@yolk_vat-y/dsh-project-memory 0.5.8 → 0.5.9

package/src/tools/index-repo.js

@@ -1,26 +1,45 @@
 import { defineTool } from '@deepseek-ai/dsh-tools'
 import path from 'node:path'
 import { statSync } from 'node:fs'
-import { assertIndexRoot, memoryRootFor, relativePath, storeKey, walkDir } from '../util/fs.js'
+import { assertIndexRoot, assertSafeRoot, memoryRootFor, relativePath, scanLimits, storeKey, walkDir } from '../util/fs.js'
 import { DROP, OVERSIZE, UNCHANGED, commitFileUpdates, fileKind, planFileIndex, toFileUpdate } from '../index-pipeline.js'
 import { ProjectMemoryStore } from '../store.js'
 import { onFileIndexed, isTypeScriptFile } from '../enhancer.js'
 
-export async function indexRepository(ctx, config, root, { reindex = false } = {}) {
+/**
+ * 每批提交的文件数。旧实现把整棵树的 updates 攒到最后一次性 commit：一次全量扫描的
+ * 峰值内存 ≈ 整棵树的所有条目（家目录级别直接 OOM）。分批后峰值与树的大小解耦。
+ */
+const COMMIT_BATCH = 200
+
+export async function indexRepository(ctx, config, root, { reindex = false, allowUnsafe = false } = {}) {
   // 先校验根目录：缺了它，下面 `new ProjectMemoryStore(...).load()` 的 save() 会把
   // 不存在的 root 连同 .dsh-project-memory 一起 mkdirSync 出来。
   assertIndexRoot(root)
+  // 再校验安全：家目录 / 系统目录 / Homebrew 前缀整体索引会吃满内存（issue #5）。
+  assertSafeRoot(root, { allowUnsafe })
   const memoryDir = memoryRootFor(root, config.memoryDir)
   const store = new ProjectMemoryStore(memoryDir).load()
 
   const seen = new Set()
-  const updates = []
   const failures = []
+  // 增强只能在文件的基础条目**落盘之后**排队：TS 增强是「合并进已有条目」，
+  // 若先于提交跑，随后 setEntries 会把增强结果整段覆盖掉。
+  const tsFiles = []
+  let batch = []
   let indexed = 0
   let updated = 0
   let skipped = 0
 
-  for (const filePath of walkDir(root)) {
+  const flushBatch = () => {
+    if (!batch.length) return
+    // 中间批次不做 unseen 清理、不重建链接（最后一批统一做）——否则每批都要遍历整个 store。
+    commitFileUpdates(store, { updates: batch, link: false })
+    batch = []
+  }
+
+  const { files, truncated } = walkDir(root, scanLimits(config))
+  for (const filePath of files) {
     const rel = storeKey(relativePath(root, filePath))
     seen.add(rel)
     const kind = fileKind(path.extname(filePath).toLowerCase())
@@ -36,37 +55,50 @@ export async function indexRepository(ctx, config, root, { reindex = false } = {
       }
       if (plan.key === OVERSIZE) {
         // 体积超限的代码文件：旧记录一律清掉，避免检索命中一个已经不索引的文件。
-        updates.push({ rel, drop: true })
+        batch.push({ rel, drop: true })
         skipped++
+        if (batch.length >= COMMIT_BATCH) flushBatch()
         continue
       }
-      updates.push(toFileUpdate(rel, plan, record))
+      batch.push(toFileUpdate(rel, plan, record))
       if (plan.key === DROP) skipped++
-      else if (plan.type === 'code') updated++
-      else indexed++
+      else if (plan.type === 'code') {
+        updated++
+        if (isTypeScriptFile(filePath)) tsFiles.push([rel, filePath])
+      } else {
+        indexed++
+      }
+      if (batch.length >= COMMIT_BATCH) flushBatch()
     } catch {
       failures.push(rel)
     }
   }
 
-  // 单事务提交：写入 + 清理本轮未见到的旧条目 + 重建链接。
-  const { removed } = commitFileUpdates(store, { updates, unseen: seen })
+  // 收尾：写完最后一批 + 清理本轮未见到的旧条目 + 重建链接。
+  // 截断时**不做 unseen 清理**：没扫到的文件不等于被删了。
+  const { removed } = commitFileUpdates(store, {
+    updates: batch,
+    unseen: truncated ? null : seen,
+    link: true,
+  })
   const stats = store.stats()
   let report =
     `Indexed project: ${root}\n` +
     `docs indexed: ${indexed}, code symbols updated: ${updated}, unchanged skipped: ${skipped}, removed: ${removed}\n` +
     `memory store: ${stats.files} files, ${stats.entries} entries, ${stats.experience} experience notes`
+  if (truncated) {
+    const { maxFiles, maxDepth } = scanLimits(config)
+    report +=
+      `\nscan truncated at the safety limit (maxFiles=${maxFiles}, maxDepth=${maxDepth}): only part of the tree was indexed.` +
+      ' Raise maxScanFiles/maxScanDepth if this project is legitimately that large.'
+  }
   if (failures.length) {
     report += `\nfailed to index ${failures.length} file(s): ${failures.join(', ')}`
   }
 
-  // Trigger TS enhancement for code files (TS/JS only)
-  for (const update of updates) {
-    if (update.type !== 'code') continue
-    const filePath = path.join(root, update.rel)
-    if (isTypeScriptFile(filePath)) {
-      onFileIndexed(store, update.rel, filePath, config, root)
-    }
+  // Trigger TS enhancement for code files (TS/JS only), now that the base entries are on disk.
+  for (const [rel, filePath] of tsFiles) {
+    onFileIndexed(store, rel, filePath, config, root)
   }
 
   return report
@@ -100,6 +132,7 @@ export function indexRepoTool(ctx, config) {
       // 透传原始入参：Windows 风格路径在 POSIX 上会被 resolve 成 <cwd>/D:\...，
       // 报错时要点明这是路径风格问题，而不是“目录被删了”。
       assertIndexRoot(root, args.root)
+      assertSafeRoot(root, { requested: args.root, allowUnsafe: config?.allowUnsafeRoots === true })
       return indexRepository(ctx, config, root, { reindex: Boolean(args.reindex) })
     },
   })

package/src/tools/lesson-tools.js

@@ -1,14 +1,11 @@
 import { defineTool } from '@deepseek-ai/dsh-tools'
-import { assertIndexRoot, memoryRootFor, resolveIndexRoot } from '../util/fs.js'
+import { assertIndexRoot, memoryRootFor, resolveSafeIndexRoot } from '../util/fs.js'
 import { ProjectMemoryStore } from '../store.js'
 import { truncate } from '../util/text.js'
 import { cfgInsight, saveInsight, defaultGlobalFile, GlobalStore } from '../insight-store.js'
 import { ensureGlobalInit } from '../global-seed.js'
 import { INSIGHT_KINDS, INSIGHT_SCOPES } from '../insight-store.js'
-
-function sessionIdOf(exec) {
-  return exec?.agent?.session?.id || exec?.ctx?.session?.id
-}
+import { sessionIdOf } from '../util/task-view.js'
 
 export function lessonTool(config) {
   const kindDesc = `insight 语义：lesson(曾踩坑/纠偏, pattern→fix) | decision(权衡选型, choice→reason) | procedure(多步指南, steps) | experience(problem→solution，v0.4 兼容)。默认 lesson。所有 kind 都可带 trigger：命中即在动手前确定性注入。`
@@ -76,7 +73,7 @@ export function lessonTool(config) {
     },
     output: { schema: { type: 'string' }, render: (_a, v) => [{ type: 'text', text: v }] },
     async execute(args, exec) {
-      const root = resolveIndexRoot(exec, args.root)
+      const root = resolveSafeIndexRoot(exec, args.root, config)
       assertIndexRoot(root, args.root || root)
       const memoryDir = memoryRootFor(root, config.memoryDir)
       const store = new ProjectMemoryStore(memoryDir).load()

package/src/tools/query-memory.js

@@ -1,25 +1,17 @@
 import { defineTool } from '@deepseek-ai/dsh-tools'
 import path from 'node:path'
-import { memoryRootFor, resolveIndexRoot } from '../util/fs.js'
+import { memoryRootFor, resolveSafeIndexRoot } from '../util/fs.js'
 import { ProjectMemoryStore, storeOverview } from '../store.js'
 import { expandQuery } from '../llm.js'
 import { resolveRoute } from '../llm-route.js'
 import { GlobalStore, cfgInsight, defaultGlobalFile, recordHit } from '../insight-store.js'
 import { recallItems } from '../recall.js'
 import { truncate } from '../util/text.js'
+import { stepContent, stepStatus } from '../util/task-view.js'
 function toAbs(root, rel) {
   return path.isAbsolute(rel) ? rel : path.join(root, rel)
 }
 
-/** 步骤在历史数据里可能是字符串或 {content|text, status}：TaskBridge/注入/反思都按 content||text 读。 */
-function stepContent(s) {
-  if (typeof s === 'string') return s
-  return s?.content ?? s?.text ?? ''
-}
-function stepStatus(s) {
-  return typeof s === 'string' ? 'pending' : (s?.status || 'pending')
-}
-
 export function queryMemoryTool(ctx, config) {
   return defineTool({
     name: 'query_memory',
@@ -54,7 +46,7 @@ export function queryMemoryTool(ctx, config) {
       render: (_args, value) => [{ type: 'text', text: value }],
     },
     async execute(args, exec) {
-      const root = resolveIndexRoot(exec, args.root)
+      const root = resolveSafeIndexRoot(exec, args.root, config)
       // 空查询不是"全部"：recallItems 会过滤空串，rankEntriesStreaming 随即返回
       // entries.slice(0, limit)（任意条目、分数 0），task 分支的 includes('') 更是命中所有任务。
       if (!String(args.query ?? '').trim()) {

package/src/tools/remember.js

@@ -1,5 +1,5 @@
 import { defineTool } from '@deepseek-ai/dsh-tools'
-import { assertIndexRoot, memoryRootFor, resolveIndexRoot } from '../util/fs.js'
+import { assertIndexRoot, memoryRootFor, resolveSafeIndexRoot } from '../util/fs.js'
 import { ProjectMemoryStore } from '../store.js'
 
 export function rememberTool(config) {
@@ -34,7 +34,7 @@ export function rememberTool(config) {
       render: (_args, value) => [{ type: 'text', text: value }],
     },
     async execute(args, exec) {
-      const root = resolveIndexRoot(exec, args.root)
+      const root = resolveSafeIndexRoot(exec, args.root, config)
       // 写盘前校验根：否则一个拼错的 root 会被 mkdir 成字面量目录（连同 .dsh-project-memory）。
       assertIndexRoot(root, args.root || root)
       const memoryDir = memoryRootFor(root, config.memoryDir)

package/src/tools/stats.js

@@ -1,5 +1,5 @@
 import { defineTool } from '@deepseek-ai/dsh-tools'
-import { memoryRootFor, resolveIndexRoot } from '../util/fs.js'
+import { memoryRootFor, resolveSafeIndexRoot } from '../util/fs.js'
 import { ProjectMemoryStore, storeOverview } from '../store.js'
 import { truncate } from '../util/text.js'
 
@@ -22,7 +22,7 @@ export function statsTool(config) {
       render: (_args, value) => [{ type: 'text', text: value }],
     },
     async execute(args, exec) {
-      const root = resolveIndexRoot(exec, args.root)
+      const root = resolveSafeIndexRoot(exec, args.root, config)
       const store = new ProjectMemoryStore(memoryRootFor(root, config.memoryDir)).load()
       const overview = storeOverview(store)
       const files = Object.entries(store.files).sort((a, b) => String(b[1].indexedAt || '').localeCompare(String(a[1].indexedAt || '')))

package/src/tools/task-tools.js

@@ -1,29 +1,15 @@
 import { defineTool } from '@deepseek-ai/dsh-tools'
-import { assertIndexRoot, memoryRootFor, resolveIndexRoot } from '../util/fs.js'
+import { assertIndexRoot, memoryRootFor, resolveSafeIndexRoot } from '../util/fs.js'
 import { ProjectMemoryStore } from '../store.js'
 import { truncate } from '../util/text.js'
+import { sessionIdOf, stepProgress, timeAgo } from '../util/task-view.js'
 import { genTaskId, hash8, adoptStepsToSession, shouldAdoptToHost } from '../setup/taskbridge.js'
 import { fireReflect } from '../reflection-pipeline.js'
 import { resolveRoute } from '../llm-route.js'
 import { createHash } from 'node:crypto'
 
-function sessionIdOf(exec) {
-  return exec?.agent?.session?.id || exec?.ctx?.session?.id
-}
-
-function timeAgo(iso) {
-  const diff = Date.now() - new Date(iso).getTime()
-  const m = Math.floor(diff / 60000)
-  if (m < 1) return '刚刚'
-  if (m < 60) return `${m}分钟前`
-  const h = Math.floor(m / 60)
-  if (h < 24) return `${h}小时前`
-  return `${Math.floor(h / 24)}天前`
-}
-
 function summaryOf(task) {
-  const done = (task.steps || []).filter((s) => s.status === 'completed').length
-  const total = (task.steps || []).length
+  const { done, total } = stepProgress(task)
   const files = (task.files || []).length
   const mark = task.archived ? ' [归档]' : ''
   return `### ${task.title}${mark}\n- 进度: ${done}/${total} 完成\n- 文件: ${files} 个\n- 最后活动: ${timeAgo(task.lastActiveAt || task.updatedAt)}`
@@ -39,7 +25,7 @@ export function listTasksTool(config) {
     },
     output: { schema: { type: 'string' }, render: (_a, v) => [{ type: 'text', text: v }] },
     async execute(args, exec) {
-      const root = resolveIndexRoot(exec, args.root)
+      const root = resolveSafeIndexRoot(exec, args.root, config)
       assertIndexRoot(root, args.root || root)
       const store = new ProjectMemoryStore(memoryRootFor(root, config.memoryDir)).load()
       const tasks = store.getTasks()
@@ -66,7 +52,7 @@ export function selectTaskTool(config, host) {
     },
     output: { schema: { type: 'string' }, render: (_a, v) => [{ type: 'text', text: v }] },
     async execute(args, exec) {
-      const root = resolveIndexRoot(exec, args.root)
+      const root = resolveSafeIndexRoot(exec, args.root, config)
       assertIndexRoot(root, args.root || root)
       const store = new ProjectMemoryStore(memoryRootFor(root, config.memoryDir)).load()
       const sid = sessionIdOf(exec)
@@ -185,7 +171,7 @@ export function archiveTaskTool(config, host) {
     },
     output: { schema: { type: 'string' }, render: (_a, v) => [{ type: 'text', text: v }] },
     async execute(args, exec) {
-      const root = resolveIndexRoot(exec, args.root)
+      const root = resolveSafeIndexRoot(exec, args.root, config)
       assertIndexRoot(root, args.root || root)
       const store = new ProjectMemoryStore(memoryRootFor(root, config.memoryDir)).load()
       const task = store.getTask(args.taskId)

package/src/tools/watch-repo.js

@@ -1,6 +1,6 @@
 import { defineTool } from '@deepseek-ai/dsh-tools'
 import path from 'node:path'
-import { assertIndexRoot, isUnwatchableRoot, memoryRootFor, resolveIndexRoot } from '../util/fs.js'
+import { assertIndexRoot, assertSafeRoot, isUnsafeRoot, memoryRootFor, sessionMemoryRootOrNull } from '../util/fs.js'
 import { ProjectMemoryStore } from '../store.js'
 
 export function watchRepoTool(watchManager, config) {
@@ -29,23 +29,24 @@ export function watchRepoTool(watchManager, config) {
       const root = path.resolve(args.root)
       // 不存在的根不写进 watchlist：watch 每轮会 commit → save → mkdirSync，把它重新造出来。
       // 根是**文件**时同样要拦：否则 save() 的 mkdirSync 会抛裸 ENOTDIR。
+      // 家目录 / 系统目录 / Homebrew 前缀也不监听：整体轮询扫描会吃满内存（issue #5）。
       if (args.watch !== false) {
         try {
           assertIndexRoot(root, args.root)
+          assertSafeRoot(root, { requested: args.root, allowUnsafe: config?.allowUnsafeRoots === true })
         } catch (err) {
           return `Not watching: ${err.message}`
         }
       }
-      // 文件系统根 / 共享临时目录不整体监听（子目录允许）：会把无关程序和测试夹具的临时文件全扫进来
-      if (args.watch !== false && isUnwatchableRoot(root)) {
-        return `Refusing to watch ${root}: it is the filesystem root or the shared temp directory. Pass a project subdirectory instead.`
-      }
       const memoryDir = memoryRootFor(root, config.memoryDir)
-      const sessionRoot = resolveIndexRoot(exec)
-      const sessionMemoryDir = memoryRootFor(sessionRoot, config.memoryDir)
-      const store = new ProjectMemoryStore(memoryDir).load()
+      // 会话记忆根与工具侧同一套解析（标记优先 → 会话 cwd）；拿不到就跳过镜像。
+      const sessionRoot = sessionMemoryRootOrNull(exec, config)
+      const sessionMemoryDir = sessionRoot ? memoryRootFor(sessionRoot, config.memoryDir) : null
 
       const mirrorSessionWatchlist = async (present) => {
+        // 会话根不可用（家目录/系统目录且无标记）时跳过镜像：那会在不该有项目记忆的目录里
+        // 造出 watch.json，而 watch.json 一旦落在那里，下次以该目录为 cwd 启动又会把它读回来。
+        if (!sessionRoot || !sessionMemoryDir) return
         if (path.resolve(sessionMemoryDir) === path.resolve(memoryDir)) return
         const sessionStore = new ProjectMemoryStore(sessionMemoryDir).load()
         const removed = sessionStore.removeWatch(root)
@@ -55,11 +56,17 @@ export function watchRepoTool(watchManager, config) {
 
       if (args.watch === false) {
         watchManager.removeRoot(root)
-        store.commit((s) => s.removeWatch(root))
+        // 危险根的 store 一律不读不写：load() 一个历史遗留的超大 store 光读盘就能 OOM
+        // （这正是要修的场景），而写它会在家目录里造出 .dsh-project-memory。那份
+        // watch.json 现在也没有任何启动路径会读取（restorePersisted 只认会话 cwd），
+        // 留着即可；会话侧的镜像条目照常摘掉。
+        if (!isUnsafeRoot(root)) {
+          new ProjectMemoryStore(memoryDir).load().commit((s) => s.removeWatch(root))
+        }
         await mirrorSessionWatchlist(false)
         return `Stopped watching: ${root}`
       }
-      store.commit((s) => s.addWatch(root))
+      new ProjectMemoryStore(memoryDir).load().commit((s) => s.addWatch(root))
       await mirrorSessionWatchlist(true)
       watchManager.addRoot(root)
       watchManager.start(config.watchInterval * 1000)