nexusmem 0.3.2 → 0.3.3

package/CHANGELOG.md

@@ -9,6 +9,32 @@ built from, matched by publish timestamp: `v0.1.0` → `67a4776`, `v0.1.1` → `
 
 ## [Unreleased]
 
+## [0.3.3] — 2026-08-16
+
+### Added
+
+- **`nexusmem status` now shows failure→fix chain counts** — `N/M failure(s) resolved (X retry, Y
+  discussion)`, plus a hint to run `sync --link-failures` when failures remain unresolved. The
+  chain feature is this project's most distinctive capability, but was previously invisible to
+  anyone who didn't already know to query `node_links` directly. Backed by the new
+  `getChainStats` in `src/correlate/failure-fix.ts`, which dedupes failures resolved by both
+  heuristics rather than double-counting them.
+
+### Fixed
+
+- **Discussion-bridge heuristic (`sync --link-failures`): corpus-relative boilerplate tokens no
+  longer produce false-positive failure→fix links.** Re-dogfooded at larger scale against a second
+  real project's history: a command made entirely of words that saturate a project's own corpus
+  (e.g. this repo's own name/verbs) could AND-match an unrelated turn that just happened to mention
+  the same words, and bm25 score alone could not separate that from a true positive (measured: the
+  false positive scored *stronger* than two real true positives). `filterBoilerplateTokens` in
+  `src/correlate/failure-fix.ts` drops any token that appears in over 20% of a project's own
+  `conversation_turn`/`session_summary` history before building the match query — measured against
+  real data, not guessed — and skips the discussion-match attempt entirely (rather than falling back
+  unfiltered) when every token turns out to be boilerplate, since a missed link is preferred over a
+  false one for this heuristic. Below 10 discussable nodes the filter is skipped, since frequency
+  isn't a meaningful signal yet on a young project.
+
 ## [0.3.2] — 2026-08-16
 
 ### Added
@@ -250,7 +276,8 @@ First public release.
   there is no local-model summarization pass, and the conversation collector has never been audited
   for the stale-node bug that was found and fixed in the docs collector.
 
-[Unreleased]: https://github.com/yaminbkk/NexusMem/compare/v0.3.2...HEAD
+[Unreleased]: https://github.com/yaminbkk/NexusMem/compare/v0.3.3...HEAD
+[0.3.3]: https://github.com/yaminbkk/NexusMem/compare/v0.3.2...v0.3.3
 [0.3.2]: https://github.com/yaminbkk/NexusMem/compare/v0.3.1...v0.3.2
 [0.3.1]: https://github.com/yaminbkk/NexusMem/compare/v0.3.0...v0.3.1
 [0.3.0]: https://github.com/yaminbkk/NexusMem/compare/v0.2.0...v0.3.0

package/dist/cli/index.js

@@ -710,11 +710,6 @@ function toMatchQuery(input) {
   if (kept.length === 0) return null;
   return kept.map((t) => `"${t}"*`).join(" OR ");
 }
-function toStrictMatchQuery(input) {
-  const kept = significantTokens(input);
-  if (kept.length === 0) return null;
-  return kept.map((t) => `"${t}"*`).join(" AND ");
-}
 
 // src/store/schema.ts
 var V1 = `
@@ -1521,6 +1516,21 @@ var RESOLVED_BY_DISCUSSION = "resolved_by:discussion";
 function normalizeCommand(command) {
   return command.trim().replace(/\s+/g, " ").toLowerCase();
 }
+var MAX_TOKEN_DOC_FREQUENCY = 0.2;
+var MIN_CORPUS_FOR_FREQUENCY_FILTER = 10;
+function filterBoilerplateTokens(db, projectId, tokens) {
+  if (tokens.length === 0) return tokens;
+  const total = db.prepare(`SELECT COUNT(*) AS c FROM nodes WHERE project_id = ? AND kind IN ('conversation_turn', 'session_summary')`).get(projectId).c;
+  if (total < MIN_CORPUS_FOR_FREQUENCY_FILTER) return tokens;
+  const countMatching = db.prepare(
+    `SELECT COUNT(*) AS c FROM nodes_fts JOIN nodes n ON n.rowid = nodes_fts.rowid
+     WHERE nodes_fts MATCH ? AND n.project_id = ? AND n.kind IN ('conversation_turn', 'session_summary')`
+  );
+  return tokens.filter((t) => {
+    const matching = countMatching.get(`"${t}"*`, projectId).c;
+    return matching / total <= MAX_TOKEN_DOC_FREQUENCY;
+  });
+}
 function correlateFailures(store, projectId, opts = {}) {
   const retryWindowMs = opts.retryWindowMs ?? DEFAULT_RETRY_WINDOW_MS;
   const discussionWindowMs = opts.discussionWindowMs ?? DEFAULT_DISCUSSION_WINDOW_MS;
@@ -1565,7 +1575,8 @@ function correlateFailures(store, projectId, opts = {}) {
       store.linkNodes(failure.id, retry.id, RESOLVED_BY_RETRY);
       linkedByRetry += 1;
     }
-    const match = toStrictMatchQuery(failure.command);
+    const tokens = filterBoilerplateTokens(db, projectId, significantTokens(failure.command));
+    const match = tokens.length > 0 ? tokens.map((t) => `"${t}"*`).join(" AND ") : null;
     if (match) {
       const discussion = findDiscussion.get(match, projectId, failure.ts_epoch, failure.ts_epoch + discussionWindowMs);
       if (discussion) {
@@ -1576,6 +1587,25 @@ function correlateFailures(store, projectId, opts = {}) {
   }
   return { failuresExamined: failures.length, linkedByRetry, linkedByDiscussion };
 }
+function getChainStats(store, projectId) {
+  const db = store.raw;
+  const failuresTotal = db.prepare(
+    `SELECT COUNT(*) AS c FROM nodes
+         WHERE project_id = ? AND kind = 'shell_command'
+           AND json_extract(meta, '$.exitCode') IS NOT NULL AND json_extract(meta, '$.exitCode') != 0`
+  ).get(projectId).c;
+  const countDistinctLinked = (relations) => db.prepare(
+    `SELECT COUNT(DISTINCT nl.from_node_id) AS c
+           FROM node_links nl JOIN nodes n ON n.id = nl.from_node_id
+           WHERE n.project_id = ? AND nl.relation IN (${relations.map(() => "?").join(", ")})`
+  ).get(projectId, ...relations).c;
+  return {
+    failuresTotal,
+    resolvedByRetry: countDistinctLinked([RESOLVED_BY_RETRY]),
+    resolvedByDiscussion: countDistinctLinked([RESOLVED_BY_DISCUSSION]),
+    resolvedTotal: countDistinctLinked([RESOLVED_BY_RETRY, RESOLVED_BY_DISCUSSION])
+  };
+}
 
 // src/retrieval/fuse.ts
 var RRF_K = 60;
@@ -4293,6 +4323,7 @@ async function runStatus(opts) {
     const sources = store.listSyncState(projectId);
     const gitCursor = sources.find((s) => s.source === "git")?.cursor ?? null;
     const schema = currentSchemaVersion(store.raw);
+    const chains = getChainStats(store, projectId);
     const dbBytes = fileSize(ws.dbPath) + fileSize(`${ws.dbPath}-wal`);
     const kinds = Object.entries(stats.byKind).sort((a, b) => b[1] - a[1]).map(([kind, n]) => `    ${String(n).padStart(6)}  ${kind}`);
     process.stdout.write(
@@ -4314,7 +4345,8 @@ async function runStatus(opts) {
           return `    ${s.source.padEnd(14)} ${pc13.dim(`last run ${when}`)}  ${pc13.dim(`cursor ${cursorLabel}`)}`;
         }),
         gitCursor && gitCursor !== repo.head ? `${pc13.yellow("git behind HEAD")} \u2014 run ${pc13.bold("nexusmem sync")}` : "",
-        ""
+        "",
+        chains.failuresTotal ? `${pc13.dim("chains  ")} ${pc13.bold(String(chains.resolvedTotal))}/${chains.failuresTotal} failure(s) resolved ${pc13.dim(`(${chains.resolvedByRetry} retry, ${chains.resolvedByDiscussion} discussion)`)}${chains.resolvedTotal < chains.failuresTotal ? ` \u2014 run ${pc13.bold("nexusmem sync --link-failures")} to link more` : ""}` : ""
       ].filter((line) => line !== "").join("\n").concat("\n")
     );
     return 0;