claude-mem-lite 2.1.4 → 2.2.0

package/.claude-plugin/marketplace.json

@@ -10,7 +10,7 @@
   "plugins": [
     {
       "name": "claude-mem-lite",
-      "version": "2.1.4",
+      "version": "2.1.6",
       "source": "./",
       "description": "Lightweight persistent memory system for Claude Code — FTS5 search, episode batching, error-triggered recall"
     }

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-mem-lite",
-  "version": "2.1.4",
+  "version": "2.2.0",
   "description": "Lightweight persistent memory system for Claude Code — FTS5 search, episode batching, error-triggered recall",
   "author": {
     "name": "sdsrss"

package/README.md

@@ -95,6 +95,7 @@ The original sends **everything to the LLM and hopes it filters well**. claude-m
 - **Exploration bonus** -- New resources in the registry get a fair chance in composite ranking; zombie resources (high recommend, zero adopt) are penalized
 - **LLM concurrency control** -- File-based semaphore limits background workers to 2 concurrent LLM calls, preventing resource contention
 - **stdin overflow protection** -- Hook input truncated at 256KB with regex-based action salvage for oversized tool outputs
+- **Cross-session handoff** -- Captures session state (request, completed work, next steps, key files) on `/clear` or `/exit`, then injects context when the next session detects continuation intent via explicit keywords or FTS5 term overlap
 
 ## Platform Support
 
@@ -224,7 +225,7 @@ rm -rf ~/claude-mem-lite/   # pre-v0.5 unhidden (if not auto-moved)
 
 ## Database Schema
 
-Four core tables with FTS5 virtual tables for search:
+Five core tables with FTS5 virtual tables for search:
 
 **observations** -- Individual coding observations (decisions, bugfixes, features, etc.)
 ```
@@ -250,6 +251,12 @@ started_at, completed_at, status, prompt_counter
 id, content_session_id, prompt_text, prompt_number
 ```
 
+**session_handoffs** -- Cross-session handoff snapshots (UPSERT, max 2 per project)
+```
+project, type, session_id, working_on, completed, unfinished,
+key_files, key_decisions, match_keywords, created_at_epoch
+```
+
 FTS5 indexes: `observations_fts`, `session_summaries_fts`, `user_prompts_fts`
 
 ## How It Works
@@ -258,7 +265,7 @@ FTS5 indexes: `observations_fts`, `session_summaries_fts`, `user_prompts_fts`
 
 ```
 SessionStart
-  -> Generate session ID
+  -> Generate session ID (or save handoff snapshot on /clear)
   -> Mark stale sessions (>24h active) as abandoned
   -> Clean orphaned/stale lock files
   -> Query recent observations (24h)
@@ -281,11 +288,13 @@ PreToolUse (before tool execution)
 UserPromptSubmit
   -> Capture user prompt text to user_prompts table
   -> Increment session prompt counter
+  -> Handoff: detect continuation intent → inject previous session context
   -> Dispatch: recommend skill/agent based on user's actual prompt (Tier 0→1→2)
   -> Primary dispatch point — user intent is clearest here
 
 Stop
   -> Flush final episode buffer
+  -> Save handoff snapshot (on /exit)
   -> Collect dispatch feedback: adoption detection + outcome scoring
   -> Mark session completed
   -> Spawn LLM summary worker (poll-based wait)
@@ -419,6 +428,7 @@ claude-mem-lite/
   hook.mjs             # Claude Code hooks: episode capture, error recall, session management
   hook-llm.mjs         # Background LLM workers: episode extraction, session summaries
   hook-shared.mjs      # Shared hook infrastructure: session management, DB access, LLM calls
+  hook-handoff.mjs     # Cross-session handoff: state extraction, intent detection, injection
   hook-context.mjs     # CLAUDE.md context injection and token budgeting
   hook-episode.mjs     # Episode buffer management: atomic writes, pending entry merging
   hook-semaphore.mjs   # LLM concurrency control: file-based semaphore for background workers
@@ -444,7 +454,7 @@ claude-mem-lite/
     convert-commands.mjs # Converts command .md → SKILL.md in managed plugins
     index-managed.mjs  # Offline indexer for managed resources
   # Test & benchmark (dev only)
-  tests/               # Unit, property, integration, contract, E2E, pipeline tests (581 tests)
+  tests/               # Unit, property, integration, contract, E2E, pipeline tests (789 tests)
   benchmark/           # BM25 search quality benchmarks + CI gate
 ```
 
@@ -466,7 +476,7 @@ The benchmark suite runs as a CI gate (`npm run benchmark:gate`) to prevent sear
 
 ```bash
 npm run lint              # ESLint static analysis
-npm test                  # Run all 581 tests (vitest)
+npm test                  # Run all 789 tests (vitest)
 npm run test:smoke        # Run 5 core smoke tests
 npm run test:coverage     # Run tests with V8 coverage (≥70% lines/functions, ≥60% branches)
 npm run benchmark         # Run full search quality benchmark

package/README.zh-CN.md

@@ -95,6 +95,7 @@
 - **探索奖励** -- 注册表中的新资源在复合排名中获得公平机会；高推荐零采纳的"僵尸"资源被惩罚
 - **LLM 并发控制** -- 基于文件的信号量将后台 worker 限制为 2 个并发 LLM 调用，防止资源争用
 - **stdin 溢出保护** -- Hook 输入在 256KB 处截断，对超大工具输出使用正则挽救关键信息
+- **跨会话交接** -- 在 `/clear` 或 `/exit` 时捕获会话状态（请求、已完成工作、后续步骤、关键文件），下次会话检测到继续意图时自动注入上下文（支持显式关键词和 FTS5 术语重叠匹配）
 
 ## 平台支持
 
@@ -224,7 +225,7 @@ rm -rf ~/claude-mem-lite/   # v0.5 前的非隐藏目录（如未自动迁移）
 
 ## 数据库结构
 
-四张核心表 + FTS5 虚拟表用于搜索：
+五张核心表 + FTS5 虚拟表用于搜索：
 
 **observations** -- 单条编码观察（决策、bug修复、功能等）
 ```
@@ -250,6 +251,12 @@ started_at, completed_at, status, prompt_counter
 id, content_session_id, prompt_text, prompt_number
 ```
 
+**session_handoffs** -- 跨会话交接快照（UPSERT，每个项目最多 2 行）
+```
+project, type, session_id, working_on, completed, unfinished,
+key_files, key_decisions, match_keywords, created_at_epoch
+```
+
 FTS5 索引：`observations_fts`、`session_summaries_fts`、`user_prompts_fts`
 
 ## 工作原理
@@ -258,7 +265,7 @@ FTS5 索引：`observations_fts`、`session_summaries_fts`、`user_prompts_fts`
 
 ```
 SessionStart
-  -> 生成会话 ID
+  -> 生成会话 ID（/clear 时保存交接快照）
   -> 标记过期会话（活跃 >24h）为 abandoned
   -> 清理孤儿/过期锁文件
   -> 查询最近观察（24 小时内）
@@ -281,11 +288,13 @@ PreToolUse（工具执行前）
 UserPromptSubmit
   -> 捕获用户提示文本到 user_prompts 表
   -> 递增会话提示计数器
+  -> 交接：检测继续意图 → 注入上一次会话上下文
   -> 调度：根据用户实际提示推荐 skill/agent（Tier 0→1→2）
   -> 主要调度触发点 — 用户意图在此最为明确
 
 Stop
   -> 刷新最终 episode 缓冲区
+  -> 保存交接快照（/exit 时）
   -> 收集调度反馈：采纳检测 + 结果评分
   -> 标记会话为已完成
   -> 启动 LLM 摘要 worker（轮询等待）
@@ -419,6 +428,7 @@ claude-mem-lite/
   hook.mjs             # Claude Code 钩子：episode 捕获、错误回忆、会话管理
   hook-llm.mjs         # 后台 LLM worker：episode 提取、会话摘要
   hook-shared.mjs      # 共享钩子基础设施：会话管理、数据库访问、LLM 调用
+  hook-handoff.mjs     # 跨会话交接：状态提取、意图检测、上下文注入
   hook-context.mjs     # CLAUDE.md 上下文注入与 token 预算
   hook-episode.mjs     # Episode 缓冲区管理：原子写入、待处理条目合并
   hook-semaphore.mjs   # LLM 并发控制：基于文件的信号量
@@ -444,7 +454,7 @@ claude-mem-lite/
     convert-commands.mjs # 将 command .md 转换为托管插件中的 SKILL.md
     index-managed.mjs  # 托管资源离线索引器
   # 测试和基准（仅开发）
-  tests/               # 单元、属性、集成、契约、E2E、管线测试（581 个）
+  tests/               # 单元、属性、集成、契约、E2E、管线测试（789 个）
   benchmark/           # BM25 搜索质量基准 + CI 门控
 ```
 
@@ -466,7 +476,7 @@ claude-mem-lite/
 
 ```bash
 npm run lint              # ESLint 静态分析
-npm test                  # 运行全部 581 个测试（vitest）
+npm test                  # 运行全部 789 个测试（vitest）
 npm run test:smoke        # 运行 5 个核心冒烟测试
 npm run test:coverage     # 运行测试并生成 V8 覆盖率（≥70% 行/函数，≥60% 分支）
 npm run benchmark         # 运行完整搜索质量基准测试

package/dispatch-inject.mjs

@@ -24,7 +24,7 @@ const ALLOWED_BASES = [
 
 function isAllowedPath(filePath) {
   if (!filePath) return false;
-  return ALLOWED_BASES.some(base => filePath.startsWith(base));
+  return ALLOWED_BASES.some(base => filePath === base || filePath.startsWith(base + '/'));
 }
 
 // ─── Template Detection ──────────────────────────────────────────────────────

package/dispatch.mjs

@@ -494,7 +494,7 @@ function inferTechFromPrompt(prompt) {
     [/\b(typescript|ts)\b/i, 'typescript'],
     [/\b(python|django|flask|fastapi)\b/i, 'python'],
     [/\b(rust|cargo)\b/i, 'rust'],
-    [/\b(golang|go\s+\w+)\b/i, 'go'],
+    [/\b(golang|go\s+(?:build|test|run|get|mod|install|fmt|vet|generate|clean|work|tool))\b/i, 'go'],
     [/\b(java|spring|maven|gradle)\b/i, 'java'],
     [/\b(ruby|rails)\b/i, 'ruby'],
     [/\b(php|laravel|symfony)\b/i, 'php'],
@@ -578,7 +578,10 @@ export function needsHaikuDispatch(results) {
 
   if (results.length === 0) return true;
 
-  const topScore = Math.abs(results[0].relevance);
+  // Prefer composite_score (includes behavioral signals) over raw BM25 relevance.
+  // Both are negative (more negative = better). Use absolute values for comparison.
+  const scoreOf = r => Math.abs(r.composite_score ?? r.relevance);
+  const topScore = scoreOf(results[0]);
 
   // Relative threshold: if only one result or few results, use absolute minimum
   // For larger result sets, use mean-relative threshold
@@ -588,14 +591,14 @@ export function needsHaikuDispatch(results) {
   }
 
   // Compute mean relevance across results
-  const meanScore = results.reduce((sum, r) => sum + Math.abs(r.relevance), 0) / results.length;
+  const meanScore = results.reduce((sum, r) => sum + scoreOf(r), 0) / results.length;
 
   // Top result should be significantly above mean (at least 1.5x)
   if (topScore < meanScore * 1.5 && topScore < 3.0) return true;
 
   // Top two results too close → ambiguous, need Haiku to disambiguate
   if (results.length > 1) {
-    const gap = topScore - Math.abs(results[1].relevance);
+    const gap = topScore - scoreOf(results[1]);
     // Gap should be at least 10% of top score, or at least 0.5 absolute
     if (gap < Math.max(topScore * 0.1, 0.5)) return true;
   }
@@ -633,19 +636,19 @@ JSON: {"query":"search keywords for finding the right skill or agent","type":"sk
 // ─── Cooldown & Dedup (DB-persisted, survives process restarts) ─────────────
 
 export function isRecentlyRecommended(db, resourceId, sessionId) {
-  // Check 1: Per-session recommendation cap (avoid overwhelming user with suggestions)
+  // Check 1 & 2: Session-scoped checks (cap + dedup) — only when sessionId is available
   if (sessionId) {
     const sessionCount = db.prepare(
       'SELECT COUNT(*) as cnt FROM invocations WHERE session_id = ? AND recommended = 1'
     ).get(sessionId);
     if (sessionCount.cnt >= SESSION_RECOMMEND_CAP) return true;
-  }
 
-  // Check 2: Already recommended in this session (session dedup)
-  const sessionHit = db.prepare(
-    'SELECT 1 FROM invocations WHERE resource_id = ? AND session_id = ? LIMIT 1'
-  ).get(resourceId, sessionId);
-  if (sessionHit) return true;
+    // Already recommended in this session (session dedup)
+    const sessionHit = db.prepare(
+      'SELECT 1 FROM invocations WHERE resource_id = ? AND session_id = ? AND recommended = 1 LIMIT 1'
+    ).get(resourceId, sessionId);
+    if (sessionHit) return true;
+  }
 
   // Check 3: Recommended within cooldown window (cross-session cooldown)
   const cooldownHit = db.prepare(
@@ -702,7 +705,9 @@ function applyAdoptionDecay(results) {
 
     if (multiplier === 0) return null;
     if (multiplier < 1) {
-      return { ...r, relevance: r.relevance * multiplier, _decayed: true };
+      // Composite scores are negative (more negative = more relevant).
+      // To penalize: multiply by multiplier (<1) to make less negative (worse rank).
+      return { ...r, composite_score: (r.composite_score ?? r.relevance) * multiplier, _decayed: true };
     }
     return r;
   }).filter(Boolean);
@@ -791,12 +796,18 @@ export async function dispatchOnSessionStart(db, userPrompt, sessionId) {
       if (haikuResult?.query) {
         const haikuQuery = buildQueryFromText(haikuResult.query);
         if (haikuQuery) {
-          const haikuResults = retrieveResources(db, haikuQuery, {
+          let haikuResults = retrieveResources(db, haikuQuery, {
             type: haikuResult.type === 'either' ? undefined : haikuResult.type,
             limit: 3,
             projectDomains,
           });
-          if (haikuResults.length > 0) results = haikuResults;
+          if (haikuResults.length > 0) {
+            // Apply same post-processing as Tier2 to prevent zombie/low-confidence bypass
+            haikuResults = reRankByKeywords(haikuResults, signals.rawKeywords);
+            haikuResults = applyAdoptionDecay(haikuResults);
+            haikuResults = passesConfidenceGate(haikuResults, signals);
+            if (haikuResults.length > 0) results = haikuResults;
+          }
         }
       }
     }

package/hook-context.mjs

@@ -78,14 +78,13 @@ export function selectWithTokenBudget(db, project, budget = 2000) {
     LIMIT 10
   `).all(project, now_ms - windows.sessWindow);
 
-  const now = Date.now();
   const selectedObs = [];
   const selectedSess = [];
   let totalTokens = 0;
 
   // Score each candidate: value = recency * importance, cost = tokens
   const scoredObs = obsPool.map(o => {
-    const ageDays = (now - o.created_at_epoch) / 86400000;
+    const ageDays = (now_ms - o.created_at_epoch) / 86400000;
     const recency = 1 / (1 + ageDays);
     const impBoost = 0.5 + 0.5 * (o.importance || 1);
     const value = recency * impBoost;
@@ -94,7 +93,7 @@ export function selectWithTokenBudget(db, project, budget = 2000) {
   });
 
   const scoredSess = sessPool.map(s => {
-    const ageDays = (now - s.created_at_epoch) / 86400000;
+    const ageDays = (now_ms - s.created_at_epoch) / 86400000;
     const recency = 1 / (1 + ageDays);
     const value = recency * 1.5; // Session summaries slightly boosted
     const cost = estimateTokens((s.request || '') + (s.completed || '') + (s.next_steps || ''));
@@ -155,7 +154,7 @@ export function updateClaudeMd(contextBlock) {
   const startIdx = content.indexOf(startTag);
   const endIdx = content.indexOf(endTag);
 
-  if (startIdx !== -1 && endIdx !== -1) {
+  if (startIdx !== -1 && endIdx !== -1 && startIdx < endIdx) {
     // Replace existing section in-place — preserves surrounding content (including hint if present)
     content = content.slice(0, startIdx) + newSection + content.slice(endIdx + endTag.length);
   } else if (content.length > 0) {

package/hook-episode.mjs

@@ -210,13 +210,21 @@ export function mergePendingEntries(episode) {
 
 /**
  * Check if an episode has significant content worth processing with LLM.
- * Significant = contains file edits or Bash errors.
+ * Significant = contains file edits, Bash errors, or a review/research pattern
+ * (5+ Read/Grep entries indicate investigation worth recording).
  * @param {object} episode The episode to check
  * @returns {boolean} true if the episode has significant content
  */
 export function episodeHasSignificantContent(episode) {
-  return episode.entries.some(e =>
+  const hasEditsOrErrors = episode.entries.some(e =>
     EDIT_TOOLS.has(e.tool) ||
     (e.tool === 'Bash' && e.isError)
   );
+  if (hasEditsOrErrors) return true;
+
+  // Review/research pattern: reading many files indicates investigation
+  const readCount = episode.entries.filter(e =>
+    e.tool === 'Read' || e.tool === 'Grep'
+  ).length;
+  return readCount >= 5;
 }

package/hook-llm.mjs

@@ -183,6 +183,47 @@ export function buildDegradedTitle(episode) {
   return desc.replace(/ → (?:ERROR: )?\{.*$/, hasError ? ' (error)' : '');
 }
 
+/**
+ * Build a rule-based observation from episode metadata for immediate DB persistence.
+ * Used as pre-save (before LLM) and as fallback when LLM is unavailable.
+ * @param {object} episode Episode with entries, files, filesRead arrays
+ * @returns {object} Observation object ready for saveObservation()
+ */
+export function buildImmediateObservation(episode) {
+  const hasError = episode.entries.some(e => e.isError);
+  const hasEdit = episode.entries.some(e => EDIT_TOOLS.has(e.tool));
+  const readCount = episode.entries.filter(e => e.tool === 'Read' || e.tool === 'Grep').length;
+  const isReviewPattern = !hasEdit && !hasError && readCount >= 5;
+  const inferredType = hasError ? 'bugfix' : hasEdit ? 'change' : 'discovery';
+  const fileList = (episode.files || []).map(f => basename(f)).join(', ') || '(multiple)';
+
+  // Review/research episodes: use a descriptive title with file count
+  let title;
+  if (isReviewPattern) {
+    const allFiles = [...new Set([
+      ...(episode.files || []),
+      ...(episode.filesRead || []),
+    ])].map(f => basename(f));
+    const names = allFiles.slice(0, 4).join(', ');
+    const suffix = allFiles.length > 4 ? ` +${allFiles.length - 4} more` : '';
+    title = truncate(`Reviewed ${allFiles.length} files: ${names}${suffix}`, 120);
+  } else {
+    title = truncate(buildDegradedTitle(episode), 120);
+  }
+
+  return {
+    type: inferredType,
+    title,
+    subtitle: fileList,
+    narrative: episode.entries.map(e => e.desc).join('; '),
+    concepts: [],
+    facts: [],
+    files: episode.files,
+    filesRead: episode.filesRead || [],
+    importance: isReviewPattern ? Math.max(2, computeRuleImportance(episode)) : computeRuleImportance(episode),
+  };
+}
+
 // ─── Background: LLM Episode Extraction (Tier 2 F) ──────────────────────────
 
 export async function handleLLMEpisode() {
@@ -282,20 +323,7 @@ importance: 1=routine, 2=notable (error fix, arch decision, config change), 3=cr
       try { unlinkSync(tmpFile); } catch {}
       return;
     }
-    const hasError = episode.entries.some(e => e.isError);
-    const hasEdit = episode.entries.some(e => EDIT_TOOLS.has(e.tool));
-    const inferredType = hasError ? 'bugfix' : hasEdit ? 'change' : 'discovery';
-    obs = {
-      type: inferredType,
-      title: truncate(buildDegradedTitle(episode), 120),
-      subtitle: fileList,
-      narrative: episode.entries.map(e => e.desc).join('; '),
-      concepts: [],
-      facts: [],
-      files: episode.files,
-      filesRead: episode.filesRead || [],
-      importance: ruleImportance,
-    };
+    obs = buildImmediateObservation(episode);
   }
 
   const db = openDb();
@@ -371,16 +399,25 @@ export async function handleLLMSummary() {
     if (recentObs.length < 1) return;
 
     const obsList = recentObs.map((o, i) =>
-      `${i + 1}. [${o.type}] ${o.title}${o.narrative ? ': ' + truncate(o.narrative, 80) : ''}`
+      `${i + 1}. [${o.type}] ${o.title}${o.narrative ? ': ' + truncate(o.narrative, 200) : ''}`
     ).join('\n');
 
+    // Include user prompts for richer context
+    const userPrompts = db.prepare(`
+      SELECT prompt_text FROM user_prompts
+      WHERE content_session_id = ? ORDER BY prompt_number ASC LIMIT 10
+    `).all(sessionId).map(p => truncate(p.prompt_text, 300));
+    const promptCtx = userPrompts.length > 0
+      ? `\nUser requests: ${userPrompts.join(' → ')}\n`
+      : '';
+
     const prompt = `Summarize this coding session. Return ONLY valid JSON, no markdown fences.
 
-Project: ${project}
+Project: ${project}${promptCtx}
 Observations (${recentObs.length} total):
 ${obsList}
 
-JSON: {"request":"what the user was working on","investigated":"what was explored/analyzed","learned":"key findings","completed":"what was accomplished","next_steps":"suggested follow-up"}`;
+JSON: {"request":"what the user was working on","completed":"specific items accomplished with file names","remaining_items":"specific unfinished items from the original request — compare investigation scope with actual changes to infer what was NOT yet done; be precise with file:issue format, or empty string if all done","next_steps":"suggested follow-up"}`;
 
     if (!(await acquireLLMSlot())) {
       debugLog('WARN', 'llm-summary', 'semaphore timeout, skipping summary');
@@ -398,12 +435,13 @@ JSON: {"request":"what the user was working on","investigated":"what was explore
     if (llmParsed && llmParsed.request) {
       const now = new Date();
       db.prepare(`
-        INSERT INTO session_summaries (memory_session_id, project, request, investigated, learned, completed, next_steps, files_read, files_edited, notes, created_at, created_at_epoch)
-        VALUES (?, ?, ?, ?, ?, ?, ?, '[]', '[]', '', ?, ?)
+        INSERT INTO session_summaries (memory_session_id, project, request, investigated, learned, completed, next_steps, remaining_items, files_read, files_edited, notes, created_at, created_at_epoch)
+        VALUES (?, ?, ?, ?, ?, ?, ?, ?, '[]', '[]', '', ?, ?)
       `).run(
         sessionId, project,
         llmParsed.request || '', llmParsed.investigated || '', llmParsed.learned || '',
         llmParsed.completed || '', llmParsed.next_steps || '',
+        llmParsed.remaining_items || '',
         now.toISOString(), now.getTime()
       );
     }

package/hook-memory.mjs

@@ -28,7 +28,7 @@ export function searchRelevantMemories(db, userPrompt, project, excludeIds = [])
 
     const selectStmt = db.prepare(`
       SELECT o.id, o.type, o.title, o.importance,
-             bm25(observations_fts) as relevance
+             bm25(observations_fts, 10, 5, 5, 3, 3, 2) as relevance
       FROM observations_fts
       JOIN observations o ON o.id = observations_fts.rowid
       WHERE observations_fts MATCH ?
@@ -36,7 +36,7 @@ export function searchRelevantMemories(db, userPrompt, project, excludeIds = [])
         AND o.importance >= 2
         AND o.created_at_epoch > ?
         AND COALESCE(o.compressed_into, 0) = 0
-      ORDER BY bm25(observations_fts)
+      ORDER BY bm25(observations_fts, 10, 5, 5, 3, 3, 2)
       LIMIT 10
     `);
     const rows = selectStmt.all(ftsQuery, project, cutoff);

package/hook-shared.mjs

@@ -26,6 +26,12 @@ export const RELATED_OBS_WINDOW_MS = 7 * 86400000;       // 7 days
 export const FALLBACK_OBS_WINDOW_MS = 7 * 24 * 60 * 60 * 1000; // 7 days
 export const RESOURCE_RESCAN_INTERVAL_MS = 60 * 60 * 1000;    // 1 hour
 
+// Handoff system constants
+export const HANDOFF_EXPIRY_CLEAR = 3600000;                   // 1 hour
+export const HANDOFF_EXPIRY_EXIT = 7 * 24 * 60 * 60 * 1000;   // 7 days
+export const HANDOFF_MATCH_THRESHOLD = 3;                       // min weighted score
+export const CONTINUE_KEYWORDS = /继续|接着|上次|之前的|前面的|刚才|\bcontinue\b|\bresume\b|\bwhere[\s\-]+we[\s\-]+left\b|\bpick[\s\-]+up\b|\bcarry[\s\-]+on\b/i;
+
 // Ensure runtime directory exists
 try { if (!existsSync(RUNTIME_DIR)) mkdirSync(RUNTIME_DIR, { recursive: true }); } catch {}
 
@@ -121,9 +127,10 @@ export function spawnBackground(bgEvent, ...extraArgs) {
 
 export function sleep(ms) { return new Promise(r => setTimeout(r, ms)); }
 
-// ─── Injection Budget (per-session, in-memory) ──────────────────────────────
-// Limits total context injections across all hooks to prevent context bloat.
-// Reset at session-start. Each hook checks before injecting.
+// ─── Injection Budget (per hook invocation, in-memory) ───────────────────────
+// Limits context injections within a single hook process to prevent context bloat.
+// Note: each hook event runs in a separate process, so this is per-invocation,
+// not per-session. Session-level dedup is handled by cooldown/sessionId checks.
 
 export const MAX_INJECTIONS_PER_SESSION = 3;
 let _injectionCount = 0;

package/hook.mjs

@@ -10,7 +10,7 @@ import { readFileSync, writeFileSync, unlinkSync, readdirSync, renameSync, statS
 import {
   truncate, typeIcon, inferProject, detectBashSignificance,
   extractErrorKeywords, extractFilePaths, isRelatedToEpisode,
-  makeEntryDesc, scrubSecrets, computeRuleImportance, EDIT_TOOLS, debugCatch, debugLog, fmtTime,
+  makeEntryDesc, scrubSecrets, EDIT_TOOLS, debugCatch, debugLog, fmtTime,
 } from './utils.mjs';
 import {
   readEpisodeRaw, episodeFile,
@@ -29,8 +29,9 @@ import {
   closeRegistryDb, spawnBackground, appendToolEvent, readAndClearToolEvents,
   resetInjectionBudget, hasInjectionBudget, incrementInjection,
 } from './hook-shared.mjs';
-import { handleLLMEpisode, handleLLMSummary, saveObservation, buildDegradedTitle } from './hook-llm.mjs';
+import { handleLLMEpisode, handleLLMSummary, saveObservation, buildImmediateObservation } from './hook-llm.mjs';
 import { searchRelevantMemories } from './hook-memory.mjs';
+import { buildAndSaveHandoff, detectContinuationIntent, renderHandoffInjection } from './hook-handoff.mjs';
 
 // Prevent recursive hooks from background claude -p calls
 // Background workers (llm-episode, llm-summary, resource-scan) are exempt — they're ours
@@ -88,21 +89,7 @@ function flushEpisode(episode) {
   // LLM background worker will upgrade title/narrative/importance later.
   if (isSignificant) {
     try {
-      const hasError = episode.entries.some(e => e.isError);
-      const hasEdit = episode.entries.some(e => EDIT_TOOLS.has(e.tool));
-      const inferredType = hasError ? 'bugfix' : hasEdit ? 'change' : 'discovery';
-      const fileList = (episode.files || []).map(f => basename(f)).join(', ') || '(multiple)';
-      const obs = {
-        type: inferredType,
-        title: truncate(buildDegradedTitle(episode), 120),
-        subtitle: fileList,
-        narrative: episode.entries.map(e => e.desc).join('; '),
-        concepts: [],
-        facts: [],
-        files: episode.files,
-        filesRead: episode.filesRead || [],
-        importance: computeRuleImportance(episode),
-      };
+      const obs = buildImmediateObservation(episode);
       const id = saveObservation(obs, episode.project, episode.sessionId);
       if (id) episode.savedId = id;
     } catch (e) { debugCatch(e, 'flushEpisode-immediateSave'); }
@@ -159,7 +146,7 @@ async function handlePostToolUse() {
 
   // Skip noise
   if (SKIP_TOOLS.has(tool_name)) return;
-  if (tool_name.startsWith('mem_') || tool_name.startsWith('mcp__mem__')) return;
+  if (tool_name.startsWith('mem_') || tool_name.startsWith('mcp__mem__') || tool_name.startsWith('mcp__plugin_claude-mem-lite')) return;
   if (tool_name.startsWith('mcp__sequential') || tool_name.startsWith('mcp__plugin_context7')) return;
 
   const resp = typeof tool_response === 'string' ? tool_response : JSON.stringify(tool_response || '');
@@ -318,6 +305,9 @@ async function handleStop() {
   const sessionId = getSessionId();
   const project = inferProject();
 
+  // Snapshot episode BEFORE flush for handoff extraction
+  const episodeSnapshot = readEpisodeRaw();
+
   // Flush remaining episode buffer (locked to prevent race with handlePostToolUse)
   if (acquireLock(1000)) {
     try {
@@ -340,6 +330,13 @@ async function handleStop() {
         if (episode && episode.entries && episode.entries.length > 0 && episodeHasSignificantContent(episode)) {
           if (!episode.sessionId) episode.sessionId = sessionId;
           if (!episode.project) episode.project = project;
+          // Immediate save: persist rule-based observation to DB before spawning background worker.
+          // Without this, data is lost if the background worker fails.
+          try {
+            const obs = buildImmediateObservation(episode);
+            const id = saveObservation(obs, episode.project, episode.sessionId);
+            if (id) episode.savedId = id;
+          } catch (e) { debugCatch(e, 'handleStop-fallback-immediateSave'); }
           const flushFile = join(RUNTIME_DIR, `ep-flush-${Date.now()}-${randomUUID().slice(0, 8)}.json`);
           writeFileSync(flushFile, JSON.stringify(episode));
           spawnBackground('llm-episode', flushFile);
@@ -350,7 +347,7 @@ async function handleStop() {
     } catch (e) { debugCatch(e, 'handleStop-fallback'); }
   }
 
-  // Mark session completed (sync, instant)
+  // Mark session completed + save handoff (sync, instant)
   const db = openDb();
   if (db) {
     try {
@@ -358,6 +355,9 @@ async function handleStop() {
         UPDATE sdk_sessions SET status = 'completed', completed_at = ?, completed_at_epoch = ?
         WHERE content_session_id = ? AND status = 'active'
       `).run(new Date().toISOString(), Date.now(), sessionId);
+      // Save handoff snapshot for cross-session continuity
+      try { buildAndSaveHandoff(db, sessionId, project, 'exit', episodeSnapshot); }
+      catch (e) { debugCatch(e, 'handleStop-handoff'); }
     } finally {
       db.close();
     }
@@ -366,10 +366,11 @@ async function handleStop() {
   // Dispatch: collect feedback on recommendations using actual tool events
   // PostToolUse tracks Skill/Task/Edit/Write/Bash events in a JSONL file.
   // These events drive adoption detection (Skill/Task) and outcome detection (Edit/Bash errors).
+  // Always clear event file to prevent stale events accumulating if registry DB is unavailable.
   try {
+    const sessionEvents = readAndClearToolEvents();
     const rdb = getRegistryDb();
     if (rdb) {
-      const sessionEvents = readAndClearToolEvents();
       await collectFeedback(rdb, sessionId, sessionEvents);
     }
   } catch (e) { debugCatch(e, 'handleStop-feedback'); }
@@ -386,6 +387,9 @@ async function handleStop() {
 async function handleSessionStart() {
   resetInjectionBudget();
 
+  // Snapshot episode BEFORE flush for handoff extraction
+  const episodeSnapshot = readEpisodeRaw();
+
   // Flush any leftover episode buffer from previous session (e.g. after /clear)
   if (acquireLock()) {
     try {
@@ -464,6 +468,10 @@ async function handleSessionStart() {
     // ── Non-transactional operations (side effects, background work) ──
 
     if (prevSessionId) {
+      // Save handoff for cross-session continuity (/clear or /compact)
+      try { buildAndSaveHandoff(db, prevSessionId, prevProject || project, 'clear', episodeSnapshot); }
+      catch (e) { debugCatch(e, 'session-start-handoff'); }
+
       // Collect dispatch feedback for previous session
       try {
         const rdb = getRegistryDb();
@@ -774,6 +782,19 @@ async function handleUserPrompt() {
       now.toISOString(), now.getTime()
     );
 
+    // Cross-session handoff injection (first prompt only, before semantic memory)
+    if (counter?.prompt_counter === 1 && hasInjectionBudget()) {
+      try {
+        if (detectContinuationIntent(db, promptText, project)) {
+          const injection = renderHandoffInjection(db, project);
+          if (injection) {
+            process.stdout.write(injection + '\n');
+            incrementInjection();
+          }
+        }
+      } catch (e) { debugCatch(e, 'handleUserPrompt-handoff'); }
+    }
+
     // Semantic memory injection: search past observations for the user's prompt
     if (hasInjectionBudget()) {
       try {
@@ -857,6 +878,7 @@ async function handleResourceScan() {
     }
 
     // Upsert changed resources with fallback metadata (no Haiku)
+    let firstErr = true;
     for (const res of toIndex) {
       try {
         upsertResource(rdb, {
@@ -871,7 +893,7 @@ async function handleResourceScan() {
           trigger_patterns: `when user needs ${res.name.replace(/-/g, ' ').replace(/\//g, ' ')}`,
           capability_summary: `${res.type}: ${res.name.replace(/-/g, ' ')}`,
         });
-      } catch {}
+      } catch (e) { if (firstErr) { debugCatch(e, 'handleResourceScan-upsert'); firstErr = false; } }
     }
 
     // Disable resources no longer on filesystem

package/install.mjs

@@ -1213,7 +1213,7 @@ async function install() {
   const SOURCE_FILES = [
     'server.mjs', 'server-internals.mjs', 'tool-schemas.mjs',
     'hook.mjs', 'hook-shared.mjs', 'hook-llm.mjs', 'hook-memory.mjs',
-    'hook-semaphore.mjs', 'hook-episode.mjs', 'hook-context.mjs',
+    'hook-semaphore.mjs', 'hook-episode.mjs', 'hook-context.mjs', 'hook-handoff.mjs',
     'haiku-client.mjs', 'utils.mjs', 'schema.mjs', 'package.json', 'skill.md',
     'registry.mjs', 'registry-scanner.mjs', 'registry-indexer.mjs',
     'registry-retriever.mjs', 'resource-discovery.mjs',
@@ -1581,7 +1581,7 @@ async function install() {
 async function uninstall() {
   console.log('\nclaude-mem-lite uninstaller\n');
 
-  // 1. Remove MCP
+  // 1. Remove MCP (legacy hook-based install)
   try {
     execFileSync('claude', ['mcp', 'remove', '-s', 'user', 'mem'], { stdio: 'pipe' });
     ok('MCP server removed');
@@ -1589,7 +1589,7 @@ async function uninstall() {
     warn('MCP server not found or already removed');
   }
 
-  // 2. Remove hooks (match both npx and git-clone install paths)
+  // 2. Remove hooks from settings.json (match both npx and git-clone install paths)
   const settings = readSettings();
   if (settings.hooks) {
     for (const [event, configs] of Object.entries(settings.hooks)) {
@@ -1598,11 +1598,67 @@ async function uninstall() {
       if (settings.hooks[event].length === 0) delete settings.hooks[event];
     }
     if (Object.keys(settings.hooks).length === 0) delete settings.hooks;
-    writeSettings(settings);
-    ok('Hooks removed');
   }
 
-  // 3. Purge data if requested
+  // 3. Clean plugin system entries from settings.json
+  const pluginKey = 'claude-mem-lite@sdsrss';
+  const marketplaceKey = 'sdsrss';
+  if (settings.enabledPlugins) {
+    delete settings.enabledPlugins[pluginKey];
+  }
+  if (settings.extraKnownMarketplaces) {
+    delete settings.extraKnownMarketplaces[marketplaceKey];
+  }
+  writeSettings(settings);
+  ok('Hooks and plugin settings cleaned');
+
+  // 4. Clean plugin system registry files
+  const pluginsDir = join(homedir(), '.claude', 'plugins');
+
+  // 4a. Remove marketplace directory
+  const marketplaceDir = join(pluginsDir, 'marketplaces', marketplaceKey);
+  if (existsSync(marketplaceDir)) {
+    rmSync(marketplaceDir, { recursive: true, force: true });
+    ok('Marketplace directory removed');
+  }
+
+  // 4b. Remove cache directory
+  const cacheDir = join(pluginsDir, 'cache', marketplaceKey);
+  if (existsSync(cacheDir)) {
+    rmSync(cacheDir, { recursive: true, force: true });
+    ok('Plugin cache removed');
+  }
+
+  // 4c. Clean known_marketplaces.json
+  const knownPath = join(pluginsDir, 'known_marketplaces.json');
+  try {
+    const known = JSON.parse(readFileSync(knownPath, 'utf8'));
+    if (marketplaceKey in known) {
+      delete known[marketplaceKey];
+      writeFileSync(knownPath, JSON.stringify(known, null, 2) + '\n');
+      ok('Removed from known_marketplaces.json');
+    }
+  } catch { /* file may not exist */ }
+
+  // 4d. Clean installed_plugins.json
+  const installedPath = join(pluginsDir, 'installed_plugins.json');
+  try {
+    const installed = JSON.parse(readFileSync(installedPath, 'utf8'));
+    const plugins = installed.plugins || installed;
+    let cleaned = false;
+    for (const key of Object.keys(plugins)) {
+      if (key.includes('claude-mem-lite') || key.includes('sdsrss')) {
+        delete plugins[key];
+        cleaned = true;
+      }
+    }
+    if (cleaned) {
+      writeFileSync(installedPath, JSON.stringify(installed, null, 2) + '\n');
+      ok('Removed from installed_plugins.json');
+    }
+  } catch { /* file may not exist */ }
+
+  // 5. Purge data if requested
   if (flags.has('--purge')) {
     const expectedPurgePath = join(homedir(), '.claude-mem-lite');
     if (existsSync(DATA_DIR) && DATA_DIR === expectedPurgePath) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-mem-lite",
-  "version": "2.1.4",
+  "version": "2.2.0",
   "description": "Lightweight persistent memory system for Claude Code",
   "type": "module",
   "engines": {

package/registry-indexer.mjs

@@ -54,13 +54,13 @@ function fallbackExtract(resource) {
     infra: 'infrastructure,devops,cloud',
   };
 
-  let intentTags = '';
+  const intentTagSet = new Set();
   for (const [key, tags] of Object.entries(intentMap)) {
     if (name.includes(key) || content.includes(key)) {
-      intentTags = tags;
-      break;
+      for (const t of tags.split(',')) intentTagSet.add(t);
     }
   }
+  const intentTags = [...intentTagSet].join(',');
 
   // Infer domain tags from content
   const domainPatterns = [

package/registry-retriever.mjs

@@ -197,8 +197,9 @@ export function buildEnhancedQuery(signals) {
   // directly across name, intent_tags, capability_summary, trigger_patterns.
   if (signals.rawKeywords?.length > 0) {
     for (const kw of signals.rawKeywords) {
-      parts.push(`intent_tags:${kw}`);
-      parts.push(kw); // literal, no synonym expansion
+      const safeKw = expandToken(kw);
+      parts.push(`intent_tags:${safeKw}`);
+      parts.push(safeKw);
     }
   }
 
@@ -338,8 +339,9 @@ export function filterByProjectDomain(results, projectDomains) {
 // Sign convention: bm25() returns NEGATIVE (more negative = more relevant).
 // We keep the negative direction and SUBTRACT positive behavioral signals to make
 // better resources more negative. ORDER BY ... ASC puts most negative (best) first.
-const COMPOSITE_ORDER = `
-  ORDER BY (
+// Composite score expression (shared between SELECT and ORDER BY)
+// Sign convention: more negative = better. BM25 is negative, behavioral signals are subtracted.
+const COMPOSITE_EXPR = `(
     bm25(resources_fts, 5.0, 3.0, 3.0, 2.0, 2.0, 1.0, 1.0, 1.0) * 0.4
     - COALESCE(r.repo_stars * 1.0 / (r.repo_stars + 100.0), 0) * 0.15
     - (
@@ -369,29 +371,37 @@ const COMPOSITE_ORDER = `
            AND (r.adopt_count + 1.0) / (r.recommend_count + 2.0) < 0.1
         THEN 0.10
         ELSE 0 END
-  ) ASC
-`;
+  )`;
+
+// COMPOSITE_ORDER kept for SEARCH_BY_TYPE_SQL and other queries
+const COMPOSITE_ORDER = `ORDER BY ${COMPOSITE_EXPR} ASC`;
 
 const SEARCH_SQL = `
-  SELECT r.*,
-    bm25(resources_fts, 5.0, 3.0, 3.0, 2.0, 2.0, 1.0, 1.0, 1.0) AS relevance
-  FROM resources_fts
-  JOIN resources r ON r.id = resources_fts.rowid
-  WHERE resources_fts MATCH ?
-    AND r.status = 'active'
-  ${COMPOSITE_ORDER}
+  SELECT *, composite_score FROM (
+    SELECT r.*,
+      bm25(resources_fts, 5.0, 3.0, 3.0, 2.0, 2.0, 1.0, 1.0, 1.0) AS relevance,
+      ${COMPOSITE_EXPR} AS composite_score
+    FROM resources_fts
+    JOIN resources r ON r.id = resources_fts.rowid
+    WHERE resources_fts MATCH ?
+      AND r.status = 'active'
+  ) sub
+  ORDER BY composite_score ASC
   LIMIT ?
 `;
 
 const SEARCH_BY_TYPE_SQL = `
-  SELECT r.*,
-    bm25(resources_fts, 5.0, 3.0, 3.0, 2.0, 2.0, 1.0, 1.0, 1.0) AS relevance
-  FROM resources_fts
-  JOIN resources r ON r.id = resources_fts.rowid
-  WHERE resources_fts MATCH ?
-    AND r.status = 'active'
-    AND r.type = ?
-  ${COMPOSITE_ORDER}
+  SELECT *, composite_score FROM (
+    SELECT r.*,
+      bm25(resources_fts, 5.0, 3.0, 3.0, 2.0, 2.0, 1.0, 1.0, 1.0) AS relevance,
+      ${COMPOSITE_EXPR} AS composite_score
+    FROM resources_fts
+    JOIN resources r ON r.id = resources_fts.rowid
+    WHERE resources_fts MATCH ?
+      AND r.status = 'active'
+      AND r.type = ?
+  ) sub
+  ORDER BY composite_score ASC
   LIMIT ?
 `;
 

package/registry.mjs

@@ -4,7 +4,7 @@
 import Database from 'better-sqlite3';
 import { existsSync, mkdirSync } from 'fs';
 import { dirname } from 'path';
-// debugLog, debugCatch available from utils.mjs if needed
+import { debugCatch } from './utils.mjs';
 
 // ─── Schema ──────────────────────────────────────────────────────────────────
 
@@ -178,6 +178,9 @@ export function ensureRegistryDb(dbPath) {
     const schema = db.prepare(`SELECT sql FROM sqlite_master WHERE type='table' AND name='invocations'`).get();
     if (schema?.sql && !schema.sql.includes('user_prompt')) {
       db.transaction(() => {
+        // Clean up leftover from previous failed migration attempt
+        const hasOld = db.prepare(`SELECT 1 FROM sqlite_master WHERE type='table' AND name='invocations_old'`).get();
+        if (hasOld) db.exec(`DROP TABLE invocations_old`);
         db.exec(`ALTER TABLE invocations RENAME TO invocations_old`);
         db.exec(INVOCATIONS_SCHEMA);
         db.exec(`INSERT INTO invocations
@@ -187,7 +190,7 @@ export function ensureRegistryDb(dbPath) {
         db.exec(`DROP TABLE invocations_old`);
       })();
     }
-  } catch {}
+  } catch (e) { debugCatch(e, 'ensureRegistryDb-migration'); }
 
   db.exec(PREINSTALLED_SCHEMA);
 
@@ -223,7 +226,7 @@ const UPSERT_SQL = `
  */
 export function upsertResource(db, r) {
   return db.transaction(() => {
-    const result = db.prepare(UPSERT_SQL).run(
+    db.prepare(UPSERT_SQL).run(
       r.name, r.type, r.status || 'active', r.source || 'preinstalled',
       r.repo_url || null, r.repo_stars || 0, r.local_path,
       r.file_hash || null, r.invocation_name || '',
@@ -233,7 +236,6 @@ export function upsertResource(db, r) {
       r.keywords || '', r.tech_stack || '', r.use_cases || '', r.complexity || 'intermediate',
       r.indexed_at || null
     );
-    if (result.changes > 0 && result.lastInsertRowid) return Number(result.lastInsertRowid);
     const row = db.prepare('SELECT id FROM resources WHERE type = ? AND name = ?').get(r.type, r.name);
     return row?.id || 0;
   })();

package/schema.mjs

@@ -74,6 +74,20 @@ const CORE_SCHEMA = `
     created_at_epoch INTEGER NOT NULL,
     FOREIGN KEY(content_session_id) REFERENCES sdk_sessions(content_session_id) ON DELETE CASCADE ON UPDATE CASCADE
   );
+
+  CREATE TABLE IF NOT EXISTS session_handoffs (
+    project TEXT NOT NULL,
+    type TEXT NOT NULL,
+    session_id TEXT NOT NULL,
+    working_on TEXT,
+    completed TEXT,
+    unfinished TEXT,
+    key_files TEXT,
+    key_decisions TEXT,
+    match_keywords TEXT,
+    created_at_epoch INTEGER,
+    PRIMARY KEY (project, type)
+  );
 `;
 
 // Column migrations (idempotent — only swallow "duplicate column" errors)
@@ -83,6 +97,7 @@ const MIGRATIONS = [
   'ALTER TABLE observations ADD COLUMN minhash_sig TEXT',
   'ALTER TABLE observations ADD COLUMN access_count INTEGER DEFAULT 0',
   'ALTER TABLE observations ADD COLUMN compressed_into INTEGER DEFAULT NULL',
+  'ALTER TABLE session_summaries ADD COLUMN remaining_items TEXT',
 ];
 
 /**
@@ -139,7 +154,7 @@ export function initSchema(db) {
 
   // FTS5 full-text search tables + triggers (idempotent)
   ensureFTS(db, 'observations_fts', 'observations', ['title', 'subtitle', 'narrative', 'text', 'facts', 'concepts']);
-  ensureFTS(db, 'session_summaries_fts', 'session_summaries', ['request', 'investigated', 'learned', 'completed', 'next_steps', 'notes']);
+  ensureFTS(db, 'session_summaries_fts', 'session_summaries', ['request', 'investigated', 'learned', 'completed', 'next_steps', 'notes', 'remaining_items']);
   ensureFTS(db, 'user_prompts_fts', 'user_prompts', ['prompt_text']);
 
   return db;
@@ -182,7 +197,12 @@ export function ensureDb() {
   db.pragma('synchronous = NORMAL');
   db.pragma('foreign_keys = OFF'); // Enabled after dedup migration
 
-  return initSchema(db);
+  try {
+    return initSchema(db);
+  } catch (e) {
+    try { db.close(); } catch {}
+    throw e;
+  }
 }
 
 /**
@@ -197,10 +217,12 @@ export function ensureDb() {
  */
 export function rebuildFTS(db) {
   const FTS_TABLES = ['observations_fts', 'session_summaries_fts', 'user_prompts_fts'];
+  const idRe = /^[a-z][a-z0-9_]*$/;
   const rebuilt = [];
   const errors = [];
   for (const fts of FTS_TABLES) {
     try {
+      if (!idRe.test(fts)) { errors.push(`${fts}: invalid identifier`); continue; }
       const exists = db.prepare(`SELECT 1 FROM sqlite_master WHERE type='table' AND name=?`).get(fts);
       if (!exists) { errors.push(`${fts}: not found`); continue; }
       db.exec(`INSERT INTO ${fts}(${fts}) VALUES('rebuild')`);
@@ -219,10 +241,12 @@ export function rebuildFTS(db) {
  */
 export function checkFTSIntegrity(db) {
   const FTS_TABLES = ['observations_fts', 'session_summaries_fts', 'user_prompts_fts'];
+  const idRe = /^[a-z][a-z0-9_]*$/;
   const details = [];
   let healthy = true;
   for (const fts of FTS_TABLES) {
     try {
+      if (!idRe.test(fts)) { details.push(`${fts}: invalid identifier`); healthy = false; continue; }
       const exists = db.prepare(`SELECT 1 FROM sqlite_master WHERE type='table' AND name=?`).get(fts);
       if (!exists) { details.push(`${fts}: missing`); healthy = false; continue; }
       db.exec(`INSERT INTO ${fts}(${fts}) VALUES('integrity-check')`);
@@ -240,7 +264,7 @@ export function ensureFTS(db, ftsName, tableName, columns) {
   if (exists) return;
 
   // Validate identifiers to prevent SQL injection
-  const idRe = /^[a-z_]+$/;
+  const idRe = /^[a-z][a-z0-9_]*$/;
   if (!idRe.test(ftsName) || !idRe.test(tableName) || !columns.every(c => idRe.test(c))) {
     throw new Error(`Invalid identifier in ensureFTS: ${ftsName}, ${tableName}`);
   }

package/scripts/post-tool-use.sh

@@ -50,7 +50,7 @@ case "$tool" in
     exit 0
     ;;
   # Prefix filters
-  mem_*|mcp__mem__*|mcp__sequential*|mcp__plugin_context7*)
+  mem_*|mcp__mem__*|mcp__plugin_claude-mem-lite*|mcp__sequential*|mcp__plugin_context7*)
     exit 0
     ;;
 esac

package/server.mjs

@@ -61,7 +61,7 @@ const RECENCY_HALF_LIFE_MS = 1209600000; // 14 days in milliseconds
 // ─── MCP Server ─────────────────────────────────────────────────────────────
 
 const server = new McpServer(
-  { name: 'claude-mem-lite', version: '2.0.0' },
+  { name: 'claude-mem-lite', version: '2.1.6' },
   {
     instructions: [
       'Proactively search memory to leverage past experience. This is your long-term memory across sessions.',
@@ -939,6 +939,12 @@ server.registerTool(
         const narrative = obs.map(o => `- ${o.title || '(untitled)'}`).join('\n');
         const sessionId = obs[0].project ? `compress-${obs[0].project}` : 'compress-manual';
 
+        // Use median timestamp of compressed observations instead of now,
+        // so the summary appears at the correct position in timeline/recency scoring.
+        const sortedEpochs = obs.map(o => o.created_at_epoch).sort((a, b) => a - b);
+        const medianEpoch = sortedEpochs[Math.floor(sortedEpochs.length / 2)];
+        const medianDate = new Date(medianEpoch);
+
         // Ensure session exists (INSERT OR IGNORE avoids race condition)
         const now = new Date();
         db.prepare(`
@@ -948,7 +954,7 @@ server.registerTool(
 
         const summaryResult = insertSummary.run(
           sessionId, proj, narrative, dominantType, title, narrative,
-          now.toISOString(), now.getTime()
+          medianDate.toISOString(), medianEpoch
         );
         const summaryId = Number(summaryResult.lastInsertRowid);
 

package/utils.mjs

@@ -622,12 +622,11 @@ export function fmtTime(iso) {
  */
 export function isoWeekKey(epochMs) {
   const d = new Date(epochMs);
-  const tmp = new Date(d.getTime());
-  tmp.setHours(0, 0, 0, 0);
-  tmp.setDate(tmp.getDate() + 4 - (tmp.getDay() || 7));
-  const yearStart = new Date(tmp.getFullYear(), 0, 1);
+  const tmp = new Date(Date.UTC(d.getUTCFullYear(), d.getUTCMonth(), d.getUTCDate()));
+  tmp.setUTCDate(tmp.getUTCDate() + 4 - (tmp.getUTCDay() || 7));
+  const yearStart = new Date(Date.UTC(tmp.getUTCFullYear(), 0, 1));
   const weekNum = Math.ceil(((tmp - yearStart) / 86400000 + 1) / 7);
-  const isoYear = tmp.getFullYear();
+  const isoYear = tmp.getUTCFullYear();
   return `${isoYear}-W${String(weekNum).padStart(2, '0')}`;
 }
 
@@ -676,3 +675,63 @@ export function parseJsonFromLLM(text) {
   if (obj) try { return JSON.parse(obj[0]); } catch {}
   return null;
 }
+
+// ─── Handoff Utilities ──────────────────────────────────────────────────────
+
+/** Stop words for handoff keyword extraction (broader than ERROR_STOP_WORDS). */
+export const HANDOFF_STOP_WORDS = new Set([
+  'the', 'and', 'for', 'that', 'this', 'with', 'from', 'are', 'was', 'were',
+  'been', 'have', 'has', 'had', 'does', 'did', 'will', 'would', 'should', 'could',
+  'can', 'may', 'must', 'not', 'but', 'its', 'all', 'any', 'each', 'some',
+  'into', 'over', 'after', 'before', 'between', 'about', 'also', 'just', 'then',
+  'than', 'when', 'where', 'how', 'what', 'which', 'who', 'why', 'here', 'there',
+  'more', 'very', 'only', 'still', 'now', 'new', 'old', 'get', 'got', 'set',
+  'true', 'false', 'null', 'undefined', 'function', 'return', 'const', 'let', 'var',
+  'import', 'export', 'default', 'class', 'async', 'await', 'try', 'catch',
+]);
+
+/**
+ * Tokenize text for handoff keyword matching.
+ * Splits on whitespace/punctuation, lowercases, filters short tokens.
+ * @param {string} text Input text
+ * @returns {string[]} Array of lowercase tokens (length >= 3)
+ */
+export function tokenizeHandoff(text) {
+  if (!text) return [];
+  return text
+    .split(/[\s,;:.()[\]{}'"`<>→|/\\#@!?=+*&^%$~]+/)
+    .map(w => w.toLowerCase().replace(/^[.\-]+|[.\-]+$/g, ''))
+    .filter(w => w.length >= 3);
+}
+
+/**
+ * Check if a token is a "specific" term (file name, identifier, etc.)
+ * that should get double weight in intent matching.
+ * @param {string} token Lowercase token
+ * @returns {boolean}
+ */
+export function isSpecificTerm(token) {
+  if (!token || token.length < 3) return false;
+  if (token.includes('_') || token.includes('-')) return true;
+  if (HANDOFF_STOP_WORDS.has(token)) return false;
+  return token.length >= 4 && !/^\d+$/.test(token);
+}
+
+/**
+ * Extract match keywords from text and file paths for handoff intent matching.
+ * @param {string} text Combined text from prompts, observations, etc.
+ * @param {string[]} files Array of file paths
+ * @returns {string} Space-separated keywords
+ */
+export function extractMatchKeywords(text, files) {
+  const terms = new Set();
+  for (const f of files) {
+    const base = basename(f).replace(/\.[^.]+$/, '');
+    if (base.length >= 3) terms.add(base.toLowerCase());
+  }
+  const words = tokenizeHandoff(text);
+  for (const w of words) {
+    if (!HANDOFF_STOP_WORDS.has(w)) terms.add(w);
+  }
+  return [...terms].join(' ');
+}