feat(data-process): 接入重新生成配置流程

2026-07-25 22:41:06 +08:00
parent 396d3f6f47
commit 06e7455630
12 changed files with 648 additions and 145 deletions
--- a/frontend/src/api/modules/dataProcess.ts
+++ b/frontend/src/api/modules/dataProcess.ts
@@ -10,6 +10,8 @@ import type {
  DataProcessPreviewItem,
  DataProcessPreviewUpdatePayload,
  DataProcessProgress,
+  DataProcessRegeneratePayload,
+  DataProcessRegenerateResult,
  DataProcessPublishPayload,
  DataProcessPublishResult,
  DataProcessQualityScore,
@@ -39,6 +41,8 @@ export type {
  DataProcessPreviewItem,
  DataProcessPreviewUpdatePayload,
  DataProcessProgress,
+  DataProcessRegeneratePayload,
+  DataProcessRegenerateResult,
  DataProcessPublishPayload,
  DataProcessPublishResult,
  DataProcessQualityScore,
@@ -74,6 +78,14 @@ export const createDataProcessTask = (payload: DataProcessTaskCreatePayload) =>
 export const updateDataProcessTask = (taskId: string | number, payload: DataProcessTaskUpdatePayload) =>
  put<DataProcessTask>(`/data-process/${encodeURIComponent(taskId)}`, payload)

+export const regenerateDataProcessTask = (
+  taskId: string | number,
+  payload: DataProcessRegeneratePayload,
+) => post<DataProcessRegenerateResult>(
+  `/data-process/${encodeURIComponent(taskId)}/regenerate`,
+  payload,
+)
+
 export const deleteDataProcessTask = (taskId: string | number) =>
  del<{ deleted: string | number }>(`/data-process/${encodeURIComponent(taskId)}`)

--- a/frontend/src/router/index.ts
+++ b/frontend/src/router/index.ts
@@ -140,6 +140,12 @@ const routes: RouteRecordRaw[] = [
        component: () => import('@/views/data-process/DataProcessCreateView.vue'),
        meta: { title: '新建数据处理任务', pageSurface: 'self' },
      },
+      {
+        path: 'data-process/:id/regenerate',
+        name: 'data-process-regenerate',
+        component: () => import('@/views/data-process/DataProcessCreateView.vue'),
+        meta: { title: '重新生成数据处理任务', pageSurface: 'self' },
+      },
      {
        path: 'data-process/:id',
        name: 'data-process-detail',
--- a/frontend/src/stores/models.ts
+++ b/frontend/src/stores/models.ts
@@ -14,7 +14,7 @@ export const useModelsStore = defineStore('models', () => {

  async function load(force = false) {
    if (loaded.value && !force) return
-    if (pendingLoad && !force) return pendingLoad
+    if (pendingLoad) return pendingLoad

    pendingLoad = (async () => {
      try {
@@ -22,6 +22,7 @@ export const useModelsStore = defineStore('models', () => {
        loaded.value = true
      } catch {
        list.value = []
+        loaded.value = false
      } finally {
        pendingLoad = null
      }
--- a/frontend/src/types/dataProcess.ts
+++ b/frontend/src/types/dataProcess.ts
@@ -53,6 +53,7 @@ export interface DataProcessTask {
  started_at?: string | null
  complete_time?: string | null
  completed_at?: string | null
+  updated_at: string
  duration?: string | null
  duration_seconds?: number | null
  failure_reason?: string | null
@@ -74,6 +75,16 @@ export interface DataProcessTaskCreatePayload {
  config: DataProcessConfig
 }

+export interface DataProcessRegeneratePayload extends DataProcessTaskCreatePayload {
+  expected_updated_at: string
+}
+
+export interface DataProcessRegenerateResult {
+  task: DataProcessTask
+  preview_invalidated: boolean
+  published_outputs_preserved: boolean
+}
+
 export type DataProcessTaskUpdatePayload = Partial<DataProcessTaskCreatePayload>

 export interface DataProcessSourceFile {
--- a/frontend/src/views/data-process/DataProcessCreateView.vue
+++ b/frontend/src/views/data-process/DataProcessCreateView.vue
@@ -14,9 +14,12 @@ import { DEFAULT_SOURCE_TEXT, estimateTokenCount } from './create/previewModel'
 import {
  createDefaultStructuredOptions,
  createDefaultUnstructuredOptions,
+  generationAffectingOptionsFor,
+  previewAffectingOptionsFor,
 } from './create/dataProcessCreateState'
 import { useDataProcessGeneration } from './create/useDataProcessGeneration'
 import { useDataProcessPreviewBuild } from './create/useDataProcessPreviewBuild'
+import { useDataProcessRegeneration } from './create/useDataProcessRegeneration'
 import {
  mapDataProcessSourceFile,
  useDataProcessSourceUpload,
@@ -51,7 +54,7 @@ import type {

 const router = useRouter()
 const modelsStore = useModelsStore()
-const { list: modelList } = storeToRefs(modelsStore)
+const { list: modelList, loaded: modelsLoaded } = storeToRefs(modelsStore)
 // 候选范围与模型管理保持一致，不在数据处理页面重复定义模型过滤规则。
 const generationModels = computed(() => modelList.value)
 const taskSetupRef = ref<InstanceType<typeof TaskSetupStep>>()
@@ -98,6 +101,7 @@ const selectedPreviewFileId = ref<string | null>(null)
 const selectedPreviewId = ref<string | null>(null)
 const selectedPreviewIdsByFile = ref<Record<string, string>>({})
 const dirty = ref(false)
+const modelSubmitLoading = ref(false)
 let allowLeave = false

 const {
@@ -236,7 +240,7 @@ function taskPayload() {
  return {
    name: task.name.trim(),
    description: task.description.trim(),
-    process_type: processType.value,
+    process_type: originalProcessType.value || processType.value,
    config: toBackendConfig(),
  }
 }
@@ -274,82 +278,11 @@ function mapPreviewItem(item: DataProcessPreviewItem): PreviewItem {
 }

 function previewAffectingOptions() {
-  if (processType.value === 'structured') {
-    return {
-      preprocessOptions: structuredOptions.value.preprocessOptions,
-    }
-  }
-  if (processType.value === 'unstructured') {
-    const {
-      preprocessOptions,
-      chunkMethod,
-      chunkSize,
-      chunkOverlap,
-      minChunkSize,
-      semanticBreakpointPercentile,
-      preserveTables,
-      preserveCodeBlocks,
-      preserveLists,
-    } = unstructuredOptions.value
-    return {
-      preprocessOptions,
-      chunkMethod,
-      chunkSize,
-      chunkOverlap,
-      minChunkSize,
-      semanticBreakpointPercentile,
-      preserveTables,
-      preserveCodeBlocks,
-      preserveLists,
-    }
-  }
-  return null
+  return previewAffectingOptionsFor(processType.value, structuredOptions.value, unstructuredOptions.value)
 }

 function generationAffectingOptions() {
-  if (processType.value === 'structured') {
-    const {
-      semanticEnrichment, qaPairsPerRow, datasetSplit, generationModelId, generationPrompt,
-      temperature, maxTokens, jsonMode,
-      qualityFilterEnabled, filterLowQuality, filterShortContent, minOutputLength,
-    } = structuredOptions.value
-    return {
-      semanticEnrichment, qaPairsPerRow, datasetSplit, generationModelId, generationPrompt,
-      temperature, maxTokens, jsonMode,
-      qualityFilterEnabled, filterLowQuality, filterShortContent, minOutputLength,
-    }
-  }
-  if (processType.value === 'unstructured') {
-    const {
-      semanticEnrichment,
-      qaPairsPerChunk,
-      datasetSplit,
-      generationModelId,
-      generationPrompt,
-      temperature,
-      maxTokens,
-      jsonMode,
-      qualityFilterEnabled,
-      filterLowQuality,
-      filterShortContent,
-      minOutputLength,
-    } = unstructuredOptions.value
-    return {
-      semanticEnrichment,
-      qaPairsPerChunk,
-      datasetSplit,
-      generationModelId,
-      generationPrompt,
-      temperature,
-      maxTokens,
-      jsonMode,
-      qualityFilterEnabled,
-      filterLowQuality,
-      filterShortContent,
-      minOutputLength,
-    }
-  }
-  return null
+  return generationAffectingOptionsFor(processType.value, structuredOptions.value, unstructuredOptions.value)
 }

 const generationOptionsSignature = computed(() => JSON.stringify(generationAffectingOptions()))
@@ -365,19 +298,58 @@ function buildPreviewSignature() {
  return `${buildPreviewConfigSignature()}:${filesSignature}`
 }

+const {
+  isRegeneration,
+  originalProcessType,
+  regenerationPrepared,
+  hydrating,
+  initializationError,
+  loadSource: loadRegenerationSource,
+  confirmPreviewConfigChange,
+  prepareRegeneration,
+} = useDataProcessRegeneration({
+  task,
+  processType,
+  structuredOptions,
+  unstructuredOptions,
+  uploadedFiles,
+  previewItems,
+  selectedPreviewFileId,
+  selectedPreviewId,
+  selectedPreviewIdsByFile,
+  previewSignature,
+  dirty,
+  buildPreviewConfigSignature,
+  buildPreviewSignature,
+  mapPreviewItem,
+  resetDownstream,
+})
+const leaveWarningMessage = computed(() => regenerationPrepared.value
+  ? '仍有尚未完成的本地操作；已提交到服务端的修改不会因离开页面而撤销。'
+  : '当前存在未保存修改，离开后这些修改将不会保留。')
+const leaveConfirmText = computed(() => regenerationPrepared.value ? '离开页面' : '放弃修改')
+
 watch(
  [() => task.name, () => task.description, processType, structuredOptions, unstructuredOptions, externalSource],
-  () => { dirty.value = true },
+  () => {
+    if (!hydrating.value) dirty.value = true
+  },
  { deep: true },
 )

 watch(processType, (nextType, previousType) => {
+  if (hydrating.value) return
+  if (isRegeneration.value && originalProcessType.value && nextType !== originalProcessType.value) {
+    processType.value = originalProcessType.value
+    return
+  }
  if (nextType === previousType || uploadedFiles.value.length === 0) return
  resetSourceDataForProcessTypeChange()
  ElMessage.info('处理类型已变更，请重新上传或拉取匹配的源数据')
 })

 watch(generationOptionsSignature, (currentSignature, previousSignature) => {
+  if (hydrating.value) return
  if (currentSignature === previousSignature) return
  resetDownstream()
 })
@@ -531,21 +503,50 @@ function resetSourceDataForProcessTypeChange() {
 async function nextFromCreate() {
  const valid = await taskSetupRef.value?.validate()
  if (!valid) return
+  const confirmed = await confirmPreviewConfigChange((options) => (
+    confirmDialogRef.value?.open(options) ?? Promise.resolve(false)
+  ))
+  if (!confirmed) return
  goToStep('model')
 }

 async function nextFromModel() {
-  const valid = await modelSelectionRef.value?.validate()
-  if (!valid) return
+  if (modelSubmitLoading.value) return
+  modelSubmitLoading.value = true
  try {
-    const saved = taskId.value
-      ? await updateDataProcessTask(taskId.value, taskPayload())
-      : await createDataProcessTask(taskPayload())
-    taskId.value = String(saved.id)
+    await modelsStore.load(true)
+    if (!modelsLoaded.value) {
+      ElMessage.error('模型列表加载失败，未提交任何修改，请稍后重试')
+      return
+    }
+    const modelId = modelSelectionOptions.value.generationModelId
+    const modelExists = generationModels.value.some(model => String(model.id) === String(modelId))
+    if (modelId !== '' && !modelExists) {
+      ElMessage.error(isRegeneration.value ? '原任务使用的模型已删除，请重新选择模型' : '所选模型已删除，请重新选择')
+      return
+    }
+    const valid = await modelSelectionRef.value?.validate()
+    if (!valid) return
+    if (isRegeneration.value) {
+      const regenerated = await prepareRegeneration(taskPayload())
+      taskId.value = String(regenerated.task.id)
+      if (regenerated.preview_invalidated) {
+        ElMessage.info('切分配置已变化，现有源文件将在下一步按新配置重新切分')
+      } else if (regenerated.published_outputs_preserved) {
+        ElMessage.info('已保留原切片；已发布的三个数据集将在重新发布前保持不变')
+      }
+    } else {
+      const saved = taskId.value
+        ? await updateDataProcessTask(taskId.value, taskPayload())
+        : await createDataProcessTask(taskPayload())
+      taskId.value = String(saved.id)
+    }
    dirty.value = true
    goToStep('upload')
  } catch {
    // 请求层已展示名称冲突或配置非法等具体原因。
+  } finally {
+    modelSubmitLoading.value = false
  }
 }

@@ -812,8 +813,8 @@ async function handleCancel() {
  }
  const confirmed = await confirmDialogRef.value?.open({
    title: '确认离开当前页面？',
-    message: '当前存在未保存修改，离开后这些修改将不会保留。',
-    confirmText: '放弃修改',
+    message: leaveWarningMessage.value,
+    confirmText: leaveConfirmText.value,
    cancelText: '继续编辑',
    tone: 'danger',
  })
@@ -830,8 +831,8 @@ onBeforeRouteLeave(async () => {
  if (allowLeave || !dirty.value) return true
  const confirmed = await confirmDialogRef.value?.open({
    title: '确认离开当前页面？',
-    message: '当前存在未保存修改，离开后这些修改将不会保留。',
-    confirmText: '放弃修改',
+    message: leaveWarningMessage.value,
+    confirmText: leaveConfirmText.value,
    cancelText: '继续编辑',
    tone: 'danger',
  })
@@ -845,6 +846,7 @@ onBeforeUnmount(() => {
 onMounted(() => {
  localStorage.removeItem('yg-data-process-create-draft')
  void modelsStore.load(true)
+  if (isRegeneration.value) void loadRegenerationSource()
 })
 </script>

@@ -882,15 +884,20 @@ onMounted(() => {
          </div>
        </div>

-        <div class="wizard-content">
+        <div class="wizard-content" v-loading="hydrating">
+          <div v-if="initializationError" class="initialization-error" role="alert">
+            <el-alert type="error" :closable="false" :title="initializationError" show-icon />
+            <el-button type="primary" :loading="hydrating" @click="loadRegenerationSource">重试加载原任务</el-button>
+          </div>
          <TaskSetupStep
-            v-if="currentStepId === 'create'"
+            v-else-if="currentStepId === 'create'"
            ref="taskSetupRef"
            v-model:name="task.name"
            v-model:description="task.description"
            v-model:process-type="processType"
            v-model:structured-options="structuredOptions"
            v-model:unstructured-options="unstructuredOptions"
+            :process-type-locked="isRegeneration"
          />

          <ModelSelectionStep
@@ -974,8 +981,8 @@ onMounted(() => {
        <el-button
          class="wizard-primary-action"
          type="primary"
-          :loading="generation.status === 'running' || (currentStepId === 'upload' && (sourceUploading || previewBuilding))"
-          :disabled="(currentStepId === 'generate' && generation.status === 'running') || previewBuilding || sourceUploading || (currentStepId === 'upload' && hasUnfinishedUploads)"
+          :loading="modelSubmitLoading || generation.status === 'running' || (currentStepId === 'upload' && (sourceUploading || previewBuilding))"
+          :disabled="hydrating || modelSubmitLoading || Boolean(initializationError) || (currentStepId === 'generate' && generation.status === 'running') || previewBuilding || sourceUploading || (currentStepId === 'upload' && hasUnfinishedUploads)"
          @click="handlePrimaryAction"
        >
          {{ primaryActionLabel }} <i class="fa" :class="primaryActionIcon" style="margin-left: 6px;" />
--- a/frontend/src/views/data-process/DataProcessDetailView.vue
+++ b/frontend/src/views/data-process/DataProcessDetailView.vue
@@ -1,7 +1,7 @@
 <script setup lang="ts">
 import { computed, onBeforeUnmount, onMounted, reactive, ref, watch } from 'vue'
 import { useRoute, useRouter } from 'vue-router'
-import { ElMessage, ElMessageBox } from 'element-plus'
+import { ElMessage } from 'element-plus'
 import PageCard from '@/components/PageCard.vue'
 import ModelStatusTag from '@/components/ModelStatusTag.vue'
 import { usePolling } from '@/composables/usePolling'
@@ -167,11 +167,14 @@ const outputDatasets = computed(() => {
 const outputDatasetName = computed(() => (
  outputDatasets.value.map((item) => item.name).join('、')
 ))
-const outputDatasetBaseName = computed(() => {
-  const name = String(outputDatasets.value[0]?.name || '').trim()
-  return name.replace(/-(?:训练集|验证集|测试集)$/, '')
-})
 const outputDatasetId = computed(() => detail.value?.output_dataset_id || null)
+const canRegenerate = computed(() => {
+  const status = detail.value?.status
+  return status === 'pending'
+    || status === 'failed'
+    || status === 'stopped'
+    || (status === 'completed' && Boolean(outputDatasetId.value))
+})
 const creatorName = computed(() => detail.value?.creator_name || detail.value?.creator || '-')
 const createTime = computed(() => detail.value?.create_time || detail.value?.created_at)
 const startTime = computed(() => detail.value?.start_time || detail.value?.started_at)
@@ -428,10 +431,6 @@ function configuredSplit(): DataProcessDatasetSplit {

 function openPublishDialog() {
  if (!detail.value) return
-  if (outputDatasetId.value) {
-    void router.push({ path: '/dataset', query: { tab: 'task', task_id: taskId.value } })
-    return
-  }
  publishForm.dataset_name = `${detail.value.name}-数据集`
  publishForm.split = configuredSplit()
  publishDialogVisible.value = true
@@ -461,31 +460,8 @@ async function publishDataset() {
  }
 }

-async function resyncPublishedDataset() {
-  if (!detail.value || !outputDatasetId.value || publishing.value) return
-  try {
-    await ElMessageBox.confirm(
-      '将按当前 8:1:1 配置同步为训练集、验证集、测试集三个独立数据集。',
-      '重新同步三个数据集？',
-      { type: 'warning', confirmButtonText: '重新同步', cancelButtonText: '取消' },
-    )
-  } catch {
-    return
-  }
-
-  publishing.value = true
-  try {
-    const published = await publishDataProcess(taskId.value, {
-      ...publishForm,
-      dataset_name: outputDatasetBaseName.value || `${detail.value.name}-数据集`,
-      split: configuredSplit(),
-    })
-    const datasets = published.datasets || published.output_datasets || []
-    ElMessage.success(`训练集、验证集和测试集已同步，共 ${datasets.length || 3} 个数据集`)
-    await router.push({ path: '/dataset', query: { tab: 'task', task_id: taskId.value } })
-  } finally {
-    publishing.value = false
-  }
+function startRegeneration() {
+  void router.push({ name: 'data-process-regenerate', params: { id: taskId.value } })
 }

 watch([currentPage, pageSize], () => void loadResults())
@@ -504,20 +480,20 @@ onBeforeUnmount(() => {
          <h1>{{ detail.name }}</h1>
          <ModelStatusTag :status="detail.status" />
          <el-button
-            v-if="detail.status === 'completed'"
+            v-if="detail.status === 'completed' && !outputDatasetId"
            class="publish-button"
            type="primary"
            @click="openPublishDialog"
          >
-            <i class="fa" :class="outputDatasetId ? 'fa-external-link' : 'fa-database'" />
-            {{ outputDatasetId ? '查看三个数据集' : '发布为三个数据集' }}
+            <i class="fa fa-database" />发布为三个数据集
          </el-button>
          <el-button
-            v-if="detail.status === 'completed' && outputDatasetId"
-            :loading="publishing"
-            @click="resyncPublishedDataset"
+            v-if="canRegenerate"
+            class="publish-button"
+            type="primary"
+            @click="startRegeneration"
          >
-            <i class="fa fa-refresh" />重新同步数据集
+            <i class="fa fa-refresh" />重新生成
          </el-button>
        </div>
        <p>{{ detail.description || '暂无任务描述' }}</p>
--- a/frontend/src/views/data-process/create/TaskSetupStep.vue
+++ b/frontend/src/views/data-process/create/TaskSetupStep.vue
@@ -16,6 +16,7 @@ const props = defineProps<{
  processType: ProcessType
  structuredOptions: StructuredProcessOptions
  unstructuredOptions: UnstructuredProcessOptions
+  processTypeLocked?: boolean
 }>()

 const emit = defineEmits<{
@@ -153,7 +154,8 @@ defineExpose({ validate })
        <div class="section-title-row">
          <div>
            <h3>处理类型</h3>
-            <p>类型会影响下一步支持的数据源格式和后续预览方式</p>
+            <p v-if="processTypeLocked">重新生成沿用原任务处理类型，不可修改</p>
+            <p v-else>类型会影响下一步支持的数据源格式和后续预览方式</p>
          </div>
        </div>
        <el-form-item prop="processType" class="type-form-item">
@@ -162,6 +164,7 @@ defineExpose({ validate })
              type="button"
              class="type-option"
              :class="{ 'is-active': processType === 'structured' }"
+              :disabled="processTypeLocked"
              @click="emit('update:processType', 'structured')"
            >
              <span class="type-icon"><i class="fa fa-table" /></span>
@@ -175,6 +178,7 @@ defineExpose({ validate })
              type="button"
              class="type-option"
              :class="{ 'is-active': processType === 'unstructured' }"
+              :disabled="processTypeLocked"
              @click="emit('update:processType', 'unstructured')"
            >
              <span class="type-icon"><i class="fa fa-file-text-o" /></span>
@@ -188,6 +192,7 @@ defineExpose({ validate })
              type="button"
              class="type-option"
              :class="{ 'is-active': processType === 'external' }"
+              :disabled="processTypeLocked"
              @click="emit('update:processType', 'external')"
            >
              <span class="type-icon"><i class="fa fa-cloud-download" /></span>
@@ -293,12 +298,25 @@ defineExpose({ validate })
    border-color: #a8a3ff;
  }

+  &:disabled {
+    cursor: not-allowed;
+    opacity: 0.58;
+  }
+
+  &:disabled:hover {
+    border-color: #dfe3ea;
+  }
+
  &.is-active {
    background: #fafaff;
    border-color: #5b50f2;
    box-shadow: 0 0 0 1px rgba(91, 80, 242, 0.08);
  }

+  &.is-active:disabled {
+    opacity: 1;
+  }
+
  strong,
  small {
    display: block;
--- a/frontend/src/views/data-process/create/data-process-create.scss
+++ b/frontend/src/views/data-process/create/data-process-create.scss
@@ -117,6 +117,12 @@
  min-height: 400px;
 }

+.initialization-error {
+  display: grid;
+  justify-items: start;
+  gap: 16px;
+}
+
 .wizard-footer {
  display: grid;
  flex-shrink: 0;
--- a/frontend/src/views/data-process/create/dataProcessCreateState.ts
+++ b/frontend/src/views/data-process/create/dataProcessCreateState.ts
@@ -1,4 +1,12 @@
-import type { StructuredProcessOptions, UnstructuredProcessOptions } from './types'
+import type { DataProcessConfig, DataProcessDatasetSplit } from '@/types/dataProcess'
+import type {
+  GenerationControlOptions,
+  PreprocessOption,
+  StructuredProcessOptions,
+  UnstructuredPreprocessOption,
+  UnstructuredProcessOptions,
+  ProcessType,
+} from './types'

 export const DEFAULT_GENERATION_PROMPT = '你是一名专业的数据生成助手。请根据输入内容生成准确、完整、可直接用于模型训练的问答数据。仅输出符合目标格式的内容，答案应事实清晰、语言自然，不要添加分析过程、说明或无关内容。'

@@ -52,3 +60,166 @@ export function createDefaultUnstructuredOptions(): UnstructuredProcessOptions {
    minOutputLength: 20,
  }
 }
+
+function configValue<T>(config: DataProcessConfig, key: string, fallback: T): T {
+  return Object.prototype.hasOwnProperty.call(config, key) ? config[key] as T : fallback
+}
+
+function numberValue(config: DataProcessConfig, key: string, fallback: number): number {
+  const value = Number(configValue(config, key, fallback))
+  return Number.isFinite(value) ? value : fallback
+}
+
+function datasetSplitValue(config: DataProcessConfig, fallback: DataProcessDatasetSplit) {
+  const value = config.dataset_split
+  if (!value || typeof value !== 'object') return { ...fallback }
+  const split = value as unknown as Record<string, unknown>
+  const splitNumber = (key: keyof DataProcessDatasetSplit) => {
+    const parsed = Number(split[key])
+    return Number.isFinite(parsed) ? parsed : fallback[key]
+  }
+  return {
+    train: splitNumber('train'),
+    validation: splitNumber('validation'),
+    test: splitNumber('test'),
+  }
+}
+
+function generationOptionsFromConfig(
+  config: DataProcessConfig,
+  defaults: GenerationControlOptions,
+): GenerationControlOptions {
+  return {
+    generationModelId: configValue(config, 'generation_model_id', defaults.generationModelId),
+    generationPrompt: String(configValue(config, 'generation_prompt', defaults.generationPrompt)),
+    temperature: numberValue(config, 'temperature', defaults.temperature),
+    maxTokens: numberValue(config, 'max_tokens', defaults.maxTokens),
+    jsonMode: Boolean(configValue(config, 'json_mode', defaults.jsonMode)),
+    qualityFilterEnabled: Boolean(configValue(
+      config,
+      'quality_filter_enabled',
+      defaults.qualityFilterEnabled,
+    )),
+    filterLowQuality: Boolean(configValue(
+      config,
+      'filter_low_quality',
+      defaults.filterLowQuality,
+    )),
+    filterShortContent: Boolean(configValue(
+      config,
+      'filter_short_content',
+      defaults.filterShortContent,
+    )),
+    minOutputLength: numberValue(config, 'min_output_length', defaults.minOutputLength),
+  }
+}
+
+export function createStructuredOptionsFromConfig(config: DataProcessConfig): StructuredProcessOptions {
+  const defaults = createDefaultStructuredOptions()
+  const preprocessOptions = configValue<unknown>(config, 'preprocess_options', [])
+  return {
+    ...defaults,
+    ...generationOptionsFromConfig(config, defaults),
+    preprocessOptions: Array.isArray(preprocessOptions)
+      ? preprocessOptions.map(String) as PreprocessOption[]
+      : defaults.preprocessOptions,
+    semanticEnrichment: Boolean(configValue(
+      config,
+      'semantic_enrichment',
+      defaults.semanticEnrichment,
+    )),
+    qaPairsPerRow: numberValue(config, 'qa_pairs_per_row', defaults.qaPairsPerRow),
+    datasetSplit: datasetSplitValue(config, defaults.datasetSplit),
+  }
+}
+
+export function createUnstructuredOptionsFromConfig(config: DataProcessConfig): UnstructuredProcessOptions {
+  const defaults = createDefaultUnstructuredOptions()
+  const preprocessOptions = configValue<unknown>(config, 'preprocess_options', [])
+  return {
+    ...defaults,
+    ...generationOptionsFromConfig(config, defaults),
+    preprocessOptions: Array.isArray(preprocessOptions)
+      ? preprocessOptions.map(String) as UnstructuredPreprocessOption[]
+      : defaults.preprocessOptions,
+    chunkMethod: configValue(config, 'chunk_method', defaults.chunkMethod),
+    chunkSize: numberValue(config, 'chunk_size', defaults.chunkSize),
+    chunkOverlap: numberValue(config, 'chunk_overlap', defaults.chunkOverlap),
+    minChunkSize: numberValue(config, 'min_chunk_size', defaults.minChunkSize),
+    semanticBreakpointPercentile: numberValue(
+      config,
+      'semantic_breakpoint_percentile',
+      defaults.semanticBreakpointPercentile,
+    ),
+    preserveTables: Boolean(configValue(config, 'preserve_tables', defaults.preserveTables)),
+    preserveCodeBlocks: Boolean(configValue(
+      config,
+      'preserve_code_blocks',
+      defaults.preserveCodeBlocks,
+    )),
+    preserveLists: Boolean(configValue(config, 'preserve_lists', defaults.preserveLists)),
+    semanticEnrichment: Boolean(configValue(
+      config,
+      'semantic_enrichment',
+      defaults.semanticEnrichment,
+    )),
+    qaPairsPerChunk: numberValue(config, 'qa_pairs_per_chunk', defaults.qaPairsPerChunk),
+    datasetSplit: datasetSplitValue(config, defaults.datasetSplit),
+  }
+}
+
+export function previewAffectingOptionsFor(
+  processType: ProcessType,
+  structured: StructuredProcessOptions,
+  unstructured: UnstructuredProcessOptions,
+) {
+  if (processType === 'structured') return { preprocessOptions: structured.preprocessOptions }
+  if (processType !== 'unstructured') return null
+  const {
+    preprocessOptions,
+    chunkMethod,
+    chunkSize,
+    chunkOverlap,
+    minChunkSize,
+    semanticBreakpointPercentile,
+    preserveTables,
+    preserveCodeBlocks,
+    preserveLists,
+  } = unstructured
+  return {
+    preprocessOptions,
+    chunkMethod,
+    chunkSize,
+    chunkOverlap,
+    minChunkSize,
+    semanticBreakpointPercentile,
+    preserveTables,
+    preserveCodeBlocks,
+    preserveLists,
+  }
+}
+
+export function generationAffectingOptionsFor(
+  processType: ProcessType,
+  structured: StructuredProcessOptions,
+  unstructured: UnstructuredProcessOptions,
+) {
+  const options = processType === 'unstructured' ? unstructured : structured
+  if (processType === 'external') return null
+  const common = {
+    semanticEnrichment: options.semanticEnrichment,
+    datasetSplit: options.datasetSplit,
+    generationModelId: options.generationModelId,
+    generationPrompt: options.generationPrompt,
+    temperature: options.temperature,
+    maxTokens: options.maxTokens,
+    jsonMode: options.jsonMode,
+    qualityFilterEnabled: options.qualityFilterEnabled,
+    filterLowQuality: options.filterLowQuality,
+    filterShortContent: options.filterShortContent,
+    minOutputLength: options.minOutputLength,
+  }
+  return processType === 'unstructured'
+    ? { ...common, qaPairsPerChunk: unstructured.qaPairsPerChunk }
+    : { ...common, qaPairsPerRow: structured.qaPairsPerRow }
+}
--- a/frontend/src/views/data-process/create/useDataProcessRegeneration.ts
+++ b/frontend/src/views/data-process/create/useDataProcessRegeneration.ts
@@ -0,0 +1,232 @@
+import { computed, nextTick, ref, type Reactive, type Ref } from 'vue'
+import { useRoute } from 'vue-router'
+import {
+  getDataProcessPreview,
+  getDataProcessSourceContent,
+  getDataProcessTask,
+  regenerateDataProcessTask,
+} from '@/api/modules/dataProcess'
+import type {
+  DataProcessPreviewItem,
+  DataProcessRegeneratePayload,
+  DataProcessTask,
+} from '@/types/dataProcess'
+import {
+  createStructuredOptionsFromConfig,
+  createUnstructuredOptionsFromConfig,
+} from './dataProcessCreateState'
+import { mapDataProcessSourceFile } from './useDataProcessSourceUpload'
+import type {
+  PreviewItem,
+  ProcessType,
+  StructuredProcessOptions,
+  UnstructuredProcessOptions,
+  UploadedDataFile,
+} from './types'
+
+interface ConfirmOptions {
+  title: string
+  message: string
+  confirmText: string
+  cancelText: string
+  tone: 'warning'
+}
+
+interface RegenerationBindings {
+  task: Reactive<{ name: string; description: string }>
+  processType: Ref<ProcessType>
+  structuredOptions: Ref<StructuredProcessOptions>
+  unstructuredOptions: Ref<UnstructuredProcessOptions>
+  uploadedFiles: Ref<UploadedDataFile[]>
+  previewItems: Ref<PreviewItem[]>
+  selectedPreviewFileId: Ref<string | null>
+  selectedPreviewId: Ref<string | null>
+  selectedPreviewIdsByFile: Ref<Record<string, string>>
+  previewSignature: Ref<string>
+  dirty: Ref<boolean>
+  buildPreviewConfigSignature: () => string
+  buildPreviewSignature: () => string
+  mapPreviewItem: (item: DataProcessPreviewItem) => PreviewItem
+  resetDownstream: () => void
+}
+
+async function loadSourceContent(taskId: string, fileId: string | number) {
+  const chunks: string[] = []
+  let startLine = 1
+  while (true) {
+    const source = await getDataProcessSourceContent(taskId, fileId, {
+      start_line: startLine,
+      line_count: 10_000,
+    })
+    chunks.push(source.content || '')
+    if (!source.has_more) break
+    const nextLine = Number(source.end_line || startLine) + 1
+    if (nextLine <= startLine) break
+    startLine = nextLine
+  }
+  // source_content_lines 已保留原始换行；分页之间直接拼接，避免凭空增加空行并破坏偏移。
+  return chunks.join('')
+}
+
+async function loadAllPreviews(taskId: string, mapPreviewItem: RegenerationBindings['mapPreviewItem']) {
+  const first = await getDataProcessPreview(taskId, { page: 1, page_size: 500 })
+  const items = [...first.items]
+  const pages = Math.ceil(first.total / first.page_size)
+  for (let page = 2; page <= pages; page += 1) {
+    const next = await getDataProcessPreview(taskId, { page, page_size: 500 })
+    items.push(...next.items)
+  }
+  return items.map(mapPreviewItem)
+}
+
+export function useDataProcessRegeneration(bindings: RegenerationBindings) {
+  const route = useRoute()
+  const sourceTaskId = computed(() => (
+    route.name === 'data-process-regenerate' ? String(route.params.id || '') : ''
+  ))
+  const isRegeneration = computed(() => Boolean(sourceTaskId.value))
+  const originalProcessType = ref<ProcessType | null>(null)
+  const originalTaskUpdatedAt = ref('')
+  const regenerationPrepared = ref(false)
+  const originalPreviewConfigSignature = ref('')
+  const confirmedPreviewConfigSignature = ref('')
+  const hydrating = ref(false)
+  const initializationError = ref('')
+
+  async function hydrateWorkspace(task: DataProcessTask, preservePreviews: boolean) {
+    const taskId = String(task.id)
+    bindings.uploadedFiles.value = await Promise.all((task.source_files || []).map(async (file) => (
+      mapDataProcessSourceFile(file, await loadSourceContent(taskId, file.id))
+    )))
+    bindings.previewItems.value = preservePreviews
+      ? await loadAllPreviews(taskId, bindings.mapPreviewItem)
+      : []
+
+    const configSignature = bindings.buildPreviewConfigSignature()
+    const previewCounts = new Map<string, number>()
+    for (const item of bindings.previewItems.value) {
+      previewCounts.set(item.sourceFileId, (previewCounts.get(item.sourceFileId) || 0) + 1)
+    }
+    for (const file of bindings.uploadedFiles.value) {
+      const count = previewCounts.get(String(file.sourceFileId)) || 0
+      file.previewCount = count
+      file.previewStatus = preservePreviews && count > 0 ? 'success' : 'waiting'
+      file.previewProgress = preservePreviews && count > 0 ? 100 : 0
+      file.previewConfigSignature = preservePreviews && count > 0 ? configSignature : undefined
+    }
+
+    bindings.selectedPreviewFileId.value = String(bindings.uploadedFiles.value[0]?.uid ?? '') || null
+    bindings.selectedPreviewId.value = bindings.selectedPreviewFileId.value
+      ? bindings.previewItems.value.find((item) => (
+          item.sourceFileId === bindings.selectedPreviewFileId.value
+        ))?.id ?? null
+      : null
+    bindings.selectedPreviewIdsByFile.value = (
+      bindings.selectedPreviewFileId.value && bindings.selectedPreviewId.value
+    ) ? { [bindings.selectedPreviewFileId.value]: bindings.selectedPreviewId.value } : {}
+    bindings.previewSignature.value = preservePreviews && bindings.previewItems.value.length
+      ? bindings.buildPreviewSignature()
+      : ''
+    bindings.resetDownstream()
+  }
+
+  async function loadSource() {
+    if (!sourceTaskId.value) return
+    hydrating.value = true
+    initializationError.value = ''
+    try {
+      const sourceTask = await getDataProcessTask(sourceTaskId.value)
+      const sourceType = sourceTask.process_type as ProcessType
+      originalProcessType.value = sourceType
+      originalTaskUpdatedAt.value = sourceTask.updated_at
+      bindings.task.name = sourceTask.name
+      bindings.task.description = sourceTask.description || ''
+      bindings.processType.value = sourceType
+      const config = sourceTask.config || {}
+      bindings.structuredOptions.value = createStructuredOptionsFromConfig(config)
+      bindings.unstructuredOptions.value = createUnstructuredOptionsFromConfig(config)
+      originalPreviewConfigSignature.value = bindings.buildPreviewConfigSignature()
+      confirmedPreviewConfigSignature.value = ''
+      await hydrateWorkspace(sourceTask, true)
+      await nextTick()
+      bindings.dirty.value = false
+    } catch (error) {
+      initializationError.value = error instanceof Error
+        ? error.message
+        : '原数据处理任务加载失败，请返回详情页后重试'
+    } finally {
+      hydrating.value = false
+    }
+  }
+
+  async function confirmPreviewConfigChange(
+    openConfirm: (options: ConfirmOptions) => Promise<boolean | undefined>,
+  ) {
+    if (!isRegeneration.value) return true
+    if (!bindings.previewItems.value.length) return true
+    const currentSignature = bindings.buildPreviewConfigSignature()
+    const changed = currentSignature !== originalPreviewConfigSignature.value
+    if (!changed || currentSignature === confirmedPreviewConfigSignature.value) return true
+    const confirmed = await openConfirm({
+      title: '确认修改切分配置？',
+      message: '修改预处理或切分配置将删除现有切片和生成结果；已发布三数据集暂时保留，直到重新发布后才会更新。',
+      confirmText: '确认并继续',
+      cancelText: '返回检查',
+      tone: 'warning',
+    })
+    if (confirmed) confirmedPreviewConfigSignature.value = currentSignature
+    return Boolean(confirmed)
+  }
+
+  async function prepareRegeneration(
+    payload: Omit<DataProcessRegeneratePayload, 'expected_updated_at'>,
+  ) {
+    // 第一次 prepare 后，上传、切分、编辑预览和生成都会推进任务版本。
+    // 再次提交前读取同一任务的最新版本，仍由后端事务处理读取后的并发竞争。
+    if (regenerationPrepared.value) {
+      const latestTask = await getDataProcessTask(sourceTaskId.value)
+      originalTaskUpdatedAt.value = latestTask.updated_at || originalTaskUpdatedAt.value
+    }
+    const regenerated = await regenerateDataProcessTask(sourceTaskId.value, {
+      ...payload,
+      expected_updated_at: originalTaskUpdatedAt.value,
+    })
+    originalTaskUpdatedAt.value = regenerated.task.updated_at || originalTaskUpdatedAt.value
+    originalPreviewConfigSignature.value = bindings.buildPreviewConfigSignature()
+    confirmedPreviewConfigSignature.value = ''
+    regenerationPrepared.value = true
+    bindings.dirty.value = true
+    try {
+      const regeneratedTask = regenerated.task.source_files
+        ? regenerated.task
+        : await getDataProcessTask(regenerated.task.id)
+      originalTaskUpdatedAt.value = regeneratedTask.updated_at || originalTaskUpdatedAt.value
+      hydrating.value = true
+      try {
+        await hydrateWorkspace(regeneratedTask, !regenerated.preview_invalidated)
+      } finally {
+        hydrating.value = false
+      }
+    } catch (error) {
+      initializationError.value = error instanceof Error
+        ? `任务已进入重新生成状态，但工作区恢复失败：${error.message}`
+        : '任务已进入重新生成状态，但工作区恢复失败，请重试加载原任务'
+      throw error
+    }
+    return regenerated
+  }
+
+  return {
+    sourceTaskId,
+    isRegeneration,
+    originalProcessType,
+    originalTaskUpdatedAt,
+    regenerationPrepared,
+    hydrating,
+    initializationError,
+    hydrateWorkspace,
+    loadSource,
+    confirmPreviewConfigChange,
+    prepareRegeneration,
+  }
+}