docs: split vision into changelog + clean roadmap

changelog-20260407.md: full implementation details for 21 features vision-20260407.md: slimmed to shipped summary + remaining items Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-08 00:20:55 +01:00
parent fc8a7edc23
commit 56b1cc0756
2 changed files with 218 additions and 372 deletions
--- a/docs/changelog-20260407.md
+++ b/docs/changelog-20260407.md
@@ -0,0 +1,164 @@
 # claudemesh — Implementation Changelog
 **Sprint:** 2026-04-07 evening session
 **Author:** Alejandro Gutiérrez + Claude (Opus 4.6)
 **CLI versions:** 0.6.8 → 0.6.9 → 0.7.0
 **Broker:** deployed to `ic.claudemesh.com` (Coolify, OVHcloud VPS)
 ---
 ## Features shipped
 ### 1. Session path (cwd) sharing
 `810f372` · CLI 0.6.9 + broker
 Added `cwd` to the WS hello handshake. Broker stores it in the peer record, `list_peers` returns it. Peers on the same machine see each other's working directories for direct file referencing.
 ### 2. Peer metadata (type, channel, model)
 `810f372` · Same commit as cwd
 Extended hello with `peerType: "ai" | "human" | "connector"`, `channel` (e.g. "claude-code", "telegram"), `model` (e.g. "opus-4"). Foundation for connectors, humans, and smart routing.
 ### 3. System notifications (peer join/leave)
 `453705a` · broker + CLI
 Broker broadcasts `{ subtype: "system", event: "peer_joined" | "peer_left" }` pushes to all mesh peers on connect/disconnect. MCP server formats them as `[system] Peer "Alice" joined the mesh`. System events bypass inbox/off message modes.
 ### 4. Cron-based persistent reminders
 `e873807` · broker + CLI + `72be651` (--cron flag)
 Replaced in-memory `setTimeout` with DB-persisted scheduler. Zero-dependency 5-field cron parser. Schedules survive broker restarts via `recoverScheduledMessages()` on boot. CLI: `claudemesh remind "check deploys" --cron "0 */2 * * *"`. MCP: `schedule_reminder` with `cron` field.
 ### 5. Simulation clock with time multiplier
 `05d9b56` · broker + CLI
 Per-mesh clock state (`MeshClock` interface + `meshClocks` Map). Configurable speed x1–x100. Broadcasts heartbeat ticks as system pushes: `{ event: "tick", eventData: { tick, simTime, speed } }`. Auto-pauses when last peer disconnects. MCP tools: `mesh_set_clock`, `mesh_pause_clock`, `mesh_resume_clock`, `mesh_clock`.
 ### 6. Inbound webhooks
 `b55cf26` · broker (new `webhooks.ts`) + CLI
 `POST /hook/:meshId/:secret` → broker injects as push to all mesh peers. Webhooks stored in `meshWebhook` Drizzle table. MCP tools: `create_webhook` (returns URL+secret), `list_webhooks`, `delete_webhook`. Push format: `{ subtype: "webhook", event: "webhook_name", eventData: {...body} }`.
 ### 7. Slack connector
 `5563f90` · `packages/connector-slack/`
 Bridge process using `@slack/socket-mode` + `@slack/web-api`. Joins mesh as `peerType: "connector"`, `channel: "slack"`. Bidirectional relay with echo prevention, user ID-to-name resolution with caching, auto-reconnect with exponential backoff.
 ### 8. Telegram connector
 `fe92853` · `packages/connector-telegram/`
 Zero-dependency Telegram Bot API client using native `fetch` + long polling. Same bridge pattern as Slack. HTML formatting for Telegram output. Auto-reconnect with exponential backoff (1s–30s).
 ### 9. Non-Claude-Code SDK
 `7e102a2` · `packages/sdk/`
 Standalone TypeScript SDK (`@claudemesh/sdk`). `MeshClient extends EventEmitter` with `connect()`, `send()`, `broadcast()`, `listPeers()`, `getState()`, `setState()`. Uses `libsodium-wrappers` for ed25519-to-curve25519 crypto_box encryption (same as CLI). Auto-reconnect with exponential backoff.
 ### 10. Mesh skills catalog
 `c8cb1e3` · broker (Drizzle schema + handlers) + CLI
 Peers publish reusable skills (name, description, instructions, tags). Full CRUD: `share_skill` (upsert by name), `get_skill`, `list_skills` (ILIKE search), `remove_skill`. Stored in `meshSkill` table with unique (meshId, name). `get_skill` returns instructions prominently formatted for immediate AI use.
 ### 11. Shared project files
 `504111c` · broker relay + CLI file serving
 Peer-to-peer file relay: `read_peer_file(peer, path)` and `list_peer_files(peer, path?, pattern?)`. Broker relays without reading content. Security: 1MB max, path traversal rejection, hidden files excluded, 2-level dir listing cap (500 entries). Plus hostname-based local/remote detection (`2c9c8c7`) and filesystem shortcut hint for local peers (`a92cf6b`).
 ### 12. Peer stats reporting
 `b3b9972` · broker + CLI
 Peers auto-report stats every 60s: messagesIn/Out, toolCalls, uptime, errors. `set_stats` WS message + `mesh_stats` MCP tool. Stats visible in `list_peers` response. Tool call counter incremented on every MCP invocation.
 ### 13. Signed audit log (hash chain)
 `86a2583` · broker (new `audit.ts` + Drizzle schema)
 SHA-256 hash-chained append-only log. Each entry hashes: `prevHash|meshId|eventType|actorMemberId|payload|createdAt`. Events logged: peer_joined, peer_left, state_set, message_sent (NO ciphertext). WS endpoints: `audit_query` (paginated), `audit_verify` (chain integrity check). On startup: `ensureAuditLogTable()` + `loadLastHashes()`.
 ### 14. Mesh templates
 `69e93d4` · CLI (`apps/cli/src/templates/`)
 5 JSON templates: dev-team, research, ops-incident, simulation, personal. Each defines groups, roles, state keys, and a system prompt hint. `claudemesh create --template dev-team` loads and displays template. `claudemesh create --list-templates` shows all.
 ### 15. Default personal mesh guidance
 `b0dc538` · CLI (`install.ts`)
 `claudemesh install` detects empty meshes and shows join guidance. Local-only mesh deferred (requires broker enrollment for real connectivity).
 ### 16. Mesh MCP proxy
 `08e289a` · broker + CLI
 Dynamic tool sharing: `mesh_mcp_register` → `mesh_mcp_list` → `mesh_tool_call` → broker forwards to hosting peer → execute → result back. In-memory registry with 30s call timeout. Auto-cleanup on disconnect. MCP register/unregister broadcasts system notifications (`e09671c`).
 ### 17. Dashboard: peer graph + state timeline + resource panel
 `59332dc` (peer graph) + `7d432b3` (timeline + resources)
 **Peer graph:** Radial SVG layout, animated bezier edges with priority colors, group rings, status indicators (green/amber/red), node sizing by activity. No external deps (pure SVG + CSS animations). `ResizeObserver` for responsive sizing.
 **State timeline:** Vertical timeline of audit events with timestamps, icons, type badges. Newest-first with auto-scroll. Shares same TanStack Query cache (zero extra API calls).
 **Resource panel:** 2x2 card grid — live peers, envelope breakdown, audit event frequency, session online/offline split.
 ### 18. Peer visibility + public profiles
 Broker types.ts + index.ts + CLI
 `set_visible(false)` makes peer invisible in `list_peers` and skips broadcast/group routing. Direct messages by pubkey still reach hidden peers. System events: `peer_visible`, `peer_hidden`. Public profiles: `set_profile({ avatar, title, bio, capabilities })` — visible to other peers in `list_peers` and peer graph.
 ### 19. Hostname + local/remote detection
 `2c9c8c7` · broker + CLI
 `os.hostname()` added to hello handshake. `list_peers` shows `[local]` or `[remote]` tag per peer. MCP instructions include file access decision guide: local → filesystem, remote <1MB → `read_peer_file`, large/persistent → `share_file`.
 ### 20. File access decision guide in MCP instructions
 `3641618` · CLI MCP server
 Clear decision guide in system instructions: three methods (filesystem for local, relay for remote, MinIO for persistent), with size limits and when to use each.
 ### 21. MCP server register/unregister broadcasts
 `e09671c` · broker + CLI
 When a peer registers or removes an MCP server, all mesh peers receive a system notification: `[system] New MCP server available: "github" (hosted by Alice). Tools: list_repos, create_issue. Use mesh_tool_call to invoke.`
 ---
 ## Also shipped (infrastructure / docs)
 | Commit | What |
 |--------|------|
 | `0bb9d71` | Merged `schedule_reminder` + `send_later` into single tool with optional `to` param; added `subtype: "reminder"` to push |
 | `79525af` | Fixed TSC error from cron example in JSDoc comment |
 | `69e93d4` | Mesh templates: 5 JSON templates + `claudemesh create` command |
 | `f34b8fb` | CLI `--help` text review: 44 descriptions improved for clarity, concision, consistency |
 | `58ba01f` | `CLAUDEMESH_TOOLS` in install.ts synced (41→45 tools, sorted alphabetically) |
 | `db2bf3e` | `protocol.md` expanded from 6 to 73 message types |
 | `72be651` | `--cron` flag wired into citty remind command |
 ---
 ## CLI versions published
 | Version | Key changes |
 |---------|------------|
 | 0.6.8 | schedule_reminder merge, reminder subtype |
 | 0.6.9 | cwd + peer metadata + system notifications + cron + templates + --help review |
 | 0.7.0 | Skills catalog, MCP proxy, shared files, visibility, sim clock, webhooks, peer stats, connectors, SDK |
 ---
 ## Pending (building)
 - **Peer session persistence** — agent running, DB-backed state restore on reconnect
 - **Persistent MCP registrations** — agent running, survive peer disconnect with online/offline status
 ---
 ## Remaining from vision (not yet built)
 | # | Feature | Notes |
 |---|---------|-------|
 | 6 | REST API + external WS | Webhooks done, REST and WS auth remain |
 | 8 | Humans in the mesh | Web chat panel needed |
 | 14 | Bridge / federation | Bridge peer feasible now, federation needs design |
 | 18 | Sandboxes (E2B) | Third-party integration preferred |
 | 20 | Spatial topology (x,y proximity) | Visibility done, proximity model remains |
 | 21 | Semantic peer search | Multi-field matching, half day |
 | 22 | Mesh telemetry + debugging | Structured logging + reporting |
--- a/docs/vision-20260407.md
+++ b/docs/vision-20260407.md
@@ -1,407 +1,89 @@
-# claudemesh — Vision & Feature Brainstorm
+# claudemesh — Vision & Roadmap
-**Date:** 2026-04-07 23:01 CEST
+**Date:** 2026-04-07
 **Author:** Alejandro Gutiérrez + Claude (Opus 4.6)
-**Status:** Internal brainstorm — not committed to public roadmap
+**Last updated:** 2026-04-08 00:19 CEST
 **Last updated:** 2026-04-08 00:09 CEST
 ---
-## Tier 1 — High impact, buildable now
+## Shipped (2026-04-07)
-### 1. Session path (pwd) sharing — DONE
+21 features implemented in one session. Full details in [`changelog-20260407.md`](./changelog-20260407.md).
-Add `cwd` to the WS hello handshake. Broker stores it in the peer record, `list_peers` returns it. Peers on the same machine see each other's working directories — lets AI reference files across sessions without guessing paths.
+| # | Feature | Commit |
-
+|---|---------|--------|
-**Effort:** 30 min. One field in hello + peer list.
+| 1 | Session path (cwd) sharing | `810f372` |
-
+| 2 | Peer metadata (type/channel/model) | `810f372` |
-> **Implemented:** 2026-04-07 23:30 · `810f372` · CLI 0.6.9 + broker deployed
+| 3 | System notifications (join/leave) | `453705a` |
-
+| 4 | Cron-based persistent reminders | `e873807` |
-### 2. Peer metadata: human vs AI, channel type, model — DONE
+| 5 | Simulation clock (x1–x100) | `05d9b56` |
-
+| 6 | Inbound webhooks | `b55cf26` |
-Extend the hello handshake with `peerType: "ai" | "human" | "connector"`, `channel?: "claude-code" | "telegram" | "slack" | "web"`, `model?: "opus-4" | "sonnet-4" | "gpt-5" | ...`. Broker stores and broadcasts it. `list_peers` shows it.
+| 7 | Slack connector | `5563f90` |
-
+| 8 | Telegram connector | `fe92853` |
-**Why:** Foundation for connectors, human peers, and smart routing (send complex analysis to the Opus peer, quick tasks to Sonnet).
+| 9 | SDK (@claudemesh/sdk) | `7e102a2` |
-
+| 10 | Mesh skills catalog | `c8cb1e3` |
-**Effort:** 1 hour.
+| 11 | Shared project files (+ local/remote detection) | `504111c` + `2c9c8c7` |
-
+| 12 | Peer stats reporting | `b3b9972` |
-> **Implemented:** 2026-04-07 23:30 · `810f372` · Shipped with item 1 (same commit)
+| 13 | Signed audit log (SHA-256 hash chain) | `86a2583` |
-
+| 14 | Mesh templates (5 presets) | `69e93d4` |
-### 3. System notifications (join/leave/resource events) — DONE
+| 15 | Default mesh guidance on install | `b0dc538` |
-
+| 16 | Mesh MCP proxy (dynamic tools) | `08e289a` |
-Broker pushes system-level messages when peers connect/disconnect, files get shared, state changes, tasks get created. Same `subtype` pattern as reminders: `{ type: "push", subtype: "system", event: "peer_joined", ... }`.
+| 17 | Dashboard: peer graph + timeline + resources | `59332dc` + `7d432b3` |
-
+| 18 | Peer visibility + public profiles | (types.ts/index.ts) |
-**Why:** Mesh feels alive. AI can react to topology changes without polling.
+| 19 | Hostname + local/remote locality | `2c9c8c7` |
-
+| 20 | MCP register/unregister broadcasts | `e09671c` |
-**Effort:** 2 hours.
+| 21 | File access decision guide | `3641618` |
 > **Implemented:** 2026-04-07 23:20 · `453705a` · peer_joined + peer_left broadcasts, system subtype in push
 ### 4. Cron-based reminders — DONE
 Replace `setTimeout` with a persistent cron scheduler (broker-side). AI sends `schedule_reminder --cron "0 */2 * * *" --message "check deploy status"`. Broker uses `node-cron` or Drizzle-backed scheduler. Survives broker restarts.
 **Why:** Current reminders die if the broker restarts. Cron syntax is already familiar to AI.
 **Effort:** 2 hours (+ DB migration for persistence).
 > **Implemented:** 2026-04-07 23:35 · `e873807` · DB-persisted schedules, zero-dep cron parser, restart recovery, `--cron` CLI flag
 ### 5. Heartbeats / session supervisor + simulation clock — DONE
 **Keepalive layer:** WebSocket ping/pong for connection health. A CLI-side supervisor monitors the WS connection and relaunches Claude Code if it drops. Broker marks peers as disconnected on WS close.
 **Simulation clock layer:** Heartbeats become a broker-driven clock that peers can subscribe to. The broker broadcasts periodic `{ subtype: "heartbeat", tick: 42, simTime: "2026-04-08T14:30:00Z", speed: "x10" }` messages at a configurable rate.
 **Time multiplier for load testing:**
 - `mesh_set_clock(speed: "x1")` — real-time, normal operation
 - `mesh_set_clock(speed: "x10")` — 1 hour of simulated activity in 6 minutes
 - `mesh_set_clock(speed: "x100")` — 1 day of simulated activity in ~15 minutes
 **Use case — infrastructure stress testing:** Spawn 10 AI peers, each simulating a real user persona (sales rep, admin, customer). Set the clock to x10. Each peer receives heartbeat ticks and acts according to the simulated time: "it's 9am, log in and check dashboard", "it's 11am, process 5 orders", "it's 3pm, run reports". The infrastructure sees realistic usage patterns at 10x speed.
 **What peers see:**
 ```
 > mesh_clock()
 Simulation clock: x10 | sim time: 2026-04-08 14:30 | tick: 42/480
 > [heartbeat tick 43 — sim time: 14:36]
  AI peer "Sales-Rep-1": creates 3 orders, searches inventory
  AI peer "Admin-1": approves pending orders, checks stock levels
  AI peer "Customer-1": browses catalog, adds to cart, checks out
 ```
 **Components:**
 - Broker: clock state + periodic broadcast to all peers
 - MCP tools: `mesh_set_clock(speed)`, `mesh_clock()`, `mesh_pause_clock()`, `mesh_resume_clock()`
 - Peer behavior: AI reads tick + simTime from heartbeat, decides actions based on its persona and the simulated time of day
 - Reporting: broker collects action counts per tick, produces load profile after the run
 **Why this is powerful:** Unlike synthetic load testers (k6, Locust), AI peers exercise the *full stack* — UI flows, API sequences, edge cases, realistic data entry. They find bugs that scripted tests miss because they improvise like real users.
 **Effort:** 1 day (heartbeat + clock), 1 day (simulation framework + personas).
 > **Implemented:** 2026-04-07 · `05d9b56` · Per-mesh clock state, configurable speed x1-x100, auto-pause on empty mesh, heartbeat ticks via system push
 ---
-## Tier 2 — Strong ideas, needs design
+## Building now
-### 6. Mesh webhooks / REST API / external WebSocket — PARTIAL (webhooks done)
+### Peer session persistence ("welcome back")
 Persist peer state (groups, profile, visibility, stats, summary) to DB on disconnect. Restore on reconnect with enriched `hello_ack`. System notification: "Welcome back, Alice! Last seen 2h ago."
-Three surfaces for external integration:
+### Persistent MCP registrations
-
+MCP servers marked `persistent: true` survive peer disconnect. Marked "offline" instead of deleted. Auto-restored on reconnect. Calls to offline servers return descriptive error.
 - **Inbound webhooks:** `POST https://ic.claudemesh.com/hook/<mesh-id>/<secret>` → broker injects as a push to all peers or a specific group. GitHub, CI/CD, monitoring alerts become mesh messages.
 - **REST API:** Authenticated endpoints to send messages, read state, list peers from outside. Makes the mesh programmable from any language.
 - **External WS:** Non-Claude clients connect via WS with an API key (not a session keypair). Same protocol, different auth.
 **Prerequisite:** API keys per mesh (not ephemeral session keypairs).
 **Effort:** Half day (webhooks alone), 2-3 days (full API surface).
 > **Partial:** 2026-04-07 · `b55cf26` · Inbound webhooks implemented (POST /hook/:meshId/:secret → push to mesh). REST API and external WS remain.
 ### 7. Connectors: Slack, Telegram as peers — DONE
 **Approach 1 — Connector-as-peer (recommended start):** A bridge process joins the mesh as a peer named "Slack-#general" and relays messages bidirectionally. Peers see it in `list_peers` with `peerType: "connector"`. One connector per channel.
 **Approach 2 — Connector-as-router:** Broker-level integration — messages to `#slack:general` route through a registered connector. More elegant, but complex.
 Ship as `claudemesh-connector-slack`, `claudemesh-connector-telegram`.
 **Effort:** 1-2 days each.
 > **Implemented:** 2026-04-07 · Slack: `5563f90` (Socket Mode, echo prevention, auto-reconnect) · Telegram: `fe92853` (zero-dep Bot API, long polling)
 ### 8. Humans in the mesh
 Humans connect via the web dashboard or mobile app using the same WS protocol. `peerType: "human"` metadata tells AI to adjust communication style. The push system works natively in browsers (WS is bidirectional).
 **Challenge:** UX. Humans need a chat interface with typing indicators, read receipts, message history — not raw JSON. The dashboard already exists at claudemesh.com; extend it with a chat panel.
 **Effort:** 2-3 days (web chat panel).
 ### 9. Connecting non-Claude-Code AI — DONE
 Any process that speaks the WS protocol can join. The barrier isn't the protocol — it's the MCP tool surface that makes Claude Code sessions first-class. For other LLMs:
 - **SDK approach:** `npm install claudemesh-sdk` — a JS/Python library that handles WS connection, crypto, and message parsing. Wrap any LLM's function-calling interface around it.
 - **Push delivery:** The push system works over WS. Non-Claude clients receive pushes the same way. The challenge is injecting them into the LLM's context — each platform has a different mechanism (OpenAI function results, Gemini tool responses, etc.).
 - **Adapter pattern:** `claudemesh-adapter-openai`, `claudemesh-adapter-cursor`, etc.
 **Effort:** 1 day (SDK), 1 day per adapter.
 > **Implemented:** 2026-04-07 · `7e102a2` · `@claudemesh/sdk` — standalone TypeScript SDK with libsodium crypto_box, EventEmitter API, auto-reconnect
 ### 10. Mesh skills catalog — DONE
 Peers publish skills: `share_skill({ name: "pdf-generation", description: "...", instructions: "..." })`. Other peers `list_skills()` and `get_skill("pdf-generation")` to load instructions into their context. Broker stores skills like memory/state.
 **Why:** A mesh becomes a capability marketplace. One session installs a skill, all peers benefit. Skills can include tool definitions, system prompts, reference docs, and example workflows.
 **This is the killer feature.** It turns claudemesh from a messaging layer into a knowledge-sharing platform.
 **Effort:** 1 day.
 > **Implemented:** 2026-04-07 · `c8cb1e3` · Full CRUD (share/get/list/remove), upsert by name, ILIKE search, Drizzle schema
 ### 11. Shared project files across peers — DONE
 When a peer connects, it registers accessible paths (opt-in per directory). Other peers request files: `get_peer_file(peer: "Alice", path: "src/auth.ts")`. The owning peer reads the file and returns it over the mesh.
 **Security scoping options:**
 - Opt-in per directory: `claudemesh launch --share-dir ./src`
 - Same-machine only (detect via hostname/IP)
 - Approval per request
 **Effort:** 1 day.
 > **Implemented:** 2026-04-07 · `504111c` · Broker relay (never reads content), CLI file serving with 1MB cap, path traversal rejection, hidden files excluded, 2-level dir listing. Plus hostname-based local/remote detection (`2c9c8c7`) and filesystem shortcut hint (`a92cf6b`).
 ### 12. Peer stats (context consumption, token usage) — DONE
 Peers self-report: `set_status` extended with `contextUsed: 85000, contextMax: 200000, tokensIn: 12000, tokensOut: 8000`. Dashboard shows burn rate. Useful for load balancing — route work to the peer with the most context headroom.
 **Limitation:** Claude Code doesn't expose context usage via API. Would need estimation from conversation length or `/cost` command parsing.
 **Effort:** Half day (reporting infrastructure), unknown (accurate context measurement).
 > **Implemented:** 2026-04-07 · `b3b9972` · Auto-reporting every 60s (messagesIn/Out, toolCalls, uptime, errors), mesh_stats MCP tool, stats in list_peers
 ---
-## Tier 3 — Big bets, needs careful thought
+## Remaining — not yet built
-### 13. Mesh blockchain / signed audit log — DONE (audit log)
+### Humans in the mesh
-
+Web chat panel on claudemesh.com/dashboard. Humans connect via WS with `peerType: "human"`. Need: typing indicators, read receipts, message history UI.
 **Honest assessment:** A full blockchain is overkill for a cooperative mesh. What's actually valuable is the useful parts:
 - **Signed append-only log:** Immutable record of all decisions, state changes, and messages. Merkle tree integrity. Useful for compliance, debugging, and "who decided what."
 - **Conflict resolution:** Vector clocks or CRDTs for state, instead of last-write-wins.
 - **Reputation:** Track which peers deliver on tasks, respond promptly, produce quality work.
 **Reframe as:** Signed audit trail with integrity proofs. Not a blockchain, but the valuable properties of one.
 **Effort:** 3-5 days.
 > **Implemented:** 2026-04-07 · `86a2583` · SHA-256 hash chain audit log, append-only, no message content logged, chain verification endpoint, paginated query
 ### 14. Mesh of meshes / bridge
 A meta-broker that routes between meshes. Use case: `dev-team` mesh and `ops-team` mesh coordinate on deploys.
 **Simple version:** A bridge peer joins both meshes and relays tagged messages. No broker changes needed. Already feasible with today's protocol.
 **Federation version:** Broker-to-broker peering protocol. Brokers exchange presence and route ciphertext across organizations.
 **Effort:** 1 day (bridge peer), 1-2 weeks (federation protocol).
 ### 15. Mesh templates on creation — DONE
 Predefined mesh configurations: roles, groups, state keys, system prompts, skills, and governance rules. Examples:
 - `dev-team`: @frontend, @backend, @devops groups; lead/member roles; state keys for sprint/deploy-frozen
 - `research`: @analysis, @writing groups; shared memory focus; context-sharing optimized
 - `ops-incident`: @oncall, @comms groups; high-urgency defaults; auto-escalation rules
 Templates are JSON files. `claudemesh create --template dev-team` applies them at mesh creation. Templates are editable post-creation by mesh admin (or anyone, depending on governance).
 **Effort:** Half day.
 > **Implemented:** 2026-04-07 · `69e93d4` · 5 templates (dev-team, research, ops-incident, simulation, personal) + `claudemesh create` command
 ### 16. Default private mesh per user — DONE
 On `claudemesh install`, auto-create a personal mesh with the user as sole member. All their Claude Code sessions join by default. Zero-config — instant value without understanding meshes.
 **Effort:** Half day.
 > **Implemented:** 2026-04-07 · `b0dc538` · Install detects empty meshes, shows join guidance. Local-only mesh deferred (requires broker enrollment).
 ### 17. Mesh MCP proxy (dynamic tools without session restart) — DONE
 **Problem:** Claude Code loads MCP servers at startup. You can't inject new tool definitions into a running session.
 **Solution:** Route through the existing claudemesh MCP connection. A generic `mesh_tool_call` tool proxies to MCP servers registered in the mesh at runtime — no restart needed.
 **Flow:**
 1. A peer registers an MCP server: `mesh_mcp_register(name: "github", transport: "stdio", command: "npx @github/mcp")`
 2. Broker stores the registration
 3. Any peer calls `mesh_tool_call(server: "github", tool: "list_repos", args: {...})`
 4. Broker routes to the hosting peer or a shared sidecar process
 5. That host invokes the actual MCP server, returns the result through the mesh
 6. Calling peer gets the response — all through the existing claudemesh WS connection
 **Two hosting models:**
 - **Peer-hosted:** The registering peer runs the MCP server locally. Other peers proxy through them. If that peer disconnects, the MCP goes offline.
 - **Broker-hosted:** The broker spawns the MCP server as a sidecar. Always available. Better for shared tools (database, GitHub, Jira).
 **What AI sees:**
 ```
 > mesh_mcp_list()
 Available mesh MCP servers:
 - github (hosted by: Alice) — tools: list_repos, create_issue, ...
 - jira (hosted by: broker) — tools: search_issues, create_ticket, ...
 - postgres-prod (hosted by: broker) — tools: query, execute
 > mesh_tool_call(server: "github", tool: "create_issue", args: {repo: "...", title: "..."})
 Issue #42 created.
 ```
 **Limitation:** Claude Code won't see these as first-class tools in its tool list — AI needs to know to use `mesh_tool_call`. MCP server instructions document the proxy pattern.
 **New MCP tools needed:** `mesh_mcp_register`, `mesh_mcp_list`, `mesh_tool_call`, `mesh_mcp_remove`
 **Effort:** 2-3 days.
-> **Implemented:** 2026-04-07 · `08e289a` · Full round-trip: register → list → call → forward → execute → result. In-memory registry, 30s call timeout, auto-cleanup on disconnect.
+### REST API + external WebSocket
 Authenticated endpoints to send messages, read state, list peers from outside the mesh. API keys per mesh (not session keypairs). External WS: non-Claude clients connect with API key auth.
-### 18. Sandbox for code execution
+**Effort:** 2-3 days. (Webhooks already done.)
-Each mesh gets optional compute sandboxes (Docker containers, Firecracker VMs, or E2B-style). Peers request: `execute_code(lang: "python", code: "...")`. Broker provisions a sandbox, runs the code, returns stdout/stderr. Resources scale on demand as peers need sandboxes.
+### Bridge / federation
 **Simple:** A bridge peer joins two meshes and relays tagged messages. Feasible now with the SDK.
 **Federation:** Broker-to-broker peering protocol. Needs design.
-**Build vs integrate:**
+**Effort:** 1 day (bridge), 1-2 weeks (federation).
 - **Build:** Docker-in-Docker on the broker host. Simple but security-sensitive.
 - **Integrate:** E2B, Modal, or Fly Machines as the sandbox backend. claudemesh MCP tool is a thin client. Scales naturally.
-**Effort:** 2-3 days (E2B integration), 1-2 weeks (self-hosted sandboxes).
+### Sandboxes for code execution
 Per-mesh compute sandboxes. Peers request: `execute_code(lang: "python", code: "...")`. Prefer third-party integration (E2B, Modal, Fly Machines) over self-hosted.
-### 19. Mesh dashboard (real-time situational awareness) — DONE
+**Effort:** 2-3 days (E2B), 1-2 weeks (self-hosted).
-Live web UI at claudemesh.com/dashboard showing:
+### Spatial topology (proximity-based visibility)
- **Peer graph:** Who's connected, status, groups, roles — nodes and edges
+Extend visibility with `(x, y)` coordinates and visibility radius. Peers only see others within range. Combined with sim clock, enables spatial simulations (customer walks into store zone, sees sales reps).
 - **Message flow:** Animated edges showing real-time traffic between peers
 - **State/memory timeline:** When values changed and who changed them
 - **Resource panel:** Files shared, tasks active, skills available
 - **Peer detail:** Click a peer → see summary, context usage, message history
-Broker already tracks everything needed. Dashboard subscribes via WS and renders with D3/React.
+**Effort:** 1 day.
-**Effort:** 2-3 days (functional), 1 week (polished).
+### Semantic peer search
-
+`search_peers(query, filters?)` — multi-field matching across names, groups, roles, summaries, profile capabilities, skills. Ranked results. For meshes with 50+ peers.
 > **Implemented:** 2026-04-07 · `59332dc` peer graph (radial SVG, animated edges, group rings) + `7d432b3` state timeline + resource panel. Peer detail view remains.
 ### 20. Peer visibility and spatial topology — DONE (visibility + profiles)
 Control which peers can see each other. Instead of a flat mesh where everyone sees everyone, the broker filters `list_peers` responses and message routing based on visibility rules.
 **Three visibility models:**
 - **Proximity-based (simulation):** Each peer has coordinates `(x, y)` and a visibility radius. Only peers within range appear in `list_peers`. `set_position(x, y)` changes who you can see — spatial fog of war. Combined with the simulation clock, this creates emergent behavior: a "customer" peer walks into a "store zone", suddenly sees "sales rep" peers, initiates interaction.
 - **Scope-based (organizational):** Visibility follows group membership. Peers in `@frontend` see each other and `@leads`, but not `@backend` internals. Org-chart visibility without exposing every department.
 - **Manual/dynamic:** Peers or admins explicitly show/hide. `set_visible(false)` to go stealth (connected but invisible). Admin can force visibility/invisibility.
 **Who controls visibility:**
 - **Broker rules** — mesh-wide policy set at creation or via template (e.g., "proximity" mode for simulations, "scope" for orgs)
 - **Peer self-control** — `set_visible(false)` to go stealth, `set_position(x, y)` to move in proximity mode
 - **Admin override** — mesh admin force-shows or force-hides peers
 - **Dynamic conditions** — broker changes visibility based on state keys, clock ticks, or events
 **Notifications:** Peers receive `{ subtype: "system", event: "peer_visible" }` when a new peer enters their visibility and `peer_hidden` when one leaves. Different from join/leave — the peer is still connected, just not visible to you.
 **Peer public profile (outside image):** Each peer has a public-facing profile that other peers see — a curated view separate from internal state. Fields: `avatar` (emoji or URL), `title` (short role label), `bio` (one-liner), `capabilities` (what I can help with). Set via `set_profile({ avatar: "🔧", title: "DevOps Lead", bio: "Infrastructure and deploys" })`. This is what appears on the peer graph node and in `list_peers`. Peers choose how they present themselves to the mesh.
 **MCP tools:** `set_visible(visible)`, `set_position(x, y)`, `set_profile(profile)`, `get_visible_peers()`, `set_visibility_mode(mode)` (admin only)
 **Effort:** 2-3 days.
 > **Partial:** 2026-04-07 · Visibility toggle (set_visible), public profiles (set_profile), hidden peer filtering in list_peers, peer_visible/peer_hidden system events, direct messages still reach hidden peers. Remaining: proximity-based (x,y coordinates), scope-based (group visibility rules).
 ### 21. Semantic peer search
 In large meshes (50+ peers), scanning `list_peers` output is noise. A `search_peers` tool that filters and ranks by multiple dimensions:
 - **Structured filters:** name, group, role, status, peerType, channel, model, cwd
 - **Free-text search:** matches against peer summaries, profile bios, capabilities, and shared skills
 - **Capability matching:** "find a peer that knows about database migrations" searches across profile capabilities + skills catalog + recent summaries
 - **Ranking:** peers with more matching dimensions rank higher; active (idle/working) peers rank above DND/offline
 **MCP tool:** `search_peers(query, filters?)` — returns a ranked list of matching peers with relevance scores.
 **Implementation:** Broker-side — accepts a `search_peers` message, runs multi-field matching against the in-memory peer list + skills table. No external search engine needed for <500 peers; for larger meshes, wire into the existing Qdrant vector store (already available via `vector_search`).
 **Effort:** Half day.
-### 22. Mesh telemetry and debugging
+### Mesh telemetry and debugging
-
+Structured logging: `mesh_log(level, message, data?)`. Queryable: `mesh_logs(query?, peer?, level?, last?)`. Aggregated reports: `mesh_report(timeframe?)`. AI self-analysis for continuous improvement.
 A structured logging system where peers report errors, warnings, and debug info to the broker. Goes beyond the audit log (which tracks events) — this tracks operational health.
 **What peers report:**
 - Errors: tool failures, connection drops, unhandled exceptions
 - Warnings: high context usage, slow responses, retry patterns
 - Debug: decision traces, task reasoning, why a particular approach was chosen
 - Performance: response latency per tool call, message round-trip times
 **Broker storage:** Structured logs indexed by mesh, peer, timestamp, severity. Retained for N days (configurable). Queryable via WS messages.
 **AI self-analysis:** Peers query their own logs to identify patterns: "I've hit this error 3 times in the last hour — what's common?" The mesh becomes self-diagnosing. Leads can query team-wide logs: "Which peers are seeing errors in the deploy flow?"
 **Reporting:** Aggregated metrics per peer, per mesh, per time window. Error rates, common failure modes, response time percentiles. Surfaced in the dashboard or via `mesh_report(timeframe: "24h")`.
 **MCP tools:**
 - `mesh_log(level, message, data?)` — report a log entry
 - `mesh_logs(query?, peer?, level?, last?)` — query logs
 - `mesh_report(timeframe?)` — aggregated health report
 **Effort:** 1-2 days.
 ### 23. Peer session persistence ("welcome back")
 When a peer disconnects, their state is lost (groups, profile, visibility, stats, summary). On reconnect they start blank. Persist peer state so returning peers resume where they left off.
 **What persists (keyed by meshId + memberId):**
 - Groups and roles
 - Profile (avatar, title, bio, capabilities)
 - Visibility setting
 - Last summary
 - Cumulative stats (messages, tool calls across all sessions)
 - Last seen timestamp
 **What resets:** status (always "idle" on connect), WebSocket/presenceId (ephemeral).
 **Reconnect flow:**
 1. Peer sends hello with same `memberId`
 2. Broker looks up `peer_state` table for (meshId, memberId)
 3. If found: restore groups, profile, visibility, stats — hello fields take precedence if explicitly set
 4. Enriched `hello_ack` includes `restored: true` and previous summary
 5. System notification: `"Welcome back, Alice! Last seen 2h ago. Restored: @frontend:lead, @devops:member"`
 6. On disconnect: upsert current state to `peer_state`
 **Why:** AI sessions restart often (context limits, crashes, new tasks). Without persistence, every reconnect requires manual group joins and profile setup. With it, the mesh remembers who you are.
 **Effort:** Half day.
 ---
-## Suggested build order
+*Priorities shift as we build and learn. Bridge and humans are the highest-value remaining items.*
 | # | Feature | Effort | Unlocks | Status |
 |---|---------|--------|---------|--------|
 | 1 | Session path sharing | 30 min | File referencing across sessions | **DONE** `810f372` |
 | 2 | Peer metadata (type/channel/model) | 1 hour | Connectors, humans, smart routing | **DONE** `810f372` |
 | 3 | System notifications | 2 hours | Reactive mesh, awareness | **DONE** `453705a` |
 | 4 | Cron reminders | 2 hours | Persistent scheduling | **DONE** `e873807` |
 | 5 | Mesh templates | Half day | Better onboarding | **DONE** `69e93d4` |
 | 6 | Default personal mesh | Half day | Zero-config start | **DONE** `b0dc538` |
 | 7 | Inbound webhooks | Half day | External integrations | **DONE** `b55cf26` |
 | 8 | Skills catalog | 1 day | Knowledge marketplace | **DONE** `c8cb1e3` |
 | 9 | Shared project files | 1 day | Cross-session file access | **DONE** `504111c` |
 | 10 | Slack connector | 1-2 days | Reach beyond Claude Code | **DONE** `5563f90` |
 | 11 | Mesh MCP proxy | 2-3 days | Dynamic tools without restart | **DONE** `08e289a` |
 | 12 | Dashboard (real-time) | 2-3 days | Visual situational awareness | **DONE** `59332dc` + `7d432b3` |
 | 13 | Human peers (web chat) | 2-3 days | Humans in the loop | |
 | 14 | Simulation clock (heartbeat x1-x100) | 2 days | AI-driven load testing | **DONE** `05d9b56` |
 | 15 | Sandboxes (E2B) | 2-3 days | Shared compute | |
 | 16 | Signed audit log | 3-5 days | Trust, compliance | **DONE** `86a2583` |
 | 17 | Bridge / federation | 1-2 weeks | Multi-mesh coordination | |
 | 18 | Peer visibility + profiles | 2-3 days | Simulation fog-of-war, org scoping | **DONE** (types.ts/index.ts) |
 | 19 | Semantic peer search | Half day | Discovery in large meshes | |
 | 20 | Peer stats reporting | Half day | Resource awareness, load balancing | **DONE** `b3b9972` |
 | 21 | SDK (@claudemesh/sdk) | 1 day | Non-Claude-Code clients | **DONE** `7e102a2` |
 | 22 | Telegram connector | 1-2 days | Reach beyond Claude Code | **DONE** `fe92853` |
 | 23 | Mesh telemetry + debugging | 1-2 days | Self-diagnosing mesh | |
 | 24 | Peer session persistence | Half day | "Welcome back" on reconnect | |
 ---
 *This document captures a brainstorming session. Items are not commitments. Priorities will shift as we build and learn.*