fix(fleet): raise fleet-personas.spec timeout to 30s (mirror #665) (#677)

apps/gateway/src/federation/client/__tests__/query-source.service.spec.ts

@@ -0,0 +1,255 @@
+import 'reflect-metadata';
+import { describe, expect, it, vi } from 'vitest';
+import type { Db } from '@mosaicstack/db';
+import type { FederationListResponse } from '@mosaicstack/types';
+import {
+  FederationClientError,
+  type FederationClientService,
+} from '../federation-client.service.js';
+import { type QuerySourceError, QuerySourceService } from '../query-source.service.js';
+
+interface TestRow {
+  id: string;
+  title: string;
+}
+
+interface PeerRow {
+  id: string;
+  commonName: string;
+  endpointUrl: string | null;
+  clientKeyPem: string | null;
+  state: 'active' | 'pending' | 'suspended' | 'revoked';
+}
+
+const LOCAL_ROWS: TestRow[] = [
+  { id: 'local-1', title: 'Local One' },
+  { id: 'local-2', title: 'Local Two' },
+];
+
+const PEER_A: PeerRow = {
+  id: 'aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa',
+  commonName: 'peer-a',
+  endpointUrl: 'https://peer-a.example.com',
+  clientKeyPem: 'sealed-key-a',
+  state: 'active',
+};
+
+const PEER_B: PeerRow = {
+  id: 'bbbbbbbb-bbbb-bbbb-bbbb-bbbbbbbbbbbb',
+  commonName: 'peer-b',
+  endpointUrl: 'https://peer-b.example.com',
+  clientKeyPem: 'sealed-key-b',
+  state: 'active',
+};
+
+const PEER_LOCALHOST: PeerRow = {
+  id: 'cccccccc-cccc-cccc-cccc-cccccccccccc',
+  commonName: 'peer-localhost',
+  endpointUrl: 'https://localhost:3001',
+  clientKeyPem: 'sealed-key-c',
+  state: 'active',
+};
+
+function makeDb(activePeers: PeerRow[]): Db {
+  const orderBy = vi.fn().mockResolvedValue(activePeers);
+  const where = vi.fn().mockReturnValue({ orderBy });
+  const from = vi.fn().mockReturnValue({ where });
+  const select = vi.fn().mockReturnValue({ from });
+
+  return {
+    select,
+    insert: vi.fn(),
+    update: vi.fn(),
+    delete: vi.fn(),
+    transaction: vi.fn(),
+  } as unknown as Db;
+}
+
+function makeFederationClient(
+  list: (
+    peerId: string,
+    resource: string,
+    request: Record<string, unknown>,
+  ) => Promise<FederationListResponse<TestRow>>,
+): FederationClientService {
+  return {
+    list: list as unknown as FederationClientService['list'],
+  } as FederationClientService;
+}
+
+function makeLocalResponse(rows: TestRow[] = LOCAL_ROWS): Promise<FederationListResponse<TestRow>> {
+  return Promise.resolve({ items: rows });
+}
+
+describe('QuerySourceService', () => {
+  it('routes source="local" to the local executor and tags rows as local', async () => {
+    const list = vi.fn(async (): Promise<FederationListResponse<TestRow>> => ({ items: [] }));
+    const service = new QuerySourceService(makeDb([PEER_A]), makeFederationClient(list));
+
+    const result = await service.list<TestRow>({
+      source: 'local',
+      resource: 'tasks',
+      request: { cursor: 'ignored-for-local-test' },
+      local: () => makeLocalResponse(),
+    });
+
+    expect(result).toEqual({
+      items: [
+        { id: 'local-1', title: 'Local One', _source: 'local' },
+        { id: 'local-2', title: 'Local Two', _source: 'local' },
+      ],
+    });
+    expect(list).not.toHaveBeenCalled();
+  });
+
+  it('routes source="federated:<host>" to the matching active peer and tags rows with peer commonName', async () => {
+    const list = vi.fn(
+      async (): Promise<FederationListResponse<TestRow>> => ({
+        items: [{ id: 'remote-1', title: 'Remote One' }],
+      }),
+    );
+    const service = new QuerySourceService(makeDb([PEER_A, PEER_B]), makeFederationClient(list));
+
+    const result = await service.list<TestRow>({
+      source: 'federated:peer-b.example.com',
+      resource: 'tasks',
+      request: { status: 'open' },
+      local: () => makeLocalResponse(),
+    });
+
+    expect(result).toEqual({
+      items: [{ id: 'remote-1', title: 'Remote One', _source: 'peer-b' }],
+    });
+    expect(list).toHaveBeenCalledWith(PEER_B.id, 'tasks', { status: 'open' });
+  });
+
+  it('matches federated hosts by endpoint host including non-default port', async () => {
+    const list = vi.fn(
+      async (): Promise<FederationListResponse<TestRow>> => ({
+        items: [{ id: 'remote-port', title: 'Remote Port' }],
+      }),
+    );
+    const service = new QuerySourceService(makeDb([PEER_LOCALHOST]), makeFederationClient(list));
+
+    const result = await service.list<TestRow>({
+      source: 'federated:localhost:3001',
+      resource: 'tasks',
+      request: {},
+      local: () => makeLocalResponse(),
+    });
+
+    expect(result).toEqual({
+      items: [{ id: 'remote-port', title: 'Remote Port', _source: 'peer-localhost' }],
+    });
+    expect(list).toHaveBeenCalledWith(PEER_LOCALHOST.id, 'tasks', {});
+  });
+
+  it('fans out source="all" to local plus every active outbound peer in parallel and merges tagged rows', async () => {
+    const callOrder: string[] = [];
+    const list = vi.fn(async (peerId: string): Promise<FederationListResponse<TestRow>> => {
+      callOrder.push(`remote-start:${peerId}`);
+      await Promise.resolve();
+      return {
+        items: [{ id: `remote-${peerId.slice(0, 1)}`, title: `Remote ${peerId.slice(0, 1)}` }],
+      };
+    });
+    const service = new QuerySourceService(makeDb([PEER_A, PEER_B]), makeFederationClient(list));
+
+    const result = await service.list<TestRow>({
+      source: 'all',
+      resource: 'tasks',
+      request: { limit: 25 },
+      local: async () => {
+        callOrder.push('local-start');
+        await Promise.resolve();
+        return { items: [{ id: 'local-1', title: 'Local One' }] };
+      },
+    });
+
+    expect(result).toEqual({
+      items: [
+        { id: 'local-1', title: 'Local One', _source: 'local' },
+        { id: 'remote-a', title: 'Remote a', _source: 'peer-a' },
+        { id: 'remote-b', title: 'Remote b', _source: 'peer-b' },
+      ],
+    });
+    expect(list).toHaveBeenCalledTimes(2);
+    expect(callOrder).toEqual([
+      'local-start',
+      `remote-start:${PEER_A.id}`,
+      `remote-start:${PEER_B.id}`,
+    ]);
+  });
+
+  it('marks source="all" as partial and truncated when any subquery returns a cursor', async () => {
+    const list = vi.fn(
+      async (): Promise<FederationListResponse<TestRow>> => ({
+        items: [{ id: 'remote-a', title: 'Remote A' }],
+        nextCursor: 'remote-next',
+      }),
+    );
+    const service = new QuerySourceService(makeDb([PEER_A]), makeFederationClient(list));
+
+    const result = await service.list<TestRow>({
+      source: 'all',
+      resource: 'tasks',
+      request: {},
+      local: () => makeLocalResponse([{ id: 'local-1', title: 'Local One' }]),
+    });
+
+    expect(result).toEqual({
+      items: [
+        { id: 'local-1', title: 'Local One', _source: 'local' },
+        { id: 'remote-a', title: 'Remote A', _source: 'peer-a' },
+      ],
+      _partial: true,
+      _truncated: true,
+    });
+  });
+
+  it('returns _partial=true for source="all" when one peer fails without dropping successful sources', async () => {
+    const list = vi.fn(async (peerId: string): Promise<FederationListResponse<TestRow>> => {
+      if (peerId === PEER_B.id) {
+        throw new FederationClientError({
+          code: 'NETWORK',
+          message: 'peer unavailable',
+          peerId,
+        });
+      }
+      return { items: [{ id: 'remote-a', title: 'Remote A' }] };
+    });
+    const service = new QuerySourceService(makeDb([PEER_A, PEER_B]), makeFederationClient(list));
+
+    const result = await service.list<TestRow>({
+      source: 'all',
+      resource: 'tasks',
+      request: {},
+      local: () => makeLocalResponse([{ id: 'local-1', title: 'Local One' }]),
+    });
+
+    expect(result).toEqual({
+      items: [
+        { id: 'local-1', title: 'Local One', _source: 'local' },
+        { id: 'remote-a', title: 'Remote A', _source: 'peer-a' },
+      ],
+      _partial: true,
+    });
+  });
+
+  it('throws QuerySourceError when a federated host does not match an active outbound peer', async () => {
+    const list = vi.fn(async (): Promise<FederationListResponse<TestRow>> => ({ items: [] }));
+    const service = new QuerySourceService(makeDb([PEER_A]), makeFederationClient(list));
+
+    await expect(
+      service.list<TestRow>({
+        source: 'federated:missing.example.com',
+        resource: 'tasks',
+        request: {},
+        local: () => makeLocalResponse(),
+      }),
+    ).rejects.toMatchObject({
+      name: 'QuerySourceError',
+      code: 'PEER_NOT_FOUND',
+    } satisfies Partial<QuerySourceError>);
+  });
+});

apps/gateway/src/federation/client/index.ts

@@ -11,3 +11,13 @@ export {
   type FederationClientErrorCode,
   type FederationClientErrorOptions,
 } from './federation-client.service.js';
+export {
+  QuerySourceService,
+  QuerySourceError,
+  type QuerySource,
+  type QuerySourceErrorCode,
+  type QuerySourceErrorOptions,
+  type QuerySourceListOptions,
+  type QuerySourceListResponse,
+  type LocalListExecutor,
+} from './query-source.service.js';

apps/gateway/src/federation/client/query-source.service.ts

@@ -0,0 +1,261 @@
+/**
+ * QuerySourceService — gateway query source router (FED-M3-09).
+ *
+ * Accepts the federation query-layer `source` selector and routes list-style
+ * reads to local storage, one federated peer, or all active outbound peers.
+ *
+ * `source: "all"` is intentionally tolerant of per-peer failures: local data
+ * and successful peer responses are returned, and the envelope is marked
+ * `_partial: true`.  Local failures still reject because there is no safe local
+ * fallback and the gateway's own storage is expected to be authoritative.
+ */
+
+import { Inject, Injectable, Logger } from '@nestjs/common';
+import { and, eq, federationPeers, isNotNull, type Db } from '@mosaicstack/db';
+import {
+  SOURCE_LOCAL,
+  tagWithSource,
+  type FederationListResponse,
+  type SourceTag,
+} from '@mosaicstack/types';
+import { DB } from '../../database/database.module.js';
+import { FederationClientService } from './federation-client.service.js';
+
+export type QuerySource = 'local' | 'all' | `federated:${string}`;
+
+export type QuerySourceErrorCode = 'INVALID_SOURCE' | 'PEER_NOT_FOUND';
+
+export interface QuerySourceErrorOptions {
+  code: QuerySourceErrorCode;
+  message: string;
+  source: string;
+}
+
+export class QuerySourceError extends Error {
+  readonly code: QuerySourceErrorCode;
+  readonly source: string;
+
+  constructor(opts: QuerySourceErrorOptions) {
+    super(opts.message);
+    this.name = 'QuerySourceError';
+    this.code = opts.code;
+    this.source = opts.source;
+  }
+}
+
+export type LocalListExecutor<T extends object> = () => Promise<FederationListResponse<T> | T[]>;
+
+export interface QuerySourceListOptions<T extends object> {
+  source: QuerySource;
+  resource: string;
+  request?: Record<string, unknown>;
+  local: LocalListExecutor<T>;
+}
+
+export type QuerySourceListResponse<T extends object> = FederationListResponse<T & SourceTag>;
+
+interface OutboundPeer {
+  id: string;
+  commonName: string;
+  endpointUrl: string;
+}
+
+interface TaggedList<T extends object> {
+  items: Array<T & SourceTag>;
+  partial: boolean;
+  truncated: boolean;
+  nextCursor?: string;
+}
+
+@Injectable()
+export class QuerySourceService {
+  private readonly logger = new Logger(QuerySourceService.name);
+
+  constructor(
+    @Inject(DB) private readonly db: Db,
+    @Inject(FederationClientService) private readonly federationClient: FederationClientService,
+  ) {}
+
+  async list<T extends object>(
+    options: QuerySourceListOptions<T>,
+  ): Promise<QuerySourceListResponse<T>> {
+    const request = options.request ?? {};
+
+    if (options.source === 'local') {
+      const local = await this.runLocal(options.local);
+      return this.toResponse(this.tagList(local, SOURCE_LOCAL));
+    }
+
+    if (options.source === 'all') {
+      return this.listAll(options.resource, request, options.local);
+    }
+
+    if (options.source.startsWith('federated:')) {
+      const host = options.source.slice('federated:'.length).trim();
+      if (!host) {
+        throw new QuerySourceError({
+          code: 'INVALID_SOURCE',
+          message: 'Federated source must include a host after federated:',
+          source: options.source,
+        });
+      }
+
+      const peer = await this.findPeerByHost(host, options.source);
+      const remote = await this.federationClient.list<T>(peer.id, options.resource, request);
+      return this.toResponse(this.tagList(remote, peer.commonName));
+    }
+
+    throw new QuerySourceError({
+      code: 'INVALID_SOURCE',
+      message: `Unsupported query source: ${options.source}`,
+      source: options.source,
+    });
+  }
+
+  private async listAll<T extends object>(
+    resource: string,
+    request: Record<string, unknown>,
+    local: LocalListExecutor<T>,
+  ): Promise<QuerySourceListResponse<T>> {
+    const peers = await this.listActiveOutboundPeers();
+
+    const localPromise = this.runLocal(local).then((response) =>
+      this.tagList(response, SOURCE_LOCAL),
+    );
+    const remotePromises = peers.map(async (peer: OutboundPeer): Promise<TaggedList<T> | null> => {
+      try {
+        const response = await this.federationClient.list<T>(peer.id, resource, request);
+        return this.tagList(response, peer.commonName);
+      } catch (error: unknown) {
+        this.logger.warn(
+          `Federated query to peer ${peer.commonName} (${peer.id}) failed; returning partial all-source response: ${
+            error instanceof Error ? error.message : String(error)
+          }`,
+        );
+        return null;
+      }
+    });
+
+    const [localResult, ...remoteResults] = await Promise.all([localPromise, ...remotePromises]);
+    const successfulRemoteResults = remoteResults.filter(
+      (result: TaggedList<T> | null): result is TaggedList<T> => result !== null,
+    );
+    const allResults = [localResult, ...successfulRemoteResults];
+    const peerFailure = successfulRemoteResults.length !== peers.length;
+
+    return this.mergeTaggedLists(allResults, peerFailure);
+  }
+
+  private async runLocal<T extends object>(
+    local: LocalListExecutor<T>,
+  ): Promise<FederationListResponse<T>> {
+    const response = await local();
+    if (Array.isArray(response)) {
+      return { items: response };
+    }
+    return response;
+  }
+
+  private tagList<T extends object>(
+    response: FederationListResponse<T>,
+    source: string,
+  ): TaggedList<T> {
+    return {
+      items: tagWithSource(response.items, source),
+      partial: response._partial === true,
+      truncated: response._truncated === true || response.nextCursor !== undefined,
+      nextCursor: response.nextCursor,
+    };
+  }
+
+  private mergeTaggedLists<T extends object>(
+    lists: Array<TaggedList<T>>,
+    peerFailure: boolean,
+  ): QuerySourceListResponse<T> {
+    const items = lists.flatMap((list: TaggedList<T>) => list.items);
+    const partial =
+      peerFailure ||
+      lists.some((list: TaggedList<T>) => list.partial || list.nextCursor !== undefined);
+    const truncated = lists.some((list: TaggedList<T>) => list.truncated);
+
+    const response: QuerySourceListResponse<T> = { items };
+    if (partial) {
+      response._partial = true;
+    }
+    if (truncated) {
+      response._truncated = true;
+    }
+    return response;
+  }
+
+  private toResponse<T extends object>(tagged: TaggedList<T>): QuerySourceListResponse<T> {
+    const response: QuerySourceListResponse<T> = {
+      items: tagged.items,
+    };
+    if (tagged.nextCursor !== undefined) {
+      response.nextCursor = tagged.nextCursor;
+    }
+    if (tagged.partial) {
+      response._partial = true;
+    }
+    if (tagged.truncated) {
+      response._truncated = true;
+    }
+    return response;
+  }
+
+  private async findPeerByHost(sourceHost: string, source: string): Promise<OutboundPeer> {
+    const host = normalizeHost(sourceHost);
+    const peers = await this.listActiveOutboundPeers();
+    const peer = peers.find((candidate: OutboundPeer) => {
+      const commonName = normalizeHost(candidate.commonName);
+      const endpointHosts = endpointHostKeys(candidate.endpointUrl).map((endpointHost: string) =>
+        normalizeHost(endpointHost),
+      );
+      return commonName === host || endpointHosts.includes(host);
+    });
+
+    if (!peer) {
+      throw new QuerySourceError({
+        code: 'PEER_NOT_FOUND',
+        message: `No active outbound federation peer matches source ${source}`,
+        source,
+      });
+    }
+
+    return peer;
+  }
+
+  private async listActiveOutboundPeers(): Promise<OutboundPeer[]> {
+    const rows = await this.db
+      .select({
+        id: federationPeers.id,
+        commonName: federationPeers.commonName,
+        endpointUrl: federationPeers.endpointUrl,
+      })
+      .from(federationPeers)
+      .where(
+        and(
+          eq(federationPeers.state, 'active'),
+          isNotNull(federationPeers.endpointUrl),
+          isNotNull(federationPeers.clientKeyPem),
+        ),
+      )
+      .orderBy(federationPeers.commonName);
+
+    return rows.filter((row): row is OutboundPeer => typeof row.endpointUrl === 'string');
+  }
+}
+
+function normalizeHost(host: string): string {
+  return host.trim().toLowerCase();
+}
+
+function endpointHostKeys(endpointUrl: string): string[] {
+  try {
+    const url = new URL(endpointUrl);
+    return Array.from(new Set([url.host, url.hostname].filter((host: string) => host.length > 0)));
+  } catch {
+    return [];
+  }
+}

apps/gateway/src/federation/federation.module.ts

@@ -4,18 +4,20 @@ import { CaService } from './ca.service.js';
 import { EnrollmentController } from './enrollment.controller.js';
 import { EnrollmentService } from './enrollment.service.js';
 import { FederationController } from './federation.controller.js';
+import { CapabilitiesController } from './server/verbs/capabilities.controller.js';
 import { GrantsService } from './grants.service.js';
-import { FederationClientService } from './client/index.js';
+import { FederationClientService, QuerySourceService } from './client/index.js';
 import { FederationAuthGuard } from './server/index.js';
 
 @Module({
-  controllers: [EnrollmentController, FederationController],
+  controllers: [EnrollmentController, FederationController, CapabilitiesController],
   providers: [
     AdminGuard,
     CaService,
     EnrollmentService,
     GrantsService,
     FederationClientService,
+    QuerySourceService,
     FederationAuthGuard,
   ],
   exports: [
@@ -23,6 +25,7 @@ import { FederationAuthGuard } from './server/index.js';
     EnrollmentService,
     GrantsService,
     FederationClientService,
+    QuerySourceService,
     FederationAuthGuard,
   ],
 })

apps/gateway/src/federation/server/verbs/__tests__/capabilities.controller.spec.ts

@@ -0,0 +1,88 @@
+import 'reflect-metadata';
+import { RequestMethod } from '@nestjs/common';
+import { describe, expect, it } from 'vitest';
+import type { FastifyRequest } from 'fastify';
+import { FederationCapabilitiesResponseSchema, FEDERATION_VERBS } from '@mosaicstack/types';
+import { FederationScopeError } from '../../../scope-schema.js';
+import { FederationAuthGuard } from '../../federation-auth.guard.js';
+import { CapabilitiesController } from '../capabilities.controller.js';
+
+const VALID_SCOPE = {
+  resources: ['tasks', 'notes'],
+  excluded_resources: ['credentials'],
+  max_rows_per_query: 250,
+} as const;
+
+const DEFAULTED_SCOPE = {
+  resources: ['memory'],
+  max_rows_per_query: 10,
+} as const;
+
+function makeRequest(scope: Record<string, unknown>): FastifyRequest {
+  return {
+    federationContext: {
+      grantId: 'grant-1',
+      peerId: 'peer-1',
+      subjectUserId: 'user-1',
+      scope,
+    },
+  } as FastifyRequest;
+}
+
+describe('CapabilitiesController', () => {
+  it('declares GET /api/federation/v1/capabilities', () => {
+    expect(Reflect.getMetadata('path', CapabilitiesController)).toBe(
+      'api/federation/v1/capabilities',
+    );
+    expect(Reflect.getMetadata('path', CapabilitiesController.prototype.getCapabilities)).toBe('/');
+    expect(Reflect.getMetadata('method', CapabilitiesController.prototype.getCapabilities)).toBe(
+      RequestMethod.GET,
+    );
+  });
+
+  it('is protected only by FederationAuthGuard', () => {
+    const guards = Reflect.getMetadata('__guards__', CapabilitiesController) as unknown[];
+
+    expect(guards).toEqual([FederationAuthGuard]);
+  });
+
+  it('returns resources, excluded resources, max rows, and M3 supported verbs from the active grant scope', () => {
+    const controller = new CapabilitiesController();
+
+    const response = controller.getCapabilities(makeRequest(VALID_SCOPE));
+
+    expect(response).toEqual({
+      resources: ['tasks', 'notes'],
+      excluded_resources: ['credentials'],
+      max_rows_per_query: 250,
+      supported_verbs: [...FEDERATION_VERBS],
+    });
+    expect(FederationCapabilitiesResponseSchema.safeParse(response).success).toBe(true);
+  });
+
+  it('applies scope defaults without RBAC or resource filtering', () => {
+    const controller = new CapabilitiesController();
+
+    const response = controller.getCapabilities(makeRequest(DEFAULTED_SCOPE));
+
+    expect(response).toEqual({
+      resources: ['memory'],
+      excluded_resources: [],
+      max_rows_per_query: 10,
+      supported_verbs: ['list', 'get', 'capabilities'],
+    });
+  });
+
+  it('rejects invalid scope state instead of returning an invalid capabilities contract', () => {
+    const controller = new CapabilitiesController();
+
+    expect(() =>
+      controller.getCapabilities(
+        makeRequest({
+          resources: [],
+          max_rows_per_query: 0,
+        }),
+      ),
+    ).toThrow(FederationScopeError);
+  });
+});

apps/gateway/src/federation/server/verbs/capabilities.controller.ts

@@ -0,0 +1,38 @@
+/**
+ * Federation capabilities verb (FED-M3-07).
+ *
+ * Returns the read-only capability envelope for the active grant attached by
+ * FederationAuthGuard. This endpoint intentionally does not invoke native RBAC
+ * or ScopeService: an active grant is enough to ask what the grant allows.
+ */
+
+import { Controller, Get, Req, UseGuards } from '@nestjs/common';
+import type { FastifyRequest } from 'fastify';
+import {
+  FEDERATION_VERBS,
+  type FederationCapabilitiesResponse,
+  type FederationVerb,
+} from '@mosaicstack/types';
+import { parseFederationScope } from '../../scope-schema.js';
+import { FederationAuthGuard } from '../federation-auth.guard.js';
+import '../federation-context.js';
+
+@Controller('api/federation/v1/capabilities')
+@UseGuards(FederationAuthGuard)
+export class CapabilitiesController {
+  @Get()
+  getCapabilities(@Req() request: FastifyRequest): FederationCapabilitiesResponse {
+    if (!request.federationContext) {
+      throw new Error('Federation context missing after auth guard');
+    }
+
+    const scope = parseFederationScope(request.federationContext.scope);
+
+    return {
+      resources: [...scope.resources],
+      excluded_resources: [...scope.excluded_resources],
+      max_rows_per_query: scope.max_rows_per_query,
+      supported_verbs: [...FEDERATION_VERBS] satisfies FederationVerb[],
+    };
+  }
+}

docs/federation/TASKS.md

@@ -93,17 +93,17 @@ Goal: Two federated gateways exchange real data over mTLS. Inbound requests pass
 
 | id        | status      | description                                                                                                                                                                                                                                                                                            | issue | agent  | branch                               | depends_on       | estimate | notes                                                                                                                                                    |
 | --------- | ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----- | ------ | ------------------------------------ | ---------------- | -------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FED-M3-01 | not-started | `packages/types/src/federation/` — request/response DTOs for `list`, `get`, `capabilities` verbs. Wire-format zod schemas + inferred TS types. Includes `FederationRequest`, `FederationListResponse<T>`, `FederationGetResponse<T>`, `FederationCapabilitiesResponse`, error envelope, `_source` tag. | #462  | sonnet | feat/federation-m3-types             | —                | 4K       | Reusable from gateway server + client + harness. Pure types — no I/O, no NestJS.                                                                         |
-| FED-M3-02 | not-started | `tools/federation-harness/` scaffold: `docker-compose.two-gateways.yml` (Server A + Server B + step-CA), `seed.ts` (provisions grants, peers, sample tasks/notes/credentials per scope variant), `harness.ts` helper (boots stack, returns typed clients). README documents harness use.               | #462  | sonnet | feat/federation-m3-harness           | DEPLOY-04 (soft) | 8K       | Falls back to local docker-compose if `mos-test-1/-2` not yet redeployed (DEPLOY chain blocked on IMG-FIX). Permanent test infra used by M3+.            |
-| FED-M3-03 | not-started | `apps/gateway/src/federation/server/federation-auth.guard.ts` (NestJS guard). Validates inbound client cert from Fastify TLS context, extracts `grantId` + `subjectUserId` from custom OIDs, loads grant from DB, asserts `status='active'`, attaches `FederationContext` to request.                  | #462  | sonnet | feat/federation-m3-auth-guard        | M3-01            | 8K       | Reuses OID parsing logic mirrored from `ca.service.ts` post-issuance verification. 401 on malformed/missing OIDs; 403 on revoked/expired/missing grant.  |
-| FED-M3-04 | not-started | `apps/gateway/src/federation/server/scope.service.ts`. Pipeline: (1) resource allowlist + excluded check, (2) native RBAC eval as `subjectUserId`, (3) scope filter intersection (`include_teams`, `include_personal`), (4) `max_rows_per_query` cap. Pure service — DB calls injected.                | #462  | sonnet | feat/federation-m3-scope-service     | M3-01            | 10K      | Hardest correctness target in M3. Reuses `parseFederationScope` (M2-03). Returns either `{ allowed: true, filter }` or structured deny reason for audit. |
-| FED-M3-05 | not-started | `apps/gateway/src/federation/server/verbs/list.controller.ts`. Wires AuthGuard → ScopeService → tasks/notes/memory query layer; applies row cap; tags rows with `_source`. Resource selector via path param.                                                                                           | #462  | sonnet | feat/federation-m3-verb-list         | M3-03, M3-04     | 6K       | Routes: `POST /api/federation/v1/list/:resource`. No body persistence. Audit write deferred to M4.                                                       |
+| FED-M3-01 | done        | `packages/types/src/federation/` — request/response DTOs for `list`, `get`, `capabilities` verbs. Wire-format zod schemas + inferred TS types. Includes `FederationRequest`, `FederationListResponse<T>`, `FederationGetResponse<T>`, `FederationCapabilitiesResponse`, error envelope, `_source` tag. | #462  | sonnet | feat/federation-m3-types             | —                | 4K       | Reusable from gateway server + client + harness. Pure types — no I/O, no NestJS.                                                                         |
+| FED-M3-02 | done        | `tools/federation-harness/` scaffold: `docker-compose.two-gateways.yml` (Server A + Server B + step-CA), `seed.ts` (provisions grants, peers, sample tasks/notes/credentials per scope variant), `harness.ts` helper (boots stack, returns typed clients). README documents harness use.               | #462  | sonnet | feat/federation-m3-harness           | DEPLOY-04 (soft) | 8K       | Falls back to local docker-compose if `mos-test-1/-2` not yet redeployed (DEPLOY chain blocked on IMG-FIX). Permanent test infra used by M3+.            |
+| FED-M3-03 | done        | `apps/gateway/src/federation/server/federation-auth.guard.ts` (NestJS guard). Validates inbound client cert from Fastify TLS context, extracts `grantId` + `subjectUserId` from custom OIDs, loads grant from DB, asserts `status='active'`, attaches `FederationContext` to request.                  | #462  | sonnet | feat/federation-m3-auth-guard        | M3-01            | 8K       | Reuses OID parsing logic mirrored from `ca.service.ts` post-issuance verification. 401 on malformed/missing OIDs; 403 on revoked/expired/missing grant.  |
+| FED-M3-04 | in-progress | `apps/gateway/src/federation/server/scope.service.ts`. Pipeline: (1) resource allowlist + excluded check, (2) native RBAC eval as `subjectUserId`, (3) scope filter intersection (`include_teams`, `include_personal`), (4) `max_rows_per_query` cap. Pure service — DB calls injected.                | #462  | sonnet | feat/federation-m3-scope-service     | M3-01            | 10K      | Hardest correctness target in M3. Reuses `parseFederationScope` (M2-03). Returns either `{ allowed: true, filter }` or structured deny reason for audit. |
+| FED-M3-05 | in-progress | `apps/gateway/src/federation/server/verbs/list.controller.ts`. Wires AuthGuard → ScopeService → tasks/notes/memory query layer; applies row cap; tags rows with `_source`. Resource selector via path param.                                                                                           | #462  | sonnet | feat/federation-m3-verb-list         | M3-03, M3-04     | 6K       | Routes: `POST /api/federation/v1/list/:resource`. No body persistence. Audit write deferred to M4.                                                       |
 | FED-M3-06 | not-started | `apps/gateway/src/federation/server/verbs/get.controller.ts`. Single-resource fetch by id; same pipeline as list. 404 on not-found, 403 on RBAC/scope deny — both audited the same way.                                                                                                                | #462  | sonnet | feat/federation-m3-verb-get          | M3-03, M3-04     | 6K       | `POST /api/federation/v1/get/:resource/:id`. Mirrors list controller patterns.                                                                           |
-| FED-M3-07 | not-started | `apps/gateway/src/federation/server/verbs/capabilities.controller.ts`. Read-only enumeration: returns `{ resources, excluded_resources, max_rows_per_query, supported_verbs }` derived from grant scope. Always allowed for an active grant — no RBAC eval.                                            | #462  | sonnet | feat/federation-m3-verb-capabilities | M3-03            | 4K       | `GET /api/federation/v1/capabilities`. Smallest verb; useful sanity check that mTLS + auth guard work end-to-end.                                        |
-| FED-M3-08 | not-started | `apps/gateway/src/federation/client/federation-client.service.ts`. Outbound mTLS dialer: picks `(certPem, sealed clientKey)` from `federation_peers`, unwraps key, builds undici Agent with mTLS, calls peer verb, parses typed response, wraps non-2xx into `FederationClientError`.                  | #462  | sonnet | feat/federation-m3-client            | M3-01            | 8K       | Independent of server stream — can land in parallel with M3-03/04. Cert/key cached per-peer; flushed by future M5/M6 logic.                              |
-| FED-M3-09 | not-started | `apps/gateway/src/federation/client/query-source.service.ts`. Accepts `source: "local" \| "federated:<host>" \| "all"` from gateway query layer; for `"all"` fans out to local + each peer in parallel; merges results; tags every row with `_source`.                                                 | #462  | sonnet | feat/federation-m3-query-source      | M3-08            | 8K       | Per-peer failure surfaces as `_partial: true` in response, not hard failure (sets up M5 offline UX). M5 adds caching + circuit breaker on top.           |
+| FED-M3-07 | done        | `apps/gateway/src/federation/server/verbs/capabilities.controller.ts`. Read-only enumeration: returns `{ resources, excluded_resources, max_rows_per_query, supported_verbs }` derived from grant scope. Always allowed for an active grant — no RBAC eval.                                            | #462  | sonnet | feat/federation-m3-verb-capabilities | M3-03            | 4K       | `GET /api/federation/v1/capabilities`. Smallest verb; useful sanity check that mTLS + auth guard work end-to-end.                                        |
+| FED-M3-08 | done        | `apps/gateway/src/federation/client/federation-client.service.ts`. Outbound mTLS dialer: picks `(certPem, sealed clientKey)` from `federation_peers`, unwraps key, builds undici Agent with mTLS, calls peer verb, parses typed response, wraps non-2xx into `FederationClientError`.                  | #462  | sonnet | feat/federation-m3-client            | M3-01            | 8K       | Independent of server stream — can land in parallel with M3-03/04. Cert/key cached per-peer; flushed by future M5/M6 logic.                              |
+| FED-M3-09 | done        | `apps/gateway/src/federation/client/query-source.service.ts`. Accepts `source: "local" \| "federated:<host>" \| "all"` from gateway query layer; for `"all"` fans out to local + each peer in parallel; merges results; tags every row with `_source`.                                                 | #462  | sonnet | feat/federation-m3-query-source      | M3-08            | 8K       | Per-peer failure surfaces as `_partial: true` in response, not hard failure (sets up M5 offline UX). M5 adds caching + circuit breaker on top.           |
 | FED-M3-10 | not-started | Integration tests for MILESTONES.md M3 acceptance #6 (malformed OIDs → 401; valid cert + revoked grant → 403) and #7 (`max_rows_per_query` cap). Real PG, mocked TLS context (Fastify req shim).                                                                                                       | #462  | sonnet | feat/federation-m3-integration       | M3-05, M3-06     | 8K       | Vitest profile gated by `FEDERATED_INTEGRATION=1`. Single-gateway suite; no harness required.                                                            |
-| FED-M3-11 | not-started | E2E tests for MILESTONES.md M3 acceptance #1, #2, #3, #4, #5, #8, #9, #10 (8 cases). Uses harness from M3-02; two real gateways, real Step-CA, real mTLS. Each test asserts both happy-path response and audit/no-persist invariants.                                                                  | #462  | sonnet | feat/federation-m3-e2e               | M3-02, M3-09     | 12K      | Largest single task. Each acceptance gets its own `it(...)` for clear failure attribution.                                                               |
+| FED-M3-11 | not-started | E2E tests for MILESTONES.md M3 acceptance #1, #2, #3, #4, #5, #8, #9, #10 (8 cases). Uses harness from M3-02; two real gateways, real Step-CA, real mTLS. Each test asserts both happy-path response and audit/no-persist invariants.                                                                  | #462  | sonnet | feat/federation-m3-e2e               | M3-02, M3-04, M3-05, M3-06, M3-09 | 12K      | Largest single task. Each acceptance gets its own `it(...)` for clear failure attribution.                                                               |
 | FED-M3-12 | not-started | Independent security review (sonnet, not author of M3-03/04/05/06/07/08/09): focus on cert-SAN spoofing, OID extraction edge cases, scope-bypass via filter manipulation, RBAC-bypass via subjectUser swap, response leakage when scope deny.                                                          | #462  | sonnet | feat/federation-m3-security-review   | M3-11            | 10K      | Two review rounds budgeted. PRD requires explicit test for every 401/403 path — review verifies coverage.                                                |
 | FED-M3-13 | not-started | Docs update: `docs/federation/SETUP.md` mTLS handshake section, new `docs/federation/HARNESS.md` for federation-harness usage, OID reference table in SETUP.md, scope enforcement pipeline diagram. Runbook still M7-deferred.                                                                         | #462  | haiku  | feat/federation-m3-docs              | M3-12            | 5K       | One ASCII diagram for the auth-guard → scope → RBAC pipeline; helps future reviewers reason about denial paths.                                          |
 | FED-M3-14 | not-started | PR aggregate close, CI green, merge to main, close #462. Release tag `fed-v0.3.0-m3`. Update mission manifest M3 row → done; M4 row → in-progress when work begins.                                                                                                                                    | #462  | sonnet | chore/federation-m3-close            | M3-13            | 3K       | Same close pattern as M1-12 / M2-13.                                                                                                                     |
@@ -118,6 +118,10 @@ Goal: Two federated gateways exchange real data over mTLS. Inbound requests pass
 
 **Test bed fallback:** If `mos-test-1.woltje.com` / `mos-test-2.woltje.com` are still blocked on `FED-M2-DEPLOY-IMG-FIX` when M3-11 is ready to run, the harness's local `docker-compose.two-gateways.yml` is a sufficient stand-in. Production-host validation moves to M7 acceptance suite (PRD AC-12).
 
+**Backlog sync — 2026-06-24 (orchestrator):** Status reconciled against `origin/main` (release 0.0.48). Landed on main: **FED-M3-01** (DTOs, PR #506), **FED-M3-02** (harness scaffold, PR #505), **FED-M3-03** (mTLS auth-guard, PR #509 — CRIT-1/2 + HIGH-1..4 remediated in-PR), **FED-M3-08** (outbound mTLS client, PR #508). With M3-01/03/08 merged, three cards became dependency-clear and were dispatched to the idle coder lane: **FED-M3-04** scope.service → coder0 (`feat/federation-m3-scope-service`); **FED-M3-09** query-source + **FED-M3-07** capabilities verb → coder1 (`feat/federation-m3-query-source` first). Reviewer warmed for the M3 trust-boundary PRs. Remaining blocked-by-DAG: M3-05/06 (await M3-04), M3-10 (await M3-05/06), M3-11 (await M3-09), M3-12→14 (tail). Deploy chain (DEPLOY-IMG-FIX → 03/04) still independent of M3 code — harness local docker-compose fallback covers M3-11.
+
+**Backlog sync #2 — 2026-06-24 (orchestrator):** **FED-M3-09** (query-source) merged via PR #673 and **FED-M3-07** (capabilities) merged via PR #674 — both squash-merged on independent agent review-of-record + green CI (formal Gitea approve unavailable under the shared service account; merge is not gated by the self-approve guard). **FED-M3-05** (list verb) dispatched to coder1 (based on the M3-04 branch, rebase onto main once #672 lands). **FED-M3-04** (scope.service, PR #672) is in review-changes (one include_personal no-leak test outstanding). **DAG fix:** corrected `FED-M3-11` depends_on from `M3-02, M3-09` → `M3-02, M3-04, M3-05, M3-06, M3-09` — the E2E acceptance cases (#1–#5, #8–#10) exercise list/get over mTLS, so the server verbs + scope service are hard prerequisites; the original edge set omitted them and caused a premature M3-11 dispatch. Note: M3 read-path invariant for M3-11 is **no-persist + existing enrollment audit only** — read-verb audit-log writes are deferred to M4 (see M3-05/06 notes), so M3-11 must not assert read-audit-log entries.
+
 ## Milestone 4 — search + audit + rate limit (FED-M4)
 
 _Deferred. Issue #463._

docs/fleet/north-star.md

@@ -353,6 +353,25 @@ re-evaluate if isolation or write-volume demands it.
 - **Docs as projections:** `docs/TASKS.md` and `MISSION-MANIFEST.md` become generated exports of the DB, not hand-maintained.
 - **Sub-decision pending:** dedicated schema in existing PG instance (recommended) vs. dedicated PG instance. Revisit if isolation or write-volume demands it.
 
+## Decisions of record (2026-06-24, with Jason)
+
+- **Per-agent model switch (operator-configurable, NOT a global lock):** model selection is
+  **per-agent**, never a host-global pin. Claude sessions MUST NOT be locked to a single model in
+  `~/.claude/settings.json`; each agent chooses its model independently. The plumbing already exists —
+  roster `model_hint` → `MOSAIC_AGENT_MODEL` → `start-agent-session.sh` appends `--model <hint>` to that
+  agent's harness (claude or pi); settable today via `mosaic fleet add|edit <agent> --model <hint>`.
+  **North-star target:** surface this as a **per-agent model switch in the webUI** (with CLI/TUI parity
+  per MVP-X1) — read the roster, expose a per-agent model dropdown, write `model_hint` back, and restart
+  that one agent to apply. Unset = inherit the harness default. This **composes with** the budget
+  downgrade ladder (opus → sonnet → haiku, then Claude → Codex): the operator sets the per-agent model
+  _intent/ceiling_; budget pacing may downgrade within policy. Tracked as a Fleet `TASKS.md` entry under
+  the Phase-5 webUI surface.
+- **Orchestrator runtime (confirmed live):** the **orchestrator and enhancer run Claude Opus 4.8 in the
+  Claude Code harness**; only workers (coder/reviewer) run pi/gpt-5.5. Consistent with the 2026-06-20
+  "Claude reserved for Claude Code only" decision (the orchestrator runs _in_ Claude Code, not an
+  alternate Claude harness). Pi/gpt-5.5 as the orchestrator is permitted **only if proven** at least as
+  satisfactory; absent that proof, the orchestrator stays on Claude Opus 4.8.
+
 ## Future enhancements (north-star, post-MVP — not on the MVP track)
 
 - **Mosaic Claude Discord Plugin** — a first-party Mosaic Discord connector that properly

docs/scratchpads/672-fleet-personas-timeout.md

@@ -0,0 +1,25 @@
+# Scratchpad — fleet-personas spec timeout
+
+## Objective
+
+Raise the `@mosaicstack/mosaic` Vitest timeout to 30s at config level so filesystem-backed fleet drift-guard specs (`fleet-personas`, `fleet-profiles`, and siblings) stop false-reding under contended CI.
+
+## Plan
+
+1. Move timeout policy into `packages/mosaic/vitest.config.ts` with `testTimeout: 30_000`.
+2. Remove the narrower `fleet-personas.spec.ts` local override so PR #677 fixes the suite class, not one file.
+3. Run targeted fleet specs plus typecheck/lint/format gates.
+4. Commit, queue guard, push, PR update.
+
+## Evidence
+
+- `pnpm --filter @mosaicstack/mosaic test -- src/commands/fleet-personas.spec.ts` — pass (8 tests; initial narrow fix).
+- `pnpm typecheck` — pass (41 tasks; initial narrow fix).
+- `pnpm lint` — pass (23 tasks; initial narrow fix).
+- `pnpm format:check` — pass after formatting this scratchpad (initial narrow fix).
+- Package-wide timeout follow-up:
+  - `pnpm --filter @mosaicstack/mosaic test -- src/commands/fleet-personas.spec.ts src/commands/fleet-profiles.spec.ts` — pass (24 tests).
+  - `pnpm --filter @mosaicstack/mosaic test` — pass (44 files / 618 tests).
+  - `pnpm typecheck` — pass (41 tasks).
+  - `pnpm lint` — pass (23 tasks).
+  - `pnpm format:check` — pass.

docs/scratchpads/FED-M3-07-capabilities.md

@@ -0,0 +1,65 @@
+# FED-M3-07 — Capabilities Verb Scratchpad
+
+## Objective
+
+Implement `GET /api/federation/v1/capabilities` in `apps/gateway/src/federation/server/verbs/capabilities.controller.ts`.
+
+## Scope
+
+- Add read-only capabilities controller under federation server verbs.
+- Use `FederationAuthGuard` only; active grant is sufficient and no native RBAC/scope-service eval runs.
+- Response shape: `{ resources, excluded_resources, max_rows_per_query, supported_verbs }` derived from grant scope.
+- Register controller in `FederationModule`.
+- Unit-test happy path, defaults, no-context guard seam, and invalid scope handling.
+
+## Constraints / assumptions
+
+- Issue: #462.
+- Branch: `feat/federation-m3-verb-capabilities` from `origin/main` (`3eeed04e`).
+- Depends on M3-03 auth guard; guard attaches `request.federationContext.scope` after active-grant validation.
+- ASSUMPTION: `supported_verbs` is the M3 verb set from `@mosaicstack/types` (`list`, `get`, `capabilities`).
+- ASSUMPTION: `filters`/`rate_limit` are intentionally omitted for FED-M3-07 because the card’s response shape lists only the four required fields.
+- Budget: no explicit hard cap from orchestrator; working cap ~4K-8K tokens for card implementation + tests + PR cycle.
+
+## Plan
+
+1. Write controller unit tests first.
+2. Implement controller and module registration.
+3. Run scoped tests + typecheck/lint/format.
+4. Run Codex code/security review and remediate.
+5. Commit, queue guard, push, PR via wrapper.
+
+## Progress
+
+- 2026-06-24: Intake complete; fresh worktree created from origin/main.
+- 2026-06-24: Added `CapabilitiesController`, registered it in `FederationModule`, and added 5 unit tests.
+- 2026-06-24: Code/security reviews passed with no findings.
+
+## Tests run
+
+- `pnpm --filter @mosaicstack/gateway test -- capabilities.controller.spec.ts` — PASS (5 tests).
+- `pnpm --filter @mosaicstack/gateway typecheck` — PASS.
+- `pnpm --filter @mosaicstack/gateway lint` — PASS.
+- `pnpm format:check` — PASS.
+- `pnpm typecheck` — PASS (41/41 turbo tasks).
+- `pnpm lint` — PASS (23/23 turbo tasks).
+- `pnpm test` — FAIL in pre-existing/live-DB integration suite: `apps/gateway/src/__tests__/cross-user-isolation.test.ts` cleanup hit PostgreSQL connection/schema state for the `messages` table. Changed capabilities tests passed; failure is outside FED-M3-07 surface. No `fleet-personas.spec` flake encountered.
+
+## Review evidence
+
+- `~/.config/mosaic/tools/codex/codex-code-review.sh --uncommitted` — PASS/approve, no findings.
+- `~/.config/mosaic/tools/codex/codex-security-review.sh --uncommitted` — PASS, risk level none, no findings.
+
+## Risks / blockers
+
+- Full repo `pnpm test` may hit known `fleet-personas.spec` flake per orchestrator; ignore that specific flake if encountered.
+- Previous card saw local DB schema issue in `cross-user-isolation.test.ts`; scoped capabilities tests should be authoritative for this surface.
+
+## Acceptance evidence mapping
+
+| Acceptance criterion                                                       | Evidence                                                                                                                   |
+| -------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------- |
+| GET `/api/federation/v1/capabilities` exists                               | Route metadata test in `capabilities.controller.spec.ts`; scoped test PASS                                                 |
+| Uses active-grant auth guard and no RBAC eval                              | Guard metadata test confirms only `FederationAuthGuard`; controller has no service injections/RBAC calls; scoped test PASS |
+| Response enumerates resources/excluded/max rows/supported verbs from scope | Happy-path/default scope tests + response schema parse; scoped test PASS                                                   |
+| Read-only/no persistence side effects                                      | Controller only parses request `federationContext.scope` and returns a DTO; no DB/service dependency; code review PASS     |

docs/scratchpads/FED-M3-09-query-source.md

@@ -0,0 +1,67 @@
+# FED-M3-09 — Query Source Service Scratchpad
+
+## Objective
+
+Implement `apps/gateway/src/federation/client/query-source.service.ts` for `source: "local" | "federated:<host>" | "all"` routing.
+
+## Scope
+
+- Add QuerySourceService in gateway federation client layer.
+- Unit-test local-only, single federated peer, all-source fan-out/merge, and per-peer partial failures.
+- Keep `docs/federation/TASKS.md` read-only per project agent guidance.
+
+## Constraints / assumptions
+
+- Issue: #462.
+- Branch: `feat/federation-m3-query-source` from `origin/main` (`e0e7be70`).
+- ASSUMPTION: `federated:<host>` should match active outbound peers by `commonName` first and by `endpointUrl` host/hostname as compatibility fallback; source tags use `peer.commonName` per `@mosaicstack/types` source-tag docs.
+- ASSUMPTION: QuerySourceService provides list/fan-out behavior; get/source routing can be layered later because card acceptance says merge rows.
+- ASSUMPTION: `source: "all"` cannot safely return a single continuation cursor for multiple sub-sources; any subquery cursor marks the merged response `_partial: true` + `_truncated: true` while omitting `nextCursor`.
+- Budget: no explicit hard cap from orchestrator; working cap ~8K-12K tokens for card 1 implementation + tests + PR cycle.
+- OpenBrain unavailable: credential loader failed with missing `/home/jarvis/.config/mosaic/credentials.json`; not blocking code delivery.
+
+## Plan
+
+1. Review federation client/types/db patterns.
+2. Write unit tests for source behavior.
+3. Implement QuerySourceService and export/register it in FederationModule.
+4. Run scoped tests, typecheck, lint, format.
+5. Run codex uncommitted review and remediate.
+6. Commit, queue guard, push, PR via wrapper.
+
+## Progress
+
+- 2026-06-24: Intake complete; using isolated worktree to avoid dirty orchestrator files in original checkout.
+- 2026-06-24: Added QuerySourceService, module export, barrel export, and 7 unit tests.
+- 2026-06-24: First Codex review found pagination and port-host matching issues; both remediated with tests.
+
+## Tests run
+
+- `pnpm --filter @mosaicstack/gateway test -- query-source.service.spec.ts` — PASS (7 tests).
+- `pnpm --filter @mosaicstack/gateway typecheck` — PASS.
+- `pnpm --filter @mosaicstack/gateway lint` — PASS.
+- `pnpm format:check` — PASS.
+- `pnpm typecheck` — PASS (41/41 turbo tasks).
+- `pnpm lint` — PASS (23/23 turbo tasks).
+- `pnpm test` — FAIL in pre-existing/live-DB integration suite: `apps/gateway/src/__tests__/cross-user-isolation.test.ts` cleanup hit `relation "messages" does not exist` against local PostgreSQL. Changed QuerySource unit tests passed; failure is outside FED-M3-09 surface and appears tied to local DB schema state.
+
+## Review evidence
+
+- `~/.config/mosaic/tools/codex/codex-code-review.sh --uncommitted` — first pass request-changes, 2 should-fix findings (all-source cursor handling; endpoint port host matching).
+- Remediation: `_partial` + `_truncated` when any all-source subquery has `nextCursor`; endpoint match accepts URL `host` and `hostname`; added tests for both.
+- `~/.config/mosaic/tools/codex/codex-code-review.sh --uncommitted` — PASS/approve, no findings.
+- `~/.config/mosaic/tools/codex/codex-security-review.sh --uncommitted` — PASS, risk level none, no findings.
+
+## Risks / blockers
+
+- Federation query layer is not yet wired; service API needs to be stable and easy to compose.
+- Must avoid hard-failing `source: all` on remote peer failures.
+
+## Acceptance evidence mapping
+
+| Acceptance criterion                                                            | Evidence                                                                          |
+| ------------------------------------------------------------------------------- | --------------------------------------------------------------------------------- |
+| local source returns local rows tagged `_source: local`                         | `query-source.service.spec.ts` local test; scoped test PASS                       |
+| `federated:<host>` queries selected peer and tags rows with peer source         | `query-source.service.spec.ts` commonName/endpoint-host tests; scoped test PASS   |
+| `all` fans out local + active outbound peers in parallel and merges tagged rows | `query-source.service.spec.ts` all-source call-order/merge test; scoped test PASS |
+| per-peer failure on `all` returns `_partial: true`, not throw                   | `query-source.service.spec.ts` peer failure test; scoped test PASS                |

eslint.config.mjs

@@ -30,6 +30,7 @@ export default tseslint.config(
             'apps/gateway/vitest.config.ts',
             'packages/db/vitest.config.ts',
             'packages/storage/vitest.config.ts',
+            'packages/mosaic/vitest.config.ts',
             'packages/mosaic/__tests__/*.ts',
             'tools/federation-harness/*.ts',
           ],

packages/db/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mosaicstack/db",
-  "version": "0.0.3",
+  "version": "0.0.4",
   "repository": {
     "type": "git",
     "url": "https://git.mosaicstack.dev/mosaicstack/stack.git",

packages/mosaic/framework/tools/fleet/start-agent-session.sh

@@ -114,10 +114,21 @@ MOSAIC_RUNTIME_BIN_PREFIX=$(_build_runtime_bin_prefix)
 # safe single bash token regardless of the name's characters.
 AGENT_NAME_Q=$(printf '%q' "$AGENT_NAME")
 
+# MOSAIC_AGENT_CLASS must ALSO be exported INTO the pane, for the same reason as
+# MOSAIC_AGENT_NAME above: the pane inherits the tmux SERVER environment (not this
+# script's env, and not the systemd unit's EnvironmentFile), so the per-agent class
+# written to agents/<name>.env would otherwise be invisible in-pane. The launcher
+# composes the persona contract from process.env.MOSAIC_AGENT_CLASS at launch
+# (compose-contract -> readPersonaContractBlock); without this export it sees an
+# undefined class and silently injects NO persona contract. %q-quote it so it is a
+# safe single bash token; an empty/unset class %q-quotes to '' and is a harmless
+# no-op downstream (readPersonaContractBlock returns '' for an empty class).
+AGENT_CLASS_Q=$(printf '%q' "${MOSAIC_AGENT_CLASS:-}")
+
 if [ -n "$MOSAIC_RUNTIME_BIN_PREFIX" ]; then
-  PANE_SHELL_SNIPPET="export MOSAIC_AGENT_NAME=${AGENT_NAME_Q}; export PATH=\"${MOSAIC_RUNTIME_BIN_PREFIX}:\${PATH}\"; exec ${MOSAIC_AGENT_COMMAND}"
+  PANE_SHELL_SNIPPET="export MOSAIC_AGENT_NAME=${AGENT_NAME_Q}; export MOSAIC_AGENT_CLASS=${AGENT_CLASS_Q}; export PATH=\"${MOSAIC_RUNTIME_BIN_PREFIX}:\${PATH}\"; exec ${MOSAIC_AGENT_COMMAND}"
 else
-  PANE_SHELL_SNIPPET="export MOSAIC_AGENT_NAME=${AGENT_NAME_Q}; exec ${MOSAIC_AGENT_COMMAND}"
+  PANE_SHELL_SNIPPET="export MOSAIC_AGENT_NAME=${AGENT_NAME_Q}; export MOSAIC_AGENT_CLASS=${AGENT_CLASS_Q}; exec ${MOSAIC_AGENT_COMMAND}"
 fi
 
 mkdir -p "$MOSAIC_AGENT_WORKDIR"

packages/mosaic/framework/tools/fleet/test-start-agent-session.sh

@@ -104,6 +104,7 @@ PATH="$FAKE_BIN:$PATH" \
 MOSAIC_TMUX_SOCKET="$SOCKET3" \
 MOSAIC_AGENT_WORKDIR="$WORKDIR3" \
 MOSAIC_AGENT_RUNTIME="pi" \
+MOSAIC_AGENT_CLASS="code" \
 MOSAIC_RUNTIME_BIN="$FAKE_RUNTIME_BIN" \
 MOSAIC_AGENT_COMMAND="mosaic yolo pi --model openai-codex/gpt-5.5:high" \
 MOSAIC_HEARTBEAT_RUN_DIR="$HB_RUN_DIR3" \
@@ -127,6 +128,18 @@ echo "$all_args" | grep -qF "exec " || fail "pane command does not use exec"
 echo "$all_args" | grep -qF "mosaic yolo pi --model openai-codex/gpt-5.5:high" || \
   fail "pane command does not forward MOSAIC_AGENT_COMMAND with flags intact"
 
+# d) MOSAIC_AGENT_NAME and the per-agent MOSAIC_AGENT_CLASS must BOTH be exported
+#    INTO the pane. The pane inherits the tmux SERVER environment (not this
+#    script's env, nor the systemd unit's EnvironmentFile), so any per-agent var
+#    the launcher needs in-pane must be re-exported in the snippet. CLASS is
+#    load-bearing: the launcher composes the persona contract from
+#    process.env.MOSAIC_AGENT_CLASS, so a missing export silently drops the
+#    persona (regression guard for the A3a pane-propagation gap).
+echo "$all_args" | grep -qF "export MOSAIC_AGENT_NAME=" || \
+  fail "pane command does not export MOSAIC_AGENT_NAME into the pane"
+echo "$all_args" | grep -qF "export MOSAIC_AGENT_CLASS=code" || \
+  fail "pane command does not export MOSAIC_AGENT_CLASS into the pane (persona would silently drop)"
+
 # ── Test 4: when no extra runtime-bin dirs exist, exec still appears ───────────
 TMUX_ARGS_FILE2=$(mktemp)
 FAKE_BIN2=$(mktemp -d)

packages/mosaic/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mosaicstack/mosaic",
-  "version": "0.0.45",
+  "version": "0.0.48",
   "repository": {
     "type": "git",
     "url": "https://git.mosaicstack.dev/mosaicstack/stack.git",

packages/mosaic/src/commands/fleet-personas.ts

@@ -234,6 +234,21 @@ export async function resolvePersona(
     extractClassesFromDir(rolesDir),
     extractClassesFromDir(overrideDir),
   ]);
+  return resolvePersonaFrom(klass, { rolesDir, overrideDir, base, over });
+}
+
+/**
+ * Resolve a single class against ALREADY-EXTRACTED layer maps. Callers that
+ * resolve many classes against the same two directories (e.g. provisioning a
+ * full roster) should {@link extractClassesFromDir} each dir ONCE and reuse the
+ * result here, rather than paying a full directory re-scan per class. Precedence
+ * is identical to {@link resolvePersona}: override layer wins, then baseline.
+ */
+export async function resolvePersonaFrom(
+  klass: string,
+  layers: { rolesDir: string; overrideDir: string; base: DirClasses; over: DirClasses },
+): Promise<PersonaResolution | null> {
+  const { rolesDir, overrideDir, base, over } = layers;
 
   const fromLayer = async (
     dir: string,

packages/mosaic/src/commands/fleet-provision.spec.ts

@@ -0,0 +1,270 @@
+import { access, mkdir, mkdtemp, rm, writeFile } from 'node:fs/promises';
+import { constants } from 'node:fs';
+import { tmpdir } from 'node:os';
+import { dirname, join, resolve } from 'node:path';
+import { fileURLToPath } from 'node:url';
+import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
+import { loadFleetRoster } from './fleet.js';
+import { generateRoster, runProvision } from './fleet-provision.js';
+import { loadProfile } from './fleet-profiles.js';
+
+// These are INTEGRATION tests: each exercises real filesystem I/O — scanning the
+// committed framework/fleet persona library, rendering YAML, writing to a temp
+// mosaicHome, and round-tripping through the real roster parser. On a heavily
+// contended CI runner (the whole monorepo's suites run in parallel) that genuine
+// I/O can exceed vitest's 5s default even though it completes in ~400ms locally.
+// Give the legitimately I/O-bound work generous headroom so CI is deterministic.
+vi.setConfig({ testTimeout: 30_000 });
+
+// The real, committed library: packages/mosaic/src/commands -> framework/fleet.
+const frameworkFleet = resolve(
+  dirname(fileURLToPath(import.meta.url)),
+  '..',
+  '..',
+  'framework',
+  'fleet',
+);
+const rolesDir = join(frameworkFleet, 'roles');
+const profilesDir = join(frameworkFleet, 'profiles');
+
+/** A fresh temp mosaicHome whose fleet/ dir is empty (for write-path tests). */
+async function freshMosaicHome(): Promise<string> {
+  const home = await mkdtemp(join(tmpdir(), 'mosaic-provision-'));
+  await mkdir(join(home, 'fleet'), { recursive: true });
+  return home;
+}
+
+async function fileExists(path: string): Promise<boolean> {
+  try {
+    await access(path, constants.F_OK);
+    return true;
+  } catch {
+    return false;
+  }
+}
+
+describe('provision software-delivery (floor, default)', () => {
+  it('materializes only the floor seats with correct flags + valid scaffold', async () => {
+    const profile = await loadProfile('software-delivery', { profilesDir, rolesDir });
+    const { seats, yaml } = await generateRoster(profile, { profilesDir, rolesDir });
+
+    // Floor is orchestrator + enhancer.
+    expect(seats.map((s) => s.name).sort()).toEqual(['enhancer', 'orchestrator']);
+    const orch = seats.find((s) => s.name === 'orchestrator');
+    const enh = seats.find((s) => s.name === 'enhancer');
+    // RULE 2: floor + lead get persistent_persona.
+    expect(orch?.persistentPersona).toBe(true);
+    expect(enh?.persistentPersona).toBe(true);
+    // RULE 3: floor/lead do NOT reset between tasks.
+    expect(orch?.resetBetweenTasks).toBeUndefined();
+    expect(enh?.resetBetweenTasks).toBeUndefined();
+    // RULE 4: default runtime claude.
+    expect(orch?.runtime).toBe('claude');
+
+    // Scaffold round-trips through the real parser.
+    expect(yaml).toContain('version: 1');
+    expect(yaml).toContain('transport: tmux');
+    expect(yaml).toContain('socket_name: mosaic-fleet');
+  });
+});
+
+describe('provision --full', () => {
+  it('expands the entire roster, including multiplicity, deterministically', async () => {
+    const profile = await loadProfile('software-delivery', { profilesDir, rolesDir });
+    const { seats } = await generateRoster(profile, { full: true, profilesDir, rolesDir });
+
+    const names = seats.map((s) => s.name);
+    // code multiplicity 2 -> code0/code1 (RULE 1).
+    expect(names).toContain('code0');
+    expect(names).toContain('code1');
+    expect(names).not.toContain('code');
+    // Singleton seats keep the bare class name.
+    expect(names).toContain('planner');
+    expect(names).toContain('merge-gate');
+
+    // Deterministic ordering: profile roster order, multiplicity expanded inline.
+    const codeIdx0 = names.indexOf('code0');
+    expect(names[codeIdx0 + 1]).toBe('code1');
+
+    // RULE 3: a non-floor, non-lead execution seat resets between tasks.
+    const code0 = seats.find((s) => s.name === 'code0');
+    expect(code0?.resetBetweenTasks).toBe(true);
+    expect(code0?.persistentPersona).toBeUndefined();
+
+    // Seat count == sum of multiplicities.
+    const expected = profile.roster.reduce((n, e) => n + e.multiplicity, 0);
+    expect(seats.length).toBe(expected);
+  });
+});
+
+describe('generated roster round-trips through the real parser', () => {
+  it('feeds generated YAML back through loadFleetRoster (key correctness proof)', async () => {
+    const home = await freshMosaicHome();
+    try {
+      const result = await runProvision('software-delivery', {
+        mosaicHome: home,
+        profilesDir,
+        rolesDir,
+        full: true,
+        write: true,
+      });
+      expect(result.wrote).toBe(join(home, 'fleet', 'roster.yaml'));
+
+      const parsed = await loadFleetRoster(result.wrote!);
+      // It parses with no error and carries every seat.
+      const profile = await loadProfile('software-delivery', { profilesDir, rolesDir });
+      const expected = profile.roster.reduce((n, e) => n + e.multiplicity, 0);
+      expect(parsed.agents.length).toBe(expected);
+      // Classes survive the round-trip.
+      expect(parsed.agents.some((a) => a.className === 'orchestrator')).toBe(true);
+      expect(parsed.agents.filter((a) => a.className === 'code').length).toBe(2);
+      // reports_to must NOT have been emitted (parser rejects unknown keys).
+      expect(result.yaml).not.toContain('reports_to');
+    } finally {
+      await rm(home, { recursive: true, force: true });
+    }
+  });
+});
+
+describe('override-aware persona validation', () => {
+  let dir: string;
+  beforeEach(async () => {
+    dir = await mkdtemp(join(tmpdir(), 'mosaic-provision-ov-'));
+  });
+  afterEach(async () => {
+    await rm(dir, { recursive: true, force: true });
+  });
+
+  it('resolves a user-added (roles.local-only) persona without a false unresolved error', async () => {
+    const overrideDir = join(dir, 'roles.local');
+    const customProfilesDir = join(dir, 'profiles');
+    await mkdir(overrideDir, { recursive: true });
+    await mkdir(customProfilesDir, { recursive: true });
+    // A brand-new class that exists ONLY in roles.local.
+    await writeFile(
+      join(overrideDir, 'widget-maker.md'),
+      '# widget-maker\n\nThe widget-maker persona (`class: widget-maker`).\n',
+    );
+    await writeFile(
+      join(customProfilesDir, 'custom.yaml'),
+      [
+        'id: custom',
+        'title: Custom',
+        'description: a custom system',
+        'lead: widget-maker',
+        'floor: [widget-maker]',
+        'roster:',
+        '  - class: widget-maker',
+        '',
+      ].join('\n'),
+    );
+
+    const result = await runProvision('custom', {
+      mosaicHome: dir,
+      profilesDir: customProfilesDir,
+      // Point baseline rolesDir at a missing dir so resolution depends on override.
+      rolesDir: join(dir, 'no-baseline'),
+      overrideDir,
+    });
+    expect(result.yaml).toContain('class: widget-maker');
+    // It resolved from the override layer.
+    // (generateRoster records personaLayer; the seat is present.)
+    expect(result.summary).toContain('persona=override');
+  });
+
+  it('FAILS with a clear message when a profile references a bogus class', async () => {
+    const customProfilesDir = join(dir, 'profiles');
+    await mkdir(customProfilesDir, { recursive: true });
+    await writeFile(
+      join(customProfilesDir, 'bogus.yaml'),
+      [
+        'id: bogus',
+        'title: Bogus',
+        'description: bad system',
+        'lead: orchestrator',
+        'floor: [orchestrator]',
+        'roster:',
+        '  - class: orchestrator',
+        '  - class: not-a-real-persona-xyz',
+        '    reports_to: orchestrator',
+        '',
+      ].join('\n'),
+    );
+    await expect(
+      runProvision('bogus', {
+        mosaicHome: dir,
+        profilesDir: customProfilesDir,
+        rolesDir,
+        overrideDir: join(dir, 'roles.local'),
+      }),
+    ).rejects.toThrow(/not-a-real-persona-xyz|not a known persona class/);
+  });
+});
+
+describe('--write protection', () => {
+  it('refuses to clobber an existing roster.yaml without --force', async () => {
+    const home = await freshMosaicHome();
+    try {
+      const rosterPath = join(home, 'fleet', 'roster.yaml');
+      await writeFile(rosterPath, 'version: 1\n# operator customizations\n');
+      await expect(
+        runProvision('software-delivery', { mosaicHome: home, profilesDir, rolesDir, write: true }),
+      ).rejects.toThrow(/Refusing to overwrite/);
+      // The original file is untouched.
+      const { readFile } = await import('node:fs/promises');
+      expect(await readFile(rosterPath, 'utf8')).toContain('operator customizations');
+    } finally {
+      await rm(home, { recursive: true, force: true });
+    }
+  });
+
+  it('--write --force overwrites an existing roster', async () => {
+    const home = await freshMosaicHome();
+    try {
+      const rosterPath = join(home, 'fleet', 'roster.yaml');
+      await writeFile(rosterPath, 'version: 1\n# old\n');
+      const result = await runProvision('software-delivery', {
+        mosaicHome: home,
+        profilesDir,
+        rolesDir,
+        write: true,
+        force: true,
+      });
+      expect(result.wrote).toBe(rosterPath);
+      const parsed = await loadFleetRoster(rosterPath);
+      expect(parsed.agents.length).toBeGreaterThan(0);
+    } finally {
+      await rm(home, { recursive: true, force: true });
+    }
+  });
+
+  it('--write to a fresh mosaicHome creates the roster file', async () => {
+    const home = await freshMosaicHome();
+    try {
+      const result = await runProvision('software-delivery', {
+        mosaicHome: home,
+        profilesDir,
+        rolesDir,
+        write: true,
+      });
+      expect(await fileExists(result.wrote!)).toBe(true);
+    } finally {
+      await rm(home, { recursive: true, force: true });
+    }
+  });
+
+  it('dry run (no --write) writes nothing', async () => {
+    const home = await freshMosaicHome();
+    try {
+      const result = await runProvision('software-delivery', {
+        mosaicHome: home,
+        profilesDir,
+        rolesDir,
+      });
+      expect(result.wrote).toBeUndefined();
+      expect(await fileExists(join(home, 'fleet', 'roster.yaml'))).toBe(false);
+    } finally {
+      await rm(home, { recursive: true, force: true });
+    }
+  });
+});

packages/mosaic/src/commands/fleet-provision.ts

@@ -0,0 +1,406 @@
+/**
+ * `mosaic fleet provision --profile <id>` — turn a declared SYSTEM TYPE (a
+ * profile) into a concrete fleet roster (North Star H3).
+ *
+ * A profile (fleet/profiles/<id>.yaml) is a DECLARATIVE mapping from a system
+ * type to a persona roster + org topology (H2). This command MATERIALIZES that
+ * declaration into the concrete `roster.yaml` shape the live fleet consumes — the
+ * same shape `fleet.ts` parses (version/transport/tmux/defaults/runtimes/agents).
+ *
+ * DRY-RUN-FIRST + REVIEWABLE: with no --write it prints the roster it WOULD
+ * generate plus a topology summary and writes nothing. --write persists it, and
+ * REFUSES to clobber an existing roster.yaml without --force (protects operator
+ * customizations).
+ *
+ * DRY: profile parsing/validation is reused wholesale from fleet-profiles.ts
+ * (loadProfile/validateProfile) and persona resolution from fleet-personas.ts
+ * (resolvePersona, override-aware). This module owns ONLY the profile→roster
+ * generation policy, documented inline below so each default is reviewable.
+ */
+
+import { access, mkdir, writeFile } from 'node:fs/promises';
+import { constants } from 'node:fs';
+import { homedir } from 'node:os';
+import { dirname, join } from 'node:path';
+import type { Command } from 'commander';
+import YAML from 'yaml';
+import {
+  loadProfile,
+  validateProfile,
+  type FleetProfile,
+  type ProfileRosterEntry,
+  defaultProfilesDir,
+  defaultRolesDir,
+  listPersonaClassesWithOverrides,
+} from './fleet-profiles.js';
+import {
+  defaultOverrideDir,
+  extractClassesFromDir,
+  resolvePersonaFrom,
+  type PersonaLayer,
+} from './fleet-personas.js';
+
+function defaultMosaicHome(): string {
+  return process.env['MOSAIC_HOME'] ?? join(homedir(), '.config', 'mosaic');
+}
+
+// ---------------------------------------------------------------------------
+// GENERATION RULES — each default below is intentionally simple and documented
+// so a reviewer can ratify or override the policy. See the PR body for the open
+// runtime-per-class question (RULE 4).
+// ---------------------------------------------------------------------------
+
+/**
+ * RULE 4 — Runtime assignment policy (THE one open design question).
+ *
+ * Default: EVERY seat → `runtime: claude`. Claude runs every persona, so it is
+ * the safe universal default and guarantees a structurally-valid, launchable
+ * roster regardless of how the policy ultimately lands. We deliberately do NOT
+ * hardcode pi / gpt-5.5 per class here. The live roster today runs coders on
+ * pi + openai-codex/gpt-5.5:high — whether provisioning should encode a
+ * class→runtime/model map (and WHERE: the profile schema vs a separate
+ * runtime-policy file) is flagged in the PR body for ratification.
+ *
+ * Centralized so changing the policy is a ONE-edit change. If a future profile
+ * entry (or persona) declares a runtime/model preference, honor it here; until
+ * then everything defaults to claude.
+ */
+export const DEFAULT_RUNTIME = 'claude';
+
+/** Result of applying the runtime policy to one seat. */
+interface RuntimeChoice {
+  runtime: string;
+  modelHint?: string;
+}
+
+/**
+ * The single centralized runtime-policy function. Today it returns the universal
+ * `claude` default for every seat. To encode a class→runtime/model map later,
+ * edit ONLY this function (and/or extend the profile schema and read it here).
+ */
+export function resolveSeatRuntime(
+  _klass: string,
+  _isFloor: boolean,
+  _isLead: boolean,
+): RuntimeChoice {
+  return { runtime: DEFAULT_RUNTIME };
+}
+
+/** One generated seat, fully resolved for emission + topology display. */
+export interface GeneratedSeat {
+  name: string;
+  className: string;
+  runtime: string;
+  modelHint?: string;
+  persistentPersona?: boolean;
+  resetBetweenTasks?: boolean;
+  /** Topology edge from the profile (NOT emitted to roster.yaml — see RULE 6). */
+  reportsTo?: string;
+  /** Which persona layer the class resolved from (baseline/override). */
+  personaLayer: PersonaLayer;
+}
+
+export interface GenerateRosterResult {
+  seats: GeneratedSeat[];
+  /** The roster.yaml text (parser-valid, drop-in). */
+  yaml: string;
+}
+
+export interface ProvisionOptions {
+  /** Materialize the entire profile roster (multiplicity expanded). */
+  full?: boolean;
+  mosaicHome?: string;
+  /** Test overrides — mirror fleet-profiles LoadProfilesOptions. */
+  profilesDir?: string;
+  rolesDir?: string;
+  overrideDir?: string;
+}
+
+function resolveDirs(opts: ProvisionOptions): {
+  mosaicHome: string;
+  profilesDir: string;
+  rolesDir: string;
+  overrideDir: string;
+} {
+  const mosaicHome = opts.mosaicHome ?? defaultMosaicHome();
+  return {
+    mosaicHome,
+    profilesDir: opts.profilesDir ?? defaultProfilesDir(mosaicHome),
+    rolesDir: opts.rolesDir ?? defaultRolesDir(mosaicHome),
+    overrideDir: opts.overrideDir ?? defaultOverrideDir(mosaicHome),
+  };
+}
+
+/**
+ * RULE 1 — Seat naming. multiplicity 1 → name = class (e.g. `planner`).
+ * multiplicity N>1 → `<class>0`,`<class>1`,… (e.g. `code` ×2 → code0/code1).
+ * Names are deterministic, following profile roster order.
+ */
+function seatNames(entry: ProfileRosterEntry): string[] {
+  if (entry.multiplicity <= 1) return [entry.class];
+  return Array.from({ length: entry.multiplicity }, (_, i) => `${entry.class}${i}`);
+}
+
+/**
+ * Generate the concrete seats + roster.yaml for a validated profile.
+ *
+ * Seat selection:
+ *   --full  → the ENTIRE profile roster, multiplicity expanded.
+ *   default → ONLY the `floor` classes (the always-staffed minimum), matching
+ *             the profile note "two-agent floor always staffed; every other seat
+ *             added on demand."
+ *
+ * Per-seat flags:
+ *   RULE 2 persistent_persona: true for floor classes AND the lead; else omitted.
+ *   RULE 3 reset_between_tasks: true for non-floor, non-lead execution seats;
+ *           floor/lead omit it (mirrors today's coders resetting while the
+ *           orchestrator/enhancer do not).
+ *   RULE 4 runtime: via resolveSeatRuntime (defaults claude).
+ *   RULE 6 reports_to: tracked on the seat for the topology summary but NOT
+ *           emitted to roster.yaml — the fleet.ts parser rejects unknown agent
+ *           keys, so writing reports_to would break round-trip. Confirmed against
+ *           normalizeAgent's allow-list in fleet.ts.
+ *
+ * Persona resolution: every emitted class is resolved override-aware via
+ * resolvePersona so we can (a) record the layer for the summary and (b) refuse
+ * to emit a roster that references a nonexistent persona.
+ */
+export async function generateRoster(
+  profile: FleetProfile,
+  opts: ProvisionOptions,
+): Promise<GenerateRosterResult> {
+  const { rolesDir, overrideDir } = resolveDirs(opts);
+  const floor = new Set(profile.floor);
+  const lead = profile.lead;
+
+  const selected: ProfileRosterEntry[] = opts.full
+    ? profile.roster
+    : profile.roster.filter((e) => floor.has(e.class));
+
+  // Scan the persona directories ONCE, then resolve every roster entry against
+  // the in-memory maps. resolvePersona() would otherwise re-scan both dirs per
+  // entry — O(entries × files) redundant reads that push --full provisioning
+  // past the test timeout on slow/contended filesystems.
+  const [base, over] = await Promise.all([
+    extractClassesFromDir(rolesDir),
+    extractClassesFromDir(overrideDir),
+  ]);
+
+  const seats: GeneratedSeat[] = [];
+  for (const entry of selected) {
+    const isFloor = floor.has(entry.class);
+    const isLead = entry.class === lead;
+
+    const resolved = await resolvePersonaFrom(entry.class, { rolesDir, overrideDir, base, over });
+    if (!resolved) {
+      // Defensive: validateProfile already guards this, but a class can resolve
+      // for membership yet have no readable file. Fail loudly rather than emit a
+      // roster pointing at a persona we cannot load.
+      throw new Error(
+        `Cannot provision: roster class "${entry.class}" does not resolve to a readable persona.`,
+      );
+    }
+
+    const runtimeChoice = resolveSeatRuntime(entry.class, isFloor, isLead);
+    for (const name of seatNames(entry)) {
+      const seat: GeneratedSeat = {
+        name,
+        className: entry.class,
+        runtime: runtimeChoice.runtime,
+        personaLayer: resolved.layer,
+      };
+      if (runtimeChoice.modelHint) seat.modelHint = runtimeChoice.modelHint;
+      if (isFloor || isLead) seat.persistentPersona = true;
+      if (!isFloor && !isLead) seat.resetBetweenTasks = true;
+      if (entry.reportsTo) seat.reportsTo = entry.reportsTo;
+      seats.push(seat);
+    }
+  }
+
+  if (seats.length === 0) {
+    throw new Error(
+      `Profile "${profile.id}" produced no seats. ` +
+        (opts.full ? 'Its roster is empty.' : 'No floor seats are defined — try --full.'),
+    );
+  }
+
+  return { seats, yaml: renderRosterYaml(seats) };
+}
+
+/**
+ * RULE 5 — Standard roster scaffolding. We emit the same generic, non-personal
+ * scaffold the committed example presets use (socket_name: mosaic-fleet,
+ * holder_session: _holder, working_directory: ~, claude + pi runtimes) so the
+ * output is a drop-in valid roster. No operator-personal data is copied.
+ *
+ * Built via the `yaml` lib (same serializer the parser uses) so the result
+ * round-trips. reports_to is intentionally NOT included on agents (RULE 6).
+ */
+function renderRosterYaml(seats: GeneratedSeat[]): string {
+  const agents = seats.map((s) => {
+    const a: Record<string, unknown> = {
+      name: s.name,
+      runtime: s.runtime,
+      class: s.className,
+    };
+    if (s.persistentPersona) a['persistent_persona'] = true;
+    if (s.modelHint) a['model_hint'] = s.modelHint;
+    if (s.resetBetweenTasks) a['reset_between_tasks'] = true;
+    return a;
+  });
+
+  const doc = {
+    version: 1,
+    transport: 'tmux',
+    tmux: { socket_name: 'mosaic-fleet', holder_session: '_holder' },
+    defaults: { working_directory: '~' },
+    runtimes: {
+      claude: { reset_command: '/clear' },
+      pi: { reset_command: '/new' },
+    },
+    agents,
+  };
+
+  return YAML.stringify(doc);
+}
+
+// ---------------------------------------------------------------------------
+// Validation — reuse fleet-profiles.validateProfile (override-aware classes) and
+// name any unresolved class clearly. Never generate a roster referencing a
+// nonexistent persona.
+// ---------------------------------------------------------------------------
+
+/**
+ * Validate the profile against the override-aware persona library. Throws with a
+ * clear, class-naming message if any referenced class is unresolved.
+ */
+export async function validateProfileForProvision(
+  profile: FleetProfile,
+  opts: ProvisionOptions,
+): Promise<void> {
+  const { rolesDir, overrideDir } = resolveDirs(opts);
+  const validClasses = await listPersonaClassesWithOverrides(rolesDir, overrideDir);
+  const problems = validateProfile(profile, validClasses);
+  if (problems.length > 0) {
+    throw new Error(
+      `Profile "${profile.id}" is invalid; cannot provision:\n  - ${problems.join('\n  - ')}`,
+    );
+  }
+}
+
+// ---------------------------------------------------------------------------
+// Topology summary (printed in dry-run and after write).
+// ---------------------------------------------------------------------------
+
+function formatTopologySummary(seats: GeneratedSeat[]): string {
+  const lines: string[] = [];
+  lines.push(`Topology (${seats.length} seat(s)):`);
+  for (const s of seats) {
+    const reports = s.reportsTo ? `reports_to=${s.reportsTo}` : 'reports_to=- (lead)';
+    lines.push(
+      `  - ${s.name}\tclass=${s.className}\truntime=${s.runtime}\t${reports}\tpersona=${s.personaLayer}`,
+    );
+  }
+  return lines.join('\n');
+}
+
+// ---------------------------------------------------------------------------
+// CLI wiring — mirror registerFleetProfileCommand / registerFleetPersonaCommand.
+// ---------------------------------------------------------------------------
+
+export interface ProvisionRunResult {
+  yaml: string;
+  summary: string;
+  wrote?: string;
+}
+
+/**
+ * Core provision flow shared by the CLI: load + validate the profile, generate
+ * the roster, optionally write it. Returns the artifacts for printing/testing.
+ */
+export async function runProvision(
+  profileId: string,
+  opts: ProvisionOptions & { write?: boolean; force?: boolean },
+): Promise<ProvisionRunResult> {
+  const dirs = resolveDirs(opts);
+  const profile = await loadProfile(profileId, {
+    mosaicHome: dirs.mosaicHome,
+    profilesDir: dirs.profilesDir,
+    rolesDir: dirs.rolesDir,
+    overrideDir: dirs.overrideDir,
+  });
+  // loadProfile already validates, but re-run with our explicit error wording so
+  // an unresolved class is named clearly even if invoked directly.
+  await validateProfileForProvision(profile, opts);
+
+  const { seats, yaml } = await generateRoster(profile, opts);
+  const summary = formatTopologySummary(seats);
+
+  if (!opts.write) {
+    return { yaml, summary };
+  }
+
+  const rosterPath = join(dirs.mosaicHome, 'fleet', 'roster.yaml');
+  if (!opts.force) {
+    let exists = false;
+    try {
+      await access(rosterPath, constants.F_OK);
+      exists = true;
+    } catch {
+      exists = false;
+    }
+    if (exists) {
+      throw new Error(
+        `Refusing to overwrite existing roster: ${rosterPath}. ` +
+          `Pass --force to overwrite, or edit it by hand.`,
+      );
+    }
+  }
+  await mkdir(dirname(rosterPath), { recursive: true });
+  await writeFile(rosterPath, yaml, 'utf8');
+  return { yaml, summary, wrote: rosterPath };
+}
+
+/**
+ * Register `provision` under an existing `fleet` command. `mosaicHomeFor`
+ * resolves the active --mosaic-home (parent flag) at call time, exactly like the
+ * profile/persona/backlog subcommands.
+ */
+export function registerFleetProvisionCommand(
+  fleetCmd: Command,
+  mosaicHomeFor: () => string,
+): Command {
+  const provisionCmd = fleetCmd
+    .command('provision')
+    .description('Materialize a roster.yaml from a system-type profile (H3). DRY-RUN by default.')
+    .requiredOption('--profile <id>', 'System-type profile id to provision')
+    .option('--full', 'Materialize the entire profile roster (default: floor seats only)')
+    .option('--write', 'Write the generated roster to <mosaicHome>/fleet/roster.yaml')
+    .option('--force', 'Overwrite an existing roster.yaml (requires --write)')
+    .action(async (opts: { profile: string; full?: boolean; write?: boolean; force?: boolean }) => {
+      try {
+        const result = await runProvision(opts.profile, {
+          mosaicHome: mosaicHomeFor(),
+          full: opts.full,
+          write: opts.write,
+          force: opts.force,
+        });
+        if (result.wrote) {
+          console.log(`Wrote roster: ${result.wrote}`);
+          console.log('');
+          console.log(result.summary);
+        } else {
+          // DRY RUN: print the roster it WOULD generate + topology, write nothing.
+          console.log('# DRY RUN — no files written. Re-run with --write to persist.');
+          console.log(result.yaml.trimEnd());
+          console.log('');
+          console.log(result.summary);
+        }
+      } catch (err) {
+        process.stderr.write(`${err instanceof Error ? err.message : String(err)}\n`);
+        process.exitCode = 1;
+      }
+    });
+
+  return provisionCmd;
+}

packages/mosaic/src/commands/fleet.spec.ts

@@ -84,6 +84,7 @@ describe('registerFleetCommand', () => {
       'install-systemd',
       'persona',
       'profile',
+      'provision',
       'ps',
       'remove',
       'restart',
@@ -246,6 +247,8 @@ describe('fleet roster parsing', () => {
     expect(generateAgentEnv(roster, getRosterAgent(roster, 'coder0'))).toBe(
       [
         'MOSAIC_AGENT_NAME=coder0',
+        // Reflects the roster's non-default `class: implementer` (A3a).
+        'MOSAIC_AGENT_CLASS=implementer',
         'MOSAIC_AGENT_RUNTIME=codex',
         'MOSAIC_AGENT_MODEL=',
         'MOSAIC_AGENT_WORKDIR=/srv/mosaic',
@@ -255,6 +258,40 @@ describe('fleet roster parsing', () => {
     );
   });
 
+  it('emits MOSAIC_AGENT_CLASS=worker for an agent that declares no class', async () => {
+    cleanup = await tempDir();
+    const rosterPath = join(cleanup, 'roster.json');
+    await writeFile(
+      rosterPath,
+      JSON.stringify({
+        version: 1,
+        transport: 'tmux',
+        agents: [{ name: 'coder0', runtime: 'codex' }],
+      }),
+    );
+    const roster = await loadFleetRoster(rosterPath);
+    expect(generateAgentEnv(roster, getRosterAgent(roster, 'coder0'))).toContain(
+      'MOSAIC_AGENT_CLASS=worker\n',
+    );
+  });
+
+  it('shell-escapes MOSAIC_AGENT_CLASS so a launcher reads it verbatim', async () => {
+    cleanup = await tempDir();
+    const rosterPath = join(cleanup, 'roster.json');
+    await writeFile(
+      rosterPath,
+      JSON.stringify({
+        version: 1,
+        transport: 'tmux',
+        agents: [{ name: 'coder0', runtime: 'codex', class: 'orchestrator' }],
+      }),
+    );
+    const roster = await loadFleetRoster(rosterPath);
+    expect(generateAgentEnv(roster, getRosterAgent(roster, 'coder0'))).toContain(
+      'MOSAIC_AGENT_CLASS=orchestrator\n',
+    );
+  });
+
   it('preserves site-owned agent EnvironmentFile overrides while refreshing roster keys', () => {
     const generated = [
       'MOSAIC_AGENT_NAME=coder0',
@@ -286,6 +323,28 @@ describe('fleet roster parsing', () => {
     );
   });
 
+  it('updates (does not duplicate) MOSAIC_AGENT_CLASS on re-launch', () => {
+    const generated = [
+      'MOSAIC_AGENT_NAME=coder0',
+      'MOSAIC_AGENT_CLASS=orchestrator',
+      'MOSAIC_AGENT_RUNTIME=codex',
+      '',
+    ].join('\n');
+    const existing = [
+      'MOSAIC_AGENT_NAME=coder0',
+      'MOSAIC_AGENT_CLASS=worker',
+      'MOSAIC_AGENT_RUNTIME=codex',
+      '',
+    ].join('\n');
+
+    const merged = mergeAgentEnv(generated, existing);
+    // mergeAgentEnv keys by VAR name, so the regenerated CLASS wins and there is
+    // exactly one MOSAIC_AGENT_CLASS line (no stale worker value left behind).
+    expect(merged).toContain('MOSAIC_AGENT_CLASS=orchestrator');
+    expect(merged).not.toContain('MOSAIC_AGENT_CLASS=worker');
+    expect(merged.match(/^MOSAIC_AGENT_CLASS=/gm)).toHaveLength(1);
+  });
+
   it('rejects unknown roster fields instead of silently defaulting', async () => {
     cleanup = await tempDir();
     const rosterPath = join(cleanup, 'roster.yaml');

packages/mosaic/src/commands/fleet.ts

@@ -11,6 +11,7 @@ import { resolveCommsBlock } from '../fleet/comms-onboarding.js';
 import { registerFleetBacklogCommand } from './fleet-backlog.js';
 import { registerFleetPersonaCommand } from './fleet-personas.js';
 import { registerFleetProfileCommand } from './fleet-profiles.js';
+import { registerFleetProvisionCommand } from './fleet-provision.js';
 
 /**
  * A function that spawns a command with inherited stdio (TTY passthrough).
@@ -490,6 +491,9 @@ export function generateAgentEnv(roster: FleetRoster, agent: FleetAgent): string
   const workingDirectory = agent.workingDirectory ?? roster.defaults.workingDirectory;
   return [
     `MOSAIC_AGENT_NAME=${shellEnvValue(agent.name)}`,
+    // Per-agent class → start-agent-session.sh / launcher reads this to inject the
+    // matching persona contract for the agent's class (default `worker`).
+    `MOSAIC_AGENT_CLASS=${shellEnvValue(agent.className)}`,
     `MOSAIC_AGENT_RUNTIME=${shellEnvValue(agent.runtime)}`,
     // Per-agent model hint → start-agent-session.sh appends `--model <hint>` to
     // the `mosaic yolo` launch so workers run on the roster's model (e.g. pi on
@@ -1717,6 +1721,10 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
   // --mosaic-home flag.
   registerFleetPersonaCommand(cmd, () => cmd.opts<{ mosaicHome: string }>().mosaicHome);
 
+  // Provisioning (H3): materialize a concrete roster.yaml from a system-type
+  // profile. DRY-RUN by default; --write persists under the same --mosaic-home.
+  registerFleetProvisionCommand(cmd, () => cmd.opts<{ mosaicHome: string }>().mosaicHome);
+
   return cmd;
 }
 

packages/mosaic/vitest.config.ts

@@ -4,5 +4,6 @@ export default defineConfig({
   test: {
     globals: true,
     environment: 'node',
+    testTimeout: 30_000,
   },
 });