claude-mem-lite 6.17.0 → 6.17.1

package/.claude-plugin/marketplace.json

@@ -9,7 +9,7 @@
   "plugins": [
     {
       "name": "claude-mem-lite",
-      "version": "6.17.0",
+      "version": "6.17.1",
       "source": "./",
       "homepage": "https://github.com/sdsrss/claude-mem-lite",
       "description": "Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. FTS5 BM25 keyword search with episode batching. Single SQLite DB, no external services. A lighter, lower-cost alternative to claude-mem (episode batching + a smaller model; cost savings are an internal estimate, not a measured benchmark)."

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-mem-lite",
-  "version": "6.17.0",
+  "version": "6.17.1",
   "description": "Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. FTS5 BM25 keyword search with episode batching. Single SQLite DB, no external services. A lighter, lower-cost alternative to claude-mem (episode batching + a smaller model; cost savings are an internal estimate, not a measured benchmark).",
   "author": {
     "name": "sdsrss"

package/README.md

@@ -244,7 +244,8 @@ everything is pinning `claude-mem-lite@6.16.0`.
 
 - **The pre-edit lesson line asks for a lesson's `#NN` only where it changed the edit.** It no
   longer asks for an applied / not-applicable verdict on every lesson in your next reply, which
-  put lesson-id lists into replies. Old directive: `CLAUDE_MEM_SALIENCE=verdict`. Adopted
+  put lesson-id lists into replies. Old directive: `CLAUDE_MEM_SALIENCE=verdict` (since 6.17.1
+  it also says it overrides the managed row and detail doc, which keep the new wording). Adopted
   projects get the matching CLAUDE.md managed row and detail doc on the next SessionStart;
   `CLAUDE_MEM_NO_TEMPLATE_REFRESH=1` keeps the old text.
 - **SessionStart's "Deferred Work" list ends with "+N more open"** when more than its 5 rows
@@ -1086,7 +1087,7 @@ and names can change between releases.
 | `CLAUDE_MEM_TASK_IMPERATIVE` | `on`/`1` injects the single most relevant lesson at prompt position under an imperative template. | _(off)_ |
 | `CLAUDE_MEM_SUBAGENT_INJECT` | Dispatch-time memory injection for subagents. | _(off)_ |
 | `CLAUDE_MEM_RECALL_FRAMING` | First line of a PreToolUse / PostToolUse recall block. `ab` gives each session one of two wordings, the older "system-injected context, continue your planned action" or a plain statement of source, so their cite-rates can be compared in one run (`benchmark/citation-live-replay.mjs --by-framing`); `legacy` / `factual` pin one. | `ab` |
-| `CLAUDE_MEM_SALIENCE` | Selects how the pre-edit lesson line asks for a response: unset = name a lesson's `#NN` only where it changed the edit; `verdict` = the pre-6.17 per-lesson `applied` / `n/a` verdict (the directive only: the adoption row in CLAUDE.md and the detail doc keep the new wording); `bind` / `bridge` = comprehension-bridge arms (`bridge` keeps the pre-6.17 verdict wording as its fallback); `legacy` = no directive. | _(unset)_ |
+| `CLAUDE_MEM_SALIENCE` | Selects how the pre-edit lesson line asks for a response: unset = name a lesson's `#NN` only where it changed the edit; `verdict` = the pre-6.17 per-lesson `applied` / `n/a` verdict (the adoption row in CLAUDE.md and the detail doc keep the new wording, and since 6.17.1 the directive says it overrides them); `bind` / `bridge` = comprehension-bridge arms (`bridge` keeps the pre-6.17 verdict wording as its fallback; neither says it overrides the adopted text, so their measured wording stays fixed); `legacy` = no directive. | _(unset)_ |
 | `CLAUDE_MEM_EDGE_DECAY` | Enables decay of file↔observation edges. | _(off)_ |
 | `CLAUDE_MEM_EDGE_DECAY_K` | Edge-decay threshold when the flag above is on (clamped to ≥1). | `3` |
 

package/README.zh-CN.md

@@ -206,8 +206,8 @@ rm -rf ~/claude-mem-lite/   # v0.5 前的非隐藏目录（如未自动迁移）
 
 - **编辑前的 lesson 提示只在某条 lesson 改变了这次改动时，才请模型提一次它的 `#NN`。** 不再要求在
   下一条回复里对每条 lesson 逐一表态“采纳 / 不适用”——那会让回复里出现成串的 lesson 编号。恢复旧提示：
-  `CLAUDE_MEM_SALIENCE=verdict`。已接入的项目会在下次 SessionStart 时把 CLAUDE.md 托管行和详细文档
-  换成对应的新写法；想保留旧文本设 `CLAUDE_MEM_NO_TEMPLATE_REFRESH=1`。
+  `CLAUDE_MEM_SALIENCE=verdict`（6.17.1 起它会注明自己优先于托管行和详细文档，那两处保持新写法）。
+  已接入的项目会在下次 SessionStart 时把 CLAUDE.md 托管行和详细文档换成对应的新写法；想保留旧文本设 `CLAUDE_MEM_NO_TEMPLATE_REFRESH=1`。
 - **SessionStart 的 "Deferred Work" 列表（5 行）在还有更多未完成事项时，末尾加一行 "+N more open"。**
   没有开关，回退请固定 6.16.0。
 

package/hook-context.mjs

@@ -710,6 +710,16 @@ export function buildSessionContextLines(
     // asserted in tests/hook-context.test.mjs rather than left as a claim, because "it
     // only adds" is exactly the kind of sentence this repo keeps finding to be false.
     const { fileLessonQuota, keyContextQuota } = sectionQuotas(fileLessons.length, keyContext.length);
+    // The collector records the line as the caller will SEE it: this function's return runs
+    // neutralizeContextDelimiters over the whole body, and idsShownWhole matches exact lines,
+    // so a row carrying a delimiter tag was shown yet never booked (D#115 P3-1). Matches the
+    // block-level pass for any tag closed on its own line. Two cases still differ, and leave a
+    // shown row unbooked as before this fix: an UNclosed tag whose attribute tail
+    // (CONTEXT_DELIMITER_RE's `[^>]*` does not stop at a newline) runs to a later row's `>` —
+    // the rows at the two ends of that span; and the block pass failing closed (32+ nested
+    // forged tags, defangToFixpoint strips every `<` / `>`) — any shown row holding `<` or
+    // `>`. 0 of 178 live importance>=2 rows carry a tag (2026-09-27).
+    const bookedLine = (e) => ({ id: e.id, text: neutralizeContextDelimiters(e.line) });
 
     if (fileLessons.length > 0 && !quiet) {
       const shown = fileLessons.slice(0, fileLessonQuota);
@@ -718,7 +728,7 @@ export function buildSessionContextLines(
       summaryLines.push('');
       if (collector) {
         collector.keyContextIds.push(...shown.map((e) => e.id));
-        collector.keyContextLines.push(...shown.map((e) => ({ id: e.id, text: e.line })));
+        collector.keyContextLines.push(...shown.map(bookedLine));
       }
     }
     if (keyContext.length > 0 && !quiet) {
@@ -728,7 +738,7 @@ export function buildSessionContextLines(
       summaryLines.push('');
       if (collector) {
         collector.keyContextIds.push(...shown.map((e) => e.id));
-        collector.keyContextLines.push(...shown.map((e) => ({ id: e.id, text: e.line })));
+        collector.keyContextLines.push(...shown.map(bookedLine));
       }
     }
   } else if (!latestSummary && !effectiveQuiet()) {
@@ -881,11 +891,16 @@ export function buildSessionContextLines(
     }
     // The list is capped at 5 and used to stop there silently, so 10 open items read as a
     // 5-item backlog. The total is the same statement's COUNT(*) OVER (), taken before LIMIT.
-    const hidden = Number(deferredItems[0].open_total) - deferredItems.length;
+    const openTotal = Number(deferredItems[0].open_total);
+    const hidden = openTotal - deferredItems.length;
     // Both listing surfaces page at 10, so the line names the knob rather than promising "all".
+    // Their maxima differ (mem_defer_list 50, `defer list` 100): past 50 only the CLI can list
+    // them, past 100 nothing lists them all (v6.17.1 pre-tag review).
     if (hidden > 0)
       deferredLines.push(
-        `+${hidden} more open — mem_defer_list / \`defer list\` with a larger limit lists them`,
+        openTotal <= 50
+          ? `+${hidden} more open — mem_defer_list / \`defer list\` with a larger limit lists them`
+          : `+${hidden} more open — \`defer list --limit 100\` lists ${openTotal <= 100 ? 'them' : 'the first 100'}`,
       );
     deferredLines.push('');
   }

package/hook-update.mjs

@@ -180,9 +180,9 @@ export function getCachedUpdateBanner() {
 // running when the check ran, and in plugin mode the update itself is applied by
 // Claude Code — downloadAndInstall never runs, so nothing clears the flag. Judge
 // the cache against the version running NOW: returns that version when the cached
-// latest is still ahead of it, else null. Both cached faces (the SessionStart
-// banner and the throttled checkForUpdate) ask this, so neither can nag alone.
-function pendingCachedUpdate(state) {
+// latest is still ahead of it, else null. Every cached face (the SessionStart
+// banner, the throttled checkForUpdate and install.mjs `doctor`) asks this, so none can nag alone.
+export function pendingCachedUpdate(state) {
   if (!state.updateAvailable || !state.latestVersion) return null;
   const running = getCurrentVersion();
   return compareVersions(state.latestVersion, running) > 0 ? running : null;

package/install.mjs

@@ -2369,7 +2369,19 @@ async function doctor() {
       if (state.lastCheck) parts.push(`last check: ${state.lastCheck}`);
       if (state.latestVersion) parts.push(`latest: v${state.latestVersion}`);
       if (state.lastUpdate) parts.push(`last update: ${state.lastUpdate}`);
-      if (state.updateAvailable) parts.push('update pending');
+      // Judged against the version running now, like the banner (#35): in plugin mode
+      // nothing clears the cached flag once Claude Code has applied the update. Dynamic, as
+      // elsewhere in doctor, so a hook-update that cannot load costs only this judgement.
+      if (state.updateAvailable) {
+        let pending = true;
+        try {
+          const { pendingCachedUpdate } = await import('./hook-update.mjs');
+          pending = pendingCachedUpdate(state) !== null;
+        } catch {
+          /* cannot judge — report the cached flag as it stands */
+        }
+        if (pending) parts.push('update pending');
+      }
       if (state.rateLimited) parts.push('rate-limited');
       if (state.lastError) parts.push(`last error: ${state.lastError}`);
       ok(`Update state: ${parts.join(', ') || 'empty'}`);

package/lib/deferred-work.mjs

@@ -92,14 +92,21 @@ export function listOpenWithOrdinal(db, project, limit = 10) {
  * (11 open, default page 10) reads as the whole list. Shared by both surfaces; `raise`
  * names the knob in each surface's own spelling. The total comes from the page's own
  * statement (`open_total`), so a concurrent `defer add` cannot make the two disagree.
+ * A page already at the surface's maximum gets no `raise` advice: the reader cannot act on
+ * it (D#115 P3-7), so the line says which rows are missing instead.
  * @param {Array<{open_total?: number}>} page rows from listOpenWithOrdinal
  * @param {string} raise e.g. `raise --limit (max 100)`
+ * @param {number} [max] the surface's largest page
  * @returns {string}
  */
-export function formatDeferMoreHint(page, raise) {
+export function formatDeferMoreHint(page, raise, max = Infinity) {
   const hidden = page.length > 0 ? Number(page[0].open_total) - page.length : 0;
   if (!(hidden > 0)) return '';
-  return `${hidden} more open item${hidden === 1 ? '' : 's'} not shown — ${raise}`;
+  const head = `${hidden} more open item${hidden === 1 ? '' : 's'} not shown`;
+  if (page.length >= max) {
+    return `${head} — this is already the largest page (${max}); the rest sort last (lowest priority, then newest)`;
+  }
+  return `${head} — ${raise}`;
 }
 
 // ─── G11: list age + stale refresh hint (roadmap 2026-07-18) ─────────────────

package/mem-cli.mjs

@@ -1464,7 +1464,7 @@ function cmdDeferList(db, args) {
   for (const r of list) {
     out(`  ${formatDeferListRow(r)}`);
   }
-  const moreHint = formatDeferMoreHint(list, 'raise --limit (max 100)');
+  const moreHint = formatDeferMoreHint(list, 'raise --limit (max 100)', 100);
   if (moreHint) out(`  ${moreHint}`);
   const staleHint = formatDeferStaleHint(countStaleOpen(db, project));
   if (staleHint) out(`  ${staleHint}`);

package/npm-shrinkwrap.json

@@ -1,12 +1,12 @@
 {
   "name": "claude-mem-lite",
-  "version": "6.17.0",
+  "version": "6.17.1",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "claude-mem-lite",
-      "version": "6.17.0",
+      "version": "6.17.1",
       "os": [
         "darwin",
         "linux",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-mem-lite",
-  "version": "6.17.0",
+  "version": "6.17.1",
   "description": "Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. FTS5 BM25 keyword search with episode batching. Single SQLite DB, no external services. A lighter, lower-cost alternative to claude-mem (episode batching + a smaller model; cost savings are an internal estimate, not a measured benchmark).",
   "type": "module",
   "packageManager": "npm@10.9.2",

package/scripts/pre-tool-recall.js

@@ -166,11 +166,20 @@ const ACK_DIRECTIVE =
 // CLAUDE_MEM_SALIENCE=bind; default stays ACK_DIRECTIVE.
 const BIND_DIRECTIVE =
   "For each lesson: state the one concrete check it forces on the line(s) you're editing, quote the edit line that satisfies it, then report '#NN: <check> — pass' or '#NN: n/a — <why this edit can't reach it>'.";
+// Under `verdict` the adopted CLAUDE.md row ("skip ones that did not apply") and the detail
+// doc ("`#NN n/a` … 所以不必写") still carry the v6.17 wording, so the agent would hold two
+// contradicting instructions; this says which wins (tasks/specs/verdict-precedence.md). Not
+// on `bind` or `bridge`, whose per-lesson asks carry the same contradiction: both are arms
+// benchmark/efficacy-harness.mjs measures, and their text must stay the one their readings
+// were taken with.
+const VERDICT_OPT_OUT_DIRECTIVE = `${VERDICT_DIRECTIVE} CLAUDE_MEM_SALIENCE=verdict is set: this overrides the memory guidance in CLAUDE.md and .claude/plugin_claude_mem_lite.md that a lesson which did not apply needs no mention.`;
 const ACTIVE_DIRECTIVE = SALIENCE_BIND
   ? BIND_DIRECTIVE
-  : process.env.CLAUDE_MEM_SALIENCE === 'verdict' || SALIENCE_BRIDGE
-    ? VERDICT_DIRECTIVE
-    : ACK_DIRECTIVE;
+  : process.env.CLAUDE_MEM_SALIENCE === 'verdict'
+    ? VERDICT_OPT_OUT_DIRECTIVE
+    : SALIENCE_BRIDGE
+      ? VERDICT_DIRECTIVE
+      : ACK_DIRECTIVE;
 const STALE_MS = 10 * 60 * 1000; // 10 minutes cleanup threshold for legacy file
 // Feature ① (file intelligence): on the first Read of a file each session, inject
 // its approximate token size + a one-line summary so the agent can decide to read

package/server.mjs

@@ -1252,7 +1252,7 @@ server.registerTool(
     for (const r of list) {
       lines.push(formatDeferListRow(r));
     }
-    const moreHint = formatDeferMoreHint(list, 'pass a larger limit (max 50)');
+    const moreHint = formatDeferMoreHint(list, 'pass a larger limit (max 50)', 50);
     if (moreHint) lines.push(moreHint);
     const staleHint = formatDeferStaleHint(countStaleOpen(db, project));
     if (staleHint) lines.push(staleHint);