feat(asl/extraction): Complete Tool 3 M1+M2 - skeleton pipeline and HITL workbench

M1 Skeleton Pipeline:
- Scatter-dispatch + Aggregator polling pattern (PgBoss)
- PKB ACL bridge (PkbBridgeService -> PkbExportService DTOs)
- ExtractionSingleWorker with DeepSeek-V3 LLM extraction
- PermanentExtractionError for non-retryable failures
- Phantom Retry Guard (idempotent worker)
- 3-step minimal frontend (Setup -> Progress -> Workbench)
- 4 new DB tables (extraction_templates, project_templates, tasks, results)
- 3 system templates seed (RCT, Cohort, QC)
- M1 integration test suite

M2 HITL Workbench:
- MinerU VLM integration for high-fidelity table extraction
- XML-isolated DynamicPromptBuilder with flat JSON output template
- fuzzyQuoteMatch validator (3-tier confidence scoring)
- SSE real-time logging via ExtractionEventBus
- Schema-driven ExtractionDrawer (dynamic field rendering from template)
- Excel wide-table export with flattenModuleData normalization
- M2 integration test suite

Critical Fixes (data normalization):
- DynamicPromptBuilder: explicit flat key-value output format with example
- ExtractionExcelExporter: handle both array and flat data formats
- ExtractionDrawer: schema-driven rendering instead of hardcoded fields
- ExtractionValidator: array-format quote verification support
- SSE route: Fastify register encapsulation to bypass auth for EventSource
- LLM JSON sanitizer: strip illegal control chars before JSON.parse

Also includes: RVW stats verification spec, SSA expert config guide

Tested: M1 pipeline test + M2 HITL test + manual frontend verification
Co-authored-by: Cursor <cursoragent@cursor.com>

frontend-v2/src/modules/asl/api/index.ts

@@ -528,6 +528,97 @@ export async function getDeepResearchTask(
   return request(`/research/tasks/${taskId}`);
 }
 
+// ==================== 工具 3：全文智能提取 API ====================
+
+export async function getExtractionTemplates(): Promise<ApiResponse<any[]>> {
+  return request('/extraction/templates');
+}
+
+export async function getExtractionTemplate(templateId: string): Promise<ApiResponse<any>> {
+  return request(`/extraction/templates/${templateId}`);
+}
+
+export async function cloneExtractionTemplate(
+  projectId: string,
+  baseTemplateId: string
+): Promise<ApiResponse<any>> {
+  return request('/extraction/templates/clone', {
+    method: 'POST',
+    body: JSON.stringify({ projectId, baseTemplateId }),
+  });
+}
+
+export async function getExtractionKnowledgeBases(): Promise<ApiResponse<any[]>> {
+  return request('/extraction/knowledge-bases');
+}
+
+export async function getExtractionDocuments(kbId: string): Promise<ApiResponse<any[]>> {
+  return request(`/extraction/knowledge-bases/${kbId}/documents`);
+}
+
+export async function createExtractionTask(params: {
+  projectId: string;
+  projectTemplateId: string;
+  pkbKnowledgeBaseId: string;
+  documentIds: string[];
+  idempotencyKey?: string;
+}): Promise<ApiResponse<{ taskId: string }>> {
+  return request('/extraction/tasks', {
+    method: 'POST',
+    body: JSON.stringify(params),
+  });
+}
+
+export async function getExtractionTaskStatus(
+  taskId: string
+): Promise<ApiResponse<{
+  taskId: string;
+  status: string;
+  totalCount: number;
+  completedCount: number;
+  errorCount: number;
+  extractingCount: number;
+  pendingCount: number;
+  percent: number;
+}>> {
+  return request(`/extraction/tasks/${taskId}`);
+}
+
+export async function getExtractionTaskResults(
+  taskId: string
+): Promise<ApiResponse<any[]>> {
+  return request(`/extraction/tasks/${taskId}/results`);
+}
+
+export async function getExtractionResultDetail(
+  resultId: string
+): Promise<ApiResponse<any>> {
+  return request(`/extraction/results/${resultId}`);
+}
+
+export async function reviewExtractionResult(
+  resultId: string,
+  data: { reviewStatus: 'approved' | 'rejected' }
+): Promise<ApiResponse<any>> {
+  return request(`/extraction/results/${resultId}/review`, {
+    method: 'PUT',
+    body: JSON.stringify(data),
+  });
+}
+
+export async function exportExtractionResults(
+  taskId: string
+): Promise<Blob> {
+  const response = await fetch(
+    `${API_BASE_URL}/extraction/tasks/${taskId}/export`,
+    { headers: getAuthHeaders() }
+  );
+  if (!response.ok) {
+    throw new Error(`HTTP ${response.status}`);
+  }
+  return response.blob();
+}
+
 // ==================== 统一导出API对象 ====================
 
 /**
@@ -584,4 +675,17 @@ export const aslApi = {
   generateRequirement,
   executeDeepResearchTask,
   getDeepResearchTask,
+
+  // 工具 3：全文智能提取
+  getExtractionTemplates,
+  getExtractionTemplate,
+  cloneExtractionTemplate,
+  getExtractionKnowledgeBases,
+  getExtractionDocuments,
+  createExtractionTask,
+  getExtractionTaskStatus,
+  getExtractionTaskResults,
+  getExtractionResultDetail,
+  reviewExtractionResult,
+  exportExtractionResults,
 };