mcp-rag-memory 2.4.1 → 2.7.0

package/dist/db/database.js

@@ -17,18 +17,59 @@ export function getDB() {
         return _db;
     ensureDir();
     const db = new DatabaseSync(DB_PATH);
-    db.exec("PRAGMA journal_mode = WAL;");
-    db.exec("PRAGMA synchronous = NORMAL;");
-    db.exec("PRAGMA foreign_keys = ON;");
+    try {
+        // busy_timeout first: every later statement should inherit it.
+        db.exec("PRAGMA busy_timeout = 5000;");
+        db.exec("PRAGMA journal_mode = WAL;");
+        db.exec("PRAGMA synchronous = NORMAL;");
+        db.exec("PRAGMA foreign_keys = ON;");
+        // Migrate BEFORE caching the handle: a failed migration must surface and be
+        // retried on the next call, never leave a half-migrated connection cached.
+        migrate(db);
+    }
+    catch (e) {
+        // The handle is NOT cached on failure, so without this close every failed
+        // init leaked a file handle — reachable whenever a concurrent writer holds
+        // the lock, and it blocked later cleanup of the store directory on Windows.
+        try {
+            db.close();
+        }
+        catch {
+            /* already closed */
+        }
+        throw e;
+    }
     _db = db;
-    migrate(db);
     return db;
 }
 function columnExists(db, table, column) {
+    // PRAGMA cannot take a bound parameter, so the identifier is interpolated.
+    // Only ever called with literals; assert it so a future caller cannot inject.
+    if (!/^[A-Za-z_][A-Za-z0-9_]*$/.test(table))
+        throw new Error(`Unsafe table name: ${table}`);
     const cols = db.prepare(`PRAGMA table_info(${table})`).all();
     return cols.some((c) => c.name === column);
 }
 function migrate(db) {
+    // One IMMEDIATE transaction for the whole schema step: two processes opening
+    // the same fresh store (CLI + MCP server + plugin) must not race and end up
+    // with half-applied DDL or a "duplicate column" failure.
+    db.exec("BEGIN IMMEDIATE;");
+    try {
+        createSchema(db);
+        db.exec("COMMIT;");
+    }
+    catch (e) {
+        try {
+            db.exec("ROLLBACK;");
+        }
+        catch {
+            /* transaction already closed */
+        }
+        throw e;
+    }
+}
+function createSchema(db) {
     db.exec(`
     CREATE TABLE IF NOT EXISTS documents (
       id           TEXT PRIMARY KEY,
@@ -51,6 +92,10 @@ function migrate(db) {
       created_at INTEGER NOT NULL
     );
     CREATE INDEX IF NOT EXISTS idx_chunks_doc_id ON chunks(doc_id);
+    CREATE INDEX IF NOT EXISTS idx_documents_updated ON documents(updated_at DESC);
+    -- Filtered searches resolve doc ids via source/doc_id first; without this
+    -- every rag_search(source=...) scanned the whole documents table.
+    CREATE INDEX IF NOT EXISTS idx_documents_source ON documents(source);
 
     CREATE TABLE IF NOT EXISTS memories (
       id           TEXT PRIMARY KEY,
@@ -66,6 +111,7 @@ function migrate(db) {
     );
     CREATE INDEX IF NOT EXISTS idx_memories_type ON memories(type);
     CREATE INDEX IF NOT EXISTS idx_memories_prune ON memories(importance, recall_count, created_at);
+    CREATE INDEX IF NOT EXISTS idx_memories_updated ON memories(updated_at DESC);
 
     CREATE TABLE IF NOT EXISTS meta (
       key   TEXT PRIMARY KEY,
@@ -84,17 +130,24 @@ function migrate(db) {
     const ftsRow = db
         .prepare("SELECT sql FROM sqlite_master WHERE type = 'table' AND name = 'chunks_fts'")
         .get();
-    if (!ftsRow) {
-        db.exec("CREATE VIRTUAL TABLE chunks_fts USING fts5(content, tokenize = 'trigram');");
-    }
-    else if (!ftsRow.sql.includes("trigram")) {
+    if (ftsRow) {
         // Existing store built with 'unicode61' — recreate with trigram and backfill.
-        db.exec("DROP TABLE chunks_fts;");
-        db.exec("CREATE VIRTUAL TABLE chunks_fts USING fts5(content, tokenize = 'trigram');");
-        db.exec(`INSERT INTO chunks_fts(rowid, content)
-         SELECT rowid, content FROM chunks`);
+        if (!(ftsRow.sql ?? "").includes("trigram"))
+            rebuildFts(db);
+    }
+    else {
+        // First run with this schema (or a store whose FTS table was dropped):
+        // create AND backfill, otherwise existing chunks silently lose keyword search
+        // forever — the next boot sees "trigram" and would skip the rebuild.
+        rebuildFts(db);
     }
 }
+/** Runs inside the migrate() transaction. */
+function rebuildFts(db) {
+    db.exec("DROP TABLE IF EXISTS chunks_fts;");
+    db.exec("CREATE VIRTUAL TABLE chunks_fts USING fts5(content, tokenize = 'trigram');");
+    db.exec("INSERT INTO chunks_fts(rowid, content) SELECT rowid, content FROM chunks;");
+}
 /** SHA-256 hex of raw content — used for document dedup. */
 export function contentHash(content) {
     return createHash("sha256").update(content, "utf8").digest("hex");
@@ -102,13 +155,13 @@ export function contentHash(content) {
 export function newId() {
     return randomUUID();
 }
-/** Serialize a Float64Array embedding to a SQLite BLOB. */
+/** Serialize a Float64Array embedding to a SQLite BLOB (view-safe). */
 export function packVector(v) {
-    return new Uint8Array(v.buffer.slice(0));
+    return new Uint8Array(v.buffer.slice(v.byteOffset, v.byteOffset + v.byteLength));
 }
-/** Deserialize a BLOB back into a Float64Array. */
+/** Deserialize a BLOB back into a Float64Array. Returns null on absent/partial data. */
 export function unpackVector(blob) {
-    if (!blob || blob.byteLength === 0)
+    if (!blob || blob.byteLength === 0 || blob.byteLength % 8 !== 0)
         return null;
     return new Float64Array(blob.buffer.slice(blob.byteOffset, blob.byteOffset + blob.byteLength));
 }
@@ -118,24 +171,41 @@ export function nowMs() {
 export function closeDB() {
     _db?.close();
     _db = null;
+    cachedDim = null;
 }
 /* ------------------------------------------------------------------ */
 /* Embedding dimension metadata                                        */
 /* ------------------------------------------------------------------ */
+/** Cached embed_dim: locked on first write, so it is read once per process. */
+let cachedDim = null;
 export function getEmbedDim() {
-    const r = getDB().prepare("SELECT value FROM meta WHERE key = 'embed_dim'").get();
-    return r ? Number(r.value) : 0;
+    if (cachedDim === null) {
+        const r = getDB().prepare("SELECT value FROM meta WHERE key = 'embed_dim'").get();
+        const n = Number(r?.value);
+        // A corrupt row must not cache NaN: it would wedge this process with a
+        // misleading "dimension mismatch" until restart.
+        cachedDim = Number.isInteger(n) && n > 0 ? n : 0;
+    }
+    return cachedDim;
 }
 export function setEmbedMeta(dim, model) {
     const db = getDB();
     db.prepare("INSERT INTO meta(key, value) VALUES ('embed_dim', ?) ON CONFLICT(key) DO UPDATE SET value = excluded.value").run(String(dim));
     db.prepare("INSERT INTO meta(key, value) VALUES ('embed_model', ?) ON CONFLICT(key) DO UPDATE SET value = excluded.value").run(model);
+    cachedDim = dim;
+    // A completed migration restores the store to a coherent state.
+    setEmbedState("ready");
 }
 /**
  * Lock the store to one embedding dimension. Call after producing a vector.
  * Prevents silently mixing vectors of different models/providers.
  */
 export function ensureDim(vec, model) {
+    // A half-migrated store mixes old and new vectors: cosine across two spaces
+    // is meaningless and every search silently returns noise. Blocking here stops
+    // it at the one chokepoint every search and ingest already passes through,
+    // rather than letting a partial reindex look like a working store.
+    assertEmbedStateReady();
     const current = getEmbedDim();
     if (current === 0) {
         setEmbedMeta(vec.length, model);
@@ -146,9 +216,40 @@ export function ensureDim(vec, model) {
             `new vectors are ${vec.length} (model: ${model}). ` +
             `Use a consistent EMBEDDING_PROVIDER or wipe ${STORAGE_DIR}.`);
     }
+    // Same-dimension model swaps are the dangerous case: blending two vector
+    // spaces degrades search to noise with no error anywhere, and the only clue
+    // was a stale model name inside a dimension-mismatch message that never fired.
+    const currentModel = getEmbedModel();
+    if (currentModel && currentModel !== model) {
+        throw new Error(`Embedding model mismatch: DB stores ${currentModel}, requested ${model} (both ${current}-dim). ` +
+            `Point RAG_DB_DIR at a fresh store or re-ingest with a consistent EMBEDDING_MODEL. ` +
+            `Current store: ${STORAGE_DIR}.`);
+    }
 }
 export function getEmbedModel() {
     const r = getDB().prepare("SELECT value FROM meta WHERE key = 'embed_model'").get();
     return r ? r.value : "";
 }
+/**
+ * `embed_state` is '' (or 'ready') for a coherent store and 'reindexing' while a
+ * vector-space migration is in flight.
+ */
+export function getEmbedState() {
+    const r = getDB().prepare("SELECT value FROM meta WHERE key = 'embed_state'").get();
+    return r ? r.value : "";
+}
+export function setEmbedState(state) {
+    getDB()
+        .prepare("INSERT INTO meta(key, value) VALUES('embed_state', ?) ON CONFLICT(key) DO UPDATE SET value = excluded.value")
+        .run(state);
+}
+/** Throws when the store is mid-reindex. Called from ensureDim, the shared gate. */
+export function assertEmbedStateReady() {
+    const state = getEmbedState();
+    if (state !== "" && state !== "ready") {
+        throw new Error(`Store is mid-reindex (embed_state=${state}): vectors from two embedding models are ` +
+            `mixed and search results would be meaningless. Run 'reindex' again to finish the ` +
+            `migration. Current store: ${STORAGE_DIR}.`);
+    }
+}
 //# sourceMappingURL=database.js.map

package/dist/db/database.js.map

@@ -1 +1 @@
-{"version":3,"file":"database.js","sourceRoot":"","sources":["../../src/db/database.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,YAAY,EAAE,MAAM,aAAa,CAAC;AAC3C,OAAO,KAAK,IAAI,MAAM,MAAM,CAAC;AAC7B,OAAO,KAAK,EAAE,MAAM,IAAI,CAAC;AACzB,OAAO,EAAE,UAAU,EAAE,UAAU,EAAE,MAAM,aAAa,CAAC;AAErD,MAAM,CAAC,MAAM,WAAW,GAAG,OAAO,CAAC,GAAG,CAAC,UAAU;IAC/C,CAAC,CAAC,IAAI,CAAC,OAAO,CAAC,OAAO,CAAC,GAAG,CAAC,UAAU,CAAC;IACtC,CAAC,CAAC,IAAI,CAAC,OAAO,CAAC,OAAO,CAAC,GAAG,EAAE,EAAE,WAAW,CAAC,CAAC;AAE7C,MAAM,CAAC,MAAM,OAAO,GAAG,IAAI,CAAC,IAAI,CAAC,WAAW,EAAE,YAAY,CAAC,CAAC;AAE5D,IAAI,GAAG,GAAwB,IAAI,CAAC;AAEpC,SAAS,SAAS;IAChB,IAAI,CAAC,EAAE,CAAC,UAAU,CAAC,WAAW,CAAC,EAAE,CAAC;QAChC,EAAE,CAAC,SAAS,CAAC,WAAW,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;IACjD,CAAC;AACH,CAAC;AAED,MAAM,UAAU,KAAK;IACnB,IAAI,GAAG;QAAE,OAAO,GAAG,CAAC;IACpB,SAAS,EAAE,CAAC;IACZ,MAAM,EAAE,GAAG,IAAI,YAAY,CAAC,OAAO,CAAC,CAAC;IACrC,EAAE,CAAC,IAAI,CAAC,4BAA4B,CAAC,CAAC;IACtC,EAAE,CAAC,IAAI,CAAC,8BAA8B,CAAC,CAAC;IACxC,EAAE,CAAC,IAAI,CAAC,2BAA2B,CAAC,CAAC;IACrC,GAAG,GAAG,EAAE,CAAC;IACT,OAAO,CAAC,EAAE,CAAC,CAAC;IACZ,OAAO,EAAE,CAAC;AACZ,CAAC;AAED,SAAS,YAAY,CAAC,EAAgB,EAAE,KAAa,EAAE,MAAc;IACnE,MAAM,IAAI,GAAG,EAAE,CAAC,OAAO,CAAC,qBAAqB,KAAK,GAAG,CAAC,CAAC,GAAG,EAA6B,CAAC;IACxF,OAAO,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,KAAK,MAAM,CAAC,CAAC;AAC7C,CAAC;AAED,SAAS,OAAO,CAAC,EAAgB;IAC/B,EAAE,CAAC,IAAI,CAAC;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA0CP,CAAC,CAAC;IAEH,2EAA2E;IAC3E,IAAI,CAAC,YAAY,CAAC,EAAE,EAAE,WAAW,EAAE,cAAc,CAAC,EAAE,CAAC;QACnD,EAAE,CAAC,IAAI,CAAC,qDAAqD,CAAC,CAAC;IACjE,CAAC;IACD,EAAE,CAAC,IAAI,CACL,yHAAyH,CAC1H,CAAC;IAEF,sEAAsE;IACtE,yEAAyE;IACzE,4EAA4E;IAC5E,8EAA8E;IAC9E,MAAM,MAAM,GAAG,EAAE;SACd,OAAO,CAAC,4EAA4E,CAAC;SACrF,GAAG,EAAkC,CAAC;IACzC,IAAI,CAAC,MAAM,EAAE,CAAC;QACZ,EAAE,CAAC,IAAI,CAAC,4EAA4E,CAAC,CAAC;IACxF,CAAC;SAAM,IAAI,CAAC,MAAM,CAAC,GAAI,CAAC,QAAQ,CAAC,SAAS,CAAC,EAAE,CAAC;QAC5C,8EAA8E;QAC9E,EAAE,CAAC,IAAI,CAAC,wBAAwB,CAAC,CAAC;QAClC,EAAE,CAAC,IAAI,CAAC,4EAA4E,CAAC,CAAC;QACtF,EAAE,CAAC,IAAI,CACL;2CACqC,CACtC,CAAC;IACJ,CAAC;AACH,CAAC;AAED,4DAA4D;AAC5D,MAAM,UAAU,WAAW,CAAC,OAAe;IACzC,OAAO,UAAU,CAAC,QAAQ,CAAC,CAAC,MAAM,CAAC,OAAO,EAAE,MAAM,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC;AACpE,CAAC;AAED,MAAM,UAAU,KAAK;IACnB,OAAO,UAAU,EAAE,CAAC;AACtB,CAAC;AAED,2DAA2D;AAC3D,MAAM,UAAU,UAAU,CAAC,CAAe;IACxC,OAAO,IAAI,UAAU,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC;AAC3C,CAAC;AAED,mDAAmD;AACnD,MAAM,UAAU,YAAY,CAAC,IAAuB;IAClD,IAAI,CAAC,IAAI,IAAI,IAAI,CAAC,UAAU,KAAK,CAAC;QAAE,OAAO,IAAI,CAAC;IAChD,OAAO,IAAI,YAAY,CAAC,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,IAAI,CAAC,UAAU,EAAE,IAAI,CAAC,UAAU,GAAG,IAAI,CAAC,UAAU,CAAC,CAAC,CAAC;AACjG,CAAC;AAED,MAAM,UAAU,KAAK;IACnB,OAAO,IAAI,CAAC,GAAG,EAAE,CAAC;AACpB,CAAC;AAED,MAAM,UAAU,OAAO;IACrB,GAAG,EAAE,KAAK,EAAE,CAAC;IACb,GAAG,GAAG,IAAI,CAAC;AACb,CAAC;AAED,wEAAwE;AACxE,yEAAyE;AACzE,wEAAwE;AAExE,MAAM,UAAU,WAAW;IACzB,MAAM,CAAC,GAAG,KAAK,EAAE,CAAC,OAAO,CAAC,gDAAgD,CAAC,CAAC,GAAG,EAElE,CAAC;IACd,OAAO,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;AACjC,CAAC;AAED,MAAM,UAAU,YAAY,CAAC,GAAW,EAAE,KAAa;IACrD,MAAM,EAAE,GAAG,KAAK,EAAE,CAAC;IACnB,EAAE,CAAC,OAAO,CACR,4GAA4G,CAC7G,CAAC,GAAG,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,CAAC;IACnB,EAAE,CAAC,OAAO,CACR,8GAA8G,CAC/G,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;AACf,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,SAAS,CAAC,GAAiB,EAAE,KAAa;IACxD,MAAM,OAAO,GAAG,WAAW,EAAE,CAAC;IAC9B,IAAI,OAAO,KAAK,CAAC,EAAE,CAAC;QAClB,YAAY,CAAC,GAAG,CAAC,MAAM,EAAE,KAAK,CAAC,CAAC;QAChC,OAAO;IACT,CAAC;IACD,IAAI,OAAO,KAAK,GAAG,CAAC,MAAM,EAAE,CAAC;QAC3B,MAAM,IAAI,KAAK,CACb,2CAA2C,OAAO,YAAY,aAAa,EAAE,KAAK;YAChF,mBAAmB,GAAG,CAAC,MAAM,YAAY,KAAK,KAAK;YACnD,+CAA+C,WAAW,GAAG,CAChE,CAAC;IACJ,CAAC;AACH,CAAC;AAED,MAAM,UAAU,aAAa;IAC3B,MAAM,CAAC,GAAG,KAAK,EAAE,CAAC,OAAO,CAAC,kDAAkD,CAAC,CAAC,GAAG,EAEpE,CAAC;IACd,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,CAAC;AAC1B,CAAC"}
+{"version":3,"file":"database.js","sourceRoot":"","sources":["../../src/db/database.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,YAAY,EAAE,MAAM,aAAa,CAAC;AAC3C,OAAO,KAAK,IAAI,MAAM,MAAM,CAAC;AAC7B,OAAO,KAAK,EAAE,MAAM,IAAI,CAAC;AACzB,OAAO,EAAE,UAAU,EAAE,UAAU,EAAE,MAAM,aAAa,CAAC;AAErD,MAAM,CAAC,MAAM,WAAW,GAAG,OAAO,CAAC,GAAG,CAAC,UAAU;IAC/C,CAAC,CAAC,IAAI,CAAC,OAAO,CAAC,OAAO,CAAC,GAAG,CAAC,UAAU,CAAC;IACtC,CAAC,CAAC,IAAI,CAAC,OAAO,CAAC,OAAO,CAAC,GAAG,EAAE,EAAE,WAAW,CAAC,CAAC;AAE7C,MAAM,CAAC,MAAM,OAAO,GAAG,IAAI,CAAC,IAAI,CAAC,WAAW,EAAE,YAAY,CAAC,CAAC;AAE5D,IAAI,GAAG,GAAwB,IAAI,CAAC;AAEpC,SAAS,SAAS;IAChB,IAAI,CAAC,EAAE,CAAC,UAAU,CAAC,WAAW,CAAC,EAAE,CAAC;QAChC,EAAE,CAAC,SAAS,CAAC,WAAW,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;IACjD,CAAC;AACH,CAAC;AAED,MAAM,UAAU,KAAK;IACnB,IAAI,GAAG;QAAE,OAAO,GAAG,CAAC;IACpB,SAAS,EAAE,CAAC;IACZ,MAAM,EAAE,GAAG,IAAI,YAAY,CAAC,OAAO,CAAC,CAAC;IACrC,IAAI,CAAC;QACH,+DAA+D;QAC/D,EAAE,CAAC,IAAI,CAAC,6BAA6B,CAAC,CAAC;QACvC,EAAE,CAAC,IAAI,CAAC,4BAA4B,CAAC,CAAC;QACtC,EAAE,CAAC,IAAI,CAAC,8BAA8B,CAAC,CAAC;QACxC,EAAE,CAAC,IAAI,CAAC,2BAA2B,CAAC,CAAC;QACrC,4EAA4E;QAC5E,2EAA2E;QAC3E,OAAO,CAAC,EAAE,CAAC,CAAC;IACd,CAAC;IAAC,OAAO,CAAC,EAAE,CAAC;QACX,0EAA0E;QAC1E,2EAA2E;QAC3E,4EAA4E;QAC5E,IAAI,CAAC;YACH,EAAE,CAAC,KAAK,EAAE,CAAC;QACb,CAAC;QAAC,MAAM,CAAC;YACP,oBAAoB;QACtB,CAAC;QACD,MAAM,CAAC,CAAC;IACV,CAAC;IACD,GAAG,GAAG,EAAE,CAAC;IACT,OAAO,EAAE,CAAC;AACZ,CAAC;AAED,SAAS,YAAY,CAAC,EAAgB,EAAE,KAAa,EAAE,MAAc;IACnE,2EAA2E;IAC3E,8EAA8E;IAC9E,IAAI,CAAC,0BAA0B,CAAC,IAAI,CAAC,KAAK,CAAC;QAAE,MAAM,IAAI,KAAK,CAAC,sBAAsB,KAAK,EAAE,CAAC,CAAC;IAC5F,MAAM,IAAI,GAAG,EAAE,CAAC,OAAO,CAAC,qBAAqB,KAAK,GAAG,CAAC,CAAC,GAAG,EAA6B,CAAC;IACxF,OAAO,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,KAAK,MAAM,CAAC,CAAC;AAC7C,CAAC;AAED,SAAS,OAAO,CAAC,EAAgB;IAC/B,6EAA6E;IAC7E,4EAA4E;IAC5E,yDAAyD;IACzD,EAAE,CAAC,IAAI,CAAC,kBAAkB,CAAC,CAAC;IAC5B,IAAI,CAAC;QACH,YAAY,CAAC,EAAE,CAAC,CAAC;QACjB,EAAE,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;IACrB,CAAC;IAAC,OAAO,CAAC,EAAE,CAAC;QACX,IAAI,CAAC;YACH,EAAE,CAAC,IAAI,CAAC,WAAW,CAAC,CAAC;QACvB,CAAC;QAAC,MAAM,CAAC;YACP,gCAAgC;QAClC,CAAC;QACD,MAAM,CAAC,CAAC;IACV,CAAC;AACH,CAAC;AAED,SAAS,YAAY,CAAC,EAAgB;IACpC,EAAE,CAAC,IAAI,CAAC;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA+CP,CAAC,CAAC;IAEH,2EAA2E;IAC3E,IAAI,CAAC,YAAY,CAAC,EAAE,EAAE,WAAW,EAAE,cAAc,CAAC,EAAE,CAAC;QACnD,EAAE,CAAC,IAAI,CAAC,qDAAqD,CAAC,CAAC;IACjE,CAAC;IACD,EAAE,CAAC,IAAI,CACL,yHAAyH,CAC1H,CAAC;IAEF,sEAAsE;IACtE,yEAAyE;IACzE,4EAA4E;IAC5E,8EAA8E;IAC9E,MAAM,MAAM,GAAG,EAAE;SACd,OAAO,CAAC,4EAA4E,CAAC;SACrF,GAAG,EAAkC,CAAC;IACzC,IAAI,MAAM,EAAE,CAAC;QACX,8EAA8E;QAC9E,IAAI,CAAC,CAAC,MAAM,CAAC,GAAG,IAAI,EAAE,CAAC,CAAC,QAAQ,CAAC,SAAS,CAAC;YAAE,UAAU,CAAC,EAAE,CAAC,CAAC;IAC9D,CAAC;SAAM,CAAC;QACN,uEAAuE;QACvE,8EAA8E;QAC9E,qEAAqE;QACrE,UAAU,CAAC,EAAE,CAAC,CAAC;IACjB,CAAC;AACH,CAAC;AAED,6CAA6C;AAC7C,SAAS,UAAU,CAAC,EAAgB;IAClC,EAAE,CAAC,IAAI,CAAC,kCAAkC,CAAC,CAAC;IAC5C,EAAE,CAAC,IAAI,CAAC,4EAA4E,CAAC,CAAC;IACtF,EAAE,CAAC,IAAI,CAAC,2EAA2E,CAAC,CAAC;AACvF,CAAC;AAED,4DAA4D;AAC5D,MAAM,UAAU,WAAW,CAAC,OAAe;IACzC,OAAO,UAAU,CAAC,QAAQ,CAAC,CAAC,MAAM,CAAC,OAAO,EAAE,MAAM,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC;AACpE,CAAC;AAED,MAAM,UAAU,KAAK;IACnB,OAAO,UAAU,EAAE,CAAC;AACtB,CAAC;AAED,uEAAuE;AACvE,MAAM,UAAU,UAAU,CAAC,CAAe;IACxC,OAAO,IAAI,UAAU,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,UAAU,EAAE,CAAC,CAAC,UAAU,GAAG,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC;AACnF,CAAC;AAED,wFAAwF;AACxF,MAAM,UAAU,YAAY,CAAC,IAAuB;IAClD,IAAI,CAAC,IAAI,IAAI,IAAI,CAAC,UAAU,KAAK,CAAC,IAAI,IAAI,CAAC,UAAU,GAAG,CAAC,KAAK,CAAC;QAAE,OAAO,IAAI,CAAC;IAC7E,OAAO,IAAI,YAAY,CAAC,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,IAAI,CAAC,UAAU,EAAE,IAAI,CAAC,UAAU,GAAG,IAAI,CAAC,UAAU,CAAC,CAAC,CAAC;AACjG,CAAC;AAED,MAAM,UAAU,KAAK;IACnB,OAAO,IAAI,CAAC,GAAG,EAAE,CAAC;AACpB,CAAC;AAED,MAAM,UAAU,OAAO;IACrB,GAAG,EAAE,KAAK,EAAE,CAAC;IACb,GAAG,GAAG,IAAI,CAAC;IACX,SAAS,GAAG,IAAI,CAAC;AACnB,CAAC;AAED,wEAAwE;AACxE,yEAAyE;AACzE,wEAAwE;AAExE,+EAA+E;AAC/E,IAAI,SAAS,GAAkB,IAAI,CAAC;AAEpC,MAAM,UAAU,WAAW;IACzB,IAAI,SAAS,KAAK,IAAI,EAAE,CAAC;QACvB,MAAM,CAAC,GAAG,KAAK,EAAE,CAAC,OAAO,CAAC,gDAAgD,CAAC,CAAC,GAAG,EAElE,CAAC;QACd,MAAM,CAAC,GAAG,MAAM,CAAC,CAAC,EAAE,KAAK,CAAC,CAAC;QAC3B,uEAAuE;QACvE,iDAAiD;QACjD,SAAS,GAAG,MAAM,CAAC,SAAS,CAAC,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;IACnD,CAAC;IACD,OAAO,SAAS,CAAC;AACnB,CAAC;AAED,MAAM,UAAU,YAAY,CAAC,GAAW,EAAE,KAAa;IACrD,MAAM,EAAE,GAAG,KAAK,EAAE,CAAC;IACnB,EAAE,CAAC,OAAO,CACR,4GAA4G,CAC7G,CAAC,GAAG,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,CAAC;IACnB,EAAE,CAAC,OAAO,CACR,8GAA8G,CAC/G,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;IACb,SAAS,GAAG,GAAG,CAAC;IAChB,gEAAgE;IAChE,aAAa,CAAC,OAAO,CAAC,CAAC;AACzB,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,SAAS,CAAC,GAAiB,EAAE,KAAa;IACxD,4EAA4E;IAC5E,8EAA8E;IAC9E,2EAA2E;IAC3E,mEAAmE;IACnE,qBAAqB,EAAE,CAAC;IACxB,MAAM,OAAO,GAAG,WAAW,EAAE,CAAC;IAC9B,IAAI,OAAO,KAAK,CAAC,EAAE,CAAC;QAClB,YAAY,CAAC,GAAG,CAAC,MAAM,EAAE,KAAK,CAAC,CAAC;QAChC,OAAO;IACT,CAAC;IACD,IAAI,OAAO,KAAK,GAAG,CAAC,MAAM,EAAE,CAAC;QAC3B,MAAM,IAAI,KAAK,CACb,2CAA2C,OAAO,YAAY,aAAa,EAAE,KAAK;YAChF,mBAAmB,GAAG,CAAC,MAAM,YAAY,KAAK,KAAK;YACnD,+CAA+C,WAAW,GAAG,CAChE,CAAC;IACJ,CAAC;IACD,yEAAyE;IACzE,4EAA4E;IAC5E,+EAA+E;IAC/E,MAAM,YAAY,GAAG,aAAa,EAAE,CAAC;IACrC,IAAI,YAAY,IAAI,YAAY,KAAK,KAAK,EAAE,CAAC;QAC3C,MAAM,IAAI,KAAK,CACb,uCAAuC,YAAY,eAAe,KAAK,UAAU,OAAO,SAAS;YAC/F,oFAAoF;YACpF,kBAAkB,WAAW,GAAG,CACnC,CAAC;IACJ,CAAC;AACH,CAAC;AAED,MAAM,UAAU,aAAa;IAC3B,MAAM,CAAC,GAAG,KAAK,EAAE,CAAC,OAAO,CAAC,kDAAkD,CAAC,CAAC,GAAG,EAEpE,CAAC;IACd,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,CAAC;AAC1B,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,aAAa;IAC3B,MAAM,CAAC,GAAG,KAAK,EAAE,CAAC,OAAO,CAAC,kDAAkD,CAAC,CAAC,GAAG,EAEpE,CAAC;IACd,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,CAAC;AAC1B,CAAC;AAED,MAAM,UAAU,aAAa,CAAC,KAAa;IACzC,KAAK,EAAE;SACJ,OAAO,CAAC,6GAA6G,CAAC;SACtH,GAAG,CAAC,KAAK,CAAC,CAAC;AAChB,CAAC;AAED,oFAAoF;AACpF,MAAM,UAAU,qBAAqB;IACnC,MAAM,KAAK,GAAG,aAAa,EAAE,CAAC;IAC9B,IAAI,KAAK,KAAK,EAAE,IAAI,KAAK,KAAK,OAAO,EAAE,CAAC;QACtC,MAAM,IAAI,KAAK,CACb,qCAAqC,KAAK,2CAA2C;YACnF,mFAAmF;YACnF,6BAA6B,WAAW,GAAG,CAC9C,CAAC;IACJ,CAAC;AACH,CAAC"}

package/dist/env.js

@@ -6,38 +6,58 @@
  * config (MCP clients, CI, shell) always wins. Runs synchronously at import —
  * must be imported before any module that reads `process.env.*` at load time.
  * Supports `#` comments, `export KEY=` prefixes, and single/double-quoted values.
+ *
+ * Only this package's own knobs are loadable: an untrusted repo's `.env` must
+ * not be able to inject arbitrary process.env entries into the host session.
  */
 import * as fs from "fs";
 import * as path from "path";
+/** Prefixes/names this server actually reads. */
+const LOADABLE = /^(RAG_[A-Z0-9_]+|OPENCODE_[A-Z0-9_]+|EMBEDDING_[A-Z0-9_]+|SEARCH_MODE)$/;
+const VALID_KEY = /^[A-Za-z_][A-Za-z0-9_]*$/;
+/** Strip one layer of matching quotes plus any trailing `# comment`. */
+function unquote(value) {
+    const q = value[0];
+    if (q === '"' || q === "'") {
+        const close = value.indexOf(q, 1);
+        if (close > 0) {
+            const rest = value.slice(close + 1).trim();
+            if (rest === "" || rest.startsWith("#"))
+                return value.slice(1, close);
+        }
+    }
+    const hash = value.indexOf(" #");
+    return hash >= 0 ? value.slice(0, hash).trimEnd() : value;
+}
 export function loadDotenv(file) {
     let raw;
     try {
         raw = fs.readFileSync(file, "utf8");
     }
-    catch {
+    catch (e) {
+        if (process.env.RAG_ENV_FILE) {
+            process.stderr.write(`env: cannot read RAG_ENV_FILE ${file} (${e.message})\n`);
+        }
         return;
     }
     for (const line of raw.split(/\r?\n/)) {
         let t = line.trim();
         if (!t || t.startsWith("#"))
             continue;
-        if (t.startsWith("export "))
+        if (t.startsWith("export ") || t.startsWith("export\t"))
             t = t.slice(7).trimStart();
         const eq = t.indexOf("=");
         if (eq <= 0)
             continue;
         const key = t.slice(0, eq).trim();
-        let value = t.slice(eq + 1).trim();
-        // Strip trailing inline comments for unquoted values (e.g. `KEY=val # note`).
-        if (!value.startsWith('"') && !value.startsWith("'")) {
-            const hash = value.indexOf(" #");
-            if (hash >= 0)
-                value = value.slice(0, hash).trimEnd();
-        }
-        if (value.length >= 2 && ((value.startsWith('"') && value.endsWith('"')) || (value.startsWith("'") && value.endsWith("'")))) {
-            value = value.slice(1, -1);
+        if (!VALID_KEY.test(key))
+            continue;
+        if (!LOADABLE.test(key)) {
+            process.stderr.write(`env: ignoring ${key} (not an mcp-rag-memory variable)\n`);
+            continue;
         }
-        if (key && process.env[key] === undefined)
+        const value = unquote(t.slice(eq + 1).trim());
+        if (process.env[key] === undefined)
             process.env[key] = value;
     }
 }

package/dist/mcp/rag-server.js

@@ -4,13 +4,32 @@ import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js"
 import { z } from "zod";
 import * as path from "path";
 import { createRequire } from "node:module";
-import { STORAGE_DIR } from "../db/database.js";
+import { STORAGE_DIR, closeDB, getEmbedState } from "../db/database.js";
 import { embeddingInfo } from "../rag/embeddings.js";
-import { ingestText, ingestFile, ingestDirectory, searchDocs, retrieve, listDocuments, deleteDocument, documentStats, } from "../rag/pipeline.js";
+import { reindex } from "../rag/reindex.js";
+import { ingestText, ingestFile, ingestDirectory, searchDocs, retrieve, listDocuments, deleteDocument, documentStats, MAX_INGEST_CHARS, } from "../rag/pipeline.js";
 import { ingestSession as syncSession, ingestLatest as syncLatest, } from "../session/transcript.js";
 import { remember, recall, listMemories, getMemory, updateMemory, forget, consolidate, memoryStats, contextPrompt, MEMORY_TYPES, } from "../memory/memory.js";
 const require = createRequire(import.meta.url);
 const serverVersion = require("../../package.json").version;
+/**
+ * Input bounds for every tool schema.
+ *
+ * These were all unbounded `z.string().min(1)`, which meant a single tool call
+ * could push a megabyte of text straight into the chunker and embedder (a
+ * synchronous CPU spin that blocks the whole stdio server), or a path long
+ * enough to be a denial of service. The caps sit above any realistic input and
+ * well below anything that would stall the process.
+ */
+const MAX_ID = 200;
+const MAX_QUERY = 2_000;
+const MAX_PATH = 4_096;
+const MAX_TITLE = 500;
+const MAX_TAG = 64;
+const MAX_TAGS = 64;
+const MAX_TOPIC = 500;
+/** A memory is a self-contained statement, not a document. */
+const MAX_MEMORY_CONTENT = 20_000;
 const server = new McpServer({
     name: "rag-memory-server",
     version: serverVersion,
@@ -24,25 +43,65 @@ server.registerTool("system_stats", {
 }, async () => {
     const docs = documentStats();
     const mem = memoryStats();
+    // Surface the embed_state too: a store stuck mid-reindex refuses every search,
+    // and system_stats is the first thing anyone calls when a tool starts failing.
+    const state = getEmbedState();
     return {
         content: [
             {
                 type: "text",
-                text: JSON.stringify({ dbDir: STORAGE_DIR, embedding: embeddingInfo(), documents: docs, memories: mem }, null, 2),
+                text: JSON.stringify({
+                    dbDir: STORAGE_DIR,
+                    embedding: embeddingInfo(),
+                    storeState: state === "" || state === "ready" ? "ready" : state,
+                    ...(state !== "" && state !== "ready"
+                        ? { remediation: "Run 'rag_reindex' to finish the interrupted migration." }
+                        : {}),
+                    documents: docs,
+                    memories: mem,
+                }, null, 2),
             },
         ],
     };
 });
 /* ------------------------------------------------------------------ */
+/* Maintenance                                                         */
+/* ------------------------------------------------------------------ */
+server.registerTool("rag_reindex", {
+    description: "Re-embed every stored vector for the currently configured EMBEDDING_PROVIDER/MODEL. " +
+        "Use after changing the embedding model or dimension to migrate the existing store in place " +
+        "instead of wiping and re-ingesting. Searches are blocked while it runs; re-run to resume " +
+        "after an interruption.",
+    inputSchema: {
+        batch_size: z
+            .number()
+            .int()
+            .min(1)
+            .max(200)
+            .optional()
+            .default(32)
+            .describe("Chunks embedded per transaction. Lower uses less memory, higher is faster."),
+    },
+}, async (args) => {
+    const res = await reindex({
+        batchSize: args.batch_size ?? 32,
+        onProgress: (p) => {
+            if (p.total > 0)
+                process.stderr.write(`reindex ${p.phase}: ${p.done}/${p.total}\n`);
+        },
+    });
+    return { content: [{ type: "text", text: JSON.stringify(res, null, 2) }] };
+});
+/* ------------------------------------------------------------------ */
 /* RAG: ingest                                                         */
 /* ------------------------------------------------------------------ */
 server.registerTool("rag_ingest_text", {
     description: "Store raw text as a knowledge document (chunked + embedded for later retrieval)",
     inputSchema: {
-        content: z.string().min(1),
-        title: z.string().describe("Document title"),
-        contentType: z.string().optional().describe("e.g. markdown, typescript, text, json"),
-        metadata: z.record(z.string(), z.unknown()).optional(),
+        content: z.string().min(1).max(MAX_INGEST_CHARS),
+        title: z.string().max(MAX_TITLE).describe("Document title"),
+        contentType: z.string().max(64).optional().describe("e.g. markdown, typescript, text, json"),
+        metadata: z.record(z.string().max(MAX_TAG), z.unknown()).optional(),
     },
 }, async (args) => {
     const res = await ingestText(args.content, args.title, {
@@ -52,10 +111,10 @@ server.registerTool("rag_ingest_text", {
     return { content: [{ type: "text", text: JSON.stringify(res, null, 2) }] };
 });
 server.registerTool("rag_ingest_file", {
-    description: "Read a file and store it as a knowledge document",
+    description: "Read a file and store it as a knowledge document. Honours RAG_ALLOWED_DIRS when set.",
     inputSchema: {
-        path: z.string().describe("Absolute path to the file"),
-        metadata: z.record(z.string(), z.unknown()).optional(),
+        path: z.string().min(1).max(MAX_PATH).describe("Absolute path to the file"),
+        metadata: z.record(z.string().max(MAX_TAG), z.unknown()).optional(),
     },
 }, async (args) => {
     const res = await ingestFile(args.path, { metadata: args.metadata });
@@ -64,9 +123,9 @@ server.registerTool("rag_ingest_file", {
 server.registerTool("rag_ingest_dir", {
     description: "Recursively ingest supported source files from a directory",
     inputSchema: {
-        path: z.string().describe("Absolute path to the directory"),
+        path: z.string().min(1).max(MAX_PATH).describe("Absolute path to the directory"),
         recursive: z.boolean().optional().default(true),
-        extensions: z.array(z.string()).optional().describe("File extensions to include, e.g. ['.ts', '.md']"),
+        extensions: z.array(z.string().min(1).max(16)).min(1).max(64).optional().describe("File extensions to include, e.g. ['.ts', '.md']"),
     },
 }, async (args) => {
     const res = await ingestDirectory(args.path, { recursive: args.recursive, extensions: args.extensions });
@@ -76,19 +135,20 @@ server.registerTool("rag_ingest_dir", {
 /* RAG: search / retrieve                                              */
 /* ------------------------------------------------------------------ */
 server.registerTool("rag_search", {
-    description: "Hybrid semantic + keyword search over stored documents. Returns chunks ranked by relevance with scores.",
+    description: "Hybrid semantic + keyword search over stored documents. Returns chunks ranked by relevance with scores. Set explain to see per-leg scores (vector cosine, keyword BM25, RRF contribution) and diagnose ranking.",
     inputSchema: {
-        query: z.string().min(1),
+        query: z.string().min(1).max(MAX_QUERY),
         top_k: z.number().int().min(1).max(50).optional().default(10),
         min_score: z.number().min(0).max(1).optional().default(0.08),
-        doc_id: z.string().optional().describe("Only search within this document"),
-        source: z.string().optional().describe("Only search documents with this source (e.g. 'opencode-db', 'session-log')"),
+        doc_id: z.string().max(MAX_ID).optional().describe("Only search within this document"),
+        source: z.string().max(MAX_ID).optional().describe("Only search documents with this source (e.g. 'opencode-db', 'session-log')"),
+        explain: z.boolean().optional().default(false).describe("Include per-leg vector/keyword/RRF scores on every hit"),
     },
 }, async (args) => {
     const hits = await searchDocs(args.query, args.top_k ?? 10, args.min_score ?? 0.08, {
         docId: args.doc_id,
         source: args.source,
-    });
+    }, args.explain ?? false);
     return {
         content: [{ type: "text", text: JSON.stringify(hits, null, 2) }],
     };
@@ -96,11 +156,11 @@ server.registerTool("rag_search", {
 server.registerTool("rag_retrieve", {
     description: "Retrieve relevant context chunks as a ready-to-inject context block for the LLM. Prefer this over rag_search when the result will be used as context.",
     inputSchema: {
-        query: z.string().min(1),
+        query: z.string().min(1).max(MAX_QUERY),
         top_k: z.number().int().min(1).max(20).optional().default(6),
         min_score: z.number().min(0).max(1).optional().default(0.08),
-        doc_id: z.string().optional().describe("Only retrieve within this document"),
-        source: z.string().optional().describe("Only retrieve documents with this source"),
+        doc_id: z.string().max(MAX_ID).optional().describe("Only retrieve within this document"),
+        source: z.string().max(MAX_ID).optional().describe("Only retrieve documents with this source"),
     },
 }, async (args) => {
     const res = await retrieve(args.query, args.top_k ?? 6, args.min_score ?? 0.08, {
@@ -124,10 +184,13 @@ server.registerTool("rag_retrieve", {
 /* RAG: document management                                            */
 /* ------------------------------------------------------------------ */
 server.registerTool("rag_list_documents", {
-    description: "List all stored knowledge documents",
-    inputSchema: {},
-}, async () => {
-    const docs = listDocuments();
+    description: "List stored knowledge documents (newest first, paginated)",
+    inputSchema: {
+        limit: z.number().int().min(1).max(1000).optional().default(100).describe("Max documents to return"),
+        offset: z.number().int().min(0).optional().default(0).describe("Skip this many documents"),
+    },
+}, async (args) => {
+    const docs = listDocuments({ limit: args.limit, offset: args.offset });
     return { content: [{ type: "text", text: JSON.stringify(docs, null, 2) }] };
 });
 server.registerTool("rag_document_stats", {
@@ -139,7 +202,7 @@ server.registerTool("rag_document_stats", {
 server.registerTool("rag_delete_document", {
     description: "Delete a document and all its chunks by ID",
     inputSchema: {
-        doc_id: z.string().min(1),
+        doc_id: z.string().min(1).max(MAX_ID),
     },
 }, async (args) => {
     const res = deleteDocument(args.doc_id);
@@ -151,23 +214,23 @@ server.registerTool("rag_delete_document", {
 server.registerTool("rag_sync_session", {
     description: "Ingest an opencode session's user inputs (or the latest active session) into the RAG store as searchable documents. Use with the session id from opencode, or omit session_id and pass directory to auto-pick the most recent session in that workspace.",
     inputSchema: {
-        session_id: z.string().optional().describe("opencode session id; omit to use the latest active session"),
-        directory: z.string().optional().describe("Workspace path used to pick the latest session when session_id is omitted"),
-        limit: z.number().int().min(1).optional().describe("Only ingest the first N user messages"),
+        session_id: z.string().min(1).max(MAX_ID).optional().describe("opencode session id; omit to use the latest active session"),
+        directory: z.string().min(1).max(MAX_PATH).optional().describe("Workspace path used to pick the latest session when session_id is omitted (defaults to the server's working directory)"),
+        limit: z.number().int().min(1).max(2000).optional().describe("Only ingest the first N user messages"),
     },
 }, async (args) => {
     const res = args.session_id
         ? await syncSession(args.session_id, { limit: args.limit })
-        : await syncLatest({ limit: args.limit, directory: args.directory });
+        : await syncLatest({ limit: args.limit, directory: args.directory ?? process.cwd() });
     return { content: [{ type: "text", text: JSON.stringify(res, null, 2) }] };
 });
 server.registerTool("memory_remember", {
     description: "Store a piece of long-term memory (fact, decision, preference, instruction, task, insight, conversation). Use this to persist things that should be remembered across sessions.",
     inputSchema: {
-        content: z.string().min(1).describe("The memory content, written as a self-contained statement"),
+        content: z.string().min(1).max(MAX_MEMORY_CONTENT).describe("The memory content, written as a self-contained statement"),
         type: z.enum(MEMORY_TYPES).optional().default("fact"),
         importance: z.number().min(0).max(1).optional().default(0.5).describe("0..1, higher = keep longer"),
-        tags: z.array(z.string()).optional().describe("Tags for filtering"),
+        tags: z.array(z.string().max(MAX_TAG)).max(MAX_TAGS).optional().describe("Tags for filtering"),
     },
 }, async (args) => {
     const rec = await remember({
@@ -181,7 +244,7 @@ server.registerTool("memory_remember", {
 server.registerTool("memory_recall", {
     description: "Semantically search long-term memories relevant to a query. This is how you remember past context.",
     inputSchema: {
-        query: z.string().min(1),
+        query: z.string().min(1).max(MAX_QUERY),
         top_k: z.number().int().min(1).max(30).optional().default(8),
         min_score: z.number().min(0).max(1).optional().default(0.1),
     },
@@ -193,7 +256,7 @@ server.registerTool("memory_list", {
     description: "List memories, optionally filtered by type, tag, or minimum importance",
     inputSchema: {
         type: z.enum(MEMORY_TYPES).optional(),
-        tag: z.string().optional(),
+        tag: z.string().max(MAX_TAG).optional(),
         min_importance: z.number().min(0).max(1).optional(),
         limit: z.number().int().min(1).max(500).optional().default(100),
     },
@@ -209,7 +272,7 @@ server.registerTool("memory_list", {
 server.registerTool("memory_get", {
     description: "Get a single memory by ID",
     inputSchema: {
-        id: z.string().min(1),
+        id: z.string().min(1).max(MAX_ID),
     },
 }, async (args) => {
     const rec = getMemory(args.id);
@@ -220,13 +283,18 @@ server.registerTool("memory_get", {
 server.registerTool("memory_update", {
     description: "Update content / type / importance / tags of an existing memory",
     inputSchema: {
-        id: z.string().min(1),
-        content: z.string().optional(),
+        id: z.string().min(1).max(MAX_ID),
+        content: z.string().max(MAX_MEMORY_CONTENT).optional(),
         type: z.enum(MEMORY_TYPES).optional(),
         importance: z.number().min(0).max(1).optional(),
-        tags: z.array(z.string()).optional(),
+        tags: z.array(z.string().max(MAX_TAG)).max(MAX_TAGS).optional(),
     },
 }, async (args) => {
+    // An all-undefined patch used to re-embed the text and bump updated_at,
+    // silently reordering the store.
+    if (args.content === undefined && args.type === undefined && args.importance === undefined && args.tags === undefined) {
+        return { content: [{ type: "text", text: "Nothing to update: provide content, type, importance and/or tags." }] };
+    }
     const rec = await updateMemory(args.id, {
         content: args.content,
         type: args.type,
@@ -240,7 +308,7 @@ server.registerTool("memory_update", {
 server.registerTool("memory_forget", {
     description: "Delete a memory by ID",
     inputSchema: {
-        id: z.string().min(1),
+        id: z.string().min(1).max(MAX_ID),
     },
 }, async (args) => {
     const res = forget(args.id);
@@ -262,7 +330,7 @@ server.registerTool("memory_stats", {
 server.registerTool("memory_context", {
     description: "Build a compact context block from the most relevant memories for a given topic. Best for injecting memory into prompts.",
     inputSchema: {
-        topic: z.string().min(1),
+        topic: z.string().min(1).max(MAX_TOPIC),
         top_k: z.number().int().min(1).max(20).optional().default(6),
     },
 }, async (args) => {
@@ -282,4 +350,37 @@ server.registerTool("memory_context", {
 const transport = new StdioServerTransport();
 await server.connect(transport);
 console.error(`RAG + Context Management MCP server running (db: ${path.resolve(STORAGE_DIR)})`);
+/**
+ * Close the SQLite handle before the process exits.
+ *
+ * SQLite in DELETE journal mode rolls back on an abrupt exit, so a hard kill is
+ * safe, but it leaves the `-journal` file behind and skips any WAL checkpoint.
+ * On a stdio MCP server the host closing the pipe is the normal way this
+ * process dies, so an explicit shutdown keeps the store tidy and lets a WAL
+ * database truncate instead of growing.
+ *
+ * Exit is forced after a grace period because the host may not respond to
+ * `server.close()`, and a server that refuses to die is worse than one that
+ * drops an unflushed log line.
+ */
+let shuttingDown = false;
+function shutdown(signal) {
+    if (shuttingDown)
+        return;
+    shuttingDown = true;
+    console.error(`RAG memory: ${signal} received, closing database.`);
+    try {
+        closeDB();
+    }
+    catch (err) {
+        console.error(`RAG memory: database close failed: ${String(err)}`);
+    }
+    void server.close().finally(() => {
+        process.exit(0);
+    });
+    setTimeout(() => process.exit(0), 2_000).unref();
+}
+process.on("SIGINT", () => shutdown("SIGINT"));
+process.on("SIGTERM", () => shutdown("SIGTERM"));
+process.on("SIGHUP", () => shutdown("SIGHUP"));
 //# sourceMappingURL=rag-server.js.map