feat: 询价标题AI压缩 + 采集器品类化 + 询价搜索与品类多选框

- TitleCompressorService: 发布前超长标题(>50字)调 MiniMax 压缩(保留公司名+物料+采购类型), JSON结构化输出对抗推理模型思考噪音, 失败硬截断兜底
- publishToDirev 集成标题压缩, 保留原50字预校验作为防御
- crawler resolveKeywords: 采集器配置优先按关联品类展开关键词库, 中电建每关键词独立状态文件
- InquiryPage: 新增关键词搜索(fSearch → GET /api/leads?search=)
- RuleCenterPage: 采集器配置由 keywords 改为品类多选框(categories JSON数组)

apps/api/src/crawler/crawler.service.ts

@@ -118,9 +118,11 @@ export class CrawlerService implements OnModuleInit {
         results = await this.runGenericScript(config)
       }
 
+      this.logger.log(`脚本返回 ${results.length} 条原始结果`)
       let successCount = 0
 
       const validResults = results.filter(r => r.noticeId)
+      this.logger.log(`有效结果 ${validResults.length} 条 (有 noticeId)`)
       const categoryMap = await this.categoryInference.batchInfer(
         validResults.map(r => ({ id: r.noticeId, title: r.title })),
       )
@@ -161,11 +163,13 @@ export class CrawlerService implements OnModuleInit {
             },
           })
           successCount++
-        } catch {
+        } catch (e: unknown) {
-          // 其他异常跳过
+          this.logger.warn(`入库失败 [${r.noticeId}] ${r.title.slice(0, 30)}: ${(e as Error).message}`)
         }
       }
 
+      this.logger.log(`入库成功 ${successCount} / ${validResults.length} 条`)
+
       return this.prisma.crawlerConfig.update({
         where: { id },
         data: {
@@ -185,19 +189,42 @@ export class CrawlerService implements OnModuleInit {
     }
   }
 
-  private async runPowerChina(config: { keywords?: string | null }): Promise<FetchResult[]> {
+  private async resolveKeywords(config: { categories?: string | null; keywords?: string | null }): Promise<string[]> {
+    if (config.categories) {
+      try {
+        const catNames: string[] = JSON.parse(config.categories)
+        if (catNames.length > 0) {
+          const cats = await this.prisma.productCategory.findMany({
+            where: { name: { in: catNames } },
+          })
+          const kwSet = new Set<string>()
+          for (const cat of cats) {
+            try {
+              const kws: string[] = JSON.parse(cat.keywords)
+              kws.forEach((k) => kwSet.add(k))
+            } catch { /* skip */ }
+          }
+          if (kwSet.size > 0) return Array.from(kwSet)
+        }
+      } catch { /* fallback */ }
+    }
+
+    if (config.keywords) {
+      try {
+        return JSON.parse(config.keywords)
+      } catch { /* skip */ }
+    }
+
+    return ['']
+  }
+
+  private async runPowerChina(config: { categories?: string | null; keywords?: string | null }): Promise<FetchResult[]> {
     const scriptPath = path.join(TENDER_FETCHER_DIR, 'fetch-v1.2.js')
     if (!fs.existsSync(scriptPath)) {
       throw new Error('中电建抓取脚本不存在')
     }
 
-    let keywords: string[]
+    const keywords = await this.resolveKeywords(config)
-    try {
-      keywords = config.keywords ? JSON.parse(config.keywords) : []
-    } catch {
-      keywords = []
-    }
-    if (keywords.length === 0) keywords = ['']
 
     const today = new Date().toISOString().split('T')[0]
     const baseDir = path.join(process.env.HOME || '', 'desktop/招标公告', today)
@@ -207,22 +234,29 @@ export class CrawlerService implements OnModuleInit {
     for (const kw of keywords) {
       const kwFlag = kw ? ` --keyword "${kw}"` : ''
       try {
+        this.logger.log(`执行关键词 [${kw || '(空)'}] 抓取脚本`)
         execSync(`node "${scriptPath}"${kwFlag}`, {
           encoding: 'utf-8',
           maxBuffer: 10 * 1024 * 1024,
           timeout: 180000,
         })
-      } catch {
+      } catch (e: unknown) {
-        // 单个 keyword 失败不影响其他 keyword
+        this.logger.warn(`关键词 [${kw || '(空)'}] 抓取失败: ${(e as { stderr?: string; message?: string }).stderr || (e as { message?: string }).message}`)
         continue
       }
 
-      const statePath = path.join(baseDir, 'downloaded.json')
+      // 每个关键词有独立的状态文件: downloaded_<keyword>.json
-      if (!fs.existsSync(statePath)) continue
+      const stateFileName = kw ? `downloaded_${kw}.json` : 'downloaded.json'
+      const statePath = path.join(baseDir, stateFileName)
+      if (!fs.existsSync(statePath)) {
+        this.logger.warn(`关键词 [${kw || '(空)'}] 状态文件不存在: ${statePath}`)
+        continue
+      }
 
       try {
         const state = JSON.parse(fs.readFileSync(statePath, 'utf-8'))
         const downloaded = state.downloaded || {}
+        this.logger.log(`关键词 [${kw || '(空)'}] 状态文件读取成功: ${Object.keys(downloaded).length} 条记录`)
 
         const outputDir = path.dirname(statePath)
         const pdfDir = path.join(outputDir, 'pdf')
@@ -265,15 +299,17 @@ export class CrawlerService implements OnModuleInit {
             regionDetail,
           })
         }
-      } catch {
+      } catch (e: unknown) {
+        this.logger.error(`关键词 [${kw || '(空)'}] 状态文件解析失败: ${(e as Error).message}`)
         continue
       }
     }
 
+    this.logger.log(`抓取汇总: ${allResults.length} 条公告待入库`)
     return allResults
   }
 
-  private async runGenericScript(config: { type: string; sourceName?: string | null; scriptPath?: string | null; keywords?: string | null }): Promise<FetchResult[]> {
+  private async runGenericScript(config: { type: string; sourceName?: string | null; scriptPath?: string | null; categories?: string | null; keywords?: string | null }): Promise<FetchResult[]> {
     const slug = config.type.replace(/^bid_/, '')
     const scriptFile = config.scriptPath || `fetch-${slug}.py`
     const scriptPath = path.join(TENDER_FETCHER_DIR, scriptFile)
@@ -284,13 +320,7 @@ export class CrawlerService implements OnModuleInit {
       throw new Error(`抓取脚本不存在: ${scriptFile}`)
     }
 
-    let keywords: string[]
+    const keywords = await this.resolveKeywords(config)
-    try {
-      keywords = config.keywords ? JSON.parse(config.keywords) : []
-    } catch {
-      keywords = []
-    }
-    if (keywords.length === 0) keywords = ['']
 
     const today = new Date().toISOString().split('T')[0]
     const baseDir = path.join(process.env.HOME || '', 'desktop/招标公告', today)

apps/api/src/lead/lead.module.ts

@@ -5,13 +5,14 @@ import { CrawlerModule } from '../crawler/crawler.module'
 import { ProductCategoryModule } from '../product-category/product-category.module'
 import { LeadService } from './lead.service'
 import { MaterialExtractorService } from './material-extractor.service'
+import { TitleCompressorService } from './title-compressor.service'
 import { LeadController } from './lead.controller'
 import { LeadNotesController } from './lead-notes.controller'
 
 @Module({
   imports: [PrismaModule, IntegrationModule, CrawlerModule, ProductCategoryModule],
   controllers: [LeadController, LeadNotesController],
-  providers: [LeadService, MaterialExtractorService],
+  providers: [LeadService, MaterialExtractorService, TitleCompressorService],
   exports: [LeadService],
 })
 export class LeadModule {}

apps/api/src/lead/lead.service.ts

@@ -4,6 +4,7 @@ import { IntegrationService } from '../integration/integration.service'
 import { ProductCategoryService } from '../product-category/product-category.service'
 import { CategoryInferenceService } from '../product-category/category-inference.service'
 import { MaterialExtractorService } from './material-extractor.service'
+import { TitleCompressorService } from './title-compressor.service'
 
 @Injectable()
 export class LeadService {
@@ -15,6 +16,7 @@ export class LeadService {
     private categoryService: ProductCategoryService,
     private categoryInference: CategoryInferenceService,
     private materialExtractor: MaterialExtractorService,
+    private titleCompressor: TitleCompressorService,
   ) {}
 
   async findAll(params?: { status?: string; level?: string; search?: string; star?: string; source?: string; category?: string; assignedTo?: string; timeRange?: string }) {
@@ -35,11 +37,7 @@ export class LeadService {
     }
     if (params?.source) where.source = params.source
     if (params?.category) {
-      const categoryRecord = await this.prisma.productCategory.findUnique({ where: { name: params.category } })
+      where.category = params.category
-      if (categoryRecord) {
-        const keywords: string[] = JSON.parse(categoryRecord.keywords)
-        where.OR = keywords.map(kw => ({ title: { contains: kw } }))
-      }
     }
     if (params?.assignedTo) {
       where.assignedTo = params.assignedTo === '未分配' ? null : params.assignedTo
@@ -316,9 +314,15 @@ export class LeadService {
       }
 
     // 预校验: B2B 平台字段长度限制 (tb_inquiry.title varchar(50))
-    // 在调 MCP 之前先报错，避免拿到通用的"服务器内部异常"
+    // 超长标题先 AI 压缩（保留 公司名+物料+采购类型），压缩失败自动硬截断兜底
     const TITLE_MAX_LEN = 50
     if (publishArgs.title && String(publishArgs.title).length > TITLE_MAX_LEN) {
+      publishArgs.title = await this.titleCompressor.compress(
+        String(publishArgs.title),
+        TITLE_MAX_LEN,
+      )
+    }
+    if (String(publishArgs.title).length > TITLE_MAX_LEN) {
       const titleLen = String(publishArgs.title).length
       throw new ServiceUnavailableException(
         [

apps/api/src/lead/title-compressor.service.ts

@@ -0,0 +1,88 @@
+import { Injectable, Logger } from '@nestjs/common'
+
+const MINIMAX_ENDPOINT = 'https://api.minimaxi.com/v1/chat/completions'
+const MINIMAX_MODEL = process.env.MINIMAX_MODEL || 'MiniMax-M2.7'
+const MINIMAX_TIMEOUT_MS = 30000
+
+// 压缩规则: 只保留 公司名(简称) + 物料 + 采购类型
+// 给 B2B 平台 50 字上限留 5 字余量, 避免平台侧校验边界
+const MAX_COMPRESS_LEN = 45
+// M2.7 推理模型会把思考过程输出在正文里且风格多变, 行级正则过滤不可靠,
+// 改为要求 JSON 结构化输出, 解析不到就硬截断兜底
+const PROMPT = `把采购公告标题压缩成询价标题, 只保留: 采购公司名称(简称)、物料、采购类型。
+要求:
+1. 压缩后不超过 45 个汉字
+2. 只输出 JSON: {"title": "压缩后的标题"}
+3. 不要输出任何其他内容、解释、序号、markdown
+
+示例:
+输入: 中国电建集团港航建设有限公司 定襄县农村饮水管网改造工程第1标段项目管材采购公开询比采购公告
+输出: {"title": "电建港航定襄县管网改造一标管材询比采购"}`
+
+@Injectable()
+export class TitleCompressorService {
+  private readonly logger = new Logger(TitleCompressorService.name)
+
+  async compress(title: string, maxLength: number): Promise<string> {
+    if (!title || title.length <= maxLength) return title
+
+    const apiKey = process.env.MINIMAX_API_KEY
+    if (!apiKey) {
+      this.logger.warn('MINIMAX_API_KEY 未配置, 标题硬截断')
+      return title.slice(0, maxLength)
+    }
+
+    try {
+      const raw = await this.callMinimax(title, apiKey, Math.min(maxLength, MAX_COMPRESS_LEN))
+      const parsedTitle = this.extractJsonTitle(raw)
+
+      if (!parsedTitle) {
+        this.logger.warn(`AI 压缩无有效输出, 硬截断: ${raw.slice(0, 100)}`)
+        return title.slice(0, maxLength)
+      }
+
+      const result = parsedTitle.length > maxLength ? parsedTitle.slice(0, maxLength) : parsedTitle
+      this.logger.log(`标题 AI 压缩 (${title.length}字→${result.length}字): "${result}"`)
+      return result
+    } catch (e: any) {
+      this.logger.warn(`AI 压缩失败, 硬截断: ${e.message}`)
+      return title.slice(0, maxLength)
+    }
+  }
+
+  /** M2.7 常在 JSON 前后夹杂思考文本, 用正则提取第一个合法的 {"title":"..."} 片段 */
+  private extractJsonTitle(raw: string): string {
+    const m = raw.match(/\{"title"\s*:\s*"([^"]+)"\}/)
+    if (m) return m[1]
+    const loose = raw.match(/"title"\s*:\s*"([^"]+)"/)
+    return loose ? loose[1] : ''
+  }
+
+  private async callMinimax(title: string, apiKey: string, maxLen: number): Promise<string> {
+    const r = await fetch(MINIMAX_ENDPOINT, {
+      method: 'POST',
+      headers: {
+        'Authorization': `Bearer ${apiKey}`,
+        'Content-Type': 'application/json',
+      },
+      body: JSON.stringify({
+        model: MINIMAX_MODEL,
+        messages: [
+          { role: 'system', content: PROMPT.replace('45', String(maxLen)) },
+          { role: 'user', content: title },
+        ],
+        temperature: 0,
+        max_tokens: 800, // M2.7 推理模型会输出明文思考, 400 会被思考过程耗尽导致答案截断 (AGENTS.md: 标题提取用 800)
+      }),
+      signal: AbortSignal.timeout(MINIMAX_TIMEOUT_MS),
+    })
+
+    if (!r.ok) {
+      const errText = await r.text().catch(() => '')
+      throw new Error(`MiniMax API ${r.status}: ${errText.slice(0, 200)}`)
+    }
+
+    const data = (await r.json()) as { choices?: Array<{ message?: { content?: string } }> }
+    return data.choices?.[0]?.message?.content || ''
+  }
+}

apps/web/src/components/InquiryPage.tsx

@@ -111,6 +111,7 @@ export default function InquiryPage({ onLeadDetail }: { onLeadDetail?: (id: stri
   const { showToast } = useToast()
   const pageSize = 10
 
+  const [fSearch, setFSearch] = useState('')
   const [fTime, setFTime] = useState('全部日期')
   const [fStar, setFStar] = useState('全部星级')
   const [fStatus, setFStatus] = useState('全部状态')
@@ -144,9 +145,10 @@ export default function InquiryPage({ onLeadDetail }: { onLeadDetail?: (id: stri
   const [fSource, setFSource] = useState('全部来源')
   const [fPerson, setFPerson] = useState('全部人员')
 
-  const loadLeads = useCallback(async (star?: string, status?: string, level?: string, cat?: string, source?: string, person?: string, timeRange?: string) => {
+  const loadLeads = useCallback(async (search?: string, star?: string, status?: string, level?: string, cat?: string, source?: string, person?: string, timeRange?: string) => {
     setLoading(true)
     const params = new URLSearchParams()
+    if (search && search.trim()) params.set('search', search.trim())
     if (star && star !== '全部星级') {
       if (star === '5星') params.set('star', '5')
       else if (star === '4星') params.set('star', '4')
@@ -177,10 +179,10 @@ export default function InquiryPage({ onLeadDetail }: { onLeadDetail?: (id: stri
     }).catch(() => {})
   }, [])
 
-  useEffect(() => { loadLeads(fStar, fStatus, fLevel, fCat, fSource, fPerson, fTime) }, [loadLeads, fStar, fStatus, fLevel, fCat, fSource, fPerson, fTime])
+  useEffect(() => { loadLeads(fSearch, fStar, fStatus, fLevel, fCat, fSource, fPerson, fTime) }, [loadLeads, fSearch, fStar, fStatus, fLevel, fCat, fSource, fPerson, fTime])
 
   const refreshLeads = async () => {
-    await loadLeads(fStar, fStatus, fLevel, fCat, fSource, fPerson, fTime)
+    await loadLeads(fSearch, fStar, fStatus, fLevel, fCat, fSource, fPerson, fTime)
   }
 
   const totalPages = Math.ceil(filtered.length / pageSize)
@@ -501,6 +503,26 @@ export default function InquiryPage({ onLeadDetail }: { onLeadDetail?: (id: stri
               </div>
             )}
           </div>
+          <div className="flex flex-col gap-1">
+            <span className="text-[10px] font-bold tracking-wider text-on-surface-variant uppercase">搜索</span>
+            <div className="relative">
+              <input
+                type="text"
+                value={fSearch}
+                onChange={e => setFSearch(e.target.value)}
+                placeholder="输入关键词搜索"
+                className="bg-surface-container-low border border-border-subtle rounded pl-2 pr-6 py-1 text-xs w-40 focus:ring-secondary outline-none placeholder:text-slate-400"
+              />
+              {fSearch && (
+                <button
+                  type="button"
+                  onClick={() => setFSearch('')}
+                  className="absolute right-1 top-1/2 -translate-y-1/2 w-4 h-4 flex items-center justify-center text-slate-400 hover:text-slate-600 hover:bg-slate-200 rounded-full text-[10px]"
+                  title="清空搜索"
+                >×</button>
+              )}
+            </div>
+          </div>
         </div>
         <div className="flex items-center gap-2 ml-auto">
           <span className="text-xs text-on-surface-variant">批量操作:</span>

apps/web/src/components/RuleCenterPage.tsx

@@ -138,9 +138,9 @@ export default function RuleCenterPage() {
   const [crawlers, setCrawlers] = useState<CrawlerConfig[]>([])
   const [crawlersLoading, setCrawlersLoading] = useState(true)
   const [editCrawlerId, setEditCrawlerId] = useState<string | null>(null)
-  const [editForm, setEditForm] = useState<{ name: string; targetUrl: string; type: string; sourceName: string; scriptPath: string; schedule: string; keywords: string; categories: string }>({ name: '', targetUrl: '', type: 'bid', sourceName: '', scriptPath: '', schedule: '', keywords: '', categories: '' })
+  const [editForm, setEditForm] = useState<{ name: string; targetUrl: string; type: string; sourceName: string; scriptPath: string; schedule: string; keywords: string; categories: string }>({ name: '', targetUrl: '', type: 'bid', sourceName: '', scriptPath: '', schedule: '', keywords: '', categories: '[]' })
   const [showAddModal, setShowAddModal] = useState(false)
-  const [addForm, setAddForm] = useState<{ name: string; targetUrl: string; type: string; sourceName: string; scriptPath: string; schedule: string; keywords: string; categories: string }>({ name: '', targetUrl: '', type: 'bid', sourceName: '', scriptPath: '', schedule: '0 */6 * * *', keywords: '', categories: '' })
+  const [addForm, setAddForm] = useState<{ name: string; targetUrl: string; type: string; sourceName: string; scriptPath: string; schedule: string; keywords: string; categories: string }>({ name: '', targetUrl: '', type: 'bid', sourceName: '', scriptPath: '', schedule: '0 */6 * * *', keywords: '', categories: '[]' })
   const [runModal, setRunModal] = useState<{ id: string; name: string } | null>(null)
   const [runResult, setRunResult] = useState<'running' | 'success' | 'error'>('running')
 
@@ -290,18 +290,17 @@ export default function RuleCenterPage() {
       sourceName: c.sourceName || '',
       scriptPath: c.scriptPath || '',
       schedule: c.schedule || '',
-      keywords: c.keywords ? (() => { try { return JSON.parse(c.keywords).join(', ') } catch { return c.keywords } })() : '',
+      keywords: '',
-      categories: c.categories ? (() => { try { return JSON.parse(c.categories).join(', ') } catch { return c.categories } })() : '',
+      categories: c.categories ? (() => { try { const p = JSON.parse(c.categories); return Array.isArray(p) ? JSON.stringify(p) : '[]' } catch { return '[]' } })() : '[]',
     })
   }
 
   const saveCrawler = async (id: string) => {
     const payload: Record<string, string | null> = { name: editForm.name, targetUrl: editForm.targetUrl, type: editForm.type, sourceName: editForm.sourceName || null, scriptPath: editForm.scriptPath || null }
     if (editForm.schedule) payload.schedule = editForm.schedule
-    const kwArr = editForm.keywords.split(/[,，、\s]+/).filter(Boolean)
+    const catArr: string[] = editForm.categories ? JSON.parse(editForm.categories) : []
-    payload.keywords = kwArr.length > 0 ? JSON.stringify(kwArr) : ''
+    payload.categories = catArr.length > 0 ? JSON.stringify(catArr) : null
-    const catArr = editForm.categories.split(/[,，、\s]+/).filter(Boolean)
+    // 新配置不再使用 keywords 字段，但不清理旧数据（resolveKeywords 有 fallback）
-    payload.categories = catArr.length > 0 ? JSON.stringify(catArr) : ''
     try {
       const res = await fetch(`${CRAWLER_API}/${id}`, {
         method: 'PUT',
@@ -334,8 +333,7 @@ export default function RuleCenterPage() {
 
   const addCrawler = async () => {
     if (!addForm.name.trim() || !addForm.targetUrl.trim()) return
-    const kwArr = addForm.keywords.split(/[,，、\s]+/).filter(Boolean)
+    const catArr: string[] = addForm.categories ? JSON.parse(addForm.categories) : []
-    const catArr = addForm.categories.split(/[,，、\s]+/).filter(Boolean)
     try {
       const res = await fetch(CRAWLER_API, {
         method: 'POST',
@@ -347,7 +345,7 @@ export default function RuleCenterPage() {
           sourceName: addForm.sourceName || null,
           scriptPath: addForm.scriptPath || null,
           schedule: addForm.schedule || null,
-          keywords: kwArr.length > 0 ? JSON.stringify(kwArr) : null,
+          keywords: null,
           categories: catArr.length > 0 ? JSON.stringify(catArr) : null,
         }),
       })
@@ -355,7 +353,7 @@ export default function RuleCenterPage() {
       const created: CrawlerConfig = await res.json()
       setCrawlers(prev => [...prev, created])
       setShowAddModal(false)
-      setAddForm({ name: '', targetUrl: '', type: 'bid', sourceName: '', scriptPath: '', schedule: '0 */6 * * *', keywords: '', categories: '' })
+      setAddForm({ name: '', targetUrl: '', type: 'bid', sourceName: '', scriptPath: '', schedule: '0 */6 * * *', keywords: '', categories: '[]' })
     } catch { alert('创建失败') }
   }
 
@@ -739,7 +737,7 @@ export default function RuleCenterPage() {
                     <th className="p-3 text-[10px] font-bold tracking-wider text-on-surface-variant uppercase">采集器名称</th>
                     <th className="p-3 text-[10px] font-bold tracking-wider text-on-surface-variant uppercase">目标网址</th>
                     <th className="p-3 text-[10px] font-bold tracking-wider text-on-surface-variant uppercase">抓取定时</th>
-                    <th className="p-3 text-[10px] font-bold tracking-wider text-on-surface-variant uppercase">过滤关键词</th>
+                    <th className="p-3 text-[10px] font-bold tracking-wider text-on-surface-variant uppercase">关联品类</th>
                     <th className="p-3 text-[10px] font-bold tracking-wider text-on-surface-variant uppercase">状态</th>
                     <th className="p-3 text-[10px] font-bold tracking-wider text-on-surface-variant uppercase">运行统计</th>
                     <th className="p-3 text-[10px] font-bold tracking-wider text-on-surface-variant uppercase">操作</th>
@@ -762,7 +760,28 @@ export default function RuleCenterPage() {
                             </select>
                           </td>
                           <td className="p-3">
-                            <input value={editForm.keywords} onChange={e => setEditForm(f => ({ ...f, keywords: e.target.value }))} placeholder="用逗号分隔" className="w-full border border-border-subtle rounded px-2 py-1 text-sm outline-none focus:ring-2 focus:ring-secondary/20" />
+                            <div className="max-h-[150px] overflow-y-auto space-y-1 text-xs">
+                              {categories.length === 0 ? (
+                                <span className="text-slate-400">请先在「关键词库管理」添加品类</span>
+                              ) : categories.map(cat => {
+                                const current: string[] = editForm.categories ? JSON.parse(editForm.categories) : []
+                                const selected = current.includes(cat.name)
+                                return (
+                                  <label key={cat.id} className="flex items-center gap-1.5 cursor-pointer hover:bg-slate-50 rounded p-0.5">
+                                    <input
+                                      type="checkbox"
+                                      checked={selected}
+                                      onChange={() => {
+                                        const next = selected ? current.filter(n => n !== cat.name) : [...current, cat.name]
+                                        setEditForm(f => ({ ...f, categories: JSON.stringify(next) }))
+                                      }}
+                                      className="accent-secondary"
+                                    />
+                                    {cat.name}
+                                  </label>
+                                )
+                              })}
+                            </div>
                           </td>
                           <td className="p-3">
                             <span className={`px-2 py-0.5 text-[10px] font-medium rounded-full border ${getStatusStyle(c.status)}`}>
@@ -785,15 +804,22 @@ export default function RuleCenterPage() {
                           <td className="p-3 text-xs text-on-surface-variant max-w-[200px] truncate">{c.targetUrl}</td>
                           <td className="p-3 text-xs text-on-surface-variant">{getCronLabel(c.schedule)}</td>
                           <td className="p-3">
-                            {c.keywords ? (
+                            {c.categories ? (
                               <div className="flex flex-wrap gap-1">
-                                {(JSON.parse(c.keywords) as string[]).slice(0, 3).map((kw, i) => (
+                                {(JSON.parse(c.categories) as string[]).slice(0, 3).map((cat, i) => (
-                                  <span key={i} className="px-1.5 py-0.5 bg-blue-50 text-blue-600 text-[10px] rounded">{kw}</span>
+                                  <span key={i} className="px-1.5 py-0.5 bg-purple-50 text-purple-600 text-[10px] rounded">{cat}</span>
                                 ))}
-                                {(JSON.parse(c.keywords) as string[]).length > 3 && (
+                                {(JSON.parse(c.categories) as string[]).length > 3 && (
-                                  <span className="text-[10px] text-slate-400">+{JSON.parse(c.keywords).length - 3}</span>
+                                  <span className="text-[10px] text-slate-400">+{JSON.parse(c.categories).length - 3}</span>
                                 )}
                               </div>
+                            ) : c.keywords ? (
+                              <div className="flex flex-wrap gap-1 items-center">
+                                {(JSON.parse(c.keywords) as string[]).slice(0, 3).map((kw, i) => (
+                                  <span key={i} className="px-1.5 py-0.5 bg-slate-100 text-slate-500 text-[10px] rounded">{kw}</span>
+                                ))}
+                                <span className="text-[10px] text-slate-400">(旧)</span>
+                              </div>
                             ) : <span className="text-xs text-slate-400">全部</span>}
                           </td>
                            <td className="p-3">
@@ -1085,12 +1111,34 @@ export default function RuleCenterPage() {
                   </select>
                 </div>
                 <div className="col-span-2">
-                  <span className="text-[10px] font-bold tracking-wider text-on-surface-variant uppercase block mb-1">过滤关键词（逗号分隔，留空表示抓取全部）</span>
+                  <span className="text-[10px] font-bold tracking-wider text-on-surface-variant uppercase block mb-2">关联品类（选中的品类关键词用于过滤公告）</span>
-                  <input value={addForm.keywords} onChange={e => setAddForm(f => ({ ...f, keywords: e.target.value }))} placeholder="电缆, 防火门, 配电箱" className="w-full border border-border-subtle rounded-lg px-3 py-2 text-sm outline-none focus:ring-2 focus:ring-secondary/20" />
+                  <div className="max-h-[200px] overflow-y-auto border border-border-subtle rounded-lg p-3 space-y-2">
+                    {categories.length === 0 ? (
+                      <p className="text-xs text-on-surface-variant">暂无品类，请先在「关键词库管理」中添加品类</p>
+                    ) : categories.map(cat => {
+                      const current: string[] = addForm.categories ? JSON.parse(addForm.categories) : []
+                      const selected = current.includes(cat.name)
+                      return (
+                        <label key={cat.id} className="flex items-center gap-2 cursor-pointer hover:bg-slate-50 p-1 rounded">
+                          <input
+                            type="checkbox"
+                            checked={selected}
+                            onChange={() => {
+                              const next = selected ? current.filter(n => n !== cat.name) : [...current, cat.name]
+                              setAddForm(f => ({ ...f, categories: JSON.stringify(next) }))
+                            }}
+                            className="accent-secondary"
+                          />
+                          <span className="text-sm">{cat.name}</span>
+                          {(() => { try { const k = JSON.parse(cat.keywords); return Array.isArray(k) ? k : [] } catch { return [] } })().length > 0 && (
+                            <span className="text-[10px] text-on-surface-variant">
+                              ({(() => { try { const k = JSON.parse(cat.keywords); return Array.isArray(k) ? k.slice(0, 3).join(', ') : '' } catch { return '' } })()})
+                            </span>
+                          )}
+                        </label>
+                      )
+                    })}
                   </div>
-                <div className="col-span-2">
-                  <span className="text-[10px] font-bold tracking-wider text-on-surface-variant uppercase block mb-1">所属品类（逗号分隔，留空表示全部品类）</span>
-                  <input value={addForm.categories} onChange={e => setAddForm(f => ({ ...f, categories: e.target.value }))} placeholder="工程建材, 电力设备, 钢材" className="w-full border border-border-subtle rounded-lg px-3 py-2 text-sm outline-none focus:ring-2 focus:ring-secondary/20" />
                 </div>
               </div>
               <div className="flex gap-3 pt-2">

scripts/tender-fetcher/fetch-v1.2.js

@@ -31,17 +31,20 @@ const args = process.argv.slice(2)
 const keywordIdx = args.indexOf('--keyword')
 const KEYWORD = (keywordIdx >= 0 && args[keywordIdx + 1]) ? args[keywordIdx + 1] : ''
 
-// 公告类型：可按需增减。支持的类型值见 API 返回的 announcementType 字段
+// 公告类型：与 API 返回的 announcementType 字段值严格一致
-const TYPES = ['招采公告'];
+const TYPES = ['招采公告', '变更公告'];
-// 可选：留空则从上次抓取日期继续；有值则从指定日期开始
+// 可选：留空则从上次抓取日期继续；有值则从指定日期开始（支持环境变量覆盖）
-const START_DATE = '';
+const START_DATE = process.env.START_DATE || '';
 const END_DATE = new Date().toISOString().split('T')[0];  // 今天
 // 跨天首次运行(state 为空)时回溯 N 天, 避免错过前一天后半天发布的公告
 const BACKFILL_DAYS = 3;
 const OUTPUT_DIR = path.join(process.env.HOME, 'desktop/招标公告', END_DATE);
 const PDF_DIR = path.join(OUTPUT_DIR, 'pdf');     // PDF 附件
 const HTML_DIR = path.join(OUTPUT_DIR, 'html');    // HTML 转换（待安装转换技能）
-const STATE_FILE = path.join(OUTPUT_DIR, 'downloaded.json');  // 已下载记录
+// 每个关键词使用独立的状态文件，避免多关键词共用状态导致后续关键词跳过
+const STATE_FILE = KEYWORD
+  ? path.join(OUTPUT_DIR, `downloaded_${KEYWORD}.json`)
+  : path.join(OUTPUT_DIR, 'downloaded.json');
 const LOG_FILE = path.join(OUTPUT_DIR, 'fetch.log');  // 运行日志
 const CONCURRENCY = 3;  // 并发下载数
 const RETRY_TIMES = 3;
@@ -104,9 +107,10 @@ function request(url, options = {}, retries = RETRY_TIMES) {
     };
 
     const req = protocol.request(reqOptions, (res) => {
-      let data = '';
+      const chunks = [];
-      res.on('data', chunk => data += chunk);
+      res.on('data', chunk => chunks.push(chunk));
       res.on('end', () => {
+        const data = Buffer.concat(chunks).toString('utf8');
         if (res.statusCode === 301 || res.statusCode === 302) {
           const location = res.headers.location;
           if (location.startsWith('http')) {
@@ -348,15 +352,21 @@ async function main() {
 
   log(`========== 开始抓取: ${KEYWORD} ==========`);
 
-  // 确定起始日期（差量：上次运行日期 或 配置的 START_DATE；跨天首次运行回溯 N 天）
+  // 确定起始日期：START_DATE 为空时退缩到上次运行的前 1 天（重叠 24 小时，覆盖 cron 间隔内漏抓的公告）
-  const sinceDate = START_DATE || (state.lastRun ? state.lastRun.split('T')[0] : null) || (() => {
+  // state.downloaded 通过 systemId 去重，重叠不会造成重复入库
+  let sinceDate = START_DATE || (state.lastRun ? state.lastRun.split('T')[0] : null) || (() => {
     const d = new Date(Date.now() - BACKFILL_DAYS * 86400 * 1000);
     return d.toISOString().split('T')[0];
   })();
+  // 增加 1 天回溯，覆盖 lastRun 之后但在 cron 间隔内发布的公告
+  if (!START_DATE && state.lastRun) {
+    const yesterday = new Date(Date.now() - 86400 * 1000).toISOString().split('T')[0];
+    sinceDate = yesterday;
+  }
   if (START_DATE) {
     log(`指定日期范围: ${START_DATE} ~ ${END_DATE}`);
   } else if (state.lastRun) {
-    log(`差量模式: 自 ${state.lastRun.substring(0, 10)} 以来新增`);
+    log(`增量模式(含 1 天回溯): ${sinceDate} ~ ${END_DATE}`);
   } else if (sinceDate !== END_DATE) {
     log(`跨天补抓: ${sinceDate} ~ ${END_DATE}`);
   } else {