Fix session persistence and auto-start container system

- Fix session mount path: ~/.claude/ now mounts to /home/node/.claude/ (container runs as 'node' user with HOME=/home/node, not root) - Fix ~/.gmail-mcp/ mount path similarly - Use absolute paths for GROUPS_DIR and DATA_DIR (required for container mounts) - Auto-start Apple Container system on NanoClaw startup - Update debug skill with session troubleshooting guide - Update spec.md with startup sequence and troubleshooting Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-01 11:31:52 +02:00
parent 67e0295d82
commit 8ca4c95517
7 changed files with 130 additions and 21 deletions
--- a/.claude/skills/debug/SKILL.md
+++ b/.claude/skills/debug/SKILL.md
@@ -20,9 +20,12 @@ src/container-runner.ts               container/agent-runner/
    ├── data/env/env ──────────────> /workspace/env-dir/env
    ├── groups/{folder} ───────────> /workspace/group
    ├── data/ipc ──────────────────> /workspace/ipc
+    ├── ~/.claude/ ────────────────> /home/node/.claude/ (sessions)
    └── (main only) project root ──> /workspace/project
 ```

+**Important:** The container runs as user `node` with `HOME=/home/node`. Session files must be mounted to `/home/node/.claude/` (not `/root/.claude/`) for session resumption to work.
+
 ## Log Locations

 | Log | Location | Content |
@@ -131,7 +134,38 @@ container run --rm --entrypoint /bin/bash nanoclaw-agent:latest -c '

 All of `/workspace/` and `/app/` should be owned by `node`.

-### 5. MCP Server Failures
+### 5. Session Not Resuming / "Claude Code process exited with code 1"
+
+If sessions aren't being resumed (new session ID every time), or Claude Code exits with code 1 when resuming:
+
+**Root cause:** The SDK looks for sessions at `$HOME/.claude/projects/`. Inside the container, `HOME=/home/node`, so it looks at `/home/node/.claude/projects/`.
+
+**Check the mount path:**
+```bash
+# In container-runner.ts, verify mount is to /home/node/.claude/, NOT /root/.claude/
+grep -A3 "Claude sessions" src/container-runner.ts
+```
+
+**Verify sessions are accessible:**
+```bash
+container run --rm --entrypoint /bin/bash \
+  -v ~/.claude:/home/node/.claude \
+  nanoclaw-agent:latest -c '
+echo "HOME=$HOME"
+ls -la $HOME/.claude/projects/ 2>&1 | head -5
+'
+```
+
+**Fix:** Ensure `container-runner.ts` mounts to `/home/node/.claude/`:
+```typescript
+mounts.push({
+  hostPath: claudeDir,
+  containerPath: '/home/node/.claude',  // NOT /root/.claude
+  readonly: false
+});
+```
+
+### 6. MCP Server Failures

 If an MCP server fails to start, the agent may exit. Test MCP servers individually:

@@ -229,7 +263,14 @@ container run --rm --entrypoint /bin/bash nanoclaw-agent:latest -c '

 ## Session Persistence

-Claude sessions are stored in `~/.claude/` which is mounted into the container. To clear sessions:
+Claude sessions are stored in `~/.claude/projects/` on the host, mounted to `/home/node/.claude/projects/` inside the container.
+
+**Critical:** The mount path must match the container user's HOME directory:
+- Container user: `node`
+- Container HOME: `/home/node`
+- Mount target: `/home/node/.claude/` (NOT `/root/.claude/`)
+
+To clear sessions:

 ```bash
 # Clear all sessions
@@ -237,6 +278,15 @@ rm -rf ~/.claude/projects/

 # Clear sessions for a specific group
 rm -rf ~/.claude/projects/*workspace-group*/
+
+# Also clear the session ID from NanoClaw's tracking
+echo '{}' > data/sessions.json
+```
+
+To verify session resumption is working, check the logs for the same session ID across messages:
+```bash
+grep "Session initialized" logs/nanoclaw.log | tail -5
+# Should show the SAME session ID for consecutive messages in the same group
 ```

 ## IPC Debugging
@@ -267,15 +317,22 @@ echo -e "\n1. API Key configured?"
 echo -e "\n2. Env file copied for container?"
 [ -f data/env/env ] && echo "OK" || echo "MISSING - will be created on first run"

-echo -e "\n3. Container image exists?"
-container images 2>/dev/null | grep -q nanoclaw-agent && echo "OK" || echo "MISSING - run ./container/build.sh"
+echo -e "\n3. Apple Container system running?"
+container system status &>/dev/null && echo "OK" || echo "NOT RUNNING - NanoClaw should auto-start it; check logs"

-echo -e "\n4. Apple Container running?"
-container system info &>/dev/null && echo "OK" || echo "NOT RUNNING - run: container system start"
+echo -e "\n4. Container image exists?"
+echo '{}' | container run -i --entrypoint /bin/echo nanoclaw-agent:latest "OK" 2>/dev/null || echo "MISSING - run ./container/build.sh"

-echo -e "\n5. Groups directory?"
+echo -e "\n5. Session mount path correct?"
+grep -q "/home/node/.claude" src/container-runner.ts 2>/dev/null && echo "OK" || echo "WRONG - should mount to /home/node/.claude/, not /root/.claude/"
+
+echo -e "\n6. Groups directory?"
 ls -la groups/ 2>/dev/null || echo "MISSING - run setup"

-echo -e "\n6. Recent container logs?"
+echo -e "\n7. Recent container logs?"
 ls -t groups/*/logs/container-*.log 2>/dev/null | head -3 || echo "No container logs yet"
+
+echo -e "\n8. Session continuity working?"
+SESSIONS=$(grep "Session initialized" logs/nanoclaw.log 2>/dev/null | tail -5 | awk '{print $NF}' | sort -u | wc -l)
+[ "$SESSIONS" -le 2 ] && echo "OK (recent sessions reusing IDs)" || echo "CHECK - multiple different session IDs, may indicate resumption issues"
 ```
--- a/.claude/skills/setup/SKILL.md
+++ b/.claude/skills/setup/SKILL.md
@@ -33,10 +33,12 @@ If not installed, tell the user:
 Wait for user confirmation, then verify:

 ```bash
-container system start 2>/dev/null || true
+container system start
 container --version
 ```

+**Note:** NanoClaw automatically starts the Apple Container system when it launches, so you don't need to start it manually after reboots.
+
 ## 3. Configure API Key

 Ask the user:
@@ -268,6 +270,10 @@ The user should receive a response in WhatsApp.

 **Service not starting**: Check `logs/nanoclaw.error.log`

+**Container agent fails with "Claude Code process exited with code 1"**:
+- Ensure Apple Container is running: `container system start`
+- Check container logs: `cat groups/main/logs/container-*.log | tail -50`
+
 **No response to messages**:
 - Verify the trigger pattern matches (e.g., `@AssistantName` at start of message)
 - Check that the chat JID is in `data/registered_groups.json`
--- a/SPEC.md
+++ b/SPEC.md
@@ -164,12 +164,17 @@ nanoclaw/
 Configuration constants are in `src/config.ts`:

 ```typescript
+import path from 'path';
+
 export const ASSISTANT_NAME = process.env.ASSISTANT_NAME || 'Andy';
 export const POLL_INTERVAL = 2000;
 export const SCHEDULER_POLL_INTERVAL = 60000;
-export const STORE_DIR = './store';
-export const GROUPS_DIR = './groups';
-export const DATA_DIR = './data';
+
+// Paths are absolute (required for container mounts)
+const PROJECT_ROOT = process.cwd();
+export const STORE_DIR = path.resolve(PROJECT_ROOT, 'store');
+export const GROUPS_DIR = path.resolve(PROJECT_ROOT, 'groups');
+export const DATA_DIR = path.resolve(PROJECT_ROOT, 'data');

 // Container configuration
 export const CONTAINER_IMAGE = process.env.CONTAINER_IMAGE || 'nanoclaw-agent:latest';
@@ -180,6 +185,8 @@ export const TRIGGER_PATTERN = new RegExp(`^@${ASSISTANT_NAME}\\b`, 'i');
 export const CLEAR_COMMAND = '/clear';
 ```

+**Note:** Paths must be absolute for Apple Container volume mounts to work correctly.
+
 ### Container Configuration

 Groups can have additional directories mounted via `containerConfig` in `data/registered_groups.json`:
@@ -489,6 +496,17 @@ Provides email capabilities. Requires Google Cloud OAuth setup.

 NanoClaw runs as a single macOS launchd service.

+### Startup Sequence
+
+When NanoClaw starts, it:
+1. **Ensures Apple Container system is running** - Automatically starts it if needed (survives reboots)
+2. Initializes the SQLite database
+3. Loads state (registered groups, sessions, router state)
+4. Connects to WhatsApp
+5. Starts the message polling loop
+6. Starts the scheduler loop
+7. Starts the IPC watcher for container messages
+
 ### Service: com.nanoclaw

 **launchd/com.nanoclaw.plist:**
@@ -601,9 +619,12 @@ chmod 700 groups/
 | Issue | Cause | Solution |
 |-------|-------|----------|
 | No response to messages | Service not running | Check `launchctl list | grep nanoclaw` |
+| "Claude Code process exited with code 1" | Apple Container failed to start | Check logs; NanoClaw auto-starts container system but may fail |
+| "Claude Code process exited with code 1" | Session mount path wrong | Ensure mount is to `/home/node/.claude/` not `/root/.claude/` |
+| Session not continuing | Session ID not saved | Check `data/sessions.json` |
+| Session not continuing | Mount path mismatch | Container user is `node` with HOME=/home/node; sessions must be at `/home/node/.claude/` |
 | "QR code expired" | WhatsApp session expired | Delete store/auth/ and restart |
 | "No groups registered" | Haven't added groups | Use `@Andy add group "Name"` in main |
-| Session not continuing | Session ID not saved | Check `data/sessions.json` |

 ### Log Location

--- a/container/agent-runner/src/index.ts
+++ b/container/agent-runner/src/index.ts
@@ -111,12 +111,13 @@ async function main(): Promise<void> {
    });

  } catch (err) {
-    log(`Agent error: ${err instanceof Error ? err.message : String(err)}`);
+    const errorMessage = err instanceof Error ? err.message : String(err);
+    log(`Agent error: ${errorMessage}`);
    writeOutput({
      status: 'error',
      result: null,
      newSessionId,
-      error: err instanceof Error ? err.message : String(err)
+      error: errorMessage
    });
    process.exit(1);
  }
--- a/src/config.ts
+++ b/src/config.ts
@@ -1,9 +1,14 @@
+import path from 'path';
+
 export const ASSISTANT_NAME = process.env.ASSISTANT_NAME || 'Andy';
 export const POLL_INTERVAL = 2000;
 export const SCHEDULER_POLL_INTERVAL = 60000; // Check for due tasks every minute
-export const STORE_DIR = './store';
-export const GROUPS_DIR = './groups';
-export const DATA_DIR = './data';
+
+// Use absolute paths for container mounts
+const PROJECT_ROOT = process.cwd();
+export const STORE_DIR = path.resolve(PROJECT_ROOT, 'store');
+export const GROUPS_DIR = path.resolve(PROJECT_ROOT, 'groups');
+export const DATA_DIR = path.resolve(PROJECT_ROOT, 'data');
 export const MAIN_GROUP_FOLDER = 'main';

 // Container configuration
--- a/src/container-runner.ts
+++ b/src/container-runner.ts
@@ -80,11 +80,12 @@ function buildVolumeMounts(group: RegisteredGroup, isMain: boolean): VolumeMount
  }

  // Claude sessions directory (for session persistence)
+  // Container runs as 'node' user with HOME=/home/node
  const claudeDir = path.join(homeDir, '.claude');
  if (fs.existsSync(claudeDir)) {
    mounts.push({
      hostPath: claudeDir,
-      containerPath: '/root/.claude',
+      containerPath: '/home/node/.claude',
      readonly: false
    });
  }
@@ -94,7 +95,7 @@ function buildVolumeMounts(group: RegisteredGroup, isMain: boolean): VolumeMount
  if (fs.existsSync(gmailDir)) {
    mounts.push({
      hostPath: gmailDir,
-      containerPath: '/root/.gmail-mcp',
+      containerPath: '/home/node/.gmail-mcp',
      readonly: false
    });
  }
--- a/src/index.ts
+++ b/src/index.ts
@@ -5,7 +5,7 @@ import makeWASocket, {
  WASocket
 } from '@whiskeysockets/baileys';
 import pino from 'pino';
-import { exec } from 'child_process';
+import { exec, execSync } from 'child_process';
 import fs from 'fs';
 import path from 'path';

@@ -376,7 +376,25 @@ async function startMessageLoop(): Promise<void> {
  }
 }

+function ensureContainerSystemRunning(): void {
+  try {
+    // Check if container system is already running
+    execSync('container system status', { stdio: 'pipe' });
+    logger.debug('Apple Container system already running');
+  } catch {
+    // Not running, try to start it
+    logger.info('Starting Apple Container system...');
+    try {
+      execSync('container system start', { stdio: 'pipe', timeout: 30000 });
+      logger.info('Apple Container system started');
+    } catch (err) {
+      logger.error({ err }, 'Failed to start Apple Container system - agents will not work');
+    }
+  }
+}
+
 async function main(): Promise<void> {
+  ensureContainerSystemRunning();
  initDatabase();
  logger.info('Database initialized');
  loadState();