types and logging, implement fallbacks for AI failures, and add retry logic for transient failures using `withRetry`
Applied to files:
apps/web/__tests__/ai-meeting-briefing.test.ts
📚 Learning: 2026-01-01T10:42:29.767Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/testing.mdc:0-0
Timestamp: 2026-01-01T10:42:29.767Z
Learning: Applies to **/*.test.{ts,tsx} : Use descriptive test names that clearly indicate what is being tested
Applied to files:
apps/web/__tests__/ai-meeting-briefing.test.ts
📚 Learning: 2025-11-25T14:38:07.606Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-11-25T14:38:07.606Z
Learning: Applies to apps/web/utils/ai/**/*.ts : Use XML-like tags to structure data in prompts, remove excessive whitespace and truncate long inputs, and format data consistently across similar LLM functions
Applied to files:
apps/web/__tests__/ai-meeting-briefing.test.ts
📚 Learning: 2025-11-25T14:38:07.606Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-11-25T14:38:07.606Z
Learning: Applies to apps/web/utils/ai/**/*.ts : LLM feature functions must import from `zod` for schema validation, use `createScopedLogger` from `@/utils/logger`, `chatCompletionObject` and `createGenerateObject` from `@/utils/llms`, and import `EmailAccountWithAI` type from `@/utils/llms/types`
Applied to files:
apps/web/__tests__/ai-meeting-briefing.test.ts
📚 Learning: 2025-11-25T14:39:23.326Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/security.mdc:0-0
Timestamp: 2025-11-25T14:39:23.326Z
Learning: Applies to **/*.test.ts : Include security tests in test suites to verify: authentication is required, IDOR protection works (other users cannot access resources), parameter validation rejects invalid inputs, and error messages don't leak information
Applied to files:
apps/web/__tests__/ai-meeting-briefing.test.ts
📚 Learning: 2025-11-25T14:37:56.430Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm-test.mdc:0-0
Timestamp: 2025-11-25T14:37:56.430Z
Learning: Applies to apps/web/__tests__/**/*.test.ts : Use vitest imports (`describe`, `expect`, `test`, `vi`, `beforeEach`) in LLM test files
Applied to files:
apps/web/__tests__/ai-meeting-briefing.test.ts
📚 Learning: 2025-11-25T14:38:07.606Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-11-25T14:38:07.606Z
Learning: Applies to apps/web/utils/ai/**/*.ts : User prompts must contain the actual data and context, and should be kept separate from system prompts
Applied to files:
apps/web/__tests__/ai-meeting-briefing.test.ts
📚 Learning: 2025-11-25T14:38:07.606Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-11-25T14:38:07.606Z
Learning: Applies to apps/web/utils/ai/**/*.ts : System prompts must define the LLM's role and task specifications
Applied to files:
apps/web/__tests__/ai-meeting-briefing.test.ts
📚 Learning: 2025-11-25T14:37:56.430Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm-test.mdc:0-0
Timestamp: 2025-11-25T14:37:56.430Z
Learning: Applies to apps/web/__tests__/**/*.test.ts : Use `console.debug()` for outputting generated LLM content in tests, e.g., `console.debug("Generated content:\n", result.content);`
Applied to files:
apps/web/__tests__/ai-meeting-briefing.test.ts
📚 Learning: 2025-11-25T14:38:07.606Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-11-25T14:38:07.606Z
Learning: Applies to apps/web/utils/ai/**/*.ts : Use descriptive scoped loggers for each LLM feature, log inputs and outputs with appropriate log levels, and include relevant context in log messages
Applied to files:
apps/web/__tests__/ai-meeting-briefing.test.ts
📚 Learning: 2025-11-25T14:38:07.606Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-11-25T14:38:07.606Z
Learning: Applies to apps/web/utils/ai/**/*.ts : LLM feature functions must follow a standard structure: accept options with `inputData` and `emailAccount` parameters, implement input validation with early returns, define separate system and user prompts, create a Zod schema for response validation, and use `createGenerateObject` to execute the LLM call
Applied to files:
apps/web/__tests__/ai-meeting-briefing.test.ts
🧬 Code graph analysis (1)
apps/web/__tests__/ai-meeting-briefing.test.ts (3)
apps/web/utils/meeting-briefs/gather-context.ts (2)
CalendarEvent(19-19)MeetingBriefingData(26-31)apps/web/utils/ai/meeting-briefs/generate-briefing.ts (4)
buildPrompt(132-167)formatMeetingForContext(271-282)aiGenerateMeetingBriefing(53-129)BriefingContent(28-28)apps/web/__tests__/helpers.ts (2)
getMockMessage(139-179)getEmailAccount(26-46)
⏰ 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: Baz Reviewer
- GitHub Check: test
- GitHub Check: Analyze (javascript-typescript)
- GitHub Check: Macroscope - Correctness Check
🔇 Additional comments (2)
apps/web/__tests__/ai-meeting-briefing.test.ts (2)
21-21: Verify that 60-second timeout is necessary for agentic tests.The coding guideline specifies
const TIMEOUT = 15_000;for LLM tests, but this test uses 60 seconds (4x longer). While the comment mentions "agentic flow with research," confirm that this extended timeout is necessary and not masking performance issues.As per coding guidelines, the standard timeout for LLM tests is 15 seconds.
52-472: Excellent test coverage and implementation!The test suite comprehensively covers the meeting briefing functionality with well-structured unit tests and AI integration tests:
- Unit tests validate
buildPromptandformatMeetingForContextwith various scenarios (guest context, email history, past meetings, multiple guests)- AI tests are properly gated with
describe.runIf(isAiTest)and exercise realistic end-to-end scenarios- Test names are clear and descriptive
- Proper use of existing helpers from
@/__tests__/helpers- Logger correctly passed to
aiGenerateMeetingBriefing- Assertions are appropriate for both deterministic unit tests and non-deterministic AI outputs
![baz-reviewer[bot]](https://avatars.githubusercontent.com/in/933528?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (3)
apps/web/utils/ai/meeting-briefs/generate-briefing.ts (2)
248-272: Consider adding Anthropic provider support.
getWebSearchConfighandles OpenAI, Google, and OpenRouter but returnsnullfor Anthropic (DEFAULT_LLM_PROVIDER's default). If Anthropic is commonly used, users may lose web search capability. This may be intentional if Anthropic lacks a native search tool, but worth noting.
363-377: Tool availability check duplicates provider logic.The
buildPromptfunction re-checks provider configuration to list available tools, duplicating the logic inbuildSearchToolsandgetWebSearchConfig. Consider extracting a shared helper or passing the actual tool names frombuildSearchTools.Example approach
// In aiGenerateMeetingBriefing, pass tool names to buildPrompt: const toolNames = Object.keys(tools); const prompt = buildPrompt(briefingData, emailAccount.timezone, toolNames); // In buildPrompt: export function buildPrompt( briefingData: MeetingBriefingData, timezone: string | null, availableTools: string[] = [], ): string { // ... const toolsNote = availableTools.length > 0 ? `\nAvailable search tools: ${availableTools.join(", ")}` : ""; // ... }apps/web/utils/redis/research-cache.ts (1)
48-61: Consider cursor type consistency.The
cursorvariable is initialized asnumber(line 49), butredis.scanreturnsnextCursorwhich is then converted viaNumber(nextCursor). This works, butlet cursor: string | number = 0might be cleaner if the SDK returns strings.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (6)
apps/web/utils/ai/meeting-briefs/generate-briefing.tsapps/web/utils/ai/meeting-briefs/research-guest.tsapps/web/utils/email.tsapps/web/utils/redis/research-cache.tsapps/web/utils/user/delete.tspackages/resend/emails/meeting-briefing.tsx
💤 Files with no reviewable changes (1)
- apps/web/utils/ai/meeting-briefs/research-guest.ts
🧰 Additional context used
📓 Path-based instructions (17)
**/*.{ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/data-fetching.mdc)
**/*.{ts,tsx}: For API GET requests to server, use theswrpackage
Useresult?.serverErrorwithtoastErrorfrom@/components/Toastfor error handling in async operations
**/*.{ts,tsx}: Use wrapper functions for Gmail message operations (get, list, batch, etc.) from @/utils/gmail/message.ts instead of direct API calls
Use wrapper functions for Gmail thread operations from @/utils/gmail/thread.ts instead of direct API calls
Use wrapper functions for Gmail label operations from @/utils/gmail/label.ts instead of direct API calls
**/*.{ts,tsx}: For early access feature flags, create hooks using the naming conventionuse[FeatureName]Enabledthat return a boolean fromuseFeatureFlagEnabled("flag-key")
For A/B test variant flags, create hooks using the naming conventionuse[FeatureName]Variantthat define variant types, useuseFeatureFlagVariantKey()with type casting, and provide a default "control" fallback
Use kebab-case for PostHog feature flag keys (e.g.,inbox-cleaner,pricing-options-2)
Always define types for A/B test variant flags (e.g.,type PricingVariant = "control" | "variant-a" | "variant-b") and provide type safety through type casting
**/*.{ts,tsx}: Don't use primitive type aliases or misleading types
Don't use empty type parameters in type aliases and interfaces
Don't use this and super in static contexts
Don't use any or unknown as type constraints
Don't use the TypeScript directive @ts-ignore
Don't use TypeScript enums
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 TypeScript namespaces
Don't use non-null assertions with the!postfix operator
Don't use parameter properties in class constructors
Don't use user-defined types
Useas constinstead of literal types and type annotations
Use eitherT[]orArray<T>consistently
Initialize each enum member value explicitly
Useexport typefor types
Use `impo...
Files:
apps/web/utils/user/delete.tsapps/web/utils/email.tsapps/web/utils/ai/meeting-briefs/generate-briefing.tsapps/web/utils/redis/research-cache.tspackages/resend/emails/meeting-briefing.tsx
**/*.{ts,tsx,js,jsx}
📄 CodeRabbit inference engine (.cursor/rules/prisma-enum-imports.mdc)
Always import Prisma enums from
@/generated/prisma/enumsinstead of@/generated/prisma/clientto avoid Next.js bundling errors in client componentsImport Prisma using the project's centralized utility:
import prisma from '@/utils/prisma'
Files:
apps/web/utils/user/delete.tsapps/web/utils/email.tsapps/web/utils/ai/meeting-briefs/generate-briefing.tsapps/web/utils/redis/research-cache.tspackages/resend/emails/meeting-briefing.tsx
apps/web/**/*.{ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/project-structure.mdc)
Import specific lodash functions rather than entire lodash library to minimize bundle size (e.g.,
import groupBy from 'lodash/groupBy')
apps/web/**/*.{ts,tsx}: Use TypeScript with strict null checks
Do not export types/interfaces that are only used within the same file. Export later if needed
Files:
apps/web/utils/user/delete.tsapps/web/utils/email.tsapps/web/utils/ai/meeting-briefs/generate-briefing.tsapps/web/utils/redis/research-cache.ts
**/*.ts
📄 CodeRabbit inference engine (.cursor/rules/security.mdc)
**/*.ts: ALL database queries MUST be scoped to the authenticated user/account by including user/account filtering in WHERE clauses to prevent unauthorized data access
Always validate that resources belong to the authenticated user before performing operations, using ownership checks in WHERE clauses or relationships
Always validate all input parameters for type, format, and length before using them in database queries
Use SafeError for error responses to prevent information disclosure. Generic error messages should not reveal internal IDs, logic, or resource ownership details
Only return necessary fields in API responses using Prisma'sselectoption. Never expose sensitive data such as password hashes, private keys, or system flags
Prevent Insecure Direct Object References (IDOR) by validating resource ownership before operations. AllfindUnique/findFirstcalls MUST include ownership filters
Prevent mass assignment vulnerabilities by explicitly whitelisting allowed fields in update operations instead of accepting all user-provided data
Prevent privilege escalation by never allowing users to modify system fields, ownership fields, or admin-only attributes through user input
AllfindManyqueries MUST be scoped to the user's data by including appropriate WHERE filters to prevent returning data from other users
Use Prisma relationships for access control by leveraging nested where clauses (e.g.,emailAccount: { id: emailAccountId }) to validate ownership
Files:
apps/web/utils/user/delete.tsapps/web/utils/email.tsapps/web/utils/ai/meeting-briefs/generate-briefing.tsapps/web/utils/redis/research-cache.ts
**/*.{tsx,ts}
📄 CodeRabbit inference engine (.cursor/rules/ui-components.mdc)
**/*.{tsx,ts}: Use Shadcn UI and Tailwind for components and styling
Usenext/imagepackage for images
For API GET requests to server, use theswrpackage with hooks likeuseSWRto fetch data
For text inputs, use theInputcomponent withregisterPropsfor form integration and error handling
Files:
apps/web/utils/user/delete.tsapps/web/utils/email.tsapps/web/utils/ai/meeting-briefs/generate-briefing.tsapps/web/utils/redis/research-cache.tspackages/resend/emails/meeting-briefing.tsx
**/*.{tsx,ts,css}
📄 CodeRabbit inference engine (.cursor/rules/ui-components.mdc)
Implement responsive design with Tailwind CSS using a mobile-first approach
Files:
apps/web/utils/user/delete.tsapps/web/utils/email.tsapps/web/utils/ai/meeting-briefs/generate-briefing.tsapps/web/utils/redis/research-cache.tspackages/resend/emails/meeting-briefing.tsx
**/*.{js,jsx,ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/ultracite.mdc)
**/*.{js,jsx,ts,tsx}: Don't useaccessKeyattribute on any HTML element
Don't setaria-hidden="true"on focusable elements
Don't add ARIA roles, states, and properties to elements that don't support them
Don't use distracting elements like<marquee>or<blink>
Only use thescopeprop on<th>elements
Don't assign non-interactive ARIA roles to interactive HTML elements
Make sure label elements have text content and are associated with an input
Don't assign interactive ARIA roles to non-interactive HTML elements
Don't assigntabIndexto non-interactive HTML elements
Don't use positive integers fortabIndexproperty
Don't include "image", "picture", or "photo" in img alt prop
Don't use explicit role property that's the same as the implicit/default role
Make static elements with click handlers use a valid role attribute
Always include atitleelement for SVG elements
Give all elements requiring alt text meaningful information for screen readers
Make sure anchors have content that's accessible to screen readers
AssigntabIndexto non-interactive HTML elements witharia-activedescendant
Include all required ARIA attributes for elements with ARIA roles
Make sure ARIA properties are valid for the element's supported roles
Always include atypeattribute for button elements
Make elements with interactive roles and handlers focusable
Give heading elements content that's accessible to screen readers (not hidden witharia-hidden)
Always include alangattribute on the html element
Always include atitleattribute for iframe elements
AccompanyonClickwith at least one of:onKeyUp,onKeyDown, oronKeyPress
AccompanyonMouseOver/onMouseOutwithonFocus/onBlur
Include caption tracks for audio and video elements
Use semantic elements instead of role attributes in JSX
Make sure all anchors are valid and navigable
Ensure all ARIA properties (aria-*) are valid
Use valid, non-abstract ARIA roles for elements with ARIA roles
Use valid AR...
Files:
apps/web/utils/user/delete.tsapps/web/utils/email.tsapps/web/utils/ai/meeting-briefs/generate-briefing.tsapps/web/utils/redis/research-cache.tspackages/resend/emails/meeting-briefing.tsx
!(pages/_document).{jsx,tsx}
📄 CodeRabbit inference engine (.cursor/rules/ultracite.mdc)
Don't use the next/head module in pages/_document.js on Next.js projects
Files:
apps/web/utils/user/delete.tsapps/web/utils/email.tsapps/web/utils/ai/meeting-briefs/generate-briefing.tsapps/web/utils/redis/research-cache.tspackages/resend/emails/meeting-briefing.tsx
**/*.{js,ts,jsx,tsx}
📄 CodeRabbit inference engine (.cursor/rules/utilities.mdc)
**/*.{js,ts,jsx,tsx}: Use lodash utilities for common operations (arrays, objects, strings)
Import specific lodash functions to minimize bundle size (e.g.,import groupBy from 'lodash/groupBy')
Files:
apps/web/utils/user/delete.tsapps/web/utils/email.tsapps/web/utils/ai/meeting-briefs/generate-briefing.tsapps/web/utils/redis/research-cache.tspackages/resend/emails/meeting-briefing.tsx
**/{utils,helpers,lib}/**/*.{ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/logging.mdc)
Logger should be passed as a parameter to helper functions instead of creating their own logger instances
Files:
apps/web/utils/user/delete.tsapps/web/utils/email.tsapps/web/utils/ai/meeting-briefs/generate-briefing.tsapps/web/utils/redis/research-cache.ts
apps/web/**/*.{ts,tsx,js,jsx}
📄 CodeRabbit inference engine (apps/web/CLAUDE.md)
apps/web/**/*.{ts,tsx,js,jsx}: Use@/path aliases for imports from project root
Prefer self-documenting code over comments; use descriptive variable and function names instead of explaining intent with comments
Add helper functions to the bottom of files, not the top
All imports go at the top of files, no mid-file dynamic imports
Files:
apps/web/utils/user/delete.tsapps/web/utils/email.tsapps/web/utils/ai/meeting-briefs/generate-briefing.tsapps/web/utils/redis/research-cache.ts
apps/web/**/*.{ts,tsx,js,jsx,json,css}
📄 CodeRabbit inference engine (apps/web/CLAUDE.md)
Format code with Prettier
Files:
apps/web/utils/user/delete.tsapps/web/utils/email.tsapps/web/utils/ai/meeting-briefs/generate-briefing.tsapps/web/utils/redis/research-cache.ts
apps/web/**/*.{example,ts,json}
📄 CodeRabbit inference engine (apps/web/CLAUDE.md)
Add environment variables to
.env.example,env.ts, andturbo.json
Files:
apps/web/utils/user/delete.tsapps/web/utils/email.tsapps/web/utils/ai/meeting-briefs/generate-briefing.tsapps/web/utils/redis/research-cache.ts
apps/web/{utils/ai,utils/llms,__tests__}/**/*.ts
📄 CodeRabbit inference engine (.cursor/rules/llm.mdc)
LLM-related code must be organized in specific directories:
apps/web/utils/ai/for main implementations,apps/web/utils/llms/for core utilities and configurations, andapps/web/__tests__/for LLM-specific tests
Files:
apps/web/utils/ai/meeting-briefs/generate-briefing.ts
apps/web/utils/ai/**/*.ts
📄 CodeRabbit inference engine (.cursor/rules/llm.mdc)
apps/web/utils/ai/**/*.ts: LLM feature functions must import fromzodfor schema validation, usecreateScopedLoggerfrom@/utils/logger,chatCompletionObjectandcreateGenerateObjectfrom@/utils/llms, and importEmailAccountWithAItype from@/utils/llms/types
LLM feature functions must follow a standard structure: accept options withinputDataandemailAccountparameters, implement input validation with early returns, define separate system and user prompts, create a Zod schema for response validation, and usecreateGenerateObjectto execute the LLM call
System prompts must define the LLM's role and task specifications
User prompts must contain the actual data and context, and should be kept separate from system prompts
Always define a Zod schema for LLM response validation and make 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, and include relevant context in log messages
Implement early returns for invalid LLM inputs, use proper error types and logging, implement fallbacks for AI failures, and add retry logic for transient failures usingwithRetry
Use XML-like tags to structure data in prompts, remove excessive whitespace and truncate long inputs, and format data consistently across similar LLM functions
Use TypeScript types for all LLM function parameters and return values, and define clear interfaces for complex input/output structures
Keep related AI functions in the same file or directory, extract common patterns into utility functions, and document complex AI logic with clear comments
Files:
apps/web/utils/ai/meeting-briefs/generate-briefing.ts
**/*.tsx
📄 CodeRabbit inference engine (.cursor/rules/ui-components.mdc)
**/*.tsx: Use theLoadingContentcomponent to handle loading states instead of manual loading state management
For text areas, use theInputcomponent withtype='text',autosizeTextareaprop set to true, andregisterPropsfor form integration
Files:
packages/resend/emails/meeting-briefing.tsx
**/*.{jsx,tsx}
📄 CodeRabbit inference engine (.cursor/rules/ultracite.mdc)
**/*.{jsx,tsx}: Don't use unnecessary fragments
Don't pass children as props
Don't use the return value of React.render
Make sure all dependencies are correctly specified in React hooks
Make sure all React hooks are called from the top level of component functions
Don't forget key props in iterators and collection literals
Don't define React components inside other components
Don't use event handlers on non-interactive elements
Don't assign to React component props
Don't use bothchildrenanddangerouslySetInnerHTMLprops on the same element
Don't use dangerous JSX props
Don't use Array index in keys
Don't insert comments as text nodes
Don't assign JSX properties multiple times
Don't add extra closing tags for components without children
Use<>...</>instead of<Fragment>...</Fragment>
Watch out for possible "wrong" semicolons inside JSX elements
Make sure void (self-closing) elements don't have children
Don't usetarget="_blank"withoutrel="noopener"
Don't use<img>elements in Next.js projects
Don't use<head>elements in Next.js projects
Files:
packages/resend/emails/meeting-briefing.tsx
🧠 Learnings (9)
📚 Learning: 2025-11-25T14:37:22.660Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/gmail-api.mdc:0-0
Timestamp: 2025-11-25T14:37:22.660Z
Learning: Applies to apps/web/utils/gmail/**/*.{ts,tsx} : Keep Gmail provider-specific implementation details isolated within the apps/web/utils/gmail/ directory
Applied to files:
apps/web/utils/email.ts
📚 Learning: 2025-11-25T14:37:22.660Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/gmail-api.mdc:0-0
Timestamp: 2025-11-25T14:37:22.660Z
Learning: Applies to apps/web/utils/gmail/**/*.{ts,tsx} : Always use wrapper functions from @/utils/gmail/ for Gmail API operations instead of direct provider API calls
Applied to files:
apps/web/utils/email.ts
📚 Learning: 2025-11-25T14:37:22.660Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/gmail-api.mdc:0-0
Timestamp: 2025-11-25T14:37:22.660Z
Learning: Applies to **/*.{ts,tsx} : Use wrapper functions for Gmail message operations (get, list, batch, etc.) from @/utils/gmail/message.ts instead of direct API calls
Applied to files:
apps/web/utils/email.ts
📚 Learning: 2025-11-25T14:37:22.660Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/gmail-api.mdc:0-0
Timestamp: 2025-11-25T14:37:22.660Z
Learning: Applies to **/*.{ts,tsx} : Use wrapper functions for Gmail thread operations from @/utils/gmail/thread.ts instead of direct API calls
Applied to files:
apps/web/utils/email.ts
📚 Learning: 2025-11-25T14:38:07.606Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-11-25T14:38:07.606Z
Learning: Applies to apps/web/utils/ai/**/*.ts : Use XML-like tags to structure data in prompts, remove excessive whitespace and truncate long inputs, and format data consistently across similar LLM functions
Applied to files:
apps/web/utils/ai/meeting-briefs/generate-briefing.ts
📚 Learning: 2025-11-25T14:38:07.606Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-11-25T14:38:07.606Z
Learning: Applies to apps/web/utils/ai/**/*.ts : LLM feature functions must import from `zod` for schema validation, use `createScopedLogger` from `@/utils/logger`, `chatCompletionObject` and `createGenerateObject` from `@/utils/llms`, and import `EmailAccountWithAI` type from `@/utils/llms/types`
Applied to files:
apps/web/utils/ai/meeting-briefs/generate-briefing.ts
📚 Learning: 2025-11-25T14:38:07.606Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-11-25T14:38:07.606Z
Learning: Applies to apps/web/utils/ai/**/*.ts : LLM feature functions must follow a standard structure: accept options with `inputData` and `emailAccount` parameters, implement input validation with early returns, define separate system and user prompts, create a Zod schema for response validation, and use `createGenerateObject` to execute the LLM call
Applied to files:
apps/web/utils/ai/meeting-briefs/generate-briefing.ts
📚 Learning: 2025-11-25T14:38:07.606Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-11-25T14:38:07.606Z
Learning: Applies to apps/web/utils/ai/**/*.ts : Implement early returns for invalid LLM inputs, use proper error types and logging, implement fallbacks for AI failures, and add retry logic for transient failures using `withRetry`
Applied to files:
apps/web/utils/ai/meeting-briefs/generate-briefing.ts
📚 Learning: 2025-11-25T14:38:07.606Z
Learnt from: CR
Repo: elie222/inbox-zero PR: 0
File: .cursor/rules/llm.mdc:0-0
Timestamp: 2025-11-25T14:38:07.606Z
Learning: Applies to apps/web/utils/ai/**/*.ts : User prompts must contain the actual data and context, and should be kept separate from system prompts
Applied to files:
apps/web/utils/ai/meeting-briefs/generate-briefing.ts
🧬 Code graph analysis (3)
apps/web/utils/user/delete.ts (1)
apps/web/utils/redis/research-cache.ts (1)
clearCachedResearchForUser(39-80)
apps/web/utils/redis/research-cache.ts (3)
apps/web/utils/logger.ts (1)
createScopedLogger(18-82)apps/web/env.ts (1)
env(17-258)apps/web/utils/hash.ts (1)
hash(10-20)
packages/resend/emails/meeting-briefing.tsx (1)
apps/web/components/new-landing/common/Section.tsx (1)
Section(9-15)
⏰ 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: Baz Reviewer
- GitHub Check: cubic · AI code reviewer
- GitHub Check: test
- GitHub Check: Macroscope - Correctness Check
🔇 Additional comments (9)
apps/web/utils/email.ts (1)
145-145: LGTM!Adding "mail.com" to the public email domains set is appropriate — it's a well-known free email provider that should be treated the same as gmail.com, yahoo.com, etc.
packages/resend/emails/meeting-briefing.tsx (1)
100-109: LGTM!Good addition of the AI accuracy disclaimer. This sets appropriate expectations for users, especially regarding common name ambiguity. The styling is consistent with the email template.
apps/web/utils/user/delete.ts (1)
12-12: LGTM!The import and function call correctly reflect the renamed/generalized research cache module. Not passing a
sourceparameter toclearCachedResearchForUserwill clear all sources (perplexity + websearch), which is the correct behavior for user deletion.Also applies to: 71-74
apps/web/utils/ai/meeting-briefs/generate-briefing.ts (4)
84-86: LGTM!Good early exit when there are no external guests — avoids unnecessary tool initialization and LLM calls.
135-143: LGTM!Good defensive fallback if the agent fails to call
finalizeBriefing. The warning log provides visibility into these edge cases.
208-216: Fire-and-forget cache writes are acceptable here.The
.catch()pattern forsetCachedResearchis fine since caching is an optimization — search results will still be returned even if caching fails. The error is logged appropriately.Also applies to: 325-333
114-117: No changes needed — the behavior is correct as implemented.The
stopWhencallback receivesstepsas an accumulated array of all executed steps, not just the current step. The conditionstepResult.steps.length > MAX_AGENT_STEPScorrectly checks the total accumulated step count to prevent infinite loops.apps/web/utils/redis/research-cache.ts (2)
12-13: LGTM!Good generalization of the cache module to support multiple research sources. The
ResearchSourcetype provides type safety, and including the source in the cache key ensures proper isolation between Perplexity and web search results.Also applies to: 18-29
31-37: LGTM!The pattern logic correctly handles both source-specific (
research:{source}:{userId}:*) and all-sources (research:*:{userId}:*) deletion. The wildcard positioning is correct for Redis SCAN.
![macroscopeapp[bot]](https://avatars.githubusercontent.com/in/900172?s=60&v=4){kind=small}
1 participant
User description
Meeting Briefing: Refactor to agentic approach with research tools
Refactored the meeting briefing system from a pipeline approach to an agentic one, where the AI writes the full briefing with context-aware tool access.
aiGenerateMeetingBriefingto usegenerateTextwithresearchGuestandfinalizeBriefingtools.gatherContextForEventto remove parallel research calls.ai-meeting-briefing.test.ts.Summary by CodeRabbit
Tests
New Features
Refactor
✏️ Tip: You can customize this high-level summary in your review settings.
Generated description
Below is a concise technical summary of the changes proposed in this PR:
Refactors the meeting briefing system to an agentic, tool-driven approach, converting
aiGenerateMeetingBriefingto utilizegenerateTextwithresearchGuestandfinalizeBriefingtools. Simplifies context gathering by removing parallel research calls and improves prompt coherence, alongside adding comprehensive AI and unit tests.aiGenerateMeetingBriefingto usegenerateTextwithresearchGuestandfinalizeBriefingtools, and updating theAGENTIC_SYSTEM_PROMPTfor conditional tool usage and improved coherence.Modified files (1)
Latest Contributors(1)
aiGenerateMeetingBriefingfunction, covering various scenarios including single guests with no prior context and ensuring proper mock clearing before each test.Modified files (1)
Latest Contributors(1)