✨ Create ContestTaskPair table (#2627) #2628
Conversation
WalkthroughAdds planning docs for multi-contest task mapping, introduces a new Prisma model ContestTaskPair, SQL migration to create Changes
Sequence Diagram(s)sequenceDiagram
autonumber
participant Admin as Admin / Seeder
participant App as App Service (future CRUD)
participant Prisma as Prisma Client
participant DB as Postgres
rect rgb(238,245,255)
note right of App: Create / upsert ContestTaskPair (planned flow)
Admin->>App: createContestTaskPair(contestId, taskId, taskTableIndex)
App->>Prisma: upsert ContestTaskPair
Prisma->>DB: INSERT ... ON CONFLICT (contestId, taskId) DO UPDATE
DB-->>Prisma: row
Prisma-->>App: ContestTaskPair
App-->>Admin: result
end
rect rgb(245,238,255)
note right of App: Read by contest (planned flow)
Admin->>App: getContestTaskPairs(contestId)
App->>Prisma: findMany where contestId
Prisma->>DB: SELECT ... WHERE contestId=?
DB-->>Prisma: rows
Prisma-->>App: ContestTaskPairs
App-->>Admin: list
end
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Poem
Pre-merge checks and finishing touches❌ Failed checks (2 warnings)
✅ Passed checks (3 passed)
✨ Finishing touches🧪 Generate unit tests
📜 Recent review detailsConfiguration used: CodeRabbit UI Review profile: CHILL Plan: Pro Cache: Disabled due to data retention organization setting Knowledge base: Disabled due to data retention organization setting 📒 Files selected for processing (1)
🔇 Additional comments (4)
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 |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 6
🧹 Nitpick comments (5)
prisma/schema.prisma (2)
111-123: Add supporting index for common access pattern by (contestId, taskTableIndex).Fetching tasks within a contest ordered by letter/index is common; add a composite index. Consider a uniqueness guarantee if your domain requires one.
model ContestTaskPair { // ... @@unique([contestId, taskId]) @@index([contestId]) + @@index([contestId, taskTableIndex]) + // If the contest letter must be unique within a contest, enforce it: + // @@unique([contestId, taskTableIndex]) @@map("contesttaskpair") }
113-113: Consider using database UUID type forid(optional).If you’re okay with a slight inconsistency vs. existing tables, prefer
@db.Uuid+@default(uuid())so Postgres stores UUIDs natively.- id String @id @default(uuid()) + id String @id @db.Uuid @default(uuid())prisma/migrations/20250928072152_create_contest_task_pair/migration.sql (1)
13-17: Add helpful indexes for query patterns.Add indexes to support reverse lookups and in‑contest ordering.
CREATE INDEX "contesttaskpair_contestId_idx" ON "public"."contesttaskpair"("contestId"); +CREATE INDEX "contesttaskpair_taskId_idx" ON "public"."contesttaskpair"("taskId"); +CREATE INDEX "contesttaskpair_contestId_taskTableIndex_idx" ON "public"."contesttaskpair"("contestId","taskTableIndex"); -- Optionally enforce uniqueness if required by domain: -- CREATE UNIQUE INDEX "contesttaskpair_contestId_taskTableIndex_key" ON "public"."contesttaskpair"("contestId","taskTableIndex");prisma/ERD.md (1)
129-137: Show relation to Task in ERD (after schema change).Once you add
ContestTaskPair.task -> Task.task_id, re-run ERD generation so the diagram reflects the link.docs/dev-notes/2025-09-17/contest-task-mapping/initial_plan.md (1)
176-189: Fix markdownlint MD040: specify language on code fences.Add a language to the directory tree block (e.g.,
text) to satisfy linting.-``` +```text src/routes/admin/import/ ├── problems/ # 問題データインポート │ ├── +page.svelte │ └── types.ts ├── mapping/ # コンテスト-問題マッピング │ ├── +page.svelte │ ├── bulk/ │ └── selective/ └── shared/ # 共通コンポーネント ├── ImportStatus.svelte └── ValidationResults.svelte</blockquote></details> </blockquote></details> <details> <summary>📜 Review details</summary> **Configuration used**: CodeRabbit UI **Review profile**: CHILL **Plan**: Pro **Cache: Disabled due to data retention organization setting** **Knowledge base: Disabled due to data retention organization setting** <details> <summary>📥 Commits</summary> Reviewing files that changed from the base of the PR and between 07586d60698fefbae50a0e250b2eac2b10c73614 and 858761171777872228814448352945cf3c73c8d0. </details> <details> <summary>📒 Files selected for processing (6)</summary> * `docs/dev-notes/2025-09-17/contest-task-mapping/initial_plan.md` (1 hunks) * `docs/dev-notes/2025-09-23/contest-task-pair-mapping/plan.md` (1 hunks) * `prisma/ERD.md` (2 hunks) * `prisma/migrations/20250928072152_create_contest_task_pair/migration.sql` (1 hunks) * `prisma/schema.prisma` (2 hunks) * `src/lib/types/contest_task_pair.ts` (1 hunks) </details> <details> <summary>🧰 Additional context used</summary> <details> <summary>🪛 markdownlint-cli2 (0.18.1)</summary> <details> <summary>docs/dev-notes/2025-09-17/contest-task-mapping/initial_plan.md</summary> 176-176: Fenced code blocks should have a language specified (MD040, fenced-code-language) </details> </details> </details> <details> <summary>⏰ 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). (1)</summary> * GitHub Check: preview </details> <details> <summary>🔇 Additional comments (4)</summary><blockquote> <details> <summary>prisma/schema.prisma (2)</summary><blockquote> `8-9`: **Confirm binaryTargets match deploy runtime (OpenSSL 3.x).** If your deploy images aren’t RHEL/OpenSSL 3.x, Prisma engines may fail to load. Verify the runtime and adjust if needed. --- `35-39`: **Nice: camelCase for new/modified models.** This follows the note about Lucia v3 and gradual migration. No action needed. </blockquote></details> <details> <summary>src/lib/types/contest_task_pair.ts (1)</summary><blockquote> `1-5`: **Types look good and align with Prisma model.** Lightweight aliases; ready for use in services. If you maintain barrel exports (e.g., `src/lib/types/index.ts`), add these types there for discoverability. </blockquote></details> <details> <summary>docs/dev-notes/2025-09-17/contest-task-mapping/initial_plan.md (1)</summary><blockquote> `121-141`: **Good phased plan and adapter sketch.** The compatibility layer and key format are pragmatic for staged migration. </blockquote></details> </blockquote></details> </details> <!-- This is an auto-generated comment by CodeRabbit for review status -->
There was a problem hiding this comment.
Actionable comments posted: 1
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
Cache: Disabled due to data retention organization setting
Knowledge base: Disabled due to data retention organization setting
📒 Files selected for processing (1)
docs/dev-notes/2025-09-23/contest-task-pair-mapping/plan.md(1 hunks)
🧰 Additional context used
🪛 GitHub Actions: CI
docs/dev-notes/2025-09-23/contest-task-pair-mapping/plan.md
[error] 1-1: Prettier formatting check failed. Run 'prettier --write' to fix code style issues.
🔇 Additional comments (1)
docs/dev-notes/2025-09-23/contest-task-pair-mapping/plan.md (1)
302-356: Replace assertions with throwing guards inTaskMapAdapter.Line 304 still uses
console.assert, which only logs even when the condition fails. The test plan in this document expectsadapter.get('')andadapter.get('task1', '')to throw, so copying this code will keep the bug we discussed earlier. Please swap the assertions for explicit guards that throwErrors when the inputs are invalid.@@ - console.assert( - typeof taskId === 'string' && taskId.length > 0, - 'taskId must be non-empty string', - ); + if (typeof taskId !== 'string' || taskId.length === 0) { + throw new Error('taskId must be a non-empty string'); + } @@ - console.assert( - typeof contestId === 'string' && contestId.length > 0, - 'contestId must be non-empty string', - ); - console.assert( - typeof taskId === 'string' && taskId.length > 0, - 'taskId must be non-empty string', - ); + if (typeof contestId !== 'string' || contestId.length === 0) { + throw new Error('contestId must be a non-empty string'); + } + if (typeof taskId !== 'string' || taskId.length === 0) { + throw new Error('taskId must be a non-empty string'); + }
There was a problem hiding this comment.
Actionable comments posted: 4
🧹 Nitpick comments (5)
docs/dev-notes/2025-09-23/contest-task-pair-mapping/plan.md (5)
308-318: Avoid performance.now portability issues in Nodeperformance may not be in lib.dom for TS; prefer Date.now() or import from node:perf_hooks.
Apply:
- const start = performance.now(); + const start = Date.now(); ... - `TaskMapAdapter.get: enhanced hit (${(performance.now() - start).toFixed(2)}ms)`, + `TaskMapAdapter.get: enhanced hit (${(Date.now() - start).toFixed(2)}ms)`, ... - console.log(`TaskMapAdapter.get: legacy hit (${(performance.now() - start).toFixed(2)}ms)`); + console.log(`TaskMapAdapter.get: legacy hit (${(Date.now() - start).toFixed(2)}ms)`); ... - `TaskMapAdapter.get: enhanced scan hit (${(performance.now() - start).toFixed(2)}ms)`, + `TaskMapAdapter.get: enhanced scan hit (${(Date.now() - start).toFixed(2)}ms)`,Or
import { performance } from 'node:perf_hooks'and keep performance.now.Also applies to: 326-327, 337-338
89-117: Race between existence check and createBetween findUnique and create, concurrent writers can still hit P2002. Prefer upsert (if updating taskTableIndex is acceptable) or catch P2002 explicitly.
Apply (catch P2002, preserving “create-only” semantics):
- // 新規レコード作成 - const contestTaskPair = await db.contestTaskPair.create({ - data: { - contestId, - taskTableIndex, - taskId, - }, - }); + // 新規レコード作成（競合時は穏当に無視） + let contestTaskPair: ContestTaskPair | undefined; + try { + contestTaskPair = await db.contestTaskPair.create({ + data: { contestId, taskTableIndex, taskId }, + }); + } catch (e: unknown) { + if (e && typeof e === 'object' && 'code' in e && (e as any).code === 'P2002') { + console.log(`ContestTaskPair already exists (race): contestId=${contestId}, taskId=${taskId}`); + return; + } + throw e; + }Alternatively, use upsert to update taskTableIndex when the pair exists.
202-204: Unify type aliases for contest-task keyed mapsNames and shapes diverge: TaskResultMapByContestTaskPair vs TaskResultByContestTaskPair. Standardize on one generic alias and use consistently in snippets and imports.
Apply:
-// マップの型（明示的） -type TaskResultMapByContestTaskPair = Map<ContestTaskPairKey, TaskResult>; +// Generic map type keyed by ContestTaskPairKey +export type MapByContestTaskPair<T> = Map<ContestTaskPairKey, T>;-type TaskResultByContestTaskPair<T> = Map<ContestTaskPairKey, T>; +export type TaskResultByContestTaskPair<T> = Map<ContestTaskPairKey, T>;And ensure service usage/imports reference the exported alias:
-import { TaskMapAdapter } from '$lib/utils/task_results'; +import { TaskMapAdapter, TaskResultByContestTaskPair } from '$lib/utils/task_results';Also applies to: 283-286, 440-446
409-418: Remove unused contestTaskPairMap or return/use itcontestTaskPairMap is built but unused. Drop it or include it in the returned object and use downstream.
Apply:
- // contestId:taskId -> Task のマップ（TaskResult 作成で直接参照しやすい） - const contestTaskPairMap = new Map<string, Task>(); - for (const t of tasks) { - const contests = contestTaskPairs.get(t.task_id) ?? [t.contest_id]; - for (const c of contests) { - contestTaskPairMap.set(`${c}:${t.task_id}`, t); - } - } - - return { tasks, contestTaskPairs, contestTaskPairMap }; + return { tasks, contestTaskPairs };
145-149: Update only mutable fields in updateContestTaskPairPassing contestId/taskId in data is redundant and risks accidental key changes. Update taskTableIndex only.
Apply:
data: { - contestId, - taskTableIndex, - taskId, + taskTableIndex, },
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
Cache: Disabled due to data retention organization setting
Knowledge base: Disabled due to data retention organization setting
📒 Files selected for processing (1)
docs/dev-notes/2025-09-23/contest-task-pair-mapping/plan.md(1 hunks)
⏰ 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). (1)
- GitHub Check: preview
🔇 Additional comments (3)
docs/dev-notes/2025-09-23/contest-task-pair-mapping/plan.md (3)
425-427: Ensure types are exported/imported consistentlyTaskResultByContestTaskPair is used here but not imported in the snippet. Export it from utils and import alongside TaskMapAdapter.
Apply:
-import { TaskMapAdapter } from '$lib/utils/task_results'; +import { TaskMapAdapter, TaskResultByContestTaskPair } from '$lib/utils/task_results';Please confirm the actual file exports/imports match this.
Also applies to: 440-446
373-381: Syntax error: missing closing brace in createContestTaskPairKeyClose the second if block before returning; otherwise this snippet won’t compile.
Apply:
export function createContestTaskPairKey(contestId: string, taskId: string): ContestTaskPairKey { if (!contestId || contestId.trim() === '') { throw new Error('contestId must be a non-empty string'); } if (!taskId || taskId.trim() === '') { throw new Error('taskId must be a non-empty string'); } + return `${contestId}:${taskId}`; }
302-307: Replace console.assert with throwing guards (aligns with tests)console.assert won’t throw; tests expect errors on invalid inputs. Add explicit validation in get and makeKey (also validate contestId when provided).
Apply:
get(taskId: string, contestId?: string): T | undefined { - console.assert( - typeof taskId === 'string' && taskId.length > 0, - 'taskId must be non-empty string', - ); + if (typeof taskId !== 'string' || taskId.trim().length === 0) { + throw new Error('taskId must be a non-empty string'); + } + if (contestId !== undefined && (typeof contestId !== 'string' || contestId.trim().length === 0)) { + throw new Error('contestId must be a non-empty string when provided'); + }private makeKey(contestId: string, taskId: string): ContestTaskPairKey { - console.assert( - typeof contestId === 'string' && contestId.length > 0, - 'contestId must be non-empty string', - ); - console.assert( - typeof taskId === 'string' && taskId.length > 0, - 'taskId must be non-empty string', - ); + if (typeof contestId !== 'string' || contestId.trim().length === 0) { + throw new Error('contestId must be a non-empty string'); + } + if (typeof taskId !== 'string' || taskId.trim().length === 0) { + throw new Error('taskId must be a non-empty string'); + }Also applies to: 348-356, 241-246
| class TaskResultMapAdapter<T> { | ||
| constructor( | ||
| private legacyMap?: Map<string, T>, // 既存: taskId -> value | ||
| private enhancedMap?: Map<TaskResultByContestTaskPair, T>, // 新形式: contestId:taskId -> value | ||
| ) {} | ||
|
|
||
| private makeKey(contestId: string, taskId: string): ContestTaskPairKey { | ||
| return `${contestId}:${taskId}`; | ||
| } |
There was a problem hiding this comment.
Type error: wrong Map key type for enhancedMap
The key should be ContestTaskPairKey, not TaskResultByContestTaskPair (which is a Map type). Current generics won’t type-check.
Apply:
class TaskResultMapAdapter<T> {
constructor(
private legacyMap?: Map<string, T>, // 既存: taskId -> value
- private enhancedMap?: Map<TaskResultByContestTaskPair, T>, // 新形式: contestId:taskId -> value
+ private enhancedMap?: Map<ContestTaskPairKey, T>, // 新形式: contestId:taskId -> value
) {}📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| class TaskResultMapAdapter<T> { | |
| constructor( | |
| private legacyMap?: Map<string, T>, // 既存: taskId -> value | |
| private enhancedMap?: Map<TaskResultByContestTaskPair, T>, // 新形式: contestId:taskId -> value | |
| ) {} | |
| private makeKey(contestId: string, taskId: string): ContestTaskPairKey { | |
| return `${contestId}:${taskId}`; | |
| } | |
| class TaskResultMapAdapter<T> { | |
| constructor( | |
| private legacyMap?: Map<string, T>, // 既存: taskId -> value | |
| private enhancedMap?: Map<ContestTaskPairKey, T>, // 新形式: contestId:taskId -> value | |
| ) {} | |
| private makeKey(contestId: string, taskId: string): ContestTaskPairKey { | |
| return `${contestId}:${taskId}`; | |
| } | |
| } |
🤖 Prompt for AI Agents
In docs/dev-notes/2025-09-23/contest-task-pair-mapping/plan.md around lines 217
to 225, the enhancedMap field is typed as Map<TaskResultByContestTaskPair, T>
which is incorrect because TaskResultByContestTaskPair is a Map type; change the
enhancedMap declaration to use ContestTaskPairKey as the key type (i.e.
Map<ContestTaskPairKey, T>) and ensure the makeKey method’s return type is
ContestTaskPairKey so the key types align.
| // 他のメソッド (has, set, delete) も同様に実装 | ||
| } |
There was a problem hiding this comment.
Adapter method mismatch: has/set/delete not implemented but used
TaskMapAdapter is used with adapter.has(...); the utils snippet only implements get. This will not compile at usage sites.
Apply:
- // 他のメソッド (has, set, delete) も同様に実装
+ has(taskId: string, contestId?: string): boolean {
+ if (contestId && this.enhancedMap) {
+ return this.enhancedMap.has(this.makeKey(contestId, taskId));
+ }
+ if (this.legacyMap?.has(taskId)) return true;
+ if (this.enhancedMap) {
+ for (const key of this.enhancedMap.keys()) {
+ if (key.endsWith(`:${taskId}`)) return true;
+ }
+ }
+ return false;
+ }
+
+ set(taskId: string, value: T, contestId?: string): void {
+ this.legacyMap?.set(taskId, value);
+ if (contestId && this.enhancedMap) {
+ this.enhancedMap.set(this.makeKey(contestId, taskId), value);
+ }
+ }
+
+ delete(taskId: string, contestId?: string): boolean {
+ let ok = false;
+ if (contestId && this.enhancedMap) {
+ ok = this.enhancedMap.delete(this.makeKey(contestId, taskId)) || ok;
+ }
+ if (this.legacyMap) {
+ ok = this.legacyMap.delete(taskId) || ok;
+ }
+ return ok;
+ }Also applies to: 480-482
🤖 Prompt for AI Agents
In docs/dev-notes/2025-09-23/contest-task-pair-mapping/plan.md around lines
361-362 (and likewise lines 480-482), the TaskMapAdapter utility only implements
get(...) but calling sites use adapter.has(...), adapter.set(...), and
adapter.delete(...); add matching method signatures and implementations for has,
set, and delete to the adapter interface/implementation so compilation succeeds.
Implement has to return a boolean presence check, set to store/update the value,
and delete to remove the key, ensuring their behavior mirrors get (including
async/await if get is async) and update any type/interface definitions and
usages accordingly.
| if (isLoggedIn && adapter.has(task.task_id, task.contest_id)) { | ||
| const answer = adapter.get(task.task_id, task.contest_id); | ||
| const status = statusById.get(answer?.status_id); | ||
| taskResult.status_name = status.status_name; | ||
| taskResult.submission_status_image_path = status.image_path; | ||
| taskResult.submission_status_label_name = status.label_name; | ||
| taskResult.is_ac = status.is_ac; | ||
| taskResult.updated_at = answer?.updated_at ?? taskResult.updated_at; | ||
| } |
There was a problem hiding this comment.
Guard against undefined status to avoid runtime crash
statusById.get(...) can be undefined; dereferencing will throw.
Apply:
- if (isLoggedIn && adapter.has(task.task_id, task.contest_id)) {
- const answer = adapter.get(task.task_id, task.contest_id);
- const status = statusById.get(answer?.status_id);
- taskResult.status_name = status.status_name;
- taskResult.submission_status_image_path = status.image_path;
- taskResult.submission_status_label_name = status.label_name;
- taskResult.is_ac = status.is_ac;
- taskResult.updated_at = answer?.updated_at ?? taskResult.updated_at;
- }
+ if (isLoggedIn && adapter.has(task.task_id, task.contest_id)) {
+ const answer = adapter.get(task.task_id, task.contest_id);
+ const status = statusById.get(answer?.status_id);
+ if (status) {
+ taskResult.status_name = status.status_name;
+ taskResult.submission_status_image_path = status.image_path;
+ taskResult.submission_status_label_name = status.label_name;
+ taskResult.is_ac = status.is_ac;
+ }
+ taskResult.updated_at = answer?.updated_at ?? taskResult.updated_at;
+ }📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| if (isLoggedIn && adapter.has(task.task_id, task.contest_id)) { | |
| const answer = adapter.get(task.task_id, task.contest_id); | |
| const status = statusById.get(answer?.status_id); | |
| taskResult.status_name = status.status_name; | |
| taskResult.submission_status_image_path = status.image_path; | |
| taskResult.submission_status_label_name = status.label_name; | |
| taskResult.is_ac = status.is_ac; | |
| taskResult.updated_at = answer?.updated_at ?? taskResult.updated_at; | |
| } | |
| if (isLoggedIn && adapter.has(task.task_id, task.contest_id)) { | |
| const answer = adapter.get(task.task_id, task.contest_id); | |
| const status = statusById.get(answer?.status_id); | |
| if (status) { | |
| taskResult.status_name = status.status_name; | |
| taskResult.submission_status_image_path = status.image_path; | |
| taskResult.submission_status_label_name = status.label_name; | |
| taskResult.is_ac = status.is_ac; | |
| } | |
| taskResult.updated_at = answer?.updated_at ?? taskResult.updated_at; | |
| } |
🤖 Prompt for AI Agents
In docs/dev-notes/2025-09-23/contest-task-pair-mapping/plan.md around lines 480
to 488, statusById.get(answer?.status_id) can return undefined and the
subsequent property dereferences will crash; update the block to first check
that status is defined (e.g., if (status) { ... }) or use safe optional chaining
with sensible fallbacks so you only assign status_name, image_path, label_name,
is_ac, and updated_at when status exists, and preserve existing taskResult
values or set defaults when it does not.
| // console.log ベースの監視（開発環境のみ） | ||
| export async function getTaskResults(userId: string): Promise<TaskResults> { | ||
| if (process.env.NODE_ENV === 'development') { | ||
| console.time('getTaskResults'); | ||
| console.log(`Processing ${answers.size} answers for user ${userId}`); | ||
| } | ||
|
|
||
| const results = await getTaskResults(userId); | ||
|
|
||
| if (process.env.NODE_ENV === 'development') { | ||
| console.log(`Generated ${results.length} task results`); | ||
| console.timeEnd('getTaskResults'); | ||
|
|
||
| // メモリ使用量確認 | ||
| const memory = process.memoryUsage(); | ||
| console.log(`Memory usage: ${Math.round(memory.heapUsed / 1024 / 1024)}MB`); | ||
| } | ||
|
|
||
| return results; | ||
| } |
There was a problem hiding this comment.
Infinite recursion in monitoring snippet
getTaskResults calls itself; this will stack overflow. Wrap the real implementation instead.
Apply:
-export async function getTaskResults(userId: string): Promise<TaskResults> {
+export async function getTaskResults(userId: string): Promise<TaskResults> {
if (process.env.NODE_ENV === 'development') {
console.time('getTaskResults');
- console.log(`Processing ${answers.size} answers for user ${userId}`);
+ console.log(`Processing task results for user ${userId}`);
}
- const results = await getTaskResults(userId);
+ const results = await getTaskResultsCore(userId);
if (process.env.NODE_ENV === 'development') {
console.log(`Generated ${results.length} task results`);
console.timeEnd('getTaskResults');
@@
return results;
}
+
+// Extract the core implementation to avoid recursion in the wrapper.
+async function getTaskResultsCore(userId: string): Promise<TaskResults> {
+ // ...existing non-profiling logic...
+}Committable suggestion skipped: line range outside the PR's diff.
🤖 Prompt for AI Agents
In docs/dev-notes/2025-09-23/contest-task-pair-mapping/plan.md around lines 602
to 621, the exported getTaskResults wraps monitoring but currently calls itself
(infinite recursion); extract or call the real implementation instead (e.g.,
rename the actual logic to fetchTaskResults or _getTaskResults and call that
inside the monitoring wrapper), ensure the wrapper logs/times only in
development, and return the result from the underlying function.
close #2627
Summary by CodeRabbit