Merge branch 'main' into cleanup/security-docs-v2

Mount allowlist: honor the readOnly key and stop caching parse errors

.claude/skills/manage-mounts/SKILL.md

@@ -13,18 +13,18 @@ Configure which host directories NanoClaw agent containers can access. The mount
 cat ~/.config/nanoclaw/mount-allowlist.json 2>/dev/null || echo "No mount allowlist configured"
 ```
 
-Show the current config to the user in a readable format: which directories are allowed, whether non-main agents are read-only.
+Show the current config to the user in a readable format: which directories are allowed, and whether each is read-only or read-write.
 
 ## Add Directories
 
 Ask which directories the user wants agents to access. For each path:
 - Validate the path exists
-- Ask if it should be read-only for non-main agents (default: yes)
+- Ask if it should be read-write (`allowReadWrite: true`) or read-only (`allowReadWrite: false`, the safer default)
 
 Build the JSON config and write it:
 
 ```bash
-pnpm exec tsx setup/index.ts --step mounts --force -- --json '{"allowedRoots":[{"path":"/path/to/dir","readOnly":false}],"blockedPatterns":[],"nonMainReadOnly":true}'
+pnpm exec tsx setup/index.ts --step mounts --force -- --json '{"allowedRoots":[{"path":"/path/to/dir","allowReadWrite":true}],"blockedPatterns":[]}'
 ```
 
 Use `--force` to overwrite the existing config.
@@ -34,7 +34,7 @@ Use `--force` to overwrite the existing config.
 Read the current config, show it, ask which entry to remove, then write the updated config through the same write path (build the trimmed JSON and pass it to `--step mounts --force -- --json`):
 
 ```bash
-pnpm exec tsx setup/index.ts --step mounts --force -- --json '{"allowedRoots":[],"blockedPatterns":[],"nonMainReadOnly":true}'
+pnpm exec tsx setup/index.ts --step mounts --force -- --json '{"allowedRoots":[],"blockedPatterns":[]}'
 ```
 
 ## Reset to Empty
@@ -45,12 +45,10 @@ pnpm exec tsx setup/index.ts --step mounts --force -- --empty
 
 ## After Changes
 
-Restart the service so containers pick up the new config (the unit/label names are per-install — see `setup/lib/install-slug.sh`).
+The allowlist is read fresh when a container is spawned, so new mounts apply to newly spawned containers automatically — no service restart needed.
 
-Run from your NanoClaw project root:
+To apply the new config to a group that already has a running container, restart just that group:
 
 ```bash
-source setup/lib/install-slug.sh
-launchctl kickstart -k gui/$(id -u)/$(launchd_label)  # macOS
-systemctl --user restart $(systemd_unit)              # Linux
+ncl groups restart --id <group-id>
 ```

README.md

@@ -80,7 +80,7 @@ See [docs/v1-to-v2-changes.md](docs/v1-to-v2-changes.md) for what's different an
 - **Per-agent workspace** — each agent group has its own `CLAUDE.md`, its own memory, its own container, and only the mounts you allow. Nothing crosses the boundary unless you wire it to.
 - **Scheduled tasks** — recurring jobs that run Claude and can message you back
 - **Web access** — search and fetch content from the web
-- **Container isolation** — agents are sandboxed in Docker (macOS/Linux/WSL2), with optional [Docker Sandboxes](docs/docker-sandboxes.md) micro-VM isolation or Apple Container as a macOS-native opt-in
+- **Container isolation** — agents are sandboxed in Docker (macOS/Linux/WSL2), with optional Docker Sandboxes micro-VM isolation
 - **Credential security** — agents never hold raw API keys. Outbound requests route through [OneCLI's Agent Vault](https://github.com/onecli/onecli), which injects credentials at request time and enforces per-agent policies and rate limits.
 - **Agent templates**: stamp a ready-to-run agent (instructions + MCP tools + skills, no secrets) from a reusable bundle, via the setup wizard or `ncl groups create --template <ref>`. Load from the [public library](https://github.com/nanocoai/nanoclaw-templates), a local folder, or any git repo. See [docs/templates.md](docs/templates.md).
 
@@ -165,7 +165,7 @@ Key files:
 
 **Why Docker?**
 
-Docker provides cross-platform support (macOS, Linux and Windows via WSL2) and a mature ecosystem. On macOS, Apple Container is also supported as a lighter-weight native runtime. For additional isolation, [Docker Sandboxes](docs/docker-sandboxes.md) run each container inside a micro VM.
+Docker provides cross-platform support (macOS, Linux and Windows via WSL2) and a mature ecosystem. For additional isolation, Docker Sandboxes run each container inside a micro VM.
 
 **Can I run this on Linux or Windows?**
 

container/agent-runner/src/current-batch.ts

@@ -1,29 +0,0 @@
-/**
- * Per-batch context the poll loop publishes for downstream consumers
- * (MCP tools, etc.) that don't sit on the poll-loop's call stack.
- *
- * Today the only field is `inReplyTo` — the id of the first inbound
- * message in the batch the agent is currently processing. MCP tools like
- * `send_message` and `send_file` read this and stamp it onto the outbound
- * row so the host's a2a return-path routing can correlate replies back to
- * the originating session.
- *
- * This is module-level state on purpose: the agent-runner is single-process
- * and processes one batch at a time. Poll-loop calls `setCurrentInReplyTo`
- * before invoking the provider and `clearCurrentInReplyTo` after the batch
- * completes (or errors out).
- */
-let currentInReplyTo: string | null = null;
-
-export function setCurrentInReplyTo(id: string | null): void {
-  currentInReplyTo = id;
-}
-
-export function clearCurrentInReplyTo(): void {
-  currentInReplyTo = null;
-}
-
-export function getCurrentInReplyTo(): string | null {
-  return currentInReplyTo;
-}
-

container/agent-runner/src/db/connection.ts

@@ -48,7 +48,11 @@ export function openInboundDb(): Database {
   // so the singleton survives for the rest of the test.
   if (_testMode && _inbound) {
     const db = _inbound;
-    return { prepare: (sql: string) => db.prepare(sql), exec: (sql: string) => db.exec(sql), close: () => {} } as unknown as Database;
+    return {
+      prepare: (sql: string) => db.prepare(sql),
+      exec: (sql: string) => db.exec(sql),
+      close: () => {},
+    } as unknown as Database;
   }
   const db = new Database(DEFAULT_INBOUND_PATH, { readonly: true });
   db.exec('PRAGMA busy_timeout = 5000');
@@ -260,11 +264,3 @@ export function closeSessionDb(): void {
   _outbound?.close();
   _outbound = null;
 }
-
-/**
- * @deprecated Use getInboundDb() / getOutboundDb() instead.
- * Kept for backward compatibility during migration.
- */
-export function getSessionDb(): Database {
-  return getInboundDb();
-}

container/agent-runner/src/db/index.ts

@@ -1,7 +1,6 @@
 export {
   getInboundDb,
   getOutboundDb,
-  getSessionDb,
   initTestSessionDb,
   closeSessionDb,
   touchHeartbeat,

container/agent-runner/src/db/session-state.ts

@@ -77,3 +77,47 @@ export function setContinuation(providerName: string, id: string): void {
 export function clearContinuation(providerName: string): void {
   deleteValue(continuationKey(providerName));
 }
+
+/**
+ * The a2a reply stamp: the id of the first inbound message in the batch the
+ * agent is currently processing. The poll loop publishes it at batch start;
+ * MCP tools (`send_message`, `send_file`) read it and stamp it onto outbound
+ * rows so the host's a2a return-path routing can correlate replies back to
+ * the originating session.
+ *
+ * This lives in outbound.db rather than module state because the MCP server
+ * runs as a separate stdio subprocess from the poll loop — module state set
+ * by the poll loop is invisible to it. Both processes open outbound.db
+ * (journal_mode=DELETE + busy_timeout make intra-container access safe).
+ */
+const IN_REPLY_TO_KEY = 'current_in_reply_to';
+
+/**
+ * Ignore a stamp older than this. The poll loop clears the stamp in a
+ * finally, but a container killed mid-batch (SIGKILL) can leave one behind;
+ * the guard stops a later out-of-batch read from picking up a dead stamp.
+ * Generous so a long-running batch's late sends still stamp correctly.
+ */
+const IN_REPLY_TO_MAX_AGE_MS = 30 * 60 * 1000;
+
+export function setCurrentInReplyTo(id: string | null): void {
+  if (id === null) {
+    clearCurrentInReplyTo();
+    return;
+  }
+  setValue(IN_REPLY_TO_KEY, id);
+}
+
+export function clearCurrentInReplyTo(): void {
+  deleteValue(IN_REPLY_TO_KEY);
+}
+
+export function getCurrentInReplyTo(): string | null {
+  const row = getOutboundDb()
+    .prepare('SELECT value, updated_at FROM session_state WHERE key = ?')
+    .get(IN_REPLY_TO_KEY) as { value: string; updated_at: string } | undefined;
+  if (!row) return null;
+  const age = Date.now() - new Date(row.updated_at).getTime();
+  if (!Number.isFinite(age) || age > IN_REPLY_TO_MAX_AGE_MS) return null;
+  return row.value;
+}

container/agent-runner/src/mcp-tools/core.test.ts

@@ -4,14 +4,31 @@
  * batch in poll-loop, and outbound writes from MCP tools (send_message,
  * send_file) must pick it up so a2a return-path routing on the host can
  * correlate replies back to the originating session.
+ *
+ * The stamp is published through session_state in outbound.db, not module
+ * state — the MCP server runs as a separate stdio subprocess from the poll
+ * loop, so it can only see the stamp through the shared DB. These tests seed
+ * it the same way the poll-loop process does (a direct DB write) rather than
+ * via any in-memory helper, so they exercise the real process boundary.
  */
 import { describe, it, expect, beforeEach, afterEach } from 'bun:test';
 
-import { initTestSessionDb, closeSessionDb, getInboundDb } from '../db/connection.js';
+import { initTestSessionDb, closeSessionDb, getInboundDb, getOutboundDb } from '../db/connection.js';
 import { getUndeliveredMessages } from '../db/messages-out.js';
-import { setCurrentInReplyTo, clearCurrentInReplyTo } from '../current-batch.js';
 import { sendMessage } from './core.js';
 
+/**
+ * Publish the a2a reply stamp the way the poll loop does: a direct write to
+ * session_state in outbound.db. `ageMs` back-dates updated_at to exercise the
+ * staleness guard MCP tools apply when reading it.
+ */
+function publishInReplyTo(id: string, ageMs = 0): void {
+  const updatedAt = new Date(Date.now() - ageMs).toISOString();
+  getOutboundDb()
+    .prepare('INSERT OR REPLACE INTO session_state (key, value, updated_at) VALUES (?, ?, ?)')
+    .run('current_in_reply_to', id, updatedAt);
+}
+
 beforeEach(() => {
   initTestSessionDb();
   // Seed a peer agent destination
@@ -24,13 +41,12 @@ beforeEach(() => {
 });
 
 afterEach(() => {
-  clearCurrentInReplyTo();
   closeSessionDb();
 });
 
 describe('send_message MCP tool — in_reply_to plumbing', () => {
-  it('stamps current batch in_reply_to on outbound rows', async () => {
-    setCurrentInReplyTo('inbound-msg-1');
+  it('stamps the batch in_reply_to (published via the DB) on outbound rows', async () => {
+    publishInReplyTo('inbound-msg-1');
 
     await sendMessage.handler({ to: 'peer', text: 'hello' });
 
@@ -40,7 +56,17 @@ describe('send_message MCP tool — in_reply_to plumbing', () => {
   });
 
   it('writes null when no batch is active', async () => {
-    // No setCurrentInReplyTo before this call — simulates ad-hoc / out-of-batch invocation.
+    // Nothing published to session_state — simulates ad-hoc / out-of-batch invocation.
+    await sendMessage.handler({ to: 'peer', text: 'hello' });
+
+    const out = getUndeliveredMessages();
+    expect(out).toHaveLength(1);
+    expect(out[0].in_reply_to).toBeNull();
+  });
+
+  it('ignores a stale stamp left behind by a killed container', async () => {
+    publishInReplyTo('inbound-msg-1', 60 * 60 * 1000); // an hour old
+
     await sendMessage.handler({ to: 'peer', text: 'hello' });
 
     const out = getUndeliveredMessages();

container/agent-runner/src/mcp-tools/core.ts

@@ -9,9 +9,9 @@
 import fs from 'fs';
 import path from 'path';
 
-import { getCurrentInReplyTo } from '../current-batch.js';
 import { findByName, getAllDestinations } from '../destinations.js';
 import { getMessageIdBySeq, getRoutingBySeq, writeMessageOut } from '../db/messages-out.js';
+import { getCurrentInReplyTo } from '../db/session-state.js';
 import { getSessionRouting } from '../db/session-routing.js';
 import { registerTools } from './server.js';
 import type { McpToolDefinition } from './types.js';

container/agent-runner/src/poll-loop.ts

@@ -2,8 +2,13 @@ import { findByName, getAllDestinations, type DestinationEntry } from './destina
 import { getPendingMessages, markProcessing, markCompleted, type MessageInRow } from './db/messages-in.js';
 import { writeMessageOut } from './db/messages-out.js';
 import { getInboundDb, touchHeartbeat, clearStaleProcessingAcks } from './db/connection.js';
-import { clearContinuation, migrateLegacyContinuation, setContinuation } from './db/session-state.js';
-import { clearCurrentInReplyTo, setCurrentInReplyTo } from './current-batch.js';
+import {
+  clearContinuation,
+  clearCurrentInReplyTo,
+  migrateLegacyContinuation,
+  setContinuation,
+  setCurrentInReplyTo,
+} from './db/session-state.js';
 import {
   formatMessages,
   extractRouting,

docs/APPLE-CONTAINER-NETWORKING.md

@@ -1,90 +0,0 @@
-# Apple Container Networking Setup (macOS 26)
-
-Apple Container's vmnet networking requires manual configuration for containers to access the internet. Without this, containers can communicate with the host but cannot reach external services (DNS, HTTPS, APIs).
-
-## Quick Setup
-
-Run these two commands (requires `sudo`):
-
-```bash
-# 1. Enable IP forwarding so the host routes container traffic
-sudo sysctl -w net.inet.ip.forwarding=1
-
-# 2. Enable NAT so container traffic gets masqueraded through your internet interface
-echo "nat on en0 from 192.168.64.0/24 to any -> (en0)" | sudo pfctl -ef -
-```
-
-> **Note:** Replace `en0` with your active internet interface. Check with: `route get 8.8.8.8 | grep interface`
-
-## Making It Persistent
-
-These settings reset on reboot. To make them permanent:
-
-**IP Forwarding** — add to `/etc/sysctl.conf`:
-```
-net.inet.ip.forwarding=1
-```
-
-**NAT Rules** — add to `/etc/pf.conf` (before any existing rules):
-```
-nat on en0 from 192.168.64.0/24 to any -> (en0)
-```
-
-Then reload: `sudo pfctl -f /etc/pf.conf`
-
-## IPv6 DNS Issue
-
-By default, DNS resolvers return IPv6 (AAAA) records before IPv4 (A) records. Since our NAT only handles IPv4, Node.js applications inside containers will try IPv6 first and fail.
-
-The container image and runner are configured to prefer IPv4 via:
-```
-NODE_OPTIONS=--dns-result-order=ipv4first
-```
-
-This is set both in the `Dockerfile` and passed via `-e` flag in `container-runner.ts`.
-
-## Verification
-
-```bash
-# Check IP forwarding is enabled
-sysctl net.inet.ip.forwarding
-# Expected: net.inet.ip.forwarding: 1
-
-# Test container internet access
-container run --rm --entrypoint curl nanoclaw-agent:latest \
-  -s4 --connect-timeout 5 -o /dev/null -w "%{http_code}" https://api.anthropic.com
-# Expected: 404
-
-# Check bridge interface (only exists when a container is running)
-ifconfig bridge100
-```
-
-## Troubleshooting
-
-| Symptom | Cause | Fix |
-|---------|-------|-----|
-| `curl: (28) Connection timed out` | IP forwarding disabled | `sudo sysctl -w net.inet.ip.forwarding=1` |
-| HTTP works, HTTPS times out | IPv6 DNS resolution | Add `NODE_OPTIONS=--dns-result-order=ipv4first` |
-| `Could not resolve host` | DNS not forwarded | Check bridge100 exists, verify pfctl NAT rules |
-| Container hangs after output | Missing `process.exit(0)` in agent-runner | Rebuild container image |
-
-## How It Works
-
-```
-Container VM (192.168.64.x)
-    │
-    ├── eth0 → gateway 192.168.64.1
-    │
-bridge100 (192.168.64.1) ← host bridge, created by vmnet when container runs
-    │
-    ├── IP forwarding (sysctl) routes packets from bridge100 → en0
-    │
-    ├── NAT (pfctl) masquerades 192.168.64.0/24 → en0's IP
-    │
-en0 (your WiFi/Ethernet) → Internet
-```
-
-## References
-
-- [apple/container#469](https://github.com/apple/container/issues/469) — No network from container on macOS 26
-- [apple/container#656](https://github.com/apple/container/issues/656) — Cannot access internet URLs during building

docs/README.md

@@ -9,5 +9,3 @@ The files in this directory are original design documents and developer referenc
 | [SPEC.md](SPEC.md) | [Architecture](https://docs.nanoclaw.dev/concepts/architecture) |
 | [SECURITY.md](SECURITY.md) | [Security model](https://docs.nanoclaw.dev/concepts/security) |
 | [REQUIREMENTS.md](REQUIREMENTS.md) | [Introduction](https://docs.nanoclaw.dev/introduction) |
-| [docker-sandboxes.md](docker-sandboxes.md) | [Docker Sandboxes](https://docs.nanoclaw.dev/advanced/docker-sandboxes) |
-| [APPLE-CONTAINER-NETWORKING.md](APPLE-CONTAINER-NETWORKING.md) | [Container runtime](https://docs.nanoclaw.dev/advanced/container-runtime) |

docs/SECURITY.md

@@ -2,69 +2,101 @@
 
 ## Trust Model
 
+Privilege is **user-level**, persisted in the `user_roles` table (owner /
+admin, global or scoped to an agent group) plus `agent_group_members` (the
+unprivileged access gate).
+
 | Entity | Trust Level | Rationale |
 |--------|-------------|-----------|
-| Main group | Trusted | Private self-chat, admin control |
-| Non-main groups | Untrusted | Other users may be malicious |
-| Container agents | Sandboxed | Isolated execution environment |
-| Incoming messages | User input | Potential prompt injection |
+| Owners / admins (`user_roles`) | Trusted | Hold owner/admin roles; gate admin commands and approve credentialed actions |
+| Group members (`agent_group_members`) | Access-gated | Membership grants access to an agent group, but their messages are still untrusted input |
+| Unregistered senders | Untrusted | Subject to each messaging group's `unknown_sender_policy` |
+| Agent containers | Sandboxed | Long-lived per-session container; isolated by mounts, non-root, no host reach |
+| Incoming messages | User input | Potential prompt injection regardless of who sent them |
 
 ## Security Boundaries
 
 ### 1. Container Isolation (Primary Boundary)
 
-Agents execute in containers (lightweight Linux VMs), providing:
-- **Process isolation** - Container processes cannot affect the host
-- **Filesystem isolation** - Only explicitly mounted directories are visible
-- **Non-root execution** - Runs as unprivileged `node` user (uid 1000)
-- **Ephemeral containers** - Fresh environment per invocation (`--rm`)
+Agents execute in containers (Docker), providing:
+- **Process isolation** — container processes cannot affect the host
+- **Filesystem isolation** — only explicitly mounted directories are visible
+- **Non-root execution** — runs as an unprivileged user (`node`, uid 1000, or the host uid remapped in)
+- **Per-session containers** — one long-lived container per session polls that session's DBs and handles many messages, then is torn down (`--rm`) when the session goes idle.
 
-This is the primary security boundary. Rather than relying on application-level permission checks, the attack surface is limited by what's mounted.
+This is the primary security boundary. Rather than relying on application-level
+permission checks, the attack surface is limited by what's mounted.
 
 ### 2. Mount Security
 
-**External Allowlist** - Mount permissions stored at `~/.config/nanoclaw/mount-allowlist.json`, which is:
-- Outside project root
-- Never mounted into containers
-- Cannot be modified by agents
+`buildMounts` (`src/container-runner.ts`) composes a fixed set of mounts per
+spawn. For the default (Claude) provider these are:
 
-**Default Blocked Patterns:**
+| Container path | Host source | Mode | Purpose |
+|---|---|---|---|
+| `/workspace` | `data/v2-sessions/<group>/<session>/` | RW | Session folder — `inbound.db`, `outbound.db`, `outbox/`, `.claude/` |
+| `/workspace/agent` | `groups/<folder>/` | RW | Agent group working files + `CLAUDE.local.md` |
+| `/workspace/agent/container.json` | group `container.json` | RO | Container config — readable, not writable |
+| `/workspace/agent/CLAUDE.md` | composed `CLAUDE.md` | RO | Regenerated every spawn; agent edits would be clobbered |
+| `/workspace/agent/.claude-fragments` | group `.claude-fragments/` | RO | Composer skill/MCP fragments |
+| `/workspace/global` | `groups/global/` | RO | Shared global memory |
+| `/app/CLAUDE.md` | `container/CLAUDE.md` | RO | Shared base doc imported by the composed entry point |
+| `/home/node/.claude` | `data/v2-sessions/<group>/.claude-shared/` | RW | Claude state, settings, skill symlinks |
+| `/app/src` | `container/agent-runner/src/` | RO | Shared agent-runner source (same for all groups) |
+| `/app/skills` | `container/skills/` | RO | Shared container skills |
+| `/workspace/extra/<name>` | allowlisted host dir | RO (RW only if allowed) | Operator-configured additional mounts |
+
+The config mounts (`container.json`, `CLAUDE.md`, `.claude-fragments`) are
+**nested read-only mounts on top of the read-write group dir** — the agent can
+read its config but cannot modify it. The project root is **never mounted**: the
+container only ever sees the paths above plus any provider-contributed mounts
+(e.g. an OpenCode XDG dir). Host application source (`src/`, `dist/`,
+`package.json`) is not reachable.
+
+**Additional-mount allowlist** — extra mounts from a group's container config
+are validated against an allowlist at `~/.config/nanoclaw/mount-allowlist.json`,
+which is:
+- Outside the project root
+- Never mounted into containers
+- Not modifiable by agents
+
+Its schema:
+
+```json
+{
+  "allowedRoots": [
+    { "path": "~/projects", "allowReadWrite": true, "description": "Dev projects" },
+    { "path": "~/Documents/work", "allowReadWrite": false, "description": "Read-only" }
+  ],
+  "blockedPatterns": ["password", "secret", "token"]
+}
 ```
-.ssh, .gnupg, .aws, .azure, .gcloud, .kube, .docker,
-credentials, .env, .netrc, .npmrc, id_rsa, id_ed25519,
+
+**Default blocked patterns** (merged with any in the file):
+```
+.ssh, .gnupg, .gpg, .aws, .azure, .gcloud, .kube, .docker,
+credentials, .env, .netrc, .npmrc, .pypirc, id_rsa, id_ed25519,
 private_key, .secret
 ```
 
-**Protections:**
-- Symlink resolution before validation (prevents traversal attacks)
-- Container path validation (rejects `..` and absolute paths)
-- `nonMainReadOnly` option forces read-only for non-main groups
-
-**Read-Only Project Root:**
-
-The main group's project root is mounted read-only. Writable paths the agent needs (store, group folder, IPC, `.claude/`) are mounted separately. This prevents the agent from modifying host application code (`src/`, `dist/`, `package.json`, etc.) which would bypass the sandbox entirely on next restart. The `store/` directory is mounted read-write so the main agent can access the SQLite database directly.
+**Enforcement** (`src/modules/mount-security/index.ts`):
+- **No allowlist file ⇒ every additional mount is blocked** — the fixed mounts above are unaffected, but nothing extra is granted until the operator creates the file.
+- Symlinks are resolved to their real path (`realpathSync`) before any check, defeating traversal via symlink.
+- The real path is rejected if it matches a blocked pattern, and rejected unless it sits under one of `allowedRoots`.
+- The container path is validated: relative, non-empty, no `..`, no leading `/`, no `:` (blocks Docker `-v` option injection). It is mounted under `/workspace/extra/`.
+- **Read-write is granted only when the mount requests it (`readonly: false`) *and* the matched root has `allowReadWrite: true`.** Otherwise the mount is forced read-only.
 
 ### 3. Session Isolation
 
-Each group has isolated Claude sessions at `data/sessions/{group}/.claude/`:
-- Groups cannot see other groups' conversation history
-- Session data includes full message history and file contents read
-- Prevents cross-group information disclosure
+Per-session state lives under `data/v2-sessions/<agent-group>/<session>/`
+(`inbound.db`, `outbound.db`, `outbox/`, `.claude/`). Claude state
+(`.claude-shared`) and the working folder are scoped to the agent group, so:
+- Different agent groups cannot see each other's conversation history or files.
+- A group's sessions share that group's memory but keep separate message DBs.
 
-### 4. IPC Authorization
+This prevents cross-group information disclosure.
 
-Messages and task operations are verified against group identity:
-
-| Operation | Main Group | Non-Main Group |
-|-----------|------------|----------------|
-| Send message to own chat | ✓ | ✓ |
-| Send message to other chats | ✓ | ✗ |
-| Schedule task for self | ✓ | ✓ |
-| Schedule task for others | ✓ | ✗ |
-| View all tasks | ✓ | Own only |
-| Manage other groups | ✓ | ✗ |
-
-### 5. Credential Isolation (OneCLI Agent Vault)
+### 4. Credential Isolation (OneCLI Agent Vault)
 
 Real API credentials **never enter containers**. NanoClaw uses [OneCLI's Agent Vault](https://github.com/onecli/onecli) to proxy outbound requests and inject credentials at the gateway level.
 
@@ -77,13 +109,12 @@ Real API credentials **never enter containers**. NanoClaw uses [OneCLI's Agent V
 **Per-agent policies:**
 Each NanoClaw group gets its own OneCLI agent identity. This allows different credential policies per group (e.g. your sales agent vs. support agent). OneCLI supports rate limits, and time-bound access and approval flows are on the roadmap.
 
-**NOT Mounted:**
-- Channel auth sessions (`store/auth/`) — host only
-- Mount allowlist — external, never mounted
-- Any credentials matching blocked patterns
-- `.env` is shadowed with `/dev/null` in the project root mount
+**Never on the container filesystem:**
+- The project root and `.env` — never mounted; the container only receives the paths in the mount table above.
+- The mount allowlist — external (`~/.config/nanoclaw/…`), never mounted.
+- Real credentials — injected per request by the OneCLI gateway, never written into any mount.
 
-### 6. Egress Lockdown (Forced Proxy)
+### 5. Egress Lockdown (Forced Proxy)
 
 The `HTTPS_PROXY` env var only redirects *proxy-aware* clients — a tool that
 ignores it (or a raw socket) could reach the internet directly and bypass
@@ -111,31 +142,42 @@ no `host-gateway` route).
   exception: a heal failure there is logged but not fatal, since already-running
   agents stay on the internal net (no leak) until the gateway returns.
 
+**Default: egress is open.** Lockdown is **off** unless you opt in; by default
+the agent reaches the OneCLI gateway over the host-gateway path and outbound
+traffic is not confined to the internal network.
+
 **Configuration:**
 
 | Env | Default | Meaning |
 | --- | --- | --- |
-| `NANOCLAW_EGRESS_LOCKDOWN` | `false` | Set `true` to opt in (otherwise the host-gateway path is used). Enabled automatically by `/add-golden-registry`. |
+| `NANOCLAW_EGRESS_LOCKDOWN` | `false` | Set `true` to opt in (otherwise the host-gateway path is used). |
 | `NANOCLAW_EGRESS_NETWORK` | `nanoclaw-egress` | Network name. |
 | `ONECLI_GATEWAY_CONTAINER` | `onecli` | Gateway container to attach. |
 
+These variables are read from the **host process** environment (the service's
+environment / `.env`), not from inside the container. The agent container is
+started with only `TZ` and any provider-declared variables — host environment
+variables, including secrets, are never forwarded into the agent.
+
 **⚠ Behavior when enabled:** with lockdown on, agents have **no direct
 internet** — all traffic must go through OneCLI. Proxy-aware clients (npm, pnpm,
 pip, curl, node/bun with the proxy env) are unaffected. Any workflow that relies
 on a **non-proxy-aware** tool reaching the internet directly will fail by design.
 Lockdown is **off by default**; opt in with `NANOCLAW_EGRESS_LOCKDOWN=true`.
 
-## Privilege Comparison
+## Resource Limits
 
-| Capability | Main Group | Non-Main Group |
-|------------|------------|----------------|
-| Project root access | `/workspace/project` (ro) | None |
-| Store (SQLite DB) | `/workspace/project/store` (rw) | None |
-| Group folder | `/workspace/group` (rw) | `/workspace/group` (rw) |
-| Global memory | Implicit via project | `/workspace/global` (ro) |
-| Additional mounts | Configurable | Read-only unless allowed |
-| Network access | Unrestricted | Unrestricted |
-| MCP tools | All | All |
+Per-container CPU and memory caps are **opt-in and unset by default** — a runaway
+agent is not throttled unless the operator configures a limit:
+
+| Env | Default | Meaning |
+| --- | --- | --- |
+| `CONTAINER_CPU_LIMIT` | *(empty — unbounded)* | Passed to `--cpus` when set (e.g. `2`). |
+| `CONTAINER_MEMORY_LIMIT` | *(empty — unbounded)* | Passed to `--memory` when set (e.g. `8g`). |
+
+Only `--memory` is a container-level cap; whether it's a *hard* cap depends on
+the host having no swap (a deployment concern). On a swapless host a runaway is
+OOM-killed at the limit.
 
 ## Security Architecture Diagram
 
@@ -149,7 +191,7 @@ Lockdown is **off by default**; opt in with `NANOCLAW_EGRESS_LOCKDOWN=true`.
 ┌──────────────────────────────────────────────────────────────────┐
 │                     HOST PROCESS (TRUSTED)                        │
 │  • Message routing                                                │
-│  • IPC authorization                                              │
+│  • Role / access checks (user_roles, agent_group_members)        │
 │  • Mount validation (external allowlist)                          │
 │  • Container lifecycle                                            │
 │  • OneCLI Agent Vault (injects credentials, enforces policies)   │

docs/docker-sandboxes.md

@@ -1,359 +0,0 @@
-# Running NanoClaw in Docker Sandboxes (Manual Setup)
-
-This guide walks through setting up NanoClaw inside a [Docker Sandbox](https://docs.docker.com/ai/sandboxes/) from scratch — no install script, no pre-built fork. You'll clone the upstream repo, apply the necessary patches, and have agents running in full hypervisor-level isolation.
-
-## Architecture
-
-```
-Host (macOS / Windows WSL)
-└── Docker Sandbox (micro VM with isolated kernel)
-    ├── NanoClaw process (Node.js)
-    │   ├── Channel adapters (WhatsApp, Telegram, etc.)
-    │   └── Container spawner → nested Docker daemon
-    └── Docker-in-Docker
-        └── nanoclaw-agent containers
-            └── Claude Agent SDK
-```
-
-Each agent runs in its own container, inside a micro VM that is fully isolated from your host. Two layers of isolation: per-agent containers + the VM boundary.
-
-The sandbox provides a MITM proxy at `host.docker.internal:3128` that handles network access and injects your Anthropic API key automatically.
-
-> **Note:** This guide is based on a validated setup running on macOS (Apple Silicon) with WhatsApp. Other channels (Telegram, Slack, etc.) and environments (Windows WSL) may require additional proxy patches for their specific HTTP/WebSocket clients. The core patches (container runner, credential proxy, Dockerfile) apply universally — channel-specific proxy configuration varies.
-
-## Prerequisites
-
-- **Docker Desktop v4.40+** with Sandbox support
-- **Anthropic API key** (the sandbox proxy manages injection)
-- For **Telegram**: a bot token from [@BotFather](https://t.me/BotFather) and your chat ID
-- For **WhatsApp**: a phone with WhatsApp installed
-
-Verify sandbox support:
-```bash
-docker sandbox version
-```
-
-## Step 1: Create the Sandbox
-
-On your host machine:
-
-```bash
-# Create a workspace directory
-mkdir -p ~/nanoclaw-workspace
-
-# Create a shell sandbox with the workspace mounted
-docker sandbox create shell ~/nanoclaw-workspace
-```
-
-If you're using WhatsApp, configure proxy bypass so WhatsApp's Noise protocol isn't MITM-inspected:
-
-```bash
-docker sandbox network proxy shell-nanoclaw-workspace \
-  --bypass-host web.whatsapp.com \
-  --bypass-host "*.whatsapp.com" \
-  --bypass-host "*.whatsapp.net"
-```
-
-Telegram does not need proxy bypass.
-
-Enter the sandbox:
-```bash
-docker sandbox run shell-nanoclaw-workspace
-```
-
-## Step 2: Install Prerequisites
-
-Inside the sandbox:
-
-```bash
-sudo apt-get update && sudo apt-get install -y build-essential python3
-npm config set strict-ssl false
-```
-
-## Step 3: Clone and Install NanoClaw
-
-NanoClaw must live inside the workspace directory — Docker-in-Docker can only bind-mount from the shared workspace path.
-
-```bash
-# Clone to home first (virtiofs can corrupt git pack files during clone)
-cd ~
-git clone https://github.com/nanocoai/nanoclaw.git
-
-# Replace with YOUR workspace path (the host path you passed to `docker sandbox create`)
-WORKSPACE=/Users/you/nanoclaw-workspace
-
-# Move into workspace so DinD mounts work
-mv nanoclaw "$WORKSPACE/nanoclaw"
-cd "$WORKSPACE/nanoclaw"
-
-# Install dependencies
-pnpm install
-pnpm install https-proxy-agent
-```
-
-## Step 4: Apply Proxy and Sandbox Patches
-
-NanoClaw needs several patches to work inside a Docker Sandbox. These handle proxy routing, CA certificates, and Docker-in-Docker mount restrictions.
-
-### 4a. Dockerfile — proxy args for container image build
-
-`pnpm install` inside `docker build` fails with `SELF_SIGNED_CERT_IN_CHAIN` because the sandbox's MITM proxy presents its own certificate. Add proxy build args to `container/Dockerfile`:
-
-Add these lines after the `FROM` line:
-
-```dockerfile
-# Accept proxy build args
-ARG http_proxy
-ARG https_proxy
-ARG no_proxy
-ARG NODE_EXTRA_CA_CERTS
-ARG npm_config_strict_ssl=true
-RUN npm config set strict-ssl ${npm_config_strict_ssl}
-```
-
-And after the `RUN pnpm install` line:
-
-```dockerfile
-RUN npm config set strict-ssl true
-```
-
-### 4b. Build script — forward proxy args
-
-Patch `container/build.sh` to pass proxy env vars to `docker build`:
-
-Add these `--build-arg` flags to the `docker build` command:
-
-```bash
---build-arg http_proxy="${http_proxy:-$HTTP_PROXY}" \
---build-arg https_proxy="${https_proxy:-$HTTPS_PROXY}" \
---build-arg no_proxy="${no_proxy:-$NO_PROXY}" \
---build-arg npm_config_strict_ssl=false \
-```
-
-### 4c. Container runner — proxy forwarding, CA cert mount, /dev/null fix
-
-Three changes to `src/container-runner.ts`:
-
-**Replace `/dev/null` shadow mount.** The sandbox rejects `/dev/null` bind mounts. Find where `.env` is shadow-mounted to `/dev/null` and replace it with an empty file:
-
-```typescript
-// Create an empty file to shadow .env (Docker Sandbox rejects /dev/null mounts)
-const emptyEnvPath = path.join(DATA_DIR, 'empty-env');
-if (!fs.existsSync(emptyEnvPath)) fs.writeFileSync(emptyEnvPath, '');
-// Use emptyEnvPath instead of '/dev/null' in the mount
-```
-
-**Forward proxy env vars** to spawned agent containers. Add `-e` flags for `HTTP_PROXY`, `HTTPS_PROXY`, `NO_PROXY` and their lowercase variants.
-
-**Mount CA certificate.** If `NODE_EXTRA_CA_CERTS` or `SSL_CERT_FILE` is set, copy the cert into the project directory and mount it into agent containers:
-
-```typescript
-const caCertSrc = process.env.NODE_EXTRA_CA_CERTS || process.env.SSL_CERT_FILE;
-if (caCertSrc) {
-  const certDir = path.join(DATA_DIR, 'ca-cert');
-  fs.mkdirSync(certDir, { recursive: true });
-  fs.copyFileSync(caCertSrc, path.join(certDir, 'proxy-ca.crt'));
-  // Mount: certDir -> /workspace/ca-cert (read-only)
-  // Set NODE_EXTRA_CA_CERTS=/workspace/ca-cert/proxy-ca.crt in the container
-}
-```
-
-### 4d. Container runtime — prevent self-termination
-
-In `src/container-runtime.ts`, the `cleanupOrphans()` function matches containers by the `nanoclaw-` prefix. Inside a sandbox, the sandbox container itself may match (e.g., `nanoclaw-docker-sandbox`). Filter out the current hostname:
-
-```typescript
-// In cleanupOrphans(), filter out os.hostname() from the list of containers to stop
-```
-
-### 4e. Credential proxy — route through MITM proxy
-
-In `src/credential-proxy.ts`, upstream API requests need to go through the sandbox proxy. Add `HttpsProxyAgent` to outbound requests:
-
-```typescript
-import { HttpsProxyAgent } from 'https-proxy-agent';
-
-const proxyUrl = process.env.HTTPS_PROXY || process.env.https_proxy;
-const upstreamAgent = proxyUrl ? new HttpsProxyAgent(proxyUrl) : undefined;
-// Pass upstreamAgent to https.request() options
-```
-
-### 4f. Setup script — proxy build args
-
-Patch `setup/container.ts` to pass the same proxy `--build-arg` flags as `build.sh` (Step 4b).
-
-## Step 5: Build
-
-```bash
-pnpm run build
-bash container/build.sh
-```
-
-## Step 6: Add a Channel
-
-### Telegram
-
-```bash
-# Apply the Telegram skill
-pnpm exec tsx scripts/apply-skill.ts .claude/skills/add-telegram
-
-# Rebuild after applying the skill
-pnpm run build
-
-# Configure .env
-cat > .env << EOF
-TELEGRAM_BOT_TOKEN=<your-token-from-botfather>
-ASSISTANT_NAME=nanoclaw
-ANTHROPIC_API_KEY=proxy-managed
-EOF
-mkdir -p data/env && cp .env data/env/env
-
-# Register your chat
-pnpm exec tsx setup/index.ts --step register \
-  --jid "tg:<your-chat-id>" \
-  --name "My Chat" \
-  --trigger "@nanoclaw" \
-  --folder "telegram_main" \
-  --channel telegram \
-  --assistant-name "nanoclaw" \
-  --is-main \
-  --no-trigger-required
-```
-
-**To find your chat ID:** Send any message to your bot, then:
-```bash
-curl -s --proxy $HTTPS_PROXY "https://api.telegram.org/bot<TOKEN>/getUpdates" | python3 -m json.tool
-```
-
-**Telegram in groups:** Disable Group Privacy in @BotFather (`/mybots` > Bot Settings > Group Privacy > Turn off), then remove and re-add the bot.
-
-**Important:** If the Telegram skill creates `src/channels/telegram.ts`, you'll need to patch it for proxy support. Add an `HttpsProxyAgent` and pass it to grammy's `Bot` constructor via `baseFetchConfig.agent`. Then rebuild.
-
-### WhatsApp
-
-Make sure you configured proxy bypass in [Step 1](#step-1-create-the-sandbox) first.
-
-```bash
-# Apply the WhatsApp skill
-pnpm exec tsx scripts/apply-skill.ts .claude/skills/add-whatsapp
-
-# Rebuild
-pnpm run build
-
-# Configure .env
-cat > .env << EOF
-ASSISTANT_NAME=nanoclaw
-ANTHROPIC_API_KEY=proxy-managed
-EOF
-mkdir -p data/env && cp .env data/env/env
-
-# Authenticate (choose one):
-
-# QR code — scan with WhatsApp camera:
-pnpm exec tsx src/whatsapp-auth.ts
-
-# OR pairing code — enter code in WhatsApp > Linked Devices > Link with phone number:
-pnpm exec tsx src/whatsapp-auth.ts --pairing-code --phone <phone-number-no-plus>
-
-# Register your chat (JID = your phone number + @s.whatsapp.net)
-pnpm exec tsx setup/index.ts --step register \
-  --jid "<phone>@s.whatsapp.net" \
-  --name "My Chat" \
-  --trigger "@nanoclaw" \
-  --folder "whatsapp_main" \
-  --channel whatsapp \
-  --assistant-name "nanoclaw" \
-  --is-main \
-  --no-trigger-required
-```
-
-**Important:** The WhatsApp skill files (`src/channels/whatsapp.ts` and `src/whatsapp-auth.ts`) also need proxy patches — add `HttpsProxyAgent` for WebSocket connections and a proxy-aware version fetch. Then rebuild.
-
-### Both Channels
-
-Apply both skills, patch both for proxy support, combine the `.env` variables, and register each chat separately.
-
-## Step 7: Run
-
-```bash
-pnpm start
-```
-
-You don't need to set `ANTHROPIC_API_KEY` manually. The sandbox proxy intercepts requests and replaces `proxy-managed` with your real key automatically.
-
-## Networking Details
-
-### How the proxy works
-
-All traffic from the sandbox routes through the host proxy at `host.docker.internal:3128`:
-
-```
-Agent container → DinD bridge → Sandbox VM → host.docker.internal:3128 → Host proxy → api.anthropic.com
-```
-
-**"Bypass" does not mean traffic skips the proxy.** It means the proxy passes traffic through without MITM inspection. Node.js doesn't automatically use `HTTP_PROXY` env vars — you need explicit `HttpsProxyAgent` configuration in every HTTP/WebSocket client.
-
-### Shared paths for DinD mounts
-
-Only the workspace directory is available for Docker-in-Docker bind mounts. Paths outside the workspace fail with "path not shared":
-- `/dev/null` → replace with an empty file in the project dir
-- `/usr/local/share/ca-certificates/` → copy cert to project dir
-- `/home/agent/` → clone to workspace instead
-
-### Git clone and virtiofs
-
-The workspace is mounted via virtiofs. Git's pack file handling can corrupt over virtiofs during clone. Workaround: clone to `/home/agent` first, then `mv` into the workspace.
-
-## Troubleshooting
-
-### pnpm install fails with SELF_SIGNED_CERT_IN_CHAIN
-```bash
-npm config set strict-ssl false
-```
-
-### Container build fails with proxy errors
-```bash
-docker build \
-  --build-arg http_proxy=$http_proxy \
-  --build-arg https_proxy=$https_proxy \
-  -t nanoclaw-agent:latest container/
-```
-
-### Agent containers fail with "path not shared"
-All bind-mounted paths must be under the workspace directory. Check:
-- Is NanoClaw cloned into the workspace? (not `/home/agent/`)
-- Is the CA cert copied to the project root?
-- Has the empty `.env` shadow file been created?
-
-### Agent containers can't reach Anthropic API
-Verify proxy env vars are forwarded to agent containers. Check container logs for `HTTP_PROXY=http://host.docker.internal:3128`.
-
-### WhatsApp error 405
-The version fetch is returning a stale version. Make sure the proxy-aware `fetchWaVersionViaProxy` patch is applied — it fetches `sw.js` through `HttpsProxyAgent` and parses `client_revision`.
-
-### WhatsApp "Connection failed" immediately
-Proxy bypass not configured. From the **host**, run:
-```bash
-docker sandbox network proxy <sandbox-name> \
-  --bypass-host web.whatsapp.com \
-  --bypass-host "*.whatsapp.com" \
-  --bypass-host "*.whatsapp.net"
-```
-
-### Telegram bot doesn't receive messages
-1. Check the grammy proxy patch is applied (look for `HttpsProxyAgent` in `src/channels/telegram.ts`)
-2. Check Group Privacy is disabled in @BotFather if using in groups
-
-### Git clone fails with "inflate: data stream error"
-Clone to a non-workspace path first, then move:
-```bash
-cd ~ && git clone https://github.com/nanocoai/nanoclaw.git && mv nanoclaw /path/to/workspace/nanoclaw
-```
-
-### WhatsApp QR code doesn't display
-Run the auth command interactively inside the sandbox (not piped through `docker sandbox exec`):
-```bash
-docker sandbox run shell-nanoclaw-workspace
-# Then inside:
-pnpm exec tsx src/whatsapp-auth.ts
-```

package.json

@@ -1,6 +1,6 @@
 {
   "name": "nanoclaw",
-  "version": "2.1.33",
+  "version": "2.1.36",
   "description": "Personal Claude assistant. Lightweight, secure, customizable.",
   "type": "module",
   "packageManager": "pnpm@10.33.0",

repo-tokens/badge.svg

@@ -1,5 +1,5 @@
-<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" width="90" height="20" role="img" aria-label="207k tokens, 104% of context window">
-  <title>207k tokens, 104% of context window</title>
+<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" width="90" height="20" role="img" aria-label="208k tokens, 104% of context window">
+  <title>208k tokens, 104% of context window</title>
   <linearGradient id="s" x2="0" y2="100%">
     <stop offset="0" stop-color="#bbb" stop-opacity=".1"/>
     <stop offset="1" stop-opacity=".1"/>
@@ -15,8 +15,8 @@
       <g fill="#fff" text-anchor="middle" font-family="Verdana,Geneva,DejaVu Sans,sans-serif" font-size="11">
         <text aria-hidden="true" x="26" y="15" fill="#010101" fill-opacity=".3">tokens</text>
         <text x="26" y="14">tokens</text>
-        <text aria-hidden="true" x="71" y="15" fill="#010101" fill-opacity=".3">207k</text>
-        <text x="71" y="14">207k</text>
+        <text aria-hidden="true" x="71" y="15" fill="#010101" fill-opacity=".3">208k</text>
+        <text x="71" y="14">208k</text>
       </g>
     </g>
   </a>

scripts/test-v2-agent.ts

@@ -33,7 +33,9 @@ db.exec(`
 `);
 
 // Insert test message
-db.prepare(`INSERT INTO messages_in (id, kind, timestamp, status, content) VALUES (?, 'chat', datetime('now'), 'pending', ?)`).run(
+db.prepare(
+  `INSERT INTO messages_in (id, kind, timestamp, status, content) VALUES (?, 'chat', datetime('now'), 'pending', ?)`,
+).run(
   'test-1',
   JSON.stringify({ sender: 'Gavriel', text: 'Say "Hello from v2!" and nothing else. Do not use any tools.' }),
 );
@@ -44,7 +46,7 @@ db.close();
 process.env.SESSION_DB_PATH = DB_PATH;
 process.env.AGENT_PROVIDER = 'claude';
 
-const { getSessionDb, closeSessionDb } = await import('../container/agent-runner/src/db/connection.js');
+const { getInboundDb, closeSessionDb } = await import('../container/agent-runner/src/db/connection.js');
 const { getUndeliveredMessages } = await import('../container/agent-runner/src/db/messages-out.js');
 const { getPendingMessages } = await import('../container/agent-runner/src/db/messages-in.js');
 const { createProvider } = await import('../container/agent-runner/src/providers/factory.js');

scripts/test-v2-channel-e2e.ts

@@ -71,7 +71,7 @@ import { routeInbound } from '../src/router.js';
 import { setDeliveryAdapter, startActiveDeliveryPoll, stopDeliveryPolls } from '../src/delivery.js';
 import { getChannelAdapter, registerChannelAdapter, initChannelAdapters } from '../src/channels/channel-registry.js';
 import { findSession } from '../src/db/sessions.js';
-import { sessionDbPath } from '../src/session-manager.js';
+import { inboundDbPath } from '../src/session-manager.js';
 import type { ChannelAdapter, ChannelSetup, OutboundMessage } from '../src/channels/adapter.js';
 
 // Track delivered messages
@@ -99,7 +99,9 @@ const mockAdapter: ChannelAdapter = {
 
   async setTyping() {},
   async teardown() {},
-  isConnected() { return true; },
+  isConnected() {
+    return true;
+  },
 };
 
 // Register mock adapter
@@ -179,15 +181,19 @@ console.log(`✓ Container status: ${session.container_status}`);
 import { execSync } from 'child_process';
 const checkContainerLogs = () => {
   try {
-    const containers = execSync('docker ps -a --filter name=nanoclaw-v2-test-channel --format "{{.Names}}"').toString().trim();
+    const containers = execSync('docker ps -a --filter name=nanoclaw-v2-test-channel --format "{{.Names}}"')
+      .toString()
+      .trim();
     for (const name of containers.split('\n').filter(Boolean)) {
       console.log(`\nContainer logs (${name}):`);
       console.log(execSync(`docker logs ${name} 2>&1`).toString());
     }
-  } catch { /* ignore */ }
+  } catch {
+    /* ignore */
+  }
 };
 
-const sessDbPath = sessionDbPath('ag-chan', session.id);
+const sessDbPath = inboundDbPath('ag-chan', session.id);
 console.log(`✓ Session DB: ${sessDbPath}`);
 
 // --- Step 4: Wait for delivery through mock adapter ---
@@ -210,7 +216,9 @@ await new Promise<void>((resolve) => {
         console.log(`  messages_out rows: ${out.length}`);
         if (out.length > 0) console.log('  (messages exist but delivery failed)');
         db.close();
-      } catch { /* ignore */ }
+      } catch {
+        /* ignore */
+      }
       checkContainerLogs();
       cleanup();
       process.exit(1);

src/db/session-db.ts

@@ -181,14 +181,6 @@ export function syncProcessingAcks(inDb: Database.Database, outDb: Database.Data
   })();
 }
 
-export function getStuckProcessingIds(outDb: Database.Database): string[] {
-  return (
-    outDb.prepare("SELECT message_id FROM processing_ack WHERE status = 'processing'").all() as Array<{
-      message_id: string;
-    }>
-  ).map((r) => r.message_id);
-}
-
 export interface ProcessingClaim {
   message_id: string;
   status_changed: string;

src/index.ts

@@ -24,16 +24,7 @@ import { enforceUpgradeTripwire } from './upgrade-state.js';
 // effects, and the modules call registerResponseHandler/onShutdown at top
 // level — which would hit a TDZ error if the arrays lived here. Re-exported
 // here so existing callers see the same surface.
-import {
-  registerResponseHandler,
-  getResponseHandlers,
-  onShutdown,
-  getShutdownCallbacks,
-  type ResponsePayload,
-  type ResponseHandler,
-} from './response-registry.js';
-export { registerResponseHandler, onShutdown };
-export type { ResponsePayload, ResponseHandler };
+import { getResponseHandlers, getShutdownCallbacks, type ResponsePayload } from './response-registry.js';
 
 async function dispatchResponse(payload: ResponsePayload): Promise<void> {
   for (const handler of getResponseHandlers()) {

src/modules/mount-security/index.test.ts

@@ -0,0 +1,119 @@
+/**
+ * Tests for the mount allowlist loader/validator.
+ *
+ * Covers the two cleanups:
+ *  - The loader honors the per-root `readOnly` key (translating it to
+ *    `allowReadWrite`) and tolerates the top-level `nonMainReadOnly` key that
+ *    setup writes into every fresh install.
+ *  - The allowlist is read per call (mtime-keyed cache), so a parse error is
+ *    never cached permanently — a fixed file is picked up without a restart.
+ */
+import fs from 'fs';
+import os from 'os';
+import path from 'path';
+
+import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
+
+// The config path is a module-level const in production; point it at a
+// per-test temp file via a getter so each test is isolated from the cache.
+const mockState = vi.hoisted(() => ({ allowlistPath: '' }));
+
+vi.mock('../../config.js', async () => {
+  const actual = await vi.importActual<Record<string, unknown>>('../../config.js');
+  return {
+    ...actual,
+    get MOUNT_ALLOWLIST_PATH() {
+      return mockState.allowlistPath;
+    },
+  };
+});
+
+import { loadMountAllowlist, validateMount } from './index.js';
+
+let tmpDir: string;
+let configFile: string;
+let projectsDir: string;
+let repoDir: string;
+
+beforeEach(() => {
+  tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'mnt-sec-'));
+  configFile = path.join(tmpDir, 'mount-allowlist.json');
+  mockState.allowlistPath = configFile;
+
+  projectsDir = path.join(tmpDir, 'projects');
+  repoDir = path.join(projectsDir, 'repo');
+  fs.mkdirSync(repoDir, { recursive: true });
+});
+
+afterEach(() => {
+  fs.rmSync(tmpDir, { recursive: true, force: true });
+});
+
+function writeAllowlist(obj: unknown): void {
+  fs.writeFileSync(configFile, JSON.stringify(obj, null, 2) + '\n');
+}
+
+describe('loadMountAllowlist', () => {
+  it('translates per-root readOnly:false into a read-write grant', () => {
+    writeAllowlist({
+      allowedRoots: [{ path: projectsDir, readOnly: false }],
+      blockedPatterns: [],
+    });
+
+    const allowlist = loadMountAllowlist();
+    expect(allowlist).not.toBeNull();
+    expect(allowlist!.allowedRoots[0].allowReadWrite).toBe(true);
+
+    // ...and a mount that requests read-write actually gets it.
+    const result = validateMount({ hostPath: repoDir, readonly: false });
+    expect(result.allowed).toBe(true);
+    expect(result.effectiveReadonly).toBe(false);
+  });
+
+  it('keeps readOnly:true as a read-only grant', () => {
+    writeAllowlist({
+      allowedRoots: [{ path: projectsDir, readOnly: true }],
+      blockedPatterns: [],
+    });
+
+    const allowlist = loadMountAllowlist();
+    expect(allowlist!.allowedRoots[0].allowReadWrite).toBe(false);
+
+    const result = validateMount({ hostPath: repoDir, readonly: false });
+    expect(result.allowed).toBe(true);
+    expect(result.effectiveReadonly).toBe(true);
+  });
+
+  it('tolerates an unknown top-level nonMainReadOnly key', () => {
+    writeAllowlist({
+      allowedRoots: [{ path: projectsDir, allowReadWrite: true }],
+      blockedPatterns: [],
+      nonMainReadOnly: true,
+    });
+
+    const allowlist = loadMountAllowlist();
+    expect(allowlist).not.toBeNull();
+    expect(allowlist!.allowedRoots).toHaveLength(1);
+    expect(allowlist!.allowedRoots[0].allowReadWrite).toBe(true);
+  });
+
+  it('picks up a fixed file without a restart (parse errors are not cached)', () => {
+    // A broken edit blocks all mounts...
+    fs.writeFileSync(configFile, 'not valid json {');
+    expect(loadMountAllowlist()).toBeNull();
+
+    // ...but fixing the file recovers on the very next call — no restart.
+    writeAllowlist({
+      allowedRoots: [{ path: projectsDir, allowReadWrite: true }],
+      blockedPatterns: [],
+    });
+    const allowlist = loadMountAllowlist();
+    expect(allowlist).not.toBeNull();
+    expect(allowlist!.allowedRoots).toHaveLength(1);
+  });
+
+  it('returns null when the allowlist file is missing', () => {
+    // No file written.
+    expect(loadMountAllowlist()).toBeNull();
+  });
+});

src/modules/mount-security/index.ts

@@ -29,9 +29,11 @@ export interface AllowedRoot {
   description?: string;
 }
 
-// Cache the allowlist in memory - only reloads on process restart
-let cachedAllowlist: MountAllowlist | null = null;
-let allowlistLoadError: string | null = null;
+// Cache the last successfully-parsed allowlist, keyed on the file's path +
+// mtime. A changed or fixed file is picked up on the next call (no restart),
+// and a parse error is never cached permanently — one bad edit blocks mounts
+// only until the file is fixed.
+let cache: { path: string; mtimeMs: number; allowlist: MountAllowlist } | null = null;
 
 /**
  * Default blocked patterns - paths that should never be mounted
@@ -57,60 +59,108 @@ const DEFAULT_BLOCKED_PATTERNS = [
 ];
 
 /**
- * Load the mount allowlist from the external config location.
- * Returns null if the file doesn't exist or is invalid.
- * Result is cached in memory for the lifetime of the process.
+ * Normalize a raw allowed-root entry into an {@link AllowedRoot}.
+ *
+ * The read-only decision is per-root. Historically this validator only read
+ * `allowReadWrite`, but the /manage-mounts skill and setup write `readOnly`
+ * instead — so a `readOnly: false` grant was silently forced read-only.
+ * Translate `readOnly` → `allowReadWrite = !readOnly` (with a warning) unless an
+ * explicit `allowReadWrite` is already present. With neither key, default to
+ * read-only (fail safe).
  */
-export function loadMountAllowlist(): MountAllowlist | null {
-  if (cachedAllowlist !== null) {
-    return cachedAllowlist;
+function normalizeRoot(root: Record<string, unknown>): AllowedRoot {
+  const rootPath = typeof root.path === 'string' ? root.path : '';
+  const description = typeof root.description === 'string' ? root.description : undefined;
+
+  let allowReadWrite: boolean;
+  if (typeof root.allowReadWrite === 'boolean') {
+    allowReadWrite = root.allowReadWrite;
+  } else if (typeof root.readOnly === 'boolean') {
+    allowReadWrite = !root.readOnly;
+    log.warn('Mount allowlist root uses "readOnly" — translating to allowReadWrite', {
+      root: rootPath,
+      readOnly: root.readOnly,
+    });
+  } else {
+    allowReadWrite = false;
   }
 
-  if (allowlistLoadError !== null) {
-    // Already tried and failed, don't spam logs
+  return { path: rootPath, allowReadWrite, description };
+}
+
+/**
+ * Load the mount allowlist from the external config location.
+ * Returns null if the file doesn't exist or is invalid.
+ * Re-reads on every call, but serves from an in-memory cache while the file's
+ * mtime is unchanged. A parse error is never cached — fix the file and the next
+ * call recovers without a service restart.
+ */
+export function loadMountAllowlist(): MountAllowlist | null {
+  // Missing-file behavior: warn and block additional mounts, but do NOT cache
+  // the miss — the file may be created later without a restart.
+  let stat: fs.Stats;
+  try {
+    stat = fs.statSync(MOUNT_ALLOWLIST_PATH);
+  } catch {
+    log.warn(
+      'Mount allowlist not found - additional mounts will be BLOCKED. Create the file to enable additional mounts.',
+      { path: MOUNT_ALLOWLIST_PATH },
+    );
     return null;
   }
 
-  try {
-    if (!fs.existsSync(MOUNT_ALLOWLIST_PATH)) {
-      // Do NOT cache this as an error — file may be created later without restart.
-      // Only parse/structural errors are permanently cached.
-      log.warn(
-        'Mount allowlist not found - additional mounts will be BLOCKED. Create the file to enable additional mounts.',
-        { path: MOUNT_ALLOWLIST_PATH },
-      );
-      return null;
-    }
+  // Serve from cache only while the same file is unchanged since the last
+  // successful load. Any edit (including fixing a previously broken file) bumps
+  // the mtime and is picked up on the next call.
+  if (cache !== null && cache.path === MOUNT_ALLOWLIST_PATH && cache.mtimeMs === stat.mtimeMs) {
+    return cache.allowlist;
+  }
 
+  try {
     const content = fs.readFileSync(MOUNT_ALLOWLIST_PATH, 'utf-8');
-    const allowlist = JSON.parse(content) as MountAllowlist;
+    const raw = JSON.parse(content) as Record<string, unknown>;
 
     // Validate structure
-    if (!Array.isArray(allowlist.allowedRoots)) {
+    if (!Array.isArray(raw.allowedRoots)) {
       throw new Error('allowedRoots must be an array');
     }
 
-    if (!Array.isArray(allowlist.blockedPatterns)) {
+    if (!Array.isArray(raw.blockedPatterns)) {
       throw new Error('blockedPatterns must be an array');
     }
 
-    // Merge with default blocked patterns
-    const mergedBlockedPatterns = [...new Set([...DEFAULT_BLOCKED_PATTERNS, ...allowlist.blockedPatterns])];
-    allowlist.blockedPatterns = mergedBlockedPatterns;
+    // Warn-and-ignore the top-level `nonMainReadOnly` key. Setup writes it into
+    // every fresh install, but this validator has no concept of a "main" agent —
+    // read-only is decided per-root. Do NOT throw: a hard reject would fail
+    // closed and brick all mounts on a standard install.
+    if ('nonMainReadOnly' in raw) {
+      log.warn('Mount allowlist has unsupported top-level "nonMainReadOnly" key — ignoring (read-only is per-root)', {
+        path: MOUNT_ALLOWLIST_PATH,
+      });
+    }
 
-    cachedAllowlist = allowlist;
+    const allowedRoots = (raw.allowedRoots as Array<Record<string, unknown>>).map(normalizeRoot);
+
+    // Merge with default blocked patterns
+    const blockedPatterns = [...new Set([...DEFAULT_BLOCKED_PATTERNS, ...(raw.blockedPatterns as string[])])];
+
+    const allowlist: MountAllowlist = { allowedRoots, blockedPatterns };
+
+    cache = { path: MOUNT_ALLOWLIST_PATH, mtimeMs: stat.mtimeMs, allowlist };
     log.info('Mount allowlist loaded successfully', {
       path: MOUNT_ALLOWLIST_PATH,
       allowedRoots: allowlist.allowedRoots.length,
       blockedPatterns: allowlist.blockedPatterns.length,
     });
 
-    return cachedAllowlist;
+    return allowlist;
   } catch (err) {
-    allowlistLoadError = err instanceof Error ? err.message : String(err);
+    // Do NOT poison the cache — a corrupt edit blocks mounts only until it's
+    // fixed, then the next call re-reads and recovers.
+    cache = null;
     log.error('Failed to load mount allowlist - additional mounts will be BLOCKED', {
       path: MOUNT_ALLOWLIST_PATH,
-      error: allowlistLoadError,
+      error: err instanceof Error ? err.message : String(err),
     });
     return null;
   }

src/session-manager.ts

@@ -64,14 +64,6 @@ export function heartbeatPath(agentGroupId: string, sessionId: string): string {
   return path.join(sessionDir(agentGroupId, sessionId), '.heartbeat');
 }
 
-/**
- * @deprecated Use inboundDbPath / outboundDbPath instead.
- * Kept temporarily for test compatibility during migration.
- */
-export function sessionDbPath(agentGroupId: string, sessionId: string): string {
-  return inboundDbPath(agentGroupId, sessionId);
-}
-
 function generateId(): string {
   return `sess-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`;
 }
@@ -402,34 +394,6 @@ export function writeOutboundDirect(
   }
 }
 
-/**
- * @deprecated Use openInboundDb / openOutboundDb instead.
- */
-export function openSessionDb(agentGroupId: string, sessionId: string): Database.Database {
-  return openInboundDb(agentGroupId, sessionId);
-}
-
-/** Write a system response to a session's inbound.db so the container's findQuestionResponse() picks it up. */
-export function writeSystemResponse(
-  agentGroupId: string,
-  sessionId: string,
-  requestId: string,
-  status: string,
-  result: Record<string, unknown>,
-): void {
-  writeSessionMessage(agentGroupId, sessionId, {
-    id: `sys-resp-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`,
-    kind: 'system',
-    timestamp: new Date().toISOString(),
-    content: JSON.stringify({
-      type: 'question_response',
-      questionId: requestId,
-      status,
-      result,
-    }),
-  });
-}
-
 /**
  * Load outbox attachments for a delivered message.
  *