Boot restore now checks runner /health to see what's already running,
then updates DB status to match. Fixes the bug where broker restart
marked running services as 'failed' because it tried to re-deploy
without shared source volume.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Runner /load now accepts gitUrl, npxPackage, or sourcePath. It handles
git clone and npm install internally. Broker no longer needs shared
volume for source extraction — just tells the runner what to fetch.
CLI mesh_mcp_deploy now supports npx_package as a third source type.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- apps/runner/: Dockerfile (node22 + python3 + uv + bun) + supervisor.mjs
(HTTP API for load/call/unload/health)
- docker-compose: runner service with shared services-data volume
- Broker mcp_deploy: git clone or zip extract → runner /load → MCP spawn
- Broker mcp_call: routes managed services to runner via HTTP, falls back
to live-proxy for peer-hosted servers
- RUNNER_URL env var for broker → runner communication
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- broker-crypto.ts: AES-256-GCM encrypt/decrypt with BROKER_ENCRYPTION_KEY
- mcp_deploy stores env as _encryptedEnv in mesh.service.config (no plaintext in DB)
- boot restore: decrypts _encryptedEnv and re-spawns services via service-manager
- auto-generates ephemeral key if BROKER_ENCRYPTION_KEY not set (logs warning)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
claudemesh launch now supports:
--resume <id> / -r — resume a previous Claude Code session
--continue / -c — continue the most recent conversation
When resuming, skips generating a new session ID so the mesh peer
identity persists. The detectClaudeSessionId() fallback in ws/client.ts
picks up the existing session UUID from the .jsonl file.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
claudemesh launch now generates a UUID and passes it to claude via
--session-id flag + CLAUDEMESH_SESSION_ID env var. The MCP server
reads this and sends it in the hello handshake.
Fallback: when launched without claudemesh launch (e.g., claude --resume),
detectClaudeSessionId() scans ~/.claude/projects/ for the most recent
.jsonl file and extracts the session UUID from the filename.
Benefits:
- Broker detects reconnections (same session = restore state)
- Multiple peers in same project dir get unique identities
- Session identity persists across --resume
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The Wave 3I handlers (vault_set, vault_list, vault_delete, mesh_mcp_deploy,
mesh_mcp_undeploy, mesh_mcp_update, mesh_mcp_logs, mesh_mcp_scope,
mesh_mcp_schema, mesh_mcp_catalog, mesh_skill_deploy) were lost during
the re-apply phase. Tools were registered in tools/list but returned
"Unknown tool" because the switch cases in server.ts were missing.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Simplify getting-started to 2 steps: npm install + launch --join.
Remove "claudemesh install" section, update join page to show
launch --join as the primary flow, update invite format examples.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Drop /install route (curl|bash script). Install is just `npm i -g
claudemesh-cli`. Update hero, FAQ, getting-started, and join flow to
reflect the simplified 3-step onboarding: install → join → launch.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add the foundation for deploying and managing MCP servers on the VPS
broker, with per-peer credential vaults and visibility scopes.
Architecture:
- One Docker container per mesh with a Node supervisor
- Each MCP server runs as a child process with its own stdio pipe
- claudemesh launch installs native MCP entries in ~/.claude.json
- Mid-session deploys fall back to svc__* dynamic tools + list_changed
New components:
- DB: mesh.service + mesh.vault_entry tables, mesh.skill extensions
- Broker: 19 wire protocol types, 11 message handlers, service catalog
in hello_ack with scope filtering, service-manager.ts (775 lines)
- CLI: 13 tool definitions, 12 WS client methods, tool call handlers,
startServiceProxy() for native MCP proxy mode
- Launch: catalog fetch, native MCP entry install, stale sweep, cleanup,
MCP_TIMEOUT=30s, MAX_MCP_OUTPUT_TOKENS=50k
Security: path sanitization on service names, column whitelist on
upsertService, returning()-based delete checks, vault E2E encryption.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Shows the full hierarchy: Organization → Mesh → @groups → Peers
with live state + memory. Six coordination patterns below with
code snippets: lead-gather, delegation, voting, chain review,
broadcast, targeted views. Footer: 'All patterns are conventions
in system prompts. The broker routes; Claude coordinates.'
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Shows the 12 capability categories that flow through the mesh:
messages, groups, state, memory, files, SQL, vectors, graph,
tasks, context, streams, scheduled. Each with a mono icon tag
and one-line description. Anchored by '43 MCP tools, 5
persistence backends' footer.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The CSS import error was caused by richtext-lexical being in
serverExternalPackages — Node can't require .css files. Removing
it lets Turbopack bundle it (handling CSS natively). Other payload
packages stay external (they don't import CSS).
Restores turbopack as the default production bundler.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- generateMetadata instead of metadata (getMetadata returns a function)
- Use TURBOPACK=0 env prefix instead of --no-turbopack flag (not recognized in Docker)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The --no-turbopack flag isn't recognized when Next.js runs inside the
Docker builder stage. The Dockerfile already sets ENV TURBOPACK=0 which
achieves the same effect.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Persistent MCP servers (opt-in via `persistent: true`) survive host
disconnects — they appear as offline in mcp_list and auto-restore when
the host reconnects. Ephemeral servers (default) still clean up on
disconnect. Offline servers return a clear error on mcp_call with
time-since-disconnect info.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Save groups, profile, visibility, summary, display name, and cumulative
stats to a new mesh.peer_state table on disconnect. On reconnect (same
meshId + memberId), restore them automatically — hello groups take
precedence over stored groups if provided. Broadcast peer_returned
system event with last-seen time and summary to other peers.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Peers now receive [system] notifications when MCP servers join or
leave the mesh, with tool names and hosting peer info.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Teaches AI when to use filesystem (local), read_peer_file (remote
<1MB), or share_file (persistent, no size limit).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
When read_peer_file targets a local peer (same hostname), prepend a
hint with the direct filesystem path. Still executes the relay as
fallback — AI learns the shortcut without being blocked.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Peers report os.hostname() in the hello handshake. list_peers shows
[local] or [remote] tag per peer. MCP instructions teach AI to read
local peers' files directly via filesystem instead of relay.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add the webhook handler module (webhooks.ts) that verifies secrets
against the mesh.webhook table and broadcasts incoming HTTP POST
payloads to all connected mesh peers. This completes the webhook
feature whose schema, types, WS CRUD handlers, and CLI tools were
added in the previous commits.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Wire up MCP tool handlers for the peer file sharing relay. Peers can
now read files and list directories from other peers' local filesystems
through the mesh broker. Includes name-to-pubkey resolution, base64
decode, and instructions table update.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Broker-driven clock that broadcasts periodic heartbeat ticks to all
peers in a mesh. Speed is configurable from x1 (real-time, 60s ticks)
to x100 (600ms ticks) for load testing simulations. Auto-pauses when
the last peer disconnects.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds share_skill, get_skill, list_skills, and remove_skill across the full
stack (Drizzle schema, broker CRUD + WS handlers, CLI client methods, MCP
tools). Skills are mesh-scoped, unique by name, and searchable via ILIKE
on name/description/tags.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add tamper-evident audit logging where each entry includes a SHA-256
hash of the previous entry, forming a verifiable chain per mesh.
Events tracked: peer_joined, peer_left, state_set, message_sent
(never logs message content). New WS handlers: audit_query for
paginated retrieval, audit_verify for chain integrity verification.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Peers self-report resource usage via set_stats; stats visible in
list_peers responses and the new mesh_stats MCP tool. CLI auto-reports
every 60s and tracks messagesIn/Out, toolCalls, uptime, and errors.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Peers can register MCP servers with the mesh and other peers can invoke
those tools through the existing claudemesh connection without restarting.
Broker: in-memory MCP registry with mcp_register/unregister/list/call
handlers, call forwarding to hosting peer with 30s timeout, and automatic
cleanup on peer disconnect.
CLI: mcpRegister/mcpUnregister/mcpList/mcpCall client methods, inbound
mcp_call_forward handler, and 4 new MCP tools (mesh_mcp_register,
mesh_mcp_list, mesh_tool_call, mesh_mcp_remove).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Two new panels below the existing peer graph + live stream grid:
- StateTimelinePanel: vertical timeline of audit events and presence
status changes, auto-scrolling, sorted newest-first
- ResourcePanel: 2x2 card grid showing live peers, envelopes by
priority, audit event breakdown, and session status
Both share the same TanStack Query cache key as the existing panels
(no extra API calls). Matches the --cm-* dark terminal aesthetic.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
After MCP registration and hooks setup, `claudemesh install` now checks
the config for joined meshes. If empty, it prints actionable guidance
(join command + dashboard URL) instead of the generic "Next:" line.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Replace in-memory-only setTimeout scheduling with a DB-backed system
that survives broker restarts. Adds:
- `scheduled_message` table in mesh schema (Drizzle + raw CREATE TABLE
for zero-downtime deploys)
- Minimal 5-field cron parser (no dependencies) with next-fire-time
calculation for recurring entries
- On broker boot, all non-cancelled entries are loaded from PostgreSQL
and timers re-armed automatically
- CLI `schedule_reminder` MCP tool accepts optional `cron` expression
- CLI `remind` command accepts `--cron` flag
- One-shot reminders remain backward compatible — no cron field = same
behavior as before
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
