fix: distinguish review, output validation and connection failures in grading UI
This commit is contained in:
+10
-4
@@ -31,8 +31,14 @@ const evidencePlace = (evidence: any) => `第 ${evidence.page} ${isSlideEvidence
|
||||
const evidencePreviewLabel = (evidence: any) => isSlideEvidence(evidence) ? '查看该张幻灯片的完整图像' : '查看该页的完整图像';
|
||||
const pageTypeLabels: Record<string, string> = { cover: '封面', abstract: '摘要', toc: '目录', body: '正文', appendix: '附录', references: '参考文献', unknown: '识别不确定', mixed: '目录与正文混合页' };
|
||||
const pageTypeLabel = (value: string) => pageTypeLabels[value] || '未分类页面';
|
||||
const statusLabels: Record<string, string> = { pending: '待评分', scored: '模型已评分', reviewed: '教师已复核', needs_review: '待教师复核', unscorable: '材料缺失或解析失败', failed: '模型调用失败' };
|
||||
const statusLabels: Record<string, string> = { pending: '待评分', scored: '模型已评分', reviewed: '教师已复核', needs_review: '待教师复核', unscorable: '材料缺失或解析失败', failed: '评分失败' };
|
||||
const statusLabel = (value: string) => statusLabels[value] || value;
|
||||
const scoreStatusLabel = (row: any) => {
|
||||
if (row.status !== 'failed') return statusLabel(row.status);
|
||||
if (/模型证据|target_id|评分项或满分|JSON校验/.test(row.error || '')) return '模型输出校验失败';
|
||||
if (/ConnectError|Timeout|Network|连接|超时|HTTP/i.test(row.error || '')) return '模型连接失败';
|
||||
return '评分失败';
|
||||
};
|
||||
const statusColor = (value: string) => ({ scored: 'green', reviewed: 'green', needs_review: 'gold', unscorable: 'red', failed: 'red' }[value] || 'blue');
|
||||
const batchStatusLabels: Record<string, string> = { created: '待启动', queued: '排队中', running: '运行中', completed: '已完成', review_required: '已完成，有待复核项', partial: '部分完成', failed: '失败' };
|
||||
const batchStatusLabel = (value: string) => batchStatusLabels[value] || value;
|
||||
@@ -52,7 +58,7 @@ function JsonField({ value, onChange, disabled, rows = 4, resetKey }: { value: a
|
||||
function Dashboard() {
|
||||
const [data, setData] = useState<any>({});
|
||||
useEffect(() => { load('/dashboard', setData); }, []);
|
||||
return <><Title level={2}>工作概览</Title><Paragraph>先确认课程版本与规则，再扫描挂载目录，创建评分批次并逐项复核。</Paragraph><Row gutter={18}>{[['课程', data.courses], ['学生项目', data.projects], ['评分批次', data.batches], ['待处理评分项', data.needs_attention], ['待教师复核', data.needs_review]].map(([label, count]) => <Col xs={24} sm={12} lg={4} key={label}><Card><Statistic title={label} value={count ?? 0} /></Card></Col>)}</Row><Alert className="top-gap" type="info" showIcon message="学生材料仅从只读挂载目录读取；缺失和解析失败的材料会在项目与评分详情中标出。“待教师复核”表示该项只检索到目录、摘要或章节标题，没有可用于内容判断的正文证据，系统不会自动给低分。" /></>;
|
||||
return <><Title level={2}>工作概览</Title><Paragraph>先确认课程版本与规则，再扫描挂载目录，创建评分批次并逐项复核。</Paragraph><Row gutter={18}>{[['课程', data.courses], ['学生项目', data.projects], ['评分批次', data.batches], ['待处理评分项', data.needs_attention], ['待教师复核', data.needs_review]].map(([label, count]) => <Col xs={24} sm={12} lg={4} key={label}><Card><Statistic title={label} value={count ?? 0} /></Card></Col>)}</Row><Alert className="top-gap" type="info" showIcon message="学生材料仅从只读挂载目录读取；缺失和解析失败的材料会在项目与评分详情中标出。“待教师复核”表示未检索到可用正文，或模型认为当前证据不足以自动评分；请查看具体原因，系统不会自动给低分。" /></>;
|
||||
}
|
||||
|
||||
function Courses() {
|
||||
@@ -233,8 +239,8 @@ function Scores({ batchId, projectId }: { batchId?: number; projectId?: number }
|
||||
</Space>
|
||||
{selectedBatch && <Alert className="top-gap" type="info" showIcon
|
||||
message={`批次 #${batch} 包含 ${scopedProjects.length} 个项目。下方分数仅对应当前选中的学生项目。`} />}
|
||||
{result && <>{result.rows.some((r: any) => r.status === 'failed') && <Alert className="top-gap" type="error" showIcon message={`当前项目有 ${result.rows.filter((r: any) => r.status === 'failed').length} 项评分失败`} description="具体原因见下表。网络恢复后，可在评分批次页点击启动/重试；已经成功的评分和教师复核会保留。" />}<Card className="top-gap" title={`${result.student_no} ${result.name} · ${result.topic}`}><Space wrap>{Object.entries(result.totals).map(([key, value]) => <Tag key={key} color={value === null ? 'orange' : 'blue'}>{key}: {String(value ?? '待处理')}</Tag>)}</Space>{result.facts?.consistency_issues?.length > 0 && <Alert className="top-gap" type="warning" message="跨文档一致性提醒" description={result.facts.consistency_issues.map((issue: any) => issue.description).join('；')} />}</Card><Table className="top-gap" rowKey={(row: any) => row.criterion.criterion_id} dataSource={result.rows} pagination={false} columns={[{ title: '评分项', render: (_, r) => <><Tag>{categories[r.criterion.category] || r.criterion.category}</Tag>{r.criterion.name}</> }, { title: '模型原始分', render: (_, r) => `${r.model_score ?? '—'} / ${r.criterion.max_score}` }, { title: '教师分', render: (_, r) => r.teacher_score ?? '—' }, { title: '最终分', render: (_, r) => r.final_score ?? '待处理' }, { title: '状态 / 失败原因', render: (_, r) => <Space direction="vertical"><Tag color={statusColor(r.status)}>{statusLabel(r.status)}</Tag>{r.error && <Text type="secondary" style={{ maxWidth: 300 }}>{r.error}</Text>}</Space> }, { title: '操作', render: (_, r) => <Button onClick={() => { setReview(r); form.setFieldsValue(reviewFormValues(r)); }}>查看证据/复核</Button> }]} /></>}
|
||||
<Modal open={!!review} title={review?.criterion?.name} width={850} onCancel={() => setReview(undefined)} onOk={async () => { try { const values = await form.validateFields(); await put(`/criterion-scores/${review.score_id}/review`, values); setReview(undefined); refresh(); message.success('复核记录已保存'); } catch (e) { fail(e); } }} okText="保存教师复核" okButtonProps={{ disabled: !review?.score_id }}>{review && <>{review.status === 'needs_review' && <Alert type="warning" showIcon className="top-gap" message="本项缺少正文证据，需要教师复核" description={`未找到正文证据的目标：${(review.evidence_gaps || []).map((gap: any) => gap.target_label).join('、') || review.missing_evidence?.join('、') || '见缺失证据'}。系统未给出模型分，也没有按低分处理；请核对材料后直接填写教师评分。`} />}<Descriptions column={1} items={[{ key: 'model', label: '模型分数/评语', children: `${review.model_score ?? '未给出'} · ${review.model_comment || ''}` }, { key: 'confidence', label: '模型置信度', children: review.confidence ?? '—' }, { key: 'missing', label: '缺失证据', children: review.missing_evidence?.join('；') || '无' }, { key: 'gaps', label: '缺正文证据的目标', children: (review.evidence_gaps || []).map((gap: any) => `${gap.target_label}（检索范围：${(gap.searched_page_types || []).map(pageTypeLabel).join('、') || '正文'}）`).join('；') || '无' }, { key: 'suggestion', label: '改进建议', children: review.suggestion || '无' }, { key: 'error', label: '异常', children: review.error || '无' }]} /><Divider />{review.evidence?.map((ev: any, index: number) => <Card size="small" key={index} className="evidence"><Space wrap><Text strong>{ev.document} · {evidencePlace(ev)}</Text><Tag color={ev.page_type === 'body' || ev.page_type === 'appendix' ? 'green' : 'orange'}>{pageTypeLabel(ev.page_type)}</Tag>{ev.historical && <Tag>历史评分引用</Tag>}{ev.target_label && <Tag>{ev.target_label}</Tag>}</Space><Paragraph>{ev.quote}</Paragraph><Space wrap>{ev.url && <a href={ev.url} target="_blank" rel="noreferrer">查看页面文字</a>}{ev.image_url && <a href={ev.image_url} target="_blank" rel="noreferrer">{evidencePreviewLabel(ev)}（核对引文）</a>}</Space></Card>)}<Divider /><Form form={form} layout="vertical"><Form.Item label="教师评分" name="score" rules={[{ required: true, message: '请填写教师评分' }]}><InputNumber min={0} max={review.criterion.max_score} placeholder="请填写" /></Form.Item><Form.Item label="教师评语" name="comment" rules={[{ required: true }]}><Input.TextArea rows={3} /></Form.Item><Form.Item label="修改说明" name="reason"><Input /></Form.Item></Form>{review.score_id && <Button onClick={async () => { try { setRevisions(await api(`/criterion-scores/${review.score_id}/revisions`)); } catch (e) { fail(e); } }}>查看修改记录</Button>}{revisions.length > 0 && <pre className="json-view">{JSON.stringify(revisions, null, 2)}</pre>}</>}</Modal>
|
||||
{result && <>{result.rows.some((r: any) => r.status === 'failed') && <Alert className="top-gap" type="error" showIcon message={`当前项目有 ${result.rows.filter((r: any) => r.status === 'failed').length} 项评分失败`} description="具体原因见下表。连接失败请检查模型端点和网络；输出校验失败可重试，若重复发生请核对具体校验原因。可在评分批次页点击启动/重试；已经成功的评分和教师复核会保留。" />}<Card className="top-gap" title={`${result.student_no} ${result.name} · ${result.topic}`}><Space wrap>{Object.entries(result.totals).map(([key, value]) => <Tag key={key} color={value === null ? 'orange' : 'blue'}>{key}: {String(value ?? '待处理')}</Tag>)}</Space>{result.facts?.consistency_issues?.length > 0 && <Alert className="top-gap" type="warning" message="跨文档一致性提醒" description={result.facts.consistency_issues.map((issue: any) => issue.description).join('；')} />}</Card><Table className="top-gap" rowKey={(row: any) => row.criterion.criterion_id} dataSource={result.rows} pagination={false} columns={[{ title: '评分项', render: (_, r) => <><Tag>{categories[r.criterion.category] || r.criterion.category}</Tag>{r.criterion.name}</> }, { title: '模型原始分', render: (_, r) => `${r.model_score ?? '—'} / ${r.criterion.max_score}` }, { title: '教师分', render: (_, r) => r.teacher_score ?? '—' }, { title: '最终分', render: (_, r) => r.final_score ?? '待处理' }, { title: '状态 / 失败原因', render: (_, r) => <Space direction="vertical"><Tag color={statusColor(r.status)}>{scoreStatusLabel(r)}</Tag>{r.error && <Text type="secondary" style={{ maxWidth: 300 }}>{r.error}</Text>}</Space> }, { title: '操作', render: (_, r) => <Button onClick={() => { setReview(r); form.setFieldsValue(reviewFormValues(r)); }}>查看证据/复核</Button> }]} /></>}
|
||||
<Modal open={!!review} title={review?.criterion?.name} width={850} onCancel={() => setReview(undefined)} onOk={async () => { try { const values = await form.validateFields(); await put(`/criterion-scores/${review.score_id}/review`, values); setReview(undefined); refresh(); message.success('复核记录已保存'); } catch (e) { fail(e); } }} okText="保存教师复核" okButtonProps={{ disabled: !review?.score_id }}>{review && <>{review.status === 'needs_review' && <Alert type="warning" showIcon className="top-gap" message="本项证据不足以自动评分，需要教师复核" description={`缺少或尚不足以支撑判断的目标：${(review.evidence_gaps || []).map((gap: any) => gap.target_label).join('、') || review.missing_evidence?.join('、') || '见缺失证据'}。系统未给出模型分，也没有按低分处理；请核对下方证据，补充或更正材料后重试，或直接填写教师评分。`} />}<Descriptions column={1} items={[{ key: 'model', label: '模型分数/评语', children: `${review.model_score ?? '未给出'} · ${review.model_comment || ''}` }, { key: 'confidence', label: '模型置信度', children: review.confidence ?? '—' }, { key: 'missing', label: '缺失证据', children: review.missing_evidence?.join('；') || '无' }, { key: 'gaps', label: '待核对的证据目标', children: (review.evidence_gaps || []).map((gap: any) => `${gap.target_label}（检索范围：${(gap.searched_page_types || []).map(pageTypeLabel).join('、') || '正文'}）`).join('；') || '无' }, { key: 'suggestion', label: '改进建议', children: review.suggestion || '无' }, { key: 'error', label: '异常', children: review.error || '无' }]} /><Divider />{review.evidence?.map((ev: any, index: number) => <Card size="small" key={index} className="evidence"><Space wrap><Text strong>{ev.document} · {evidencePlace(ev)}</Text><Tag color={ev.page_type === 'body' || ev.page_type === 'appendix' ? 'green' : 'orange'}>{pageTypeLabel(ev.page_type)}</Tag>{ev.historical && <Tag>历史评分引用</Tag>}{ev.target_label && <Tag>{ev.target_label}</Tag>}</Space><Paragraph>{ev.quote}</Paragraph><Space wrap>{ev.url && <a href={ev.url} target="_blank" rel="noreferrer">查看页面文字</a>}{ev.image_url && <a href={ev.image_url} target="_blank" rel="noreferrer">{evidencePreviewLabel(ev)}（核对引文）</a>}</Space></Card>)}<Divider /><Form form={form} layout="vertical"><Form.Item label="教师评分" name="score" rules={[{ required: true, message: '请填写教师评分' }]}><InputNumber min={0} max={review.criterion.max_score} placeholder="请填写" /></Form.Item><Form.Item label="教师评语" name="comment" rules={[{ required: true }]}><Input.TextArea rows={3} /></Form.Item><Form.Item label="修改说明" name="reason"><Input /></Form.Item></Form>{review.score_id && <Button onClick={async () => { try { setRevisions(await api(`/criterion-scores/${review.score_id}/revisions`)); } catch (e) { fail(e); } }}>查看修改记录</Button>}{revisions.length > 0 && <pre className="json-view">{JSON.stringify(revisions, null, 2)}</pre>}</>}</Modal>
|
||||
</>;
|
||||
}
|
||||
|
||||
|
||||
@@ -148,10 +148,15 @@ export function Batches({ openBatch }: { openBatch: (id: number, projectId?: num
|
||||
{ title: '状态', width: 140, render: (_, batch) => <Space wrap>
|
||||
<Tag color={batch.status === 'completed' ? 'green' : batch.status === 'review_required' ? 'gold' : ['partial', 'failed'].includes(batch.status) ? 'orange' : 'blue'}>{labels[batch.status] || batch.status}</Tag>
|
||||
{batch.needs_review > 0 && <Tag color="gold">待复核 {batch.needs_review}</Tag>}
|
||||
{batch.failed > 0 && <Tag color="red">评分失败 {batch.failed}</Tag>}
|
||||
{batch.unscorable > 0 && <Tag color="red">材料异常 {batch.unscorable}</Tag>}
|
||||
</Space> },
|
||||
{ title: '进度', width: 160, render: (_, batch) => <>
|
||||
{ title: '处理进度', width: 190, render: (_, batch) => <>
|
||||
<Typography.Text>{batch.progress_done} / {batch.progress_total} 项</Typography.Text>
|
||||
<Progress percent={batch.progress_total ? Math.round(batch.progress_done / batch.progress_total * 100) : 0} size="small" />
|
||||
{batch.progress_total > 0 && batch.progress_done >= batch.progress_total &&
|
||||
(batch.needs_review > 0 || batch.failed > 0 || batch.unscorable > 0) &&
|
||||
<Typography.Text type="secondary">处理结束，仍有未评分项</Typography.Text>}
|
||||
</> },
|
||||
{ title: '异常', dataIndex: 'error', width: 150 },
|
||||
{ title: '操作', width: 180, render: (_, batch) => <Space wrap>
|
||||
|
||||
@@ -149,6 +149,40 @@ test('failed scoring shows the network error and retry guidance on the page', as
|
||||
await expect(page.getByText(/已经成功的评分和教师复核会保留/)).toBeVisible();
|
||||
});
|
||||
|
||||
test('batch progress exposes failures separately from teacher review', async ({ page }) => {
|
||||
await setup(page);
|
||||
await page.route('**/api/scoring-batches', route => route.fulfill({ json: [{
|
||||
id: 71, course_version_id: 1, project_ids: [11], status: 'partial',
|
||||
progress_done: 22, progress_total: 22, needs_review: 2, failed: 1, unscorable: 0,
|
||||
}] }));
|
||||
await page.goto('/?page=batches');
|
||||
const row = page.getByRole('row').filter({ hasText: '#71' });
|
||||
await expect(row).toContainText('评分失败 1');
|
||||
await expect(row).toContainText('待复核 2');
|
||||
await expect(row).toContainText('处理结束，仍有未评分项');
|
||||
});
|
||||
|
||||
test('output validation and insufficient evidence are not presented as network failures', async ({ page }) => {
|
||||
await setup(page);
|
||||
await page.route('**/api/projects/11/scores?*', route => route.fulfill({ json: {
|
||||
student_no: '9000000001', name: '学生甲', topic: '项目', totals: { overall: null }, facts: {},
|
||||
rows: [
|
||||
{ criterion: { criterion_id: 'stage2.experiment', category: 'stage2', name: '实验方案', max_score: 20 },
|
||||
status: 'failed', error: '模型证据未关联该片段的检索目标', evidence: [] },
|
||||
{ criterion: { criterion_id: 'stage3.plan', category: 'stage3', name: '下一阶段计划', max_score: 10 },
|
||||
status: 'needs_review', error: '模型认为现有正文证据不足以判断该项，转教师复核。',
|
||||
evidence: [], missing_evidence: ['计划'], evidence_gaps: [], model_comment: '当前片段不足。' },
|
||||
],
|
||||
} }));
|
||||
await page.goto('/?page=scores&batch_id=71&project_id=11');
|
||||
await expect(page.getByText('模型输出校验失败', { exact: true })).toBeVisible();
|
||||
await expect(page.getByText('模型调用失败', { exact: true })).toHaveCount(0);
|
||||
await expect(page.getByText(/输出校验失败可重试/)).toBeVisible();
|
||||
await page.getByRole('row').filter({ hasText: '下一阶段计划' }).getByRole('button', { name: '查看证据/复核' }).click();
|
||||
await expect(page.getByText('本项证据不足以自动评分，需要教师复核', { exact: true })).toBeVisible();
|
||||
await expect(page.getByText(/缺少或尚不足以支撑判断的目标：计划/)).toBeVisible();
|
||||
});
|
||||
|
||||
test('a slow project list keeps the student specified in a multi-project batch link', async ({ page }) => {
|
||||
const state = await setup(page);
|
||||
await page.route('**/api/scoring-batches', route => route.fulfill({ json: [{
|
||||
|
||||
Reference in New Issue
Block a user