test(system): compare Auto-tagging with the concept against the real backend

This commit is contained in:
Vito Sansevero
2026-10-27 00:24:48 -07:00
parent 584cf5fed6
commit 106c2c67fd
2 changed files with 17 additions and 6 deletions
@@ -285,7 +285,7 @@ function mapBatchConcept(reference, plan) {
title: 'Review tag output images',
tree: ['h3', 'dl.meta-grid', 'p.small', 'div.notice', 'div.dialog-actions'],
heading: { ...reference.heading, text: 'Tag output images' },
grid: { ...reference.grid, rows: [['Model', 'WD14 SwinV2 · ~400 MB'], ['Existing tags', 'Skip already tagged'],
grid: { ...reference.grid, rows: [['Model', 'WD14 SwinV2 · ~400 MB'], ['Existing tags', 'Merge with existing'],
['Images linked', number(plan.images)], ['Prompts', number(plan.prompts)], ['Already tagged', number(plan.already_tagged)],
['Prompts to tag', `up to ${number(plan.to_tag)}`], ['Settings', 'General 0.35 · Character 0.85'],
['Backup', 'Create and verify before changes']] },
@@ -308,6 +308,9 @@ async function conceptReview(page, theme) {
async function productionReview(page, theme) {
await productionTagging(page, theme);
// Every concept-fixture prompt with an image is already tagged, so under the saved Skip there is nothing to start
// (the Cancel-only review). Merge reviews a batch with work: the full review the concept's shell is compared with.
await page.locator('#workspace-main #tag-existing').selectOption('merge');
const answer = page.waitForResponse(response => response.url().endsWith(PREVIEW_URL));
await page.locator('#workspace-main .operation').getByRole('button', { name: 'Review', exact: true }).click();
const plan = await (await answer).json();
@@ -323,7 +326,7 @@ for (const theme of THEMES) for (const [width, height] of SIZES) {
expect(concept.tree).toEqual(['p.demo-note', 'h3', 'dl.meta-grid', 'p.small', 'div.dialog-actions']);
await page.screenshot({ path: testInfo.outputPath(`concept-plan-review-${theme}-${width}.png`) });
const { plan, production } = await productionReview(page, theme);
// The concept fixture links images to prompts, some untagged: the batch has work to review.
// Under Merge every prompt with a linked image is tagged again: the batch has work to review.
expect(plan.to_tag).toBeGreaterThan(0);
await page.screenshot({ path: testInfo.outputPath(`production-tagging-review-${theme}-${width}.png`) });
expect(diffInventory(mapBatchConcept(concept, plan), production)).toEqual([]);
@@ -164,7 +164,8 @@ test('defaults save through Save preferences and the Tag image dialog uses them'
test('a refused value shows the server\'s message', async ({ page, request }) => {
const before = (await serverJson(request, SETTINGS_URL)).settings;
await openTagging(page);
// An image is selected, so Preview tagging review is held back only by the invalid value below.
await selectThenOpen(page, FIRST);
await page.locator('#threshold-general').fill('1.5');
await page.locator('#threshold-general').press('Tab');
await save(page).click();
@@ -173,13 +174,18 @@ test('a refused value shows the server\'s message', async ({ page, request }) =>
// Nothing was written; the draft is kept for the next Save.
expect((await serverJson(request, SETTINGS_URL)).settings.autotag_general_threshold).toBe(before.autotag_general_threshold);
await expect(page.locator('#threshold-general')).toHaveValue('1.5');
// While the value is invalid, Preview tagging review explains instead of opening.
await actionOf(page, 'Preview tagging review').click();
// While the value is invalid, Preview tagging review is aria-disabled and explains instead of opening (Playwright
// waits on an aria-disabled control, so it is pressed from the keyboard, as a user can).
await expect(actionOf(page, 'Preview tagging review')).toHaveAttribute('aria-disabled', 'true');
await actionOf(page, 'Preview tagging review').focus();
await page.keyboard.press('Enter');
await expect(toast(page)).toHaveText('General-tag confidence must be between 0 and 1.');
await expect(tagDialog(page)).toHaveCount(0);
await page.locator('#threshold-general').fill('0.5');
await page.locator('#threshold-general').press('Tab');
await expect(page.locator('#threshold-general')).not.toHaveAttribute('aria-invalid', 'true');
await expect(status(page)).toHaveText('Unsaved changes.');
await expect(actionOf(page, 'Preview tagging review')).not.toHaveAttribute('aria-disabled', 'true');
});
test('Download starts the job and Activity shows it without Cancel', async ({ page, request }) => {
@@ -341,7 +347,9 @@ test('a model that is not downloaded cannot be reviewed for a batch; the button
await openTagging(page);
await page.locator('#tag-model').selectOption('gguf');
await expect(reviewButton(page)).toHaveAttribute('aria-disabled', 'true');
await reviewButton(page).click();
// Playwright waits on an aria-disabled control: press it from the keyboard, as a user can.
await reviewButton(page).focus();
await page.keyboard.press('Enter');
await expect(toast(page)).toHaveText('GGUF JoyCaption is not downloaded. Download it first.');
await expect(dialog(page)).toHaveCount(0);
expect(page.modelCalls.filter(call => call.includes('/batch/preview'))).toEqual([]);