chore: consolidate new foundation and archive v1 (#1495)

This commit is contained in:
2026-09-07 12:32:57 -05:00
3511 changed files with 727899 additions and 10 deletions
+10
View File
@@ -0,0 +1,10 @@
#!/usr/bin/env bash
# Exit 0 only when the capability probe itself succeeds and advertises verify.
# A failed help command and a successful response without verify are both
# unsupported, matching the historical e2e-install-test.sh conditional.
set -uo pipefail
gateway_help_rc=0
gateway_help="$(mosaic gateway --help 2>&1)" || gateway_help_rc=$?
[[ "$gateway_help_rc" -eq 0 ]] || exit 1
grep -q 'verify' <<<"$gateway_help"
+184
View File
@@ -0,0 +1,184 @@
#!/usr/bin/env bash
# ─── Mosaic Stack — End-to-End Install Test ────────────────────────────────────
#
# Runs a clean-container install test to verify the full first-run flow:
# tools/install.sh -> mosaic wizard (non-interactive)
# -> mosaic gateway install
# -> mosaic gateway verify
#
# Usage:
# bash tools/e2e-install-test.sh
#
# Requirements:
# - Docker (skips gracefully if not available)
# - Run from the repository root
#
# How it works:
# 1. Mounts the repository into a node:22-alpine container.
# 2. Installs prerequisites (bash, curl, jq, git) inside the container.
# 3. Runs `bash tools/install.sh --yes --no-auto-launch` to install the
# framework and CLI from the Gitea registry.
# 4. Runs `mosaic wizard --non-interactive` to set up SOUL/USER.
# 5. Runs `mosaic gateway install` with piped defaults (non-interactive).
# 6. Runs `mosaic gateway verify` and checks its exit code.
# NOTE: `mosaic gateway verify` is a new command added in the
# feat/mosaic-first-run-ux branch. If the installed CLI version
# pre-dates this branch (does not have `gateway verify`), the test
# marks this step as EXPECTED-SKIP and reports the installed version.
# 7. Reports PASS or FAIL with a summary.
#
# To run manually:
# cd /path/to/mosaic-stack
# bash tools/e2e-install-test.sh
#
# ──────────────────────────────────────────────────────────────────────────────
set -euo pipefail
REPO_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
IMAGE="node:22-alpine"
CONTAINER_NAME="mosaic-e2e-install-$$"
# ─── Colour helpers ───────────────────────────────────────────────────────────
if [[ -t 1 ]]; then
R=$'\033[0;31m' G=$'\033[0;32m' Y=$'\033[0;33m' BOLD=$'\033[1m' RESET=$'\033[0m'
else
R="" G="" Y="" BOLD="" RESET=""
fi
info() { echo "${BOLD}[e2e]${RESET} $*"; }
ok() { echo "${G}[PASS]${RESET} $*"; }
fail() { echo "${R}[FAIL]${RESET} $*" >&2; }
warn() { echo "${Y}[WARN]${RESET} $*"; }
# ─── Docker availability check ────────────────────────────────────────────────
if ! command -v docker &>/dev/null; then
warn "Docker not found — skipping e2e install test."
warn "Install Docker and re-run this script to exercise the full install flow."
exit 0
fi
if ! docker info &>/dev/null 2>&1; then
warn "Docker daemon is not running or not accessible — skipping e2e install test."
exit 0
fi
info "Docker available — proceeding with e2e install test."
info "Repo root: ${REPO_ROOT}"
info "Container image: ${IMAGE}"
# ─── Inline script that runs INSIDE the container ────────────────────────────
INNER_SCRIPT="$(mktemp /tmp/mosaic-e2e-inner-XXXXXX.sh)"
trap 'rm -f "$INNER_SCRIPT"' EXIT
cat > "$INNER_SCRIPT" <<'INNER_SCRIPT_EOF'
#!/bin/sh
# Bootstrap: /bin/sh until bash is installed, then re-exec.
set -e
echo "=== [inner] Installing system prerequisites ==="
apk add --no-cache bash curl jq git 2>/dev/null || \
apt-get install -y -q bash curl jq git 2>/dev/null || true
# Re-exec under bash.
if [ -z "${BASH_VERSION:-}" ] && command -v bash >/dev/null 2>&1; then
exec bash "$0" "$@"
fi
# ── bash from here ────────────────────────────────────────────────────────────
set -euo pipefail
echo "=== [inner] Node.js / npm versions ==="
node --version
npm --version
echo "=== [inner] Setting up npm global prefix ==="
export NPM_PREFIX="/root/.npm-global"
mkdir -p "$NPM_PREFIX/bin"
npm config set prefix "$NPM_PREFIX" 2>/dev/null || true
export PATH="$NPM_PREFIX/bin:$PATH"
echo "=== [inner] Running install.sh --yes --no-auto-launch ==="
# Install both framework and CLI from the Gitea registry.
MOSAIC_SKIP_SKILLS_SYNC=1 \
MOSAIC_ASSUME_YES=1 \
bash /repo/tools/install.sh --yes --no-auto-launch
INSTALLED_VERSION="$(mosaic --version 2>/dev/null || echo 'unknown')"
echo "[inner] mosaic CLI installed: ${INSTALLED_VERSION}"
echo "=== [inner] Running mosaic wizard (non-interactive) ==="
mosaic wizard \
--non-interactive \
--name "test-agent" \
--user-name "tester" \
--pronouns "they/them" \
--timezone "UTC" || {
echo "[WARN] mosaic wizard exited non-zero — continuing"
}
echo "=== [inner] Running mosaic gateway install ==="
# Feed non-interactive answers:
# "1" → storage tier: local
# "" → port: accept default (14242)
# "" → ANTHROPIC_API_KEY: skip
# "" → CORS origin: accept default
# Then admin bootstrap: name, email, password
printf '1\n\n\n\nTest Admin\[email protected]\ntestpassword123\n' \
| mosaic gateway install
INSTALL_EXIT="$?"
if [ "${INSTALL_EXIT}" -ne 0 ]; then
echo "[ERR] mosaic gateway install exited ${INSTALL_EXIT}"
mosaic gateway status 2>/dev/null || true
exit "${INSTALL_EXIT}"
fi
echo "=== [inner] Running mosaic gateway verify ==="
# `gateway verify` was added in feat/mosaic-first-run-ux.
# If the installed version pre-dates this, skip gracefully.
if ! bash /repo/tools/e2e-gateway-verify-supported.sh; then
echo "[SKIP] 'mosaic gateway verify' not available in installed version ${INSTALLED_VERSION}."
echo "[SKIP] This command was added in the feat/mosaic-first-run-ux release."
echo "[SKIP] Re-run after the new version is published to validate this step."
# Treat as pass — the install flow itself worked.
exit 0
fi
mosaic gateway verify
VERIFY_EXIT="$?"
echo "=== [inner] verify exit code: ${VERIFY_EXIT} ==="
exit "${VERIFY_EXIT}"
INNER_SCRIPT_EOF
chmod +x "$INNER_SCRIPT"
# ─── Pull image ───────────────────────────────────────────────────────────────
info "Pulling ${IMAGE}"
docker pull "${IMAGE}" --quiet
# ─── Run container ────────────────────────────────────────────────────────────
info "Starting container ${CONTAINER_NAME}"
EXIT_CODE=0
docker run --rm \
--name "${CONTAINER_NAME}" \
--volume "${REPO_ROOT}:/repo:ro" \
--volume "${INNER_SCRIPT}:/e2e-inner.sh:ro" \
--network host \
"${IMAGE}" \
/bin/sh /e2e-inner.sh \
|| EXIT_CODE=$?
# ─── Report ───────────────────────────────────────────────────────────────────
echo ""
if [[ "$EXIT_CODE" -eq 0 ]]; then
ok "End-to-end install test PASSED (exit ${EXIT_CODE})"
else
fail "End-to-end install test FAILED (exit ${EXIT_CODE})"
echo ""
echo " Troubleshooting:"
echo " - Review the output above for the failing step."
echo " - Re-run with bash -x tools/e2e-install-test.sh for verbose trace."
echo " - Run mosaic gateway logs inside a manual container for daemon output."
exit 1
fi
+254
View File
@@ -0,0 +1,254 @@
# Federation Test Harness
Local two-gateway federation test infrastructure for Mosaic Stack M3+.
This harness boots two real gateway instances (`gateway-a`, `gateway-b`) on a
shared Docker bridge network, each backed by its own Postgres (pgvector) +
Valkey, sharing a single Step-CA. It is the test bed for all M3+ federation
E2E tests.
## Prerequisites
- Docker with Compose v2 (`docker compose version` ≥ 2.20)
- pnpm (for running via repo scripts)
- `infra/step-ca/dev-password` must exist (copy from `infra/step-ca/dev-password.example`)
## Network Topology
```
Host machine
├── localhost:14001 → gateway-a (Server A — home / requesting)
├── localhost:14002 → gateway-b (Server B — work / serving)
├── localhost:15432 → postgres-a
├── localhost:15433 → postgres-b
├── localhost:16379 → valkey-a
├── localhost:16380 → valkey-b
└── localhost:19000 → step-ca (shared CA)
Docker network: fed-test-net (bridge)
gateway-a ←──── mTLS ────→ gateway-b
↘ ↗
step-ca
```
Ports are chosen to avoid collision with the base dev stack (5433, 6380, 14242, 9000).
## Starting the Harness
```bash
# From repo root
docker compose -f tools/federation-harness/docker-compose.two-gateways.yml up -d
# Wait for all services to be healthy (~60-90s on first boot due to NestJS cold start)
docker compose -f tools/federation-harness/docker-compose.two-gateways.yml ps
```
## Seeding Test Data
The seed script provisions three grant scope variants (A, B, C) and walks the
full enrollment flow so Server A ends up with active peers pointing at Server B.
```bash
# Assumes stack is already running
pnpm tsx tools/federation-harness/seed.ts
# Or boot + seed in one step
pnpm tsx tools/federation-harness/seed.ts --boot
```
### Scope Variants
| Variant | Resources | Filters | Excluded | Purpose |
| ------- | ------------------ | ---------------------------------- | ----------- | ------------------------------- |
| A | tasks, notes | include_personal: true | (none) | Personal data federation |
| B | tasks | include_teams: ['T1'], no personal | (none) | Team-scoped, no personal |
| C | tasks, credentials | include_personal: true | credentials | Sanity: excluded wins over list |
## Using from Vitest
```ts
import {
bootHarness,
tearDownHarness,
serverA,
serverB,
seed,
} from '../../tools/federation-harness/harness.js';
import type { HarnessHandle } from '../../tools/federation-harness/harness.js';
let handle: HarnessHandle;
beforeAll(async () => {
handle = await bootHarness();
}, 180_000); // allow 3 min for Docker pull + NestJS cold start
afterAll(async () => {
await tearDownHarness(handle);
});
test('variant A: list tasks returns personal tasks', async () => {
// NOTE: Only 'all' is supported for now — per-variant narrowing is M3-11.
const seedResult = await seed(handle, 'all');
const a = serverA(handle);
const res = await fetch(`${a.baseUrl}/api/federation/tasks`, {
headers: { 'x-federation-grant': seedResult.grants.variantA.id },
});
expect(res.status).toBe(200);
});
```
> **Note:** `seed()` bootstraps a fresh admin user on each gateway via
> `POST /api/bootstrap/setup`. Both gateways must have zero users (pristine DB).
> If either gateway already has users, `seed()` throws with a clear error.
> Reset state with `docker compose down -v`.
The `bootHarness()` function is **idempotent**: if both gateways are already
healthy, it reuses the running stack and returns `ownedStack: false`. Tests
should not call `tearDownHarness` when `ownedStack` is false unless they
explicitly want to shut down a shared stack.
## Vitest Config (pnpm test:federation)
Add to `vitest.config.ts` at repo root (or a dedicated config):
```ts
// vitest.federation.config.ts
import { defineConfig } from 'vitest/config';
export default defineConfig({
test: {
include: ['**/*.federation.test.ts'],
testTimeout: 60_000,
hookTimeout: 180_000,
reporters: ['verbose'],
},
});
```
Then add to root `package.json`:
```json
"test:federation": "vitest run --config vitest.federation.config.ts"
```
## Nuking State
```bash
# Remove containers AND volumes (ephemeral state — CA keys, DBs, everything)
docker compose -f tools/federation-harness/docker-compose.two-gateways.yml down -v
```
On next `up`, Step-CA re-initialises from scratch and generates new CA keys.
## Step-CA Root Certificate
The CA root lives in the `fed-harness-step-ca` Docker volume at
`/home/step/certs/root_ca.crt`. To extract it to the host:
```bash
docker run --rm \
-v fed-harness-step-ca:/home/step \
alpine cat /home/step/certs/root_ca.crt > /tmp/fed-harness-root-ca.crt
```
## Troubleshooting
### Port conflicts
Default host ports: 14001, 14002, 15432, 15433, 16379, 16380, 19000.
Override via environment variables before `docker compose up`:
```bash
GATEWAY_A_HOST_PORT=14101 GATEWAY_B_HOST_PORT=14102 \
docker compose -f tools/federation-harness/docker-compose.two-gateways.yml up -d
```
### Image pull failures
The gateway image is digest-pinned to:
```
git.mosaicstack.dev/mosaicstack/stack/gateway@sha256:1069117740e00ccfeba357cae38c43f3729fe5ae702740ce474f6512414d7c02
```
(sha-9f1a081, post-#491 IMG-FIX)
If the registry is unreachable, Docker will use the locally cached image if
present. If no local image exists, the compose up will fail with a pull error.
In that case:
1. Ensure you can reach `git.mosaicstack.dev` (VPN, DNS, etc.).
2. Log in: `docker login git.mosaicstack.dev`
3. Pull manually: `docker pull git.mosaicstack.dev/mosaicstack/stack/gateway@sha256:1069117740e00ccfeba357cae38c43f3729fe5ae702740ce474f6512414d7c02`
### NestJS cold start
Gateway containers take 4060 seconds to become healthy on first boot (Node.js
module resolution + NestJS DI bootstrap). The `start_period: 60s` in the
compose healthcheck covers this. `bootHarness()` polls for up to 3 minutes.
### Step-CA startup
Step-CA initialises on first boot (generates CA keys). This takes ~5-10s.
The `start_period: 30s` in the healthcheck covers it. Both gateways wait for
Step-CA to be healthy before starting (`depends_on: step-ca: condition: service_healthy`).
### dev-password missing
The Step-CA container requires `infra/step-ca/dev-password` to be mounted.
Copy the example and set a local password:
```bash
cp infra/step-ca/dev-password.example infra/step-ca/dev-password
# Edit the file to set your preferred dev CA password
```
The file is `.gitignore`d — do not commit it.
## Image Digest Note
The gateway image is pinned to `sha256:1069117740e00ccfeba357cae38c43f3729fe5ae702740ce474f6512414d7c02`
(sha-9f1a081). This is the digest promoted by PR #491 (IMG-FIX). The `latest`
tag is forbidden per Mosaic image policy. When a new gateway build is promoted,
update the digest in `docker-compose.two-gateways.yml` and in this file.
## Known Limitations
### BETTER_AUTH_URL enrollment URL bug (upstream production code — not yet fixed)
`apps/gateway/src/federation/federation.controller.ts:145` constructs the
enrollment URL using `process.env['BETTER_AUTH_URL'] ?? 'http://localhost:14242'`.
This is an upstream bug: `BETTER_AUTH_URL` is the Better Auth origin (typically
the web app), not the gateway's own base URL. In non-harness deployments this
produces an enrollment URL pointing to the wrong host or port.
**How the harness handles this:**
1. **In-cluster calls (container-to-container):** The compose file sets
`BETTER_AUTH_URL: 'http://gateway-b:3000'` so the enrollment URL returned by
the gateway uses the Docker internal hostname. This lets other containers in the
`fed-test-net` network resolve and reach Server B's enrollment endpoint.
2. **Host-side URL rewrite (seed script):** The `seed.ts` script runs on the host
machine where `gateway-b` is not a resolvable hostname. Before calling
`fetch(enrollmentUrl, ...)`, the seed script rewrites the URL: it extracts only
the token path segment from `enrollmentUrl` and reassembles the URL using the
host-accessible `serverBUrl` (default: `http://localhost:14002`). This lets the
seed script redeem enrollment tokens from the host without being affected by the
in-cluster hostname in the returned URL.
**TODO:** Fix `federation.controller.ts` to derive the enrollment URL from its own
listening address (e.g. `GATEWAY_BASE_URL` env var or a dedicated
`FEDERATION_ENROLLMENT_BASE_URL` env var) rather than reusing `BETTER_AUTH_URL`.
Tracked as a follow-up to PR #505 — do not bundle with harness changes.
## Permanent Infrastructure
This harness is designed to outlive M3 and be reused by M4+ milestone tests.
It is not a throwaway scaffold — treat it as production test infrastructure:
- Keep it idempotent.
- Do not hardcode test assumptions in the harness layer (put them in tests).
- Update the seed script when new scope variants are needed.
- The README and harness should be kept in sync as the federation API evolves.
@@ -0,0 +1,247 @@
# tools/federation-harness/docker-compose.two-gateways.yml
#
# Two-gateway federation test harness — local-only, no Portainer/Swarm needed.
#
# USAGE (manual):
# docker compose -f tools/federation-harness/docker-compose.two-gateways.yml up -d
# docker compose -f tools/federation-harness/docker-compose.two-gateways.yml down -v
#
# USAGE (from harness.ts):
# const handle = await bootHarness();
# ...
# await tearDownHarness(handle);
#
# TOPOLOGY:
# gateway-a — "home" instance (Server A, the requesting side)
# └── postgres-a (pgvector/pg17, port 15432)
# └── valkey-a (port 16379)
# gateway-b — "work" instance (Server B, the serving side)
# └── postgres-b (pgvector/pg17, port 15433)
# └── valkey-b (port 16380)
# step-ca — shared CA for both gateways (port 19000)
#
# All services share the `fed-test-net` bridge network.
# Host port ranges (15432-15433, 16379-16380, 14001-14002, 19000) are chosen
# to avoid collision with the base dev stack (5433, 6380, 14242, 9000).
#
# IMAGE:
# Pinned to the immutable digest sha256:1069117740e00ccfeba357cae38c43f3729fe5ae702740ce474f6512414d7c02
# (sha-9f1a081, post-#491 IMG-FIX, smoke-tested locally).
# Update this digest only after a new CI build is promoted to the registry.
#
# STEP-CA:
# Single shared Step-CA instance. Both gateways connect to it.
# CA volume is ephemeral per `docker compose down -v`; regenerated on next up.
# The harness seed script provisions the CA roots cross-trust after first boot.
services:
# ─── Shared Certificate Authority ────────────────────────────────────────────
step-ca:
image: smallstep/step-ca:0.27.4
container_name: fed-harness-step-ca
restart: unless-stopped
ports:
- '${STEP_CA_HOST_PORT:-19000}:9000'
volumes:
- step_ca_data:/home/step
- ../../infra/step-ca/init.sh:/usr/local/bin/mosaic-step-ca-init.sh:ro
- ../../infra/step-ca/templates:/etc/step-ca-templates:ro
- ../../infra/step-ca/dev-password:/run/secrets/ca_password:ro
entrypoint: ['/bin/sh', '/usr/local/bin/mosaic-step-ca-init.sh']
networks:
- fed-test-net
healthcheck:
test:
[
'CMD',
'step',
'ca',
'health',
'--ca-url',
'https://localhost:9000',
'--root',
'/home/step/certs/root_ca.crt',
]
interval: 10s
timeout: 5s
retries: 5
start_period: 30s
# ─── Server A — Home / Requesting Gateway ────────────────────────────────────
postgres-a:
image: pgvector/pgvector:pg17
container_name: fed-harness-postgres-a
restart: unless-stopped
ports:
- '${PG_A_HOST_PORT:-15432}:5432'
environment:
POSTGRES_USER: mosaic
POSTGRES_PASSWORD: mosaic
POSTGRES_DB: mosaic
volumes:
- pg_a_data:/var/lib/postgresql/data
- ../../infra/pg-init:/docker-entrypoint-initdb.d:ro
networks:
- fed-test-net
healthcheck:
test: ['CMD-SHELL', 'pg_isready -U mosaic']
interval: 5s
timeout: 3s
retries: 5
valkey-a:
image: valkey/valkey:8-alpine
container_name: fed-harness-valkey-a
restart: unless-stopped
ports:
- '${VALKEY_A_HOST_PORT:-16379}:6379'
volumes:
- valkey_a_data:/data
networks:
- fed-test-net
healthcheck:
test: ['CMD', 'valkey-cli', 'ping']
interval: 5s
timeout: 3s
retries: 5
gateway-a:
image: git.mosaicstack.dev/mosaicstack/stack/gateway@sha256:1069117740e00ccfeba357cae38c43f3729fe5ae702740ce474f6512414d7c02
# Tag for human reference: sha-9f1a081 (post-#491 IMG-FIX; smoke-tested locally)
container_name: fed-harness-gateway-a
restart: unless-stopped
ports:
- '${GATEWAY_A_HOST_PORT:-14001}:3000'
environment:
MOSAIC_TIER: federated
DATABASE_URL: postgres://mosaic:mosaic@postgres-a:5432/mosaic
VALKEY_URL: redis://valkey-a:6379
GATEWAY_PORT: '3000'
GATEWAY_CORS_ORIGIN: 'http://localhost:14001'
BETTER_AUTH_SECRET: harness-secret-server-a-do-not-use-in-prod
BETTER_AUTH_URL: 'http://gateway-a:3000'
STEP_CA_URL: 'https://step-ca:9000'
FEDERATION_PEER_HOSTNAME: gateway-a
# Bootstrap password for POST /api/bootstrap/setup — used by seed.ts to create
# the first admin user. Only valid on a pristine (zero-user) database.
# Not the same as ADMIN_API_KEY — there is no static API key in the gateway.
ADMIN_BOOTSTRAP_PASSWORD: harness-admin-password-a
depends_on:
postgres-a:
condition: service_healthy
valkey-a:
condition: service_healthy
step-ca:
condition: service_healthy
networks:
- fed-test-net
healthcheck:
test:
[
'CMD',
'node',
'-e',
"require('http').get('http://127.0.0.1:3000/api/health', r => process.exit(r.statusCode === 200 ? 0 : 1)).on('error', () => process.exit(1))",
]
interval: 10s
timeout: 5s
retries: 5
start_period: 60s
# ─── Server B — Work / Serving Gateway ──────────────────────────────────────
postgres-b:
image: pgvector/pgvector:pg17
container_name: fed-harness-postgres-b
restart: unless-stopped
ports:
- '${PG_B_HOST_PORT:-15433}:5432'
environment:
POSTGRES_USER: mosaic
POSTGRES_PASSWORD: mosaic
POSTGRES_DB: mosaic
volumes:
- pg_b_data:/var/lib/postgresql/data
- ../../infra/pg-init:/docker-entrypoint-initdb.d:ro
networks:
- fed-test-net
healthcheck:
test: ['CMD-SHELL', 'pg_isready -U mosaic']
interval: 5s
timeout: 3s
retries: 5
valkey-b:
image: valkey/valkey:8-alpine
container_name: fed-harness-valkey-b
restart: unless-stopped
ports:
- '${VALKEY_B_HOST_PORT:-16380}:6379'
volumes:
- valkey_b_data:/data
networks:
- fed-test-net
healthcheck:
test: ['CMD', 'valkey-cli', 'ping']
interval: 5s
timeout: 3s
retries: 5
gateway-b:
image: git.mosaicstack.dev/mosaicstack/stack/gateway@sha256:1069117740e00ccfeba357cae38c43f3729fe5ae702740ce474f6512414d7c02
# Tag for human reference: sha-9f1a081 (post-#491 IMG-FIX; smoke-tested locally)
container_name: fed-harness-gateway-b
restart: unless-stopped
ports:
- '${GATEWAY_B_HOST_PORT:-14002}:3000'
environment:
MOSAIC_TIER: federated
DATABASE_URL: postgres://mosaic:mosaic@postgres-b:5432/mosaic
VALKEY_URL: redis://valkey-b:6379
GATEWAY_PORT: '3000'
GATEWAY_CORS_ORIGIN: 'http://localhost:14002'
BETTER_AUTH_SECRET: harness-secret-server-b-do-not-use-in-prod
BETTER_AUTH_URL: 'http://gateway-b:3000'
STEP_CA_URL: 'https://step-ca:9000'
FEDERATION_PEER_HOSTNAME: gateway-b
# Bootstrap password for POST /api/bootstrap/setup — used by seed.ts to create
# the first admin user. Only valid on a pristine (zero-user) database.
# Not the same as ADMIN_API_KEY — there is no static API key in the gateway.
ADMIN_BOOTSTRAP_PASSWORD: harness-admin-password-b
depends_on:
postgres-b:
condition: service_healthy
valkey-b:
condition: service_healthy
step-ca:
condition: service_healthy
networks:
- fed-test-net
healthcheck:
test:
[
'CMD',
'node',
'-e',
"require('http').get('http://127.0.0.1:3000/api/health', r => process.exit(r.statusCode === 200 ? 0 : 1)).on('error', () => process.exit(1))",
]
interval: 10s
timeout: 5s
retries: 5
start_period: 60s
networks:
fed-test-net:
name: fed-test-net
driver: bridge
volumes:
step_ca_data:
name: fed-harness-step-ca
pg_a_data:
name: fed-harness-pg-a
valkey_a_data:
name: fed-harness-valkey-a
pg_b_data:
name: fed-harness-pg-b
valkey_b_data:
name: fed-harness-valkey-b
+290
View File
@@ -0,0 +1,290 @@
/**
* tools/federation-harness/harness.ts
*
* Vitest-consumable helpers for the two-gateway federation harness.
*
* USAGE (in a vitest test file):
*
* import { bootHarness, tearDownHarness, serverA, serverB, seed } from
* '../../tools/federation-harness/harness.js';
*
* let handle: HarnessHandle;
*
* beforeAll(async () => {
* handle = await bootHarness();
* }, 180_000);
*
* afterAll(async () => {
* await tearDownHarness(handle);
* });
*
* test('variant A — list tasks', async () => {
* const seedResult = await seed(handle, 'all');
* const a = serverA(handle);
* const res = await fetch(`${a.baseUrl}/api/federation/list/tasks`, {
* headers: { Authorization: `Bearer ${seedResult.adminTokenA}` },
* });
* expect(res.status).toBe(200);
* });
*
* NOTE: The `seed()` helper currently only supports scenario='all'. Passing any
* other value throws immediately. Per-variant narrowing is deferred to M3-11.
*
* ESM / NodeNext: all imports use .js extensions.
*/
import { execSync, execFileSync } from 'node:child_process';
import { resolve, dirname } from 'node:path';
import { fileURLToPath } from 'node:url';
import { runSeed, type SeedResult } from './seed.js';
// ─── Types ───────────────────────────────────────────────────────────────────
export interface GatewayAccessor {
/** Base URL reachable from the host machine, e.g. http://localhost:14001 */
baseUrl: string;
/** Bootstrap password used for POST /api/bootstrap/setup on a pristine gateway */
bootstrapPassword: string;
/** Internal Docker network hostname (for container-to-container calls) */
internalHostname: string;
}
export interface HarnessHandle {
/** Server A accessor */
a: GatewayAccessor;
/** Server B accessor */
b: GatewayAccessor;
/** Absolute path to the docker-compose file */
composeFile: string;
/** Whether this instance booted the stack (vs. reusing an existing one) */
ownedStack: boolean;
/** Optional seed result if seed() was called */
seedResult?: SeedResult;
}
/**
* Scenario to seed. Currently only 'all' is implemented; per-variant narrowing
* is tracked as M3-11. Passing any other value throws immediately with a clear
* error rather than silently over-seeding.
*/
export type SeedScenario = 'variantA' | 'variantB' | 'variantC' | 'all';
// ─── Constants ────────────────────────────────────────────────────────────────
const __dirname = dirname(fileURLToPath(import.meta.url));
const COMPOSE_FILE = resolve(__dirname, 'docker-compose.two-gateways.yml');
const GATEWAY_A_URL = process.env['GATEWAY_A_URL'] ?? 'http://localhost:14001';
const GATEWAY_B_URL = process.env['GATEWAY_B_URL'] ?? 'http://localhost:14002';
const ADMIN_BOOTSTRAP_PASSWORD_A =
process.env['ADMIN_BOOTSTRAP_PASSWORD_A'] ?? 'harness-admin-password-a';
const ADMIN_BOOTSTRAP_PASSWORD_B =
process.env['ADMIN_BOOTSTRAP_PASSWORD_B'] ?? 'harness-admin-password-b';
const READINESS_TIMEOUT_MS = 180_000;
const READINESS_POLL_MS = 3_000;
// ─── Internal helpers ─────────────────────────────────────────────────────────
async function isGatewayHealthy(baseUrl: string): Promise<boolean> {
try {
const res = await fetch(`${baseUrl}/api/health`, { signal: AbortSignal.timeout(5_000) });
return res.ok;
} catch {
return false;
}
}
/**
* Poll both gateways in parallel until both are healthy or the shared deadline
* expires. Polling in parallel (rather than sequentially) avoids the bug where
* a slow gateway-a consumes all of the readiness budget before gateway-b is
* checked.
*/
async function waitForStack(handle: HarnessHandle): Promise<void> {
const gateways: Array<{ label: string; url: string }> = [
{ label: 'gateway-a', url: handle.a.baseUrl },
{ label: 'gateway-b', url: handle.b.baseUrl },
];
await Promise.all(
gateways.map(async (gw) => {
// Each gateway gets its own independent deadline.
const deadline = Date.now() + READINESS_TIMEOUT_MS;
process.stdout.write(`[harness] Waiting for ${gw.label}...`);
while (Date.now() < deadline) {
if (await isGatewayHealthy(gw.url)) {
process.stdout.write(` ready\n`);
return;
}
if (Date.now() + READINESS_POLL_MS > deadline) {
throw new Error(
`[harness] ${gw.label} did not become healthy within ${READINESS_TIMEOUT_MS.toString()}ms`,
);
}
await new Promise((r) => setTimeout(r, READINESS_POLL_MS));
process.stdout.write('.');
}
throw new Error(
`[harness] ${gw.label} did not become healthy within ${READINESS_TIMEOUT_MS.toString()}ms`,
);
}),
);
}
function isStackRunning(): boolean {
try {
const output = execFileSync(
'docker',
['compose', '-f', COMPOSE_FILE, 'ps', '--format', 'json'],
{ encoding: 'utf8', stdio: ['pipe', 'pipe', 'pipe'] },
);
if (!output.trim()) return false;
// Parse JSON lines — each running service emits a JSON object per line
const lines = output.trim().split('\n').filter(Boolean);
const runningServices = lines.filter((line) => {
try {
const obj = JSON.parse(line) as { State?: string };
return obj.State === 'running';
} catch {
return false;
}
});
// Expect at least gateway-a and gateway-b running
return runningServices.length >= 2;
} catch {
return false;
}
}
// ─── Public API ───────────────────────────────────────────────────────────────
/**
* Boot the harness stack.
*
* Idempotent: if the stack is already running and both gateways are healthy,
* this function reuses the existing stack and returns a handle with
* `ownedStack: false`. Callers that set `ownedStack: false` should NOT call
* `tearDownHarness` unless they explicitly want to tear down a pre-existing stack.
*
* If the stack is not running, it starts it with `docker compose up -d` and
* waits for both gateways to pass their /api/health probe.
*/
export async function bootHarness(): Promise<HarnessHandle> {
const handle: HarnessHandle = {
a: {
baseUrl: GATEWAY_A_URL,
bootstrapPassword: ADMIN_BOOTSTRAP_PASSWORD_A,
internalHostname: 'gateway-a',
},
b: {
baseUrl: GATEWAY_B_URL,
bootstrapPassword: ADMIN_BOOTSTRAP_PASSWORD_B,
internalHostname: 'gateway-b',
},
composeFile: COMPOSE_FILE,
ownedStack: false,
};
// Check if both gateways are already healthy
const [aHealthy, bHealthy] = await Promise.all([
isGatewayHealthy(handle.a.baseUrl),
isGatewayHealthy(handle.b.baseUrl),
]);
if (aHealthy && bHealthy) {
console.log('[harness] Stack already running — reusing existing stack.');
handle.ownedStack = false;
return handle;
}
console.log('[harness] Starting federation harness stack...');
execSync(`docker compose -f "${COMPOSE_FILE}" up -d`, { stdio: 'inherit' });
handle.ownedStack = true;
await waitForStack(handle);
console.log('[harness] Stack is ready.');
return handle;
}
/**
* Tear down the harness stack.
*
* Runs `docker compose down -v` to remove containers AND volumes (ephemeral state).
* Only tears down if `handle.ownedStack` is true unless `force` is set.
*/
export async function tearDownHarness(
handle: HarnessHandle,
opts?: { force?: boolean },
): Promise<void> {
if (!handle.ownedStack && !opts?.force) {
console.log(
'[harness] Stack not owned by this handle — skipping teardown (pass force: true to override).',
);
return;
}
console.log('[harness] Tearing down federation harness stack...');
execSync(`docker compose -f "${handle.composeFile}" down -v`, { stdio: 'inherit' });
console.log('[harness] Stack torn down.');
}
/**
* Return the Server A accessor from a harness handle.
* Convenience wrapper for test readability.
*/
export function serverA(handle: HarnessHandle): GatewayAccessor {
return handle.a;
}
/**
* Return the Server B accessor from a harness handle.
* Convenience wrapper for test readability.
*/
export function serverB(handle: HarnessHandle): GatewayAccessor {
return handle.b;
}
/**
* Seed the harness with test data for one or more scenarios.
*
* @param handle The harness handle returned by bootHarness().
* @param scenario Which scope variants to provision. Currently only 'all' is
* supported — passing any other value throws immediately with a
* clear error. Per-variant narrowing is tracked as M3-11.
*
* Returns a SeedResult with grant IDs, peer IDs, and admin tokens for each
* gateway, which test assertions can reference.
*
* IMPORTANT: The harness assumes a pristine database on both gateways. The seed
* bootstraps an admin user on each gateway via POST /api/bootstrap/setup. If
* either gateway already has users, seed() throws with a clear error message.
* Run 'docker compose down -v' to reset state.
*/
export async function seed(
handle: HarnessHandle,
scenario: SeedScenario = 'all',
): Promise<SeedResult> {
if (scenario !== 'all') {
throw new Error(
`seed: scenario narrowing not yet implemented; pass "all" for now. ` +
`Got: "${scenario}". Per-variant narrowing is tracked as M3-11.`,
);
}
const result = await runSeed({
serverAUrl: handle.a.baseUrl,
serverBUrl: handle.b.baseUrl,
adminBootstrapPasswordA: handle.a.bootstrapPassword,
adminBootstrapPasswordB: handle.b.bootstrapPassword,
});
handle.seedResult = result;
return result;
}
+603
View File
@@ -0,0 +1,603 @@
#!/usr/bin/env tsx
/**
* tools/federation-harness/seed.ts
*
* Provisions test data for the two-gateway federation harness.
* Run via: tsx tools/federation-harness/seed.ts
*
* What this script does:
* 1. (Optional) Boots the compose stack if --boot flag is passed.
* 2. Waits for both gateways to be healthy.
* 3. Bootstraps an admin user + token on each gateway via POST /api/bootstrap/setup.
* 4. Creates three grants on Server B matching the M3 acceptance test scenarios:
* - Scope variant A: tasks + notes, include_personal: true
* - Scope variant B: tasks only, include_teams: ['T1'], exclude T2
* - Scope variant C: tasks + credentials in resources, credentials excluded (sanity)
* 5. For each grant, walks the full enrollment flow:
* a. Server B creates a peer keypair (represents the requesting side).
* b. Server B creates the grant referencing that peer.
* c. Server B issues an enrollment token.
* d. Server A creates its own peer keypair (represents its view of B).
* e. Server A redeems the enrollment token at Server B's enrollment endpoint,
* submitting A's CSR → receives signed cert back.
* f. Server A stores the cert on its peer record → peer becomes active.
* 6. Inserts representative test tasks/notes/credentials on Server B.
*
* IMPORTANT: This script uses the real admin REST API — no direct DB writes.
* It exercises the full enrollment flow as M3 acceptance tests will.
*
* ESM / NodeNext: all imports use .js extensions.
*/
import { execSync } from 'node:child_process';
import { resolve, dirname } from 'node:path';
import { fileURLToPath } from 'node:url';
// ─── Constants ───────────────────────────────────────────────────────────────
const __dirname = dirname(fileURLToPath(import.meta.url));
const COMPOSE_FILE = resolve(__dirname, 'docker-compose.two-gateways.yml');
/** Base URLs as seen from the host machine (mapped host ports). */
const SERVER_A_URL = process.env['GATEWAY_A_URL'] ?? 'http://localhost:14001';
const SERVER_B_URL = process.env['GATEWAY_B_URL'] ?? 'http://localhost:14002';
/**
* Bootstrap passwords used when calling POST /api/bootstrap/setup on each
* gateway. Each gateway starts with zero users and requires a one-time setup
* call before any admin-guarded endpoints can be used.
*/
const ADMIN_BOOTSTRAP_PASSWORD_A =
process.env['ADMIN_BOOTSTRAP_PASSWORD_A'] ?? 'harness-admin-password-a';
const ADMIN_BOOTSTRAP_PASSWORD_B =
process.env['ADMIN_BOOTSTRAP_PASSWORD_B'] ?? 'harness-admin-password-b';
const READINESS_TIMEOUT_MS = 120_000;
const READINESS_POLL_MS = 3_000;
// ─── Scope variant definitions (for M3 acceptance tests) ─────────────────────
/** Scope variant A — tasks + notes, personal data included. */
export const SCOPE_VARIANT_A = {
resources: ['tasks', 'notes'],
filters: {
tasks: { include_personal: true },
notes: { include_personal: true },
},
excluded_resources: [] as string[],
max_rows_per_query: 500,
};
/** Scope variant B — tasks only, team T1 only, no personal. */
export const SCOPE_VARIANT_B = {
resources: ['tasks'],
filters: {
tasks: { include_teams: ['T1'], include_personal: false },
},
excluded_resources: [] as string[],
max_rows_per_query: 500,
};
/**
* Scope variant C — tasks + credentials in resources list, but credentials
* explicitly in excluded_resources. Sanity test: credentials must still be
* inaccessible even though they appear in resources.
*/
export const SCOPE_VARIANT_C = {
resources: ['tasks', 'credentials'],
filters: {
tasks: { include_personal: true },
},
excluded_resources: ['credentials'],
max_rows_per_query: 500,
};
// ─── Inline types (no import from packages/types — M3-01 branch not yet merged) ─
interface AdminFetchOptions {
method?: string;
body?: unknown;
adminToken: string;
}
interface PeerRecord {
peerId: string;
csrPem: string;
}
interface GrantRecord {
id: string;
status: string;
scope: unknown;
}
interface EnrollmentTokenResult {
token: string;
expiresAt: string;
enrollmentUrl: string;
}
interface EnrollmentRedeemResult {
certPem: string;
certChainPem: string;
}
interface BootstrapResult {
adminUserId: string;
adminToken: string;
}
export interface SeedResult {
serverAUrl: string;
serverBUrl: string;
adminTokenA: string;
adminTokenB: string;
adminUserIdA: string;
adminUserIdB: string;
grants: {
variantA: GrantRecord;
variantB: GrantRecord;
variantC: GrantRecord;
};
peers: {
variantA: PeerRecord & { grantId: string };
variantB: PeerRecord & { grantId: string };
variantC: PeerRecord & { grantId: string };
};
}
// ─── HTTP helpers ─────────────────────────────────────────────────────────────
/**
* Authenticated admin fetch. Sends `Authorization: Bearer <adminToken>` which
* is the only path supported by AdminGuard (DB-backed sha256 token lookup).
* No `x-admin-key` header path exists in the gateway.
*/
async function adminFetch<T>(baseUrl: string, path: string, opts: AdminFetchOptions): Promise<T> {
const url = `${baseUrl}${path}`;
const res = await fetch(url, {
method: opts.method ?? 'GET',
headers: {
'Content-Type': 'application/json',
Authorization: `Bearer ${opts.adminToken}`,
},
body: opts.body !== undefined ? JSON.stringify(opts.body) : undefined,
});
if (!res.ok) {
const text = await res.text().catch(() => '(no body)');
throw new Error(`${opts.method ?? 'GET'} ${url}${res.status}: ${text}`);
}
return res.json() as Promise<T>;
}
// ─── Admin bootstrap ──────────────────────────────────────────────────────────
/**
* Bootstrap an admin user on a pristine gateway.
*
* Steps:
* 1. GET /api/bootstrap/status — confirms needsSetup === true.
* 2. POST /api/bootstrap/setup with { name, email, password } — returns
* { user, token: { plaintext } }.
*
* The harness assumes a fresh DB. If needsSetup is false the harness fails
* fast with a clear error rather than proceeding with an unknown token.
*/
async function bootstrapAdmin(
baseUrl: string,
label: string,
password: string,
): Promise<BootstrapResult> {
console.log(`[seed] Bootstrapping admin on ${label} (${baseUrl})...`);
// 1. Check status
const statusRes = await fetch(`${baseUrl}/api/bootstrap/status`);
if (!statusRes.ok) {
throw new Error(`[seed] GET ${baseUrl}/api/bootstrap/status → ${statusRes.status.toString()}`);
}
const status = (await statusRes.json()) as { needsSetup: boolean };
if (!status.needsSetup) {
throw new Error(
`[seed] ${label} at ${baseUrl} already has users (needsSetup=false). ` +
`The harness requires a pristine database. Run 'docker compose down -v' to reset.`,
);
}
// 2. Bootstrap
const setupRes = await fetch(`${baseUrl}/api/bootstrap/setup`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
name: `Harness Admin (${label})`,
email: `harness-admin-${label.toLowerCase().replace(/\s+/g, '-')}@example.invalid`,
password,
}),
});
if (!setupRes.ok) {
const body = await setupRes.text().catch(() => '(no body)');
throw new Error(
`[seed] POST ${baseUrl}/api/bootstrap/setup → ${setupRes.status.toString()}: ${body}`,
);
}
const result = (await setupRes.json()) as {
user: { id: string };
token: { plaintext: string };
};
console.log(`[seed] ${label} admin user: ${result.user.id}`);
console.log(`[seed] ${label} admin token: ${result.token.plaintext.slice(0, 8)}...`);
return {
adminUserId: result.user.id,
adminToken: result.token.plaintext,
};
}
// ─── Readiness probe ──────────────────────────────────────────────────────────
async function waitForGateway(baseUrl: string, label: string): Promise<void> {
const deadline = Date.now() + READINESS_TIMEOUT_MS;
let lastError: string = '';
while (Date.now() < deadline) {
try {
const res = await fetch(`${baseUrl}/api/health`, { signal: AbortSignal.timeout(5_000) });
if (res.ok) {
console.log(`[seed] ${label} is ready (${baseUrl})`);
return;
}
lastError = `HTTP ${res.status.toString()}`;
} catch (err) {
lastError = err instanceof Error ? err.message : String(err);
}
await new Promise((r) => setTimeout(r, READINESS_POLL_MS));
}
throw new Error(
`[seed] ${label} did not become ready within ${READINESS_TIMEOUT_MS.toString()}ms — last error: ${lastError}`,
);
}
// ─── Enrollment flow ──────────────────────────────────────────────────────────
/**
* Walk the full enrollment flow for one grant.
*
* The correct two-sided flow (matching the data model's FK semantics):
*
* 1. On Server B: POST /api/admin/federation/peers/keypair
* → peerId_B (Server B's peer record representing the requesting side)
* 2. On Server B: POST /api/admin/federation/grants with peerId: peerId_B
* → grant (FK to Server B's own federation_peers table — no violation)
* 3. On Server B: POST /api/admin/federation/grants/:id/tokens
* → enrollmentUrl pointing back to Server B
* 4. On Server A: POST /api/admin/federation/peers/keypair
* → peerId_A + csrPem_A (Server A's local record of Server B)
* 5. Server A → Server B: POST enrollmentUrl with { csrPem: csrPem_A }
* → certPem signed by Server B's CA
* 6. On Server A: PATCH /api/admin/federation/peers/:peerId_A/cert with certPem
* → Server A's peer record transitions to active
*
* Returns the activated grant (from Server B) and Server A's peer record.
*/
async function enrollGrant(opts: {
label: string;
subjectUserId: string;
scope: unknown;
adminTokenA: string;
adminTokenB: string;
serverAUrl: string;
serverBUrl: string;
}): Promise<{ grant: GrantRecord; peer: PeerRecord & { grantId: string } }> {
const { label, subjectUserId, scope, adminTokenA, adminTokenB, serverAUrl, serverBUrl } = opts;
console.log(`\n[seed] Enrolling grant for scope variant ${label}...`);
// 1. Create peer keypair on Server B (represents the requesting peer from B's perspective)
const peerB = await adminFetch<PeerRecord>(serverBUrl, '/api/admin/federation/peers/keypair', {
method: 'POST',
adminToken: adminTokenB,
body: {
commonName: `harness-peer-${label.toLowerCase()}-from-b`,
displayName: `Harness Peer ${label} (Server A as seen from B)`,
endpointUrl: serverAUrl,
},
});
console.log(`[seed] Created peer on B: ${peerB.peerId}`);
// 2. Create grant on Server B referencing B's own peer record
const grant = await adminFetch<GrantRecord>(serverBUrl, '/api/admin/federation/grants', {
method: 'POST',
adminToken: adminTokenB,
body: {
peerId: peerB.peerId,
subjectUserId,
scope,
},
});
console.log(`[seed] Created grant on B: ${grant.id} (status: ${grant.status})`);
// 3. Generate enrollment token on Server B
const tokenResult = await adminFetch<EnrollmentTokenResult>(
serverBUrl,
`/api/admin/federation/grants/${grant.id}/tokens`,
{ method: 'POST', adminToken: adminTokenB, body: { ttlSeconds: 900 } },
);
console.log(`[seed] Enrollment token: ${tokenResult.token.slice(0, 8)}...`);
console.log(`[seed] Enrollment URL: ${tokenResult.enrollmentUrl}`);
// 4. Create peer keypair on Server A (Server A's local record of Server B)
const peerA = await adminFetch<PeerRecord>(serverAUrl, '/api/admin/federation/peers/keypair', {
method: 'POST',
adminToken: adminTokenA,
body: {
commonName: `harness-peer-${label.toLowerCase()}-from-a`,
displayName: `Harness Peer ${label} (Server B as seen from A)`,
endpointUrl: serverBUrl,
},
});
console.log(`[seed] Created peer on A: ${peerA.peerId}`);
// 5. Redeem token at Server B's enrollment endpoint with A's CSR.
// The enrollment endpoint is not admin-guarded — the one-time token IS the credential.
//
// The enrollmentUrl returned by the gateway is built using BETTER_AUTH_URL which
// resolves to the in-cluster Docker hostname (gateway-b:3000). That URL is only
// reachable from other containers, not from the host machine running this script.
// We rewrite the host portion to use the host-accessible serverBUrl so the
// seed script can reach the endpoint from the host.
const parsedEnrollment = new URL(tokenResult.enrollmentUrl);
const tokenSegment = parsedEnrollment.pathname.split('/').pop()!;
const redeemUrl = `${serverBUrl}/api/federation/enrollment/${tokenSegment}`;
console.log(`[seed] Rewritten redeem URL (host-accessible): ${redeemUrl}`);
const redeemRes = await fetch(redeemUrl, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ csrPem: peerA.csrPem }),
});
if (!redeemRes.ok) {
const body = await redeemRes.text().catch(() => '(no body)');
throw new Error(`Enrollment redemption failed: ${redeemRes.status.toString()}${body}`);
}
const redeemResult = (await redeemRes.json()) as EnrollmentRedeemResult;
console.log(`[seed] Cert issued (${redeemResult.certPem.length.toString()} bytes)`);
// 6. Store cert on Server A's peer record → transitions to active
await adminFetch<unknown>(serverAUrl, `/api/admin/federation/peers/${peerA.peerId}/cert`, {
method: 'PATCH',
adminToken: adminTokenA,
body: { certPem: redeemResult.certPem },
});
console.log(`[seed] Cert stored on A — peer ${peerA.peerId} is now active`);
// Verify grant flipped to active on B
const activeGrant = await adminFetch<GrantRecord>(
serverBUrl,
`/api/admin/federation/grants/${grant.id}`,
{ adminToken: adminTokenB },
);
console.log(`[seed] Grant status on B: ${activeGrant.status}`);
return { grant: activeGrant, peer: { ...peerA, grantId: grant.id } };
}
// ─── Test data insertion ──────────────────────────────────────────────────────
/**
* Insert representative test data on Server B via its admin APIs.
*
* NOTE: The gateway's task/note/credential APIs require an authenticated user
* session. For the harness, we seed via admin-level endpoints if available,
* or document the gap here for M3-11 to fill in with proper user session seeding.
*
* ASSUMPTION: Server B exposes POST /api/admin/tasks (or similar) for test data.
* If that endpoint does not yet exist, this function logs a warning and skips
* without failing — M3-11 will add the session-based seeding path.
*/
async function seedTestData(
subjectUserId: string,
scopeLabel: string,
serverBUrl: string,
adminTokenB: string,
): Promise<void> {
console.log(`\n[seed] Seeding test data on Server B for ${scopeLabel}...`);
const testTasks = [
{
title: `${scopeLabel} Task 1`,
description: 'Federation harness test task',
userId: subjectUserId,
},
{
title: `${scopeLabel} Task 2`,
description: 'Team-scoped test task',
userId: subjectUserId,
teamId: 'T1',
},
];
const testNotes = [
{
title: `${scopeLabel} Note 1`,
content: 'Personal note for federation test',
userId: subjectUserId,
},
];
// Attempt to insert — tolerate 404 (endpoint not yet implemented)
for (const task of testTasks) {
try {
await adminFetch<unknown>(serverBUrl, '/api/admin/tasks', {
method: 'POST',
adminToken: adminTokenB,
body: task,
});
console.log(`[seed] Inserted task: "${task.title}"`);
} catch (err) {
const msg = err instanceof Error ? err.message : String(err);
if (msg.includes('404') || msg.includes('Cannot POST')) {
console.warn(
`[seed] WARN: /api/admin/tasks not found — skipping task insertion (expected until M3-11)`,
);
break;
}
throw err;
}
}
for (const note of testNotes) {
try {
await adminFetch<unknown>(serverBUrl, '/api/admin/notes', {
method: 'POST',
adminToken: adminTokenB,
body: note,
});
console.log(`[seed] Inserted note: "${note.title}"`);
} catch (err) {
const msg = err instanceof Error ? err.message : String(err);
if (msg.includes('404') || msg.includes('Cannot POST')) {
console.warn(
`[seed] WARN: /api/admin/notes not found — skipping note insertion (expected until M3-11)`,
);
break;
}
throw err;
}
}
console.log(`[seed] Test data seeding for ${scopeLabel} complete.`);
}
// ─── Main entrypoint ──────────────────────────────────────────────────────────
export async function runSeed(opts?: {
serverAUrl?: string;
serverBUrl?: string;
adminBootstrapPasswordA?: string;
adminBootstrapPasswordB?: string;
subjectUserIds?: { variantA: string; variantB: string; variantC: string };
}): Promise<SeedResult> {
const aUrl = opts?.serverAUrl ?? SERVER_A_URL;
const bUrl = opts?.serverBUrl ?? SERVER_B_URL;
const passwordA = opts?.adminBootstrapPasswordA ?? ADMIN_BOOTSTRAP_PASSWORD_A;
const passwordB = opts?.adminBootstrapPasswordB ?? ADMIN_BOOTSTRAP_PASSWORD_B;
// Use provided or default subject user IDs.
// In a real run these would be real user UUIDs from Server B's DB.
// For the harness, the admin bootstrap user on Server B is used as the subject.
// These are overridden after bootstrap if opts.subjectUserIds is not provided.
const subjectIds = opts?.subjectUserIds;
console.log('[seed] Waiting for gateways to be ready...');
await Promise.all([waitForGateway(aUrl, 'Server A'), waitForGateway(bUrl, 'Server B')]);
// Bootstrap admin users on both gateways (requires pristine DBs).
console.log('\n[seed] Bootstrapping admin accounts...');
const [bootstrapA, bootstrapB] = await Promise.all([
bootstrapAdmin(aUrl, 'Server A', passwordA),
bootstrapAdmin(bUrl, 'Server B', passwordB),
]);
// Default subject user IDs to the admin user on Server B (guaranteed to exist).
const resolvedSubjectIds = subjectIds ?? {
variantA: bootstrapB.adminUserId,
variantB: bootstrapB.adminUserId,
variantC: bootstrapB.adminUserId,
};
// Enroll all three scope variants sequentially to avoid race conditions on
// the step-ca signing queue. Parallel enrollment would work too but
// sequential is easier to debug when something goes wrong.
console.log('\n[seed] Enrolling scope variants...');
const resultA = await enrollGrant({
label: 'A',
subjectUserId: resolvedSubjectIds.variantA,
scope: SCOPE_VARIANT_A,
adminTokenA: bootstrapA.adminToken,
adminTokenB: bootstrapB.adminToken,
serverAUrl: aUrl,
serverBUrl: bUrl,
});
const resultB = await enrollGrant({
label: 'B',
subjectUserId: resolvedSubjectIds.variantB,
scope: SCOPE_VARIANT_B,
adminTokenA: bootstrapA.adminToken,
adminTokenB: bootstrapB.adminToken,
serverAUrl: aUrl,
serverBUrl: bUrl,
});
const resultC = await enrollGrant({
label: 'C',
subjectUserId: resolvedSubjectIds.variantC,
scope: SCOPE_VARIANT_C,
adminTokenA: bootstrapA.adminToken,
adminTokenB: bootstrapB.adminToken,
serverAUrl: aUrl,
serverBUrl: bUrl,
});
// Seed test data on Server B for each scope variant
await Promise.all([
seedTestData(resolvedSubjectIds.variantA, 'A', bUrl, bootstrapB.adminToken),
seedTestData(resolvedSubjectIds.variantB, 'B', bUrl, bootstrapB.adminToken),
seedTestData(resolvedSubjectIds.variantC, 'C', bUrl, bootstrapB.adminToken),
]);
const result: SeedResult = {
serverAUrl: aUrl,
serverBUrl: bUrl,
adminTokenA: bootstrapA.adminToken,
adminTokenB: bootstrapB.adminToken,
adminUserIdA: bootstrapA.adminUserId,
adminUserIdB: bootstrapB.adminUserId,
grants: {
variantA: resultA.grant,
variantB: resultB.grant,
variantC: resultC.grant,
},
peers: {
variantA: resultA.peer,
variantB: resultB.peer,
variantC: resultC.peer,
},
};
console.log('\n[seed] Seed complete.');
console.log('[seed] Summary:');
console.log(` Variant A grant: ${result.grants.variantA.id} (${result.grants.variantA.status})`);
console.log(` Variant B grant: ${result.grants.variantB.id} (${result.grants.variantB.status})`);
console.log(` Variant C grant: ${result.grants.variantC.id} (${result.grants.variantC.status})`);
return result;
}
// ─── CLI entry ────────────────────────────────────────────────────────────────
const isCli =
process.argv[1] != null &&
fileURLToPath(import.meta.url).endsWith(process.argv[1]!.split('/').pop()!);
if (isCli) {
const shouldBoot = process.argv.includes('--boot');
if (shouldBoot) {
console.log('[seed] --boot flag detected — starting compose stack...');
execSync(`docker compose -f "${COMPOSE_FILE}" up -d`, { stdio: 'inherit' });
}
runSeed()
.then(() => {
process.exit(0);
})
.catch((err) => {
console.error('[seed] Fatal:', err);
process.exit(1);
});
}
+253
View File
@@ -0,0 +1,253 @@
#!/usr/bin/env bash
set -euo pipefail
ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
TMP="$(mktemp -d "${TMPDIR:-/tmp}/mosaic-next-install-test-XXXXXX")"
trap 'rm -rf "$TMP"' EXIT
FAKE_BIN="$TMP/bin"
HOME_DIR="$TMP/home"
PREFIX="$TMP/prefix"
MOSAIC_HOME="$TMP/mosaic"
STATE="$TMP/state"
LOG="$TMP/npm.log"
mkdir -p "$FAKE_BIN" "$HOME_DIR" "$STATE"
REAL_NODE="$(command -v node)"
export MOSAIC_TEST_REAL_NODE="$REAL_NODE"
cat > "$FAKE_BIN/node" <<'FAKE_NODE'
#!/usr/bin/env bash
set -euo pipefail
if [[ "$*" == *'process.versions.node.split'* ]]; then
printf '%s' "${MOSAIC_TEST_NODE_MAJOR:-22}"
exit 0
fi
if [[ "${1:-}" == "--version" ]]; then
printf 'v%s.0.0\n' "${MOSAIC_TEST_NODE_MAJOR:-22}"
exit 0
fi
exec "${MOSAIC_TEST_REAL_NODE:?}" "$@"
FAKE_NODE
chmod +x "$FAKE_BIN/node"
cat > "$FAKE_BIN/npm" <<'FAKE_NPM'
#!/usr/bin/env bash
set -euo pipefail
LOG="${MOSAIC_TEST_NPM_LOG:?}"
STATE="${MOSAIC_TEST_STATE:?}"
echo "$*" >> "$LOG"
if [[ "$1" == "view" ]]; then
case "$2 $3" in
"@mosaicstack/mosaic@next version") echo "0.0.49-next.999" ;;
"@mosaicstack/gateway@next version") echo "${MOSAIC_TEST_GATEWAY_NEXT_VERSION:-0.0.7-next.999}" ;;
"@mosaicstack/mosaic version") echo "0.0.48" ;;
*) echo "unexpected npm view: $*" >&2; exit 1 ;;
esac
exit 0
fi
if [[ "$1" == "install" ]]; then
case "$*" in
*"@mosaicstack/[email protected]"*)
echo "0.0.49-next.999" > "$STATE/mosaic"
;;
*"@mosaicstack/[email protected]"*)
if [[ "${MOSAIC_TEST_FAIL_NEXT_GATEWAY_INSTALL:-0}" == "1" ]]; then
echo "forced gateway install failure" >&2
exit 1
fi
echo "0.0.7-next.999" > "$STATE/gateway"
;;
*"mosaicstack-mosaic-0.0.0-source.tgz"*)
echo "0.0.0-source" > "$STATE/mosaic"
;;
*"mosaicstack-gateway-0.0.0-source.tgz"*)
echo "0.0.0-source" > "$STATE/gateway"
;;
*) echo "unexpected npm install: $*" >&2; exit 1 ;;
esac
exit 0
fi
if [[ "$1" == "ls" ]]; then
cli="$(cat "$STATE/mosaic" 2>/dev/null || true)"
gateway="$(cat "$STATE/gateway" 2>/dev/null || true)"
node -e '
const cli = process.argv[1];
const gateway = process.argv[2];
const dependencies = {};
if (cli) dependencies["@mosaicstack/mosaic"] = { version: cli };
if (gateway) dependencies["@mosaicstack/gateway"] = { version: gateway };
process.stdout.write(JSON.stringify({ dependencies }));
' "$cli" "$gateway"
exit 0
fi
echo "unexpected npm command: $*" >&2
exit 1
FAKE_NPM
chmod +x "$FAKE_BIN/npm"
cat > "$FAKE_BIN/curl" <<'FAKE_CURL'
#!/usr/bin/env bash
set -euo pipefail
# The fake tar creates the source tree; curl only needs to keep the pipe alive.
exit 0
FAKE_CURL
chmod +x "$FAKE_BIN/curl"
cat > "$FAKE_BIN/tar" <<'FAKE_TAR'
#!/usr/bin/env bash
set -euo pipefail
dest=""
while [[ $# -gt 0 ]]; do
case "$1" in
-C) dest="$2"; shift 2 ;;
*) shift ;;
esac
done
if [[ -z "$dest" ]]; then
echo "fake tar missing -C destination" >&2
exit 1
fi
mkdir -p "$dest/stack/packages/mosaic" "$dest/stack/apps/gateway"
FAKE_TAR
chmod +x "$FAKE_BIN/tar"
cat > "$FAKE_BIN/pnpm" <<'FAKE_PNPM'
#!/usr/bin/env bash
set -euo pipefail
LOG="${MOSAIC_TEST_NPM_LOG:?}"
echo "pnpm $*" >> "$LOG"
if [[ "$1" == "pack" ]]; then
out=""
while [[ $# -gt 0 ]]; do
case "$1" in
--pack-destination) out="$2"; shift 2 ;;
*) shift ;;
esac
done
if [[ -z "$out" ]]; then
echo "fake pnpm pack missing destination" >&2
exit 1
fi
mkdir -p "$out"
case "$PWD" in
*/apps/gateway) touch "$out/mosaicstack-gateway-0.0.0-source.tgz" ;;
*/packages/mosaic) touch "$out/mosaicstack-mosaic-0.0.0-source.tgz" ;;
*) echo "unexpected pnpm pack cwd: $PWD" >&2; exit 1 ;;
esac
exit 0
fi
# install/build commands are no-ops in this harness.
exit 0
FAKE_PNPM
chmod +x "$FAKE_BIN/pnpm"
reset_state() {
: > "$LOG"
rm -f "$STATE"/*
}
reset_state
echo "[test] --next rejects Node 20 before any install action"
if OUTPUT="$(
HOME="$HOME_DIR" MOSAIC_HOME="$MOSAIC_HOME" MOSAIC_PREFIX="$PREFIX" MOSAIC_NO_COLOR=1 \
MOSAIC_TEST_NPM_LOG="$LOG" MOSAIC_TEST_STATE="$STATE" MOSAIC_TEST_REAL_NODE="$REAL_NODE" \
MOSAIC_TEST_NODE_MAJOR=20 PATH="$FAKE_BIN:$PATH" \
bash "$ROOT/tools/install.sh" --cli --next --yes --no-auto-launch 2>&1
)"; then
echo "expected Node 20 next-lane install to fail" >&2
exit 1
fi
grep -qF 'Node.js >= 22 required for the --next lane' <<<"$OUTPUT"
[[ ! -s "$LOG" ]] || { echo "Node 20 gate ran npm actions" >&2; exit 1; }
reset_state
echo "[test] --next fast path pins resolved package versions"
OUTPUT="$(
HOME="$HOME_DIR" \
MOSAIC_HOME="$MOSAIC_HOME" \
MOSAIC_PREFIX="$PREFIX" \
MOSAIC_NO_COLOR=1 \
MOSAIC_TEST_NPM_LOG="$LOG" \
MOSAIC_TEST_STATE="$STATE" \
PATH="$FAKE_BIN:$PATH" \
bash "$ROOT/tools/install.sh" --cli --next --yes --no-auto-launch
)"
grep -qF 'Installed @next packages: CLI 0.0.49-next.999, gateway 0.0.7-next.999' <<<"$OUTPUT"
grep -qF 'install -g @mosaicstack/[email protected]' "$LOG"
grep -qF 'install -g @mosaicstack/[email protected]' "$LOG"
if grep -qE '^install -g .+@next( |$)' "$LOG"; then
echo "expected exact-version installs, found mutable @next install" >&2
exit 1
fi
if grep -qF 'Downloading source from next' <<<"$OUTPUT"; then
echo "fast path unexpectedly fell back to source" >&2
exit 1
fi
reset_state
echo "[test] fast path failure falls back to source build"
OUTPUT="$(
HOME="$HOME_DIR" \
MOSAIC_HOME="$MOSAIC_HOME" \
MOSAIC_PREFIX="$PREFIX" \
MOSAIC_NO_COLOR=1 \
MOSAIC_TEST_NPM_LOG="$LOG" \
MOSAIC_TEST_STATE="$STATE" \
MOSAIC_TEST_FAIL_NEXT_GATEWAY_INSTALL=1 \
PATH="$FAKE_BIN:$PATH" \
bash "$ROOT/tools/install.sh" --cli --next --yes --no-auto-launch
)"
grep -qF 'Fast gateway @next install failed.' <<<"$OUTPUT"
grep -qF 'Falling back to source build at ref next; --next will not hard-fail on registry issues.' <<<"$OUTPUT"
grep -qF 'Downloading source from next' <<<"$OUTPUT"
grep -qF 'Installed from source: CLI 0.0.0-source' <<<"$OUTPUT"
grep -qF 'install -g @mosaicstack/[email protected]' "$LOG"
grep -qE 'install -g .*/mosaicstack-gateway-0\.0\.0-source\.tgz' "$LOG"
grep -qE 'install -g .*/mosaicstack-mosaic-0\.0\.0-source\.tgz' "$LOG"
[[ "$(cat "$STATE/mosaic")" == "0.0.0-source" ]]
[[ "$(cat "$STATE/gateway")" == "0.0.0-source" ]]
reset_state
echo "[test] explicit --ref keeps source lane and avoids @next lookup"
OUTPUT="$(
HOME="$HOME_DIR" \
MOSAIC_HOME="$MOSAIC_HOME" \
MOSAIC_PREFIX="$PREFIX" \
MOSAIC_NO_COLOR=1 \
MOSAIC_TEST_NPM_LOG="$LOG" \
MOSAIC_TEST_STATE="$STATE" \
PATH="$FAKE_BIN:$PATH" \
bash "$ROOT/tools/install.sh" --check --cli --next --ref feature-x
)"
grep -qF 'explicit ref wins, build-from-source' <<<"$OUTPUT"
if grep -qF '@next version' "$LOG"; then
echo "explicit ref should not query @next dist-tags" >&2
exit 1
fi
reset_state
echo "[test] --check --next warns on mismatched prerelease pipeline suffixes"
OUTPUT="$(
HOME="$HOME_DIR" \
MOSAIC_HOME="$MOSAIC_HOME" \
MOSAIC_PREFIX="$PREFIX" \
MOSAIC_NO_COLOR=1 \
MOSAIC_TEST_NPM_LOG="$LOG" \
MOSAIC_TEST_STATE="$STATE" \
MOSAIC_TEST_GATEWAY_NEXT_VERSION="0.0.7-next.1000" \
PATH="$FAKE_BIN:$PATH" \
bash "$ROOT/tools/install.sh" --check --cli --next
)"
grep -qF '@next registry lane incomplete, mismatched, or unreachable; --next would fall back to source.' <<<"$OUTPUT"
echo "[test] installer next lane tests passed"
+1170
View File
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,43 @@
# tools/matrix-presence-harness — RFC-001 P1 validation (A1A5)
> **DEV-ONLY. LOCAL SANDBOX.** Drives the local `infra/matrix` Synapse only.
> Never point it at live infra.
The dev validation harness for the presence slice. It is the **minimal P1
provisioner** + an end-to-end demo that proves the acceptance criteria against
a real Synapse.
## Pieces
- `provision.ts` — the **minimal provisioner**: registers ≥3 agent MXIDs, creates
the fleet presence room, joins the agents. Reuses the existing tested
`@mosaicstack/appservice` intent library (register / createRoom / join). It is
deliberately **not** the P2 appservice (no auto-enroll / taxonomy / token minting).
- `agent-proc.ts` — one presence agent as its **own OS process** (via
`@mosaicstack/comms`): joins the fleet room and heartbeats `mosaic.presence`.
Standalone so the harness can `SIGKILL` it for a true hard-kill (A3).
- `validate.ts` — provisions, spawns the agents, then asserts:
- **A2** ≥3 agents show **online** in the fleet room.
- **A3** a `SIGKILL`'d agent flips to **offline within `dark_threshold`**,
deterministically (heartbeat-age based, not native-presence timeout), while
survivors stay online.
- **A4** prints the human-readable fleet liveness board.
- `run.sh` — wires dev secrets + env and runs `validate.ts` over the self-signed
TLS endpoint (A1). Exits non-zero on any failed assertion.
## Usage
```bash
../../infra/matrix/dev-up.sh # bring Synapse up first
./run.sh # provision + validate (A2/A3/A4)
```
Tunables (env): `HEARTBEAT_INTERVAL_MS` (1000), `MISS_TOLERANCE` (2),
`DARK_THRESHOLD_MS` (6000), `AGENT_SLUGS` (`alpha,bravo,charlie`),
`VICTIM_SLUG` (`charlie`), `MATRIX_CS_URL` (defaults to the TLS endpoint).
## Note on `NODE_TLS_REJECT_UNAUTHORIZED=0`
`run.sh` sets this **only** because the dev homeserver uses a self-signed cert.
It is a dev convenience for exercising the SDK over TLS and must never be used
against a real CA-issued endpoint.
@@ -0,0 +1,70 @@
/**
* tools/matrix-presence-harness/agent-proc.ts
*
* *** DEV harness — LOCAL SANDBOX ONLY. ***
*
* Runs ONE presence agent as its own OS process: joins the fleet presence
* room and heartbeats `mosaic.presence` via @mosaicstack/comms (RFC-001 P1).
* Kept as a standalone process so the validation harness can `kill -9` it to
* prove A3 (hard-kill -> offline within dark_threshold) against a real crash,
* not a graceful shutdown.
*
* Auth in DEV is Application-Service masquerade: the process presents the
* as_token and acts as its own @agent-<slug> MXID. (Per-agent minted tokens
* are P2, RFC-001 §2.2/§8.)
*
* ESM / NodeNext: .js import extensions.
*/
import { MinimalMatrixClient, PresenceAgent, type LivenessPolicy } from '@mosaicstack/comms';
const env = (k: string, fallback?: string): string => {
const v = process.env[k] ?? fallback;
if (v === undefined) throw new Error(`missing env ${k}`);
return v;
};
async function main(): Promise<void> {
const homeserverUrl = env('MATRIX_CS_URL');
const asToken = env('MOSAIC_AS_TOKEN');
const serverName = env('MATRIX_SERVER_NAME');
const slug = env('AGENT_SLUG');
const roomId = env('FLEET_ROOM_ID');
const intervalMs = Number(env('HEARTBEAT_INTERVAL_MS', '1000'));
const mxid = `@agent-${slug}:${serverName}`;
const policy: LivenessPolicy = {
heartbeatIntervalMs: intervalMs,
missTolerance: Number(env('MISS_TOLERANCE', '2')),
darkThresholdMs: Number(env('DARK_THRESHOLD_MS', '6000')),
};
const client = new MinimalMatrixClient({
homeserverUrl,
accessToken: asToken,
actAsUserId: mxid,
});
const agent = new PresenceAgent({
client,
agent: { mxid, slug, harness: 'claude-code' },
roomId,
intervalMs,
policy,
onError: (err) => console.error(`[${slug}] heartbeat error:`, (err as Error).message),
});
await agent.connect();
agent.start();
console.log(`[${slug}] pid=${process.pid} mxid=${mxid} heartbeating every ${intervalMs}ms`);
// Graceful stop only on SIGTERM; the A3 test uses SIGKILL (no cleanup runs).
process.on('SIGTERM', () => {
void agent.stop().finally(() => process.exit(0));
});
// Keep the event loop alive indefinitely.
setInterval(() => {}, 1 << 30);
}
main().catch((err) => {
console.error('agent-proc fatal:', err);
process.exit(1);
});
@@ -0,0 +1,24 @@
{
"name": "@mosaicstack/matrix-presence-harness",
"version": "0.0.1",
"type": "module",
"private": true,
"description": "DEV-ONLY validation harness for RFC-001 P1 (Matrix presence). Not shipped.",
"scripts": {
"build": "tsc --noEmit",
"lint": "eslint .",
"typecheck": "tsc --noEmit",
"test": "vitest run --passWithNoTests",
"validate": "./run.sh"
},
"dependencies": {
"@mosaicstack/appservice": "workspace:*",
"@mosaicstack/comms": "workspace:*"
},
"devDependencies": {
"@types/node": "^22.0.0",
"tsx": "^4.19.0",
"typescript": "^5.8.0",
"vitest": "^2.0.0"
}
}
@@ -0,0 +1,89 @@
/**
* tools/matrix-presence-harness/provision.ts
*
* *** DEV harness — LOCAL SANDBOX ONLY. ***
*
* The MINIMAL P1 provisioner (RFC-001 §10 P1): its ONLY job is to register a
* few agent MXIDs, create the fleet presence room, and join the agents. It is
* deliberately NOT the P2 appservice (no auto-enroll, no room taxonomy, no
* token minting, no introductions).
*
* It reuses the existing, tested `@mosaicstack/appservice` core library
* (AppserviceIntent: register / createRoom / join over the AS API) rather than
* reinventing Matrix plumbing.
*
* ESM / NodeNext: .js import extensions.
*/
import { AppserviceIntent, type AppserviceConfig } from '@mosaicstack/appservice';
export interface ProvisionOptions {
homeserverUrl: string;
serverName: string;
asToken: string;
hsToken: string;
agentSlugs: string[];
fleetAlias?: string; // localpart, default "mosaic-fleet"
}
export interface ProvisionResult {
roomId: string;
senderUserId: string;
agents: { slug: string; mxid: string }[];
}
/** Register agents, create the fleet presence room, join everyone. Idempotent. */
export async function provision(opts: ProvisionOptions): Promise<ProvisionResult> {
const cfg: AppserviceConfig = {
homeserverUrl: opts.homeserverUrl,
domain: opts.serverName,
asToken: opts.asToken,
hsToken: opts.hsToken,
};
const intent = new AppserviceIntent(cfg);
const fleetAlias = opts.fleetAlias ?? 'mosaic-fleet';
// 1. Register the virtual agent MXIDs (bypasses enable_registration:false).
const agents = [];
for (const slug of opts.agentSlugs) {
const mxid = await intent.ensureRegistered(slug);
await intent.setDisplayName(slug, `agent ${slug} (DEV)`);
agents.push({ slug, mxid });
}
// 2. Create the single fleet presence room, inviting all agents (RFC-001 §4.6).
// Idempotent: if the alias already exists, reuse that room instead.
let roomId: string;
try {
const created = await intent.createRoom({
name: 'Fleet Presence (DEV)',
alias: fleetAlias,
topic: 'RFC-001 P1 — mosaic.presence heartbeats. Who is alive?',
invite: agents.map((a) => a.mxid),
});
roomId = created.roomId;
} catch (err) {
// Alias already taken (re-run): resolve the existing room id.
const aliasFq = `#${fleetAlias}:${opts.serverName}`;
roomId = await resolveAlias(opts, aliasFq);
void err;
}
// 3. Join every agent into the fleet room (invite + join; idempotent).
for (const { slug } of agents) {
await intent.ensureJoined(roomId, slug);
}
return { roomId, senderUserId: intent.senderUserId, agents };
}
async function resolveAlias(
opts: Pick<ProvisionOptions, 'homeserverUrl' | 'asToken'>,
aliasFq: string,
): Promise<string> {
const url = `${opts.homeserverUrl.replace(/\/$/, '')}/_matrix/client/v3/directory/room/${encodeURIComponent(aliasFq)}`;
const res = await fetch(url, { headers: { Authorization: `Bearer ${opts.asToken}` } });
if (!res.ok) throw new Error(`resolveAlias ${aliasFq} -> ${res.status}`);
const data = (await res.json()) as { room_id?: string };
if (!data.room_id) throw new Error(`resolveAlias ${aliasFq} returned no room_id`);
return data.room_id;
}
+50
View File
@@ -0,0 +1,50 @@
#!/usr/bin/env bash
# ============================================================================
# run.sh — RFC-001 P1 presence validation harness (A1A5) *** DEV-ONLY ***
# ============================================================================
#
# Assumes the dev Synapse is already up (infra/matrix/dev-up.sh). Provisions 3
# agents, heartbeats them, proves A2/A3/A4 against the LOCAL dev homeserver,
# exercising @mosaicstack/comms over the self-signed TLS endpoint (A1).
#
# NODE_TLS_REJECT_UNAUTHORIZED=0 is set ONLY because the dev cert is
# self-signed. This is a DEV convenience and must never be used in prod.
# ----------------------------------------------------------------------------
set -euo pipefail
HERE="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
REPO="$(cd "${HERE}/../.." && pwd)"
DATA="${REPO}/infra/matrix/.data"
if [[ ! -f "${DATA}/dev-secrets.env" ]]; then
echo "run.sh: ${DATA}/dev-secrets.env not found — run infra/matrix/dev-up.sh first" >&2
exit 1
fi
# shellcheck disable=SC1091
set -a; source "${DATA}/dev-secrets.env"; set +a
export MATRIX_SERVER_NAME="${MATRIX_SERVER_NAME:-matrix.localhost}"
export MATRIX_TLS_PORT="${MATRIX_TLS_PORT:-18448}"
# Exercise the SDK over the self-signed TLS listener (A1). Use the plain HTTP
# port instead by exporting MATRIX_CS_URL=http://127.0.0.1:18008 before running.
export MATRIX_CS_URL="${MATRIX_CS_URL:-https://127.0.0.1:${MATRIX_TLS_PORT}}"
export NODE_TLS_REJECT_UNAUTHORIZED=0
export HEARTBEAT_INTERVAL_MS="${HEARTBEAT_INTERVAL_MS:-1000}"
export MISS_TOLERANCE="${MISS_TOLERANCE:-2}"
export DARK_THRESHOLD_MS="${DARK_THRESHOLD_MS:-6000}"
export AGENT_SLUGS="${AGENT_SLUGS:-alpha,bravo,charlie}"
export VICTIM_SLUG="${VICTIM_SLUG:-charlie}"
shopt -s nullglob
TSX_CANDIDATES=("${REPO}"/node_modules/.pnpm/tsx@*/node_modules/tsx/dist/cli.mjs)
shopt -u nullglob
TSX_CLI="${TSX_CANDIDATES[0]:-}"
if [[ -z "${TSX_CLI}" ]]; then
echo "run.sh: tsx not found under node_modules — run pnpm install first" >&2
exit 1
fi
export TSX_CLI
echo "[run] CS=${MATRIX_CS_URL} server_name=${MATRIX_SERVER_NAME} dark_threshold=${DARK_THRESHOLD_MS}ms"
cd "${REPO}"
exec node "${TSX_CLI}" "${HERE}/validate.ts"
@@ -0,0 +1,9 @@
{
"extends": "../../tsconfig.base.json",
"compilerOptions": {
"noEmit": true,
"rootDir": "."
},
"include": ["*.ts"],
"exclude": ["node_modules"]
}
@@ -0,0 +1,210 @@
/**
* tools/matrix-presence-harness/validate.ts
*
* *** DEV harness — LOCAL SANDBOX ONLY. Never point at live infra. ***
*
* End-to-end proof of RFC-001 P1 acceptance criteria against the local dev
* Synapse (infra/matrix):
*
* A2 provision >=3 agents, they heartbeat, all show ONLINE in the fleet
* presence room.
* A3 hard-kill (SIGKILL) one agent's process; assert it flips to OFFLINE
* within dark_threshold, DETERMINISTICALLY (heartbeat-age based, not
* native-presence-timeout), while the survivors stay ONLINE.
* A4 dump the human-readable fleet liveness board.
*
* Exits 0 on success, 1 on any failed assertion.
* ESM / NodeNext: .js import extensions.
*/
import { spawn, type ChildProcess } from 'node:child_process';
import { fileURLToPath } from 'node:url';
import { dirname, resolve } from 'node:path';
import {
FleetLivenessReader,
MinimalMatrixClient,
type AgentLiveness,
type LivenessPolicy,
} from '@mosaicstack/comms';
import { provision } from './provision.js';
const HERE = dirname(fileURLToPath(import.meta.url));
const env = (k: string, fallback?: string): string => {
const v = process.env[k] ?? fallback;
if (v === undefined) throw new Error(`missing env ${k}`);
return v;
};
const sleep = (ms: number): Promise<void> => new Promise((r) => setTimeout(r, ms));
const board = (rows: AgentLiveness[]): Record<string, string> =>
Object.fromEntries(rows.map((r) => [r.slug, r.status]));
async function main(): Promise<void> {
const homeserverUrl = env('MATRIX_CS_URL');
const asToken = env('MOSAIC_AS_TOKEN');
const hsToken = env('MOSAIC_HS_TOKEN', 'unused-in-p1');
const serverName = env('MATRIX_SERVER_NAME');
const intervalMs = Number(env('HEARTBEAT_INTERVAL_MS', '1000'));
const missTolerance = Number(env('MISS_TOLERANCE', '2'));
const darkThresholdMs = Number(env('DARK_THRESHOLD_MS', '6000'));
const slugs = env('AGENT_SLUGS', 'alpha,bravo,charlie').split(',');
const victim = env('VICTIM_SLUG', 'charlie');
const policy: LivenessPolicy = {
heartbeatIntervalMs: intervalMs,
missTolerance,
darkThresholdMs,
};
const failures: string[] = [];
const assert = (ok: boolean, msg: string): void => {
console.log(` ${ok ? 'PASS' : 'FAIL'} ${msg}`);
if (!ok) failures.push(msg);
};
// ── Provision (register agents, create fleet room, join) ──────────────────
console.log(`\n[validate] provisioning ${slugs.length} agents + fleet presence room...`);
const { roomId, senderUserId } = await provision({
homeserverUrl,
serverName,
asToken,
hsToken,
agentSlugs: slugs,
});
console.log(`[validate] fleet room ${roomId} (sender ${senderUserId})`);
// Reader masquerades as the AS sender (a room member) to read heartbeats.
const reader = new FleetLivenessReader({
client: new MinimalMatrixClient({
homeserverUrl,
accessToken: asToken,
actAsUserId: senderUserId,
}),
roomId,
policy,
});
// ── Spawn each agent as its own OS process ────────────────────────────────
const procs = new Map<string, ChildProcess>();
for (const slug of slugs) {
// `--import tsx` runs agent-proc.ts IN-PROCESS (no tsx grandchild), so the
// spawned pid IS the agent — a SIGKILL to it is a true hard-kill (A3).
// cwd=HERE so the `tsx` specifier resolves against the harness node_modules.
const child = spawn('node', ['--import', 'tsx', resolve(HERE, 'agent-proc.ts')], {
cwd: HERE,
env: {
...process.env,
AGENT_SLUG: slug,
FLEET_ROOM_ID: roomId,
MATRIX_CS_URL: homeserverUrl,
MOSAIC_AS_TOKEN: asToken,
MATRIX_SERVER_NAME: serverName,
HEARTBEAT_INTERVAL_MS: String(intervalMs),
MISS_TOLERANCE: String(missTolerance),
DARK_THRESHOLD_MS: String(darkThresholdMs),
},
stdio: ['ignore', 'inherit', 'inherit'],
});
procs.set(slug, child);
}
const hardKill = (pid: number): void => {
try {
process.kill(pid, 'SIGKILL'); // pid is the in-process agent — a true kill
} catch {
/* already gone */
}
};
const cleanup = (): void => {
for (const [, c] of procs) {
if (c.pid) hardKill(c.pid);
}
};
process.on('exit', cleanup);
try {
// ── A2: let a few beats flow, assert all online ─────────────────────────
console.log(`\n[validate] A2 — waiting for heartbeats (${intervalMs}ms interval)...`);
await sleep(intervalMs * 4 + 1000);
const a2 = await reader.read();
console.log('[validate] board:', board(a2));
for (const slug of slugs) {
assert(a2.find((r) => r.slug === slug)?.status === 'online', `A2 ${slug} is online`);
}
assert(a2.length >= 3, 'A2 >=3 agents present in fleet room');
// ── A4: human-readable board ────────────────────────────────────────────
console.log('\n[validate] A4 — fleet liveness board (human view):');
console.log(await reader.formatBoard());
// ── A3: hard-kill the victim, measure flip-to-offline latency ───────────
const victimProc = procs.get(victim);
if (!victimProc?.pid) throw new Error(`no pid for victim ${victim}`);
console.log(
`\n[validate] A3 — SIGKILL ${victim} (pid ${victimProc.pid}); dark_threshold=${darkThresholdMs}ms`,
);
const killTs = Date.now();
hardKill(victimProc.pid);
let victimOffline: AgentLiveness | undefined;
let detectMs = 0;
const deadline = killTs + darkThresholdMs + 6000;
while (Date.now() < deadline) {
await sleep(400);
const rows = await reader.read();
const v = rows.find((r) => r.slug === victim);
const elapsed = Date.now() - killTs;
if (v) {
console.log(
` t+${String(elapsed).padStart(5)}ms ${victim}=${v.status} (age=${v.ageMs}ms) ` +
`survivors=${slugs
.filter((s) => s !== victim)
.map((s) => `${s}:${rows.find((r) => r.slug === s)?.status}`)
.join(',')}`,
);
if (v.status === 'offline') {
victimOffline = v;
detectMs = elapsed;
break;
}
}
}
assert(!!victimOffline, `A3 ${victim} flipped to offline after kill`);
if (victimOffline) {
// Deterministic: the flip is driven by heartbeat age reaching dark_threshold.
assert(
victimOffline.ageMs >= darkThresholdMs,
`A3 flip is heartbeat-deterministic (age ${victimOffline.ageMs}ms >= dark_threshold ${darkThresholdMs}ms)`,
);
assert(
detectMs <= darkThresholdMs + 2000,
`A3 detected within dark_threshold + poll slack (detected at t+${detectMs}ms)`,
);
}
// Survivors unaffected.
const finalRows = await reader.read();
for (const slug of slugs.filter((s) => s !== victim)) {
assert(
finalRows.find((r) => r.slug === slug)?.status === 'online',
`A3 survivor ${slug} still online`,
);
}
console.log('\n[validate] final board after kill:');
console.log(await reader.formatBoard());
} finally {
cleanup();
}
console.log(
`\n[validate] ${failures.length === 0 ? 'ALL PASSED ✅' : `FAILED ❌ (${failures.length})`}`,
);
process.exit(failures.length === 0 ? 0 : 1);
}
main().catch((err) => {
console.error('[validate] fatal:', err);
process.exit(1);
});