feat: define internal semantic workspace schema

2026-08-08 16:43:54 +02:00
parent 4fe4049a24
commit 2f7f923c4d
9 changed files with 463 additions and 154 deletions
@@ -0,0 +1,101 @@
+import { expect, test } from "vitest";
+import { migrateWorkspaceV2ToV3 } from "../src/workspaces/migrate-v2-qdrant.js";
+import { parseWorkspaceYaml } from "../src/workspaces/schema.js";
+
+const workspaceV2Yaml = `workspace:
+  schema_version: 2
+  id: psd-clinical
+  name: Policlinico San Donato
+  description: Clinical data warehouse workspace
+  language: it
+dwh:
+  engine: postgres
+  database: postgres
+  schema: datawarehouse
+  supported_transports:
+    - postgres_direct
+    - rest_api
+semantic_index:
+  vector_store:
+    engine: pgvector
+    database: postgres
+    schema: vectors
+    collection: clinical_documents
+    dimensions: 768
+    distance: inner_product
+    supported_transports:
+      - pgvector_direct
+      - rest_api
+  embedding:
+    provider: openai_compatible
+    model: text-embedding-3-large
+    dimensions: 768
+llm_policy:
+  default: zai/glm-5.2
+  allowed:
+    - zai/glm-5.2
+diagnostics:
+  dwh_rest:
+    method: POST
+    path: /rpc/dwh
+    auth: bearer
+    response:
+      database: database
+      schema: schema
+  vector_rest:
+    metadata:
+      method: GET
+      path: /vector
+      auth: bearer
+      response:
+        collection: collection
+        dimensions: dimensions
+        distance: distance
+  embedding:
+    method: GET
+    path: /models
+    auth: none
+    response:
+      model: model
+      dimensions: dimensions
+`;
+
+test("migrates a schema v2 workspace to the internal qdrant schema v3 shape", () => {
+  const legacy = parseWorkspaceYaml(workspaceV2Yaml);
+
+  const migrated = migrateWorkspaceV2ToV3(legacy, "psd-clinical");
+
+  expect(migrated).toMatchObject({
+    workspace: { schema_version: 3, id: "psd-clinical", name: "Policlinico San Donato" },
+    dwh: legacy.dwh,
+    semantic_index: {
+      vector_store: {
+        engine: "qdrant",
+        collection: "psd-clinical",
+        dimensions: 1024,
+        distance: "cosine",
+      },
+      embedding: {
+        provider: "ollama_internal",
+        model: "qwen3-embedding:0.6b",
+        dimensions: 1024,
+      },
+    },
+    llm_policy: legacy.llm_policy,
+    diagnostics: {
+      dwh_rest: legacy.diagnostics?.dwh_rest,
+    },
+  });
+});
+
+test("drops vector and embedding diagnostics and transports during v2 to v3 migration", () => {
+  const legacy = parseWorkspaceYaml(workspaceV2Yaml);
+
+  const migrated = migrateWorkspaceV2ToV3(legacy, "psd-clinical");
+
+  expect(migrated.diagnostics).toEqual({
+    dwh_rest: legacy.diagnostics?.dwh_rest,
+  });
+  expect(migrated.semantic_index.vector_store).not.toHaveProperty("supported_transports");
+  expect(migrated.semantic_index.embedding).not.toHaveProperty("timeout_ms");
+});