@yolk_vat-y/dsh-project-memory 0.1.6 → 0.2.0

package/CHANGELOG.md

@@ -1,5 +1,15 @@
 # Changelog
 
+## 0.2.0 (2026-08-27)
+
+### CJK 检索增强
+- 链接侧：非拉丁符号名改用 CJK 边界正则 `(?<![CJK])名(?![CJK])`，解决 `用户服务` 误链 `用户服务管理器`；英文分支零改动
+- 查询侧：BM25 增加精确短语乘法加分 —— 3+ 字 CJK 短语命中 `title`/`keywords` 时 `score *= 1.5` 并重排，自适应不压过高相关结果
+- 查询侧：同义词表（`数据库连接池` ↔ `连接池` ↔ `DB pool`），查询展开后再走短语加分
+
+### 经验笔记 supersede 阈值收紧
+- 双向重叠判定：`overlap / query_tokens ≥ 0.7` 且 `overlap / item_tokens ≥ 0.7`（原单向 0.6），减少短问题误吞长笔记
+
 ## 0.1.6 (2026-08-25)
 
 ### 存储

package/README.md

@@ -149,7 +149,7 @@ These commands are for **maintaining the plugin code** — regular users do not
 
 ```bash
 npm install
-npm test          # 101 checks: chunker / symbols / store / tools / BM25 / links / watch / lazy / config / dump / concurrency / restore / size limit
+npm test          # chunker / symbols / store / tools / BM25 / links / watch / lazy / config / dump / concurrency / restore / size limit
 ```
 
 ## License

package/README.zh-CN.md

@@ -149,7 +149,7 @@ dsh web --patch ./config.yml
 
 ```bash
 npm install
-npm test          # 101 项检查：chunker / symbols / store / tools / BM25 / links / watch / lazy / config / dump / concurrency / restore / size limit
+npm test          # 检查项：chunker / symbols / store / tools / BM25 / links / watch / lazy / config / dump / concurrency / restore / size limit
 ```
 
 ## 许可证

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@yolk_vat-y/dsh-project-memory",
-  "version": "0.1.6",
+  "version": "0.2.0",
   "description": "Persistent project memory for dsh agents: index docs (PDF/Markdown/text) and code symbols into a searchable per-workspace store, recall them with cited sources, and keep experience entries (problems -> solutions) searchable on demand.",
   "type": "module",
   "main": "src/index.js",

package/src/link.js

@@ -1,9 +1,13 @@
 const LATIN_NAME = /^[A-Za-z0-9_]+$/
+const CJK_CHAR = /[\u3400-\u9fff\uf900-\ufaff\u3040-\u309f\u30a0-\u30ff\uac00-\ud7af]/
 
 function buildMatcher(name) {
   const lower = name.toLowerCase()
-  if (!LATIN_NAME.test(name)) return { lower, re: null }
-  return { lower, re: new RegExp(`(?<![a-z0-9_$])${lower}(?![a-z0-9_$])`) }
+  if (LATIN_NAME.test(name)) {
+    return { lower, re: new RegExp(`(?<![a-z0-9_$])${lower}(?![a-z0-9_$])`) }
+  }
+  const escaped = lower.replace(/[.*+?^${}()|[\]\\]/g, '\\$&')
+  return { lower, re: new RegExp(`(?<!${CJK_CHAR.source})${escaped}(?!${CJK_CHAR.source})`) }
 }
 
 export function linkEntries(store) {

package/src/store.js

@@ -303,8 +303,10 @@ export class ProjectMemoryStore {
     for (const item of this.experience) {
       const itemTokens = tokenize(item.problem)
       const overlap = itemTokens.filter((t) => tokens.includes(t)).length
-      const base = Math.min(tokens.length, itemTokens.length)
-      if (base && overlap / base >= 0.6 && overlap > bestOverlap) {
+      if (overlap === 0) continue
+      const ratioQuery = overlap / tokens.length
+      const ratioItem = overlap / itemTokens.length
+      if (ratioQuery >= 0.7 && ratioItem >= 0.7 && overlap > bestOverlap) {
         best = item
         bestOverlap = overlap
       }

package/src/util/search.js

@@ -1,6 +1,42 @@
 export const CJK_RANGE =
   /[\u3400-\u9fff\uf900-\ufaff\u3040-\u309f\u30a0-\u30ff\uac00-\ud7af]/
 
+const SYNONYMS = new Map([
+  ['数据库连接池', ['连接池', 'DB pool', 'db pool']],
+  ['连接池', ['数据库连接池', 'DB pool', 'db pool']],
+  ['DB pool', ['数据库连接池', '连接池']],
+  ['db pool', ['数据库连接池', '连接池']],
+])
+
+function extractCjkPhrases(text) {
+  const phrases = []
+  let run = ''
+  for (const ch of text) {
+    if (CJK_RANGE.test(ch)) {
+      run += ch
+    } else if (run.length >= 3) {
+      phrases.push(run)
+      run = ''
+    } else {
+      run = ''
+    }
+  }
+  if (run.length >= 3) phrases.push(run)
+  return phrases
+}
+
+function expandQuery(query) {
+  const lower = query.toLowerCase()
+  const expanded = new Set([lower])
+  for (const [key, vals] of SYNONYMS) {
+    if (lower.includes(key.toLowerCase())) {
+      for (const v of vals) expanded.add(v.toLowerCase())
+    }
+  }
+  const cjkPhrases = extractCjkPhrases(query)
+  return { original: lower, expanded: [...expanded], cjkPhrases }
+}
+
 export function tokenizeRaw(text) {
   if (!text) return []
   const lower = text.toLowerCase()
@@ -43,7 +79,9 @@ export function buildBm25(docs, getFieldText) {
     const terms = tokenizeRaw(text)
     const tf = {}
     for (const t of terms) tf[t] = (tf[t] || 0) + 1
-    return { doc, length: terms.length, tf }
+    const title = (doc.title || '').toLowerCase()
+    const keywords = (doc.keywords || []).join(' ').toLowerCase()
+    return { doc, length: terms.length, tf, title, keywords }
   })
   const df = {}
   for (const d of documents) {
@@ -55,7 +93,12 @@ export function buildBm25(docs, getFieldText) {
   return {
     idf,
     score(query) {
-      const q = tokenize(query)
+      const { expanded, cjkPhrases } = expandQuery(query)
+      const qTokens = new Set()
+      for (const term of expanded) {
+        for (const tok of tokenizeRaw(term)) qTokens.add(tok)
+      }
+      const q = [...qTokens]
       if (!q.length) return []
       const avgLen = avgdl
       return documents
@@ -67,6 +110,12 @@ export function buildBm25(docs, getFieldText) {
             if (!tf) continue
             score += idf(t) * ((tf * (K1 + 1)) / (tf + K1 * (1 - B + (B * len) / avgLen)))
           }
+          for (const phrase of cjkPhrases) {
+            const lowerPhrase = phrase.toLowerCase()
+            if (d.title.includes(lowerPhrase) || d.keywords.includes(lowerPhrase)) {
+              score *= 1.5
+            }
+          }
           return { doc: d.doc, score }
         })
         .filter((r) => r.score > 0)