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>
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>
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>
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>
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>
Extend the WS hello handshake with optional peerType, channel, and model
fields so peers can advertise what kind of client they are. The broker
stores these in-memory on PeerConn and returns them (along with cwd) in
the peers_list response. CLI peers command and MCP list_peers tool now
display the new metadata.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
When a peer connects or disconnects, the broker now broadcasts a
system push (subtype: "system") to all other peers in the same mesh.
The CLI formats these as [system] channel notifications so AI sessions
can react to topology changes without polling.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- claim_task/complete_task: send taskId not id
- graph_result: read msg.records not msg.rows
- message_status: try all mesh clients, not only first
- broker: omit state_result for set_state (fixes get_state cross-contamination)
- error handler: unblock first pending resolver on unmatched broker errors
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
broker: owner also fetches sealedKey from mesh.file_key (not skipped),
only non-owners are blocked when key is missing
cli: explicit error when encrypted file has no sealedKey (no silent raw download)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
broker: expand member groups to ancestor paths at drain time (pull model)
- @flexicar message reaches peers in @flexicar/core, @flexicar/output, etc.
- Resolved at drainForMember — no DB changes, fully backward-compatible
- Any depth: flexicar/team/backend also matches @flexicar and @flexicar/team
cli: wire --role all the way through to session config + env
- Config.role field added
- launch.ts stores role in sessionConfig, passes CLAUDEMESH_ROLE env var
- mcp/server.ts includes role in identity string
- manager.ts auto-joins groups from config on WS connect (--groups flag now works)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Node.js stdout to a pipe is buffered. Without periodic event loop
activity, WS callback → server.notification() → stdout.write() may
not flush until the next I/O event. A 1s setInterval (NOT unref'd)
keeps the event loop ticking so notifications flush immediately.
This is why claude-intercom worked: its 1s HTTP poll kept the event
loop active as a side effect. Claudemesh's passive WS listener let
the event loop settle, causing stdout to buffer indefinitely.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Sends test messages to self through the full pipeline per priority
and measures round-trip timing. Reports send→ack and send→receive
latency. Detects broker priority gating (status=working holds next/low).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Revert poll-based drain (v0.5.2 overcorrection). Claude Code source
confirms notifications are processed event-driven via React
useEffect, not polled. The WS onPush → server.notification() path
is correct.
Added section 13 to SPEC.md documenting the full Claude Code
notification pipeline, feature gates, priority gating, and common
push delivery issues.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace WS onPush→notification with timer-based buffer drain.
The old claude-intercom used 1s polling and worked reliably.
WS async callbacks may not flush stdio properly for MCP
notifications. Polling on a timer ensures consistent delivery.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
--inbox: count-only notifications, no content in context
--no-messages: tools only, zero prompt injection risk
Default: push (real-time, current behavior)
Wizard shows mode picker when no flag provided.
MCP instructions tell Claude its current mode.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Files: MinIO-backed file sharing built into the broker.
share_file for persistent mesh files, send_message(file:) for
ephemeral attachments. Presigned URLs for download, access
tracking per peer.
Broker infra: MinIO in docker-compose, internal network.
HTTP POST /upload endpoint. WS handlers for get_file,
list_files, file_status, delete_file.
Multi-target: send_message(to:) accepts string or array.
Targets deduplicated before delivery.
Targeted views: MCP instructions teach Claude to send
tailored messages per audience instead of generic broadcasts.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Phase B + C + message delivery status.
State: shared key-value store per mesh. set_state pushes changes
to all peers. get_state/list_state for reads. Peers coordinate
through shared facts instead of messages.
Memory: persistent knowledge with full-text search (tsvector).
remember/recall/forget. New peers recall context from past sessions.
message_status: check delivery status with per-recipient detail
(delivered/held/disconnected).
Multicast fix: broadcast and @group messages now push directly to
all connected peers instead of racing through queue drain.
MCP instructions: dynamic identity injection (name, groups, role),
comprehensive tool reference, group coordination guide.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Phase A of the claudemesh spec. Peers can now join named groups
with roles, and messages route to @group targets.
Broker:
- @group routing in fan-out (matches peer group membership)
- @all alias for broadcast
- join_group/leave_group WS messages + DB persistence
- list_peers returns group metadata
- drainForMember matches @group targetSpecs in SQL
CLI:
- join_group/leave_group MCP tools
- send_message supports @group targets
- list_peers shows group membership
- PeerInfo includes groups array
- Peer name cache for push notifications
Launch:
- --role flag (optional peer role)
- --groups flag (comma-separated, e.g. "frontend:lead,reviewers")
- Interactive wizard for role + groups when flags omitted
- Groups written to session config for broker hello
Spec: SPEC.md added with full v0.2 vision (groups, state, memory)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
onPush now queries list_peers to resolve the sender's pubkey to their
display name. Instructions updated to tell Claude to reply by name
instead of raw pubkey. Fixes two-way messaging between named peers.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
resolveClient() now resolves display names via list_peers WS query.
Supports exact match, partial match (unique substring), and falls
back to pubkey/channel/broadcast pass-through.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Remove ALL Payload imports, withPayload wrapper, and (payload)
routes. Blog index + changelog are now static data arrays.
Blog post at /blog/peer-messaging-claude-code is static TSX.
Payload CMS stays as a dev dependency for future local admin
but has zero presence in the production build.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Running \`claudemesh\` with no args now detects install state and
prints context-appropriate guidance: suggests \`install\` if MCP
not registered, \`join\` if no meshes, \`launch\` if ready.
Replaces the static HELP dump with a first-run wizard that meets
users where they are.
Static HELP still available via --help.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Three Tier-2 polish commands for debugging + discoverability:
- claudemesh --version / -v: print CLI version (baked from
package.json at build time via Bun JSON import).
- claudemesh status: WS-probe each joined mesh's broker, report
reachability per mesh. Exit 1 if any broker unreachable.
- claudemesh doctor: run 6 preconditions — Node>=20, claude on PATH,
MCP registered, hooks registered, config file parses + chmod 0600,
mesh keypairs validate. Each check has a pass/fail + fix hint.
Exit 0 if all pass.
Help text now leads with version (\"claudemesh v0.1.3 —\").
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The push handler previously fell through to base64-decoding the
raw ciphertext whenever decryptDirect() returned null. For direct
(crypto_box) messages that produces garbage binary which surfaces
as garbled bytes in Claude's <channel> reminder. Limit the base64
fallback to legacy broadcast/channel messages (no senderPubkey),
and emit a clearer "⚠ message from <pubkey> failed to decrypt"
warning when direct decryption fails.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Full parity with claude-peers:
1. Push-injection (the "tap on shoulder" UX)
- MCP server now declares experimental.claude/channel capability
- BrokerClient onPush handlers emit server.notification({
method: "notifications/claude/channel",
params: { content, meta: {from_id, from_name, mesh_slug,
mesh_id, priority, sent_at, delivered_at, kind}}
})
- Claude Code injects each push as <channel source="claudemesh">
system reminder, so the receiver session sees inbound messages
WITHOUT calling check_messages manually
- Updated MCP instructions with the "RESPOND IMMEDIATELY" framing
(adapted from claude-peers)
2. Status hooks in install (default-on, --no-hooks to opt out)
- new apps/cli/src/commands/hook.ts: reads stdin JSON (Claude Code
hook payload), extracts cwd+session_id, POSTs /hook/set-status
to every joined mesh's broker in parallel with process.ppid +
1s timeout per POST. Silent fail, fire-and-forget.
- install.ts: writes to ~/.claude/settings.json registering
`claudemesh hook idle` on Stop + `claudemesh hook working` on
UserPromptSubmit. Idempotent, preserves other hook entries.
- uninstall.ts: removes both hook entries + MCP entry; leaves
unrelated hook/MCP entries alone.
- dedupes by brokerUrl (multiple meshes on same broker → one POST)
3. CLI surface
- new subcommand: `claudemesh hook <status>` (internal, but
exposed so Claude Code can invoke it via the hook shell command)
- `install --no-hooks` for users who want bare MCP registration
- --help updated
Coexistence with claude-peers: both tools register Stop and
UserPromptSubmit hooks, each POSTs to its own broker. Claude Code
fires multiple hooks per event without conflict.
npm version 0.1.0 → 0.1.1 (patch).
Verified:
- install with hooks → 2 entries added to settings.json ✓
- install --no-hooks → "Hooks skipped" ✓
- uninstall → both MCP entry + 2 hook entries removed ✓
- `echo '{...}' | claudemesh hook idle` with no joined meshes →
silent no-op ("no joined meshes, nothing to do") ✓
- MCP initialize response includes experimental.claude/channel ✓
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Pairs with claudemesh-2's new /join/[token] landing page. Users can
now paste a clickable HTTPS URL instead of the dev-only ic:// scheme.
apps/cli/src/invite/parse.ts — new extractInviteToken() handles
four input formats before handing the raw base64url token to the
existing parseInviteLink pipeline:
- https://claudemesh.com/join/<token> (primary, clickable)
- https://claudemesh.com/<locale>/join/<token> (i18n prefix)
- ic://join/<token> (still supported, dev)
- <raw-token> (last resort: bare base64url)
User-facing strings updated to the HTTPS form:
- cli help: "join <url>"
- install success message
- list (no-meshes) hint
- MCP server "no meshes" error
- README.md primary example
- docs/QUICKSTART.md Path A + Path B
Verified extractInviteToken() on all 4 formats — each returns the
same base64url token → same broker /join lookup.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
@claudemesh/cli was already taken on npm by an unrelated project
(claudemesh "domain packages", v1.0.7). PM picked option A: publish
unscoped as claudemesh-cli. Binary name stays "claudemesh" — users
type the natural thing on install:
npm install -g claudemesh-cli
claudemesh install
claudemesh join ic://join/...
renamed references everywhere:
- apps/cli/package.json: name
- apps/cli/README.md: title + install command
- apps/cli/src/{index.ts, mcp/server.ts, commands/install.ts} headers
- docs/QUICKSTART.md: install command, version banner, npx hint
- docs/roadmap.md: package name
also (PM journey-friction #5): surface the "restart Claude Code" step
LOUDLY in install output. Added a yellow-bold warning line after the
✓ success lines so new users don't miss the restart step (MCP tools
only load on Claude Code restart).
⚠ RESTART CLAUDE CODE for MCP tools to appear.
ANSI colors gated on isTTY + NO_COLOR/TERM=dumb guards.
bundle rebuilt. ready for npm publish pending user's `npm adduser`.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Direct messages between peers are now end-to-end encrypted. The
broker only ever sees {nonce, ciphertext} — plaintext lives on the
two endpoints.
apps/cli/src/crypto/envelope.ts:
- encryptDirect(message, recipientPubkeyHex, senderSecretKeyHex)
→ {nonce, ciphertext} via crypto_box_easy, 24-byte fresh nonce
- decryptDirect(envelope, senderPubkeyHex, recipientSecretKeyHex)
→ plaintext or null (null on MAC failure / malformed input)
- ed25519 keys (from Step 17) are converted to X25519 on the fly via
crypto_sign_ed25519_{pk,sk}_to_curve25519 — one signing keypair
covers both signing + encryption roles.
BrokerClient.send():
- if targetSpec is a 64-hex pubkey → encrypt via crypto_box
- else (broadcast "*" or channel "#foo") → base64-wrapped plaintext
(shared-key encryption for channels lands in a later step)
InboundPush now carries:
- plaintext: string | null (decrypted body, null if decryption failed
OR it's a non-direct message)
- kind: "direct" | "broadcast" | "channel" | "unknown"
MCP check_messages formatter reads plaintext directly.
side-fixes pulled in during 18a:
- apps/broker/scripts/seed-test-mesh.ts now generates real ed25519
keypairs (the previous "aaaa…" / "bbbb…" fillers weren't valid
curve points, so crypto_sign_ed25519_pk_to_curve25519 rejected
them). Seed output now includes secretKey for each peer.
- apps/broker/src/broker.ts drainForMember wraps the atomic claim in
a CTE + outer ORDER BY so FIFO ordering is SQL-sourced, not
JS-sorted (Postgres microsecond timestamps collapse to the same
Date.getTime() milliseconds otherwise).
- vitest.config.ts fileParallelism: false — test files share
DB state via cleanupAllTestMeshes afterAll, so running them in
parallel caused one file's cleanup to race another's inserts.
- integration/health.test.ts "returns 200" now uses waitFullyHealthy
(a 200-only waiter) instead of waitHealthyOrAny — prevents a race
with the startup DB ping.
verified live:
- apps/cli/scripts/roundtrip.ts (direct A→B): ciphertext in DB is
opaque bytes (not base64-plaintext), decrypted correctly on arrival
- apps/cli/scripts/join-roundtrip.ts (full join → encrypted send):
PASSED
- 48/48 broker tests green
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
broker-client: full WS client with hello handshake + ack, auto-reconnect
with exponential backoff (1s → 30s capped), in-memory outbound queue
(max 100) during reconnect, 500-entry push buffer for check_messages.
MCP tool integration:
- send_message: "slug:target" prefix or single-mesh fast path
- check_messages: drains push buffers across all clients
- set_status: fans manual override across all connected meshes
- set_summary: stubbed (broker protocol extension needed)
- list_peers: stubbed — lists connected mesh slugs + statuses
manager module holds Map<meshId, BrokerClient>, starts on MCP server
boot for every joined mesh in ~/.claudemesh/config.json.
new CLI command: seed-test-mesh injects a mesh row for dev testing.
also fixes a broker-side hello race: handleHello sent hello_ack before
the caller closure assigned presenceId, so clients sending right after
the ack hit the no_hello check. Fix: return presenceId, caller sets
closure var, THEN sends hello_ack. Queue drain is fire-and-forget now.
round-trip verified: two clients, A→B, push received with correct
senderPubkey + ciphertext. 44/44 broker tests still pass.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
