claude-mem-lite 6.35.0 → 6.35.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -9,7 +9,7 @@
9
9
  "plugins": [
10
10
  {
11
11
  "name": "claude-mem-lite",
12
- "version": "6.35.0",
12
+ "version": "6.35.1",
13
13
  "source": "./",
14
14
  "homepage": "https://github.com/sdsrss/claude-mem-lite",
15
15
  "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)."
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "claude-mem-lite",
3
- "version": "6.35.0",
3
+ "version": "6.35.1",
4
4
  "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).",
5
5
  "author": {
6
6
  "name": "sdsrss"
package/hook.mjs CHANGED
@@ -164,19 +164,17 @@ import {
164
164
  } from './lib/maintain-core.mjs';
165
165
  import { snapshotDb } from './lib/db-backup.mjs';
166
166
  import {
167
- extractCitationsFromTranscript,
168
- extractInjectedBySurface,
169
- buildCitationRelevanceSet,
167
+ citationRelevanceSetFrom,
170
168
  unionSurfaces,
171
169
  extractInjectedFromKeyContext,
172
170
  bumpCitationAccess,
173
- computeCiteRecall,
171
+ citeRecallStats,
174
172
  applyCitationDecay,
175
173
  recordCitationFunnel,
176
174
  recordCitationSurfaces,
177
- collectSubagentSurface,
178
- hasMainThreadAssistantText,
175
+ subagentSurfaceFrom,
179
176
  } from './lib/citation-tracker.mjs';
177
+ import { digestTranscript, DIGEST_FILE_PREFIX } from './lib/transcript-digest.mjs';
180
178
  import { resolveEdgeAttribution, readPreRecallFileEdges } from './lib/edge-attribution.mjs';
181
179
  import { extractTailAssistantText, extractStructuredSummary } from './lib/summary-extractor.mjs';
182
180
  import { recordTurnReply, TURN_REPLIES_PREFIX } from './lib/turn-replies.mjs';
@@ -211,11 +209,10 @@ import {
211
209
  } from './hook-handoff.mjs';
212
210
  import {
213
211
  loadCiteBackForEpisode,
214
- extractCiteBackSignals,
215
212
  buildUnsavedBugfixHint,
216
213
  claimBugfixNudge,
217
214
  BUGFIX_NUDGE_MARKER_PREFIX,
218
- countUnsavedBugfixShape,
215
+ bugfixShapeStats,
219
216
  buildCiteRecallNudge as libBuildCiteRecallNudge,
220
217
  nextCiteStreakState,
221
218
  } from './lib/cite-back-hint.mjs';
@@ -1279,21 +1276,26 @@ async function readStopHookInput() {
1279
1276
  return { ccSessionId, transcriptPath, lastAssistantMessage };
1280
1277
  }
1281
1278
 
1279
+ /**
1280
+ * This turn's final reply: the host's `last_assistant_message` when it sends one, else the
1281
+ * transcript's last assistant text, read backwards from the end of the file. A forward parse of
1282
+ * the whole file took 1.6 s on a 475 MB transcript, on every turn (issue #53). Claude Code
1283
+ * 2.1.322 omits the field only when its last assistant message carries no text.
1284
+ */
1285
+ function stopFinalReply({ transcriptPath, lastAssistantMessage }) {
1286
+ if (lastAssistantMessage !== null) return lastAssistantMessage;
1287
+ return transcriptPath ? extractTailAssistantText(transcriptPath) : null;
1288
+ }
1289
+
1282
1290
  /**
1283
1291
  * D#825 — record this turn's final reply under this Stop's memory session and its current prompt
1284
- * number, for the summary worker (lib/turn-replies.mjs). The host's `last_assistant_message`
1285
- * when it sends one; from a host that does not, the transcript's last assistant text, the reply
1292
+ * number, for the summary worker (lib/turn-replies.mjs). The reply is stopFinalReply's, the one
1286
1293
  * the Stop baseline reads. A turn answering a task notice stores no prompt, so its reply lands
1287
1294
  * on the prompt before it and replaces that reply: a turn's last reply wins. Never throws.
1288
1295
  */
1289
1296
  function recordStopTurnReply(db, { sessionId, transcriptPath, lastAssistantMessage }) {
1290
1297
  try {
1291
- const reply =
1292
- lastAssistantMessage !== null
1293
- ? lastAssistantMessage
1294
- : transcriptPath
1295
- ? extractTailAssistantText(transcriptPath)
1296
- : null;
1298
+ const reply = stopFinalReply({ transcriptPath, lastAssistantMessage });
1297
1299
  if (!reply || !reply.trim()) return;
1298
1300
  const n =
1299
1301
  db
@@ -1423,7 +1425,7 @@ function markSessionCompletedAndSaveHandoff(
1423
1425
  }
1424
1426
 
1425
1427
  /** Fast summary baseline — ensures a summary exists even if the background LLM fails. */
1426
- function writeFastSummaryBaseline(db, { sessionId, project, transcriptPath }) {
1428
+ function writeFastSummaryBaseline(db, { sessionId, project, transcriptPath, lastAssistantMessage }) {
1427
1429
  // Stop fires once per assistant TURN and the mem session survives it (R10-P1-1), so this
1428
1430
  // runs on every turn of a session. The first turn with anything to say INSERTs the row
1429
1431
  // (T4-P2-B's guard: never a second row); every later turn REFRESHES that row from its tail's
@@ -1439,8 +1441,7 @@ function writeFastSummaryBaseline(db, { sessionId, project, transcriptPath }) {
1439
1441
  // CLAUDE.md §10 mandates Done/Not done/Failed/Uncertain markers, so the
1440
1442
  // tail is deterministically parseable without Haiku. Prior baseline left
1441
1443
  // remaining_items=='' for every session whose Haiku pass failed (≈66%
1442
- // in prod data), losing the user-visible "Not done" list. handleStop calls this
1443
- // AFTER trackCitationsAtStop so the parse is the one it left memoized.
1444
+ // in prod data), losing the user-visible "Not done" list.
1444
1445
  let structuredCompleted = '';
1445
1446
  let structuredNotDone = '';
1446
1447
  let structuredNotes = '';
@@ -1448,7 +1449,7 @@ function writeFastSummaryBaseline(db, { sessionId, project, transcriptPath }) {
1448
1449
  // (D#121, lib/fast-summary.mjs writeStopSummary).
1449
1450
  let tail = null;
1450
1451
  try {
1451
- tail = transcriptPath ? extractTailAssistantText(transcriptPath) : null;
1452
+ tail = stopFinalReply({ transcriptPath, lastAssistantMessage });
1452
1453
  if (tail) {
1453
1454
  const s = extractStructuredSummary(tail);
1454
1455
  structuredCompleted = s.done;
@@ -1488,23 +1489,26 @@ function trackCitationsAtStop(db, { sessionId, project, ccSessionId, transcriptP
1488
1489
  // applyCitationDecay checks separately.
1489
1490
  try {
1490
1491
  if (transcriptPath && !process.env.CLAUDE_MEM_NO_CITATION_TRACK) {
1492
+ // Issue #53: every question below is answered from the digest, which parses only the
1493
+ // bytes appended since the previous Stop (lib/transcript-digest.mjs). Each of them used
1494
+ // to parse the whole transcript: one shared parse per Stop within lib/transcript-scan.mjs's
1495
+ // heap budget (256 MB at most), one parse per question above it. Each answer is copied
1496
+ // where the code below used to get a fresh Set and may add to it.
1497
+ const digest = digestTranscript(transcriptPath, { runtimeDir: RUNTIME_DIR });
1498
+ if (!digest.complete) {
1499
+ // A transcript first seen larger than one Stop's read budget is caught up over several
1500
+ // Stops. Writing from part of it would bank verdicts the rest contradicts — an id cited
1501
+ // later in the unread part would be decided uncited — so this Stop writes nothing.
1502
+ debugLog('DEBUG', 'handleStop', 'citations: transcript digest still catching up; nothing written');
1503
+ return;
1504
+ }
1505
+ const d = digest.main;
1491
1506
  // D#152/D#177: the `subagent` face, collected ONCE, up front, and used twice —
1492
1507
  // by the decay block below (only under CLAUDE_MEM_SUBAGENT_DECAY) and by its own
1493
- // metering call at the tail. It used to be collected at the tail only, with a
1494
- // comment saying the position was load-bearing because lib/transcript-scan.mjs
1495
- // memoizes ONE file and reading the sidechains evicts the parent. That constraint
1496
- // is real but it is not "last" — it is "not BETWEEN two parent scans". Running it
1497
- // FIRST parses the sidechains before anything has memoized the parent, so the
1498
- // parent is then parsed once and stays memoized for every scanner after it:
1499
- // still one parent parse per Stop, the property the tail comment was protecting.
1500
- let sub = { injected: new Set(), cited: new Set(), files: 0 };
1501
- try {
1502
- sub = collectSubagentSurface(transcriptPath);
1503
- } catch (e) {
1504
- debugCatch(e, 'handleStop-subagent-collect');
1505
- }
1508
+ // metering call at the tail.
1509
+ const sub = subagentSurfaceFrom(digest.subagents);
1506
1510
 
1507
- const ids = extractCitationsFromTranscript(transcriptPath);
1511
+ const ids = new Set(d.cited);
1508
1512
  if (ids.size > 0) {
1509
1513
  // Gate the access-count channel on relevance (audit FLOW-2 / D#179). The cited
1510
1514
  // set is every `#NN` in this session's assistant text and cannot tell a
@@ -1512,8 +1516,9 @@ function trackCitationsAtStop(db, { sessionId, project, ccSessionId, transcriptP
1512
1516
  // session names dozens of ids in prose, and access_count > 3 promotes a row a
1513
1517
  // tier via boostAccessed. The population to credit — all seven faces, and why
1514
1518
  // extractAllInjected alone is the wrong five — lives in the builder.
1515
- const relevant = buildCitationRelevanceSet({
1516
- transcriptPath,
1519
+ const relevant = citationRelevanceSetFrom({
1520
+ attachmentInjected: unionSurfaces(d.injected),
1521
+ userTyped: d.userTyped,
1517
1522
  runtimeDir: RUNTIME_DIR,
1518
1523
  project,
1519
1524
  sessionId: ccSessionId,
@@ -1531,11 +1536,9 @@ function trackCitationsAtStop(db, { sessionId, project, ccSessionId, transcriptP
1531
1536
  );
1532
1537
  }
1533
1538
 
1534
- // v32 citation-decay: tighter feedback loop on top of P4. Re-scan
1535
- // transcript with main-thread filter, extract injected IDs from BOTH
1536
- // surfaces (PTR + UserPromptSubmit <memory-context>) via extractAllInjected,
1537
- // then mutate importance/streak per applyCitationDecay's contract.
1538
- // Cheap (file still in OS cache).
1539
+ // v32 citation-decay: tighter feedback loop on top of P4. The main-thread
1540
+ // injected ids from every attachment face (PTR + UserPromptSubmit
1541
+ // <memory-context> + …), then mutate the streaks per applyCitationDecay's contract.
1539
1542
  //
1540
1543
  // v34.x: pre-v34 this only saw pre-tool-recall injections, leaving the
1541
1544
  // UPS surface (highest-volume — all decision-type FTS hits) starved.
@@ -1552,13 +1555,13 @@ function trackCitationsAtStop(db, { sessionId, project, ccSessionId, transcriptP
1552
1555
  // survives to citation_surface_log below so "which face earns its
1553
1556
  // budget" becomes answerable. Before this, every face was merged
1554
1557
  // before anything was recorded and no lever had a target.
1555
- const injectedBySurface = extractInjectedBySurface(transcriptPath, { mainOnly: true });
1558
+ const injectedBySurface = d.injectedMain;
1556
1559
  const injected = unionSurfaces(injectedBySurface);
1557
1560
  // P5 ①: cite-back signals — observations whose warned file the agent
1558
1561
  // edited this session. Union into injected so they're resolved (they
1559
1562
  // were injected via pre-tool-recall) and, below, into cited so the
1560
1563
  // edit promotes them even without a literal #NN in text.
1561
- const citeBackIds = extractCiteBackSignals(transcriptPath);
1564
+ const citeBackIds = d.citeBack;
1562
1565
  for (const id of citeBackIds) injected.add(id);
1563
1566
  // D#124, promotion-only (v3.66.1): the SessionStart Key Context block
1564
1567
  // leaves no hook attachment, so its ids come from the per-session
@@ -1595,14 +1598,14 @@ function trackCitationsAtStop(db, { sessionId, project, ccSessionId, transcriptP
1595
1598
  // contract is "NEXT time you produce user-facing text," so a
1596
1599
  // session with zero main-thread text gets a free pass — the
1597
1600
  // next Stop in the same session will re-evaluate.
1598
- if (!hasMainThreadAssistantText(transcriptPath)) {
1601
+ if (!d.mainText.seen) {
1599
1602
  debugLog(
1600
1603
  'DEBUG',
1601
1604
  'handleStop',
1602
1605
  `citation-decay: skipped (no main-thread assistant text yet, injected=${injected.size})`,
1603
1606
  );
1604
1607
  } else {
1605
- const citedMain = extractCitationsFromTranscript(transcriptPath, { mainOnly: true });
1608
+ const citedMain = new Set(d.citedMain);
1606
1609
  for (const id of citeBackIds) citedMain.add(id);
1607
1610
  // D#177: admit the `subagent` face to the decay loop. It cannot ride the
1608
1611
  // normal path because its injection lands in a dispatched agent's PROMPT
@@ -1731,15 +1734,9 @@ function trackCitationsAtStop(db, { sessionId, project, ccSessionId, transcriptP
1731
1734
  }
1732
1735
 
1733
1736
  // Persist cite-recall ratio for the next SessionStart to surface as
1734
- // feedback. This block re-scans the transcript rather than threading the
1735
- // count through `extractCitationsFromTranscript`, so the bump path stays
1736
- // unchanged — and since P2-8 every scanner in it shares ONE parse via
1737
- // lib/transcript-scan.mjs, so "scan again" costs an array iteration, not a
1738
- // re-read. (The old wording, "cheap; the file is already in OS cache", was
1739
- // arguing the pre-memo case: the OS cache saved the read, never the parse,
1740
- // which was ~all of the cost.)
1737
+ // feedback.
1741
1738
  try {
1742
- const stats = computeCiteRecall(transcriptPath);
1739
+ const stats = citeRecallStats(d.citeRecall);
1743
1740
  // D#19: the RATIO GATE's own denominator, alongside the wide one. `stats` counts
1744
1741
  // every `#NN`-shaped token in non-assistant text — tool_result bodies, file
1745
1742
  // contents, CLI output, pasted reports — which is the right caliber for "what has
@@ -1747,24 +1744,19 @@ function trackCitationsAtStop(db, { sessionId, project, ccSessionId, transcriptP
1747
1744
  // (measured 11.2x inflation, R11-B-P2-2). Both are persisted; buildCiteRecallNudge
1748
1745
  // gates on this pair and falls back to the wide one for older payloads.
1749
1746
  //
1750
- // Cost is an array iteration, not a parse: this block runs after the decay loop's
1751
- // own extractInjectedBySurface on the same path, and lib/transcript-scan.mjs memoizes
1752
- // the parse. mainOnly mirrors the decay loop — an id injected only inside a subagent
1747
+ // mainOnly mirrors the decay loop — an id injected only inside a subagent
1753
1748
  // would otherwise enter the denominator while its citation lands in another
1754
1749
  // transcript, scoring a miss the main thread never had a chance to avoid.
1755
1750
  let gate = { gateInjected: null, gateRecalled: null, gateRatio: null };
1756
1751
  try {
1757
- const gateInjectedIds = unionSurfaces(extractInjectedBySurface(transcriptPath, { mainOnly: true }));
1752
+ const gateInjectedIds = unionSurfaces(d.injectedMain);
1758
1753
  // The nudge asks whether the agent ANSWERED what the hooks showed it, so a
1759
1754
  // `#NN n/a — <reason>` still counts. Since D#98 the default directive asks for no
1760
1755
  // reply on a lesson that did not apply, so that silence now reads as a miss here and
1761
1756
  // the gate fires more (projected 78/95 → up to 87/95 qualifying sessions,
1762
1757
  // docs/audits/20260927-d98-dismissal-baseline.md). Left as is: the gate already fired
1763
1758
  // on most sessions and self-silences after 3; D#111's readout re-measures it.
1764
- const gateCited = extractCitationsFromTranscript(transcriptPath, {
1765
- mainOnly: true,
1766
- includeDismissed: true,
1767
- });
1759
+ const gateCited = d.citedMainAnswered;
1768
1760
  let hit = 0;
1769
1761
  for (const id of gateInjectedIds) if (gateCited.has(id)) hit++;
1770
1762
  gate = {
@@ -1779,9 +1771,8 @@ function trackCitationsAtStop(db, { sessionId, project, ccSessionId, transcriptP
1779
1771
  }
1780
1772
  // B2 (v2.83.1): also persist the bugfix-shape nudge/save delta so
1781
1773
  // the next SessionStart can surface "N unsaved bugfix-shape edits"
1782
- // alongside cite-recall. Same scan target (transcript already in OS
1783
- // cache); same persistence file; one extra line in buildCiteRecallNudge.
1784
- const bugfixStats = countUnsavedBugfixShape(transcriptPath);
1774
+ // alongside cite-recall. Same persistence file; one extra line in buildCiteRecallNudge.
1775
+ const bugfixStats = bugfixShapeStats(d.bugfixShape);
1785
1776
  const dest = citeRecallPathFor(RUNTIME_DIR, project);
1786
1777
  // Carry the consecutive-low-cite streak forward so the SessionStart
1787
1778
  // nag can self-silence after the project has ignored it N times.
@@ -1812,11 +1803,11 @@ function trackCitationsAtStop(db, { sessionId, project, ccSessionId, transcriptP
1812
1803
  `,
1813
1804
  )
1814
1805
  .all(sessionId);
1815
- const d = detectUnpersistedDecision({
1806
+ const u = detectUnpersistedDecision({
1816
1807
  prompts: promptRows.map((r) => r.prompt_text),
1817
- transcriptPath,
1808
+ persistenceCount: d.persistence.count,
1818
1809
  });
1819
- if (d.fire) decisionSignal = d.signal;
1810
+ if (u.fire) decisionSignal = u.signal;
1820
1811
  } catch (e) {
1821
1812
  debugCatch(e, 'handleStop-persist-reminder');
1822
1813
  }
@@ -1853,25 +1844,14 @@ function trackCitationsAtStop(db, { sessionId, project, ccSessionId, transcriptP
1853
1844
  // promotion all keep the un-widened set. `CLAUDE_MEM_SUBAGENT_DECAY=0` returns
1854
1845
  // the face to metering-only.
1855
1846
  //
1856
- // The "placed LAST" note below is now historical: `collectSubagentSurface` runs
1857
- // at the HEAD of this block (the decay loop needs its result), and `sub` here is
1858
- // that same object rather than a second call. The parse-count property the note
1859
- // defends is unchanged — see the comment at the collection site.
1860
- // earlier, this block costs ONE extra parse of the parent — the memo
1861
- // re-caches on the first re-read, so it is one, not one per later
1862
- // scanner — and breaks the "one parse per Stop" property the block
1863
- // above documents. Measured by instrumenting the parse: 1 parent parse
1864
- // at this position, 2 when relocated earlier. ~25ms on the largest
1865
- // real transcript here (5.4MB), matching lib/transcript-scan.mjs's
1866
- // own header figure.
1847
+ // `sub` is the one collected at the head of this block (the decay loop needs it too).
1867
1848
  // The text floor is re-checked rather than inherited — same reason as
1868
1849
  // every other face: a tool-only Stop must not bank a verdict, and it
1869
1850
  // must not enter the funnel's session denominator either.
1870
1851
  try {
1871
- if (hasMainThreadAssistantText(transcriptPath)) {
1872
- // `sub` is the one collected at the top of this block — a second
1873
- // collectSubagentSurface call here would re-parse every sidechain file and,
1874
- // worse, could disagree with the set the decay loop above just scored.
1852
+ if (d.mainText.seen) {
1853
+ // `sub` is the one collected at the top of this block, so this records the set
1854
+ // the decay loop above just scored.
1875
1855
  if (sub.injected.size > 0) {
1876
1856
  recordCitationSurfaces(
1877
1857
  db,
@@ -1920,11 +1900,8 @@ async function handleStop() {
1920
1900
  if (db) {
1921
1901
  try {
1922
1902
  markSessionCompletedAndSaveHandoff(db, { sessionId, project, ccSessionId, episodeSnapshot, stopEpoch });
1923
- // Citations first: they read the subagent transcripts before the parent, so the parent is
1924
- // parsed once and stays memoized (D#152). The summary reads the parent's tail on every
1925
- // turn; run before them, it parsed the parent a second time in any session with subagents.
1926
1903
  trackCitationsAtStop(db, { sessionId, project, ccSessionId, transcriptPath });
1927
- writeFastSummaryBaseline(db, { sessionId, project, transcriptPath });
1904
+ writeFastSummaryBaseline(db, { sessionId, project, transcriptPath, lastAssistantMessage });
1928
1905
  } catch (e) {
1929
1906
  // Another process held the write lock past HOOK_DB_DEADLINE_MS: this turn's handoff,
1930
1907
  // citations and baseline are lost either way. The summary worker below does not run under
@@ -2017,7 +1994,8 @@ function gcStalePreRecallCooldowns() {
2017
1994
  name.startsWith('.claude-mem-keyctx-') || // D#123 Key Context marker — same per-session growth, same 24h GC
2018
1995
  name.startsWith(BUGFIX_NUDGE_MARKER_PREFIX) || // §9-B once-per-session nudge claim — same shape
2019
1996
  name.startsWith(RECALL_SHOWN_PREFIX) || // injection budget C1/C3 per-thread marker — same shape
2020
- name.startsWith(TURN_REPLIES_PREFIX); // D#825 per-session turn replies; its workers read it within minutes
1997
+ name.startsWith(TURN_REPLIES_PREFIX) || // D#825 per-session turn replies; its workers read it within minutes
1998
+ name.startsWith(DIGEST_FILE_PREFIX); // issue #53 per-transcript Stop digest; a later Stop re-reads from byte 0
2021
1999
  if (!isCooldown && !isInjectedMarker) continue;
2022
2000
  try {
2023
2001
  const p = join(RUNTIME_DIR, name);