You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The machine integration job keeps failing on 429 Too Many Requests from the Backend API. All 21 failed job logs I pulled (from 30 failed machine jobs in the last 150 CI runs) show it. Most of the 429s come from createFakeMachineNetwork in beforeAll, and the rest from creating and deleting OAuth apps.
Two things cause it:
beforeAll runs once per worker. The machine auth describe blocks use mode: 'parallel'. In that mode Playwright runs beforeAll in every worker that picks up a test from the block, so each block boots several apps and creates several sets of machines and tokens against the shared with-api-keys instance. Each CI retry runs it again. A local test with Playwright 1.62.1 and 4 workers ran beforeAll 4 times in parallel mode and once in default mode.
No backoff on 429.createTestUtils already wraps its client in withRetry (integration/testUtils/index.ts), but createMachineClient and createOAuthClient created plain clients, so one 429 failed the whole block.
This PR:
Switches the machine auth describe blocks in machineAuthHelpers.ts and next-machine.test.ts to mode: 'default'. Each block now sets up once, and blocks still run in parallel across workers.
Wraps createMachineClient and createOAuthClient in the existing withRetry.
Not yet verified: the machine suite hasn't been run against the real instances. This PR's CI run will be the first check.
Checklist
pnpm test runs as expected.
pnpm build runs as expected.
(If applicable) JSDoc comments have been added or updated for any package exports
Run each machine auth describe block in default mode so beforeAll runs
once per block instead of once per worker, and wrap the machine and
OAuth Clerk clients in withRetry so 429s back off instead of failing.
No actionable comments were generated in the recent review.
Walkthrough
The machine and OAuth Clerk test clients now use withRetry. Five machine-related Playwright test groups change from parallel to default mode. The CI integration-test command adds --force for the machine test case; the Electron command remains unchanged. The changeset file adds empty frontmatter and declares no package, release type, or description.
Machine and OAuth setup retries could leave duplicate resources or make cleanup fail after an ambiguous server error. This is a low-risk, non-blocking concern for the test infrastructure.
Pre-merge checks: 5
Check name
Status
Explanation
Title check
The title clearly and concisely describes the main change: preventing machine authentication end-to-end tests from triggering BAPI rate limits.
Description check
The description directly explains the reported 429 failures and the changes to Playwright execution mode and retry handling.
Docstring Coverage
No eligible functions found in the changed files. Skipping docstring coverage check. Docstring coverage is scoped to functions touched by this diff with cyclomatic complexity of at least 2. Documentat…
Linked Issues check
Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check
Check skipped because no linked issues were found for this pull request.
Full details: Docstring Coverage
Explanation
No eligible functions found in the changed files. Skipping docstring coverage check. Docstring coverage is scoped to functions touched by this diff with cyclomatic complexity of at least 2. Documentation-only edits and deletions within surviving functions are included; unchanged diff context and fully deleted functions are excluded. Analyzed 0 functions across 2 files. (1 skipped: 1 unsupported.)
Autofix · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts
Warning
Linked repositories: Some configured repositories could not be included in this review. Cross-repository analysis may be incomplete. Please check linked-repository access and settings.
Machine auth blocks set up once, still parallel across blocks
Each M2M block now runs beforeAll once on its own worker instead of 3 times across 3 workers, cutting mock BAPI writes from 64 to 24 with all 12 tests passing and the two blocks still on separate workers.
Merge-base
This PR a765c9dd
Also checked · 1 match · 1 not run
Machine suite against real instances · Blocked Machine and OAuth clients retry a 429
Important
Blocked on missing secrets
Machine suite against real instances: Running the real machine suite against the with-api-keys instance needs INTEGRATION_INSTANCE_KEYS, which the sandbox lacks. The PR's CI run is the check for this.
Proof on a765c9dd · Did Proof get it right? Yes · No
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
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.
wobsoriano
left a comment
Description
The
machineintegration job keeps failing on429 Too Many Requestsfrom the Backend API. All 21 failed job logs I pulled (from 30 failedmachinejobs in the last 150 CI runs) show it. Most of the 429s come fromcreateFakeMachineNetworkinbeforeAll, and the rest from creating and deleting OAuth apps.Two things cause it:
beforeAllruns once per worker. The machine auth describe blocks usemode: 'parallel'. In that mode Playwright runsbeforeAllin every worker that picks up a test from the block, so each block boots several apps and creates several sets of machines and tokens against the sharedwith-api-keysinstance. Each CI retry runs it again. A local test with Playwright 1.62.1 and 4 workers ranbeforeAll4 times inparallelmode and once indefaultmode.createTestUtilsalready wraps its client inwithRetry(integration/testUtils/index.ts), butcreateMachineClientandcreateOAuthClientcreated plain clients, so one 429 failed the whole block.This PR:
machineAuthHelpers.tsandnext-machine.test.tstomode: 'default'. Each block now sets up once, and blocks still run in parallel across workers.createMachineClientandcreateOAuthClientin the existingwithRetry.Not yet verified: the machine suite hasn't been run against the real instances. This PR's CI run will be the first check.
Checklist
pnpm testruns as expected.pnpm buildruns as expected.Type of change