Compare commits

..
Author SHA1 Message Date
ms-lead-reviewer 3831d5e377 docs(#834): document T-C branch protection posture
ci/woodpecker/pr/ci Pipeline was successful
2026-07-19 22:52:50 -05:00
337 changed files with 1171 additions and 52536 deletions
-1
View File
@@ -8,7 +8,6 @@ coverage
.env.local
*.tsbuildinfo
.pnpm-store
__pycache__/
docs/reports/
# Step-CA dev password — real file is gitignored; commit only the .example
+1 -1
View File
@@ -1 +1 @@
pnpm preflight && pnpm typecheck && pnpm lint && pnpm format:check
pnpm typecheck && pnpm lint && pnpm format:check
+4 -4
View File
@@ -1,5 +1,5 @@
@mosaicstack:registry=https://git.mosaicstack.dev/api/packages/mosaicstack/npm/
# HOME resolves to /root in the ci-base image, preserving its warmed-store path.
# Non-root checkouts use their own HOME. Override without editing this file via
# NPM_CONFIG_STORE_DIR (pnpm's environment form of the store-dir setting).
store-dir=${HOME}/.local/share/pnpm/store
# Pin the pnpm store to the same path the ci-base image warms (Dockerfile.ci),
# so the pipeline `pnpm install --prefer-offline` consumes the baked store
# instead of repopulating a fresh one.
store-dir=/root/.local/share/pnpm/store
-9
View File
@@ -4,15 +4,6 @@ pnpm-lock.yaml
**/node_modules
**/drizzle
**/.next
# Python build/test artifacts — same category as node_modules/dist/.next above.
# Prettier must never scan generated trees; without these a local venv poisons
# `pnpm format:check` with thousands of third-party files.
**/venv
**/__pycache__
**/.mypy_cache
**/.pytest_cache
**/htmlcov
.claude/
docs/tess/TASKS.md
docs/scratchpads/
packages/mosaic/src/fleet/testdata/documentation-publication-v1/inline-migration-v1.json
-11
View File
@@ -41,11 +41,6 @@ steps:
# (Constitution + dispatcher + each RUNTIME.md slice). See DESIGN §7 / R9.
- bash packages/mosaic/framework/tools/quality/scripts/check-resident-budget.sh --self-test
- bash packages/mosaic/framework/tools/quality/scripts/check-resident-budget.sh
# Test-membership guard (#1017): also first link of test:framework-shell.
# Invoked from BOTH surfaces it audits (F2, PR #1018) — the guard is link
# [0] of the pnpm chain, so severing that chain would silence it together
# with everything it guards; this direct line keeps one instrument running.
- bash packages/mosaic/framework/tools/quality/scripts/check-test-enumeration.sh
# Blocking gate (#791): a framework upgrade must never write or delete an
# operator-owned path. The HARD GATE proves an unanticipated operator sentinel
@@ -103,12 +98,6 @@ steps:
DATABASE_URL: postgresql://mosaic:mosaic@ci-postgres:5432/mosaic
commands:
- *enable_pnpm
# openssl (#912) is the wake HMAC signer: the digest H1/H2, beacon B12,
# and install I8 legs hard-require it in CI. It is baked into ci-base via
# Dockerfile.ci, but ci-base only rebuilds on push-to-main/tag — this
# `apk add` guarantees openssl is present on PR pipelines too (and is a
# fast no-op once the rebuilt image already ships it).
- apk add --no-cache openssl
# postgresql-client (pg_isready) is baked into ci-base.
# Wait up to 60s for CI postgres to be ready; fail fast if it never comes up.
- |
+5 -104
View File
@@ -1,5 +1,5 @@
# Build, publish npm packages, and push Docker images
# Runs on main for stable publishes and on next for integration-line prereleases/images
# Runs only on main branch push/tag
variables:
# Pre-baked CI base (see .woodpecker/ci-image.yml): node:24-alpine +
@@ -23,21 +23,9 @@ 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, next]
- branch: [main]
event: [push, manual, tag]
steps:
@@ -115,84 +103,6 @@ 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 $RESOLVED_VERSION"
depends_on:
- build
# TODO: Uncomment when ready to publish to npmjs.org
# publish-npmjs:
# image: *node_image
@@ -224,17 +134,8 @@ steps:
- echo "{\"auths\":{\"git.mosaicstack.dev\":{\"username\":\"$REGISTRY_USER\",\"password\":\"$REGISTRY_PASS\"}}}" > /kaniko/.docker/config.json
- |
DESTINATIONS="--destination git.mosaicstack.dev/mosaicstack/stack/gateway:sha-${CI_COMMIT_SHA:0:7}"
if [ "$CI_COMMIT_BRANCH" = "next" ]; then
if [ -n "$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
if [ "$CI_COMMIT_BRANCH" = "main" ]; then
DESTINATIONS="$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"
@@ -245,7 +146,7 @@ steps:
build-appservice:
image: gcr.io/kaniko-project/executor:debug
when: *main_image_build_when
when: *image_build_when
environment:
REGISTRY_USER:
from_secret: gitea_username
@@ -271,7 +172,7 @@ steps:
build-web:
image: gcr.io/kaniko-project/executor:debug
when: *main_image_build_when
when: *image_build_when
environment:
REGISTRY_USER:
from_secret: gitea_username
+1 -4
View File
@@ -25,10 +25,7 @@ FROM node:24-alpine
# postgresql-client used by the test step's pg_isready readiness probe. `bash`,
# `git`, and `jq` are baked here too — framework shell tests and the shipped
# Codex review wrappers require them without per-run installation in ci.yml.
# `openssl` (#912) is the non-circular HMAC signer for the wake trust layer:
# the digest H1/H2, beacon B12, and install I8 legs hard-require it in CI so the
# §4 G6 evidence comes from an actually-run HMAC leg, not a skipped one.
RUN apk add --no-cache python3 make g++ postgresql-client bash git jq openssl
RUN apk add --no-cache python3 make g++ postgresql-client bash git jq
# Pin pnpm to the repo's packageManager version via corepack.
RUN corepack enable && corepack prepare [email protected] --activate
+1 -27
View File
@@ -30,16 +30,6 @@ 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
@@ -211,21 +201,8 @@ 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
@@ -253,7 +230,6 @@ 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)
@@ -371,9 +347,7 @@ 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 --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 --ref v1.0 # Install from a specific git ref
bash tools/install.sh --yes # Non-interactive, accept all defaults
bash tools/install.sh --no-auto-launch # Skip auto-launch of wizard
```
@@ -1,519 +0,0 @@
/**
* 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,
});
});
});
@@ -1,11 +1,9 @@
import { Controller, Get, Inject, Optional, UseGuards } from '@nestjs/common';
import { Controller, Get, Inject, 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';
@@ -16,9 +14,6 @@ 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()
@@ -60,14 +55,6 @@ 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 {
@@ -1,4 +1,3 @@
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';
@@ -13,7 +12,6 @@ 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: [],
})),
@@ -74,24 +72,17 @@ const mockChatGateway = {
broadcastSessionInfo: vi.fn(),
};
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 {
function buildService(): CommandExecutorService {
return new CommandExecutorService(
mockRegistry as never,
mockAgentService as never,
mockSystemOverride as never,
mockSessionGC as never,
redis as never,
mockRedis as never,
mockBrain as never,
null,
mockChatGateway as never,
mcpClient as never,
null,
);
}
@@ -140,22 +131,6 @@ 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 };
@@ -267,124 +242,4 @@ 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();
});
});
@@ -23,10 +23,7 @@ export class CommandExecutorService {
@Inject(AgentService) private readonly agentService: AgentService,
@Inject(SystemOverrideService) private readonly systemOverride: SystemOverrideService,
@Inject(SessionGCService) private readonly sessionGC: SessionGCService,
// On Local tier COMMANDS_REDIS is null — provider login caching is skipped.
@Optional()
@Inject(COMMANDS_REDIS)
private readonly redis: QueueHandle['redis'] | null,
@Inject(COMMANDS_REDIS) private readonly redis: QueueHandle['redis'],
@Inject(BRAIN) private readonly brain: Brain,
@Optional()
@Inject(forwardRef(() => ReloadService))
@@ -159,13 +156,8 @@ export class CommandExecutorService {
};
}
} catch (err) {
this.logger.error(`Command /${command} failed`, err);
return {
command,
conversationId,
success: false,
message: 'Command failed due to an internal error.',
};
this.logger.error(`Command /${command} failed: ${err}`);
return { command, conversationId, success: false, message: String(err) };
}
}
@@ -341,11 +333,11 @@ export class CommandExecutorService {
data: { agentId: newAgent.id, agentName: newAgent.name },
};
} catch (err) {
this.logger.error(`Failed to create agent "${namePart}" for user ${userId}`, err);
this.logger.error(`Failed to create agent: ${err}`);
return {
command: 'agent',
success: false,
message: 'Failed to create agent due to an internal error.',
message: `Failed to create agent: ${String(err)}`,
conversationId,
};
}
@@ -396,11 +388,11 @@ export class CommandExecutorService {
data: { agentId: agentConfig.id, agentName: agentConfig.name, model: agentConfig.model },
};
} catch (err) {
this.logger.error(`Failed to switch agent "${agentName}"`, err);
this.logger.error(`Failed to switch agent "${agentName}": ${err}`);
return {
command: 'agent',
success: false,
message: 'Failed to switch agent due to an internal error.',
message: `Failed to switch agent: ${String(err)}`,
conversationId,
};
}
@@ -451,16 +443,14 @@ export class CommandExecutorService {
byte.toString(16).padStart(2, '0'),
).join('');
const key = `mosaic:auth:poll:${tokenHash}`;
if (this.redis) {
// Persist only a short-lived token digest. The raw token is delivered only by
// the authenticated dashboard flow, never in chat output or command metadata.
await this.redis.set(
key,
JSON.stringify({ status: 'pending', provider: providerName, userId }),
'EX',
300,
);
}
// Persist only a short-lived token digest. The raw token is delivered only by
// the authenticated dashboard flow, never in chat output or command metadata.
await this.redis.set(
key,
JSON.stringify({ status: 'pending', provider: providerName, userId }),
'EX',
300,
);
return {
command: 'provider',
success: true,
@@ -613,12 +603,11 @@ 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 "${serverName}" due to an internal error.`,
message: `Failed to reconnect MCP server "${serverName}": ${err instanceof Error ? err.message : String(err)}`,
};
}
}
+5 -15
View File
@@ -1,7 +1,5 @@
import { forwardRef, Inject, Module, Optional, type OnApplicationShutdown } from '@nestjs/common';
import { forwardRef, Inject, Module, 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';
@@ -18,17 +16,13 @@ const COMMANDS_QUEUE_HANDLE = 'COMMANDS_QUEUE_HANDLE';
providers: [
{
provide: COMMANDS_QUEUE_HANDLE,
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;
useFactory: (): QueueHandle => {
return createQueue();
},
inject: [MOSAIC_CONFIG],
},
{
provide: COMMANDS_REDIS,
useFactory: (handle: QueueHandle | null) => handle?.redis ?? null,
useFactory: (handle: QueueHandle) => handle.redis,
inject: [COMMANDS_QUEUE_HANDLE],
},
CommandRegistryService,
@@ -44,13 +38,9 @@ const COMMANDS_QUEUE_HANDLE = 'COMMANDS_QUEUE_HANDLE';
],
})
export class CommandsModule implements OnApplicationShutdown {
constructor(
@Optional()
@Inject(COMMANDS_QUEUE_HANDLE)
private readonly handle: QueueHandle | null,
) {}
constructor(@Inject(COMMANDS_QUEUE_HANDLE) private readonly handle: QueueHandle) {}
async onApplicationShutdown(): Promise<void> {
await this.handle?.close().catch(() => {});
await this.handle.close().catch(() => {});
}
}
@@ -5,8 +5,6 @@ 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';
@@ -14,13 +12,7 @@ import { ListController } from './server/verbs/list.controller.js';
import { FederationListQueryService } from './server/verbs/list-query.service.js';
@Module({
controllers: [
EnrollmentController,
FederationController,
CapabilitiesController,
ListController,
GetController,
],
controllers: [EnrollmentController, FederationController, CapabilitiesController, ListController],
providers: [
AdminGuard,
CaService,
@@ -31,7 +23,6 @@ import { FederationListQueryService } from './server/verbs/list-query.service.js
FederationAuthGuard,
FederationScopeService,
FederationListQueryService,
FederationGetQueryService,
],
exports: [
CaService,
@@ -42,7 +33,6 @@ import { FederationListQueryService } from './server/verbs/list-query.service.js
FederationAuthGuard,
FederationScopeService,
FederationListQueryService,
FederationGetQueryService,
],
})
export class FederationModule {}
@@ -1,348 +0,0 @@
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',
});
});
});
@@ -1,207 +0,0 @@
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();
});
});
@@ -1,311 +0,0 @@
/**
* 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 };
}
}
@@ -1,100 +0,0 @@
/**
* 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 } };
}
}
+5 -15
View File
@@ -1,7 +1,5 @@
import { Module, type OnApplicationShutdown, Inject, Optional } from '@nestjs/common';
import { Module, type OnApplicationShutdown, Inject } 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';
@@ -11,17 +9,13 @@ const GC_QUEUE_HANDLE = 'GC_QUEUE_HANDLE';
providers: [
{
provide: GC_QUEUE_HANDLE,
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;
useFactory: (): QueueHandle => {
return createQueue();
},
inject: [MOSAIC_CONFIG],
},
{
provide: REDIS,
useFactory: (handle: QueueHandle | null) => handle?.redis ?? null,
useFactory: (handle: QueueHandle) => handle.redis,
inject: [GC_QUEUE_HANDLE],
},
SessionGCService,
@@ -29,13 +23,9 @@ const GC_QUEUE_HANDLE = 'GC_QUEUE_HANDLE';
exports: [SessionGCService],
})
export class GCModule implements OnApplicationShutdown {
constructor(
@Optional()
@Inject(GC_QUEUE_HANDLE)
private readonly handle: QueueHandle | null,
) {}
constructor(@Inject(GC_QUEUE_HANDLE) private readonly handle: QueueHandle) {}
async onApplicationShutdown(): Promise<void> {
await this.handle?.close().catch(() => {});
await this.handle.close().catch(() => {});
}
}
@@ -119,19 +119,6 @@ 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');
+8 -15
View File
@@ -1,4 +1,4 @@
import { Inject, Injectable, Optional } from '@nestjs/common';
import { Inject, Injectable } from '@nestjs/common';
import type { QueueHandle } from '@mosaicstack/queue';
import type { LogService } from '@mosaicstack/log';
import { LOG_SERVICE } from '../log/log.tokens.js';
@@ -21,10 +21,7 @@ function escapeRedisGlobLiteral(value: string): string {
@Injectable()
export class SessionGCService {
constructor(
// Local tier has no Redis; lifecycle cleanup still demotes this session's logs.
@Optional()
@Inject(REDIS)
private readonly redis: QueueHandle['redis'] | null,
@Inject(REDIS) private readonly redis: QueueHandle['redis'],
@Inject(LOG_SERVICE) private readonly logService: LogService,
) {}
@@ -32,10 +29,8 @@ 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 {
@@ -52,14 +47,12 @@ export class SessionGCService {
async collect(sessionId: string): Promise<GCResult> {
const result: GCResult = { sessionId, cleaned: {} };
// 1. Valkey: delete all session-scoped keys (skipped on Local tier).
if (this.redis) {
const pattern = `mosaic:session:${escapeRedisGlobLiteral(sessionId)}:*`;
const valkeyKeys = await this.scanKeys(pattern);
if (valkeyKeys.length > 0) {
await this.redis.del(...valkeyKeys);
result.cleaned.valkeyKeys = valkeyKeys.length;
}
// 1. Valkey: delete all session-scoped keys
const pattern = `mosaic:session:${escapeRedisGlobLiteral(sessionId)}:*`;
const valkeyKeys = await this.scanKeys(pattern);
if (valkeyKeys.length > 0) {
await this.redis.del(...valkeyKeys);
result.cleaned.valkeyKeys = valkeyKeys.length;
}
// 2. PG: demote hot-tier agent logs for this session only.
+3 -9
View File
@@ -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: Array<Worker<MosaicJobData>> = [];
private readonly registeredWorkers: Worker<MosaicJobData>[] = [];
constructor(
@Inject(SummarizationService) private readonly summarization: SummarizationService,
@@ -26,12 +26,6 @@ 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
@@ -45,7 +39,7 @@ export class CronService implements OnModuleInit, OnModuleDestroy {
const summarizationWorker = this.queueService.registerWorker(QUEUE_SUMMARIZATION, async () => {
await this.summarization.runSummarization();
});
if (summarizationWorker) this.registeredWorkers.push(summarizationWorker);
this.registeredWorkers.push(summarizationWorker);
// M6-005: Tier management repeatable job
await this.queueService.addRepeatableJob(
@@ -57,7 +51,7 @@ export class CronService implements OnModuleInit, OnModuleDestroy {
const tierWorker = this.queueService.registerWorker(QUEUE_TIER_MANAGEMENT, async () => {
await this.summarization.runTierManagement();
});
if (tierWorker) this.registeredWorkers.push(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.
@@ -1,44 +0,0 @@
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);
});
});
@@ -189,7 +189,7 @@ export class McpClientService implements OnModuleInit, OnModuleDestroy {
);
} catch (err) {
const message = err instanceof Error ? err.message : String(err);
serverEntry.error = 'Connection failed (see server logs).';
serverEntry.error = message;
serverEntry.connected = false;
this.logger.error(`Failed to connect to MCP server "${config.name}": ${message}`);
}
@@ -1,23 +0,0 @@
import { describe, expect, it } from 'vitest';
import type { MosaicConfig } from '@mosaicstack/config';
import { SystemOverrideService } from './system-override.service.js';
const localConfig = { queue: { type: 'local' } } as MosaicConfig;
describe('SystemOverrideService local tier', () => {
it('keeps ephemeral overrides isolated by tenant and user scope', async () => {
const service = new SystemOverrideService(localConfig);
const firstScope = { tenantId: 'tenant-a', userId: 'user-a' };
const secondScope = { tenantId: 'tenant-b', userId: 'user-b' };
await service.set('shared-session', 'first override', firstScope);
await service.set('shared-session', 'second override', secondScope);
await expect(service.get('shared-session', firstScope)).resolves.toBe('first override');
await expect(service.get('shared-session', secondScope)).resolves.toBe('second override');
await service.clear('shared-session', firstScope);
await expect(service.get('shared-session', firstScope)).resolves.toBeNull();
await expect(service.get('shared-session', secondScope)).resolves.toBe('second override');
});
});
@@ -1,8 +1,6 @@
import { Inject, Injectable, Logger, Optional, type OnApplicationShutdown } from '@nestjs/common';
import { Injectable, Logger } from '@nestjs/common';
import { createQueue, type QueueHandle } from '@mosaicstack/queue';
import type { MosaicConfig } from '@mosaicstack/config';
import type { ActorTenantScope } from '../auth/session-scope.js';
import { MOSAIC_CONFIG } from '../config/config.module.js';
const scopedSessionId = (sessionId: string, scope: ActorTenantScope) =>
`${scope.tenantId}:${scope.userId}:${sessionId}`;
@@ -17,45 +15,16 @@ interface OverrideFragment {
addedAt: number;
}
interface LocalOverrideEntry {
condensed: string;
fragments: OverrideFragment[];
}
@Injectable()
export class SystemOverrideService implements OnApplicationShutdown {
export class SystemOverrideService {
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>();
private readonly handle: QueueHandle;
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(() => {});
constructor() {
this.handle = createQueue();
}
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
@@ -85,14 +54,10 @@ export class SystemOverrideService implements OnApplicationShutdown {
}
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);
@@ -100,11 +65,6 @@ export class SystemOverrideService implements OnApplicationShutdown {
}
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),
@@ -1,36 +0,0 @@
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.',
});
});
});
+6 -65
View File
@@ -8,9 +8,7 @@ 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';
// ---------------------------------------------------------------------------
@@ -110,42 +108,21 @@ 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.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;
this.connection = getConnection();
}
onModuleInit(): void {
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',
);
}
this.logger.log('QueueService initialised (BullMQ)');
}
async onModuleDestroy(): Promise<void> {
if (this.enabled) {
await this.closeAll();
}
await this.closeAll();
}
// -------------------------------------------------------------------------
@@ -154,10 +131,8 @@ 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> | null {
if (!this.enabled) return null;
getQueue<T extends MosaicJobData = MosaicJobData>(name: string): Queue<T> {
let queue = this.queues.get(name) as Queue<T> | undefined;
if (!queue) {
queue = new Queue<T>(name, { connection: this.connection });
@@ -169,7 +144,6 @@ 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,
@@ -177,13 +151,7 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
data: T,
cronExpression: string,
): Promise<void> {
if (!this.enabled) {
this.logger.debug(
`Skipping repeatable job "${jobName}" on "${queueName}" (local tier — BullMQ disabled)`,
);
return;
}
const queue = this.getQueue<T>(queueName)!;
const queue = this.getQueue<T>(queueName);
// eslint-disable-next-line @typescript-eslint/no-explicit-any
await (queue as Queue<any>).add(jobName, data, {
repeat: { pattern: cronExpression },
@@ -199,14 +167,7 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
* safe retirement of previously registered system-wide jobs.
*/
async removeRepeatableJobs(queueName: string, jobName: string): Promise<number> {
if (!this.enabled) {
this.logger.debug(
`Skipping repeatable-job removal for "${jobName}" on "${queueName}" (local tier — BullMQ disabled)`,
);
return 0;
}
const queue = this.getQueue(queueName);
if (!queue) return 0;
const jobs = await queue.getRepeatableJobs();
const matchingJobs = jobs.filter((job) => job.name === jobName);
await Promise.all(matchingJobs.map((job) => queue.removeRepeatableByKey(job.key)));
@@ -221,18 +182,8 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
/**
* Register a Worker for the given queue name with error handling and
* exponential backoff.
* Returns null on Local tier where BullMQ is disabled.
*/
registerWorker<T extends MosaicJobData>(
queueName: string,
handler: JobHandler<T>,
): Worker<T> | null {
if (!this.enabled) {
this.logger.debug(
`Skipping worker registration for "${queueName}" (local tier — BullMQ disabled)`,
);
return null;
}
registerWorker<T extends MosaicJobData>(queueName: string, handler: JobHandler<T>): Worker<T> {
const worker = new Worker<T>(
queueName,
async (job) => {
@@ -289,12 +240,8 @@ 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;
@@ -325,10 +272,8 @@ 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]
@@ -355,10 +300,8 @@ 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>".' };
@@ -390,7 +333,6 @@ 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 "${name}" not found.` };
await queue.pause();
@@ -402,7 +344,6 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
* Resume a paused queue by name.
*/
async resumeQueue(name: string): Promise<{ ok: boolean; message: string }> {
if (!this.enabled) return { ok: false, message: 'BullMQ is disabled on local tier.' };
const queue = this.queues.get(name);
if (!queue) return { ok: false, message: `Queue "${name}" not found.` };
await queue.resume();
@@ -1,8 +1,5 @@
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 {
@@ -107,79 +104,3 @@ 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();
});
});
+2 -4
View File
@@ -58,8 +58,7 @@ export class ReloadService implements OnApplicationBootstrap, OnApplicationShutd
await plugin.onUnload();
reloaded.push(name);
} catch (err) {
this.logger.error(`Plugin "${name}" failed during onUnload: ${err}`);
errors.push(`${name}: unload failed (internal error)`);
errors.push(`${name}: unload failed — ${err}`);
}
}
}
@@ -70,8 +69,7 @@ export class ReloadService implements OnApplicationBootstrap, OnApplicationShutd
try {
await plugin.onLoad();
} catch (err) {
this.logger.error(`Plugin "${name}" failed during onLoad: ${err}`);
errors.push(`${name}: load failed (internal error)`);
errors.push(`${name}: load failed ${err}`);
}
}
}
@@ -1,104 +0,0 @@
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,
});
});
});
@@ -1,11 +1,7 @@
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,
type BootstrapProjectResult,
} from './project-bootstrap.service.js';
import { CreateWorkspaceDto } from './workspace.dto.js';
import { ProjectBootstrapService } from './project-bootstrap.service.js';
@Controller('api/workspaces')
@UseGuards(AuthGuard)
@@ -15,14 +11,20 @@ export class WorkspaceController {
@Post()
async create(
@CurrentUser() user: { id: string },
@Body() dto: CreateWorkspaceDto,
): Promise<BootstrapProjectResult> {
@Body()
body: {
name: string;
description?: string;
teamId?: string;
repoUrl?: string;
},
) {
return this.bootstrap.bootstrap({
name: dto.name,
description: dto.description,
name: body.name,
description: body.description,
userId: user.id,
teamId: dto.teamId,
repoUrl: dto.repoUrl,
teamId: body.teamId,
repoUrl: body.repoUrl,
});
}
}
@@ -1,33 +0,0 @@
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;
}
@@ -1,33 +1,11 @@
import { BadRequestException } from '@nestjs/common';
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 { describe, it, expect, beforeEach } 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,
}));
import path from 'node:path';
describe('WorkspaceService', () => {
let service: WorkspaceService;
beforeEach(() => {
execFileMock.mockReset();
execFileMock.mockImplementation((_command, _args, _options, callback) => {
callback(null, '', '');
});
service = new WorkspaceService();
});
@@ -98,69 +76,4 @@ 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),
);
});
});
});
@@ -1,30 +1,10 @@
import { BadRequestException, Injectable, Logger } from '@nestjs/common';
import { 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;
@@ -59,32 +39,14 @@ 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 !== undefined) {
// Clone existing repo. Defense in depth keeps dangerous local helpers
// 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 },
);
if (repoUrl) {
// Clone existing repo
await execFileAsync('git', ['clone', repoUrl, '.'], { cwd: workspacePath });
this.logger.log(`Cloned ${repoUrl} into workspace ${workspacePath}`);
} else {
// Init new git repo
-30
View File
@@ -1,30 +0,0 @@
<!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>
+2 -8
View File
@@ -3,10 +3,8 @@
"version": "0.0.2",
"private": true,
"scripts": {
"build": "node ../../scripts/build-web.mjs",
"build:vite": "vite build",
"build": "next build",
"dev": "next dev",
"dev:vite": "vite",
"lint": "eslint src",
"typecheck": "tsc --noEmit",
"test": "vitest run --passWithNoTests",
@@ -15,14 +13,12 @@
},
"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"
},
@@ -32,11 +28,9 @@
"@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",
"vite": "^8.2.1",
"vitest": "^3.2.7"
"vitest": "^2.0.0"
}
}
@@ -3,56 +3,41 @@
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 type { SsoProviderDiscovery } from '@/lib/sso';
import { getSsoProvider } from '@/lib/sso-providers';
export default function AuthProviderRedirectPage(): React.ReactElement {
const params = useParams<{ provider: string }>();
const searchParams = useSearchParams();
const providerId = typeof params.provider === 'string' ? params.provider : '';
const requestedCallbackURL = searchParams.get('callbackURL');
const [providerName, setProviderName] = useState<string | null>(null);
const provider = getSsoProvider(providerId);
const callbackURL = searchParams.get('callbackURL') ?? '/chat';
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> {
try {
const callbackURL = resolveAuthCallbackURL(requestedCallbackURL, window.location.origin);
const providers = await api<SsoProviderDiscovery[]>('/api/sso/providers');
if (cancelled) return;
const result = await signIn.oauth2({
providerId: activeProvider.id,
callbackURL,
});
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 ?? `${provider.name} sign in failed.`);
}
} catch (caught: unknown) {
if (!cancelled) {
setError(caught instanceof Error ? caught.message : 'Unable to start single sign-on.');
}
if (!cancelled && result?.error) {
setError(result.error.message ?? `${activeProvider.buttonLabel} sign in failed.`);
}
}
@@ -61,22 +46,19 @@ export default function AuthProviderRedirectPage(): React.ReactElement {
return () => {
cancelled = true;
};
}, [providerId, requestedCallbackURL]);
}, [callbackURL, provider]);
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}...`
{provider
? `Redirecting you to ${provider.buttonLabel.replace('Continue with ', '')}...`
: '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"
>
<div 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"
-57
View File
@@ -1,57 +0,0 @@
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,
});
});
});
+3 -1
View File
@@ -1,3 +1,5 @@
const GATEWAY_URL = process.env['NEXT_PUBLIC_GATEWAY_URL'] ?? 'http://localhost:14242';
export interface ApiRequestInit extends Omit<RequestInit, 'body'> {
body?: unknown;
}
@@ -23,7 +25,7 @@ export async function api<T>(path: string, init?: ApiRequestInit): Promise<T> {
headers['Content-Type'] = 'application/json';
}
const res = await fetch(path, {
const res = await fetch(`${GATEWAY_URL}${path}`, {
credentials: 'include',
...rest,
headers,
-29
View File
@@ -1,29 +0,0 @@
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');
});
});
+1 -2
View File
@@ -1,9 +1,8 @@
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()],
});
-30
View File
@@ -1,30 +0,0 @@
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');
});
});
-23
View File
@@ -1,23 +0,0 @@
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;
}
}
-61
View File
@@ -1,61 +0,0 @@
// 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>;
-98
View File
@@ -1,98 +0,0 @@
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);
});
});
+13 -17
View File
@@ -1,27 +1,23 @@
import { io } from 'socket.io-client';
import type { ChatSocket } from './chat-contract';
import { io, type Socket } from 'socket.io-client';
let socket: ChatSocket | null = null;
const GATEWAY_URL = process.env['NEXT_PUBLIC_GATEWAY_URL'] ?? 'http://localhost:14242';
export function getSocket(): ChatSocket {
let socket: Socket | null = null;
export function getSocket(): Socket {
if (!socket) {
// 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', {
socket = io(`${GATEWAY_URL}/chat`, {
withCredentials: true,
autoConnect: false,
transports: ['websocket', 'polling'],
}) as unknown as ChatSocket;
});
// A transient `disconnect` (network blip, server restart) must NOT null
// the singleton: socket.io-client auto-reconnects this same instance,
// and its listeners stay registered across that reconnect. Nulling here
// previously orphaned those listeners on the next getSocket() call by
// handing back a brand-new, unconnected instance. Only destroySocket()
// (an explicit, intentional teardown) may reset the singleton.
// Reset singleton reference when socket is fully closed so the next
// getSocket() call creates a fresh instance instead of returning a
// closed/dead socket.
socket.on('disconnect', () => {
socket = null;
});
}
return socket;
}
+48
View File
@@ -0,0 +1,48 @@
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();
});
});
+53
View File
@@ -0,0 +1,53 @@
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';
}
}
-19
View File
@@ -1,19 +0,0 @@
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>,
);
-51
View File
@@ -1,51 +0,0 @@
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);
}
@@ -1,280 +0,0 @@
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();
});
});
-164
View File
@@ -1,164 +0,0 @@
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>
);
}
-98
View File
@@ -1,98 +0,0 @@
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>
);
}
-22
View File
@@ -1,22 +0,0 @@
/**
* 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;
@@ -1,39 +0,0 @@
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>
);
}
-49
View File
@@ -1,49 +0,0 @@
/**
* 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;
}
-68
View File
@@ -1,68 +0,0 @@
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>
);
}
@@ -1,125 +0,0 @@
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,
};
}
@@ -1,63 +0,0 @@
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();
});
});
-24
View File
@@ -1,24 +0,0 @@
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>
);
}
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
-135
View File
@@ -1,135 +0,0 @@
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');
});
});
-23
View File
@@ -1,23 +0,0 @@
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 />;
}
@@ -1,87 +0,0 @@
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();
});
});
@@ -1,22 +0,0 @@
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>
);
}
-636
View File
@@ -1,636 +0,0 @@
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();
});
});
-92
View File
@@ -1,92 +0,0 @@
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>
);
}
-152
View File
@@ -1,152 +0,0 @@
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>
);
}
-116
View File
@@ -1,116 +0,0 @@
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>
);
}
@@ -1,90 +0,0 @@
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',
});
});
});
-91
View File
@@ -1,91 +0,0 @@
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>
);
}
-9
View File
@@ -1,9 +0,0 @@
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>
);
}
-70
View File
@@ -1,70 +0,0 @@
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);
});
});
-14
View File
@@ -1,14 +0,0 @@
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);
});
});
-23
View File
@@ -1,23 +0,0 @@
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,
},
});
}
-24
View File
@@ -1,24 +0,0 @@
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 },
},
},
});
-12
View File
@@ -1,21 +1,9 @@
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/**'],
},
});
+4 -17
View File
@@ -10,8 +10,6 @@ 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
@@ -23,22 +21,11 @@ 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 --chown=node:node --from=builder /deploy/node_modules ./node_modules
COPY --chown=node:node --from=builder /deploy/package.json ./package.json
COPY --from=builder /deploy/node_modules ./node_modules
COPY --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 --chown=node:node --from=builder /app/apps/gateway/dist ./dist
# gateway defaults to port 14242 (apps/gateway/src/main.ts)
EXPOSE 14242
USER node
COPY --from=builder /app/apps/gateway/dist ./dist
EXPOSE 4000
CMD ["node", "dist/main.js"]
+1 -3
View File
@@ -8,11 +8,9 @@ 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 @mosaicstack/web build
RUN pnpm --filter @mosaic/web build
FROM base AS runner
WORKDIR /app
+4 -23
View File
@@ -16,24 +16,10 @@
## Fleet configuration management
- [Fleet configuration entry point](fleet/README.md) — desired-versus-observed decision tree and complete operator link map.
- [Desired, derived, and observed state](fleet/concepts/desired-vs-observed-state.md) — roster authority, generation, ownership, and drift.
- [Identity, class, and runtime](fleet/concepts/identity-class-runtime.md) — stable name, display alias, class, runtime, provider, and model separation.
- [Role authority and leases](fleet/concepts/role-authority-and-leases.md) — validator/merge-gate separation and bounded lease authority.
- [Generated launch chain](fleet/concepts/generated-env-launch-chain.md) — strict data parsing, precedence, and quarantine.
- [Roster v2 structural contract](fleet/reference/roster-v2-fields.md) — schema, supported values, required fields, defaults, and constraints.
- [Fleet CLI reference](fleet/reference/cli.md) — local desired-state commands, JSON/exit behavior, and gateway-catalog separation.
- [Lifecycle transitions](fleet/reference/lifecycle-transitions.md) — create/apply/reboot/migration/rollback boundaries.
- [Status and drift](fleet/reference/status-and-drift.md) — desired/managed/observed state and current/future classifications.
- [Safe agent CRUD](fleet/how-to/create-update-delete-agent.md) — expected generation, dry-run, and partial-failure recovery.
- [Local lifecycle operations](fleet/how-to/start-stop-restart.md) — persisted versus one-shot actions.
- [Configurable interaction instance](fleet/how-to/configure-tess-interaction.md) and [validator instance](fleet/how-to/configure-ultron-validator.md) — generic identities and protected limits.
- [Reconcile and recover](fleet/operations/reconcile-and-recover.md) — plan/apply lock and recovery behavior.
- [Environment quarantine](fleet/operations/env-quarantine.md) — private evidence and value-free diagnostics.
- [Systemd/tmux troubleshooting](fleet/operations/systemd-tmux-troubleshooting.md) — socket, holder, unmanaged-session, and lock decisions.
- [Backup/restore boundary](fleet/operations/backup-restore.md) and [upgrade-assets hold](fleet/operations/upgrade-assets.md).
- [v1-to-v2 migration preview](fleet/migration/v1-to-v2.md) and [executable artifact dispositions](fleet/migration/example-profile-disposition.md).
- [FCM M5 closure evidence](reports/documentation/758-fleet-config-ia-closure.md) and [approved deferrals](reports/deferred/758-fleet-config-deferrals.md).
- [Generated environment boundary](fleet/reference/generated-env-boundary.md) — roster-derived launch projection, strict local data, legacy quarantine, and downstream interface evidence.
- [Roster v2 structural contract](fleet/reference/roster-v2-fields.md) — local-tmux schema v2 parsing and structural validation.
- [Role classes and authority](fleet/reference/role-classes.md) — canonical role resolver and protected authority boundaries.
- [Executable asset dispositions](fleet/migration/example-profile-disposition.md) — shipped v1 fixture/profile/service validation posture.
## Official channel plugins
@@ -96,8 +82,3 @@
- [Logical identity and connector lease/fencing implementation](https://git.mosaicstack.dev/mosaicstack/stack/issues/755)
- [M1 logical identity and fencing architecture](architecture/mos-runtime-portability-m1.md)
- [M1 connector lease operations](guides/mos-connector-lease-operations.md)
## Comms evolution — Matrix-native MACP (design, draft)
- [RFC-001 — MACP: a Mosaic-native, Matrix-native comms layer](rfcs/RFC-001-MACP-MATRIX-NATIVE.md) — Synapse + Mosaic appservice backbone, MACP v1 protocol, presence/escalation, federation, strangler migration off the Hermes MCP bridge.
- [RFC-002 — Install, configuration & topology for the Matrix/MACP comms system](rfcs/RFC-002-INSTALL-CONFIG-TOPOLOGY.md) — open-source install topology modes, ACME cert provisioning, pluggable secret backend, and config precedence.
+14 -14
View File
@@ -52,20 +52,20 @@ Active workstream is **W1 — Federation v1**. Workers should:
> the repository quality gates, independent code and security review, terminal-green CI, and
> the applicable acceptance evidence before merge. Issue #758 remains open until M5 closes.
| id | status | description | issue | agent | repo | branch | depends_on | estimate | notes |
| ---------- | ----------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----- | ------------- | ----------------- | --------------------------------------- | ---------------------------------------------- | -------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| FCM-M0-001 | done | Publish normative PRD requirements/acceptance criteria, this M0M5 DAG, docs-IA checklist, and legacy example/profile disposition inventory; no implementation changes | #758 | sonnet | mosaicstack/stack | `docs/758-fleet-config-management` | — | 18K | Merged via #760 (`c32d85a`); parent #758 intentionally remains open through M5 |
| FCM-M1-001 | done | Implement narrow local-tmux v2 roster structural contract/compiler with YAML/JSON canonicalization and schema/parser parity tests | #758 | coder0 | mosaicstack/stack | `feat/758-roster-v2-compiler` | FCM-M0-001 | 30K | #764 squash `aa5b43b`; exact-head RoR and PR/main terminal-green CI; no lifecycle or live mutation |
| FCM-M1-002 | done | Reuse existing profile/persona/provision resolver for roster semantics; add canonical class/authority validation and approved aliases | #758 | native-sonnet | mosaicstack/stack | `feat/758-shared-role-resolution` | FCM-M0-001 | 25K | #768 squash `a5e8e55`; shared resolver and canonical authority/alias validation delivered |
| FCM-M1-003 | done | Convert the M0 legacy inventory into executable example/profile/service-preset validation and explicit v1-version/retirement checks | #758 | codex | mosaicstack/stack | `test/758-example-profile-dispositions` | FCM-M1-001, FCM-M1-002 | 20K | #770 squash `e9c4aa3`; shipped artifact disposition validation delivered |
| FCM-M2-001 | done | Migrate generic launch chain to deterministic `.env.generated` plus strict data-only `.env.local`; quarantine forbidden legacy keys | #758 | codex | mosaicstack/stack | `feat/758-generated-env-boundary` | FCM-M1-001, FCM-M1-002 | 30K | #772 squash `191efae`; generated/local boundary and private quarantine delivered |
| FCM-M2-002 | done | Add generation-guarded local fleet agent create/get/update/delete mutations with plan/dry-run, atomic roster writes, and recovery output | #758 | codex | mosaicstack/stack | `feat/758-fleet-agent-crud` | FCM-M1-001, FCM-M2-001 | 30K | #773 squash `bc5e736`; generation-guarded atomic CRUD and recovery contracts delivered |
| FCM-M3-001 | done | Implement local roster-owned reconcile/apply plus lifecycle/status/verify/doctor contracts and stable JSON/exit codes | #758 | codex | mosaicstack/stack | `feat/758-local-reconciler` | FCM-M2-001, FCM-M2-002 | 35K | #785 squash `4990905`; exact roster-owned systemd/tmux reconcile and lifecycle contracts delivered |
| FCM-M3-002 | in-progress | Add isolated systemd/tmux lifecycle, drift, socket, unmanaged-session, crash, and rollback acceptance coverage | #758 | sonnet | mosaicstack/stack | `test/758-reconciler-lifecycle-gates` | FCM-M3-001 | 25K | Canonical v2 named-socket + legacy-v1 default-server boundaries; fake adapters/temp fixtures only |
| FCM-M4-001 | done | Implement field-complete v1-to-v2 inventory/preview/migrator with alias, lifecycle, env-quarantine, and remote/connector disposition evidence | #758 | codex | mosaicstack/stack | `feat/758-v1-v2-migrator` | FCM-M1-003, FCM-M3-001 | 35K | PR #788; final head `d63bb0206a1d312ab8352ec1d3ca3631146b0baa`; tree `4da210da9a71b035130d4160a4a2e691bdfde2da`; squash `9745bc3f29c26b021a478b7ad03cfb494f6c9de3`; descendant-main pipeline 1855 terminal success |
| FCM-M4-002 | not-started | Add reversible canary migration, rollback, stale-projection/orphan classification, and current-host 9-managed/3-unmanaged fixture coverage | #758 | sonnet | mosaicstack/stack | `test/758-migration-rollback-gates` | FCM-M4-001, FCM-M3-002 | 25K | HOLD: never starts a previously stopped agent or kills an unproven unmanaged session; not authorized by FCM-M5-001 |
| FCM-M5-001 | done | Deliver the accepted fleet documentation IA, how-to/operations/migration references, and link/example validation | #758 | haiku | mosaicstack/stack | `docs/758-fleet-config-operator-docs` | FCM-M1-003, FCM-M2-002, FCM-M3-001, FCM-M4-001 | 24K | #789 content squash 627cf2bb; de-flake repair PR#851/#849 squash 77c9a826; completion proof wp1937 @aa999daf push/ci step 49632 recovery_runtime_unittest.py 3/3 OK (closes wp1932 step 49576 Errno111) |
| FCM-M5-002 | not-started | Package/update asset-drift checks, rolling local canary, independent validation certificate, and release evidence | #758 | sonnet | mosaicstack/stack | `feat/758-fleet-config-release-gate` | FCM-M3-002, FCM-M4-002, FCM-M5-001 | 30K | HOLD: final #758 gate; quality, independent code/security review, validator certificate, merge-gate approval, and green CI remain out of M5-001 |
| id | status | description | issue | agent | repo | branch | depends_on | estimate | notes |
| ---------- | ----------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----- | ------------- | ----------------- | --------------------------------------- | ---------------------------------------------- | -------- | ---------------------------------------------------------------------------------------------------------------- |
| FCM-M0-001 | done | Publish normative PRD requirements/acceptance criteria, this M0M5 DAG, docs-IA checklist, and legacy example/profile disposition inventory; no implementation changes | #758 | sonnet | mosaicstack/stack | `docs/758-fleet-config-management` | — | 18K | Merged via #760 (`c32d85a`); parent #758 intentionally remains open through M5 |
| FCM-M1-001 | done | Implement narrow local-tmux v2 roster structural contract/compiler with YAML/JSON canonicalization and schema/parser parity tests | #758 | coder0 | mosaicstack/stack | `feat/758-roster-v2-compiler` | FCM-M0-001 | 30K | #764 squash `aa5b43b`; exact-head RoR and PR/main terminal-green CI; no lifecycle or live mutation |
| FCM-M1-002 | done | Reuse existing profile/persona/provision resolver for roster semantics; add canonical class/authority validation and approved aliases | #758 | native-sonnet | mosaicstack/stack | `feat/758-shared-role-resolution` | FCM-M0-001 | 25K | #768 squash `a5e8e55`; shared resolver and canonical authority/alias validation delivered |
| FCM-M1-003 | done | Convert the M0 legacy inventory into executable example/profile/service-preset validation and explicit v1-version/retirement checks | #758 | codex | mosaicstack/stack | `test/758-example-profile-dispositions` | FCM-M1-001, FCM-M1-002 | 20K | #770 squash `e9c4aa3`; shipped artifact disposition validation delivered |
| FCM-M2-001 | done | Migrate generic launch chain to deterministic `.env.generated` plus strict data-only `.env.local`; quarantine forbidden legacy keys | #758 | codex | mosaicstack/stack | `feat/758-generated-env-boundary` | FCM-M1-001, FCM-M1-002 | 30K | #772 squash `191efae`; generated/local boundary and private quarantine delivered |
| FCM-M2-002 | done | Add generation-guarded local fleet agent create/get/update/delete mutations with plan/dry-run, atomic roster writes, and recovery output | #758 | codex | mosaicstack/stack | `feat/758-fleet-agent-crud` | FCM-M1-001, FCM-M2-001 | 30K | #773 squash `bc5e736`; generation-guarded atomic CRUD and recovery contracts delivered |
| FCM-M3-001 | done | Implement local roster-owned reconcile/apply plus lifecycle/status/verify/doctor contracts and stable JSON/exit codes | #758 | codex | mosaicstack/stack | `feat/758-local-reconciler` | FCM-M2-001, FCM-M2-002 | 35K | #785 squash `4990905`; exact roster-owned systemd/tmux reconcile and lifecycle contracts delivered |
| FCM-M3-002 | in-progress | Add isolated systemd/tmux lifecycle, drift, socket, unmanaged-session, crash, and rollback acceptance coverage | #758 | sonnet | mosaicstack/stack | `test/758-reconciler-lifecycle-gates` | FCM-M3-001 | 25K | Canonical v2 named-socket + legacy-v1 default-server boundaries; fake adapters/temp fixtures only |
| FCM-M4-001 | not-started | Implement field-complete v1-to-v2 inventory/preview/migrator with alias, lifecycle, env-quarantine, and remote/connector disposition evidence | #758 | codex | mosaicstack/stack | `feat/758-v1-v2-migrator` | FCM-M1-003, FCM-M3-001 | 35K | Preview first; no unreviewed lifecycle inference |
| FCM-M4-002 | not-started | Add reversible canary migration, rollback, stale-projection/orphan classification, and current-host 9-managed/3-unmanaged fixture coverage | #758 | sonnet | mosaicstack/stack | `test/758-migration-rollback-gates` | FCM-M4-001, FCM-M3-002 | 25K | Never starts a previously stopped agent or kills an unproven unmanaged session |
| FCM-M5-001 | not-started | Deliver the accepted fleet documentation IA, how-to/operations/migration references, and link/example validation | #758 | haiku | mosaicstack/stack | `docs/758-fleet-config-operator-docs` | FCM-M1-003, FCM-M2-002, FCM-M3-001, FCM-M4-001 | 24K | Must close every checklist item or record an approved deferral |
| FCM-M5-002 | not-started | Package/update asset-drift checks, rolling local canary, independent validation certificate, and release evidence | #758 | sonnet | mosaicstack/stack | `feat/758-fleet-config-release-gate` | FCM-M3-002, FCM-M4-002, FCM-M5-001 | 30K | Final #758 gate: quality, independent code/security review, validator certificate, merge-gate approval, green CI |
## Thin-core prompt diet (#528) — feat/contract-thin-core
@@ -1,63 +0,0 @@
# 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.
+31 -23
View File
@@ -5,17 +5,28 @@
This checklist is an acceptance contract for documentation and examples. It does not authorize
schema, runtime, systemd, role, profile, or live-fleet changes. An item is complete only when its
named artifact exists, is linked from the fleet documentation entry point, and its evidence is
recorded in the M5 closure report and linked deferral evidence.
recorded in the M0 task/PR.
## M0 baseline acceptance
- [x] `docs/PRD.md` states the roster as desired-state SSOT; generated environment, systemd, tmux, and heartbeat artifacts as non-authoritative projections; and fail-closed handling of unsupported or quarantined legacy input.
- [x] `docs/PRD.md` defines the required classes and authority boundary: `validator` certifies but does not merge; `merge-gate` remains sole approve-to-land/merge authority; `team-leader` capacity is lease-bounded; `interaction` is request/status only; instance names such as Tess and Ultron remain configurable.
- [x] `docs/PRD.md` defines local lifecycle semantics for `enabled`, persisted desired state, and observed state, including stopped-state preservation through migration, apply, and reboot.
- [x] `docs/PRD.md` defines the generated-env/local-override boundary, explicitly denies arbitrary command overrides in M1M5, and requires key-name/hash-only quarantine diagnostics.
- [x] `docs/PRD.md` identifies the M1M5 local-tmux scope and excludes remote reconciliation, connector mutation, secret references, arbitrary commands/channels, gateway convergence, and UI configuration storage.
- [x] `docs/TASKS.md` contains the complete M0M5 one-card/one-PR dependency DAG for #758 with agent tier, branch, dependency, estimate, and evidence expectations.
- [x] `docs/fleet/LEGACY-EXAMPLE-PROFILE-DISPOSITION-INVENTORY.md` classifies every current shipped fleet example, profile, and service preset before M1 implementation starts.
- [ ] `docs/PRD.md` states the roster as desired-state SSOT; generated environment, systemd,
tmux, and heartbeat artifacts as non-authoritative projections; and fail-closed handling of
unsupported or quarantined legacy input.
- [ ] `docs/PRD.md` defines the required classes and authority boundary: `validator` certifies but
does not merge; `merge-gate` remains sole approve-to-land/merge authority; `team-leader`
capacity is lease-bounded; `interaction` is request/status only; instance names such as Tess
and Ultron remain configurable.
- [ ] `docs/PRD.md` defines local lifecycle semantics for `enabled`, persisted desired state, and
observed state, including stopped-state preservation through migration, apply, and reboot.
- [ ] `docs/PRD.md` defines the generated-env/local-override boundary, explicitly denies arbitrary
command overrides in M1M5, and requires key-name/hash-only quarantine diagnostics.
- [ ] `docs/PRD.md` identifies the M1M5 local-tmux scope and excludes remote reconciliation,
connector mutation, secret references, arbitrary commands/channels, gateway convergence, and
UI configuration storage.
- [ ] `docs/TASKS.md` contains the complete M0M5 one-card/one-PR dependency DAG for #758 with
agent tier, branch, dependency, estimate, and evidence expectations.
- [ ] `docs/fleet/LEGACY-EXAMPLE-PROFILE-DISPOSITION-INVENTORY.md` classifies every current shipped
fleet example, profile, and service preset before M1 implementation starts.
## Required documentation IA for M1M5
@@ -61,18 +72,15 @@ recorded in the M5 closure report and linked deferral evidence.
## Cross-cutting evidence gates
- [x] Every retained or migrated YAML/JSON example, profile, and service preset validates through the same declared executable production parser/resolver path recorded by the disposition inventory; versioned v1 fixtures are not forced through the v2 compiler.
- [x] Every retired example/profile/service preset has a replacement link and deprecation note; no unresolved legacy class or tool-policy alias remains silently shipped.
- [x] Documentation examples contain no secret values, arbitrary command override, or product-hardcoded Tess/Ultron identity.
- [x] CLI snippets distinguish local fleet desired-state commands from the separate gateway-backed mosaic agent catalog.
- [x] Migration, quarantine, lifecycle, status, and troubleshooting documentation state that values of legacy sensitive keys are never printed.
- [x] M5 documentation validation verifies required IA paths, local file and heading-fragment links, the canonical roster through the production compiler/resolver, and fenced/canonical-example safety checks.
- [ ] FCM-M5-001 does not deterministically assert owner/evidence/deferral metadata for every checklist row. Closure and deferral reports provide human-reviewable evidence only; broader assertion coverage remains unclaimed.
## Held downstream gates
These unchecked items are intentionally outside FCM-M5-001 and are not authorized by this checklist:
- [ ] FCM-M4-002 executes and evidences live cutover, canary, stopped-state preservation, and rollback.
- [ ] FCM-M5-002 completes independent exact-head review and issues the validator certificate.
- [ ] The exact PR head reaches terminal-green CI after independent review.
- [ ] Every retained or migrated YAML/JSON example, profile, and service preset validates through the
same executable schema and shared baseline-plus-`roles.local` resolver used by the CLI.
- [ ] Every retired example/profile/service preset has a replacement link and deprecation note; no
unresolved legacy class or tool-policy alias remains silently shipped.
- [ ] Documentation examples contain no secret values, arbitrary command override, or product-hardcoded
Tess/Ultron identity.
- [ ] CLI snippets distinguish local fleet desired-state commands from the separate gateway-backed
`mosaic agent` catalog.
- [ ] Migration, quarantine, lifecycle, status, and troubleshooting documentation state that values of
legacy sensitive keys are never printed.
- [ ] M5 release review verifies links, schema/example validation, and that all checklist rows have
owner/evidence or an explicit approved deferral.
+11 -11
View File
@@ -8,11 +8,11 @@ Generated environment files are rebuildable projections, not an operator-editabl
| Layer | Responsibility |
| ------------------- | ------------------------------------------------------------------------------------------------------------------------------- |
| Roster | `fleet/roster.yaml` supplies the agent name, class, supported runtime, model, reasoning, tool policy, workdir, and tmux socket. |
| Projection writer | Renders deterministic fleet/agents/<name>.env.generated from the roster. |
| Optional local data | Reads a strict, data-only fleet/agents/<name>.env.local; it cannot shadow generated keys. |
| systemd | Starts the launcher with env -i and fixed bootstrap data. It does not preload either environment file. |
| Projection writer | Renders deterministic `fleet/agents/<name>.env.generated` from the roster. |
| Optional local data | Reads a strict, data-only `fleet/agents/<name>.env.local`; it cannot shadow generated keys. |
| systemd | Starts the launcher with `env -i` and fixed bootstrap data. It does not preload either environment file. |
| session launcher | Validates generated and local data before it queries, creates, or stops an exact tmux session. |
| runtime launch | Derives the fixed mosaic yolo <runtime> argument array from validated roster data, then seeds the runtime contract. |
| runtime launch | Derives the fixed `mosaic yolo <runtime>` argument array from validated roster data, then seeds the runtime contract. |
The launcher never `source`s or `eval`s an environment file and never accepts an environment-supplied
command. `MOSAIC_AGENT_COMMAND`, command/channel overrides, unknown keys, generated-key shadowing,
@@ -20,7 +20,7 @@ secret-like key names, duplicate keys, comments, quoted/export syntax, and unsaf
## Generated and local files
<name>.env.generated is complete, deterministic, and written only by Mosaic. Its ordered keys are:
`<name>.env.generated` is complete, deterministic, and written only by Mosaic. Its ordered keys are:
```dotenv
MOSAIC_AGENT_NAME=<roster name>
@@ -33,12 +33,12 @@ MOSAIC_AGENT_WORKDIR=<absolute roster work directory>
MOSAIC_TMUX_SOCKET=<roster socket or empty>
```
The generated launch contract supports `claude`, `codex`, `opencode`, and `pi`. mosaic fleet add
The generated launch contract supports `claude`, `codex`, `opencode`, and `pi`. `mosaic fleet add`
rejects another runtime before it writes the roster or modifies generated, local, or quarantine state.
The legacy dogfood stub remains an observability-only canary on its separate `mosaic-factory` socket;
it has no generated-launch adapter and cannot be added through this path.
<name>.env.local is optional and may contain only non-secret machine data:
`<name>.env.local` is optional and may contain only non-secret machine data:
- `MOSAIC_RUNTIME_BIN`
- `MOSAIC_HEARTBEAT_RUN_DIR`
@@ -52,9 +52,9 @@ private, non-symlink paths. Violations fail closed before tmux interaction.
## Legacy input and diagnostics
A legacy <name>.env is input only during projection generation. Roster-owned keys are regenerated;
A legacy `<name>.env` is input only during projection generation. Roster-owned keys are regenerated;
valid allowed local data can move to `.env.local`; invalid legacy input is privately retained at
<name>.env.quarantine. Neither legacy nor quarantine files are launch authority.
`<name>.env.quarantine`. Neither legacy nor quarantine files are launch authority.
Diagnostics expose only rule code, key name, and a SHA-256 content hash. They do not reveal command
text, credentials, or other values.
@@ -62,11 +62,11 @@ text, credentials, or other values.
## Launch and stop behavior
The launcher obtains the agent's socket only from the validated generated projection. It creates or
checks the exact =<agent-name> tmux target; it never uses an ambient socket or fuzzy session match.
checks the exact `=<agent-name>` tmux target; it never uses an ambient socket or fuzzy session match.
The same strict parser runs before exact-stop behavior. A fresh native Pi heartbeat remains authoritative;
the shell sidecar only provides fallback state when the native marker is stale or absent.
mosaic agent comms-block <exact-member> can inspect that exact roster member's resolved Fleet-Comms
`mosaic agent comms-block <exact-member>` can inspect that exact roster member's resolved Fleet-Comms
block. It is a read-only inspection tool and fails loudly for an unknown exact member or missing roster.
On Linux, the installed roster, TOOLS contract, and executable helper are opened through a held
descriptor chain rooted at `/`; every managed path component uses no-follow traversal, and content plus
@@ -14,7 +14,7 @@ parallel resolver. The current executable implementation and per-artifact outcom
| Shipped file | Current class evidence | M0 disposition decision | Required M1/M4 evidence |
| ---------------------------------------------------- | ------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------- |
| `framework/fleet/examples/coding.yaml` | `orchestrator`, `enhancer`, `implementer`, `reviewer` | Migrate: implementer → code, reviewer → review; retain orchestration/enhancer intent | v2 fixture validates; role aliases and authority matrix tested |
| `framework/fleet/examples/coding.yaml` | `orchestrator`, `enhancer`, `implementer`, `reviewer` | Migrate: `implementer → code`, `reviewer → review`; retain orchestration/enhancer intent | v2 fixture validates; role aliases and authority matrix tested |
| `framework/fleet/examples/general.yaml` | `orchestrator`, `enhancer`, `worker` | Migrate only after operator chooses a concrete canonical role for `worker`; no implicit conversion | Explicit replacement class, or versioned v1 fixture/retirement note |
| `framework/fleet/examples/hybrid.yaml` | `orchestrator`, `enhancer`, `implementer`, `researcher`, `reviewer` | Migrate aliases; resolve `researcher` through existing role resolver or retain/version | Shared resolver validation; no ad-hoc class scanner |
| `framework/fleet/examples/local-canary.yaml` | `orchestrator`, `implementer`, `reviewer` | Migrate aliases; preserve its local-tmux canary purpose | v2 fixture validates and preserves safe stopped/running behavior |
@@ -34,14 +34,14 @@ parallel resolver. The current executable implementation and per-artifact outcom
## Service presets
| Shipped file | Current policy evidence | M0 disposition decision | Required M1/M4 evidence |
| ---------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `framework/fleet/services/operator-interaction.yaml` | Generic policy only: runtime: pi, model: openai/gpt-5.6-sol, reasoning: high, tool_policy: operator-interaction; provisioning supplies the agent name as data | Retain as a generic service policy, not a Tess identity. Migrate tool_policy: operator-interaction only through the approved interaction tool-policy alias/semantic resolver; do not infer a class or machine name from this file. | Service-policy fixture validates runtime/model/reasoning and alias behavior; generic provisioning proves a configured interaction instance is supplied without a hardcoded Tess name. |
| Shipped file | Current policy evidence | M0 disposition decision | Required M1/M4 evidence |
| ---------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `framework/fleet/services/operator-interaction.yaml` | Generic policy only: `runtime: pi`, `model: openai/gpt-5.6-sol`, `reasoning: high`, `tool_policy: operator-interaction`; provisioning supplies the agent name as data | Retain as a generic service policy, not a Tess identity. Migrate `tool_policy: operator-interaction` only through the approved interaction tool-policy alias/semantic resolver; do not infer a class or machine name from this file. | Service-policy fixture validates runtime/model/reasoning and alias behavior; generic provisioning proves a configured interaction instance is supplied without a hardcoded Tess name. |
## Required disposition controls
1. **No silent aliasing:** only implementer → code, reviewer → review, and
operator-interaction → interaction are approved deterministic aliases in this M0 baseline.
1. **No silent aliasing:** only `implementer → code`, `reviewer → review`, and
`operator-interaction → interaction` are approved deterministic aliases in this M0 baseline.
`worker`, `analyst`, `canary`, and domain-specific classes require resolver evidence or an
explicit version/retirement decision.
2. **No identity hardcoding:** Tess and Ultron are optional instance/display names. An example/profile
+1 -1
View File
@@ -33,7 +33,7 @@ The Mosaic Backlog is the backlog of record + dispatch engine, built on Mosaic's
- **AC-NS-4** — TTL is enforced on claims; token caps remain advisory until a real meter exists.
- **AC-NS-5** — Flipping fleet/run/PAUSED halts dispatch and merges within one tick.
- **AC-NS-6** — A user can declare a system type and the fleet provisions the matching persona roster + topology from the baseline library, with no code change.
- **AC-NS-7** — A user-customized persona (edited or added via the orchestrator) survives mosaic update: baseline reseed never clobbers user overrides.
- **AC-NS-7** — A user-customized persona (edited or added via the orchestrator) survives `mosaic update`: baseline reseed never clobbers user overrides.
## Workstreams
+1 -1
View File
@@ -97,7 +97,7 @@ success_criteria:
- id: AC-NS-7
text: >-
A user-customized persona (edited or added via the orchestrator) survives
mosaic update: baseline reseed never clobbers user overrides.
`mosaic update`: baseline reseed never clobbers user overrides.
workstreams:
- id: A
+34 -34
View File
@@ -8,7 +8,7 @@
## Mission
Turn the proven fleet primitives into a **user-installable, AI-free-configurable fleet product**:
a user runs mosaic fleet init, answers a few questions (general / coding / research / hybrid),
a user runs `mosaic fleet init`, answers a few questions (general / coding / research / hybrid),
gets a recommended set of agents plus one always-on orchestrator wired for chat-ops, and can
operate, mutate, re-create, and observe the fleet — over tmux today and Matrix tomorrow — from
CLI/TUI and (designed-for) the webUI.
@@ -21,25 +21,25 @@ functional, we use the fleet itself to continue the work.
### A. Configure-without-AI CLI
| ID | Requirement |
| --- | ----------------------------------------------------------------------------------------------------------- |
| R1 | mosaic fleet command set is functional end-to-end (init/install/start/stop/status/ps/verify + agent verbs). |
| R2 | mosaic fleet init is an interactive, **AI-free** CLI wizard. |
| R3 | Init asks the **configuration type**: `general`, `coding`, `research`, `hybrid`, … (extensible). |
| R4 | Based on the answer, the fleet is populated with a **recommended set of agents** (a preset). |
| R5 | **Exactly one main orchestrator agent** is always configured, regardless of type. |
| R10 | A set of **recommended configurations (presets)** ships for easy duplication. |
| R8 | User can **re-create** the fleet when config needs change (idempotent re-init / reconfigure). |
| R17 | Fleet controls are **simple and intuitive**. |
| ID | Requirement |
| --- | ------------------------------------------------------------------------------------------------------------- |
| R1 | `mosaic fleet` command set is functional end-to-end (init/install/start/stop/status/ps/verify + agent verbs). |
| R2 | `mosaic fleet init` is an interactive, **AI-free** CLI wizard. |
| R3 | Init asks the **configuration type**: `general`, `coding`, `research`, `hybrid`, … (extensible). |
| R4 | Based on the answer, the fleet is populated with a **recommended set of agents** (a preset). |
| R5 | **Exactly one main orchestrator agent** is always configured, regardless of type. |
| R10 | A set of **recommended configurations (presets)** ships for easy duplication. |
| R8 | User can **re-create** the fleet when config needs change (idempotent re-init / reconfigure). |
| R17 | Fleet controls are **simple and intuitive**. |
### B. Comms & orchestrator chat-ops
| ID | Requirement |
| --- | ----------------------------------------------------------------------------------------------------------------------------- |
| R6 | Init can wire the orchestrator to a chat connector — **Telegram / Discord / Matrix / Slack** — for command + comms. |
| R7 | Designed with the end-goal of **Matrix comms on a locally-controlled server**. |
| R16 | Fleet supports **tmux AND Matrix** comms, **user-configurable** at init or any time. Not all users want Matrix. |
| R19 | **"Mos" orchestrator on Discord** (chan 1517622518662434996 / srv 1112631390438166618) on `w-jarvis` — the first live target. |
| ID | Requirement |
| --- | --------------------------------------------------------------------------------------------------------------------------------- |
| R6 | Init can wire the orchestrator to a chat connector — **Telegram / Discord / Matrix / Slack** — for command + comms. |
| R7 | Designed with the end-goal of **Matrix comms on a locally-controlled server**. |
| R16 | Fleet supports **tmux AND Matrix** comms, **user-configurable** at init or any time. Not all users want Matrix. |
| R19 | **"Mos" orchestrator on Discord** (`chan 1517622518662434996` / `srv 1112631390438166618`) on `w-jarvis` — the first live target. |
### C. Runtime, health, lifecycle
@@ -64,46 +64,46 @@ functional, we use the fleet itself to continue the work.
- **Orchestrator agent:** always present; carries the chat connector config (connector type + target IDs) so it can be commanded over chat. tmux is the substrate; the connector bridges chat ↔ the orchestrator session.
- **Comms layers (R16):** (1) **tmux** inter-agent (`agent-send`, proven) — default, always available. (2) **chat connector** for human↔orchestrator (Discord now; Matrix the strategic target). (3) **Matrix** as the locally-controlled cross-agent bus (future). Connector is pluggable + reconfigurable.
- **Heartbeat (R15):** runtime-agnostic launcher sidecar already covers pi/claude/codex (#584). Refine per-runtime (native HB) with the **custom Pi harness** (R14) + a Claude path.
- **Updates (R13):** mosaic update (CLI) + a fleet-aware harness-update step that refreshes pi/claude/codex and re-launches agents safely (drain → update → relaunch via the durable launcher).
- **webUI (R18):** the fleet exposes machine-readable state (fleet ps --json already carries tenant/host/heartbeat/managed) + control verbs (start/stop/watch/send); webUI consumes these (control plane rides federation per north star). Ensure a stable JSON contract + a terminate/attach(butt-in) path.
- **Updates (R13):** `mosaic update` (CLI) + a fleet-aware harness-update step that refreshes pi/claude/codex and re-launches agents safely (drain → update → relaunch via the durable launcher).
- **webUI (R18):** the fleet exposes machine-readable state (`fleet ps --json` already carries tenant/host/heartbeat/managed) + control verbs (start/stop/watch/send); webUI consumes these (control plane rides federation per north star). Ensure a stable JSON contract + a terminate/attach(butt-in) path.
## Phases (incremental, each shippable)
| Phase | Deliverable | Notes |
| --------------------------------- | --------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------- |
| **F1 Presets + init wizard** | preset rosters (general/coding/research/hybrid) + always-orchestrator + AI-free fleet init selecting a preset; re-init idempotent | R1R5, R8, R10, R17 |
| **F2 Connector + Mos-on-Discord** | orchestrator chat-connector config (Discord first) + **Mos live on Discord 1517…/1112…** on w-jarvis | R6, R19, partial R16 |
| **F3 Heartbeat + harness** | HB confirmed for claude + pi/gpt; **custom Pi harness** (tool usage, native HB, model self-report); graceful harness updates | R13, R14, R15 |
| **F4 Matrix + comms toggle** | Matrix connector (local server) + user toggle tmux/Matrix at init/anytime | R7, R16 |
| **F5 Orchestrator-mutable fleet** | orchestrator can add/remove agents at runtime | R9 |
| **F6 webUI hooks** | stable JSON contract + terminate/attach surface for webUI view/monitor/terminate/butt-in | R18 |
| **F7 Test + docs** | install+test on w-jarvis AND dragon-lin; user docs (install/configure/use) | R11, R12 (runs alongside every phase) |
| Phase | Deliverable | Notes |
| --------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------- |
| **F1 Presets + init wizard** | preset rosters (general/coding/research/hybrid) + always-orchestrator + AI-free `fleet init` selecting a preset; re-init idempotent | R1R5, R8, R10, R17 |
| **F2 Connector + Mos-on-Discord** | orchestrator chat-connector config (Discord first) + **Mos live on Discord `1517…`/`1112…`** on w-jarvis | R6, R19, partial R16 |
| **F3 Heartbeat + harness** | HB confirmed for claude + pi/gpt; **custom Pi harness** (tool usage, native HB, model self-report); graceful harness updates | R13, R14, R15 |
| **F4 Matrix + comms toggle** | Matrix connector (local server) + user toggle tmux/Matrix at init/anytime | R7, R16 |
| **F5 Orchestrator-mutable fleet** | orchestrator can add/remove agents at runtime | R9 |
| **F6 webUI hooks** | stable JSON contract + terminate/attach surface for webUI view/monitor/terminate/butt-in | R18 |
| **F7 Test + docs** | install+test on w-jarvis AND dragon-lin; user docs (install/configure/use) | R11, R12 (runs alongside every phase) |
## Work division (proposed — confirm with dragon-lin)
- **Jarvis @ w-jarvis (Lead):** F1 presets+wizard, F2 connector+Mos-on-Discord, F5 mutability, F6 webUI hooks; merge authority + dual-engine reviews; co-testing on w-jarvis.
- **coder @ dragon-lin:** F3 custom Pi harness + harness-update flow (pi/codex-savvy); plus its in-flight constitution P4P6 (P4 installer rework underpins fleet init/updates — coordinate the install path). Co-testing on dragon-lin (R11).
- **coder @ dragon-lin:** F3 custom Pi harness + harness-update flow (pi/codex-savvy); plus its in-flight constitution P4P6 (P4 installer rework underpins `fleet init`/updates — coordinate the install path). Co-testing on dragon-lin (R11).
- **Shared:** F4 Matrix (whoever has bandwidth); F7 testing/docs continuous.
## Immediate target: Mos on Discord (F2 first slice)
The discord plugin is available (~/.claude.json). Path: configure the **orchestrator** as a durable
The discord plugin is available (`~/.claude.json`). Path: configure the **orchestrator** as a durable
fleet session running Claude Code with the discord plugin bridged to channel `1517622518662434996`
(server `1112631390438166618`) on w-jarvis, with the existing Discord Bridge Protocol (ack within
~3s, reply via `mcp__discord__reply`, no `AskUserQuestion`). Heartbeat via the launcher sidecar.
## Success criteria
- A non-AI user can mosaic fleet init, pick a type, and get a working fleet + orchestrator.
- **Mos answers in Discord 1517…** on w-jarvis.
- Fleet runs + is observable (fleet ps) on **both** w-jarvis and dragon-lin.
- A non-AI user can `mosaic fleet init`, pick a type, and get a working fleet + orchestrator.
- **Mos answers in Discord `1517…`** on w-jarvis.
- Fleet runs + is observable (`fleet ps`) on **both** w-jarvis and dragon-lin.
- Harness updates handled gracefully; HB healthy for claude + pi/gpt agents.
- Docs let a new operator install/configure/use the fleet.
- Re-init + orchestrator mutation work.
## Assumptions (veto-able)
- `ASSUMPTION:` presets ship as example rosters under the framework (fleet/examples/\*.yaml), selected by `init`.
- `ASSUMPTION:` presets ship as example rosters under the framework (`fleet/examples/*.yaml`), selected by `init`.
- `ASSUMPTION:` chat connectors are pluggable; Discord first (target exists), Matrix is the strategic default later.
- `ASSUMPTION:` "Mos" = a Claude Code orchestrator session with the discord plugin (reuses the documented Discord Bridge Protocol).
- `ASSUMPTION:` per north star, runtimes default to Codex/pi-on-Codex for workers; the orchestrator "Mos" runs Claude Code (in Claude Code, which is allowed).
+30 -30
View File
@@ -10,8 +10,8 @@
The durable tmux fleet runs on the isolated `mosaic-fleet` socket. That isolation
(which protects the operator's default tmux) makes the fleet **invisible** to default
tooling, and truth is split across three planes no single command joins — systemd
(systemctl --user), tmux (-L mosaic-fleet), and the process tree (`pstree`).
agent tail (`capture-pane`) returns **blank for full-screen TUIs**, and agent send
(`systemctl --user`), tmux (`-L mosaic-fleet`), and the process tree (`pstree`).
`agent tail` (`capture-pane`) returns **blank for full-screen TUIs**, and `agent send`
confirms only keystroke injection, not acceptance. Net: the operator has near-zero
observability and no safe way to watch a session.
@@ -32,22 +32,22 @@ observability and no safe way to watch a session.
## Functional requirements
| ID | Requirement |
| ---- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| FR-1 | mosaic fleet ps [--json] prints one row per roster agent joining: name · tenant · host · runtime · systemd(active/enabled) · pane(alive/dead) · pid · idle · **last-heartbeat age** · **drift** flag (roster runtime ≠ actual pane command) · **boot-enable** warning (active but `UnitFileState=disabled`). |
| FR-2 | **Heartbeat protocol v1** (see below); `dogfood-agent.py` implements the responder. fleet ps issues probes (or reads last-seen) and reports health per FR-1. |
| FR-3 | mosaic agent watch <name> opens a **read-only** view of the pane (grouped session or tmux attach -r) that cannot send keystrokes and does not shrink the agent's window. |
| FR-4 | mosaic agent attach <name> remains the **explicit** interactive-takeover path (separate verb, documented as the only one that can type). |
| FR-5 | mosaic agent send <name> --verify confirms the message was **accepted** (not left as an unsubmitted draft) and returns non-zero if delivery cannot be verified. |
| FR-6 | All structured output (`--json`) includes `tenant_id` and `host` fields. |
| ID | Requirement |
| ---- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| FR-1 | `mosaic fleet ps [--json]` prints one row per roster agent joining: name · tenant · host · runtime · systemd(active/enabled) · pane(alive/dead) · pid · idle · **last-heartbeat age** · **drift** flag (roster runtime ≠ actual pane command) · **boot-enable** warning (active but `UnitFileState=disabled`). |
| FR-2 | **Heartbeat protocol v1** (see below); `dogfood-agent.py` implements the responder. `fleet ps` issues probes (or reads last-seen) and reports health per FR-1. |
| FR-3 | `mosaic agent watch <name>` opens a **read-only** view of the pane (grouped session or `tmux attach -r`) that cannot send keystrokes and does not shrink the agent's window. |
| FR-4 | `mosaic agent attach <name>` remains the **explicit** interactive-takeover path (separate verb, documented as the only one that can type). |
| FR-5 | `mosaic agent send <name> --verify` confirms the message was **accepted** (not left as an unsubmitted draft) and returns non-zero if delivery cannot be verified. |
| FR-6 | All structured output (`--json`) includes `tenant_id` and `host` fields. |
## Heartbeat protocol v1
- **Probe:** operator/fleet ps writes a sentinel line to the agent's input or a
well-known per-agent heartbeat file path ~/.config/mosaic/fleet/run/<agent>.hb.
- **Response:** the runtime updates <agent>.hb with ts=<iso8601> pid=<pid> status=<ok|busy>
- **Probe:** operator/`fleet ps` writes a sentinel line to the agent's input or a
well-known per-agent heartbeat file path `~/.config/mosaic/fleet/run/<agent>.hb`.
- **Response:** the runtime updates `<agent>.hb` with `ts=<iso8601> pid=<pid> status=<ok|busy>`
on a fixed interval (default 15s) and on demand when probed.
- **Health rule:** `healthy` if now - ts <= 3 × interval; else `stale`; missing file = `unknown`.
- **Health rule:** `healthy` if `now - ts <= 3 × interval`; else `stale`; missing file = `unknown`.
- **Contract:** every runtime (dogfood stub now; claude/codex/pi/opencode in Phase 3)
MUST emit the heartbeat. The protocol is file-based so it works for headless stubs and
full-screen TUIs alike (no `capture-pane` dependency).
@@ -56,15 +56,15 @@ observability and no safe way to watch a session.
## Acceptance criteria
- mosaic fleet ps shows all 5 live sessions on `mosaic-fleet` with correct
- `mosaic fleet ps` shows all 5 live sessions on `mosaic-fleet` with correct
pane/pid/idle and flags the dogfood **drift** (`canary-pi` runtime=pi but pane runs
`dogfood-agent.py`) and the **boot-enable** gap (active but disabled).
- Killing one agent's pane flips its row to dead/stale within one `interval`.
- agent watch shows live output and provably cannot type into the pane; detaching
- `agent watch` shows live output and provably cannot type into the pane; detaching
leaves the agent's window size unchanged.
- agent send --verify returns success on an accepting pane and non-zero on a wedged/draft pane.
- Quality gates green: pnpm typecheck, pnpm lint, pnpm format:check, plus
pnpm --filter @mosaicstack/mosaic test.
- `agent send --verify` returns success on an accepting pane and non-zero on a wedged/draft pane.
- Quality gates green: `pnpm typecheck`, `pnpm lint`, `pnpm format:check`, plus
`pnpm --filter @mosaicstack/mosaic test`.
- Independent review passed; dogfood evidence captured against the live fleet.
## Test plan
@@ -72,18 +72,18 @@ observability and no safe way to watch a session.
- Unit/CLI specs in `packages/mosaic/src/commands/fleet.spec.ts` (and a new
`fleet-ps`/`watch`/`send-verify` spec) using the injected `CommandRunner` to assert
exact tmux/systemd command construction and JSON shape (tenant+host present).
- Situational: run against the live `mosaic-fleet` fleet; capture fleet ps output,
a kill-and-detect cycle, a read-only `watch`, and a send --verify pass/fail pair.
- Situational: run against the live `mosaic-fleet` fleet; capture `fleet ps` output,
a kill-and-detect cycle, a read-only `watch`, and a `send --verify` pass/fail pair.
## Known limitations
- **Verify heuristic is best-effort:** agent send --verify uses a > -prefix draft
- **Verify heuristic is best-effort:** `agent send --verify` uses a `>` -prefix draft
heuristic that is specific to pi/claude TUIs. Draft detection for codex and opencode
TUIs is best-effort only; those runtimes may not use the same input-line indicator.
- **Pane-change check is the best Phase-2 signal; verify now polls up to a bounded
timeout:** agent send --verify captures a BEFORE snapshot, sends the message, then
timeout:** `agent send --verify` captures a BEFORE snapshot, sends the message, then
polls `capture-pane` every ~400 ms up to a configurable total timeout (default ~6 s,
controlled by --verify-timeout <ms>). On each poll it runs classifySendResult: if
controlled by `--verify-timeout <ms>`). On each poll it runs classifySendResult: if
the pane shows 'accepted' or 'draft' the loop exits immediately; while the result is
'unverifiable' (no pane change yet) it keeps polling. After the timeout with no
definitive result, it fails closed: exit 1 with "no pane change after send". This
@@ -92,15 +92,15 @@ observability and no safe way to watch a session.
requires a runtime acknowledgement (Phase-3 heartbeat-ack); the bounded pane-change
poll is the best signal available against an opaque TUI for Phase-2.
- **Blank AFTER capture fails closed:** Full-screen TUIs (claude, codex, opencode, pi)
render blank for tmux capture-pane. When the AFTER snapshot is empty, send --verify
render blank for `tmux capture-pane`. When the AFTER snapshot is empty, `send --verify`
returns non-zero with an "unverifiable" message rather than silently succeeding. This
is an intentional fail-closed design (FR-5).
- **agent watch uses a grouped viewer session:** tmux attach -r directly against the
agent session lets the viewer terminal shrink the agent's window. agent watch instead
creates a throwaway grouped session (tmux new-session -d -t '=<agent>' -s
'<agent>-watch-<pid>'), attaches read-only to that session, and kills it on detach.
- **`agent watch` uses a grouped viewer session:** `tmux attach -r` directly against the
agent session lets the viewer terminal shrink the agent's window. `agent watch` instead
creates a throwaway grouped session (`tmux new-session -d -t '=<agent>' -s
'<agent>-watch-<pid>'`), attaches read-only to that session, and kills it on detach.
The grouped session shares the agent's windows but has independent sizing, so the
agent's window is never affected. tmux attach is still interactive and requires
agent's window is never affected. `tmux attach` is still interactive and requires
inherited stdio; the `interactiveRunner` handles TTY passthrough.
## Surfaces & parity (MVP-X1)
-63
View File
@@ -1,63 +0,0 @@
# Fleet Configuration Management
This book documents the local roster-v2 desired-state control plane delivered under issue #758. The normative requirements are the [FCM section of the repository PRD](../PRD.md#fleet-declarative-configuration-management-workstream-fcm-758), not the older fleet-suite or observability planning pages.
## Authority boundary
<MOSAIC_HOME>/fleet/roster.yaml is the sole writable desired-state authority for local fleet membership, launch policy, and persisted lifecycle. Generated environment files, systemd enablement, tmux sessions, heartbeat files, and status output are derived or observed. Rebuild projections from the roster; never edit them as desired state.
This control plane is local tmux/systemd only. Remote/SSH entries and connectors are inventory, not reconciliation targets. Arbitrary commands, channels, secret references, gateway catalog convergence, and UI configuration storage are outside this workstream. `mos-comms` is temporary transport glue, not permanent fleet architecture.
## Choose the right workflow
1. **Need to inspect intent?** Read the roster and use mosaic fleet get; see [desired versus observed state](concepts/desired-vs-observed-state.md).
2. **Need to inspect reality?** Use `status` or `doctor`; use `verify` for a strict non-zero drift/ownership gate. These commands do not repair anything.
3. **Need to change membership or persisted policy?** Use generation-guarded `plan`, `create`, `update`, or `delete`; see [safe CRUD](how-to/create-update-delete-agent.md).
4. **Need a one-time runtime action?** Use `start`, `stop`, or `restart`. These do not change persisted desired state.
5. **Need convergence?** Review apply --dry-run, resolve blockers, then use `apply` with the same current generation; see [reconcile and recover](operations/reconcile-and-recover.md).
6. **Need v1 migration evidence?** Use preview only. Cutover, canary, and rollback remain held for FCM-M4-002.
7. **Need the gateway-backed agent catalog?** That is the separate mosaic agent surface, not local fleet desired state.
## Concepts
- [Desired versus observed state](concepts/desired-vs-observed-state.md)
- [Identity, class, runtime, provider, and model](concepts/identity-class-runtime.md)
- [Role authority and leases](concepts/role-authority-and-leases.md)
- [Generated environment launch chain](concepts/generated-env-launch-chain.md)
## Operator how-to
- [Create, inspect, update, and delete](how-to/create-update-delete-agent.md)
- [Start, stop, restart, and reconcile](how-to/start-stop-restart.md)
- [Configure an interaction instance](how-to/configure-tess-interaction.md)
- [Configure a validator instance](how-to/configure-ultron-validator.md)
- [Customize roles](how-to/customize-roles.md)
## Operations and recovery
- [Reconcile and recover](operations/reconcile-and-recover.md)
- [Environment quarantine](operations/env-quarantine.md)
- [Systemd/tmux troubleshooting](operations/systemd-tmux-troubleshooting.md)
- [Backup and restore boundary](operations/backup-restore.md)
- [Upgrade and asset-drift hold](operations/upgrade-assets.md)
## Reference and migration
- [Roster v2 fields](reference/roster-v2-fields.md) · [executable JSON Schema](reference/roster-v2.schema.json) · [validated example](examples/roster-v2.yaml)
- [CLI and exit codes](reference/cli.md)
- [Role classes](reference/role-classes.md)
- [Lifecycle transitions](reference/lifecycle-transitions.md)
- [Status and drift](reference/status-and-drift.md)
- [Generated environment boundary](reference/generated-env-boundary.md)
- [v1-to-v2 preview](migration/v1-to-v2.md)
- [Example/profile dispositions](migration/example-profile-disposition.md)
- [Legacy class aliases](migration/legacy-class-aliases.md)
## Acceptance evidence and holds
- [M0/M5 IA checklist](FLEET-CONFIG-DOCS-IA-CHECKLIST.md)
- [Legacy example/profile inventory](LEGACY-EXAMPLE-PROFILE-DISPOSITION-INVENTORY.md)
- [M5 closure evidence](../reports/documentation/758-fleet-config-ia-closure.md)
- [Approved-existing deferrals and live-action holds](../reports/deferred/758-fleet-config-deferrals.md)
The canonical publishing source remains this repository. This card does not publish externally, run a migration, operate a live fleet, or close parent issue #758.
+13 -13
View File
@@ -7,21 +7,21 @@
> Mission: `mvp-20260312` · PRD: [docs/fleet/PRD.md](./PRD.md) · North star: [docs/fleet/north-star.md](./north-star.md)
> Status: `not-started` | `in-progress` | `done` | `blocked` | `failed`
| id | status | description | depends_on | agent | pr | notes |
| ------------- | ----------- | ---------------------------------------------------------------------------------------------------------------- | --------------------- | ----------- | --- | --------------------------------------------------------------------------------------------------------------------------- |
| FLEET-OBS-000 | done | Plan: north-star + Phase-2 PRD + workstream scaffolding | — | lead | — | persisted 2026-06-20 on `feat/fleet-observability` |
| FLEET-OBS-001 | done | Heartbeat protocol v1 spec finalized in PRD + framework doc | FLEET-OBS-000 | lead | — | file-based ~/.config/mosaic/fleet/run/<agent>.hb; spec in PRD |
| FLEET-OBS-002 | in-progress | Implement heartbeat responder in `dogfood-agent.py` | FLEET-OBS-001 | fleet-coder | — | dispatched to ad-hoc mosaic yolo fleet agent (dogfood) |
| FLEET-OBS-003 | done | mosaic fleet ps — join systemd+tmux+proc+idle+heartbeat; tenant+host tagged; drift + boot-enable flags; `--json` | FLEET-OBS-001 | worker | — | commit ab47831; LIVE-verified on mosaic-fleet; caught canary-pi DRIFT + BOOT-ENABLE. Polish: idleSeconds parse returns null |
| FLEET-OBS-004 | done | mosaic agent watch <name> — read-only join (no resize, no keystrokes) | FLEET-OBS-000 | worker | — | attach -r; verb wired |
| FLEET-OBS-005 | done | mosaic agent send --verify — delivery/acceptance receipt | FLEET-OBS-000 | worker | — | --verify flag; draft-heuristic verify |
| FLEET-OBS-006 | done | CLI specs for ps/watch/send-verify (tenant+host shape, command construction) | FLEET-OBS-003,004,005 | worker | — | 62 tests green (31 new); re-verified by lead |
| FLEET-OBS-007 | not-started | Framework doc: fleet observability guide + verbs | FLEET-OBS-003,004,005 | lead | — | `docs/guides/` or `framework/tools/.../README` |
| FLEET-OBS-008 | not-started | Independent review + dogfood verification on live fleet | FLEET-OBS-002..007 | reviewer | — | author ≠ reviewer; capture evidence in scratchpad |
| FLEET-OBS-009 | not-started | Open PR → green CI (queue guard) → squash-merge → close `fleet-observability-1` | FLEET-OBS-008 | lead | — | trunk merge; no direct push to main |
| id | status | description | depends_on | agent | pr | notes |
| ------------- | ----------- | ------------------------------------------------------------------------------------------------------------------ | --------------------- | ----------- | --- | --------------------------------------------------------------------------------------------------------------------------- |
| FLEET-OBS-000 | done | Plan: north-star + Phase-2 PRD + workstream scaffolding | — | lead | — | persisted 2026-06-20 on `feat/fleet-observability` |
| FLEET-OBS-001 | done | Heartbeat protocol v1 spec finalized in PRD + framework doc | FLEET-OBS-000 | lead | — | file-based `~/.config/mosaic/fleet/run/<agent>.hb`; spec in PRD |
| FLEET-OBS-002 | in-progress | Implement heartbeat responder in `dogfood-agent.py` | FLEET-OBS-001 | fleet-coder | — | dispatched to ad-hoc `mosaic yolo` fleet agent (dogfood) |
| FLEET-OBS-003 | done | `mosaic fleet ps` — join systemd+tmux+proc+idle+heartbeat; tenant+host tagged; drift + boot-enable flags; `--json` | FLEET-OBS-001 | worker | — | commit ab47831; LIVE-verified on mosaic-fleet; caught canary-pi DRIFT + BOOT-ENABLE. Polish: idleSeconds parse returns null |
| FLEET-OBS-004 | done | `mosaic agent watch <name>` — read-only join (no resize, no keystrokes) | FLEET-OBS-000 | worker | — | `attach -r`; verb wired |
| FLEET-OBS-005 | done | `mosaic agent send --verify` — delivery/acceptance receipt | FLEET-OBS-000 | worker | — | --verify flag; draft-heuristic verify |
| FLEET-OBS-006 | done | CLI specs for ps/watch/send-verify (tenant+host shape, command construction) | FLEET-OBS-003,004,005 | worker | — | 62 tests green (31 new); re-verified by lead |
| FLEET-OBS-007 | not-started | Framework doc: fleet observability guide + verbs | FLEET-OBS-003,004,005 | lead | — | `docs/guides/` or `framework/tools/.../README` |
| FLEET-OBS-008 | not-started | Independent review + dogfood verification on live fleet | FLEET-OBS-002..007 | reviewer | — | author ≠ reviewer; capture evidence in scratchpad |
| FLEET-OBS-009 | not-started | Open PR → green CI (queue guard) → squash-merge → close `fleet-observability-1` | FLEET-OBS-008 | lead | — | trunk merge; no direct push to main |
## Proposed MVP rollup row (for the MVP orchestrator — not written by this workstream)
```text-table
```
| W-FLEET | in-progress | Fleet (agent-session execution layer) | Phase 2/5 | docs/fleet/TASKS.md | observability dogfooded on live stub fleet; control plane rides federation (W1) |
```
+30 -28
View File
@@ -2,10 +2,10 @@
The **backlog** is Mosaic's native backlog-of-record for fleet work. It is built
end-to-end on Mosaic's own storage layer (`@mosaicstack/db`, drizzle/Postgres)
and surfaced as mosaic fleet backlog <sub> --json.
and surfaced as `mosaic fleet backlog <sub> --json`.
> **Mosaic-native, no Hermes.** This backlog REPLACES the former Hermes adapter.
> There is **no** runtime dependency on Hermes, hermes kanban, or ~/.hermes
> There is **no** runtime dependency on Hermes, `hermes kanban`, or `~/.hermes`
> anywhere in this feature. Anything previously delegated to Hermes is recreated
> here on Mosaic's own Postgres storage layer.
@@ -18,7 +18,7 @@ engine (no sqlite, no raw client).
| ---------------------------------- | -------------------- | ---------------------------------------------------------------- |
| `DATABASE_URL` injected at runtime | Full server Postgres | the verified runtime database; it never authorizes migration/DDL |
| `PGLITE_DATA_DIR` set (no URL) | Embedded PGlite | that directory |
| neither (default) | Embedded PGlite | ~/.config/mosaic/fleet/backlog |
| neither (default) | Embedded PGlite | `~/.config/mosaic/fleet/backlog` |
PGlite is real Postgres semantics in-process — including the row locks the atomic
claim relies on — so the **same code** runs on a laptop (embedded, single-host
@@ -28,9 +28,9 @@ For embedded PGlite only, the local backlog routine may prepare its local schema
### Update safety
The embedded PGlite store lives under ~/.config/mosaic/fleet/backlog, which is
The embedded PGlite store lives under `~/.config/mosaic/fleet/backlog`, which is
listed in `PRESERVE_PATHS` in `packages/mosaic/framework/install.sh`. This means
mosaic update (which runs the framework sync with rsync --delete) will **not**
`mosaic update` (which runs the framework sync with `rsync --delete`) will **not**
wipe the operator's backlog — same protection as the roster, per-agent env, and
heartbeat run dir.
@@ -46,10 +46,10 @@ A card is one row in the `backlog` table:
| `phase` | text (nullable) | Board/phase grouping (see below). |
| `priority` | int (default 0) | **Higher = sooner.** Claim picks the max-priority ready card. |
| `status` | enum | `ready` \| `claimed` \| `blocked` \| `done`. |
| `depends_on` | jsonb string[] | DAG edges — ids of cards this one depends on. |
| `depends_on` | jsonb `string[]` | DAG edges — ids of cards this one depends on. |
| `claim_owner` | text (nullable) | Owner token of the active claim. |
| `claim_ttl_seconds` | int (nullable) | TTL of the active claim. |
| `claimed_at` | timestamptz (null) | When the claim was taken. claimed_at + ttl = expiry. |
| `claimed_at` | timestamptz (null) | When the claim was taken. `claimed_at + ttl` = expiry. |
| `attempts` | int (default 0) | Incremented each time the card is claimed. |
| `idempotency_key` | text (unique, null) | Dedups `create`; NULLs are distinct in Postgres. |
| `acceptance` | jsonb (nullable) | Acceptance criteria (array of strings or object). |
@@ -65,12 +65,12 @@ would add ceremony without benefit.
### Board / phase convention
`phase` is a free-form grouping string used as the board column / milestone label
(e.g. `M1`, `fleet`, `infra`). list --phase <phase> filters to one board lane.
(e.g. `M1`, `fleet`, `infra`). `list --phase <phase>` filters to one board lane.
`priority` orders cards **within** the ready pool regardless of phase.
## Status lifecycle
```text-diagram
```
create
@@ -87,49 +87,51 @@ would add ceremony without benefit.
- **blocked** — explicitly parked; never auto-claimed.
- **done** — completed; satisfies dependents.
## Atomic claim (FOR UPDATE SKIP LOCKED) + TTL
## Atomic claim (`FOR UPDATE SKIP LOCKED`) + TTL
`claim` is atomic. Inside a single transaction it locks candidate `ready` rows
with SELECT ... FOR UPDATE SKIP LOCKED (via the drizzle `sql` operator), picks
with `SELECT ... FOR UPDATE SKIP LOCKED` (via the drizzle `sql` operator), picks
the highest-priority deps-satisfied card, and flips it to `claimed`. Because a row
already locked by a concurrent claimer is **skipped**, two claimers can **never**
both win the same card — the loser falls through to the next candidate or gets
`null`. (Proven by the concurrency tests in `packages/db/src/backlog.spec.ts`.)
- **Deps gate:** a card is only claimable when every id in `depends_on` is `done`.
- **TTL:** claim --ttl <sec> (default **900s**) records `claim_ttl_seconds`.
- **reclaim:** releases claims whose claimed_at + ttl is in the past (expired)
back to `ready`, clearing the claim fields. reclaim --id <id> force-releases a
- **TTL:** `claim --ttl <sec>` (default **900s**) records `claim_ttl_seconds`.
- **reclaim:** releases claims whose `claimed_at + ttl` is in the past (expired)
back to `ready`, clearing the claim fields. `reclaim --id <id>` force-releases a
specific card regardless of expiry. This is how a crashed worker's card returns
to the pool.
## CLI — mosaic fleet backlog <sub> --json
## CLI — `mosaic fleet backlog <sub> --json`
All subcommands support `--json`.
| Subcommand | Purpose |
| ------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------- |
| create --id --title [--body --phase --priority --depends-on --acceptance --idempotency-key] | Create a card; `idempotency_key` dedups (repeat returns the existing card). |
| list [--status --phase --ready-only] | List cards. `--ready-only` = status `ready` AND all deps `done`. |
| claim --owner [--ttl <sec> --id <id>] | Atomically claim the highest-priority ready card (or `--id`). Returns the card or `null`. |
| reclaim [--id <id>] | Release expired claims (or a specific card) back to `ready`. |
| link --from --to | Add a `depends_on` edge (`--from` depends on `--to`). |
| `stats` | Counts by status, oldest-ready age, expired-claim count. |
| block --id | Set a card to `blocked`. |
| complete --id | Set a card to `done` (releases any claim). |
| Subcommand | Purpose |
| --------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------- |
| `create --id --title [--body --phase --priority --depends-on --acceptance --idempotency-key]` | Create a card; `idempotency_key` dedups (repeat returns the existing card). |
| `list [--status --phase --ready-only]` | List cards. `--ready-only` = status `ready` AND all deps `done`. |
| `claim --owner [--ttl <sec> --id <id>]` | Atomically claim the highest-priority ready card (or `--id`). Returns the card or `null`. |
| `reclaim [--id <id>]` | Release expired claims (or a specific card) back to `ready`. |
| `link --from --to` | Add a `depends_on` edge (`--from` depends on `--to`). |
| `stats` | Counts by status, oldest-ready age, expired-claim count. |
| `block --id` | Set a card to `blocked`. |
| `complete --id` | Set a card to `done` (releases any claim). |
### Example
Seed two cards; the second depends on the first. Because A2 is gated on A1, claim returns A1 first. Finish A1, then list A2 as ready. Recover stalled work.
```fleet-command
```sh
# Seed two cards, the second depends on the first.
mosaic fleet backlog create --id A1 --title "schema" --priority 5
mosaic fleet backlog create --id A2 --title "service" --depends-on A1 --priority 9
# A2 is gated on A1, so claim returns A1 first.
mosaic fleet backlog claim --owner worker-1 --ttl 600 --json
# Finish A1; now A2 is ready.
mosaic fleet backlog complete --id A1
mosaic fleet backlog list --ready-only --json
# Recover stalled work.
mosaic fleet backlog reclaim --json
```
@@ -1,42 +0,0 @@
# Desired, Derived, and Observed Fleet State
## One writable authority
The canonical local v2 roster at <MOSAIC_HOME>/fleet/roster.yaml is desired state. Membership, stable identity, class, runtime/provider/model selection, launch policy, enablement, and persisted `running`/`stopped` intent are written only through generation-guarded roster mutations.
Derived projections are reproducible consequences of that authority:
- <name>.env.generated;
- exact roster-named tmux sessions on the configured socket after reconciliation;
- systemd service targets managed by installation/reconciliation.
Current systemd unit enablement is not yet lifecycle-conformant at boot: installation can enable every
agent unit, and the launcher projection does not carry `enabled` or `desired_state`. Therefore reboot
preservation for stopped/disabled agents remains an FCM-M3-002 acceptance hold, not a guaranteed
projection behavior.
Observed evidence available to current roster-v2 status commands includes systemd active state, tmux
presence, holder ownership, and unmanaged sessions. Heartbeat files are observational in the wider fleet,
but roster-v2 `status`, `doctor`, and `verify` do not currently read them. Observation never writes back
to the roster.
## Generation and ownership
`generation` is a positive integer concurrency fence. A mutating request must provide the current value. Successful changed CRUD increments it exactly once; stale or concurrent writers fail before mutation. Apply/reconcile rereads the canonical roster under a private exclusive lock and uses only that generation and content for effects.
Ownership is exact, never fuzzy. Reconciliation is limited to roster names, the configured socket, the exact holder session, a private installation identity, and private managed paths. An ownership mismatch, unmanaged session, unsafe path, stale generation, or ambiguous lock fails closed.
## Drift decisions
| Observation | Interpretation | Safe response |
| ---------------------------------------- | ------------------------ | ---------------------------------------------------------------------- |
| Generated file differs or is missing | Derived projection drift | Review apply --dry-run; regenerate from the roster. |
| Desired `running`, exact session missing | `missing-session` | Diagnose ownership/runtime, then reconcile if safe. |
| Desired `stopped`, exact session present | `unexpected-session` | Inspect; reconciliation may stop only the proven roster target. |
| Disabled agent running | `disabled-running` | Inspect; disabled state wins during explicit safe reconciliation. |
| Unknown session on the configured socket | Unmanaged state | Report only. Do not adopt, rename, or kill it. |
| Heartbeat stale in the wider fleet | Liveness evidence | Diagnose separately; current roster-v2 status does not read heartbeat. |
`status` and `doctor` classify. `verify` is also observational but exits non-zero when ownership, drift, or unmanaged-state checks fail. `plan`/apply --dry-run validates proposed projection and lifecycle work without mutation. `apply` and `reconcile` converge only after all preconditions pass.
A partial projection failure does not roll the roster back. Treat the committed roster as authority and regenerate. A lifecycle failure after projection completion preserves both roster and projections for inspection. Sensitive legacy values are never printed; diagnostics are bounded to stable codes, key names where applicable, and hashes.
@@ -1,23 +0,0 @@
# Generated Environment Launch Chain
The launcher consumes validated data, not shell configuration.
1. Read and validate the canonical roster.
2. Render deterministic <name>.env.generated data from that roster.
3. Parse optional <name>.env.local through a strict allowlist.
4. Reject generated-key shadowing, unknown or sensitive-looking keys, unsafe paths/values, duplicates, malformed lines, shell syntax, and command overrides.
5. Derive the runtime command from validated runtime/model/reasoning data.
6. Target only the exact configured tmux socket and roster session after ownership checks.
## File precedence and ownership
| File | Owner | Use |
| ----------------- | ------------------------ | --------------------------------------------------------------------------- |
| `.env.generated` | Mosaic projection writer | Complete deterministic roster projection. Rebuild; do not edit. |
| `.env.local` | Operator | Optional, private, strict machine-local data. Cannot shadow generated keys. |
| `.env` | Legacy input | One-time migration input only; never launch authority. |
| `.env.quarantine` | Private quarantine | Retained unsafe legacy evidence; never loaded by the launcher. |
Neither systemd nor the launcher sources these files. No `eval`, shell expansion, arbitrary `MOSAIC_AGENT_COMMAND`, channel, or secret-reference compatibility path exists. Safe legacy generated keys are regenerated, allowed local keys are relocated, and unsafe material is quarantined.
Diagnostics never expose the rejected value, credential material, or command text. They are bounded to stable rule code, key name where safe, and SHA-256 content identity. See [generated environment reference](../reference/generated-env-boundary.md) and [quarantine operations](../operations/env-quarantine.md).
@@ -1,20 +0,0 @@
# Fleet Identity, Class, and Runtime
Each roster field has one job. Do not use names or model strings as authority shortcuts.
| Concern | Field | Contract |
| ----------------------- | ----------------------------- | -------------------------------------------------------------------------------------------- |
| Stable machine identity | agents[].name | Unique, immutable mutation target and exact service/session name. |
| Display identity | agents[].alias | Human-facing label only; may be changed and grants no authority. |
| Behavioral contract | agents[].class | Resolves through the shared baseline plus `roles.local` persona library. |
| Tool boundary | agents[].tool_policy | Must match protected canonical classes; cannot independently grant authority. |
| Harness | agents[].runtime | One of `claude`, `codex`, `opencode`, or `pi`, declared in `runtimes`. |
| Backend selection | agents[].provider and `model` | Explicit non-empty data; capability validity is not inferred from the display name or class. |
| Effort | agents[].reasoning | `low`, `medium`, or `high`. |
| Local placement | `working_directory` | Explicit safe local work path; not remote placement authority. |
Tess and Ultron are conventional instance/display names only. They are not products, required machine identities, role aliases, or authority-bearing classes. A configurable interaction instance uses class: interaction; a configurable validation instance uses class: validator. Any stable name and alias satisfying the structural contract may be used.
Class aliases are deliberately narrow: implementer → code, reviewer → review, and operator-interaction → interaction. No runtime, provider, model, persona prose, or instance name changes this mapping. See [role classes](../reference/role-classes.md) and the [validated generic example](../examples/roster-v2.yaml).
Roster v2 is local-only. It contains no host/SSH placement, connector, channel, secret-reference, arbitrary-command, per-agent socket, or gateway mapping fields. Those concerns require separate requirements and threat models.
@@ -1,22 +0,0 @@
# Fleet Role Authority and Leases
Role content describes behavior; protected authority is immutable code metadata derived only from the canonical class.
## Required workstream classes
`code`, `review`, `validator`, `orchestrator`, `team-leader`, `enhancer`, and `interaction` are required FCM classes. `merge-gate` is additionally protected because it remains the sole approve-to-land and merge authority.
| Class | Authority | Boundary |
| -------------------------------------------- | ------------------------------------------------- | -------------------------------------------------------------------------------------- |
| `merge-gate` | Approve-to-land and merge | Sole merge authority. |
| `validator` | Issue independent validation evidence/certificate | Never approves landing or merges. |
| `orchestrator` | Orchestrate topology and issue bounded leases | Does not gain merge authority. |
| `team-leader` | Use explicitly leased capacity | Cannot issue leases or mutate roster, credentials, topology authority, or merge state. |
| `interaction` | Receive requests and report status | Cannot orchestrate, issue leases, mutate configuration, or merge. |
| `code`, `review`, `enhancer`, custom classes | No protected authority by default | Persona prose cannot grant protected powers. |
A lease is capacity authorization from an orchestrator, not ownership. It must identify a bounded task or period and does not alter the leased agent's roster identity, role contract, credentials, authority, or persisted lifecycle. Expiry/revocation returns capacity; it does not rewrite the roster.
Semantic validation rejects protected class/tool-policy mismatch in either direction. An instance named Ultron with class: validator remains validation-only. An instance named Tess with class: interaction remains request/status-only. Renaming either instance changes no authority.
For resolver layering and safe customization, see [role classes](../reference/role-classes.md) and [customize roles](../how-to/customize-roles.md).
-61
View File
@@ -1,61 +0,0 @@
version: 2
generation: 1
transport: tmux
tmux:
socket_name: mosaic-fleet
holder_session: _holder
defaults:
working_directory: ~/src
runtime: pi
runtimes:
pi:
reset_command: /new
agents:
- name: code-example
alias: Code Example
class: code
runtime: pi
provider: example-provider
model: example-model
reasoning: medium
tool_policy: code
working_directory: ~/src
persistent_persona: false
reset_between_tasks: true
lifecycle:
enabled: true
desired_state: stopped
launch:
yolo: false
- name: interaction-example
alias: Interaction Example
class: interaction
runtime: pi
provider: example-provider
model: example-model
reasoning: low
tool_policy: interaction
working_directory: ~/src
persistent_persona: true
reset_between_tasks: false
lifecycle:
enabled: true
desired_state: stopped
launch:
yolo: false
- name: validator-example
alias: Validator Example
class: validator
runtime: pi
provider: example-provider
model: example-model
reasoning: high
tool_policy: validator
working_directory: ~/src
persistent_persona: false
reset_between_tasks: true
lifecycle:
enabled: true
desired_state: stopped
launch:
yolo: false
+11 -11
View File
@@ -15,7 +15,7 @@ core.
Connectors implement one small, uniform interface (`src/fleet/connectors/types.ts`):
```typescript
```ts
interface OrchestratorConnector {
readonly kind: 'tmux' | 'discord' | 'matrix';
send(message: OutboundMessage): Promise<SendResult>; // orchestrator → human
@@ -25,11 +25,11 @@ interface OrchestratorConnector {
```
- **send / subscribe / health** — the only surface fleet core depends on. `SendResult` is the
ack half; health() is the liveness half.
ack half; `health()` is the liveness half.
- **Thread-aware by metadata**`OutboundMessage.threadId` / `InboundMessage.threadId` are
optional, so thread-capable connectors (Matrix rooms/threads, the future first-party Mosaic
Discord plugin) fit **without an interface change**.
- **Registry** (`registry.ts`) — implementations register a factory by kind; createConnector(config)
- **Registry** (`registry.ts`) — implementations register a factory by kind; `createConnector(config)`
resolves one from roster config. Phase 1 ships the registry + `resolveConnectorKind` (defaults
`tmux` when a roster declares no connector — **back-compat**); the factories land in Phase 2.
@@ -39,7 +39,7 @@ A roster may carry an optional `connector` block (`roster.schema.json`); absent
```yaml
connector:
kind: matrix
kind: matrix # tmux | discord | matrix
matrix:
homeserver_url: https://matrix.example.internal
user_id: '@mos:example.internal'
@@ -55,12 +55,12 @@ reject a token committed to a shipped file anyway.
The connector speaks the **Matrix client-server API** directly over HTTPS (`fetch` — no SDK needed
for MVP), so it is **homeserver-agnostic**:
| Op | Matrix CS-API |
| ----------- | ----------------------------------------------------------------------- |
| `send` | PUT /\_matrix/client/v3/rooms/{roomId}/send/m.room.message/{txnId} |
| `subscribe` | GET /\_matrix/client/v3/sync (long-poll, `since` token) → room timeline |
| `health` | GET /\_matrix/client/versions (reachable) + …/account/whoami (authed) |
| threads | `m.thread` relations ↔ `threadId` |
| Op | Matrix CS-API |
| ----------- | ------------------------------------------------------------------------ |
| `send` | `PUT /_matrix/client/v3/rooms/{roomId}/send/m.room.message/{txnId}` |
| `subscribe` | `GET /_matrix/client/v3/sync` (long-poll, `since` token) → room timeline |
| `health` | `GET /_matrix/client/versions` (reachable) + `…/account/whoami` (authed) |
| threads | `m.thread` relations ↔ `threadId` |
## Local homeserver (infra, not connector code)
@@ -79,7 +79,7 @@ homeserver choice is a **deployment** concern (a Phase-2 deploy guide), not conn
| ----- | --------------------------------------------------------------------------------------- | ------- |
| **1** | Connector interface + types, registry + kind resolution, roster `connector` schema, doc | ✅ yes |
| 2 | Matrix CS-API client (fetch-based send/sync/health) + registered factory + tests | follow |
| 2 | fleet init / `configure` connector-selection UX; roster parse wires the block | follow |
| 2 | `fleet init` / `configure` connector-selection UX; roster parse wires the block | follow |
| 2 | systemd launch wiring so the orchestrator starts on the chosen connector | follow |
| 3 | Conduit deploy guide; first-party Mosaic Discord (threads) registers as a connector | follow |

Some files were not shown because too many files have changed in this diff Show More