feat: Add API Pagination to Backend List Endpoints#308
Open
sharma-sugurthi wants to merge 3 commits intoAOSSIE-Org:mainfrom
Open
feat: Add API Pagination to Backend List Endpoints#308sharma-sugurthi wants to merge 3 commits intoAOSSIE-Org:mainfrom
sharma-sugurthi wants to merge 3 commits intoAOSSIE-Org:mainfrom
Conversation
- Create pagination utility module (utils/pagination.py) - Add pagination support to all 7 list endpoints: - GET /users/ - GET /audience-insights/ - GET /sponsorships/ - GET /posts/ - GET /sponsorship-applications/ - GET /sponsorship-payments/ - GET /collaborations/ - Support skip/limit query parameters with validation - Return paginated response with metadata (data, skip, limit, count)
Contributor
|
Warning Rate limit exceeded
⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. 📒 Files selected for processing (1)
📝 WalkthroughWalkthroughAdds query-based pagination to seven GET endpoints in Changes
Sequence Diagram(s)sequenceDiagram
participant Client
participant API as FastAPI (post routes)
participant Pager as Pagination Utils
participant DB as Supabase
Client->>API: GET /posts?skip=50&limit=25
API->>Pager: get_pagination_params(skip, limit)
Pager-->>API: (start, end, sanitized_skip, sanitized_limit)
API->>DB: query .order("id").range(start, end)
DB-->>API: paged rows
API->>DB: query count
DB-->>API: total_count
API->>Pager: paginate_query(query_result, skip, limit, total_count)
Pager-->>API: {data, skip, limit, count, total_count}
API-->>Client: 200 OK with paginated payload
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Poem
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
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 |
Author
|
Please review @Zahnentferner |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 2
🧹 Nitpick comments (1)
Backend/app/utils/pagination.py (1)
9-17: Consider more specific type hint for return value.Using
Tuple[int, int]instead oftupleprovides better type safety and IDE support.♻️ Proposed fix
-from typing import Dict, Any +from typing import Dict, Any, Tuple DEFAULT_SKIP = 0 DEFAULT_LIMIT = 50 MAX_LIMIT = 100 -def get_pagination_params(skip: int = DEFAULT_SKIP, limit: int = DEFAULT_LIMIT) -> tuple: +def get_pagination_params(skip: int = DEFAULT_SKIP, limit: int = DEFAULT_LIMIT) -> Tuple[int, int]: """Validate and return pagination parameters."""🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@Backend/app/utils/pagination.py` around lines 9 - 17, The function get_pagination_params currently annotates its return type as generic "tuple"; change it to a concrete Tuple[int, int] for better type safety by updating the signature to use Tuple[int, int] and add the necessary import (from typing import Tuple) at the top of the module; keep the function logic unchanged and ensure any callers expecting a tuple continue to work since Tuple[int, int] is compatible.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@Backend/app/routes/post.py`:
- Around line 55-65: The get_users endpoint (and the six other paginated
endpoints in this file) uses supabase.table(...).select(...).range(...) without
an explicit ORDER BY, causing non-deterministic pagination; update each
paginated handler (e.g., get_users) to apply a deterministic order before
calling .range() by adding an explicit order clause on the intended sort column
plus the unique primary key as a tiebreaker (e.g., order("created_at", {
ascending: false }) then order("id", { ascending: true })) so ties are resolved
consistently, and keep using get_pagination_params and paginate_query unchanged;
apply the same pattern to all seven endpoints referenced in the review.
In `@Backend/app/utils/pagination.py`:
- Around line 20-32: The paginate_query function currently returns "count" as
the page length, not the total records; update paginate_query(query_result,
skip: int, limit: int) to include a "total_count" field that represents the full
dataset size by first checking for a total on the result (e.g., use
query_result.count or query_result.total if present) and, if absent,
perform/accept a separate exact-count query result and merge its count; preserve
existing "count" as page length but add "total_count" to the returned dict and
handle missing/None safely (default to len(data)) so clients can compute total
pages and detect more pages.
---
Nitpick comments:
In `@Backend/app/utils/pagination.py`:
- Around line 9-17: The function get_pagination_params currently annotates its
return type as generic "tuple"; change it to a concrete Tuple[int, int] for
better type safety by updating the signature to use Tuple[int, int] and add the
necessary import (from typing import Tuple) at the top of the module; keep the
function logic unchanged and ensure any callers expecting a tuple continue to
work since Tuple[int, int] is compatible.
- Add .order('id') to all paginated queries for deterministic ordering
- Add count query to get total_count for pagination UX
- Update paginate_query to include total_count in response
Addresses CodeRabbit review feedback
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
Backend/app/routes/post.py (1)
56-60: Consider removing redundant validation layer.FastAPI's
Queryconstraints (ge=0,ge=1,le=100) already reject invalid input with a 422 response before the handler executes. Theget_pagination_paramscall then re-validates the same constraints.If
get_pagination_paramsis only used by FastAPI endpoints, consider simplifying it to just return the tuple without re-validation. If it needs to support non-FastAPI callers, the current design is fine.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@Backend/app/routes/post.py` around lines 56 - 60, The handler get_users currently re-validates pagination that FastAPI already enforces via Query; remove the redundant validation by changing the call to get_pagination_params(skip, limit) so that get_pagination_params no longer re-checks Query constraints and simply returns (skip, limit), or if you need get_pagination_params to remain reusable outside FastAPI keep its validation but call it only from non-FastAPI code—i.e., simplify get_pagination_params to a passthrough (return skip, limit) when used by get_users, and update the function signature/implementation accordingly to avoid duplicate checks.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@Backend/app/routes/post.py`:
- Around line 64-67: The count queries currently fetch full rows (e.g., in the
block that calls supabase.table("users").select("*", count="exact").execute())
which defeats pagination; update each count query to request only the count by
adding .limit(0) before .execute() so no rows are transferred. Apply this change
in all endpoints that compute total_count (functions/getters named
get_audience_insights, get_sponsorships, get_posts,
get_sponsorship_applications, get_sponsorship_payments, get_collaborations and
the users listing that calls paginate_query) and keep using count_result.count
(with the existing fallback to len(count_result.data)) to derive total_count.
Ensure the modified calls still pass the result into paginate_query(result,
skip, limit, total_count).
---
Nitpick comments:
In `@Backend/app/routes/post.py`:
- Around line 56-60: The handler get_users currently re-validates pagination
that FastAPI already enforces via Query; remove the redundant validation by
changing the call to get_pagination_params(skip, limit) so that
get_pagination_params no longer re-checks Query constraints and simply returns
(skip, limit), or if you need get_pagination_params to remain reusable outside
FastAPI keep its validation but call it only from non-FastAPI code—i.e.,
simplify get_pagination_params to a passthrough (return skip, limit) when used
by get_users, and update the function signature/implementation accordingly to
avoid duplicate checks.
ℹ️ Review info
Configuration used: defaults
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
Backend/app/routes/post.pyBackend/app/utils/pagination.py
🚧 Files skipped from review as they are similar to previous changes (1)
- Backend/app/utils/pagination.py
- Add .limit(0) to all count queries to prevent fetching data - Returns only count metadata without transferring rows - Addresses CodeRabbit performance feedback
Author
|
also fixed some issues that pointed from the review of bot!!! |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
This PR implements pagination support for all backend list endpoints to prevent performance degradation as the database grows.
Changes Made
GET /users/GET /audience-insights/GET /sponsorships/GET /posts/GET /sponsorship-applications/GET /sponsorship-payments/GET /collaborations/Implementation Details
Query Parameters
All list endpoints now accept:
skip(int, default=0, min=0): Number of records to skip (offset)limit(int, default=50, min=1, max=100): Maximum records to return per pageResponse Format
Returns paginated response with metadata:
{ "data": [...], "skip": 0, "limit": 50, "count": 50 }Summary by CodeRabbit