From af7d0b1824ca06dc5a3e6fe21919039468f8f344 Mon Sep 17 00:00:00 2001 From: DongHyeonka Date: Wed, 4 Nov 2026 20:59:31 +0900 Subject: [PATCH] =?UTF-8?q?fix(browser-transfer):=20=EC=9E=AC=EC=A1=B0?= =?UTF-8?q?=EC=A0=95=EC=97=90=EC=84=9C=20checkpoint=20=EC=82=AD=EC=A0=9C?= =?UTF-8?q?=EA=B0=80=20=EC=8B=A4=ED=8C=A8=ED=95=B4=EB=8F=84=20resourceId?= =?UTF-8?q?=EB=A5=BC=20=EC=A4=80=EB=8B=A4?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 문제: complete 응답을 잃은 뒤 다음 upload()가 재조정해 서버 status QUARANTINED를 찾았을 때, 로컬 checkpoint 삭제가 한 번 실패하면 runtime이 그 실패를 그대로 돌려준다({UNAVAILABLE, UPLOAD_RECONCILE, retryable:true, RESUME}). 서버에는 자원이 이미 있는데 이 호출은 resourceId를 잃는다. 같은 상황의 complete 경로는 삭제 실패를 무시하고 성공을 준다. 고친 방법: 재조정의 QUARANTINED 분기도 complete 경로와 같이 삭제 결과와 상관없이 {QUARANTINED, resourceId, replayed:true}를 준다. 남은 행은 다음 upload()나 abort()가 같은 자원으로 정리한다. 설계 문서 4.3절의 같은 규칙 줄에 재조정 경우를 더했다. 위험·한계: 삭제가 계속 실패하는 저장소에서는 행이 남는다. 다음 호출마다 status를 한 번 읽고 같은 resourceId를 replayed로 준다. complete 경로와 같은 한계다. 검증: - 새 테스트: 고치기 전 {ok:false, UNAVAILABLE, UPLOAD_RECONCILE} (리뷰 X4와 같다), 고친 뒤 {ok:true, QUARANTINED, resource_01, replayed:true}, 행 남음, 다음 호출이 정리 - 영역 단위 테스트 15파일 276건 통과 - check:types(test), eslint(바꾼 파일) 통과 Refs: docs/reviews/2026-11-03-maturity-review/01-adapters-browser-transfer.md 0929/01-02 --- .../presigned-transfer-and-image-cdn.md | 4 +- .../resumable-upload-runtime.ts | 11 ++-- .../resumable-upload-runtime-recovery.test.ts | 50 +++++++++++++++++++ 3 files changed, 58 insertions(+), 7 deletions(-) diff --git a/docs/architecture/presigned-transfer-and-image-cdn.md b/docs/architecture/presigned-transfer-and-image-cdn.md index a608520f..cce2e93c 100644 --- a/docs/architecture/presigned-transfer-and-image-cdn.md +++ b/docs/architecture/presigned-transfer-and-image-cdn.md @@ -390,7 +390,9 @@ complete 결과를 모를 때 클라이언트는 다음처럼 동작한다. resourceId 없이 닫는다(`resumable-upload-runtime.ts` `readCompletedResourceId`). - 서버가 complete를 반영한 뒤 로컬 checkpoint 삭제가 실패해도(IndexedDB 오류, complete 직후 caller abort) `upload()`는 성공을 돌려준다. 남은 행은 다음 - `upload()`나 `abort()`가 같은 자원으로 정리한다. + `upload()`나 `abort()`가 같은 자원으로 정리한다. 응답을 잃은 complete를 다음 + `upload()`가 재조정해 서버 status `QUARANTINED`를 찾았을 때도 같다 + (0929/01-02, `reconcileActiveCheckpoint`). 서버 계약 — complete 진행 중(`ResumableUploadControlPlane.complete` 주석): diff --git a/src/adapters/browser-transfer/resumable-upload/resumable-upload-runtime.ts b/src/adapters/browser-transfer/resumable-upload/resumable-upload-runtime.ts index 9599873d..da280ebe 100644 --- a/src/adapters/browser-transfer/resumable-upload/resumable-upload-runtime.ts +++ b/src/adapters/browser-transfer/resumable-upload/resumable-upload-runtime.ts @@ -582,12 +582,11 @@ async function reconcileActiveCheckpoint( ); if (!status.ok) return status; if (status.value.state === "QUARANTINED") { - const removed = await removeCheckpoint( - dependencies, - checkpoint, - request.signal, - ); - if (!removed.ok) return removed; + // 0929/01-02. The server already holds the resource. A failed local + // cleanup leaves the row for the next upload() or abort(), which finds the + // same resource; it does not cost this caller the resourceId, as on the + // complete path. + await removeCheckpoint(dependencies, checkpoint, request.signal); return browserDataSuccess( Object.freeze({ kind: "COMPLETED" as const, diff --git a/tests/unit/resumable-upload-runtime-recovery.test.ts b/tests/unit/resumable-upload-runtime-recovery.test.ts index 5f0f8f27..35959762 100644 --- a/tests/unit/resumable-upload-runtime-recovery.test.ts +++ b/tests/unit/resumable-upload-runtime-recovery.test.ts @@ -751,6 +751,56 @@ describe("resumable upload completed-result reporting (01-02)", () => { expect(checkpoints.rows.has(key)).toBe(false); }); + // 0929/01-02 (2026-11-03 리뷰 2절). The reconcile path finds the lost + // complete applied; a failed local cleanup must not cost the caller the + // resourceId, exactly as on the complete path above. + it("reports the reconciled resource even when the local checkpoint cleanup fails", async () => { + const harness = committingHarness("LOST"); + const checkpoints = new MemoryCheckpointStore(); + const remove = checkpoints.remove.bind(checkpoints); + let failRemove = false; + checkpoints.remove = async (input) => + failRemove + ? browserDataFailure("UNAVAILABLE", "UPLOAD_RECONCILE", { + retryable: true, + recovery: "RESUME", + }) + : await remove(input); + const runtime = createResumableUploadRuntime({ + controlPlane: harness.control, + partExecutor: executorFor(harness), + checkpoints, + mutationLock: noContentionLock, + crypto, + policy: runtimePolicy({ maxRetries: 0 }), + now: () => 1_000, + sleep: async () => {}, + }); + const key = "upload_key_reconcile_cleanup_fails"; + expect((await runtime.upload(request(key))).ok).toBe(false); + + failRemove = true; + const reconciled = await runtime.upload(request(key)); + + expect(reconciled).toEqual({ + ok: true, + value: { + state: "QUARANTINED", + resourceId: "resource_01", + byteLength: 4, + replayed: true, + }, + }); + // The stale row is the next call's to clean up, with the same resource. + expect(checkpoints.rows.has(key)).toBe(true); + failRemove = false; + expect(await runtime.upload(request(key))).toMatchObject({ + ok: true, + value: { resourceId: "resource_01", replayed: true }, + }); + expect(checkpoints.rows.has(key)).toBe(false); + }); + it("returns the resourceId when abort() finds the lost complete already applied", async () => { const harness = committingHarness("LOST"); const checkpoints = new MemoryCheckpointStore();