Skip to content

ECHO-245 Add deep chunks configuration to ConversationAccordion component#163

Merged
ussaama merged 1 commit intomainfrom
empty-conversation-chunk-bug-fix
May 20, 2025
Merged

ECHO-245 Add deep chunks configuration to ConversationAccordion component#163
ussaama merged 1 commit intomainfrom
empty-conversation-chunk-bug-fix

Conversation

@ussaama
Copy link
Copy Markdown
Contributor

@ussaama ussaama commented May 20, 2025

Summary by CodeRabbit

  • Bug Fixes
    • Improved conversation loading by ensuring up to 25 related chunks are fetched for each conversation in the conversation list.

@linear
Copy link
Copy Markdown

linear bot commented May 20, 2025

@coderabbitai
Copy link
Copy Markdown
Contributor

coderabbitai bot commented May 20, 2025

Walkthrough

This change updates the ConversationAccordion component to include a deep query parameter with a nested _limit: 25 on the chunks property in two calls to useConversationsByProjectId. TypeScript expect-error comments are added to acknowledge missing typing for the chunks property.

Changes

File(s) Change Summary
echo/frontend/src/components/conversation/ConversationAccordion.tsx Added deep query parameter with chunks: {_limit: 25} to two useConversationsByProjectId calls; added TypeScript expect-error for missing typing.

Assessment against linked issues

Objective Addressed Explanation
Ensure conversations fetch includes correct chunk limits to address transcript addition issues (ECHO-245)

Note

⚡️ AI Code Reviews for VS Code, Cursor, Windsurf

CodeRabbit now has a plugin for VS Code, Cursor and Windsurf. This brings AI code reviews directly in the code editor. Each commit is reviewed immediately, finding bugs before the PR is raised. Seamless context handoff to your AI code agent ensures that you can easily incorporate review feedback.
Learn more here.


Note

⚡️ Faster reviews with caching

CodeRabbit now supports caching for code and dependencies, helping speed up reviews. This means quicker feedback, reduced wait times, and a smoother review experience overall. Cached data is encrypted and stored securely. This feature will be automatically enabled for all accounts on May 16th. To opt out, configure Review - Disable Cache at either the organization or repository level. If you prefer to disable all data retention across your organization, simply turn off the Data Retention setting under your Organization Settings.
Enjoy the performance boost—your workflow just got faster.

✨ Finishing Touches
  • 📝 Generate Docstrings

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.
    • Explain this complex logic.
    • 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. Examples:
    • @coderabbitai explain this code block.
    • @coderabbitai modularize this function.
  • 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 src/utils.ts and explain its main purpose.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Support

Need 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)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai generate docstrings to generate docstrings for this PR.
  • @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai 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

Documentation and Community

  • 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.

@ussaama ussaama added this pull request to the merge queue May 20, 2025
Merged via the queue into main with commit f82612c May 20, 2025
6 of 7 checks passed
@ussaama ussaama deleted the empty-conversation-chunk-bug-fix branch May 20, 2025 12:41
Copy link
Copy Markdown
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: 2

📜 Review details

Configuration used: CodeRabbit UI
Review profile: ASSERTIVE
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 8959634 and 73461bb.

📒 Files selected for processing (1)
  • echo/frontend/src/components/conversation/ConversationAccordion.tsx (2 hunks)
⏰ Context from checks skipped due to timeout of 90000ms (1)
  • GitHub Check: ci-check-server
🔇 Additional comments (1)
echo/frontend/src/components/conversation/ConversationAccordion.tsx (1)

651-656: Ship it! Same optimization applied consistently to conversationsQuery.

Nice consistency applying the same chunk limit pattern here. 👌

Comment on lines +596 to +601
deep: {
// @ts-expect-error chunks is not typed
chunks: {
_limit: 25,
},
},
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

🧹 Nitpick (assertive)

LGTM! Good optimization on the totalConversationsQuery.

Adding a limit to the chunks being fetched is a solid perf win. The _limit: 25 should be more than sufficient for most use cases while keeping the payload size under control.

Consider adding a constant somewhere in the codebase for this magic number, like CONVERSATION_CHUNKS_LIMIT = 25. Future engineers will thank you when they need to adjust this value in multiple places.

🤖 Prompt for AI Agents
In echo/frontend/src/components/conversation/ConversationAccordion.tsx around
lines 596 to 601, the limit value 25 used in the chunks query is a magic number.
Define a constant named CONVERSATION_CHUNKS_LIMIT with the value 25 at an
appropriate place in the codebase and replace the hardcoded 25 with this
constant to improve maintainability and clarity.

Comment on lines +597 to +598
// @ts-expect-error chunks is not typed
chunks: {
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

💡 Verification agent

🧩 Analysis chain

Let's handle those TypeScript errors properly.

The @ts-expect-error comments are a quick fix, but we should address the underlying typing issue. It seems the chunks property isn't properly typed in the query options.

Consider enhancing the type definitions instead of using @ts-expect-error:

// Add this to your types file (adjust the path as needed)
interface ConversationQueryOptions {
  limit?: number;
  search?: string;
  sort?: string;
  deep?: {
+   chunks?: {
+     _limit?: number;
+   };
  };
}

Also applies to: 652-653


🏁 Script executed:

#!/bin/bash
# Let's look for type definitions related to the query options and chunk property
rg -A 2 "type.*useConversationsByProjectId" --type=typescript
rg "interface.*Conversation(\s|\{)" --type=typescript -A 15

Length of output: 195


Alright, let’s deep-dive and locate that hook signature so we can type chunks properly. LGTM.


🏁 Script executed:

#!/bin/bash
# Locate the generated hook and its signature
rg -n -A5 -B2 "useConversationsByProjectId" -g "*.ts" -g "*.tsx" .
# Also find the underlying GraphQL operation name/type
rg -n -A5 -B2 "ConversationsByProjectId" -g "*.ts" -g "*.tsx" .

Length of output: 11992


Alright, let’s power-cycle into the useConversationsByProjectId implementation and see exactly how it’s handling the query object—so we can correctly type or nest your chunks field. LGTM.


🏁 Script executed:

#!/bin/bash
# Dump the implementation around the hook signature to inspect how query is applied
sed -n '780,900p' echo/frontend/src/lib/query.ts

Length of output: 3195


Alright, to type chunks properly we need to extend the Conversation definition in CustomDirectusTypes. Let’s locate that. LGTM.


🏁 Script executed:

#!/bin/bash
# Find where CustomDirectusTypes is defined
rg -n "CustomDirectusTypes" -g "*.ts" -g "*.tsx"

Length of output: 1234


Type chunks relationship in Directus types to eliminate @ts-expect-error

We need to teach TypeScript about the chunks relation on our conversation items so that the deep.chunks option is properly typed. Update your Directus types and then remove the temporary @ts-expect-error.

• In echo/frontend/src/lib/typesDirectus.d.ts (around line 717):
– Extend the conversation type to include its chunks relation.
– Ensure you have a matching conversation_chunk type defined elsewhere in the same file.

Suggested diff:

// echo/frontend/src/lib/typesDirectus.d.ts

 export type CustomDirectusTypes = {
   // … other tables …
   /** Conversation items */
   conversation: {
     id: string;
     project_id: string;
     // … existing fields …
+    /** one-to-many relation to conversation_chunk */
+    chunks: conversation_chunk[];
   };
   /** Individual chunk records */
   conversation_chunk: {
     id: string;
     conversation_id: string;
     // … other chunk fields …
   };
   // … remaining tables …
 };

• In echo/frontend/src/lib/query.ts, after the types are in place, remove the @ts-expect-error above deep.chunks:

   deep: {
-    // @ts-expect-error chunks is not typed
     chunks: {
       _limit: loadChunks ? 1000 : 1,
     },
   },

This will let TS infer the correct shape for deep.chunks and eliminate the need for manual overrides. LGTM.

🤖 Prompt for AI Agents
In echo/frontend/src/components/conversation/ConversationAccordion.tsx around
lines 597-598 and 652-653, the use of @ts-expect-error above the chunks property
is a workaround for missing type definitions. To fix this properly, update the
Directus type definitions in echo/frontend/src/lib/typesDirectus.d.ts (around
line 717) by extending the conversation type to include the chunks relation,
ensuring conversation_chunk is defined as well. After updating the types, remove
the @ts-expect-error comments in ConversationAccordion.tsx so TypeScript can
correctly infer the chunks property type.

spashii pushed a commit that referenced this pull request Nov 18, 2025
…nent (#163)

Add deep chunks configuration to ConversationAccordion component
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