homegraph 1.1.3 → 1.4.1

package/dist/index.js

@@ -49,6 +49,7 @@ const queries_1 = require("./db/queries");
 const directory_1 = require("./directory");
 const extraction_1 = require("./extraction");
 const context_1 = require("./extraction/context");
+const arkts_1 = require("./extraction/languages/arkts");
 const resolution_1 = require("./resolution");
 const graph_1 = require("./graph");
 const context_2 = require("./context");
@@ -57,6 +58,8 @@ const sync_1 = require("./sync");
 const extraction_version_1 = require("./extraction/extraction-version");
 const directory_2 = require("./directory");
 const query_utils_1 = require("./search/query-utils");
+const identifier_segments_1 = require("./search/identifier-segments");
+const cooperative_yield_1 = require("./resolution/cooperative-yield");
 const version_1 = require("./mcp/version");
 // Re-export types for consumers
 __exportStar(require("./types"), exports);
@@ -157,6 +160,10 @@ class HomeGraph {
         this.graphManager = new graph_1.GraphQueryManager(this.queries);
         this.traverser = new graph_1.GraphTraverser(this.queries);
         this.contextBuilder = (0, context_2.createContextBuilder)(this.projectRoot, this.queries, this.traverser);
+        (0, arkts_1.restoreOhosApiDbAttach)(this.queries);
+        if (!this.queries.getOhosApiDbPath()) {
+            (0, arkts_1.bindOhosApiDbForProject)(this.projectRoot, this.queries);
+        }
     }
     /**
      * Heal a stale database handle in place. If `.homegraph/` was removed and
@@ -271,6 +278,48 @@ class HomeGraph {
         }
         return instance;
     }
+    /**
+     * Rebuild the project's database from scratch and return a fresh, empty
+     * instance — the "same result as a fresh init" semantics that `codegraph
+     * index` documents.
+     *
+     * Unlike `open()` followed by `clear()`, this DISCARDS the existing
+     * `.codegraph/codegraph.db` (and its `-wal`/`-shm` sidecars) before
+     * re-initializing, instead of opening the old database and DELETE-ing every
+     * row. On a large or pre-fix poisoned index — e.g. an old graph that scanned
+     * an ignored gitlink corpus (#1065) into ~1.6M nodes with a multi-GB WAL —
+     * the per-row `nodes_fts` delete-trigger churn blocks the main thread long
+     * enough to trip the #850 liveness watchdog before indexing even starts, so a
+     * full re-index could never recover the bad state (#1067). Discarding the
+     * files is O(1) regardless of size, reclaims the disk, and sidesteps opening
+     * (and running migrations against) the poisoned database entirely.
+     */
+    static async recreate(projectRoot) {
+        await (0, extraction_1.initGrammars)();
+        const resolvedRoot = path.resolve(projectRoot);
+        // Check if initialized — recreate REBUILDS an existing project; it is not a
+        // first-time `init`.
+        if (!(0, directory_1.isInitialized)(resolvedRoot)) {
+            throw new Error(`HomeGraph not initialized in ${resolvedRoot}. Run init() first.`);
+        }
+        const dbPath = (0, db_1.getDatabasePath)(resolvedRoot);
+        try {
+            (0, db_1.removeDatabaseFiles)(dbPath);
+        }
+        catch (err) {
+            // POSIX unlinks an open file fine; this fires mainly on Windows when a
+            // live daemon/MCP server still holds the database. Turn the raw EBUSY into
+            // an actionable instruction instead of a generic failure.
+            const reason = err instanceof Error ? err.message : String(err);
+            throw new Error(`Could not rebuild the index — the database file is in use (${reason}). ` +
+                `Stop any running HomeGraph MCP server/daemon for this project and retry, ` +
+                `or remove the ${(0, directory_2.getHomeGraphDir)(resolvedRoot)} directory and run "homegraph init".`);
+        }
+        // Re-create an empty, freshly-schema'd database at the same path.
+        const db = db_1.DatabaseConnection.initialize(dbPath);
+        const queries = new queries_1.QueryBuilder(db.getDb());
+        return new HomeGraph(db, queries, resolvedRoot);
+    }
     /**
      * Open synchronously (without sync)
      */
@@ -330,6 +379,17 @@ class HomeGraph {
             }
             try {
                 const before = this.queries.getNodeAndEdgeCount();
+                // Mark the index as in-flight BEFORE any writes: a run killed mid-index
+                // leaves this marker behind so `homegraph status` can tell a truncated
+                // index from a completed one.
+                try {
+                    this.queries.setMetadata('index_state', 'indexing');
+                }
+                catch { /* metadata is advisory */ }
+                try {
+                    this.queries.clearNameSegmentVocab();
+                }
+                catch { /* vocab is advisory — never fail an index over it */ }
                 const result = await this.orchestrator.indexAll(options.onProgress, options.signal, options.verbose);
                 // Re-detect frameworks now that the index is populated. The resolver
                 // is constructed with createResolver() before any files exist, so
@@ -364,10 +424,10 @@ class HomeGraph {
                     // receiver conforms to (protocol-extension / inherited / default-
                     // interface). Needs the implements/extends edges the main pass just
                     // built, so it runs after resolution (#750).
-                    this.resolver.resolveChainedCallsViaConformance();
+                    await this.resolver.resolveChainedCallsViaConformance();
                     // Same lifecycle for `this.<member>` callback registrations whose
                     // member is inherited from a supertype (#808).
-                    this.resolver.resolveDeferredThisMemberRefs();
+                    await this.resolver.resolveDeferredThisMemberRefs();
                 }
                 // Refresh planner stats + checkpoint the WAL after bulk writes.
                 // Cheap and non-blocking; never load-bearing for correctness.
@@ -393,7 +453,43 @@ class HomeGraph {
                         this.queries.setMetadata('indexed_with_extraction_version', String(extraction_version_1.EXTRACTION_VERSION));
                     }
                     catch { /* metadata is advisory — never fail an index over it */ }
+                    const languages = Object.entries(this.getStats().filesByLanguage)
+                        .filter(([, count]) => count > 0)
+                        .map(([lang]) => lang);
+                    const ohosBinding = (0, arkts_1.bindOhosApiDbForProject)(this.projectRoot, this.queries, languages);
+                    if (ohosBinding && 'code' in ohosBinding) {
+                        result.errors.push({ message: ohosBinding.message, severity: 'warning', code: ohosBinding.code });
+                    }
                 }
+                // Reconcile the scan's ground truth against what the pipeline accounted for.
+                try {
+                    if (!result.success) {
+                        this.queries.setMetadata('index_state', 'failed');
+                    }
+                    else {
+                        const accounted = result.filesIndexed + result.filesSkipped + result.filesErrored;
+                        const discovered = result.filesDiscovered;
+                        const shortfall = discovered !== undefined ? discovered - accounted : 0;
+                        if (discovered !== undefined && shortfall > 0) {
+                            this.queries.setMetadata('index_state', 'partial');
+                            this.queries.setMetadata('index_files_discovered', String(discovered));
+                            this.queries.setMetadata('index_files_accounted', String(accounted));
+                            result.errors.push({
+                                message: `Index is missing ${shortfall} of ${discovered} discovered files (indexed ${result.filesIndexed}, skipped ${result.filesSkipped}, errored ${result.filesErrored}). The index is PARTIAL — re-run \`homegraph index\`.`,
+                                severity: 'warning',
+                                code: 'index_partial',
+                            });
+                        }
+                        else {
+                            this.queries.setMetadata('index_state', 'complete');
+                            if (discovered !== undefined) {
+                                this.queries.setMetadata('index_files_discovered', String(discovered));
+                                this.queries.setMetadata('index_files_accounted', String(accounted));
+                            }
+                        }
+                    }
+                }
+                catch { /* metadata is advisory — never fail an index over it */ }
                 return result;
             }
             finally {
@@ -436,6 +532,18 @@ class HomeGraph {
                 return { filesChecked: 0, filesAdded: 0, filesModified: 0, filesRemoved: 0, nodesUpdated: 0, durationMs: 0 };
             }
             try {
+                // Captured BEFORE the sync runs: the sync's own incremental writes
+                // populate vocab rows for the files it touches, so an end-of-sync
+                // emptiness check would see "non-empty" and skip the backfill forever,
+                // leaving every unchanged file's names unsegmented.
+                const vocabWasEmpty = (() => {
+                    try {
+                        return this.queries.isNameSegmentVocabEmpty();
+                    }
+                    catch {
+                        return false;
+                    }
+                })();
                 const result = await this.orchestrator.sync(options.onProgress);
                 // Cross-file finalization (e.g. NestJS RouterModule prefixes). Run on
                 // every sync that touched files so edits to `app.module.ts` propagate
@@ -444,11 +552,25 @@ class HomeGraph {
                 if (result.filesAdded > 0 || result.filesModified > 0) {
                     this.resolver.runPostExtract();
                 }
+                else if (result.filesRemoved > 0) {
+                    // A pure-removal sync still resolves refs below — the deletion path
+                    // resurrects the removed file's incoming edges as pending refs
+                    // (#1240 removal case) and the orphan sweep consumes them. In a
+                    // long-lived process (daemon) the resolver's name caches were
+                    // warmed against the pre-removal graph; drop them so resolution
+                    // sees the post-removal state. (runPostExtract above clears caches
+                    // itself, so the changed-files branch is already covered.)
+                    this.resolver.clearCaches();
+                }
                 // Resolve references if files were updated
-                if (result.filesAdded > 0 || result.filesModified > 0) {
+                const filesChanged = result.filesAdded > 0 || result.filesModified > 0;
+                if (filesChanged) {
                     if (result.changedFilePaths) {
                         // Scope resolution to changed files (git fast path — bounded set)
+                        const tRefLoad = Date.now();
                         const unresolvedRefs = this.queries.getUnresolvedReferencesByFiles(result.changedFilePaths);
+                        if (process.env.HOMEGRAPH_SYNTH_TIMINGS)
+                            console.error(`[phase-timing] sync-ref-load: ${Date.now() - tRefLoad}ms (${unresolvedRefs.length} refs)`);
                         options.onProgress?.({
                             phase: 'resolving',
                             current: 0,
@@ -461,6 +583,32 @@ class HomeGraph {
                                 total,
                             });
                         });
+                        // Retry previously-failed refs the changed files may now satisfy
+                        // (#1240). Scoped resolution above only re-resolves refs FROM the
+                        // changed files — but when a changed file gains an export/symbol,
+                        // refs in UNCHANGED files that failed against the old graph can
+                        // now resolve, and nothing else ever revisits them (their rows
+                        // were parked as status='failed' by an earlier completed pass).
+                        // Look them up by the symbol names the changed files now carry
+                        // and re-resolve just that set. On a sync where no failed ref
+                        // matches, this is one indexed lookup.
+                        const tRetry = Date.now();
+                        const retryable = this.queries.getRetryableFailedReferences(this.queries.getNodeNamesByFiles(result.changedFilePaths));
+                        if (retryable.length > 0) {
+                            options.onProgress?.({
+                                phase: 'resolving',
+                                current: 0,
+                                total: retryable.length,
+                            });
+                            await this.resolver.resolveAndPersistListYielding(retryable);
+                            options.onProgress?.({
+                                phase: 'resolving',
+                                current: retryable.length,
+                                total: retryable.length,
+                            });
+                        }
+                        if (process.env.HOMEGRAPH_SYNTH_TIMINGS)
+                            console.error(`[phase-timing] sync-failed-ref-retry: ${Date.now() - tRetry}ms (${retryable.length} refs)`);
                     }
                     else {
                         // No git info — use batched resolution to avoid OOM
@@ -476,20 +624,75 @@ class HomeGraph {
                                 current,
                                 total,
                             });
+                        }, (done, totalPasses) => {
+                            options.onProgress?.({
+                                phase: 'linking',
+                                current: done,
+                                total: totalPasses,
+                            });
                         });
                     }
+                }
+                // Orphan sweep (#1187). A resolution pass that dies mid-run — the #850
+                // daemon liveness watchdog's SIGKILL (#1122), Ctrl-C, a crash — leaves
+                // the refs it never reached in unresolved_refs, and the git-scoped fast
+                // path above never revisits them (it reads only the changed files'
+                // rows). Those files' call edges were then missing PERMANENTLY, with
+                // nothing to see except a too-small blast radius, until a full
+                // re-index. A completed pass takes every row it processed out of the
+                // PENDING set (resolved rows are deleted, unresolvable ones parked as
+                // status='failed' for the #1240 retry above), so any pending row now
+                // is such an orphan — or a row from an older engine's scoped pass.
+                // Grind them down with the batched resolver; this also makes a bare
+                // `homegraph sync` the recovery command for a wedged index. On a
+                // healthy index this is one COUNT query.
+                const orphanCount = this.queries.getUnresolvedReferencesCount();
+                if (orphanCount > 0) {
+                    options.onProgress?.({
+                        phase: 'resolving',
+                        current: 0,
+                        total: orphanCount,
+                    });
+                    await this.resolveReferencesBatched((current, total) => {
+                        options.onProgress?.({
+                            phase: 'resolving',
+                            current,
+                            total,
+                        });
+                    }, (done, totalPasses) => {
+                        options.onProgress?.({
+                            phase: 'linking',
+                            current: done,
+                            total: totalPasses,
+                        });
+                    });
+                }
+                if (filesChanged || orphanCount > 0) {
                     // Second pass: chained calls whose method lives on a supertype the
                     // receiver conforms to (protocol-extension / inherited). Needs the
                     // implements/extends edges built above (#750).
-                    this.resolver.resolveChainedCallsViaConformance();
+                    await this.resolver.resolveChainedCallsViaConformance();
                     // Same lifecycle for `this.<member>` callback registrations whose
                     // member is inherited from a supertype (#808).
-                    this.resolver.resolveDeferredThisMemberRefs();
+                    await this.resolver.resolveDeferredThisMemberRefs();
                 }
                 // Refresh planner stats + checkpoint the WAL after bulk writes.
-                if (result.filesAdded > 0 || result.filesModified > 0 || result.filesRemoved > 0) {
-                    this.db.runMaintenance();
+                // Off-thread — see indexAll's call site.
+                if (filesChanged || result.filesRemoved > 0 || orphanCount > 0) {
+                    await this.db.runMaintenance();
+                }
+                // Heal the segment vocabulary on indexes built before the table
+                // existed (upgrade path): incremental writes above only cover changed
+                // files, so a vocab that was empty when this sync STARTED means the
+                // bulk was never segmented — backfill it (INSERT OR IGNORE, so the
+                // rows the sync just wrote are fine). Batched + yielding — sync can
+                // run on the daemon's liveness-watchdog thread (#850/#1091).
+                try {
+                    if (vocabWasEmpty && this.queries.getNodeAndEdgeCount().nodes > 0) {
+                        await this.rebuildNameSegmentVocab();
+                    }
                 }
+                catch { /* vocab is advisory — never fail a sync over it */ }
                 return result;
             }
             finally {
@@ -600,6 +803,24 @@ class HomeGraph {
     getLastIndexedAt() {
         return this.queries.getLastIndexedAt();
     }
+    /**
+     * Access the underlying query layer. Used by the MCP query-cache layer.
+     */
+    getQueryBuilder() {
+        return this.queries;
+    }
+    /**
+     * Completeness of the last full index run. `'complete'` is the only good
+     * state. `'indexing'` after the fact means a run was killed mid-index;
+     * `'partial'` means the run finished but silently dropped files;
+     * `'failed'` means it reported failure. `null` = index predates this marker.
+     */
+    getIndexState() {
+        const raw = this.queries.getMetadata('index_state');
+        return raw === 'indexing' || raw === 'complete' || raw === 'partial' || raw === 'failed'
+            ? raw
+            : null;
+    }
     /**
      * Which engine built the current index: the package version + extraction
      * version stamped at the last full `indexAll`. Either field is null for an
@@ -612,6 +833,19 @@ class HomeGraph {
         const parsed = ev != null ? parseInt(ev, 10) : NaN;
         return { version, extractionVersion: Number.isFinite(parsed) ? parsed : null };
     }
+    /** Bound OHOS API db for this project, if any. */
+    getOhosApiBinding() {
+        const version = this.queries.getMetadata(arkts_1.OHOS_API_VERSION_META);
+        const dbPath = this.queries.getMetadata(arkts_1.OHOS_API_DB_PATH_META);
+        if (!version || !dbPath)
+            return null;
+        return {
+            version,
+            dbPath,
+            packageName: (0, arkts_1.ohosApiDbPackageName)(version),
+            installed: false,
+        };
+    }
     /**
      * True when the on-disk index was built by an engine whose extraction is
      * older than the one now running — i.e. a re-index would add data a migration
@@ -652,12 +886,22 @@ class HomeGraph {
      * Resolve references in batches to keep memory bounded on large codebases.
      * Processes chunks of unresolved refs, persisting results after each batch.
      */
-    async resolveReferencesBatched(onProgress) {
-        return this.resolver.resolveAndPersistBatched(onProgress);
+    async resolveReferencesBatched(onProgress, onSynthesisProgress) {
+        return this.resolver.resolveAndPersistBatched(onProgress, undefined, onSynthesisProgress);
     }
     /**
      * Get detected frameworks in the project
      */
+    /**
+     * References extracted but never attempted by a resolution pass. Zero on a
+     * healthy index — a completed pass consumes every pending row (resolving it
+     * or parking it as failed, #1240). Non-zero at rest means a pass was
+     * interrupted mid-run (#1187), so some files' call edges are missing; the
+     * next `sync` sweeps them.
+     */
+    getPendingReferenceCount() {
+        return this.queries.getUnresolvedReferencesCount();
+    }
     getDetectedFrameworks() {
         return this.resolver.getDetectedFrameworks();
     }
@@ -737,6 +981,178 @@ class HomeGraph {
      * bias, which would otherwise pull overloaded tokens toward whichever stack
      * embeds the project name.
      */
+    /**
+     * Graph-derived prompt matching for the front-load hook's MEDIUM tier:
+     * which indexed symbols do these prose words name? "state machine des
+     * commandes" → `OrderStateMachine`, in any human language whose technical
+     * nouns are Latin script — no keyword list involved.
+     *
+     * Precision comes from the repo's own naming statistics, not vocabulary:
+     * - CO-OCCURRENCE: ≥2 words that are segments of the SAME name ("state" +
+     *   "machine" → OrderStateMachine) is strong evidence and always qualifies.
+     * - RARITY: a single matched word qualifies only when its segment is
+     *   discriminative here (≤ {@link SEGMENT_RARITY_CEILING} distinct names) —
+     *   "checkout" in a shop backend yes, "state" in a react app no.
+     * Every candidate is re-verified against `nodes` before being returned
+     * (vocab rows are proposals; deletions leave orphans by design), so a
+     * returned symbol is guaranteed to exist right now.
+     */
+    getSegmentMatches(words, limit = 6) {
+        if (words.length === 0)
+            return [];
+        // Variant → original word (plural folding), for coverage accounting.
+        const variantToWord = new Map();
+        for (const word of words) {
+            for (const variant of (0, identifier_segments_1.segmentLookupVariants)(word)) {
+                if (!variantToWord.has(variant))
+                    variantToWord.set(variant, word);
+            }
+        }
+        const variants = [...variantToWord.keys()];
+        // Tier A: co-occurrence. The SQL folds variants back to their original
+        // word (#1146), so minWords=2 means two distinct PROMPT WORDS — a name
+        // matching both `service` and `services` can't tie with (or crowd past
+        // the LIMIT) a genuine two-word match. The JS re-check below recomputes
+        // the fold from live segments as the honesty layer.
+        const variantPairs = [...variantToWord.entries()].map(([segment, word]) => ({ segment, word }));
+        const candidates = [];
+        for (const hit of this.queries.getSegmentCoOccurrence(variantPairs, 2, 24)) {
+            const matched = this.wordsMatchingName(hit.name, variantToWord);
+            if (matched.size >= 2)
+                candidates.push({ name: hit.name, matchedWords: matched });
+        }
+        // Tier B: single rare word. Only when co-occurrence found nothing — a
+        // co-occurring name is categorically stronger evidence — and under
+        // stricter rules, because one word is thin: the word must be ≥5 chars
+        // (measured FPs: "this", "typo"); the segment must appear in AT LEAST TWO
+        // names (a concept the codebase is about clusters across names —
+        // CheckoutService/CheckoutController — while a prose coincidence is a
+        // singleton: measured FP "deploy to PRODUCTION" → the one name
+        // matchesNonProductionDir); and the candidate name must have ≥2 segments
+        // (a bare common verb matching a bare function name — "write" → `write` —
+        // is prose coincidence, not the user naming a symbol).
+        if (candidates.length === 0) {
+            const singleWordVariants = variants.filter((v) => variantToWord.get(v).length >= 5);
+            const counts = this.queries.getSegmentNameCounts(singleWordVariants);
+            const rare = [...counts.entries()]
+                .filter(([, n]) => n >= 2 && n <= HomeGraph.SEGMENT_RARITY_CEILING)
+                .sort((a, b) => a[1] - b[1])
+                .slice(0, 2);
+            for (const [variant] of rare) {
+                const word = variantToWord.get(variant);
+                for (const name of this.queries.getNamesForSegment(variant, 12)) {
+                    if ((0, identifier_segments_1.splitIdentifierSegments)(name).length < 2)
+                        continue;
+                    candidates.push({ name, matchedWords: new Set([word]) });
+                }
+            }
+        }
+        // Verify against nodes (the honesty gate) and pick a representative
+        // definition per name. A name whose only nodes are file/import kind has
+        // no real definition to point at — surfacing the import statement instead
+        // reads as a matched symbol but isn't one (#1144) — so it's skipped, the
+        // same way an orphaned vocab row is. (Import names no longer enter the
+        // vocab at write time, but rows written before that exclusion persist
+        // until the next full index.)
+        const out = [];
+        const seen = new Set();
+        candidates.sort((a, b) => b.matchedWords.size - a.matchedWords.size || a.name.length - b.name.length);
+        for (const candidate of candidates) {
+            if (out.length >= limit)
+                break;
+            if (seen.has(candidate.name))
+                continue;
+            seen.add(candidate.name);
+            const nodes = this.queries.getNodesByName(candidate.name);
+            if (nodes.length === 0)
+                continue; // orphaned vocab row — name no longer exists
+            const rep = nodes.find((n) => n.kind !== 'file' && n.kind !== 'import');
+            if (!rep)
+                continue; // no real definition — don't surface an import/file as one
+            out.push({
+                name: candidate.name,
+                kind: rep.kind,
+                filePath: rep.filePath,
+                startLine: rep.startLine ?? 0,
+                matchedWords: [...candidate.matchedWords].sort(),
+            });
+        }
+        return out;
+    }
+    /** A single word ("state") can match hundreds of names in a big repo — that
+     *  is noise, not signal. Ceiling for the single-word tier; co-occurrence is
+     *  exempt because two words on one name is already discriminative. */
+    static SEGMENT_RARITY_CEILING = 25;
+    /** Which of the prompt's original words match `name`'s segments (via
+     *  variants). Segments are recomputed in JS — a name-keyed vocab lookup
+     *  would scan the (segment, name) primary key. */
+    wordsMatchingName(name, variantToWord) {
+        const segments = new Set((0, identifier_segments_1.splitIdentifierSegments)(name));
+        const matched = new Set();
+        for (const [variant, word] of variantToWord) {
+            if (segments.has(variant))
+                matched.add(word);
+        }
+        return matched;
+    }
+    /**
+     * One-shot upgrade heal for callers that open the graph WITHOUT syncing —
+     * concretely the prompt hook, whose MEDIUM tier reads the segment
+     * vocabulary: a database migrated from before the vocab table existed
+     * starts with it empty, and the only other backfill lives inside `sync()`,
+     * which such callers never run (#1142). Returns true when the vocab is
+     * usable (already populated — the overwhelmingly common one-SELECT case —
+     * or healed here); false when it isn't (empty graph, or another process
+     * holds the index lock — that process's own sync heals it).
+     */
+    async healSegmentVocabIfEmpty() {
+        const empty = (() => {
+            try {
+                return this.queries.isNameSegmentVocabEmpty();
+            }
+            catch {
+                return false;
+            }
+        })();
+        if (!empty)
+            return true;
+        if (this.queries.getNodeAndEdgeCount().nodes === 0)
+            return false;
+        return this.indexMutex.withLock(async () => {
+            try {
+                this.fileLock.acquire();
+            }
+            catch {
+                return false; // an index/sync is running — it backfills the vocab itself
+            }
+            try {
+                if (!this.queries.isNameSegmentVocabEmpty())
+                    return true; // raced: healed meanwhile
+                await this.rebuildNameSegmentVocab();
+                return true;
+            }
+            finally {
+                this.fileLock.release();
+            }
+        });
+    }
+    /**
+     * Rebuild the segment vocabulary from the current graph, batched and
+     * yielding — the upgrade-heal path for indexes built before the vocab table
+     * existed. Runs inside the index mutex/lock (sync and
+     * healSegmentVocabIfEmpty hold them).
+     */
+    async rebuildNameSegmentVocab() {
+        const maybeYield = (0, cooperative_yield_1.createYielder)();
+        const BATCH = 2000;
+        for (let offset = 0;; offset += BATCH) {
+            const names = this.queries.getDistinctNodeNames(BATCH, offset);
+            if (names.length === 0)
+                break;
+            this.queries.insertNameSegmentsBatch(names);
+            await maybeYield();
+        }
+    }
     getProjectNameTokens() {
         return this.queries.getProjectNameTokens();
     }
@@ -1018,6 +1434,7 @@ class HomeGraph {
      */
     clear() {
         this.queries.clear();
+        (0, arkts_1.resetArkTSBatch)();
     }
     /**
      * Alias for close() for backwards compatibility.