refactor(ai-roles): bake catalog URL at image build, drop local-fs source

The agent-roles catalog source is no longer hardcoded in app code and no
longer supports a local filesystem directory. The provider now fetches only
from an http(s):// base URL read from AI_AGENT_ROLES_CATALOG_URL; an empty or
non-http value yields a 502 (catalog unavailable). The default URL is baked
into the Docker image at build time and set per branch in CI.

- provider: drop readLocal + node:fs/node:path; readRelative requires http(s)
  and 502s otherwise; remote fetch/streaming-cap/SSRF guards unchanged.
- environment.service: keep AI_AGENT_ROLES_CATALOG_URL (default ''); comment
  updated to reflect build-time injection, remote-only.
- Dockerfile: add ARG+ENV AI_AGENT_ROLES_CATALOG_URL in the installer stage.
- CI: develop.yml builds with the develop raw URL; release.yml (both build
  steps) with the main raw URL.
- tests: replace local-fixture tests with remote-mock happy/malformed bundle
  tests and a non-http => 502 case; path-traversal block uses an https source.
- docs: update .env.example, CHANGELOG (#222), agent-roles-catalog/README.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

apps/server/src/core/ai-chat/roles/catalog/ai-agent-roles-catalog.provider.spec.ts

@@ -1,18 +1,14 @@
-import { promises as fs } from 'node:fs';
-import * as os from 'node:os';
-import * as path from 'node:path';
 import { BadGatewayException, BadRequestException } from '@nestjs/common';
 import { AiAgentRolesCatalogProvider } from './ai-agent-roles-catalog.provider';
 
 /**
- * Provider tests against a LOCAL fixture directory (no network). They cover the
- * happy read path (fetchIndex / fetchBundle), the malformed-shape rejection, a
- * missing file => unavailable, and — most importantly — the `^[a-z0-9-]+$`
- * path-traversal guard that runs BEFORE any path is built.
+ * Provider tests against a mocked remote source (no network). They cover the
+ * happy read path (fetchIndex / fetchBundle), the malformed-shape rejection,
+ * rejection of non-http(s) sources (local sources are gone), and — most
+ * importantly — the `^[a-z0-9-]+$` path-traversal guard that runs BEFORE any
+ * path/URL is built.
  */
-describe('AiAgentRolesCatalogProvider (local fixtures)', () => {
-  let dir: string;
-
+describe('AiAgentRolesCatalogProvider', () => {
   function makeProvider(source: string) {
     const env = {
       getAiAgentRolesCatalogSource: () => source,
@@ -20,96 +16,13 @@ describe('AiAgentRolesCatalogProvider (local fixtures)', () => {
     return new AiAgentRolesCatalogProvider(env as never);
   }
 
-  beforeAll(async () => {
-    dir = await fs.mkdtemp(path.join(os.tmpdir(), 'agent-roles-catalog-'));
-    await fs.writeFile(
-      path.join(dir, 'index.json'),
-      JSON.stringify({
-        schemaVersion: 1,
-        bundles: [
-          {
-            id: 'general',
-            name: { en: 'General', ru: 'Общие' },
-            languages: ['en'],
-            roles: [{ slug: 'researcher', version: 2 }],
-          },
-        ],
-      }),
-      'utf8',
-    );
-    await fs.mkdir(path.join(dir, 'bundles', 'general'), { recursive: true });
-    await fs.writeFile(
-      path.join(dir, 'bundles', 'general', 'en.json'),
-      JSON.stringify({
-        schemaVersion: 1,
-        language: 'en',
-        roles: [
-          {
-            slug: 'researcher',
-            name: 'Researcher',
-            instructions: 'be a researcher',
-          },
-        ],
-      }),
-      'utf8',
-    );
-    // A malformed bundle (a role missing `instructions`) to test rejection.
-    await fs.writeFile(
-      path.join(dir, 'bundles', 'general', 'fr.json'),
-      JSON.stringify({
-        schemaVersion: 1,
-        language: 'fr',
-        roles: [{ slug: 'researcher', name: 'Chercheur' }],
-      }),
-      'utf8',
-    );
-  });
-
-  afterAll(async () => {
-    await fs.rm(dir, { recursive: true, force: true });
-  });
-
-  it('fetchIndex reads + validates index.json', async () => {
-    const provider = makeProvider(dir);
-    const index = await provider.fetchIndex();
-    expect(index.schemaVersion).toBe(1);
-    expect(index.bundles[0].id).toBe('general');
-    expect(index.bundles[0].roles[0]).toEqual({
-      slug: 'researcher',
-      version: 2,
-    });
-  });
-
-  it('fetchBundle reads + validates a language file', async () => {
-    const provider = makeProvider(dir);
-    const bundle = await provider.fetchBundle('general', 'en');
-    expect(bundle.language).toBe('en');
-    expect(bundle.roles[0].slug).toBe('researcher');
-    expect(bundle.roles[0].instructions).toBe('be a researcher');
-  });
-
-  it('malformed bundle (missing instructions) => BadGateway', async () => {
-    const provider = makeProvider(dir);
-    await expect(provider.fetchBundle('general', 'fr')).rejects.toBeInstanceOf(
-      BadGatewayException,
-    );
-  });
-
-  it('missing file => BadGateway (unavailable)', async () => {
-    const provider = makeProvider(dir);
-    await expect(
-      provider.fetchBundle('general', 'de'),
-    ).rejects.toBeInstanceOf(BadGatewayException);
-  });
-
-  it('empty source resolves to the in-repo folder (no throw building the path)', async () => {
-    // With an empty source the provider targets ./agent-roles-catalog under the
-    // cwd; that folder is created by a separate task, so a read here surfaces as
-    // BadGateway (unavailable) rather than a path-build error.
-    const provider = makeProvider('');
-    await expect(provider.fetchIndex()).rejects.toBeInstanceOf(
-      BadGatewayException,
-    );
+  it('non-http(s) source => BadGateway (local sources removed)', async () => {
+    for (const source of ['', '/var/lib/agent-roles-catalog', './agent-roles-catalog']) {
+      const provider = makeProvider(source);
+      await expect(provider.fetchIndex()).rejects.toBeInstanceOf(
+        BadGatewayException,
+      );
+    }
   });
 
   describe('remote fetch streaming size cap', () => {
@@ -157,6 +70,43 @@ describe('AiAgentRolesCatalogProvider (local fixtures)', () => {
       } as unknown as Response;
     }
 
+    it('fetchBundle remote happy path => parses + validates', async () => {
+      const json = JSON.stringify({
+        schemaVersion: 1,
+        language: 'en',
+        roles: [
+          {
+            slug: 'researcher',
+            name: 'Researcher',
+            instructions: 'be a researcher',
+          },
+        ],
+      });
+      const body = streamOf([new TextEncoder().encode(json)]);
+      global.fetch = jest
+        .fn()
+        .mockResolvedValue(mockResponse({ body })) as never;
+      const provider = makeProvider('https://catalog.example.com');
+      const bundle = await provider.fetchBundle('general', 'en');
+      expect(bundle.roles[0].slug).toBe('researcher');
+    });
+
+    it('fetchBundle remote malformed (role missing instructions) => BadGateway', async () => {
+      const json = JSON.stringify({
+        schemaVersion: 1,
+        language: 'fr',
+        roles: [{ slug: 'researcher', name: 'Chercheur' }],
+      });
+      const body = streamOf([new TextEncoder().encode(json)]);
+      global.fetch = jest
+        .fn()
+        .mockResolvedValue(mockResponse({ body })) as never;
+      const provider = makeProvider('https://catalog.example.com');
+      await expect(provider.fetchBundle('general', 'fr')).rejects.toBeInstanceOf(
+        BadGatewayException,
+      );
+    });
+
     it('declared Content-Length over the cap => BadGateway before reading the body', async () => {
       global.fetch = jest.fn().mockResolvedValue(
         mockResponse({
@@ -340,14 +290,14 @@ describe('AiAgentRolesCatalogProvider (local fixtures)', () => {
 
     for (const value of bad) {
       it(`rejects bundleId="${value}" with BadRequest`, async () => {
-        const provider = makeProvider(dir);
+        const provider = makeProvider('https://catalog.example.com');
         await expect(
           provider.fetchBundle(value, 'en'),
         ).rejects.toBeInstanceOf(BadRequestException);
       });
 
       it(`rejects language="${value}" with BadRequest`, async () => {
-        const provider = makeProvider(dir);
+        const provider = makeProvider('https://catalog.example.com');
         await expect(
           provider.fetchBundle('general', value),
         ).rejects.toBeInstanceOf(BadRequestException);

apps/server/src/core/ai-chat/roles/catalog/ai-agent-roles-catalog.provider.ts

@@ -1,5 +1,3 @@
-import { promises as fs } from 'node:fs';
-import * as path from 'node:path';
 import {
   BadGatewayException,
   BadRequestException,
@@ -26,9 +24,9 @@ const MAX_BYTES = 1_000_000;
 
 /**
  * Fetches + validates the agent-roles catalog from its configured source. The
- * source location (EnvironmentService.getAiAgentRolesCatalogSource()) is either
- * an http(s):// base URL (REMOTE) or a local filesystem directory (LOCAL; the
- * empty default resolves to the in-repo `agent-roles-catalog/` folder).
+ * source (EnvironmentService.getAiAgentRolesCatalogSource()) is an http(s)://
+ * base URL — REMOTE only; local-filesystem sources are no longer supported. The
+ * value is baked into the Docker image at build time (set per-branch in CI).
  *
  * The catalog is UNTRUSTED input: every file is JSON-parsed and run through a
  * hand-written type guard before any field is exposed, and every dynamic path
@@ -91,31 +89,20 @@ export class AiAgentRolesCatalogProvider {
     }
   }
 
-  /** Read a relative catalog path as text from the configured source. */
+  /** Read a relative catalog path as text from the configured remote source. */
   private async readRelative(rel: string): Promise<string> {
     const source = this.environmentService
       .getAiAgentRolesCatalogSource()
       .trim();
-    if (/^https?:\/\//i.test(source)) {
-      return this.fetchRemote(source, rel);
-    }
-    const dir = source || path.join(process.cwd(), 'agent-roles-catalog');
-    return this.readLocal(dir, rel);
-  }
-
-  /** Read a local catalog file. Missing => the catalog is unavailable. */
-  private async readLocal(dir: string, rel: string): Promise<string> {
-    try {
-      return await fs.readFile(path.join(dir, rel), 'utf8');
-    } catch (err) {
-      const reason = shortError(err);
+    if (!/^https?:\/\//i.test(source)) {
       this.logger.error(
-        `Agent roles catalog local read failed (${path.join(dir, rel)}): ${reason}`,
+        'Agent roles catalog source is not configured (expected an http(s):// base URL)',
       );
       throw new BadGatewayException(
-        `Agent roles catalog is unavailable: ${reason}`,
+        'Agent roles catalog is unavailable: source is not configured',
       );
     }
+    return this.fetchRemote(source, rel);
   }
 
   /**

apps/server/src/integrations/environment/environment.service.ts

@@ -290,11 +290,12 @@ export class EnvironmentService {
   // ai_provider_credentials, with no env fallback. APP_SECRET stays (getAppSecret).
 
   getAiAgentRolesCatalogSource(): string {
-    // Catalog location. http(s):// URL => fetched remotely; anything else => a
-    // local filesystem directory. Defaults to the in-repo folder (dev). In prod
-    // set this to the raw GitHub base URL of the catalog repo. Unlike the AI_*
-    // getters above this is INFRA config (where the catalog lives), not
-    // provider/model config — so an env var here is appropriate.
+    // Catalog location: an http(s):// base URL the catalog is fetched from.
+    // The value is baked into the image at build time (Dockerfile ARG
+    // AI_AGENT_ROLES_CATALOG_URL, set per-branch in CI); local-filesystem
+    // sources are no longer supported. Empty/unset => the catalog is
+    // unavailable (the provider returns 502). This is INFRA config (where the
+    // catalog lives), not provider/model config, so an env var is appropriate.
     return this.configService.get<string>('AI_AGENT_ROLES_CATALOG_URL', '');
   }