sensemaking 0.23.1 → 0.24.1

package/dist/esm/store/shared.js.map

@@ -1 +1 @@
-{"version":3,"sources":["/Users/kevin/Dev/OpenSource/ai/sensemaking/src/store/shared.ts"],"sourcesContent":["import type { Connection } from './types.ts';\n\n// SQL and meta-table primitives both stores' open()/reconcile() need. Engine-neutral: both\n// stores' Connection satisfies the same async exec/prepare/runBatch shape (types.ts).\n\n// Rows that cannot conflict, at whatever speed this connection offers: the append path where the\n// store has one, else `conflictSql` bound the ordinary way. `conflictSql` stays the caller's own\n// guarded statement, so a store without appendRows behaves exactly as it did before.\nexport async function appendRows(conn: Connection, table: string, columns: string[], conflictSql: string, rows: unknown[][]): Promise<void> {\n  if (rows.length === 0) return;\n  if (conn.appendRows) await conn.appendRows(table, columns, rows);\n  else await conn.runBatch(conflictSql, rows);\n}\n\nexport function quoteIdent(name: string): string {\n  return `\"${name.split('\"').join('\"\"')}\"`;\n}\n\nexport async function getColumns(conn: Connection): Promise<Set<string>> {\n  const stmt = await conn.prepare('PRAGMA table_info(frontmatter)');\n  const rows = (await stmt.all()) as Array<{ name: string }>;\n  return new Set(rows.map((r) => r.name));\n}\n\nexport async function getMeta(conn: Connection, key: string): Promise<string | null> {\n  const stmt = await conn.prepare('SELECT value FROM meta WHERE key = ?');\n  const row = (await stmt.get(key)) as { value: string } | undefined;\n  return row ? row.value : null;\n}\n\nexport async function setMeta(conn: Connection, key: string, value: string | null): Promise<void> {\n  if (value === null) {\n    const stmt = await conn.prepare('DELETE FROM meta WHERE key = ?');\n    await stmt.run(key);\n    return;\n  }\n  const stmt = await conn.prepare('INSERT INTO meta (key, value) VALUES (?, ?) ON CONFLICT(key) DO UPDATE SET value = excluded.value');\n  await stmt.run(key, value);\n}\n\n// Reconcile's own write-transaction duration, for open()'s derived busy_timeout: keep the\n// observed max so a big watcher reconcile's lock hold is what the next open bounds its wait against.\nexport async function recordReconcileDuration(conn: Connection, ms: number): Promise<void> {\n  const prevRaw = await getMeta(conn, 'reconcile_max_ms');\n  // -1, not 0, so a genuinely 0ms first reconcile (sub-millisecond, common on a tiny tree)\n  // still gets recorded instead of losing to the \"nothing recorded yet\" default.\n  const prevMax = prevRaw === null ? -1 : Number(prevRaw);\n  if (ms > prevMax) await setMeta(conn, 'reconcile_max_ms', String(ms));\n}\n"],"names":["appendRows","conn","table","columns","conflictSql","rows","length","runBatch","quoteIdent","name","split","join","getColumns","stmt","prepare","all","Set","map","r","getMeta","key","row","get","value","setMeta","run","recordReconcileDuration","ms","prevRaw","prevMax","Number","String"],"mappings":"AAEA,2FAA2F;AAC3F,sFAAsF;AAEtF,iGAAiG;AACjG,iGAAiG;AACjG,qFAAqF;AACrF,OAAO,eAAeA,WAAWC,IAAgB,EAAEC,KAAa,EAAEC,OAAiB,EAAEC,WAAmB,EAAEC,IAAiB;IACzH,IAAIA,KAAKC,MAAM,KAAK,GAAG;IACvB,IAAIL,KAAKD,UAAU,EAAE,MAAMC,KAAKD,UAAU,CAACE,OAAOC,SAASE;SACtD,MAAMJ,KAAKM,QAAQ,CAACH,aAAaC;AACxC;AAEA,OAAO,SAASG,WAAWC,IAAY;IACrC,OAAO,CAAC,CAAC,EAAEA,KAAKC,KAAK,CAAC,KAAKC,IAAI,CAAC,MAAM,CAAC,CAAC;AAC1C;AAEA,OAAO,eAAeC,WAAWX,IAAgB;IAC/C,MAAMY,OAAO,MAAMZ,KAAKa,OAAO,CAAC;IAChC,MAAMT,OAAQ,MAAMQ,KAAKE,GAAG;IAC5B,OAAO,IAAIC,IAAIX,KAAKY,GAAG,CAAC,CAACC,IAAMA,EAAET,IAAI;AACvC;AAEA,OAAO,eAAeU,QAAQlB,IAAgB,EAAEmB,GAAW;IACzD,MAAMP,OAAO,MAAMZ,KAAKa,OAAO,CAAC;IAChC,MAAMO,MAAO,MAAMR,KAAKS,GAAG,CAACF;IAC5B,OAAOC,MAAMA,IAAIE,KAAK,GAAG;AAC3B;AAEA,OAAO,eAAeC,QAAQvB,IAAgB,EAAEmB,GAAW,EAAEG,KAAoB;IAC/E,IAAIA,UAAU,MAAM;QAClB,MAAMV,OAAO,MAAMZ,KAAKa,OAAO,CAAC;QAChC,MAAMD,KAAKY,GAAG,CAACL;QACf;IACF;IACA,MAAMP,OAAO,MAAMZ,KAAKa,OAAO,CAAC;IAChC,MAAMD,KAAKY,GAAG,CAACL,KAAKG;AACtB;AAEA,0FAA0F;AAC1F,qGAAqG;AACrG,OAAO,eAAeG,wBAAwBzB,IAAgB,EAAE0B,EAAU;IACxE,MAAMC,UAAU,MAAMT,QAAQlB,MAAM;IACpC,yFAAyF;IACzF,+EAA+E;IAC/E,MAAM4B,UAAUD,YAAY,OAAO,CAAC,IAAIE,OAAOF;IAC/C,IAAID,KAAKE,SAAS,MAAML,QAAQvB,MAAM,oBAAoB8B,OAAOJ;AACnE"}
+{"version":3,"sources":["/Users/kevin/Dev/OpenSource/ai/sensemaking/src/store/shared.ts"],"sourcesContent":["import type { Connection } from './types.ts';\n\n// SQL and meta-table primitives both stores' open()/reconcile() need. Engine-neutral: both\n// stores' Connection satisfies the same async exec/prepare/runBatch shape (types.ts).\n\n// Rows that cannot conflict, at whatever speed this connection offers: the append path where the\n// store has one, else the caller's own guarded `conflictSql` statement bound the ordinary way.\nexport async function appendRows(conn: Connection, table: string, columns: string[], conflictSql: string, rows: unknown[][]): Promise<void> {\n  if (rows.length === 0) return;\n  if (conn.appendRows) await conn.appendRows(table, columns, rows);\n  else await conn.runBatch(conflictSql, rows);\n}\n\nexport function quoteIdent(name: string): string {\n  return `\"${name.split('\"').join('\"\"')}\"`;\n}\n\nexport async function getColumns(conn: Connection): Promise<Set<string>> {\n  const stmt = await conn.prepare('PRAGMA table_info(frontmatter)');\n  const rows = (await stmt.all()) as Array<{ name: string }>;\n  return new Set(rows.map((r) => r.name));\n}\n\nexport async function getMeta(conn: Connection, key: string): Promise<string | null> {\n  const stmt = await conn.prepare('SELECT value FROM meta WHERE key = ?');\n  const row = (await stmt.get(key)) as { value: string } | undefined;\n  return row ? row.value : null;\n}\n\nexport async function setMeta(conn: Connection, key: string, value: string | null): Promise<void> {\n  if (value === null) {\n    const stmt = await conn.prepare('DELETE FROM meta WHERE key = ?');\n    await stmt.run(key);\n    return;\n  }\n  const stmt = await conn.prepare('INSERT INTO meta (key, value) VALUES (?, ?) ON CONFLICT(key) DO UPDATE SET value = excluded.value');\n  await stmt.run(key, value);\n}\n\n// Reconcile's own write-transaction duration, for open()'s derived busy_timeout: keep the\n// observed max so a big watcher reconcile's lock hold is what the next open bounds its wait against.\nexport async function recordReconcileDuration(conn: Connection, ms: number): Promise<void> {\n  const prevRaw = await getMeta(conn, 'reconcile_max_ms');\n  // -1, not 0, so a genuinely 0ms first reconcile (sub-millisecond, common on a tiny tree)\n  // still gets recorded instead of losing to the \"nothing recorded yet\" default.\n  const prevMax = prevRaw === null ? -1 : Number(prevRaw);\n  if (ms > prevMax) await setMeta(conn, 'reconcile_max_ms', String(ms));\n}\n"],"names":["appendRows","conn","table","columns","conflictSql","rows","length","runBatch","quoteIdent","name","split","join","getColumns","stmt","prepare","all","Set","map","r","getMeta","key","row","get","value","setMeta","run","recordReconcileDuration","ms","prevRaw","prevMax","Number","String"],"mappings":"AAEA,2FAA2F;AAC3F,sFAAsF;AAEtF,iGAAiG;AACjG,+FAA+F;AAC/F,OAAO,eAAeA,WAAWC,IAAgB,EAAEC,KAAa,EAAEC,OAAiB,EAAEC,WAAmB,EAAEC,IAAiB;IACzH,IAAIA,KAAKC,MAAM,KAAK,GAAG;IACvB,IAAIL,KAAKD,UAAU,EAAE,MAAMC,KAAKD,UAAU,CAACE,OAAOC,SAASE;SACtD,MAAMJ,KAAKM,QAAQ,CAACH,aAAaC;AACxC;AAEA,OAAO,SAASG,WAAWC,IAAY;IACrC,OAAO,CAAC,CAAC,EAAEA,KAAKC,KAAK,CAAC,KAAKC,IAAI,CAAC,MAAM,CAAC,CAAC;AAC1C;AAEA,OAAO,eAAeC,WAAWX,IAAgB;IAC/C,MAAMY,OAAO,MAAMZ,KAAKa,OAAO,CAAC;IAChC,MAAMT,OAAQ,MAAMQ,KAAKE,GAAG;IAC5B,OAAO,IAAIC,IAAIX,KAAKY,GAAG,CAAC,CAACC,IAAMA,EAAET,IAAI;AACvC;AAEA,OAAO,eAAeU,QAAQlB,IAAgB,EAAEmB,GAAW;IACzD,MAAMP,OAAO,MAAMZ,KAAKa,OAAO,CAAC;IAChC,MAAMO,MAAO,MAAMR,KAAKS,GAAG,CAACF;IAC5B,OAAOC,MAAMA,IAAIE,KAAK,GAAG;AAC3B;AAEA,OAAO,eAAeC,QAAQvB,IAAgB,EAAEmB,GAAW,EAAEG,KAAoB;IAC/E,IAAIA,UAAU,MAAM;QAClB,MAAMV,OAAO,MAAMZ,KAAKa,OAAO,CAAC;QAChC,MAAMD,KAAKY,GAAG,CAACL;QACf;IACF;IACA,MAAMP,OAAO,MAAMZ,KAAKa,OAAO,CAAC;IAChC,MAAMD,KAAKY,GAAG,CAACL,KAAKG;AACtB;AAEA,0FAA0F;AAC1F,qGAAqG;AACrG,OAAO,eAAeG,wBAAwBzB,IAAgB,EAAE0B,EAAU;IACxE,MAAMC,UAAU,MAAMT,QAAQlB,MAAM;IACpC,yFAAyF;IACzF,+EAA+E;IAC/E,MAAM4B,UAAUD,YAAY,OAAO,CAAC,IAAIE,OAAOF;IAC/C,IAAID,KAAKE,SAAS,MAAML,QAAQvB,MAAM,oBAAoB8B,OAAOJ;AACnE"}

package/dist/esm/store/sqlite/lexical.js

@@ -1,9 +1,6 @@
 import { segmentMatch } from '../../text/segment.js';
-// snippet() re-tokenizes each candidate doc, superlinearly: ~10s for one 1MB doc
-// (benchmark/reports/2026-08-23-0.13.2-hub-release-battery.md); past this bound, hit stays NULL for the caller's JS excerpt fallback.
-const SNIPPET_BOUND = 16384;
 const WEIGHTED_BM25 = 'bm25(content, 10.0, 5.0, 1.0, 0, 10.0, 5.0, 1.0)';
-// Ranked BM25 word-match query with excerpt, scoped by the caller-built SQL fragments. An
+// Ranked BM25 word-match query, scoped by the caller-built SQL fragments. An
 // unspaced-script run in `terms` becomes a quoted grapheme phrase against the `_seg` sidecars.
 export async function queryLexical(conn, terms, opts) {
     const { whereJoin, whereCond, scopeCond, limit } = opts;
@@ -11,7 +8,7 @@ export async function queryLexical(conn, terms, opts) {
     // A run of pure unspaced-script punctuation segments to nothing searchable: an empty MATCH
     // string is an FTS5 syntax error, not zero rows, so return zero rows directly rather than issuing it.
     if (query.trim() === '') return [];
-    const sql = `SELECT content.path AS path, CASE WHEN length(content.text) <= ${SNIPPET_BOUND} THEN snippet(content, 2, '«', '»', '…', 10) ELSE NULL END AS hit FROM content ${whereJoin} WHERE content MATCH ? ${whereCond} ${scopeCond} ORDER BY ${WEIGHTED_BM25} LIMIT ${limit}`;
+    const sql = `SELECT content.path AS path FROM content ${whereJoin} WHERE content MATCH ? ${whereCond} ${scopeCond} ORDER BY ${WEIGHTED_BM25} LIMIT ${limit}`;
     const stmt = await conn.prepare(sql);
     return await stmt.all(query);
 }

package/dist/esm/store/sqlite/lexical.js.map

@@ -1 +1 @@
-{"version":3,"sources":["/Users/kevin/Dev/OpenSource/ai/sensemaking/src/store/sqlite/lexical.ts"],"sourcesContent":["import { segmentMatch } from '../../text/segment.ts';\nimport type { Connection, LexicalHit, LexicalQueryOptions } from '../types.ts';\n\n// snippet() re-tokenizes each candidate doc, superlinearly: ~10s for one 1MB doc\n// (benchmark/reports/2026-08-23-0.13.2-hub-release-battery.md); past this bound, hit stays NULL for the caller's JS excerpt fallback.\nconst SNIPPET_BOUND = 16_384;\nconst WEIGHTED_BM25 = 'bm25(content, 10.0, 5.0, 1.0, 0, 10.0, 5.0, 1.0)';\n\n// Ranked BM25 word-match query with excerpt, scoped by the caller-built SQL fragments. An\n// unspaced-script run in `terms` becomes a quoted grapheme phrase against the `_seg` sidecars.\nexport async function queryLexical(conn: Connection, terms: string, opts: LexicalQueryOptions): Promise<LexicalHit[]> {\n  const { whereJoin, whereCond, scopeCond, limit } = opts;\n  const query = segmentMatch(terms);\n  // A run of pure unspaced-script punctuation segments to nothing searchable: an empty MATCH\n  // string is an FTS5 syntax error, not zero rows, so return zero rows directly rather than issuing it.\n  if (query.trim() === '') return [];\n  const sql = `SELECT content.path AS path, CASE WHEN length(content.text) <= ${SNIPPET_BOUND} THEN snippet(content, 2, '«', '»', '…', 10) ELSE NULL END AS hit FROM content ${whereJoin} WHERE content MATCH ? ${whereCond} ${scopeCond} ORDER BY ${WEIGHTED_BM25} LIMIT ${limit}`;\n  const stmt = await conn.prepare(sql);\n  return (await stmt.all(query)) as unknown as LexicalHit[];\n}\n"],"names":["segmentMatch","SNIPPET_BOUND","WEIGHTED_BM25","queryLexical","conn","terms","opts","whereJoin","whereCond","scopeCond","limit","query","trim","sql","stmt","prepare","all"],"mappings":"AAAA,SAASA,YAAY,QAAQ,wBAAwB;AAGrD,iFAAiF;AACjF,sIAAsI;AACtI,MAAMC,gBAAgB;AACtB,MAAMC,gBAAgB;AAEtB,0FAA0F;AAC1F,+FAA+F;AAC/F,OAAO,eAAeC,aAAaC,IAAgB,EAAEC,KAAa,EAAEC,IAAyB;IAC3F,MAAM,EAAEC,SAAS,EAAEC,SAAS,EAAEC,SAAS,EAAEC,KAAK,EAAE,GAAGJ;IACnD,MAAMK,QAAQX,aAAaK;IAC3B,2FAA2F;IAC3F,sGAAsG;IACtG,IAAIM,MAAMC,IAAI,OAAO,IAAI,OAAO,EAAE;IAClC,MAAMC,MAAM,CAAC,+DAA+D,EAAEZ,cAAc,+EAA+E,EAAEM,UAAU,uBAAuB,EAAEC,UAAU,CAAC,EAAEC,UAAU,UAAU,EAAEP,cAAc,OAAO,EAAEQ,OAAO;IACjR,MAAMI,OAAO,MAAMV,KAAKW,OAAO,CAACF;IAChC,OAAQ,MAAMC,KAAKE,GAAG,CAACL;AACzB"}
+{"version":3,"sources":["/Users/kevin/Dev/OpenSource/ai/sensemaking/src/store/sqlite/lexical.ts"],"sourcesContent":["import { segmentMatch } from '../../text/segment.ts';\nimport type { Connection, LexicalHit, LexicalQueryOptions } from '../types.ts';\n\nconst WEIGHTED_BM25 = 'bm25(content, 10.0, 5.0, 1.0, 0, 10.0, 5.0, 1.0)';\n\n// Ranked BM25 word-match query, scoped by the caller-built SQL fragments. An\n// unspaced-script run in `terms` becomes a quoted grapheme phrase against the `_seg` sidecars.\nexport async function queryLexical(conn: Connection, terms: string, opts: LexicalQueryOptions): Promise<LexicalHit[]> {\n  const { whereJoin, whereCond, scopeCond, limit } = opts;\n  const query = segmentMatch(terms);\n  // A run of pure unspaced-script punctuation segments to nothing searchable: an empty MATCH\n  // string is an FTS5 syntax error, not zero rows, so return zero rows directly rather than issuing it.\n  if (query.trim() === '') return [];\n  const sql = `SELECT content.path AS path FROM content ${whereJoin} WHERE content MATCH ? ${whereCond} ${scopeCond} ORDER BY ${WEIGHTED_BM25} LIMIT ${limit}`;\n  const stmt = await conn.prepare(sql);\n  return (await stmt.all(query)) as unknown as LexicalHit[];\n}\n"],"names":["segmentMatch","WEIGHTED_BM25","queryLexical","conn","terms","opts","whereJoin","whereCond","scopeCond","limit","query","trim","sql","stmt","prepare","all"],"mappings":"AAAA,SAASA,YAAY,QAAQ,wBAAwB;AAGrD,MAAMC,gBAAgB;AAEtB,6EAA6E;AAC7E,+FAA+F;AAC/F,OAAO,eAAeC,aAAaC,IAAgB,EAAEC,KAAa,EAAEC,IAAyB;IAC3F,MAAM,EAAEC,SAAS,EAAEC,SAAS,EAAEC,SAAS,EAAEC,KAAK,EAAE,GAAGJ;IACnD,MAAMK,QAAQV,aAAaI;IAC3B,2FAA2F;IAC3F,sGAAsG;IACtG,IAAIM,MAAMC,IAAI,OAAO,IAAI,OAAO,EAAE;IAClC,MAAMC,MAAM,CAAC,yCAAyC,EAAEN,UAAU,uBAAuB,EAAEC,UAAU,CAAC,EAAEC,UAAU,UAAU,EAAEP,cAAc,OAAO,EAAEQ,OAAO;IAC5J,MAAMI,OAAO,MAAMV,KAAKW,OAAO,CAACF;IAChC,OAAQ,MAAMC,KAAKE,GAAG,CAACL;AACzB"}

package/dist/esm/store/sqlite/store.js

@@ -5,11 +5,8 @@ import { fieldStats } from './fieldStats.js';
 import { queryLexical } from './lexical.js';
 import { scanCandidates, scanSimilar, writeVectorBatch } from './vectors.js';
 export const CAPABILITIES = new Set([
-    'phrases',
-    'snippets',
-    'lexical',
     'vectors',
-    'sql-functions'
+    'segment'
 ]);
 // Wraps the synchronous DatabaseSync connection in the async Store interface, sharing one
 // Connection instance (conn) with the builder's own reconcile call so transaction depth is tracked against the same object everywhere.

package/dist/esm/store/sqlite/store.js.map

@@ -1 +1 @@
-{"version":3,"sources":["/Users/kevin/Dev/OpenSource/ai/sensemaking/src/store/sqlite/store.ts"],"sourcesContent":["import type { DatabaseSync } from 'node:sqlite';\nimport { getColumns } from '../shared.ts';\nimport { withTransaction } from '../transaction.ts';\nimport type { Capability, Connection, Statement, Store, VectorWriteRow } from '../types.ts';\nimport { hasVectorRow, pendingRows } from '../vectors.ts';\nimport { fieldStats } from './fieldStats.ts';\nimport { queryLexical } from './lexical.ts';\nimport { scanCandidates, scanSimilar, writeVectorBatch } from './vectors.ts';\n\nexport const CAPABILITIES: ReadonlySet<Capability> = new Set(['phrases', 'snippets', 'lexical', 'vectors', 'sql-functions']);\n\n// Wraps the synchronous DatabaseSync connection in the async Store interface, sharing one\n// Connection instance (conn) with the builder's own reconcile call so transaction depth is tracked against the same object everywhere.\nexport function createStore(db: DatabaseSync, conn: Connection): Store {\n  return {\n    name: 'sqlite',\n    capabilities: CAPABILITIES,\n    async exec(sql: string): Promise<void> {\n      await conn.exec(sql);\n    },\n    async prepare(sql: string): Promise<Statement> {\n      return conn.prepare(sql);\n    },\n    async runBatch(sql: string, paramRows: unknown[][]): Promise<void> {\n      await conn.runBatch(sql, paramRows);\n    },\n    async transaction<T>(fn: () => Promise<T>): Promise<T> {\n      return withTransaction(conn, fn);\n    },\n    docs: {\n      async columns() {\n        return [...(await getColumns(conn))];\n      },\n      async fieldStats(columns, scopeWhere) {\n        return fieldStats(conn, columns, scopeWhere);\n      },\n    },\n    lexical: {\n      async query(terms, opts) {\n        return queryLexical(conn, terms, opts);\n      },\n    },\n    vectors: {\n      async pending() {\n        return pendingRows(conn);\n      },\n      async writeVectors(rows: VectorWriteRow[]) {\n        await writeVectorBatch(conn, rows);\n      },\n      async candidates(qv, storeDims, fetch, allowed) {\n        return scanCandidates(conn, qv, storeDims, fetch, allowed);\n      },\n      async similar(path, opts) {\n        return scanSimilar(conn, path, opts);\n      },\n      async hasVector(path) {\n        return hasVectorRow(conn, path);\n      },\n    },\n    async engineStatus() {\n      // Read back rather than recomputed: this is what open() actually set (3x the largest\n      // recorded reconcile, floored at 30s, capped at 10min), not a value re-derived here.\n      const row = db.prepare('PRAGMA busy_timeout').get() as { timeout: number };\n      return { busy_timeout: `${row.timeout}ms (derived: 3x the largest reconcile this cache has recorded, floored at 30000ms)` };\n    },\n    raw: {\n      async prepare(sql: string) {\n        const stmt = db.prepare(sql);\n        stmt.setReadBigInts(true); // int64 past 2^53 arrives as BigInt instead of throwing at step time\n        return {\n          columns: () => stmt.columns(),\n          // sense sql streams through an async iterator wrapping the sync iterate().\n          iterate: async function* (...params: unknown[]) {\n            yield* stmt.iterate(...(params as Parameters<typeof stmt.iterate>));\n          },\n        };\n      },\n    },\n    async close() {\n      db.close();\n    },\n  };\n}\n"],"names":["getColumns","withTransaction","hasVectorRow","pendingRows","fieldStats","queryLexical","scanCandidates","scanSimilar","writeVectorBatch","CAPABILITIES","Set","createStore","db","conn","name","capabilities","exec","sql","prepare","runBatch","paramRows","transaction","fn","docs","columns","scopeWhere","lexical","query","terms","opts","vectors","pending","writeVectors","rows","candidates","qv","storeDims","fetch","allowed","similar","path","hasVector","engineStatus","row","get","busy_timeout","timeout","raw","stmt","setReadBigInts","iterate","params","close"],"mappings":"AACA,SAASA,UAAU,QAAQ,eAAe;AAC1C,SAASC,eAAe,QAAQ,oBAAoB;AAEpD,SAASC,YAAY,EAAEC,WAAW,QAAQ,gBAAgB;AAC1D,SAASC,UAAU,QAAQ,kBAAkB;AAC7C,SAASC,YAAY,QAAQ,eAAe;AAC5C,SAASC,cAAc,EAAEC,WAAW,EAAEC,gBAAgB,QAAQ,eAAe;AAE7E,OAAO,MAAMC,eAAwC,IAAIC,IAAI;IAAC;IAAW;IAAY;IAAW;IAAW;CAAgB,EAAE;AAE7H,0FAA0F;AAC1F,uIAAuI;AACvI,OAAO,SAASC,YAAYC,EAAgB,EAAEC,IAAgB;IAC5D,OAAO;QACLC,MAAM;QACNC,cAAcN;QACd,MAAMO,MAAKC,GAAW;YACpB,MAAMJ,KAAKG,IAAI,CAACC;QAClB;QACA,MAAMC,SAAQD,GAAW;YACvB,OAAOJ,KAAKK,OAAO,CAACD;QACtB;QACA,MAAME,UAASF,GAAW,EAAEG,SAAsB;YAChD,MAAMP,KAAKM,QAAQ,CAACF,KAAKG;QAC3B;QACA,MAAMC,aAAeC,EAAoB;YACvC,OAAOrB,gBAAgBY,MAAMS;QAC/B;QACAC,MAAM;YACJ,MAAMC;gBACJ,OAAO;uBAAK,MAAMxB,WAAWa;iBAAO;YACtC;YACA,MAAMT,YAAWoB,OAAO,EAAEC,UAAU;gBAClC,OAAOrB,WAAWS,MAAMW,SAASC;YACnC;QACF;QACAC,SAAS;YACP,MAAMC,OAAMC,KAAK,EAAEC,IAAI;gBACrB,OAAOxB,aAAaQ,MAAMe,OAAOC;YACnC;QACF;QACAC,SAAS;YACP,MAAMC;gBACJ,OAAO5B,YAAYU;YACrB;YACA,MAAMmB,cAAaC,IAAsB;gBACvC,MAAMzB,iBAAiBK,MAAMoB;YAC/B;YACA,MAAMC,YAAWC,EAAE,EAAEC,SAAS,EAAEC,KAAK,EAAEC,OAAO;gBAC5C,OAAOhC,eAAeO,MAAMsB,IAAIC,WAAWC,OAAOC;YACpD;YACA,MAAMC,SAAQC,IAAI,EAAEX,IAAI;gBACtB,OAAOtB,YAAYM,MAAM2B,MAAMX;YACjC;YACA,MAAMY,WAAUD,IAAI;gBAClB,OAAOtC,aAAaW,MAAM2B;YAC5B;QACF;QACA,MAAME;YACJ,qFAAqF;YACrF,qFAAqF;YACrF,MAAMC,MAAM/B,GAAGM,OAAO,CAAC,uBAAuB0B,GAAG;YACjD,OAAO;gBAAEC,cAAc,GAAGF,IAAIG,OAAO,CAAC,kFAAkF,CAAC;YAAC;QAC5H;QACAC,KAAK;YACH,MAAM7B,SAAQD,GAAW;gBACvB,MAAM+B,OAAOpC,GAAGM,OAAO,CAACD;gBACxB+B,KAAKC,cAAc,CAAC,OAAO,qEAAqE;gBAChG,OAAO;oBACLzB,SAAS,IAAMwB,KAAKxB,OAAO;oBAC3B,2EAA2E;oBAC3E0B,SAAS,gBAAiB,GAAGC,MAAiB;wBAC5C,OAAOH,KAAKE,OAAO,IAAKC;oBAC1B;gBACF;YACF;QACF;QACA,MAAMC;YACJxC,GAAGwC,KAAK;QACV;IACF;AACF"}
+{"version":3,"sources":["/Users/kevin/Dev/OpenSource/ai/sensemaking/src/store/sqlite/store.ts"],"sourcesContent":["import type { DatabaseSync } from 'node:sqlite';\nimport { getColumns } from '../shared.ts';\nimport { withTransaction } from '../transaction.ts';\nimport type { Capability, Connection, Statement, Store, VectorWriteRow } from '../types.ts';\nimport { hasVectorRow, pendingRows } from '../vectors.ts';\nimport { fieldStats } from './fieldStats.ts';\nimport { queryLexical } from './lexical.ts';\nimport { scanCandidates, scanSimilar, writeVectorBatch } from './vectors.ts';\n\nexport const CAPABILITIES: ReadonlySet<Capability> = new Set(['vectors', 'segment']);\n\n// Wraps the synchronous DatabaseSync connection in the async Store interface, sharing one\n// Connection instance (conn) with the builder's own reconcile call so transaction depth is tracked against the same object everywhere.\nexport function createStore(db: DatabaseSync, conn: Connection): Store {\n  return {\n    name: 'sqlite',\n    capabilities: CAPABILITIES,\n    async exec(sql: string): Promise<void> {\n      await conn.exec(sql);\n    },\n    async prepare(sql: string): Promise<Statement> {\n      return conn.prepare(sql);\n    },\n    async runBatch(sql: string, paramRows: unknown[][]): Promise<void> {\n      await conn.runBatch(sql, paramRows);\n    },\n    async transaction<T>(fn: () => Promise<T>): Promise<T> {\n      return withTransaction(conn, fn);\n    },\n    docs: {\n      async columns() {\n        return [...(await getColumns(conn))];\n      },\n      async fieldStats(columns, scopeWhere) {\n        return fieldStats(conn, columns, scopeWhere);\n      },\n    },\n    lexical: {\n      async query(terms, opts) {\n        return queryLexical(conn, terms, opts);\n      },\n    },\n    vectors: {\n      async pending() {\n        return pendingRows(conn);\n      },\n      async writeVectors(rows: VectorWriteRow[]) {\n        await writeVectorBatch(conn, rows);\n      },\n      async candidates(qv, storeDims, fetch, allowed) {\n        return scanCandidates(conn, qv, storeDims, fetch, allowed);\n      },\n      async similar(path, opts) {\n        return scanSimilar(conn, path, opts);\n      },\n      async hasVector(path) {\n        return hasVectorRow(conn, path);\n      },\n    },\n    async engineStatus() {\n      // Read back rather than recomputed: this is what open() actually set (3x the largest\n      // recorded reconcile, floored at 30s, capped at 10min), not a value re-derived here.\n      const row = db.prepare('PRAGMA busy_timeout').get() as { timeout: number };\n      return { busy_timeout: `${row.timeout}ms (derived: 3x the largest reconcile this cache has recorded, floored at 30000ms)` };\n    },\n    raw: {\n      async prepare(sql: string) {\n        const stmt = db.prepare(sql);\n        stmt.setReadBigInts(true); // int64 past 2^53 arrives as BigInt instead of throwing at step time\n        return {\n          columns: () => stmt.columns(),\n          // sense sql streams through an async iterator wrapping the sync iterate().\n          iterate: async function* (...params: unknown[]) {\n            yield* stmt.iterate(...(params as Parameters<typeof stmt.iterate>));\n          },\n        };\n      },\n    },\n    async close() {\n      db.close();\n    },\n  };\n}\n"],"names":["getColumns","withTransaction","hasVectorRow","pendingRows","fieldStats","queryLexical","scanCandidates","scanSimilar","writeVectorBatch","CAPABILITIES","Set","createStore","db","conn","name","capabilities","exec","sql","prepare","runBatch","paramRows","transaction","fn","docs","columns","scopeWhere","lexical","query","terms","opts","vectors","pending","writeVectors","rows","candidates","qv","storeDims","fetch","allowed","similar","path","hasVector","engineStatus","row","get","busy_timeout","timeout","raw","stmt","setReadBigInts","iterate","params","close"],"mappings":"AACA,SAASA,UAAU,QAAQ,eAAe;AAC1C,SAASC,eAAe,QAAQ,oBAAoB;AAEpD,SAASC,YAAY,EAAEC,WAAW,QAAQ,gBAAgB;AAC1D,SAASC,UAAU,QAAQ,kBAAkB;AAC7C,SAASC,YAAY,QAAQ,eAAe;AAC5C,SAASC,cAAc,EAAEC,WAAW,EAAEC,gBAAgB,QAAQ,eAAe;AAE7E,OAAO,MAAMC,eAAwC,IAAIC,IAAI;IAAC;IAAW;CAAU,EAAE;AAErF,0FAA0F;AAC1F,uIAAuI;AACvI,OAAO,SAASC,YAAYC,EAAgB,EAAEC,IAAgB;IAC5D,OAAO;QACLC,MAAM;QACNC,cAAcN;QACd,MAAMO,MAAKC,GAAW;YACpB,MAAMJ,KAAKG,IAAI,CAACC;QAClB;QACA,MAAMC,SAAQD,GAAW;YACvB,OAAOJ,KAAKK,OAAO,CAACD;QACtB;QACA,MAAME,UAASF,GAAW,EAAEG,SAAsB;YAChD,MAAMP,KAAKM,QAAQ,CAACF,KAAKG;QAC3B;QACA,MAAMC,aAAeC,EAAoB;YACvC,OAAOrB,gBAAgBY,MAAMS;QAC/B;QACAC,MAAM;YACJ,MAAMC;gBACJ,OAAO;uBAAK,MAAMxB,WAAWa;iBAAO;YACtC;YACA,MAAMT,YAAWoB,OAAO,EAAEC,UAAU;gBAClC,OAAOrB,WAAWS,MAAMW,SAASC;YACnC;QACF;QACAC,SAAS;YACP,MAAMC,OAAMC,KAAK,EAAEC,IAAI;gBACrB,OAAOxB,aAAaQ,MAAMe,OAAOC;YACnC;QACF;QACAC,SAAS;YACP,MAAMC;gBACJ,OAAO5B,YAAYU;YACrB;YACA,MAAMmB,cAAaC,IAAsB;gBACvC,MAAMzB,iBAAiBK,MAAMoB;YAC/B;YACA,MAAMC,YAAWC,EAAE,EAAEC,SAAS,EAAEC,KAAK,EAAEC,OAAO;gBAC5C,OAAOhC,eAAeO,MAAMsB,IAAIC,WAAWC,OAAOC;YACpD;YACA,MAAMC,SAAQC,IAAI,EAAEX,IAAI;gBACtB,OAAOtB,YAAYM,MAAM2B,MAAMX;YACjC;YACA,MAAMY,WAAUD,IAAI;gBAClB,OAAOtC,aAAaW,MAAM2B;YAC5B;QACF;QACA,MAAME;YACJ,qFAAqF;YACrF,qFAAqF;YACrF,MAAMC,MAAM/B,GAAGM,OAAO,CAAC,uBAAuB0B,GAAG;YACjD,OAAO;gBAAEC,cAAc,GAAGF,IAAIG,OAAO,CAAC,kFAAkF,CAAC;YAAC;QAC5H;QACAC,KAAK;YACH,MAAM7B,SAAQD,GAAW;gBACvB,MAAM+B,OAAOpC,GAAGM,OAAO,CAACD;gBACxB+B,KAAKC,cAAc,CAAC,OAAO,qEAAqE;gBAChG,OAAO;oBACLzB,SAAS,IAAMwB,KAAKxB,OAAO;oBAC3B,2EAA2E;oBAC3E0B,SAAS,gBAAiB,GAAGC,MAAiB;wBAC5C,OAAOH,KAAKE,OAAO,IAAKC;oBAC1B;gBACF;YACF;QACF;QACA,MAAMC;YACJxC,GAAGwC,KAAK;QACV;IACF;AACF"}

package/dist/esm/store/sqlite/vectors.js

@@ -1,4 +1,4 @@
-import { asCosine, sampleEvenly } from '../vectors.js';
+import { asCosine, compareVectorScores, sampleEvenly } from '../vectors.js';
 // One runBatch call per provider batch: the caller (embed/query.ts) already batches by the
 // provider's batchCap, so this is one crossing per batch, never per row.
 export async function writeVectorBatch(conn, rows) {
@@ -13,57 +13,86 @@ export async function writeVectorBatch(conn, rows) {
 // Best chunk per file by cosine, its line range riding along: the JS loop over stored int8
 // BLOBs this store's scan strategy is (a native store scans differently, same contract).
 export async function scanCandidates(conn, qv, storeDims, fetch, allowed) {
-    const stmt = await conn.prepare('SELECT "path", start_line, end_line, scale, vector FROM embeddings WHERE vector IS NOT NULL');
+    const stmt = await conn.prepare('SELECT "path", chunk, start_line, end_line, vector FROM embeddings WHERE vector IS NOT NULL ORDER BY "path", chunk');
     const rows = await stmt.all();
+    let queryNorm = 0;
+    for(let d = 0; d < Math.min(storeDims, qv.length); d++)queryNorm += qv[d] * qv[d];
+    queryNorm = Math.sqrt(queryNorm);
     const best = new Map();
     for (const row of rows){
         if (allowed && !allowed.has(row.path)) continue;
         const q = new Int8Array(row.vector.buffer, row.vector.byteOffset, Math.min(storeDims, row.vector.byteLength));
+        // Rounding to int8 costs the stored row its unit norm, so dividing by that norm is what makes
+        // this a cosine rather than a scaled dot product. `scale` cancels out of the ratio.
         let dot = 0;
-        for(let d = 0; d < q.length; d++)dot += q[d] * qv[d];
-        const score = dot * row.scale;
+        let norm = 0;
+        const length = Math.min(q.length, qv.length);
+        for(let d = 0; d < length; d++){
+            dot += q[d] * qv[d];
+            norm += q[d] * q[d];
+        }
+        for(let d = length; d < q.length; d++)norm += q[d] * q[d];
+        const score = norm === 0 || queryNorm === 0 ? 0 : dot / (Math.sqrt(norm) * queryNorm);
         const existing = best.get(row.path);
-        if (!existing || score > existing.score) best.set(row.path, {
-            score,
-            lines: `L${row.start_line}-${row.end_line}`
-        });
+        if (!existing || score > existing.score || score === existing.score && row.chunk < existing.chunk) {
+            best.set(row.path, {
+                score,
+                chunk: row.chunk,
+                lines: `L${row.start_line}-${row.end_line}`
+            });
+        }
     }
     return [
         ...best.entries()
-    ].sort((a, b)=>b[1].score - a[1].score).slice(0, fetch).map(([path, b])=>({
+    ].map(([path, value])=>({
+            path,
+            ...value
+        })).sort(compareVectorScores).slice(0, fetch).map(({ path, lines, score })=>({
             path,
-            lines: b.lines,
-            similarity: asCosine(b.score)
+            lines,
+            similarity: asCosine(score)
         }));
 }
 // Note-to-note similarity is the max cosine over (target chunk, other chunk) pairs, one linear
 // scan of stored vectors.
 export async function scanSimilar(conn, path, opts) {
-    const targetStmt = await conn.prepare('SELECT scale, vector FROM embeddings WHERE "path" = ? AND vector IS NOT NULL ORDER BY chunk');
+    const targetStmt = await conn.prepare('SELECT vector FROM embeddings WHERE "path" = ? AND vector IS NOT NULL ORDER BY chunk');
     const targetRows = await targetStmt.all(path);
     if (targetRows.length === 0) return [];
-    const target = sampleEvenly(targetRows).map((row)=>({
-            v: new Int8Array(row.vector.buffer, row.vector.byteOffset, row.vector.byteLength),
-            scale: row.scale
-        }));
-    const stmt = await conn.prepare('SELECT "path", scale, vector FROM embeddings WHERE vector IS NOT NULL');
+    // Each side's norm divides its own dot product, so both are taken once here rather than per pair.
+    const target = sampleEvenly(targetRows).map((row)=>{
+        const v = new Int8Array(row.vector.buffer, row.vector.byteOffset, row.vector.byteLength);
+        let norm = 0;
+        for(let d = 0; d < v.length; d++)norm += v[d] * v[d];
+        return {
+            v,
+            norm: Math.sqrt(norm)
+        };
+    });
+    const stmt = await conn.prepare('SELECT "path", vector FROM embeddings WHERE vector IS NOT NULL');
     const rows = await stmt.all();
     const best = new Map();
     for (const row of rows){
         if (row.path === path || opts.exclude.has(row.path) || opts.allowed && !opts.allowed.has(row.path)) continue;
         const other = new Int8Array(row.vector.buffer, row.vector.byteOffset, row.vector.byteLength);
+        let otherNorm = 0;
+        for(let d = 0; d < other.length; d++)otherNorm += other[d] * other[d];
+        otherNorm = Math.sqrt(otherNorm);
         for (const t of target){
             let dot = 0;
             const len = Math.min(t.v.length, other.length);
             for(let d = 0; d < len; d++)dot += t.v[d] * other[d];
-            const score = dot * t.scale * row.scale;
+            const score = t.norm === 0 || otherNorm === 0 ? 0 : dot / (t.norm * otherNorm);
             const existing = best.get(row.path);
             if (existing === undefined || score > existing) best.set(row.path, score);
         }
     }
     return [
         ...best.entries()
-    ].sort((a, b)=>b[1] - a[1]).slice(0, opts.k).map(([p, score])=>({
+    ].map(([p, score])=>({
+            path: p,
+            score
+        })).sort(compareVectorScores).slice(0, opts.k).map(({ path: p, score })=>({
             path: p,
             similarity: asCosine(score)
         }));

package/dist/esm/store/sqlite/vectors.js.map

@@ -1 +1 @@
-{"version":3,"sources":["/Users/kevin/Dev/OpenSource/ai/sensemaking/src/store/sqlite/vectors.ts"],"sourcesContent":["import type { Connection, VectorCandidate, VectorSimilar, VectorWriteRow } from '../types.ts';\nimport { asCosine, sampleEvenly } from '../vectors.ts';\n\n// One runBatch call per provider batch: the caller (embed/query.ts) already batches by the\n// provider's batchCap, so this is one crossing per batch, never per row.\nexport async function writeVectorBatch(conn: Connection, rows: VectorWriteRow[]): Promise<void> {\n  if (rows.length === 0) return;\n  await conn.runBatch(\n    'UPDATE embeddings SET scale = ?, vector = ? WHERE \"path\" = ? AND chunk = ?',\n    rows.map((row) => [row.scale, row.vector, row.path, row.chunk])\n  );\n}\n\n// Best chunk per file by cosine, its line range riding along: the JS loop over stored int8\n// BLOBs this store's scan strategy is (a native store scans differently, same contract).\nexport async function scanCandidates(conn: Connection, qv: Float32Array, storeDims: number, fetch: number, allowed?: Set<string>): Promise<VectorCandidate[]> {\n  const stmt = await conn.prepare('SELECT \"path\", start_line, end_line, scale, vector FROM embeddings WHERE vector IS NOT NULL');\n  const rows = (await stmt.all()) as Array<{\n    path: string;\n    start_line: number;\n    end_line: number;\n    scale: number;\n    vector: Uint8Array;\n  }>;\n\n  const best = new Map<string, { score: number; lines: string }>();\n  for (const row of rows) {\n    if (allowed && !allowed.has(row.path)) continue;\n    const q = new Int8Array(row.vector.buffer, row.vector.byteOffset, Math.min(storeDims, row.vector.byteLength));\n    let dot = 0;\n    for (let d = 0; d < q.length; d++) dot += q[d] * qv[d];\n    const score = dot * row.scale;\n    const existing = best.get(row.path);\n    if (!existing || score > existing.score) best.set(row.path, { score, lines: `L${row.start_line}-${row.end_line}` });\n  }\n  return [...best.entries()]\n    .sort((a, b) => b[1].score - a[1].score)\n    .slice(0, fetch)\n    .map(([path, b]) => ({ path, lines: b.lines, similarity: asCosine(b.score) }));\n}\n\n// Note-to-note similarity is the max cosine over (target chunk, other chunk) pairs, one linear\n// scan of stored vectors.\nexport async function scanSimilar(conn: Connection, path: string, opts: { exclude: Set<string>; allowed?: Set<string>; k: number }): Promise<VectorSimilar[]> {\n  const targetStmt = await conn.prepare('SELECT scale, vector FROM embeddings WHERE \"path\" = ? AND vector IS NOT NULL ORDER BY chunk');\n  const targetRows = (await targetStmt.all(path)) as Array<{ scale: number; vector: Uint8Array }>;\n  if (targetRows.length === 0) return [];\n  const target = sampleEvenly(targetRows).map((row) => ({ v: new Int8Array(row.vector.buffer, row.vector.byteOffset, row.vector.byteLength), scale: row.scale }));\n\n  const stmt = await conn.prepare('SELECT \"path\", scale, vector FROM embeddings WHERE vector IS NOT NULL');\n  const rows = (await stmt.all()) as Array<{ path: string; scale: number; vector: Uint8Array }>;\n  const best = new Map<string, number>();\n  for (const row of rows) {\n    if (row.path === path || opts.exclude.has(row.path) || (opts.allowed && !opts.allowed.has(row.path))) continue;\n    const other = new Int8Array(row.vector.buffer, row.vector.byteOffset, row.vector.byteLength);\n    for (const t of target) {\n      let dot = 0;\n      const len = Math.min(t.v.length, other.length);\n      for (let d = 0; d < len; d++) dot += t.v[d] * other[d];\n      const score = dot * t.scale * row.scale;\n      const existing = best.get(row.path);\n      if (existing === undefined || score > existing) best.set(row.path, score);\n    }\n  }\n\n  return [...best.entries()]\n    .sort((a, b) => b[1] - a[1])\n    .slice(0, opts.k)\n    .map(([p, score]) => ({ path: p, similarity: asCosine(score) }));\n}\n"],"names":["asCosine","sampleEvenly","writeVectorBatch","conn","rows","length","runBatch","map","row","scale","vector","path","chunk","scanCandidates","qv","storeDims","fetch","allowed","stmt","prepare","all","best","Map","has","q","Int8Array","buffer","byteOffset","Math","min","byteLength","dot","d","score","existing","get","set","lines","start_line","end_line","entries","sort","a","b","slice","similarity","scanSimilar","opts","targetStmt","targetRows","target","v","exclude","other","t","len","undefined","k","p"],"mappings":"AACA,SAASA,QAAQ,EAAEC,YAAY,QAAQ,gBAAgB;AAEvD,2FAA2F;AAC3F,yEAAyE;AACzE,OAAO,eAAeC,iBAAiBC,IAAgB,EAAEC,IAAsB;IAC7E,IAAIA,KAAKC,MAAM,KAAK,GAAG;IACvB,MAAMF,KAAKG,QAAQ,CACjB,8EACAF,KAAKG,GAAG,CAAC,CAACC,MAAQ;YAACA,IAAIC,KAAK;YAAED,IAAIE,MAAM;YAAEF,IAAIG,IAAI;YAAEH,IAAII,KAAK;SAAC;AAElE;AAEA,2FAA2F;AAC3F,yFAAyF;AACzF,OAAO,eAAeC,eAAeV,IAAgB,EAAEW,EAAgB,EAAEC,SAAiB,EAAEC,KAAa,EAAEC,OAAqB;IAC9H,MAAMC,OAAO,MAAMf,KAAKgB,OAAO,CAAC;IAChC,MAAMf,OAAQ,MAAMc,KAAKE,GAAG;IAQ5B,MAAMC,OAAO,IAAIC;IACjB,KAAK,MAAMd,OAAOJ,KAAM;QACtB,IAAIa,WAAW,CAACA,QAAQM,GAAG,CAACf,IAAIG,IAAI,GAAG;QACvC,MAAMa,IAAI,IAAIC,UAAUjB,IAAIE,MAAM,CAACgB,MAAM,EAAElB,IAAIE,MAAM,CAACiB,UAAU,EAAEC,KAAKC,GAAG,CAACd,WAAWP,IAAIE,MAAM,CAACoB,UAAU;QAC3G,IAAIC,MAAM;QACV,IAAK,IAAIC,IAAI,GAAGA,IAAIR,EAAEnB,MAAM,EAAE2B,IAAKD,OAAOP,CAAC,CAACQ,EAAE,GAAGlB,EAAE,CAACkB,EAAE;QACtD,MAAMC,QAAQF,MAAMvB,IAAIC,KAAK;QAC7B,MAAMyB,WAAWb,KAAKc,GAAG,CAAC3B,IAAIG,IAAI;QAClC,IAAI,CAACuB,YAAYD,QAAQC,SAASD,KAAK,EAAEZ,KAAKe,GAAG,CAAC5B,IAAIG,IAAI,EAAE;YAAEsB;YAAOI,OAAO,CAAC,CAAC,EAAE7B,IAAI8B,UAAU,CAAC,CAAC,EAAE9B,IAAI+B,QAAQ,EAAE;QAAC;IACnH;IACA,OAAO;WAAIlB,KAAKmB,OAAO;KAAG,CACvBC,IAAI,CAAC,CAACC,GAAGC,IAAMA,CAAC,CAAC,EAAE,CAACV,KAAK,GAAGS,CAAC,CAAC,EAAE,CAACT,KAAK,EACtCW,KAAK,CAAC,GAAG5B,OACTT,GAAG,CAAC,CAAC,CAACI,MAAMgC,EAAE,GAAM,CAAA;YAAEhC;YAAM0B,OAAOM,EAAEN,KAAK;YAAEQ,YAAY7C,SAAS2C,EAAEV,KAAK;QAAE,CAAA;AAC/E;AAEA,+FAA+F;AAC/F,0BAA0B;AAC1B,OAAO,eAAea,YAAY3C,IAAgB,EAAEQ,IAAY,EAAEoC,IAAgE;IAChI,MAAMC,aAAa,MAAM7C,KAAKgB,OAAO,CAAC;IACtC,MAAM8B,aAAc,MAAMD,WAAW5B,GAAG,CAACT;IACzC,IAAIsC,WAAW5C,MAAM,KAAK,GAAG,OAAO,EAAE;IACtC,MAAM6C,SAASjD,aAAagD,YAAY1C,GAAG,CAAC,CAACC,MAAS,CAAA;YAAE2C,GAAG,IAAI1B,UAAUjB,IAAIE,MAAM,CAACgB,MAAM,EAAElB,IAAIE,MAAM,CAACiB,UAAU,EAAEnB,IAAIE,MAAM,CAACoB,UAAU;YAAGrB,OAAOD,IAAIC,KAAK;QAAC,CAAA;IAE5J,MAAMS,OAAO,MAAMf,KAAKgB,OAAO,CAAC;IAChC,MAAMf,OAAQ,MAAMc,KAAKE,GAAG;IAC5B,MAAMC,OAAO,IAAIC;IACjB,KAAK,MAAMd,OAAOJ,KAAM;QACtB,IAAII,IAAIG,IAAI,KAAKA,QAAQoC,KAAKK,OAAO,CAAC7B,GAAG,CAACf,IAAIG,IAAI,KAAMoC,KAAK9B,OAAO,IAAI,CAAC8B,KAAK9B,OAAO,CAACM,GAAG,CAACf,IAAIG,IAAI,GAAI;QACtG,MAAM0C,QAAQ,IAAI5B,UAAUjB,IAAIE,MAAM,CAACgB,MAAM,EAAElB,IAAIE,MAAM,CAACiB,UAAU,EAAEnB,IAAIE,MAAM,CAACoB,UAAU;QAC3F,KAAK,MAAMwB,KAAKJ,OAAQ;YACtB,IAAInB,MAAM;YACV,MAAMwB,MAAM3B,KAAKC,GAAG,CAACyB,EAAEH,CAAC,CAAC9C,MAAM,EAAEgD,MAAMhD,MAAM;YAC7C,IAAK,IAAI2B,IAAI,GAAGA,IAAIuB,KAAKvB,IAAKD,OAAOuB,EAAEH,CAAC,CAACnB,EAAE,GAAGqB,KAAK,CAACrB,EAAE;YACtD,MAAMC,QAAQF,MAAMuB,EAAE7C,KAAK,GAAGD,IAAIC,KAAK;YACvC,MAAMyB,WAAWb,KAAKc,GAAG,CAAC3B,IAAIG,IAAI;YAClC,IAAIuB,aAAasB,aAAavB,QAAQC,UAAUb,KAAKe,GAAG,CAAC5B,IAAIG,IAAI,EAAEsB;QACrE;IACF;IAEA,OAAO;WAAIZ,KAAKmB,OAAO;KAAG,CACvBC,IAAI,CAAC,CAACC,GAAGC,IAAMA,CAAC,CAAC,EAAE,GAAGD,CAAC,CAAC,EAAE,EAC1BE,KAAK,CAAC,GAAGG,KAAKU,CAAC,EACflD,GAAG,CAAC,CAAC,CAACmD,GAAGzB,MAAM,GAAM,CAAA;YAAEtB,MAAM+C;YAAGb,YAAY7C,SAASiC;QAAO,CAAA;AACjE"}
+{"version":3,"sources":["/Users/kevin/Dev/OpenSource/ai/sensemaking/src/store/sqlite/vectors.ts"],"sourcesContent":["import type { Connection, VectorCandidate, VectorSimilar, VectorWriteRow } from '../types.ts';\nimport { asCosine, compareVectorScores, sampleEvenly } from '../vectors.ts';\n\n// One runBatch call per provider batch: the caller (embed/query.ts) already batches by the\n// provider's batchCap, so this is one crossing per batch, never per row.\nexport async function writeVectorBatch(conn: Connection, rows: VectorWriteRow[]): Promise<void> {\n  if (rows.length === 0) return;\n  await conn.runBatch(\n    'UPDATE embeddings SET scale = ?, vector = ? WHERE \"path\" = ? AND chunk = ?',\n    rows.map((row) => [row.scale, row.vector, row.path, row.chunk])\n  );\n}\n\n// Best chunk per file by cosine, its line range riding along: the JS loop over stored int8\n// BLOBs this store's scan strategy is (a native store scans differently, same contract).\nexport async function scanCandidates(conn: Connection, qv: Float32Array, storeDims: number, fetch: number, allowed?: Set<string>): Promise<VectorCandidate[]> {\n  const stmt = await conn.prepare('SELECT \"path\", chunk, start_line, end_line, vector FROM embeddings WHERE vector IS NOT NULL ORDER BY \"path\", chunk');\n  const rows = (await stmt.all()) as Array<{\n    path: string;\n    chunk: number;\n    start_line: number;\n    end_line: number;\n    vector: Uint8Array;\n  }>;\n\n  let queryNorm = 0;\n  for (let d = 0; d < Math.min(storeDims, qv.length); d++) queryNorm += qv[d] * qv[d];\n  queryNorm = Math.sqrt(queryNorm);\n\n  const best = new Map<string, { score: number; chunk: number; lines: string }>();\n  for (const row of rows) {\n    if (allowed && !allowed.has(row.path)) continue;\n    const q = new Int8Array(row.vector.buffer, row.vector.byteOffset, Math.min(storeDims, row.vector.byteLength));\n    // Rounding to int8 costs the stored row its unit norm, so dividing by that norm is what makes\n    // this a cosine rather than a scaled dot product. `scale` cancels out of the ratio.\n    let dot = 0;\n    let norm = 0;\n    const length = Math.min(q.length, qv.length);\n    for (let d = 0; d < length; d++) {\n      dot += q[d] * qv[d];\n      norm += q[d] * q[d];\n    }\n    for (let d = length; d < q.length; d++) norm += q[d] * q[d];\n    const score = norm === 0 || queryNorm === 0 ? 0 : dot / (Math.sqrt(norm) * queryNorm);\n    const existing = best.get(row.path);\n    if (!existing || score > existing.score || (score === existing.score && row.chunk < existing.chunk)) {\n      best.set(row.path, { score, chunk: row.chunk, lines: `L${row.start_line}-${row.end_line}` });\n    }\n  }\n  return [...best.entries()]\n    .map(([path, value]) => ({ path, ...value }))\n    .sort(compareVectorScores)\n    .slice(0, fetch)\n    .map(({ path, lines, score }) => ({ path, lines, similarity: asCosine(score) }));\n}\n\n// Note-to-note similarity is the max cosine over (target chunk, other chunk) pairs, one linear\n// scan of stored vectors.\nexport async function scanSimilar(conn: Connection, path: string, opts: { exclude: Set<string>; allowed?: Set<string>; k: number }): Promise<VectorSimilar[]> {\n  const targetStmt = await conn.prepare('SELECT vector FROM embeddings WHERE \"path\" = ? AND vector IS NOT NULL ORDER BY chunk');\n  const targetRows = (await targetStmt.all(path)) as Array<{ vector: Uint8Array }>;\n  if (targetRows.length === 0) return [];\n  // Each side's norm divides its own dot product, so both are taken once here rather than per pair.\n  const target = sampleEvenly(targetRows).map((row) => {\n    const v = new Int8Array(row.vector.buffer, row.vector.byteOffset, row.vector.byteLength);\n    let norm = 0;\n    for (let d = 0; d < v.length; d++) norm += v[d] * v[d];\n    return { v, norm: Math.sqrt(norm) };\n  });\n\n  const stmt = await conn.prepare('SELECT \"path\", vector FROM embeddings WHERE vector IS NOT NULL');\n  const rows = (await stmt.all()) as Array<{ path: string; vector: Uint8Array }>;\n  const best = new Map<string, number>();\n  for (const row of rows) {\n    if (row.path === path || opts.exclude.has(row.path) || (opts.allowed && !opts.allowed.has(row.path))) continue;\n    const other = new Int8Array(row.vector.buffer, row.vector.byteOffset, row.vector.byteLength);\n    let otherNorm = 0;\n    for (let d = 0; d < other.length; d++) otherNorm += other[d] * other[d];\n    otherNorm = Math.sqrt(otherNorm);\n    for (const t of target) {\n      let dot = 0;\n      const len = Math.min(t.v.length, other.length);\n      for (let d = 0; d < len; d++) dot += t.v[d] * other[d];\n      const score = t.norm === 0 || otherNorm === 0 ? 0 : dot / (t.norm * otherNorm);\n      const existing = best.get(row.path);\n      if (existing === undefined || score > existing) best.set(row.path, score);\n    }\n  }\n\n  return [...best.entries()]\n    .map(([p, score]) => ({ path: p, score }))\n    .sort(compareVectorScores)\n    .slice(0, opts.k)\n    .map(({ path: p, score }) => ({ path: p, similarity: asCosine(score) }));\n}\n"],"names":["asCosine","compareVectorScores","sampleEvenly","writeVectorBatch","conn","rows","length","runBatch","map","row","scale","vector","path","chunk","scanCandidates","qv","storeDims","fetch","allowed","stmt","prepare","all","queryNorm","d","Math","min","sqrt","best","Map","has","q","Int8Array","buffer","byteOffset","byteLength","dot","norm","score","existing","get","set","lines","start_line","end_line","entries","value","sort","slice","similarity","scanSimilar","opts","targetStmt","targetRows","target","v","exclude","other","otherNorm","t","len","undefined","p","k"],"mappings":"AACA,SAASA,QAAQ,EAAEC,mBAAmB,EAAEC,YAAY,QAAQ,gBAAgB;AAE5E,2FAA2F;AAC3F,yEAAyE;AACzE,OAAO,eAAeC,iBAAiBC,IAAgB,EAAEC,IAAsB;IAC7E,IAAIA,KAAKC,MAAM,KAAK,GAAG;IACvB,MAAMF,KAAKG,QAAQ,CACjB,8EACAF,KAAKG,GAAG,CAAC,CAACC,MAAQ;YAACA,IAAIC,KAAK;YAAED,IAAIE,MAAM;YAAEF,IAAIG,IAAI;YAAEH,IAAII,KAAK;SAAC;AAElE;AAEA,2FAA2F;AAC3F,yFAAyF;AACzF,OAAO,eAAeC,eAAeV,IAAgB,EAAEW,EAAgB,EAAEC,SAAiB,EAAEC,KAAa,EAAEC,OAAqB;IAC9H,MAAMC,OAAO,MAAMf,KAAKgB,OAAO,CAAC;IAChC,MAAMf,OAAQ,MAAMc,KAAKE,GAAG;IAQ5B,IAAIC,YAAY;IAChB,IAAK,IAAIC,IAAI,GAAGA,IAAIC,KAAKC,GAAG,CAACT,WAAWD,GAAGT,MAAM,GAAGiB,IAAKD,aAAaP,EAAE,CAACQ,EAAE,GAAGR,EAAE,CAACQ,EAAE;IACnFD,YAAYE,KAAKE,IAAI,CAACJ;IAEtB,MAAMK,OAAO,IAAIC;IACjB,KAAK,MAAMnB,OAAOJ,KAAM;QACtB,IAAIa,WAAW,CAACA,QAAQW,GAAG,CAACpB,IAAIG,IAAI,GAAG;QACvC,MAAMkB,IAAI,IAAIC,UAAUtB,IAAIE,MAAM,CAACqB,MAAM,EAAEvB,IAAIE,MAAM,CAACsB,UAAU,EAAET,KAAKC,GAAG,CAACT,WAAWP,IAAIE,MAAM,CAACuB,UAAU;QAC3G,8FAA8F;QAC9F,oFAAoF;QACpF,IAAIC,MAAM;QACV,IAAIC,OAAO;QACX,MAAM9B,SAASkB,KAAKC,GAAG,CAACK,EAAExB,MAAM,EAAES,GAAGT,MAAM;QAC3C,IAAK,IAAIiB,IAAI,GAAGA,IAAIjB,QAAQiB,IAAK;YAC/BY,OAAOL,CAAC,CAACP,EAAE,GAAGR,EAAE,CAACQ,EAAE;YACnBa,QAAQN,CAAC,CAACP,EAAE,GAAGO,CAAC,CAACP,EAAE;QACrB;QACA,IAAK,IAAIA,IAAIjB,QAAQiB,IAAIO,EAAExB,MAAM,EAAEiB,IAAKa,QAAQN,CAAC,CAACP,EAAE,GAAGO,CAAC,CAACP,EAAE;QAC3D,MAAMc,QAAQD,SAAS,KAAKd,cAAc,IAAI,IAAIa,MAAOX,CAAAA,KAAKE,IAAI,CAACU,QAAQd,SAAQ;QACnF,MAAMgB,WAAWX,KAAKY,GAAG,CAAC9B,IAAIG,IAAI;QAClC,IAAI,CAAC0B,YAAYD,QAAQC,SAASD,KAAK,IAAKA,UAAUC,SAASD,KAAK,IAAI5B,IAAII,KAAK,GAAGyB,SAASzB,KAAK,EAAG;YACnGc,KAAKa,GAAG,CAAC/B,IAAIG,IAAI,EAAE;gBAAEyB;gBAAOxB,OAAOJ,IAAII,KAAK;gBAAE4B,OAAO,CAAC,CAAC,EAAEhC,IAAIiC,UAAU,CAAC,CAAC,EAAEjC,IAAIkC,QAAQ,EAAE;YAAC;QAC5F;IACF;IACA,OAAO;WAAIhB,KAAKiB,OAAO;KAAG,CACvBpC,GAAG,CAAC,CAAC,CAACI,MAAMiC,MAAM,GAAM,CAAA;YAAEjC;YAAM,GAAGiC,KAAK;QAAC,CAAA,GACzCC,IAAI,CAAC7C,qBACL8C,KAAK,CAAC,GAAG9B,OACTT,GAAG,CAAC,CAAC,EAAEI,IAAI,EAAE6B,KAAK,EAAEJ,KAAK,EAAE,GAAM,CAAA;YAAEzB;YAAM6B;YAAOO,YAAYhD,SAASqC;QAAO,CAAA;AACjF;AAEA,+FAA+F;AAC/F,0BAA0B;AAC1B,OAAO,eAAeY,YAAY7C,IAAgB,EAAEQ,IAAY,EAAEsC,IAAgE;IAChI,MAAMC,aAAa,MAAM/C,KAAKgB,OAAO,CAAC;IACtC,MAAMgC,aAAc,MAAMD,WAAW9B,GAAG,CAACT;IACzC,IAAIwC,WAAW9C,MAAM,KAAK,GAAG,OAAO,EAAE;IACtC,kGAAkG;IAClG,MAAM+C,SAASnD,aAAakD,YAAY5C,GAAG,CAAC,CAACC;QAC3C,MAAM6C,IAAI,IAAIvB,UAAUtB,IAAIE,MAAM,CAACqB,MAAM,EAAEvB,IAAIE,MAAM,CAACsB,UAAU,EAAExB,IAAIE,MAAM,CAACuB,UAAU;QACvF,IAAIE,OAAO;QACX,IAAK,IAAIb,IAAI,GAAGA,IAAI+B,EAAEhD,MAAM,EAAEiB,IAAKa,QAAQkB,CAAC,CAAC/B,EAAE,GAAG+B,CAAC,CAAC/B,EAAE;QACtD,OAAO;YAAE+B;YAAGlB,MAAMZ,KAAKE,IAAI,CAACU;QAAM;IACpC;IAEA,MAAMjB,OAAO,MAAMf,KAAKgB,OAAO,CAAC;IAChC,MAAMf,OAAQ,MAAMc,KAAKE,GAAG;IAC5B,MAAMM,OAAO,IAAIC;IACjB,KAAK,MAAMnB,OAAOJ,KAAM;QACtB,IAAII,IAAIG,IAAI,KAAKA,QAAQsC,KAAKK,OAAO,CAAC1B,GAAG,CAACpB,IAAIG,IAAI,KAAMsC,KAAKhC,OAAO,IAAI,CAACgC,KAAKhC,OAAO,CAACW,GAAG,CAACpB,IAAIG,IAAI,GAAI;QACtG,MAAM4C,QAAQ,IAAIzB,UAAUtB,IAAIE,MAAM,CAACqB,MAAM,EAAEvB,IAAIE,MAAM,CAACsB,UAAU,EAAExB,IAAIE,MAAM,CAACuB,UAAU;QAC3F,IAAIuB,YAAY;QAChB,IAAK,IAAIlC,IAAI,GAAGA,IAAIiC,MAAMlD,MAAM,EAAEiB,IAAKkC,aAAaD,KAAK,CAACjC,EAAE,GAAGiC,KAAK,CAACjC,EAAE;QACvEkC,YAAYjC,KAAKE,IAAI,CAAC+B;QACtB,KAAK,MAAMC,KAAKL,OAAQ;YACtB,IAAIlB,MAAM;YACV,MAAMwB,MAAMnC,KAAKC,GAAG,CAACiC,EAAEJ,CAAC,CAAChD,MAAM,EAAEkD,MAAMlD,MAAM;YAC7C,IAAK,IAAIiB,IAAI,GAAGA,IAAIoC,KAAKpC,IAAKY,OAAOuB,EAAEJ,CAAC,CAAC/B,EAAE,GAAGiC,KAAK,CAACjC,EAAE;YACtD,MAAMc,QAAQqB,EAAEtB,IAAI,KAAK,KAAKqB,cAAc,IAAI,IAAItB,MAAOuB,CAAAA,EAAEtB,IAAI,GAAGqB,SAAQ;YAC5E,MAAMnB,WAAWX,KAAKY,GAAG,CAAC9B,IAAIG,IAAI;YAClC,IAAI0B,aAAasB,aAAavB,QAAQC,UAAUX,KAAKa,GAAG,CAAC/B,IAAIG,IAAI,EAAEyB;QACrE;IACF;IAEA,OAAO;WAAIV,KAAKiB,OAAO;KAAG,CACvBpC,GAAG,CAAC,CAAC,CAACqD,GAAGxB,MAAM,GAAM,CAAA;YAAEzB,MAAMiD;YAAGxB;QAAM,CAAA,GACtCS,IAAI,CAAC7C,qBACL8C,KAAK,CAAC,GAAGG,KAAKY,CAAC,EACftD,GAAG,CAAC,CAAC,EAAEI,MAAMiD,CAAC,EAAExB,KAAK,EAAE,GAAM,CAAA;YAAEzB,MAAMiD;YAAGb,YAAYhD,SAASqC;QAAO,CAAA;AACzE"}

package/dist/esm/store/turso/connection.js

@@ -3,6 +3,7 @@ import { rewriteInsert } from '../batch.js';
 import { setMeta } from '../shared.js';
 import { BEGIN_WRITE, withTransaction } from '../transaction.js';
 import { CONNECT_OPTS, tursoApi } from './native.js';
+import { rewriteFunctions } from './sql-functions.js';
 // @tursodatabase/database/compat offers a synchronous escape hatch, but it measured only 4-12%
 // faster than this promise client, so this wraps the async client in the same Connection/Statement shape 1:1.
 let TursoStatementWrapper = class TursoStatementWrapper {
@@ -82,7 +83,7 @@ export function createConnection(db) {
             await db.exec(sql);
         },
         async prepare (sql) {
-            return new TursoStatementWrapper(await db.prepare(sql));
+            return new TursoStatementWrapper(await db.prepare(rewriteFunctions(sql)));
         },
         // Folds a plain INSERT into one multi-row VALUES statement (shared rewriteInsert, ../batch.ts):
         // no bind-variable ceiling to chunk against, measured empirically. UPDATE/DELETE keep the per-row loop.
@@ -102,7 +103,7 @@ export function createConnection(db) {
                     return;
                 }
                 // Finalized here because nothing else will: open() hands back a connection the caller
-                // can hold across many batches, and the db.batch() this replaced finalized its own.
+                // can hold across many batches, and nothing else owns this statement's lifetime.
                 const stmt = await db.prepare(sql);
                 try {
                     for (const row of paramRows)await stmt.run(...row);

package/dist/esm/store/turso/connection.js.map

@@ -1 +1 @@
-{"version":3,"sources":["/Users/kevin/Dev/OpenSource/ai/sensemaking/src/store/turso/connection.ts"],"sourcesContent":["import { stat } from 'node:fs/promises';\nimport type { Database } from '@tursodatabase/database';\nimport { rewriteInsert } from '../batch.ts';\nimport { setMeta } from '../shared.ts';\nimport { BEGIN_WRITE, withTransaction } from '../transaction.ts';\nimport type { Connection, RunResult, Statement } from '../types.ts';\nimport { CONNECT_OPTS, tursoApi } from './native.ts';\n\n// The client's own Statement class isn't re-exported by name from '@tursodatabase/database',\n// so its type is derived structurally from Database.prepare()'s return type instead.\ntype TursoStatement = Awaited<ReturnType<Database['prepare']>>;\n\n// @tursodatabase/database/compat offers a synchronous escape hatch, but it measured only 4-12%\n// faster than this promise client, so this wraps the async client in the same Connection/Statement shape 1:1.\nclass TursoStatementWrapper implements Statement {\n  private stmt: TursoStatement;\n\n  constructor(stmt: TursoStatement) {\n    this.stmt = stmt;\n  }\n\n  async run(...params: unknown[]): Promise<RunResult> {\n    return this.stmt.run(...params);\n  }\n\n  async get(...params: unknown[]): Promise<unknown> {\n    return this.stmt.get(...params);\n  }\n\n  async all(...params: unknown[]): Promise<unknown[]> {\n    return this.stmt.all(...params);\n  }\n\n  async *iterate(...params: unknown[]): AsyncIterable<unknown> {\n    yield* this.stmt.iterate(...params);\n  }\n\n  columns(): Array<{ name: string }> {\n    return this.stmt.columns();\n  }\n\n  setReadBigInts(enabled: boolean): void {\n    this.stmt.safeIntegers(enabled);\n  }\n}\n\n// This client leaves the WAL behind for the next opener, where node:sqlite checkpoints on the last\n// close, so a tree reconciled over and over grows one without bound. Best-effort: close must not throw.\nexport async function checkpointWal(db: Database): Promise<void> {\n  try {\n    await db.exec('PRAGMA wal_checkpoint(TRUNCATE)');\n  } catch (err) {\n    console.error(`sense: turso WAL checkpoint failed, the -wal file will keep growing until one succeeds: ${(err as Error).message}`);\n  }\n}\n\n// The main cache file's path, or null when unresolvable. The store holds a Database and\n// Connection, not a path (PLAN 3.52), so the path is read from the database itself.\nexport async function cacheFilePath(conn: Connection): Promise<string | null> {\n  const rows = (await (await conn.prepare('PRAGMA database_list')).all()) as Array<{ name: string; file: string }>;\n  return rows.find((r) => r.name === 'main')?.file || null;\n}\n\nexport async function fileSize(path: string): Promise<number | null> {\n  try {\n    return (await stat(path)).size;\n  } catch {\n    return null;\n  }\n}\n\n// Reclaims turso#8170's FTS space amplification (PLAN 3.41), on a throwaway connection after the\n// store's own has closed: `vacuum` doubles incremental reconcile cost merely by being enabled (3.54).\nexport async function reclaimSpace(path: string): Promise<void> {\n  try {\n    const turso = await tursoApi();\n    const db = await turso.connect(path, { ...CONNECT_OPTS, experimental: [...CONNECT_OPTS.experimental, 'vacuum'] });\n    try {\n      await db.exec('VACUUM');\n      const size = await fileSize(path);\n      // Recorded here, not by the caller: this connection is the only one still open on the file.\n      if (size !== null) await setMeta(createConnection(db), 'compact_size', String(size));\n      await checkpointWal(db);\n    } finally {\n      await db.close();\n    }\n  } catch (err) {\n    console.error(`sense: turso VACUUM failed, the cache will keep the space until one succeeds: ${(err as Error).message}`);\n  }\n}\n\nexport function createConnection(db: Database): Connection {\n  const conn: Connection = {\n    async exec(sql: string): Promise<void> {\n      await db.exec(sql);\n    },\n    async prepare(sql: string): Promise<Statement> {\n      return new TursoStatementWrapper(await db.prepare(sql));\n    },\n    // Folds a plain INSERT into one multi-row VALUES statement (shared rewriteInsert, ../batch.ts):\n    // no bind-variable ceiling to chunk against, measured empirically. UPDATE/DELETE keep the per-row loop.\n    async runBatch(sql: string, paramRows: unknown[][]): Promise<void> {\n      if (paramRows.length === 0) return;\n      await withTransaction(\n        conn,\n        async () => {\n          const rewritten = rewriteInsert(sql, paramRows.length);\n          if (rewritten) {\n            const stmt = await db.prepare(rewritten.sql);\n            try {\n              // One flat array, not spread: spreading tens of thousands of args hits a JS call-stack\n              // limit well before turso enforces any variable-count ceiling (measured; see PLAN.md).\n              await stmt.run(paramRows.flat());\n            } finally {\n              await stmt.close();\n            }\n            return;\n          }\n          // Finalized here because nothing else will: open() hands back a connection the caller\n          // can hold across many batches, and the db.batch() this replaced finalized its own.\n          const stmt = await db.prepare(sql);\n          try {\n            for (const row of paramRows) await stmt.run(...row);\n          } finally {\n            await stmt.close();\n          }\n        },\n        BEGIN_WRITE\n      );\n    },\n  };\n  return conn;\n}\n"],"names":["stat","rewriteInsert","setMeta","BEGIN_WRITE","withTransaction","CONNECT_OPTS","tursoApi","TursoStatementWrapper","run","params","stmt","get","all","iterate","columns","setReadBigInts","enabled","safeIntegers","checkpointWal","db","exec","err","console","error","message","cacheFilePath","conn","rows","prepare","find","r","name","file","fileSize","path","size","reclaimSpace","turso","connect","experimental","createConnection","String","close","sql","runBatch","paramRows","length","rewritten","flat","row"],"mappings":"AAAA,SAASA,IAAI,QAAQ,mBAAmB;AAExC,SAASC,aAAa,QAAQ,cAAc;AAC5C,SAASC,OAAO,QAAQ,eAAe;AACvC,SAASC,WAAW,EAAEC,eAAe,QAAQ,oBAAoB;AAEjE,SAASC,YAAY,EAAEC,QAAQ,QAAQ,cAAc;AAMrD,+FAA+F;AAC/F,8GAA8G;AAC9G,IAAA,AAAMC,wBAAN,MAAMA;IAOJ,MAAMC,IAAI,GAAGC,MAAiB,EAAsB;QAClD,OAAO,IAAI,CAACC,IAAI,CAACF,GAAG,IAAIC;IAC1B;IAEA,MAAME,IAAI,GAAGF,MAAiB,EAAoB;QAChD,OAAO,IAAI,CAACC,IAAI,CAACC,GAAG,IAAIF;IAC1B;IAEA,MAAMG,IAAI,GAAGH,MAAiB,EAAsB;QAClD,OAAO,IAAI,CAACC,IAAI,CAACE,GAAG,IAAIH;IAC1B;IAEA,OAAOI,QAAQ,GAAGJ,MAAiB,EAA0B;QAC3D,OAAO,IAAI,CAACC,IAAI,CAACG,OAAO,IAAIJ;IAC9B;IAEAK,UAAmC;QACjC,OAAO,IAAI,CAACJ,IAAI,CAACI,OAAO;IAC1B;IAEAC,eAAeC,OAAgB,EAAQ;QACrC,IAAI,CAACN,IAAI,CAACO,YAAY,CAACD;IACzB;IA1BA,YAAYN,IAAoB,CAAE;QAChC,IAAI,CAACA,IAAI,GAAGA;IACd;AAyBF;AAEA,mGAAmG;AACnG,wGAAwG;AACxG,OAAO,eAAeQ,cAAcC,EAAY;IAC9C,IAAI;QACF,MAAMA,GAAGC,IAAI,CAAC;IAChB,EAAE,OAAOC,KAAK;QACZC,QAAQC,KAAK,CAAC,CAAC,wFAAwF,EAAE,AAACF,IAAcG,OAAO,EAAE;IACnI;AACF;AAEA,wFAAwF;AACxF,oFAAoF;AACpF,OAAO,eAAeC,cAAcC,IAAgB;QAE3CC;IADP,MAAMA,OAAQ,MAAM,AAAC,CAAA,MAAMD,KAAKE,OAAO,CAAC,uBAAsB,EAAGhB,GAAG;IACpE,OAAOe,EAAAA,aAAAA,KAAKE,IAAI,CAAC,CAACC,IAAMA,EAAEC,IAAI,KAAK,qBAA5BJ,iCAAAA,WAAqCK,IAAI,KAAI;AACtD;AAEA,OAAO,eAAeC,SAASC,IAAY;IACzC,IAAI;QACF,OAAO,AAAC,CAAA,MAAMlC,KAAKkC,KAAI,EAAGC,IAAI;IAChC,EAAE,OAAM;QACN,OAAO;IACT;AACF;AAEA,iGAAiG;AACjG,sGAAsG;AACtG,OAAO,eAAeC,aAAaF,IAAY;IAC7C,IAAI;QACF,MAAMG,QAAQ,MAAM/B;QACpB,MAAMa,KAAK,MAAMkB,MAAMC,OAAO,CAACJ,MAAM;YAAE,GAAG7B,YAAY;YAAEkC,cAAc;mBAAIlC,aAAakC,YAAY;gBAAE;aAAS;QAAC;QAC/G,IAAI;YACF,MAAMpB,GAAGC,IAAI,CAAC;YACd,MAAMe,OAAO,MAAMF,SAASC;YAC5B,4FAA4F;YAC5F,IAAIC,SAAS,MAAM,MAAMjC,QAAQsC,iBAAiBrB,KAAK,gBAAgBsB,OAAON;YAC9E,MAAMjB,cAAcC;QACtB,SAAU;YACR,MAAMA,GAAGuB,KAAK;QAChB;IACF,EAAE,OAAOrB,KAAK;QACZC,QAAQC,KAAK,CAAC,CAAC,8EAA8E,EAAE,AAACF,IAAcG,OAAO,EAAE;IACzH;AACF;AAEA,OAAO,SAASgB,iBAAiBrB,EAAY;IAC3C,MAAMO,OAAmB;QACvB,MAAMN,MAAKuB,GAAW;YACpB,MAAMxB,GAAGC,IAAI,CAACuB;QAChB;QACA,MAAMf,SAAQe,GAAW;YACvB,OAAO,IAAIpC,sBAAsB,MAAMY,GAAGS,OAAO,CAACe;QACpD;QACA,gGAAgG;QAChG,wGAAwG;QACxG,MAAMC,UAASD,GAAW,EAAEE,SAAsB;YAChD,IAAIA,UAAUC,MAAM,KAAK,GAAG;YAC5B,MAAM1C,gBACJsB,MACA;gBACE,MAAMqB,YAAY9C,cAAc0C,KAAKE,UAAUC,MAAM;gBACrD,IAAIC,WAAW;oBACb,MAAMrC,OAAO,MAAMS,GAAGS,OAAO,CAACmB,UAAUJ,GAAG;oBAC3C,IAAI;wBACF,uFAAuF;wBACvF,uFAAuF;wBACvF,MAAMjC,KAAKF,GAAG,CAACqC,UAAUG,IAAI;oBAC/B,SAAU;wBACR,MAAMtC,KAAKgC,KAAK;oBAClB;oBACA;gBACF;gBACA,sFAAsF;gBACtF,oFAAoF;gBACpF,MAAMhC,OAAO,MAAMS,GAAGS,OAAO,CAACe;gBAC9B,IAAI;oBACF,KAAK,MAAMM,OAAOJ,UAAW,MAAMnC,KAAKF,GAAG,IAAIyC;gBACjD,SAAU;oBACR,MAAMvC,KAAKgC,KAAK;gBAClB;YACF,GACAvC;QAEJ;IACF;IACA,OAAOuB;AACT"}
+{"version":3,"sources":["/Users/kevin/Dev/OpenSource/ai/sensemaking/src/store/turso/connection.ts"],"sourcesContent":["import { stat } from 'node:fs/promises';\nimport type { Database } from '@tursodatabase/database';\nimport { rewriteInsert } from '../batch.ts';\nimport { setMeta } from '../shared.ts';\nimport { BEGIN_WRITE, withTransaction } from '../transaction.ts';\nimport type { Connection, RunResult, Statement } from '../types.ts';\nimport { CONNECT_OPTS, tursoApi } from './native.ts';\nimport { rewriteFunctions } from './sql-functions.ts';\n\n// The client's own Statement class isn't re-exported by name from '@tursodatabase/database',\n// so its type is derived structurally from Database.prepare()'s return type instead.\ntype TursoStatement = Awaited<ReturnType<Database['prepare']>>;\n\n// @tursodatabase/database/compat offers a synchronous escape hatch, but it measured only 4-12%\n// faster than this promise client, so this wraps the async client in the same Connection/Statement shape 1:1.\nclass TursoStatementWrapper implements Statement {\n  private stmt: TursoStatement;\n\n  constructor(stmt: TursoStatement) {\n    this.stmt = stmt;\n  }\n\n  async run(...params: unknown[]): Promise<RunResult> {\n    return this.stmt.run(...params);\n  }\n\n  async get(...params: unknown[]): Promise<unknown> {\n    return this.stmt.get(...params);\n  }\n\n  async all(...params: unknown[]): Promise<unknown[]> {\n    return this.stmt.all(...params);\n  }\n\n  async *iterate(...params: unknown[]): AsyncIterable<unknown> {\n    yield* this.stmt.iterate(...params);\n  }\n\n  columns(): Array<{ name: string }> {\n    return this.stmt.columns();\n  }\n\n  setReadBigInts(enabled: boolean): void {\n    this.stmt.safeIntegers(enabled);\n  }\n}\n\n// This client leaves the WAL behind for the next opener, where node:sqlite checkpoints on the last\n// close, so a tree reconciled over and over grows one without bound. Best-effort: close must not throw.\nexport async function checkpointWal(db: Database): Promise<void> {\n  try {\n    await db.exec('PRAGMA wal_checkpoint(TRUNCATE)');\n  } catch (err) {\n    console.error(`sense: turso WAL checkpoint failed, the -wal file will keep growing until one succeeds: ${(err as Error).message}`);\n  }\n}\n\n// The main cache file's path, or null when unresolvable. The store holds a Database and\n// Connection, not a path (PLAN 3.52), so the path is read from the database itself.\nexport async function cacheFilePath(conn: Connection): Promise<string | null> {\n  const rows = (await (await conn.prepare('PRAGMA database_list')).all()) as Array<{ name: string; file: string }>;\n  return rows.find((r) => r.name === 'main')?.file || null;\n}\n\nexport async function fileSize(path: string): Promise<number | null> {\n  try {\n    return (await stat(path)).size;\n  } catch {\n    return null;\n  }\n}\n\n// Reclaims turso#8170's FTS space amplification (PLAN 3.41), on a throwaway connection after the\n// store's own has closed: `vacuum` doubles incremental reconcile cost merely by being enabled (3.54).\nexport async function reclaimSpace(path: string): Promise<void> {\n  try {\n    const turso = await tursoApi();\n    const db = await turso.connect(path, { ...CONNECT_OPTS, experimental: [...CONNECT_OPTS.experimental, 'vacuum'] });\n    try {\n      await db.exec('VACUUM');\n      const size = await fileSize(path);\n      // Recorded here, not by the caller: this connection is the only one still open on the file.\n      if (size !== null) await setMeta(createConnection(db), 'compact_size', String(size));\n      await checkpointWal(db);\n    } finally {\n      await db.close();\n    }\n  } catch (err) {\n    console.error(`sense: turso VACUUM failed, the cache will keep the space until one succeeds: ${(err as Error).message}`);\n  }\n}\n\nexport function createConnection(db: Database): Connection {\n  const conn: Connection = {\n    async exec(sql: string): Promise<void> {\n      await db.exec(sql);\n    },\n    async prepare(sql: string): Promise<Statement> {\n      return new TursoStatementWrapper(await db.prepare(rewriteFunctions(sql)));\n    },\n    // Folds a plain INSERT into one multi-row VALUES statement (shared rewriteInsert, ../batch.ts):\n    // no bind-variable ceiling to chunk against, measured empirically. UPDATE/DELETE keep the per-row loop.\n    async runBatch(sql: string, paramRows: unknown[][]): Promise<void> {\n      if (paramRows.length === 0) return;\n      await withTransaction(\n        conn,\n        async () => {\n          const rewritten = rewriteInsert(sql, paramRows.length);\n          if (rewritten) {\n            const stmt = await db.prepare(rewritten.sql);\n            try {\n              // One flat array, not spread: spreading tens of thousands of args hits a JS call-stack\n              // limit well before turso enforces any variable-count ceiling (measured; see PLAN.md).\n              await stmt.run(paramRows.flat());\n            } finally {\n              await stmt.close();\n            }\n            return;\n          }\n          // Finalized here because nothing else will: open() hands back a connection the caller\n          // can hold across many batches, and nothing else owns this statement's lifetime.\n          const stmt = await db.prepare(sql);\n          try {\n            for (const row of paramRows) await stmt.run(...row);\n          } finally {\n            await stmt.close();\n          }\n        },\n        BEGIN_WRITE\n      );\n    },\n  };\n  return conn;\n}\n"],"names":["stat","rewriteInsert","setMeta","BEGIN_WRITE","withTransaction","CONNECT_OPTS","tursoApi","rewriteFunctions","TursoStatementWrapper","run","params","stmt","get","all","iterate","columns","setReadBigInts","enabled","safeIntegers","checkpointWal","db","exec","err","console","error","message","cacheFilePath","conn","rows","prepare","find","r","name","file","fileSize","path","size","reclaimSpace","turso","connect","experimental","createConnection","String","close","sql","runBatch","paramRows","length","rewritten","flat","row"],"mappings":"AAAA,SAASA,IAAI,QAAQ,mBAAmB;AAExC,SAASC,aAAa,QAAQ,cAAc;AAC5C,SAASC,OAAO,QAAQ,eAAe;AACvC,SAASC,WAAW,EAAEC,eAAe,QAAQ,oBAAoB;AAEjE,SAASC,YAAY,EAAEC,QAAQ,QAAQ,cAAc;AACrD,SAASC,gBAAgB,QAAQ,qBAAqB;AAMtD,+FAA+F;AAC/F,8GAA8G;AAC9G,IAAA,AAAMC,wBAAN,MAAMA;IAOJ,MAAMC,IAAI,GAAGC,MAAiB,EAAsB;QAClD,OAAO,IAAI,CAACC,IAAI,CAACF,GAAG,IAAIC;IAC1B;IAEA,MAAME,IAAI,GAAGF,MAAiB,EAAoB;QAChD,OAAO,IAAI,CAACC,IAAI,CAACC,GAAG,IAAIF;IAC1B;IAEA,MAAMG,IAAI,GAAGH,MAAiB,EAAsB;QAClD,OAAO,IAAI,CAACC,IAAI,CAACE,GAAG,IAAIH;IAC1B;IAEA,OAAOI,QAAQ,GAAGJ,MAAiB,EAA0B;QAC3D,OAAO,IAAI,CAACC,IAAI,CAACG,OAAO,IAAIJ;IAC9B;IAEAK,UAAmC;QACjC,OAAO,IAAI,CAACJ,IAAI,CAACI,OAAO;IAC1B;IAEAC,eAAeC,OAAgB,EAAQ;QACrC,IAAI,CAACN,IAAI,CAACO,YAAY,CAACD;IACzB;IA1BA,YAAYN,IAAoB,CAAE;QAChC,IAAI,CAACA,IAAI,GAAGA;IACd;AAyBF;AAEA,mGAAmG;AACnG,wGAAwG;AACxG,OAAO,eAAeQ,cAAcC,EAAY;IAC9C,IAAI;QACF,MAAMA,GAAGC,IAAI,CAAC;IAChB,EAAE,OAAOC,KAAK;QACZC,QAAQC,KAAK,CAAC,CAAC,wFAAwF,EAAE,AAACF,IAAcG,OAAO,EAAE;IACnI;AACF;AAEA,wFAAwF;AACxF,oFAAoF;AACpF,OAAO,eAAeC,cAAcC,IAAgB;QAE3CC;IADP,MAAMA,OAAQ,MAAM,AAAC,CAAA,MAAMD,KAAKE,OAAO,CAAC,uBAAsB,EAAGhB,GAAG;IACpE,OAAOe,EAAAA,aAAAA,KAAKE,IAAI,CAAC,CAACC,IAAMA,EAAEC,IAAI,KAAK,qBAA5BJ,iCAAAA,WAAqCK,IAAI,KAAI;AACtD;AAEA,OAAO,eAAeC,SAASC,IAAY;IACzC,IAAI;QACF,OAAO,AAAC,CAAA,MAAMnC,KAAKmC,KAAI,EAAGC,IAAI;IAChC,EAAE,OAAM;QACN,OAAO;IACT;AACF;AAEA,iGAAiG;AACjG,sGAAsG;AACtG,OAAO,eAAeC,aAAaF,IAAY;IAC7C,IAAI;QACF,MAAMG,QAAQ,MAAMhC;QACpB,MAAMc,KAAK,MAAMkB,MAAMC,OAAO,CAACJ,MAAM;YAAE,GAAG9B,YAAY;YAAEmC,cAAc;mBAAInC,aAAamC,YAAY;gBAAE;aAAS;QAAC;QAC/G,IAAI;YACF,MAAMpB,GAAGC,IAAI,CAAC;YACd,MAAMe,OAAO,MAAMF,SAASC;YAC5B,4FAA4F;YAC5F,IAAIC,SAAS,MAAM,MAAMlC,QAAQuC,iBAAiBrB,KAAK,gBAAgBsB,OAAON;YAC9E,MAAMjB,cAAcC;QACtB,SAAU;YACR,MAAMA,GAAGuB,KAAK;QAChB;IACF,EAAE,OAAOrB,KAAK;QACZC,QAAQC,KAAK,CAAC,CAAC,8EAA8E,EAAE,AAACF,IAAcG,OAAO,EAAE;IACzH;AACF;AAEA,OAAO,SAASgB,iBAAiBrB,EAAY;IAC3C,MAAMO,OAAmB;QACvB,MAAMN,MAAKuB,GAAW;YACpB,MAAMxB,GAAGC,IAAI,CAACuB;QAChB;QACA,MAAMf,SAAQe,GAAW;YACvB,OAAO,IAAIpC,sBAAsB,MAAMY,GAAGS,OAAO,CAACtB,iBAAiBqC;QACrE;QACA,gGAAgG;QAChG,wGAAwG;QACxG,MAAMC,UAASD,GAAW,EAAEE,SAAsB;YAChD,IAAIA,UAAUC,MAAM,KAAK,GAAG;YAC5B,MAAM3C,gBACJuB,MACA;gBACE,MAAMqB,YAAY/C,cAAc2C,KAAKE,UAAUC,MAAM;gBACrD,IAAIC,WAAW;oBACb,MAAMrC,OAAO,MAAMS,GAAGS,OAAO,CAACmB,UAAUJ,GAAG;oBAC3C,IAAI;wBACF,uFAAuF;wBACvF,uFAAuF;wBACvF,MAAMjC,KAAKF,GAAG,CAACqC,UAAUG,IAAI;oBAC/B,SAAU;wBACR,MAAMtC,KAAKgC,KAAK;oBAClB;oBACA;gBACF;gBACA,sFAAsF;gBACtF,iFAAiF;gBACjF,MAAMhC,OAAO,MAAMS,GAAGS,OAAO,CAACe;gBAC9B,IAAI;oBACF,KAAK,MAAMM,OAAOJ,UAAW,MAAMnC,KAAKF,GAAG,IAAIyC;gBACjD,SAAU;oBACR,MAAMvC,KAAKgC,KAAK;gBAClB;YACF,GACAxC;QAEJ;IACF;IACA,OAAOwB;AACT"}

package/dist/esm/store/turso/lexical-text.d.ts

@@ -0,0 +1 @@
+export declare function stemFolded(text: string): string;

package/dist/esm/store/turso/lexical-text.js

@@ -0,0 +1,12 @@
+import { stemmer } from 'stemmer';
+import { foldForSearch, searchTokens } from '../../text/segment.js';
+export function stemFolded(text) {
+    let out = '';
+    let end = 0;
+    for (const token of searchTokens(text)){
+        out += text.slice(end, token.start).replace(/[\u0027\u2019]/gu, ' ');
+        out += token.unspaced ? token.text : stemmer(foldForSearch(token.text));
+        end = token.end;
+    }
+    return out + text.slice(end).replace(/[\u0027\u2019]/gu, ' ');
+}

package/dist/esm/store/turso/lexical-text.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["/Users/kevin/Dev/OpenSource/ai/sensemaking/src/store/turso/lexical-text.ts"],"sourcesContent":["import { stemmer } from 'stemmer';\nimport { foldForSearch, searchTokens } from '../../text/segment.ts';\n\nexport function stemFolded(text: string): string {\n  let out = '';\n  let end = 0;\n  for (const token of searchTokens(text)) {\n    out += text.slice(end, token.start).replace(/[\\u0027\\u2019]/gu, ' ');\n    out += token.unspaced ? token.text : stemmer(foldForSearch(token.text));\n    end = token.end;\n  }\n  return out + text.slice(end).replace(/[\\u0027\\u2019]/gu, ' ');\n}\n"],"names":["stemmer","foldForSearch","searchTokens","stemFolded","text","out","end","token","slice","start","replace","unspaced"],"mappings":"AAAA,SAASA,OAAO,QAAQ,UAAU;AAClC,SAASC,aAAa,EAAEC,YAAY,QAAQ,wBAAwB;AAEpE,OAAO,SAASC,WAAWC,IAAY;IACrC,IAAIC,MAAM;IACV,IAAIC,MAAM;IACV,KAAK,MAAMC,SAASL,aAAaE,MAAO;QACtCC,OAAOD,KAAKI,KAAK,CAACF,KAAKC,MAAME,KAAK,EAAEC,OAAO,CAAC,oBAAoB;QAChEL,OAAOE,MAAMI,QAAQ,GAAGJ,MAAMH,IAAI,GAAGJ,QAAQC,cAAcM,MAAMH,IAAI;QACrEE,MAAMC,MAAMD,GAAG;IACjB;IACA,OAAOD,MAAMD,KAAKI,KAAK,CAACF,KAAKI,OAAO,CAAC,oBAAoB;AAC3D"}

package/dist/esm/store/turso/lexical.js

@@ -1,17 +1,23 @@
 // T1: Tantivy FTS via fts_match/fts_score on the default-tokenizer index for bare words and
 // quoted phrases, plus a second ngram-tokenized index over "_ngram" sidecars for unspaced-script runs.
 import { SenseError } from '../../errors.js';
-import { hasUnspacedRun } from '../../text/segment.js';
+import { matchesSearchPhrase, searchTokens } from '../../text/segment.js';
+import { stemFolded } from './lexical-text.js';
 const FIELDS = [
-    'title',
-    'summary',
-    'text'
+    'title_stem',
+    'summary_stem',
+    'text_stem'
 ];
 const NGRAM_FIELDS = [
     'title_ngram',
     'summary_ngram',
     'text_ngram'
 ];
+const AUTHORED_FIELDS = [
+    'title',
+    'summary',
+    'text'
+];
 // FTS5 operator syntax a bare query would otherwise treat as literal text (PRINCIPLES:
 // no-silent-modes). `^` is rejected either way: boost to Tantivy, initial-token match to FTS5.
 const FTS5_OPERATORS = [
@@ -53,22 +59,30 @@ function splitTerms(terms) {
     const words = [];
     const phrases = [];
     const unspaced = [];
+    let emptyPhrase = false;
     const withoutPhrases = terms.replace(/"([^"]*)"/g, (_m, inner)=>{
         const phrase = inner.trim();
-        if (phrase.length === 0) return ' ';
-        if (hasUnspacedRun(phrase)) unspaced.push(phrase);
-        else phrases.push(phrase);
+        const tokens = searchTokens(phrase);
+        if (tokens.length === 0) {
+            emptyPhrase = true;
+            return ' ';
+        }
+        unspaced.push(...tokens.filter((token)=>token.unspaced).map((token)=>token.text));
+        phrases.push(tokens);
         return ' ';
     });
     for (const tok of withoutPhrases.split(/\s+/)){
         if (tok.length === 0) continue;
-        if (hasUnspacedRun(tok)) unspaced.push(tok);
-        else words.push(tok);
+        for (const token of searchTokens(tok)){
+            if (token.unspaced) unspaced.push(token.text);
+            else words.push(token.text);
+        }
     }
     return {
         words,
         phrases,
-        unspaced
+        unspaced,
+        emptyPhrase
     };
 }
 // fts_match/fts_score's query argument must be a SQL literal: bound as `?`, the row set stays
@@ -79,9 +93,16 @@ function escapeFtsLiteral(query) {
 // Terms are quoted ("O'Brien's" is a parse error bare) and AND-joined: Tantivy's default for
 // bare terms is disjunctive, so space-joining would loosen "apple banana" into "apple OR banana".
 function buildQueries(words, phrases, unspaced) {
+    const phraseParts = phrases.flatMap((phrase)=>{
+        const latin = phrase.filter((token)=>!token.unspaced).map((token)=>stemFolded(token.text));
+        if (latin.length === 0) return [];
+        return phrase.some((token)=>token.unspaced) ? latin : [
+            latin.join(' ')
+        ];
+    });
     const defaultParts = [
-        ...words,
-        ...phrases
+        ...words.map(stemFolded),
+        ...phraseParts
     ].map((t)=>`"${t}"`);
     const unspacedParts = unspaced.map((t)=>`"${t}"`);
     return {
@@ -98,31 +119,45 @@ function ftsBranch(cols, query, opts) {
     FROM content ${opts.whereJoin} WHERE fts_match(${colList}, '${lit}') ${opts.whereCond} ${opts.scopeCond}`;
 }
 // Ranked query, scoped by the caller-built SQL fragments (same shape sqlite's/duckdb's
-// queryLexical take). `hit` is always NULL: fts_highlight returns the full column text, not a bounded snippet, so every row goes through the caller's JS excerpt fallback (commands/search.ts).
+// queryLexical take). `snippets` is always NULL: fts_highlight returns the full column text, not a bounded snippet, so every row goes through the caller's JS snippet fallback (commands/search.ts).
 export async function queryLexical(conn, terms, opts) {
     const unsupported = unsupportedOperator(terms);
     if (unsupported !== null) {
         throw new SenseError('STORE_CAPABILITY_MISSING', `store "turso" does not implement FTS5's ${unsupported.label} ("${unsupported.token}") in this build; rephrase "${terms.trim()}" without it, or set "store" to "sqlite" in this tree's config to search it as written`);
     }
-    const { words, phrases, unspaced } = splitTerms(terms);
+    const { words, phrases, unspaced, emptyPhrase } = splitTerms(terms);
+    if (emptyPhrase) return [];
     const { defaultQuery, ngramQuery } = buildQueries(words, phrases, unspaced);
     if (defaultQuery === '' && ngramQuery === '') return [];
     const branches = [];
     if (defaultQuery !== '') branches.push(ftsBranch(FIELDS, defaultQuery, opts));
     if (ngramQuery !== '') branches.push(ftsBranch(NGRAM_FIELDS, ngramQuery, opts));
     // HAVING COUNT(*) = branches.length is the AND across indexes; with one branch it is a no-op,
-    // `path` being content's primary key. fts_score is higher-is-better BM25, so DESC.
-    const sql = `SELECT path, NULL AS hit FROM (
-    SELECT path, SUM(score) AS score FROM (
+    // `path` being content's primary key. fts_score is higher-is-better BM25, so DESC. Phrase
+    // candidates carry authored fields through the join below so the shared verifier can reject
+    // cross-field, reordered, and non-adjacent matches before applying the caller's limit.
+    const ranked = `SELECT path, SUM(score) AS score FROM (
       ${branches.join(' UNION ALL ')}
-    ) parts GROUP BY path HAVING COUNT(*) = ${branches.length}
-  ) sq ORDER BY score DESC, path LIMIT ?`;
+    ) parts GROUP BY path HAVING COUNT(*) = ${branches.length}`;
+    const phraseSelect = phrases.length > 0 ? ', content.title, content.summary, content.text' : '';
+    const phraseJoin = phrases.length > 0 ? ' JOIN content ON content.path = sq.path' : '';
+    const sql = `SELECT sq.path, sq.score${phraseSelect} FROM (
+    ${ranked}
+  ) sq${phraseJoin} ORDER BY sq.score DESC, sq.path${phrases.length > 0 ? '' : ' LIMIT ?'}`;
     const stmt = await conn.prepare(sql);
-    const rows = await stmt.all(opts.limit);
+    const rows = await stmt.all(...phrases.length > 0 ? [] : [
+        opts.limit
+    ]);
     // A concurrent FTS read during an open write transaction can yield a {path: null} row. Raised,
     // not filtered: filtering returns a silently short result (PRINCIPLES: no-silent-modes).
     if (rows.some((r)=>r.path === null)) {
         throw new SenseError('LEXICAL_NULL_PATH', 'store "turso" returned a search hit with no path (a known engine anomaly under concurrent FTS reads); retry the query');
     }
-    return rows;
+    const matches = phrases.length === 0 ? rows : rows.filter((row)=>phrases.every((phrase)=>AUTHORED_FIELDS.some((field)=>{
+                var _row_field;
+                return matchesSearchPhrase((_row_field = row[field]) !== null && _row_field !== void 0 ? _row_field : '', phrase);
+            })));
+    return matches.slice(0, opts.limit).map(({ path })=>({
+            path
+        }));
 }

package/dist/esm/store/turso/lexical.js.map

@@ -1 +1 @@
-{"version":3,"sources":["/Users/kevin/Dev/OpenSource/ai/sensemaking/src/store/turso/lexical.ts"],"sourcesContent":["// T1: Tantivy FTS via fts_match/fts_score on the default-tokenizer index for bare words and\n// quoted phrases, plus a second ngram-tokenized index over \"_ngram\" sidecars for unspaced-script runs.\nimport { SenseError } from '../../errors.ts';\nimport { hasUnspacedRun } from '../../text/segment.ts';\nimport type { Connection, LexicalHit, LexicalQueryOptions } from '../types.ts';\n\nconst FIELDS = ['title', 'summary', 'text'] as const;\nconst NGRAM_FIELDS = ['title_ngram', 'summary_ngram', 'text_ngram'] as const;\n\n// FTS5 operator syntax a bare query would otherwise treat as literal text (PRINCIPLES:\n// no-silent-modes). `^` is rejected either way: boost to Tantivy, initial-token match to FTS5.\nconst FTS5_OPERATORS: Array<{ label: string; re: RegExp }> = [\n  { label: 'prefix query', re: /[\\p{L}\\p{N}_]+\\*(?=\\s|$)/u },\n  { label: 'boolean operator', re: /(?:^|\\s)(?:AND|OR|NOT)(?=\\s|$)/ },\n  { label: 'NEAR operator', re: /(?:^|\\s)NEAR\\b/ },\n  { label: 'boost/initial-token operator', re: /\\S*\\^\\S*/ },\n  { label: 'column filter', re: /(?:^|\\s)[\\p{L}_]\\w*\\s*:/u },\n];\n\nfunction unsupportedOperator(terms: string): { label: string; token: string } | null {\n  const withoutPhrases = terms.replace(/\"[^\"]*\"/g, ' ');\n  for (const { label, re } of FTS5_OPERATORS) {\n    const m = withoutPhrases.match(re);\n    if (m) return { label, token: m[0].trim() };\n  }\n  return null;\n}\n\n// A run whose script marks no word boundaries indexes as one opaque token under every tokenizer\n// but ngram, so such runs -- bare or quoted -- go to the ngram sidecar index instead.\nfunction splitTerms(terms: string): { words: string[]; phrases: string[]; unspaced: string[] } {\n  const words: string[] = [];\n  const phrases: string[] = [];\n  const unspaced: string[] = [];\n  const withoutPhrases = terms.replace(/\"([^\"]*)\"/g, (_m, inner: string) => {\n    const phrase = inner.trim();\n    if (phrase.length === 0) return ' ';\n    if (hasUnspacedRun(phrase)) unspaced.push(phrase);\n    else phrases.push(phrase);\n    return ' ';\n  });\n  for (const tok of withoutPhrases.split(/\\s+/)) {\n    if (tok.length === 0) continue;\n    if (hasUnspacedRun(tok)) unspaced.push(tok);\n    else words.push(tok);\n  }\n  return { words, phrases, unspaced };\n}\n\n// fts_match/fts_score's query argument must be a SQL literal: bound as `?`, the row set stays\n// correct but fts_score silently returns 0 for every row (PRINCIPLES: no-silent-modes).\nfunction escapeFtsLiteral(query: string): string {\n  return query.replace(/'/g, \"''\");\n}\n\n// Terms are quoted (\"O'Brien's\" is a parse error bare) and AND-joined: Tantivy's default for\n// bare terms is disjunctive, so space-joining would loosen \"apple banana\" into \"apple OR banana\".\nfunction buildQueries(words: string[], phrases: string[], unspaced: string[]): { defaultQuery: string; ngramQuery: string } {\n  const defaultParts = [...words, ...phrases].map((t) => `\"${t}\"`);\n  const unspacedParts = unspaced.map((t) => `\"${t}\"`);\n  return { defaultQuery: defaultParts.join(' AND '), ngramQuery: unspacedParts.join(' AND ') };\n}\n\n// fts_score() is real only as a SELECT's bare projected expression, and only for the index that\n// SELECT's fts_match() chose; every other form silently returns 0. Hence one SELECT per index.\nfunction ftsBranch(cols: readonly string[], query: string, opts: LexicalQueryOptions): string {\n  const colList = cols.map((c) => `content.${c}`).join(', ');\n  const lit = escapeFtsLiteral(query);\n  return `SELECT content.\"path\" AS path, fts_score(${colList}, '${lit}') AS score\n    FROM content ${opts.whereJoin} WHERE fts_match(${colList}, '${lit}') ${opts.whereCond} ${opts.scopeCond}`;\n}\n\n// Ranked query, scoped by the caller-built SQL fragments (same shape sqlite's/duckdb's\n// queryLexical take). `hit` is always NULL: fts_highlight returns the full column text, not a bounded snippet, so every row goes through the caller's JS excerpt fallback (commands/search.ts).\nexport async function queryLexical(conn: Connection, terms: string, opts: LexicalQueryOptions): Promise<LexicalHit[]> {\n  const unsupported = unsupportedOperator(terms);\n  if (unsupported !== null) {\n    throw new SenseError('STORE_CAPABILITY_MISSING', `store \"turso\" does not implement FTS5's ${unsupported.label} (\"${unsupported.token}\") in this build; rephrase \"${terms.trim()}\" without it, or set \"store\" to \"sqlite\" in this tree's config to search it as written`);\n  }\n  const { words, phrases, unspaced } = splitTerms(terms);\n  const { defaultQuery, ngramQuery } = buildQueries(words, phrases, unspaced);\n  if (defaultQuery === '' && ngramQuery === '') return [];\n\n  const branches: string[] = [];\n  if (defaultQuery !== '') branches.push(ftsBranch(FIELDS, defaultQuery, opts));\n  if (ngramQuery !== '') branches.push(ftsBranch(NGRAM_FIELDS, ngramQuery, opts));\n\n  // HAVING COUNT(*) = branches.length is the AND across indexes; with one branch it is a no-op,\n  // `path` being content's primary key. fts_score is higher-is-better BM25, so DESC.\n  const sql = `SELECT path, NULL AS hit FROM (\n    SELECT path, SUM(score) AS score FROM (\n      ${branches.join(' UNION ALL ')}\n    ) parts GROUP BY path HAVING COUNT(*) = ${branches.length}\n  ) sq ORDER BY score DESC, path LIMIT ?`;\n  const stmt = await conn.prepare(sql);\n  const rows = (await stmt.all(opts.limit)) as unknown as LexicalHit[];\n  // A concurrent FTS read during an open write transaction can yield a {path: null} row. Raised,\n  // not filtered: filtering returns a silently short result (PRINCIPLES: no-silent-modes).\n  if (rows.some((r) => r.path === null)) {\n    throw new SenseError('LEXICAL_NULL_PATH', 'store \"turso\" returned a search hit with no path (a known engine anomaly under concurrent FTS reads); retry the query');\n  }\n  return rows;\n}\n"],"names":["SenseError","hasUnspacedRun","FIELDS","NGRAM_FIELDS","FTS5_OPERATORS","label","re","unsupportedOperator","terms","withoutPhrases","replace","m","match","token","trim","splitTerms","words","phrases","unspaced","_m","inner","phrase","length","push","tok","split","escapeFtsLiteral","query","buildQueries","defaultParts","map","t","unspacedParts","defaultQuery","join","ngramQuery","ftsBranch","cols","opts","colList","c","lit","whereJoin","whereCond","scopeCond","queryLexical","conn","unsupported","branches","sql","stmt","prepare","rows","all","limit","some","r","path"],"mappings":"AAAA,4FAA4F;AAC5F,uGAAuG;AACvG,SAASA,UAAU,QAAQ,kBAAkB;AAC7C,SAASC,cAAc,QAAQ,wBAAwB;AAGvD,MAAMC,SAAS;IAAC;IAAS;IAAW;CAAO;AAC3C,MAAMC,eAAe;IAAC;IAAe;IAAiB;CAAa;AAEnE,uFAAuF;AACvF,+FAA+F;AAC/F,MAAMC,iBAAuD;IAC3D;QAAEC,OAAO;QAAgBC,IAAI;IAA4B;IACzD;QAAED,OAAO;QAAoBC,IAAI;IAAiC;IAClE;QAAED,OAAO;QAAiBC,IAAI;IAAiB;IAC/C;QAAED,OAAO;QAAgCC,IAAI;IAAW;IACxD;QAAED,OAAO;QAAiBC,IAAI;IAA2B;CAC1D;AAED,SAASC,oBAAoBC,KAAa;IACxC,MAAMC,iBAAiBD,MAAME,OAAO,CAAC,YAAY;IACjD,KAAK,MAAM,EAAEL,KAAK,EAAEC,EAAE,EAAE,IAAIF,eAAgB;QAC1C,MAAMO,IAAIF,eAAeG,KAAK,CAACN;QAC/B,IAAIK,GAAG,OAAO;YAAEN;YAAOQ,OAAOF,CAAC,CAAC,EAAE,CAACG,IAAI;QAAG;IAC5C;IACA,OAAO;AACT;AAEA,gGAAgG;AAChG,sFAAsF;AACtF,SAASC,WAAWP,KAAa;IAC/B,MAAMQ,QAAkB,EAAE;IAC1B,MAAMC,UAAoB,EAAE;IAC5B,MAAMC,WAAqB,EAAE;IAC7B,MAAMT,iBAAiBD,MAAME,OAAO,CAAC,cAAc,CAACS,IAAIC;QACtD,MAAMC,SAASD,MAAMN,IAAI;QACzB,IAAIO,OAAOC,MAAM,KAAK,GAAG,OAAO;QAChC,IAAIrB,eAAeoB,SAASH,SAASK,IAAI,CAACF;aACrCJ,QAAQM,IAAI,CAACF;QAClB,OAAO;IACT;IACA,KAAK,MAAMG,OAAOf,eAAegB,KAAK,CAAC,OAAQ;QAC7C,IAAID,IAAIF,MAAM,KAAK,GAAG;QACtB,IAAIrB,eAAeuB,MAAMN,SAASK,IAAI,CAACC;aAClCR,MAAMO,IAAI,CAACC;IAClB;IACA,OAAO;QAAER;QAAOC;QAASC;IAAS;AACpC;AAEA,8FAA8F;AAC9F,wFAAwF;AACxF,SAASQ,iBAAiBC,KAAa;IACrC,OAAOA,MAAMjB,OAAO,CAAC,MAAM;AAC7B;AAEA,6FAA6F;AAC7F,kGAAkG;AAClG,SAASkB,aAAaZ,KAAe,EAAEC,OAAiB,EAAEC,QAAkB;IAC1E,MAAMW,eAAe;WAAIb;WAAUC;KAAQ,CAACa,GAAG,CAAC,CAACC,IAAM,CAAC,CAAC,EAAEA,EAAE,CAAC,CAAC;IAC/D,MAAMC,gBAAgBd,SAASY,GAAG,CAAC,CAACC,IAAM,CAAC,CAAC,EAAEA,EAAE,CAAC,CAAC;IAClD,OAAO;QAAEE,cAAcJ,aAAaK,IAAI,CAAC;QAAUC,YAAYH,cAAcE,IAAI,CAAC;IAAS;AAC7F;AAEA,gGAAgG;AAChG,+FAA+F;AAC/F,SAASE,UAAUC,IAAuB,EAAEV,KAAa,EAAEW,IAAyB;IAClF,MAAMC,UAAUF,KAAKP,GAAG,CAAC,CAACU,IAAM,CAAC,QAAQ,EAAEA,GAAG,EAAEN,IAAI,CAAC;IACrD,MAAMO,MAAMf,iBAAiBC;IAC7B,OAAO,CAAC,yCAAyC,EAAEY,QAAQ,GAAG,EAAEE,IAAI;iBACrD,EAAEH,KAAKI,SAAS,CAAC,iBAAiB,EAAEH,QAAQ,GAAG,EAAEE,IAAI,GAAG,EAAEH,KAAKK,SAAS,CAAC,CAAC,EAAEL,KAAKM,SAAS,EAAE;AAC7G;AAEA,uFAAuF;AACvF,gMAAgM;AAChM,OAAO,eAAeC,aAAaC,IAAgB,EAAEtC,KAAa,EAAE8B,IAAyB;IAC3F,MAAMS,cAAcxC,oBAAoBC;IACxC,IAAIuC,gBAAgB,MAAM;QACxB,MAAM,IAAI/C,WAAW,4BAA4B,CAAC,wCAAwC,EAAE+C,YAAY1C,KAAK,CAAC,GAAG,EAAE0C,YAAYlC,KAAK,CAAC,4BAA4B,EAAEL,MAAMM,IAAI,GAAG,sFAAsF,CAAC;IACzQ;IACA,MAAM,EAAEE,KAAK,EAAEC,OAAO,EAAEC,QAAQ,EAAE,GAAGH,WAAWP;IAChD,MAAM,EAAEyB,YAAY,EAAEE,UAAU,EAAE,GAAGP,aAAaZ,OAAOC,SAASC;IAClE,IAAIe,iBAAiB,MAAME,eAAe,IAAI,OAAO,EAAE;IAEvD,MAAMa,WAAqB,EAAE;IAC7B,IAAIf,iBAAiB,IAAIe,SAASzB,IAAI,CAACa,UAAUlC,QAAQ+B,cAAcK;IACvE,IAAIH,eAAe,IAAIa,SAASzB,IAAI,CAACa,UAAUjC,cAAcgC,YAAYG;IAEzE,8FAA8F;IAC9F,mFAAmF;IACnF,MAAMW,MAAM,CAAC;;MAET,EAAED,SAASd,IAAI,CAAC,eAAe;4CACO,EAAEc,SAAS1B,MAAM,CAAC;wCACtB,CAAC;IACvC,MAAM4B,OAAO,MAAMJ,KAAKK,OAAO,CAACF;IAChC,MAAMG,OAAQ,MAAMF,KAAKG,GAAG,CAACf,KAAKgB,KAAK;IACvC,+FAA+F;IAC/F,yFAAyF;IACzF,IAAIF,KAAKG,IAAI,CAAC,CAACC,IAAMA,EAAEC,IAAI,KAAK,OAAO;QACrC,MAAM,IAAIzD,WAAW,qBAAqB;IAC5C;IACA,OAAOoD;AACT"}
+{"version":3,"sources":["/Users/kevin/Dev/OpenSource/ai/sensemaking/src/store/turso/lexical.ts"],"sourcesContent":["// T1: Tantivy FTS via fts_match/fts_score on the default-tokenizer index for bare words and\n// quoted phrases, plus a second ngram-tokenized index over \"_ngram\" sidecars for unspaced-script runs.\nimport { SenseError } from '../../errors.ts';\nimport { matchesSearchPhrase, type SearchToken, searchTokens } from '../../text/segment.ts';\nimport type { Connection, LexicalHit, LexicalQueryOptions } from '../types.ts';\nimport { stemFolded } from './lexical-text.ts';\n\nconst FIELDS = ['title_stem', 'summary_stem', 'text_stem'] as const;\nconst NGRAM_FIELDS = ['title_ngram', 'summary_ngram', 'text_ngram'] as const;\nconst AUTHORED_FIELDS = ['title', 'summary', 'text'] as const;\ntype AuthoredField = (typeof AUTHORED_FIELDS)[number];\n\n// FTS5 operator syntax a bare query would otherwise treat as literal text (PRINCIPLES:\n// no-silent-modes). `^` is rejected either way: boost to Tantivy, initial-token match to FTS5.\nconst FTS5_OPERATORS: Array<{ label: string; re: RegExp }> = [\n  { label: 'prefix query', re: /[\\p{L}\\p{N}_]+\\*(?=\\s|$)/u },\n  { label: 'boolean operator', re: /(?:^|\\s)(?:AND|OR|NOT)(?=\\s|$)/ },\n  { label: 'NEAR operator', re: /(?:^|\\s)NEAR\\b/ },\n  { label: 'boost/initial-token operator', re: /\\S*\\^\\S*/ },\n  { label: 'column filter', re: /(?:^|\\s)[\\p{L}_]\\w*\\s*:/u },\n];\n\nfunction unsupportedOperator(terms: string): { label: string; token: string } | null {\n  const withoutPhrases = terms.replace(/\"[^\"]*\"/g, ' ');\n  for (const { label, re } of FTS5_OPERATORS) {\n    const m = withoutPhrases.match(re);\n    if (m) return { label, token: m[0].trim() };\n  }\n  return null;\n}\n\n// A run whose script marks no word boundaries indexes as one opaque token under every tokenizer\n// but ngram, so such runs -- bare or quoted -- go to the ngram sidecar index instead.\nfunction splitTerms(terms: string): { words: string[]; phrases: SearchToken[][]; unspaced: string[]; emptyPhrase: boolean } {\n  const words: string[] = [];\n  const phrases: SearchToken[][] = [];\n  const unspaced: string[] = [];\n  let emptyPhrase = false;\n  const withoutPhrases = terms.replace(/\"([^\"]*)\"/g, (_m, inner: string) => {\n    const phrase = inner.trim();\n    const tokens = searchTokens(phrase);\n    if (tokens.length === 0) {\n      emptyPhrase = true;\n      return ' ';\n    }\n    unspaced.push(...tokens.filter((token) => token.unspaced).map((token) => token.text));\n    phrases.push(tokens);\n    return ' ';\n  });\n  for (const tok of withoutPhrases.split(/\\s+/)) {\n    if (tok.length === 0) continue;\n    for (const token of searchTokens(tok)) {\n      if (token.unspaced) unspaced.push(token.text);\n      else words.push(token.text);\n    }\n  }\n  return { words, phrases, unspaced, emptyPhrase };\n}\n\n// fts_match/fts_score's query argument must be a SQL literal: bound as `?`, the row set stays\n// correct but fts_score silently returns 0 for every row (PRINCIPLES: no-silent-modes).\nfunction escapeFtsLiteral(query: string): string {\n  return query.replace(/'/g, \"''\");\n}\n\n// Terms are quoted (\"O'Brien's\" is a parse error bare) and AND-joined: Tantivy's default for\n// bare terms is disjunctive, so space-joining would loosen \"apple banana\" into \"apple OR banana\".\nfunction buildQueries(words: string[], phrases: SearchToken[][], unspaced: string[]): { defaultQuery: string; ngramQuery: string } {\n  const phraseParts = phrases.flatMap((phrase) => {\n    const latin = phrase.filter((token) => !token.unspaced).map((token) => stemFolded(token.text));\n    if (latin.length === 0) return [];\n    return phrase.some((token) => token.unspaced) ? latin : [latin.join(' ')];\n  });\n  const defaultParts = [...words.map(stemFolded), ...phraseParts].map((t) => `\"${t}\"`);\n  const unspacedParts = unspaced.map((t) => `\"${t}\"`);\n  return { defaultQuery: defaultParts.join(' AND '), ngramQuery: unspacedParts.join(' AND ') };\n}\n\n// fts_score() is real only as a SELECT's bare projected expression, and only for the index that\n// SELECT's fts_match() chose; every other form silently returns 0. Hence one SELECT per index.\nfunction ftsBranch(cols: readonly string[], query: string, opts: LexicalQueryOptions): string {\n  const colList = cols.map((c) => `content.${c}`).join(', ');\n  const lit = escapeFtsLiteral(query);\n  return `SELECT content.\"path\" AS path, fts_score(${colList}, '${lit}') AS score\n    FROM content ${opts.whereJoin} WHERE fts_match(${colList}, '${lit}') ${opts.whereCond} ${opts.scopeCond}`;\n}\n\n// Ranked query, scoped by the caller-built SQL fragments (same shape sqlite's/duckdb's\n// queryLexical take). `snippets` is always NULL: fts_highlight returns the full column text, not a bounded snippet, so every row goes through the caller's JS snippet fallback (commands/search.ts).\nexport async function queryLexical(conn: Connection, terms: string, opts: LexicalQueryOptions): Promise<LexicalHit[]> {\n  const unsupported = unsupportedOperator(terms);\n  if (unsupported !== null) {\n    throw new SenseError('STORE_CAPABILITY_MISSING', `store \"turso\" does not implement FTS5's ${unsupported.label} (\"${unsupported.token}\") in this build; rephrase \"${terms.trim()}\" without it, or set \"store\" to \"sqlite\" in this tree's config to search it as written`);\n  }\n  const { words, phrases, unspaced, emptyPhrase } = splitTerms(terms);\n  if (emptyPhrase) return [];\n  const { defaultQuery, ngramQuery } = buildQueries(words, phrases, unspaced);\n  if (defaultQuery === '' && ngramQuery === '') return [];\n\n  const branches: string[] = [];\n  if (defaultQuery !== '') branches.push(ftsBranch(FIELDS, defaultQuery, opts));\n  if (ngramQuery !== '') branches.push(ftsBranch(NGRAM_FIELDS, ngramQuery, opts));\n\n  // HAVING COUNT(*) = branches.length is the AND across indexes; with one branch it is a no-op,\n  // `path` being content's primary key. fts_score is higher-is-better BM25, so DESC. Phrase\n  // candidates carry authored fields through the join below so the shared verifier can reject\n  // cross-field, reordered, and non-adjacent matches before applying the caller's limit.\n  const ranked = `SELECT path, SUM(score) AS score FROM (\n      ${branches.join(' UNION ALL ')}\n    ) parts GROUP BY path HAVING COUNT(*) = ${branches.length}`;\n  const phraseSelect = phrases.length > 0 ? ', content.title, content.summary, content.text' : '';\n  const phraseJoin = phrases.length > 0 ? ' JOIN content ON content.path = sq.path' : '';\n  const sql = `SELECT sq.path, sq.score${phraseSelect} FROM (\n    ${ranked}\n  ) sq${phraseJoin} ORDER BY sq.score DESC, sq.path${phrases.length > 0 ? '' : ' LIMIT ?'}`;\n  const stmt = await conn.prepare(sql);\n  const rows = (await stmt.all(...(phrases.length > 0 ? [] : [opts.limit]))) as Array<LexicalHit & Partial<Record<AuthoredField, string>>>;\n  // A concurrent FTS read during an open write transaction can yield a {path: null} row. Raised,\n  // not filtered: filtering returns a silently short result (PRINCIPLES: no-silent-modes).\n  if (rows.some((r) => r.path === null)) {\n    throw new SenseError('LEXICAL_NULL_PATH', 'store \"turso\" returned a search hit with no path (a known engine anomaly under concurrent FTS reads); retry the query');\n  }\n  const matches = phrases.length === 0 ? rows : rows.filter((row) => phrases.every((phrase) => AUTHORED_FIELDS.some((field) => matchesSearchPhrase(row[field] ?? '', phrase))));\n  return matches.slice(0, opts.limit).map(({ path }) => ({ path }));\n}\n"],"names":["SenseError","matchesSearchPhrase","searchTokens","stemFolded","FIELDS","NGRAM_FIELDS","AUTHORED_FIELDS","FTS5_OPERATORS","label","re","unsupportedOperator","terms","withoutPhrases","replace","m","match","token","trim","splitTerms","words","phrases","unspaced","emptyPhrase","_m","inner","phrase","tokens","length","push","filter","map","text","tok","split","escapeFtsLiteral","query","buildQueries","phraseParts","flatMap","latin","some","join","defaultParts","t","unspacedParts","defaultQuery","ngramQuery","ftsBranch","cols","opts","colList","c","lit","whereJoin","whereCond","scopeCond","queryLexical","conn","unsupported","branches","ranked","phraseSelect","phraseJoin","sql","stmt","prepare","rows","all","limit","r","path","matches","row","every","field","slice"],"mappings":"AAAA,4FAA4F;AAC5F,uGAAuG;AACvG,SAASA,UAAU,QAAQ,kBAAkB;AAC7C,SAASC,mBAAmB,EAAoBC,YAAY,QAAQ,wBAAwB;AAE5F,SAASC,UAAU,QAAQ,oBAAoB;AAE/C,MAAMC,SAAS;IAAC;IAAc;IAAgB;CAAY;AAC1D,MAAMC,eAAe;IAAC;IAAe;IAAiB;CAAa;AACnE,MAAMC,kBAAkB;IAAC;IAAS;IAAW;CAAO;AAGpD,uFAAuF;AACvF,+FAA+F;AAC/F,MAAMC,iBAAuD;IAC3D;QAAEC,OAAO;QAAgBC,IAAI;IAA4B;IACzD;QAAED,OAAO;QAAoBC,IAAI;IAAiC;IAClE;QAAED,OAAO;QAAiBC,IAAI;IAAiB;IAC/C;QAAED,OAAO;QAAgCC,IAAI;IAAW;IACxD;QAAED,OAAO;QAAiBC,IAAI;IAA2B;CAC1D;AAED,SAASC,oBAAoBC,KAAa;IACxC,MAAMC,iBAAiBD,MAAME,OAAO,CAAC,YAAY;IACjD,KAAK,MAAM,EAAEL,KAAK,EAAEC,EAAE,EAAE,IAAIF,eAAgB;QAC1C,MAAMO,IAAIF,eAAeG,KAAK,CAACN;QAC/B,IAAIK,GAAG,OAAO;YAAEN;YAAOQ,OAAOF,CAAC,CAAC,EAAE,CAACG,IAAI;QAAG;IAC5C;IACA,OAAO;AACT;AAEA,gGAAgG;AAChG,sFAAsF;AACtF,SAASC,WAAWP,KAAa;IAC/B,MAAMQ,QAAkB,EAAE;IAC1B,MAAMC,UAA2B,EAAE;IACnC,MAAMC,WAAqB,EAAE;IAC7B,IAAIC,cAAc;IAClB,MAAMV,iBAAiBD,MAAME,OAAO,CAAC,cAAc,CAACU,IAAIC;QACtD,MAAMC,SAASD,MAAMP,IAAI;QACzB,MAAMS,SAASxB,aAAauB;QAC5B,IAAIC,OAAOC,MAAM,KAAK,GAAG;YACvBL,cAAc;YACd,OAAO;QACT;QACAD,SAASO,IAAI,IAAIF,OAAOG,MAAM,CAAC,CAACb,QAAUA,MAAMK,QAAQ,EAAES,GAAG,CAAC,CAACd,QAAUA,MAAMe,IAAI;QACnFX,QAAQQ,IAAI,CAACF;QACb,OAAO;IACT;IACA,KAAK,MAAMM,OAAOpB,eAAeqB,KAAK,CAAC,OAAQ;QAC7C,IAAID,IAAIL,MAAM,KAAK,GAAG;QACtB,KAAK,MAAMX,SAASd,aAAa8B,KAAM;YACrC,IAAIhB,MAAMK,QAAQ,EAAEA,SAASO,IAAI,CAACZ,MAAMe,IAAI;iBACvCZ,MAAMS,IAAI,CAACZ,MAAMe,IAAI;QAC5B;IACF;IACA,OAAO;QAAEZ;QAAOC;QAASC;QAAUC;IAAY;AACjD;AAEA,8FAA8F;AAC9F,wFAAwF;AACxF,SAASY,iBAAiBC,KAAa;IACrC,OAAOA,MAAMtB,OAAO,CAAC,MAAM;AAC7B;AAEA,6FAA6F;AAC7F,kGAAkG;AAClG,SAASuB,aAAajB,KAAe,EAAEC,OAAwB,EAAEC,QAAkB;IACjF,MAAMgB,cAAcjB,QAAQkB,OAAO,CAAC,CAACb;QACnC,MAAMc,QAAQd,OAAOI,MAAM,CAAC,CAACb,QAAU,CAACA,MAAMK,QAAQ,EAAES,GAAG,CAAC,CAACd,QAAUb,WAAWa,MAAMe,IAAI;QAC5F,IAAIQ,MAAMZ,MAAM,KAAK,GAAG,OAAO,EAAE;QACjC,OAAOF,OAAOe,IAAI,CAAC,CAACxB,QAAUA,MAAMK,QAAQ,IAAIkB,QAAQ;YAACA,MAAME,IAAI,CAAC;SAAK;IAC3E;IACA,MAAMC,eAAe;WAAIvB,MAAMW,GAAG,CAAC3B;WAAgBkC;KAAY,CAACP,GAAG,CAAC,CAACa,IAAM,CAAC,CAAC,EAAEA,EAAE,CAAC,CAAC;IACnF,MAAMC,gBAAgBvB,SAASS,GAAG,CAAC,CAACa,IAAM,CAAC,CAAC,EAAEA,EAAE,CAAC,CAAC;IAClD,OAAO;QAAEE,cAAcH,aAAaD,IAAI,CAAC;QAAUK,YAAYF,cAAcH,IAAI,CAAC;IAAS;AAC7F;AAEA,gGAAgG;AAChG,+FAA+F;AAC/F,SAASM,UAAUC,IAAuB,EAAEb,KAAa,EAAEc,IAAyB;IAClF,MAAMC,UAAUF,KAAKlB,GAAG,CAAC,CAACqB,IAAM,CAAC,QAAQ,EAAEA,GAAG,EAAEV,IAAI,CAAC;IACrD,MAAMW,MAAMlB,iBAAiBC;IAC7B,OAAO,CAAC,yCAAyC,EAAEe,QAAQ,GAAG,EAAEE,IAAI;iBACrD,EAAEH,KAAKI,SAAS,CAAC,iBAAiB,EAAEH,QAAQ,GAAG,EAAEE,IAAI,GAAG,EAAEH,KAAKK,SAAS,CAAC,CAAC,EAAEL,KAAKM,SAAS,EAAE;AAC7G;AAEA,uFAAuF;AACvF,qMAAqM;AACrM,OAAO,eAAeC,aAAaC,IAAgB,EAAE9C,KAAa,EAAEsC,IAAyB;IAC3F,MAAMS,cAAchD,oBAAoBC;IACxC,IAAI+C,gBAAgB,MAAM;QACxB,MAAM,IAAI1D,WAAW,4BAA4B,CAAC,wCAAwC,EAAE0D,YAAYlD,KAAK,CAAC,GAAG,EAAEkD,YAAY1C,KAAK,CAAC,4BAA4B,EAAEL,MAAMM,IAAI,GAAG,sFAAsF,CAAC;IACzQ;IACA,MAAM,EAAEE,KAAK,EAAEC,OAAO,EAAEC,QAAQ,EAAEC,WAAW,EAAE,GAAGJ,WAAWP;IAC7D,IAAIW,aAAa,OAAO,EAAE;IAC1B,MAAM,EAAEuB,YAAY,EAAEC,UAAU,EAAE,GAAGV,aAAajB,OAAOC,SAASC;IAClE,IAAIwB,iBAAiB,MAAMC,eAAe,IAAI,OAAO,EAAE;IAEvD,MAAMa,WAAqB,EAAE;IAC7B,IAAId,iBAAiB,IAAIc,SAAS/B,IAAI,CAACmB,UAAU3C,QAAQyC,cAAcI;IACvE,IAAIH,eAAe,IAAIa,SAAS/B,IAAI,CAACmB,UAAU1C,cAAcyC,YAAYG;IAEzE,8FAA8F;IAC9F,0FAA0F;IAC1F,4FAA4F;IAC5F,uFAAuF;IACvF,MAAMW,SAAS,CAAC;MACZ,EAAED,SAASlB,IAAI,CAAC,eAAe;4CACO,EAAEkB,SAAShC,MAAM,EAAE;IAC7D,MAAMkC,eAAezC,QAAQO,MAAM,GAAG,IAAI,mDAAmD;IAC7F,MAAMmC,aAAa1C,QAAQO,MAAM,GAAG,IAAI,4CAA4C;IACpF,MAAMoC,MAAM,CAAC,wBAAwB,EAAEF,aAAa;IAClD,EAAED,OAAO;MACP,EAAEE,WAAW,gCAAgC,EAAE1C,QAAQO,MAAM,GAAG,IAAI,KAAK,YAAY;IACzF,MAAMqC,OAAO,MAAMP,KAAKQ,OAAO,CAACF;IAChC,MAAMG,OAAQ,MAAMF,KAAKG,GAAG,IAAK/C,QAAQO,MAAM,GAAG,IAAI,EAAE,GAAG;QAACsB,KAAKmB,KAAK;KAAC;IACvE,+FAA+F;IAC/F,yFAAyF;IACzF,IAAIF,KAAK1B,IAAI,CAAC,CAAC6B,IAAMA,EAAEC,IAAI,KAAK,OAAO;QACrC,MAAM,IAAItE,WAAW,qBAAqB;IAC5C;IACA,MAAMuE,UAAUnD,QAAQO,MAAM,KAAK,IAAIuC,OAAOA,KAAKrC,MAAM,CAAC,CAAC2C,MAAQpD,QAAQqD,KAAK,CAAC,CAAChD,SAAWnB,gBAAgBkC,IAAI,CAAC,CAACkC;oBAA8BF;uBAApBvE,qBAAoBuE,aAAAA,GAAG,CAACE,MAAM,cAAVF,wBAAAA,aAAc,IAAI/C;;IACnK,OAAO8C,QAAQI,KAAK,CAAC,GAAG1B,KAAKmB,KAAK,EAAEtC,GAAG,CAAC,CAAC,EAAEwC,IAAI,EAAE,GAAM,CAAA;YAAEA;QAAK,CAAA;AAChE"}

package/dist/esm/store/turso/open.d.ts

@@ -3,7 +3,7 @@ import type { ResolvedConfig } from '../../config/index.js';
 import type { OpenResult } from '../open.js';
 import type { OpenDialect } from '../types.js';
 export declare const DB_FILENAME = "cache.turso.db";
-export declare const SCHEMA_VERSION = "5";
+export declare const SCHEMA_VERSION = "8";
 export type { OpenResult };
 export declare const tursoOpenDialect: OpenDialect<Database>;
 export declare function openTurso(cfg: ResolvedConfig): Promise<OpenResult>;

package/dist/esm/store/turso/open.js

@@ -11,12 +11,12 @@ import { createStore } from './store.js';
 export const DB_FILENAME = 'cache.turso.db';
 // Independent of sqlite's and duckdb's SCHEMA_VERSION: each store's cache shape evolves
 // separately. Covers the FTS indexes, the "_ngram" sidecar columns, and embeddings.vector's width.
-export const SCHEMA_VERSION = '5';
+export const SCHEMA_VERSION = '8';
 // This store's Handle (types.ts's OpenDialect<Handle>) is the connected Database itself: no
 // extra native state to thread, unlike duckdb's separate instance/connection pair.
 async function ensureSchema(_handle, conn, cfg) {
     await conn.exec(`CREATE TABLE IF NOT EXISTS frontmatter ("path" TEXT PRIMARY KEY, "_mtime" REAL, "_ctime" REAL, "_size" INTEGER, "_parse_error" TEXT)`);
-    await conn.exec(`CREATE TABLE IF NOT EXISTS content ("path" TEXT PRIMARY KEY, title TEXT, summary TEXT, text TEXT, title_ngram TEXT, summary_ngram TEXT, text_ngram TEXT)`);
+    await conn.exec(`CREATE TABLE IF NOT EXISTS content ("path" TEXT PRIMARY KEY, title TEXT, summary TEXT, text TEXT, title_stem TEXT, summary_stem TEXT, text_stem TEXT, title_ngram TEXT, summary_ngram TEXT, text_ngram TEXT)`);
     for (const ddl of CONTENT_FTS_DDL)await conn.exec(ddl);
     await conn.exec(`CREATE TABLE IF NOT EXISTS preset_files ("path" TEXT, preset TEXT, PRIMARY KEY ("path", preset))`);
     await conn.exec('CREATE INDEX IF NOT EXISTS preset_files_preset ON preset_files(preset)');