@yolk_vat-y/dsh-project-memory 0.5.0 → 0.5.2

package/src/tools/index-repo.js

@@ -1,7 +1,7 @@
 import { defineTool } from '@deepseek-ai/dsh-tools'
 import path from 'node:path'
-import { readFileSync, statSync } from 'node:fs'
-import { isSupportedCode, isSupportedDoc, looksLikeDump, memoryRootFor, relativePath, sha256OfFile, storeKey, walkDir } from '../util/fs.js'
+import { statSync } from 'node:fs'
+import { isSupportedCode, isSupportedDoc, looksLikeDump, memoryRootFor, readFileForIndex, relativePath, storeKey, walkDir } from '../util/fs.js'
 import { buildDocEntries } from '../doc-pipeline.js'
 import { scanSymbols } from '../symbols.js'
 import { linkEntries } from '../link.js'
@@ -38,8 +38,8 @@ export async function indexRepository(ctx, config, root, { reindex = false } = {
         continue
       }
 
-      // existing declared above before hash
-      const { hash } = await sha256OfFile(filePath)
+      // 单次读盘：同一 buffer 供哈希与正文使用（不再 sha256OfFile + readFileSync 读两遍）
+      const { hash, buffer } = readFileForIndex(filePath)
       if (!reindex && existing && existing.sha256 === hash) {
         skipped++
         continue
@@ -47,12 +47,11 @@ export async function indexRepository(ctx, config, root, { reindex = false } = {
 
       let entries
       if (isSupportedCode(ext)) {
-        const content = readFileSync(filePath, 'utf8')
-        entries = scanSymbols(rel, filePath, content)
+        entries = scanSymbols(rel, filePath, buffer.toString('utf8'))
         fileUpdates.push({ rel, expectedHash: existing?.sha256, hash, size, entries, type: 'code' })
         updated++
       } else {
-        const content = readFileSync(filePath, 'utf8')
+        const content = buffer.toString('utf8')
         if (looksLikeDump(content)) {
           fileUpdates.push({ rel, deleted: true })
           skipped++

package/src/util/fs.js

@@ -1,4 +1,4 @@
-import { accessSync, constants, readdirSync, statSync } from 'node:fs'
+import { accessSync, constants, readdirSync, readFileSync, statSync } from 'node:fs'
 import { readFile } from 'node:fs/promises'
 import { createHash } from 'node:crypto'
 import path from 'node:path'
@@ -32,6 +32,18 @@ export async function sha256OfFile(filePath) {
   return { hash: sha256OfBuffer(buf), size: buf.length }
 }
 
+/**
+ * 单次同步读：同一 buffer 同时供内容哈希与正文解码使用。
+ *
+ * 替代 “await sha256OfFile() + readFileSync()” 的二次读盘。对大量小文件的批量
+ * 索引，逐文件 `async readFile` 的线程池往返是主要开销（实测 2000 文件 260ms →
+ * 单次同步读 ~6ms）；调用方拿到 buffer 后按需 toString('utf8')，未变更文件无需解码。
+ */
+export function readFileForIndex(filePath) {
+  const buffer = readFileSync(filePath)
+  return { hash: sha256OfBuffer(buffer), size: buffer.length, buffer }
+}
+
 export async function readTextFile(filePath, maxBytes = 2 * 1024 * 1024) {
   const buf = await readFile(filePath)
   if (buf.length > maxBytes) {

package/src/watch.js

@@ -1,6 +1,6 @@
-import { existsSync, readFileSync, statSync } from 'node:fs'
+import { existsSync, statSync } from 'node:fs'
 import path from 'node:path'
-import { isSupportedCode, isSupportedDoc, memoryRootFor, relativePath, sha256OfFile, storeKey, walkDir } from './util/fs.js'
+import { isSupportedCode, isSupportedDoc, memoryRootFor, readFileForIndex, relativePath, storeKey, walkDir } from './util/fs.js'
 import { buildDocEntries } from './doc-pipeline.js'
 import { scanSymbols } from './symbols.js'
 import { linkEntries } from './link.js'
@@ -13,13 +13,14 @@ export class WatchManager {
     this.config = config
     this.roots = new Map()
     this.timer = null
+    this._polling = false
   }
 
   restorePersisted() {
     const cwd = process.cwd()
-    const store = new ProjectMemoryStore(memoryRootFor(cwd, this.config.memoryDir))
+    // 用 load() 的返回值：storeCache 命中时 load() 返回的是缓存实例，忽略返回值会拿到空 store
+    const store = new ProjectMemoryStore(memoryRootFor(cwd, this.config.memoryDir)).load()
     if (existsSync(store.dir)) {
-      store.load()
       for (const root of store.watchlist) {
         if (typeof root === 'string' && root) this.addRoot(root)
       }
@@ -43,7 +44,11 @@ export class WatchManager {
 
   start(intervalMs = 15000) {
     if (this.timer) return
-    this.timer = setInterval(() => this.poll(), Math.max(intervalMs, 1000))
+    // NaN/undefined 会让 setInterval 退化成 1ms 轮询（Node 只发一条 TimeoutNaNWarning），
+    // 足以打满事件循环让 agent 无法响应；非法值回退到 15s。
+    const raw = Number(intervalMs)
+    const ms = Number.isFinite(raw) ? Math.max(raw, 1000) : 15000
+    this.timer = setInterval(() => this.poll(), ms)
     if (this.timer.unref) this.timer.unref()
   }
 
@@ -53,12 +58,20 @@ export class WatchManager {
   }
 
   async poll() {
-    for (const [root, state] of this.roots) {
-      try {
-        await this.pollRoot(root, state)
-      } catch (err) {
-        console.error(`[dsh-project-memory] watch poll failed for ${root}: ${err.message}`)
+    // setInterval 不等待上一轮：大仓库/文档 LLM 摘要让一轮 >interval 时，
+    // 轮询会叠加成并发索引，最终打满事件循环。用重入锁让慢轮询自然跳过。
+    if (this._polling) return
+    this._polling = true
+    try {
+      for (const [root, state] of this.roots) {
+        try {
+          await this.pollRoot(root, state)
+        } catch (err) {
+          console.error(`[dsh-project-memory] watch poll failed for ${root}: ${err.message}`)
+        }
       }
+    } finally {
+      this._polling = false
     }
   }
 
@@ -89,14 +102,15 @@ export class WatchManager {
         continue
       }
 
-      const { hash } = await sha256OfFile(filePath)
+      // 单次读盘：同一 buffer 供哈希与正文使用
+      const { hash, buffer } = readFileForIndex(filePath)
       const existing = state.store.fileRecord(rel)
       if (existing && existing.sha256 === hash) continue
 
       try {
         let entries
         if (isSupportedCode(ext)) {
-          entries = scanSymbols(rel, filePath, readFileSync(filePath, 'utf8'))
+          entries = scanSymbols(rel, filePath, buffer.toString('utf8'))
         } else {
           entries = await buildDocEntries(this.ctx.llm, rel, filePath, {
             chunkChars: this.config.chunkChars,