@jami-studio/harness-store-hosted 0.1.0

package/LICENSE

@@ -0,0 +1,159 @@
+Apache License
+Version 2.0, January 2004
+https://www.apache.org/licenses/
+
+TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+1. Definitions.
+
+"License" shall mean the terms and conditions for use, reproduction, and
+distribution as defined by Sections 1 through 9 of this document.
+
+"Licensor" shall mean the copyright owner or entity authorized by the
+copyright owner that is granting the License.
+
+"Legal Entity" shall mean the union of the acting entity and all other
+entities that control, are controlled by, or are under common control with
+that entity. For the purposes of this definition, "control" means (i) the
+power, direct or indirect, to cause the direction or management of such
+entity, whether by contract or otherwise, or (ii) ownership of fifty percent
+or more of the outstanding shares, or (iii) beneficial ownership of such
+entity.
+
+"You" or "Your" shall mean an individual or Legal Entity exercising
+permissions granted by this License.
+
+"Source" form shall mean the preferred form for making modifications,
+including but not limited to software source code, documentation source, and
+configuration files.
+
+"Object" form shall mean any form resulting from mechanical transformation or
+translation of a Source form, including but not limited to compiled object
+code, generated documentation, and conversions to other media types.
+
+"Work" shall mean the work of authorship, whether in Source or Object form,
+made available under the License, as indicated by a copyright notice that is
+included in or attached to the work.
+
+"Derivative Works" shall mean any work, whether in Source or Object form,
+that is based on or derived from the Work and for which the editorial
+revisions, annotations, elaborations, or other modifications represent, as a
+whole, an original work of authorship. For the purposes of this License,
+Derivative Works shall not include works that remain separable from, or
+merely link or bind by name to the interfaces of, the Work and Derivative
+Works thereof.
+
+"Contribution" shall mean any work of authorship, including the original
+version of the Work and any modifications or additions to that Work or
+Derivative Works thereof, that is intentionally submitted to Licensor for
+inclusion in the Work by the copyright owner or by an individual or Legal
+Entity authorized to submit on behalf of the copyright owner. For the purposes
+of this definition, "submitted" means any form of electronic, verbal, or
+written communication sent to the Licensor or its representatives, including
+but not limited to communication on electronic mailing lists, source code
+control systems, and issue tracking systems that are managed by, or on behalf
+of, the Licensor for the purpose of discussing and improving the Work, but
+excluding communication that is conspicuously marked or otherwise designated
+in writing by the copyright owner as "Not a Contribution."
+
+"Contributor" shall mean Licensor and any individual or Legal Entity on
+behalf of whom a Contribution has been received by Licensor and subsequently
+incorporated within the Work.
+
+2. Grant of Copyright License. Subject to the terms and conditions of this
+License, each Contributor hereby grants to You a perpetual, worldwide,
+non-exclusive, no-charge, royalty-free, irrevocable copyright license to
+reproduce, prepare Derivative Works of, publicly display, publicly perform,
+sublicense, and distribute the Work and such Derivative Works in Source or
+Object form.
+
+3. Grant of Patent License. Subject to the terms and conditions of this
+License, each Contributor hereby grants to You a perpetual, worldwide,
+non-exclusive, no-charge, royalty-free, irrevocable patent license to make,
+have made, use, offer to sell, sell, import, and otherwise transfer the Work,
+where such license applies only to those patent claims licensable by such
+Contributor that are necessarily infringed by their Contribution alone or by
+combination of their Contribution with the Work to which such Contribution was
+submitted. If You institute patent litigation against any entity alleging that
+the Work or a Contribution incorporated within the Work constitutes direct or
+contributory patent infringement, then any patent licenses granted to You
+under this License for that Work shall terminate as of the date such
+litigation is filed.
+
+4. Redistribution. You may reproduce and distribute copies of the Work or
+Derivative Works thereof in any medium, with or without modifications, and in
+Source or Object form, provided that You meet the following conditions:
+
+(a) You must give any other recipients of the Work or Derivative Works a copy
+of this License; and
+
+(b) You must cause any modified files to carry prominent notices stating that
+You changed the files; and
+
+(c) You must retain, in the Source form of any Derivative Works that You
+distribute, all copyright, patent, trademark, and attribution notices from the
+Source form of the Work, excluding those notices that do not pertain to any
+part of the Derivative Works; and
+
+(d) If the Work includes a "NOTICE" text file as part of its distribution, then
+any Derivative Works that You distribute must include a readable copy of the
+attribution notices contained within such NOTICE file, excluding those notices
+that do not pertain to any part of the Derivative Works, in at least one of
+the following places: within a NOTICE text file distributed as part of the
+Derivative Works; within the Source form or documentation, if provided along
+with the Derivative Works; or within a display generated by the Derivative
+Works, if and wherever such third-party notices normally appear. The contents
+of the NOTICE file are for informational purposes only and do not modify the
+License. You may add Your own attribution notices within Derivative Works that
+You distribute, alongside or as an addendum to the NOTICE text from the Work,
+provided that such additional attribution notices cannot be construed as
+modifying the License.
+
+You may add Your own copyright statement to Your modifications and may provide
+additional or different license terms and conditions for use, reproduction, or
+distribution of Your modifications, or for any such Derivative Works as a
+whole, provided Your use, reproduction, and distribution of the Work otherwise
+complies with the conditions stated in this License.
+
+5. Submission of Contributions. Unless You explicitly state otherwise, any
+Contribution intentionally submitted for inclusion in the Work by You to the
+Licensor shall be under the terms and conditions of this License, without any
+additional terms or conditions. Notwithstanding the above, nothing herein shall
+supersede or modify the terms of any separate license agreement you may have
+executed with Licensor regarding such Contributions.
+
+6. Trademarks. This License does not grant permission to use the trade names,
+trademarks, service marks, or product names of the Licensor, except as
+required for reasonable and customary use in describing the origin of the Work
+and reproducing the content of the NOTICE file.
+
+7. Disclaimer of Warranty. Unless required by applicable law or agreed to in
+writing, Licensor provides the Work on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+CONDITIONS OF ANY KIND, either express or implied, including, without
+limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT,
+MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely
+responsible for determining the appropriateness of using or redistributing the
+Work and assume any risks associated with Your exercise of permissions under
+this License.
+
+8. Limitation of Liability. In no event and under no legal theory, whether in
+tort, contract, or otherwise, unless required by applicable law or agreed to in
+writing, shall any Contributor be liable to You for damages, including any
+direct, indirect, special, incidental, or consequential damages of any
+character arising as a result of this License or out of the use or inability
+to use the Work, including but not limited to damages for loss of goodwill,
+work stoppage, computer failure or malfunction, or any and all other
+commercial damages or losses, even if such Contributor has been advised of the
+possibility of such damages.
+
+9. Accepting Warranty or Additional Liability. While redistributing the Work or
+Derivative Works thereof, You may choose to offer, and charge a fee for,
+acceptance of support, warranty, indemnity, or other liability obligations
+and/or rights consistent with this License. However, in accepting such
+obligations, You may act only on Your own behalf and on Your sole
+responsibility, not on behalf of any other Contributor, and only if You agree
+to indemnify, defend, and hold each Contributor harmless for any liability
+incurred by, or claims asserted against, such Contributor by reason of your
+accepting any such warranty or additional liability.
+
+END OF TERMS AND CONDITIONS

package/README.md

@@ -0,0 +1,36 @@
+# @jami-studio/harness-store-hosted
+
+Hosted **Postgres + pgvector** durable memory store for Jami Harness.
+
+It provides org-scoped, ranked vector retrieval over `node-postgres`, using the deterministic local
+embedding contract from `@jami-studio/harness-memory` so local and hosted similarity are comparable.
+The Drizzle ORM schema (`memoryRecords`) is the source of truth for columns and migrations.
+
+## No-fallback / fail-closed posture
+
+There is **no in-memory or noop fallback**. The store is real hosted code:
+
+- Without an injected driver and without a `DATABASE_URL`, every operation throws
+  `HostedStoreError("hosted_store_unavailable")` — it never serves an in-memory substitute behind a
+  hosted claim.
+- If `DATABASE_URL` is set but the optional `pg` driver is not installed, operations throw
+  `HostedStoreError("hosted_driver_missing")`.
+- Every operation is org-scoped. A missing `orgId` throws
+  `HostedStoreError("org_isolation_required")`, so records can never leak across organizations.
+
+## Capabilities
+
+- `init()` — creates the `vector` extension, `memory_records` table, the org index, and an HNSW
+  cosine index.
+- `write(input)` — upserts a normalized memory record with its embedding.
+- `search(query)` — org-scoped ranked retrieval (`embedding <=> $vector` cosine distance) with
+  project / user / freshness / recency filters, permission filtering, and `minScore` / `limit`.
+- `delete(memoryId, { orgId })`, `purgeExpired({ orgId })` — retention/deletion at the query
+  boundary.
+
+## Verification status
+
+The SQL generation, org isolation, ranking, and fail-closed behavior are covered by a deterministic
+driver-boundary contract test (the driver is injected at the boundary). A live Postgres + pgvector
+integration is **operator-deferred**: provision a database, set `DATABASE_URL`, install `pg`, and run
+`init()` to exercise the real engine. No database is provisioned in CI by default.

package/package.json

@@ -0,0 +1,41 @@
+{
+  "name": "@jami-studio/harness-store-hosted",
+  "version": "0.1.0",
+  "description": "Hosted Postgres + pgvector durable memory store for Jami Harness: org-scoped, ranked vector retrieval with explicit fail-closed behavior when no database is provisioned.",
+  "license": "Apache-2.0",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/studio-jami/jami-harness.git",
+    "directory": "packages/store-hosted"
+  },
+  "type": "module",
+  "exports": {
+    ".": "./src/index.mjs"
+  },
+  "publishConfig": {
+    "access": "public"
+  },
+  "files": [
+    "src/",
+    "README.md"
+  ],
+  "jamiRelease": {
+    "publishable": true
+  },
+  "dependencies": {
+    "@jami-studio/harness-context": "0.1.0",
+    "@jami-studio/harness-memory": "0.1.0",
+    "drizzle-orm": "0.45.2"
+  },
+  "optionalDependencies": {
+    "pg": "^8.13.1"
+  },
+  "peerDependenciesMeta": {
+    "pg": {
+      "optional": true
+    }
+  },
+  "scripts": {
+    "test": "node --test test/*.test.mjs"
+  }
+}

package/src/index.mjs

@@ -0,0 +1,278 @@
+import { pgTable, text, timestamp, jsonb, vector, index } from "drizzle-orm/pg-core";
+import { embedText, cosineSimilarity, normalizeMemoryRecord, memoryEmbeddingDimension } from "@jami-studio/harness-memory";
+
+/**
+ * Drizzle ORM schema for the hosted Postgres + pgvector memory store. This is the source of truth
+ * for columns and migrations; the adapter below runs parameterized queries against the same shape.
+ */
+export const memoryRecords = pgTable(
+  "memory_records",
+  {
+    memoryId: text("memory_id").primaryKey(),
+    orgId: text("org_id").notNull(),
+    projectId: text("project_id").notNull(),
+    userId: text("user_id"),
+    kind: text("kind").notNull(),
+    summary: text("summary"),
+    content: text("content"),
+    record: jsonb("record").notNull(),
+    embedding: vector("embedding", { dimensions: memoryEmbeddingDimension }).notNull(),
+    freshnessClass: text("freshness_class").notNull(),
+    forgetAfter: timestamp("forget_after", { withTimezone: true }).notNull(),
+    recordedAt: timestamp("recorded_at", { withTimezone: true }).notNull(),
+  },
+  (table) => ({
+    orgIdx: index("memory_records_org_idx").on(table.orgId),
+    embeddingIdx: index("memory_records_embedding_idx").using("hnsw", table.embedding.op("vector_cosine_ops")),
+  }),
+);
+
+export class HostedStoreError extends Error {
+  constructor(code, message) {
+    super(message);
+    this.name = "HostedStoreError";
+    this.code = code;
+  }
+}
+
+const CREATE_STATEMENTS = [
+  "CREATE EXTENSION IF NOT EXISTS vector",
+  `CREATE TABLE IF NOT EXISTS memory_records (
+    memory_id text PRIMARY KEY,
+    org_id text NOT NULL,
+    project_id text NOT NULL,
+    user_id text,
+    kind text NOT NULL,
+    summary text,
+    content text,
+    record jsonb NOT NULL,
+    embedding vector(${memoryEmbeddingDimension}) NOT NULL,
+    freshness_class text NOT NULL,
+    forget_after timestamptz NOT NULL,
+    recorded_at timestamptz NOT NULL
+  )`,
+  "CREATE INDEX IF NOT EXISTS memory_records_org_idx ON memory_records (org_id)",
+  "CREATE INDEX IF NOT EXISTS memory_records_embedding_idx ON memory_records USING hnsw (embedding vector_cosine_ops)",
+];
+
+/**
+ * Hosted Postgres + pgvector memory store.
+ *
+ * Real org-scoped vector retrieval over node-postgres. There is NO in-memory or noop fallback: if no
+ * driver and no connection string are available the store is constructed but every operation fails
+ * closed with HostedStoreError("hosted_store_unavailable"). Every query is org-scoped; a missing
+ * orgId fails closed with HostedStoreError("org_isolation_required") so records can never leak across
+ * organizations.
+ *
+ * options:
+ *   - driver:           injected driver `{ query(text, params) => Promise<{ rows }>, end?() }`
+ *                       (used for the deterministic driver-boundary contract test).
+ *   - connectionString: Postgres URL; defaults to process.env.DATABASE_URL.
+ *   - now:              clock function for retention.
+ */
+export function createHostedMemoryStore(options = {}) {
+  const now = options.now ?? (() => new Date());
+  const connectionString = options.connectionString ?? process.env.DATABASE_URL ?? null;
+  let driver = options.driver ?? null;
+  let ownsDriver = false;
+  let driverInit = null;
+
+  async function resolveDriver() {
+    if (driver) return driver;
+    if (!connectionString) {
+      throw new HostedStoreError(
+        "hosted_store_unavailable",
+        "hosted memory store requires an injected driver or DATABASE_URL connection string; refusing to serve an in-memory substitute for a hosted claim",
+      );
+    }
+    if (!driverInit) {
+      driverInit = (async () => {
+        let pg;
+        try {
+          pg = await import("pg");
+        } catch {
+          throw new HostedStoreError(
+            "hosted_driver_missing",
+            "the optional 'pg' driver is not installed; install pg + a reachable Postgres with the pgvector extension to use the hosted memory store",
+          );
+        }
+        const Pool = pg.default?.Pool ?? pg.Pool;
+        const pool = new Pool({ connectionString });
+        ownsDriver = true;
+        driver = {
+          query: (sql, params) => pool.query(sql, params),
+          end: () => pool.end(),
+        };
+        return driver;
+      })();
+    }
+    return driverInit;
+  }
+
+  return {
+    capabilities: { mode: "hosted_pgvector", readable: true, writable: true, searchable: true, ranked: true, hosted: true, durable: true },
+
+    async init() {
+      const db = await resolveDriver();
+      for (const statement of CREATE_STATEMENTS) {
+        await db.query(statement);
+      }
+      return { initialized: true };
+    },
+
+    async write(input) {
+      const orgId = requireOrgId(input.orgId);
+      const record = normalizeMemoryRecord(input, { now });
+      const embedding = formatVector(embedText(`${record.summary ?? ""} ${record.content ?? ""}`));
+      const db = await resolveDriver();
+      await db.query(
+        `INSERT INTO memory_records
+          (memory_id, org_id, project_id, user_id, kind, summary, content, record, embedding, freshness_class, forget_after, recorded_at)
+         VALUES ($1,$2,$3,$4,$5,$6,$7,$8,$9,$10,$11,$12)
+         ON CONFLICT (memory_id) DO UPDATE SET
+           org_id = EXCLUDED.org_id,
+           project_id = EXCLUDED.project_id,
+           user_id = EXCLUDED.user_id,
+           kind = EXCLUDED.kind,
+           summary = EXCLUDED.summary,
+           content = EXCLUDED.content,
+           record = EXCLUDED.record,
+           embedding = EXCLUDED.embedding,
+           freshness_class = EXCLUDED.freshness_class,
+           forget_after = EXCLUDED.forget_after,
+           recorded_at = EXCLUDED.recorded_at`,
+        [
+          record.memoryId,
+          orgId,
+          record.scope.projectId,
+          input.userId ?? null,
+          record.kind,
+          record.summary ?? null,
+          record.content ?? null,
+          JSON.stringify(record),
+          embedding,
+          record.freshness.class,
+          record.retention.forgetAfter,
+          record.source.recordedAt,
+        ],
+      );
+      return { written: true, record };
+    },
+
+    async search(query = {}) {
+      const orgId = requireOrgId(query.orgId);
+      const db = await resolveDriver();
+      const params = [orgId, isoNow(now)];
+      const conditions = ["org_id = $1", "forget_after > $2"];
+
+      if (query.projectId) {
+        params.push(query.projectId);
+        conditions.push(`project_id = $${params.length}`);
+      }
+      if (query.userId) {
+        params.push(query.userId);
+        conditions.push(`user_id = $${params.length}`);
+      }
+      if (query.freshness) {
+        const allowed = Array.isArray(query.freshness) ? query.freshness : [query.freshness];
+        params.push(allowed);
+        conditions.push(`freshness_class = ANY($${params.length})`);
+      }
+
+      let order = "recorded_at DESC, memory_id ASC";
+      let scoreSelect = "NULL::float8 AS score";
+      if (query.text) {
+        params.push(formatVector(embedText(query.text)));
+        const vectorParam = `$${params.length}`;
+        scoreSelect = `1 - (embedding <=> ${vectorParam}) AS score`;
+        order = `embedding <=> ${vectorParam} ASC`;
+      }
+
+      const sql = `SELECT record, ${scoreSelect} FROM memory_records WHERE ${conditions.join(" AND ")} ORDER BY ${order}`;
+      const { rows } = await db.query(sql, params);
+
+      const minScore = Number.isFinite(query.minScore) ? query.minScore : null;
+      const droppedItems = [];
+      const items = [];
+      const limit = Number.isInteger(query.limit) && query.limit >= 0 ? query.limit : null;
+      for (const row of rows) {
+        const record = typeof row.record === "string" ? JSON.parse(row.record) : row.record;
+        if (!canReadMemory(record, query.actor ?? {})) {
+          droppedItems.push({ sourceRef: record.memoryId, reason: "permission_denied" });
+          continue;
+        }
+        const score = row.score === null || row.score === undefined ? null : Number(row.score);
+        if (minScore !== null && score !== null && score < minScore) continue;
+        items.push({
+          record: redactForRecall(record),
+          citation: record.citation,
+          score,
+          inclusionReason: score === null ? "org-scoped match" : "org-scoped vector relevance match",
+        });
+        if (limit !== null && items.length >= limit) break;
+      }
+      return { items, droppedItems };
+    },
+
+    async delete(memoryId, opts = {}) {
+      const orgId = requireOrgId(opts.orgId);
+      const db = await resolveDriver();
+      const { rowCount } = await db.query("DELETE FROM memory_records WHERE memory_id = $1 AND org_id = $2", [memoryId, orgId]);
+      return { deleted: (rowCount ?? 0) > 0, memoryId };
+    },
+
+    async purgeExpired(opts = {}) {
+      const orgId = requireOrgId(opts.orgId);
+      const db = await resolveDriver();
+      const { rowCount } = await db.query("DELETE FROM memory_records WHERE org_id = $1 AND forget_after <= $2", [orgId, isoNow(now)]);
+      return { purged: rowCount ?? 0 };
+    },
+
+    async close() {
+      if (ownsDriver && driver?.end) await driver.end();
+    },
+  };
+}
+
+// --- internals -------------------------------------------------------------
+
+function requireOrgId(orgId) {
+  if (typeof orgId !== "string" || orgId.length === 0) {
+    throw new HostedStoreError("org_isolation_required", "hosted memory operations require an orgId; org-scoped isolation cannot be bypassed");
+  }
+  return orgId;
+}
+
+function canReadMemory(record, actor) {
+  const allowedActorIds = record.scope?.allowedActorIds ?? [];
+  if (allowedActorIds.length > 0 && !allowedActorIds.includes(actor.actorId)) return false;
+  const actorScopes = new Set(actor.scopes ?? []);
+  return (record.scope?.allowedScopes ?? []).every((scope) => actorScopes.has(scope));
+}
+
+function redactForRecall(record) {
+  if (record.redaction?.mode === "omitted") {
+    return { ...record, content: undefined, summary: "[omitted]" };
+  }
+  if (record.redaction?.mode !== "redacted") return record;
+  return {
+    ...record,
+    content: redactString(record.content),
+    summary: redactString(record.summary),
+  };
+}
+
+function redactString(value) {
+  if (typeof value !== "string") return value;
+  return value.replace(/(secret|token|password|credential)[^\s]*/gi, "[redacted]");
+}
+
+function formatVector(vectorArray) {
+  return `[${vectorArray.join(",")}]`;
+}
+
+function isoNow(now) {
+  return now().toISOString();
+}
+
+export { cosineSimilarity };