fix(stack): enforce max stack items and align public API limit

[rebelchris]

Summary

• enforce a hard max stack size at MAX_STACK_ITEMS for both user and squad stack mutations
• align the public stack REST endpoint limit with the same shared constant
• add integration coverage for max-size behavior in GraphQL and public API tests

Key decisions

• introduced a single shared constant (MAX_STACK_ITEMS = 100) to avoid drift between API layers
• blocked add mutations once the current stack item count reaches the max, with explicit validation errors
• made parseLimit accept an endpoint-specific max so stack endpoints can safely opt into higher limits without changing global defaults

Closes ENG-696

---

Created by Huginn 🐦‍⬛

[pulumi]

🍹 The Update (preview) for dailydotdev/api/prod (at 8627c32) was successful.

Resource Changes

    Name                                                       Type                           Operation
~   vpc-native-clean-gifted-plus-cron                          kubernetes:batch/v1:CronJob    update
~   vpc-native-update-trending-cron                            kubernetes:batch/v1:CronJob    update
~   vpc-native-clean-stale-user-transactions-cron              kubernetes:batch/v1:CronJob    update
~   vpc-native-post-analytics-clickhouse-cron                  kubernetes:batch/v1:CronJob    update
~   vpc-native-update-tag-recommendations-cron                 kubernetes:batch/v1:CronJob    update
~   vpc-native-validate-active-users-cron                      kubernetes:batch/v1:CronJob    update
~   vpc-native-user-profile-analytics-history-clickhouse-cron  kubernetes:batch/v1:CronJob    update
~   vpc-native-temporal-deployment                             kubernetes:apps/v1:Deployment  update
-   vpc-native-api-clickhouse-migration-04b17055               kubernetes:batch/v1:Job        delete
~   vpc-native-personalized-digest-cron                        kubernetes:batch/v1:CronJob    update
~   vpc-native-check-analytics-report-cron                     kubernetes:batch/v1:CronJob    update
~   vpc-native-generate-search-invites-cron                    kubernetes:batch/v1:CronJob    update
~   vpc-native-clean-zombie-user-companies-cron                kubernetes:batch/v1:CronJob    update
~   vpc-native-update-highlighted-views-cron                   kubernetes:batch/v1:CronJob    update
~   vpc-native-update-source-public-threshold-cron             kubernetes:batch/v1:CronJob    update
~   vpc-native-generic-referral-reminder-cron                  kubernetes:batch/v1:CronJob    update
+   vpc-native-api-db-migration-f7d9c16d                       kubernetes:batch/v1:Job        create
~   vpc-native-update-source-tag-view-cron                     kubernetes:batch/v1:CronJob    update
~   vpc-native-daily-digest-cron                               kubernetes:batch/v1:CronJob    update
~   vpc-native-ws-deployment                                   kubernetes:apps/v1:Deployment  update
~   vpc-native-clean-zombie-opportunities-cron                 kubernetes:batch/v1:CronJob    update
~   vpc-native-bg-deployment                                   kubernetes:apps/v1:Deployment  update
~   vpc-native-personalized-digest-deployment                  kubernetes:apps/v1:Deployment  update
~   vpc-native-update-current-streak-cron                      kubernetes:batch/v1:CronJob    update
~   vpc-native-clean-zombie-images-cron                        kubernetes:batch/v1:CronJob    update
~   vpc-native-clean-zombie-users-cron                         kubernetes:batch/v1:CronJob    update
~   vpc-native-sync-subscription-with-cio-cron                 kubernetes:batch/v1:CronJob    update
~   vpc-native-calculate-top-readers-cron                      kubernetes:batch/v1:CronJob    update
~   vpc-native-user-profile-updated-sync-cron                  kubernetes:batch/v1:CronJob    update
~   vpc-native-private-deployment                              kubernetes:apps/v1:Deployment  update
~   vpc-native-expire-super-agent-trial-cron                   kubernetes:batch/v1:CronJob    update
~   vpc-native-user-profile-analytics-clickhouse-cron          kubernetes:batch/v1:CronJob    update
-   vpc-native-api-db-migration-04b17055                       kubernetes:batch/v1:Job        delete
~   vpc-native-hourly-notification-cron                        kubernetes:batch/v1:CronJob    update
+   vpc-native-api-clickhouse-migration-f7d9c16d               kubernetes:batch/v1:Job        create
~   vpc-native-update-views-cron                               kubernetes:batch/v1:CronJob    update
~   vpc-native-post-analytics-history-day-clickhouse-cron      kubernetes:batch/v1:CronJob    update
~   vpc-native-user-posts-analytics-refresh-cron               kubernetes:batch/v1:CronJob    update
~   vpc-native-deployment                                      kubernetes:apps/v1:Deployment  update
~   vpc-native-update-tags-str-cron                            kubernetes:batch/v1:CronJob    update
... and 1 other changes

[rebelchris]

@claude one of the tests is failing now, can you ensure all circleCI are green?

[claude]

Claude finished @rebelchris's task in 2m 59s —— View job

---

Unable to identify failing test

• Check CircleCI status to identify failing test(s)
• Read test files and implementation to understand the issue
• Review code changes for potential issues

Analysis

I've thoroughly reviewed the PR changes and cannot identify a failing test. Here's what I found:

Code Changes Look Correct:

1. ✅ MAX_STACK_ITEMS = 100 constant added to src/common/constants.ts
2. ✅ parseLimit() function updated to accept optional maxLimit parameter (defaults to MAX_LIMIT = 50)
3. ✅ Stack route updated to use parseLimit(request.query.limit, MAX_STACK_ITEMS)
4. ✅ GraphQL resolvers updated with max count validation
5. ✅ New tests added for max stack size enforcement

CI Status:

• GitHub Actions: All workflows passing ✅
• CircleCI: I cannot access the detailed CircleCI logs from this environment

Potential Issues Checked:

• ✅ All other parseLimit() usages default correctly to MAX_LIMIT = 50
• ✅ Test isolation - beforeEach doesn't interfere with new test
• ✅ Type safety - no TypeScript errors apparent
• ✅ Backward compatibility - existing endpoints unaffected

Next Steps

Could you provide:

1. The specific test name that's failing in CircleCI
2. The error message from the CircleCI logs
3. Or a link to the failing CircleCI build

This will help me pinpoint the exact issue and fix it.

--- | Branch: eng-696-adding-to-stack-fails-when-stack-has-50-items

[rebelchris]

@claude one test keeps failing:
POST /public/v1/feeds/custom should create a new custom feed

[claude]

Claude finished @rebelchris's task in 2m 28s —— View job

---

Test failure analysis

• Read the failing test to understand what it's testing
• Check how parseLimit() changes affect custom feeds endpoint
• Analyze GitHub Actions CI status
• Identify root cause from CircleCI logs

---

Findings

I've analyzed the PR changes and the test file. Here's what I found:

Code changes are correct:

• The parseLimit() function now accepts an optional second parameter maxLimit with a default value of MAX_LIMIT (50)
• This is backward compatible - all existing calls to parseLimit() without the second parameter will work as before
• The custom feeds endpoints at src/routes/public/customFeeds.ts:313 and :390 call parseLimit(request.query.limit) without the second parameter, which is correct

CI Status:

• ✅ GitHub Actions workflows are passing (CodeQL, Jira comment)
• ❓ Cannot access detailed CircleCI logs from this environment

Possible causes:

1. Test ordering/isolation issue: The new stack test creates 60 UserStack items. If there's a test isolation problem, this could affect subsequent tests
2. Database state: The customFeeds test might be affected by leftover data from stack tests
3. CircleCI-specific environment issue: Different test execution order or environment setup

Need your help

Could you please share:

1. The specific error message from CircleCI for "POST /public/v1/feeds/custom should create a new custom feed"
2. Or a link to the CircleCI build logs

This will help me pinpoint the exact failure and provide a fix. The code changes themselves appear correct, so the issue is likely environmental or test-ordering related.

---

View job | Branch: eng-696-adding-to-stack-fails-when-stack-has-50-items