Drops the in-chat credential-collection flow introduced in e92b245. Agents
can no longer collect API keys via a secure modal — users must add secrets
through OneCLI directly. Keeps the OneCLI manual-approval handler and
threaded-routing work from the same commit intact.
Removed:
* container/agent-runner/src/mcp-tools/credentials.ts (MCP tool)
* src/credentials.ts (host-side modal/OneCLI pipeline)
* src/db/credentials.ts + migration 005 (pending_credentials table)
* src/onecli-secrets.ts (createSecret CLI facade, only caller was credentials.ts)
* findCredentialResponse from agent-runner DB layer
* PendingCredential types
* Four credential hooks from ChannelSetup (getCredentialForModal,
onCredentialReject, onCredentialSubmit, onCredentialChannelUnsupported)
* Credential card/modal handling in chat-sdk-bridge (nccr/nccm prefixes,
Modal/TextInput imports)
* credential_request text fallback in WhatsApp adapter
* request_credential system-action case in delivery.ts
Added:
* Migration 009 drops pending_credentials on existing installs.
Vercel skill now tells the agent to ask the user to register the token via
OneCLI instead of invoking the removed tool.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Baileys 6.7.21 silently failed the pairing handshake. Upgrade to 6.17.16
which fixes this. Three related issues:
1. proto is no longer a named ESM export in 6.17.x — use createRequire
to import via CJS (matching the proven v1 pattern).
2. Setup auth script didn't handle the 515 stream restart that WhatsApp
sends after successful pairing. Refactored to reconnect (matching v1's
connectSocket(isReconnect) pattern) instead of hanging until timeout.
3. Added succeeded guard and process.exit(0) to prevent timeout race
after successful auth.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Avoids running `ls -d ~/.openclaw` as a separate Bash command which
triggers permission prompts for reading outside the project directory.
The environment step now reports OPENCLAW_PATH in its status block.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Enable Linear channel adapter. Fix setup permission rules: use specific
npm install entries per adapter package, replace cp -r with rsync -a to
avoid built-in cp safety prompt, add head to allow list for chained
commands. Update Linear API key URL.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add unregistered_senders table to capture dropped message origins
(one row per sender, upserted with message_count and last_seen)
- Add inbound DM logging to chat-sdk-bridge for debugging
- Add vercel CLI to base container image
- Install vercel-cli and frontend-engineer container skills
- Default requiresTrigger to false in register step
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Disable sandbox by default in project settings
- Setup: remove Apple Container option (Docker only), single channel selection
with plain text list, move fork to end, auto-set empty mounts, add command
pre-approval step, add UTC timezone confirmation, add wait-on-user guidance,
add 5m timeouts for long steps
- iMessage: improve Full Disk Access UX with Finder open + drag instructions
- Add /manage-mounts skill for post-setup mount configuration
- Enable iMessage channel import
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The dev-agent-in-worktree approach for source self-modification is abandoned
in favor of a direct draft/activate flow with OS-level RO enforcement
(planned, not yet implemented). Strip the whole subgraph:
src/builder-agent/, pending-swaps DB module + migration 006, builder-agent
MCP tools, and all host wiring (startup sweep, approval routing, deadman,
worktree mount, freeze gate). Tool descriptions in self-mod.ts / agents.ts
no longer cross-reference create_dev_agent. CLAUDE.md + v2-checklist updated
to describe the new direction.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Checkpoints the builder-agent dev-agent/worktree/swap flow (create_dev_agent,
request_swap, classifier, deadman, promote) before pivoting to a unified
draft-activate approach with OS-level RO enforcement. Lifts container_config
out of the agent_groups row into groups/<folder>/container.json so install_packages,
add_mcp_server, and rebuild flows can eventually route through the same draft
path as source edits.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- create_agent is not admin-gated (host has no role check on the system
action; agentTools unconditionally in the container MCP tool list).
- install_packages / add_mcp_server approval is owner/admin via
pickApprover, not "admin-only".
- Chat-first setup bootstrap + post-handoff welcome are partially done
via /setup + /init-first-agent (still TODO: single top-level entrypoint,
welcome prompt expansion).
- Add entries for cold-DM infrastructure (ChannelAdapter.openDM,
ensureUserDm, user_dms cache) and /init-first-agent skill under
Channel Adapters.
- Add entry for delivery ACL throw-on-unauthorized + implicit-origin
allow + auto-create agent_destinations on wire (the silent-drop bug
fix from the welcome-DM end-to-end test).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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>
Claude Code's @-import directive only follows paths inside the project
memory tree (cwd + ancestors). Both `@/workspace/global/CLAUDE.md` and
`@../global/CLAUDE.md` are silently ignored because `/workspace/global`
is outside `/workspace/agent` (the cwd). The import line is parsed but
the content is never loaded — validated with a sentinel passphrase test
against a live container.
Fix: drop a `.claude-global.md` symlink into each group's dir pointing
at `/workspace/global/CLAUDE.md`. The link path is absolute on container
terms (dangling on host, valid via the /workspace/global mount) and the
symlink file itself is inside cwd, so Claude's @-import is happy. The
group's CLAUDE.md imports via `@./.claude-global.md`.
- src/group-init.ts: initGroupFilesystem now drops the symlink (idempotent,
uses lstat so existsSync doesn't trip on the dangling target on the
host). Default CLAUDE.md body uses `@./.claude-global.md`.
- scripts/migrate-group-claude-md.ts: creates the symlink for existing
groups and rewrites any broken `@/workspace/global/CLAUDE.md` or
`@../global/CLAUDE.md` import line to `@./.claude-global.md`.
- groups/main/CLAUDE.md: migration rewrote the import.
Validated: live container with the symlinked import correctly surfaces
global CLAUDE.md content (passphrase `quinoa-submarine-42` added to
global, retrieved via claude -p, removed).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Each group's on-disk state (CLAUDE.md, .claude-shared/, agent-runner-src/)
is now initialized exactly once at group creation and owned by the group
forever after. Spawn does only mounts — no copies, no settings.json
overwrites, no skill clobbers, no source resyncs.
Global memory composition switches from "host reads /workspace/global/CLAUDE.md
at bootstrap and stuffs it into systemPrompt.append" to "group CLAUDE.md
imports it via @/workspace/global/CLAUDE.md at the top." Edits to global
propagate instantly through the existing read-only mount; no copy, no
restart.
- src/group-init.ts: new initGroupFilesystem(group, opts?) — idempotent,
populates groups/<folder>/, .claude-shared/, agent-runner-src/ only when
paths don't already exist.
- src/container-runner.ts: buildMounts() calls init defensively at the
top (catches existing groups on first spawn after this change), drops
the inline settings.json write, skills cpSync loop, and agent-runner-src
rm-then-copy. Just mounts now.
- src/delivery.ts: create_agent flow uses initGroupFilesystem with
optional instructions, replacing the inline mkdirSync + writeFileSync.
- container/agent-runner/src/index.ts: drops GLOBAL_CLAUDE_MD reading.
systemContext.instructions is now only the runtime-generated
destinations addendum.
- scripts/migrate-group-claude-md.ts: one-shot migration that prepends
the @-import to existing groups' CLAUDE.md. Skips if global doesn't
exist or if the @-import is already present (regex match on the @ form
to avoid false positives from prose mentions of the path).
- groups/main/CLAUDE.md: prepended by the migration.
Existing groups need a one-time wipe of their agent-runner-src/ dir so
init re-populates from current host source — done locally before this
commit. Future host-side updates to container/skills/ or
container/agent-runner/src/ won't auto-propagate; that's the trade-off
for unconditional persistence and will be covered by host-mediated
refresh tools in a follow-up.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
fs.cpSync never removes files that disappeared from the source, so
renamed or deleted files linger in data/v2-sessions/<group>/agent-runner-src/.
The container's entrypoint runs tsc over the whole mounted src via
tsconfig's `include: ["src/**/*"]`, so a single stale file fails the
compile and the container exits 2.
Latent since the dir was introduced — surfaced when the provider
interface refactor made a leftover index-v2.ts stop typechecking.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Reshape AgentProvider so provider-specific assumptions stop leaking into
the generic layer. No change to what reaches sdkQuery() — same values,
different plumbing.
- QueryInput: opaque `continuation` replaces `sessionId` + `resumeAt`;
`systemContext.instructions` replaces ambiguous `systemPrompt`;
`mcpServers`, `env`, `additionalDirectories` move to `ProviderOptions`
at construction time.
- AgentProvider gains `isSessionInvalid(err)` and
`supportsNativeSlashCommands` so the poll-loop stops regex-matching
Claude error strings and gates passthrough slash commands per provider.
- ClaudeProvider owns `CLAUDE_CODE_AUTO_COMPACT_WINDOW` and the
stale-session regex internally.
- ProviderEvent.activity kept and documented as the liveness signal
(fires on every SDK message so the idle timer stays honest during
long tool runs); init carries `continuation` instead of `sessionId`.
- poll-loop drops mcpServers/env/systemPrompt from its config; admin
user id now passed explicitly.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
send_file and send_message with an explicit `to` parameter were always
setting thread_id to null, causing files and messages to land in the
Discord channel root instead of the thread the session is bound to.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Aligns with upstream feat/chat-sdk-integration pattern: regex-based
routing (/webhook/{adapterName}), response streaming, cleanup function.
Updates Slack and Teams skill docs to match /webhook/{name} convention
used by all other v2 channel skills.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Route webhook requests through chat.webhooks[name]() instead of calling
adapter.handleWebhook() directly, getting proper auto-initialization and
signature verification. Extract Node↔Web Request/Response conversion
into reusable helpers, parse URL pathname properly for query string
safety, and support all HTTP methods (not just POST).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Move all raw SQL out of session-manager, delivery, and host-sweep into
a dedicated DB module. Make session schemas idempotent (IF NOT EXISTS)
so initSessionFolder always applies them. Revert the markdown
plain-text retry from 4c477ac.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- session-manager.ts: shrink the cross-mount invariant header from 31
lines to 12, keeping each invariant's cause and consequence inline.
- agent-runner/db/connection.ts: parallel cross-mount comment for the
container-side reader (inbound.db must be journal_mode=DELETE).
- agent-runner/db/messages-out.ts: document that even/odd seq parity
is load-bearing — seq is the agent-facing message ID returned by
send_message and consumed by edit_message / add_reaction, looked
up across both tables.
- v2-checklist.md: record the cross-mount invariants and seq parity
under Core Architecture so future "simplifications" don't regress
them.
- scripts/sanity-live-poll.ts: empirical validation harness for the
three cross-mount invariants — flips each one and observes silent
message loss / corruption.
- delivery.ts: inline routeAgentMessage at its single callsite (-17
net lines). The wrapper added more boilerplate than it factored.
- docs/v2-architecture-diagram.{md,html}: rendered Mermaid diagrams
of the v2 system, message flow, named destinations, entity model,
and the two-DB split.
- channels/adapter.ts, chat-sdk-bridge.ts, credentials.ts,
db/sessions.ts, db/db-v2.test.ts: prettier format pass.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Mark OneCLI manual-approval integration and credential collection from chat
as partial with concrete sub-TODOs. Add upstream asks:
* Chat SDK input support beyond Slack — platforms support it natively
(Discord modals, Teams/GChat/Webex Adaptive Cards, WhatsApp Flows), Chat
SDK just doesn't expose the surfaces yet. Concrete per-platform mapping
captured.
* Built-in OneCLI apps shadow generic secrets on the same host; the
collection tool should check apps-list first and surface the connect URL
when an app exists.
* Tunneled OneCLI dashboard fallback for channels with no native form input.
* Per-agent-group secret scoping via OneCLI agentId.
* SDK-native secret management to replace the shell facade in onecli-secrets.
Also:
* Admin model refactor — instance-level default admin + per-group override
+ DM delivery when supported.
* Discord-specific Chat SDK quirks (first-message @mention requirement,
sub-thread materialization on subscribe).
* OneCLI migration check under Migration — flag whether existing installs
need OneCLI re-init (new SDK version, credentials re-scoped).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
session_state was added after the initial v2 schema with a lazy
`CREATE TABLE IF NOT EXISTS` in getOutboundDb(), so older session
outbound.db files have a session_state table from before updated_at
existed. The lazy create is a no-op when the table already exists,
leaving the column missing and causing:
Error: table session_state has no column named updated_at
on every `INSERT OR REPLACE INTO session_state` call.
Follow up the CREATE IF NOT EXISTS with a PRAGMA table_info check and
ALTER TABLE ADD COLUMN when updated_at is missing. Cheap on every open,
only runs DDL once per DB.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Three features built on top of @onecli-sh/sdk 0.3.1, landed together because
they share wiring surfaces (session DB schema, delivery dispatcher, Chat SDK
bridge, channel adapter contract).
## OneCLI manual-approval handler
* `src/onecli-approvals.ts` — long-polls OneCLI via the SDK's
`configureManualApproval`; on each request, delivers an `ask_question` card
to the admin agent group's first messaging group, persists a
`pending_approvals` row, and waits on an in-memory Promise resolved by the
admin's button click or an expiry timer. Expired cards are edited to
"Expired (...)" and a startup sweep flushes any rows left over from a
previous process.
* Short 11-byte approval id (`oa-<8 base36>`) instead of the SDK's UUID so the
Telegram 64-byte `callback_data` limit is respected; the OneCLI UUID stays
in the persisted payload for audit.
* Migration 003 consolidated: `pending_approvals` now has the OneCLI-aware
columns from the start (`agent_group_id`, `channel_type`, `platform_id`,
`platform_message_id`, `expires_at`, `status`), `session_id` relaxed to
nullable so cross-session approvals fit.
* `handleQuestionResponse` in `src/index.ts` now routes OneCLI approvals
through `resolveOneCLIApproval` before falling back to the
session-bound approval path.
## Credential collection from chat
New `trigger_credential_collection` MCP tool — the agent researches a
third-party API, calls the tool with `{name, hostPattern, headerName,
valueFormat, description}`, and blocks until the host reports saved, rejected,
or failed. The credential value never enters the agent's context: the user
submits it into a Chat SDK Modal on the host side, the host writes it to
OneCLI via a thin facade (`src/onecli-secrets.ts` — shells out to
`onecli secrets create`, shape mirrors the SDK we expect upstream), and only
the status string flows back to the container via a system message.
* `src/credentials.ts` — host-side handler: delivers the card to the
conversation's own channel (not the admin channel — credential collection
is a user-facing flow, distinct from admin approval), persists a
`pending_credentials` row, drives the submit → `createSecret` → notify
pipeline. Falls back gracefully when the channel doesn't support modals.
* `src/db/credentials.ts` + migration 005: `pending_credentials` table.
* `src/channels/chat-sdk-bridge.ts`: renders a `credential_request` card,
handles the `nccr:` action prefix by opening a Modal with a TextInput,
registers an `onModalSubmit` handler for the `nccm:` callback prefix.
* `container/agent-runner/src/mcp-tools/credentials.ts`: the blocking MCP
tool, mirroring the `ask_user_question` polling pattern.
* `container/agent-runner/src/db/messages-in.ts`: `findCredentialResponse`
helper to pick up the system message the host writes back.
## Threaded adapter routing
The destination layer previously didn't carry thread context, so agent replies
to Discord always landed in the root channel regardless of which thread the
inbound came from.
* `ChannelAdapter.supportsThreads: boolean` — declared by every channel skill
at `createChatSdkBridge`. Threaded: Discord, Slack, Teams, Google Chat,
Linear, GitHub, Webex. Non-threaded: Telegram, WhatsApp Cloud, Matrix,
Resend, iMessage.
* `src/router.ts`: non-threaded adapters strip `threadId` at ingest (threads
collapse to channel-level sessions). Threaded adapters override the
wiring's `session_mode` to `'per-thread'` so each thread = a session
(except `agent-shared`, which is preserved as a cross-channel intent the
adapter can't know about).
* `session_routing` table in `inbound.db` — single-row default reply routing
written by the host on every container wake from
`session.messaging_group_id` + `session.thread_id`. Forward-compat
`CREATE TABLE IF NOT EXISTS` handles older session DBs lazily.
* `container/agent-runner/src/db/session-routing.ts` — container-side reader.
* `send_message` / `send_file` / `ask_user_question` / `send_card` /
scheduling tools all default their routing (channel, platform, **and**
thread) from the session when no explicit `to` is given. Explicit `to`
uses the destination's channel with `thread_id = null` (cross-destination
sends start a new conversation elsewhere).
* `poll-loop.ts::sendToDestination` (the final-text single-destination
shortcut) now inherits `thread_id` from `RoutingContext` too — this was
the root cause of Discord replies landing in the root channel even after
`send_message` was wired correctly.
## Related cleanups
* `src/container-runner.ts`: OneCLI agent identifier switched from the lossy
folder-derived string to `agent_group.id`, making `getAgentGroup(externalId)`
a trivial reverse lookup for per-agent scoping.
* `wakeContainer` race fix via an in-flight promise map — concurrent wakes
during the async buildContainerArgs / OneCLI `applyContainerConfig` window
no longer double-spawn containers against the same session directory.
* `src/db/db-v2.test.ts`: dropped the brittle `expect(row.v).toBe(N)` schema
version assertion — it had to be bumped on every migration addition.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Capture the product direction that's been landing in recent work:
everything configurable from chat once bootstrap is done, skills as
the primary extension mechanism, and mark named destinations / agent
self-modification / agent-to-agent comms as complete.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The /workspace/ipc/* tree is a v1 leftover — v2 routes everything
through inbound.db / outbound.db. Refresh the surrounding comment to
describe what the entrypoint actually does.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The v2 poll loop held the session ID in a local variable, so every
container restart started a fresh SDK session even though the .jsonl
transcript was still sitting in the shared .claude mount. Store it in
outbound.db (container-owned, already per channel/thread), seed the
loop on startup, clear on /clear, and recover from stale-session
errors the same way v1 did.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The per-session destination map was being written as a sidecar JSON file
(/workspace/.nanoclaw-destinations.json) — inconsistent with the rest of
v2, where all host↔container IO goes through inbound.db / outbound.db.
Move it into a `destinations` table in INBOUND_SCHEMA. The host writes
it before every container wake AND on demand (e.g. after create_agent)
so the creator sees the new child destination mid-session without a
restart. The container queries the table live on every lookup — no
cache, no staleness window.
- src/db/schema.ts: add `destinations` table to INBOUND_SCHEMA.
- src/session-manager.ts: writeDestinationsFile → writeDestinations,
writes via DELETE + INSERT inside a transaction.
- src/delivery.ts: create_agent handler calls writeDestinations on the
creator's session after inserting the new destination rows.
- container/agent-runner/src/destinations.ts: queries inbound.db
directly in every findByName/getAllDestinations/findByRouting call.
No more cache. No setDestinationsForTest (obsolete). No fs import.
- container/agent-runner/src/index.ts and mcp-tools/index.ts: remove
loadDestinations() calls — no longer needed.
- Test helper initTestSessionDb creates the destinations table.
Integration test inserts a row directly instead of mocking the cache.
No backwards compatibility: sessions predating the schema update must
be recreated. This is fine on the v2 branch.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When an agent has exactly one configured destination, wrapping output in
<message to="..."> blocks is unnecessary. Plain text goes to the sole
destination automatically. This preserves the simple "just reply" flow
for the common case of one user on one channel.
Applies in three places:
- System prompt addendum: single-destination case gets a simplified
explanation ("your messages are delivered to X, just write directly").
Multi-destination case keeps the <message to="..."> syntax docs.
- Main output parser: if zero <message> blocks are found and there is
exactly one destination, the entire cleaned text (with <internal>
stripped) is sent to that destination.
- send_message / send_file MCP tools: `to` parameter is now optional.
With one destination, omitted defaults to it. With multiple, omitting
returns an error listing the options.
Multi-destination behavior is unchanged — explicit <message to="..."> is
still required, and untagged text is still scratchpad.
groups/global/CLAUDE.md updated to describe both cases.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replaces implicit routing context (NANOCLAW_PLATFORM_ID env vars) with
per-agent named destination maps. Agents reference channels and peer
agents by local names; the host re-validates every outbound route against
a new agent_destinations table that is both the routing map and the ACL.
Model changes:
- New migration 004 adds agent_destinations (agent_group_id, local_name,
target_type, target_id). Backfills from existing messaging_group_agents.
- Host writes /workspace/.nanoclaw-destinations.json before every container
wake so admin changes take effect on next start.
- Container loads map at startup, appends system-prompt addendum listing
available destinations and the <message to="name">…</message> syntax.
- Agent main output is parsed for <message to="..."> blocks; each block
becomes a messages_out row with routing resolved via the local map.
Untagged text and <internal>…</internal> are scratchpad (logged only).
- send_message MCP tool now takes `to` (destination name) instead of raw
routing fields. send_to_agent deleted (redundant — agents are just
destinations). send_file/edit_message/add_reaction route via map too.
- Inbound formatter adds from="name" attribute via reverse-lookup so the
agent sees a consistent namespace in both directions.
Permission enforcement:
- Host checks hasDestination() before every channel delivery AND every
agent-to-agent route. Unauthorized messages dropped and logged.
- routeAgentMessage simplified: ~15 lines, no JSON parse, content copied
verbatim (target formatter resolves the sender via its own local map).
- create_agent is admin-only, checked at both the container (tool not
registered for non-admins) and the host (re-check on receive). Inserts
bidirectional destination rows so parent↔child comms work immediately.
Includes path-traversal guard on folder name.
Self-modification cleanup:
- add_mcp_server now requires admin approval (previously had none).
- install_packages validates package names on BOTH sides (container tool
+ host receiver) with strict regex. Max 20 packages per request.
- All three self-mod tools are fire-and-forget: write request, return
immediately with "submitted" message. Admin approval triggers a chat
notification to the requesting agent — no tool-call polling, no 5-min
holds. On rebuild/mcp_server approval, the container is killed so the
next wake picks up new config/image.
- Approval delivery extracted into requestApproval() helper (the one
place where three call sites were literally identical).
Also folded in the phase-1 dynamic import cleanup (create_agent no longer
does `await import('./db/agent-groups.js')`) and removes NANOCLAW_PLATFORM_ID
/ CHANNEL_TYPE / THREAD_ID env-var routing entirely.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Self-customize skill lives in container/skills/ so it's loaded into the
agent container at runtime. Documents the builder-agent pattern with
diff size limits for safer self-modification.
CLAUDE.md communication section now has three tiers (short / longer /
long-running) instead of a single blanket rule — agents should
acknowledge upfront on longer work and update before slow operations,
but stay silent on quick tasks.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Pre-agent scripts: [~] → [ ] (formatter references scriptOutput but
no execution logic exists)
- Add typing indicator as completed (triggerTyping in router)
- Remove "stub exists" from register_group/reset_session (no stubs found)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
After wiring a channel to an agent group, register.ts writes a task
message to the session that triggers the /welcome container skill.
The agent introduces itself immediately — the user sees typing and
then a greeting without having to send a message first.
Uses kind 'task' (not 'system') so the poll loop picks it up normally.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Channel adapters prefix platform IDs with their channel type
(e.g. "telegram:123"). Normalize in register.ts so the DB always
stores the canonical format. Removes fallback lookup from router.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Move prefix handling from register.ts to router.ts. Users register with
raw platform IDs (what they naturally have), adapters send prefixed IDs
(their internal format). Router now tries stripping the channel type
prefix when the exact lookup fails, matching either format.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Chat SDK adapters use prefixed platform IDs (e.g. "telegram:6037840640",
"discord:guildId:channelId") but users provide raw IDs during setup.
Without the prefix, the router can't match the registered messaging group
to incoming messages and silently drops them.
register.ts now auto-prefixes with the channel type if not already present.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Use platformId directly as thread ID in deliver() and setTyping()
instead of calling encodeThreadId with Discord-shaped args — platformId
is already in the adapter's encoded format (e.g. "telegram:6037840640")
- Add triggerTyping() in delivery.ts, call from router on message route
- Enable Telegram channel in barrel
- Verified E2E: Telegram message in → agent → typing indicator → response
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add three-level isolation model (shared session, same agent, separate agent)
with agent-shared session mode for cross-channel shared sessions
- Create /manage-channels skill for wiring channels to agent groups
- Refactor all 12 v2 channel skills: lean SKILL.md + VERIFY.md + REMOVE.md
with structured Channel Info section for platform-specific metadata
- Create /add-discord-v2 skill (was missing)
- Add step 5a to setup SKILL.md invoking /manage-channels after channel install
- Update setup/verify.ts to check all 12 channel token types
- Add docs/v2-isolation-model.md explaining the isolation model
- Update v2-checklist.md and v2-setup-wiring.md to reflect completed work
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Detailed status document for next session: what's done (two-DB split,
OneCLI, barrel, register.ts), what's not (channel skills don't call
register, no group creation step in setup, v1 add-discord incompatible).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Discord was directly imported in src/index.ts before the barrel wiring.
Moving to the barrel without uncommenting it broke Discord.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Import channel barrel from src/index.ts so channel skills that
uncomment lines in src/channels/index.ts actually execute
- Rewrite setup/register.ts to create v2 entities (agent_groups,
messaging_groups, messaging_group_agents) in data/v2.db instead
of v1's store/messages.db
- Fix setup/verify.ts to check v2 central DB for registered groups
- Add prominent "MESSAGE DROPPED" warnings in router when no agent
groups are wired, with actionable guidance
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Eliminates SQLite write contention across the host-container mount
boundary by splitting the single session.db into two files, each with
exactly one writer:
inbound.db — host writes (messages_in, delivered tracking)
outbound.db — container writes (messages_out, processing_ack)
Key changes:
- Host uses even seq numbers, container uses odd (collision-free)
- Container heartbeat via file touch instead of DB UPDATE
- Scheduling MCP tools now emit system actions via messages_out
(host applies them to inbound.db during delivery)
- Host sweep reads processing_ack + heartbeat file for stale detection
- OneCLI ensureAgent() call added (was missing from v2, caused
applyContainerConfig to reject unknown agent identifiers)
Verified: tsc clean, 327 tests pass, real e2e through Docker works.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace `as never` cast with proper polyfill for channelIdFromThreadId.
Narrow GatewayAdapter cast to only the gateway code path in bridge.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Move all v1 files (index, router, container-runner, db, ipc, types,
logger, channels/registry, and all utilities) to src/v1/ as a
fully self-contained archive with no shared dependencies
- Rename v2 files to remove -v2 suffix (index-v2.ts → index.ts, etc.)
- Update all imports across v2 source, tests, and setup files
- Migrate shared utilities (config, env, container-runtime, mount-security,
timezone, group-folder) from pino logger to v2 log module
- Migrate setup/ files from logger to log with argument order swap
- Container agent-runner: move v1 entry to v1/, rename v2 to index.ts
- Update setup skill to offer all 13 v2 channels
- Install all Chat SDK adapter packages
- dist/index.js now runs v2; dist/v1/index.js runs v1
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Replace in-memory Chat SDK state with SqliteStateAdapter — thread
subscriptions now persist across restarts
- Add migration 002 for chat_sdk_kv, subscriptions, locks, lists tables
- Handle /clear in agent-runner (reset sessionId) — SDK has
supportsNonInteractive:false for this command
- Pass /compact, /context, /cost, /files through to SDK as admin commands
- Skip admin commands in follow-up poll so they start fresh queries
- Emit compact_boundary events as user-visible feedback messages
- Pass NANOCLAW_ADMIN_USER_ID and NANOCLAW_ASSISTANT_NAME to containers
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
End-to-end ask_user_question flow:
- Agent MCP tool writes question card to messages_out
- Host delivery creates pending_questions row, delivers as Discord Card with buttons
- Local webhook server receives Gateway INTERACTION_CREATE events
- Acknowledges interaction + updates card to show selected answer
- Routes response back to session DB as system message
- MCP tool poll picks up response and returns to agent
Key fixes:
- Poll loop now skips system messages (reserved for MCP tool responses)
- Gateway listener uses webhookUrl forwarding mode for interaction support
- Button custom_id encodes questionId + option text for self-contained routing
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Host sweep: fix DELETE journal mode, busy_timeout, seq in recurrence INSERT
- Outbound files: delivery reads from outbox dir, passes buffers to adapter,
cleans up after delivery. Chat SDK bridge sends files via postMessage.
- Inbound attachments: formatter includes attachment info in prompts
- Commands: categorize /commands as admin, filtered, or passthrough.
Admin commands check sender against NANOCLAW_ADMIN_USER_ID.
Filtered commands silently dropped. Passthrough sent raw to agent.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Use DELETE journal mode for session DBs instead of WAL. WAL doesn't
sync reliably across Docker volume mounts (VirtioFS), causing dropped
writes and duplicate deliveries.
- Add 20s idle detection to end the query stream. The concurrent poll
tracks SDK activity via a new 'activity' provider event. When no SDK
events arrive for 20s and no messages are pending, the stream ends
and the poll loop continues.
- Add touchProcessing heartbeat so the host can distinguish active
agents from idle ones by checking status_changed recency.
- Catch query errors in the poll loop and write error responses to
messages_out instead of crashing the process.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
ChannelAdapter interface with setup/deliver/teardown/setTyping lifecycle.
Self-registration pattern via channel-registry. Host wiring in index-v2
bridges inbound messages to routeInbound and outbound delivery to adapters.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Override entrypoint to compile and run index-v2.js (no stdin)
- Add better-sqlite3 + @types to agent-runner dependencies
- Exclude test files from agent-runner tsconfig (Docker build)
- Add real e2e test script (host → container → Claude → session DB)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Host orchestrator connecting channel events to session DBs and
delivering responses back through channel adapters.
- session-manager.ts: session folder/DB lifecycle, message writing
- container-runner-v2.ts: Docker spawn with session + agent group
mounts, OneCLI, idle timeout, agent-runner recompilation
- router-v2.ts: inbound routing (channel → messaging group → agent
group → session → messages_in → wake container)
- delivery.ts: two-tier polling (1s active, 60s sweep) for
messages_out, channel adapter delivery
- host-sweep.ts: stale detection with backoff, recurrence, wake
containers for due messages
- index-v2.ts: thin entry point wiring everything together
- scripts/test-v2-agent.ts: real Claude provider integration test
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Poll loop end-to-end with mock provider: message pickup, batch
processing, concurrent polling for late arrivals.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
AgentProvider abstraction with Claude and Mock implementations.
Poll loop reads messages_in, formats by kind, queries provider,
writes results to messages_out. Concurrent polling pushes follow-up
messages into active queries.
- providers/types.ts: AgentProvider, AgentQuery, ProviderEvent
- providers/claude.ts: wraps Agent SDK with MessageStream, hooks,
transcript archiving
- providers/mock.ts: canned responses with push() support
- providers/factory.ts: createProvider()
- formatter.ts: format by kind (chat/task/webhook/system), XML
escaping, routing extraction
- poll-loop.ts: poll → format → query → write, concurrent polling
- mcp-tools.ts: MCP server with send_message tool
- index-v2.ts: new entry point (config from env, enters poll loop)
- 11 new tests, all 288 tests pass
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add the v2 data layer: typed interfaces, central DB with migration
runner, per-entity CRUD, and agent-runner session DB operations.
- src/log.ts: concise message-first logging API
- src/types-v2.ts: AgentGroup, MessagingGroup, Session, MessageIn/Out
- src/db/: connection (WAL), migration runner, 001-initial schema,
CRUD for agent_groups, messaging_groups, sessions, pending_questions
- container/agent-runner/src/db/: session DB connection, messages_in
reads + status transitions, messages_out writes
- 31 new tests, all 277 tests pass
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Skills document env vars in SKILL.md instead of patching config.ts.
Prettier printWidth 120 to keep log calls and signatures on one line.
Thin logging wrapper for one-line structured log calls.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Based on analysis of 33 skill branches. Maps each conflict hotspot
(index.ts, config.ts, container-runner.ts, db.ts) to its v2 solution.
Adds mount registration pattern so channel skills don't edit
container-runner. Config stays in the module that uses it.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Split DB by entity (agent-groups.ts, messaging-groups.ts, sessions.ts)
instead of one monolith. Numbered migration files replace inline
ALTER TABLE blocks. Channels use barrel pattern for self-registration.
Session DB split into messages-in.ts and messages-out.ts.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Channels, MCP tools, and providers use registration patterns so
skill branches can add capabilities without conflicting. Index
stays thin. File map updated with channels/ and mcp-tools/
directories.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Supply chain protection — npm will not install package versions
published less than 7 days ago.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
1. Lint schedule now uses NanoClaw scheduled_tasks table instead of
Claude Code cron — runs in the group's agent container
2. CLAUDE.md must enforce one-at-a-time file ingestion — never batch
3. Expanded CLAUDE.md guidance: explain system, index files, point to
container skill, enforce ingest discipline
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Remove hardcoded file path checks. Step 4 now discusses source types
with the user and helps install needed skills dynamically. Fix "use use"
typo and change curl example to file download.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Remove pre-written container skill. Instead, include llm-wiki.md
(Karpathy's gist) as the reference material and have the setup skill
guide the user through collaboratively building their own wiki schema,
container skill, and directory structure based on the pattern.
Add NanoClaw-specific notes: image vision, PDF reader, voice
transcription, curl for full document fetch, file attachment handling.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Container skill teaches the agent to maintain a structured, interlinked
wiki from ingested sources. Feature skill bootstraps the setup — directory
structure, group CLAUDE.md, optional scheduled lint.
Based on Karpathy's LLM Wiki pattern.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Replace macOS-only `stat -f%z` with portable `wc -c` for Linux compat
- Replace `find | while` pipes with process substitution so TOTAL_FREED
counter survives the loop (pipe runs in subshell, losing mutations)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Session files (JSONLs, debug logs, todos, telemetry, group logs) accumulate
unboundedly — especially from daily cron tasks. This adds a cleanup script
that prunes old artifacts while protecting active sessions (read from DB),
and wires it into the main process on a 24h interval.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Use sonnet[1m] for full 1M context window and set auto-compact at 200k
tokens to keep costs down while preserving access to extended context.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
