Skip to content

Commit b6ae87c

Browse files
test(qa-scenarios): add the travel_expense mid-tier scenario card (#30600)
<!-- claude-projects-attribution: {"github_login":"marchtian"} --> _Requested by **田騏** · [project thread](https://claude.ai/code/project/chan_01VmuUhXU9SSUzqJYyXSmYSi?thread=cmsg_01VmuUhXU9SSUzqJYyXSmYSiNjyvCdXYygFqntMNR7S2dW)_ Fixes #30476 Clause-②: no Metadata-protocol: none ## 维护者速读 - **改了什么**:新增「差旅报销」中档场景卡(7 个对象、两级审批、3 个角色其中 2 个按行限定、1 个支出报表、120 张报销单跨 7–10 月、10 道问数、6 个写操作、4 个 agent 动作),并配一份只属于这张卡的真值测试。 - **为什么改**:落实 cloud#3600 九个场景中的财务场景,让 AI 建应用、问数、代办写操作都有一张能用代码判分的差旅报销卡。 - **风险与回滚**:只加测试数据和测试,所在包私有、不发布,运行时零改动;回滚即删两个新文件并还原 `library.test.ts` 一行。 - **先看**:① `docs/qa/scenarios/travel_expense.json` 的 `run.questions` 与 `run.operations`;② `packages/qa/scenarios/test/travel-expense.test.ts` 的 `EXPECTED_TRUTHS`;③ `packages/qa/scenarios/test/library.test.ts` 第 102 行(控制卡清单加了本卡)。 - **两分钟验证**:`pnpm --filter @objectstack/scenarios test`,预期 4 个测试文件、64 个用例全绿。 - **需要你做的**:无,席位落地。 ## What changes - `docs/qa/scenarios/travel_expense.json` (new): the 差旅报销 travel-expense mid-tier card. - Seven objects: `department`, `employee`, `travel_standard` (a cap per grade and expense type), `trip_request`, `expense_claim`, `claim_line` and `approval_step` (the two-step approval: department manager, then Finance). - Three personas: `employee` (own rows) and `dept_manager` (own department) carry a row scope; `finance_officer` sees every claim but no trip request. - Seed: 120 claims dated July to October 2026, plus 280 lines, 204 approval steps and 126 trips. The arithmetic rule that generated it is stated in the card's `$comment`, so every truth can be worked by hand. - Run half: 10 questions, 6 operations and 4 agent actions (one confirm-gated); `iterate` adds travel advances. - `packages/qa/scenarios/test/travel-expense.test.ts` (new): this card's own test file. - It pins all 10 computed truths and the 7 per-persona truths against hand-worked values. - It asserts the mid-tier floor and the seed's own consistency: each claim total is the sum of its lines, and a line is `over_standard` exactly when it is above the grade cap. - It shows that a wrong seed cell or a wrong truth spec in a fixture copy goes red against those pins. - `packages/qa/scenarios/test/library.test.ts`: one line. The library-wide test asserts the exact set of loaded card ids, so `travel_expense` is added to that list. Its truths are pinned in the card's own file, not here. ## Tests `pnpm --filter @objectstack/scenarios test`: 4 files, 64 tests passed. `pnpm --filter @objectstack/scenarios typecheck`: exit 0, after building the closure with `pnpm --filter '@objectstack/scenarios^...' build`. ## Acceptance notes - **File name.** The card is `travel_expense.json`, not `travel-expense.json` as the issue spells it. A card's `id` must be a snake_case machine name, and the loader requires it to equal the file's basename, so a hyphenated basename cannot load. The schema was not changed. - **No schema field for some floor items.** Three floor items have no field in the schema: - an approval or automation flow as a structural expectation; - "declarative preferred"; - a report as distinct from a dashboard. The card states them in `prompt.detailed` (zh and en) and in `capabilities`, seeds `approval_step` as an expected object, and declares the report under `expect.dashboards`. Nothing in the loader grades them. - **Seven operation kinds, six operations.** The issue names seven operation kinds and caps the card at six operations. So `file_and_submit_from_text` covers two of them: entry from free text with lines, and the multi-step chain (file, add two lines, submit, route to the manager). - **Routed approval step not asserted.** The post-state of `file_and_submit_from_text` does not assert the routed step-1 row. A `where` cannot name the new claim's id, and `step 1 · approver e01 · pending` also matches a seeded row. - **README step 3.** `docs/qa/scenarios/README.md` "Adding a card" step 3 says to add a card's truths to `test/library.test.ts`, but this card's truths live in its own file. The README is unchanged here. - **Sibling cards.** Every sibling mid-tier card has to edit the same `library.test.ts` line, so their PRs will conflict on it in turn. - **Unreachable references.** `objectstack-ai/templates` and `objectstack-ai/cloud` answer 403 from this session. The domain is designed from the card text alone, and the rulings are applied as the card states them. ## Verification <details> <summary>scenarios test + typecheck (head 130acb8)</summary> ``` Test Files 4 passed (4) Tests 64 passed (64) > tsc --noEmit os-verify-lock: VERDICT command-exit 0 ``` </details> <details> <summary>dispatch-gates --commands (50 commands, local)</summary> All 50 derived commands exit 0. The `--ran` reconciliation reads: 50 derived, 50 run, 0 NOT-MEASURED, 0 UNRUN, a derived zero because every line recorded its exit code. Three of them first exited 3 (PREREQUISITE NOT MET: a dist was not built). Each exited 0 after the build it names: - `check:doc-formula-expressions`, after building `@objectstack/formula` and `@objectstack/lint`; - `check:lean-entry-closure`, after building `@objectstack/objectql`; - `check:dual-build-cjs-loads`, after a full `turbo run build`. Changed lines: 1337 (+1336 / -1, 3 files), under the 3000 threshold. </details> --- 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude <noreply@anthropic.com>
1 parent 135c2fb commit b6ae87c

4 files changed

Lines changed: 1343 additions & 3 deletions

File tree

‎docs/qa/scenarios/README.md‎

Lines changed: 3 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -156,4 +156,6 @@ meet this floor:
156156
1. Write `<id>.json` here; `id` equals the basename.
157157
2. Keep it generic — a scenario anyone could write from the domain alone.
158158
3. Run `pnpm --filter @objectstack/scenarios test`: a refusal names the file and the field
159-
path. Then add the card's hand-worked truths, per persona too, to `test/library.test.ts`.
159+
path. Then pin the card's hand-worked truths, per persona too, in its own
160+
`packages/qa/scenarios/test/<id>.test.ts` (model: `travel-expense.test.ts`). The three control
161+
cards keep theirs in `test/library.test.ts`.

0 commit comments

Comments
 (0)