feat: unify installation model catalog

This commit is contained in:
Codex
2026-09-02 18:45:33 +02:00
parent ae053961a3
commit 7b7927bfe5
169 changed files with 3696 additions and 4572 deletions
+3 -16
View File
@@ -5,14 +5,12 @@ import { createLocalAuthFixture } from "./auth-test-fixtures.js";
function fakeService(): PiManagementService {
return {
status: vi.fn(async () => ({ ready: true })),
options: vi.fn(async () => ({ providers: [], models: [], reasoning: [], checkedAt: "2026-08-17T00:00:00.000Z" })),
configure: vi.fn(async (value) => ({ ...value, updatedAt: "2026-08-17T00:00:00.000Z" })),
test: vi.fn(async () => ({ ready: true, checkedAt: "2026-08-17T00:00:00.000Z" })),
logs: vi.fn(async () => ({ lines: [] })),
};
}
test("a local HTTPS cookie session authorizes Pi writes through an untrusted internal HTTP hop", async () => {
test("a local HTTPS cookie session authorizes the Pi smoke check through an untrusted internal HTTP hop", async () => {
const service = fakeService();
const fixture = await createLocalAuthFixture(
{ piManagement: service },
@@ -25,31 +23,21 @@ test("a local HTTPS cookie session authorizes Pi writes through an untrusted int
expect(fixture.publicUrl).toBe("HTTPS://thothii.example.test");
const proxyHeaders = fixture.sessionHeaders({ host: "127.0.0.1:8080" });
const configured = await fixture.app.inject({
method: "PUT",
url: "/pi-management/config",
headers: proxyHeaders,
payload: { provider: "zai", model: "glm-5.2", reasoning: "high" },
});
const smoke = await fixture.app.inject({
method: "POST",
url: "/pi-management/test",
headers: proxyHeaders,
});
expect(configured.statusCode).toBe(200);
expect(smoke.statusCode).toBe(200);
expect(service.configure).toHaveBeenCalledTimes(1);
expect(service.test).toHaveBeenCalledTimes(1);
fixture.resetDownstreamHits();
vi.mocked(service.configure).mockClear();
vi.mocked(service.test).mockClear();
const wrongOrigin = await fixture.app.inject({
method: "PUT",
url: "/pi-management/config",
method: "POST",
url: "/pi-management/test",
headers: fixture.sessionHeaders({ host: "127.0.0.1:8080", origin: "https://evil.example" }),
payload: { provider: "zai", model: "glm-5.2", reasoning: "high" },
});
const wrongCsrf = await fixture.app.inject({
method: "POST",
@@ -62,7 +50,6 @@ test("a local HTTPS cookie session authorizes Pi writes through an untrusted int
expect(response.json()).toEqual({ code: "csrf_failed", error: "Request origin validation failed" });
}
expect(fixture.downstreamHits()).toBe(0);
expect(service.configure).not.toHaveBeenCalled();
expect(service.test).not.toHaveBeenCalled();
} finally {
await fixture.close();
@@ -19,16 +19,11 @@ afterEach(() => {
});
const workspace: WorkspaceDescriptor = {
workspace: { schema_version: 3, id: "psd-clinical", name: "Policlinico San Donato", language: "it" },
workspace: { schema_version: 4, id: "psd-clinical", name: "Policlinico San Donato", language: "it" },
dwh: {
engine: "postgres", database: "warehouse", schema: "datawarehouse", port: 5432,
supported_transports: ["postgres_direct", "rest_api"],
},
semantic_index: {
vector_store: { engine: "qdrant", collection: "psd", dimensions: 1024, distance: "cosine" },
embedding: { provider: "ollama_internal", model: "qwen3-embedding:0.6b", dimensions: 1024 },
},
llm_policy: { allowed: ["zai/glm-5.2"] },
diagnostics: { dwh_rest: { method: "GET", path: "/health", auth: "bearer", response: { database: "database", schema: "schema" } } },
};
const revision: WorkspaceRevision = { id: "psd-clinical", commit: "a".repeat(40), blob: "b".repeat(40), snapshotPath: "/tmp/psd.yaml" };
@@ -24,7 +24,7 @@ import type { WorkspaceDescriptor } from "../src/workspaces/schema.js";
const workspace: WorkspaceDescriptor = {
workspace: {
schema_version: 3,
schema_version: 4,
id: "psd-clinical",
name: "Policlinico San Donato",
language: "it",
@@ -36,11 +36,6 @@ const workspace: WorkspaceDescriptor = {
port: 5432,
supported_transports: ["postgres_direct"],
},
semantic_index: {
vector_store: { engine: "qdrant", collection: "psd", dimensions: 1024, distance: "cosine" },
embedding: { provider: "ollama_internal", model: "qwen3-embedding:0.6b", dimensions: 1024 },
},
llm_policy: { allowed: ["zai/glm-5.2"] },
};
const revision: WorkspaceRevision = {
id: "psd-clinical",
@@ -49,7 +44,7 @@ const revision: WorkspaceRevision = {
snapshotPath: "/tmp/psd.yaml",
};
const configuredModel: ResolvedMetadataGenerationModel = {
id: "openai-mini",
id: "openai/gpt-4.1-mini",
provider: "openai",
model: "gpt-4.1-mini",
apiKeyEnv: "OPENAI_API_KEY",
@@ -705,7 +700,7 @@ test("generates one selected Catalog Column from a single JSON code fence", asyn
expect(completionRequest.messages[0]?.content).toContain('{"results":[');
expect(completionRequest.messages[1]?.content).toContain(`"targetId":"${column.id}"`);
expect(completionRequest.messages[1]?.content).not.toMatch(/source rows|samples|example values/i);
expect(start.body).not.toMatch(/test-provider-secret|gpt-4\.1|openai\/gpt|Catalog metadata/);
expect(start.body).not.toMatch(/test-provider-secret|Catalog metadata/);
resolveCompletion(`\`\`\`json\n${JSON.stringify({
results: [{
@@ -2909,7 +2904,7 @@ test("validates selected targets and resolves every requested target before laun
const unknownModel = await app.inject({
method: "POST",
url: `/catalog/databases/${database.id}/description-generation-runs`,
payload: { modelId: "unknown-model", scope: "selected_columns", targetIds: [column.id] },
payload: { modelId: "openai/unknown-model", scope: "selected_columns", targetIds: [column.id] },
});
expect(unknownModel.statusCode).toBe(409);
expect(unknownModel.json().code).toBe("metadata_generation_model_unavailable");
@@ -14,6 +14,7 @@ import { up as upDescriptionGeneration } from "../src/catalog/migrations/005_des
import { up as upSensitiveDataFlag } from "../src/catalog/migrations/006_sensitive_data_flag.js";
import { up as upSensitiveSuggestionRuns } from "../src/catalog/migrations/007_sensitive_data_suggestion_runs.js";
import { up as upAiTokenUsage } from "../src/catalog/migrations/009_ai_token_usage.js";
import { up as upCanonicalModelIds } from "../src/catalog/migrations/010_canonical_model_ids.js";
import { KyselyCatalogRepository, type CatalogDatabase } from "../src/catalog/repository.js";
import { loadConfig } from "../src/config.js";
import type { WorkspaceRegistry } from "../src/workspaces/registry.js";
@@ -50,6 +51,7 @@ test.skipIf(!dockerAvailable)("Fastify persists Description Generation success a
await upDescriptionGeneration(db);
await upSensitiveSuggestionRuns(db);
await upAiTokenUsage(db);
await upCanonicalModelIds(db);
const repository = new KyselyCatalogRepository(db);
const database = await repository.create({
workspaceId: "psd-clinical",
@@ -158,9 +160,9 @@ test.skipIf(!dockerAvailable)("Fastify persists Description Generation success a
}),
};
const models: MetadataGenerationModels = {
catalog: () => ({ models: [{ id: "openai-mini", label: "OpenAI Mini" }], default: "openai-mini" }),
catalog: () => ({ models: [{ id: "openai/gpt-4.1-mini", label: "OpenAI Mini" }], default: "openai/gpt-4.1-mini" }),
resolve: () => ({
id: "openai-mini",
id: "openai/gpt-4.1-mini",
provider: "openai",
model: "gpt-4.1-mini",
apiKeyEnv: "OPENAI_API_KEY",
@@ -205,12 +207,12 @@ test.skipIf(!dockerAvailable)("Fastify persists Description Generation success a
method: "POST",
url: `/catalog/databases/${database.id}/description-generation-runs`,
payload: {
modelId: "openai-mini",
modelId: "openai/gpt-4.1-mini",
scope: "selected_columns",
targetIds: [status.id, birthDate.id],
},
});
expect(successfulStart.statusCode).toBe(202);
expect(successfulStart.statusCode, successfulStart.body).toBe(202);
expect(await terminalRun(app, successfulStart.json().id)).toMatchObject({
status: "completed",
total: 2,
@@ -233,7 +235,7 @@ test.skipIf(!dockerAvailable)("Fastify persists Description Generation success a
const tableStart = await app.inject({
method: "POST",
url: `/catalog/databases/${database.id}/description-generation-runs`,
payload: { modelId: "openai-mini", scope: "selected_tables", targetIds: [table.id] },
payload: { modelId: "openai/gpt-4.1-mini", scope: "selected_tables", targetIds: [table.id] },
});
expect(tableStart.statusCode).toBe(202);
expect(await terminalRun(app, tableStart.json().id)).toMatchObject({
@@ -253,7 +255,7 @@ test.skipIf(!dockerAvailable)("Fastify persists Description Generation success a
const failedStart = await app.inject({
method: "POST",
url: `/catalog/databases/${database.id}/description-generation-runs`,
payload: { modelId: "openai-mini", scope: "selected_columns", targetIds: [status.id] },
payload: { modelId: "openai/gpt-4.1-mini", scope: "selected_columns", targetIds: [status.id] },
});
expect(failedStart.statusCode).toBe(202);
const failedRun = await terminalRun(app, failedStart.json().id);
@@ -283,7 +285,7 @@ test.skipIf(!dockerAvailable)("Fastify persists Description Generation success a
const allStart = await app.inject({
method: "POST",
url: `/catalog/databases/${database.id}/description-generation-runs`,
payload: { modelId: "openai-mini", scope: "all" },
payload: { modelId: "openai/gpt-4.1-mini", scope: "all" },
});
expect(allStart.statusCode).toBe(202);
const allRun = await terminalRun(app, allStart.json().id);
@@ -327,7 +329,7 @@ test.skipIf(!dockerAvailable)("Fastify persists Description Generation success a
const missingStart = await app.inject({
method: "POST",
url: `/catalog/databases/${database.id}/description-generation-runs`,
payload: { modelId: "openai-mini", scope: "missing" },
payload: { modelId: "openai/gpt-4.1-mini", scope: "missing" },
});
expect(missingStart.statusCode).toBe(202);
expect(await terminalRun(app, missingStart.json().id)).toMatchObject({
@@ -14,6 +14,7 @@ import { up as upSensitiveDataFlag } from "../src/catalog/migrations/006_sensiti
import { up as upSensitiveSuggestionRuns } from "../src/catalog/migrations/007_sensitive_data_suggestion_runs.js";
import { up as upLogicalRelationships } from "../src/catalog/migrations/008_catalog_logical_relationships.js";
import { up as upAiTokenUsage } from "../src/catalog/migrations/009_ai_token_usage.js";
import { up as upCanonicalModelIds } from "../src/catalog/migrations/010_canonical_model_ids.js";
const dockerAvailable = spawnSync("docker", ["info"], { stdio: "ignore" }).status === 0;
@@ -32,6 +33,7 @@ test.skipIf(!dockerAvailable)("PostgreSQL migration enforces one database per wo
await upDescriptionGeneration(db);
await upSensitiveSuggestionRuns(db);
await upAiTokenUsage(db);
await upCanonicalModelIds(db);
await sql`CREATE ROLE thothii_catalog_runtime`.execute(db);
await upRuntimeSequencePrivileges(db);
const sequencePrivilege = await sql<{ allowed: boolean }>`
@@ -391,6 +393,7 @@ test.skipIf(!dockerAvailable)("PostgreSQL repository persists description and se
await upDescriptionGeneration(db);
await upSensitiveSuggestionRuns(db);
await upAiTokenUsage(db);
await upCanonicalModelIds(db);
const repository = new KyselyCatalogRepository(db);
const firstDatabase = await repository.create({
workspaceId: "generation-one",
@@ -428,14 +431,14 @@ test.skipIf(!dockerAvailable)("PostgreSQL repository persists description and se
const run = await repository.createDescriptionGenerationRun(
firstDatabase.id,
"selected_columns",
"openai-mini",
"openai/gpt-4.1-mini",
"it",
1,
);
expect(run).toMatchObject({
databaseId: firstDatabase.id,
scope: "selected_columns",
modelId: "openai-mini",
modelId: "openai/gpt-4.1-mini",
language: "it",
status: "queued",
total: 1,
@@ -450,7 +453,7 @@ test.skipIf(!dockerAvailable)("PostgreSQL repository persists description and se
await expect(repository.createDescriptionGenerationRun(
secondDatabase.id,
"selected_columns",
"openai-mini",
"openai/gpt-4.1-mini",
"en",
1,
)).rejects.toThrow("A description generation run is already active");
@@ -461,7 +464,7 @@ test.skipIf(!dockerAvailable)("PostgreSQL repository persists description and se
await expect(repository.createDescriptionGenerationRun(
secondDatabase.id,
"selected_columns",
"openai-mini",
"openai/gpt-4.1-mini",
"en",
1,
)).rejects.toThrow("A description generation run is already active");
@@ -505,7 +508,7 @@ test.skipIf(!dockerAvailable)("PostgreSQL repository persists description and se
const next = await repository.createDescriptionGenerationRun(
secondDatabase.id,
"missing",
"openai-mini",
"openai/gpt-4.1-mini",
"en",
1,
);
@@ -533,7 +536,7 @@ test.skipIf(!dockerAvailable)("PostgreSQL repository persists description and se
const allRun = await repository.createDescriptionGenerationRun(
firstDatabase.id,
"all",
"openai-mini",
"openai/gpt-4.1-mini",
"it",
2,
);
@@ -562,7 +565,7 @@ test.skipIf(!dockerAvailable)("PostgreSQL repository persists description and se
const suggestionRun = await repository.createSensitiveDataSuggestionRun(
firstDatabase.id,
"selected_columns",
"openai-mini",
"openai/gpt-4.1-mini",
);
expect(suggestionRun).toMatchObject({
databaseId: firstDatabase.id,
@@ -604,7 +607,7 @@ test.skipIf(!dockerAvailable)("PostgreSQL repository persists description and se
const interruptedSuggestionRun = await repository.createSensitiveDataSuggestionRun(
secondDatabase.id,
"all",
"openai-mini",
"openai/gpt-4.1-mini",
);
expect(await repository.interruptActiveSensitiveDataSuggestionRuns(
"Sensitive-field suggestion generation was interrupted by backend restart.",
+1 -6
View File
@@ -16,13 +16,8 @@ const roots: string[] = [];
afterEach(() => { for (const root of roots.splice(0)) rmSync(root, { recursive: true, force: true }); });
const workspace: WorkspaceDescriptor = {
workspace: { schema_version: 3, id: "psd-clinical", name: "Policlinico San Donato", language: "it" },
workspace: { schema_version: 4, id: "psd-clinical", name: "Policlinico San Donato", language: "it" },
dwh: { engine: "postgres", database: "warehouse", schema: "datawarehouse", port: 5432, supported_transports: ["postgres_direct"] },
semantic_index: {
vector_store: { engine: "qdrant", collection: "psd", dimensions: 1024, distance: "cosine" },
embedding: { provider: "ollama_internal", model: "qwen3-embedding:0.6b", dimensions: 1024 },
},
llm_policy: { allowed: ["zai/glm-5.2"] },
};
const revision: WorkspaceRevision = { id: "psd-clinical", commit: "a".repeat(40), blob: "b".repeat(40), snapshotPath: "/tmp/psd.yaml" };
+1 -6
View File
@@ -13,16 +13,11 @@ const roots: string[] = [];
afterEach(() => { for (const root of roots.splice(0)) rmSync(root, { recursive: true, force: true }); });
const workspace: WorkspaceDescriptor = {
workspace: { schema_version: 3, id: "psd-clinical", name: "Policlinico San Donato", language: "it" },
workspace: { schema_version: 4, id: "psd-clinical", name: "Policlinico San Donato", language: "it" },
dwh: {
engine: "postgres", database: "warehouse", schema: "datawarehouse", port: 5432,
supported_transports: ["postgres_direct", "rest_api"],
},
semantic_index: {
vector_store: { engine: "qdrant", collection: "psd", dimensions: 1024, distance: "cosine" },
embedding: { provider: "ollama_internal", model: "qwen3-embedding:0.6b", dimensions: 1024 },
},
llm_policy: { allowed: ["zai/glm-5.2"] },
diagnostics: { dwh_rest: { method: "GET", path: "/health", auth: "bearer", response: { database: "database", schema: "schema" } } },
};
const revision: WorkspaceRevision = {
+17
View File
@@ -71,6 +71,7 @@ test("loadConfig keeps local development defaults", () => {
workspaceSecretRuntimeRoot: "/tmp/thothii-workspace-secrets",
internalQdrantUrl: "http://qdrant:6333",
internalEmbeddingUrl: "http://embedding:11434",
internalEmbeddingId: "ollama/qwen3-embedding:0.6b",
internalEmbeddingModel: "qwen3-embedding:0.6b",
internalEmbeddingDimensions: 1024,
authMode: "none",
@@ -198,6 +199,22 @@ test("loadConfig accepts only the allowed internal semantic runtime hosts", () =
.toThrow(/internal.*embedding|invalid/i);
});
test("loadConfig derives the embedding runtime model from its canonical catalog identity", () => {
expect(loadConfig({
THT_INTERNAL_EMBEDDING_ID: "ollama/nomic-embed-text",
THT_INTERNAL_EMBEDDING_MODEL: "nomic-embed-text",
})).toMatchObject({
internalEmbeddingId: "ollama/nomic-embed-text",
internalEmbeddingModel: "nomic-embed-text",
});
expect(() => loadConfig({
THT_INTERNAL_EMBEDDING_ID: "ollama/nomic-embed-text",
THT_INTERNAL_EMBEDDING_MODEL: "different-model",
})).toThrow("does not match its canonical identity");
expect(() => loadConfig({ THT_INTERNAL_EMBEDDING_ID: "not-canonical" }))
.toThrow("embedding identity configuration is invalid");
});
test("loadConfig enables the legacy workspace request only through explicit local mode", () => {
expect(loadConfig({ THT_LEGACY_WORKSPACE_MODE: "local" }).legacyWorkspaceMode).toBe(true);
+6 -2
View File
@@ -11,6 +11,7 @@ import {
const semanticRuntime = {
internalQdrantUrl: "http://qdrant:6333",
internalEmbeddingUrl: "http://embedding:11434",
internalEmbeddingId: "ollama/qwen3-embedding:0.6b",
internalEmbeddingModel: "qwen3-embedding:0.6b",
internalEmbeddingDimensions: 1024,
};
@@ -102,11 +103,11 @@ function restRendered(): Record<string, unknown> {
}
const directCanonical =
`{"schemaVersion":1,"dwh":{` +
`{"schemaVersion":2,"dwh":{` +
`"engine":"postgres","database":"postgres","schema":"datawarehouse",` +
`"transport":"postgres_direct","host":"dwh.internal","port":5432,"user":"thoth_reader"},` +
`"vector":{"collection":"psd-clinical","dimensions":1024,"distance":"cosine"},` +
`"embedding":{"model":"qwen3-embedding:0.6b","dimensions":1024},` +
`"embedding":{"id":"ollama/qwen3-embedding:0.6b","model":"qwen3-embedding:0.6b","dimensions":1024},` +
`"roots":{"artifacts":"/data/sessions/psd-clinical/artifacts",` +
`"indexes":"/data/sessions/psd-clinical/indexes"}}`;
@@ -192,6 +193,9 @@ test("DWH-affecting changes alter the effective config identity", () => {
const changedCollection = { ...base, resources: { ...base.resources, vector: { ...(base.resources as Record<string, any>).vector, collection: "other" } } };
expect(effectiveConfigIdentity("psd-clinical", changedCollection)).not.toBe(identityBefore);
const changedEmbeddingIdentity = { ...base, resources: { ...base.resources, embeddings: { ...(base.resources as Record<string, any>).embeddings, model: "other-embedding" } } };
expect(effectiveConfigIdentity("psd-clinical", changedEmbeddingIdentity)).not.toBe(identityBefore);
const changedTransport = restRendered();
expect(effectiveConfigIdentity("psd-clinical", changedTransport)).not.toBe(identityBefore);
});
+85 -247
View File
@@ -1,15 +1,12 @@
import { chmodSync, mkdtempSync, rmSync, writeFileSync } from "node:fs";
import { tmpdir } from "node:os";
import { join } from "node:path";
import { afterEach, expect, test, vi } from "vitest";
import { buildApp } from "../src/app.js";
import { MemoryCatalogRepository } from "../src/catalog/memory-repository.js";
import { afterEach, expect, test } from "vitest";
import {
loadMetadataGenerationModels,
MetadataGenerationModelUnavailableError,
} from "../src/catalog/metadata-generation-models.js";
import { loadConfig } from "../src/config.js";
import type { WorkspaceRegistry } from "../src/workspaces/registry.js";
import { loadRuntimeModelCatalog, splitCanonicalModelId } from "../src/models/runtime-model-catalog.js";
const roots: string[] = [];
@@ -17,260 +14,101 @@ afterEach(() => {
for (const root of roots.splice(0)) rmSync(root, { recursive: true, force: true });
});
function metadataConfiguration(
metadataGeneration: string,
secrets = "OPENAI_API_KEY=raw-provider-secret\n",
) {
const root = mkdtempSync(join(tmpdir(), "thothii-metadata-models-"));
function runtimeCatalog(overrides: Record<string, unknown> = {}, secrets = "OPENAI_API_KEY=raw-provider-secret\n") {
const root = mkdtempSync(join(tmpdir(), "thothii-runtime-models-"));
roots.push(root);
const installationFile = join(root, "thothii-installation.yaml");
const catalogFile = join(root, "catalog.json");
const secretsFile = join(root, "thothii.secrets");
writeFileSync(installationFile, metadataGeneration, { mode: 0o600 });
writeFileSync(secretsFile, secrets, { mode: 0o600 });
chmodSync(installationFile, 0o600);
chmodSync(secretsFile, 0o600);
return { installationFile, secretsFile };
}
function appFor(installationFile: string, secretsFile: string) {
const config = loadConfig({
NODE_ENV: "test",
THT_HARNESS_DIR: "/missing",
THT_INSTALLATION_CONFIG_FILE: installationFile,
THT_SECRETS_FILE: secretsFile,
PI_PROVIDER: "unrelated-pi-provider",
PI_MODEL: "unrelated-pi-model",
});
return buildApp(config, {
thtRunner: {} as never,
workspaceRegistry: { list: vi.fn(async () => []) } as unknown as WorkspaceRegistry,
workspaceDiagnoser: vi.fn(),
catalogRepository: new MemoryCatalogRepository(),
});
}
test("exposes only safe metadata-generation choices and their configured default", async () => {
const { installationFile, secretsFile } = metadataConfiguration(`metadataGeneration:
default: openai-mini
models:
- id: openai-mini
label: OpenAI Mini
litellm:
provider: openai
model: gpt-4.1-mini
endpoint:
baseUrl: https://api.openai.example/v1
apiVersion: "2026-08-01"
apiKeyEnv: OPENAI_API_KEY
`);
const app = appFor(installationFile, secretsFile);
const response = await app.inject({ method: "GET", url: "/catalog/metadata-generation/models" });
expect(response.statusCode).toBe(200);
expect(response.json()).toEqual({
models: [{ id: "openai-mini", label: "OpenAI Mini" }],
default: "openai-mini",
});
expect(response.body).not.toMatch(/openai\/gpt|gpt-4\.1|api\.openai|OPENAI_API_KEY|raw-provider-secret/);
await app.close();
});
test("rejects an unprotected installation descriptor", () => {
const { installationFile, secretsFile } = metadataConfiguration(`metadataGeneration:
default: openai-mini
models:
- id: openai-mini
label: OpenAI Mini
litellm: {provider: openai, model: gpt-4.1-mini}
apiKeyEnv: OPENAI_API_KEY
`);
chmodSync(installationFile, 0o644);
expect(() => loadMetadataGenerationModels({ installationFile, secretsFile }))
.toThrow("metadata-generation installation is unavailable");
});
test("returns an empty safe catalog when no metadata-generation model is configured", async () => {
const { installationFile, secretsFile } = metadataConfiguration("profile: local\n");
const app = appFor(installationFile, secretsFile);
const response = await app.inject({ method: "GET", url: "/catalog/metadata-generation/models" });
expect(response.statusCode).toBe(200);
expect(response.json()).toEqual({ models: [], default: null });
await app.close();
});
test("resolves only a configured selection for the later generation boundary", () => {
const { installationFile, secretsFile } = metadataConfiguration(`metadataGeneration:
default: openai-mini
models:
- id: openai-mini
label: OpenAI Mini
litellm:
provider: openai
model: gpt-4.1-mini
endpoint: {baseUrl: https://api.openai.example/v1, apiVersion: "2026-08-01"}
apiKeyEnv: OPENAI_API_KEY
`);
const models = loadMetadataGenerationModels({ installationFile, secretsFile });
expect(models.resolve("openai-mini")).toEqual({
id: "openai-mini",
provider: "openai",
model: "gpt-4.1-mini",
endpoint: { baseUrl: "https://api.openai.example/v1", apiVersion: "2026-08-01" },
apiKeyEnv: "OPENAI_API_KEY",
apiKey: "raw-provider-secret",
});
expect(() => models.resolve("unknown-model")).toThrow(MetadataGenerationModelUnavailableError);
});
test("loads DeepSeek models, GLM, and an explicit keyless Qwen endpoint from installation setup", () => {
const { installationFile, secretsFile } = metadataConfiguration(`metadataGeneration:
default: glm-53
models:
- id: deepseek-v4-pro
label: DeepSeek V4 Pro
litellm: {provider: deepseek, model: deepseek-v4-pro}
apiKeyEnv: DEEPSEEK_API_KEY
- id: deepseek-v4-flash
label: DeepSeek V4 Flash
litellm: {provider: deepseek, model: deepseek-v4-flash}
apiKeyEnv: DEEPSEEK_API_KEY
- id: glm-53
label: GLM 5.3
litellm:
provider: openai
model: glm-5.3
endpoint: {baseUrl: https://api.z.ai/api/coding/paas/v4}
apiKeyEnv: ZAI_API_KEY
- id: qwen-36
label: Qwen 3.6
litellm:
provider: openai
model: qwen3.6-35b-a3b
disableThinking: true
endpoint: {baseUrl: https://models.internal.example/v1}
`, "DEEPSEEK_API_KEY=deepseek-secret\nZAI_API_KEY=zai-secret\n");
const models = loadMetadataGenerationModels({ installationFile, secretsFile });
expect(models.catalog()).toEqual({
const catalog = {
schemaVersion: 1,
defaultSession: "zai/glm-5.3",
defaultMetadataGeneration: "zai/glm-5.3",
embedding: { id: "ollama/qwen3-embedding:0.6b", dimensions: 1024 },
models: [
{ id: "deepseek-v4-pro", label: "DeepSeek V4 Pro" },
{ id: "deepseek-v4-flash", label: "DeepSeek V4 Flash" },
{ id: "glm-53", label: "GLM 5.3" },
{ id: "qwen-36", label: "Qwen 3.6" },
{
id: "zai/glm-5.3", provider: "zai", model: "glm-5.3", label: "GLM 5.3",
upstreamModel: "glm-5.3", endpoint: { baseUrl: "https://api.z.ai/v1" },
authentication: { mode: "secret_env", apiKeyEnv: "OPENAI_API_KEY" },
sessionAdapter: { mode: "openai_compatible" },
metadataAdapter: { litellmProvider: "openai" },
session: { reasoning: true, contextWindow: 200000, maxTokens: 131072 },
metadataGeneration: { disableThinking: false },
},
{
id: "deepseek/deepseek-v4-pro", provider: "deepseek", model: "deepseek-v4-pro",
label: "DeepSeek V4 Pro", upstreamModel: "deepseek-v4-pro",
authentication: { mode: "pi_auth" }, sessionAdapter: { mode: "pi_builtin" },
session: { reasoning: false },
},
],
default: "glm-53",
...overrides,
};
writeFileSync(catalogFile, JSON.stringify(catalog), { mode: 0o600 });
writeFileSync(secretsFile, secrets, { mode: 0o600 });
chmodSync(catalogFile, 0o600);
chmodSync(secretsFile, 0o600);
return { catalogFile, secretsFile };
}
test("loads session default and safe metadata choices from the normalized runtime catalog", () => {
const { catalogFile, secretsFile } = runtimeCatalog();
const runtime = loadRuntimeModelCatalog(catalogFile);
const metadata = loadMetadataGenerationModels({ catalogFile, secretsFile });
expect(runtime.defaultSession).toBe("zai/glm-5.3");
expect(runtime.hasSession("deepseek/deepseek-v4-pro")).toBe(true);
expect(metadata.catalog()).toEqual({
models: [{ id: "zai/glm-5.3", label: "GLM 5.3" }],
default: "zai/glm-5.3",
});
expect(models.resolve("deepseek-v4-pro")).toMatchObject({
apiKeyEnv: "DEEPSEEK_API_KEY",
apiKey: "deepseek-secret",
});
expect(models.resolve("qwen-36")).toEqual({
id: "qwen-36",
provider: "openai",
model: "qwen3.6-35b-a3b",
disableThinking: true,
endpoint: { baseUrl: "https://models.internal.example/v1" },
expect(metadata.resolve("zai/glm-5.3")).toEqual({
id: "zai/glm-5.3", provider: "openai", model: "glm-5.3",
endpoint: { baseUrl: "https://api.z.ai/v1" },
apiKeyEnv: "OPENAI_API_KEY", apiKey: "raw-provider-secret",
});
expect(() => metadata.resolve("zai/missing")).toThrow(MetadataGenerationModelUnavailableError);
});
test("loads an explicit keyless endpoint without a secret bundle", () => {
const { installationFile } = metadataConfiguration(`metadataGeneration:
default: qwen-36
models:
- id: qwen-36
label: Qwen 3.6
litellm:
provider: openai
model: qwen3.6-35b-a3b
disableThinking: true
endpoint: {baseUrl: https://models.internal.example/v1}
`);
test("returns empty catalogs when no runtime projection is configured", () => {
expect(loadRuntimeModelCatalog().defaultSession).toBeNull();
expect(loadMetadataGenerationModels({}).catalog()).toEqual({ models: [], default: null });
});
expect(loadMetadataGenerationModels({ installationFile }).resolve("qwen-36")).toEqual({
id: "qwen-36",
provider: "openai",
model: "qwen3.6-35b-a3b",
disableThinking: true,
endpoint: { baseUrl: "https://models.internal.example/v1" },
test("rejects a drifted default and an unprotected projection", () => {
const drifted = runtimeCatalog({ defaultSession: "zai/missing" });
expect(() => loadRuntimeModelCatalog(drifted.catalogFile)).toThrow("session default is invalid");
const unprotected = runtimeCatalog();
chmodSync(unprotected.catalogFile, 0o666);
expect(() => loadRuntimeModelCatalog(unprotected.catalogFile)).toThrow("runtime model catalog is unavailable");
});
test("rejects authentication semantics that cannot come from the installation catalog", () => {
const invalid = runtimeCatalog({
defaultMetadataGeneration: undefined,
models: [{
id: "zai/glm-5.3",
provider: "zai",
model: "glm-5.3",
label: "GLM 5.3",
upstreamModel: "glm-5.3",
authentication: { mode: "secret_env" },
sessionAdapter: { mode: "pi_builtin" },
session: { reasoning: true },
}],
});
expect(() => loadRuntimeModelCatalog(invalid.catalogFile)).toThrow("runtime model catalog is invalid");
});
test.each([
["invalid YAML", "metadataGeneration: [\n", "OPENAI_API_KEY=secret\n", /invalid YAML/],
["duplicate ids", `metadataGeneration:
default: openai-mini
models:
- {id: openai-mini, label: One, litellm: {provider: openai, model: gpt-4.1-mini}, apiKeyEnv: OPENAI_API_KEY}
- {id: openai-mini, label: Two, litellm: {provider: openai, model: gpt-4.1}, apiKeyEnv: OPENAI_API_KEY}
`, "OPENAI_API_KEY=secret\n", /model id "openai-mini" is duplicated/],
["missing default", `metadataGeneration:
models:
- {id: openai-mini, label: One, litellm: {provider: openai, model: gpt-4.1-mini}, apiKeyEnv: OPENAI_API_KEY}
`, "OPENAI_API_KEY=secret\n", /default is required/],
["unknown default", `metadataGeneration:
default: absent
models:
- {id: openai-mini, label: One, litellm: {provider: openai, model: gpt-4.1-mini}, apiKeyEnv: OPENAI_API_KEY}
`, "OPENAI_API_KEY=secret\n", /default "absent" is not configured/],
["malformed settings", `metadataGeneration:
default: openai-mini
models:
- {id: openai-mini, label: One, litellm: {provider: "open ai", model: gpt-4.1-mini}, apiKeyEnv: OPENAI_API_KEY}
`, "OPENAI_API_KEY=secret\n", /configuration is invalid/],
["malformed endpoint", `metadataGeneration:
default: openai-mini
models:
- id: openai-mini
label: One
litellm: {provider: openai, model: gpt-4.1-mini, endpoint: {baseUrl: not-a-url}}
apiKeyEnv: OPENAI_API_KEY
`, "OPENAI_API_KEY=secret\n", /configuration is invalid/],
["keyless hosted model without endpoint", `metadataGeneration:
default: openai-mini
models:
- {id: openai-mini, label: One, litellm: {provider: openai, model: gpt-4.1-mini}}
`, "", /configuration is invalid/],
["disable thinking without endpoint", `metadataGeneration:
default: openai-mini
models:
- id: openai-mini
label: One
litellm: {provider: openai, model: gpt-4.1-mini, disableThinking: true}
apiKeyEnv: OPENAI_API_KEY
`, "OPENAI_API_KEY=secret\n", /configuration is invalid/],
["unallowed secret reference", `metadataGeneration:
default: openai-mini
models:
- {id: openai-mini, label: One, litellm: {provider: openai, model: gpt-4.1-mini}, apiKeyEnv: THT_DWH_API_KEY}
`, "THT_DWH_API_KEY=secret\n", /configuration is invalid/],
["missing referenced secret", `metadataGeneration:
default: openai-mini
models:
- {id: openai-mini, label: One, litellm: {provider: openai, model: gpt-4.1-mini}, apiKeyEnv: OPENAI_API_KEY}
`, "THT_DWH_API_KEY=secret\n", /secret "OPENAI_API_KEY" is missing/],
["unusable referenced secret", `metadataGeneration:
default: openai-mini
models:
- {id: openai-mini, label: One, litellm: {provider: openai, model: gpt-4.1-mini}, apiKeyEnv: OPENAI_API_KEY}
`, "OPENAI_API_KEY=secret with whitespace\n", /secret "OPENAI_API_KEY" is unusable/],
] as const)("rejects %s metadata-generation configuration", (_name, yaml, secrets, expected) => {
const { installationFile, secretsFile } = metadataConfiguration(yaml, secrets);
expect(() => loadMetadataGenerationModels({ installationFile, secretsFile })).toThrow(expected);
test("fails closed for missing or unusable provider secrets", () => {
const missing = runtimeCatalog({}, "THT_DWH_API_KEY=other\n");
expect(() => loadMetadataGenerationModels(missing)).toThrow('secret "OPENAI_API_KEY" is missing');
const unusable = runtimeCatalog({}, "OPENAI_API_KEY=contains whitespace\n");
expect(() => loadMetadataGenerationModels(unusable)).toThrow('secret "OPENAI_API_KEY" is unusable');
});
test("rejects a missing secret-bundle declaration for configured models", () => {
const { installationFile } = metadataConfiguration(`metadataGeneration:
default: openai-mini
models:
- {id: openai-mini, label: One, litellm: {provider: openai, model: gpt-4.1-mini}, apiKeyEnv: OPENAI_API_KEY}
`);
expect(() => loadMetadataGenerationModels({ installationFile }))
.toThrow("metadata-generation keyed models require THT_SECRETS_FILE");
test("splits canonical session identities without provider aliases", () => {
expect(splitCanonicalModelId("zai/glm-5.3")).toEqual({ provider: "zai", model: "glm-5.3" });
expect(() => splitCanonicalModelId("glm-5.3")).toThrow("model identity is invalid");
});
+18 -108
View File
@@ -1,13 +1,13 @@
import { mkdtempSync, readFileSync, readdirSync, rmSync } from "node:fs";
import { mkdtempSync } from "node:fs";
import { tmpdir } from "node:os";
import { join } from "node:path";
import { expect, test, vi } from "vitest";
import { loadConfig } from "../src/config.js";
import {
PiManagementError,
createPiManagement,
type PiExecFile,
} from "../src/pi/management.js";
import type { RuntimeModelCatalog } from "../src/models/runtime-model-catalog.js";
function configFor(settingsFile = join(mkdtempSync(join(tmpdir(), "tht-pi-management-")), "settings.json")) {
return loadConfig({
@@ -18,10 +18,14 @@ function configFor(settingsFile = join(mkdtempSync(join(tmpdir(), "tht-pi-manage
});
}
const supportedModels = [
{ provider: "zai", id: "glm-5.2", name: "GLM 5.2", reasoning: true },
{ provider: "deepseek", id: "deepseek-v4", name: "DeepSeek V4", reasoning: true },
];
const modelCatalog: RuntimeModelCatalog = {
defaultSession: "zai/glm-5.2",
defaultMetadataGeneration: null,
embedding: { id: "ollama/qwen3-embedding:0.6b", dimensions: 1024 },
sessionModels: () => [],
metadataModels: () => [],
hasSession: (id) => id === "zai/glm-5.2",
};
function successfulExec(calls: Array<{ command: string; args: string[]; timeout: number }>): PiExecFile {
return async (command, args, options) => {
@@ -36,7 +40,7 @@ test("status parses only a Pi version from a fixed execFile argument array", asy
const calls: Array<{ command: string; args: string[]; timeout: number }> = [];
const service = createPiManagement(configFor(), {
execute: successfulExec(calls),
listModels: async () => supportedModels,
modelCatalog,
readSettings: () => ({ provider: "zai", model: "glm-5.2", thinking: "medium" }),
credentialStatus: () => "missing",
now: () => new Date("2026-08-05T10:00:00.000Z"),
@@ -63,7 +67,7 @@ test.each(["present", "missing"] as const)(
const checkedProviders: Array<string | undefined> = [];
const service = createPiManagement(configFor(), {
execute: successfulExec([]),
listModels: async () => supportedModels,
modelCatalog,
readSettings: () => ({ provider: "zai", model: "glm-5.2", thinking: "medium" }),
credentialStatus: (provider) => {
checkedProviders.push(provider);
@@ -85,100 +89,6 @@ test.each(["present", "missing"] as const)(
},
);
// Catches an options response that leaks provider metadata or lets callers choose model IDs that
// Pi did not explicitly enable for this installation.
test("options expose only closed provider, model, and reasoning choices", async () => {
const service = createPiManagement(configFor(), {
execute: successfulExec([]),
listModels: async () => supportedModels,
now: () => new Date("2026-08-05T10:00:00.000Z"),
});
await expect(service.options()).resolves.toEqual({
providers: ["zai", "deepseek"],
models: [
{ provider: "zai", id: "glm-5.2" },
{ provider: "deepseek", id: "deepseek-v4" },
],
reasoning: ["low", "medium", "high"],
checkedAt: "2026-08-05T10:00:00.000Z",
});
});
// Catches raw managed models.json validation details being collapsed into an ambiguous model-list
// failure or escaping through the Pi Management options API.
test("options report invalid managed model configuration with a stable sanitized error", async () => {
const service = createPiManagement(configFor(), {
execute: successfulExec([]),
listModels: async () => {
throw Object.assign(
new Error("!sensitive-command /private/models.json raw-secret"),
{ code: "PI_MANAGED_CONFIG_INVALID" },
);
},
});
let caught: unknown;
try {
await service.options();
} catch (error) {
caught = error;
}
expect(caught).toMatchObject<PiManagementError>({
code: "pi_management_unavailable",
message: "Pi provider/model configuration is invalid",
});
expect(String(caught)).not.toMatch(/sensitive|private|models\.json|secret/i);
});
// Catches configuration writes that accept whitespace, unknown choices, or extra free-form fields
// before reaching the durable installation settings file.
test("config rejects invalid free-form values before writing settings", async () => {
const directory = mkdtempSync(join(tmpdir(), "tht-pi-management-invalid-"));
try {
let writes = 0;
const service = createPiManagement(configFor(join(directory, "settings.json")), {
execute: successfulExec([]),
listModels: async () => supportedModels,
readSettings: () => ({}),
saveSettings: () => { writes += 1; return {}; },
});
await expect(service.configure({
provider: "zai ", model: "glm-5.2", reasoning: "medium", unexpected: "value",
} as any)).rejects.toMatchObject<PiManagementError>({ code: "pi_management_invalid_config" });
expect(writes).toBe(0);
} finally {
rmSync(directory, { recursive: true, force: true });
}
});
// Catches a non-atomic implementation that can leave partial settings or temporary files after a
// normal installation-default update.
test("config validates closed choices and atomically persists non-secret defaults", async () => {
const directory = mkdtempSync(join(tmpdir(), "tht-pi-management-write-"));
const settingsFile = join(directory, "settings.json");
try {
const service = createPiManagement(configFor(settingsFile), {
execute: successfulExec([]),
listModels: async () => supportedModels,
now: () => new Date("2026-08-05T10:00:00.000Z"),
});
await expect(service.configure({
provider: "zai", model: "glm-5.2", reasoning: "high",
})).resolves.toEqual({
provider: "zai", model: "glm-5.2", reasoning: "high", updatedAt: "2026-08-05T10:00:00.000Z",
});
expect(JSON.parse(readFileSync(settingsFile, "utf8"))).toEqual({
provider: "zai", model: "glm-5.2", thinking: "high",
});
expect(readdirSync(directory)).toEqual(["settings.json"]);
} finally {
rmSync(directory, { recursive: true, force: true });
}
});
// Catches a hung Pi smoke check that leaves an operator waiting indefinitely or returns raw child
// diagnostics containing provider credentials.
test("smoke uses the configured timeout and reports a sanitized timeout", async () => {
@@ -188,7 +98,7 @@ test("smoke uses the configured timeout and reports a sanitized timeout", async
calls.push({ command, args, timeout: options.timeout });
throw Object.assign(new Error("provider token=raw-provider-token"), { code: "ETIMEDOUT" });
},
listModels: async () => supportedModels,
modelCatalog,
readSettings: () => ({ provider: "zai", model: "glm-5.2", thinking: "medium" }),
now: () => new Date("2026-08-05T10:00:00.000Z"),
});
@@ -210,7 +120,7 @@ test("smoke exercises the configured provider and model", async () => {
const providerChecks: unknown[] = [];
const service = createPiManagement(configFor(), {
execute: successfulExec([]),
listModels: async () => supportedModels,
modelCatalog,
readSettings: () => ({ provider: "zai", model: "glm-5.2", thinking: "medium" }),
smokeProvider: async (request) => { providerChecks.push(request); },
now: () => new Date("2026-08-05T10:00:00.000Z"),
@@ -230,7 +140,7 @@ test("smoke exercises the configured provider and model", async () => {
test("smoke fails closed and sanitizes configured-provider authentication errors", async () => {
const service = createPiManagement(configFor(), {
execute: successfulExec([]),
listModels: async () => supportedModels,
modelCatalog,
readSettings: () => ({ provider: "zai", model: "glm-5.2", thinking: "medium" }),
smokeProvider: async () => {
throw new Error('401 {"token":"raw-expired-token","output":"raw-provider-output"}');
@@ -252,7 +162,7 @@ test("smoke fails closed and sanitizes configured-provider authentication errors
test("smoke reports invalid managed provider configuration with a stable sanitized error", async () => {
const service = createPiManagement(configFor(), {
execute: successfulExec([]),
listModels: async () => supportedModels,
modelCatalog,
readSettings: () => ({ provider: "zai", model: "glm-5.2", thinking: "medium" }),
smokeProvider: async () => {
throw Object.assign(
@@ -284,7 +194,7 @@ test("smoke applies one deadline across version and a hung provider turn", async
() => resolve({ stdout: "pi 0.80.3\n", stderr: "" }),
500,
)),
listModels: async () => supportedModels,
modelCatalog,
readSettings: () => ({ provider: "zai", model: "glm-5.2", thinking: "medium" }),
smokeProvider: async ({ timeoutMs }) => {
providerTimeouts.push(timeoutMs);
@@ -320,7 +230,7 @@ test("logs keep only the latest 200 redacted lines", async () => {
source[201] = "THT_MODEL_API_KEY=raw-env-secret";
const service = createPiManagement(configFor(), {
execute: successfulExec([]),
listModels: async () => supportedModels,
modelCatalog,
readLogs: () => source.join("\n"),
now: () => new Date("2026-08-05T10:00:00.000Z"),
});
+48
View File
@@ -8,6 +8,7 @@ import {
} from "node:fs";
import { tmpdir } from "node:os";
import { PiProcessManager } from "../src/pi/pi-process-manager.js";
import type { RuntimeModelCatalog, RuntimeModel } from "../src/models/runtime-model-catalog.js";
import { loadConfig } from "../src/config.js";
import {
PI_MANAGED_CONFIG_ERROR_MESSAGE,
@@ -641,6 +642,53 @@ test("session Pi spawn reads the single secret bundle and scrubs its path", asyn
}
});
test("session Pi spawn resolves the selected catalog credential from the secret bundle", () => {
const root = mkdtempSync(path.join(tmpdir(), "thothii-catalog-credential-"));
const agentDir = path.join(root, "agent");
mkdirSync(agentDir, { mode: 0o700 });
writeFileSync(path.join(agentDir, "auth.json"), "{}\n", { mode: 0o600 });
writeFileSync(path.join(agentDir, "models.json"), '{"providers":{}}\n', { mode: 0o600 });
const secret = path.join(root, "thothii.secrets");
writeFileSync(secret, "ZAI_API_KEY=catalog-secret\nTHT_MODEL_API_KEY=legacy-secret\n", { mode: 0o600 });
const model: RuntimeModel = {
id: "openai/test-model",
provider: "openai",
model: "test-model",
label: "Test model",
upstreamModel: "test-model",
authentication: { mode: "secret_env", apiKeyEnv: "ZAI_API_KEY" },
sessionAdapter: { mode: "pi_builtin" },
session: { reasoning: false },
};
const modelCatalog: RuntimeModelCatalog = {
defaultSession: model.id,
defaultMetadataGeneration: null,
embedding: null,
sessionModels: () => [model],
metadataModels: () => [],
hasSession: (id) => id === model.id,
};
const calls: any[][] = [];
const child = recordingChild();
child.stderr.resume = () => {};
vi.stubEnv("PI_CODING_AGENT_DIR", agentDir);
const mgr = new PiProcessManager(loadConfig({ THT_SECRETS_FILE: secret }), {
modelCatalog,
authProviders: () => new Set(),
spawnFn: (...args: any[]) => { calls.push(args); return child as any; },
});
try {
mgr.createFor("catalog-credential", { provider: "openai", model: "test-model" });
expect(calls[0][2].env.ZAI_API_KEY).toBe("catalog-secret");
expect(calls[0][2].env).not.toHaveProperty("OPENAI_API_KEY");
expect(calls[0][2].env).not.toHaveProperty("THT_MODEL_API_KEY");
} finally {
mgr.teardown("catalog-credential");
vi.unstubAllEnvs();
rmSync(root, { recursive: true, force: true });
}
});
test.each([["OpenAI", "openai"], ["gemini", "google"]])(
"set_model uses canonical packaged provider ID for %s", async (provider, canonical) => {
const secret = path.resolve(__dirname, `.canonical-key-${process.pid}-${provider}`);
+48 -2
View File
@@ -1,9 +1,11 @@
import { EventEmitter } from "node:events";
import { existsSync, readFileSync, readdirSync } from "node:fs";
import { dirname } from "node:path";
import { existsSync, mkdtempSync, readFileSync, readdirSync, rmSync, writeFileSync } from "node:fs";
import { tmpdir } from "node:os";
import { dirname, join } from "node:path";
import { afterEach, expect, test, vi } from "vitest";
import { loadConfig } from "../src/config.js";
import { createPiProviderSmoke } from "../src/pi/provider-smoke.js";
import type { RuntimeModel, RuntimeModelCatalog } from "../src/models/runtime-model-catalog.js";
afterEach(() => vi.unstubAllEnvs());
@@ -44,6 +46,50 @@ function successfulProviderChild() {
const MANAGED_CONFIG_ERROR = "Pi provider/model configuration is invalid";
test("provider smoke resolves the selected catalog credential from the secret bundle", async () => {
const root = mkdtempSync(join(tmpdir(), "thothii-smoke-catalog-credential-"));
const secret = join(root, "thothii.secrets");
writeFileSync(secret, "ZAI_API_KEY=catalog-secret\nTHT_MODEL_API_KEY=legacy-secret\n", { mode: 0o600 });
const model: RuntimeModel = {
id: "openai/test-model",
provider: "openai",
model: "test-model",
label: "Test model",
upstreamModel: "test-model",
authentication: { mode: "secret_env", apiKeyEnv: "ZAI_API_KEY" },
sessionAdapter: { mode: "pi_builtin" },
session: { reasoning: false },
};
const modelCatalog: RuntimeModelCatalog = {
defaultSession: model.id,
defaultMetadataGeneration: null,
embedding: null,
sessionModels: () => [model],
metadataModels: () => [],
hasSession: (id) => id === model.id,
};
let spawnEnv: NodeJS.ProcessEnv | undefined;
const smoke = createPiProviderSmoke(loadConfig({ THT_SECRETS_FILE: secret }), {
modelCatalog,
authProviders: () => new Set(),
readModelsStore: () => undefined,
spawnFn: (_command, _args, options) => {
spawnEnv = options.env;
return successfulProviderChild();
},
});
try {
await expect(smoke({
provider: "openai", model: "test-model", reasoning: "medium", timeoutMs: 750,
})).resolves.toBeUndefined();
expect(spawnEnv?.ZAI_API_KEY).toBe("catalog-secret");
expect(spawnEnv).not.toHaveProperty("OPENAI_API_KEY");
expect(spawnEnv).not.toHaveProperty("THT_MODEL_API_KEY");
} finally {
rmSync(root, { recursive: true, force: true });
}
});
// Catches an isolated smoke agent that copies auth.json but drops the selected custom
// provider/model from models.json, causing set_model to fail before the real request.
test("provider smoke reaches the selected custom provider from an isolated models.json", async () => {
+1 -8
View File
@@ -2,18 +2,11 @@ import { expect, test } from "vitest";
import { ReadinessManager } from "../src/runtime/readiness-manager.js";
const workspace = {
workspace: { schema_version: 3, id: "psd", name: "PSD", language: "it" },
workspace: { schema_version: 4, id: "psd", name: "PSD", language: "it" },
dwh: {
engine: "postgres", database: "warehouse", schema: "public",
supported_transports: ["postgres_direct"],
},
semantic_index: {
vector_store: { engine: "qdrant", collection: "psd", dimensions: 1024, distance: "cosine" },
embedding: {
provider: "ollama_internal", model: "qwen3-embedding:0.6b", dimensions: 1024,
},
},
llm_policy: { allowed: ["zai/glm-5.2"] },
} as const;
function deferred<T>() {
+1 -13
View File
@@ -15,7 +15,7 @@ afterEach(() => {
});
const validYaml = `workspace:
schema_version: 3
schema_version: 4
id: psd-clinical
name: Policlinico San Donato
language: it
@@ -24,18 +24,6 @@ dwh:
database: postgres
schema: datawarehouse
supported_transports: [postgres_direct]
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:
allowed: [zai/glm-5.2]
`;
async function git(cwd: string, args: string[]): Promise<string> {
+1 -13
View File
@@ -20,7 +20,7 @@ async function git(cwd: string, args: string[]): Promise<string> {
}
const descriptor = `workspace:
schema_version: 3
schema_version: 4
id: research
name: Research
language: en
@@ -29,18 +29,6 @@ dwh:
database: analytics
schema: mart
supported_transports: [postgres_direct]
semantic_index:
vector_store:
engine: qdrant
collection: research
dimensions: 1024
distance: cosine
embedding:
provider: ollama_internal
model: qwen3-embedding:0.6b
dimensions: 1024
llm_policy:
allowed: [zai/glm-5.2]
evidence:
source:
type: filesystem
+9 -27
View File
@@ -14,11 +14,6 @@ function fakeService(): PiManagementService {
config: { provider: "zai", model: "glm-5.2", reasoning: "medium" },
checkedAt: "2026-08-05T10:00:00.000Z",
})),
options: vi.fn(async () => ({
providers: ["zai"], models: [{ provider: "zai", id: "glm-5.2" }],
reasoning: ["low", "medium", "high"], checkedAt: "2026-08-05T10:00:00.000Z",
})),
configure: vi.fn(async (value) => ({ ...value, updatedAt: "2026-08-05T10:00:00.000Z" })),
test: vi.fn(async () => ({ ready: true, checkedAt: "2026-08-05T10:00:00.000Z" })),
logs: vi.fn(async () => ({ lines: ["Pi smoke check succeeded"], checkedAt: "2026-08-05T10:00:00.000Z" })),
};
@@ -106,24 +101,17 @@ test("loopback-only AUTH_MODE=none may read the sanitized Pi status", async () =
});
// A local implicit administrator has pi.manage, but a browser origin still cannot borrow that
// authority to mutate local configuration or trigger provider work.
// authority to trigger provider work.
test("loopback-only management rejects cross-origin writes for its local administrator", async () => {
const service = fakeService();
const app = appWith(service);
try {
const configured = await app.inject({
method: "PUT", url: "/pi-management/config",
headers: { host: "127.0.0.1:8080", origin: "https://evil.example" },
payload: { provider: "zai", model: "glm-5.2", reasoning: "high" },
});
const smoke = await app.inject({
method: "POST", url: "/pi-management/test",
headers: { host: "127.0.0.1:8080", origin: "https://evil.example" },
});
expect(configured.statusCode).toBe(403);
expect(smoke.statusCode).toBe(403);
expect(service.configure).not.toHaveBeenCalled();
expect(service.test).not.toHaveBeenCalled();
} finally {
await app.close();
@@ -132,14 +120,13 @@ test("loopback-only management rejects cross-origin writes for its local adminis
// Catches an origin guard that also blocks the same-origin Docker frontend or non-browser local
// lifecycle clients that do not send Origin.
test("loopback-only management preserves same-origin frontend and origin-less local writes", async () => {
test("loopback-only management preserves same-origin and origin-less smoke checks", async () => {
const service = fakeService();
const app = appWith(service);
try {
const sameOrigin = await app.inject({
method: "PUT", url: "/pi-management/config",
method: "POST", url: "/pi-management/test",
headers: { host: "127.0.0.1:8080", origin: "http://127.0.0.1:8080" },
payload: { provider: "zai", model: "glm-5.2", reasoning: "high" },
});
const lifecycleClient = await app.inject({ method: "POST", url: "/pi-management/test" });
@@ -150,25 +137,20 @@ test("loopback-only management preserves same-origin frontend and origin-less lo
}
});
// Catches route wiring that bypasses closed service validation or gives the browser a Docker/image
// lifecycle endpoint rather than only installation-default configuration and diagnostics.
test("trusted admins receive only configuration, smoke, options, and log endpoints", async () => {
// Catches a regression that reintroduces a browser-writable provider/model source.
test("trusted admins receive only status, smoke, and log endpoints", async () => {
const service = fakeService();
const app = appWith(service, exposedServerEnv);
try {
const options = await app.inject({ method: "GET", url: "/pi-management/options", headers: adminHeaders });
const configured = await app.inject({
method: "PUT", url: "/pi-management/config", headers: adminHeaders,
payload: { provider: "zai", model: "glm-5.2", reasoning: "high" },
});
const status = await app.inject({ method: "GET", url: "/pi-management/status", headers: adminHeaders });
const smoke = await app.inject({ method: "POST", url: "/pi-management/test", headers: adminHeaders });
const logs = await app.inject({ method: "GET", url: "/pi-management/logs", headers: adminHeaders });
expect(options.statusCode).toBe(200);
expect(configured.statusCode).toBe(200);
expect(configured.json()).toMatchObject({ provider: "zai", model: "glm-5.2", reasoning: "high" });
expect(status.statusCode).toBe(200);
expect(smoke.statusCode).toBe(200);
expect(logs.statusCode).toBe(200);
expect((await app.inject({ method: "GET", url: "/pi-management/options", headers: adminHeaders })).statusCode).toBe(404);
expect((await app.inject({ method: "PUT", url: "/pi-management/config", headers: adminHeaders })).statusCode).toBe(404);
expect(app.printRoutes()).not.toContain("update");
expect(app.printRoutes()).not.toContain("rollback");
} finally {
+45 -44
View File
@@ -18,25 +18,25 @@ const SCRIPT = path.resolve("../harness/tests/fake_pi/scripts/f1_disambiguation.
function operationalWorkspace(id = "default") {
return {
workspace: { schema_version: 3, id, name: id, language: "en" },
workspace: { schema_version: 4, id, name: id, language: "en" },
dwh: {
engine: "postgres", database: "warehouse", schema: "public",
supported_transports: ["postgres_direct"],
},
semantic_index: {
vector_store: {
engine: "qdrant", collection: id, dimensions: 1024, distance: "cosine",
},
embedding: {
provider: "ollama_internal", model: "qwen3-embedding:0.6b", dimensions: 1024,
},
},
llm_policy: {
allowed: ["zai/glm-5.2", "deepseek/deepseek-v4-pro", "local-qwen/qwen3.6-35b-a3b"],
},
} as const;
}
function sessionCatalog(defaultSession = "zai/glm-5.2", available = [defaultSession]) {
return {
defaultSession,
defaultMetadataGeneration: null,
embedding: { id: "ollama/qwen3-embedding:0.6b", dimensions: 1024 },
sessionModels: () => [],
metadataModels: () => [],
hasSession: (id: string) => available.includes(id),
} as any;
}
const defaultWorkspaceRegistry = {
list: vi.fn(async () => [{
id: "default", commit: "e".repeat(40), blob: "f".repeat(40),
@@ -495,8 +495,8 @@ test("creates a session from the active immutable workspace revision", async ()
workspaceRegistry: {
read: vi.fn(async () => ({
workspace: {
workspace: { schema_version: 2, id: "psd-clinical", name: "PSD", language: "it" },
dwh: {}, semantic_index: {}, llm_policy: { allowed: ["zai/glm-5.2"] },
workspace: { schema_version: 4, id: "psd-clinical", name: "PSD", language: "it" },
dwh: {},
},
revision: {
id: "psd-clinical", commit: "a".repeat(40), blob: "b".repeat(40),
@@ -589,22 +589,11 @@ test("rejects an SSH-only workspace before persisting or starting a session", as
workspaceRegistry: {
acquireSessionRevision: vi.fn(async () => ({
workspace: {
workspace: { schema_version: 2, id: "ssh-workspace", name: "SSH", language: "en" },
workspace: { schema_version: 4, id: "ssh-workspace", name: "SSH", language: "en" },
dwh: {
engine: "postgres", database: "postgres", schema: "public",
supported_transports: ["ssh_tunnel"],
},
semantic_index: {
vector_store: {
engine: "pgvector", database: "postgres", schema: "vectors",
collection: "documents", dimensions: 768, distance: "cosine",
supported_transports: ["ssh_tunnel"],
},
embedding: {
provider: "ollama_compatible", model: "nomic-embed-text", dimensions: 768,
},
},
llm_policy: { allowed: ["zai/glm-5.2"] },
},
revision: {
id: "ssh-workspace", commit: "a".repeat(40), blob: "b".repeat(40),
@@ -632,7 +621,7 @@ test("hands a revision lease to retention only after the session manifest is dur
const markPersisted = vi.fn(async () => {});
const abort = vi.fn(async () => {});
const acquireSessionRevision = vi.fn(async () => ({
workspace: { llm_policy: { allowed: ["zai/glm-5.2"] } },
workspace: operationalWorkspace("leased"),
revision: {
id: "leased", commit: "a".repeat(40), blob: "b".repeat(40),
snapshotPath: `/data/workspace-registry/snapshots/${"a".repeat(40)}/leased.yaml`,
@@ -670,7 +659,7 @@ test("creates a session from the configured default workspace revision when work
const sessionNew = vi.fn(async () => ({ id: "default-pinned" }));
const registry = {
read: vi.fn(async (id: string) => ({
workspace: { llm_policy: { allowed: ["zai/glm-5.2"] } },
workspace: operationalWorkspace(id),
revision: {
id, commit: "c".repeat(40), blob: "d".repeat(40),
snapshotPath: `/data/workspace-registry/snapshots/${"c".repeat(40)}/${id}.yaml`,
@@ -758,7 +747,7 @@ test("session lifecycle locates a B session when installation default is A", asy
listModels: async () => [{ provider: "zai", id: "glm-5.2", name: "GLM 5.2", reasoning: true }],
workspaceRegistry: {
read: async (id: string) => ({
workspace: { llm_policy: { allowed: ["zai/glm-5.2"] } },
workspace: operationalWorkspace(id),
revision: { id, commit: "b".repeat(40), blob: "d".repeat(40), snapshotPath: bPath },
}),
list: async () => [
@@ -793,7 +782,7 @@ test("session lifecycle locates a B session when installation default is A", asy
expect(runtimeOptions).toEqual(["/runtime/1.yaml", "/runtime/2.yaml"]);
});
test("POST /sessions usa i settings (workspace/provider/model/thinking) e crea+avvia", async () => {
test("POST /sessions uses the catalog default with workspace/thinking settings and starts", async () => {
const modelKey = path.join(os.tmpdir(), `thoth-model-key-${process.pid}`);
writeFileSync(modelKey, "test-model-key", { mode: 0o600 });
chmodSync(modelKey, 0o600);
@@ -808,7 +797,8 @@ test("POST /sessions usa i settings (workspace/provider/model/thinking) e crea+a
sessionNew: async (o: any) => { sessionNewArg = o; return { id: "s1" }; },
sessionList: async () => [{ id: "s1" }],
} as any,
getSettings: () => ({ workspace: "w", provider: "zai", model: "glm-5.2", thinking: "high" }),
getSettings: () => ({ workspace: "w", thinking: "high" }),
runtimeModelCatalog: sessionCatalog(),
listModels: async () => [
{ provider: "zai", id: "glm-5.2", name: "GLM 5.2", reasoning: true },
],
@@ -2565,32 +2555,43 @@ test("POST /sessions proceeds when ollamaEnsure succeeds", async () => {
expect(ensureWs).toContain(`/snapshots/${"e".repeat(40)}/psd.yaml`);
});
test("POST /sessions rejects an unavailable saved model before persisting a session", async () => {
test("POST /sessions falls back from a stale requested model to the catalog default", async () => {
let created = 0;
let persisted: any;
const runtime = { bridge: { onClientEvent: () => {} } };
const app = buildApp(loadConfig({ THT_HARNESS_DIR: "../harness" }), {
thtRunner: {
sessionNew: async () => { created += 1; return { id: "must-not-exist" }; },
sessionNew: async (options: any) => { created += 1; persisted = options; return { id: "fallback" }; },
searchPack: async () => {},
} as any,
readiness: { ensure: async () => ({ ok: true }) } as any,
getSettings: () => ({
workspace: "psd",
provider: "deepseek",
model: "deepseek-v4-pro",
thinking: "medium",
}) as any,
getSettings: () => ({ workspace: "psd", thinking: "medium" }) as any,
runtimeModelCatalog: sessionCatalog(),
listModels: async () => [
{ provider: "zai", id: "glm-5.2", name: "GLM 5.2", reasoning: true },
],
mgr: {
teardownForPrincipal: () => [],
createFor: () => runtime,
get: () => runtime,
configure: async () => {},
start: () => {},
} as any,
});
const res = await app.inject({ method: "POST", url: "/sessions", payload: { question: "q" } });
const res = await app.inject({
method: "POST",
url: "/sessions",
payload: { question: "q", provider: "deepseek", model: "deepseek-v4-pro" },
});
expect(res.statusCode).toBe(503);
expect(res.statusCode).toBe(200);
expect(res.json()).toEqual({
error: "Selected model is unavailable. Check Pi authentication and model settings, then try again.",
code: "model_unavailable",
id: "fallback",
warning: "Configured model deepseek/deepseek-v4-pro is unavailable; using zai/glm-5.2.",
});
expect(created).toBe(0);
expect(persisted).toMatchObject({ provider: "zai", model: "glm-5.2" });
expect(created).toBe(1);
});
test("POST /sessions marks a persisted session failed when runtime construction throws", async () => {
+16 -16
View File
@@ -21,7 +21,7 @@ function appWithTmpSettings(extraEnv: Record<string, string> = {}, deps = {}) {
return { app, dir };
}
test("GET /settings returns effective defaults (env provider/model/thinking, first workspace)", async () => {
test("GET /settings returns thinking and the first workspace without legacy model defaults", async () => {
const { app, dir } = appWithTmpSettings({ PI_PROVIDER: "zai", PI_MODEL: "glm-5.2", PI_THINKING: "medium" }, {
listModels: async () => [{ provider: "zai", id: "glm-5.2", name: "GLM 5.2", reasoning: true }],
});
@@ -29,8 +29,8 @@ test("GET /settings returns effective defaults (env provider/model/thinking, fir
const res = await app.inject({ method: "GET", url: "/settings" });
expect(res.statusCode).toBe(200);
const body = res.json();
expect(body.provider).toBe("zai");
expect(body.model).toBe("glm-5.2");
expect(body).not.toHaveProperty("provider");
expect(body).not.toHaveProperty("model");
expect(body.thinking).toBe("medium");
expect(typeof body.workspace).toBe("string"); // first workspace from ../harness/workspaces
} finally {
@@ -62,7 +62,9 @@ test("PUT /settings does not persist personal workspace or LLM choices", async (
});
expect(put.statusCode).toBe(200);
const got = await app.inject({ method: "GET", url: "/settings" });
expect(got.json()).toMatchObject({ provider: "zai", model: "glm-5.2", thinking: "medium" });
expect(got.json()).toMatchObject({ thinking: "medium" });
expect(got.json()).not.toHaveProperty("provider");
expect(got.json()).not.toHaveProperty("model");
expect(got.json()).not.toMatchObject({ workspace: "psd", thinking: "high" });
} finally {
rmSync(dir, { recursive: true, force: true });
@@ -114,7 +116,7 @@ test("settings no longer read or write principal-specific preferences", async ()
expect(preferences.size).toBe(0);
});
test("GET /settings retains complete legacy installation defaults without seeding a private profile", async () => {
test("GET /settings drops legacy installation model fields without seeding a private profile", async () => {
let preferences: Record<string, unknown> = {};
const writes: Record<string, unknown>[] = [];
const runner = {
@@ -135,9 +137,7 @@ test("GET /settings retains complete legacy installation defaults without seedin
const first = await app.inject({ method: "GET", url: "/settings" });
const second = await app.inject({ method: "GET", url: "/settings" });
const expected = {
workspace: "local", provider: "local-qwen", model: "qwen3.6-35b-a3b", thinking: "low",
};
const expected = { workspace: "local", thinking: "low" };
expect(first.statusCode).toBe(200);
expect(first.json()).toEqual(expected);
expect(second.json()).toEqual(expected);
@@ -167,15 +167,13 @@ test("GET /settings ignores stale private preferences in favor of installation d
const response = await app.inject({ method: "GET", url: "/settings" });
expect(response.statusCode).toBe(200);
expect(response.json()).toEqual({
workspace: "local", provider: "local-qwen", model: "qwen3.6-35b-a3b", thinking: "low",
});
expect(response.json()).toEqual({ workspace: "local", thinking: "low" });
} finally {
rmSync(dir, { recursive: true, force: true });
}
});
test("PUT /settings rejects an unknown model when a model list is available", async () => {
test("PUT /settings ignores a legacy unknown model because the catalog owns model validity", async () => {
const { app, dir } = appWithTmpSettings({}, {
listModels: async () => [{ provider: "zai", id: "glm-5.2", name: "GLM 5.2", reasoning: true }],
});
@@ -184,14 +182,14 @@ test("PUT /settings rejects an unknown model when a model list is available", as
method: "PUT", url: "/settings",
payload: { workspace: "psd", provider: "zai", model: "does-not-exist", thinking: "low" },
});
expect(put.statusCode).toBe(400);
expect(put.json()).toMatchObject({ error: expect.stringMatching(/model/i) });
expect(put.statusCode).toBe(200);
expect(put.json()).not.toHaveProperty("model");
} finally {
rmSync(dir, { recursive: true, force: true });
}
});
test("PUT /settings validates provider and model as one composite identifier", async () => {
test("PUT /settings ignores legacy provider/model pairs", async () => {
const { app, dir } = appWithTmpSettings({}, {
listModels: async () => [
{ provider: "provider-a", id: "shared-id", name: "A", reasoning: false },
@@ -204,7 +202,7 @@ test("PUT /settings validates provider and model as one composite identifier", a
workspace: "psd", provider: "provider-b", model: "shared-id", thinking: "low",
},
});
expect(wrongProvider.statusCode).toBe(400);
expect(wrongProvider.statusCode).toBe(200);
const exactPair = await app.inject({
method: "PUT", url: "/settings",
@@ -213,6 +211,8 @@ test("PUT /settings validates provider and model as one composite identifier", a
},
});
expect(exactPair.statusCode).toBe(200);
expect(exactPair.json()).not.toHaveProperty("provider");
expect(exactPair.json()).not.toHaveProperty("model");
} finally {
rmSync(dir, { recursive: true, force: true });
}
+25 -33
View File
@@ -1,4 +1,4 @@
import { test, expect, vi } from "vitest";
import { test, expect } from "vitest";
import Fastify from "fastify";
import { buildApp } from "../src/app.js";
import { loadConfig } from "../src/config.js";
@@ -156,12 +156,23 @@ test("registry-backed SQL preview resolves and uses the session's pinned runtime
// Workspace registry route coverage lives in routes-workspaces.test.ts. `/workspaces` no longer
// reads legacy harness files: the Git registry is the single shared source of truth.
test("GET /models returns {models:[...]} from injected listModels stub", async () => {
test("GET /models returns session choices from the installation model catalog", async () => {
const app = buildApp(loadConfig({ THT_HARNESS_DIR: "../harness" }), {
thtRunner: {} as any,
listModels: async () => [
{ provider: "zai", id: "glm-5.2", name: "GLM 5.2", reasoning: true },
],
runtimeModelCatalog: {
defaultSession: "zai/glm-5.2",
defaultMetadataGeneration: null,
embedding: { id: "ollama/qwen3-embedding:0.6b", dimensions: 1024 },
sessionModels: () => [{
id: "zai/glm-5.2", provider: "zai", model: "glm-5.2", label: "GLM 5.2",
upstreamModel: "glm-5.2", authentication: { mode: "pi_auth" },
sessionAdapter: { mode: "pi_builtin" }, session: { reasoning: true },
}],
metadataModels: () => [],
hasSession: (id: string) => id === "zai/glm-5.2",
},
// Runtime introspection is a health gate for starting a session, not a second catalog.
listModels: async () => { throw new Error("Pi is unavailable"); },
});
const res = await app.inject({ method: "GET", url: "/models" });
@@ -172,36 +183,17 @@ test("GET /models returns {models:[...]} from injected listModels stub", async (
});
});
test("GET /models returns {models:[]} when listModels throws (graceful fallback)", async () => {
test("GET /models returns an empty list when the catalog has no session models", async () => {
const app = buildApp(loadConfig({ THT_HARNESS_DIR: "../harness" }), {
thtRunner: {} as any,
listModels: async () => { throw new Error("Pi not running"); },
});
const res = await app.inject({ method: "GET", url: "/models" });
expect(res.statusCode).toBe(200);
expect(res.json()).toEqual({ models: [] });
});
test("GET /models logs a sanitized warning when listing fails", async () => {
const app = buildApp(loadConfig({ THT_HARNESS_DIR: "../harness" }), {
thtRunner: {} as any,
listModels: async () => { throw new Error("credential-value-must-not-appear"); },
});
const warn = vi.spyOn(app.log, "warn");
const res = await app.inject({ method: "GET", url: "/models" });
expect(res.json()).toEqual({ models: [] });
expect(JSON.stringify(warn.mock.calls)).not.toContain("credential-value-must-not-appear");
expect(warn).toHaveBeenCalled();
});
test("GET /models with empty listModels stub returns empty array", async () => {
const app = buildApp(loadConfig({ THT_HARNESS_DIR: "../harness" }), {
thtRunner: {} as any,
listModels: async () => [],
runtimeModelCatalog: {
defaultSession: null,
defaultMetadataGeneration: null,
embedding: null,
sessionModels: () => [],
metadataModels: () => [],
hasSession: () => false,
},
});
const res = await app.inject({ method: "GET", url: "/models" });
+3 -17
View File
@@ -14,7 +14,7 @@ import type { AuthDiagnoser, AuthDiagnostics } from "../src/auth/diagnostics.js"
const workspace: CanonicalWorkspace = {
workspace: {
schema_version: 3,
schema_version: 4,
id: "psd-clinical",
name: "Policlinico San Donato",
description: "Clinical analytics workspace",
@@ -26,20 +26,6 @@ const workspace: CanonicalWorkspace = {
schema: "datawarehouse",
supported_transports: ["postgres_direct"],
},
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: { allowed: ["zai/glm-5.2"] },
};
const revision: WorkspaceRevision = {
@@ -194,7 +180,7 @@ test("lists workspace summaries and reads a validated immutable workspace", asyn
expect(read.json()).toEqual({ workspace, revision });
});
test("validates a schema v3 workspace without mutating the repository", async () => {
test("validates a schema v4 workspace without mutating the repository", async () => {
const app = appFor(registryFake());
const response = await app.inject({
@@ -284,7 +270,7 @@ test.each([1, 2])("rejects schema v%s at the validation boundary with a sanitize
expect(response.body).not.toMatch(/migration_required|schema version/i);
});
test("runs diagnostics for a schema v3 workspace", async () => {
test("runs diagnostics for a schema v4 workspace", async () => {
const diagnose = vi.fn(async () => ({ activatable: true, diagnostics: [] }));
const app = appFor(registryFake(), diagnose);
+6 -6
View File
@@ -27,9 +27,9 @@ test("saveSettings writes the file and loadSettings reads it back", () => {
const dir = mkdtempSync(join(tmpdir(), "tht-set-"));
try {
const cfg = cfgWith(join(dir, "nested", "settings.json"));
const saved = saveSettings(cfg, { workspace: "psd", provider: "zai", model: "glm-5.2", thinking: "medium" });
expect(saved.model).toBe("glm-5.2");
expect(loadSettings(cfg)).toEqual({ workspace: "psd", provider: "zai", model: "glm-5.2", thinking: "medium" });
const saved = saveSettings(cfg, { workspace: "psd", thinking: "medium" });
expect(saved.thinking).toBe("medium");
expect(loadSettings(cfg)).toEqual({ workspace: "psd", thinking: "medium" });
} finally {
rmSync(dir, { recursive: true, force: true });
}
@@ -55,11 +55,11 @@ test("saveSettings restores the previous file when post-rename directory durabil
const dir = mkdtempSync(join(tmpdir(), "tht-set-transaction-"));
try {
const cfg = cfgWith(join(dir, "settings.json"));
saveSettings(cfg, { provider: "old", model: "old-model", thinking: "low" });
saveSettings(cfg, { thinking: "low" });
let syncs = 0;
expect(() => saveSettings(
cfg,
{ provider: "new", model: "new-model", thinking: "high" },
{ thinking: "high" },
{
syncDirectory(directory: string) {
syncs += 1;
@@ -69,7 +69,7 @@ test("saveSettings restores the previous file when post-rename directory durabil
},
},
)).toThrow(/directory fsync failure/);
expect(loadSettings(cfg)).toEqual({ provider: "old", model: "old-model", thinking: "low" });
expect(loadSettings(cfg)).toEqual({ thinking: "low" });
expect(syncs).toBeGreaterThanOrEqual(2);
} finally {
rmSync(dir, { recursive: true, force: true });
+1 -8
View File
@@ -8,18 +8,11 @@ const keywordIndexes = [
];
const workspace: CanonicalWorkspace = {
workspace: { schema_version: 3, id: "psd", name: "PSD", language: "it" },
workspace: { schema_version: 4, id: "psd", name: "PSD", language: "it" },
dwh: {
engine: "postgres", database: "warehouse", schema: "public",
supported_transports: ["postgres_direct"],
},
semantic_index: {
vector_store: { engine: "qdrant", collection: "psd", dimensions: 1024, distance: "cosine" },
embedding: {
provider: "ollama_internal", model: "qwen3-embedding:0.6b", dimensions: 1024,
},
},
llm_policy: { allowed: ["zai/glm-5.2"] },
};
function runner(request: (...args: any[]) => Promise<any>) {
@@ -19,12 +19,13 @@ afterEach(() => {
const semanticRuntime = {
internalQdrantUrl: "http://qdrant:6333",
internalEmbeddingUrl: "http://embedding:11434",
internalEmbeddingId: "ollama/qwen3-embedding:0.6b",
internalEmbeddingModel: "qwen3-embedding:0.6b",
internalEmbeddingDimensions: 1024,
};
const baseWorkspace = parseWorkspaceYaml(`workspace:
schema_version: 3
schema_version: 4
id: psd-clinical
name: Runtime Lease
language: en
@@ -33,21 +34,9 @@ dwh:
database: analytics
schema: mart
supported_transports: [postgres_direct]
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:
allowed: [zai/glm-5.2]
`);
const filesystemWorkspace = parseWorkspaceYaml(`${baseWorkspace ? '' : ''}workspace:
schema_version: 3
schema_version: 4
id: fs-workspace
name: Filesystem
language: en
@@ -56,25 +45,13 @@ dwh:
database: analytics
schema: mart
supported_transports: [postgres_direct]
semantic_index:
vector_store:
engine: qdrant
collection: fs-workspace
dimensions: 1024
distance: cosine
embedding:
provider: ollama_internal
model: qwen3-embedding:0.6b
dimensions: 1024
llm_policy:
allowed: [zai/glm-5.2]
evidence:
source:
type: filesystem
uri: fs-workspace/evidence
`);
const privateHttpWorkspace = parseWorkspaceYaml(`workspace:
schema_version: 3
schema_version: 4
id: http-workspace
name: Http
language: en
@@ -83,18 +60,6 @@ dwh:
database: analytics
schema: mart
supported_transports: [postgres_direct]
semantic_index:
vector_store:
engine: qdrant
collection: http-workspace
dimensions: 1024
distance: cosine
embedding:
provider: ollama_internal
model: qwen3-embedding:0.6b
dimensions: 1024
llm_policy:
allowed: [zai/glm-5.2]
evidence:
source:
type: http
@@ -125,7 +90,7 @@ function runtime(workspace = baseWorkspace, workspaceId = workspace.workspace.id
bindingDigest: "sha256:bindings",
semanticQdrantUrl: "http://qdrant:6333",
effectiveConfig: {
schemaVersion: 1,
schemaVersion: 2,
dwh: {
engine: "postgres",
database: "analytics",
@@ -136,7 +101,7 @@ function runtime(workspace = baseWorkspace, workspaceId = workspace.workspace.id
user: "reader",
},
vector: { collection: workspaceId, dimensions: 1024, distance: "cosine" },
embedding: { model: "qwen3-embedding:0.6b", dimensions: 1024 },
embedding: { id: "ollama/qwen3-embedding:0.6b", model: "qwen3-embedding:0.6b", dimensions: 1024 },
roots: { artifacts: "/data/artifacts", indexes: "/data/indexes" },
},
effectiveConfigIdentity: "workspace://psd-clinical@v1:" + "d".repeat(64),
@@ -28,13 +28,15 @@ test("job state creates durable 0600 JSON and enforces same-revision resume", as
catalogBlob: "c".repeat(40),
configDigest: "sha256:config",
bindingDigest: "sha256:bindings",
embeddingId: "ollama/qwen3-embedding:0.6b",
embeddingDimensions: 1024,
});
const path = store.jobPath(job.runId);
expect(existsSync(path)).toBe(true);
expect(statSync(path).mode & 0o777).toBe(0o600);
expect(JSON.parse(readFileSync(path, "utf8"))).toMatchObject({
schemaVersion: 1,
schemaVersion: 2,
operation: "preprocess dwh",
workspaceId: "psd-clinical",
workspaceRevision: "a".repeat(40),
@@ -42,6 +44,8 @@ test("job state creates durable 0600 JSON and enforces same-revision resume", as
catalogBlob: "c".repeat(40),
configDigest: "sha256:config",
bindingDigest: "sha256:bindings",
embeddingId: "ollama/qwen3-embedding:0.6b",
embeddingDimensions: 1024,
});
await expect(store.beginJob({
@@ -52,6 +56,20 @@ test("job state creates durable 0600 JSON and enforces same-revision resume", as
catalogBlob: "c".repeat(40),
configDigest: "sha256:config",
bindingDigest: "sha256:bindings",
embeddingId: "ollama/qwen3-embedding:0.6b",
embeddingDimensions: 1024,
})).rejects.toMatchObject({ code: "preprocessing_resume_mismatch" });
await expect(store.beginJob({
operation: "preprocess dwh",
runId: job.runId,
workspaceRevision: "a".repeat(40),
descriptorBlob: "b".repeat(40),
catalogBlob: "c".repeat(40),
configDigest: "sha256:config",
bindingDigest: "sha256:bindings",
embeddingId: "ollama/replacement-embedding",
embeddingDimensions: 1024,
})).rejects.toMatchObject({ code: "preprocessing_resume_mismatch" });
const resumed = await store.beginJob({
@@ -62,6 +80,8 @@ test("job state creates durable 0600 JSON and enforces same-revision resume", as
catalogBlob: "c".repeat(40),
configDigest: "sha256:config",
bindingDigest: "sha256:bindings",
embeddingId: "ollama/qwen3-embedding:0.6b",
embeddingDimensions: 1024,
});
expect(resumed.runId).toBe(job.runId);
});
@@ -75,10 +75,6 @@ function workspaceVariant(
return {
...workspace,
workspace: { ...workspace.workspace, ...changes, id },
semantic_index: {
...workspace.semantic_index,
vector_store: { ...workspace.semantic_index.vector_store, collection: id },
},
...(workspace.evidence?.source.type === "filesystem"
? {
evidence: {
@@ -182,7 +178,7 @@ test("shared deployment fixtures remain valid standalone descriptors with canoni
expect(smoke).toMatchObject({
workspace: {
schema_version: 3,
schema_version: 4,
id: "local",
name: "Local",
description: "Isolated workspace registry smoke fixture.",
@@ -193,14 +189,14 @@ test("shared deployment fixtures remain valid standalone descriptors with canoni
},
});
expect(task13).toMatchObject({
workspace: { schema_version: 3, id: "task13-smoke", name: "Task 13 Smoke" },
workspace: { schema_version: 4, id: "task13-smoke", name: "Task 13 Smoke" },
evidence: {
source: { type: "filesystem", uri: "task13-smoke/evidence", patterns: ["**/*.md"] },
policy: { max_chunk_chars: 4000, retain_published_generations: 3 },
},
});
expect(windows).toMatchObject({
workspace: { schema_version: 3, id: "task13-windows", name: "Task 13 Windows" },
workspace: { schema_version: 4, id: "task13-windows", name: "Task 13 Windows" },
evidence: {
source: { type: "filesystem", uri: "task13-windows/evidence", patterns: ["**/*.md"] },
policy: { max_chunk_chars: 4000, retain_published_generations: 3 },
@@ -282,7 +278,7 @@ test("registry rejects orphan descriptors, metadata mismatches, and the retired
});
});
test("Windows clone contract copies the shared complete schema v3 descriptor into the nested registry layout", () => {
test("Windows clone contract copies the shared complete schema v4 descriptor into the nested registry layout", () => {
const descriptor = parseWorkspaceYaml(readFixture("workspace-registry-windows.yaml"));
const windows = readFileSync(
new URL("../../scripts/test-windows-clone-contract.ps1", import.meta.url),
@@ -299,7 +295,7 @@ test("Windows clone contract copies the shared complete schema v3 descriptor int
expect(windows).not.toContain('schema_version: 3');
expect(descriptor).toMatchObject({
workspace: {
schema_version: 3,
schema_version: 4,
id: "task13-windows",
name: "Task 13 Windows",
language: "en",
+6 -57
View File
@@ -15,7 +15,7 @@ import {
import type { WorkspaceRegistryConfig } from "../src/workspaces/types.js";
const validYaml = `workspace:
schema_version: 3
schema_version: 4
id: psd-clinical
name: Policlinico San Donato
language: it
@@ -24,18 +24,6 @@ dwh:
database: postgres
schema: datawarehouse
supported_transports: [postgres_direct]
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:
allowed: [zai/glm-5.2]
`;
function withFilesystemEvidence(source: string, id = "psd-clinical"): string {
@@ -146,7 +134,7 @@ function legacyV1Yaml(source = validYaml): string {
.replace(" model: qwen3-embedding:0.6b", " model: nomic-embed-text-v2-moe")
.replace(" dimensions: 1024", " dimensions: 768")
.replace("distance: cosine\n", "distance: cosine\n supported_transports: [pgvector_direct]\n")
.replace("schema_version: 3", "schema_version: 1");
.replace("schema_version: 4", "schema_version: 1");
}
function legacyV2Yaml(source = validYaml): string {
@@ -158,7 +146,7 @@ function legacyV2Yaml(source = validYaml): string {
.replace(" model: qwen3-embedding:0.6b", " model: nomic-embed-text-v2-moe")
.replace(" dimensions: 1024", " dimensions: 768")
.replace("distance: cosine\n", "distance: cosine\n supported_transports: [pgvector_direct]\n")
.replace("schema_version: 3", "schema_version: 2");
.replace("schema_version: 4", "schema_version: 2");
}
const runFile = promisify(execFile);
@@ -197,7 +185,7 @@ async function fixture(workspaceSource = validYaml): Promise<{
await git(source, ["init", "--initial-branch=main"]);
await git(source, ["config", "user.name", "Workspace Registry Test"]);
await git(source, ["config", "user.email", "workspace-registry@example.invalid"]);
const workspace = workspaceSource.includes("schema_version: 3")
const workspace = workspaceSource.includes("schema_version: 4")
? parseWorkspaceYaml(workspaceSource) : undefined;
mkdirSync(join(source, "psd-clinical"), { recursive: true });
writeFileSync(join(source, "thoth-workspaces.yaml"), catalogYaml([
@@ -256,7 +244,7 @@ async function multiWorkspaceFixture(workspaces: Record<string, string>): Promis
await git(source, ["config", "user.email", "workspace-registry@example.invalid"]);
const entries = [];
for (const [id, workspaceSource] of Object.entries(workspaces)) {
const workspace = workspaceSource.includes("schema_version: 3") ? parseWorkspaceYaml(workspaceSource) : undefined;
const workspace = workspaceSource.includes("schema_version: 4") ? parseWorkspaceYaml(workspaceSource) : undefined;
entries.push({ id, name: workspace.workspace.name, ...(workspace.workspace.description ? { description: workspace.workspace.description } : {}) });
mkdirSync(join(source, id), { recursive: true });
writeFileSync(join(source, id, "workspace.yaml"), workspaceSource);
@@ -788,7 +776,7 @@ test("normalizes historical operational state during offline fallback after rest
expect(read.revision).not.toHaveProperty("state");
});
test("fails closed when a retained snapshot descriptor is not schema v3", async () => {
test("fails closed when a retained snapshot descriptor is not schema v4", async () => {
const remote = await fixture();
const root = join(remote.root, "registry");
await new WorkspaceRegistry(config(root, remote.remote)).bootstrap();
@@ -820,45 +808,6 @@ test("keeps the last valid snapshot when a pulled commit has invalid YAML", asyn
});
});
test("rejects duplicate schema v3 collection ownership and keeps the previous active snapshot", async () => {
const v3Yaml = validYaml;
const remote = await multiWorkspaceFixture({
"psd-clinical": v3Yaml,
"research-clinical": v3Yaml
.replace("id: psd-clinical", "id: research-clinical")
.replace("name: Policlinico San Donato", "name: Research Clinical")
.replace("collection: psd-clinical", "collection: research-clinical"),
});
const registry = new WorkspaceRegistry(config(join(remote.root, "registry"), remote.remote));
await registry.bootstrap();
writeFileSync(
join(remote.source, "research-clinical", "workspace.yaml"),
v3Yaml
.replace("id: psd-clinical", "id: research-clinical")
.replace("name: Policlinico San Donato", "name: Research Clinical")
.replace("collection: psd-clinical", "collection: shared"),
);
writeFileSync(
join(remote.source, "psd-clinical", "workspace.yaml"),
v3Yaml.replace("collection: psd-clinical", "collection: shared"),
);
await git(remote.source, ["add", "-A"]);
await git(remote.source, ["commit", "-m", "Duplicate collection ownership"]);
await git(remote.source, ["push", "origin", "main"]);
await expect(registry.pull()).rejects.toMatchObject({
code: "workspace_invalid",
message: "Workspace repository content is invalid",
});
await expect(registry.read("psd-clinical")).resolves.toMatchObject({
revision: { commit: remote.initialCommit },
});
await expect(registry.read("research-clinical")).resolves.toMatchObject({
revision: { commit: remote.initialCommit },
});
});
test("retains a historical snapshot while a resumable manifest still references its revision", async () => {
const remote = await fixture();
const root = join(remote.root, "registry");
@@ -66,7 +66,7 @@ workspaces: [{id: psd-clinical, name: Runtime Lease}]
`);
mkdirSync(join(source, "psd-clinical", "evidence"), { recursive: true });
writeFileSync(join(source, "psd-clinical", "workspace.yaml"), `workspace:
schema_version: 3
schema_version: 4
id: psd-clinical
name: Runtime Lease
language: en
@@ -75,18 +75,6 @@ dwh:
database: analytics
schema: mart
supported_transports: [postgres_direct]
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:
allowed: [zai/glm-5.2]
evidence:
source:
type: filesystem
+2 -14
View File
@@ -21,7 +21,7 @@ const thtBin = join(harnessDir, ".venv", "bin", "tht");
const roots: string[] = [];
const canonicalWorkspace = `workspace:
schema_version: 3
schema_version: 4
id: psd-clinical
name: Runtime handoff
language: en
@@ -30,18 +30,6 @@ dwh:
database: analytics
schema: mart
supported_transports: [postgres_direct]
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:
allowed: [zai/glm-5.2]
`;
const filesystemWorkspace = `${canonicalWorkspace}evidence:
@@ -145,7 +133,7 @@ function runnerFor(f: Awaited<ReturnType<typeof fixture>>): ThtRunner {
} as any);
}
test("real schema-v3 registry revision loads through ThtRunner and the harness contract", async () => {
test("real schema-v4 registry revision loads through ThtRunner and the harness contract", async () => {
const f = await fixture();
const runner = runnerFor(f);
@@ -12,8 +12,8 @@ import {
import { supportsSessionRuntime } from "../src/workspaces/bindings.js";
import { parseWorkspaceYaml } from "../src/workspaces/schema.js";
const workspaceV3 = parseWorkspaceYaml(`workspace:
schema_version: 3
const workspaceV4 = parseWorkspaceYaml(`workspace:
schema_version: 4
id: psd-clinical
name: Policlinico San Donato
language: it
@@ -22,19 +22,6 @@ dwh:
database: postgres
schema: datawarehouse
supported_transports: [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]
`);
const paths: RuntimePaths = {
sessions: "/data/workspaces/psd-clinical/sessions",
@@ -45,6 +32,7 @@ const paths: RuntimePaths = {
const semanticRuntime: SemanticRuntimeConfig = {
internalQdrantUrl: "http://qdrant:6333",
internalEmbeddingUrl: "http://embedding:11434",
internalEmbeddingId: "ollama/qwen3-embedding:0.6b",
internalEmbeddingModel: "qwen3-embedding:0.6b",
internalEmbeddingDimensions: 1024,
};
@@ -63,8 +51,8 @@ const directBindings: RuntimeBindings = {
evidence: { missing: [], values: {} },
};
test("renders only the schema-v3 internal Qdrant and Ollama runtime shape", () => {
const rendered = parse(renderRuntimeConfig(workspaceV3, directBindings, paths, {
test("derives the internal Qdrant and Ollama runtime shape from workspace v4 plus installation config", () => {
const rendered = parse(renderRuntimeConfig(workspaceV4, directBindings, paths, {
workspaceId: "psd-clinical", workspaceRevision: "a".repeat(40),
}, {}, semanticRuntime));
@@ -95,8 +83,8 @@ test("renders only the schema-v3 internal Qdrant and Ollama runtime shape", () =
expect(rendered).not.toHaveProperty("vector_rest");
});
test("renders schema-v3 DWH REST without exposing secret contents", () => {
const rendered = parse(renderRuntimeConfig(workspaceV3, {
test("renders workspace-v4 DWH REST without exposing secret contents", () => {
const rendered = parse(renderRuntimeConfig(workspaceV4, {
dwh: {
transport: "rest_api", missing: [], values: {
THT_WS_PSD_CLINICAL_DWH_BASE_URL: "https://dwh.example.test",
@@ -152,7 +140,7 @@ function evidenceWorkspace(
}
const canonicalEvidenceWorkspace = `workspace:
schema_version: 3
schema_version: 4
id: psd-clinical
name: Runtime Evidence
language: en
@@ -161,18 +149,6 @@ dwh:
database: analytics
schema: mart
supported_transports: [postgres_direct]
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:
allowed: [zai/glm-5.2]
`;
const evidenceRevision = "1".repeat(40);
@@ -374,7 +350,7 @@ test("renders static S3 Evidence with endpoint policy, limits, and file paths bu
test("omits Evidence configuration and policy when the descriptor has no Evidence", () => {
const rendered = parse(renderRuntimeConfig(
workspaceV3,
workspaceV4,
directBindings,
paths,
evidenceContext,
@@ -14,7 +14,7 @@ const roots: string[] = [];
function workspace(extra = "") {
return parseWorkspaceYaml(`workspace:
schema_version: 3
schema_version: 4
id: psd-clinical
name: Policlinico San Donato
language: en
@@ -23,10 +23,6 @@ dwh:
database: postgres
schema: datawarehouse
supported_transports: [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: { allowed: [zai/glm-5.2] }
${extra}`);
}
@@ -0,0 +1,36 @@
import { expect, test } from "vitest";
import { migrateWorkspaceV3Yaml, parseWorkspaceYaml } from "../src/workspaces/schema.js";
const legacy = `workspace:
schema_version: 3
id: abc
name: Example
language: en
dwh:
engine: postgres
database: warehouse
schema: public
supported_transports: [postgres_direct]
semantic_index:
vector_store: {engine: qdrant, collection: abc, dimensions: 1024, distance: cosine}
embedding: {provider: ollama_internal, model: qwen3-embedding:0.6b, dimensions: 1024}
llm_policy:
default: zai/glm-5.3
allowed: [zai/glm-5.3]
`;
test("strict workspace v4 rejects model-bearing v3 descriptors", () => {
expect(() => parseWorkspaceYaml(legacy)).toThrow();
});
test("v3 to v4 migration removes only model/vector policy and bumps the version", () => {
const migrated = migrateWorkspaceV3Yaml(legacy);
const workspace = parseWorkspaceYaml(migrated);
expect(workspace.workspace).toMatchObject({ schema_version: 4, id: "abc" });
expect(migrated).not.toMatch(/semantic_index|llm_policy/);
expect(workspace.dwh).toEqual({
engine: "postgres", database: "warehouse", schema: "public",
supported_transports: ["postgres_direct"],
});
});
+12 -28
View File
@@ -9,8 +9,8 @@ import {
} from "../src/workspaces/bindings.js";
import { parseWorkspaceYaml } from "../src/workspaces/schema.js";
const workspaceV3 = parseWorkspaceYaml(`workspace:
schema_version: 3
const workspaceV4 = parseWorkspaceYaml(`workspace:
schema_version: 4
id: psd-clinical
name: Policlinico San Donato
language: it
@@ -19,10 +19,6 @@ dwh:
database: postgres
schema: datawarehouse
supported_transports: [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: { allowed: [zai/glm-5.2] }
`);
const temporaryRoots: string[] = [];
@@ -40,9 +36,9 @@ function secretPath(name: string): { root: string; path: string } {
return { root: secrets, path };
}
test("resolves schema-v3 direct DWH bindings from the stable namespace", () => {
test("resolves workspace-v4 direct DWH bindings from the stable namespace", () => {
const password = secretPath("dwh-password");
const result = resolveBinding(workspaceV3, "DWH", {
const result = resolveBinding(workspaceV4, "DWH", {
THT_WS_PSD_CLINICAL_DWH_TRANSPORT: "postgres_direct",
THT_WS_PSD_CLINICAL_DWH_HOST: "dwh.internal",
THT_WS_PSD_CLINICAL_DWH_PORT: "5432",
@@ -61,14 +57,14 @@ test("resolves schema-v3 direct DWH bindings from the stable namespace", () => {
});
});
test("requires schema-v3 REST credentials unless the DWH diagnostic declares auth none", () => {
expect(resolveBinding(workspaceV3, "DWH", {
test("requires workspace-v4 REST credentials unless the DWH diagnostic declares auth none", () => {
expect(resolveBinding(workspaceV4, "DWH", {
THT_WS_PSD_CLINICAL_DWH_TRANSPORT: "rest_api",
THT_WS_PSD_CLINICAL_DWH_BASE_URL: "https://dwh.example.test",
}, []).missing).toContain("THT_WS_PSD_CLINICAL_DWH_API_KEY_FILE");
const noAuth = parseWorkspaceYaml(`workspace:
schema_version: 3
schema_version: 4
id: psd-clinical
name: No auth
language: en
@@ -77,16 +73,12 @@ dwh:
database: postgres
schema: public
supported_transports: [rest_api]
semantic_index:
vector_store: { engine: qdrant, collection: psd-clinical, dimensions: 1024, distance: cosine }
embedding: { provider: ollama_internal, model: qwen3-embedding:0.6b, dimensions: 1024 }
diagnostics:
dwh_rest:
method: GET
path: /health
auth: none
response: { database: database, schema: schema }
llm_policy: { allowed: [zai/glm-5.2] }
`);
expect(resolveBinding(noAuth, "DWH", {
THT_WS_PSD_CLINICAL_DWH_TRANSPORT: "rest_api",
@@ -98,7 +90,7 @@ test("rejects unsupported transports and secret paths outside configured roots",
const outside = secretPath("outside-password");
const allowed = secretPath("allowed-password");
const directOnly = parseWorkspaceYaml(`workspace:
schema_version: 3
schema_version: 4
id: psd-clinical
name: Direct only
language: en
@@ -107,15 +99,11 @@ dwh:
database: postgres
schema: public
supported_transports: [postgres_direct]
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: { allowed: [zai/glm-5.2] }
`);
expect(resolveBinding(directOnly, "DWH", {
THT_WS_PSD_CLINICAL_DWH_TRANSPORT: "rest_api",
}, []).missing).toContain("THT_WS_PSD_CLINICAL_DWH_TRANSPORT");
const result = resolveBinding(workspaceV3, "DWH", {
const result = resolveBinding(workspaceV4, "DWH", {
THT_WS_PSD_CLINICAL_DWH_TRANSPORT: "postgres_direct",
THT_WS_PSD_CLINICAL_DWH_HOST: "dwh.internal",
THT_WS_PSD_CLINICAL_DWH_PORT: "5432",
@@ -128,7 +116,7 @@ llm_policy: { allowed: [zai/glm-5.2] }
test("runtime bindings contain only DWH and Evidence roles", () => {
const password = secretPath("dwh-password");
const bindings = resolveRuntimeBindings(workspaceV3, {
const bindings = resolveRuntimeBindings(workspaceV4, {
THT_WS_PSD_CLINICAL_DWH_TRANSPORT: "postgres_direct",
THT_WS_PSD_CLINICAL_DWH_HOST: "dwh.internal",
THT_WS_PSD_CLINICAL_DWH_PORT: "5432",
@@ -143,7 +131,7 @@ test("runtime bindings contain only DWH and Evidence roles", () => {
function withEvidence(source: Record<string, unknown>) {
return parseWorkspaceYaml(`workspace:
schema_version: 3
schema_version: 4
id: psd-clinical
name: Policlinico San Donato
language: it
@@ -152,10 +140,6 @@ dwh:
database: postgres
schema: datawarehouse
supported_transports: [postgres_direct]
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: { allowed: [zai/glm-5.2] }
evidence:
source: ${JSON.stringify(source)}
`);
@@ -260,7 +244,7 @@ test("rejects relative, missing, directory, unreadable, and escaping symlink Evi
});
test("includes Evidence binding completeness in session runtime support without changing v3 compatibility", () => {
const unsigned = resolveRuntimeBindings(workspaceV3, {}, ["/run/secrets"]);
const unsigned = resolveRuntimeBindings(workspaceV4, {}, ["/run/secrets"]);
expect(unsigned.evidence).toEqual({ values: {}, missing: [] });
expect(supportsSessionRuntime(unsigned)).toBe(true);
+1 -5
View File
@@ -7,7 +7,7 @@ import {
} from "../src/workspaces/catalog.js";
const descriptor = parseWorkspaceYaml(`workspace:
schema_version: 3
schema_version: 4
id: psd
name: Policlinico San Donato
description: Clinical warehouse
@@ -17,10 +17,6 @@ dwh:
database: postgres
schema: datawarehouse
supported_transports: [rest_api]
semantic_index:
vector_store: { engine: qdrant, collection: psd, dimensions: 1024, distance: cosine }
embedding: { provider: ollama_internal, model: qwen3-embedding:0.6b, dimensions: 1024 }
llm_policy: { allowed: [zai/glm-5.2] }
`);
test("parses the strict ordered root catalog", () => {
+11 -20
View File
@@ -5,8 +5,8 @@ import { join } from "node:path";
import { buildInstallationContract, renderWorkspaceDocs } from "../src/workspaces/contracts.js";
import { type CanonicalWorkspace, parseWorkspaceYaml } from "../src/workspaces/schema.js";
const workspaceV3 = parseWorkspaceYaml(`workspace:
schema_version: 3
const workspaceV4 = parseWorkspaceYaml(`workspace:
schema_version: 4
id: psd-clinical
name: Policlinico San Donato
language: it
@@ -15,17 +15,12 @@ dwh:
database: postgres
schema: datawarehouse
supported_transports: [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:
allowed: [zai/glm-5.2]
`);
test("schema-v3 installation contracts expose only DWH bindings and no semantic variables", () => {
const contract = buildInstallationContract(workspaceV3);
test("workspace-v4 installation contracts expose only DWH bindings and no semantic variables", () => {
const contract = buildInstallationContract(workspaceV4);
const names = contract.variables.map((variable) => variable.name);
const docs = renderWorkspaceDocs(workspaceV3);
const docs = renderWorkspaceDocs(workspaceV4);
expect(contract.workspaceId).toBe("psd-clinical");
expect(contract.namespace).toBe("PSD_CLINICAL");
@@ -54,22 +49,22 @@ test.each([
test("validates public contract and documentation inputs at runtime", () => {
const unsafeWorkspace = {
...workspaceV3,
workspace: { ...workspaceV3.workspace, id: "psd\nclinical" },
...workspaceV4,
workspace: { ...workspaceV4.workspace, id: "psd\nclinical" },
} as CanonicalWorkspace;
expect(() => buildInstallationContract(unsafeWorkspace)).toThrow(/id/i);
expect(() => renderWorkspaceDocs(unsafeWorkspace)).toThrow(/id/i);
});
test("v3 installation contract omits external vector and embedding bindings", () => {
const contract = buildInstallationContract(workspaceV3);
test("v4 installation contract omits external vector and embedding bindings", () => {
const contract = buildInstallationContract(workspaceV4);
const names = contract.variables.map((variable) => variable.name);
expect(names).toContain("THT_WS_PSD_CLINICAL_DWH_TRANSPORT");
expect(names.some((name) => name.includes("_VECTOR_"))).toBe(false);
expect(names.some((name) => name.includes("_EMBEDDING_"))).toBe(false);
expect(renderWorkspaceDocs(workspaceV3).markdown).not.toContain("Embedding service");
expect(renderWorkspaceDocs(workspaceV4).markdown).not.toContain("Embedding service");
});
@@ -114,7 +109,7 @@ test.each([
function renderWorkspaceWithoutEvidence(): string {
return `workspace:
schema_version: 3
schema_version: 4
id: psd-clinical
name: Policlinico San Donato
language: it
@@ -123,10 +118,6 @@ dwh:
database: postgres
schema: datawarehouse
supported_transports: [postgres_direct]
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: { allowed: [zai/glm-5.2] }
`;
}
+6 -26
View File
@@ -12,7 +12,7 @@ import type { RuntimeBindings } from "../src/workspaces/runtime-renderer.js";
import { parseWorkspaceYaml, resolveDiagnosticUrl } from "../src/workspaces/schema.js";
const workspace = parseWorkspaceYaml(`workspace:
schema_version: 3
schema_version: 4
id: psd-clinical
name: Policlinico San Donato
language: it
@@ -22,18 +22,6 @@ dwh:
schema: datawarehouse
timeout_ms: 8000
supported_transports: [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:
allowed: [zai/glm-5.2]
`);
const bindings: RuntimeBindings = {
@@ -78,7 +66,7 @@ afterEach(() => {
vi.restoreAllMocks();
});
test("diagnoses schema-v3 DWH, internal Qdrant, and internal Ollama without semantic bindings", async () => {
test("diagnoses workspace-v4 DWH plus installation-derived Qdrant and Ollama", async () => {
const adapters = successfulAdapters();
const result = await diagnose(adapters)(workspace, bindings, { writeProbe: false });
@@ -139,7 +127,7 @@ test("reports only sanitized DWH and Evidence binding names before network diagn
expect(adapters.inspectQdrant).not.toHaveBeenCalled();
});
test("keeps schema-v3 DWH SSH diagnostic-only and runtime-inactive", async () => {
test("keeps workspace-v4 DWH SSH diagnostic-only and runtime-inactive", async () => {
const adapters = successfulAdapters();
const result = await diagnose(adapters)(workspace, {
...bindings,
@@ -152,9 +140,9 @@ test("keeps schema-v3 DWH SSH diagnostic-only and runtime-inactive", async () =>
expect(adapters.probeConnector).not.toHaveBeenCalled();
});
test("uses the schema-v3 declared DWH REST diagnostic and auth policy", async () => {
test("uses the workspace-v4 declared DWH REST diagnostic and auth policy", async () => {
const restWorkspace = parseWorkspaceYaml(`workspace:
schema_version: 3
schema_version: 4
id: psd-clinical
name: REST workspace
language: en
@@ -163,16 +151,12 @@ dwh:
database: warehouse
schema: datawarehouse
supported_transports: [rest_api]
semantic_index:
vector_store: { engine: qdrant, collection: psd-clinical, dimensions: 1024, distance: cosine }
embedding: { provider: ollama_internal, model: qwen3-embedding:0.6b, dimensions: 1024 }
diagnostics:
dwh_rest:
method: POST
path: /rpc/ping
auth: bearer
response: { database: database, schema: schema }
llm_policy: { allowed: [zai/glm-5.2] }
`);
const adapters = successfulAdapters();
const result = await diagnose(adapters)(restWorkspace, {
@@ -423,7 +407,7 @@ test("uses a REST secret only as a header and redacts it from failed diagnostics
const canary = "CANARY-REST-AUTH-SECRET";
await writeFile(credentialFile, canary);
const restDescriptor = parseWorkspaceYaml(`workspace:
schema_version: 3
schema_version: 4
id: psd-clinical
name: REST auth
language: en
@@ -432,16 +416,12 @@ dwh:
database: warehouse
schema: datawarehouse
supported_transports: [rest_api]
semantic_index:
vector_store: { engine: qdrant, collection: psd-clinical, dimensions: 1024, distance: cosine }
embedding: { provider: ollama_internal, model: qwen3-embedding:0.6b, dimensions: 1024 }
diagnostics:
dwh_rest:
method: GET
path: /health
auth: bearer
response: { database: database, schema: schema }
llm_policy: { allowed: [zai/glm-5.2] }
`);
const fetchMock = vi.fn()
.mockResolvedValueOnce(new Response("upstream CANARY-REST-AUTH-SECRET", { status: 503 }))
@@ -53,7 +53,7 @@ async function makeRepo(id: string, annotations: string | Buffer | "dir" | "syml
writeFileSync(join(source, "thoth-workspaces.yaml"),
`schema_version: 1\nworkspaces: [{id: ${id}, name: Workspace}]\n`);
mkdirSync(join(source, id, "schema"), { recursive: true });
writeFileSync(join(source, id, "workspace.yaml"), `workspace:\n schema_version: 3\n id: ${id}\n`);
writeFileSync(join(source, id, "workspace.yaml"), `workspace:\n schema_version: 4\n id: ${id}\n`);
const annotationsPath = join(source, id, "schema", "annotations.yaml");
if (annotations === "dir") {
mkdirSync(annotationsPath, { recursive: true });
+1 -1
View File
@@ -47,7 +47,7 @@ async function fixture(layout: EvidenceLayout): Promise<{ root: string; remote:
await git(source, ["config", "user.email", "evidence@example.invalid"]);
writeFileSync(join(source, "thoth-workspaces.yaml"), "schema_version: 1\nworkspaces: [{id: research, name: Research}]\n");
mkdirSync(join(source, "research"), { recursive: true });
writeFileSync(join(source, "research", "workspace.yaml"), "workspace:\n schema_version: 3\n id: research\n");
writeFileSync(join(source, "research", "workspace.yaml"), "workspace:\n schema_version: 4\n id: research\n");
const evidence = join(source, "research", "evidence");
if (layout === "tree") {
mkdirSync(join(evidence, "nested"), { recursive: true });
+1 -16
View File
@@ -12,7 +12,7 @@ import {
import type { WorkspaceRegistryConfig } from "../src/workspaces/types.js";
const validYaml = `workspace:
schema_version: 2
schema_version: 4
id: psd-clinical
name: Policlinico San Donato
language: it
@@ -21,21 +21,6 @@ dwh:
database: postgres
schema: datawarehouse
supported_transports: [postgres_direct]
semantic_index:
vector_store:
engine: pgvector
database: postgres
schema: vectors
collection: clinical_documents
dimensions: 768
distance: cosine
supported_transports: [pgvector_direct]
embedding:
provider: ollama_compatible
model: nomic-embed-text-v2-moe
dimensions: 768
llm_policy:
allowed: [zai/glm-5.2]
`;
const runFile = promisify(execFile);
@@ -13,20 +13,11 @@ import {
import { renderRuntimeConfig, type RuntimeBindings } from "../src/workspaces/runtime-renderer.js";
const unsupportedWorkspace = {
workspace: { schema_version: 2, id: "legacy-workspace", name: "Legacy", language: "en" },
workspace: { schema_version: 3, id: "legacy-workspace", name: "Legacy", language: "en" },
dwh: {
engine: "postgres", database: "warehouse", schema: "public",
supported_transports: ["postgres_direct"],
},
semantic_index: {
vector_store: {
engine: "pgvector", database: "warehouse", schema: "vectors",
collection: "documents", dimensions: 768, distance: "cosine",
supported_transports: ["pgvector_direct"],
},
embedding: { provider: "ollama_compatible", model: "legacy", dimensions: 768 },
},
llm_policy: { allowed: ["zai/glm-5.2"] },
};
const bindings: RuntimeBindings = {
@@ -40,31 +31,31 @@ const adapters: DiagnosticAdapters = {
probeEmbedding: vi.fn(),
};
test("renderer rejects callers that bypass the schema-v3 type contract", () => {
test("renderer rejects callers that bypass the schema-v4 type contract", () => {
expect(() => renderRuntimeConfig(unsupportedWorkspace as never, bindings, {
sessions: "/data/sessions", artifacts: "/data/artifacts", indexes: "/data/indexes",
})).toThrow("Runtime renderer supports only workspace schema version 3");
})).toThrow("Runtime renderer supports only workspace schema version 4");
});
test("installation contract rejects callers that bypass the schema-v3 type contract", () => {
test("installation contract rejects callers that bypass the schema-v4 type contract", () => {
expect(() => buildInstallationContract(unsupportedWorkspace as never))
.toThrow("Installation contract supports only workspace schema version 3");
.toThrow("Installation contract supports only workspace schema version 4");
});
test("binding entry points reject callers that bypass the schema-v3 type contract", () => {
test("binding entry points reject callers that bypass the schema-v4 type contract", () => {
expect(() => resolveBinding(unsupportedWorkspace as never, "DWH", {}, []))
.toThrow("Workspace bindings support only workspace schema version 3");
.toThrow("Workspace bindings support only workspace schema version 4");
expect(() => resolveEvidenceBinding(unsupportedWorkspace as never, {}, []))
.toThrow("Workspace bindings support only workspace schema version 3");
.toThrow("Workspace bindings support only workspace schema version 4");
expect(() => resolveRuntimeBindings(unsupportedWorkspace as never, {}, []))
.toThrow("Workspace bindings support only workspace schema version 3");
.toThrow("Workspace bindings support only workspace schema version 4");
});
test("diagnoser factories reject callers that bypass the schema-v3 type contract", async () => {
test("diagnoser factories reject callers that bypass the schema-v4 type contract", async () => {
await expect(createWorkspaceDiagnoser(adapters)(unsupportedWorkspace as never, bindings, {
writeProbe: false,
})).rejects.toThrow("Workspace diagnoser supports only workspace schema version 3");
})).rejects.toThrow("Workspace diagnoser supports only workspace schema version 4");
await expect(createProductionWorkspaceDiagnoser(5_000, adapters)(
unsupportedWorkspace as never, bindings, { writeProbe: false },
)).rejects.toThrow("Workspace diagnoser supports only workspace schema version 3");
)).rejects.toThrow("Workspace diagnoser supports only workspace schema version 4");
});
+17 -103
View File
@@ -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);
});
@@ -46,7 +46,7 @@ async function fixture(): Promise<{ root: string; remote: string; commit: string
await git(source, ["config", "user.email", "evidence-materializer@example.invalid"]);
writeFileSync(join(source, "thoth-workspaces.yaml"), "schema_version: 1\nworkspaces: [{id: research, name: Research}]\n");
mkdirSync(join(source, "research", "evidence", "nested"), { recursive: true });
writeFileSync(join(source, "research", "workspace.yaml"), "workspace:\n schema_version: 3\n id: research\n");
writeFileSync(join(source, "research", "workspace.yaml"), "workspace:\n schema_version: 4\n id: research\n");
writeFileSync(join(source, "research", "evidence", "guide.md"), "# guide\n");
writeFileSync(join(source, "research", "evidence", "nested", "deep.md"), "# deep\n");
await git(source, ["add", "-A"]);
@@ -102,7 +102,7 @@ test("refuses symlink-containing trees and bound violations without publishing",
await git(source, ["config", "user.email", "e@e.invalid"]);
writeFileSync(join(source, "thoth-workspaces.yaml"), "schema_version: 1\nworkspaces: [{id: research, name: Research}]\n");
mkdirSync(join(source, "research", "evidence"), { recursive: true });
writeFileSync(join(source, "research", "workspace.yaml"), "workspace:\n schema_version: 3\n id: research\n");
writeFileSync(join(source, "research", "workspace.yaml"), "workspace:\n schema_version: 4\n id: research\n");
writeFileSync(join(source, "research", "outside.md"), "# outside\n");
symlinkSync("../outside.md", join(source, "research", "evidence", "link.md"));
await git(source, ["add", "-A"]);