fix(gateway): sanitize raw exceptions in /mcp status + /reload sources (P3 re-review#5 blocker)

Co-Authored-By: Claude Haiku 4.5 <[email protected]>

.gitignore

@@ -8,6 +8,7 @@ coverage
 .env.local
 *.tsbuildinfo
 .pnpm-store
+__pycache__/
 docs/reports/
 
 # Step-CA dev password — real file is gitignored; commit only the .example

.husky/pre-push

@@ -1 +1 @@
-pnpm typecheck && pnpm lint && pnpm format:check
+pnpm preflight && pnpm typecheck && pnpm lint && pnpm format:check

.npmrc

@@ -1,5 +1,5 @@
 @mosaicstack:registry=https://git.mosaicstack.dev/api/packages/mosaicstack/npm/
-# Pin the pnpm store to the same path the ci-base image warms (Dockerfile.ci),
+# HOME resolves to /root in the ci-base image, preserving its warmed-store path.
-# so the pipeline `pnpm install --prefer-offline` consumes the baked store
+# Non-root checkouts use their own HOME. Override without editing this file via
-# instead of repopulating a fresh one.
+# NPM_CONFIG_STORE_DIR (pnpm's environment form of the store-dir setting).
-store-dir=/root/.local/share/pnpm/store
+store-dir=${HOME}/.local/share/pnpm/store

.woodpecker/publish.yml

@@ -1,5 +1,5 @@
 # Build, publish npm packages, and push Docker images
-# Runs only on main branch push/tag
+# Runs on main for stable publishes and on next for integration-line prereleases/images
 
 variables:
   # Pre-baked CI base (see .woodpecker/ci-image.yml): node:24-alpine +
@@ -23,9 +23,21 @@ variables:
           - 'docs/**'
           - '**/*.md'
           - '.woodpecker/**'
+    - event: [push, manual]
+      branch: next
+  - &main_image_build_when
+    - event: tag
+    - event: [push, manual]
+      branch: main
+      path:
+        exclude:
+          - 'packages/mosaic/**'
+          - 'docs/**'
+          - '**/*.md'
+          - '.woodpecker/**'
 
 when:
-  - branch: [main]
+  - branch: [main, next]
     event: [push, manual, tag]
 
 steps:
@@ -103,6 +115,84 @@ steps:
     depends_on:
       - build
 
+  publish-next-npm:
+    image: *node_image
+    # Durable @next integration-line publish. Runs only on next; never writes
+    # the latest dist-tag and never commits the computed prerelease versions.
+    when:
+      - event: [push, manual]
+        branch: next
+    environment:
+      NPM_TOKEN:
+        from_secret: gitea_token
+      CI_COMMIT_BRANCH: ${CI_COMMIT_BRANCH}
+      CI_PIPELINE_NUMBER: ${CI_PIPELINE_NUMBER}
+    commands:
+      - *enable_pnpm
+      - |
+        if [ "$CI_COMMIT_BRANCH" != "next" ]; then
+          echo "[publish-next] FATAL: publish-next-npm may only run on next (got '$CI_COMMIT_BRANCH')" >&2
+          exit 1
+        fi
+        if [ -z "$CI_PIPELINE_NUMBER" ]; then
+          echo "[publish-next] FATAL: CI_PIPELINE_NUMBER is required for prerelease versioning" >&2
+          exit 1
+        fi
+        echo "//git.mosaicstack.dev/api/packages/mosaicstack/npm/:_authToken=$NPM_TOKEN" > ~/.npmrc
+        echo "@mosaicstack:registry=https://git.mosaicstack.dev/api/packages/mosaicstack/npm/" >> ~/.npmrc
+        DIST_TAGS_JSON="$(npm view @mosaicstack/mosaic dist-tags --registry https://git.mosaicstack.dev/api/packages/mosaicstack/npm/ --json)"
+        DIST_TAGS_JSON="$DIST_TAGS_JSON" node -e 'const tags = JSON.parse(process.env.DIST_TAGS_JSON || "{}"); if (!tags || typeof tags !== "object" || !Object.hasOwn(tags, "latest")) { throw new Error("Gitea npm registry did not return a usable dist-tags object"); } console.log("[publish-next] registry dist-tags OK: latest=" + tags.latest);'
+        node <<'NODE'
+        const fs = require('node:fs');
+        const path = require('node:path');
+
+        const pipelineNumber = process.env.CI_PIPELINE_NUMBER;
+        const roots = ['apps', 'packages', 'plugins'];
+        const updated = [];
+
+        function walk(dir) {
+          if (!fs.existsSync(dir)) return;
+          for (const entry of fs.readdirSync(dir, { withFileTypes: true })) {
+            if (entry.name === 'node_modules' || entry.name === 'dist' || entry.name === '.turbo') continue;
+            const fullPath = path.join(dir, entry.name);
+            if (entry.isDirectory()) {
+              const packagePath = path.join(fullPath, 'package.json');
+              if (fs.existsSync(packagePath)) updatePackage(packagePath);
+              walk(fullPath);
+            }
+          }
+        }
+
+        function updatePackage(packagePath) {
+          const manifest = JSON.parse(fs.readFileSync(packagePath, 'utf8'));
+          if (!manifest.name?.startsWith('@mosaicstack/') || manifest.private) return;
+          const stableMatch = /^(\d+)\.(\d+)\.(\d+)(?:[-+].*)?$/.exec(manifest.version);
+          if (!stableMatch) {
+            throw new Error(manifest.name + " has unsupported semver version '" + manifest.version + "'");
+          }
+          const [, major, minor, patch] = stableMatch;
+          const oldVersion = manifest.version;
+          manifest.version = major + '.' + minor + '.' + (Number(patch) + 1) + '-next.' + pipelineNumber;
+          fs.writeFileSync(packagePath, JSON.stringify(manifest, null, 2) + '\n');
+          updated.push(manifest.name + ' ' + oldVersion + ' -> ' + manifest.version);
+        }
+
+        for (const root of roots) walk(root);
+        if (updated.length === 0) throw new Error('No publishable @mosaicstack/* packages found');
+        console.log('[publish-next] computed prerelease versions for ' + updated.length + ' packages:');
+        for (const line of updated) console.log('[publish-next] ' + line);
+        NODE
+        pnpm --filter "@mosaicstack/*" --filter "!@mosaicstack/web" --filter "!@mosaicstack/mosaic-as" publish --no-git-checks --access public --tag next
+        EXPECTED_VERSION="$(node -p "require('./packages/mosaic/package.json').version")"
+        RESOLVED_VERSION="$(npm view @mosaicstack/mosaic@next version --registry https://git.mosaicstack.dev/api/packages/mosaicstack/npm/)"
+        if [ "$RESOLVED_VERSION" != "$EXPECTED_VERSION" ]; then
+          echo "[publish-next] FATAL: @mosaicstack/mosaic@next resolved '$RESOLVED_VERSION', expected '$EXPECTED_VERSION'" >&2
+          exit 1
+        fi
+        echo "[publish-next] @mosaicstack/mosaic@next resolves to $RESOLVED_VERSION"
+    depends_on:
+      - build
+
   # TODO: Uncomment when ready to publish to npmjs.org
   # publish-npmjs:
   #   image: *node_image
@@ -134,8 +224,17 @@ steps:
       - echo "{\"auths\":{\"git.mosaicstack.dev\":{\"username\":\"$REGISTRY_USER\",\"password\":\"$REGISTRY_PASS\"}}}" > /kaniko/.docker/config.json
       - |
         DESTINATIONS="--destination git.mosaicstack.dev/mosaicstack/stack/gateway:sha-${CI_COMMIT_SHA:0:7}"
-        if [ "$CI_COMMIT_BRANCH" = "main" ]; then
+        if [ "$CI_COMMIT_BRANCH" = "next" ]; then
+          if [ -n "$CI_COMMIT_TAG" ]; then
+            echo "[publish] FATAL: next gateway publish must be sha-only; refusing tag '$CI_COMMIT_TAG'" >&2
+            exit 1
+          fi
+          echo "[publish] next gateway publish is sha-only"
+        elif [ "$CI_COMMIT_BRANCH" = "main" ]; then
           DESTINATIONS="$DESTINATIONS --destination git.mosaicstack.dev/mosaicstack/stack/gateway:latest"
+        elif [ -z "$CI_COMMIT_TAG" ]; then
+          echo "[publish] FATAL: gateway image publish may only run for main, next, or tag events" >&2
+          exit 1
         fi
         if [ -n "$CI_COMMIT_TAG" ]; then
           DESTINATIONS="$DESTINATIONS --destination git.mosaicstack.dev/mosaicstack/stack/gateway:$CI_COMMIT_TAG"
@@ -146,7 +245,7 @@ steps:
 
   build-appservice:
     image: gcr.io/kaniko-project/executor:debug
-    when: *image_build_when
+    when: *main_image_build_when
     environment:
       REGISTRY_USER:
         from_secret: gitea_username
@@ -172,7 +271,7 @@ steps:
 
   build-web:
     image: gcr.io/kaniko-project/executor:debug
-    when: *image_build_when
+    when: *main_image_build_when
     environment:
       REGISTRY_USER:
         from_secret: gitea_username

README.md

@@ -30,6 +30,16 @@ This installs both components:
 | **Framework**           | Bash launcher, guides, runtime configs, tools, skills            | `~/.config/mosaic/`  |
 | **@mosaicstack/mosaic** | Unified `mosaic` CLI — TUI, gateway client, wizard, auto-updater | `~/.npm-global/bin/` |
 
+### Install lanes
+
+| Lane                     | Command                               | Use when                                              | Source                                                                  |
+| ------------------------ | ------------------------------------- | ----------------------------------------------------- | ----------------------------------------------------------------------- |
+| Stable                   | `bash tools/install.sh`               | You want the released Mosaic CLI/framework            | npm registry `@mosaicstack/mosaic@latest` + framework archive at `main` |
+| Prerelease integration   | `bash tools/install.sh --next`        | You want the current `next` integration branch        | Build-from-source at `next`                                             |
+| Contributor/source build | `bash tools/install.sh --dev --ref X` | You are testing a branch before release; `--ref` wins | Build-from-source at the requested ref                                  |
+
+`--next` is shorthand for the prerelease integration lane: it enables source-build mode and uses `next` unless an explicit `--ref` or `MOSAIC_REF` is provided.
+
 After install, the wizard runs automatically or you can invoke it manually:
 
 ```bash
@@ -201,8 +211,21 @@ git clone [email protected]:mosaicstack/stack.git
 cd stack
 
 # Install dependencies. The local tier uses in-process PGlite; leave DATABASE_URL unset.
+# The pnpm store defaults to $HOME/.local/share/pnpm/store. Override it without
+# editing the checkout with NPM_CONFIG_STORE_DIR=$HOME/another-store if needed.
 pnpm install
 
+# Verify dependencies and generated state before running source-quality gates.
+# Missing dependencies exit 42; stale/foreign apps/web/.next state exits 43.
+# The web build certifies its exact standalone symlink manifest; added, removed,
+# retargeted, or manifest-only-tampered generated links also exit 43. This detects
+# accidental, independent, stale, and foreign-residue mutation—the class exposed by
+# a five-month-stale .next that produced 19 phantom TS2307 errors.
+# It does NOT defend against a same-UID actor that can rewrite both manifest and
+# marker consistently (CWE-345). RM-59 tracks the required executor/spine-side
+# trust anchor outside worktree authority.
+pnpm preflight
+
 # Optional local queue service only. This does not start PostgreSQL.
 docker compose up -d valkey
 
@@ -230,6 +253,7 @@ Gateway start command until KBN-101-02 makes that state fail closed.
 ### Quality Gates
 
 ```bash
+pnpm preflight               # Checkout/dependency/generated-state validation
 pnpm typecheck               # TypeScript type checking (all packages)
 pnpm lint                    # ESLint (all packages)
 pnpm test                    # Vitest (all packages)
@@ -347,7 +371,9 @@ The CLI also performs a background update check on every invocation (cached for
 bash tools/install.sh --check           # Version check only
 bash tools/install.sh --framework       # Framework only (skip npm CLI)
 bash tools/install.sh --cli             # npm CLI only (skip framework)
-bash tools/install.sh --ref v1.0        # Install from a specific git ref
+bash tools/install.sh --next            # Prerelease lane: source build from next
+bash tools/install.sh --dev             # Contributor lane: source build at --ref/main
+bash tools/install.sh --ref v1.0        # Install from a specific git ref (--ref wins over --next)
 bash tools/install.sh --yes             # Non-interactive, accept all defaults
 bash tools/install.sh --no-auto-launch  # Skip auto-launch of wizard
 ```

apps/gateway/src/__tests__/integration/federation-m3-list.integration.test.ts

@@ -0,0 +1,519 @@
+/**
+ * Federation M3 single-gateway integration tests (FED-M3-10).
+ *
+ * Covers MILESTONES.md M3 acceptance:
+ *  - #6: malformed certificate OIDs fail with 401; valid cert + revoked grant fails with 403.
+ *  - #7: max_rows_per_query caps list results.
+ *
+ * Strategy:
+ *  - Real PostgreSQL via @mosaicstack/db.
+ *  - Mocked TLS context/Fastify request shim for FederationAuthGuard.
+ *  - Direct controller calls using the real POST /api/federation/v1/list/:resource contract.
+ *
+ * Run:
+ *   FEDERATED_INTEGRATION=1 pnpm --filter @mosaicstack/gateway test -- \
+ *     src/__tests__/integration/federation-m3-list.integration.test.ts
+ */
+
+import 'reflect-metadata';
+import * as crypto from 'node:crypto';
+import type { ExecutionContext } from '@nestjs/common';
+import { Test, type TestingModule } from '@nestjs/testing';
+import type { FastifyReply, FastifyRequest } from 'fastify';
+import {
+  and,
+  createDb,
+  eq,
+  federationGrants,
+  federationPeers,
+  inArray,
+  missionTasks,
+  missions,
+  projects,
+  tasks,
+  teamMembers,
+  teams,
+  type Db,
+  type DbHandle,
+  users,
+} from '@mosaicstack/db';
+import { afterAll, beforeAll, describe, expect, it } from 'vitest';
+import { DB } from '../../database/database.module.js';
+import { GrantsService } from '../../federation/grants.service.js';
+import { FederationAuthGuard } from '../../federation/server/federation-auth.guard.js';
+import { FederationScopeService } from '../../federation/server/scope.service.js';
+import { FederationListQueryService } from '../../federation/server/verbs/list-query.service.js';
+import { ListController } from '../../federation/server/verbs/list.controller.js';
+import {
+  makeMosaicIssuedCert,
+  makeSelfSignedCert,
+} from '../../federation/__tests__/helpers/test-cert.js';
+
+const run = process.env['FEDERATED_INTEGRATION'] === '1';
+const PG_URL = process.env['DATABASE_URL'] ?? 'postgresql://mosaic:mosaic@localhost:5433/mosaic';
+const RUN_ID = `fed-m3-10-${crypto.randomUUID()}`;
+const CERT_SERIAL_HEX = crypto.randomUUID().replace(/-/g, '').toUpperCase();
+
+interface TestIds {
+  readonly subjectUserId: string;
+  readonly otherUserId: string;
+  readonly peerId: string;
+  readonly revokedPeerId: string;
+  readonly activeGrantId: string;
+  readonly revokedGrantId: string;
+  readonly subjectProjectId: string;
+  readonly subjectMissionId: string;
+  readonly otherProjectId: string;
+  readonly teamId: string;
+  readonly unauthorizedTeamId: string;
+  readonly teamProjectId: string;
+  readonly taskIds: readonly string[];
+  readonly excludedTaskIds: readonly string[];
+  readonly subjectNoteId: string;
+  readonly otherUserNoteId: string;
+}
+
+function pemToDer(pem: string): Buffer {
+  return Buffer.from(
+    pem
+      .replace(/-----BEGIN CERTIFICATE-----/, '')
+      .replace(/-----END CERTIFICATE-----/, '')
+      .replace(/\s+/g, ''),
+    'base64',
+  );
+}
+
+function makeFederationRequest(certPem: string): FastifyRequest {
+  return {
+    raw: {
+      socket: {
+        getPeerCertificate: () => ({
+          raw: pemToDer(certPem),
+          serialNumber: CERT_SERIAL_HEX,
+        }),
+      },
+    },
+  } as unknown as FastifyRequest;
+}
+
+function makeGuardContext(request: FastifyRequest): {
+  readonly context: ExecutionContext;
+  readonly sent: { statusCode?: number; payload?: unknown };
+} {
+  const sent: { statusCode?: number; payload?: unknown } = {};
+  const reply = {
+    status: (statusCode: number) => {
+      sent.statusCode = statusCode;
+      return {
+        header: () => ({
+          send: (payload: unknown) => {
+            sent.payload = payload;
+          },
+        }),
+      };
+    },
+  } as unknown as FastifyReply;
+
+  const context = {
+    switchToHttp: () => ({
+      getRequest: () => request,
+      getResponse: () => reply,
+    }),
+  } as unknown as ExecutionContext;
+
+  return { context, sent };
+}
+
+async function insertUser(db: Db, id: string, label: string): Promise<void> {
+  await db.insert(users).values({
+    id,
+    name: `${RUN_ID}-${label}`,
+    email: `${RUN_ID}-${label}@federation-test.invalid`,
+    emailVerified: false,
+  });
+}
+
+async function seedFixtures(db: Db): Promise<TestIds> {
+  const subjectUserId = `${RUN_ID}-subject`;
+  const otherUserId = `${RUN_ID}-other`;
+  const peerId = crypto.randomUUID();
+  const revokedPeerId = crypto.randomUUID();
+  const activeGrantId = crypto.randomUUID();
+  const revokedGrantId = crypto.randomUUID();
+  const subjectProjectId = crypto.randomUUID();
+  const subjectMissionId = crypto.randomUUID();
+  const otherProjectId = crypto.randomUUID();
+  const teamId = crypto.randomUUID();
+  const unauthorizedTeamId = crypto.randomUUID();
+  const teamProjectId = crypto.randomUUID();
+  const taskIds = [crypto.randomUUID(), crypto.randomUUID(), crypto.randomUUID()] as const;
+  const excludedTaskIds = [crypto.randomUUID(), crypto.randomUUID()] as const;
+  const subjectNoteId = crypto.randomUUID();
+  const otherUserNoteId = crypto.randomUUID();
+
+  await insertUser(db, subjectUserId, 'subject');
+  await insertUser(db, otherUserId, 'other');
+
+  await db.insert(teams).values([
+    {
+      id: teamId,
+      name: `${RUN_ID} allowed team`,
+      slug: `${RUN_ID}-allowed-team`,
+      ownerId: subjectUserId,
+      managerId: subjectUserId,
+    },
+    {
+      id: unauthorizedTeamId,
+      name: `${RUN_ID} unauthorized team`,
+      slug: `${RUN_ID}-unauthorized-team`,
+      ownerId: otherUserId,
+      managerId: otherUserId,
+    },
+  ]);
+
+  await db.insert(teamMembers).values([
+    { teamId, userId: subjectUserId, role: 'member' },
+    { teamId: unauthorizedTeamId, userId: subjectUserId, role: 'member' },
+  ]);
+
+  await db.insert(projects).values([
+    {
+      id: subjectProjectId,
+      name: `${RUN_ID} subject personal project`,
+      ownerType: 'user',
+      ownerId: subjectUserId,
+    },
+    {
+      id: otherProjectId,
+      name: `${RUN_ID} other personal project`,
+      ownerType: 'user',
+      ownerId: otherUserId,
+    },
+    {
+      id: teamProjectId,
+      name: `${RUN_ID} unauthorized team project`,
+      ownerType: 'team',
+      teamId: unauthorizedTeamId,
+    },
+  ]);
+
+  await db.insert(missions).values({
+    id: subjectMissionId,
+    name: `${RUN_ID} subject mission`,
+    projectId: subjectProjectId,
+    userId: subjectUserId,
+  });
+
+  await db.insert(tasks).values([
+    {
+      id: taskIds[0],
+      title: `${RUN_ID} visible task 1`,
+      missionId: subjectMissionId,
+      createdAt: new Date('2026-06-25T03:00:00.000Z'),
+      updatedAt: new Date('2026-06-25T03:00:00.000Z'),
+    },
+    {
+      id: taskIds[1],
+      title: `${RUN_ID} visible task 2`,
+      projectId: subjectProjectId,
+      createdAt: new Date('2026-06-25T02:00:00.000Z'),
+      updatedAt: new Date('2026-06-25T02:00:00.000Z'),
+    },
+    {
+      id: taskIds[2],
+      title: `${RUN_ID} visible task 3`,
+      projectId: subjectProjectId,
+      createdAt: new Date('2026-06-25T01:00:00.000Z'),
+      updatedAt: new Date('2026-06-25T01:00:00.000Z'),
+    },
+    {
+      id: excludedTaskIds[0],
+      title: `${RUN_ID} other user task`,
+      projectId: otherProjectId,
+      createdAt: new Date('2026-06-25T04:00:00.000Z'),
+      updatedAt: new Date('2026-06-25T04:00:00.000Z'),
+    },
+    {
+      id: excludedTaskIds[1],
+      title: `${RUN_ID} unauthorized team task`,
+      projectId: teamProjectId,
+      createdAt: new Date('2026-06-25T05:00:00.000Z'),
+      updatedAt: new Date('2026-06-25T05:00:00.000Z'),
+    },
+  ]);
+
+  await db.insert(missionTasks).values([
+    {
+      id: subjectNoteId,
+      missionId: subjectMissionId,
+      userId: subjectUserId,
+      notes: `${RUN_ID} subject visible note`,
+      createdAt: new Date('2026-06-25T03:30:00.000Z'),
+      updatedAt: new Date('2026-06-25T03:30:00.000Z'),
+    },
+    {
+      id: otherUserNoteId,
+      missionId: subjectMissionId,
+      userId: otherUserId,
+      notes: `${RUN_ID} other user note on subject mission`,
+      createdAt: new Date('2026-06-25T04:30:00.000Z'),
+      updatedAt: new Date('2026-06-25T04:30:00.000Z'),
+    },
+  ]);
+
+  await db.insert(federationPeers).values([
+    {
+      id: peerId,
+      commonName: `${RUN_ID}-active-peer`,
+      displayName: `${RUN_ID} Active Peer`,
+      certPem: '-----BEGIN CERTIFICATE-----\nMOCK\n-----END CERTIFICATE-----\n',
+      certSerial: CERT_SERIAL_HEX,
+      certNotAfter: new Date(Date.now() + 86_400_000),
+      state: 'active',
+    },
+    {
+      id: revokedPeerId,
+      commonName: `${RUN_ID}-revoked-peer`,
+      displayName: `${RUN_ID} Revoked Peer`,
+      certPem: '-----BEGIN CERTIFICATE-----\nMOCK\n-----END CERTIFICATE-----\n',
+      certSerial: `${CERT_SERIAL_HEX}${RUN_ID.replace(/-/g, '').slice(0, 8).toUpperCase()}`,
+      certNotAfter: new Date(Date.now() + 86_400_000),
+      state: 'active',
+    },
+  ]);
+
+  await db.insert(federationGrants).values([
+    {
+      id: activeGrantId,
+      peerId,
+      subjectUserId,
+      status: 'active',
+      scope: {
+        resources: ['tasks', 'notes'],
+        excluded_resources: [],
+        filters: {
+          tasks: { include_personal: true, include_teams: [] },
+          notes: { include_personal: true, include_teams: [] },
+        },
+        max_rows_per_query: 2,
+      },
+    },
+    {
+      id: revokedGrantId,
+      peerId,
+      subjectUserId,
+      status: 'revoked',
+      revokedAt: new Date(),
+      revokedReason: `${RUN_ID} revoked grant fixture`,
+      scope: {
+        resources: ['tasks'],
+        excluded_resources: [],
+        max_rows_per_query: 2,
+      },
+    },
+  ]);
+
+  return {
+    subjectUserId,
+    otherUserId,
+    peerId,
+    revokedPeerId,
+    activeGrantId,
+    revokedGrantId,
+    subjectProjectId,
+    subjectMissionId,
+    otherProjectId,
+    teamId,
+    unauthorizedTeamId,
+    teamProjectId,
+    taskIds,
+    excludedTaskIds,
+    subjectNoteId,
+    otherUserNoteId,
+  };
+}
+
+async function cleanupFixtures(db: Db, ids: TestIds | undefined): Promise<void> {
+  if (!ids) {
+    return;
+  }
+
+  await db
+    .delete(missionTasks)
+    .where(inArray(missionTasks.id, [ids.subjectNoteId, ids.otherUserNoteId]))
+    .catch(() => {});
+  await db
+    .delete(tasks)
+    .where(inArray(tasks.id, [...ids.taskIds, ...ids.excludedTaskIds]))
+    .catch(() => {});
+  await db
+    .delete(missions)
+    .where(eq(missions.id, ids.subjectMissionId))
+    .catch(() => {});
+  await db
+    .delete(projects)
+    .where(inArray(projects.id, [ids.subjectProjectId, ids.otherProjectId, ids.teamProjectId]))
+    .catch(() => {});
+  await db
+    .delete(teamMembers)
+    .where(
+      and(
+        eq(teamMembers.userId, ids.subjectUserId),
+        inArray(teamMembers.teamId, [ids.teamId, ids.unauthorizedTeamId]),
+      ),
+    )
+    .catch(() => {});
+  await db
+    .delete(teams)
+    .where(inArray(teams.id, [ids.teamId, ids.unauthorizedTeamId]))
+    .catch(() => {});
+  await db
+    .delete(federationGrants)
+    .where(inArray(federationGrants.id, [ids.activeGrantId, ids.revokedGrantId]))
+    .catch(() => {});
+  await db
+    .delete(federationPeers)
+    .where(inArray(federationPeers.id, [ids.peerId, ids.revokedPeerId]))
+    .catch(() => {});
+  await db
+    .delete(users)
+    .where(inArray(users.id, [ids.subjectUserId, ids.otherUserId]))
+    .catch(() => {});
+}
+
+describe.skipIf(!run)('federation M3 list verb — single-gateway integration', () => {
+  let handle: DbHandle;
+  let db: Db;
+  let moduleRef: TestingModule;
+  let guard: FederationAuthGuard;
+  let listController: ListController;
+  let ids: TestIds | undefined;
+
+  beforeAll(async () => {
+    handle = createDb(PG_URL);
+    db = handle.db;
+    ids = await seedFixtures(db);
+
+    moduleRef = await Test.createTestingModule({
+      controllers: [ListController],
+      providers: [
+        { provide: DB, useValue: db },
+        GrantsService,
+        FederationAuthGuard,
+        FederationScopeService,
+        FederationListQueryService,
+      ],
+    }).compile();
+
+    guard = moduleRef.get(FederationAuthGuard);
+    listController = moduleRef.get(ListController);
+  }, 30_000);
+
+  afterAll(async () => {
+    await moduleRef?.close().catch((e: unknown) => console.error('[fed-m3-10 cleanup]', e));
+    await cleanupFixtures(db, ids).catch((e: unknown) => console.error('[fed-m3-10 cleanup]', e));
+    await handle?.close().catch((e: unknown) => console.error('[fed-m3-10 cleanup]', e));
+  });
+
+  it('#6 — rejects a client cert with malformed/missing Mosaic OIDs with 401', async () => {
+    const malformedOidCert = await makeSelfSignedCert();
+    const request = makeFederationRequest(malformedOidCert);
+    const { context, sent } = makeGuardContext(request);
+
+    await expect(guard.canActivate(context)).resolves.toBe(false);
+    expect(sent.statusCode).toBe(401);
+    expect(sent.payload).toMatchObject({
+      error: {
+        code: 'unauthorized',
+        message: expect.stringContaining('missing required OID'),
+      },
+    });
+    expect(request.federationContext).toBeUndefined();
+  });
+
+  it('#6 — rejects a valid client cert when its grant is revoked with 403', async () => {
+    expect(ids).toBeDefined();
+    const revokedCert = await makeMosaicIssuedCert({
+      grantId: ids!.revokedGrantId,
+      subjectUserId: ids!.subjectUserId,
+    });
+    const request = makeFederationRequest(revokedCert);
+    const { context, sent } = makeGuardContext(request);
+
+    await expect(guard.canActivate(context)).resolves.toBe(false);
+    expect(sent.statusCode).toBe(403);
+    expect(sent.payload).toMatchObject({
+      error: {
+        code: 'forbidden',
+        message: 'Federation access denied',
+      },
+    });
+    expect(request.federationContext).toBeUndefined();
+  });
+
+  it('#7 — enforces max_rows_per_query on POST /api/federation/v1/list/:resource', async () => {
+    expect(ids).toBeDefined();
+    const activeCert = await makeMosaicIssuedCert({
+      grantId: ids!.activeGrantId,
+      subjectUserId: ids!.subjectUserId,
+    });
+    const request = makeFederationRequest(activeCert);
+    const { context } = makeGuardContext(request);
+
+    await expect(guard.canActivate(context)).resolves.toBe(true);
+
+    const response = await listController.list('tasks', request, { limit: 100 });
+    const returnedIds = response.items.map((item) => item['id']);
+
+    expect(response.items).toHaveLength(2);
+    expect(response._truncated).toBe(true);
+    expect(response.nextCursor).toEqual(expect.any(String));
+    expect(returnedIds).toEqual([ids!.taskIds[0], ids!.taskIds[1]]);
+    expect(returnedIds).not.toContain(ids!.taskIds[2]);
+    for (const excludedId of ids!.excludedTaskIds) {
+      expect(returnedIds).not.toContain(excludedId);
+    }
+    expect(response.items.every((item) => item._source === 'local')).toBe(true);
+  });
+
+  it('excludes another user mission task notes on the same authorized mission', async () => {
+    expect(ids).toBeDefined();
+    const activeCert = await makeMosaicIssuedCert({
+      grantId: ids!.activeGrantId,
+      subjectUserId: ids!.subjectUserId,
+    });
+    const request = makeFederationRequest(activeCert);
+    const { context } = makeGuardContext(request);
+
+    await expect(guard.canActivate(context)).resolves.toBe(true);
+
+    const response = await listController.list('notes', request, { limit: 10 });
+    const returnedIds = response.items.map((item) => item['id']);
+
+    expect(returnedIds).toEqual([ids!.subjectNoteId]);
+    expect(returnedIds).not.toContain(ids!.otherUserNoteId);
+    expect(response.items.every((item) => item._source === 'local')).toBe(true);
+  });
+
+  it('fails closed for unsupported list resources', async () => {
+    expect(ids).toBeDefined();
+    const activeCert = await makeMosaicIssuedCert({
+      grantId: ids!.activeGrantId,
+      subjectUserId: ids!.subjectUserId,
+    });
+    const request = makeFederationRequest(activeCert);
+    const { context } = makeGuardContext(request);
+
+    await expect(guard.canActivate(context)).resolves.toBe(true);
+
+    await expect(listController.list('widgets', request, {})).rejects.toMatchObject({
+      response: {
+        error: {
+          code: 'scope_violation',
+          message: 'Requested federation resource is not supported',
+        },
+      },
+      status: 403,
+    });
+  });
+});

apps/gateway/src/admin/admin-health.controller.ts

@@ -1,9 +1,11 @@
-import { Controller, Get, Inject, UseGuards } from '@nestjs/common';
+import { Controller, Get, Inject, Optional, UseGuards } from '@nestjs/common';
 import { sql, type Db } from '@mosaicstack/db';
 import { createQueue } from '@mosaicstack/queue';
+import type { MosaicConfig } from '@mosaicstack/config';
 import { DB } from '../database/database.module.js';
 import { AgentService } from '../agent/agent.service.js';
 import { ProviderService } from '../agent/provider.service.js';
+import { MOSAIC_CONFIG } from '../config/config.module.js';
 import { AdminGuard } from './admin.guard.js';
 import type { HealthStatusDto, ServiceStatusDto } from './admin.dto.js';
 
@@ -14,6 +16,9 @@ export class AdminHealthController {
     @Inject(DB) private readonly db: Db,
     @Inject(AgentService) private readonly agentService: AgentService,
     @Inject(ProviderService) private readonly providerService: ProviderService,
+    @Optional()
+    @Inject(MOSAIC_CONFIG)
+    private readonly mosaicConfig: MosaicConfig | null,
   ) {}
 
   @Get()
@@ -55,6 +60,14 @@ export class AdminHealthController {
   }
 
   private async checkCache(): Promise<ServiceStatusDto> {
+    // On Local tier there is no Redis. The cache is intentionally absent, which
+    // is a healthy state for this tier — report 'ok' rather than opening a new
+    // ioredis connection on every admin health check (which would spam
+    // ECONNREFUSED and create/destroy a connection per request). latencyMs 0
+    // signals "no cache backend to measure" for this tier.
+    if (this.mosaicConfig?.queue?.type === 'local') {
+      return { status: 'ok', latencyMs: 0 };
+    }
     const start = Date.now();
     const handle = createQueue();
     try {

apps/gateway/src/commands/command-executor-p8012.spec.ts

@@ -1,3 +1,4 @@
+import { Logger } from '@nestjs/common';
 import { describe, it, expect, vi, beforeEach } from 'vitest';
 import { CommandExecutorService } from './command-executor.service.js';
 import type { SlashCommandPayload } from '@mosaicstack/types';
@@ -12,6 +13,7 @@ const mockRegistry = {
       { name: 'agent', aliases: ['a'], scope: 'agent', execution: 'socket', available: true },
       { name: 'prdy', aliases: [], scope: 'agent', execution: 'socket', available: true },
       { name: 'tools', aliases: [], scope: 'agent', execution: 'socket', available: true },
+      { name: 'mcp', aliases: [], scope: 'agent', execution: 'socket', available: true },
     ],
     skills: [],
   })),
@@ -72,17 +74,24 @@ const mockChatGateway = {
   broadcastSessionInfo: vi.fn(),
 };
 
-function buildService(): CommandExecutorService {
+function buildService(
+  redis: typeof mockRedis | null = mockRedis,
+  mcpClient: {
+    reconnectServer: ReturnType<typeof vi.fn>;
+    getServerStatuses: ReturnType<typeof vi.fn>;
+    getToolDefinitions: ReturnType<typeof vi.fn>;
+  } | null = null,
+): CommandExecutorService {
   return new CommandExecutorService(
     mockRegistry as never,
     mockAgentService as never,
     mockSystemOverride as never,
     mockSessionGC as never,
-    mockRedis as never,
+    redis as never,
     mockBrain as never,
     null,
     mockChatGateway as never,
-    null,
+    mcpClient as never,
   );
 }
 
@@ -131,6 +140,22 @@ describe('CommandExecutorService — P8-012 commands', () => {
     expect(ttl).toBe(300);
   });
 
+  it('/provider login remains available without Redis on the local tier', async () => {
+    const localService = buildService(null);
+    const payload: SlashCommandPayload = {
+      command: 'provider',
+      args: 'login anthropic',
+      conversationId,
+    };
+
+    const result = await localService.execute(payload, userScope);
+
+    expect(result.success).toBe(true);
+    expect(result.message).not.toContain('token=');
+    expect(result.data).toEqual({ provider: 'anthropic' });
+    expect(mockRedis.set).not.toHaveBeenCalled();
+  });
+
   // /provider with no args — returns usage
   it('/provider with no args returns usage message', async () => {
     const payload: SlashCommandPayload = { command: 'provider', conversationId };
@@ -242,4 +267,124 @@ describe('CommandExecutorService — P8-012 commands', () => {
     expect(result.command).toBe('tools');
     expect(result.message).toContain('tools');
   });
+
+  // Top-level catch sanitization (P3-4 re-review finding #1): a rejected
+  // Redis `set` inside /provider login is the only reachable path into the
+  // top-level catch in `execute()`. The raw exception must be logged
+  // server-side but never handed back to the socket client.
+  it('sanitizes the top-level command catch, logging the raw exception but never returning it to the client', async () => {
+    const distinctiveRawFailure = 'ECONNREFUSED distinctive-raw-redis-failure-token-9f31';
+    const rawError = new Error(distinctiveRawFailure);
+    const failingRedis = {
+      set: vi.fn().mockRejectedValue(rawError),
+      get: vi.fn(),
+      del: vi.fn(),
+    };
+    const failingService = buildService(failingRedis as unknown as typeof mockRedis);
+    const loggerErrorSpy = vi.spyOn(Logger.prototype, 'error').mockImplementation(() => undefined);
+
+    const payload: SlashCommandPayload = {
+      command: 'provider',
+      args: 'login anthropic',
+      conversationId,
+    };
+    const result = await failingService.execute(payload, userScope);
+
+    expect(result.success).toBe(false);
+    expect(result.command).toBe('provider');
+    expect(result.message).toBe('Command failed due to an internal error.');
+    expect(result.message).not.toContain(distinctiveRawFailure);
+    expect(result.message).not.toContain('ECONNREFUSED');
+
+    // The real exception is still logged server-side, as the raw Error
+    // object itself (not stringified/interpolated into the log message).
+    expect(loggerErrorSpy).toHaveBeenCalled();
+    const loggedRawError = loggerErrorSpy.mock.calls.some((call) => call.includes(rawError));
+    expect(loggedRawError).toBe(true);
+
+    loggerErrorSpy.mockRestore();
+  });
+
+  // Inner catch sanitization (P3-5 operator ruling): every catch in
+  // command-executor.service.ts that returns a SlashCommandResultPayload
+  // must sanitize the client-facing message the same way the top-level
+  // catch does, while still logging the raw exception server-side.
+  it('/agent new sanitizes agent-creation failures, logging the raw exception but never returning it to the client', async () => {
+    const marker = new Error('distinctive-agent-create-failure-token-A17f');
+    mockBrain.agents.create.mockRejectedValueOnce(marker);
+    const loggerErrorSpy = vi.spyOn(Logger.prototype, 'error').mockImplementation(() => undefined);
+
+    const payload: SlashCommandPayload = {
+      command: 'agent',
+      args: 'new my-new-agent',
+      conversationId,
+    };
+    const result = await service.execute(payload, userScope);
+
+    expect(result.success).toBe(false);
+    expect(result.command).toBe('agent');
+    expect(result.message).toBe('Failed to create agent due to an internal error.');
+    expect(result.message).not.toContain('distinctive-agent-create-failure-token-A17f');
+
+    expect(loggerErrorSpy).toHaveBeenCalled();
+    const loggedRawError = loggerErrorSpy.mock.calls.some((call) => call.includes(marker));
+    expect(loggedRawError).toBe(true);
+
+    loggerErrorSpy.mockRestore();
+  });
+
+  it('/agent <name> switch sanitizes agent-lookup failures, logging the raw exception but never returning it to the client', async () => {
+    const marker = new Error('distinctive-agent-switch-failure-token-B29c');
+    mockBrain.agents.findByName.mockRejectedValueOnce(marker);
+    const loggerErrorSpy = vi.spyOn(Logger.prototype, 'error').mockImplementation(() => undefined);
+
+    const payload: SlashCommandPayload = {
+      command: 'agent',
+      args: 'some-other-agent',
+      conversationId,
+    };
+    const result = await service.execute(payload, userScope);
+
+    expect(result.success).toBe(false);
+    expect(result.command).toBe('agent');
+    expect(result.message).toBe('Failed to switch agent due to an internal error.');
+    expect(result.message).not.toContain('distinctive-agent-switch-failure-token-B29c');
+
+    expect(loggerErrorSpy).toHaveBeenCalled();
+    const loggedRawError = loggerErrorSpy.mock.calls.some((call) => call.includes(marker));
+    expect(loggedRawError).toBe(true);
+
+    loggerErrorSpy.mockRestore();
+  });
+
+  it('/mcp reconnect sanitizes MCP client failures, logging the raw exception but never returning it to the client', async () => {
+    const marker = new Error('distinctive-mcp-reconnect-failure-token-C33e');
+    const mockMcpClient = {
+      reconnectServer: vi.fn().mockRejectedValue(marker),
+      getServerStatuses: vi.fn(() => []),
+      getToolDefinitions: vi.fn(() => []),
+    };
+    const mcpService = buildService(mockRedis, mockMcpClient);
+    const loggerErrorSpy = vi.spyOn(Logger.prototype, 'error').mockImplementation(() => undefined);
+
+    const payload: SlashCommandPayload = {
+      command: 'mcp',
+      args: 'reconnect my-server',
+      conversationId,
+    };
+    const result = await mcpService.execute(payload, userScope);
+
+    expect(result.success).toBe(false);
+    expect(result.command).toBe('mcp');
+    expect(result.message).toBe(
+      'Failed to reconnect MCP server "my-server" due to an internal error.',
+    );
+    expect(result.message).not.toContain('distinctive-mcp-reconnect-failure-token-C33e');
+
+    expect(loggerErrorSpy).toHaveBeenCalled();
+    const loggedRawError = loggerErrorSpy.mock.calls.some((call) => call.includes(marker));
+    expect(loggedRawError).toBe(true);
+
+    loggerErrorSpy.mockRestore();
+  });
 });

apps/gateway/src/commands/command-executor.service.ts

@@ -23,7 +23,10 @@ export class CommandExecutorService {
     @Inject(AgentService) private readonly agentService: AgentService,
     @Inject(SystemOverrideService) private readonly systemOverride: SystemOverrideService,
     @Inject(SessionGCService) private readonly sessionGC: SessionGCService,
-    @Inject(COMMANDS_REDIS) private readonly redis: QueueHandle['redis'],
+    // On Local tier COMMANDS_REDIS is null — provider login caching is skipped.
+    @Optional()
+    @Inject(COMMANDS_REDIS)
+    private readonly redis: QueueHandle['redis'] | null,
     @Inject(BRAIN) private readonly brain: Brain,
     @Optional()
     @Inject(forwardRef(() => ReloadService))
@@ -156,8 +159,13 @@ export class CommandExecutorService {
           };
       }
     } catch (err) {
-      this.logger.error(`Command /${command} failed: ${err}`);
+      this.logger.error(`Command /${command} failed`, err);
-      return { command, conversationId, success: false, message: String(err) };
+      return {
+        command,
+        conversationId,
+        success: false,
+        message: 'Command failed due to an internal error.',
+      };
     }
   }
 
@@ -333,11 +341,11 @@ export class CommandExecutorService {
           data: { agentId: newAgent.id, agentName: newAgent.name },
         };
       } catch (err) {
-        this.logger.error(`Failed to create agent: ${err}`);
+        this.logger.error(`Failed to create agent "${namePart}" for user ${userId}`, err);
         return {
           command: 'agent',
           success: false,
-          message: `Failed to create agent: ${String(err)}`,
+          message: 'Failed to create agent due to an internal error.',
           conversationId,
         };
       }
@@ -388,11 +396,11 @@ export class CommandExecutorService {
         data: { agentId: agentConfig.id, agentName: agentConfig.name, model: agentConfig.model },
       };
     } catch (err) {
-      this.logger.error(`Failed to switch agent "${agentName}": ${err}`);
+      this.logger.error(`Failed to switch agent "${agentName}"`, err);
       return {
         command: 'agent',
         success: false,
-        message: `Failed to switch agent: ${String(err)}`,
+        message: 'Failed to switch agent due to an internal error.',
         conversationId,
       };
     }
@@ -443,14 +451,16 @@ export class CommandExecutorService {
           byte.toString(16).padStart(2, '0'),
         ).join('');
         const key = `mosaic:auth:poll:${tokenHash}`;
-        // Persist only a short-lived token digest. The raw token is delivered only by
+        if (this.redis) {
-        // the authenticated dashboard flow, never in chat output or command metadata.
+          // Persist only a short-lived token digest. The raw token is delivered only by
-        await this.redis.set(
+          // the authenticated dashboard flow, never in chat output or command metadata.
-          key,
+          await this.redis.set(
-          JSON.stringify({ status: 'pending', provider: providerName, userId }),
+            key,
-          'EX',
+            JSON.stringify({ status: 'pending', provider: providerName, userId }),
-          300,
+            'EX',
-        );
+            300,
+          );
+        }
         return {
           command: 'provider',
           success: true,
@@ -603,11 +613,12 @@ export class CommandExecutorService {
             message: `MCP server "${serverName}" reconnected successfully.`,
           };
         } catch (err) {
+          this.logger.error(`Failed to reconnect MCP server "${serverName}"`, err);
           return {
             command: 'mcp',
             conversationId,
             success: false,
-            message: `Failed to reconnect MCP server "${serverName}": ${err instanceof Error ? err.message : String(err)}`,
+            message: `Failed to reconnect MCP server "${serverName}" due to an internal error.`,
           };
         }
       }

apps/gateway/src/commands/commands.module.ts

@@ -1,5 +1,7 @@
-import { forwardRef, Inject, Module, type OnApplicationShutdown } from '@nestjs/common';
+import { forwardRef, Inject, Module, Optional, type OnApplicationShutdown } from '@nestjs/common';
 import { createQueue, type QueueHandle } from '@mosaicstack/queue';
+import type { MosaicConfig } from '@mosaicstack/config';
+import { MOSAIC_CONFIG } from '../config/config.module.js';
 import { ChatModule } from '../chat/chat.module.js';
 import { GCModule } from '../gc/gc.module.js';
 import { ReloadModule } from '../reload/reload.module.js';
@@ -16,13 +18,17 @@ const COMMANDS_QUEUE_HANDLE = 'COMMANDS_QUEUE_HANDLE';
   providers: [
     {
       provide: COMMANDS_QUEUE_HANDLE,
-      useFactory: (): QueueHandle => {
+      useFactory: (config: MosaicConfig | null): QueueHandle | null => {
+        // On Local tier there is no Redis — skip the ioredis connection.
+        // CommandExecutorService falls back to no-cache for /provider login on local.
+        if (config?.queue?.type === 'local') return null;
         return createQueue();
       },
+      inject: [MOSAIC_CONFIG],
     },
     {
       provide: COMMANDS_REDIS,
-      useFactory: (handle: QueueHandle) => handle.redis,
+      useFactory: (handle: QueueHandle | null) => handle?.redis ?? null,
       inject: [COMMANDS_QUEUE_HANDLE],
     },
     CommandRegistryService,
@@ -38,9 +44,13 @@ const COMMANDS_QUEUE_HANDLE = 'COMMANDS_QUEUE_HANDLE';
   ],
 })
 export class CommandsModule implements OnApplicationShutdown {
-  constructor(@Inject(COMMANDS_QUEUE_HANDLE) private readonly handle: QueueHandle) {}
+  constructor(
+    @Optional()
+    @Inject(COMMANDS_QUEUE_HANDLE)
+    private readonly handle: QueueHandle | null,
+  ) {}
 
   async onApplicationShutdown(): Promise<void> {
-    await this.handle.close().catch(() => {});
+    await this.handle?.close().catch(() => {});
   }
 }

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

@@ -5,6 +5,8 @@ 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 { GetController } from './server/verbs/get.controller.js';
+import { FederationGetQueryService } from './server/verbs/get-query.service.js';
 import { GrantsService } from './grants.service.js';
 import { FederationClientService, QuerySourceService } from './client/index.js';
 import { FederationAuthGuard, FederationScopeService } from './server/index.js';
@@ -12,7 +14,13 @@ import { ListController } from './server/verbs/list.controller.js';
 import { FederationListQueryService } from './server/verbs/list-query.service.js';
 
 @Module({
-  controllers: [EnrollmentController, FederationController, CapabilitiesController, ListController],
+  controllers: [
+    EnrollmentController,
+    FederationController,
+    CapabilitiesController,
+    ListController,
+    GetController,
+  ],
   providers: [
     AdminGuard,
     CaService,
@@ -23,6 +31,7 @@ import { FederationListQueryService } from './server/verbs/list-query.service.js
     FederationAuthGuard,
     FederationScopeService,
     FederationListQueryService,
+    FederationGetQueryService,
   ],
   exports: [
     CaService,
@@ -33,6 +42,7 @@ import { FederationListQueryService } from './server/verbs/list-query.service.js
     FederationAuthGuard,
     FederationScopeService,
     FederationListQueryService,
+    FederationGetQueryService,
   ],
 })
 export class FederationModule {}

apps/gateway/src/federation/server/verbs/__tests__/get-query.service.spec.ts

@@ -0,0 +1,348 @@
+import { afterAll, beforeAll, describe, expect, it, vi } from 'vitest';
+import {
+  createPgliteDb,
+  missionTasks,
+  missions,
+  projects,
+  runPgliteMigrations,
+  teams,
+  users,
+  type Db,
+  type DbHandle,
+} from '@mosaicstack/db';
+import type { FederationScopeQueryFilter } from '../../scope.service.js';
+import { FederationGetQueryService } from '../get-query.service.js';
+
+const CREDENTIAL_FILTER: FederationScopeQueryFilter = {
+  resource: 'credentials',
+  subjectUserId: 'user-1',
+  includePersonal: true,
+  teamIds: [],
+  limit: 1,
+  maxRowsPerQuery: 25,
+};
+
+const SUBJECT_USER_ID = 'fed-m3-06-subject';
+const OTHER_USER_ID = 'fed-m3-06-other';
+const TEAM_ID = '06000000-0000-4000-8000-000000000001';
+const UNAUTHORIZED_TEAM_ID = '06000000-0000-4000-8000-000000000002';
+const PERSONAL_PROJECT_ID = '06000000-0000-4000-8000-000000000101';
+const TEAM_PROJECT_ID = '06000000-0000-4000-8000-000000000102';
+const UNAUTHORIZED_PROJECT_ID = '06000000-0000-4000-8000-000000000103';
+const PERSONAL_MISSION_ID = '06000000-0000-4000-8000-000000000201';
+const TEAM_MISSION_ID = '06000000-0000-4000-8000-000000000202';
+const UNAUTHORIZED_MISSION_ID = '06000000-0000-4000-8000-000000000203';
+const SUBJECT_TEAM_NOTE_ID = '06000000-0000-4000-8000-000000000301';
+const OTHER_TEAM_NOTE_ID = '06000000-0000-4000-8000-000000000302';
+const SUBJECT_PERSONAL_NOTE_ID = '06000000-0000-4000-8000-000000000303';
+const SUBJECT_UNAUTHORIZED_NOTE_ID = '06000000-0000-4000-8000-000000000304';
+
+let dbHandle: DbHandle | undefined;
+
+function makeService() {
+  return new FederationGetQueryService({} as Db);
+}
+
+function makeDbService() {
+  if (!dbHandle) {
+    throw new Error('test DB not initialized');
+  }
+  return new FederationGetQueryService(dbHandle.db);
+}
+
+async function seedNotesFixture() {
+  if (!dbHandle) {
+    throw new Error('test DB not initialized');
+  }
+
+  await dbHandle.db.insert(users).values([
+    {
+      id: SUBJECT_USER_ID,
+      name: 'Federation Subject',
+      email: `${SUBJECT_USER_ID}@example.test`,
+      emailVerified: false,
+    },
+    {
+      id: OTHER_USER_ID,
+      name: 'Federation Other',
+      email: `${OTHER_USER_ID}@example.test`,
+      emailVerified: false,
+    },
+  ]);
+
+  await dbHandle.db.insert(teams).values([
+    {
+      id: TEAM_ID,
+      name: 'FED-M3-06 Team',
+      slug: 'fed-m3-06-team',
+      ownerId: SUBJECT_USER_ID,
+      managerId: SUBJECT_USER_ID,
+    },
+    {
+      id: UNAUTHORIZED_TEAM_ID,
+      name: 'FED-M3-06 Unauthorized Team',
+      slug: 'fed-m3-06-unauthorized-team',
+      ownerId: OTHER_USER_ID,
+      managerId: OTHER_USER_ID,
+    },
+  ]);
+
+  await dbHandle.db.insert(projects).values([
+    {
+      id: PERSONAL_PROJECT_ID,
+      name: 'FED-M3-06 Personal Project',
+      ownerId: SUBJECT_USER_ID,
+      ownerType: 'user',
+    },
+    {
+      id: TEAM_PROJECT_ID,
+      name: 'FED-M3-06 Team Project',
+      teamId: TEAM_ID,
+      ownerType: 'team',
+    },
+    {
+      id: UNAUTHORIZED_PROJECT_ID,
+      name: 'FED-M3-06 Unauthorized Project',
+      teamId: UNAUTHORIZED_TEAM_ID,
+      ownerType: 'team',
+    },
+  ]);
+
+  await dbHandle.db.insert(missions).values([
+    {
+      id: PERSONAL_MISSION_ID,
+      name: 'FED-M3-06 Personal Mission',
+      projectId: PERSONAL_PROJECT_ID,
+      userId: SUBJECT_USER_ID,
+    },
+    {
+      id: TEAM_MISSION_ID,
+      name: 'FED-M3-06 Team Mission',
+      projectId: TEAM_PROJECT_ID,
+      userId: SUBJECT_USER_ID,
+    },
+    {
+      id: UNAUTHORIZED_MISSION_ID,
+      name: 'FED-M3-06 Unauthorized Mission',
+      projectId: UNAUTHORIZED_PROJECT_ID,
+      userId: SUBJECT_USER_ID,
+    },
+  ]);
+
+  await dbHandle.db.insert(missionTasks).values([
+    {
+      id: SUBJECT_TEAM_NOTE_ID,
+      missionId: TEAM_MISSION_ID,
+      userId: SUBJECT_USER_ID,
+      notes: 'subject note on team mission',
+      createdAt: new Date('2026-06-24T03:00:00.000Z'),
+      updatedAt: new Date('2026-06-24T03:00:00.000Z'),
+    },
+    {
+      id: OTHER_TEAM_NOTE_ID,
+      missionId: TEAM_MISSION_ID,
+      userId: OTHER_USER_ID,
+      notes: 'other user note on team mission',
+      createdAt: new Date('2026-06-24T02:00:00.000Z'),
+      updatedAt: new Date('2026-06-24T02:00:00.000Z'),
+    },
+    {
+      id: SUBJECT_PERSONAL_NOTE_ID,
+      missionId: PERSONAL_MISSION_ID,
+      userId: SUBJECT_USER_ID,
+      notes: 'subject note on personal mission',
+      createdAt: new Date('2026-06-24T01:00:00.000Z'),
+      updatedAt: new Date('2026-06-24T01:00:00.000Z'),
+    },
+    {
+      id: SUBJECT_UNAUTHORIZED_NOTE_ID,
+      missionId: UNAUTHORIZED_MISSION_ID,
+      userId: SUBJECT_USER_ID,
+      notes: 'subject note outside grant-visible missions',
+      createdAt: new Date('2026-06-24T04:00:00.000Z'),
+      updatedAt: new Date('2026-06-24T04:00:00.000Z'),
+    },
+  ]);
+}
+
+describe('FederationGetQueryService', () => {
+  beforeAll(async () => {
+    dbHandle = createPgliteDb(`memory://fed-m3-06-get-${Date.now()}`);
+    await runPgliteMigrations(dbHandle);
+    await seedNotesFixture();
+  });
+
+  afterAll(async () => {
+    await dbHandle?.close();
+    dbHandle = undefined;
+  });
+
+  it('denies sensitive resources in native RBAC for M3 get reads', async () => {
+    const service = makeService();
+
+    await expect(
+      service.evaluateReadAccess({
+        grantId: 'grant-1',
+        peerId: 'peer-1',
+        subjectUserId: 'user-1',
+        resource: 'credentials',
+      }),
+    ).resolves.toMatchObject({
+      allowed: false,
+      reason: 'credentials federation get access is not implemented in M3',
+    });
+  });
+
+  it('allows personal memory reads without requiring team lookup', async () => {
+    const service = makeService();
+
+    await expect(
+      service.evaluateReadAccess({
+        grantId: 'grant-1',
+        peerId: 'peer-1',
+        subjectUserId: 'user-1',
+        resource: 'memory',
+      }),
+    ).resolves.toEqual({
+      allowed: true,
+      access: { includePersonal: true, teamIds: [] },
+    });
+  });
+
+  it('uses subject team membership as the native RBAC upper bound for task and note reads', async () => {
+    const service = makeService();
+    const listSubjectTeamIds = vi.fn().mockResolvedValue(['team-1', 'team-2']);
+    (
+      service as unknown as {
+        listSubjectTeamIds: (subjectUserId: string) => Promise<string[]>;
+      }
+    ).listSubjectTeamIds = listSubjectTeamIds;
+
+    await expect(
+      service.evaluateReadAccess({
+        grantId: 'grant-1',
+        peerId: 'peer-1',
+        subjectUserId: 'user-1',
+        resource: 'tasks',
+      }),
+    ).resolves.toEqual({
+      allowed: true,
+      access: { includePersonal: true, teamIds: ['team-1', 'team-2'] },
+    });
+    expect(listSubjectTeamIds).toHaveBeenCalledWith('user-1');
+  });
+
+  it('does not query storage for sensitive get resources even if scope allowed them', async () => {
+    const service = makeService();
+
+    await expect(service.get({ filter: CREDENTIAL_FILTER, id: 'cred-1' })).resolves.toEqual({
+      status: 'denied',
+      reason: 'credentials federation get is not implemented',
+    });
+  });
+
+  it('fails closed for unsupported resources instead of returning undefined', async () => {
+    const service = makeService();
+
+    await expect(
+      service.get({
+        filter: {
+          ...CREDENTIAL_FILTER,
+          resource: 'unknown-resource' as FederationScopeQueryFilter['resource'],
+        },
+        id: 'row-1',
+      }),
+    ).resolves.toEqual({
+      status: 'denied',
+      reason: 'Unsupported federation get resource: unknown-resource',
+    });
+  });
+
+  it('does not leak another user mission task note through team-scoped get reads', async () => {
+    const service = makeDbService();
+
+    await expect(
+      service.get({
+        filter: {
+          resource: 'notes',
+          subjectUserId: SUBJECT_USER_ID,
+          includePersonal: false,
+          teamIds: [TEAM_ID],
+          limit: 1,
+          maxRowsPerQuery: 10,
+        },
+        id: OTHER_TEAM_NOTE_ID,
+      }),
+    ).resolves.toEqual({
+      status: 'denied',
+      reason: 'Note is outside the federated scope',
+    });
+  });
+
+  it('does not return subject notes from missions outside the grant-visible project set', async () => {
+    const service = makeDbService();
+
+    await expect(
+      service.get({
+        filter: {
+          resource: 'notes',
+          subjectUserId: SUBJECT_USER_ID,
+          includePersonal: true,
+          teamIds: [TEAM_ID],
+          limit: 1,
+          maxRowsPerQuery: 10,
+        },
+        id: SUBJECT_UNAUTHORIZED_NOTE_ID,
+      }),
+    ).resolves.toEqual({
+      status: 'denied',
+      reason: 'Note is outside the federated scope',
+    });
+  });
+
+  it('returns a subject note only when subject ownership and authorized mission intersect', async () => {
+    const service = makeDbService();
+
+    await expect(
+      service.get({
+        filter: {
+          resource: 'notes',
+          subjectUserId: SUBJECT_USER_ID,
+          includePersonal: false,
+          teamIds: [TEAM_ID],
+          limit: 1,
+          maxRowsPerQuery: 10,
+        },
+        id: SUBJECT_TEAM_NOTE_ID,
+      }),
+    ).resolves.toMatchObject({
+      status: 'found',
+      item: {
+        id: SUBJECT_TEAM_NOTE_ID,
+        missionId: TEAM_MISSION_ID,
+        content: 'subject note on team mission',
+      },
+    });
+  });
+
+  it('does not return subject personal notes when includePersonal is false', async () => {
+    const service = makeDbService();
+
+    await expect(
+      service.get({
+        filter: {
+          resource: 'notes',
+          subjectUserId: SUBJECT_USER_ID,
+          includePersonal: false,
+          teamIds: [TEAM_ID],
+          limit: 1,
+          maxRowsPerQuery: 10,
+        },
+        id: SUBJECT_PERSONAL_NOTE_ID,
+      }),
+    ).resolves.toEqual({
+      status: 'denied',
+      reason: 'Note is outside the federated scope',
+    });
+  });
+});

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

@@ -0,0 +1,207 @@
+import 'reflect-metadata';
+import { RequestMethod } from '@nestjs/common';
+import type { FastifyRequest } from 'fastify';
+import { beforeEach, describe, expect, it, vi } from 'vitest';
+import { FederationAuthGuard } from '../../federation-auth.guard.js';
+import type {
+  FederationScopeEvaluationResult,
+  FederationScopeQueryFilter,
+} from '../../scope.service.js';
+import { GetController } from '../get.controller.js';
+import type { FederationGetQueryResult } from '../get-query.service.js';
+
+const FEDERATION_CONTEXT = {
+  grantId: 'grant-1',
+  peerId: 'peer-1',
+  subjectUserId: 'user-1',
+  scope: { resources: ['tasks'], max_rows_per_query: 25 },
+};
+
+const TASK_FILTER: FederationScopeQueryFilter = {
+  resource: 'tasks',
+  subjectUserId: 'user-1',
+  includePersonal: true,
+  teamIds: ['team-1'],
+  limit: 1,
+  maxRowsPerQuery: 25,
+};
+
+function makeRequest(): FastifyRequest {
+  return { federationContext: FEDERATION_CONTEXT } as unknown as FastifyRequest;
+}
+
+function allowedScope(
+  filter: FederationScopeQueryFilter = TASK_FILTER,
+): FederationScopeEvaluationResult {
+  return { allowed: true, filter };
+}
+
+function makeController(opts?: {
+  scopeResult?: FederationScopeEvaluationResult;
+  queryResult?: FederationGetQueryResult;
+}) {
+  const scope = {
+    evaluateAccess: vi.fn().mockResolvedValue(opts?.scopeResult ?? allowedScope()),
+  };
+  const query = {
+    evaluateReadAccess: vi.fn(),
+    get: vi.fn().mockResolvedValue(
+      opts?.queryResult ?? {
+        status: 'found',
+        item: {
+          id: 'task-1',
+          title: 'Federated task',
+          createdAt: new Date('2026-06-24T00:00:00.000Z'),
+        },
+      },
+    ),
+  };
+
+  return {
+    controller: new GetController(scope as never, query as never),
+    scope,
+    query,
+  };
+}
+
+describe('GetController', () => {
+  beforeEach(() => {
+    vi.clearAllMocks();
+  });
+
+  it('declares POST /api/federation/v1/get/:resource/:id protected only by FederationAuthGuard', () => {
+    expect(Reflect.getMetadata('path', GetController)).toBe('api/federation/v1/get');
+    expect(Reflect.getMetadata('path', GetController.prototype.get)).toBe(':resource/:id');
+    expect(Reflect.getMetadata('method', GetController.prototype.get)).toBe(RequestMethod.POST);
+    expect(Reflect.getMetadata('__guards__', GetController)).toEqual([FederationAuthGuard]);
+  });
+
+  it('runs AuthGuard context through ScopeService and returns one local-source tagged row', async () => {
+    const { controller, scope, query } = makeController();
+
+    const response = await controller.get('tasks', 'task-1', makeRequest());
+
+    expect(scope.evaluateAccess).toHaveBeenCalledWith({
+      context: FEDERATION_CONTEXT,
+      resource: 'tasks',
+      requestedLimit: 1,
+      nativeRbac: query,
+    });
+    expect(query.get).toHaveBeenCalledWith({ filter: TASK_FILTER, id: 'task-1' });
+    expect(response).toEqual({
+      item: {
+        id: 'task-1',
+        title: 'Federated task',
+        createdAt: new Date('2026-06-24T00:00:00.000Z'),
+        _source: 'local',
+      },
+    });
+  });
+
+  it('returns a federation error envelope when auth guard context is missing', async () => {
+    const { controller, scope, query } = makeController();
+
+    await expect(
+      controller.get('tasks', 'task-1', {} as unknown as FastifyRequest),
+    ).rejects.toMatchObject({
+      response: {
+        error: {
+          code: 'unauthorized',
+          message: 'Federation context missing',
+        },
+      },
+      status: 401,
+    });
+    expect(scope.evaluateAccess).not.toHaveBeenCalled();
+    expect(query.get).not.toHaveBeenCalled();
+  });
+
+  it('returns a federation error envelope when scope evaluation denies access', async () => {
+    const { controller, query } = makeController({
+      scopeResult: {
+        allowed: false,
+        deny: {
+          code: 'resource_excluded',
+          stage: 'resource_exclusion',
+          statusCode: 403,
+          message: 'Requested federation resource is explicitly excluded by grant scope',
+          grantId: 'grant-1',
+          peerId: 'peer-1',
+          subjectUserId: 'user-1',
+          resource: 'credentials',
+        },
+      },
+    });
+
+    await expect(controller.get('credentials', 'cred-1', makeRequest())).rejects.toMatchObject({
+      response: {
+        error: {
+          code: 'scope_violation',
+          message: 'Requested federation resource is explicitly excluded by grant scope',
+        },
+      },
+      status: 403,
+    });
+    expect(query.get).not.toHaveBeenCalled();
+  });
+
+  it('returns 404 when the scoped query layer cannot find the resource id', async () => {
+    const { controller } = makeController({ queryResult: { status: 'not_found' } });
+
+    await expect(controller.get('tasks', 'missing-task', makeRequest())).rejects.toMatchObject({
+      response: { error: { code: 'not_found' } },
+      status: 404,
+    });
+  });
+
+  it('returns 403 when the resource exists outside the RBAC/scope intersection', async () => {
+    const { controller } = makeController({
+      queryResult: { status: 'denied', reason: 'Task is outside the federated scope' },
+    });
+
+    await expect(controller.get('tasks', 'task-2', makeRequest())).rejects.toMatchObject({
+      response: {
+        error: {
+          code: 'scope_violation',
+          message: 'Task is outside the federated scope',
+        },
+      },
+      status: 403,
+    });
+  });
+
+  it('fails closed when the query layer denies an unsupported resource', async () => {
+    const unsupportedFilter: FederationScopeQueryFilter = {
+      ...TASK_FILTER,
+      resource: 'unknown-resource' as FederationScopeQueryFilter['resource'],
+    };
+    const { controller } = makeController({
+      scopeResult: allowedScope(unsupportedFilter),
+      queryResult: {
+        status: 'denied',
+        reason: 'Unsupported federation get resource: unknown-resource',
+      },
+    });
+
+    await expect(controller.get('unknown-resource', 'row-1', makeRequest())).rejects.toMatchObject({
+      response: {
+        error: {
+          code: 'scope_violation',
+          message: 'Unsupported federation get resource: unknown-resource',
+        },
+      },
+      status: 403,
+    });
+  });
+
+  it('rejects empty ids before evaluating scope', async () => {
+    const { controller, scope, query } = makeController();
+
+    await expect(controller.get('tasks', '   ', makeRequest())).rejects.toMatchObject({
+      response: { error: { code: 'invalid_request' } },
+      status: 400,
+    });
+    expect(scope.evaluateAccess).not.toHaveBeenCalled();
+    expect(query.get).not.toHaveBeenCalled();
+  });
+});

apps/gateway/src/federation/server/verbs/get-query.service.ts

@@ -0,0 +1,311 @@
+/**
+ * Federation get query layer (FED-M3-06).
+ *
+ * Read-only DB adapter used by GetController after FederationAuthGuard and
+ * FederationScopeService have established the subject user, allowed resource,
+ * native-RBAC intersection, and row cap. Audit writes are intentionally
+ * deferred to M4.
+ */
+
+import { Inject, Injectable } from '@nestjs/common';
+import {
+  and,
+  eq,
+  inArray,
+  insights,
+  or,
+  missionTasks,
+  missions,
+  preferences,
+  projects,
+  tasks,
+  teamMembers,
+  type Db,
+} from '@mosaicstack/db';
+import { DB } from '../../../database/database.module.js';
+import type {
+  FederationNativeRbacEvaluator,
+  FederationNativeRbacRequest,
+  FederationNativeRbacResult,
+  FederationScopeQueryFilter,
+} from '../scope.service.js';
+
+export interface FederationGetQueryRequest {
+  readonly filter: FederationScopeQueryFilter;
+  readonly id: string;
+}
+
+export interface FederationGetQueryFoundResult<T extends object = Record<string, unknown>> {
+  readonly status: 'found';
+  readonly item: T;
+}
+
+export interface FederationGetQueryNotFoundResult {
+  readonly status: 'not_found';
+}
+
+export interface FederationGetQueryDeniedResult {
+  readonly status: 'denied';
+  readonly reason: string;
+}
+
+export type FederationGetQueryResult<T extends object = Record<string, unknown>> =
+  | FederationGetQueryFoundResult<T>
+  | FederationGetQueryNotFoundResult
+  | FederationGetQueryDeniedResult;
+
+type RowObject = Record<string, unknown>;
+
+function firstRow<T>(rows: T[]): T | undefined {
+  return rows[0];
+}
+
+function rowBelongsToAccessibleProjectOrMission(
+  row: { projectId?: string | null; missionId?: string | null },
+  projectIds: readonly string[],
+  missionIds: readonly string[],
+): boolean {
+  return (
+    (typeof row.projectId === 'string' && projectIds.includes(row.projectId)) ||
+    (typeof row.missionId === 'string' && missionIds.includes(row.missionId))
+  );
+}
+
+@Injectable()
+export class FederationGetQueryService implements FederationNativeRbacEvaluator {
+  constructor(@Inject(DB) private readonly db: Db) {}
+
+  async evaluateReadAccess(
+    request: FederationNativeRbacRequest,
+  ): Promise<FederationNativeRbacResult> {
+    if (request.resource === 'credentials' || request.resource === 'api_keys') {
+      return {
+        allowed: false,
+        reason: `${request.resource} federation get access is not implemented in M3`,
+        details: { resource: request.resource },
+      };
+    }
+
+    if (request.resource === 'memory') {
+      return { allowed: true, access: { includePersonal: true, teamIds: [] } };
+    }
+
+    const teamIds = await this.listSubjectTeamIds(request.subjectUserId);
+    return { allowed: true, access: { includePersonal: true, teamIds } };
+  }
+
+  async get<T extends RowObject = RowObject>(
+    request: FederationGetQueryRequest,
+  ): Promise<FederationGetQueryResult<T>> {
+    return this.getByResource(request.filter, request.id) as Promise<FederationGetQueryResult<T>>;
+  }
+
+  private async getByResource(
+    filter: FederationScopeQueryFilter,
+    id: string,
+  ): Promise<FederationGetQueryResult> {
+    switch (filter.resource) {
+      case 'tasks':
+        return this.getTask(filter, id);
+      case 'notes':
+        return this.getNote(filter, id);
+      case 'memory':
+        return this.getMemory(filter, id);
+      case 'credentials':
+      case 'api_keys':
+        return { status: 'denied', reason: `${filter.resource} federation get is not implemented` };
+      default:
+        return {
+          status: 'denied',
+          reason: `Unsupported federation get resource: ${String(filter.resource)}`,
+        };
+    }
+  }
+
+  private async listSubjectTeamIds(subjectUserId: string): Promise<string[]> {
+    const rows = await this.db
+      .select({ teamId: teamMembers.teamId })
+      .from(teamMembers)
+      .where(eq(teamMembers.userId, subjectUserId));
+
+    return rows.map((row) => row.teamId);
+  }
+
+  private async listAccessibleProjectIds(filter: FederationScopeQueryFilter): Promise<string[]> {
+    const clauses = [];
+    if (filter.includePersonal) {
+      clauses.push(and(eq(projects.ownerType, 'user'), eq(projects.ownerId, filter.subjectUserId)));
+    }
+    if (filter.teamIds.length > 0) {
+      // Project team ownership follows TeamsService.canAccessProject: team-owned
+      // rows are authorized through projects.teamId, while ownerId remains the
+      // user who created/bootstrapped the project.
+      clauses.push(
+        and(eq(projects.ownerType, 'team'), inArray(projects.teamId, [...filter.teamIds])),
+      );
+    }
+
+    if (clauses.length === 0) {
+      return [];
+    }
+
+    const rows = await this.db
+      .select({ id: projects.id })
+      .from(projects)
+      .where(clauses.length === 1 ? clauses[0] : or(...clauses));
+
+    return rows.map((row) => row.id);
+  }
+
+  private async listMissionIds(projectIds: readonly string[]): Promise<string[]> {
+    if (projectIds.length === 0) {
+      return [];
+    }
+
+    const rows = await this.db
+      .select({ id: missions.id })
+      .from(missions)
+      .where(inArray(missions.projectId, [...projectIds]));
+
+    return rows.map((row) => row.id);
+  }
+
+  private async getTask(
+    filter: FederationScopeQueryFilter,
+    id: string,
+  ): Promise<FederationGetQueryResult> {
+    const row = firstRow(
+      await this.db
+        .select({
+          id: tasks.id,
+          title: tasks.title,
+          description: tasks.description,
+          status: tasks.status,
+          priority: tasks.priority,
+          projectId: tasks.projectId,
+          missionId: tasks.missionId,
+          assignee: tasks.assignee,
+          tags: tasks.tags,
+          dueDate: tasks.dueDate,
+          metadata: tasks.metadata,
+          createdAt: tasks.createdAt,
+          updatedAt: tasks.updatedAt,
+        })
+        .from(tasks)
+        .where(eq(tasks.id, id))
+        .limit(1),
+    );
+
+    if (!row) {
+      return { status: 'not_found' };
+    }
+
+    const projectIds = await this.listAccessibleProjectIds(filter);
+    const missionIds = await this.listMissionIds(projectIds);
+    if (!rowBelongsToAccessibleProjectOrMission(row, projectIds, missionIds)) {
+      return { status: 'denied', reason: 'Task is outside the federated scope' };
+    }
+
+    return { status: 'found', item: row as RowObject };
+  }
+
+  private async getNote(
+    filter: FederationScopeQueryFilter,
+    id: string,
+  ): Promise<FederationGetQueryResult> {
+    const row = firstRow(
+      await this.db
+        .select({
+          id: missionTasks.id,
+          missionId: missionTasks.missionId,
+          taskId: missionTasks.taskId,
+          userId: missionTasks.userId,
+          status: missionTasks.status,
+          content: missionTasks.notes,
+          createdAt: missionTasks.createdAt,
+          updatedAt: missionTasks.updatedAt,
+        })
+        .from(missionTasks)
+        .where(eq(missionTasks.id, id))
+        .limit(1),
+    );
+
+    if (!row || row.content === null || row.content === '') {
+      return { status: 'not_found' };
+    }
+
+    const projectIds = await this.listAccessibleProjectIds(filter);
+    const missionIds = await this.listMissionIds(projectIds);
+
+    // mission_tasks rows are user-scoped even when the mission belongs to a team.
+    // Scope-visible missions must intersect with subject ownership; team scope
+    // narrows mission IDs but never widens note reads to another user's rows.
+    if (row.userId !== filter.subjectUserId || !missionIds.includes(row.missionId)) {
+      return { status: 'denied', reason: 'Note is outside the federated scope' };
+    }
+
+    const item = { ...row } as RowObject;
+    delete item['userId'];
+    return { status: 'found', item };
+  }
+
+  private async getMemory(
+    filter: FederationScopeQueryFilter,
+    id: string,
+  ): Promise<FederationGetQueryResult> {
+    const [insightRow, preferenceRow] = await Promise.all([
+      this.db
+        .select({
+          id: insights.id,
+          userId: insights.userId,
+          kind: insights.source,
+          content: insights.content,
+          category: insights.category,
+          relevanceScore: insights.relevanceScore,
+          metadata: insights.metadata,
+          createdAt: insights.createdAt,
+          updatedAt: insights.updatedAt,
+        })
+        .from(insights)
+        .where(eq(insights.id, id))
+        .limit(1)
+        .then(firstRow),
+      this.db
+        .select({
+          id: preferences.id,
+          userId: preferences.userId,
+          kind: preferences.category,
+          key: preferences.key,
+          value: preferences.value,
+          source: preferences.source,
+          mutable: preferences.mutable,
+          createdAt: preferences.createdAt,
+          updatedAt: preferences.updatedAt,
+        })
+        .from(preferences)
+        .where(eq(preferences.id, id))
+        .limit(1)
+        .then(firstRow),
+    ]);
+
+    const candidates = [insightRow, preferenceRow].filter(
+      (row): row is NonNullable<typeof row> => row !== undefined,
+    );
+    if (candidates.length === 0) {
+      return { status: 'not_found' };
+    }
+
+    if (!filter.includePersonal) {
+      return { status: 'denied', reason: 'Memory personal rows are outside the federated scope' };
+    }
+
+    const accessible = candidates.find((row) => row.userId === filter.subjectUserId);
+    if (!accessible) {
+      return { status: 'denied', reason: 'Memory row belongs to another subject user' };
+    }
+
+    const item = { ...accessible } as RowObject;
+    delete item['userId'];
+    return { status: 'found', item };
+  }
+}

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

@@ -0,0 +1,100 @@
+/**
+ * Federation get verb (FED-M3-06).
+ *
+ * POST /api/federation/v1/get/:resource/:id
+ *
+ * Pipeline: FederationAuthGuard attaches the active grant context, then
+ * FederationScopeService enforces grant scope + native RBAC intersection, then
+ * the read-only query layer fetches one local row and tags it with `_source`.
+ * Read audit-log writes are deferred to M4; this controller does not persist
+ * request or response bodies.
+ */
+
+import { Controller, HttpException, Inject, Param, Post, Req, UseGuards } from '@nestjs/common';
+import type { FastifyRequest } from 'fastify';
+import {
+  FederationInvalidRequestError,
+  FederationNotFoundError,
+  FederationScopeViolationError,
+  FederationUnauthorizedError,
+  SOURCE_LOCAL,
+  type FederationGetResponse,
+  type SourceTag,
+} from '@mosaicstack/types';
+import { FederationAuthGuard } from '../federation-auth.guard.js';
+import '../federation-context.js';
+import { FederationScopeService } from '../scope.service.js';
+import { FederationGetQueryService } from './get-query.service.js';
+
+type FederatedRow = Record<string, unknown> & SourceTag;
+
+function scopeDenyToHttpException(deny: {
+  readonly statusCode: 400 | 403;
+  readonly message: string;
+}): HttpException {
+  const ErrorClass =
+    deny.statusCode === 400 ? FederationInvalidRequestError : FederationScopeViolationError;
+  return new HttpException(new ErrorClass(deny.message, deny).toEnvelope(), deny.statusCode);
+}
+
+@Controller('api/federation/v1/get')
+@UseGuards(FederationAuthGuard)
+export class GetController {
+  constructor(
+    @Inject(FederationScopeService) private readonly scope: FederationScopeService,
+    @Inject(FederationGetQueryService) private readonly query: FederationGetQueryService,
+  ) {}
+
+  @Post(':resource/:id')
+  async get(
+    @Param('resource') resource: string,
+    @Param('id') id: string,
+    @Req() request: FastifyRequest,
+  ): Promise<FederationGetResponse<FederatedRow>> {
+    if (!request.federationContext) {
+      throw new HttpException(
+        new FederationUnauthorizedError('Federation context missing').toEnvelope(),
+        401,
+      );
+    }
+    if (id.trim().length === 0) {
+      throw new HttpException(
+        new FederationInvalidRequestError('Federation get id must not be empty').toEnvelope(),
+        400,
+      );
+    }
+
+    const scopeResult = await this.scope.evaluateAccess({
+      context: request.federationContext,
+      resource,
+      requestedLimit: 1,
+      nativeRbac: this.query,
+    });
+
+    if (!scopeResult.allowed) {
+      throw scopeDenyToHttpException(scopeResult.deny);
+    }
+
+    const result = await this.query.get({ filter: scopeResult.filter, id });
+    if (result.status === 'not_found') {
+      throw new HttpException(
+        new FederationNotFoundError('Requested federation resource was not found').toEnvelope(),
+        404,
+      );
+    }
+    if (result.status === 'denied') {
+      throw new HttpException(
+        new FederationScopeViolationError(result.reason, {
+          resource,
+          id,
+          grantId: request.federationContext.grantId,
+          peerId: request.federationContext.peerId,
+          subjectUserId: request.federationContext.subjectUserId,
+        }).toEnvelope(),
+        403,
+      );
+    }
+
+    return { item: { ...result.item, _source: SOURCE_LOCAL } };
+  }
+}

apps/gateway/src/gc/gc.module.ts

@@ -1,5 +1,7 @@
-import { Module, type OnApplicationShutdown, Inject } from '@nestjs/common';
+import { Module, type OnApplicationShutdown, Inject, Optional } from '@nestjs/common';
 import { createQueue, type QueueHandle } from '@mosaicstack/queue';
+import type { MosaicConfig } from '@mosaicstack/config';
+import { MOSAIC_CONFIG } from '../config/config.module.js';
 import { SessionGCService } from './session-gc.service.js';
 import { REDIS } from './gc.tokens.js';
 
@@ -9,13 +11,17 @@ const GC_QUEUE_HANDLE = 'GC_QUEUE_HANDLE';
   providers: [
     {
       provide: GC_QUEUE_HANDLE,
-      useFactory: (): QueueHandle => {
+      useFactory: (config: MosaicConfig | null): QueueHandle | null => {
+        // On Local tier there is no Redis — skip the ioredis connection entirely.
+        // The Valkey GC sweep is a no-op on Local (no session keys stored there).
+        if (config?.queue?.type === 'local') return null;
         return createQueue();
       },
+      inject: [MOSAIC_CONFIG],
     },
     {
       provide: REDIS,
-      useFactory: (handle: QueueHandle) => handle.redis,
+      useFactory: (handle: QueueHandle | null) => handle?.redis ?? null,
       inject: [GC_QUEUE_HANDLE],
     },
     SessionGCService,
@@ -23,9 +29,13 @@ const GC_QUEUE_HANDLE = 'GC_QUEUE_HANDLE';
   exports: [SessionGCService],
 })
 export class GCModule implements OnApplicationShutdown {
-  constructor(@Inject(GC_QUEUE_HANDLE) private readonly handle: QueueHandle) {}
+  constructor(
+    @Optional()
+    @Inject(GC_QUEUE_HANDLE)
+    private readonly handle: QueueHandle | null,
+  ) {}
 
   async onApplicationShutdown(): Promise<void> {
-    await this.handle.close().catch(() => {});
+    await this.handle?.close().catch(() => {});
   }
 }

apps/gateway/src/gc/session-gc.service.spec.ts

@@ -119,6 +119,19 @@ describe('SessionGCService', () => {
     ).resolves.toEqual({ allowed: true });
   });
 
+  it('collect() skips Valkey but still demotes only the requested session on local tier', async () => {
+    const localService = new SessionGCService(null, mockLogService as unknown as LogService);
+
+    const result = await localService.collect('local-session');
+
+    expect(result.sessionId).toBe('local-session');
+    expect(result.cleaned.valkeyKeys).toBeUndefined();
+    expect(mockLogService.logs.promoteSessionToWarm).toHaveBeenCalledWith(
+      'local-session',
+      expect.any(Date),
+    );
+  });
+
   it('collect() returns sessionId in result', async () => {
     const result = await service.collect('test-session-id');
     expect(result.sessionId).toBe('test-session-id');

apps/gateway/src/gc/session-gc.service.ts

@@ -1,4 +1,4 @@
-import { Inject, Injectable } from '@nestjs/common';
+import { Inject, Injectable, Optional } from '@nestjs/common';
 import type { QueueHandle } from '@mosaicstack/queue';
 import type { LogService } from '@mosaicstack/log';
 import { LOG_SERVICE } from '../log/log.tokens.js';
@@ -21,7 +21,10 @@ function escapeRedisGlobLiteral(value: string): string {
 @Injectable()
 export class SessionGCService {
   constructor(
-    @Inject(REDIS) private readonly redis: QueueHandle['redis'],
+    // Local tier has no Redis; lifecycle cleanup still demotes this session's logs.
+    @Optional()
+    @Inject(REDIS)
+    private readonly redis: QueueHandle['redis'] | null,
     @Inject(LOG_SERVICE) private readonly logService: LogService,
   ) {}
 
@@ -29,8 +32,10 @@ export class SessionGCService {
    * Scan Valkey for all keys matching a pattern using SCAN (non-blocking).
    * KEYS is avoided because it blocks the Valkey event loop for the full scan
    * duration, which can cause latency spikes under production key volumes.
+   * Returns an empty population on the Local tier where Redis is disabled.
    */
   private async scanKeys(pattern: string): Promise<string[]> {
+    if (!this.redis) return [];
     const collected: string[] = [];
     let cursor = '0';
     do {
@@ -47,12 +52,14 @@ export class SessionGCService {
   async collect(sessionId: string): Promise<GCResult> {
     const result: GCResult = { sessionId, cleaned: {} };
 
-    // 1. Valkey: delete all session-scoped keys
+    // 1. Valkey: delete all session-scoped keys (skipped on Local tier).
-    const pattern = `mosaic:session:${escapeRedisGlobLiteral(sessionId)}:*`;
+    if (this.redis) {
-    const valkeyKeys = await this.scanKeys(pattern);
+      const pattern = `mosaic:session:${escapeRedisGlobLiteral(sessionId)}:*`;
-    if (valkeyKeys.length > 0) {
+      const valkeyKeys = await this.scanKeys(pattern);
-      await this.redis.del(...valkeyKeys);
+      if (valkeyKeys.length > 0) {
-      result.cleaned.valkeyKeys = valkeyKeys.length;
+        await this.redis.del(...valkeyKeys);
+        result.cleaned.valkeyKeys = valkeyKeys.length;
+      }
     }
 
     // 2. PG: demote hot-tier agent logs for this session only.

apps/gateway/src/log/cron.service.ts

@@ -18,7 +18,7 @@ import type { MosaicJobData } from '../queue/queue.service.js';
 @Injectable()
 export class CronService implements OnModuleInit, OnModuleDestroy {
   private readonly logger = new Logger(CronService.name);
-  private readonly registeredWorkers: Worker<MosaicJobData>[] = [];
+  private readonly registeredWorkers: Array<Worker<MosaicJobData>> = [];
 
   constructor(
     @Inject(SummarizationService) private readonly summarization: SummarizationService,
@@ -26,6 +26,12 @@ export class CronService implements OnModuleInit, OnModuleDestroy {
   ) {}
 
   async onModuleInit(): Promise<void> {
+    // Local tier deliberately has no BullMQ consumers or repeatable jobs.
+    if (!this.queueService.isEnabled()) {
+      this.logger.log('CronService: BullMQ disabled on local tier — no jobs will be scheduled');
+      return;
+    }
+
     const summarizationSchedule = process.env['SUMMARIZATION_CRON'] ?? '0 */6 * * *'; // every 6 hours
     const tierManagementSchedule = process.env['TIER_MANAGEMENT_CRON'] ?? '0 3 * * *'; // daily at 3am
 
@@ -39,7 +45,7 @@ export class CronService implements OnModuleInit, OnModuleDestroy {
     const summarizationWorker = this.queueService.registerWorker(QUEUE_SUMMARIZATION, async () => {
       await this.summarization.runSummarization();
     });
-    this.registeredWorkers.push(summarizationWorker);
+    if (summarizationWorker) this.registeredWorkers.push(summarizationWorker);
 
     // M6-005: Tier management repeatable job
     await this.queueService.addRepeatableJob(
@@ -51,7 +57,7 @@ export class CronService implements OnModuleInit, OnModuleDestroy {
     const tierWorker = this.queueService.registerWorker(QUEUE_TIER_MANAGEMENT, async () => {
       await this.summarization.runTierManagement();
     });
-    this.registeredWorkers.push(tierWorker);
+    if (tierWorker) this.registeredWorkers.push(tierWorker);
 
     // Retire any repeatable global GC schedule created by older deployments.
     // Session cleanup is now triggered only by an authorized session lifecycle operation.

apps/gateway/src/mcp-client/mcp-client.service.spec.ts

@@ -0,0 +1,44 @@
+import { Logger } from '@nestjs/common';
+import { Client } from '@modelcontextprotocol/sdk/client/index.js';
+import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
+import { McpClientService } from './mcp-client.service.js';
+
+const MCP_LEAK_MARKER = 'MCP_LEAK_MARKER /srv/secret';
+
+describe('McpClientService — failed connect error sanitization', () => {
+  const originalMcpServers = process.env['MCP_SERVERS'];
+
+  beforeEach(() => {
+    process.env['MCP_SERVERS'] = JSON.stringify([
+      { name: 'leaky-server', url: 'http://localhost:9999/mcp' },
+    ]);
+  });
+
+  afterEach(() => {
+    vi.restoreAllMocks();
+    if (originalMcpServers === undefined) {
+      delete process.env['MCP_SERVERS'];
+    } else {
+      process.env['MCP_SERVERS'] = originalMcpServers;
+    }
+  });
+
+  it('stores a generic serverEntry.error while logging the raw exception server-side', async () => {
+    vi.spyOn(Client.prototype, 'connect').mockRejectedValue(new Error(MCP_LEAK_MARKER));
+    const errorSpy = vi.spyOn(Logger.prototype, 'error').mockImplementation(() => undefined);
+
+    const service = new McpClientService();
+    await service.onModuleInit();
+
+    const statuses = service.getServerStatuses();
+    expect(statuses).toHaveLength(1);
+    expect(statuses[0]?.connected).toBe(false);
+    expect(statuses[0]?.error).toBe('Connection failed (see server logs).');
+    expect(statuses[0]?.error).not.toContain(MCP_LEAK_MARKER);
+
+    const loggedRawMarker = errorSpy.mock.calls.some((call) =>
+      call.some((arg) => typeof arg === 'string' && arg.includes(MCP_LEAK_MARKER)),
+    );
+    expect(loggedRawMarker).toBe(true);
+  });
+});

apps/gateway/src/mcp-client/mcp-client.service.ts

@@ -189,7 +189,7 @@ export class McpClientService implements OnModuleInit, OnModuleDestroy {
       );
     } catch (err) {
       const message = err instanceof Error ? err.message : String(err);
-      serverEntry.error = message;
+      serverEntry.error = 'Connection failed (see server logs).';
       serverEntry.connected = false;
       this.logger.error(`Failed to connect to MCP server "${config.name}": ${message}`);
     }

apps/gateway/src/preferences/system-override.service.spec.ts

@@ -0,0 +1,23 @@
+import { describe, expect, it } from 'vitest';
+import type { MosaicConfig } from '@mosaicstack/config';
+import { SystemOverrideService } from './system-override.service.js';
+
+const localConfig = { queue: { type: 'local' } } as MosaicConfig;
+
+describe('SystemOverrideService local tier', () => {
+  it('keeps ephemeral overrides isolated by tenant and user scope', async () => {
+    const service = new SystemOverrideService(localConfig);
+    const firstScope = { tenantId: 'tenant-a', userId: 'user-a' };
+    const secondScope = { tenantId: 'tenant-b', userId: 'user-b' };
+
+    await service.set('shared-session', 'first override', firstScope);
+    await service.set('shared-session', 'second override', secondScope);
+
+    await expect(service.get('shared-session', firstScope)).resolves.toBe('first override');
+    await expect(service.get('shared-session', secondScope)).resolves.toBe('second override');
+
+    await service.clear('shared-session', firstScope);
+    await expect(service.get('shared-session', firstScope)).resolves.toBeNull();
+    await expect(service.get('shared-session', secondScope)).resolves.toBe('second override');
+  });
+});

apps/gateway/src/preferences/system-override.service.ts

@@ -1,6 +1,8 @@
-import { Injectable, Logger } from '@nestjs/common';
+import { Inject, Injectable, Logger, Optional, type OnApplicationShutdown } from '@nestjs/common';
 import { createQueue, type QueueHandle } from '@mosaicstack/queue';
+import type { MosaicConfig } from '@mosaicstack/config';
 import type { ActorTenantScope } from '../auth/session-scope.js';
+import { MOSAIC_CONFIG } from '../config/config.module.js';
 
 const scopedSessionId = (sessionId: string, scope: ActorTenantScope) =>
   `${scope.tenantId}:${scope.userId}:${sessionId}`;
@@ -15,16 +17,45 @@ interface OverrideFragment {
   addedAt: number;
 }
 
-@Injectable()
+interface LocalOverrideEntry {
-export class SystemOverrideService {
+  condensed: string;
-  private readonly logger = new Logger(SystemOverrideService.name);
+  fragments: OverrideFragment[];
-  private readonly handle: QueueHandle;
+}
 
-  constructor() {
+@Injectable()
-    this.handle = createQueue();
+export class SystemOverrideService implements OnApplicationShutdown {
+  private readonly logger = new Logger(SystemOverrideService.name);
+  private readonly handle: QueueHandle | null;
+  /** Local-tier fallback, keyed by the same tenant/user/session scope as Redis. */
+  private readonly localStore = new Map<string, LocalOverrideEntry>();
+
+  constructor(
+    @Optional()
+    @Inject(MOSAIC_CONFIG)
+    private readonly mosaicConfig: MosaicConfig | null,
+  ) {
+    this.handle = this.mosaicConfig?.queue?.type === 'local' ? null : createQueue();
+  }
+
+  async onApplicationShutdown(): Promise<void> {
+    await this.handle?.close().catch(() => {});
   }
 
   async set(sessionId: string, override: string, scope: ActorTenantScope): Promise<void> {
+    if (!this.handle) {
+      const key = scopedSessionId(sessionId, scope);
+      const entry = this.localStore.get(key) ?? { condensed: '', fragments: [] };
+      entry.fragments.push({ text: override, addedAt: Date.now() });
+      entry.condensed = await this.condenseOverrides(
+        entry.fragments.map((fragment) => fragment.text),
+      );
+      this.localStore.set(key, entry);
+      this.logger.debug(
+        `Set system override for session ${sessionId} (local, ${entry.fragments.length} fragment(s))`,
+      );
+      return;
+    }
+
     // Load existing fragments
     const existing = await this.handle.redis.get(SESSION_SYSTEM_FRAGMENTS_KEY(sessionId, scope));
     const fragments: OverrideFragment[] = existing
@@ -54,10 +85,14 @@ export class SystemOverrideService {
   }
 
   async get(sessionId: string, scope: ActorTenantScope): Promise<string | null> {
+    if (!this.handle) {
+      return this.localStore.get(scopedSessionId(sessionId, scope))?.condensed ?? null;
+    }
     return this.handle.redis.get(SESSION_SYSTEM_KEY(sessionId, scope));
   }
 
   async renew(sessionId: string, scope: ActorTenantScope): Promise<void> {
+    if (!this.handle) return;
     const pipeline = this.handle.redis.pipeline();
     pipeline.expire(SESSION_SYSTEM_KEY(sessionId, scope), SYSTEM_OVERRIDE_TTL_SECONDS);
     pipeline.expire(SESSION_SYSTEM_FRAGMENTS_KEY(sessionId, scope), SYSTEM_OVERRIDE_TTL_SECONDS);
@@ -65,6 +100,11 @@ export class SystemOverrideService {
   }
 
   async clear(sessionId: string, scope: ActorTenantScope): Promise<void> {
+    if (!this.handle) {
+      this.localStore.delete(scopedSessionId(sessionId, scope));
+      this.logger.debug(`Cleared system override for session ${sessionId} (local)`);
+      return;
+    }
     await this.handle.redis.del(
       SESSION_SYSTEM_KEY(sessionId, scope),
       SESSION_SYSTEM_FRAGMENTS_KEY(sessionId, scope),

apps/gateway/src/queue/queue.service.spec.ts

@@ -0,0 +1,36 @@
+import { describe, expect, it, vi } from 'vitest';
+import type { MosaicConfig } from '@mosaicstack/config';
+import { QueueService } from './queue.service.js';
+
+const localConfig = {
+  queue: { type: 'local' },
+} as MosaicConfig;
+
+describe('QueueService local tier', () => {
+  it('disables BullMQ and treats queue operations as local no-ops', async () => {
+    const service = new QueueService(null, localConfig);
+
+    expect(service.isEnabled()).toBe(false);
+    expect(service.getQueue('mosaic-test')).toBeNull();
+    expect(service.registerWorker('mosaic-test', vi.fn())).toBeNull();
+
+    await expect(
+      service.addRepeatableJob('mosaic-test', 'local-noop', {}, '* * * * *'),
+    ).resolves.toBeUndefined();
+    await expect(service.removeRepeatableJobs('mosaic-test', 'local-noop')).resolves.toBe(0);
+    await expect(service.getHealthStatus()).resolves.toEqual({ queues: {}, healthy: true });
+    await expect(service.listJobs()).resolves.toEqual([]);
+    await expect(service.retryJob('mosaic-test__1')).resolves.toEqual({
+      ok: false,
+      message: 'BullMQ is disabled on local tier.',
+    });
+    await expect(service.pauseQueue('mosaic-test')).resolves.toEqual({
+      ok: false,
+      message: 'BullMQ is disabled on local tier.',
+    });
+    await expect(service.resumeQueue('mosaic-test')).resolves.toEqual({
+      ok: false,
+      message: 'BullMQ is disabled on local tier.',
+    });
+  });
+});

apps/gateway/src/queue/queue.service.ts

@@ -8,7 +8,9 @@ import {
 } from '@nestjs/common';
 import { Queue, Worker, type Job, type ConnectionOptions } from 'bullmq';
 import type { LogService } from '@mosaicstack/log';
+import type { MosaicConfig } from '@mosaicstack/config';
 import { LOG_SERVICE } from '../log/log.tokens.js';
+import { MOSAIC_CONFIG } from '../config/config.module.js';
 import type { JobDto, JobStatus } from './queue-admin.dto.js';
 
 // ---------------------------------------------------------------------------
@@ -108,21 +110,42 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
   private readonly connection: ConnectionOptions;
   private readonly queues = new Map<string, Queue<MosaicJobData>>();
   private readonly workers = new Map<string, Worker<MosaicJobData>>();
+  /** False on Local tier — BullMQ/Redis operations become no-ops. */
+  private readonly enabled: boolean;
 
   constructor(
     @Optional()
     @Inject(LOG_SERVICE)
     private readonly logService: LogService | null,
+    @Optional()
+    @Inject(MOSAIC_CONFIG)
+    private readonly mosaicConfig: MosaicConfig | null,
   ) {
-    this.connection = getConnection();
+    this.enabled = this.mosaicConfig?.queue?.type !== 'local';
+    this.connection = this.enabled
+      ? getConnection()
+      : ({ host: '127.0.0.1', port: 6380 } as ConnectionOptions);
+  }
+
+  /** Returns true when BullMQ/Redis is active (Standalone and Federated tiers). */
+  isEnabled(): boolean {
+    return this.enabled;
   }
 
   onModuleInit(): void {
-    this.logger.log('QueueService initialised (BullMQ)');
+    if (this.enabled) {
+      this.logger.log('QueueService initialised (BullMQ)');
+    } else {
+      this.logger.log(
+        'QueueService: BullMQ disabled for local tier — no Redis connections will be opened',
+      );
+    }
   }
 
   async onModuleDestroy(): Promise<void> {
-    await this.closeAll();
+    if (this.enabled) {
+      await this.closeAll();
+    }
   }
 
   // -------------------------------------------------------------------------
@@ -131,8 +154,10 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
 
   /**
    * Get or create a BullMQ Queue for the given queue name.
+   * Returns null on Local tier where BullMQ is disabled.
    */
-  getQueue<T extends MosaicJobData = MosaicJobData>(name: string): Queue<T> {
+  getQueue<T extends MosaicJobData = MosaicJobData>(name: string): Queue<T> | null {
+    if (!this.enabled) return null;
     let queue = this.queues.get(name) as Queue<T> | undefined;
     if (!queue) {
       queue = new Queue<T>(name, { connection: this.connection });
@@ -144,6 +169,7 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
   /**
    * Add a BullMQ repeatable job (cron-style).
    * Uses `jobId` as a deterministic key so duplicate registrations are idempotent.
+   * No-op on Local tier.
    */
   async addRepeatableJob<T extends MosaicJobData>(
     queueName: string,
@@ -151,7 +177,13 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
     data: T,
     cronExpression: string,
   ): Promise<void> {
-    const queue = this.getQueue<T>(queueName);
+    if (!this.enabled) {
+      this.logger.debug(
+        `Skipping repeatable job "${jobName}" on "${queueName}" (local tier — BullMQ disabled)`,
+      );
+      return;
+    }
+    const queue = this.getQueue<T>(queueName)!;
     // eslint-disable-next-line @typescript-eslint/no-explicit-any
     await (queue as Queue<any>).add(jobName, data, {
       repeat: { pattern: cronExpression },
@@ -167,7 +199,14 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
    * safe retirement of previously registered system-wide jobs.
    */
   async removeRepeatableJobs(queueName: string, jobName: string): Promise<number> {
+    if (!this.enabled) {
+      this.logger.debug(
+        `Skipping repeatable-job removal for "${jobName}" on "${queueName}" (local tier — BullMQ disabled)`,
+      );
+      return 0;
+    }
     const queue = this.getQueue(queueName);
+    if (!queue) return 0;
     const jobs = await queue.getRepeatableJobs();
     const matchingJobs = jobs.filter((job) => job.name === jobName);
     await Promise.all(matchingJobs.map((job) => queue.removeRepeatableByKey(job.key)));
@@ -182,8 +221,18 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
   /**
    * Register a Worker for the given queue name with error handling and
    * exponential backoff.
+   * Returns null on Local tier where BullMQ is disabled.
    */
-  registerWorker<T extends MosaicJobData>(queueName: string, handler: JobHandler<T>): Worker<T> {
+  registerWorker<T extends MosaicJobData>(
+    queueName: string,
+    handler: JobHandler<T>,
+  ): Worker<T> | null {
+    if (!this.enabled) {
+      this.logger.debug(
+        `Skipping worker registration for "${queueName}" (local tier — BullMQ disabled)`,
+      );
+      return null;
+    }
     const worker = new Worker<T>(
       queueName,
       async (job) => {
@@ -240,8 +289,12 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
 
   /**
    * Return queue health statistics for all managed queues.
+   * Returns an empty healthy result on Local tier.
    */
   async getHealthStatus(): Promise<QueueHealthStatus> {
+    if (!this.enabled) {
+      return { queues: {}, healthy: true };
+    }
     const queues: QueueHealthStatus['queues'] = {};
     let healthy = true;
 
@@ -272,8 +325,10 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
   /**
    * List jobs across all managed queues, optionally filtered by status.
    * BullMQ jobs are fetched by state type from each queue.
+   * Returns empty array on Local tier.
    */
   async listJobs(status?: JobStatus): Promise<JobDto[]> {
+    if (!this.enabled) return [];
     const jobs: JobDto[] = [];
     const states: JobStatus[] = status
       ? [status]
@@ -300,8 +355,10 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
    * Retry a specific failed job by its BullMQ job ID (format: "queueName:id").
    * The caller passes "<queueName>__<jobId>" as the composite ID because BullMQ
    * job IDs are not globally unique — they are scoped to their queue.
+   * Returns an error on Local tier.
    */
   async retryJob(compositeId: string): Promise<{ ok: boolean; message: string }> {
+    if (!this.enabled) return { ok: false, message: 'BullMQ is disabled on local tier.' };
     const sep = compositeId.lastIndexOf('__');
     if (sep === -1) {
       return { ok: false, message: 'Invalid job id format. Expected "<queue>__<jobId>".' };
@@ -333,6 +390,7 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
    * Pause a queue by name.
    */
   async pauseQueue(name: string): Promise<{ ok: boolean; message: string }> {
+    if (!this.enabled) return { ok: false, message: 'BullMQ is disabled on local tier.' };
     const queue = this.queues.get(name);
     if (!queue) return { ok: false, message: `Queue "${name}" not found.` };
     await queue.pause();
@@ -344,6 +402,7 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
    * Resume a paused queue by name.
    */
   async resumeQueue(name: string): Promise<{ ok: boolean; message: string }> {
+    if (!this.enabled) return { ok: false, message: 'BullMQ is disabled on local tier.' };
     const queue = this.queues.get(name);
     if (!queue) return { ok: false, message: `Queue "${name}" not found.` };
     await queue.resume();

apps/gateway/src/reload/reload.service.spec.ts

@@ -1,5 +1,8 @@
+import { Logger } from '@nestjs/common';
 import { describe, expect, it, vi } from 'vitest';
+import type { SlashCommandPayload, SystemReloadPayload } from '@mosaicstack/types';
 import { ReloadService } from './reload.service.js';
+import { CommandExecutorService } from '../commands/command-executor.service.js';
 
 function createMockCommandRegistry() {
   return {
@@ -104,3 +107,79 @@ describe('ReloadService', () => {
     expect(() => service.registerPlugin('my-plugin', {})).not.toThrow();
   });
 });
+
+describe('ReloadService — /reload command sanitizes plugin errors', () => {
+  it('generic per-plugin errors reach the chat surface while raw markers stay server-side only', async () => {
+    const registry = {
+      getManifest: vi.fn().mockReturnValue({
+        version: 1,
+        commands: [
+          { name: 'reload', aliases: [], scope: 'core', execution: 'socket', available: true },
+        ],
+        skills: [],
+      }),
+    };
+    const reloadService = new ReloadService(registry as never);
+
+    const RELOAD_LOAD_LEAK_MARKER = 'RELOAD_LOAD_LEAK_MARKER /srv/load-secret';
+    const RELOAD_UNLOAD_LEAK_MARKER = 'RELOAD_UNLOAD_LEAK_MARKER /srv/unload-secret';
+
+    reloadService.registerPlugin('unload-fails', {
+      pluginName: 'unload-fails',
+      onLoad: vi.fn().mockResolvedValue(undefined),
+      onUnload: vi.fn().mockRejectedValue(new Error(RELOAD_UNLOAD_LEAK_MARKER)),
+    });
+    reloadService.registerPlugin('load-fails', {
+      pluginName: 'load-fails',
+      onLoad: vi.fn().mockRejectedValue(new Error(RELOAD_LOAD_LEAK_MARKER)),
+      onUnload: vi.fn().mockResolvedValue(undefined),
+    });
+
+    const errorSpy = vi.spyOn(Logger.prototype, 'error').mockImplementation(() => undefined);
+    const broadcastReload = vi.fn();
+    const mockChatGateway = { broadcastReload };
+    const mockAgentService = { getSession: vi.fn(), applyAgentConfig: vi.fn() };
+    const mockSystemOverride = { set: vi.fn(), get: vi.fn(), clear: vi.fn() };
+    const mockSessionGC = { sweepOrphans: vi.fn() };
+    const mockBrain = { agents: { findByName: vi.fn(), findById: vi.fn(), create: vi.fn() } };
+
+    const executor = new CommandExecutorService(
+      registry as never,
+      mockAgentService as never,
+      mockSystemOverride as never,
+      mockSessionGC as never,
+      null,
+      mockBrain as never,
+      reloadService,
+      mockChatGateway as never,
+      null,
+    );
+
+    const payload: SlashCommandPayload = { command: 'reload', conversationId: 'conv-1' };
+    const result = await executor.execute(payload, { userId: 'user-1', tenantId: 'user-1' });
+
+    expect(result.success).toBe(true);
+    expect(result.message).toContain('unload-fails: unload failed (internal error)');
+    expect(result.message).toContain('load-fails: load failed (internal error)');
+    expect(result.message).not.toContain(RELOAD_UNLOAD_LEAK_MARKER);
+    expect(result.message).not.toContain(RELOAD_LOAD_LEAK_MARKER);
+
+    expect(broadcastReload).toHaveBeenCalledOnce();
+    const broadcastPayload = broadcastReload.mock.calls[0]?.[0] as SystemReloadPayload;
+    expect(broadcastPayload.message).toContain('unload-fails: unload failed (internal error)');
+    expect(broadcastPayload.message).toContain('load-fails: load failed (internal error)');
+    expect(broadcastPayload.message).not.toContain(RELOAD_UNLOAD_LEAK_MARKER);
+    expect(broadcastPayload.message).not.toContain(RELOAD_LOAD_LEAK_MARKER);
+
+    const loggedUnloadMarker = errorSpy.mock.calls.some((call) =>
+      call.some((arg) => typeof arg === 'string' && arg.includes(RELOAD_UNLOAD_LEAK_MARKER)),
+    );
+    const loggedLoadMarker = errorSpy.mock.calls.some((call) =>
+      call.some((arg) => typeof arg === 'string' && arg.includes(RELOAD_LOAD_LEAK_MARKER)),
+    );
+    expect(loggedUnloadMarker).toBe(true);
+    expect(loggedLoadMarker).toBe(true);
+
+    errorSpy.mockRestore();
+  });
+});

apps/gateway/src/reload/reload.service.ts

@@ -58,7 +58,8 @@ export class ReloadService implements OnApplicationBootstrap, OnApplicationShutd
           await plugin.onUnload();
           reloaded.push(name);
         } catch (err) {
-          errors.push(`${name}: unload failed — ${err}`);
+          this.logger.error(`Plugin "${name}" failed during onUnload: ${err}`);
+          errors.push(`${name}: unload failed (internal error)`);
         }
       }
     }
@@ -69,7 +70,8 @@ export class ReloadService implements OnApplicationBootstrap, OnApplicationShutd
         try {
           await plugin.onLoad();
         } catch (err) {
-          errors.push(`${name}: load failed — ${err}`);
+          this.logger.error(`Plugin "${name}" failed during onLoad: ${err}`);
+          errors.push(`${name}: load failed (internal error)`);
         }
       }
     }

apps/gateway/src/workspace/workspace.controller.spec.ts

@@ -0,0 +1,104 @@
+import 'reflect-metadata';
+import {
+  type CanActivate,
+  type ExecutionContext,
+  type INestApplication,
+  ValidationPipe,
+} from '@nestjs/common';
+import { FastifyAdapter, type NestFastifyApplication } from '@nestjs/platform-fastify';
+import { Test } from '@nestjs/testing';
+import request from 'supertest';
+import { afterAll, beforeAll, beforeEach, describe, expect, it, vi } from 'vitest';
+import { AuthGuard } from '../auth/auth.guard.js';
+import { ProjectBootstrapService } from './project-bootstrap.service.js';
+import { WorkspaceController } from './workspace.controller.js';
+
+const bootstrapMock = vi.fn(() =>
+  Promise.resolve({
+    projectId: 'project-1',
+    workspacePath: '/opt/mosaic/.workspaces/users/user-1/project-1',
+  }),
+);
+
+const authGuard: CanActivate = {
+  canActivate(context: ExecutionContext): boolean {
+    const requestContext = context.switchToHttp().getRequest<{ user?: { id: string } }>();
+    requestContext.user = { id: 'user-1' };
+    return true;
+  },
+};
+
+describe('POST /api/workspaces repoUrl validation', () => {
+  let app: INestApplication;
+
+  beforeAll(async () => {
+    const moduleRef = await Test.createTestingModule({
+      controllers: [WorkspaceController],
+      providers: [
+        {
+          provide: ProjectBootstrapService,
+          useValue: { bootstrap: bootstrapMock },
+        },
+      ],
+    })
+      .overrideGuard(AuthGuard)
+      .useValue(authGuard)
+      .compile();
+
+    app = moduleRef.createNestApplication<NestFastifyApplication>(new FastifyAdapter());
+    app.useGlobalPipes(
+      new ValidationPipe({
+        whitelist: true,
+        forbidNonWhitelisted: true,
+        transform: true,
+      }),
+    );
+    await app.init();
+    await app.getHttpAdapter().getInstance().ready();
+  });
+
+  beforeEach(() => {
+    bootstrapMock.mockClear();
+  });
+
+  afterAll(async () => {
+    await app.close();
+  });
+
+  it.each([
+    ['a leading-dash value', '--upload-pack=sh -c id'],
+    ['an ext remote helper', 'ext::sh -c id'],
+    ['a file URL', 'file:///tmp/repository'],
+    ['an unparseable value', 'not a url'],
+    ['an SSH shorthand', '[email protected]:acme/repository.git'],
+    ['a scheme without //', 'https:example.com/acme/repository.git'],
+    ['a hostless git URL', 'git:///tmp/repository'],
+  ])('returns 400 for %s', async (_description, repoUrl) => {
+    const response = await request(app.getHttpServer())
+      .post('/api/workspaces')
+      .send({ name: 'Example', repoUrl })
+      .set('Content-Type', 'application/json');
+
+    expect(response.status).toBe(400);
+    expect(bootstrapMock).not.toHaveBeenCalled();
+  });
+
+  it.each([
+    ['a plain HTTPS repository URL', 'https://example.com/acme/repository.git'],
+    ['a git protocol repository URL', 'git://example.com/acme/repository.git'],
+  ])('accepts %s', async (_description, repoUrl) => {
+    const response = await request(app.getHttpServer())
+      .post('/api/workspaces')
+      .send({ name: 'Example', repoUrl })
+      .set('Content-Type', 'application/json');
+
+    expect(response.status).toBe(201);
+    expect(bootstrapMock).toHaveBeenCalledWith({
+      name: 'Example',
+      description: undefined,
+      userId: 'user-1',
+      teamId: undefined,
+      repoUrl,
+    });
+  });
+});

apps/gateway/src/workspace/workspace.controller.ts

@@ -1,7 +1,11 @@
 import { Body, Controller, Post, UseGuards } from '@nestjs/common';
 import { AuthGuard } from '../auth/auth.guard.js';
 import { CurrentUser } from '../auth/current-user.decorator.js';
-import { ProjectBootstrapService } from './project-bootstrap.service.js';
+import {
+  ProjectBootstrapService,
+  type BootstrapProjectResult,
+} from './project-bootstrap.service.js';
+import { CreateWorkspaceDto } from './workspace.dto.js';
 
 @Controller('api/workspaces')
 @UseGuards(AuthGuard)
@@ -11,20 +15,14 @@ export class WorkspaceController {
   @Post()
   async create(
     @CurrentUser() user: { id: string },
-    @Body()
+    @Body() dto: CreateWorkspaceDto,
-    body: {
+  ): Promise<BootstrapProjectResult> {
-      name: string;
-      description?: string;
-      teamId?: string;
-      repoUrl?: string;
-    },
-  ) {
     return this.bootstrap.bootstrap({
-      name: body.name,
+      name: dto.name,
-      description: body.description,
+      description: dto.description,
       userId: user.id,
-      teamId: body.teamId,
+      teamId: dto.teamId,
-      repoUrl: body.repoUrl,
+      repoUrl: dto.repoUrl,
     });
   }
 }

apps/gateway/src/workspace/workspace.dto.ts

@@ -0,0 +1,33 @@
+import { IsOptional, IsString, IsUrl, Matches, MaxLength } from 'class-validator';
+
+export class CreateWorkspaceDto {
+  @IsString()
+  @MaxLength(255)
+  name!: string;
+
+  @IsOptional()
+  @IsString()
+  @MaxLength(10_000)
+  description?: string;
+
+  @IsOptional()
+  @IsString()
+  teamId?: string;
+
+  @IsOptional()
+  @IsString()
+  @Matches(/^(?:https|git):\/\//i, {
+    message: 'repoUrl must be a valid https:// or git:// URL',
+  })
+  @IsUrl(
+    {
+      protocols: ['https', 'git'],
+      require_host: true,
+      require_protocol: true,
+      require_tld: false,
+      require_valid_protocol: true,
+    },
+    { message: 'repoUrl must be a valid https:// or git:// URL' },
+  )
+  repoUrl?: string;
+}

apps/gateway/src/workspace/workspace.service.spec.ts

@@ -1,11 +1,33 @@
-import { describe, it, expect, beforeEach } from 'vitest';
+import { BadRequestException } from '@nestjs/common';
-import { WorkspaceService } from './workspace.service.js';
+import fs from 'node:fs/promises';
+import os from 'node:os';
 import path from 'node:path';
+import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
+import { WorkspaceService } from './workspace.service.js';
+
+type ExecFileMock = (
+  command: string,
+  args: readonly string[],
+  options: { cwd: string },
+  callback: (error: Error | null, stdout: string, stderr: string) => void,
+) => void;
+
+const { execFileMock } = vi.hoisted(() => ({
+  execFileMock: vi.fn<ExecFileMock>(),
+}));
+
+vi.mock('node:child_process', () => ({
+  execFile: execFileMock,
+}));
 
 describe('WorkspaceService', () => {
   let service: WorkspaceService;
 
   beforeEach(() => {
+    execFileMock.mockReset();
+    execFileMock.mockImplementation((_command, _args, _options, callback) => {
+      callback(null, '', '');
+    });
     service = new WorkspaceService();
   });
 
@@ -76,4 +98,69 @@ describe('WorkspaceService', () => {
       }
     });
   });
+
+  describe('create', () => {
+    const project = {
+      id: 'project-1',
+      ownerType: 'user',
+      userId: 'user-1',
+      teamId: null,
+    } as const;
+
+    let originalRoot: string | undefined;
+    let temporaryRoot: string;
+
+    beforeEach(async () => {
+      originalRoot = process.env['MOSAIC_ROOT'];
+      temporaryRoot = await fs.mkdtemp(path.join(os.tmpdir(), 'mosaic-workspace-'));
+      process.env['MOSAIC_ROOT'] = temporaryRoot;
+      service = new WorkspaceService();
+    });
+
+    afterEach(async () => {
+      if (originalRoot === undefined) {
+        delete process.env['MOSAIC_ROOT'];
+      } else {
+        process.env['MOSAIC_ROOT'] = originalRoot;
+      }
+      await fs.rm(temporaryRoot, { recursive: true, force: true });
+    });
+
+    it.each([
+      ['a leading-dash URL', '--upload-pack=sh -c id'],
+      ['an ext remote helper', 'ext::sh -c id'],
+      ['a file URL', 'file:///tmp/repository'],
+      ['an unparseable value', 'not a url'],
+      ['an SSH shorthand', '[email protected]:acme/repository.git'],
+      ['a scheme without //', 'https:example.com/acme/repository.git'],
+      ['a hostless git URL', 'git:///tmp/repository'],
+    ])('rejects %s before invoking git', async (_description, repoUrl) => {
+      await expect(service.create(project, repoUrl)).rejects.toBeInstanceOf(BadRequestException);
+      expect(execFileMock).not.toHaveBeenCalled();
+    });
+
+    it.each([
+      ['an HTTPS URL', 'https://example.com/acme/repository.git'],
+      ['a git protocol URL', 'git://example.com/acme/repository.git'],
+    ])('accepts %s and invokes hardened git clone arguments', async (_description, repoUrl) => {
+      const workspacePath = await service.create(project, repoUrl);
+
+      expect(execFileMock).toHaveBeenCalledOnce();
+      expect(execFileMock).toHaveBeenCalledWith(
+        'git',
+        [
+          '-c',
+          'protocol.ext.allow=never',
+          '-c',
+          'protocol.file.allow=never',
+          'clone',
+          '--',
+          repoUrl,
+          '.',
+        ],
+        { cwd: workspacePath },
+        expect.any(Function),
+      );
+    });
+  });
 });

apps/gateway/src/workspace/workspace.service.ts

@@ -1,10 +1,30 @@
-import { Injectable, Logger } from '@nestjs/common';
+import { BadRequestException, Injectable, Logger } from '@nestjs/common';
 import fs from 'node:fs/promises';
 import path from 'node:path';
 import { execFile } from 'node:child_process';
 import { promisify } from 'node:util';
 
 const execFileAsync = promisify(execFile);
+const allowedRepositoryProtocols = new Set(['https:', 'git:']);
+const repositoryUrlPrefixPattern = /^(?:https|git):\/\//i;
+const repositoryUrlError = 'repoUrl must be a valid https:// or git:// URL';
+
+function assertAllowedRepositoryUrl(repoUrl: string): void {
+  if (repoUrl.startsWith('-') || !repositoryUrlPrefixPattern.test(repoUrl)) {
+    throw new BadRequestException(repositoryUrlError);
+  }
+
+  let parsedUrl: URL;
+  try {
+    parsedUrl = new URL(repoUrl);
+  } catch {
+    throw new BadRequestException(repositoryUrlError);
+  }
+
+  if (!allowedRepositoryProtocols.has(parsedUrl.protocol) || parsedUrl.hostname.length === 0) {
+    throw new BadRequestException(repositoryUrlError);
+  }
+}
 
 export interface WorkspaceProject {
   id: string;
@@ -39,14 +59,32 @@ export class WorkspaceService {
    * If repoUrl is provided, clone instead of init.
    */
   async create(project: WorkspaceProject, repoUrl?: string): Promise<string> {
+    if (repoUrl !== undefined) {
+      assertAllowedRepositoryUrl(repoUrl);
+    }
+
     const workspacePath = this.resolvePath(project);
 
     // Create directory
     await fs.mkdir(workspacePath, { recursive: true });
 
-    if (repoUrl) {
+    if (repoUrl !== undefined) {
-      // Clone existing repo
+      // Clone existing repo. Defense in depth keeps dangerous local helpers
-      await execFileAsync('git', ['clone', repoUrl, '.'], { cwd: workspacePath });
+      // disabled and terminates option parsing before positional arguments.
+      await execFileAsync(
+        'git',
+        [
+          '-c',
+          'protocol.ext.allow=never',
+          '-c',
+          'protocol.file.allow=never',
+          'clone',
+          '--',
+          repoUrl,
+          '.',
+        ],
+        { cwd: workspacePath },
+      );
       this.logger.log(`Cloned ${repoUrl} into workspace ${workspacePath}`);
     } else {
       // Init new git repo

apps/web/index.html

@@ -0,0 +1,30 @@
+<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="UTF-8" />
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+    <title>Mosaic</title>
+    <meta name="description" content="Mosaic Stack Dashboard" />
+    <link rel="preconnect" href="https://fonts.googleapis.com" />
+    <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+    <link
+      rel="stylesheet"
+      href="https://fonts.googleapis.com/css2?family=Outfit:wght@300;400;500;600;700&family=Fira+Code:wght@400;500&display=swap"
+    />
+    <script>
+      // set data-theme before first paint so the stored theme never flashes
+      (function () {
+        try {
+          var theme = window.localStorage.getItem('mosaic-theme') || 'dark';
+          document.documentElement.setAttribute('data-theme', theme === 'light' ? 'light' : 'dark');
+        } catch (error) {
+          document.documentElement.setAttribute('data-theme', 'dark');
+        }
+      })();
+    </script>
+  </head>
+  <body>
+    <div id="root"></div>
+    <script type="module" src="/src/main.tsx"></script>
+  </body>
+</html>

apps/web/package.json

@@ -3,8 +3,10 @@
   "version": "0.0.2",
   "private": true,
   "scripts": {
-    "build": "next build",
+    "build": "node ../../scripts/build-web.mjs",
+    "build:vite": "vite build",
     "dev": "next dev",
+    "dev:vite": "vite",
     "lint": "eslint src",
     "typecheck": "tsc --noEmit",
     "test": "vitest run --passWithNoTests",
@@ -13,12 +15,14 @@
   },
   "dependencies": {
     "@mosaicstack/design-tokens": "workspace:^",
+    "@mosaicstack/types": "workspace:^",
     "better-auth": "^1.5.5",
     "clsx": "^2.1.0",
     "next": "^16.0.0",
     "react": "^19.0.0",
     "react-dom": "^19.0.0",
     "react-markdown": "^10.1.0",
+    "react-router-dom": "^7.18.2",
     "socket.io-client": "^4.8.0",
     "tailwind-merge": "^3.5.0"
   },
@@ -28,9 +32,11 @@
     "@types/node": "^22.0.0",
     "@types/react": "^19.0.0",
     "@types/react-dom": "^19.0.0",
+    "@vitejs/plugin-react": "^6.0.5",
     "jsdom": "^29.0.0",
     "tailwindcss": "^4.0.0",
     "typescript": "^5.8.0",
-    "vitest": "^2.0.0"
+    "vite": "^8.2.1",
+    "vitest": "^3.2.7"
   }
 }

apps/web/src/app/auth/provider/[provider]/page.tsx

@@ -3,41 +3,56 @@
 import Link from 'next/link';
 import { useEffect, useState } from 'react';
 import { useParams, useSearchParams } from 'next/navigation';
+import { api } from '@/lib/api';
+import { resolveAuthCallbackURL } from '@/lib/auth-redirect';
 import { signIn } from '@/lib/auth-client';
-import { getSsoProvider } from '@/lib/sso-providers';
+import type { SsoProviderDiscovery } from '@/lib/sso';
 
 export default function AuthProviderRedirectPage(): React.ReactElement {
   const params = useParams<{ provider: string }>();
   const searchParams = useSearchParams();
   const providerId = typeof params.provider === 'string' ? params.provider : '';
-  const provider = getSsoProvider(providerId);
+  const requestedCallbackURL = searchParams.get('callbackURL');
-  const callbackURL = searchParams.get('callbackURL') ?? '/chat';
+  const [providerName, setProviderName] = useState<string | null>(null);
   const [error, setError] = useState<string | null>(null);
 
   useEffect(() => {
-    const currentProvider = provider;
-
-    if (!currentProvider) {
-      setError('Unknown SSO provider.');
-      return;
-    }
-
-    if (!currentProvider.enabled) {
-      setError(`${currentProvider.buttonLabel} is not enabled in this deployment.`);
-      return;
-    }
-
-    const activeProvider = currentProvider;
     let cancelled = false;
 
     async function redirectToProvider(): Promise<void> {
-      const result = await signIn.oauth2({
+      try {
-        providerId: activeProvider.id,
+        const callbackURL = resolveAuthCallbackURL(requestedCallbackURL, window.location.origin);
-        callbackURL,
+        const providers = await api<SsoProviderDiscovery[]>('/api/sso/providers');
-      });
+        if (cancelled) return;
 
-      if (!cancelled && result?.error) {
+        const provider = providers.find((candidate) => candidate.id === providerId);
-        setError(result.error.message ?? `${activeProvider.buttonLabel} sign in failed.`);
+        if (!provider) {
+          setError('Unknown SSO provider.');
+          return;
+        }
+
+        setProviderName(provider.name);
+        if (!provider.configured) {
+          setError(`${provider.name} is not enabled in this deployment.`);
+          return;
+        }
+        if (provider.loginMode !== 'oidc') {
+          setError(`${provider.name} is not available for OIDC sign in.`);
+          return;
+        }
+
+        const result = await signIn.oauth2({
+          providerId: provider.id,
+          callbackURL,
+        });
+
+        if (!cancelled && result?.error) {
+          setError(result.error.message ?? `${provider.name} sign in failed.`);
+        }
+      } catch (caught: unknown) {
+        if (!cancelled) {
+          setError(caught instanceof Error ? caught.message : 'Unable to start single sign-on.');
+        }
       }
     }
 
@@ -46,19 +61,22 @@ export default function AuthProviderRedirectPage(): React.ReactElement {
     return () => {
       cancelled = true;
     };
-  }, [callbackURL, provider]);
+  }, [providerId, requestedCallbackURL]);
 
   return (
     <div className="mx-auto flex min-h-[50vh] max-w-md flex-col justify-center">
       <h1 className="text-2xl font-semibold text-text-primary">Single sign-on</h1>
       <p className="mt-2 text-sm text-text-secondary">
-        {provider
+        {providerName
-          ? `Redirecting you to ${provider.buttonLabel.replace('Continue with ', '')}...`
+          ? `Redirecting you to ${providerName}...`
           : 'Preparing your sign-in request...'}
       </p>
 
       {error ? (
-        <div className="mt-6 rounded-lg border border-error/30 bg-error/10 px-4 py-3 text-sm text-error">
+        <div
+          role="alert"
+          className="mt-6 rounded-lg border border-error/30 bg-error/10 px-4 py-3 text-sm text-error"
+        >
           <p>{error}</p>
           <Link
             href="/login"

apps/web/src/lib/api.spec.ts

@@ -0,0 +1,57 @@
+import { afterEach, describe, expect, it, vi } from 'vitest';
+import { api } from './api';
+
+describe('api', () => {
+  afterEach(() => {
+    vi.unstubAllGlobals();
+  });
+
+  it('fetches the supplied relative path with credentials and a JSON body', async () => {
+    const fetchMock = vi.fn<typeof fetch>();
+    fetchMock.mockResolvedValue(
+      new Response(JSON.stringify({ ok: true }), {
+        status: 200,
+        headers: { 'Content-Type': 'application/json' },
+      }),
+    );
+    vi.stubGlobal('fetch', fetchMock);
+
+    await expect(
+      api<{ ok: boolean }>('/api/projects', {
+        method: 'POST',
+        body: { name: 'Mosaic' },
+      }),
+    ).resolves.toEqual({ ok: true });
+
+    expect(fetchMock).toHaveBeenCalledOnce();
+    expect(fetchMock).toHaveBeenCalledWith(
+      '/api/projects',
+      expect.objectContaining({
+        method: 'POST',
+        credentials: 'include',
+        body: JSON.stringify({ name: 'Mosaic' }),
+        headers: expect.objectContaining({
+          Accept: 'application/json',
+          'Content-Type': 'application/json',
+        }),
+      }),
+    );
+  });
+
+  it('throws the gateway JSON error with its statusCode', async () => {
+    const fetchMock = vi.fn<typeof fetch>();
+    fetchMock.mockResolvedValue(
+      new Response(JSON.stringify({ statusCode: 403, message: 'Forbidden' }), {
+        status: 403,
+        headers: { 'Content-Type': 'application/json' },
+      }),
+    );
+    vi.stubGlobal('fetch', fetchMock);
+
+    await expect(api('/api/admin/users')).rejects.toMatchObject({
+      name: 'Error',
+      message: 'Forbidden',
+      statusCode: 403,
+    });
+  });
+});

apps/web/src/lib/api.ts

@@ -1,5 +1,3 @@
-const GATEWAY_URL = process.env['NEXT_PUBLIC_GATEWAY_URL'] ?? 'http://localhost:14242';
-
 export interface ApiRequestInit extends Omit<RequestInit, 'body'> {
   body?: unknown;
 }
@@ -25,7 +23,7 @@ export async function api<T>(path: string, init?: ApiRequestInit): Promise<T> {
     headers['Content-Type'] = 'application/json';
   }
 
-  const res = await fetch(`${GATEWAY_URL}${path}`, {
+  const res = await fetch(path, {
     credentials: 'include',
     ...rest,
     headers,

apps/web/src/lib/auth-client.spec.ts

@@ -0,0 +1,29 @@
+import { afterEach, describe, expect, it, vi } from 'vitest';
+
+describe('auth client origin contract', () => {
+  afterEach(() => {
+    vi.unstubAllGlobals();
+    vi.resetModules();
+  });
+
+  it('uses the same-origin BetterAuth mount at /api/auth', async () => {
+    const fetchMock = vi.fn<typeof fetch>();
+    fetchMock.mockResolvedValue(
+      new Response(JSON.stringify({ session: null, user: null }), {
+        status: 200,
+        headers: { 'Content-Type': 'application/json' },
+      }),
+    );
+    vi.stubGlobal('fetch', fetchMock);
+
+    const { authClient } = await import('./auth-client');
+    await authClient.getSession();
+
+    expect(fetchMock).toHaveBeenCalledOnce();
+    const firstCall = fetchMock.mock.calls.at(0);
+    expect(firstCall).toBeDefined();
+    const requestURL = new URL(String(firstCall?.[0]), window.location.origin);
+    expect(requestURL.origin).toBe(window.location.origin);
+    expect(requestURL.pathname).toBe('/api/auth/get-session');
+  });
+});

apps/web/src/lib/auth-client.ts

@@ -1,8 +1,9 @@
 import { createAuthClient } from 'better-auth/react';
 import { adminClient, genericOAuthClient } from 'better-auth/client/plugins';
 
+// The gateway and BetterAuth client both use /api/auth. Omitting baseURL keeps
+// every browser request on the current origin in development and production.
 export const authClient = createAuthClient({
-  baseURL: process.env['NEXT_PUBLIC_GATEWAY_URL'] ?? 'http://localhost:14242',
   plugins: [adminClient(), genericOAuthClient()],
 });
 

apps/web/src/lib/auth-redirect.spec.ts

@@ -0,0 +1,30 @@
+import { describe, expect, it } from 'vitest';
+import { resolveAuthCallbackURL } from './auth-redirect';
+
+const CURRENT_ORIGIN = 'https://mosaic.example';
+
+describe('resolveAuthCallbackURL', () => {
+  it('preserves a canonical same-origin path with search and hash', () => {
+    expect(resolveAuthCallbackURL('/projects?view=active#current', CURRENT_ORIGIN)).toBe(
+      '/projects?view=active#current',
+    );
+  });
+
+  it.each([
+    null,
+    'chat',
+    '//evil.example',
+    '/..//evil.com',
+    '/..//evil.com/x',
+    '/./..//evil.com',
+    '/../..//evil.com',
+    '/foo/..//evil.com',
+    '/\\evil.example',
+    '/\n//evil.example',
+    '/\r//evil.example',
+    '/\t//evil.example',
+    'https://evil.example/phish',
+  ])('falls back to chat for an unsafe callback target %#', (candidate) => {
+    expect(resolveAuthCallbackURL(candidate, CURRENT_ORIGIN)).toBe('/chat');
+  });
+});

apps/web/src/lib/auth-redirect.ts

@@ -0,0 +1,23 @@
+const DEFAULT_AUTH_CALLBACK_URL = '/chat';
+
+/**
+ * Return a canonical same-origin path for post-auth navigation.
+ *
+ * Parsing before comparing origins rejects protocol-relative URLs, backslash
+ * variants, and control characters that the WHATWG parser normalizes away.
+ */
+export function resolveAuthCallbackURL(candidate: string | null, currentOrigin: string): string {
+  if (!candidate?.startsWith('/')) return DEFAULT_AUTH_CALLBACK_URL;
+
+  try {
+    const expectedOrigin = new URL(currentOrigin).origin;
+    const resolved = new URL(candidate, expectedOrigin);
+    if (resolved.origin !== expectedOrigin || resolved.pathname.startsWith('//')) {
+      return DEFAULT_AUTH_CALLBACK_URL;
+    }
+
+    return `${resolved.pathname}${resolved.search}${resolved.hash}`;
+  } catch {
+    return DEFAULT_AUTH_CALLBACK_URL;
+  }
+}

apps/web/src/lib/chat-contract.ts

@@ -0,0 +1,61 @@
+// Centralizes the type-only import of the shared `/chat` Socket.IO contract from
+// the public `@mosaicstack/types` package. `import type` is erased at compile
+// time, so this introduces no runtime dependency — it only reuses the exact
+// payload shapes instead of redeclaring them.
+import type { Socket } from 'socket.io-client';
+import type {
+  AbortPayload,
+  AgentEndPayload,
+  AgentStartPayload,
+  AgentTextPayload,
+  AgentThinkingPayload,
+  ChatMessagePayload,
+  ClientToServerEvents,
+  CommandDef,
+  CommandManifest,
+  CommandManifestPayload,
+  ErrorPayload,
+  MessageAckPayload,
+  RoutingDecisionInfo,
+  ServerToClientEvents,
+  SessionInfoPayload,
+  SessionUsagePayload,
+  SetThinkingPayload,
+  SkillCommandDef,
+  SlashCommandApprovalResultPayload,
+  SlashCommandPayload,
+  SlashCommandResultPayload,
+  SystemReloadPayload,
+  ToolEndPayload,
+  ToolStartPayload,
+} from '@mosaicstack/types';
+
+export type {
+  AbortPayload,
+  AgentEndPayload,
+  AgentStartPayload,
+  AgentTextPayload,
+  AgentThinkingPayload,
+  ChatMessagePayload,
+  ClientToServerEvents,
+  CommandDef,
+  CommandManifest,
+  CommandManifestPayload,
+  ErrorPayload,
+  MessageAckPayload,
+  RoutingDecisionInfo,
+  ServerToClientEvents,
+  SessionInfoPayload,
+  SessionUsagePayload,
+  SetThinkingPayload,
+  SkillCommandDef,
+  SlashCommandApprovalResultPayload,
+  SlashCommandPayload,
+  SlashCommandResultPayload,
+  SystemReloadPayload,
+  ToolEndPayload,
+  ToolStartPayload,
+};
+
+/** The `/chat` namespace socket, narrowed to the exact typed event contract. */
+export type ChatSocket = Socket<ServerToClientEvents, ClientToServerEvents>;

apps/web/src/lib/socket.spec.ts

@@ -0,0 +1,98 @@
+import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
+
+const { ioMock } = vi.hoisted(() => ({
+  ioMock: vi.fn(),
+}));
+
+vi.mock('socket.io-client', () => ({
+  io: ioMock,
+}));
+
+import { destroySocket, getSocket } from './socket';
+
+interface MockChatSocket {
+  on: ReturnType<typeof vi.fn>;
+  offAny: ReturnType<typeof vi.fn>;
+  disconnect: ReturnType<typeof vi.fn>;
+  /** Test-only helper: fires every handler registered for `event` via
+   * `.on`, mirroring how a real socket.io-client instance invokes its own
+   * listeners (e.g. calling the registered `disconnect` handler(s) on a
+   * real transient disconnect). */
+  trigger(event: string): void;
+}
+
+function createMockSocket(): MockChatSocket {
+  const handlers = new Map<string, Set<() => void>>();
+  const mockSocket: MockChatSocket = {
+    on: vi.fn((event: string, handler: () => void) => {
+      if (!handlers.has(event)) handlers.set(event, new Set());
+      handlers.get(event)?.add(handler);
+      return mockSocket;
+    }),
+    offAny: vi.fn(() => mockSocket),
+    disconnect: vi.fn(() => mockSocket),
+    trigger(event: string): void {
+      for (const handler of handlers.get(event) ?? []) handler();
+    },
+  };
+  return mockSocket;
+}
+
+let currentMock!: MockChatSocket;
+
+describe('chat socket', () => {
+  beforeEach(() => {
+    ioMock.mockReset();
+    // A fresh object per io() call so identity assertions (same singleton vs.
+    // a genuinely new instance) are meaningful.
+    ioMock.mockImplementation(() => {
+      currentMock = createMockSocket();
+      return currentMock;
+    });
+  });
+
+  afterEach(() => {
+    destroySocket();
+  });
+
+  it('creates one same-origin /chat namespace socket', () => {
+    const first = getSocket();
+    const second = getSocket();
+
+    expect(first).toBe(second);
+    expect(ioMock).toHaveBeenCalledOnce();
+    expect(ioMock).toHaveBeenCalledWith('/chat', {
+      withCredentials: true,
+      autoConnect: false,
+      transports: ['websocket', 'polling'],
+    });
+  });
+
+  it('keeps the same singleton instance across a transient disconnect', () => {
+    const first = getSocket();
+
+    // socket.ts must not react to a real socket's `disconnect` event by
+    // nulling the singleton — it registers no such handler at all now.
+    // Actually fire every handler registered via `.on('disconnect', ...)`
+    // (mirroring a real socket.io-client reconnect) instead of merely
+    // calling getSocket() again: this is what makes the test fail if
+    // production reintroduces `socket.on('disconnect', () => { socket =
+    // null; })`, since that handler would run here and null the singleton
+    // before the next getSocket() call.
+    currentMock.trigger('disconnect');
+    const second = getSocket();
+
+    expect(second).toBe(first);
+    expect(ioMock).toHaveBeenCalledOnce();
+  });
+
+  it('only creates a new singleton after an explicit destroySocket()', () => {
+    const first = getSocket();
+
+    destroySocket();
+    const second = getSocket();
+
+    expect(second).not.toBe(first);
+    expect(ioMock).toHaveBeenCalledTimes(2);
+  });
+});

apps/web/src/lib/socket.ts

@@ -1,23 +1,27 @@
-import { io, type Socket } from 'socket.io-client';
+import { io } from 'socket.io-client';
+import type { ChatSocket } from './chat-contract';
 
-const GATEWAY_URL = process.env['NEXT_PUBLIC_GATEWAY_URL'] ?? 'http://localhost:14242';
+let socket: ChatSocket | null = null;
 
-let socket: Socket | null = null;
+export function getSocket(): ChatSocket {
-
-export function getSocket(): Socket {
   if (!socket) {
-    socket = io(`${GATEWAY_URL}/chat`, {
+    // socket.io-client 4.8.3's `io()` factory declaration always returns the
+    // default unparameterized Socket (it accepts no <ListenEvents, EmitEvents>
+    // generics), so this one cast is the unavoidable boundary between that and the
+    // typed `/chat` contract. Every other call site uses the resulting ChatSocket
+    // with no further assertions.
+    socket = io('/chat', {
       withCredentials: true,
       autoConnect: false,
       transports: ['websocket', 'polling'],
-    });
+    }) as unknown as ChatSocket;
 
-    // Reset singleton reference when socket is fully closed so the next
+    // A transient `disconnect` (network blip, server restart) must NOT null
-    // getSocket() call creates a fresh instance instead of returning a
+    // the singleton: socket.io-client auto-reconnects this same instance,
-    // closed/dead socket.
+    // and its listeners stay registered across that reconnect. Nulling here
-    socket.on('disconnect', () => {
+    // previously orphaned those listeners on the next getSocket() call by
-      socket = null;
+    // handing back a brand-new, unconnected instance. Only destroySocket()
-    });
+    // (an explicit, intentional teardown) may reset the singleton.
   }
   return socket;
 }

apps/web/src/lib/sso-providers.test.ts

@@ -1,48 +0,0 @@
-import { afterEach, describe, expect, it, vi } from 'vitest';
-import { getEnabledSsoProviders, getSsoProvider } from './sso-providers';
-
-describe('sso-providers', () => {
-  afterEach(() => {
-    vi.unstubAllEnvs();
-  });
-
-  it('returns the enabled providers in login button order', () => {
-    vi.stubEnv('NEXT_PUBLIC_WORKOS_ENABLED', 'true');
-    vi.stubEnv('NEXT_PUBLIC_KEYCLOAK_ENABLED', 'true');
-
-    expect(getEnabledSsoProviders()).toEqual([
-      {
-        id: 'workos',
-        buttonLabel: 'Continue with WorkOS',
-        description: 'Enterprise SSO via WorkOS',
-        enabled: true,
-        href: '/auth/provider/workos',
-      },
-      {
-        id: 'keycloak',
-        buttonLabel: 'Continue with Keycloak',
-        description: 'Enterprise SSO via Keycloak',
-        enabled: true,
-        href: '/auth/provider/keycloak',
-      },
-    ]);
-  });
-
-  it('marks disabled providers without exposing them in the enabled list', () => {
-    vi.stubEnv('NEXT_PUBLIC_WORKOS_ENABLED', 'true');
-    vi.stubEnv('NEXT_PUBLIC_KEYCLOAK_ENABLED', 'false');
-
-    expect(getEnabledSsoProviders().map((provider) => provider.id)).toEqual(['workos']);
-    expect(getSsoProvider('keycloak')).toEqual({
-      id: 'keycloak',
-      buttonLabel: 'Continue with Keycloak',
-      description: 'Enterprise SSO via Keycloak',
-      enabled: false,
-      href: '/auth/provider/keycloak',
-    });
-  });
-
-  it('returns null for unknown providers', () => {
-    expect(getSsoProvider('authentik')).toBeNull();
-  });
-});

apps/web/src/lib/sso-providers.ts

@@ -1,53 +0,0 @@
-export type SsoProviderId = 'workos' | 'keycloak';
-
-export interface SsoProvider {
-  id: SsoProviderId;
-  buttonLabel: string;
-  description: string;
-  enabled: boolean;
-  href: string;
-}
-
-const PROVIDER_METADATA: Record<SsoProviderId, Omit<SsoProvider, 'enabled' | 'href'>> = {
-  workos: {
-    id: 'workos',
-    buttonLabel: 'Continue with WorkOS',
-    description: 'Enterprise SSO via WorkOS',
-  },
-  keycloak: {
-    id: 'keycloak',
-    buttonLabel: 'Continue with Keycloak',
-    description: 'Enterprise SSO via Keycloak',
-  },
-};
-
-export function getEnabledSsoProviders(): SsoProvider[] {
-  return (Object.keys(PROVIDER_METADATA) as SsoProviderId[])
-    .map((providerId) => getSsoProvider(providerId))
-    .filter((provider): provider is SsoProvider => provider?.enabled === true);
-}
-
-export function getSsoProvider(providerId: string): SsoProvider | null {
-  if (!isSsoProviderId(providerId)) {
-    return null;
-  }
-
-  return {
-    ...PROVIDER_METADATA[providerId],
-    enabled: isSsoProviderEnabled(providerId),
-    href: `/auth/provider/${providerId}`,
-  };
-}
-
-function isSsoProviderId(value: string): value is SsoProviderId {
-  return value === 'workos' || value === 'keycloak';
-}
-
-function isSsoProviderEnabled(providerId: SsoProviderId): boolean {
-  switch (providerId) {
-    case 'workos':
-      return process.env['NEXT_PUBLIC_WORKOS_ENABLED'] === 'true';
-    case 'keycloak':
-      return process.env['NEXT_PUBLIC_KEYCLOAK_ENABLED'] === 'true';
-  }
-}

apps/web/src/main.tsx

@@ -0,0 +1,19 @@
+import { StrictMode } from 'react';
+import { createRoot } from 'react-dom/client';
+import { RouterProvider } from 'react-router-dom';
+import { ThemeProvider } from '@/providers/theme-provider';
+import { createAppRouter } from '@/routes';
+import '@/app/globals.css';
+
+const container = document.getElementById('root');
+if (!container) {
+  throw new Error('missing #root element');
+}
+
+createRoot(container).render(
+  <StrictMode>
+    <ThemeProvider>
+      <RouterProvider router={createAppRouter()} />
+    </ThemeProvider>
+  </StrictMode>,
+);

apps/web/src/routes.tsx

@@ -0,0 +1,51 @@
+import type { ReactElement } from 'react';
+import { createBrowserRouter, Navigate, Outlet, type RouteObject } from 'react-router-dom';
+import { LoginPage } from '@/spa/pages/login';
+import { RegisterPage } from '@/spa/pages/register';
+import { SsoCallbackPage } from '@/spa/pages/sso-callback';
+import { ChatPage } from '@/spa/pages/chat';
+import { ChatRouteErrorBoundary } from '@/spa/pages/chat-error-boundary';
+import { AuthGuard, GuestGuard } from '@/spa/guards';
+import { Placeholder } from '@/spa/placeholder';
+
+function GuestLayout(): ReactElement {
+  return (
+    <div className="flex min-h-screen items-center justify-center bg-surface-bg px-4 py-8">
+      <div className="w-full max-w-md rounded-xl border border-surface-border bg-surface-card p-8 shadow-lg">
+        <Outlet />
+      </div>
+    </div>
+  );
+}
+
+export const routes: RouteObject[] = [
+  {
+    element: <GuestGuard />,
+    children: [
+      {
+        element: <GuestLayout />,
+        children: [
+          { path: '/login', element: <LoginPage /> },
+          { path: '/register', element: <RegisterPage /> },
+          { path: '/auth/provider/:provider', element: <SsoCallbackPage /> },
+        ],
+      },
+    ],
+  },
+  {
+    element: <AuthGuard />,
+    children: [
+      { path: '/', element: <Navigate to="/chat" replace /> },
+      { path: '/chat', element: <ChatPage />, errorElement: <ChatRouteErrorBoundary /> },
+      { path: '/projects', element: <Placeholder title="Projects" /> },
+      { path: '/projects/:id', element: <Placeholder title="Project" /> },
+      { path: '/tasks', element: <Placeholder title="Tasks" /> },
+      { path: '/settings', element: <Placeholder title="Settings" /> },
+      { path: '/admin', element: <Placeholder title="Admin" /> },
+    ],
+  },
+];
+
+export function createAppRouter(): ReturnType<typeof createBrowserRouter> {
+  return createBrowserRouter(routes);
+}

apps/web/src/spa/chat/commands-panel.spec.tsx

@@ -0,0 +1,280 @@
+import { act } from 'react';
+import { createRoot, type Root } from 'react-dom/client';
+import { afterAll, afterEach, beforeAll, describe, expect, it, vi } from 'vitest';
+import { CommandsPanel } from './commands-panel';
+
+beforeAll(() => {
+  Object.defineProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT', {
+    configurable: true,
+    value: true,
+  });
+});
+
+afterAll(() => {
+  Reflect.deleteProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT');
+});
+
+let root: Root | null;
+let container: HTMLElement | null;
+
+async function render(node: Parameters<Root['render']>[0]): Promise<void> {
+  container = document.createElement('div');
+  document.body.append(container);
+  root = createRoot(container);
+  await act(async () => {
+    root?.render(node);
+  });
+}
+
+afterEach(async () => {
+  await act(async () => {
+    root?.unmount();
+  });
+  document.body.replaceChildren();
+  root = null;
+  container = null;
+});
+
+describe('CommandsPanel', () => {
+  it('shows the frozen local pendingApproval args in the confirmation area, regardless of misleading server message text', async () => {
+    await render(
+      <CommandsPanel
+        manifest={null}
+        results={[]}
+        approval={{
+          conversationId: 'c1',
+          command: 'deploy', // matches pendingApproval — this is a legitimately approved request
+          success: true,
+          approvalId: 'ap1',
+          expiresAt: '2026-01-01T00:00:00.000Z',
+          // Free-text server message claims a different, less alarming target
+          // than what will actually be sent — the UI must not rely on this.
+          message: 'This will only affect the staging environment.',
+        }}
+        pendingApproval={{ command: 'deploy', args: 'prod' }}
+        hasConversation
+        onExecute={vi.fn()}
+        onApprove={vi.fn()}
+        onRunApproved={vi.fn()}
+      />,
+    );
+
+    // The exact frozen combined action is visible...
+    expect(container?.textContent).toContain('/deploy');
+    expect(container?.textContent).toContain('prod');
+    // ...and the misleading server free-text is never shown next to it.
+    expect(container?.textContent).not.toContain('staging environment');
+  });
+
+  it('does not throw when a manifest commands entry is null', async () => {
+    const manifest = {
+      commands: [
+        null,
+        {
+          name: 'model',
+          aliases: [],
+          description: 'Change the active model',
+          scope: 'core',
+          execution: 'socket',
+          available: true,
+        },
+      ],
+      skills: [null],
+      version: 1,
+    } as unknown as Parameters<typeof CommandsPanel>[0]['manifest'];
+
+    await expect(
+      render(
+        <CommandsPanel
+          manifest={manifest}
+          results={[]}
+          approval={null}
+          pendingApproval={null}
+          hasConversation={false}
+          onExecute={vi.fn()}
+          onApprove={vi.fn()}
+          onRunApproved={vi.fn()}
+        />,
+      ),
+    ).resolves.not.toThrow();
+
+    expect(container?.textContent).toContain('model');
+  });
+
+  it('shows an explicit no-args fallback when the frozen pendingApproval has no args', async () => {
+    await render(
+      <CommandsPanel
+        manifest={null}
+        results={[]}
+        approval={{
+          conversationId: 'c1',
+          command: 'deploy',
+          success: true,
+          approvalId: 'ap1',
+          expiresAt: '2026-01-01T00:00:00.000Z',
+        }}
+        pendingApproval={{ command: 'deploy' }}
+        hasConversation
+        onExecute={vi.fn()}
+        onApprove={vi.fn()}
+        onRunApproved={vi.fn()}
+      />,
+    );
+
+    expect(container?.textContent?.toLowerCase()).toContain('no args');
+  });
+
+  it('renders skills from a skills-only manifest', async () => {
+    await render(
+      <CommandsPanel
+        manifest={{
+          commands: [],
+          skills: [{ name: 'brave-search', description: 'Search the web', available: true }],
+          version: 1,
+        }}
+        results={[]}
+        approval={null}
+        pendingApproval={null}
+        hasConversation={false}
+        onExecute={vi.fn()}
+        onApprove={vi.fn()}
+        onRunApproved={vi.fn()}
+      />,
+    );
+
+    expect(container?.textContent).toContain('brave-search');
+    expect(container?.textContent).toContain('Search the web');
+  });
+
+  it('does not show the Run affordance when approval.success/approvalId are objects, even though command matches pendingApproval', async () => {
+    const approval = {
+      conversationId: 'c1',
+      command: 'deploy',
+      success: { truthy: 'object' },
+      approvalId: { also: 'object' },
+    } as unknown as Parameters<typeof CommandsPanel>[0]['approval'];
+
+    await render(
+      <CommandsPanel
+        manifest={null}
+        results={[]}
+        approval={approval}
+        pendingApproval={{ command: 'deploy', args: 'prod' }}
+        hasConversation
+        onExecute={vi.fn()}
+        onApprove={vi.fn()}
+        onRunApproved={vi.fn()}
+      />,
+    );
+
+    expect(
+      [...(container?.querySelectorAll('button') ?? [])].some((button) =>
+        button.textContent?.includes('Run approved command'),
+      ),
+    ).toBe(false);
+  });
+
+  it('shows the guarded server-provided denial reason for a denied approval', async () => {
+    await render(
+      <CommandsPanel
+        manifest={null}
+        results={[]}
+        approval={{
+          conversationId: 'c1',
+          command: 'deploy',
+          success: false,
+          message: 'Not authorized',
+        }}
+        pendingApproval={{ command: 'deploy', args: 'prod' }}
+        hasConversation
+        onExecute={vi.fn()}
+        onApprove={vi.fn()}
+        onRunApproved={vi.fn()}
+      />,
+    );
+
+    expect(container?.textContent).toContain('Not authorized');
+  });
+
+  it('falls back to a stable "Denied." copy when a denial has no usable message', async () => {
+    await render(
+      <CommandsPanel
+        manifest={null}
+        results={[]}
+        approval={{ conversationId: 'c1', command: 'deploy', success: false }}
+        pendingApproval={{ command: 'deploy', args: 'prod' }}
+        hasConversation
+        onExecute={vi.fn()}
+        onApprove={vi.fn()}
+        onRunApproved={vi.fn()}
+      />,
+    );
+
+    expect(container?.textContent).toContain('Denied.');
+  });
+
+  it('shows the guarded contract-provided reason for a failed command result, falling back to a stable copy only when absent', async () => {
+    await render(
+      <CommandsPanel
+        manifest={null}
+        results={[
+          { conversationId: 'c1', command: 'model', success: false, message: 'Unknown model' },
+          { conversationId: 'c1', command: 'deploy', success: false },
+        ]}
+        approval={null}
+        pendingApproval={null}
+        hasConversation={false}
+        onExecute={vi.fn()}
+        onApprove={vi.fn()}
+        onRunApproved={vi.fn()}
+      />,
+    );
+
+    expect(container?.textContent).toContain('Unknown model');
+    expect(container?.textContent).toContain('Command failed.');
+  });
+
+  it('bounds an oversized command result message at the render site as defense-in-depth', async () => {
+    const hostileMessage = 'y'.repeat(50_000);
+    await render(
+      <CommandsPanel
+        manifest={null}
+        results={[
+          { conversationId: 'c1', command: 'model', success: false, message: hostileMessage },
+        ]}
+        approval={null}
+        pendingApproval={null}
+        hasConversation={false}
+        onExecute={vi.fn()}
+        onApprove={vi.fn()}
+        onRunApproved={vi.fn()}
+      />,
+    );
+
+    const text = container?.textContent ?? '';
+    expect(text.length).toBeLessThan(hostileMessage.length);
+  });
+
+  it('does not throw when the manifest fields are malformed (non-array commands/skills)', async () => {
+    const manifest = {
+      commands: 'not-an-array',
+      skills: null,
+      version: 1,
+    } as unknown as Parameters<typeof CommandsPanel>[0]['manifest'];
+
+    await expect(
+      render(
+        <CommandsPanel
+          manifest={manifest}
+          results={[]}
+          approval={null}
+          pendingApproval={null}
+          hasConversation={false}
+          onExecute={vi.fn()}
+          onApprove={vi.fn()}
+          onRunApproved={vi.fn()}
+        />,
+      ),
+    ).resolves.not.toThrow();
+  });
+});

apps/web/src/spa/chat/commands-panel.tsx

@@ -0,0 +1,164 @@
+import { useState, type ReactElement } from 'react';
+import type { PendingApproval } from './use-chat-connection';
+import { MAX_COMMAND_MESSAGE_CHARS } from './limits';
+import { asNonEmptyString, asString } from './runtime-guards';
+import type {
+  CommandManifest,
+  SlashCommandApprovalResultPayload,
+  SlashCommandResultPayload,
+} from '@/lib/chat-contract';
+
+/** Stable fallback copy shown for a failed command only when the server's
+ * own guarded, non-empty `message` (e.g. "Unknown model") is absent or
+ * malformed — the structured contract reason itself is otherwise shown
+ * directly, never a raw thrown exception, stack trace, or object value. */
+const COMMAND_FAILURE_COPY = 'Command failed.';
+
+/** Render-site defense-in-depth: `use-chat-connection.ts` already bounds a
+ * stored command:result message at ingestion, but this component must never
+ * assume every caller went through that path — bounding again here means a
+ * hostile/oversized message can never force an unbounded render. */
+function boundMessage(value: string): string {
+  return value.length > MAX_COMMAND_MESSAGE_CHARS
+    ? value.slice(0, MAX_COMMAND_MESSAGE_CHARS)
+    : value;
+}
+
+interface CommandsPanelProps {
+  manifest: CommandManifest | null;
+  results: SlashCommandResultPayload[];
+  approval: SlashCommandApprovalResultPayload | null;
+  pendingApproval: PendingApproval | null;
+  hasConversation: boolean;
+  onExecute: (input: { command: string; args?: string }) => void;
+  onApprove: (input: { command: string; args?: string }) => void;
+  onRunApproved: () => void;
+}
+
+export function CommandsPanel({
+  manifest,
+  results,
+  approval,
+  pendingApproval,
+  hasConversation,
+  onExecute,
+  onApprove,
+  onRunApproved,
+}: CommandsPanelProps): ReactElement {
+  const [command, setCommand] = useState('');
+  const [args, setArgs] = useState('');
+
+  // Defense-in-depth: the reducer already normalizes success/approvalId
+  // before storing `approval`, but a matching command string alone must
+  // never be trusted here either — require the literal boolean `true` and a
+  // non-empty string approvalId, not merely truthy values.
+  const canRunApproved =
+    approval?.success === true &&
+    typeof approval.approvalId === 'string' &&
+    approval.approvalId.length > 0 &&
+    !!pendingApproval &&
+    pendingApproval.command === approval.command;
+
+  // A manifest arrives from the server as untyped JSON at runtime — guard
+  // both collections before mapping so a malformed manifest cannot throw.
+  const commands = Array.isArray(manifest?.commands) ? manifest.commands : [];
+  const skills = Array.isArray(manifest?.skills) ? manifest.skills : [];
+
+  return (
+    <section aria-label="Commands" className="flex flex-col gap-2 border-b px-4 py-3 text-xs">
+      {commands.length > 0 ? (
+        <ul aria-label="Available commands" className="flex flex-col gap-1">
+          {commands.map((cmd, index) => (
+            <li key={asString(cmd?.name) || `cmd-${index}`}>
+              <strong>/{asString(cmd?.name)}</strong> — {asString(cmd?.description)}
+            </li>
+          ))}
+        </ul>
+      ) : null}
+
+      {skills.length > 0 ? (
+        <ul aria-label="Available skills" className="flex flex-col gap-1">
+          {skills.map((skill, index) => (
+            <li key={asString(skill?.name) || `skill-${index}`}>
+              <strong>/skill:{asString(skill?.name)}</strong> — {asString(skill?.description)}
+            </li>
+          ))}
+        </ul>
+      ) : null}
+
+      <div className="flex flex-wrap items-center gap-2">
+        <input
+          aria-label="Command name"
+          value={command}
+          onChange={(event) => setCommand(event.target.value)}
+          placeholder="command"
+        />
+        <input
+          aria-label="Command arguments"
+          value={args}
+          onChange={(event) => setArgs(event.target.value)}
+          placeholder="args (optional)"
+        />
+        <button
+          type="button"
+          disabled={!hasConversation || !command.trim()}
+          onClick={() => onExecute({ command: command.trim(), args: args.trim() || undefined })}
+        >
+          Run command
+        </button>
+        <button
+          type="button"
+          disabled={!hasConversation || !command.trim()}
+          onClick={() => onApprove({ command: command.trim(), args: args.trim() || undefined })}
+        >
+          Request approval
+        </button>
+      </div>
+
+      {approval ? (
+        <div role={approval.success ? 'status' : 'alert'} className="flex items-center gap-2">
+          {/* A successful approval shows stable client copy only — never
+              the server-controlled approval.message or echoed
+              approval.command as the primary confirmation. The frozen local
+              pendingApproval below (not this line) is the sole authoritative
+              statement of what will run. A denial, by contrast, is not an
+              execution authority and safely surfaces the guarded structured
+              reason the server gave (e.g. "Not authorized"), falling back to
+              a stable copy only when absent/malformed. */}
+          <span>
+            {approval.success ? 'Approved.' : asNonEmptyString(approval.message, 'Denied.')}
+          </span>
+          {canRunApproved && pendingApproval ? (
+            <>
+              {/* Authoritative frozen local command+args — what the click below
+                  will actually emit. The server's `approval` above is display-only
+                  and must never be trusted to represent the executed payload. */}
+              <span>
+                Will run: /{pendingApproval.command}{' '}
+                {pendingApproval.args ? pendingApproval.args : '(no args)'}
+              </span>
+              <button type="button" onClick={onRunApproved}>
+                Run approved command
+              </button>
+            </>
+          ) : null}
+        </div>
+      ) : null}
+
+      {results.length > 0 ? (
+        <ul aria-label="Command results" className="flex flex-col gap-1">
+          {results.map((result, index) => (
+            <li key={`${result.command}-${index}`} role={result.success ? 'status' : 'alert'}>
+              /{asString(result.command)}: {result.success ? 'success' : 'failed'}
+              {result.success
+                ? typeof result.message === 'string' && result.message
+                  ? ` — ${boundMessage(result.message)}`
+                  : ''
+                : ` — ${boundMessage(asNonEmptyString(result.message, COMMAND_FAILURE_COPY))}`}
+            </li>
+          ))}
+        </ul>
+      ) : null}
+    </section>
+  );
+}

apps/web/src/spa/chat/composer.tsx

@@ -0,0 +1,98 @@
+import { useState, type KeyboardEvent, type ReactElement } from 'react';
+
+interface ComposerProps {
+  onSend: (input: { content: string; provider?: string; modelId?: string }) => void;
+  onStop: () => void;
+  streaming: boolean;
+  /** True from local send time through server turn startup/ack and
+   * throughout streaming — a superset of `streaming` that also covers the
+   * pre-ack window where a second send could otherwise slip through. */
+  sending: boolean;
+  hasConversation: boolean;
+}
+
+export function Composer({
+  onSend,
+  onStop,
+  streaming,
+  sending,
+  hasConversation,
+}: ComposerProps): ReactElement {
+  const [content, setContent] = useState('');
+  const [provider, setProvider] = useState('');
+  const [modelId, setModelId] = useState('');
+  const busy = streaming || sending;
+
+  function submit(): void {
+    if (busy) return;
+    const trimmed = content.trim();
+    if (!trimmed) return;
+    onSend({
+      content: trimmed,
+      provider: provider.trim() || undefined,
+      modelId: modelId.trim() || undefined,
+    });
+    setContent('');
+  }
+
+  function handleKeyDown(event: KeyboardEvent<HTMLTextAreaElement>): void {
+    if (event.key === 'Enter' && !event.shiftKey) {
+      event.preventDefault();
+      submit();
+    }
+  }
+
+  return (
+    <form
+      onSubmit={(event) => {
+        event.preventDefault();
+        submit();
+      }}
+      className="flex flex-col gap-2 border-t p-4"
+    >
+      <div className="flex flex-wrap gap-2">
+        <input
+          aria-label="Provider"
+          value={provider}
+          onChange={(event) => setProvider(event.target.value)}
+          placeholder="Provider (optional)"
+          className="rounded border px-2 py-1 text-xs"
+        />
+        <input
+          aria-label="Model"
+          value={modelId}
+          onChange={(event) => setModelId(event.target.value)}
+          placeholder="Model (optional)"
+          className="rounded border px-2 py-1 text-xs"
+        />
+      </div>
+      <div className="flex items-end gap-2">
+        <textarea
+          aria-label="Message"
+          value={content}
+          onChange={(event) => setContent(event.target.value)}
+          onKeyDown={handleKeyDown}
+          rows={2}
+          placeholder="Message… (Enter to send, Shift+Enter for a new line)"
+          className="flex-1 resize-none rounded border px-3 py-2 text-sm"
+        />
+        <button
+          type="submit"
+          disabled={!content.trim() || busy}
+          className="rounded px-3 py-2 text-sm font-medium"
+        >
+          Send
+        </button>
+        <button
+          type="button"
+          aria-label="Stop"
+          disabled={!hasConversation || !streaming}
+          onClick={onStop}
+          className="rounded px-3 py-2 text-sm font-medium"
+        >
+          Stop
+        </button>
+      </div>
+    </form>
+  );
+}

apps/web/src/spa/chat/limits.ts

@@ -0,0 +1,22 @@
+/**
+ * Bounds on server-fed chat state. A hostile or malfunctioning gateway can
+ * flood any of these collections; caps keep memory/render cost flat instead
+ * of growing unboundedly for the lifetime of the connection.
+ */
+
+/** Max characters retained for the in-flight streamed text/thinking buffers. */
+export const MAX_STREAM_CHARS = 20_000;
+/** Max transcript turns retained (oldest dropped first). */
+export const MAX_MESSAGES = 500;
+/** Max tool-call entries (including anomaly entries) retained per turn history. */
+export const MAX_TOOLS = 200;
+/** Max slash-command results retained. */
+export const MAX_COMMAND_RESULTS = 200;
+/** Max commands/skills accepted from a single manifest push. */
+export const MAX_MANIFEST_ITEMS = 500;
+/** Max executed approval IDs remembered for single-flight dedup. */
+export const MAX_EXECUTED_APPROVAL_IDS = 200;
+/** Max characters retained for a single command:result message — a hostile
+ * or malfunctioning gateway must not be able to push an unbounded curated
+ * success/failure reason into state (or, defensively, onto the page). */
+export const MAX_COMMAND_MESSAGE_CHARS = 1_000;

apps/web/src/spa/chat/message-transcript.tsx

@@ -0,0 +1,39 @@
+import type { ReactElement } from 'react';
+import type { ChatTranscriptMessage } from './use-chat-connection';
+
+interface MessageTranscriptProps {
+  messages: ChatTranscriptMessage[];
+  streaming: boolean;
+  text: string;
+}
+
+export function MessageTranscript({
+  messages,
+  streaming,
+  text,
+}: MessageTranscriptProps): ReactElement {
+  return (
+    <div
+      role="log"
+      aria-live="polite"
+      aria-label="Conversation"
+      className="flex flex-1 flex-col gap-3 overflow-y-auto p-4"
+    >
+      {messages.map((message) => (
+        <div key={message.id} data-role={message.role} className="whitespace-pre-wrap text-sm">
+          <span className="font-medium">{message.role === 'user' ? 'You' : 'Assistant'}: </span>
+          <span>{message.text}</span>
+          {message.thinking ? (
+            <div className="pt-1 text-xs italic opacity-70">{message.thinking}</div>
+          ) : null}
+        </div>
+      ))}
+      {streaming ? (
+        <div data-role="assistant-streaming" className="whitespace-pre-wrap text-sm">
+          <span className="font-medium">Assistant: </span>
+          <span>{text || 'Thinking…'}</span>
+        </div>
+      ) : null}
+    </div>
+  );
+}

apps/web/src/spa/chat/runtime-guards.ts

@@ -0,0 +1,49 @@
+/**
+ * Socket.IO payloads are only statically typed at the call site — a
+ * misbehaving or compromised gateway can send anything at runtime. These
+ * guards protect the dereference sites that would otherwise throw (`.map` on
+ * a non-array, `.toFixed` on a non-number) or render an object as a React
+ * child.
+ */
+
+export function asString(value: unknown, fallback = ''): string {
+  return typeof value === 'string' ? value : fallback;
+}
+
+/** Like `asString`, but an empty string also falls back — used for guarded
+ * contract-provided reason strings (e.g. a denial or failure message) where
+ * an empty string is not a meaningful value to display in place of the
+ * stable fallback copy. */
+export function asNonEmptyString(value: unknown, fallback: string): string {
+  return typeof value === 'string' && value.length > 0 ? value : fallback;
+}
+
+export function asFiniteNumber(value: unknown, fallback = 0): number {
+  return typeof value === 'number' && Number.isFinite(value) ? value : fallback;
+}
+
+/** Like `asFiniteNumber`, but returns `null` on failure instead of a numeric
+ * fallback — callers that must not fabricate a plausible-looking value (e.g.
+ * `0 tokens` / `$0.0000` for genuinely unknown usage) use this to render an
+ * honest "unavailable" label instead. */
+export function asFiniteNumberOrNull(value: unknown): number | null {
+  return typeof value === 'number' && Number.isFinite(value) ? value : null;
+}
+
+export function asStringArray(value: unknown): string[] {
+  return Array.isArray(value) && value.every((item) => typeof item === 'string') ? value : [];
+}
+
+export function isRecord(value: unknown): value is Record<string, unknown> {
+  return typeof value === 'object' && value !== null;
+}
+
+/** The single point of truth for what counts as a valid conversation ID
+ * anywhere a scoped server event may adopt one into state — a non-empty
+ * string, nothing else. Every site that establishes or compares
+ * `state.conversationId` against a raw socket payload must route through
+ * this guard so a malformed first frame (null/object/number/empty string)
+ * can never be adopted verbatim. */
+export function asConversationId(value: unknown): string | null {
+  return typeof value === 'string' && value.length > 0 ? value : null;
+}

apps/web/src/spa/chat/session-panel.tsx

@@ -0,0 +1,68 @@
+import type { ReactElement } from 'react';
+import type { SessionInfoPayload } from '@/lib/chat-contract';
+import { MAX_MANIFEST_ITEMS } from './limits';
+import { asString, asStringArray } from './runtime-guards';
+
+interface SessionPanelProps {
+  sessionInfo: SessionInfoPayload | null;
+  onSetThinking: (level: string) => void;
+}
+
+const THINKING_LEVEL_UNAVAILABLE = '';
+
+export function SessionPanel({
+  sessionInfo,
+  onSetThinking,
+}: SessionPanelProps): ReactElement | null {
+  if (!sessionInfo) return null;
+
+  // The reducer already caps this before storing it, but the render site
+  // defends independently — a hostile payload must never be able to force
+  // this <select> to lay out an unbounded number of options.
+  const availableThinkingLevels = asStringArray(sessionInfo.availableThinkingLevels).slice(
+    0,
+    MAX_MANIFEST_ITEMS,
+  );
+  const hasThinkingLevels = availableThinkingLevels.length > 0;
+
+  return (
+    <section
+      aria-label="Session info"
+      className="flex flex-wrap items-center gap-3 border-b px-4 py-2 text-xs"
+    >
+      <span>{asString(sessionInfo.provider, 'unknown')}</span>
+      <span>{asString(sessionInfo.modelId, 'unknown')}</span>
+      <label className="flex items-center gap-2">
+        <span>Thinking level</span>
+        <select
+          aria-label="Thinking level"
+          value={
+            hasThinkingLevels ? asString(sessionInfo.thinkingLevel) : THINKING_LEVEL_UNAVAILABLE
+          }
+          onChange={(event) => {
+            // The placeholder option is not a real, settable level — a
+            // malformed availableThinkingLevels list must never let the
+            // client emit set:thinking for it.
+            if (!hasThinkingLevels) return;
+            onSetThinking(event.target.value);
+          }}
+        >
+          {hasThinkingLevels ? (
+            availableThinkingLevels.map((level) => (
+              <option key={level} value={level}>
+                {level}
+              </option>
+            ))
+          ) : (
+            <option value={THINKING_LEVEL_UNAVAILABLE}>Thinking level unavailable</option>
+          )}
+        </select>
+      </label>
+      {sessionInfo.routingDecision ? (
+        <span title={asString(sessionInfo.routingDecision.ruleName)}>
+          {asString(sessionInfo.routingDecision.reason)}
+        </span>
+      ) : null}
+    </section>
+  );
+}

apps/web/src/spa/chat/test-support/fake-chat-socket.ts

@@ -0,0 +1,125 @@
+import { vi } from 'vitest';
+import type { ClientToServerEvents, ServerToClientEvents } from '@/lib/chat-contract';
+
+type ServerEvent = keyof ServerToClientEvents;
+type ClientEvent = keyof ClientToServerEvents;
+type ServerHandler<K extends ServerEvent> = ServerToClientEvents[K];
+type ClientPayload<K extends ClientEvent> = Parameters<ClientToServerEvents[K]>[0];
+
+export interface EmittedEvent<K extends ClientEvent = ClientEvent> {
+  event: K;
+  payload: ClientPayload<K>;
+}
+
+/** The subset of a Socket.IO `ChatSocket` that `useChatConnection` drives. */
+export interface FakeChatSocket {
+  connected: boolean;
+  connect(): FakeChatSocket;
+  on<K extends ServerEvent>(event: K, handler: ServerHandler<K>): FakeChatSocket;
+  off<K extends ServerEvent>(event: K, handler: ServerHandler<K>): FakeChatSocket;
+  emit<K extends ClientEvent>(event: K, payload: ClientPayload<K>): FakeChatSocket;
+}
+
+/**
+ * A typed in-memory stand-in for `getSocket()`. Unlike a bare
+ * `(event: string, payload: unknown) => void` mock, every public method here is
+ * checked against the real `/chat` contract — a typo'd event name or a payload
+ * missing a required field fails to compile instead of silently no-op'ing at
+ * runtime.
+ */
+/** Socket.IO's built-in connection-state events. Not part of the app-level
+ * ServerToClientEvents contract, but real sockets always support them and
+ * `useChatConnection` registers a `disconnect` handler on the real socket. */
+type LifecycleEvent = 'connect' | 'disconnect';
+
+export function createFakeChatSocket(): {
+  socket: FakeChatSocket;
+  listeners: Map<ServerEvent, Set<(payload: never) => void>>;
+  emitted: EmittedEvent[];
+  serverEmit<K extends ServerEvent>(
+    event: K,
+    payload: Parameters<ServerToClientEvents[K]>[0],
+  ): void;
+  /** Escape hatch for malformed-payload tests: bypasses the compile-time
+   * payload contract to simulate a genuinely untrusted runtime value from the
+   * server, e.g. a `session:info` with a non-array `availableThinkingLevels`. */
+  serverEmitRaw(event: ServerEvent, payload: unknown): void;
+  /** Simulates a transient Socket.IO `disconnect` — fires any handler(s)
+   * registered via `socket.on('disconnect', ...)` without clearing any
+   * listeners, mirroring how a real reconnecting socket behaves. */
+  simulateDisconnect(): void;
+  /** Simulates socket.io-client's automatic reconnect of the *same*
+   * instance after a transient disconnect: marks the socket connected again
+   * and fires any handler(s) registered via `socket.on('connect', ...)`,
+   * without clearing or replacing any listeners. */
+  simulateReconnect(): void;
+} {
+  const listeners = new Map<ServerEvent, Set<(payload: never) => void>>();
+  const emitted: EmittedEvent[] = [];
+
+  // Internal storage is intentionally keyed loosely (the per-event handler shape
+  // varies by K, which a single Map can't express); the generic signatures on the
+  // exported `socket`/`serverEmit` above and below are what keep test call sites
+  // type-checked against ServerToClientEvents/ClientToServerEvents.
+  const socket = {
+    connected: false,
+    connect: vi.fn(function connect(this: void) {
+      socket.connected = true;
+      return socket;
+    }),
+    on: vi.fn(function on(this: void, event: ServerEvent, handler: (payload: never) => void) {
+      if (!listeners.has(event)) listeners.set(event, new Set());
+      listeners.get(event)?.add(handler);
+      return socket;
+    }),
+    off: vi.fn(function off(this: void, event: ServerEvent, handler: (payload: never) => void) {
+      listeners.get(event)?.delete(handler);
+      return socket;
+    }),
+    emit: vi.fn(function emit(this: void, event: ClientEvent, payload: unknown) {
+      emitted.push({ event, payload } as EmittedEvent);
+      return socket;
+    }),
+  } as unknown as FakeChatSocket;
+
+  function serverEmit<K extends ServerEvent>(
+    event: K,
+    payload: Parameters<ServerToClientEvents[K]>[0],
+  ): void {
+    for (const handler of listeners.get(event) ?? []) {
+      (handler as (payload: Parameters<ServerToClientEvents[K]>[0]) => void)(payload);
+    }
+  }
+
+  function serverEmitRaw(event: ServerEvent, payload: unknown): void {
+    for (const handler of listeners.get(event) ?? []) {
+      (handler as (payload: unknown) => void)(payload);
+    }
+  }
+
+  function simulateDisconnect(): void {
+    socket.connected = false;
+    const lifecycleKey = 'disconnect' satisfies LifecycleEvent as unknown as ServerEvent;
+    for (const handler of listeners.get(lifecycleKey) ?? []) {
+      (handler as () => void)();
+    }
+  }
+
+  function simulateReconnect(): void {
+    socket.connected = true;
+    const lifecycleKey = 'connect' satisfies LifecycleEvent as unknown as ServerEvent;
+    for (const handler of listeners.get(lifecycleKey) ?? []) {
+      (handler as () => void)();
+    }
+  }
+
+  return {
+    socket,
+    listeners,
+    emitted,
+    serverEmit,
+    serverEmitRaw,
+    simulateDisconnect,
+    simulateReconnect,
+  };
+}

apps/web/src/spa/chat/tool-call-list.spec.tsx

@@ -0,0 +1,63 @@
+import { act } from 'react';
+import { createRoot, type Root } from 'react-dom/client';
+import { afterAll, afterEach, beforeAll, describe, expect, it, vi } from 'vitest';
+import { ToolCallList } from './tool-call-list';
+
+beforeAll(() => {
+  Object.defineProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT', {
+    configurable: true,
+    value: true,
+  });
+});
+
+afterAll(() => {
+  Reflect.deleteProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT');
+});
+
+let root: Root | null;
+let container: HTMLElement | null;
+
+async function render(node: Parameters<Root['render']>[0]): Promise<void> {
+  container = document.createElement('div');
+  document.body.append(container);
+  root = createRoot(container);
+  await act(async () => {
+    root?.render(node);
+  });
+}
+
+afterEach(async () => {
+  await act(async () => {
+    root?.unmount();
+  });
+  document.body.replaceChildren();
+  root = null;
+  container = null;
+});
+
+describe('ToolCallList', () => {
+  it('renders two entries independently, without a duplicate-key warning, when a valid toolCallId is shared', async () => {
+    const consoleError = vi.spyOn(console, 'error').mockImplementation(() => {});
+
+    await render(
+      <ToolCallList
+        tools={[
+          { toolCallId: 'dup', toolName: 'search', status: 'success' },
+          { toolCallId: 'dup', toolName: 'search', status: 'running' },
+        ]}
+      />,
+    );
+
+    const items = [...(container?.querySelectorAll('li') ?? [])];
+    expect(items).toHaveLength(2);
+    expect(items[0]?.textContent).toContain('success');
+    expect(items[1]?.textContent).toContain('running');
+
+    const duplicateKeyWarning = consoleError.mock.calls.some((args) =>
+      args.some((arg) => typeof arg === 'string' && arg.includes('same key')),
+    );
+    expect(duplicateKeyWarning).toBe(false);
+
+    consoleError.mockRestore();
+  });
+});

apps/web/src/spa/chat/tool-call-list.tsx

@@ -0,0 +1,24 @@
+import type { ReactElement } from 'react';
+import type { ToolCallState } from './use-chat-connection';
+
+export function ToolCallList({ tools }: { tools: ToolCallState[] }): ReactElement | null {
+  if (tools.length === 0) return null;
+
+  return (
+    <ul aria-label="Tool calls" className="flex flex-col gap-1 px-4 pb-2 text-xs">
+      {tools.map((tool, index) => (
+        <li
+          // A valid server-controlled toolCallId can legitimately repeat
+          // (e.g. two tool:start events sharing one id) — keying on it alone
+          // would give React two identical keys. Pairing it with its
+          // (stable, append-only) render index keeps every key unique.
+          key={`${tool.toolCallId}-${index}`}
+          role={tool.status === 'error' || tool.status === 'anomaly' ? 'alert' : 'status'}
+        >
+          {tool.toolName} —{' '}
+          {tool.status === 'anomaly' ? 'unexpected end (unknown tool call)' : tool.status}
+        </li>
+      ))}
+    </ul>
+  );
+}

apps/web/src/spa/guards.spec.tsx

@@ -0,0 +1,135 @@
+import { act } from 'react';
+import { createRoot, type Root } from 'react-dom/client';
+import { createMemoryRouter, RouterProvider, type RouteObject } from 'react-router-dom';
+import { afterAll, afterEach, beforeAll, describe, expect, it, vi } from 'vitest';
+
+const { useSessionMock } = vi.hoisted(() => ({
+  useSessionMock: vi.fn(),
+}));
+
+vi.mock('@/lib/auth-client', () => ({
+  useSession: useSessionMock,
+}));
+
+import { AuthGuard, GuestGuard } from './guards';
+
+interface RenderedRouter {
+  container: HTMLDivElement;
+  router: ReturnType<typeof createMemoryRouter>;
+}
+
+const mountedRoots: Root[] = [];
+
+beforeAll(() => {
+  Object.defineProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT', {
+    configurable: true,
+    value: true,
+  });
+});
+
+afterAll(() => {
+  Reflect.deleteProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT');
+});
+
+async function renderRouter(
+  routeObjects: RouteObject[],
+  initialEntry: string,
+): Promise<RenderedRouter> {
+  const container = document.createElement('div');
+  document.body.append(container);
+  const router = createMemoryRouter(routeObjects, { initialEntries: [initialEntry] });
+  const root = createRoot(container);
+  mountedRoots.push(root);
+
+  await act(async () => {
+    root.render(<RouterProvider router={router} />);
+  });
+
+  return { container, router };
+}
+
+afterEach(async () => {
+  for (const root of mountedRoots.splice(0)) {
+    await act(async () => {
+      root.unmount();
+    });
+  }
+  document.body.replaceChildren();
+  useSessionMock.mockReset();
+});
+
+const guestRoutes: RouteObject[] = [
+  {
+    path: '/login',
+    element: <GuestGuard />,
+    children: [{ index: true, element: <p>Guest page</p> }],
+  },
+  { path: '/chat', element: <p>Chat page</p> },
+];
+
+const authenticatedRoutes: RouteObject[] = [
+  {
+    path: '/chat',
+    element: <AuthGuard />,
+    children: [{ index: true, element: <p>Private page</p> }],
+  },
+  { path: '/login', element: <p>Login page</p> },
+];
+
+describe('GuestGuard', () => {
+  it('renders the guest outlet while session lookup is pending', async () => {
+    useSessionMock.mockReturnValue({ data: null, isPending: true });
+
+    const view = await renderRouter(guestRoutes, '/login');
+
+    expect(view.container.textContent).toContain('Guest page');
+    expect(view.router.state.location.pathname).toBe('/login');
+  });
+
+  it('renders the guest outlet when no session exists', async () => {
+    useSessionMock.mockReturnValue({ data: null, isPending: false });
+
+    const view = await renderRouter(guestRoutes, '/login');
+
+    expect(view.container.textContent).toContain('Guest page');
+    expect(view.router.state.location.pathname).toBe('/login');
+  });
+
+  it('redirects an authenticated session to chat', async () => {
+    useSessionMock.mockReturnValue({ data: { user: { id: 'user-1' } }, isPending: false });
+
+    const view = await renderRouter(guestRoutes, '/login');
+
+    expect(view.container.textContent).toContain('Chat page');
+    expect(view.router.state.location.pathname).toBe('/chat');
+  });
+});
+
+describe('AuthGuard', () => {
+  it('renders the existing loading treatment while session lookup is pending', async () => {
+    useSessionMock.mockReturnValue({ data: null, isPending: true });
+
+    const view = await renderRouter(authenticatedRoutes, '/chat');
+
+    expect(view.container.textContent).toContain('Loading...');
+    expect(view.router.state.location.pathname).toBe('/chat');
+  });
+
+  it('redirects an unauthenticated visitor to login', async () => {
+    useSessionMock.mockReturnValue({ data: null, isPending: false });
+
+    const view = await renderRouter(authenticatedRoutes, '/chat');
+
+    expect(view.container.textContent).toContain('Login page');
+    expect(view.router.state.location.pathname).toBe('/login');
+  });
+
+  it('renders the authenticated outlet when a session exists', async () => {
+    useSessionMock.mockReturnValue({ data: { user: { id: 'user-1' } }, isPending: false });
+
+    const view = await renderRouter(authenticatedRoutes, '/chat');
+
+    expect(view.container.textContent).toContain('Private page');
+    expect(view.router.state.location.pathname).toBe('/chat');
+  });
+});

apps/web/src/spa/guards.tsx

@@ -0,0 +1,23 @@
+import type { ReactElement } from 'react';
+import { Navigate, Outlet } from 'react-router-dom';
+import { useSession } from '@/lib/auth-client';
+
+export function GuestGuard(): ReactElement {
+  const { data: session } = useSession();
+
+  return session ? <Navigate to="/chat" replace /> : <Outlet />;
+}
+
+export function AuthGuard(): ReactElement {
+  const { data: session, isPending } = useSession();
+
+  if (isPending) {
+    return (
+      <div className="flex min-h-screen items-center justify-center">
+        <div className="text-sm text-text-muted">Loading...</div>
+      </div>
+    );
+  }
+
+  return session ? <Outlet /> : <Navigate to="/login" replace />;
+}

apps/web/src/spa/pages/chat-error-boundary.spec.tsx

@@ -0,0 +1,87 @@
+import { act } from 'react';
+import { createRoot, type Root } from 'react-dom/client';
+import { createMemoryRouter, RouterProvider, type RouteObject } from 'react-router-dom';
+import { afterAll, afterEach, beforeAll, describe, expect, it, vi } from 'vitest';
+
+const { useSessionMock } = vi.hoisted(() => ({
+  useSessionMock: vi.fn(),
+}));
+
+vi.mock('@/lib/auth-client', () => ({
+  useSession: useSessionMock,
+}));
+
+import { routes } from '@/routes';
+
+beforeAll(() => {
+  Object.defineProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT', {
+    configurable: true,
+    value: true,
+  });
+});
+
+afterAll(() => {
+  Reflect.deleteProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT');
+});
+
+function Boom(): never {
+  throw new Error('render blew up');
+}
+
+/** Recursively clones the real exported route table, replacing only the
+ * `/chat` route's `element` with `<Boom />` — every other route (including
+ * the real `AuthGuard` nesting and the real `/chat` `errorElement`) is left
+ * exactly as exported. This is what makes the test fail if a future change
+ * removes the real route's `errorElement`, unlike a hand-built independent
+ * route tree that could drift from production undetected. */
+function replaceChatElementWithBoom(nodes: RouteObject[]): RouteObject[] {
+  return nodes.map((node) => {
+    const cloned: RouteObject = { ...node };
+    if (cloned.path === '/chat') {
+      cloned.element = <Boom />;
+    }
+    if (cloned.children) {
+      cloned.children = replaceChatElementWithBoom(cloned.children);
+    }
+    return cloned;
+  });
+}
+
+let root: Root | null;
+let container: HTMLElement;
+
+afterEach(async () => {
+  await act(async () => {
+    root?.unmount();
+  });
+  document.body.replaceChildren();
+  root = null;
+  useSessionMock.mockReset();
+});
+
+describe('ChatRouteErrorBoundary', () => {
+  it('renders a recoverable, non-blank fallback when the /chat route element throws during render', async () => {
+    useSessionMock.mockReturnValue({ data: { user: { id: 'user-1' } }, isPending: false });
+
+    const routeObjects = replaceChatElementWithBoom(routes);
+    const router = createMemoryRouter(routeObjects, { initialEntries: ['/chat'] });
+
+    container = document.createElement('div');
+    document.body.append(container);
+    root = createRoot(container);
+
+    const consoleErrorSpy = vi.spyOn(console, 'error').mockImplementation(() => {});
+    try {
+      await act(async () => {
+        root?.render(<RouterProvider router={router} />);
+      });
+
+      expect(consoleErrorSpy).toHaveBeenCalled();
+    } finally {
+      consoleErrorSpy.mockRestore();
+    }
+
+    expect(container.textContent).not.toBe('');
+    expect(container.querySelector('[role="alert"]')).toBeTruthy();
+  });
+});

apps/web/src/spa/pages/chat-error-boundary.tsx

@@ -0,0 +1,22 @@
+import type { ReactElement } from 'react';
+import { useRouteError } from 'react-router-dom';
+
+/**
+ * `/chat` renders live, server-driven state (streamed text, tool calls,
+ * manifests) that can carry malformed payloads no compile-time contract can
+ * fully rule out at every dereference site. This is the last line of
+ * defense: if something still throws during render, show a recoverable
+ * alert instead of leaving the user on a blank/white screen.
+ */
+export function ChatRouteErrorBoundary(): ReactElement {
+  useRouteError();
+
+  return (
+    <div role="alert" className="flex min-h-screen flex-col items-center justify-center gap-3 p-8">
+      <p className="text-sm font-medium">Something went wrong loading chat.</p>
+      <a href="/chat" className="text-sm underline">
+        Reload chat
+      </a>
+    </div>
+  );
+}

apps/web/src/spa/pages/chat.spec.tsx

@@ -0,0 +1,636 @@
+import { act } from 'react';
+import { createRoot, type Root } from 'react-dom/client';
+import { afterAll, afterEach, beforeAll, beforeEach, describe, expect, it, vi } from 'vitest';
+import { createFakeChatSocket } from '@/spa/chat/test-support/fake-chat-socket';
+import { MAX_MANIFEST_ITEMS } from '@/spa/chat/limits';
+
+const { getSocketMock, destroySocketMock } = vi.hoisted(() => ({
+  getSocketMock: vi.fn(),
+  destroySocketMock: vi.fn(),
+}));
+
+vi.mock('@/lib/socket', () => ({
+  getSocket: getSocketMock,
+  destroySocket: destroySocketMock,
+}));
+
+import { ChatPage } from './chat';
+
+function setValue(el: HTMLInputElement | HTMLTextAreaElement, value: string): void {
+  const proto =
+    el instanceof HTMLTextAreaElement ? HTMLTextAreaElement.prototype : HTMLInputElement.prototype;
+  const setter = Object.getOwnPropertyDescriptor(proto, 'value')?.set;
+  setter?.call(el, value);
+  el.dispatchEvent(new Event('input', { bubbles: true }));
+}
+
+function selectValue(el: HTMLSelectElement, value: string): void {
+  const setter = Object.getOwnPropertyDescriptor(HTMLSelectElement.prototype, 'value')?.set;
+  setter?.call(el, value);
+  el.dispatchEvent(new Event('change', { bubbles: true }));
+}
+
+function findButton(container: HTMLElement, text: string): HTMLButtonElement {
+  const button = [...container.querySelectorAll('button')].find((candidate) =>
+    candidate.textContent?.includes(text),
+  );
+  if (!button) throw new Error(`Button with text "${text}" not found`);
+  return button;
+}
+
+let fake: ReturnType<typeof createFakeChatSocket>;
+let root: Root | null;
+let container: HTMLElement;
+
+beforeAll(() => {
+  Object.defineProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT', {
+    configurable: true,
+    value: true,
+  });
+});
+
+afterAll(() => {
+  Reflect.deleteProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT');
+});
+
+beforeEach(async () => {
+  fake = createFakeChatSocket();
+  getSocketMock.mockReset().mockReturnValue(fake.socket);
+  destroySocketMock.mockReset();
+  container = document.createElement('div');
+  document.body.append(container);
+  root = createRoot(container);
+  await act(async () => {
+    root?.render(<ChatPage />);
+  });
+});
+
+afterEach(async () => {
+  await act(async () => {
+    root?.unmount();
+  });
+  document.body.replaceChildren();
+});
+
+describe('ChatPage', () => {
+  it('streams agent:text and agent:thinking, shows tool status, and finalizes on agent:end with usage', async () => {
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+      fake.serverEmit('agent:start', { conversationId: 'c1' });
+    });
+    await act(async () => {
+      fake.serverEmit('agent:thinking', { conversationId: 'c1', text: 'pondering…' });
+      fake.serverEmit('agent:text', { conversationId: 'c1', text: 'Hel' });
+      fake.serverEmit('agent:text', { conversationId: 'c1', text: 'lo!' });
+      fake.serverEmit('agent:tool:start', {
+        conversationId: 'c1',
+        toolCallId: 't1',
+        toolName: 'web_search',
+      });
+    });
+
+    expect(container.textContent).toContain('pondering…');
+    expect(container.textContent).toContain('Hello!');
+    expect(container.textContent).toContain('web_search');
+    expect(container.textContent).toMatch(/running/i);
+
+    await act(async () => {
+      fake.serverEmit('agent:tool:end', {
+        conversationId: 'c1',
+        toolCallId: 't1',
+        toolName: 'web_search',
+        isError: false,
+      });
+      fake.serverEmit('agent:end', {
+        conversationId: 'c1',
+        usage: {
+          provider: 'anthropic',
+          modelId: 'claude',
+          thinkingLevel: 'medium',
+          tokens: { input: 12, output: 34, cacheRead: 0, cacheWrite: 0, total: 46 },
+          cost: 0.02,
+          context: { percent: 3, window: 200000 },
+        },
+      });
+    });
+
+    expect(container.textContent).toMatch(/success/i);
+    expect(container.textContent).toContain('Hello!');
+    expect(container.textContent).toMatch(/46/);
+  });
+
+  it('renders the commands manifest and session info, and lets the user pick a thinking level', async () => {
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+      fake.serverEmit('commands:manifest', {
+        manifest: {
+          commands: [
+            {
+              name: 'model',
+              aliases: ['m'],
+              description: 'Change the active model',
+              scope: 'core',
+              execution: 'socket',
+              available: true,
+            },
+          ],
+          skills: [],
+          version: 1,
+        },
+      });
+      fake.serverEmit('session:info', {
+        conversationId: 'c1',
+        provider: 'anthropic',
+        modelId: 'claude',
+        thinkingLevel: 'medium',
+        availableThinkingLevels: ['low', 'medium', 'high'],
+        routingDecision: {
+          model: 'claude',
+          provider: 'anthropic',
+          ruleName: 'default',
+          reason: 'default routing',
+        },
+      });
+    });
+
+    expect(container.textContent).toContain('model');
+    expect(container.textContent).toContain('Change the active model');
+    expect(container.textContent).toContain('anthropic');
+    expect(container.textContent).toContain('default routing');
+
+    const select = container.querySelector(
+      'select[aria-label="Thinking level"]',
+    ) as HTMLSelectElement;
+    expect(select).toBeTruthy();
+    expect([...select.options].map((o) => o.value)).toEqual(['low', 'medium', 'high']);
+
+    await act(async () => {
+      selectValue(select, 'high');
+    });
+
+    expect(fake.emitted).toContainEqual({
+      event: 'set:thinking',
+      payload: { conversationId: 'c1', level: 'high' },
+    });
+  });
+
+  it('executes and approves commands with exact payloads and surfaces the approval affordance', async () => {
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+    });
+
+    const commandInput = container.querySelector(
+      'input[aria-label="Command name"]',
+    ) as HTMLInputElement;
+    const argsInput = container.querySelector(
+      'input[aria-label="Command arguments"]',
+    ) as HTMLInputElement;
+
+    await act(async () => {
+      setValue(commandInput, 'model');
+      setValue(argsInput, 'gpt-5');
+    });
+    await act(async () => {
+      findButton(container, 'Run command').click();
+    });
+
+    expect(fake.emitted).toContainEqual({
+      event: 'command:execute',
+      payload: { conversationId: 'c1', command: 'model', args: 'gpt-5' },
+    });
+
+    await act(async () => {
+      setValue(commandInput, 'deploy');
+      setValue(argsInput, 'prod');
+    });
+    await act(async () => {
+      findButton(container, 'Request approval').click();
+    });
+
+    expect(fake.emitted).toContainEqual({
+      event: 'command:approve',
+      payload: { conversationId: 'c1', command: 'deploy', args: 'prod' },
+    });
+
+    await act(async () => {
+      fake.serverEmit('command:approval', {
+        conversationId: 'c1',
+        command: 'deploy',
+        success: true,
+        approvalId: 'ap1',
+        expiresAt: '2026-01-01T00:00:00.000Z',
+      });
+    });
+
+    expect(container.textContent).toMatch(/approved/i);
+
+    await act(async () => {
+      findButton(container, 'Run approved command').click();
+    });
+
+    expect(fake.emitted).toContainEqual({
+      event: 'command:execute',
+      payload: { conversationId: 'c1', command: 'deploy', args: 'prod', approvalId: 'ap1' },
+    });
+  });
+
+  it('shows visible alert surfaces for a server error and the structured contract reason for a failed command result', async () => {
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+      fake.serverEmit('error', { conversationId: 'c1', error: 'The model is unavailable' });
+      fake.serverEmit('command:result', {
+        conversationId: 'c1',
+        command: 'model',
+        success: false,
+        message: 'Unknown model',
+      });
+    });
+
+    const alerts = [...container.querySelectorAll('[role="alert"]')];
+    const alertText = alerts.map((node) => node.textContent).join(' ');
+    expect(alertText).toContain('The model is unavailable');
+    // The structured, contract-provided denial reason is visibly rendered.
+    expect(alertText).toContain('Unknown model');
+  });
+
+  it('falls back to a stable "Command failed." copy when a failed command result has no usable message', async () => {
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+      fake.serverEmitRaw('command:result', {
+        conversationId: 'c1',
+        command: 'model',
+        success: false,
+        message: { bad: 'object' },
+      });
+    });
+
+    const alerts = [...container.querySelectorAll('[role="alert"]')];
+    const alertText = alerts.map((node) => node.textContent).join(' ');
+    expect(alertText).toContain('Command failed.');
+  });
+
+  it('caps availableThinkingLevels before storing and rendering a hostile session payload', async () => {
+    const hostileLevels = Array.from({ length: MAX_MANIFEST_ITEMS + 50 }, (_, i) => `level-${i}`);
+
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+      fake.serverEmit('session:info', {
+        conversationId: 'c1',
+        provider: 'anthropic',
+        modelId: 'claude',
+        thinkingLevel: 'level-0',
+        availableThinkingLevels: hostileLevels,
+      });
+    });
+
+    const select = container.querySelector(
+      'select[aria-label="Thinking level"]',
+    ) as HTMLSelectElement;
+    expect(select).toBeTruthy();
+    expect(select.options.length).toBeLessThanOrEqual(MAX_MANIFEST_ITEMS);
+  });
+
+  it('renders a safe fallback when session:info arrives with a malformed (non-array) availableThinkingLevels, without throwing', async () => {
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+      fake.serverEmitRaw('session:info', {
+        conversationId: 'c1',
+        provider: 'anthropic',
+        modelId: 'claude',
+        thinkingLevel: 'medium',
+        availableThinkingLevels: null,
+      });
+    });
+
+    expect(container.querySelector('section[aria-label="Session info"]')).toBeTruthy();
+    const select = container.querySelector(
+      'select[aria-label="Thinking level"]',
+    ) as HTMLSelectElement;
+    expect(select).toBeTruthy();
+    // A malformed level list still shows a visible, safe placeholder option
+    // rather than a silently empty select.
+    expect([...select.options]).toHaveLength(1);
+    expect(select.options[0]?.textContent).toMatch(/unavailable/i);
+
+    await act(async () => {
+      selectValue(select, '');
+    });
+    expect(fake.emitted.filter((e) => e.event === 'set:thinking')).toHaveLength(0);
+  });
+
+  it('renders honest unavailable labels — not fabricated zeros — when agent:end usage has malformed/missing numeric fields', async () => {
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+      fake.serverEmit('agent:start', { conversationId: 'c1' });
+      fake.serverEmitRaw('agent:end', {
+        conversationId: 'c1',
+        usage: {
+          provider: { nested: 'object' },
+          modelId: undefined,
+          thinkingLevel: 'medium',
+          tokens: { total: 'not-a-number' },
+          cost: undefined,
+          context: { percent: null, window: 200000 },
+        },
+      });
+    });
+
+    const usage = container.querySelector('[aria-label="Usage"]');
+    expect(usage).toBeTruthy();
+    expect(usage?.textContent).toContain('tokens unavailable');
+    expect(usage?.textContent).toContain('cost unavailable');
+    expect(usage?.textContent).not.toContain('0 tokens');
+    expect(usage?.textContent).not.toContain('$0.0000');
+    expect(usage?.textContent).toContain('unknown/unknown');
+  });
+
+  it('renders a safe fallback for message:ack when messageId is a malformed non-string value, without throwing', async () => {
+    await expect(
+      act(async () => {
+        fake.serverEmitRaw('message:ack', { conversationId: 'c1', messageId: { bad: 'object' } });
+      }),
+    ).resolves.not.toThrow();
+
+    const status = [...container.querySelectorAll('[role="status"]')].find((node) =>
+      node.textContent?.includes('Message accepted'),
+    );
+    expect(status).toBeTruthy();
+    // A malformed messageId gets a stable, visible fallback — never blank,
+    // never the raw object.
+    expect(status?.textContent).toContain('unknown');
+  });
+
+  it('renders safely and does not throw when system:reload.message is a malformed non-string value', async () => {
+    await expect(
+      act(async () => {
+        fake.serverEmitRaw('system:reload', {
+          commands: [],
+          skills: [],
+          providers: [],
+          message: { bad: 'object' },
+        });
+      }),
+    ).resolves.not.toThrow();
+
+    const status = container.querySelector('[role="status"]');
+    expect(status).toBeTruthy();
+    // A malformed reload message renders a stable, visible fallback rather
+    // than a silently empty status line.
+    expect(status?.textContent).toContain('Commands reloaded.');
+  });
+
+  it('renders safely and does not throw when a scoped error carries a malformed non-string error value', async () => {
+    await expect(
+      act(async () => {
+        fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+        fake.serverEmitRaw('error', { conversationId: 'c1', error: ['not', 'a', 'string'] });
+      }),
+    ).resolves.not.toThrow();
+
+    expect(container.querySelector('[role="alert"]')).toBeTruthy();
+  });
+
+  it('sends a message with optional provider/model fields and emits abort from the Stop control', async () => {
+    const textarea = container.querySelector(
+      'textarea[aria-label="Message"]',
+    ) as HTMLTextAreaElement;
+    const providerInput = container.querySelector(
+      'input[aria-label="Provider"]',
+    ) as HTMLInputElement;
+    const modelInput = container.querySelector('input[aria-label="Model"]') as HTMLInputElement;
+
+    const stopButtonBefore = container.querySelector(
+      'button[aria-label="Stop"]',
+    ) as HTMLButtonElement;
+    expect(stopButtonBefore.disabled).toBe(true);
+
+    await act(async () => {
+      setValue(textarea, 'hello there');
+      setValue(providerInput, 'anthropic');
+      setValue(modelInput, 'claude');
+    });
+    await act(async () => {
+      textarea.dispatchEvent(
+        new KeyboardEvent('keydown', { key: 'Enter', bubbles: true, cancelable: true }),
+      );
+    });
+
+    expect(fake.emitted).toContainEqual({
+      event: 'message',
+      payload: {
+        conversationId: undefined,
+        content: 'hello there',
+        provider: 'anthropic',
+        modelId: 'claude',
+      },
+    });
+    expect(container.textContent).toContain('hello there');
+
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+      fake.serverEmit('agent:start', { conversationId: 'c1' });
+    });
+
+    const stopButtonDuring = container.querySelector(
+      'button[aria-label="Stop"]',
+    ) as HTMLButtonElement;
+    expect(stopButtonDuring.disabled).toBe(false);
+
+    await act(async () => {
+      stopButtonDuring.click();
+    });
+
+    expect(fake.emitted).toContainEqual({ event: 'abort', payload: { conversationId: 'c1' } });
+  });
+
+  it('renders the session panel from a pre-ack session:info and keeps it visible after the later ack', async () => {
+    const textarea = container.querySelector(
+      'textarea[aria-label="Message"]',
+    ) as HTMLTextAreaElement;
+
+    await act(async () => {
+      setValue(textarea, 'hello');
+    });
+    await act(async () => {
+      textarea.dispatchEvent(
+        new KeyboardEvent('keydown', { key: 'Enter', bubbles: true, cancelable: true }),
+      );
+    });
+    await act(async () => {
+      fake.serverEmit('session:info', {
+        conversationId: 'c1',
+        provider: 'anthropic',
+        modelId: 'claude',
+        thinkingLevel: 'medium',
+        availableThinkingLevels: ['low', 'medium', 'high'],
+      });
+    });
+
+    expect(container.querySelector('section[aria-label="Session info"]')).toBeTruthy();
+    expect(container.textContent).toContain('anthropic');
+
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+    });
+
+    expect(container.querySelector('section[aria-label="Session info"]')).toBeTruthy();
+    expect(container.textContent).toContain('anthropic');
+  });
+
+  it('surfaces a pre-ack error as an alert without leaving the Stop control stuck active', async () => {
+    const textarea = container.querySelector(
+      'textarea[aria-label="Message"]',
+    ) as HTMLTextAreaElement;
+
+    await act(async () => {
+      setValue(textarea, 'hello');
+    });
+    await act(async () => {
+      textarea.dispatchEvent(
+        new KeyboardEvent('keydown', { key: 'Enter', bubbles: true, cancelable: true }),
+      );
+    });
+    await act(async () => {
+      fake.serverEmit('error', {
+        conversationId: 'c1',
+        error: 'Failed to start agent session. Please try again.',
+      });
+    });
+
+    const alerts = [...container.querySelectorAll('[role="alert"]')];
+    expect(alerts.some((node) => node.textContent?.includes('Failed to start agent session'))).toBe(
+      true,
+    );
+
+    const stopButton = container.querySelector('button[aria-label="Stop"]') as HTMLButtonElement;
+    expect(stopButton.disabled).toBe(true);
+  });
+
+  it('shows an accessible status once the message is acknowledged', async () => {
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+    });
+
+    const statuses = [...container.querySelectorAll('[role="status"]')];
+    expect(statuses.some((node) => node.textContent?.includes('m1'))).toBe(true);
+  });
+
+  it('renders finalized thinking text in the transcript after agent:end, not only while streaming', async () => {
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+      fake.serverEmit('agent:start', { conversationId: 'c1' });
+      fake.serverEmit('agent:thinking', { conversationId: 'c1', text: 'reasoning about it' });
+      fake.serverEmit('agent:text', { conversationId: 'c1', text: 'Done.' });
+    });
+
+    expect(container.textContent).toContain('reasoning about it');
+
+    await act(async () => {
+      fake.serverEmit('agent:end', { conversationId: 'c1' });
+    });
+
+    expect(container.textContent).toContain('reasoning about it');
+    expect(container.textContent).toContain('Done.');
+  });
+
+  it('ignores a concurrent approval request and only executes the approved command once', async () => {
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+    });
+
+    const commandInput = container.querySelector(
+      'input[aria-label="Command name"]',
+    ) as HTMLInputElement;
+    const argsInput = container.querySelector(
+      'input[aria-label="Command arguments"]',
+    ) as HTMLInputElement;
+
+    await act(async () => {
+      setValue(commandInput, 'deploy');
+      setValue(argsInput, 'prod');
+    });
+    await act(async () => {
+      findButton(container, 'Request approval').click();
+    });
+    await act(async () => {
+      setValue(argsInput, 'staging');
+    });
+    await act(async () => {
+      findButton(container, 'Request approval').click();
+    });
+
+    expect(fake.emitted.filter((e) => e.event === 'command:approve')).toHaveLength(1);
+    expect(fake.emitted).toContainEqual({
+      event: 'command:approve',
+      payload: { conversationId: 'c1', command: 'deploy', args: 'prod' },
+    });
+
+    await act(async () => {
+      fake.serverEmit('command:approval', {
+        conversationId: 'c1',
+        command: 'deploy',
+        success: true,
+        approvalId: 'ap1',
+        expiresAt: '2026-01-01T00:00:00.000Z',
+      });
+    });
+
+    await act(async () => {
+      findButton(container, 'Run approved command').click();
+      findButton(container, 'Run approved command').click();
+    });
+
+    expect(fake.emitted.filter((e) => e.event === 'command:execute')).toHaveLength(1);
+    expect(fake.emitted).toContainEqual({
+      event: 'command:execute',
+      payload: { conversationId: 'c1', command: 'deploy', args: 'prod', approvalId: 'ap1' },
+    });
+  });
+
+  it('disables sending a second message while a turn is streaming', async () => {
+    const textarea = container.querySelector(
+      'textarea[aria-label="Message"]',
+    ) as HTMLTextAreaElement;
+
+    await act(async () => {
+      setValue(textarea, 'first');
+    });
+    await act(async () => {
+      textarea.dispatchEvent(
+        new KeyboardEvent('keydown', { key: 'Enter', bubbles: true, cancelable: true }),
+      );
+    });
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+      fake.serverEmit('agent:start', { conversationId: 'c1' });
+    });
+
+    const sendButton = findButton(container, 'Send');
+    expect(sendButton.disabled).toBe(true);
+
+    await act(async () => {
+      setValue(textarea, 'second');
+    });
+    await act(async () => {
+      textarea.dispatchEvent(
+        new KeyboardEvent('keydown', { key: 'Enter', bubbles: true, cancelable: true }),
+      );
+    });
+
+    expect(fake.emitted.filter((e) => e.event === 'message')).toHaveLength(1);
+  });
+
+  it('removes socket handlers and tears down the socket on unmount, with no network calls', async () => {
+    expect(fake.listeners.size).toBeGreaterThan(0);
+
+    await act(async () => {
+      root?.unmount();
+    });
+    root = null;
+
+    for (const [, handlers] of fake.listeners) {
+      expect(handlers.size).toBe(0);
+    }
+    expect(destroySocketMock).toHaveBeenCalledOnce();
+  });
+});

apps/web/src/spa/pages/chat.tsx

@@ -0,0 +1,92 @@
+import type { ReactElement } from 'react';
+import { CommandsPanel } from '@/spa/chat/commands-panel';
+import { Composer } from '@/spa/chat/composer';
+import { MessageTranscript } from '@/spa/chat/message-transcript';
+import { asFiniteNumberOrNull, asString } from '@/spa/chat/runtime-guards';
+import { SessionPanel } from '@/spa/chat/session-panel';
+import { ToolCallList } from '@/spa/chat/tool-call-list';
+import { useChatConnection } from '@/spa/chat/use-chat-connection';
+
+/** Renders a real value normally, but an honest "unavailable" label instead
+ * of a fabricated `0` for a missing/malformed count — a real `0 tokens` and
+ * an unknown token count must never look the same. */
+function formatTokens(value: unknown): string {
+  const tokens = asFiniteNumberOrNull(value);
+  return tokens === null ? 'tokens unavailable' : `${tokens} tokens`;
+}
+
+/** Same honesty guarantee as `formatTokens`, for cost. */
+function formatCost(value: unknown): string {
+  const cost = asFiniteNumberOrNull(value);
+  return cost === null ? 'cost unavailable' : `$${cost.toFixed(4)}`;
+}
+
+export function ChatPage(): ReactElement {
+  const { state, actions } = useChatConnection();
+  const hasConversation = state.conversationId !== null;
+
+  return (
+    <div className="flex h-[calc(100vh-3.5rem)] min-h-0 flex-col overflow-hidden md:h-screen">
+      <header className="border-b px-4 py-3">
+        <h1 className="text-lg font-semibold">Chat</h1>
+      </header>
+
+      {state.systemReload ? (
+        <div role="status" className="border-b px-4 py-2 text-sm">
+          {asString(state.systemReload.message)}
+        </div>
+      ) : null}
+
+      {state.error ? (
+        <div role="alert" className="border-b px-4 py-2 text-sm">
+          {asString(state.error)}
+        </div>
+      ) : null}
+
+      {state.ack ? (
+        <div role="status" className="border-b px-4 py-1 text-xs opacity-70">
+          Message accepted · conversation {asString(state.ack.conversationId, 'unknown')} · id{' '}
+          {asString(state.ack.messageId, 'unknown')}
+        </div>
+      ) : null}
+
+      <SessionPanel sessionInfo={state.sessionInfo} onSetThinking={actions.setThinking} />
+
+      <MessageTranscript messages={state.messages} streaming={state.streaming} text={state.text} />
+
+      {state.thinking ? (
+        <section aria-label="Thinking" className="px-4 pb-2 text-xs italic opacity-80">
+          {state.thinking}
+        </section>
+      ) : null}
+
+      <ToolCallList tools={state.tools} />
+
+      {state.usage ? (
+        <div aria-label="Usage" className="px-4 pb-2 text-xs opacity-80">
+          {formatTokens(state.usage.tokens?.total)} · {formatCost(state.usage.cost)} ·{' '}
+          {asString(state.usage.provider, 'unknown')}/{asString(state.usage.modelId, 'unknown')}
+        </div>
+      ) : null}
+
+      <CommandsPanel
+        manifest={state.manifest}
+        results={state.commandResults}
+        approval={state.approval}
+        pendingApproval={state.pendingApproval}
+        hasConversation={hasConversation}
+        onExecute={actions.executeCommand}
+        onApprove={actions.approveCommand}
+        onRunApproved={actions.runApprovedCommand}
+      />
+
+      <Composer
+        onSend={actions.sendMessage}
+        onStop={actions.abort}
+        streaming={state.streaming}
+        sending={state.sending}
+        hasConversation={hasConversation}
+      />
+    </div>
+  );
+}

apps/web/src/spa/pages/login.tsx

@@ -0,0 +1,152 @@
+import { useEffect, useState, type FormEvent, type ReactElement } from 'react';
+import { Link, useNavigate } from 'react-router-dom';
+import { SsoProviderButtons } from '@/components/auth/sso-provider-buttons';
+import { api } from '@/lib/api';
+import { authClient, signIn } from '@/lib/auth-client';
+import type { SsoProviderDiscovery } from '@/lib/sso';
+
+export function LoginPage(): ReactElement {
+  const navigate = useNavigate();
+  const [error, setError] = useState<string | null>(null);
+  const [loading, setLoading] = useState(false);
+  const [ssoProviders, setSsoProviders] = useState<SsoProviderDiscovery[]>([]);
+  const [ssoLoadingProviderId, setSsoLoadingProviderId] = useState<
+    SsoProviderDiscovery['id'] | null
+  >(null);
+
+  useEffect(() => {
+    let active = true;
+
+    void api<SsoProviderDiscovery[]>('/api/sso/providers').then(
+      (providers) => {
+        if (active) setSsoProviders(providers.filter((provider) => provider.configured));
+      },
+      () => {
+        if (active) setSsoProviders([]);
+      },
+    );
+
+    return () => {
+      active = false;
+    };
+  }, []);
+
+  async function handleSubmit(event: FormEvent<HTMLFormElement>): Promise<void> {
+    event.preventDefault();
+    setError(null);
+    setLoading(true);
+
+    const form = new FormData(event.currentTarget);
+    const email = String(form.get('email') ?? '');
+    const password = String(form.get('password') ?? '');
+
+    try {
+      const result = await signIn.email({ email, password });
+
+      if (result.error) {
+        setError(result.error.message ?? 'Sign in failed');
+        return;
+      }
+
+      navigate('/chat', { replace: true });
+    } catch (caught: unknown) {
+      setError(caught instanceof Error ? caught.message : 'Sign in failed');
+    } finally {
+      setLoading(false);
+    }
+  }
+
+  async function handleSsoSignIn(providerId: SsoProviderDiscovery['id']): Promise<void> {
+    setError(null);
+    setSsoLoadingProviderId(providerId);
+
+    try {
+      const result = await authClient.signIn.oauth2({
+        providerId,
+        callbackURL: '/chat',
+        newUserCallbackURL: '/chat',
+      });
+
+      if (result.error) {
+        setError(result.error.message ?? `Sign in with ${providerId} failed`);
+        setSsoLoadingProviderId(null);
+      }
+    } catch (caught: unknown) {
+      setError(caught instanceof Error ? caught.message : `Sign in with ${providerId} failed`);
+      setSsoLoadingProviderId(null);
+    }
+  }
+
+  return (
+    <div>
+      <h1 className="text-2xl font-semibold">Sign in</h1>
+      <p className="mt-1 text-sm text-text-secondary">Sign in to your Mosaic account</p>
+
+      {error ? (
+        <div
+          role="alert"
+          className="mt-4 rounded-lg border border-error/30 bg-error/10 px-4 py-3 text-sm text-error"
+        >
+          {error}
+        </div>
+      ) : null}
+
+      <form className="mt-6 space-y-4" onSubmit={handleSubmit}>
+        <div>
+          <label htmlFor="email" className="block text-sm font-medium text-text-secondary">
+            Email
+          </label>
+          <input
+            id="email"
+            name="email"
+            type="email"
+            autoComplete="email"
+            required
+            disabled={loading}
+            className="mt-1 block w-full rounded-lg border border-surface-border bg-surface-elevated px-3 py-2 text-sm text-text-primary placeholder:text-text-muted focus:border-blue-500 focus:outline-none focus:ring-1 focus:ring-blue-500 disabled:opacity-50"
+            placeholder="[email protected]"
+          />
+        </div>
+
+        <div>
+          <label htmlFor="password" className="block text-sm font-medium text-text-secondary">
+            Password
+          </label>
+          <input
+            id="password"
+            name="password"
+            type="password"
+            autoComplete="current-password"
+            required
+            disabled={loading}
+            className="mt-1 block w-full rounded-lg border border-surface-border bg-surface-elevated px-3 py-2 text-sm text-text-primary placeholder:text-text-muted focus:border-blue-500 focus:outline-none focus:ring-1 focus:ring-blue-500 disabled:opacity-50"
+            placeholder="••••••••"
+          />
+        </div>
+
+        <button
+          type="submit"
+          disabled={loading}
+          className="w-full rounded-lg bg-blue-600 px-4 py-2.5 text-sm font-medium text-white transition-colors hover:bg-blue-700 focus:outline-none focus:ring-2 focus:ring-blue-500 focus:ring-offset-2 focus:ring-offset-surface-card disabled:opacity-50"
+        >
+          {loading ? 'Signing in...' : 'Sign in'}
+        </button>
+      </form>
+
+      <SsoProviderButtons
+        providers={ssoProviders}
+        loadingProviderId={ssoLoadingProviderId}
+        onOidcSignIn={(providerId) => {
+          void handleSsoSignIn(providerId);
+        }}
+      />
+
+      <p className="mt-4 text-center text-sm text-text-muted">
+        Don&apos;t have an account?{' '}
+        <Link to="/register" className="text-blue-400 hover:text-blue-300">
+          Sign up
+        </Link>
+      </p>
+    </div>
+  );
+}

apps/web/src/spa/pages/register.tsx

@@ -0,0 +1,116 @@
+import { useState, type FormEvent, type ReactElement } from 'react';
+import { Link, useNavigate } from 'react-router-dom';
+import { signUp } from '@/lib/auth-client';
+
+export function RegisterPage(): ReactElement {
+  const navigate = useNavigate();
+  const [error, setError] = useState<string | null>(null);
+  const [loading, setLoading] = useState(false);
+
+  async function handleSubmit(event: FormEvent<HTMLFormElement>): Promise<void> {
+    event.preventDefault();
+    setError(null);
+    setLoading(true);
+
+    const form = new FormData(event.currentTarget);
+    const name = String(form.get('name') ?? '');
+    const email = String(form.get('email') ?? '');
+    const password = String(form.get('password') ?? '');
+
+    try {
+      const result = await signUp.email({ name, email, password });
+
+      if (result.error) {
+        setError(result.error.message ?? 'Registration failed');
+        return;
+      }
+
+      navigate('/chat', { replace: true });
+    } catch (caught: unknown) {
+      setError(caught instanceof Error ? caught.message : 'Registration failed');
+    } finally {
+      setLoading(false);
+    }
+  }
+
+  return (
+    <div>
+      <h1 className="text-2xl font-semibold">Create account</h1>
+      <p className="mt-1 text-sm text-text-secondary">Get started with Mosaic</p>
+
+      {error ? (
+        <div
+          role="alert"
+          className="mt-4 rounded-lg border border-error/30 bg-error/10 px-4 py-3 text-sm text-error"
+        >
+          {error}
+        </div>
+      ) : null}
+
+      <form className="mt-6 space-y-4" onSubmit={handleSubmit}>
+        <div>
+          <label htmlFor="name" className="block text-sm font-medium text-text-secondary">
+            Name
+          </label>
+          <input
+            id="name"
+            name="name"
+            type="text"
+            autoComplete="name"
+            required
+            disabled={loading}
+            className="mt-1 block w-full rounded-lg border border-surface-border bg-surface-elevated px-3 py-2 text-sm text-text-primary placeholder:text-text-muted focus:border-blue-500 focus:outline-none focus:ring-1 focus:ring-blue-500 disabled:opacity-50"
+            placeholder="Your name"
+          />
+        </div>
+
+        <div>
+          <label htmlFor="email" className="block text-sm font-medium text-text-secondary">
+            Email
+          </label>
+          <input
+            id="email"
+            name="email"
+            type="email"
+            autoComplete="email"
+            required
+            disabled={loading}
+            className="mt-1 block w-full rounded-lg border border-surface-border bg-surface-elevated px-3 py-2 text-sm text-text-primary placeholder:text-text-muted focus:border-blue-500 focus:outline-none focus:ring-1 focus:ring-blue-500 disabled:opacity-50"
+            placeholder="[email protected]"
+          />
+        </div>
+
+        <div>
+          <label htmlFor="password" className="block text-sm font-medium text-text-secondary">
+            Password
+          </label>
+          <input
+            id="password"
+            name="password"
+            type="password"
+            autoComplete="new-password"
+            required
+            disabled={loading}
+            className="mt-1 block w-full rounded-lg border border-surface-border bg-surface-elevated px-3 py-2 text-sm text-text-primary placeholder:text-text-muted focus:border-blue-500 focus:outline-none focus:ring-1 focus:ring-blue-500 disabled:opacity-50"
+            placeholder="••••••••"
+          />
+        </div>
+
+        <button
+          type="submit"
+          disabled={loading}
+          className="w-full rounded-lg bg-blue-600 px-4 py-2.5 text-sm font-medium text-white transition-colors hover:bg-blue-700 focus:outline-none focus:ring-2 focus:ring-blue-500 focus:ring-offset-2 focus:ring-offset-surface-card disabled:opacity-50"
+        >
+          {loading ? 'Creating account...' : 'Create account'}
+        </button>
+      </form>
+
+      <p className="mt-4 text-center text-sm text-text-muted">
+        Already have an account?{' '}
+        <Link to="/login" className="text-blue-400 hover:text-blue-300">
+          Sign in
+        </Link>
+      </p>
+    </div>
+  );
+}

apps/web/src/spa/pages/sso-callback.spec.tsx

@@ -0,0 +1,90 @@
+import { act } from 'react';
+import { createRoot, type Root } from 'react-dom/client';
+import { createMemoryRouter, RouterProvider } from 'react-router-dom';
+import { afterAll, afterEach, beforeAll, beforeEach, describe, expect, it, vi } from 'vitest';
+
+const { apiMock, oauth2Mock } = vi.hoisted(() => ({
+  apiMock: vi.fn(),
+  oauth2Mock: vi.fn(),
+}));
+
+vi.mock('@/lib/api', () => ({
+  api: apiMock,
+}));
+
+vi.mock('@/lib/auth-client', () => ({
+  signIn: { oauth2: oauth2Mock },
+}));
+
+import { SsoCallbackPage } from './sso-callback';
+
+const mountedRoots: Root[] = [];
+
+beforeAll(() => {
+  Object.defineProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT', {
+    configurable: true,
+    value: true,
+  });
+});
+
+beforeEach(() => {
+  apiMock.mockResolvedValue([
+    {
+      id: 'authentik',
+      name: 'Authentik',
+      protocols: ['oidc'],
+      configured: true,
+      loginMode: 'oidc',
+      callbackPath: '/api/auth/oauth2/callback/authentik',
+      teamSync: { enabled: false, claim: null },
+      samlFallback: { configured: false, loginUrl: null },
+      warnings: [],
+    },
+  ]);
+  oauth2Mock.mockResolvedValue({ data: null, error: null });
+});
+
+afterEach(async () => {
+  for (const root of mountedRoots.splice(0)) {
+    await act(async () => {
+      root.unmount();
+    });
+  }
+  document.body.replaceChildren();
+  apiMock.mockReset();
+  oauth2Mock.mockReset();
+});
+
+afterAll(() => {
+  Reflect.deleteProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT');
+});
+
+describe('SsoCallbackPage', () => {
+  it('rejects a control-character callback that normalizes to an external origin', async () => {
+    const router = createMemoryRouter(
+      [
+        {
+          path: '/auth/provider/:provider',
+          element: <SsoCallbackPage />,
+        },
+      ],
+      {
+        initialEntries: ['/auth/provider/authentik?callbackURL=%2F%0A%2F%2Fevil.example'],
+      },
+    );
+    const container = document.createElement('div');
+    document.body.append(container);
+    const root = createRoot(container);
+    mountedRoots.push(root);
+
+    await act(async () => {
+      root.render(<RouterProvider router={router} />);
+      await new Promise((resolve) => setTimeout(resolve, 0));
+    });
+
+    expect(oauth2Mock).toHaveBeenCalledWith({
+      providerId: 'authentik',
+      callbackURL: '/chat',
+    });
+  });
+});

apps/web/src/spa/pages/sso-callback.tsx

@@ -0,0 +1,91 @@
+import { useEffect, useState, type ReactElement } from 'react';
+import { Link, useParams, useSearchParams } from 'react-router-dom';
+import { api } from '@/lib/api';
+import { resolveAuthCallbackURL } from '@/lib/auth-redirect';
+import { signIn } from '@/lib/auth-client';
+import type { SsoProviderDiscovery } from '@/lib/sso';
+
+export function SsoCallbackPage(): ReactElement {
+  const { provider: providerId = '' } = useParams<'provider'>();
+  const [searchParams] = useSearchParams();
+  const requestedCallbackURL = searchParams.get('callbackURL');
+  const [providerName, setProviderName] = useState<string | null>(null);
+  const [error, setError] = useState<string | null>(null);
+
+  useEffect(() => {
+    let cancelled = false;
+
+    async function redirectToProvider(): Promise<void> {
+      try {
+        const callbackURL = resolveAuthCallbackURL(requestedCallbackURL, window.location.origin);
+        const providers = await api<SsoProviderDiscovery[]>('/api/sso/providers');
+        if (cancelled) return;
+
+        const provider = providers.find((candidate) => candidate.id === providerId);
+        if (!provider) {
+          setError('Unknown SSO provider.');
+          return;
+        }
+
+        setProviderName(provider.name);
+        if (!provider.configured) {
+          setError(`${provider.name} is not enabled in this deployment.`);
+          return;
+        }
+        if (provider.loginMode !== 'oidc') {
+          setError(`${provider.name} is not available for OIDC sign in.`);
+          return;
+        }
+
+        const result = await signIn.oauth2({
+          providerId: provider.id,
+          callbackURL,
+        });
+
+        if (!cancelled && result?.error) {
+          setError(result.error.message ?? `${provider.name} sign in failed.`);
+        }
+      } catch (caught: unknown) {
+        if (!cancelled) {
+          setError(caught instanceof Error ? caught.message : 'Unable to start single sign-on.');
+        }
+      }
+    }
+
+    void redirectToProvider();
+
+    return () => {
+      cancelled = true;
+    };
+  }, [providerId, requestedCallbackURL]);
+
+  return (
+    <div className="mx-auto flex min-h-[50vh] max-w-md flex-col justify-center">
+      <h1 className="text-2xl font-semibold text-text-primary">Single sign-on</h1>
+      <p className="mt-2 text-sm text-text-secondary">
+        {providerName
+          ? `Redirecting you to ${providerName}...`
+          : 'Preparing your sign-in request...'}
+      </p>
+
+      {error ? (
+        <div
+          role="alert"
+          className="mt-6 rounded-lg border border-error/30 bg-error/10 px-4 py-3 text-sm text-error"
+        >
+          <p>{error}</p>
+          <Link
+            to="/login"
+            className="mt-3 inline-block font-medium text-blue-400 hover:text-blue-300"
+          >
+            Return to login
+          </Link>
+        </div>
+      ) : (
+        <div className="mt-6 rounded-lg border border-surface-border bg-surface-elevated px-4 py-3 text-sm text-text-secondary">
+          If the redirect does not start automatically, return to the login page and try again.
+        </div>
+      )}
+    </div>
+  );
+}

apps/web/src/spa/placeholder.tsx

@@ -0,0 +1,9 @@
+import type { ReactElement } from 'react';
+
+export function Placeholder({ title }: { title: string }): ReactElement {
+  return (
+    <main className="flex min-h-screen items-center justify-center">
+      <h1 className="text-xl font-medium">{title}</h1>
+    </main>
+  );
+}

apps/web/src/spa/routes.spec.tsx

@@ -0,0 +1,70 @@
+import { isValidElement } from 'react';
+import { describe, expect, it } from 'vitest';
+import type { RouteObject } from 'react-router-dom';
+import { routes } from '@/routes';
+import { Placeholder } from '@/spa/placeholder';
+import { ChatPage } from '@/spa/pages/chat';
+
+function collectPaths(routeObjects: RouteObject[]): string[] {
+  return routeObjects.flatMap((route) => [
+    ...(route.path ? [route.path] : []),
+    ...(route.children ? collectPaths(route.children) : []),
+  ]);
+}
+
+function findRoute(routeObjects: RouteObject[], path: string): RouteObject | undefined {
+  for (const route of routeObjects) {
+    if (route.path === path) return route;
+    const nested = route.children ? findRoute(route.children, path) : undefined;
+    if (nested) return nested;
+  }
+  return undefined;
+}
+
+describe('SPA route table', () => {
+  it('covers every v1 parity route from the Phase P RFC', () => {
+    expect(collectPaths(routes).sort()).toEqual(
+      [
+        '/',
+        '/admin',
+        '/auth/provider/:provider',
+        '/chat',
+        '/login',
+        '/projects',
+        '/projects/:id',
+        '/register',
+        '/settings',
+        '/tasks',
+      ].sort(),
+    );
+  });
+
+  it('separates guest and authenticated route groups', () => {
+    const guestPaths = collectPaths(routes.at(0)?.children ?? []);
+    const authPaths = collectPaths(routes.at(1)?.children ?? []);
+    expect(guestPaths).toContain('/login');
+    expect(guestPaths).not.toContain('/chat');
+    expect(authPaths).toContain('/chat');
+  });
+
+  it.each(['/login', '/register', '/auth/provider/:provider'])(
+    'renders a real guest page instead of the P1 placeholder at %s',
+    (path) => {
+      const element = findRoute(routes, path)?.element;
+      expect(isValidElement(element)).toBe(true);
+      if (!isValidElement(element)) throw new Error(`Missing route element for ${path}`);
+      expect(element.type).not.toBe(Placeholder);
+    },
+  );
+
+  it('renders the real chat page instead of the P1 placeholder at /chat, inside the authenticated group', () => {
+    const authPaths = collectPaths(routes.at(1)?.children ?? []);
+    expect(authPaths).toContain('/chat');
+
+    const element = findRoute(routes, '/chat')?.element;
+    expect(isValidElement(element)).toBe(true);
+    if (!isValidElement(element)) throw new Error('Missing route element for /chat');
+    expect(element.type).not.toBe(Placeholder);
+    expect(element.type).toBe(ChatPage);
+  });
+});

apps/web/src/test/setup.spec.ts

@@ -0,0 +1,14 @@
+import { describe, expect, it } from 'vitest';
+
+describe('Vitest abort-controller realm', () => {
+  it('provides a global signal accepted by Node native Request', () => {
+    const controller = new AbortController();
+    const request = new Request('https://mosaic.invalid/navigation', {
+      signal: controller.signal,
+    });
+
+    expect(request.signal).toBeInstanceOf(AbortSignal);
+    controller.abort();
+    expect(request.signal.aborted).toBe(true);
+  });
+});

apps/web/src/test/setup.ts

@@ -0,0 +1,23 @@
+import { transferableAbortController } from 'node:util';
+
+// jsdom installs realm-local abort constructors while Node's undici Request
+// remains native. React Router passes a global AbortSignal to Request, so both
+// constructors must come from Node's native realm during tests.
+const nativeController = transferableAbortController();
+const nativeAbortController = nativeController.constructor;
+const nativeAbortSignal = nativeController.signal.constructor;
+
+for (const target of [globalThis, window]) {
+  Object.defineProperties(target, {
+    AbortController: {
+      configurable: true,
+      writable: true,
+      value: nativeAbortController,
+    },
+    AbortSignal: {
+      configurable: true,
+      writable: true,
+      value: nativeAbortSignal,
+    },
+  });
+}

apps/web/vite.config.ts

@@ -0,0 +1,24 @@
+import { fileURLToPath } from 'node:url';
+import react from '@vitejs/plugin-react';
+import { defineConfig } from 'vite';
+
+// The proxy exists only in dev; in production the SPA is same-origin with the gateway
+// (served by it under Candidate A, or behind one FQDN under Candidate B) and every
+// request uses a relative path, so no origin may ever be configured here or in src/.
+const gatewayTarget = 'http://localhost:14242';
+
+export default defineConfig({
+  plugins: [react()],
+  resolve: {
+    alias: {
+      '@': fileURLToPath(new URL('./src', import.meta.url)),
+    },
+  },
+  server: {
+    port: 3100,
+    proxy: {
+      '/api': gatewayTarget,
+      '/socket.io': { target: gatewayTarget, ws: true },
+    },
+  },
+});

apps/web/vitest.config.ts

@@ -1,9 +1,21 @@
+import { fileURLToPath } from 'node:url';
 import { defineConfig } from 'vitest/config';
 
 export default defineConfig({
+  resolve: {
+    alias: {
+      '@': fileURLToPath(new URL('./src', import.meta.url)),
+    },
+  },
+  // tsconfig uses "jsx": "preserve" for Next; tests need esbuild to compile it
+  esbuild: {
+    jsx: 'automatic',
+  },
   test: {
     globals: true,
     environment: 'jsdom',
+    setupFiles: ['./src/test/setup.ts'],
+    isolate: true,
     exclude: ['e2e/**', 'node_modules/**'],
   },
 });

docker/gateway.Dockerfile

@@ -10,6 +10,8 @@ COPY pnpm-workspace.yaml pnpm-lock.yaml package.json ./
 COPY apps/gateway/package.json ./apps/gateway/
 COPY packages/ ./packages/
 COPY plugins/ ./plugins/
+# the root prepare script runs scripts/install-hooks.mjs on install
+COPY scripts/ ./scripts/
 RUN pnpm install --frozen-lockfile
 COPY . .
 # Build gateway and all of its workspace dependencies via turbo dependency graph
@@ -21,11 +23,22 @@ RUN pnpm --filter @mosaicstack/gateway --prod deploy --legacy /deploy
 FROM base AS runner
 WORKDIR /app
 ENV NODE_ENV=production
+# WorkspaceService shells out to git at runtime and roots workspaces at
+# $MOSAIC_ROOT/.workspaces (apps/gateway/src/workspace/workspace.service.ts);
+# mount a volume over /opt/mosaic to persist workspaces across container restarts.
+# Intentionally unpinned: Alpine's signed repository is the trust anchor; pinning
+# git was declined so routine base-image security updates remain maintainable.
+RUN apk add --no-cache git \
+  && mkdir -p /opt/mosaic/.workspaces \
+  && chown -R node:node /opt/mosaic /app
+ENV MOSAIC_ROOT=/opt/mosaic
 # Use the pnpm deploy output — resolves all deps into a flat, self-contained node_modules
-COPY --from=builder /deploy/node_modules ./node_modules
+COPY --chown=node:node --from=builder /deploy/node_modules ./node_modules
-COPY --from=builder /deploy/package.json ./package.json
+COPY --chown=node:node --from=builder /deploy/package.json ./package.json
 # dist is declared in package.json "files" so pnpm deploy copies it into /deploy;
 # copy from builder explicitly as belt-and-suspenders
-COPY --from=builder /app/apps/gateway/dist ./dist
+COPY --chown=node:node --from=builder /app/apps/gateway/dist ./dist
-EXPOSE 4000
+# gateway defaults to port 14242 (apps/gateway/src/main.ts)
+EXPOSE 14242
+USER node
 CMD ["node", "dist/main.js"]

docker/web.Dockerfile

@@ -8,9 +8,11 @@ WORKDIR /app
 COPY pnpm-workspace.yaml pnpm-lock.yaml package.json ./
 COPY apps/web/package.json ./apps/web/
 COPY packages/ ./packages/
+# the root prepare script runs scripts/install-hooks.mjs on install
+COPY scripts/ ./scripts/
 RUN pnpm install --frozen-lockfile
 COPY . .
-RUN pnpm --filter @mosaic/web build
+RUN pnpm --filter @mosaicstack/web build
 
 FROM base AS runner
 WORKDIR /app

docs/design/prerelease-next-dist-tag-pipeline.md

@@ -0,0 +1,63 @@
+# npm `@next` prerelease lane
+
+Status: **IMPLEMENTED**
+
+## Current behavior
+
+`tools/install.sh --next` provides the prerelease integration lane for the permanent `next` branch.
+
+The lane is fast-by-default:
+
+1. Install framework files from the `next` source archive.
+2. Resolve the Gitea npm registry `next` dist-tag for the globally installed packages:
+
+   ```bash
+   npm view @mosaicstack/gateway@next version
+   npm view @mosaicstack/mosaic@next version
+   ```
+
+3. Require both resolved versions to share the same `next.<pipeline>` suffix, then install the exact resolved versions.
+4. If either `@next` package is missing, unreachable, mismatched, or fails to install, fall back to the source-build path at `next`.
+
+`--next` never hard-fails solely because the prerelease npm dist-tag is unavailable.
+
+## Published packages
+
+The `next` publish pipeline publishes non-private `@mosaicstack/*` packages to the Mosaic Gitea npm registry:
+
+```text
+https://git.mosaicstack.dev/api/packages/mosaicstack/npm/
+```
+
+Observed `next` dist-tags after enabling the pipeline:
+
+```text
+@mosaicstack/mosaic@next  -> 0.0.49-next.1633
+@mosaicstack/gateway@next -> 0.0.7-next.1633
+```
+
+The gateway also publishes a Docker image as `gateway:sha-<short>` on `next` merges. The installer fast path uses the npm gateway package when available; the Docker image is for deployed gateway/runtime harness flows.
+
+## Explicit source lanes
+
+Source builds remain available and are still the authority for explicit ref validation:
+
+- `--dev` always builds from source.
+- `--ref <ref>` / `MOSAIC_REF=<ref>` wins over `--next` and uses the source path for that exact ref.
+
+## Pipeline shape
+
+1. Trigger on `next` merges.
+2. Compute the next prerelease version from the upcoming stable version plus the Woodpecker pipeline number (`<target-stable>-next.<CI_PIPELINE_NUMBER>`).
+3. Build and publish non-private packages in CI.
+4. Publish to the Mosaic Gitea npm registry with dist-tag `next`.
+5. Keep `latest` untouched; only main/release promotion can update `latest`.
+6. Publish gateway Docker images from `next` as `gateway:sha-<short>` only.
+
+## Guardrails
+
+- `@next` is mutable prerelease convenience, not a deployment pin.
+- Stable installs continue to use `@latest`.
+- Contributor validation remains available through `--dev --ref <branch>`.
+- Pipeline output traces every prerelease package back to the source commit on `next`.
+- The installer falls back to source rather than hard-failing on prerelease registry issues.

docs/guides/dev-guide.md

@@ -195,6 +195,17 @@ pnpm format:check && pnpm typecheck && pnpm lint
 
 A pre-push hook enforces this mechanically.
 
+### CI Publish Channels
+
+Woodpecker `.woodpecker/publish.yml` keeps stable and integration-line artifacts separate:
+
+| Source                            | npm packages                                                                                                  | Gateway image                                                                            |
+| --------------------------------- | ------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------- |
+| `main` push/manual or release tag | committed package versions published to Gitea npm without changing the dist-tag workflow                      | `gateway:sha-<short>` plus `gateway:latest` on `main`, and the release tag on tag events |
+| `next` push/manual                | CI-computed prereleases, `<target-stable>-next.<CI_PIPELINE_NUMBER>`, published with `npm publish --tag next` | `gateway:sha-<short>` only                                                               |
+
+`next` never publishes npm `latest` or Docker `latest`. The next npm publish step verifies that `@mosaicstack/mosaic@next` resolves to the computed prerelease before the pipeline can pass.
+
 ---
 
 ## Adding New Agent Tools

docs/guides/user-guide.md

@@ -175,8 +175,18 @@ Or use the direct URL:
 bash <(curl -fsSL https://git.mosaicstack.dev/mosaicstack/stack/raw/branch/main/tools/install.sh)
 ```
 
-The installer places the `mosaic` binary at `~/.npm-global/bin/mosaic`. Flags for
+The installer places the `mosaic` binary at `~/.npm-global/bin/mosaic`.
-non-interactive use:
+
+Install lanes:
+
+| Lane                     | Command                               | Source                                                                                       |
+| ------------------------ | ------------------------------------- | -------------------------------------------------------------------------------------------- |
+| Stable                   | `bash tools/install.sh`               | npm `@mosaicstack/mosaic@latest` + `main`                                                    |
+| Prerelease integration   | `bash tools/install.sh --next`        | Fast npm `@mosaicstack/mosaic@next` + `@mosaicstack/gateway@next`; source fallback at `next` |
+| Contributor/source build | `bash tools/install.sh --dev --ref X` | Build-from-source at the requested ref                                                       |
+
+`--next` is fast-by-default from the Gitea npm `next` dist-tag and falls back to a source build at the permanent `next` branch if the dist-tag is missing or unreachable. Explicit `--ref` or `MOSAIC_REF` still wins and uses the source path.
+Flags for non-interactive use:
 
 ```bash
 --yes               # Accept all defaults

docs/remediation/AC-RM02-ANCHOR.md

@@ -1,58 +0,0 @@
-# RM-02 / PR #1030 — PRE-REGISTERED RE-REVIEW: the merge-base anchor round
-
-**Subject head (exact):** `fbb61912981abb250d289ec7aafd4316db6fdb11`
-**Supersedes:** the second NO-GO at `32b490a7` (D-45/D-46/D-47). That verdict is VOID.
-**Registered by:** `mos-remediation` **before any reviewer read the diff.** **Reviewer:** `rev-974`.
-
-## What the orchestrator already reproduced (do not re-spend the review here)
-
-- Derived boundary `f4fd5967` **equals** an independently computed `git merge-base HEAD origin/main`.
-- Emptying `criteria`/`gates`/`proseClaims`/`compatibilityScenarios` now fails with
-  _"population must be non-empty and anchored before evaluation"_.
-- The both-directions bootstrap statement is present in `gate-history.mjs` with the Builds 1–2 residual.
-
-## A — attack the ANCHOR (highest value)
-
-| id     | check                                                                                                                                                                                                                                                                                                                                                                     |
-| ------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **A1** | `targetRef` is the literal `refs/remotes/origin/main`. **Who controls that ref in the environment where the gate runs?** Can a PR author influence it — a `remote.origin.url` rewrite, a crafted `refs/remotes/origin/main` in their own clone, a push to a fork's `main`? If the gate trusts a locally-writable ref, the anchor moved from the manifest into git config. |
-| **A2** | **Absent/stale target:** if `refs/remotes/origin/main` is missing, stale, or the fetch is shallow, does it fail CLOSED (line 57 suggests it does) or silently derive a narrower range?                                                                                                                                                                                    |
-| **A3** | **Delayed introduction — the round-2 attack, re-run.** Commit a gate change BEFORE adding the manifest. Does it now stay in range and fail the own-tree read?                                                                                                                                                                                                             |
-| **A4** | **Branch from an old main:** branch from a point far behind `origin/main`, so merge-base is old. Does the range widen correctly (safe) or include unrelated main commits that cannot carry manifests (a new false-red)? Over-inclusion is the natural failure mode of this fix.                                                                                           |
-| **A5** | Is the **bootstrap residual** recorded as a **tracked dependency on Builds 1–2**, not prose? (D-19's third mandatory move.)                                                                                                                                                                                                                                               |
-
-## P — the non-empty/anchored precondition
-
-| id     | check                                                                                                                                                                                                                                                                                                                                               |
-| ------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **P1** | Does the precondition run **before** every quantified check, on **every** path — or only the ones the author enumerated? Find a quantified check that still runs before its precondition.                                                                                                                                                           |
-| **P2** | **Seven required gate IDs anchored to canonical sources** — can that anchor list itself be emptied, shrunk, or pointed elsewhere? An anchor list the author edits is D-45 again, one level in.                                                                                                                                                      |
-| **P3** | The author reports finding and REMOVING a **production CLI fixture-profile bypass** in their own pre-commit review. **Verify it is gone from the shipped CLI path**, that the remaining relaxation is test-support only and non-executable in production, and that the CLI rejection is tested. This was self-disclosed — confirm it independently. |
-
-## Q — clauses quantified over the population (D-47)
-
-| id     | check                                                                                                                                                                                                                                                   |
-| ------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **Q1** | `gateRefs` **exactly spans** every registered gate. Can a gate be added WITHOUT a corresponding ref — i.e. does adding a gate to the population escape the clause?                                                                                      |
-| **Q2** | Deleting `gateRefs`, or shrinking gates and refs **together**, must fail. Shrink-together is the D-46 shape; verify it is a genuine control and not a regression guard mislabelled.                                                                     |
-| **Q3** | Do the population controls **iterate all seven gates** and mutate evidence-subject and comparison-type **per gate**, or only a representative one?                                                                                                      |
-| **Q4** | Honest labelling: author claims delayed-introduction, empty-populations, fixture-profile bypass and removable gateRefs as **genuine red-first**, and shrink-together/exact-span as **regression guards**. Verify each claim against pre-fix code (D-8). |
-
-## C — head, CI, integrity
-
-| id     | check                                                                                                                                                                                |
-| ------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| **C1** | Head `fbb61912` on git and provider; `Closes #1029` present.                                                                                                                         |
-| **C2** | Exact-head CI terminal-green, full `-f json`, counts stated incl. `clone`; machine-checked with `verify-terminal-green.py --expect-commit fbb61912981abb250d289ec7aafd4316db6fdb11`. |
-| **C3** | Nothing weakened: `32b490a7` → `fbb61912` removes/relaxes no existing case, test, or assertion.                                                                                      |
-
-## Reviewer instruction
-
-Verdict bound to `fbb61912981abb250d289ec7aafd4316db6fdb11`, evidence enumerated, posted durably under
-your own identity. If a check is unrunnable, **say so**.
-
-**A1 and P2 are the ones I most want answered** — both ask whether the fix moved the author's control
-point again rather than removing it, which is now the mission's named first-class principle and has
-recurred three times. **Attack outside this set.**
-
-**No one dispatching this review may state a conclusion on an open check (D-39).**

docs/remediation/AC-RM02-HARDENING.md

@@ -1,67 +0,0 @@
-# RM-02 / PR #1030 — PRE-REGISTERED RE-REVIEW: the four-blocker hardening pass
-
-**Subject head (exact):** `32b490a712a5e8e77f13c40c60099b51feb38994`
-**Supersedes:** the NO-GO at `83d2ecb2` (D-44, four silent-defeat paths). That verdict is VOID.
-**Registered by:** `mos-remediation` **before any reviewer read the diff.** **Reviewer:** `rev-974`.
-
-## Framing — attack the FIX, not the original bug
-
-Every round on this mission, **the remediation introduced the next hole**: the commit-binding fix
-shipped a type confusion; the type-strict fix was clean but the registry around it had four defeats.
-So the highest-value checks here are **not** "was each blocker fixed" — the orchestrator already
-reproduced three of the four attacks as dead — but **"is the NEW mechanism itself defeatable?"**
-
-Blocker 1's fix replaced an author-settable field with a **derivation**. A derivation has inputs. **The
-question is who controls them.**
-
-## H — the new derivation (highest value)
-
-| id     | check                                                                                                                                                                                                                                                                                                                                                                                                  |
-| ------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| **H1** | `deriveHistoryBoundary` = parent of the first first-parent commit introducing `gates/gates.manifest.json`. **Are its inputs author-controlled?** Can a PR author influence the derived value by adding, moving, renaming, deleting-and-recreating, or symlinking that path — or by adding a SECOND manifest earlier in history? If the derivation is gameable, blocker 1 is not fixed, only relocated. |
-| **H2** | **First-parent traversal:** what happens on a merge commit, an octopus merge, a squash, a rebase that reorders, or a branch where the introducing commit is not on the first-parent chain? Does the boundary silently move, or fail closed?                                                                                                                                                            |
-| **H3** | **Shallow/partial clone:** the branch previously needed an unshallow fix (`e8959975` "unshallow gate replay history"). If history is shallow, does the derivation fail CLOSED or silently derive a wrong/empty boundary?                                                                                                                                                                               |
-| **H4** | **Path deletion:** if `gates/gates.manifest.json` is absent at HEAD, or was deleted and re-added, what is derived? Fail closed, or a boundary that excludes the deletion window?                                                                                                                                                                                                                       |
-| **H5** | Are the **three registered seam controls (HEAD, HEAD^, introduction) genuinely RED-FIRST** — do they fail against the PRE-fix code for their own stated reason? A control that was always green is a regression guard, not a must-fail control (D-8).                                                                                                                                                  |
-
-## S — the recursive schema closure
-
-| id     | check                                                                                                                                                                                                                                                  |
-| ------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| **S1** | **Is closure COMPLETE or enumerated?** The author lists the objects they closed. Find one they did **not** — any nested object anywhere in the manifest — and inject an unknown key there. If it is accepted, the fix covers instances, not the class. |
-| **S2** | **Wrong-type, not just unknown-key:** `outputPattern` as a number/array/object/null rather than misspelled. Does the closed schema type-check values, or only key names?                                                                               |
-| **S3** | **Empty/degenerate values:** `outputPattern: ""` — does an empty regex match everything and silently neuter the assertion the same way a typo did? The author claims an empty-pattern control; verify it is bound.                                     |
-| **S4** | Confirm the registered typo/wrong-type/empty-pattern controls are **genuine red-first** against pre-fix code, and that anything labelled a regression guard is honestly labelled as one.                                                               |
-
-## E — provider evidence (blocker 4)
-
-| id     | check                                                                                                                                                                                                                                           |
-| ------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **E1** | Global validation runs **before** per-commit filtering **on every path**, including the HEAD-only path the author calls out. Is there any code path that reaches per-commit assessment without it?                                              |
-| **E2** | **Duplicate identity by another key:** the fix makes pipeline NUMBER globally unique. Can two records still collide on a different identity dimension — same commit + different number, same URL, same step-id — and certify the wrong subject? |
-| **E3** | "Exactly one gate-verify step per record" — what if a record has zero, or two with different outcomes? Fail closed?                                                                                                                             |
-
-## C — clauses, integrity, CI
-
-| id     | check                                                                                                                                                                                                                                                                                                        |
-| ------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| **C1** | The three new criteria (`RM02-EVIDENCE-SUBJECT-BINDING`, `RM02-TYPE-STRICT-SCHEMA`, `RM02-HISTORY-BOUNDARY`) are **checked criteria with bidirectionally bound cases**, not prose. Orchestrator observed caseRefs 1 / 3 / 3 — verify the bindings actually run and can fail.                                 |
-| **C2** | **B1/B2 satisfied in substance:** does `RM02-EVIDENCE-SUBJECT-BINDING` express D-38 generally ("does this gate bind its evidence to its subject?") or only the one pipeline-number instance? Same for D-40 vs the one typo instance. **A clause that only covers its originating instance is not a clause.** |
-| **C3** | **Nothing weakened:** diff `83d2ecb2` → `32b490a7` removes/relaxes no existing case, test, or assertion.                                                                                                                                                                                                     |
-| **C4** | Exact-head CI terminal-green, full `-f json`, counts stated **including `clone`**; machine-checked with `verify-terminal-green.py --expect-commit 32b490a712a5e8e77f13c40c60099b51feb38994`.                                                                                                                 |
-| **C5** | `Closes #1029` still present (D-38c).                                                                                                                                                                                                                                                                        |
-
-## Reviewer instruction
-
-Verdict bound to `32b490a712a5e8e77f13c40c60099b51feb38994`, evidence enumerated, posted durably under
-your own identity. If a check is unrunnable, **say so** — never substitute a passing variant.
-
-**H1 and S1 are the two I most want answered**, because they ask whether each fix closed a **class** or
-an **instance**. Attack outside this set: four of the last five blockers on this PR came from mutating
-something nobody had registered.
-
-**Environment note:** `pnpm gate:verify` fails on `checkout-preflight` with outcome 42 (bubblewrap
-class) in at least one worktree. If you hit it, report it as an environment limitation — do not treat it
-as a finding, and do not let it mask one.
-
-**No one dispatching this review may state a conclusion on an open check (D-39).**

docs/remediation/AC-RM02-NARROW.md

@@ -1,59 +0,0 @@
-# RM-02 / PR #1030 — PRE-REGISTERED RE-REVIEW: honest narrowing + (d)-strict
-
-**Subject head (exact):** `e910a45ab3578a9c77ad3eeaa52b31b72611f6c6`
-**Supersedes:** the third NO-GO at `fbb61912` (D-45/D-46/D-47) and the D-52 stop. Those are VOID.
-**Registered by:** `mos-remediation` before any reviewer read the diff. **Reviewer:** `rev-974`.
-
-## Already reproduced by the orchestrator (do not re-spend here)
-
-- The required narrowing sentence is **verbatim** in `gates/required-gates.baseline.json` and in
-  `scripts/gate-inventory-claim-control.mjs`: _"Detects accidental and incompetent inventory drift
-  within a checkout; does NOT survive an adversary who rewrites baseline, manifest, and verifier
-  consistently — that guarantee requires RM-60's external boundary."_
-- **The overclaim control FIRES**: clean ⇒ exit 0; injecting "protected, independently anchored" into
-  the baseline purpose ⇒ **exit 84**, `INVENTORY_CLAIM_OVERSTATED`.
-- CI #2201 at the exact head, 10/10 incl. `clone`; machine check bound, `exempted_steps 0`, no anomalies.
-
-## N — the narrowing (D-52's ruling is the wording)
-
-| id     | check                                                                                                                                                                                                                                                                                |
-| ------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| **N1** | ★ Is the narrowed claim **honest EVERYWHERE**, or only where the control looks? Find any place — docs, comments, observations, manifest prose, CLI output — that still implies the baseline is protected or independently anchored. **The control only checks the files it checks.** |
-| **N2** | ★ Can the **overclaim control itself** be defeated? It is PR-controlled like everything else. Weaken/skip/reword it so an overstatement passes. If it can be trivially neutered, D-52 is re-armed one level down — the exact recursion this PR keeps producing.                      |
-| **N3** | Does the control detect **semantic** overclaim or only the literal strings it greps? An artifact could assert protection in different words and pass.                                                                                                                                |
-| **N4** | Is the narrowed claim **TRUE**? Verify the baseline genuinely catches accidental/inconsistent drift — not just that it says so. A narrowed claim that is still overstated is D-48 again.                                                                                             |
-
-## H — (d)-strict history removal
-
-| id     | check                                                                                                                                                                                                |
-| ------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **H1** | Is the verifier **structurally incapable** of reporting history-provenance-verified, or merely not currently doing so? The manifest says "structurally incapable" — test the claim.                  |
-| **H2** | ★ **TRAP 1 re-check:** nothing emits the unverifiable state as an OBSERVATION (which exits 0). Confirm no path yields exit 0 while implying provenance was considered.                               |
-| **H3** | ★ **TRAP 2 re-check:** the exclusion is **enforced**, not merely declared in `coverageBoundary.excluded`. Re-enable history provenance without a trustworthy anchor — does a registered case go RED? |
-| **H4** | The residual is stated **correctly** — no local git state is trustworthy because PR code executes before the gate — **NOT** the D-48 wording ("compromised main").                                   |
-
-## B3 / R — evidence-subject and renderer
-
-| id     | check                                                                                                                                                                          |
-| ------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| **B1** | Subject is on the **EVIDENCE side** and compared **at consumption**, not `gate.evidenceSubject === gate.id` metadata-vs-itself. Mutate the evidence-side subject **per gate**. |
-| **B2** | Can evidence still be moved or misbound while every gate satisfies its check?                                                                                                  |
-| **R1** | Renderer now covers the **final success stdout/stderr** paths.                                                                                                                 |
-
-## C — integrity + CI
-
-| id     | check                                                                                                                                           |
-| ------ | ----------------------------------------------------------------------------------------------------------------------------------------------- |
-| **C1** | Head `e910a45a` on git + provider; `Closes #1029` present.                                                                                      |
-| **C2** | Exact-head CI terminal-green, `-f json`, counts incl. `clone`; machine-checked with `--expect-commit e910a45ab3578a9c77ad3eeaa52b31b72611f6c6`. |
-| **C3** | Nothing weakened `fbb61912` → `e910a45a`. Red-first labels honest (D-8).                                                                        |
-| **C4** | **NO fourth local anchor was invented.** Blocker 1 and blocker 2's adversarial guarantee both track RM-60.                                      |
-
-## Reviewer instruction
-
-Verdict bound to `e910a45ab3578a9c77ad3eeaa52b31b72611f6c6`, evidence enumerated, posted durably.
-Unrunnable ⇒ **say so**. **N1 and N2 are the sharp ones** — this PR's history is that every fix
-relocates the defect one level down, and N2 asks whether the control that enforces honesty is itself
-honest. **Attack outside the set: six for six so far.**
-
-**No one dispatching this review may state a conclusion on an open check (D-39).**

docs/remediation/AC-RM02-REBASE.md

@@ -1,71 +0,0 @@
-# RM-02 / PR #1030 — PRE-REGISTERED ACCEPTANCE CHECKS (post-rebase, keystone)
-
-**Subject head (exact):** `83d2ecb2243f1b0987ef2bc14de47f444285a684`
-**Rebased onto:** `main` @ `f4fd5967fc5d4cbc72d680b199d88224aa855131` (post-RM-61)
-**Registered by:** `mos-remediation` **BEFORE the reviewer read the diff.** **Reviewer:** `rev-974`
-(author ≠ reviewer; branch commits are `f10-coder`'s and `coder-mos1`'s).
-**Prior reviews 63 / 65 are SUPERSEDED; this head carries NO live review of any kind.**
-
-RM-02 is the **keystone**: it is the anti-inert-gate registry every downstream gate is measured against.
-A defect that survives here propagates into every gate this mission ships.
-
-## ★ CRUX — the one non-mechanical change, made by the author, that turned a red green
-
-The rebase was clean. One further commit was **not** purely mechanical and the author disclosed it
-unprompted (`83d2ecb2` — advance registry activation seam):
-
-    gates/gates.manifest.json
-    -  "activationCommit": "f65e9ea656ec466e12640bf6ab5d46fe07ff160c"
-    +  "activationCommit": "f4fd5967fc5d4cbc72d680b199d88224aa855131"
-
-Stated rationale: after the rebase, `pnpm gate:verify` correctly failed because the newly-merged
-pre-registry RM-61 commit was treated as _prospective_ and required a manifest that could not exist.
-
-`activationCommit` sets the lower bound of `activationCommit..HEAD` — **the set of commits required to
-carry own-tree registry provenance** (`gate-history.mjs:314` → `listProspectiveCommits`). Advancing it
-**shrinks that set**.
-
-**Determine, do not assume — and I have deliberately formed and stated no verdict (D-39):**
-
-| id     | check                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
-| ------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **A1** | **Is the advance JUSTIFIED?** Can a pre-registry commit on `main` (e.g. `f4fd5967`) satisfy the provenance requirement at all, or is requiring it impossible-by-construction? If impossible, is advancing the seam the _correct_ remedy, or does a correct remedy exist that does not move an author-controlled field?                                                                                                                                                                                                                                |
-| **A2** | **Is the advance MINIMAL?** Was it advanced exactly to the new parent baseline, or beyond it? Does any commit that _should_ remain covered fall outside the new range?                                                                                                                                                                                                                                                                                                                                                                                |
-| **A3** | **Are all 7 branch commits still PROSPECTIVE under the new seam?** Enumerate them and show each is still required to carry provenance. The author claims "own-tree provenance over every registry-era branch commit" — verify the claim, do not accept it.                                                                                                                                                                                                                                                                                            |
-| **A4** | ★★ **IS THE SEAM ITSELF CONSTRAINED?** The only validation found is `merge-base --is-ancestor activationCommit head` (`gate-history.mjs:288`). **A commit is its own ancestor.** Determine what `activationCommit = HEAD` does: is the prospective range empty, does the per-commit loop iterate zero times, and does the history check therefore PASS VACUOUSLY? If so, the anti-inert-gate registry contains an author-settable field that can inert its own history check. **Run it. Report the observed exit and whether any failure is raised.** |
-| **A5** | **If A4 shows vacuity is reachable, is there a registered MUST-FAIL negative control for it?** RM-02's own founding rule is that a gate with no proven failure path manufactures evidence. Does the registry hold a case that goes RED when the seam is over-advanced? If not, that is a hole in the registry's coverage of itself.                                                                                                                                                                                                                   |
-| **A6** | **Self-verification shape (charter / D-19 / D-39b):** the field was advanced by the change's own author to make the author's gate pass. Independent of whether the value is correct, determine whether the _mechanism_ permits an audited party to relax its own audit, and whether that needs a constraint, an owner, or an escalation.                                                                                                                                                                                                              |
-
-## Registry substance — the clauses this PR must now carry
-
-| id     | check                                                                                                                                                                                                                                                                   |
-| ------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **B1** | **D-38 clause present and enforced:** the registry asks of every gate _"does this gate BIND its evidence to the subject under review?"_ Ruled in-scope for THIS PR by Mos. Verify it exists as a checked clause, not prose.                                             |
-| **B2** | **D-40 clause present and enforced:** _"discriminator and comparison inputs must be TYPE-STRICT."_ Also ruled in-scope for THIS PR. `== 0` matching `False`/`0.0` is the banked instance; the clause is the general form.                                               |
-| **B3** | **D-42's clause is CORRECTLY ABSENT** — provider-side negative control tracks separately (Mos: landing it now would give the registry a clause with nothing to satisfy it, going red on its own clause). Confirm its absence is deliberate and recorded, not forgotten. |
-| **B4** | **The four founding clauses still hold** (`MISSION.md`): every check proven **right** (red for its own stated reason), the set **covers**, no two criteria **conflict**, and criterion evolution **retains original text + restatement + reason**.                      |
-| **B5** | **Nothing was weakened, skipped, or deleted by the rebase.** Diff `f9746b23` → `83d2ecb2` and confirm no registered case, test, or assertion was removed or relaxed to make the rebase land.                                                                            |
-| **B6** | **`coverageBoundary.excluded[]` is honest in BOTH directions** (charter principle 4): what it does NOT cover is stated beside what it DOES, and the gap is tracked (`trackedBy: RM-54`) rather than implied-fixed.                                                      |
-| **B7** | **The RM-02 execution boundary** (`gate-history.mjs`, DOES / DOES NOT, owner RM-60, xref RM-59) states its limits in both directions and names a tracked owner — not a documented gap with no owner.                                                                    |
-
-## Head + CI (re-run these; do not carry them forward from the author's report)
-
-| id     | check                                                                                                                                                                                                        |
-| ------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| **C1** | Head `83d2ecb2…` on **both** git and provider; `Closes #1029` present in the body (delivery-issue rule, D-38c).                                                                                              |
-| **C2** | Exact-head CI terminal-green by **full `-f json` scan**, counts stated **including `clone`**. Note the count changed 9 → **10** (this PR adds `gate-verify`) — confirm the new step is real, not a miscount. |
-| **C3** | **Machine-check it, do not assert it:** `verify-terminal-green.py --expect-commit 83d2ecb2243f1b0987ef2bc14de47f444285a684`. Report exit, `exempted_steps`, `commit == expected_commit`.                     |
-| **C4** | `exempted_steps=0` is expected here — `ci-postgres` succeeded, so the #1000 exemption was **not needed**. Confirm the exemption is present-but-unused rather than silently inapplicable.                     |
-
-## Reviewer instruction
-
-Verdict bound to `83d2ecb2243f1b0987ef2bc14de47f444285a684`, evidence enumerated per check, posted
-durably under your own identity. If a check is unrunnable, **say so** — never substitute a variant that
-passes. Scan CI from `-f json`, never default text (D-33); state your counts.
-
-**A4 is the check I most want an answer to and the one I have least confidence about.** Attack outside
-this set as well: every blocker found on this mission so far came from mutating something nobody had
-registered a check for.
-
-**No one dispatching this review may state a conclusion on an open check (D-39).** Observations may be
-relayed to you; verdicts may not. The ruling is yours.

docs/remediation/AC-RM03-REBASE.md

@@ -1,42 +0,0 @@
-# RM-03 / PR #1032 — PRE-REGISTERED RE-REVIEW (post-freshening)
-
-**Subject head (exact):** `868b9b871a5118762aa5b8aafecd2f0592f7ab5c`
-**Rebased onto:** `main` @ `f4fd5967` **Registered by:** `mos-remediation` before the reviewer read the
-diff. **Reviewer:** `rev-974`.
-
-**Why this exists:** review 66 APPROVED and the merge-gate GO were bound to `78ec47cd`; `main` drifted
-under a long hold and the PR went `mergeable=false` (**D-50 — a GO has a shelf life**). Both verdicts
-are VOID at the new head. Jason's merge approval is **standing** and executes once this re-gates.
-
-## What the orchestrator already verified (do not re-spend here)
-
-- `git range-diff 78ec47cd...868b9b87`: commits **2–5 are `=` (patch-equivalent)**; only commit 1 differs.
-- That single difference is the `test:framework-shell` chain, resolved as a **UNION** — main's
-  `test-terminal-green-contract.sh` **and** RM-03's `tristate`, `github-checks`, `merge-queue-branch`,
-  `merge-head-pin`, plus the pre-existing `branch-absent`. **Nothing dropped from either side.**
-- CI #2199 at the exact head: 9 children, 9 success incl. `clone`; machine check exit 0, bound, no anomalies.
-- `mergeable` is now **true**.
-
-## Checks
-
-| id     | check                                                                                                                                                                                                                                                                             |
-| ------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **R1** | ★ **THE GUARD CAN FAIL.** RM-03 exists because the queue guard is ZERO-INFORMATION (D-23) — it returns pass for every possible input. Prove the rebased head's guard **actually fails** on asserted non-readiness, not merely that its tests pass. This is the whole deliverable. |
-| **R2** | ★ **NO QUEUE-GUARD SEMANTIC MOVED IN THE REBASE.** Confirm the range-diff equivalence independently. A queue-guard semantic resolved quietly re-breaks the thing this PR fixes.                                                                                                   |
-| **R3** | **Union is complete in BOTH directions:** no RM-03 suite lost to main's version, no main suite (esp. `test-terminal-green-contract.sh`) lost to RM-03's. Enumeration count reconciles.                                                                                            |
-| **R4** | **Tri-state is real** (`verified` / `written-unverified` / `failed`) — P-WRAPPER-001. Verify an indeterminate result cannot present as a pass; that is the exact defect (`state=unknown exit 0`).                                                                                 |
-| **R5** | The guard's **exit-asserting non-null-case** tests are genuine — each fails for its own stated reason against pre-fix code, not merely present (D-8).                                                                                                                             |
-| **R6** | `test:framework-shell` is **runnable to completion in CI** (canonical env). Known: it exits 97 on some hosts via a Bash 5.2.15 `BASH_LINENO` assertion — if you hit that, report it as an environment limitation, do not treat it as a finding and do not let it mask one.        |
-| **R7** | Exact-head CI terminal-green, full `-f json`, counts stated incl. `clone`; machine-checked with `--expect-commit 868b9b871a5118762aa5b8aafecd2f0592f7ab5c`.                                                                                                                       |
-| **R8** | `Closes #1019` present in the body (D-38c delivery-issue rule).                                                                                                                                                                                                                   |
-| **R9** | Nothing weakened by the rebase: no test, case, or assertion removed or relaxed to make it land.                                                                                                                                                                                   |
-
-## Reviewer instruction
-
-Verdict bound to `868b9b871a5118762aa5b8aafecd2f0592f7ab5c`, evidence enumerated, posted durably under
-your own identity. If a check is unrunnable, **say so**.
-
-**R1 is the deliverable and R2 is the risk.** Attack outside this set. **Do not cite the queue guard's
-own green as evidence of anything** — it remains inert until this very PR lands (D-23).
-
-**No one dispatching this review may state a conclusion on an open check (D-39).**

docs/remediation/AC-RM61-REREVIEW-033b2ffb.md

@@ -1,40 +0,0 @@
-# RM-61 / PR #1033 — PRE-REGISTERED RE-REVIEW ACCEPTANCE CHECKS
-
-**Subject head (exact):** `033b2ffb46674b2c0bcc5197273c109b461f62d9`
-**Supersedes:** review 67 / comment 20403 @ `e7b29219` (NO GO). That verdict is VOID — the head moved.
-**Registered by:** `mos-remediation` (orchestrator). **Reviewer:** `rev-974` (author ≠ reviewer).
-**Registered BEFORE the reviewer read the diff.** Any head move after this file is committed voids the
-re-review and requires re-registration.
-
-## Scope discipline
-
-The prior review passed AC1–AC8 and still found a blocker, because the registered set tested whether the
-signature DISCRIMINATES and never tested whether the evidence was BOUND TO ITS SUBJECT (Finding 3 /
-coverage-failure-mode-2, D-17 class). This set therefore carries the binding property as a first-class
-check, and **RR7 explicitly invites the reviewer to attack outside the set** — a registered set is
-protection against retrofitting only, never a ceiling on scrutiny.
-
-## Checks
-
-| id       | check                                                                                                                                                                                                                                                  | verdict form                                                              |
-| -------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------- |
-| **RR1**  | The full 12-case contract harness passes at the exact head: `bash test-terminal-green-contract.sh`                                                                                                                                                     | ⇒0, and states 12 cases                                                   |
-| **RR2**  | ★CRUX — the ORIGINAL ATTACK IS DEAD. Take the real `#2188` record, mutate ONLY `commit` to an unrelated 40-hex value, verify against the true expected head                                                                                            | ⇒1, `exempted_steps == 0`, anomaly naming expected vs actual              |
-| **RR3**  | Missing `--expect-commit` cannot be defaulted, inferred, or skipped                                                                                                                                                                                    | ⇒2 (not 0, not 1)                                                         |
-| **RR4**  | Malformed expected commit (short SHA, non-hex, empty) is rejected — no silent normalisation into a pass                                                                                                                                                | ⇒2                                                                        |
-| **RR5**  | A record with the `commit` key ABSENT (not merely different) is rejected — fail-closed on missing, not just on mismatch                                                                                                                                | ⇒1, `exempted_steps == 0`                                                 |
-| **RR6**  | The genuine artifact still passes when correctly bound: real `#2188` + its true head                                                                                                                                                                   | ⇒0, `exempted_steps == 1`, exactly one `WP-K8S-1000-CI-POSTGRES-TEARDOWN` |
-| **RR7**  | ★RED-FIRST, PROVED RETROACTIVELY. The four new cases must FAIL against the OLD verifier at `e7b29219` — otherwise they do not test what they claim (D-8 class). Run the new cases against the previous implementation                                  | new cases ⇒≠0 under `e7b29219`                                            |
-| **RR8**  | AC2 OF THE PRIOR SET DID NOT REGRESS: both REAL controls stay terminal red — `#2189` (`ci-postgres` exit 1) and `#2191` (exit 137, `test` exit 61)                                                                                                     | both ⇒1, `exempted_steps == 0`                                            |
-| **RR9**  | Still NO fetch / trigger / retry / re-roll / sleep / network of any kind in the verifier or harness. The coin flip must remain removed, not codified (D-21)                                                                                            | grep ⇒ no such call sites                                                 |
-| **RR10** | The doc/baseline changes REQUIRE the current provider PR head to be passed — they must not merely mention it. Check `merge-gate.md`, `CI-CD-PIPELINES.md`, `woodpecker/README.md` state it as a requirement a gate operator cannot satisfy by omission | reviewer judgement, quote the lines                                       |
-| **RR11** | Exemption remains bound to #1000 and retires with it; signature conjunction unchanged and not widened by this fix                                                                                                                                      | diff-scoped, ⇒ no widening                                                |
-| **RR12** | Case-sensitivity: an uppercase-hex record commit against a lowercase expected head must NOT silently pass by accident of comparison. State which way it resolves and whether it fails closed                                                           | state the observed behaviour                                              |
-
-## Reviewer instruction
-
-Report the verdict **bound to `033b2ffb46674b2c0bcc5197273c109b461f62d9`** and state each check's
-observed result, including counts read from `pipeline-status.sh -f json` (never default text — it omits
-`clone`, D-33). If any check is unrunnable, **say so** — never substitute a passing variant. Attack
-outside this set and report anything it finds; RR7 and RR12 exist because the last blocker was found
-exactly that way.

docs/remediation/AC-RM61-TYPESTRICT.md

@@ -1,60 +0,0 @@
-# RM-61 / PR #1033 — PRE-REGISTERED ACCEPTANCE CHECKS: `exit_code` TYPE-STRICTNESS (D-40)
-
-**Registered by:** `mos-remediation` (orchestrator) — **BEFORE the fix was pushed and before any
-reviewer read a diff.** At registration time the fix existed only as an unpushed local commit
-(`6e7a336d`) on coder-mos1's machine which **I have not read**. There is therefore no diff for these
-checks to have been retrofitted to.
-
-**Subject head:** TBD — binds to the NEW head once coder-mos1 pushes. The prior head
-`033b2ffb46674b2c0bcc5197273c109b461f62d9` and its review 69 / pipeline #2193 go VOID on that push;
-that cost was accepted deliberately by Mos's BLOCKING ruling on D-40.
-
-**Ruling being enforced (Mos, 2026-08-01):** `exit_code` must be accepted ONLY as a real integer.
-`false`, `0.0`, `"0"`, and `null` must all fail to satisfy the exemption. Wrong-ACCEPT is the
-disqualifying direction; this hole sits inside the load-bearing discriminator.
-
-## ⚠ Read this before writing the tests — RED-FIRST HERE IS NOT UNIFORM
-
-Two of the four near-miss values **already block** at `033b2ffb`. Demanding "all four observed RED
-first" would be demanding an impossible red for two of them, and the predictable response to an
-impossible demand is a fudge — weakening something real to manufacture the red. So state it precisely:
-
-| value   | behaviour at `033b2ffb` (pre-fix) | what the new case is      |
-| ------- | --------------------------------- | ------------------------- |
-| `false` | **WRONGLY EXEMPTS** (exit 0)      | **genuine RED-FIRST**     |
-| `0.0`   | **WRONGLY EXEMPTS** (exit 0)      | **genuine RED-FIRST**     |
-| `"0"`   | correctly blocks (exit 1)         | **regression guard** only |
-| `null`  | correctly blocks (exit 1)         | **regression guard** only |
-
-Claiming red-first for `"0"` or `null` would be a false claim about your own evidence. Say which is
-which. **Do not weaken anything to make a green case go red** (D-8).
-
-## Checks
-
-| id       | check                                                                                                                                                           | verdict form                                                           |
-| -------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------- |
-| **TS1**  | ★RED-FIRST. `exit_code: false` on the real #2188 record is **observed wrongly exempting at `033b2ffb`** (exit 0, `exempted_steps 1`), then blocks after the fix | pre-fix ⇒0/exempt 1 · post-fix ⇒1/exempt 0                             |
-| **TS2**  | ★RED-FIRST. Same for `exit_code: 0.0`                                                                                                                           | pre-fix ⇒0/exempt 1 · post-fix ⇒1/exempt 0                             |
-| **TS3**  | REGRESSION GUARD. `exit_code: "0"` blocked before AND after — state honestly that it was already green                                                          | both ⇒1, `exempted_steps 0`                                            |
-| **TS4**  | REGRESSION GUARD. `exit_code: null` blocked before AND after                                                                                                    | both ⇒1, `exempted_steps 0`                                            |
-| **TS5**  | ★NOT OVER-TIGHTENED. The genuine artifact — real #2188, real integer `exit_code: 0`, correctly bound head — still passes                                        | ⇒0, `exempted_steps 1`, exactly one `WP-K8S-1000-CI-POSTGRES-TEARDOWN` |
-| **TS6**  | The strictness sits on the value the EXEMPTION rests on, not on a cosmetic sibling. Show the guarded comparison is the one feeding `exemption_applies`          | reviewer quotes the line                                               |
-| **TS7**  | `bool` is excluded EXPLICITLY, not incidentally. A bare `isinstance(x, int)` still admits `True`/`False` — verify the `not isinstance(x, bool)` clause exists   | ⇒ clause present; `true` also blocks                                   |
-| **TS8**  | Negative control unaffected: a genuine failed step with a real integer non-zero exit still blocks                                                               | ⇒1, `exempted_steps 0`                                                 |
-| **TS9**  | NO REGRESSION ON THE PRIOR ROUND'S BINDING WORK: mutated record commit ⇒1; `--expect-commit` omitted ⇒2; record `commit` absent ⇒1                              | ⇒1 / ⇒2 / ⇒1                                                           |
-| **TS10** | Signature conjunction NOT widened elsewhere by this fix — `POD_NOT_FOUND` / name / type / state untouched                                                       | diff-scoped ⇒ no widening                                              |
-| **TS11** | Still no fetch / trigger / retry / re-roll / sleep / network                                                                                                    | grep ⇒ no call sites                                                   |
-| **TS12** | Full harness passes at the new head; **state the case count** (12 previously, expected 16 — confirm the actual number rather than the expected one)             | ⇒0, count stated                                                       |
-
-## Reviewer instruction
-
-Verdict bound to the NEW head, evidence enumerated per check, CI counts from `pipeline-status.sh -f json`
-(never default text — it omits `clone`, D-33). If a check is unrunnable, **say so**; never substitute a
-passing variant.
-
-**Attack outside this set and report what you find.** Both blockers on this PR so far — the missing
-commit binding, and this type confusion — were found outside the registered set, by mutating a field
-nobody had registered a check for. That is now the expectation, not a bonus.
-
-**Nobody dispatching this review may state a conclusion on an open check here (D-39).** If you are sent
-an observation, it is an observation; the ruling is yours.

docs/remediation/BOARD-LEDGER.md

@@ -23,68 +23,3 @@ Merged PR #868 (`b79336a8`) shipped a file that FAILS `pnpm format:check` ⇒ th
 ### **D-4 / P-LIFECYCLE + hygiene — a dispatched agent silently IGNORED an in-message context reset.**
 
 planner-sol was at 64.3%/372k; the brief asked it to reset first; it began work on dirty context anyway. Only an out-of-band `/new` driven by the orchestrator guaranteed clean state. Confirms the postmortem thesis: **instructions are not enforcement.** Reset must be a mechanical pre-dispatch step, not a request.
-
-<!-- board-roll: 2 entries rolled from BOARD.md -->
-
-### **D-7 / P-FLEET-001 — stale-GC-on-disk: shared 30G /tmp hit 100% ENOSPC, degrading two seats.**
-
-~5.2G was session scratch dead 8-9 days (this session's own footprint: 88K). Same missing capability as orphaned-tmux-session GC, applied to disk — not a quota or discipline problem. Resolved manually by Mos (lead coordinator) after independent verification; `/tmp` now 79%. **The gap IS the finding:** the authority to reap exists, the deterministic reaper does not. Folded into RM-50 with explicit requirements (mechanical liveness, age threshold, dry-run, audit event per reap — never a heuristic sweep). Refusing to unilaterally delete another session's scratch was correct doctrine; the fix is a reaper, not braver agents.
-
-### **D-6 / P-QUEUE-001 — the mandated queue guard returned PASS on an UNKNOWN state, live, today.**
-
-Running the required `ci-queue-wait.sh --purpose push` before pushing produced `state=unknown ... exit 0` — the exact defect at `ci-queue-wait.sh:282-288` that PR #1023 is parked on. It also evaluated `branch=main` rather than the branch being pushed. The mission's own required pre-push gate passed me on an indeterminate result. Third independent live instance of the class.
-
-<!-- board-roll: 1 entry rolled from BOARD.md -->
-
-### **D-8 / P-CONFORMANCE-001 — a PRE-REGISTERED acceptance check that was not runnable as written.**
-
-PR #1025 AC2's fixture `mkdir -p apps/*/venv/lib` creates a literal `apps/*/venv/lib` dir when the glob is unmatched — it did not test what it claimed. rev-974 ran it exactly as written, caught it, re-ran the intended assertion at an explicit path, and **disclosed** rather than silently substituting a working fixture and reporting PASS. **Pre-registration protects a check from being retrofitted to the implementation; it does not make the check correct.** An unverified gate appeared inside the mechanism built to catch unverified gates. Hard requirement on RM-02: the registry must self-verify that every registered case runs AND can fail — presence is not evidence.
-
-<!-- board-roll: Decisions-log narrative rolled from BOARD.md 2026-08-01 (D-43: meet the
-     byte budget by ROLLING OUT, never by rewording what stays) -->
-
-### Decisions log — full record in [`TASKS.md`](./TASKS.md)
-
-All 44 findings (D-1…D-6 in `BOARD-LEDGER.md`, D-7…D-43 + D-38c in `TASKS.md`) and every ruling with its
-rationale live there. **Not duplicated here** — a second copy is a second thing to go stale, which this
-board had done three times in one night (gate list, capability registry, DECISION-1 status), and three
-more times by the next rotation seam (RM-61 "building", "nothing implemented yet", DECISION-1/2/3
-"must be ruled"). The rulings a fresh seat needs are items 4–7 above; they are **not** repeated here,
-because that repetition is what went stale.
-
-<!-- board-roll: Sequencing section rolled verbatim from BOARD.md 2026-08-01 (D-43: meet the
-     byte budget by ROLLING OUT, never by rewording what stays). Canonical: MISSION.md + TASKS.md §5 -->
-
-### Sequencing — see [`MISSION.md`](./MISSION.md)
-
-Builds 1-5, the cross-cutting retirements, and DECISION-1's corrected wire-in target are stated once in
-the charter and `TASKS.md` §5. **Not repeated here** — the previous copy of DECISION-1's status on this
-board is one of the six stale restatements below.
-
-<!-- board-roll: capability/seat-identity bullets rolled verbatim from BOARD.md 2026-08-01
-     (D-43: roll out, never reword). Authoritative home: TASKS.md D-11 / D-11a / D-11b. -->
-
-- Capability is **per-path** (D-11b → **superseded in part by D-13/D-15**): a token file is **necessary,
-  not sufficient**. Three layers — token file (raw-API), `tea` login (tea paths), **repository permission**
-  (writes). Before dispatch, assert `permissions.push == true` **as that seat**, not token existence and
-  not a 200 on a read. Mos owns provisioning; escalate missing pairs.
-- Seat identity (D-11a): token identity AND `git config user.name`/`user.email` must BOTH be set and
-  agree. Exporting `MOSAIC_GIT_IDENTITY` alone does NOT fix commit authorship.
-
-<!-- board-roll: D-26 gate-restatement rationale rolled verbatim from BOARD.md 2026-08-01 -->
-
-### Why the board must not restate the delivery gates (D-26)
-
-Restating the gate from memory is how the merge-gate step went missing from mission setup twice,
-once inside the correction for it (**D-26**).
-
-<!-- board-roll: Fleet seats rolled verbatim from BOARD.md 2026-08-01 (D-43: roll out, never
-     reword). NOTE: all these seats are UNMANAGED per D-41; `mosaic fleet ps` is live truth. -->
-
-## Fleet seats
-
-- mos-remediation — project orchestrator (Claude, /src/mosaic-stack, socket `mosaic-fleet`) — ACTIVE
-- planner-opus — adversarial planner (robustness), Opus 5, socket `default` — DELIVERED, idle
-- planner-sol — adversarial planner (pragmatic), gpt-5.6-sol, socket `default` — DELIVERED, idle
-- rev-974 — mosaicstack reviewer identity (id 16, write:repository) — idle, on call
-- Mos (mos-claude) — lead coordinator, socket `default` — relay path to Jason

docs/remediation/BOARD.md

@@ -1,85 +1,93 @@
 # mos-remediation — LIVE BOARD (keep < 8 KB)
 
-**Phase:** EXECUTING — **RM-02 keystone is the front**.
+**Phase:** EXECUTING — P0 open. RM-01 MERGED; RM-02 (keystone gate registry) is next.
-**Updated:** 2026-08-05 — successor seat live. D-56 state correction applied (lost round-5 dispatch,
+**Updated:** 2026-07-31 (mos-remediation orchestrator; seat active on `mosaic-fleet`).
-4 idle days); round-5 review then ran same day: verdict id 88 REQUEST_CHANGES @ `e910a45a`,
-remediation dispatched to `coder-mos2`. Review dispatches now always leave a durable PR comment.
-⚠ That was a **MANUAL pane respawn** (prior seat ~803k tokens): it validates the checkpoint+rehydration
-**design**, NOT a lifecycle **mechanism** — P-LIFECYCLE rotation does not exist yet (**D-41 / RM-62**).
 
 ## Head
 
-- Charter + 15 decisions + 4-build plan: `MISSION.md`. Backlog + all findings: `TASKS.md`.
+- Mission charter + 15 decisions + 4-build plan: PERSISTED (`docs/remediation/MISSION.md`).
-- Planning DONE (58 tasks, P0–P5). **DECISION-1/2/3 all RULED by Mos 2026-07-31** (`TASKS.md` §5) —
+- HOLD lifted for this workstream (Jason 2026-07-31). Nothing implemented yet — planning first.
-  nothing is waiting on a decision. D-2's availability _target_ is Jason-pending and non-blocking.
+- Orchestrator seat `mos-remediation` is LIVE and owns the mission. Residency attestation: PASS.
-- **Executing, not planning.** RM-01 is MERGED; three lanes are live (see In-flight).
+- **TASK-0 DONE** — checkout repaired, all three gates green HONESTLY (no `--no-verify`), branch pushed.
-- Orchestrator seat `mos-remediation` LIVE, owns the mission, resumed across the rotation seam
+- **TASK-1 DONE** — both planners delivered independently on clean context; reconciled into `TASKS.md`
-  2026-08-01 and re-attested to Mos from the files. Residency attestation: PASS.
+  (58 tasks across P0–P5, 7 convergences, 7 adjudicated disagreements, 3 escalated decisions).
+- **NEXT ACTION IS NOT MINE:** DECISION-1/2/3 (`TASKS.md` §5) must be ruled before P0 dispatch.
+  RM-01 is dispatchable immediately regardless — it depends on nothing and blocks everything.
 
 ## In-flight
 
-| Task                | Owner           | State                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |
+| Task                                | Owner           | State                                                                     |
-| ------------------- | --------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ----------------------------------- | --------------- | ------------------------------------------------------------------------- |
-| RM-01 checkout      | —               | **MERGED** `f58b3699` (#1027)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
+| RM-01 reproducible checkout         | —               | **MERGED** `f58b3699` (PR #1027) — rev-974 APPROVE + CI #2172 8/8 green   |
-| RM-03 queue guard   | Jason (re-sync) | ✅ **MERGED** `58b971ab` (#1032), #1019 closed. ⚠ **NOT DELIVERED**: installed guard still the broken one (291 lines / 0 `ASSERTED_NOT_READY` vs main 482 / 5). Re-sync via `mosaic upgrade`, then **prove it blocks a KNOWN-RED pipeline** — **D-51**                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
+| RM-02 gate registry ★keystone       | unassigned      | **READY** — depends only on RM-01; not held by RM-03                      |
-| RM-02 registry ★key | coder-mos2      | **ROUND-5 VERDICT id 88 REQUEST_CHANGES @ `e910a45a` (2026-08-05T22:37Z, live).** 2 blockers left: renderer accepts manifest-controlled `COMPATIBILITY `-prefixed provenance-success payloads; overclaim control is lexical-not-semantic vs docs claims. Shrink-together + evidence-subject CONFIRMED CLOSED — do not weaken. Remediation dispatched to `coder-mos2` 22:5xZ (PR comment + verified tmux); context guard: checkpoint at 85%. ⚠ **MERGE PRECONDITIONS (D-55/D-55f, measured):** poster=f10-coder (1 of 3 authors); (1) explicit `-m squash` (repo default `merge` discards ALL authorship); (2) **merger ≠ f10-coder** (self-merge suppresses the trailer generator → all 3 lost); (3) **the EXECUTING pr-merge.sh must contain `MergeMessageField` — merging #1066 is NOT sufficient** (deployed wrapper `08a65e85` = 0 refs, physically cannot emit; D-51's merged≠effective class inside the remedy; Mos-as-merger verifies wrapper sha256 before ANY trailer-dependent merge and refuses on `08a65e85`); (4) ✅ **CLOSED ON MEASUREMENT** — N=2 supplied non-poster trailers BOTH land, order preserved, poster line appended last (fixture prmerge-trailer-fixture#2 → `39db9d13`, #1030's exact shape; N=3+/poster-dup-dedup/Co-committed-by absence remain unmeasured but #1030 needs N=2). Merge decision resolved: all-land ⇒ merge as planned, three authors preserved. Trade in body; **branch MUST NOT be deleted**. ACs @ `dde38717` |
+| RM-03 queue guard (3 defects)       | —               | HOLD — #1023 SUPERSEDED-PENDING-JASON                                     |
-| RM-61 CI exemption  | —               | ✅ **MERGED** `f4fd5967` (#1033). #1034 closed; **#1000 stays OPEN** (retirement trigger). Exemption is on `main`                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
+| RM-59 close D-19 residual risk      | —               | BLOCKED by RM-12/RM-21/RM-25 (spine + executor) — tracked edge, not prose |
-| RM-59 / RM-60       | Jason (infra)   | tracked deps; RM-60 option **B**                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
+| `remediation/state` snapshot → main | mos-remediation | opening at this mission seam                                              |
-| #1023 queue attempt | Jason           | SUPERSEDED-PENDING-JASON — live REQUEST_CHANGES, do **not** merge                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
-
-### For the incoming orchestrator — read this before acting
-
-1. **Lane state lives in the In-flight table above — this item does NOT restate it.** It went stale
-   three times in one session by duplicating that table (D-26's class). Read the table. ⚠ **And
-   re-derive any board claim from the provider before load-bearing use (D-43)** — the board is
-   sole-written and has no independent verifier.
-2. **`docs/remediation/TASKS.md` is authoritative**, not the newest voice in a chat. It holds 58 findings
-   (D-1…D-6 in `BOARD-LEDGER.md`, D-7…D-55c + D-38c in TASKS.md), every ruling with its rationale, and the
-   requirements each finding placed on RM-02/RM-34/RM-50/RM-55.
-3. **`MISSION.md` carries the first-class principles** — read them there, they are not listed here.
-   Two added 2026-08-01: **the anchor must live outside the audited party's authority** (D-19/D-25/D-45,
-   third arrival) and **no universally-quantified check may pass over an empty set** (D-44/D-46).
-4. **Seat identity:** `export MOSAIC_GIT_IDENTITY=<seat>` is stripped by a context reset (**D-34**) —
-   every dispatch/rehydration brief must re-export it, or the seat cannot use its credentials.
-5. **Scan CI from `-f json`, never default text** — text mode omits `clone` (**D-33**). State counts.
-6. **The queue guard is zero-information until RM-03 merges** (**D-23**) — never cite its green.
-7. **The bounded CI re-roll used on RM-02 was a one-time stopgap, NOT policy.** A per-PR free re-roll is
-   D-21 normalisation. Do not repeat it; RM-61 is the fix.
-
-## Delivery gates — REFERENCE, do not restate
-
-Canonical: `~/.config/mosaic/fleet/roles.local/merge-gate.md` (verdict authority) +
-`~/.config/mosaic/fleet/roles/validator.md`. Order and the freeze/zero-information rules: `MISSION.md`
-and `KICKSTART.md`. **Read them there** (why: **D-26**, in `BOARD-LEDGER.md`).
 
 ## Fleet seats
 
-Roster rolled verbatim to [`BOARD-LEDGER.md`](./BOARD-LEDGER.md); live truth is `mosaic fleet ps`.
+- mos-remediation — project orchestrator (Claude, /src/mosaic-stack, socket `mosaic-fleet`) — ACTIVE
+- planner-opus — adversarial planner (robustness), Opus 5, socket `default` — DELIVERED, idle
+- planner-sol — adversarial planner (pragmatic), gpt-5.6-sol, socket `default` — DELIVERED, idle
+- rev-974 — mosaicstack reviewer identity (id 16, write:repository) — idle, on call
+- Mos (mos-claude) — lead coordinator, socket `default` — relay path to Jason
 
 ## Gate status
 
+- Delivery gates active: author≠reviewer, diff-blind pre-registered checks, CI-green, merged-PR completion.
 - Freeze: LIFTED for this workstream only.
-- Git identity: orchestrator runs `MOSAIC_GIT_IDENTITY=mos-dt-0` INTERIM. Mos ruled gate-16 HOLDS (author≠reviewer is what
+- Git identity: `MOSAIC_GIT_IDENTITY=mos-dt-0` INTERIM. Mos ruled gate-16 HOLDS (author≠reviewer is what
   gate-16 protects; rev-974 reviews, mos-dt-0 never self-reviews). Dedicated identity TRACKED, Mos provisions.
-- Capability + seat identity (**D-11b / D-11a**, incl. the false-NEGATIVE twin): authoritative in
+- Capability check (D-11b): before dispatching seat X to provider Y, verify
-  `TASKS.md`. Short form — **assert the DIFFERENTIAL as that seat** (authenticated `push:true` vs
+  `~/.config/mosaic/secrets/gitea-tokens/gitea-<Y>-<X>.token` exists. Token-file set = authoritative
-  unauthenticated `push:false`); a single endpoint can be true for anyone or 403 for an unrelated
+  capability registry. Mos owns provisioning; escalate missing pairs to him.
-  scope. Full text rolled to [`BOARD-LEDGER.md`](./BOARD-LEDGER.md).
+- Seat identity (D-11a): token identity AND `git config user.name`/`user.email` must BOTH be set and
-- ⚠ **LIVE HAZARD (D-37) — one shared `.git/config` re-identifies EVERY worktree at once.** Every seat,
+  agree. Exporting `MOSAIC_GIT_IDENTITY` alone does NOT fix commit authorship.
-  including `rev-974`'s review worktree, currently authors as **`coder-mos1`**; `MOSAIC_GIT_IDENTITY`
+- Standing worker-brief doctrine (accreted, mandatory in every brief): don't weaken a RED test to make
-  does **not** override it. **STANDING ORDER: commit with explicit
+  it pass; if a check is unrunnable as written SAY SO, never silently substitute; `agent-send -f` never
-  `git -c user.name=<seat> -c user.email=<seat>@…`, and NOBODY rewrites the shared config mid-flight.**
+  `-m`; heavy artifacts off shared `/tmp`.
-  Real fix authorised, Mos owns it, sequenced at a quiet seam. **#1024 implicated.** Detail: D-37.
-- Standing worker-brief doctrine (mandatory in EVERY brief): re-export `MOSAIC_GIT_IDENTITY` (**D-34**);
-  commit early/WIP (**D-31**); don't weaken a RED test to pass; if a check is unrunnable SAY SO, never
-  substitute; `agent-send -f` never `-m`; artifacts off shared `/tmp`; scan CI from `-f json` (**D-33**);
-  **relay observations into an open review, NEVER your own conclusion on an open check (D-39)**; the
-  **author never adjudicates their own PR's blocker status** — surface evidence, prepare the fix, hold.
 - Remote control: native `/remote-control` NOT wired in this runtime. Path is **Mos-relay**
   (Jason ↔ mos-claude via Discord ↔ mos-remediation via agent-send). Not a blocker.
 
-## Decisions log — full record in [`TASKS.md`](./TASKS.md)
+## Sequencing (from MISSION.md)
 
-All 58 findings (D-1…D-6 in `BOARD-LEDGER.md`, D-7…D-55c + D-38c in `TASKS.md`) and every ruling with
+1. Spine + choke-point service (MACP wiring @ mosaic_orchestrator.py::run_single_task) + PG/Redis
-its rationale live there. **Not duplicated here.** The history of _why_ this board must not restate —
+   ⚠ **CONTESTED — see DECISION-1.** Both planners independently reject this wire-in point: that
-six stale copies across two seams — is rolled verbatim into [`BOARD-LEDGER.md`](./BOARD-LEDGER.md).
+   controller is `"enabled": false` and references a dispatcher that does not exist here. Charter text
+   left UNCHANGED pending Mos/Jason ruling; do not treat it as settled.
+2. Rotation daemon (finish Mission Control Plane, reuse packages/coord)
+3. Comms service (envelope→service→PG/Redis→adapters)
+4. Hygiene + conformance harness
+   Cross-cutting retirements: flat-file tracking, 3 MACP islands, silent MOSAIC BYPASS.
+
+## Dogfood evidence — live failure classes, not hypotheticals
+
+> Newest first. Oldest entries roll to `BOARD-LEDGER.md` via `board-roll.sh` when this file
+> exceeds its 8 KB cap. Keystone detail is duplicated in `TASKS.md` §1a, so rolling loses nothing.
+
+<!-- BOARD-ROLL:START -->
+
+### **D-8 / P-CONFORMANCE-001 — a PRE-REGISTERED acceptance check that was not runnable as written.**
+
+PR #1025 AC2's fixture `mkdir -p apps/*/venv/lib` creates a literal `apps/*/venv/lib` dir when the glob is unmatched — it did not test what it claimed. rev-974 ran it exactly as written, caught it, re-ran the intended assertion at an explicit path, and **disclosed** rather than silently substituting a working fixture and reporting PASS. **Pre-registration protects a check from being retrofitted to the implementation; it does not make the check correct.** An unverified gate appeared inside the mechanism built to catch unverified gates. Hard requirement on RM-02: the registry must self-verify that every registered case runs AND can fail — presence is not evidence.
+
+### **D-7 / P-FLEET-001 — stale-GC-on-disk: shared 30G /tmp hit 100% ENOSPC, degrading two seats.**
+
+~5.2G was session scratch dead 8-9 days (this session's own footprint: 88K). Same missing capability as orphaned-tmux-session GC, applied to disk — not a quota or discipline problem. Resolved manually by Mos (lead coordinator) after independent verification; `/tmp` now 79%. **The gap IS the finding:** the authority to reap exists, the deterministic reaper does not. Folded into RM-50 with explicit requirements (mechanical liveness, age threshold, dry-run, audit event per reap — never a heuristic sweep). Refusing to unilaterally delete another session's scratch was correct doctrine; the fix is a reaper, not braver agents.
+
+### **D-6 / P-QUEUE-001 — the mandated queue guard returned PASS on an UNKNOWN state, live, today.**
+
+Running the required `ci-queue-wait.sh --purpose push` before pushing produced `state=unknown ... exit 0` — the exact defect at `ci-queue-wait.sh:282-288` that PR #1023 is parked on. It also evaluated `branch=main` rather than the branch being pushed. The mission's own required pre-push gate passed me on an indeterminate result. Third independent live instance of the class.
+
+<!-- BOARD-ROLL:END -->
+
+## Decisions log
+
+- 2026-07-31 — Mission set up by Mos post-postmortem (15/15 decided). Dogfood posture active.
+- 2026-07-31 — Mos: stale `.mosaic/orchestrator/mission.json` is RESIDUE of the disabled Python
+  orchestrator rail that this plan RETIRES. Do NOT invest in it; do NOT build on that rail. The 0/0
+  milestone banner is cosmetic. (Supersedes any plan to repair it.)
+- 2026-07-31 — Mos: planners must be dispatched with GUARANTEED clean context, not requested-clean.
+  Prior default-socket planner sessions predate this mission; dirty context is the indicted hygiene.
+- 2026-07-31 — mos-remediation: worker briefs forbid all git ops and restrict each worker to a single
+  named output file, so two planners can share one checkout without a branch race (M2-era incident doctrine).

docs/remediation/KICKSTART.md

@@ -25,18 +25,8 @@ mechanically until Build 3 (rotation) makes it automatic.
 ## Standing invariants (never violate)
 
 - **North star:** deterministic-right-answer → code/gate; LLM only for judgment.
-- **Delivery gates — REFERENCE the canonical files, never restate them:**
+- **Delivery gates:** author≠reviewer; PRE-REGISTERED diff-blind checks committed before reading the diff;
-  `~/.config/mosaic/fleet/roles.local/merge-gate.md` (verdict authority) and
+  CI terminal-green; completion = merged PR + closed issue. rev-974 = the mosaicstack reviewer identity.
-  `~/.config/mosaic/fleet/roles/validator.md` (validator role). Order:
-  independent review (author ≠ reviewer, `rev-974`; pre-registered diff-blind checks committed before the
-  diff is read) → remediation → **CI terminal-green at the exact head by full step scan** →
-  **merge-gate verdict `GO`/`NO-GO`/`HOLD`**, commit-bound and **void the instant the head moves**, posted
-  durably with enumerated evidence under its own minted identity → **coordinator head-pinned merge**.
-  The queue guard runs but is **zero-information until RM-03 lands** (D-23) and must not be cited as evidence.
-  **After a `GO`, freeze pushes** — even a doc tweak voids the verdict. The coordinator assigns the gate seat.
-- **Query for refutation, never for confirmation.** A subordinate asked to confirm a hypothesis will
-  agree — the bias is in the question, not the answerer, and agent seats are agreeable by construction.
-  State the hypothesis as yours, ask for the evidence that KILLS it, and reproduce when it matters.
 - **Dogfooding:** every fix validated against its live seed case (MISSION.md lists them).
 - **Tracking → DB** (hard cutover); do NOT re-invest in flat-file tracking. jarvis-brain PDA is off-limits.
 - **Git identity:** export `MOSAIC_GIT_IDENTITY=<your-seat>` so wrappers author correctly and survive respawn.

docs/remediation/MISSION.md

@@ -91,99 +91,6 @@ gate/program; the LLM handles only genuine judgment.
 > seat in the loop. Residual risk bound to **RM-59** (`depends_on: RM-12, RM-21, RM-25`), where the
 > choke-point executor and spine verify from _outside_ the worktree's authority.
 
-### First-class principle — query for refutation, never for confirmation
-
-> **A subordinate asked to confirm a hypothesis will agree. Ask it to refute, with evidence.**
->
-> The bias is induced by the **query**, not by the answerer's diligence. _"The DB flaked — please
-> confirm"_ and _"confirm or refute this, with the log line that proves it"_ are different instruments,
-> and they return different answers to the same question. The first harvests agreement; only the second
-> can return **"you are wrong, and here is why."**
->
-> This matters most with agent subordinates, which are **agreeable by construction**: fluent, eager to
-> be useful, and structurally disinclined to tell the dispatcher their premise is false. A confirmation
-> query aimed at one is close to a guaranteed yes — so the discipline cannot rest on the answerer being
-> rigorous. **It has to be built into how the question is asked.**
->
-> Promoted to the charter by Mos (2026-08-01). Origin: the orchestrator hypothesised that a coincident
-> `ci-postgres` failure caused a CI test failure and asked the implementing seat to **confirm or refute**
-> it. The seat **refuted it** with the log (`ci-postgres:5432 - accepting connections`, migrations
-> completed) and identified the real cause. Reproduction on an identical head then settled it. Had the
-> query been phrased for confirmation, the agreement would have been returned, **D-21 would have been
-> re-classified on a false premise**, and a banked finding would have been silently corrupted.
->
-> **Operationally:** state your hypothesis explicitly, mark it as yours, ask for _evidence that kills
-> it_, and say what evidence would change your mind. A hypothesis you cannot describe how to falsify is
-> not yet a hypothesis. Where the answer is consequential, **reproduce** rather than accept — two
-> independent runs beat one confident report.
-
-### First-class principle — the anchor must live outside the audited party's authority
-
-> **You cannot fix "the author controls X" by deriving X from something the author ALSO controls.**
-> Deriving merely **moves** the control point; it does not remove it.
->
-> Promoted to the charter by Mos (2026-08-01) on the **THIRD INDEPENDENT ARRIVAL** of the same
-> conclusion, each reached while trying to ship something else, each from a different direction:
->
-> | arrival           | the audited party controls…                                         | found as |
-> | ----------------- | ------------------------------------------------------------------- | -------- |
-> | manifest          | the tree that certifies its own generated state (same-UID, CWE-345) | **D-19** |
-> | sandbox           | the code that enters the sandbox, before the boundary exists        | **D-25** |
-> | **registry seam** | **WHEN the tracked path is introduced, hence the derived boundary** | **D-45** |
->
-> Round 1 the value was an author-settable **field**, so it was **derived**. Round 2 the derivation
-> depended on **when the author introduces the path**. Same authority, new costume. **Three
-> impossibility-derivations of one conclusion is not a coincidence to note — it is the strongest
-> architectural evidence this mission has produced**, and it is precisely what **forces Builds 1–2**
-> rather than making them a preference.
->
-> **Operationally:** anchor to a reference the audited party cannot move. A git **merge-base against
-> `main`** is such a reference for a PR author (they own their branch; they do not own `main`).
-> **State the bootstrap in BOTH directions (D-19):** that anchor is sound against an author who cannot
-> rewrite `main` — the threat in scope — and **NOT** sound against an attacker who can. **That residual
-> is what Builds 1–2 close, and it must be recorded as a tracked dependency, never implied.**
-
-### First-class principle — no universally-quantified check may pass over an empty set
-
-> **"All registered cases ran" is VACUOUSLY TRUE when there are no registered cases.**
-> **Non-emptiness and anchoring are PRECONDITIONS asserted before the quantified check runs — not
-> properties hoped for after it.**
->
-> Promoted by Mos (2026-08-01) after the identical vacuity appeared **twice, at two different levels**:
-> `activationCommit = HEAD` emptied the **commit range** (D-44), and an emptied manifest — `criteria`,
-> `gates`, `proseClaims`, `compatibilityScenarios` all `[]` — emptied the **registry population**
-> (D-46), each yielding **exit 0**. The first was fixed **as an instance**; the principle was never
-> extracted, **so it returned one level up.**
->
-> **Delete every gate and every criterion TOGETHER and no remaining reference complains — because every
-> reference went with them.** A check that quantifies over a population must actually **range** over it,
-> and that population must be **provably complete and non-empty**.
->
-> **Corollary (same disease):** a clause written for the instance that produced it is not a clause.
-> **Do not relabel the originating instances as the general clauses** — quantify over the population.
-
-### First-class principle — redundant observation on evidence-bearing steps
-
-> **Two observers of the same evidence, disagreeing, catch what neither catches alone.** Apply redundancy
-> not only to judgement calls but to **evidence gathering itself** — the step everyone assumes is
-> mechanical and therefore skips.
->
-> Promoted by Mos (2026-08-01) from **D-33**. A seat scanned a pipeline with `-f json` and reported 9
-> steps; the orchestrator scanned the same pipeline in the wrapper's default text mode and reported 8.
-> **The default output omits `clone`.** Every "full step scan" that night had been 8-of-9 and was stated
-> as complete in good faith. No verdict changed — but the _method_ was wrong, invisibly, and **only the
-> disagreement between two counts surfaced it.**
->
-> The reason it survived: **a summary that resembles an enumeration is more dangerous than one that
-> obviously summarises.** A labelled list of named steps with states _looks_ like the artifact, so nobody
-> checks it against the record. Compare D-24 — `mergeable` was a _true answer to a different question_;
-> this was a _true answer to a smaller one_. Neither is a lie; both pass every sniff test.
->
-> **Operationally:** where a step _produces evidence a decision rests on_, have it produced twice by
-> different means, and treat **any divergence as a finding rather than as noise to reconcile**. Prefer the
-> machine-readable record over the human-readable rendering — _read the artifact, not the summary_ — and
-> state the counts observed so a divergence is detectable at all.
-
 ## Decision record (authoritative, immutable)
 
 - **15/15 proposals decided: 13 accept, 2 modify (P-AUTHORITY-001, P-INBOX-001), 0 reject.**
@@ -202,31 +109,6 @@ gate/program; the LLM handles only genuine judgment.
 | **4. Comms service**                                         | AUTHORITY, INBOX (+ versioning roadmap) | Envelope (comms/v1) → sole-path service → PG/Redis → pluggable adapters (tmux→Matrix/Discord/Slack/Telegram). Version the protocol, not participants.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |
 | **+ Hygiene & proof**                                        | FLEET, WORKFLOW, CONFORMANCE            | One roster-owned socket/host + stale GC; allowlist auto-sync; the conformance harness that fault-injects the failure classes and proves builds 1–4 hold.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
 
-## Why Builds 1–2 are necessary — two independent impossibility proofs
-
-**The choke-point executor and PG spine are not a design preference. They are forced.** Twice during
-the mission's own first deliveries, work stopped against a security property that **cannot exist** at
-the layer that needed it — and both times the only resolution was an authority _outside_ the audited
-party's control, which is precisely what Builds 1–2 provide.
-
-|                         | the audited party controls…                                                                                                  | so what fails   | found as |
-| ----------------------- | ---------------------------------------------------------------------------------------------------------------------------- | --------------- | -------- |
-| **Artifact integrity**  | the manifest that certifies its own generated tree (same-UID write ⇒ regenerate manifest _and_ marker consistently, CWE-345) | tamper-evidence | **D-19** |
-| **Execution integrity** | the code that enters the sandbox (PR-controlled config executes _before_ the boundary exists)                                | isolation       | **D-25** |
-
-Both reduce to one sentence:
-
-> **Self-verification by the audited party is not verification.**
-
-And to one consequence: **the anchor must live outside the audited party's authority.** A local check
-cannot defend against an actor who can rewrite the check; a repo cannot grant a capability to
-PR-controlled config and simultaneously prevent that config from using it.
-
-**An architecture forced by two independent impossibility proofs is stronger evidence than one argued
-for.** Neither proof was sought — both arrived while trying to ship something else, from different
-directions (a symlink manifest; a CI sandbox), at different layers. RM-59 and RM-60 are the two tracked
-dependencies this creates, and they are the same dependency in different clothes.
-
 ## The finding that sets the cost
 
 **Built-but-unwired disease.** `@mosaicstack/macp` is stranded (nothing calls it); `packages/coord` primitives
@@ -279,29 +161,6 @@ orphaned context loader, a fail-open bypass. **Work = wire + consolidate + retir
 - **Project orchestrator** `mos-remediation` (this seat) owns the mission; coordinates under Mos (lead).
 - **Adversarial task decomposition:** `planner-opus` (robustness) + `planner-sol` (pragmatic) each decompose
   the plan independently; orchestrator reconciles into `TASKS.md`/DB tasks. Oppositional by design.
-- **Delivery gates — REFERENCE, do not restate.** The authoritative definitions live at
+- **Delivery gates (non-negotiable):** author≠reviewer, PRE-REGISTERED diff-blind acceptance checks committed
-  [`~/.config/mosaic/fleet/roles.local/merge-gate.md`](file:///home/hermes/.config/mosaic/fleet/roles.local/merge-gate.md)
+  before reading the diff, CI terminal-green, completion = merged PR + closed issue. rev-974 = mosaicstack reviewer.
-  (verdict authority) and
-  [`~/.config/mosaic/fleet/roles/validator.md`](file:///home/hermes/.config/mosaic/fleet/roles/validator.md)
-  (validator/certificate role). **Read them; do not paraphrase them.** Restating an authoritative source
-  is lossy every time — see D-26, where a subset restated from memory dropped a security precondition.
-
-  **Gate order** (the sequence only; the definitions are in the files above):
-  1. Independent review, **author ≠ reviewer** (`rev-974` on mosaicstack), with PRE-REGISTERED diff-blind
-     acceptance checks committed before the diff is read
-  2. Remediation of findings
-  3. **CI terminal-green** at the exact full-40 head, by **full step scan**
-  4. **Merge-gate verdict — `GO` / `NO-GO` / `HOLD`** (class `merge-gate`; "Ultron" is an _instance name_,
-     display data, never an authority source). **Bound to a commit and VOID the instant the head moves.**
-     `HOLD` persists until replaced; a `NO-GO` answered by an empty commit must be re-issued as `NO-GO`.
-     Posted durably on the PR under the gate's own minted identity, **enumerating** its evidence — a bare
-     "GO — gates verified" is non-conforming.
-  5. **Coordinator merge**, head-pinned. The gate never merges; it holds `push=False` by design.
-
-  ⚠ **The CI queue guard runs but is ZERO-INFORMATION until RM-03 lands** (D-23: it returns pass for every
-  possible input). It must not be cited as evidence by any gate, including the coordinator's own merge path.
-
-  **Assignment:** the coordinator assigns the merge-gate seat; the orchestrator does not. The orchestrator
-  owns getting a PR _gate-ready_.
-
 - **Compaction survival:** see `KICKSTART.md` in this dir — the resume procedure. Persist typed state, not transcript.

docs/scratchpads/1000-rm-61-ci-contract-exemption.md

@@ -0,0 +1,118 @@
+# RM-61 — CI contract exemption for #1000 teardown artifact
+
+**Tracking:** RM-61 / issue #1000
+
+**Branch:** `fix/rm-61-ci-contract-exemption`
+**Owner:** `coder-mos1`
+
+## Objective
+
+Determine, by red-first provider controls, whether the `ci-postgres` pod-not-found teardown signature discriminates from a real PostgreSQL failure. Only if it discriminates may a named, bounded CI-contract exemption be implemented. The exemption must retire when #1000 is fixed; fixing #1000 is the closure path.
+
+## Pre-registered kill criterion
+
+If an injected real `ci-postgres` failure also yields `pods "wp-svc-<ULID>-ci-postgres" not found` as the service's provider-visible failure, the signature does not discriminate. Option B is unsafe; stop exemption implementation and fall to Option A (#1000).
+
+## Plan
+
+1. Capture full `-f json` records for the 11 supplied observations and state counts.
+2. Run one startup-failure control using the real pgvector/PostgreSQL image with an invalid `initdb` argument.
+3. Run one post-readiness crash control using real PostgreSQL, `pg_isready`, and a deliberate postmaster kill while a DB-dependent probe is active.
+4. Compare the raw `ci-postgres` service record independently of failures in dependent steps.
+5. Investigate runner/time/head clustering only as a hypothesis; never encode incidental correlates or retries into policy.
+6. If and only if the controls discriminate, implement and test the exact exemption, document its two-way boundary, and track retirement at #1000.
+
+## Budget
+
+No explicit token cap supplied. Working estimate: 20K–30K tokens. Limit provider controls to the two pre-registered runs; no retries or re-roll policy.
+
+## Initial evidence
+
+Historical JSON saved locally under `.evidence/rm-61/` (not for commit). Supplied pipelines: 11 total. Child-step counts: five pipelines with 9 children and six with 10 children. Seven contain the `ci-postgres` pod-not-found failure (#2170, #2175, #2180, #2181, #2182, #2187, #2188); four do not (#2158, #2167, #2184, #2186). Every observed workflow reports `agent_id=44`, so the available JSON does not separate clean and artifact runs by runner. This refutes runner identity as a discriminator in the sampled record.
+
+## Progress
+
+- [x] Requirements and kill criterion recorded before control implementation.
+- [x] Historical full-JSON records captured.
+- [x] Startup-failure control observed terminal.
+- [x] Post-readiness crash control observed terminal.
+- [x] Discrimination verdict recorded: Option B may proceed.
+- [x] Conditional exemption implementation.
+
+## Tests / evidence
+
+### Control 1 — real startup failure
+
+- Commit: `3931b0e29eb834914f7b17e4db7e221481d436fa`
+- Pipeline: #2189, exact commit match.
+- Full JSON child scan: 9 total — 7 success, 2 failure, 0 skipped/pending/running.
+- `ci-postgres`: `state=failure`, `exit_code=1`, `error=null`, with a five-second execution window.
+- `test`: `state=failure`, `exit_code=1` after the readiness budget expired.
+- Pipeline/workflow: terminal `failure`.
+
+This control is red and its service record differs from #1000 (`exit_code=0` plus pod-not-found). It proves the startup-failure direction only. It does not settle the dangerous post-readiness crash/garbage-collection path.
+
+### Control 2 — real post-readiness crash
+
+- Commit: `25ac59715a94dd1b52ef42577472eb44ecc4b446`
+- Pipeline: #2191, exact commit match.
+- Full JSON child scan: 9 total — 7 success, 2 failure, 0 skipped/pending/running.
+- Service log proves PostgreSQL reached `database system is ready to accept connections`, the test created the arm table, and the service then killed postmaster PID 7.
+- Test log proves a successful `SELECT 1` followed by `Connection refused`; it exited the pre-registered control code 61.
+- `ci-postgres`: `state=failure`, `exit_code=137`, `error=null`, with a 203-second execution window.
+- `test`: `state=failure`, `exit_code=61`.
+- Pipeline/workflow: terminal `failure`.
+
+This is the dangerous post-readiness crash path. Its service record is not pod-not-found and therefore differs from #1000 independently of the dependent test failure.
+
+### Discrimination verdict
+
+Both real failures are provider-visible as process exits (`exit_code=1` startup; `exit_code=137` crash) with no pod-not-found error. The seven observed #1000 artifacts are provider reconciliation misses (`exit_code=0` plus the exact pod-not-found error). The declared kill criterion did not fire, so Option B may proceed with a matcher requiring the full conjunction. This evidence does **not** prove every future Kubernetes failure is distinguishable; it proves these two concrete real-failure classes remain blocking and bounds the exemption to the observed reconciliation shape.
+
+### Unit red-first checkpoint
+
+The nine-case contract harness was written before the verifier. First execution exited 1 because `verify-terminal-green.py` did not exist; no exemption implementation was live. Cases pre-register ordinary green, the exact artifact, both provider controls, near-miss signatures, an independent failure, and a skipped step.
+
+### Control 2 setup attempt — invalid, excluded from evidence
+
+- Commit: `9455cd6a2650b2b7e70f746c07933d96e5cb3d20`
+- Pipeline: #2190, exact commit match.
+- Full JSON child scan: 9 total — 7 success, 2 failure, 0 skipped/pending/running.
+- Service log: `/bin/sh: 0: -c requires an argument`.
+- Root cause: Woodpecker service `commands` did not become the third `sh -c` argument. PostgreSQL never started, so this run is **not** the post-readiness crash control and provides no discrimination evidence.
+- Focused remediation: place the script directly in the third `entrypoint` element and supply `PGPASSWORD` for the marker query. This is a control-fixture correction, not a retry of #1000 and not evidence for either verdict.
+
+## Implementation evidence
+
+- `verify-terminal-green.py` consumes only the full JSON/API record; it performs no fetch, retry, or trigger.
+- Exact #2188 record: exit 0, 10 children, 9 success + 1 named exemption.
+- Historical set: #2158/#2167/#2184/#2186 pass with no exemption; #2170/#2175/#2182/#2187/#2188 pass with one named exemption; #2180/#2181 remain red because independent failures exist.
+- Provider controls: #2189 and #2191 both exit 1 under the verifier; neither is exempted.
+- Unit harness: initial 9/9 cases passed after the red-first checkpoint; review remediation expands this to 12 cases with expected-head match/missing/mismatch coverage.
+- Test-membership guard: PASS, population 45; 26 enumerated, 19 signed exclusions; all 39 surface paths present.
+- Python compile: PASS.
+- `pnpm typecheck`: PASS, 45/45 tasks.
+- `pnpm lint`: PASS, 25/25 tasks.
+- `pnpm format:check`: PASS after moving local evidence outside the repository tree.
+- `test:framework-shell`: RM-61 and all preceding suites passed, then the pre-existing wake assertion aborted with exit 97 because this host's Bash 5.2.15 reports `BASH_LINENO [3 5]` where that suite requires `[3 4]`. RM-61 does not modify the wake suite; the command is not fully runnable on this host as written and no substitute result is claimed.
+
+## Independent review
+
+- Review 67 / comment 20403 at exact head `e7b29219e11efd0a19395156ac0b154bec0c3a73`: **REQUEST CHANGES**.
+- Blocker: the verifier echoed the pipeline commit but did not bind it to the current PR head; mutating only #2188's commit still returned terminal-green.
+- Remediation: require `--expect-commit <full-40>`, add a pipeline anomaly on missing/mismatched record commits, emit expected and observed values, wire both CI documentation and the merge-gate baseline to pass provider PR head, and add match/missing/mismatch tests.
+- This binding is not prohibited head-based clustering policy: it proves the evidence belongs to the commit under verdict. Runner/node/time/head correlation remains excluded from the teardown signature itself.
+- Review 69 later approved the commit-binding remediation at exact head `033b2ffb46674b2c0bcc5197273c109b461f62d9`; pipeline #2193 was 9/9 success. Before merge-gate, an independent adjudicator found that Python treats JSON `false == 0`, allowing a non-integer exit value to match. The prior gate-ready state was withdrawn. The type-strict set distinguishes genuine red-first controls (`false`, `0.0`, which wrongly exempted) from regression guards (`true`, `"0"`, `null`, which already blocked). Remediation requires the decoded type to be exactly `int` and excludes `bool` explicitly.
+
+## Documentation checklist
+
+- [x] CI contract documented in the canonical framework CI/CD guide.
+- [x] Operator command documented in the Woodpecker tool README.
+- [x] Merge-gate baseline points to the deterministic verifier and named retirement.
+- [x] Tracking and retirement cite issue #1000.
+- [x] Both positive and negative guarantee boundaries are stated.
+- [x] No API/auth/schema/user-facing navigation change; OpenAPI, user guide, and sitemap are not applicable.
+
+## Risks
+
+The controls establish discrimination for deterministic startup failure and an armed post-readiness postmaster crash on the current Woodpecker Kubernetes provider. They cannot prove that every future Kubernetes failure mode will preserve a non-zero exit before reconciliation. The exact matcher minimizes that residual risk, and issue #1000 remains the mandatory provider-seam closure and retirement trigger.

docs/scratchpads/462-fed-m3-06-get-verb.md

@@ -0,0 +1,38 @@
+# Scratchpad — FED-M3-06 get verb
+
+## Objective
+
+Implement `POST /api/federation/v1/get/:resource/:id` for M3 inbound federation reads.
+
+## Scope
+
+- `apps/gateway/src/federation/server/verbs/get.controller.ts`
+- `apps/gateway/src/federation/server/verbs/get-query.service.ts`
+- Unit coverage for controller pipeline + query service RBAC guardrails
+- Register controller/service in `FederationModule`
+
+## Plan
+
+1. Mirror the list verb pipeline: `FederationAuthGuard` → `FederationScopeService` → read-only query service.
+2. Return one `_source: "local"` tagged item on success.
+3. Return federation error envelopes:
+   - `404 not_found` when the resource id does not exist.
+   - `403 scope_violation` when the row exists but falls outside native RBAC/scope intersection.
+   - `400 invalid_request` for malformed ids/scope requests.
+4. Keep read audit persistence deferred to M4; no body or response persistence in M3.
+
+## Verification Evidence
+
+- Rebased onto `origin/main` at `86e106fcc9a1dfa3a18f7846bb477be128794aad` after M3-05 merged; resolved `FederationModule` by registering both list and get verb controllers/services.
+- Review-change coverage added for comment 15971:
+  - get note access now requires subject ownership AND authorized mission intersection.
+  - missing federation context returns structured `401 unauthorized` envelope.
+  - unsupported get resources fail closed with structured denial.
+  - PGlite regressions cover cross-user note exclusion and subject-note unauthorized-mission exclusion.
+- `pnpm --filter @mosaicstack/gateway test -- src/federation/server/verbs/__tests__/get.controller.spec.ts src/federation/server/verbs/__tests__/get-query.service.spec.ts` — pass (2 files / 17 tests; re-run after review changes).
+- `pnpm --filter @mosaicstack/gateway build` — pass (re-run after review changes).
+- `pnpm build` — pass (23 successful tasks before review changes).
+- `pnpm typecheck` — pass (41 successful tasks; re-run after review changes).
+- `pnpm lint` — pass (23 successful tasks; re-run after review changes).
+- `pnpm format:check` — pass (re-run after review changes).
+- `~/.config/mosaic/tools/codex/codex-code-review.sh --uncommitted` — approve, 0 findings after review changes.

docs/scratchpads/B1-next-durable-publish-design.md

@@ -0,0 +1,82 @@
+# B1 / @next Durable Publish Pipeline — Design
+
+## Objective
+
+Make `next` a durable integration line that publishes the artifacts required by downstream federation boot tests without manual builds.
+
+Every merge to `next` publishes:
+
+1. **npm prerelease packages** to the Gitea npm registry with dist-tag `next`.
+2. **Gateway container image** tagged only as `gateway:sha-<short>`.
+
+The existing stable release behavior remains isolated to `main` / tags.
+
+## Registry verification
+
+Target registry: `https://git.mosaicstack.dev/api/packages/mosaicstack/npm/`.
+
+Pre-implementation checks:
+
+- `npm view @mosaicstack/mosaic dist-tags --registry https://git.mosaicstack.dev/api/packages/mosaicstack/npm/ --json` returned a dist-tags object (`latest: 0.0.48`).
+- `npm view @mosaicstack/mosaic@latest version --registry https://git.mosaicstack.dev/api/packages/mosaicstack/npm/` resolved `0.0.48`.
+- `@next` currently returns 404 because no `next` dist-tag exists yet; this is expected before the first next prerelease publish.
+
+Pipeline design includes a post-publish verification that `npm view @mosaicstack/mosaic@next version` resolves to the exact CI-computed prerelease version. If Gitea fails to honor the `next` dist-tag, the pipeline fails closed.
+
+## Version scheme
+
+The prerelease version is computed at publish time only; no `package.json` version changes are committed.
+
+For each non-private `@mosaicstack/*` package:
+
+```text
+<target-stable>-next.<CI_PIPELINE_NUMBER>
+```
+
+Where:
+
+- `CI_PIPELINE_NUMBER` is Woodpecker's monotonic pipeline number.
+- `target-stable` is the package's current committed stable version with the patch component incremented.
+  - Example: `@mosaicstack/mosaic` `0.0.48` publishes as `0.0.49-next.1626`.
+  - Example: `@mosaicstack/gateway` `0.0.6` publishes as `0.0.7-next.1626`.
+
+Rationale:
+
+- npm semver sorts `0.0.49-next.1627` above `0.0.49-next.1626`.
+- The prerelease does not overtake the future stable `0.0.49`.
+- The monotonic pipeline number avoids conflicts across repeated `next` merges.
+
+## Branch and tag guardrails
+
+| Pipeline path         | Branch/event                   | Publishes                                               | Forbidden              |
+| --------------------- | ------------------------------ | ------------------------------------------------------- | ---------------------- |
+| stable npm publish    | `main` push/manual or tag      | package versions already committed in package manifests | `@next` dist-tag       |
+| next npm publish      | `next` push/manual only        | CI-computed prereleases with `--tag next`               | `latest` dist-tag      |
+| gateway image         | `main` push/manual or tag      | `sha-<short>` + `latest` on main + tag on tag events    | next prerelease npm    |
+| gateway image         | `next` push/manual only        | `sha-<short>` only                                      | `latest`               |
+| appservice/web images | `main` push/manual or tag only | existing stable image behavior                          | next image publication |
+
+The pipeline has explicit branch checks inside the publish commands as a second fail-closed layer beyond Woodpecker `when` clauses.
+
+## Implementation plan
+
+1. Widen `.woodpecker/publish.yml` top-level `when` to include `next` so the publish pipeline runs on next merges.
+2. Keep existing `publish-npm` on `main` / tags only.
+3. Add `publish-next-npm` for `next` push/manual only:
+   - configure Gitea npm auth from existing `gitea_token` secret as `NPM_TOKEN`;
+   - preflight registry dist-tag metadata;
+   - compute prerelease versions in CI by temporarily editing package manifests in the workspace;
+   - run `pnpm publish ... --tag next` against non-private `@mosaicstack/*` packages;
+   - verify `@mosaicstack/mosaic@next` resolves to the computed version.
+4. Split image `when` anchors:
+   - `image_build_when` includes `next` and is used by `build-gateway`;
+   - `main_image_build_when` keeps appservice/web on main/tags only.
+5. Keep gateway next image destinations to `sha-<short>` only; no `latest` on next.
+
+## Risk controls
+
+- Auth/registry failures are fatal.
+- No manual image build/push path is introduced.
+- No production `latest` tags are touched from `next`.
+- No `@latest` npm dist-tags are touched from `next`.
+- All changes live in CI config and docs; no runtime source behavior changes.

docs/scratchpads/B2-skills-sync-path.md

@@ -0,0 +1,34 @@
+# B2 — Fresh-install skills sync path
+
+## Problem
+
+Greenfield wizard on `next` reported:
+
+```text
+Skills sync script not found at ~/.config/mosaic/bin/mosaic-sync-skills
+Skills: install failed
+```
+
+## Diagnosis
+
+The framework install migration removed the legacy `~/.config/mosaic/bin/` directory and now installs framework helper scripts under:
+
+```text
+~/.config/mosaic/tools/_scripts/
+```
+
+`packages/mosaic/src/stages/finalize.ts` still resolved wizard helper scripts from `mosaicHome/bin`, so wizard-selected skills failed even though `mosaic-sync-skills` was present in the current framework layout.
+
+## Fix
+
+- Resolve framework helper scripts through `tools/_scripts/<name>` first.
+- Keep a legacy `bin/<name>` fallback for pre-migration installs.
+- Point missing-script warnings at the current `tools/_scripts` layout.
+- Update the finalize skills test fixture to model the fresh framework layout.
+- Update framework README examples from legacy `bin/` helper paths to `tools/_scripts/`.
+
+## Verification
+
+- Unit: `pnpm --filter @mosaicstack/mosaic test -- finalize-skills`
+- Gates: `pnpm typecheck`, `pnpm lint`, `pnpm format:check`, `pnpm build`
+- Fresh path: ran `packages/mosaic/framework/install.sh` with a temp `MOSAIC_HOME` and `MOSAIC_SYNC_ONLY=1`; verified `tools/_scripts/mosaic-sync-skills` exists, legacy `bin/mosaic-sync-skills` does not, and the script installs a selected fake `lint` skill into Mosaic + Pi runtime skill directories.

docs/scratchpads/B3-wizard-gateway-health-order.md

@@ -0,0 +1,36 @@
+# B3 — Wizard completion ordering
+
+## Problem
+
+The wizard printed the success summary / `Mosaic is ready.` during `finalizeStage`, before the gateway configuration stage had completed its daemon health check. If the gateway health gate later failed, the user could see a success claim followed by a gateway failure.
+
+## Diagnosis
+
+`finalizeStage` handled both mutation work and terminal success messaging. Wizard paths then ran `gatewayConfigStage` and `gatewayBootstrapStage` afterward:
+
+1. finalize writes config, links runtime assets, syncs skills, runs doctor;
+2. finalize prints `Installation Summary` + `Mosaic is ready.`;
+3. gateway config starts/waits for daemon health;
+4. gateway bootstrap runs.
+
+The summary needed to be deferred until after the gateway readiness gates.
+
+## Fix
+
+- `finalizeStage` now returns a `showSummary()` callback and supports `deferSummary`.
+- Wizard/quick-start paths call finalize with `deferSummary: true`.
+- `showSummary()` is called only after gateway config reports ready and bootstrap completes, or immediately when the caller explicitly skips gateway setup.
+- If gateway health/config reports not ready, the wizard returns/aborts without printing the success summary.
+- Folded in adjacent runtime install hint fix for Pi: `curl -fsSL https://pi.dev/install.sh | sh`.
+
+## Verification
+
+- Added unified-wizard coverage for summary-after-health and no-summary-on-health-failure.
+- Targeted: `pnpm --filter @mosaicstack/mosaic test -- unified-wizard finalize-skills`
+- `pnpm format:check`
+- `pnpm typecheck`
+- `pnpm lint`
+- `pnpm build`
+- `pnpm test`
+- Codex code review: approve.
+- Codex security review: one low finding on the requested Pi `curl | sh` install hint; no security finding in the wizard completion-ordering change.

docs/scratchpads/B4-wizard-step-dedup.md

@@ -0,0 +1,36 @@
+# B4 — Wizard step deduplication
+
+## Problem
+
+Greenfield wizard testing showed completed wizard steps could be executed again after the menu marked them `[done]`. In practice this made the Providers/API-key flow and Skills flow appear twice in one wizard run.
+
+There was a second related API-key duplication path: when the Providers step was completed with no key, `gatewayConfigStage` still prompted for `ANTHROPIC_API_KEY` during Finish because it only skipped the gateway API-key prompt when `providerKey` was non-empty.
+
+## Diagnosis
+
+- `runMenuLoop` labeled completed sections with `[done]`, but still dispatched the selected step again if the user selected that row.
+- Quick Start ran Providers and Skills but did not mark those sections complete in `completedSections`.
+- `runFinishPath`/`quickStartPath` defaulted `providerType` to `none` for gateway config, which made it impossible for `gatewayConfigStage` to distinguish:
+  - provider step completed and user intentionally skipped the key, vs.
+  - provider step was never run.
+
+## Fix
+
+- Added a shared menu section key helper and a completed-step guard in `runMenuLoop`.
+- Completed menu steps now log a skip message instead of re-running their stage.
+- Quick Start marks Providers and Skills complete after running them.
+- Finish/Quick Start now pass `state.providerType` as-is to gateway config instead of defaulting to `none`.
+- `gatewayConfigStage` treats `providerType: 'none'` as an explicit completed provider setup with no key and skips the second gateway API-key prompt.
+
+## Verification
+
+- Added unified wizard regression coverage asserting repeated Providers/Skills menu selections only execute each stage once.
+- Added gateway config coverage asserting `providerType: 'none'` does not prompt for a gateway API key and writes no API key env var.
+- Targeted: `pnpm --filter @mosaicstack/mosaic test -- unified-wizard gateway-config`
+- `pnpm format:check`
+- `pnpm typecheck`
+- `pnpm lint`
+- `pnpm build`
+- `pnpm test`
+- Codex code review: approve.
+- Codex security review: no findings.