dsh-tdai-memory 0.3.2 → 0.3.3

package/vendor/tdai/core/seed/types.js

@@ -1,9 +1,9 @@
-/**
- * Shared type definitions for the `seed` command.
- *
- * Covers:
- * - Raw input shapes (Format A / B / JSONL)
- * - Normalized internal structures
- * - Validation error descriptors
- */
-export {};
+/**
+ * Shared type definitions for the `seed` command.
+ *
+ * Covers:
+ * - Raw input shapes (Format A / B / JSONL)
+ * - Normalized internal structures
+ * - Validation error descriptors
+ */
+export {};

package/vendor/tdai/core/store/bm25-client.js

@@ -1,117 +1,117 @@
-/**
- * BM25 Sparse Vector Encoding Client.
- *
- * HTTP client for the BM25 Python sidecar service (bm25_server.py).
- * Used by TCVDB backend to generate sparse vectors for hybridSearch.
- *
- * Two operations:
- * - `encodeTexts(texts)` — encode documents for upsert (TF-based)
- * - `encodeQueries(texts)` — encode queries for search (IDF-based)
- *
- * Graceful degradation: if the sidecar is unreachable, all methods
- * return empty arrays and `isHealthy()` returns false. Callers can
- * check health to dynamically downgrade to pure semantic search.
- */
-// ============================
-// Implementation
-// ============================
-const TAG = "[memory-tdai][bm25-client]";
-export class BM25Client {
-    baseUrl;
-    timeout;
-    logger;
-    /** Cached health status to avoid repeated checks on every call. */
-    _healthy;
-    _lastHealthCheck = 0;
-    static HEALTH_CHECK_INTERVAL_MS = 30_000; // re-check every 30s
-    constructor(config, logger) {
-        this.baseUrl = config.serviceUrl.replace(/\/+$/, "");
-        this.timeout = config.timeout;
-        this.logger = logger;
-    }
-    /**
-     * Encode document texts for upsert (TF-based BM25 scoring).
-     * Returns one SparseVector per input text.
-     * Returns empty array on error (non-throwing).
-     */
-    async encodeTexts(texts) {
-        if (texts.length === 0)
-            return [];
-        return this._encode("/encode_texts", texts);
-    }
-    /**
-     * Encode query texts for search (IDF-based BM25 scoring).
-     * Returns one SparseVector per input text.
-     * Returns empty array on error (non-throwing).
-     */
-    async encodeQueries(texts) {
-        if (texts.length === 0)
-            return [];
-        return this._encode("/encode_queries", texts);
-    }
-    /**
-     * Check if the BM25 sidecar is reachable.
-     * Result is cached for 30 seconds to avoid spamming health checks.
-     */
-    async isHealthy() {
-        const now = Date.now();
-        if (this._healthy !== undefined &&
-            now - this._lastHealthCheck < BM25Client.HEALTH_CHECK_INTERVAL_MS) {
-            return this._healthy;
-        }
-        try {
-            const resp = await fetch(`${this.baseUrl}/health`, {
-                signal: AbortSignal.timeout(3000),
-            });
-            this._healthy = resp.ok;
-        }
-        catch {
-            this._healthy = false;
-        }
-        this._lastHealthCheck = now;
-        if (!this._healthy) {
-            this.logger?.warn(`${TAG} BM25 sidecar health check failed (${this.baseUrl})`);
-        }
-        return this._healthy;
-    }
-    // ── Internal ──────────────────────────────────────────────────
-    async _encode(path, texts) {
-        try {
-            const resp = await fetch(`${this.baseUrl}${path}`, {
-                method: "POST",
-                headers: { "Content-Type": "application/json" },
-                body: JSON.stringify({ texts }),
-                signal: AbortSignal.timeout(this.timeout),
-            });
-            if (!resp.ok) {
-                const errBody = await resp.text().catch(() => "(unreadable)");
-                this.logger?.warn(`${TAG} ${path} HTTP ${resp.status}: ${errBody.slice(0, 200)}`);
-                return [];
-            }
-            const json = (await resp.json());
-            return json.vectors ?? [];
-        }
-        catch (err) {
-            // Mark unhealthy on connection errors
-            this._healthy = false;
-            this._lastHealthCheck = Date.now();
-            this.logger?.warn(`${TAG} ${path} failed: ${err instanceof Error ? err.message : String(err)}`);
-            return [];
-        }
-    }
-}
-// ============================
-// Factory
-// ============================
-/**
- * Create a BM25Client if BM25 is enabled in config.
- * Returns undefined if disabled — callers should check before using.
- */
-export function createBM25Client(config, logger) {
-    if (!config.enabled) {
-        logger?.info(`${TAG} BM25 sparse encoding disabled`);
-        return undefined;
-    }
-    logger?.info(`${TAG} BM25 client → ${config.serviceUrl}`);
-    return new BM25Client({ serviceUrl: config.serviceUrl, timeout: config.timeout }, logger);
-}
+/**
+ * BM25 Sparse Vector Encoding Client.
+ *
+ * HTTP client for the BM25 Python sidecar service (bm25_server.py).
+ * Used by TCVDB backend to generate sparse vectors for hybridSearch.
+ *
+ * Two operations:
+ * - `encodeTexts(texts)` — encode documents for upsert (TF-based)
+ * - `encodeQueries(texts)` — encode queries for search (IDF-based)
+ *
+ * Graceful degradation: if the sidecar is unreachable, all methods
+ * return empty arrays and `isHealthy()` returns false. Callers can
+ * check health to dynamically downgrade to pure semantic search.
+ */
+// ============================
+// Implementation
+// ============================
+const TAG = "[memory-tdai][bm25-client]";
+export class BM25Client {
+    baseUrl;
+    timeout;
+    logger;
+    /** Cached health status to avoid repeated checks on every call. */
+    _healthy;
+    _lastHealthCheck = 0;
+    static HEALTH_CHECK_INTERVAL_MS = 30_000; // re-check every 30s
+    constructor(config, logger) {
+        this.baseUrl = config.serviceUrl.replace(/\/+$/, "");
+        this.timeout = config.timeout;
+        this.logger = logger;
+    }
+    /**
+     * Encode document texts for upsert (TF-based BM25 scoring).
+     * Returns one SparseVector per input text.
+     * Returns empty array on error (non-throwing).
+     */
+    async encodeTexts(texts) {
+        if (texts.length === 0)
+            return [];
+        return this._encode("/encode_texts", texts);
+    }
+    /**
+     * Encode query texts for search (IDF-based BM25 scoring).
+     * Returns one SparseVector per input text.
+     * Returns empty array on error (non-throwing).
+     */
+    async encodeQueries(texts) {
+        if (texts.length === 0)
+            return [];
+        return this._encode("/encode_queries", texts);
+    }
+    /**
+     * Check if the BM25 sidecar is reachable.
+     * Result is cached for 30 seconds to avoid spamming health checks.
+     */
+    async isHealthy() {
+        const now = Date.now();
+        if (this._healthy !== undefined &&
+            now - this._lastHealthCheck < BM25Client.HEALTH_CHECK_INTERVAL_MS) {
+            return this._healthy;
+        }
+        try {
+            const resp = await fetch(`${this.baseUrl}/health`, {
+                signal: AbortSignal.timeout(3000),
+            });
+            this._healthy = resp.ok;
+        }
+        catch {
+            this._healthy = false;
+        }
+        this._lastHealthCheck = now;
+        if (!this._healthy) {
+            this.logger?.warn(`${TAG} BM25 sidecar health check failed (${this.baseUrl})`);
+        }
+        return this._healthy;
+    }
+    // ── Internal ──────────────────────────────────────────────────
+    async _encode(path, texts) {
+        try {
+            const resp = await fetch(`${this.baseUrl}${path}`, {
+                method: "POST",
+                headers: { "Content-Type": "application/json" },
+                body: JSON.stringify({ texts }),
+                signal: AbortSignal.timeout(this.timeout),
+            });
+            if (!resp.ok) {
+                const errBody = await resp.text().catch(() => "(unreadable)");
+                this.logger?.warn(`${TAG} ${path} HTTP ${resp.status}: ${errBody.slice(0, 200)}`);
+                return [];
+            }
+            const json = (await resp.json());
+            return json.vectors ?? [];
+        }
+        catch (err) {
+            // Mark unhealthy on connection errors
+            this._healthy = false;
+            this._lastHealthCheck = Date.now();
+            this.logger?.warn(`${TAG} ${path} failed: ${err instanceof Error ? err.message : String(err)}`);
+            return [];
+        }
+    }
+}
+// ============================
+// Factory
+// ============================
+/**
+ * Create a BM25Client if BM25 is enabled in config.
+ * Returns undefined if disabled — callers should check before using.
+ */
+export function createBM25Client(config, logger) {
+    if (!config.enabled) {
+        logger?.info(`${TAG} BM25 sparse encoding disabled`);
+        return undefined;
+    }
+    logger?.info(`${TAG} BM25 client → ${config.serviceUrl}`);
+    return new BM25Client({ serviceUrl: config.serviceUrl, timeout: config.timeout }, logger);
+}

package/vendor/tdai/core/store/bm25-local.js

@@ -1,68 +1,68 @@
-/**
- * Local BM25 Sparse Vector Encoder.
- *
- * Pure TypeScript replacement for the Python sidecar BM25 client.
- * Uses @tencentdb-agent-memory/tcvdb-text package for tokenization (jieba-wasm) and BM25 encoding.
- *
- * Two operations (same contract as the old BM25Client):
- * - `encodeTexts(texts)` — encode documents for upsert (TF-based)
- * - `encodeQueries(texts)` — encode queries for search (IDF-based)
- */
-import { BM25Encoder } from "@tencentdb-agent-memory/tcvdb-text";
-const TAG = "[memory-tdai][bm25-local]";
-// ============================
-// Implementation
-// ============================
-export class BM25LocalEncoder {
-    encoder;
-    logger;
-    constructor(language = "zh", logger) {
-        this.logger = logger;
-        this.encoder = BM25Encoder.default(language);
-        logger?.debug?.(`${TAG} Initialized BM25 local encoder (language=${language})`);
-    }
-    /**
-     * Encode document texts for upsert (TF-based BM25 scoring).
-     * Returns one SparseVector per input text.
-     */
-    encodeTexts(texts) {
-        if (texts.length === 0)
-            return [];
-        try {
-            return this.encoder.encodeTexts(texts);
-        }
-        catch (err) {
-            this.logger?.warn(`${TAG} encodeTexts failed: ${err instanceof Error ? err.message : String(err)}`);
-            return [];
-        }
-    }
-    /**
-     * Encode query texts for search (IDF-based BM25 scoring).
-     * Returns one SparseVector per input text.
-     */
-    encodeQueries(texts) {
-        if (texts.length === 0)
-            return [];
-        try {
-            return this.encoder.encodeQueries(texts);
-        }
-        catch (err) {
-            this.logger?.warn(`${TAG} encodeQueries failed: ${err instanceof Error ? err.message : String(err)}`);
-            return [];
-        }
-    }
-}
-// ============================
-// Factory
-// ============================
-/**
- * Create a BM25LocalEncoder if BM25 is enabled in config.
- * Returns undefined if disabled — callers should check before using.
- */
-export function createBM25Encoder(config, logger) {
-    if (!config.enabled) {
-        logger?.debug?.(`${TAG} BM25 sparse encoding disabled`);
-        return undefined;
-    }
-    return new BM25LocalEncoder(config.language ?? "zh", logger);
-}
+/**
+ * Local BM25 Sparse Vector Encoder.
+ *
+ * Pure TypeScript replacement for the Python sidecar BM25 client.
+ * Uses @tencentdb-agent-memory/tcvdb-text package for tokenization (jieba-wasm) and BM25 encoding.
+ *
+ * Two operations (same contract as the old BM25Client):
+ * - `encodeTexts(texts)` — encode documents for upsert (TF-based)
+ * - `encodeQueries(texts)` — encode queries for search (IDF-based)
+ */
+import { BM25Encoder } from "@tencentdb-agent-memory/tcvdb-text";
+const TAG = "[memory-tdai][bm25-local]";
+// ============================
+// Implementation
+// ============================
+export class BM25LocalEncoder {
+    encoder;
+    logger;
+    constructor(language = "zh", logger) {
+        this.logger = logger;
+        this.encoder = BM25Encoder.default(language);
+        logger?.debug?.(`${TAG} Initialized BM25 local encoder (language=${language})`);
+    }
+    /**
+     * Encode document texts for upsert (TF-based BM25 scoring).
+     * Returns one SparseVector per input text.
+     */
+    encodeTexts(texts) {
+        if (texts.length === 0)
+            return [];
+        try {
+            return this.encoder.encodeTexts(texts);
+        }
+        catch (err) {
+            this.logger?.warn(`${TAG} encodeTexts failed: ${err instanceof Error ? err.message : String(err)}`);
+            return [];
+        }
+    }
+    /**
+     * Encode query texts for search (IDF-based BM25 scoring).
+     * Returns one SparseVector per input text.
+     */
+    encodeQueries(texts) {
+        if (texts.length === 0)
+            return [];
+        try {
+            return this.encoder.encodeQueries(texts);
+        }
+        catch (err) {
+            this.logger?.warn(`${TAG} encodeQueries failed: ${err instanceof Error ? err.message : String(err)}`);
+            return [];
+        }
+    }
+}
+// ============================
+// Factory
+// ============================
+/**
+ * Create a BM25LocalEncoder if BM25 is enabled in config.
+ * Returns undefined if disabled — callers should check before using.
+ */
+export function createBM25Encoder(config, logger) {
+    if (!config.enabled) {
+        logger?.debug?.(`${TAG} BM25 sparse encoding disabled`);
+        return undefined;
+    }
+    return new BM25LocalEncoder(config.language ?? "zh", logger);
+}