Replaces the agent-group-centric "main group" concept with user-level
privileges and adds the cold-DM infrastructure needed for proactive
outbound messaging (pairing, approvals, welcome flows).
Privilege model
- New tables: users, user_roles (owner global-only; admin global or
scoped to an agent_group), agent_group_members (explicit non-
privileged access; admin/owner imply membership), user_dms (cold-DM
resolution cache).
- Removed agent_groups.is_admin, messaging_groups.admin_user_id. Replaced
with messaging_groups.unknown_sender_policy (strict | request_approval
| public) for per-chat unknown-sender gating.
- src/access.ts: canAccessAgentGroup, pickApprover, pickApprovalDelivery.
- src/router.ts: access gate on every inbound, honoring
unknown_sender_policy for unknown senders.
- src/channels/telegram.ts: pairing interceptor upserts the paired user
and promotes them to owner if hasAnyOwner() is false (first-pair-wins).
Cold DM infrastructure
- ChannelAdapter.openDM?(handle) — optional method. Chat-SDK-bridge wires
it to chat.openDM() for resolution-required channels (Discord, Slack,
Teams, Webex, gChat); direct-addressable channels (Telegram, WhatsApp,
iMessage, Matrix, Resend) fall through to the handle directly.
- src/user-dm.ts: ensureUserDm(userId) — resolves + caches via user_dms.
Approval routing
- onecli-approvals + delivery use pickApprover + pickApprovalDelivery:
scoped admins → global admins → owners (dedup), first reachable via
ensureUserDm, same-channel-kind tie-break. Approvals land in the
approver's DM, not the origin chat.
Delivery fixes
- delivery.ts ACL rejection now throws instead of returning undefined —
the outer loop previously marked rejected messages as delivered.
- Implicit-origin allow: session.messaging_group_id === target skips the
destination check.
- createMessagingGroupAgent auto-creates the companion agent_destinations
row (normalized local_name from the messaging group's name, collision-
broken within the agent's namespace).
Container
- container-runner.ts: /workspace/global always read-only; drops
NANOCLAW_IS_ADMIN; adds NANOCLAW_ADMIN_USER_IDS (owners + global admins
+ scoped admins for this agent group). Agent-runner poll-loop gates
slash commands against that set.
New skill: /init-first-agent
- Walks the operator through standing up the first agent for a channel:
channel pick → identity lookup (reads each channel SKILL.md's
## Channel Info > how-to-find-id) → DM platform_id resolution (direct-
addressable, cold-DM via "user DMs bot first + sqlite lookup", or
Telegram pair-code fallback) → run scripts/init-first-agent.ts →
verify via tail of nanoclaw.log.
- scripts/init-first-agent.ts: parameterized helper that upserts the
user + grants owner (if none), creates dm-with-<display-name> agent
group + initGroupFilesystem, reuses/creates the DM messaging_group,
wires it (auto-creates destination), resolves the session, and writes
a kind:'chat' / sender:'system' welcome message into inbound.db. Host
sweep wakes the container and the agent DMs the operator via the
normal delivery path.
/manage-channels rewrite
- Drops --is-main / --jid / main-vs-non-main isolation references.
- First-channel flow delegates to /init-first-agent.
- Explains createMessagingGroupAgent auto-creates destinations.
- Adds a privileged-users show section.
setup/
- register.ts: drop --is-main, --jid, --local-name, --trigger
requiresTrigger defaults; call initGroupFilesystem; normalize to
v2 schema (no is_admin, no admin_user_id, sets unknown_sender_policy
'strict'); let createMessagingGroupAgent handle the destination row.
- pair-telegram.ts: emit PAIRED_USER_ID (namespaced "telegram:<id>")
instead of ADMIN_USER_ID; update header comment.
- register.test.ts deleted — was v1-only, tested a registered_groups
table that no longer exists.
Docs
- v2-architecture-diagram.{md,html}: ER diagram updated to drop
is_admin/admin_user_id, add unknown_sender_policy, and include
users/user_roles/agent_group_members/user_dms.
- v2-architecture-draft.md: approval-routing paragraph rewritten for
pickApprover/pickApprovalDelivery/ensureUserDm; SQL schema block
updated; admin-verification paragraph references
NANOCLAW_ADMIN_USER_IDS.
- v2-setup-wiring.md: entity-model sketch rewritten.
- v2-checklist.md: marked privilege refactor / container filtering /
approval routing / unknown-sender gating done; removed obsolete
admin_user_id and main-vs-non-main items.
Scripts
- scripts/init-first-agent.ts (new) replaces scripts/welcome-owner-dm.ts
(removed; welcome-owner was a Discord-specific one-off).
- test-v2-host.ts, test-v2-channel-e2e.ts, seed-discord.ts: drop
is_admin + admin_user_id, use unknown_sender_policy.
Tests
- src/access.test.ts (new): 14 tests for canAccessAgentGroup, role
helpers, pickApprover, ensureUserDm, pickApprovalDelivery.
- src/db/db-v2.test.ts: adds 3 tests for the auto-created
agent_destinations row (normalized name, no duplicates, collision
break within an agent group).
- host-core.test.ts, channel-registry.test.ts: updated fixtures to
use unknown_sender_policy: 'public' where the test exercises routing
rather than the access gate.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
6.1 KiB
v2 Setup Wiring — Status & Remaining Work
Last updated: 2026-04-09, branch v2, commit 1dc5750
What's Done
Two-DB Split (session DB write isolation)
- Session DB split into
inbound.db(host-owned) andoutbound.db(container-owned) - Each file has exactly one writer — eliminates SQLite write contention across host-container mount
- Host uses even seq numbers, container uses odd (collision-free)
- Container heartbeat via file touch (
/workspace/.heartbeat) instead of DB UPDATE - Scheduling MCP tools emit system actions via messages_out; host applies them to inbound.db in
delivery.ts:handleSystemAction() - Host sweep reads
processing_acktable + heartbeat file mtime for stale detection - Container clears stale
processing_ackentries on startup (crash recovery) - Files:
src/db/schema.ts(INBOUND_SCHEMA + OUTBOUND_SCHEMA),src/session-manager.ts,src/delivery.ts,src/host-sweep.ts,container/agent-runner/src/db/connection.ts,messages-in.ts,messages-out.ts,poll-loop.ts,mcp-tools/scheduling.ts,mcp-tools/interactive.ts - Container image rebuilt with tsconfig excluding v1 (
container/agent-runner/tsconfig.json) - E2E verified: host → Docker container → Claude responds → "E2E works!" ✓
OneCLI Integration
ensureAgent()call added beforeapplyContainerConfig()insrc/container-runner.ts- Without
ensureAgent, OneCLI rejects unknown agent identifiers and returns false, leaving container with no credentials - E2E verified with OneCLI credential injection ✓
Channel Barrel
src/index.tsimports./channels/index.js(the barrel)- Channel skills uncomment lines in the barrel to enable channels
- Discord is uncommented by default (it was previously a direct import in index.ts)
Setup Registration (partially)
setup/register.tsrewritten to create v2 entities (agent_groups,messaging_groups,messaging_group_agents) indata/v2.db- Accepts
--platform-id(v2) and--jid(v1 compat) flags - Added
getMessagingGroupAgentByPair()to prevent duplicate wiring setup/verify.tsupdated to check v2 central DB (counts agent groups with wiring)
Router Logging
src/router.tslogsMESSAGE DROPPEDat WARN level when no agents wired, with actionable guidance
Previously Open — Now Resolved
1. v2 Channel Skills Don't Register Groups ✅
Channel skills now point to /manage-channels in their "Next Steps" section. Registration is handled by the /manage-channels skill, which reads each channel's ## Channel Info section for platform-specific guidance. Channel skills stay lean (credentials only).
2. v1 add-discord Skill is Incompatible ✅
Created /add-discord-v2 skill matching the v2 pattern. Setup SKILL.md updated to reference /add-discord-v2.
3. Setup SKILL.md Missing Group Registration Step ✅
Added step 5a "Wire Channels to Agent Groups" between channel installation (step 5) and mount allowlist (step 6). This step invokes /manage-channels which handles agent group creation, isolation level decisions, and wiring.
4. Channel Skills Should Know Channel Type ✅
Each v2 channel skill now has a ## Channel Info structured section with: type, terminology, how-to-find-id, supports-threads, typical-use, default-isolation. The /manage-channels skill reads this for contextual recommendations.
5. Verify Step Channel Auth Check ✅
setup/verify.ts now checks all v2 channel tokens: DISCORD_BOT_TOKEN, TELEGRAM_BOT_TOKEN, SLACK_BOT_TOKEN+SLACK_APP_TOKEN, GITHUB_TOKEN, LINEAR_API_KEY, GCHAT_CREDENTIALS, TEAMS_APP_ID+TEAMS_APP_PASSWORD, WEBEX_BOT_TOKEN, MATRIX_ACCESS_TOKEN, RESEND_API_KEY, WHATSAPP_ACCESS_TOKEN, IMESSAGE_ENABLED, plus WhatsApp Baileys auth dir.
6. Agent-Shared Session Mode ✅
Added session_mode: 'agent-shared' for cross-channel shared sessions (e.g. GitHub + Slack in one conversation). Session resolution looks up by agent_group_id instead of messaging_group_id when this mode is set.
Architecture Reference
v2 Entity Model
agent_groups (id, name, folder, agent_provider, container_config)
↕ many-to-many
messaging_groups (id, channel_type, platform_id, name, is_group, unknown_sender_policy)
via
messaging_group_agents (messaging_group_id, agent_group_id, trigger_rules, session_mode, priority)
users (id, kind, display_name) -- namespaced as "<channel>:<handle>"
user_roles (user_id, role, agent_group_id) -- owner / admin (global or scoped)
agent_group_members (user_id, agent_group_id) -- unprivileged access gate
user_dms (user_id, channel_type, messaging_group_id) -- cold-DM cache
Privilege is a user-level concept — there is no "main" agent group or "admin" messaging group. user_roles carries owner (global only, first pairing sets it) and admin (global or scoped to an agent_group_id). Unknown-sender gating is per-messaging-group via messaging_groups.unknown_sender_policy (strict | request_approval | public).
Message Flow
Channel adapter → routeInbound() → resolve messaging_group → resolve agent via messaging_group_agents
→ resolve/create session → write to inbound.db → wake container → agent-runner polls inbound.db
→ agent responds → writes to outbound.db → host delivery poll reads outbound.db → deliver via adapter
Key Files
| File | Purpose |
|---|---|
src/index.ts |
v2 entry point, imports channel barrel |
src/channels/index.ts |
Channel barrel — uncomment to enable |
src/router.ts |
Inbound routing, auto-creates messaging groups |
src/session-manager.ts |
Creates inbound.db + outbound.db per session |
src/delivery.ts |
Polls outbound.db, delivers, handles system actions |
src/host-sweep.ts |
Syncs processing_ack, stale detection, recurrence |
src/container-runner.ts |
Spawns containers, OneCLI ensureAgent + applyContainerConfig |
setup/register.ts |
Creates v2 entities (agent_group, messaging_group, wiring) |
setup/verify.ts |
Checks v2 central DB for registered groups |
container/agent-runner/src/db/connection.ts |
Two-DB connection layer (inbound read-only, outbound read-write) |