@fgv/ts-agent-memory-sqlite-vec 5.1.0-45 → 5.1.0-47
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.rush/temp/{e3385c5c74e11d46b4fbe400b497eb3f33a009b6.tar.log → 2b1ffec4a34b11a2a7317510ba4142ae814069d2.tar.log} +2 -2
- package/.rush/temp/chunked-rush-logs/ts-agent-memory-sqlite-vec.build.chunks.jsonl +2 -2
- package/.rush/temp/operation/build/all.log +2 -2
- package/.rush/temp/operation/build/log-chunks.jsonl +2 -2
- package/.rush/temp/operation/build/state.json +1 -1
- package/README.md +16 -2
- package/dist/packlets/sqlite-vec-index/sqliteVecFragmentIndex.js +144 -26
- package/dist/packlets/sqlite-vec-index/sqliteVecFragmentIndex.js.map +1 -1
- package/dist/test/unit/sqliteVecFragmentIndex.test.js +168 -7
- package/dist/test/unit/sqliteVecFragmentIndex.test.js.map +1 -1
- package/dist/ts-agent-memory-sqlite-vec.d.ts +68 -11
- package/lib/packlets/sqlite-vec-index/sqliteVecFragmentIndex.d.ts +68 -11
- package/lib/packlets/sqlite-vec-index/sqliteVecFragmentIndex.d.ts.map +1 -1
- package/lib/packlets/sqlite-vec-index/sqliteVecFragmentIndex.js +144 -26
- package/lib/packlets/sqlite-vec-index/sqliteVecFragmentIndex.js.map +1 -1
- package/lib/test/unit/sqliteVecFragmentIndex.test.js +168 -7
- package/lib/test/unit/sqliteVecFragmentIndex.test.js.map +1 -1
- package/package.json +7 -7
- package/rush-logs/ts-agent-memory-sqlite-vec.build.cache.log +1 -1
- package/rush-logs/ts-agent-memory-sqlite-vec.build.log +2 -2
- package/src/packlets/sqlite-vec-index/sqliteVecFragmentIndex.ts +184 -25
- package/src/test/unit/sqliteVecFragmentIndex.test.ts +236 -11
- package/temp/build/lint/_eslint-5eVG3S6w.json +2 -2
- package/temp/build/typescript/ts_8nwakTlr.json +1 -1
- package/temp/ts-agent-memory-sqlite-vec.api.json +2 -2
|
@@ -1,5 +1,5 @@
|
|
|
1
|
-
Start time:
|
|
2
|
-
Invoking "/usr/bin/tar -c -f /home/runner/work/fgv/fgv/common/temp/build-cache/
|
|
1
|
+
Start time: Fri Aug 07 2026 01:16:31 GMT+0000 (Coordinated Universal Time)
|
|
2
|
+
Invoking "/usr/bin/tar -c -f /home/runner/work/fgv/fgv/common/temp/build-cache/2b1ffec4a34b11a2a7317510ba4142ae814069d2-45b8b383732483ea.temp -z --files-from=-"
|
|
3
3
|
|
|
4
4
|
======= BEGIN PROCESS INPUT ======
|
|
5
5
|
.rush/temp/operation/build/all.log
|
|
@@ -5,5 +5,5 @@
|
|
|
5
5
|
{"kind":"O","text":"[build:lint] Using ESLint version 9.39.5\n"}
|
|
6
6
|
{"kind":"O","text":"[build:api-extractor] Using API Extractor version 7.58.9\n"}
|
|
7
7
|
{"kind":"O","text":"[build:api-extractor] Analysis will use the bundled TypeScript version 5.9.3\n"}
|
|
8
|
-
{"kind":"O","text":" ---- build finished (
|
|
9
|
-
{"kind":"O","text":"-------------------- Finished (
|
|
8
|
+
{"kind":"O","text":" ---- build finished (6.758s) ---- \n"}
|
|
9
|
+
{"kind":"O","text":"-------------------- Finished (6.764s) --------------------\n"}
|
|
@@ -5,5 +5,5 @@ Invoking: heft build --clean
|
|
|
5
5
|
[build:lint] Using ESLint version 9.39.5
|
|
6
6
|
[build:api-extractor] Using API Extractor version 7.58.9
|
|
7
7
|
[build:api-extractor] Analysis will use the bundled TypeScript version 5.9.3
|
|
8
|
-
---- build finished (
|
|
9
|
-
-------------------- Finished (
|
|
8
|
+
---- build finished (6.758s) ----
|
|
9
|
+
-------------------- Finished (6.764s) --------------------
|
|
@@ -5,5 +5,5 @@
|
|
|
5
5
|
{"kind":"O","text":"[build:lint] Using ESLint version 9.39.5\n"}
|
|
6
6
|
{"kind":"O","text":"[build:api-extractor] Using API Extractor version 7.58.9\n"}
|
|
7
7
|
{"kind":"O","text":"[build:api-extractor] Analysis will use the bundled TypeScript version 5.9.3\n"}
|
|
8
|
-
{"kind":"O","text":" ---- build finished (
|
|
9
|
-
{"kind":"O","text":"-------------------- Finished (
|
|
8
|
+
{"kind":"O","text":" ---- build finished (6.758s) ---- \n"}
|
|
9
|
+
{"kind":"O","text":"-------------------- Finished (6.764s) --------------------\n"}
|
package/README.md
CHANGED
|
@@ -83,12 +83,26 @@ const hits = (await retriever.retrieve({ semantic: 'refund policy', topK: 5, max
|
|
|
83
83
|
// each hit carries { target, locator: { start, end }, score } — read the record, slice the span.
|
|
84
84
|
```
|
|
85
85
|
|
|
86
|
-
- Keyed on `target_key` as a `vec0` **`PARTITION KEY`** (many rows share it), with
|
|
86
|
+
- Keyed on `target_key` as a `vec0` **`PARTITION KEY`** (many rows share it), with each fragment's identity in auxiliary columns (`+start_off`, `+end_off`, `+fragment_id`) — so `addFragments` is whole-record-replace, `remove` drops every fragment of a target, and both are per-target-clean.
|
|
87
87
|
- `query(vector, topK, maxPerRecord?)` applies the optional per-record cap **during selection, before the `topK` cut**, so one long document cannot crowd others out.
|
|
88
88
|
- Same dimension-establishment, cosine scoring (`score = 1 − cosineDistance`), reopen-recovery, and loud-failure contract as the record index — byte-identical to `InMemoryFragmentCosineIndex`.
|
|
89
89
|
|
|
90
|
+
A fragment must carry **at least one** of `locator` / `fragmentId`. The `locator` span is *advisory* — the region of the body the fragment was derived from, **not** a slice guaranteed to reproduce its text — so a rewriting segmenter should omit it and supply a `fragmentId` instead. `fragmentId` is an **opaque bytestring**: stored and returned verbatim, never parsed, never filtered on. Its stability across re-embeds is the caller's business, not this index's (`addFragments` is whole-record-replace, so an updated record re-emits its whole fragment set).
|
|
91
|
+
|
|
90
92
|
Hold the record and fragment indexes in **distinct tables** (default `memory_vectors` vs `memory_fragments`, or supply `tableName`); they are fully independent and may share one database file.
|
|
91
93
|
|
|
94
|
+
## Upgrading: `vec0` schema changes require a drop-and-re-index
|
|
95
|
+
|
|
96
|
+
**There are no in-place migrations for the `vec0` tables this package writes.** When a release changes a table's shape — a new auxiliary column, a different column set — you must **drop the table and re-index**. `DROP TABLE "memory_fragments"` (or point the index at a fresh `tableName`), then re-add every fragment.
|
|
97
|
+
|
|
98
|
+
This is a property of `vec0`, not a choice: `CREATE VIRTUAL TABLE IF NOT EXISTS` is a no-op against an existing table — SQLite never compares schemas — and `vec0` has no `ALTER TABLE ADD COLUMN`. An old table therefore survives an upgrade untouched and only fails later, opaquely, when a widened statement is prepared.
|
|
99
|
+
|
|
100
|
+
`SqliteVecFragmentIndex.create` **detects this up front** and fails with a message naming the expected and found columns and stating the remedy, rather than letting `no such column: fragment_id` surface at statement-prepare time.
|
|
101
|
+
|
|
102
|
+
**The cost is embedding time, never data.** Vectors are derived artifacts — the records in your `FileTreeMemoryStore` vault remain the source of truth — so a re-index re-derives what was dropped and loses nothing.
|
|
103
|
+
|
|
104
|
+
Known instance: the release that added `IEmbeddedFragment.fragmentId` added a `+fragment_id` auxiliary column to the fragment table. A fragment database written before it must be dropped and re-indexed. (The record table used by `SqliteVecVectorIndex` is unchanged.)
|
|
105
|
+
|
|
92
106
|
## Not in scope
|
|
93
107
|
|
|
94
108
|
Deliberately excluded — reach for the upstream libraries (or a different backend) directly if you need these:
|
|
@@ -97,7 +111,7 @@ Deliberately excluded — reach for the upstream libraries (or a different backe
|
|
|
97
111
|
- **Connection lifecycle.** You open and close the `better-sqlite3` `Database`; this index never does. Pooling, WAL/pragma tuning, backups, and multi-process coordination are yours.
|
|
98
112
|
- **Embedding.** This is a vector *index*, not an embedder — the store's consumer-wired `MemoryEmbedder` produces the vectors (`@fgv/ts-extras/ai-assist` `callProviderEmbedding`, `@fgv/ts-extras-transformers`, etc.).
|
|
99
113
|
- **A browser sibling.** `better-sqlite3` is Node-only. A WASM-SQLite browser variant, if ever needed, is a separate package.
|
|
100
|
-
- **Schema migration
|
|
114
|
+
- **Schema migration of any kind.** Re-embedding with a different-dimension model against an existing table fails loudly, and a package release that changes a `vec0` table's columns requires a drop-and-re-index — see [Upgrading](#upgrading-vec0-schema-changes-require-a-drop-and-re-index). Drop the table (or use a new `tableName`) to re-index; `vec0` cannot be altered in place.
|
|
101
115
|
|
|
102
116
|
## Runtime requirements
|
|
103
117
|
|
|
@@ -9,6 +9,19 @@ import { edgeTargetKey } from '@fgv/ts-agent-memory';
|
|
|
9
9
|
const DEFAULT_TABLE_NAME = 'memory_fragments';
|
|
10
10
|
/** A simple SQL identifier — the only shape allowed for the table name (it is interpolated into DDL). */
|
|
11
11
|
const IDENTIFIER_RE = /^[A-Za-z_][A-Za-z0-9_]*$/;
|
|
12
|
+
/**
|
|
13
|
+
* The auxiliary (`+`-prefixed) columns this version of the index writes. A table
|
|
14
|
+
* created by an earlier version carries a different set; see
|
|
15
|
+
* {@link SqliteVecFragmentIndex._readExistingDimension} for why that has to be
|
|
16
|
+
* detected explicitly rather than migrated.
|
|
17
|
+
*/
|
|
18
|
+
const AUXILIARY_COLUMNS = ['start_off', 'end_off', 'fragment_id'];
|
|
19
|
+
/**
|
|
20
|
+
* Matches one `+name` auxiliary-column declaration in a `vec0` `CREATE VIRTUAL TABLE`
|
|
21
|
+
* statement. Only ever consumed via `String.matchAll`, which iterates a clone rather
|
|
22
|
+
* than advancing this instance's `lastIndex`, so the shared `/g` regex is reusable.
|
|
23
|
+
*/
|
|
24
|
+
const AUXILIARY_COLUMN_RE = /\+\s*([A-Za-z_][A-Za-z0-9_]*)/g;
|
|
12
25
|
/**
|
|
13
26
|
* A persistent, `sqlite-vec`-backed `IFragmentVectorIndex` (from
|
|
14
27
|
* `@fgv/ts-agent-memory`) — the fragment-granular sibling of
|
|
@@ -18,12 +31,25 @@ const IDENTIFIER_RE = /^[A-Za-z_][A-Za-z0-9_]*$/;
|
|
|
18
31
|
* @remarks
|
|
19
32
|
* Where {@link SqliteVecVectorIndex} keys one vector per record on a
|
|
20
33
|
* `target_key` primary key, this index holds **many** vectors per record — one per
|
|
21
|
-
*
|
|
22
|
-
*
|
|
23
|
-
*
|
|
24
|
-
*
|
|
25
|
-
*
|
|
26
|
-
*
|
|
34
|
+
* fragment — so it keys the `vec0` table on `target_key` as a **`PARTITION KEY`**
|
|
35
|
+
* (many rows may share it) and stores each fragment's identity in three auxiliary
|
|
36
|
+
* columns (`+start_off`, `+end_off`, `+fragment_id`) that ride alongside the vector
|
|
37
|
+
* and are returned on query but never filtered — in particular `fragment_id` is
|
|
38
|
+
* stored and returned verbatim, never parsed and never part of the query path. A
|
|
39
|
+
* query is a brute-force `vec0` KNN scan across all partitions returning per-fragment
|
|
40
|
+
* hits, each carrying its record `target` plus whichever identity fields the stored
|
|
41
|
+
* fragment was added with (a fragment must carry at least one).
|
|
42
|
+
*
|
|
43
|
+
* **`vec0` schema changes require a drop-and-re-index.** A
|
|
44
|
+
* `CREATE VIRTUAL TABLE IF NOT EXISTS` is a no-op against an existing table (SQLite
|
|
45
|
+
* does not compare schemas) and `vec0` has no `ALTER TABLE ADD COLUMN`, so a database written by an
|
|
46
|
+
* earlier version of this package keeps its old auxiliary columns. `create` detects
|
|
47
|
+
* that by parsing the stored `CREATE VIRTUAL TABLE` SQL and fails with an actionable
|
|
48
|
+
* message naming the expected and found columns, rather than letting a widened
|
|
49
|
+
* `INSERT` surface an opaque `no such column` at statement-prepare time. There are no
|
|
50
|
+
* in-place migrations: drop the table (or use a fresh `tableName`) and re-index.
|
|
51
|
+
* Fragment vectors are re-derivable from the records, so this costs embedding time,
|
|
52
|
+
* never data.
|
|
27
53
|
*
|
|
28
54
|
* Semantics match `InMemoryFragmentCosineIndex` exactly: `addFragments` is
|
|
29
55
|
* whole-record-replace (a single transaction deletes every prior fragment of the
|
|
@@ -66,12 +92,15 @@ export class SqliteVecFragmentIndex {
|
|
|
66
92
|
/**
|
|
67
93
|
* Family-convention factory. Loads the `sqlite-vec` extension onto the supplied
|
|
68
94
|
* `better-sqlite3` connection and, if the fragment table already exists (a
|
|
69
|
-
* reopened persistent file),
|
|
70
|
-
* re-embedding is needed on
|
|
95
|
+
* reopened persistent file), verifies its auxiliary-column set matches this
|
|
96
|
+
* version's and recovers its established dimension so no re-embedding is needed on
|
|
97
|
+
* open.
|
|
71
98
|
*
|
|
72
99
|
* @param params - See {@link ISqliteVecFragmentIndexCreateParams}.
|
|
73
100
|
* @returns `Success` with the index, or `Failure` if the table name is not a
|
|
74
|
-
* simple identifier
|
|
101
|
+
* simple identifier, the extension fails to load, or the existing table was
|
|
102
|
+
* written by a version with a different auxiliary-column set (which requires a
|
|
103
|
+
* drop-and-re-index — `vec0` cannot be altered in place).
|
|
75
104
|
*/
|
|
76
105
|
static create(params) {
|
|
77
106
|
var _a;
|
|
@@ -98,11 +127,19 @@ export class SqliteVecFragmentIndex {
|
|
|
98
127
|
if (fragment.vector.length === 0) {
|
|
99
128
|
return Promise.resolve(fail(`fragment index: cannot add '${key}': empty fragment vector`));
|
|
100
129
|
}
|
|
130
|
+
// A fragment carrying neither identity cannot be resolved back to anything by a
|
|
131
|
+
// consumer holding the hit — the same invariant `embeddedFragmentConverter`
|
|
132
|
+
// enforces at the untyped boundary, re-checked here at the index seam.
|
|
133
|
+
if (fragment.locator === undefined && fragment.fragmentId === undefined) {
|
|
134
|
+
return Promise.resolve(fail(`fragment index: cannot add '${key}': fragment requires at least one of 'locator' or 'fragmentId'`));
|
|
135
|
+
}
|
|
101
136
|
// Locator offsets are persisted as SQLite integers (bound via BigInt). Reject a
|
|
102
137
|
// non-safe-integer offset up front with a clear message, rather than letting
|
|
103
138
|
// `BigInt(nonInteger)` throw cryptically inside the write transaction OR storing
|
|
104
139
|
// a value the read-side `_toOffset` guard would later reject on every query.
|
|
105
|
-
|
|
140
|
+
// An absent locator persists as a NULL offset pair and skips the check.
|
|
141
|
+
if (fragment.locator !== undefined &&
|
|
142
|
+
(!Number.isSafeInteger(fragment.locator.start) || !Number.isSafeInteger(fragment.locator.end))) {
|
|
106
143
|
return Promise.resolve(fail(`fragment index: cannot add '${key}': locator [${fragment.locator.start}, ${fragment.locator.end}) offsets must be safe integers`));
|
|
107
144
|
}
|
|
108
145
|
if (dimension === undefined) {
|
|
@@ -180,36 +217,39 @@ export class SqliteVecFragmentIndex {
|
|
|
180
217
|
perRecord.set(row.target_key, used + 1);
|
|
181
218
|
}
|
|
182
219
|
const key = row.target_key;
|
|
183
|
-
hits.push({
|
|
184
|
-
target: SqliteVecFragmentIndex._parseKey(key),
|
|
185
|
-
score: 1 - row.distance,
|
|
186
|
-
locator: {
|
|
187
|
-
start: SqliteVecFragmentIndex._toOffset(row.start_off, key),
|
|
188
|
-
end: SqliteVecFragmentIndex._toOffset(row.end_off, key)
|
|
189
|
-
}
|
|
190
|
-
});
|
|
220
|
+
hits.push(Object.assign({ target: SqliteVecFragmentIndex._parseKey(key), score: 1 - row.distance }, SqliteVecFragmentIndex._toIdentity(row, key)));
|
|
191
221
|
}
|
|
192
222
|
return hits;
|
|
193
223
|
}).withErrorFormat((e) => `fragment index: query failed: ${e}`));
|
|
194
224
|
}
|
|
195
|
-
/**
|
|
225
|
+
/**
|
|
226
|
+
* Create the fragment `vec0` virtual table with the established dimension. The
|
|
227
|
+
* auxiliary columns must stay in sync with `AUXILIARY_COLUMNS`, which
|
|
228
|
+
* `create` compares against an existing table's stored DDL.
|
|
229
|
+
*/
|
|
196
230
|
_createTable(dimension) {
|
|
197
231
|
this._db.exec(`CREATE VIRTUAL TABLE IF NOT EXISTS "${this._table}" USING vec0(` +
|
|
198
232
|
`target_key TEXT PARTITION KEY, embedding float[${dimension}] distance_metric=cosine, ` +
|
|
199
|
-
`+start_off integer, +end_off integer)`);
|
|
233
|
+
`+start_off integer, +end_off integer, +fragment_id text)`);
|
|
200
234
|
}
|
|
201
235
|
/** Prepare the statements the index reuses. Requires the table to exist. */
|
|
202
236
|
_prepare() {
|
|
203
237
|
const del = this._db.prepare(`DELETE FROM "${this._table}" WHERE target_key = ?`);
|
|
204
|
-
const ins = this._db.prepare(`INSERT INTO "${this._table}"(target_key, embedding, start_off, end_off)
|
|
238
|
+
const ins = this._db.prepare(`INSERT INTO "${this._table}"(target_key, embedding, start_off, end_off, fragment_id) ` +
|
|
239
|
+
`VALUES (?, ?, ?, ?, ?)`);
|
|
205
240
|
// Whole-record replace: drop every prior fragment of the target, then insert the
|
|
206
241
|
// new set, atomically. An empty set collapses to a pure delete.
|
|
207
242
|
const replaceTxn = this._db.transaction((key, fragments) => {
|
|
243
|
+
var _a;
|
|
208
244
|
del.run(key);
|
|
209
245
|
for (const fragment of fragments) {
|
|
210
246
|
ins.run(key, SqliteVecFragmentIndex._toBlob(fragment.vector),
|
|
211
|
-
// vec0 typed columns reject a JS float; bind the offsets as integers.
|
|
212
|
-
|
|
247
|
+
// vec0 typed columns reject a JS float; bind the offsets as integers. An
|
|
248
|
+
// absent locator binds the pair as NULL — never a partial pair, so the read
|
|
249
|
+
// side can treat a half-NULL pair as corruption rather than a legal shape.
|
|
250
|
+
fragment.locator === undefined ? null : BigInt(fragment.locator.start), fragment.locator === undefined ? null : BigInt(fragment.locator.end),
|
|
251
|
+
// Stored verbatim and never parsed; absent binds as NULL.
|
|
252
|
+
(_a = fragment.fragmentId) !== null && _a !== void 0 ? _a : null);
|
|
213
253
|
}
|
|
214
254
|
});
|
|
215
255
|
return {
|
|
@@ -217,15 +257,23 @@ export class SqliteVecFragmentIndex {
|
|
|
217
257
|
replace: (key, fragments) => {
|
|
218
258
|
replaceTxn(key, fragments);
|
|
219
259
|
},
|
|
220
|
-
query: this._db.prepare(`SELECT target_key, start_off, end_off, distance FROM "${this._table}"
|
|
260
|
+
query: this._db.prepare(`SELECT target_key, start_off, end_off, fragment_id, distance FROM "${this._table}" ` +
|
|
261
|
+
`WHERE embedding MATCH ? AND k = ?`),
|
|
221
262
|
fragmentCount: this._db.prepare(`SELECT count(*) AS c FROM "${this._table}"`),
|
|
222
263
|
recordCount: this._db.prepare(`SELECT count(DISTINCT target_key) AS c FROM "${this._table}"`)
|
|
223
264
|
};
|
|
224
265
|
}
|
|
225
266
|
/**
|
|
226
267
|
* Recover the established dimension of an existing fragment `vec0` table from its
|
|
227
|
-
* stored `CREATE VIRTUAL TABLE` SQL (`float[<n>]`)
|
|
268
|
+
* stored `CREATE VIRTUAL TABLE` SQL (`float[<n>]`), after checking that the table's
|
|
269
|
+
* auxiliary columns match `AUXILIARY_COLUMNS`. Returns `undefined` when the
|
|
228
270
|
* table does not exist yet (a fresh database — dimension is set by the first add).
|
|
271
|
+
*
|
|
272
|
+
* Throws when a table of that name exists but is not a usable fragment index (a
|
|
273
|
+
* mismatched auxiliary-column set, or no `vec0` embedding column); the caller runs
|
|
274
|
+
* this inside `captureResult`, so it surfaces as a loud `Failure` from `create`.
|
|
275
|
+
* The same stored DDL answers every one of those questions, so the checks cost
|
|
276
|
+
* nothing extra.
|
|
229
277
|
*/
|
|
230
278
|
static _readExistingDimension(db, table) {
|
|
231
279
|
const row = db
|
|
@@ -234,8 +282,78 @@ export class SqliteVecFragmentIndex {
|
|
|
234
282
|
if (row === undefined) {
|
|
235
283
|
return undefined;
|
|
236
284
|
}
|
|
285
|
+
SqliteVecFragmentIndex._verifyAuxiliaryColumns(row.sql, table);
|
|
237
286
|
const match = row.sql.match(/float\[(\d+)\]/);
|
|
238
|
-
|
|
287
|
+
if (match === null) {
|
|
288
|
+
// The auxiliary columns matched but there is no `float[<n>]` embedding column,
|
|
289
|
+
// so this is not a usable fragment index table. Same remedy as a column
|
|
290
|
+
// mismatch — and failing here beats handing back a dimensionless index whose
|
|
291
|
+
// first add would `CREATE VIRTUAL TABLE IF NOT EXISTS` into a no-op.
|
|
292
|
+
throw new Error(`existing table '${table}' has no vec0 embedding column, so it is not a usable fragment ` +
|
|
293
|
+
`index table. Drop it (or pass a fresh tableName) and re-add every fragment.`);
|
|
294
|
+
}
|
|
295
|
+
return Number(match[1]);
|
|
296
|
+
}
|
|
297
|
+
/**
|
|
298
|
+
* Compare an existing table's auxiliary columns against `AUXILIARY_COLUMNS`.
|
|
299
|
+
*
|
|
300
|
+
* `CREATE VIRTUAL TABLE IF NOT EXISTS` is a no-op against an existing table (SQLite
|
|
301
|
+
* never compares schemas) and `vec0` has no `ALTER TABLE ADD COLUMN`, so a table
|
|
302
|
+
* written by an earlier version of this package silently keeps its old columns and
|
|
303
|
+
* only fails later — as an opaque `no such column` when the widened `INSERT` is
|
|
304
|
+
* prepared. Detect it here instead and say what to do about it. Order is not
|
|
305
|
+
* compared: every statement names its columns explicitly, so only the set matters.
|
|
306
|
+
*/
|
|
307
|
+
static _verifyAuxiliaryColumns(sql, table) {
|
|
308
|
+
const found = Array.from(sql.matchAll(AUXILIARY_COLUMN_RE), (m) => m[1]);
|
|
309
|
+
const expected = AUXILIARY_COLUMNS;
|
|
310
|
+
const matches = found.length === expected.length && expected.every((column) => found.includes(column));
|
|
311
|
+
if (!matches) {
|
|
312
|
+
throw new Error(`existing table '${table}' has auxiliary columns [${found.join(', ')}] but this index ` +
|
|
313
|
+
`requires [${expected.join(', ')}] — it was written by a different version of ` +
|
|
314
|
+
`@fgv/ts-agent-memory-sqlite-vec, or it is not a fragment index table at all. vec0 virtual ` +
|
|
315
|
+
`tables cannot be altered in place, so this requires a drop-and-re-index: DROP TABLE ` +
|
|
316
|
+
`"${table}" (or pass a fresh tableName) and re-add every fragment. Fragment vectors are ` +
|
|
317
|
+
`re-derivable from the records, so this costs embedding time, never data.`);
|
|
318
|
+
}
|
|
319
|
+
}
|
|
320
|
+
/**
|
|
321
|
+
* Rebuild the identity fields of a hit from a persisted row, omitting each field
|
|
322
|
+
* the stored fragment did not carry (so a hit is structurally identical to one this
|
|
323
|
+
* index produced before `fragment_id` existed).
|
|
324
|
+
*
|
|
325
|
+
* A row carrying neither identity violates the write-side invariant and could not
|
|
326
|
+
* be resolved by the caller, so it fails loudly instead of yielding an anonymous
|
|
327
|
+
* hit.
|
|
328
|
+
*/
|
|
329
|
+
static _toIdentity(row, key) {
|
|
330
|
+
const locator = SqliteVecFragmentIndex._toLocator(row, key);
|
|
331
|
+
if (locator === undefined && row.fragment_id === null) {
|
|
332
|
+
throw new Error(`fragment '${key}': row carries neither a locator nor a fragment id (corrupt persisted data)`);
|
|
333
|
+
}
|
|
334
|
+
return Object.assign(Object.assign({}, (locator !== undefined ? { locator } : {})), (row.fragment_id !== null ? { fragmentId: row.fragment_id } : {}));
|
|
335
|
+
}
|
|
336
|
+
/**
|
|
337
|
+
* Rebuild a fragment's locator from its persisted offsets, or `undefined` when the
|
|
338
|
+
* fragment was stored without one (both offsets `NULL`).
|
|
339
|
+
*
|
|
340
|
+
* The pair is written all-or-nothing, so a half-`NULL` pair can only come from
|
|
341
|
+
* corrupt / externally-edited data. Throw rather than coerce — `Number(null)` is
|
|
342
|
+
* `0`, which would silently fabricate a span starting at the top of the body.
|
|
343
|
+
*/
|
|
344
|
+
static _toLocator(row, key) {
|
|
345
|
+
const start = row.start_off;
|
|
346
|
+
const end = row.end_off;
|
|
347
|
+
if (start === null && end === null) {
|
|
348
|
+
return undefined;
|
|
349
|
+
}
|
|
350
|
+
if (start === null || end === null) {
|
|
351
|
+
throw new Error(`fragment '${key}': locator has only one of its start/end offsets (corrupt persisted data)`);
|
|
352
|
+
}
|
|
353
|
+
return {
|
|
354
|
+
start: SqliteVecFragmentIndex._toOffset(start, key),
|
|
355
|
+
end: SqliteVecFragmentIndex._toOffset(end, key)
|
|
356
|
+
};
|
|
239
357
|
}
|
|
240
358
|
/** Pack a `Float32Array` as the little-endian byte blob `vec0` stores. Copies, so the caller may reuse its buffer. */
|
|
241
359
|
static _toBlob(vector) {
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"sqliteVecFragmentIndex.js","sourceRoot":"","sources":["../../../src/packlets/sqlite-vec-index/sqliteVecFragmentIndex.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAGH,OAAO,EAAE,IAAI,IAAI,aAAa,EAAE,MAAM,YAAY,CAAC;AACnD,OAAO,EAAU,aAAa,EAAE,IAAI,EAAE,OAAO,EAAE,MAAM,eAAe,CAAC;AACrE,OAAO,EAOL,aAAa,EACd,MAAM,sBAAsB,CAAC;AAG9B,0DAA0D;AAC1D,MAAM,kBAAkB,GAAW,kBAAkB,CAAC;AAEtD,yGAAyG;AACzG,MAAM,aAAa,GAAW,0BAA0B,CAAC;AAgBzD;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA8BG;AACH,MAAM,OAAO,sBAAsB;IAQjC,YAAoB,EAA0B,EAAE,KAAa,EAAE,SAA6B;QAC1F,IAAI,CAAC,GAAG,GAAG,EAAE,CAAC;QACd,IAAI,CAAC,MAAM,GAAG,KAAK,CAAC;QACpB,IAAI,CAAC,UAAU,GAAG,SAAS,CAAC;QAC5B,IAAI,CAAC,MAAM,GAAG,SAAS,KAAK,SAAS,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,IAAI,CAAC,QAAQ,EAAE,CAAC;IACtE,CAAC;IAED,yGAAyG;IACzG,IAAW,WAAW;QACpB,IAAI,IAAI,CAAC,MAAM,KAAK,SAAS,EAAE,CAAC;YAC9B,OAAO,CAAC,CAAC;QACX,CAAC;QACD,8EAA8E;QAC9E,8DAA8D;QAC9D,OAAO,MAAM,CAAE,IAAI,CAAC,MAAM,CAAC,WAAW,CAAC,GAAG,EAA6B,CAAC,CAAC,CAAC,CAAC;IAC7E,CAAC;IAED,kGAAkG;IAClG,IAAW,aAAa;QACtB,IAAI,IAAI,CAAC,MAAM,KAAK,SAAS,EAAE,CAAC;YAC9B,OAAO,CAAC,CAAC;QACX,CAAC;QACD,OAAO,MAAM,CAAE,IAAI,CAAC,MAAM,CAAC,aAAa,CAAC,GAAG,EAA6B,CAAC,CAAC,CAAC,CAAC;IAC/E,CAAC;IAED;;;;;;;;;OASG;IACI,MAAM,CAAC,MAAM,CAAC,MAA2C;;QAC9D,MAAM,KAAK,GAAW,MAAA,MAAM,CAAC,SAAS,mCAAI,kBAAkB,CAAC;QAC7D,IAAI,CAAC,aAAa,CAAC,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC;YAC/B,OAAO,OAAO,CAAC,OAAO,CACpB,IAAI,CAAC,0CAA0C,KAAK,kCAAkC,CAAC,CACxF,CAAC;QACJ,CAAC;QACD,OAAO,OAAO,CAAC,OAAO,CACpB,aAAa,CAAC,GAAG,EAAE;YACjB,aAAa,CAAC,MAAM,CAAC,QAAQ,CAAC,CAAC;YAC/B,MAAM,SAAS,GAAuB,sBAAsB,CAAC,sBAAsB,CACjF,MAAM,CAAC,QAAQ,EACf,KAAK,CACN,CAAC;YACF,OAAO,IAAI,sBAAsB,CAAC,MAAM,CAAC,QAAQ,EAAE,KAAK,EAAE,SAAS,CAAC,CAAC;QACvE,CAAC,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,oDAAoD,CAAC,EAAE,CAAC,CACnF,CAAC;IACJ,CAAC;IAED,sDAAsD;IAC/C,YAAY,CACjB,MAAmB,EACnB,SAA2C;QAE3C,MAAM,GAAG,GAAW,aAAa,CAAC,MAAM,CAAC,CAAC;QAC1C,gFAAgF;QAChF,kFAAkF;QAClF,mFAAmF;QACnF,gFAAgF;QAChF,4DAA4D;QAC5D,IAAI,SAAS,GAAuB,IAAI,CAAC,UAAU,CAAC;QACpD,KAAK,MAAM,QAAQ,IAAI,SAAS,EAAE,CAAC;YACjC,IAAI,QAAQ,CAAC,MAAM,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;gBACjC,OAAO,OAAO,CAAC,OAAO,CAAC,IAAI,CAAC,+BAA+B,GAAG,0BAA0B,CAAC,CAAC,CAAC;YAC7F,CAAC;YACD,gFAAgF;YAChF,6EAA6E;YAC7E,iFAAiF;YACjF,6EAA6E;YAC7E,IAAI,CAAC,MAAM,CAAC,aAAa,CAAC,QAAQ,CAAC,OAAO,CAAC,KAAK,CAAC,IAAI,CAAC,MAAM,CAAC,aAAa,CAAC,QAAQ,CAAC,OAAO,CAAC,GAAG,CAAC,EAAE,CAAC;gBACjG,OAAO,OAAO,CAAC,OAAO,CACpB,IAAI,CACF,+BAA+B,GAAG,eAAe,QAAQ,CAAC,OAAO,CAAC,KAAK,KAAK,QAAQ,CAAC,OAAO,CAAC,GAAG,iCAAiC,CAClI,CACF,CAAC;YACJ,CAAC;YACD,IAAI,SAAS,KAAK,SAAS,EAAE,CAAC;gBAC5B,SAAS,GAAG,QAAQ,CAAC,MAAM,CAAC,MAAM,CAAC;YACrC,CAAC;iBAAM,IAAI,QAAQ,CAAC,MAAM,CAAC,MAAM,KAAK,SAAS,EAAE,CAAC;gBAChD,OAAO,OAAO,CAAC,OAAO,CACpB,IAAI,CACF,+BAA+B,GAAG,yBAAyB,QAAQ,CAAC,MAAM,CAAC,MAAM,mCAAmC,SAAS,EAAE,CAChI,CACF,CAAC;YACJ,CAAC;QACH,CAAC;QACD,OAAO,OAAO,CAAC,OAAO,CACpB,aAAa,CAAC,GAAG,EAAE;YACjB,6EAA6E;YAC7E,0EAA0E;YAC1E,IAAI,IAAI,CAAC,MAAM,KAAK,SAAS,EAAE,CAAC;gBAC9B,IAAI,SAAS,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;oBAC3B,8DAA8D;oBAC9D,OAAO,CAAC,CAAC;gBACX,CAAC;gBACD,wEAAwE;gBACxE,yEAAyE;gBACzE,uEAAuE;gBACvE,uDAAuD;gBACvD,MAAM,WAAW,GAAW,SAAS,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,MAAM,CAAC;gBACvD,IAAI,CAAC,YAAY,CAAC,WAAW,CAAC,CAAC;gBAC/B,IAAI,CAAC,UAAU,GAAG,WAAW,CAAC;gBAC9B,IAAI,CAAC,MAAM,GAAG,IAAI,CAAC,QAAQ,EAAE,CAAC;YAChC,CAAC;YACD,IAAI,CAAC,MAAM,CAAC,OAAO,CAAC,GAAG,EAAE,SAAS,CAAC,CAAC;YACpC,OAAO,SAAS,CAAC,MAAM,CAAC;QAC1B,CAAC,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,+BAA+B,GAAG,MAAM,CAAC,EAAE,CAAC,CACvE,CAAC;IACJ,CAAC;IAED,gDAAgD;IACzC,MAAM,CAAC,MAAmB;QAC/B,OAAO,OAAO,CAAC,OAAO,CACpB,aAAa,CAAC,GAAG,EAAE;YACjB,6EAA6E;YAC7E,6BAA6B;YAC7B,IAAI,IAAI,CAAC,MAAM,KAAK,SAAS,EAAE,CAAC;gBAC9B,IAAI,CAAC,MAAM,CAAC,cAAc,CAAC,GAAG,CAAC,aAAa,CAAC,MAAM,CAAC,CAAC,CAAC;YACxD,CAAC;YACD,OAAO,MAAM,CAAC;QAChB,CAAC,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,kCAAkC,aAAa,CAAC,MAAM,CAAC,MAAM,CAAC,EAAE,CAAC,CAC5F,CAAC;IACJ,CAAC;IAED,+CAA+C;IACxC,KAAK,CACV,MAAoB,EACpB,IAAY,EACZ,YAAqB;QAErB,IAAI,IAAI,IAAI,CAAC,IAAI,IAAI,CAAC,MAAM,KAAK,SAAS,EAAE,CAAC;YAC3C,OAAO,OAAO,CAAC,OAAO,CAAC,OAAO,CAAC,EAAE,CAAC,CAAC,CAAC;QACtC,CAAC;QACD,IAAI,MAAM,CAAC,MAAM,KAAK,IAAI,CAAC,UAAU,EAAE,CAAC;YACtC,OAAO,OAAO,CAAC,OAAO,CACpB,IAAI,CACF,mCAAmC,MAAM,CAAC,MAAM,mCAAmC,IAAI,CAAC,UAAU,EAAE,CACrG,CACF,CAAC;QACJ,CAAC;QACD,MAAM,KAAK,GAAwB,IAAI,CAAC,MAAM,CAAC;QAC/C,OAAO,OAAO,CAAC,OAAO,CACpB,aAAa,CAAiC,GAAG,EAAE;;YACjD,6EAA6E;YAC7E,6EAA6E;YAC7E,2EAA2E;YAC3E,wDAAwD;YACxD,MAAM,MAAM,GACV,YAAY,KAAK,SAAS,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,MAAM,CAAE,KAAK,CAAC,aAAa,CAAC,GAAG,EAA6B,CAAC,CAAC,CAAC,CAAC;YACtG,IAAI,MAAM,IAAI,CAAC,EAAE,CAAC;gBAChB,OAAO,EAAE,CAAC;YACZ,CAAC;YACD,MAAM,IAAI,GAA2B,KAAK,CAAC,KAAK,CAAC,GAAG,CAClD,sBAAsB,CAAC,OAAO,CAAC,MAAM,CAAC,EACtC,MAAM,CACmB,CAAC;YAC5B,0EAA0E;YAC1E,mEAAmE;YACnE,MAAM,IAAI,GAAsB,EAAE,CAAC;YACnC,MAAM,SAAS,GAAwB,IAAI,GAAG,EAAkB,CAAC;YACjE,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;gBACvB,IAAI,IAAI,CAAC,MAAM,IAAI,IAAI,EAAE,CAAC;oBACxB,MAAM;gBACR,CAAC;gBACD,IAAI,YAAY,KAAK,SAAS,EAAE,CAAC;oBAC/B,MAAM,IAAI,GAAW,MAAA,SAAS,CAAC,GAAG,CAAC,GAAG,CAAC,UAAU,CAAC,mCAAI,CAAC,CAAC;oBACxD,IAAI,IAAI,IAAI,YAAY,EAAE,CAAC;wBACzB,SAAS;oBACX,CAAC;oBACD,SAAS,CAAC,GAAG,CAAC,GAAG,CAAC,UAAU,EAAE,IAAI,GAAG,CAAC,CAAC,CAAC;gBAC1C,CAAC;gBACD,MAAM,GAAG,GAAW,GAAG,CAAC,UAAU,CAAC;gBACnC,IAAI,CAAC,IAAI,CAAC;oBACR,MAAM,EAAE,sBAAsB,CAAC,SAAS,CAAC,GAAG,CAAC;oBAC7C,KAAK,EAAE,CAAC,GAAG,GAAG,CAAC,QAAQ;oBACvB,OAAO,EAAE;wBACP,KAAK,EAAE,sBAAsB,CAAC,SAAS,CAAC,GAAG,CAAC,SAAS,EAAE,GAAG,CAAC;wBAC3D,GAAG,EAAE,sBAAsB,CAAC,SAAS,CAAC,GAAG,CAAC,OAAO,EAAE,GAAG,CAAC;qBACxD;iBACF,CAAC,CAAC;YACL,CAAC;YACD,OAAO,IAAI,CAAC;QACd,CAAC,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,iCAAiC,CAAC,EAAE,CAAC,CAChE,CAAC;IACJ,CAAC;IAED,+EAA+E;IACvE,YAAY,CAAC,SAAiB;QACpC,IAAI,CAAC,GAAG,CAAC,IAAI,CACX,uCAAuC,IAAI,CAAC,MAAM,eAAe;YAC/D,kDAAkD,SAAS,4BAA4B;YACvF,uCAAuC,CAC1C,CAAC;IACJ,CAAC;IAED,4EAA4E;IACpE,QAAQ;QACd,MAAM,GAAG,GAA4B,IAAI,CAAC,GAAG,CAAC,OAAO,CACnD,gBAAgB,IAAI,CAAC,MAAM,wBAAwB,CACpD,CAAC;QACF,MAAM,GAAG,GAA4B,IAAI,CAAC,GAAG,CAAC,OAAO,CACnD,gBAAgB,IAAI,CAAC,MAAM,kEAAkE,CAC9F,CAAC;QACF,iFAAiF;QACjF,gEAAgE;QAChE,MAAM,UAAU,GAEZ,IAAI,CAAC,GAAG,CAAC,WAAW,CAAC,CAAC,GAAW,EAAE,SAA2C,EAAE,EAAE;YACpF,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;YACb,KAAK,MAAM,QAAQ,IAAI,SAAS,EAAE,CAAC;gBACjC,GAAG,CAAC,GAAG,CACL,GAAG,EACH,sBAAsB,CAAC,OAAO,CAAC,QAAQ,CAAC,MAAM,CAAC;gBAC/C,sEAAsE;gBACtE,MAAM,CAAC,QAAQ,CAAC,OAAO,CAAC,KAAK,CAAC,EAC9B,MAAM,CAAC,QAAQ,CAAC,OAAO,CAAC,GAAG,CAAC,CAC7B,CAAC;YACJ,CAAC;QACH,CAAC,CAAC,CAAC;QACH,OAAO;YACL,cAAc,EAAE,GAAG;YACnB,OAAO,EAAE,CAAC,GAAW,EAAE,SAA2C,EAAQ,EAAE;gBAC1E,UAAU,CAAC,GAAG,EAAE,SAAS,CAAC,CAAC;YAC7B,CAAC;YACD,KAAK,EAAE,IAAI,CAAC,GAAG,CAAC,OAAO,CACrB,yDAAyD,IAAI,CAAC,MAAM,qCAAqC,CAC1G;YACD,aAAa,EAAE,IAAI,CAAC,GAAG,CAAC,OAAO,CAAC,8BAA8B,IAAI,CAAC,MAAM,GAAG,CAAC;YAC7E,WAAW,EAAE,IAAI,CAAC,GAAG,CAAC,OAAO,CAAC,gDAAgD,IAAI,CAAC,MAAM,GAAG,CAAC;SAC9F,CAAC;IACJ,CAAC;IAED;;;;OAIG;IACK,MAAM,CAAC,sBAAsB,CAAC,EAA0B,EAAE,KAAa;QAC7E,MAAM,GAAG,GAAgC,EAAE;aACxC,OAAO,CAAC,iEAAiE,CAAC;aAC1E,GAAG,CAAC,KAAK,CAAgC,CAAC;QAC7C,IAAI,GAAG,KAAK,SAAS,EAAE,CAAC;YACtB,OAAO,SAAS,CAAC;QACnB,CAAC;QACD,MAAM,KAAK,GAA4B,GAAG,CAAC,GAAG,CAAC,KAAK,CAAC,gBAAgB,CAAC,CAAC;QACvE,OAAO,KAAK,KAAK,IAAI,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC;IACvD,CAAC;IAED,sHAAsH;IAC9G,MAAM,CAAC,OAAO,CAAC,MAAoB;QACzC,OAAO,IAAI,UAAU,CAAC,YAAY,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC,MAAM,CAAC,CAAC;IAC1D,CAAC;IAED;;;;;;OAMG;IACK,MAAM,CAAC,SAAS,CAAC,GAAW;QAClC,MAAM,GAAG,GAAW,GAAG,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;QACtC,IAAI,GAAG,GAAG,CAAC,EAAE,CAAC;YACZ,MAAM,IAAI,KAAK,CAAC,yBAAyB,GAAG,wDAAwD,CAAC,CAAC;QACxG,CAAC;QACD,OAAO;YACL,KAAK,EAAE,GAAG,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,CAA8B;YACrD,EAAE,EAAE,GAAG,CAAC,KAAK,CAAC,GAAG,GAAG,CAAC,CAAwB;SAC9C,CAAC;IACJ,CAAC;IAED;;;;;;;OAOG;IACK,MAAM,CAAC,SAAS,CAAC,KAAsB,EAAE,GAAW;QAC1D,MAAM,CAAC,GAAW,MAAM,CAAC,KAAK,CAAC,CAAC;QAChC,IAAI,CAAC,MAAM,CAAC,aAAa,CAAC,CAAC,CAAC,EAAE,CAAC;YAC7B,MAAM,IAAI,KAAK,CACb,aAAa,GAAG,qBAAqB,MAAM,CAAC,KAAK,CAAC,iDAAiD,CACpG,CAAC;QACJ,CAAC;QACD,OAAO,CAAC,CAAC;IACX,CAAC;CACF","sourcesContent":["/*\n * Copyright (c) 2026 Erik Fortune\n * SPDX-License-Identifier: MIT\n */\n\nimport type BetterSqlite3 from 'better-sqlite3';\nimport { load as loadSqliteVec } from 'sqlite-vec';\nimport { Result, captureResult, fail, succeed } from '@fgv/ts-utils';\nimport {\n IEdgeTarget,\n IEmbeddedFragment,\n IFragmentVectorIndex,\n IVectorQueryHit,\n MemoryId,\n MemoryScopeKey,\n edgeTargetKey\n} from '@fgv/ts-agent-memory';\nimport { ISqliteVecFragmentIndexCreateParams } from './model';\n\n/** Default name for the fragment `vec0` virtual table. */\nconst DEFAULT_TABLE_NAME: string = 'memory_fragments';\n\n/** A simple SQL identifier — the only shape allowed for the table name (it is interpolated into DDL). */\nconst IDENTIFIER_RE: RegExp = /^[A-Za-z_][A-Za-z0-9_]*$/;\n\n/**\n * One KNN row as returned by the fragment `vec0` MATCH query. The offset columns are\n * typed `number | bigint` because `better-sqlite3` returns integer columns as\n * `bigint` when a consumer enables its safe-integer mode (`defaultSafeIntegers`);\n * {@link SqliteVecFragmentIndex._toOffset} coerces them to a plain `number` (and\n * fails loudly on an out-of-safe-range value) before they reach the public locator.\n */\ninterface IKnnRow {\n readonly target_key: string;\n readonly start_off: number | bigint;\n readonly end_off: number | bigint;\n readonly distance: number;\n}\n\n/**\n * A persistent, `sqlite-vec`-backed `IFragmentVectorIndex` (from\n * `@fgv/ts-agent-memory`) — the fragment-granular sibling of\n * {@link SqliteVecVectorIndex}, and the **durable** counterpart to the in-memory\n * `InMemoryFragmentCosineIndex`.\n *\n * @remarks\n * Where {@link SqliteVecVectorIndex} keys one vector per record on a\n * `target_key` primary key, this index holds **many** vectors per record — one per\n * in-record `[start, end)` span — so it keys the `vec0` table on `target_key` as a\n * **`PARTITION KEY`** (many rows may share it) and stores each fragment's locator\n * offsets in two auxiliary columns (`+start_off`, `+end_off`) that ride alongside\n * the vector and are returned on query but never filtered. A query is a brute-force\n * `vec0` KNN scan across all partitions returning per-fragment hits, each carrying\n * its record `target` and the matched `locator`.\n *\n * Semantics match `InMemoryFragmentCosineIndex` exactly: `addFragments` is\n * whole-record-replace (a single transaction deletes every prior fragment of the\n * target, then inserts the new set), `remove` drops every fragment of a target,\n * and `query` applies the optional `maxPerRecord` cap **during selection, before\n * the topK cut** — so one long document cannot crowd others out. The dimension is\n * established by the first `addFragments` (the `vec0` column is fixed-width) and\n * recovered from the table schema when a persistent file is reopened; similarity is\n * cosine (`score = 1 - cosineDistance`), byte-identical to the in-memory index.\n * Large-N ANN indexing is explicitly out of scope, same regime as the record index.\n *\n * The `better-sqlite3` `Database` is consumer-owned (bring-your-own): this index\n * loads the `sqlite-vec` extension onto it and reads/writes the table, but never\n * opens or closes the connection.\n * @public\n */\nexport class SqliteVecFragmentIndex implements IFragmentVectorIndex {\n private readonly _db: BetterSqlite3.Database;\n private readonly _table: string;\n /** The dimension of every stored fragment vector; `undefined` until the table exists. */\n private _dimension: number | undefined;\n /** Prepared statements; created once the table exists (established or recovered). */\n private _stmts: IFragmentStatements | undefined;\n\n private constructor(db: BetterSqlite3.Database, table: string, dimension: number | undefined) {\n this._db = db;\n this._table = table;\n this._dimension = dimension;\n this._stmts = dimension === undefined ? undefined : this._prepare();\n }\n\n /** The number of records that currently have at least one stored fragment. Zero before the first add. */\n public get recordCount(): number {\n if (this._stmts === undefined) {\n return 0;\n }\n // `Number(...)` narrows the count in case the consumer enabled better-sqlite3\n // safe-integer mode (which returns `count(*)` as a `bigint`).\n return Number((this._stmts.recordCount.get() as { c: number | bigint }).c);\n }\n\n /** The total number of fragments currently held across all records. Zero before the first add. */\n public get fragmentCount(): number {\n if (this._stmts === undefined) {\n return 0;\n }\n return Number((this._stmts.fragmentCount.get() as { c: number | bigint }).c);\n }\n\n /**\n * Family-convention factory. Loads the `sqlite-vec` extension onto the supplied\n * `better-sqlite3` connection and, if the fragment table already exists (a\n * reopened persistent file), recovers its established dimension so no\n * re-embedding is needed on open.\n *\n * @param params - See {@link ISqliteVecFragmentIndexCreateParams}.\n * @returns `Success` with the index, or `Failure` if the table name is not a\n * simple identifier or the extension fails to load.\n */\n public static create(params: ISqliteVecFragmentIndexCreateParams): Promise<Result<SqliteVecFragmentIndex>> {\n const table: string = params.tableName ?? DEFAULT_TABLE_NAME;\n if (!IDENTIFIER_RE.test(table)) {\n return Promise.resolve(\n fail(`sqlite-vec fragment index: table name '${table}' is not a simple SQL identifier`)\n );\n }\n return Promise.resolve(\n captureResult(() => {\n loadSqliteVec(params.database);\n const dimension: number | undefined = SqliteVecFragmentIndex._readExistingDimension(\n params.database,\n table\n );\n return new SqliteVecFragmentIndex(params.database, table, dimension);\n }).withErrorFormat((e) => `sqlite-vec fragment index: failed to initialize: ${e}`)\n );\n }\n\n /** {@inheritDoc IFragmentVectorIndex.addFragments} */\n public addFragments(\n target: IEdgeTarget,\n fragments: ReadonlyArray<IEmbeddedFragment>\n ): Promise<Result<number>> {\n const key: string = edgeTargetKey(target);\n // Validate every fragment before touching the database, so a bad fragment never\n // leaves the record half-replaced or the dimension half-established (whole-record\n // replace is all-or-nothing). The effective dimension is the established one, or —\n // on a still-dimensionless index — the first fragment's length; it is committed\n // (via table creation) only once the whole batch validates.\n let dimension: number | undefined = this._dimension;\n for (const fragment of fragments) {\n if (fragment.vector.length === 0) {\n return Promise.resolve(fail(`fragment index: cannot add '${key}': empty fragment vector`));\n }\n // Locator offsets are persisted as SQLite integers (bound via BigInt). Reject a\n // non-safe-integer offset up front with a clear message, rather than letting\n // `BigInt(nonInteger)` throw cryptically inside the write transaction OR storing\n // a value the read-side `_toOffset` guard would later reject on every query.\n if (!Number.isSafeInteger(fragment.locator.start) || !Number.isSafeInteger(fragment.locator.end)) {\n return Promise.resolve(\n fail(\n `fragment index: cannot add '${key}': locator [${fragment.locator.start}, ${fragment.locator.end}) offsets must be safe integers`\n )\n );\n }\n if (dimension === undefined) {\n dimension = fragment.vector.length;\n } else if (fragment.vector.length !== dimension) {\n return Promise.resolve(\n fail(\n `fragment index: cannot add '${key}': fragment dimension ${fragment.vector.length} does not match index dimension ${dimension}`\n )\n );\n }\n }\n return Promise.resolve(\n captureResult(() => {\n // A same-target re-author (or an empty batch) still needs the table to exist\n // to delete prior fragments; create it lazily on the first non-empty add.\n if (this._stmts === undefined) {\n if (fragments.length === 0) {\n // Nothing stored yet and nothing to store: no table, no work.\n return 0;\n }\n // `fragments` is non-empty here (the empty case returned above), so the\n // validation loop proved every fragment shares `fragments[0]`'s length —\n // which IS the dimension to establish. Read it straight from the first\n // fragment: no cast, no invariant-dependent narrowing.\n const established: number = fragments[0].vector.length;\n this._createTable(established);\n this._dimension = established;\n this._stmts = this._prepare();\n }\n this._stmts.replace(key, fragments);\n return fragments.length;\n }).withErrorFormat((e) => `fragment index: cannot add '${key}': ${e}`)\n );\n }\n\n /** {@inheritDoc IFragmentVectorIndex.remove} */\n public remove(target: IEdgeTarget): Promise<Result<IEdgeTarget>> {\n return Promise.resolve(\n captureResult(() => {\n // Idempotent: removing a target with no fragments (or before any add created\n // the table) still succeeds.\n if (this._stmts !== undefined) {\n this._stmts.deleteByTarget.run(edgeTargetKey(target));\n }\n return target;\n }).withErrorFormat((e) => `fragment index: cannot remove '${edgeTargetKey(target)}': ${e}`)\n );\n }\n\n /** {@inheritDoc IFragmentVectorIndex.query} */\n public query(\n vector: Float32Array,\n topK: number,\n maxPerRecord?: number\n ): Promise<Result<ReadonlyArray<IVectorQueryHit>>> {\n if (topK <= 0 || this._stmts === undefined) {\n return Promise.resolve(succeed([]));\n }\n if (vector.length !== this._dimension) {\n return Promise.resolve(\n fail(\n `fragment index: query dimension ${vector.length} does not match index dimension ${this._dimension}`\n )\n );\n }\n const stmts: IFragmentStatements = this._stmts;\n return Promise.resolve(\n captureResult<ReadonlyArray<IVectorQueryHit>>(() => {\n // With a per-record cap the topK winners may lie past the first topK rows (a\n // capped record's later fragments are skipped), so fetch the full ranked set\n // and apply the cap + topK cut here — exactly as the in-memory index does.\n // Uncapped, KNN's own `k = topK` is already the answer.\n const fetchK: number =\n maxPerRecord === undefined ? topK : Number((stmts.fragmentCount.get() as { c: number | bigint }).c);\n if (fetchK <= 0) {\n return [];\n }\n const rows: ReadonlyArray<IKnnRow> = stmts.query.all(\n SqliteVecFragmentIndex._toBlob(vector),\n fetchK\n ) as ReadonlyArray<IKnnRow>;\n // sqlite-vec returns rows ascending by distance (nearest first); score is\n // `1 - cosineDistance`, so this order is already descending score.\n const hits: IVectorQueryHit[] = [];\n const perRecord: Map<string, number> = new Map<string, number>();\n for (const row of rows) {\n if (hits.length >= topK) {\n break;\n }\n if (maxPerRecord !== undefined) {\n const used: number = perRecord.get(row.target_key) ?? 0;\n if (used >= maxPerRecord) {\n continue;\n }\n perRecord.set(row.target_key, used + 1);\n }\n const key: string = row.target_key;\n hits.push({\n target: SqliteVecFragmentIndex._parseKey(key),\n score: 1 - row.distance,\n locator: {\n start: SqliteVecFragmentIndex._toOffset(row.start_off, key),\n end: SqliteVecFragmentIndex._toOffset(row.end_off, key)\n }\n });\n }\n return hits;\n }).withErrorFormat((e) => `fragment index: query failed: ${e}`)\n );\n }\n\n /** Create the fragment `vec0` virtual table with the established dimension. */\n private _createTable(dimension: number): void {\n this._db.exec(\n `CREATE VIRTUAL TABLE IF NOT EXISTS \"${this._table}\" USING vec0(` +\n `target_key TEXT PARTITION KEY, embedding float[${dimension}] distance_metric=cosine, ` +\n `+start_off integer, +end_off integer)`\n );\n }\n\n /** Prepare the statements the index reuses. Requires the table to exist. */\n private _prepare(): IFragmentStatements {\n const del: BetterSqlite3.Statement = this._db.prepare(\n `DELETE FROM \"${this._table}\" WHERE target_key = ?`\n );\n const ins: BetterSqlite3.Statement = this._db.prepare(\n `INSERT INTO \"${this._table}\"(target_key, embedding, start_off, end_off) VALUES (?, ?, ?, ?)`\n );\n // Whole-record replace: drop every prior fragment of the target, then insert the\n // new set, atomically. An empty set collapses to a pure delete.\n const replaceTxn: BetterSqlite3.Transaction<\n (key: string, fragments: ReadonlyArray<IEmbeddedFragment>) => void\n > = this._db.transaction((key: string, fragments: ReadonlyArray<IEmbeddedFragment>) => {\n del.run(key);\n for (const fragment of fragments) {\n ins.run(\n key,\n SqliteVecFragmentIndex._toBlob(fragment.vector),\n // vec0 typed columns reject a JS float; bind the offsets as integers.\n BigInt(fragment.locator.start),\n BigInt(fragment.locator.end)\n );\n }\n });\n return {\n deleteByTarget: del,\n replace: (key: string, fragments: ReadonlyArray<IEmbeddedFragment>): void => {\n replaceTxn(key, fragments);\n },\n query: this._db.prepare(\n `SELECT target_key, start_off, end_off, distance FROM \"${this._table}\" WHERE embedding MATCH ? AND k = ?`\n ),\n fragmentCount: this._db.prepare(`SELECT count(*) AS c FROM \"${this._table}\"`),\n recordCount: this._db.prepare(`SELECT count(DISTINCT target_key) AS c FROM \"${this._table}\"`)\n };\n }\n\n /**\n * Recover the established dimension of an existing fragment `vec0` table from its\n * stored `CREATE VIRTUAL TABLE` SQL (`float[<n>]`). Returns `undefined` when the\n * table does not exist yet (a fresh database — dimension is set by the first add).\n */\n private static _readExistingDimension(db: BetterSqlite3.Database, table: string): number | undefined {\n const row: { sql: string } | undefined = db\n .prepare(\"SELECT sql FROM sqlite_master WHERE type = 'table' AND name = ?\")\n .get(table) as { sql: string } | undefined;\n if (row === undefined) {\n return undefined;\n }\n const match: RegExpMatchArray | null = row.sql.match(/float\\[(\\d+)\\]/);\n return match === null ? undefined : Number(match[1]);\n }\n\n /** Pack a `Float32Array` as the little-endian byte blob `vec0` stores. Copies, so the caller may reuse its buffer. */\n private static _toBlob(vector: Float32Array): Uint8Array {\n return new Uint8Array(Float32Array.from(vector).buffer);\n }\n\n /**\n * Reverse `edgeTargetKey` — the canonical key is `scope\\0id` with NUL excluded\n * from both components, so the first NUL splits it unambiguously. A key with no\n * NUL cannot have been written by `edgeTargetKey`; rather than fabricate a wrong\n * `(scope, id)` from corrupt / externally-edited table data, throw so the query\n * surfaces it as a loud `Failure`.\n */\n private static _parseKey(key: string): IEdgeTarget {\n const nul: number = key.indexOf('\\0');\n if (nul < 0) {\n throw new Error(`malformed target key '${key}': missing scope/id separator (corrupt persisted data)`);\n }\n return {\n scope: key.slice(0, nul) as unknown as MemoryScopeKey,\n id: key.slice(nul + 1) as unknown as MemoryId\n };\n }\n\n /**\n * Coerce a persisted locator offset to a plain `number`. `better-sqlite3` returns\n * integer columns as `bigint` under safe-integer mode, so an offset can arrive as\n * either; both narrow to `number` here. A value outside the safe-integer range\n * (only reachable via corrupt / externally-edited data — the index only ever\n * writes in-document offsets) throws rather than silently losing precision, so the\n * query surfaces it as a loud `Failure`.\n */\n private static _toOffset(value: number | bigint, key: string): number {\n const n: number = Number(value);\n if (!Number.isSafeInteger(n)) {\n throw new Error(\n `fragment '${key}': locator offset ${String(value)} is not a safe integer (corrupt persisted data)`\n );\n }\n return n;\n }\n}\n\n/** The prepared statements / helpers the fragment index reuses once its table exists. */\ninterface IFragmentStatements {\n readonly deleteByTarget: BetterSqlite3.Statement;\n readonly replace: (key: string, fragments: ReadonlyArray<IEmbeddedFragment>) => void;\n readonly query: BetterSqlite3.Statement;\n readonly fragmentCount: BetterSqlite3.Statement;\n readonly recordCount: BetterSqlite3.Statement;\n}\n"]}
|
|
1
|
+
{"version":3,"file":"sqliteVecFragmentIndex.js","sourceRoot":"","sources":["../../../src/packlets/sqlite-vec-index/sqliteVecFragmentIndex.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAGH,OAAO,EAAE,IAAI,IAAI,aAAa,EAAE,MAAM,YAAY,CAAC;AACnD,OAAO,EAAU,aAAa,EAAE,IAAI,EAAE,OAAO,EAAE,MAAM,eAAe,CAAC;AACrE,OAAO,EAQL,aAAa,EACd,MAAM,sBAAsB,CAAC;AAG9B,0DAA0D;AAC1D,MAAM,kBAAkB,GAAW,kBAAkB,CAAC;AAEtD,yGAAyG;AACzG,MAAM,aAAa,GAAW,0BAA0B,CAAC;AAEzD;;;;;GAKG;AACH,MAAM,iBAAiB,GAA0B,CAAC,WAAW,EAAE,SAAS,EAAE,aAAa,CAAC,CAAC;AAEzF;;;;GAIG;AACH,MAAM,mBAAmB,GAAW,gCAAgC,CAAC;AA8BrE;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA2CG;AACH,MAAM,OAAO,sBAAsB;IAQjC,YAAoB,EAA0B,EAAE,KAAa,EAAE,SAA6B;QAC1F,IAAI,CAAC,GAAG,GAAG,EAAE,CAAC;QACd,IAAI,CAAC,MAAM,GAAG,KAAK,CAAC;QACpB,IAAI,CAAC,UAAU,GAAG,SAAS,CAAC;QAC5B,IAAI,CAAC,MAAM,GAAG,SAAS,KAAK,SAAS,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,IAAI,CAAC,QAAQ,EAAE,CAAC;IACtE,CAAC;IAED,yGAAyG;IACzG,IAAW,WAAW;QACpB,IAAI,IAAI,CAAC,MAAM,KAAK,SAAS,EAAE,CAAC;YAC9B,OAAO,CAAC,CAAC;QACX,CAAC;QACD,8EAA8E;QAC9E,8DAA8D;QAC9D,OAAO,MAAM,CAAE,IAAI,CAAC,MAAM,CAAC,WAAW,CAAC,GAAG,EAA6B,CAAC,CAAC,CAAC,CAAC;IAC7E,CAAC;IAED,kGAAkG;IAClG,IAAW,aAAa;QACtB,IAAI,IAAI,CAAC,MAAM,KAAK,SAAS,EAAE,CAAC;YAC9B,OAAO,CAAC,CAAC;QACX,CAAC;QACD,OAAO,MAAM,CAAE,IAAI,CAAC,MAAM,CAAC,aAAa,CAAC,GAAG,EAA6B,CAAC,CAAC,CAAC,CAAC;IAC/E,CAAC;IAED;;;;;;;;;;;;OAYG;IACI,MAAM,CAAC,MAAM,CAAC,MAA2C;;QAC9D,MAAM,KAAK,GAAW,MAAA,MAAM,CAAC,SAAS,mCAAI,kBAAkB,CAAC;QAC7D,IAAI,CAAC,aAAa,CAAC,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC;YAC/B,OAAO,OAAO,CAAC,OAAO,CACpB,IAAI,CAAC,0CAA0C,KAAK,kCAAkC,CAAC,CACxF,CAAC;QACJ,CAAC;QACD,OAAO,OAAO,CAAC,OAAO,CACpB,aAAa,CAAC,GAAG,EAAE;YACjB,aAAa,CAAC,MAAM,CAAC,QAAQ,CAAC,CAAC;YAC/B,MAAM,SAAS,GAAuB,sBAAsB,CAAC,sBAAsB,CACjF,MAAM,CAAC,QAAQ,EACf,KAAK,CACN,CAAC;YACF,OAAO,IAAI,sBAAsB,CAAC,MAAM,CAAC,QAAQ,EAAE,KAAK,EAAE,SAAS,CAAC,CAAC;QACvE,CAAC,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,oDAAoD,CAAC,EAAE,CAAC,CACnF,CAAC;IACJ,CAAC;IAED,sDAAsD;IAC/C,YAAY,CACjB,MAAmB,EACnB,SAA2C;QAE3C,MAAM,GAAG,GAAW,aAAa,CAAC,MAAM,CAAC,CAAC;QAC1C,gFAAgF;QAChF,kFAAkF;QAClF,mFAAmF;QACnF,gFAAgF;QAChF,4DAA4D;QAC5D,IAAI,SAAS,GAAuB,IAAI,CAAC,UAAU,CAAC;QACpD,KAAK,MAAM,QAAQ,IAAI,SAAS,EAAE,CAAC;YACjC,IAAI,QAAQ,CAAC,MAAM,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;gBACjC,OAAO,OAAO,CAAC,OAAO,CAAC,IAAI,CAAC,+BAA+B,GAAG,0BAA0B,CAAC,CAAC,CAAC;YAC7F,CAAC;YACD,gFAAgF;YAChF,4EAA4E;YAC5E,uEAAuE;YACvE,IAAI,QAAQ,CAAC,OAAO,KAAK,SAAS,IAAI,QAAQ,CAAC,UAAU,KAAK,SAAS,EAAE,CAAC;gBACxE,OAAO,OAAO,CAAC,OAAO,CACpB,IAAI,CACF,+BAA+B,GAAG,gEAAgE,CACnG,CACF,CAAC;YACJ,CAAC;YACD,gFAAgF;YAChF,6EAA6E;YAC7E,iFAAiF;YACjF,6EAA6E;YAC7E,wEAAwE;YACxE,IACE,QAAQ,CAAC,OAAO,KAAK,SAAS;gBAC9B,CAAC,CAAC,MAAM,CAAC,aAAa,CAAC,QAAQ,CAAC,OAAO,CAAC,KAAK,CAAC,IAAI,CAAC,MAAM,CAAC,aAAa,CAAC,QAAQ,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,EAC9F,CAAC;gBACD,OAAO,OAAO,CAAC,OAAO,CACpB,IAAI,CACF,+BAA+B,GAAG,eAAe,QAAQ,CAAC,OAAO,CAAC,KAAK,KAAK,QAAQ,CAAC,OAAO,CAAC,GAAG,iCAAiC,CAClI,CACF,CAAC;YACJ,CAAC;YACD,IAAI,SAAS,KAAK,SAAS,EAAE,CAAC;gBAC5B,SAAS,GAAG,QAAQ,CAAC,MAAM,CAAC,MAAM,CAAC;YACrC,CAAC;iBAAM,IAAI,QAAQ,CAAC,MAAM,CAAC,MAAM,KAAK,SAAS,EAAE,CAAC;gBAChD,OAAO,OAAO,CAAC,OAAO,CACpB,IAAI,CACF,+BAA+B,GAAG,yBAAyB,QAAQ,CAAC,MAAM,CAAC,MAAM,mCAAmC,SAAS,EAAE,CAChI,CACF,CAAC;YACJ,CAAC;QACH,CAAC;QACD,OAAO,OAAO,CAAC,OAAO,CACpB,aAAa,CAAC,GAAG,EAAE;YACjB,6EAA6E;YAC7E,0EAA0E;YAC1E,IAAI,IAAI,CAAC,MAAM,KAAK,SAAS,EAAE,CAAC;gBAC9B,IAAI,SAAS,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;oBAC3B,8DAA8D;oBAC9D,OAAO,CAAC,CAAC;gBACX,CAAC;gBACD,wEAAwE;gBACxE,yEAAyE;gBACzE,uEAAuE;gBACvE,uDAAuD;gBACvD,MAAM,WAAW,GAAW,SAAS,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,MAAM,CAAC;gBACvD,IAAI,CAAC,YAAY,CAAC,WAAW,CAAC,CAAC;gBAC/B,IAAI,CAAC,UAAU,GAAG,WAAW,CAAC;gBAC9B,IAAI,CAAC,MAAM,GAAG,IAAI,CAAC,QAAQ,EAAE,CAAC;YAChC,CAAC;YACD,IAAI,CAAC,MAAM,CAAC,OAAO,CAAC,GAAG,EAAE,SAAS,CAAC,CAAC;YACpC,OAAO,SAAS,CAAC,MAAM,CAAC;QAC1B,CAAC,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,+BAA+B,GAAG,MAAM,CAAC,EAAE,CAAC,CACvE,CAAC;IACJ,CAAC;IAED,gDAAgD;IACzC,MAAM,CAAC,MAAmB;QAC/B,OAAO,OAAO,CAAC,OAAO,CACpB,aAAa,CAAC,GAAG,EAAE;YACjB,6EAA6E;YAC7E,6BAA6B;YAC7B,IAAI,IAAI,CAAC,MAAM,KAAK,SAAS,EAAE,CAAC;gBAC9B,IAAI,CAAC,MAAM,CAAC,cAAc,CAAC,GAAG,CAAC,aAAa,CAAC,MAAM,CAAC,CAAC,CAAC;YACxD,CAAC;YACD,OAAO,MAAM,CAAC;QAChB,CAAC,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,kCAAkC,aAAa,CAAC,MAAM,CAAC,MAAM,CAAC,EAAE,CAAC,CAC5F,CAAC;IACJ,CAAC;IAED,+CAA+C;IACxC,KAAK,CACV,MAAoB,EACpB,IAAY,EACZ,YAAqB;QAErB,IAAI,IAAI,IAAI,CAAC,IAAI,IAAI,CAAC,MAAM,KAAK,SAAS,EAAE,CAAC;YAC3C,OAAO,OAAO,CAAC,OAAO,CAAC,OAAO,CAAC,EAAE,CAAC,CAAC,CAAC;QACtC,CAAC;QACD,IAAI,MAAM,CAAC,MAAM,KAAK,IAAI,CAAC,UAAU,EAAE,CAAC;YACtC,OAAO,OAAO,CAAC,OAAO,CACpB,IAAI,CACF,mCAAmC,MAAM,CAAC,MAAM,mCAAmC,IAAI,CAAC,UAAU,EAAE,CACrG,CACF,CAAC;QACJ,CAAC;QACD,MAAM,KAAK,GAAwB,IAAI,CAAC,MAAM,CAAC;QAC/C,OAAO,OAAO,CAAC,OAAO,CACpB,aAAa,CAAiC,GAAG,EAAE;;YACjD,6EAA6E;YAC7E,6EAA6E;YAC7E,2EAA2E;YAC3E,wDAAwD;YACxD,MAAM,MAAM,GACV,YAAY,KAAK,SAAS,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,MAAM,CAAE,KAAK,CAAC,aAAa,CAAC,GAAG,EAA6B,CAAC,CAAC,CAAC,CAAC;YACtG,IAAI,MAAM,IAAI,CAAC,EAAE,CAAC;gBAChB,OAAO,EAAE,CAAC;YACZ,CAAC;YACD,MAAM,IAAI,GAA2B,KAAK,CAAC,KAAK,CAAC,GAAG,CAClD,sBAAsB,CAAC,OAAO,CAAC,MAAM,CAAC,EACtC,MAAM,CACmB,CAAC;YAC5B,0EAA0E;YAC1E,mEAAmE;YACnE,MAAM,IAAI,GAAsB,EAAE,CAAC;YACnC,MAAM,SAAS,GAAwB,IAAI,GAAG,EAAkB,CAAC;YACjE,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;gBACvB,IAAI,IAAI,CAAC,MAAM,IAAI,IAAI,EAAE,CAAC;oBACxB,MAAM;gBACR,CAAC;gBACD,IAAI,YAAY,KAAK,SAAS,EAAE,CAAC;oBAC/B,MAAM,IAAI,GAAW,MAAA,SAAS,CAAC,GAAG,CAAC,GAAG,CAAC,UAAU,CAAC,mCAAI,CAAC,CAAC;oBACxD,IAAI,IAAI,IAAI,YAAY,EAAE,CAAC;wBACzB,SAAS;oBACX,CAAC;oBACD,SAAS,CAAC,GAAG,CAAC,GAAG,CAAC,UAAU,EAAE,IAAI,GAAG,CAAC,CAAC,CAAC;gBAC1C,CAAC;gBACD,MAAM,GAAG,GAAW,GAAG,CAAC,UAAU,CAAC;gBACnC,IAAI,CAAC,IAAI,iBACP,MAAM,EAAE,sBAAsB,CAAC,SAAS,CAAC,GAAG,CAAC,EAC7C,KAAK,EAAE,CAAC,GAAG,GAAG,CAAC,QAAQ,IACpB,sBAAsB,CAAC,WAAW,CAAC,GAAG,EAAE,GAAG,CAAC,EAC/C,CAAC;YACL,CAAC;YACD,OAAO,IAAI,CAAC;QACd,CAAC,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,iCAAiC,CAAC,EAAE,CAAC,CAChE,CAAC;IACJ,CAAC;IAED;;;;OAIG;IACK,YAAY,CAAC,SAAiB;QACpC,IAAI,CAAC,GAAG,CAAC,IAAI,CACX,uCAAuC,IAAI,CAAC,MAAM,eAAe;YAC/D,kDAAkD,SAAS,4BAA4B;YACvF,0DAA0D,CAC7D,CAAC;IACJ,CAAC;IAED,4EAA4E;IACpE,QAAQ;QACd,MAAM,GAAG,GAA4B,IAAI,CAAC,GAAG,CAAC,OAAO,CACnD,gBAAgB,IAAI,CAAC,MAAM,wBAAwB,CACpD,CAAC;QACF,MAAM,GAAG,GAA4B,IAAI,CAAC,GAAG,CAAC,OAAO,CACnD,gBAAgB,IAAI,CAAC,MAAM,4DAA4D;YACrF,wBAAwB,CAC3B,CAAC;QACF,iFAAiF;QACjF,gEAAgE;QAChE,MAAM,UAAU,GAEZ,IAAI,CAAC,GAAG,CAAC,WAAW,CAAC,CAAC,GAAW,EAAE,SAA2C,EAAE,EAAE;;YACpF,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;YACb,KAAK,MAAM,QAAQ,IAAI,SAAS,EAAE,CAAC;gBACjC,GAAG,CAAC,GAAG,CACL,GAAG,EACH,sBAAsB,CAAC,OAAO,CAAC,QAAQ,CAAC,MAAM,CAAC;gBAC/C,yEAAyE;gBACzE,4EAA4E;gBAC5E,2EAA2E;gBAC3E,QAAQ,CAAC,OAAO,KAAK,SAAS,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,MAAM,CAAC,QAAQ,CAAC,OAAO,CAAC,KAAK,CAAC,EACtE,QAAQ,CAAC,OAAO,KAAK,SAAS,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,MAAM,CAAC,QAAQ,CAAC,OAAO,CAAC,GAAG,CAAC;gBACpE,0DAA0D;gBAC1D,MAAA,QAAQ,CAAC,UAAU,mCAAI,IAAI,CAC5B,CAAC;YACJ,CAAC;QACH,CAAC,CAAC,CAAC;QACH,OAAO;YACL,cAAc,EAAE,GAAG;YACnB,OAAO,EAAE,CAAC,GAAW,EAAE,SAA2C,EAAQ,EAAE;gBAC1E,UAAU,CAAC,GAAG,EAAE,SAAS,CAAC,CAAC;YAC7B,CAAC;YACD,KAAK,EAAE,IAAI,CAAC,GAAG,CAAC,OAAO,CACrB,sEAAsE,IAAI,CAAC,MAAM,IAAI;gBACnF,mCAAmC,CACtC;YACD,aAAa,EAAE,IAAI,CAAC,GAAG,CAAC,OAAO,CAAC,8BAA8B,IAAI,CAAC,MAAM,GAAG,CAAC;YAC7E,WAAW,EAAE,IAAI,CAAC,GAAG,CAAC,OAAO,CAAC,gDAAgD,IAAI,CAAC,MAAM,GAAG,CAAC;SAC9F,CAAC;IACJ,CAAC;IAED;;;;;;;;;;;OAWG;IACK,MAAM,CAAC,sBAAsB,CAAC,EAA0B,EAAE,KAAa;QAC7E,MAAM,GAAG,GAAgC,EAAE;aACxC,OAAO,CAAC,iEAAiE,CAAC;aAC1E,GAAG,CAAC,KAAK,CAAgC,CAAC;QAC7C,IAAI,GAAG,KAAK,SAAS,EAAE,CAAC;YACtB,OAAO,SAAS,CAAC;QACnB,CAAC;QACD,sBAAsB,CAAC,uBAAuB,CAAC,GAAG,CAAC,GAAG,EAAE,KAAK,CAAC,CAAC;QAC/D,MAAM,KAAK,GAA4B,GAAG,CAAC,GAAG,CAAC,KAAK,CAAC,gBAAgB,CAAC,CAAC;QACvE,IAAI,KAAK,KAAK,IAAI,EAAE,CAAC;YACnB,+EAA+E;YAC/E,wEAAwE;YACxE,6EAA6E;YAC7E,qEAAqE;YACrE,MAAM,IAAI,KAAK,CACb,mBAAmB,KAAK,iEAAiE;gBACvF,6EAA6E,CAChF,CAAC;QACJ,CAAC;QACD,OAAO,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC;IAC1B,CAAC;IAED;;;;;;;;;OASG;IACK,MAAM,CAAC,uBAAuB,CAAC,GAAW,EAAE,KAAa;QAC/D,MAAM,KAAK,GAAa,KAAK,CAAC,IAAI,CAAC,GAAG,CAAC,QAAQ,CAAC,mBAAmB,CAAC,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;QACnF,MAAM,QAAQ,GAA0B,iBAAiB,CAAC;QAC1D,MAAM,OAAO,GACX,KAAK,CAAC,MAAM,KAAK,QAAQ,CAAC,MAAM,IAAI,QAAQ,CAAC,KAAK,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,KAAK,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC;QACzF,IAAI,CAAC,OAAO,EAAE,CAAC;YACb,MAAM,IAAI,KAAK,CACb,mBAAmB,KAAK,4BAA4B,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,mBAAmB;gBACrF,aAAa,QAAQ,CAAC,IAAI,CAAC,IAAI,CAAC,+CAA+C;gBAC/E,4FAA4F;gBAC5F,sFAAsF;gBACtF,IAAI,KAAK,gFAAgF;gBACzF,0EAA0E,CAC7E,CAAC;QACJ,CAAC;IACH,CAAC;IAED;;;;;;;;OAQG;IACK,MAAM,CAAC,WAAW,CAAC,GAAY,EAAE,GAAW;QAClD,MAAM,OAAO,GAAiC,sBAAsB,CAAC,UAAU,CAAC,GAAG,EAAE,GAAG,CAAC,CAAC;QAC1F,IAAI,OAAO,KAAK,SAAS,IAAI,GAAG,CAAC,WAAW,KAAK,IAAI,EAAE,CAAC;YACtD,MAAM,IAAI,KAAK,CACb,aAAa,GAAG,6EAA6E,CAC9F,CAAC;QACJ,CAAC;QACD,uCACK,CAAC,OAAO,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,OAAO,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC,GAC1C,CAAC,GAAG,CAAC,WAAW,KAAK,IAAI,CAAC,CAAC,CAAC,EAAE,UAAU,EAAE,GAAG,CAAC,WAAW,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC,EACpE;IACJ,CAAC;IAED;;;;;;;OAOG;IACK,MAAM,CAAC,UAAU,CAAC,GAAY,EAAE,GAAW;QACjD,MAAM,KAAK,GAA2B,GAAG,CAAC,SAAS,CAAC;QACpD,MAAM,GAAG,GAA2B,GAAG,CAAC,OAAO,CAAC;QAChD,IAAI,KAAK,KAAK,IAAI,IAAI,GAAG,KAAK,IAAI,EAAE,CAAC;YACnC,OAAO,SAAS,CAAC;QACnB,CAAC;QACD,IAAI,KAAK,KAAK,IAAI,IAAI,GAAG,KAAK,IAAI,EAAE,CAAC;YACnC,MAAM,IAAI,KAAK,CACb,aAAa,GAAG,2EAA2E,CAC5F,CAAC;QACJ,CAAC;QACD,OAAO;YACL,KAAK,EAAE,sBAAsB,CAAC,SAAS,CAAC,KAAK,EAAE,GAAG,CAAC;YACnD,GAAG,EAAE,sBAAsB,CAAC,SAAS,CAAC,GAAG,EAAE,GAAG,CAAC;SAChD,CAAC;IACJ,CAAC;IAED,sHAAsH;IAC9G,MAAM,CAAC,OAAO,CAAC,MAAoB;QACzC,OAAO,IAAI,UAAU,CAAC,YAAY,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC,MAAM,CAAC,CAAC;IAC1D,CAAC;IAED;;;;;;OAMG;IACK,MAAM,CAAC,SAAS,CAAC,GAAW;QAClC,MAAM,GAAG,GAAW,GAAG,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;QACtC,IAAI,GAAG,GAAG,CAAC,EAAE,CAAC;YACZ,MAAM,IAAI,KAAK,CAAC,yBAAyB,GAAG,wDAAwD,CAAC,CAAC;QACxG,CAAC;QACD,OAAO;YACL,KAAK,EAAE,GAAG,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,CAA8B;YACrD,EAAE,EAAE,GAAG,CAAC,KAAK,CAAC,GAAG,GAAG,CAAC,CAAwB;SAC9C,CAAC;IACJ,CAAC;IAED;;;;;;;OAOG;IACK,MAAM,CAAC,SAAS,CAAC,KAAsB,EAAE,GAAW;QAC1D,MAAM,CAAC,GAAW,MAAM,CAAC,KAAK,CAAC,CAAC;QAChC,IAAI,CAAC,MAAM,CAAC,aAAa,CAAC,CAAC,CAAC,EAAE,CAAC;YAC7B,MAAM,IAAI,KAAK,CACb,aAAa,GAAG,qBAAqB,MAAM,CAAC,KAAK,CAAC,iDAAiD,CACpG,CAAC;QACJ,CAAC;QACD,OAAO,CAAC,CAAC;IACX,CAAC;CACF","sourcesContent":["/*\n * Copyright (c) 2026 Erik Fortune\n * SPDX-License-Identifier: MIT\n */\n\nimport type BetterSqlite3 from 'better-sqlite3';\nimport { load as loadSqliteVec } from 'sqlite-vec';\nimport { Result, captureResult, fail, succeed } from '@fgv/ts-utils';\nimport {\n IEdgeTarget,\n IEmbeddedFragment,\n IFragmentLocator,\n IFragmentVectorIndex,\n IVectorQueryHit,\n MemoryId,\n MemoryScopeKey,\n edgeTargetKey\n} from '@fgv/ts-agent-memory';\nimport { ISqliteVecFragmentIndexCreateParams } from './model';\n\n/** Default name for the fragment `vec0` virtual table. */\nconst DEFAULT_TABLE_NAME: string = 'memory_fragments';\n\n/** A simple SQL identifier — the only shape allowed for the table name (it is interpolated into DDL). */\nconst IDENTIFIER_RE: RegExp = /^[A-Za-z_][A-Za-z0-9_]*$/;\n\n/**\n * The auxiliary (`+`-prefixed) columns this version of the index writes. A table\n * created by an earlier version carries a different set; see\n * {@link SqliteVecFragmentIndex._readExistingDimension} for why that has to be\n * detected explicitly rather than migrated.\n */\nconst AUXILIARY_COLUMNS: ReadonlyArray<string> = ['start_off', 'end_off', 'fragment_id'];\n\n/**\n * Matches one `+name` auxiliary-column declaration in a `vec0` `CREATE VIRTUAL TABLE`\n * statement. Only ever consumed via `String.matchAll`, which iterates a clone rather\n * than advancing this instance's `lastIndex`, so the shared `/g` regex is reusable.\n */\nconst AUXILIARY_COLUMN_RE: RegExp = /\\+\\s*([A-Za-z_][A-Za-z0-9_]*)/g;\n\n/**\n * One KNN row as returned by the fragment `vec0` MATCH query. The offset columns are\n * typed `number | bigint` because `better-sqlite3` returns integer columns as\n * `bigint` when a consumer enables its safe-integer mode (`defaultSafeIntegers`);\n * {@link SqliteVecFragmentIndex._toOffset} coerces them to a plain `number` (and\n * fails loudly on an out-of-safe-range value) before they reach the public locator.\n * All three identity columns are nullable: a fragment stored without a locator has\n * `NULL` offsets, and one stored without a `fragmentId` has a `NULL` `fragment_id`.\n */\ninterface IKnnRow {\n readonly target_key: string;\n // eslint-disable-next-line @rushstack/no-new-null -- SQLite returns NULL (not undefined) for an absent locator offset\n readonly start_off: number | bigint | null;\n // eslint-disable-next-line @rushstack/no-new-null -- SQLite returns NULL (not undefined) for an absent locator offset\n readonly end_off: number | bigint | null;\n // eslint-disable-next-line @rushstack/no-new-null -- SQLite returns NULL (not undefined) for an absent fragment id\n readonly fragment_id: string | null;\n readonly distance: number;\n}\n\n/**\n * The identity fields of a fragment hit, in `IVectorQueryHit` shape: a field the\n * stored fragment did not carry is *absent*, never present-but-`undefined`, so a hit\n * for a fragment stored without a `fragmentId` is structurally identical to one this\n * index produced before `fragment_id` existed.\n */\ntype FragmentIdentity = Pick<IVectorQueryHit, 'locator' | 'fragmentId'>;\n\n/**\n * A persistent, `sqlite-vec`-backed `IFragmentVectorIndex` (from\n * `@fgv/ts-agent-memory`) — the fragment-granular sibling of\n * {@link SqliteVecVectorIndex}, and the **durable** counterpart to the in-memory\n * `InMemoryFragmentCosineIndex`.\n *\n * @remarks\n * Where {@link SqliteVecVectorIndex} keys one vector per record on a\n * `target_key` primary key, this index holds **many** vectors per record — one per\n * fragment — so it keys the `vec0` table on `target_key` as a **`PARTITION KEY`**\n * (many rows may share it) and stores each fragment's identity in three auxiliary\n * columns (`+start_off`, `+end_off`, `+fragment_id`) that ride alongside the vector\n * and are returned on query but never filtered — in particular `fragment_id` is\n * stored and returned verbatim, never parsed and never part of the query path. A\n * query is a brute-force `vec0` KNN scan across all partitions returning per-fragment\n * hits, each carrying its record `target` plus whichever identity fields the stored\n * fragment was added with (a fragment must carry at least one).\n *\n * **`vec0` schema changes require a drop-and-re-index.** A\n * `CREATE VIRTUAL TABLE IF NOT EXISTS` is a no-op against an existing table (SQLite\n * does not compare schemas) and `vec0` has no `ALTER TABLE ADD COLUMN`, so a database written by an\n * earlier version of this package keeps its old auxiliary columns. `create` detects\n * that by parsing the stored `CREATE VIRTUAL TABLE` SQL and fails with an actionable\n * message naming the expected and found columns, rather than letting a widened\n * `INSERT` surface an opaque `no such column` at statement-prepare time. There are no\n * in-place migrations: drop the table (or use a fresh `tableName`) and re-index.\n * Fragment vectors are re-derivable from the records, so this costs embedding time,\n * never data.\n *\n * Semantics match `InMemoryFragmentCosineIndex` exactly: `addFragments` is\n * whole-record-replace (a single transaction deletes every prior fragment of the\n * target, then inserts the new set), `remove` drops every fragment of a target,\n * and `query` applies the optional `maxPerRecord` cap **during selection, before\n * the topK cut** — so one long document cannot crowd others out. The dimension is\n * established by the first `addFragments` (the `vec0` column is fixed-width) and\n * recovered from the table schema when a persistent file is reopened; similarity is\n * cosine (`score = 1 - cosineDistance`), byte-identical to the in-memory index.\n * Large-N ANN indexing is explicitly out of scope, same regime as the record index.\n *\n * The `better-sqlite3` `Database` is consumer-owned (bring-your-own): this index\n * loads the `sqlite-vec` extension onto it and reads/writes the table, but never\n * opens or closes the connection.\n * @public\n */\nexport class SqliteVecFragmentIndex implements IFragmentVectorIndex {\n private readonly _db: BetterSqlite3.Database;\n private readonly _table: string;\n /** The dimension of every stored fragment vector; `undefined` until the table exists. */\n private _dimension: number | undefined;\n /** Prepared statements; created once the table exists (established or recovered). */\n private _stmts: IFragmentStatements | undefined;\n\n private constructor(db: BetterSqlite3.Database, table: string, dimension: number | undefined) {\n this._db = db;\n this._table = table;\n this._dimension = dimension;\n this._stmts = dimension === undefined ? undefined : this._prepare();\n }\n\n /** The number of records that currently have at least one stored fragment. Zero before the first add. */\n public get recordCount(): number {\n if (this._stmts === undefined) {\n return 0;\n }\n // `Number(...)` narrows the count in case the consumer enabled better-sqlite3\n // safe-integer mode (which returns `count(*)` as a `bigint`).\n return Number((this._stmts.recordCount.get() as { c: number | bigint }).c);\n }\n\n /** The total number of fragments currently held across all records. Zero before the first add. */\n public get fragmentCount(): number {\n if (this._stmts === undefined) {\n return 0;\n }\n return Number((this._stmts.fragmentCount.get() as { c: number | bigint }).c);\n }\n\n /**\n * Family-convention factory. Loads the `sqlite-vec` extension onto the supplied\n * `better-sqlite3` connection and, if the fragment table already exists (a\n * reopened persistent file), verifies its auxiliary-column set matches this\n * version's and recovers its established dimension so no re-embedding is needed on\n * open.\n *\n * @param params - See {@link ISqliteVecFragmentIndexCreateParams}.\n * @returns `Success` with the index, or `Failure` if the table name is not a\n * simple identifier, the extension fails to load, or the existing table was\n * written by a version with a different auxiliary-column set (which requires a\n * drop-and-re-index — `vec0` cannot be altered in place).\n */\n public static create(params: ISqliteVecFragmentIndexCreateParams): Promise<Result<SqliteVecFragmentIndex>> {\n const table: string = params.tableName ?? DEFAULT_TABLE_NAME;\n if (!IDENTIFIER_RE.test(table)) {\n return Promise.resolve(\n fail(`sqlite-vec fragment index: table name '${table}' is not a simple SQL identifier`)\n );\n }\n return Promise.resolve(\n captureResult(() => {\n loadSqliteVec(params.database);\n const dimension: number | undefined = SqliteVecFragmentIndex._readExistingDimension(\n params.database,\n table\n );\n return new SqliteVecFragmentIndex(params.database, table, dimension);\n }).withErrorFormat((e) => `sqlite-vec fragment index: failed to initialize: ${e}`)\n );\n }\n\n /** {@inheritDoc IFragmentVectorIndex.addFragments} */\n public addFragments(\n target: IEdgeTarget,\n fragments: ReadonlyArray<IEmbeddedFragment>\n ): Promise<Result<number>> {\n const key: string = edgeTargetKey(target);\n // Validate every fragment before touching the database, so a bad fragment never\n // leaves the record half-replaced or the dimension half-established (whole-record\n // replace is all-or-nothing). The effective dimension is the established one, or —\n // on a still-dimensionless index — the first fragment's length; it is committed\n // (via table creation) only once the whole batch validates.\n let dimension: number | undefined = this._dimension;\n for (const fragment of fragments) {\n if (fragment.vector.length === 0) {\n return Promise.resolve(fail(`fragment index: cannot add '${key}': empty fragment vector`));\n }\n // A fragment carrying neither identity cannot be resolved back to anything by a\n // consumer holding the hit — the same invariant `embeddedFragmentConverter`\n // enforces at the untyped boundary, re-checked here at the index seam.\n if (fragment.locator === undefined && fragment.fragmentId === undefined) {\n return Promise.resolve(\n fail(\n `fragment index: cannot add '${key}': fragment requires at least one of 'locator' or 'fragmentId'`\n )\n );\n }\n // Locator offsets are persisted as SQLite integers (bound via BigInt). Reject a\n // non-safe-integer offset up front with a clear message, rather than letting\n // `BigInt(nonInteger)` throw cryptically inside the write transaction OR storing\n // a value the read-side `_toOffset` guard would later reject on every query.\n // An absent locator persists as a NULL offset pair and skips the check.\n if (\n fragment.locator !== undefined &&\n (!Number.isSafeInteger(fragment.locator.start) || !Number.isSafeInteger(fragment.locator.end))\n ) {\n return Promise.resolve(\n fail(\n `fragment index: cannot add '${key}': locator [${fragment.locator.start}, ${fragment.locator.end}) offsets must be safe integers`\n )\n );\n }\n if (dimension === undefined) {\n dimension = fragment.vector.length;\n } else if (fragment.vector.length !== dimension) {\n return Promise.resolve(\n fail(\n `fragment index: cannot add '${key}': fragment dimension ${fragment.vector.length} does not match index dimension ${dimension}`\n )\n );\n }\n }\n return Promise.resolve(\n captureResult(() => {\n // A same-target re-author (or an empty batch) still needs the table to exist\n // to delete prior fragments; create it lazily on the first non-empty add.\n if (this._stmts === undefined) {\n if (fragments.length === 0) {\n // Nothing stored yet and nothing to store: no table, no work.\n return 0;\n }\n // `fragments` is non-empty here (the empty case returned above), so the\n // validation loop proved every fragment shares `fragments[0]`'s length —\n // which IS the dimension to establish. Read it straight from the first\n // fragment: no cast, no invariant-dependent narrowing.\n const established: number = fragments[0].vector.length;\n this._createTable(established);\n this._dimension = established;\n this._stmts = this._prepare();\n }\n this._stmts.replace(key, fragments);\n return fragments.length;\n }).withErrorFormat((e) => `fragment index: cannot add '${key}': ${e}`)\n );\n }\n\n /** {@inheritDoc IFragmentVectorIndex.remove} */\n public remove(target: IEdgeTarget): Promise<Result<IEdgeTarget>> {\n return Promise.resolve(\n captureResult(() => {\n // Idempotent: removing a target with no fragments (or before any add created\n // the table) still succeeds.\n if (this._stmts !== undefined) {\n this._stmts.deleteByTarget.run(edgeTargetKey(target));\n }\n return target;\n }).withErrorFormat((e) => `fragment index: cannot remove '${edgeTargetKey(target)}': ${e}`)\n );\n }\n\n /** {@inheritDoc IFragmentVectorIndex.query} */\n public query(\n vector: Float32Array,\n topK: number,\n maxPerRecord?: number\n ): Promise<Result<ReadonlyArray<IVectorQueryHit>>> {\n if (topK <= 0 || this._stmts === undefined) {\n return Promise.resolve(succeed([]));\n }\n if (vector.length !== this._dimension) {\n return Promise.resolve(\n fail(\n `fragment index: query dimension ${vector.length} does not match index dimension ${this._dimension}`\n )\n );\n }\n const stmts: IFragmentStatements = this._stmts;\n return Promise.resolve(\n captureResult<ReadonlyArray<IVectorQueryHit>>(() => {\n // With a per-record cap the topK winners may lie past the first topK rows (a\n // capped record's later fragments are skipped), so fetch the full ranked set\n // and apply the cap + topK cut here — exactly as the in-memory index does.\n // Uncapped, KNN's own `k = topK` is already the answer.\n const fetchK: number =\n maxPerRecord === undefined ? topK : Number((stmts.fragmentCount.get() as { c: number | bigint }).c);\n if (fetchK <= 0) {\n return [];\n }\n const rows: ReadonlyArray<IKnnRow> = stmts.query.all(\n SqliteVecFragmentIndex._toBlob(vector),\n fetchK\n ) as ReadonlyArray<IKnnRow>;\n // sqlite-vec returns rows ascending by distance (nearest first); score is\n // `1 - cosineDistance`, so this order is already descending score.\n const hits: IVectorQueryHit[] = [];\n const perRecord: Map<string, number> = new Map<string, number>();\n for (const row of rows) {\n if (hits.length >= topK) {\n break;\n }\n if (maxPerRecord !== undefined) {\n const used: number = perRecord.get(row.target_key) ?? 0;\n if (used >= maxPerRecord) {\n continue;\n }\n perRecord.set(row.target_key, used + 1);\n }\n const key: string = row.target_key;\n hits.push({\n target: SqliteVecFragmentIndex._parseKey(key),\n score: 1 - row.distance,\n ...SqliteVecFragmentIndex._toIdentity(row, key)\n });\n }\n return hits;\n }).withErrorFormat((e) => `fragment index: query failed: ${e}`)\n );\n }\n\n /**\n * Create the fragment `vec0` virtual table with the established dimension. The\n * auxiliary columns must stay in sync with `AUXILIARY_COLUMNS`, which\n * `create` compares against an existing table's stored DDL.\n */\n private _createTable(dimension: number): void {\n this._db.exec(\n `CREATE VIRTUAL TABLE IF NOT EXISTS \"${this._table}\" USING vec0(` +\n `target_key TEXT PARTITION KEY, embedding float[${dimension}] distance_metric=cosine, ` +\n `+start_off integer, +end_off integer, +fragment_id text)`\n );\n }\n\n /** Prepare the statements the index reuses. Requires the table to exist. */\n private _prepare(): IFragmentStatements {\n const del: BetterSqlite3.Statement = this._db.prepare(\n `DELETE FROM \"${this._table}\" WHERE target_key = ?`\n );\n const ins: BetterSqlite3.Statement = this._db.prepare(\n `INSERT INTO \"${this._table}\"(target_key, embedding, start_off, end_off, fragment_id) ` +\n `VALUES (?, ?, ?, ?, ?)`\n );\n // Whole-record replace: drop every prior fragment of the target, then insert the\n // new set, atomically. An empty set collapses to a pure delete.\n const replaceTxn: BetterSqlite3.Transaction<\n (key: string, fragments: ReadonlyArray<IEmbeddedFragment>) => void\n > = this._db.transaction((key: string, fragments: ReadonlyArray<IEmbeddedFragment>) => {\n del.run(key);\n for (const fragment of fragments) {\n ins.run(\n key,\n SqliteVecFragmentIndex._toBlob(fragment.vector),\n // vec0 typed columns reject a JS float; bind the offsets as integers. An\n // absent locator binds the pair as NULL — never a partial pair, so the read\n // side can treat a half-NULL pair as corruption rather than a legal shape.\n fragment.locator === undefined ? null : BigInt(fragment.locator.start),\n fragment.locator === undefined ? null : BigInt(fragment.locator.end),\n // Stored verbatim and never parsed; absent binds as NULL.\n fragment.fragmentId ?? null\n );\n }\n });\n return {\n deleteByTarget: del,\n replace: (key: string, fragments: ReadonlyArray<IEmbeddedFragment>): void => {\n replaceTxn(key, fragments);\n },\n query: this._db.prepare(\n `SELECT target_key, start_off, end_off, fragment_id, distance FROM \"${this._table}\" ` +\n `WHERE embedding MATCH ? AND k = ?`\n ),\n fragmentCount: this._db.prepare(`SELECT count(*) AS c FROM \"${this._table}\"`),\n recordCount: this._db.prepare(`SELECT count(DISTINCT target_key) AS c FROM \"${this._table}\"`)\n };\n }\n\n /**\n * Recover the established dimension of an existing fragment `vec0` table from its\n * stored `CREATE VIRTUAL TABLE` SQL (`float[<n>]`), after checking that the table's\n * auxiliary columns match `AUXILIARY_COLUMNS`. Returns `undefined` when the\n * table does not exist yet (a fresh database — dimension is set by the first add).\n *\n * Throws when a table of that name exists but is not a usable fragment index (a\n * mismatched auxiliary-column set, or no `vec0` embedding column); the caller runs\n * this inside `captureResult`, so it surfaces as a loud `Failure` from `create`.\n * The same stored DDL answers every one of those questions, so the checks cost\n * nothing extra.\n */\n private static _readExistingDimension(db: BetterSqlite3.Database, table: string): number | undefined {\n const row: { sql: string } | undefined = db\n .prepare(\"SELECT sql FROM sqlite_master WHERE type = 'table' AND name = ?\")\n .get(table) as { sql: string } | undefined;\n if (row === undefined) {\n return undefined;\n }\n SqliteVecFragmentIndex._verifyAuxiliaryColumns(row.sql, table);\n const match: RegExpMatchArray | null = row.sql.match(/float\\[(\\d+)\\]/);\n if (match === null) {\n // The auxiliary columns matched but there is no `float[<n>]` embedding column,\n // so this is not a usable fragment index table. Same remedy as a column\n // mismatch — and failing here beats handing back a dimensionless index whose\n // first add would `CREATE VIRTUAL TABLE IF NOT EXISTS` into a no-op.\n throw new Error(\n `existing table '${table}' has no vec0 embedding column, so it is not a usable fragment ` +\n `index table. Drop it (or pass a fresh tableName) and re-add every fragment.`\n );\n }\n return Number(match[1]);\n }\n\n /**\n * Compare an existing table's auxiliary columns against `AUXILIARY_COLUMNS`.\n *\n * `CREATE VIRTUAL TABLE IF NOT EXISTS` is a no-op against an existing table (SQLite\n * never compares schemas) and `vec0` has no `ALTER TABLE ADD COLUMN`, so a table\n * written by an earlier version of this package silently keeps its old columns and\n * only fails later — as an opaque `no such column` when the widened `INSERT` is\n * prepared. Detect it here instead and say what to do about it. Order is not\n * compared: every statement names its columns explicitly, so only the set matters.\n */\n private static _verifyAuxiliaryColumns(sql: string, table: string): void {\n const found: string[] = Array.from(sql.matchAll(AUXILIARY_COLUMN_RE), (m) => m[1]);\n const expected: ReadonlyArray<string> = AUXILIARY_COLUMNS;\n const matches: boolean =\n found.length === expected.length && expected.every((column) => found.includes(column));\n if (!matches) {\n throw new Error(\n `existing table '${table}' has auxiliary columns [${found.join(', ')}] but this index ` +\n `requires [${expected.join(', ')}] — it was written by a different version of ` +\n `@fgv/ts-agent-memory-sqlite-vec, or it is not a fragment index table at all. vec0 virtual ` +\n `tables cannot be altered in place, so this requires a drop-and-re-index: DROP TABLE ` +\n `\"${table}\" (or pass a fresh tableName) and re-add every fragment. Fragment vectors are ` +\n `re-derivable from the records, so this costs embedding time, never data.`\n );\n }\n }\n\n /**\n * Rebuild the identity fields of a hit from a persisted row, omitting each field\n * the stored fragment did not carry (so a hit is structurally identical to one this\n * index produced before `fragment_id` existed).\n *\n * A row carrying neither identity violates the write-side invariant and could not\n * be resolved by the caller, so it fails loudly instead of yielding an anonymous\n * hit.\n */\n private static _toIdentity(row: IKnnRow, key: string): FragmentIdentity {\n const locator: IFragmentLocator | undefined = SqliteVecFragmentIndex._toLocator(row, key);\n if (locator === undefined && row.fragment_id === null) {\n throw new Error(\n `fragment '${key}': row carries neither a locator nor a fragment id (corrupt persisted data)`\n );\n }\n return {\n ...(locator !== undefined ? { locator } : {}),\n ...(row.fragment_id !== null ? { fragmentId: row.fragment_id } : {})\n };\n }\n\n /**\n * Rebuild a fragment's locator from its persisted offsets, or `undefined` when the\n * fragment was stored without one (both offsets `NULL`).\n *\n * The pair is written all-or-nothing, so a half-`NULL` pair can only come from\n * corrupt / externally-edited data. Throw rather than coerce — `Number(null)` is\n * `0`, which would silently fabricate a span starting at the top of the body.\n */\n private static _toLocator(row: IKnnRow, key: string): IFragmentLocator | undefined {\n const start: number | bigint | null = row.start_off;\n const end: number | bigint | null = row.end_off;\n if (start === null && end === null) {\n return undefined;\n }\n if (start === null || end === null) {\n throw new Error(\n `fragment '${key}': locator has only one of its start/end offsets (corrupt persisted data)`\n );\n }\n return {\n start: SqliteVecFragmentIndex._toOffset(start, key),\n end: SqliteVecFragmentIndex._toOffset(end, key)\n };\n }\n\n /** Pack a `Float32Array` as the little-endian byte blob `vec0` stores. Copies, so the caller may reuse its buffer. */\n private static _toBlob(vector: Float32Array): Uint8Array {\n return new Uint8Array(Float32Array.from(vector).buffer);\n }\n\n /**\n * Reverse `edgeTargetKey` — the canonical key is `scope\\0id` with NUL excluded\n * from both components, so the first NUL splits it unambiguously. A key with no\n * NUL cannot have been written by `edgeTargetKey`; rather than fabricate a wrong\n * `(scope, id)` from corrupt / externally-edited table data, throw so the query\n * surfaces it as a loud `Failure`.\n */\n private static _parseKey(key: string): IEdgeTarget {\n const nul: number = key.indexOf('\\0');\n if (nul < 0) {\n throw new Error(`malformed target key '${key}': missing scope/id separator (corrupt persisted data)`);\n }\n return {\n scope: key.slice(0, nul) as unknown as MemoryScopeKey,\n id: key.slice(nul + 1) as unknown as MemoryId\n };\n }\n\n /**\n * Coerce a persisted locator offset to a plain `number`. `better-sqlite3` returns\n * integer columns as `bigint` under safe-integer mode, so an offset can arrive as\n * either; both narrow to `number` here. A value outside the safe-integer range\n * (only reachable via corrupt / externally-edited data — the index only ever\n * writes in-document offsets) throws rather than silently losing precision, so the\n * query surfaces it as a loud `Failure`.\n */\n private static _toOffset(value: number | bigint, key: string): number {\n const n: number = Number(value);\n if (!Number.isSafeInteger(n)) {\n throw new Error(\n `fragment '${key}': locator offset ${String(value)} is not a safe integer (corrupt persisted data)`\n );\n }\n return n;\n }\n}\n\n/** The prepared statements / helpers the fragment index reuses once its table exists. */\ninterface IFragmentStatements {\n readonly deleteByTarget: BetterSqlite3.Statement;\n readonly replace: (key: string, fragments: ReadonlyArray<IEmbeddedFragment>) => void;\n readonly query: BetterSqlite3.Statement;\n readonly fragmentCount: BetterSqlite3.Statement;\n readonly recordCount: BetterSqlite3.Statement;\n}\n"]}
|