Skip to content

Conversation

junaid-shirur
Copy link
Collaborator

@junaid-shirur junaid-shirur commented Sep 3, 2025

Description

  • Update web search to consider user location when fetching results

Testing

Additional Notes

Summary by CodeRabbit

  • New Features

    • Web search now uses a dynamic, context-aware system prompt that adapts to your context and timezone, improving relevance and time-sensitive accuracy.
    • Agent-specific instructions are incorporated when provided for more tailored results.
  • Refactor

    • Prompt generation streamlined to include only relevant sections, reducing noise and improving clarity in search queries and responses.

@coderabbitai
Copy link
Contributor

coderabbitai bot commented Sep 3, 2025

Walkthrough

Introduces a new function to generate a web-search system prompt using user context and updates the provider to consume it. Refactors search query prompt rendering to conditionally include sections only when data exists. No control-flow changes beyond replacing a static prompt with a generated one.

Changes

Cohort / File(s) Summary
Prompt utilities
server/ai/prompts.ts
Added exported function webSearchSystemPrompt(userCtx: string); refactored searchQueryPrompt to conditionally render previousClassification and chainBreakClassifications; adjusted import formatting and minor whitespace/naming.
Web search provider integration
server/ai/provider/index.ts
Replaced hard-coded web search system prompt with webSearchSystemPrompt(userCtx); optionally appends parseAgentPrompt(params.agentPrompt); reformatted call to searchQueryPrompt without behavioral change.

Sequence Diagram(s)

sequenceDiagram
  autonumber
  participant UI as Caller
  participant Provider as WebSearch Provider
  participant Prompts as Prompts Module
  participant LLM as Model

  UI->>Provider: webSearchQuestion(userCtx, params)
  Provider->>Prompts: webSearchSystemPrompt(userCtx)
  Prompts-->>Provider: systemPrompt (context-aware)
  alt agentPrompt provided
    Provider->>Provider: Append parsed agent prompt
  end
  Provider->>LLM: Invoke with systemPrompt (+agentPrompt), user input
  LLM-->>Provider: Answer / Search query
  Provider-->>UI: Result
Loading

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~20 minutes

Possibly related PRs

Suggested reviewers

  • zereraz

Poem

I nibbled the prompts till they fit just right,
A dash of context, a sprinkle of light.
Static no more—now flows are spry,
Web winds whisper the user’s why.
Thump-thump! says the review queue, neat—
Query carrots, crisp and sweet. 🥕✨

✨ Finishing Touches
  • 📝 Generate Docstrings
🧪 Generate unit tests
  • Create PR with unit tests
  • Post copyable unit tests in a comment
  • Commit unit tests in branch fix/web_search

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.

❤️ Share
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

CodeRabbit Commands (Invoked using PR/Issue comments)

Type @coderabbitai help to get the list of available commands.

Other keywords and placeholders

  • Add @coderabbitai ignore or @coderabbit ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Status, Documentation and Community

  • Visit our Status Page to check the current availability of CodeRabbit.
  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Summary of Changes

Hello @junaid-shirur, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request aims to significantly improve the accuracy and relevance of web search results by integrating user location and timezone data into the search query process. The change ensures that the AI assistant provides more contextually appropriate and up-to-date information, especially for time-sensitive queries.

Highlights

  • Enhanced Web Search Relevance: The web search functionality now incorporates the user's location and timezone when fetching results. This ensures that time-sensitive information, such as current events, prices, or business hours, is accurately presented based on the user's geographical context.
Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in issue comments and review comments.
Help /gemini help Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.

Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 3

🧹 Nitpick comments (2)
server/ai/prompts.ts (1)

2348-2352: Optional: Avoid over-sharing PII in system prompts

Including full “User-Details” (name/email/domain) in a general web-search system prompt may be unnecessary. Consider restricting to location/locale/timezone to reduce exposure.

server/ai/provider/index.ts (1)

1829-1841: Pass user geo/locale to provider layer for true location-aware search

Even with a better prompt, actual search ranking often depends on engine parameters (hl/gl, lr, uule, lat/lon). Consider threading user country/region/coords through ModelParams and provider implementations (e.g., Vertex/Google) to bias results server-side.

Proposed interface change (sketch):

// types
export interface ModelParams {
  // ...
  userLocale?: { country?: string; region?: string; city?: string; lat?: number; lon?: number; tz?: string }
}

// provider usage
params.userLocale && provider.setGeo(params.userLocale)
📜 Review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

💡 Knowledge Base configuration:

  • MCP integration is disabled by default for public repositories
  • Jira integration is disabled by default for public repositories
  • Linear integration is disabled by default for public repositories

You can enable these sources in your CodeRabbit configuration.

📥 Commits

Reviewing files that changed from the base of the PR and between b3f9c8d and 2044598.

📒 Files selected for processing (2)
  • server/ai/prompts.ts (4 hunks)
  • server/ai/provider/index.ts (3 hunks)
🧰 Additional context used
🧬 Code graph analysis (2)
server/ai/provider/index.ts (2)
server/ai/prompts.ts (2)
  • searchQueryPrompt (1058-1447)
  • webSearchSystemPrompt (2348-2352)
server/ai/context.ts (1)
  • userContext (820-834)
server/ai/prompts.ts (1)
server/ai/context.ts (1)
  • userContext (820-834)
🔇 Additional comments (2)
server/ai/prompts.ts (1)

1-1: Replace static IST in userContext with dynamic timezone
In server/ai/context.ts (lines 823–833), userContext appends a hard-coded “Timezone: IST”, forcing all prompts to India time. Replace with a tz value from user.timezoneworkspace.timezoneIntl.DateTimeFormat().resolvedOptions().timeZone"UTC" and pass it into toLocaleDateString/toLocaleTimeString.

 export const userContext = ({
   user,
   workspace,
 }: PublicUserWorkspace): string => {
-  const now = new Date()
-  const currentDate = now.toLocaleDateString() // e.g., "11/10/2024"
-  const currentTime = now.toLocaleTimeString() // e.g., "10:14:03 AM"
+  const now = new Date()
+  // Prefer persisted user timezone/locale from profile or request; fall back to Intl
+  const tz =
+    user.timezone ||
+    workspace.timezone ||
+    Intl.DateTimeFormat().resolvedOptions().timeZone ||
+    "UTC"
+  const currentDate = now.toLocaleDateString(undefined, { timeZone: tz })
+  const currentTime = now.toLocaleTimeString(undefined, { timeZone: tz })
   return `My Name is ${user.name}
     Email: ${user.email}
     Company: ${workspace.name}
     Company domain: ${workspace.domain}
     Current Time: ${currentTime}
     Today is: ${currentDate}
-    Timezone: IST`
+    Timezone: ${tz}`
 }

Likely an incorrect or invalid review comment.

server/ai/provider/index.ts (1)

1483-1487: LGTM: Multi-line call improves readability; no behavior change

The reformatted call to searchQueryPrompt with three arguments preserves semantics.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants