Phase 2 of the SKILL.md already contains the Dockerfile + TOOL_ALLOWLIST
edit instructions with an "ALREADY APPLIED" short-circuit. Keeping those
edits out of trunk means users who never run /add-gmail-tool don't carry
the Gmail MCP package in their image.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds /add-gmail-tool — a Utility skill that installs Gmail as an MCP tool
in NanoClaw v2 using OneCLI for credential injection. No raw OAuth tokens
ever reach the container; the gateway swaps the "onecli-managed" stub
bearer for the real token at request time.
Scope (3 files):
- container/Dockerfile: pnpm global-install of
@gongrzhe/server-gmail-autoauth-mcp@1.1.11, pinned behind GMAIL_MCP_VERSION.
Also pins zod-to-json-schema@3.22.5 to avoid an ERR_PACKAGE_PATH_NOT_EXPORTED
crash: the MCP server's loose zod range resolves zod@3.24.x while
zod-to-json-schema@3.25.x imports the zod/v3 subpath that only exists in
zod>=3.25.
- container/agent-runner/src/providers/claude.ts: adds 'mcp__gmail__*' to
TOOL_ALLOWLIST so the agent can invoke the server's tools.
- .claude/skills/add-gmail-tool/SKILL.md: pre-flight checks (OneCLI Gmail app
connected, stubs present, mount allowlist covers ~/.gmail-mcp, agent
secret-mode), per-group wiring in container.json (mount + mcpServers),
verification steps, troubleshooting, removal instructions. Credits to
gongrzhe for the MCP server and the add-atomic-chat-tool / add-vercel
skill patterns.
Addresses #1500 (proxy Gmail OAuth through credential proxy) on the Gmail
side. Overlaps in intent with #1810 but stays surgical — no bundled
unrelated changes.
Tested end-to-end on Linux/Docker: CLI and WhatsApp self-chat agents can
list labels, search/read/send mail via OneCLI-injected tokens.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The initial /add-atomic-chat-tool merge added src edits directly to main.
That conflicts with the utility-skill pattern used elsewhere (e.g. /claw):
the skill folder should ship the file and SKILL.md should instruct copy +
idempotent edits at install time, not a git merge that carries src diffs.
- Move container/agent-runner/src/atomic-chat-mcp-stdio.ts →
.claude/skills/add-atomic-chat-tool/atomic-chat-mcp-stdio.ts
- Revert the atomic_chat mcpServers entry in agent-runner index.ts
- Revert mcp__atomic_chat__* from TOOL_ALLOWLIST in providers/claude.ts
- Revert ATOMIC_CHAT_* env forwarding and [ATOMIC] log elevation in
src/container-runner.ts
- Empty .env.example back out
- Rewrite SKILL.md: copy the shipped file, then apply deterministic Edits
(index.ts, providers/claude.ts, container-runner.ts, .env.example)
with exact before/after snippets the installer agent can match.
Main is now back to its pre-PR state for the tool; /add-atomic-chat-tool
re-applies everything at install time.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Exposes local Atomic Chat models (OpenAI-compatible API at
127.0.0.1:1337/v1) as tools to the container agent. Adds
atomic_chat_list_models and atomic_chat_generate alongside
the existing Ollama skill.
Rebased on current main:
- MCP server registered in agent-runner index.ts using bun (no tsc
step in-image), sibling path to index.ts, env: {} with ATOMIC_CHAT_*
forwarded when set.
- allowedTools entry moved to providers/claude.ts TOOL_ALLOWLIST.
- SKILL.md: drop obsolete per-group copy step (single RO mount
supersedes it); use pnpm build.
Made-with: Cursor
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The Agent SDK's default binary resolution picks the musl-linked native
binary (claude-agent-sdk-linux-arm64-musl), which cannot execute on the
Debian-based container image (glibc). Explicitly set
pathToClaudeCodeExecutable to /pnpm/claude — the pnpm global symlink
that resolves to the correct glibc binary regardless of architecture.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replaces the two overlapping old mechanisms (30-min setTimeout kill in
container-runner, 10-min heartbeat STALE_THRESHOLD reset in host-sweep)
with message-scoped stuck detection anchored to the processing_ack claim
age + an absolute 30-min ceiling that extends for long-declared Bash
tools.
Old model problems:
- IDLE_TIMEOUT setTimeout fired on plain wall-clock time; slow-but-alive
agents got killed at 30min regardless of activity
- 10-min STALE_THRESHOLD in the sweep was unreliable — the heartbeat is
only touched on SDK events, so legitimate silent tool work (sleep 30,
long WebFetch, npm install) looked identical to a hung container
- Two overlapping sources of truth for "when to let go of a container"
New model:
- Host sweep is the single source of truth.
- Container exposes a new `container_state` single-row table in outbound.db
(schema added; container writes, host reads). PreToolUse hook writes
current_tool + tool_declared_timeout_ms (read from Bash's tool_input);
PostToolUse / PostToolUseFailure clear it.
- Sweep decides with a pure helper `decideStuckAction`:
* absolute ceiling — kill if heartbeat age > max(30min, bash_timeout)
* per-claim stuck — kill if any processing_ack row has claim_age >
max(60s, bash_timeout) AND heartbeat hasn't been touched since claim
* otherwise ok
Kill paths reset leftover processing rows with exponential backoff,
reusing the existing retry machinery.
Tool blocklist expanded:
- AskUserQuestion (SDK placeholder; we have mcp__nanoclaw__ask_user_question)
- EnterPlanMode, ExitPlanMode, EnterWorktree, ExitWorktree (Claude Code UI
affordances; would hang in headless containers)
PreToolUse hook is also defense-in-depth: if a disallowed tool name slips
through, it returns `{ decision: 'block' }` so the agent sees a clear
error instead of appearing stuck.
Removed:
- container-runner.ts: IDLE_TIMEOUT setTimeout, resetIdle callback on
activeContainers entry, resetContainerIdleTimer export.
- delivery.ts: the resetContainerIdleTimer call on successful delivery.
- poll-loop.ts: IDLE_END_MS + its setInterval. Keeping the query open is
cheaper than close+reopen (no cold prompt cache). Liveness is now a
host-side concern.
- host-sweep.ts: 10-min STALE_THRESHOLD_MS + getStuckProcessingIds in the
stale-detection path (still exported for kill reset).
Tests:
- src/host-sweep.test.ts — 9 tests for decideStuckAction covering: fresh
heartbeat, absolute ceiling, absent heartbeat, Bash-timeout extension
(both ceiling and per-claim), claim age below tolerance, heartbeat
touched after claim, unparseable timestamps.
Ref: docs/v1-vs-v2/ACTION-ITEMS.md items 9, 6a, 10.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Providers now mirror the channels pattern: each module calls
registerProvider() at top level, and providers/index.ts is a barrel of
side-effect imports. createProvider() becomes a thin registry lookup;
the closed ProviderName union is gone (now a string alias, since the
env var is a runtime string anyway).
Also adds a host-side provider-container-registry so providers can
declare their own mounts and env passthrough in src/providers/<name>.ts
instead of the container-runner having to know about each one. The
resolver runs once per spawn and threads provider + contribution
through buildMounts and buildContainerArgs so side effects (mkdir,
etc.) fire exactly once.
Both barrels are append-only — adding a new provider is a new file
+ one import line per barrel, no edits to existing files. The built-in
providers (claude, mock) don't need host-side config, so src/providers/
ships with an empty barrel; the container-side barrel imports both.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Scheduled tasks can now carry a bash script that runs inside the container
before the agent is invoked. The script prints `{wakeAgent, data?}` on its
last stdout line; if `wakeAgent: false` (or the script errors) the task
row is marked completed and the agent is never queried, saving API calls
on no-op checks. On wake, the script's `data` is injected into the task
prompt. Semantics mirror V1: 30s bash timeout, 1MB buffer, last-line JSON,
error == skip.
Also blocks the Claude SDK's built-in scheduling tools (CronCreate,
CronDelete, CronList, ScheduleWakeup) via `disallowedTools` so tasks
actually flow through `mcp__nanoclaw__schedule_task` and get the script
gate. CLAUDE.md gains a soft pointer explaining why `schedule_task` is
the right path.
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>
- 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>
- 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>
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>
