feat: unify installation model catalog

backend/test/workspaces-schema.test.ts

@@ -10,7 +10,7 @@ import {
 } from "../src/workspaces/schema.js";
 
 export const validYaml = `workspace:
-  schema_version: 3
+  schema_version: 4
   id: psd-clinical
   name: Policlinico San Donato
   description: Clinical data warehouse workspace
@@ -25,33 +25,8 @@ dwh:
     - postgres_direct
     - rest_api
     - ssh_tunnel
-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:
-  default: zai/glm-5.2
-  allowed:
-    - zai/glm-5.2
-    - openai/gpt-5
 `;
 
-test("rejects a workspace whose embedding dimensions differ from its collection", () => {
-  expect(() => parseWorkspaceYaml(validYaml.replace("dimensions: 1024", "dimensions: 1536")))
-    .toThrow(/dimensions/i);
-});
-
-test("rejects an LLM default outside its allowlist", () => {
-  expect(() => parseWorkspaceYaml(validYaml.replace("- zai/glm-5.2", "- openai/gpt-5")))
-    .toThrow(/allowlist/i);
-});
-
 test("rejects unknown keys and invalid immutable IDs", () => {
   expect(() => parseWorkspaceYaml(validYaml.replace("  language: it", "  language: it\n  label: PSD")))
     .toThrow(/unrecognized key/i);
@@ -74,94 +49,34 @@ test("accepts optional connection ports and timeouts but rejects unsafe values",
     .toThrow(/port/i);
   expect(() => parseWorkspaceYaml(validYaml.replace("timeout_ms: 5000", "timeout_ms: 0")))
     .toThrow(/timeout/i);
-  expect(() => parseWorkspaceYaml(validYaml.replace("dimensions: 1024", "dimensions: 2048")))
-    .toThrow(/1024|dimensions/i);
 });
 
-test("accepts only the schema v3 internal qdrant semantic shape", () => {
+test("accepts a model-free schema v4 workspace", () => {
   expect(parseWorkspaceYaml(validYaml)).toMatchObject({
-    workspace: { schema_version: 3, id: "psd-clinical" },
-    semantic_index: {
-      vector_store: {
-        engine: "qdrant",
-        collection: "psd-clinical",
-        dimensions: 1024,
-        distance: "cosine",
-      },
-      embedding: {
-        provider: "ollama_internal",
-        model: "qwen3-embedding:0.6b",
-        dimensions: 1024,
-      },
-    },
+    workspace: { schema_version: 4, id: "psd-clinical" },
+    dwh: { database: "postgres", schema: "datawarehouse" },
   });
 });
 
-test("committed example descriptors parse as exact schema v3 workspaces", () => {
+test("committed example descriptors parse as exact schema v4 workspaces", () => {
   const example = readFileSync(resolve(process.cwd(), "../deploy/workspaces/example.yaml"), "utf8");
   const psdExample = readFileSync(resolve(process.cwd(), "../deploy/workspaces/psd.yaml.example"), "utf8");
 
   expect(() => parseWorkspaceYaml(example)).not.toThrow();
   expect(() => parseWorkspaceYaml(psdExample)).not.toThrow();
   expect(parseWorkspaceYaml(example)).toMatchObject({
-    workspace: { schema_version: 3 },
-    semantic_index: {
-      vector_store: { engine: "qdrant", distance: "cosine", dimensions: 1024 },
-      embedding: { provider: "ollama_internal", model: "qwen3-embedding:0.6b", dimensions: 1024 },
-    },
+    workspace: { schema_version: 4 },
   });
   expect(parseWorkspaceYaml(psdExample)).toMatchObject({
-    workspace: { schema_version: 3 },
-    semantic_index: {
-      vector_store: { engine: "qdrant", distance: "cosine", dimensions: 1024 },
-      embedding: { provider: "ollama_internal", model: "qwen3-embedding:0.6b", dimensions: 1024 },
-    },
+    workspace: { schema_version: 4 },
   });
 });
 
-test("rejects pgvector semantic stores in schema v3", () => {
-  expect(() => parseWorkspaceYaml(validYaml.replace("engine: qdrant", "engine: pgvector")))
-    .toThrow(/qdrant|pgvector/i);
-});
-
-test("rejects supported_transports inside schema v3 semantic identity", () => {
-  const withTransport = validYaml.replace(
-    "    distance: cosine\n",
-    "    distance: cosine\n    supported_transports:\n      - rest_api\n",
-  );
-
-  expect(() => parseWorkspaceYaml(withTransport)).toThrow(/unrecognized key|supported_transports/i);
-});
-
-test("rejects external embedding providers in schema v3", () => {
-  expect(() => parseWorkspaceYaml(validYaml.replace("provider: ollama_internal", "provider: openai_compatible")))
-    .toThrow(/ollama_internal|provider/i);
-});
-
-test("rejects non-cosine distance in schema v3", () => {
-  expect(() => parseWorkspaceYaml(validYaml.replace("distance: cosine", "distance: l2")))
-    .toThrow(/cosine|distance/i);
-});
-
-test("rejects unknown fields in schema v3 semantic identity", () => {
-  const withUnknownField = validYaml.replace(
-    "    collection: psd-clinical\n",
-    "    collection: psd-clinical\n    namespace: psd\n",
-  );
-
-  expect(() => parseWorkspaceYaml(withUnknownField)).toThrow(/unrecognized key/i);
-});
-
-test("rejects legacy semantic connector fields and diagnostics in schema v3", () => {
-  expect(() => parseWorkspaceYaml(validYaml.replace(
-    "    collection: psd-clinical\n",
-    "    collection: psd-clinical\n    database: postgres\n",
-  ))).toThrow(/unrecognized key|database/i);
-
-  expect(() => parseWorkspaceYaml(validYaml.replace(
-    "llm_policy:\n",
-    "diagnostics:\n  vector_rest:\n    metadata:\n      method: GET\n      path: /metadata\n      auth: bearer\n      response:\n        collection: collection\n        dimensions: dimensions\n        distance: distance\nllm_policy:\n",
-  ))).toThrow(/unrecognized key|vector_rest/i);
+test("rejects installation-owned model and vector fields", () => {
+  expect(() => parseWorkspaceYaml(`${validYaml}llm_policy:\n  allowed: [zai/glm-5.3]\n`))
+    .toThrow(/unrecognized key|llm_policy/i);
+  expect(() => parseWorkspaceYaml(`${validYaml}semantic_index: {}\n`))
+    .toThrow(/unrecognized key|semantic_index/i);
 });
 
 test.each([
@@ -222,8 +137,8 @@ llm_policy:
     - zai/glm-5.2
 `],
 ])("rejects schema %s descriptors at parser and object-validator boundaries", (_version, yaml) => {
-  expect(() => parseWorkspaceYaml(yaml)).toThrow(/schema_version|invalid literal|3/i);
-  expect(() => validateWorkspaceDescriptor(parse(yaml))).toThrow(/schema_version|invalid literal|3/i);
+  expect(() => parseWorkspaceYaml(yaml)).toThrow(/schema_version|invalid literal|4/i);
+  expect(() => validateWorkspaceDescriptor(parse(yaml))).toThrow(/schema_version|invalid literal|4/i);
 });
 
 test("does not expose the redundant canonical validator or v1 migration", () => {
@@ -253,9 +168,8 @@ test("rejects REST diagnostic declarations without their matching connector tran
     response:
       database: database
       schema: schema
-llm_policy:
 `;
-  const declared = validYaml.replace("llm_policy:\n", diagnostics);
+  const declared = `${validYaml}${diagnostics}`;
 
   expect(() => parseWorkspaceYaml(declared.replace("    - rest_api\n", ""))).toThrow(/dwh_rest/i);
 });
@@ -462,7 +376,7 @@ test.each(["curated/**/*.yaml", "curated/**"])(
   },
 );
 
-test("keeps evidence optional on schema v3", () => {
+test("keeps evidence optional on schema v4", () => {
   expect(validateWorkspaceDescriptor(validWorkspaceObject())).not.toHaveProperty("evidence");
 });
 
@@ -471,7 +385,7 @@ test("serializes defaulted evidence canonically and parses it without loss", ()
     type: "filesystem",
     uri: "psd-clinical/evidence",
   }));
-  if (canonical.workspace.schema_version !== 3) throw new Error("expected schema v3");
+  if (canonical.workspace.schema_version !== 4) throw new Error("expected schema v4");
 
   expect(parseWorkspaceYaml(serializeWorkspaceYaml(canonical))).toEqual(canonical);
 });