From db216a459e51acd319c53c5c88b18c72d27447cf Mon Sep 17 00:00:00 2001
From: gavrielc <gabicohen22@yahoo.com>
Date: Fri, 6 Feb 2026 07:10:26 +0200
Subject: [PATCH] fix: proper container lifecycle management to prevent stopped
 container accumulation

- Name containers (nanoclaw-{group}-{timestamp}) for trackability
- Replace SIGKILL timeout with graceful `container stop` so --rm fires
- Add startup sweep to clean up stopped nanoclaw containers from previous runs

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---
 src/container-runner.ts | 55 ++++++++++++++++++++++++++++++++---------
 src/index.ts            | 18 ++++++++++++++
 2 files changed, 62 insertions(+), 11 deletions(-)

diff --git a/src/container-runner.ts b/src/container-runner.ts
index cfcda9e..7c45446 100644
--- a/src/container-runner.ts
+++ b/src/container-runner.ts
@@ -2,7 +2,7 @@
  * Container Runner for NanoClaw
  * Spawns agent execution in Apple Container and handles IPC
  */
-import { spawn } from 'child_process';
+import { exec, spawn } from 'child_process';
 import fs from 'fs';
 import os from 'os';
 import path from 'path';
@@ -162,8 +162,8 @@ function buildVolumeMounts(
   return mounts;
 }
 
-function buildContainerArgs(mounts: VolumeMount[]): string[] {
-  const args: string[] = ['run', '-i', '--rm'];
+function buildContainerArgs(mounts: VolumeMount[], containerName: string): string[] {
+  const args: string[] = ['run', '-i', '--rm', '--name', containerName];
 
   // Apple Container: --mount for readonly, -v for read-write
   for (const mount of mounts) {
@@ -192,11 +192,14 @@ export async function runContainerAgent(
   fs.mkdirSync(groupDir, { recursive: true });
 
   const mounts = buildVolumeMounts(group, input.isMain);
-  const containerArgs = buildContainerArgs(mounts);
+  const safeName = group.folder.replace(/[^a-zA-Z0-9-]/g, '-');
+  const containerName = `nanoclaw-${safeName}-${Date.now()}`;
+  const containerArgs = buildContainerArgs(mounts, containerName);
 
   logger.debug(
     {
       group: group.name,
+      containerName,
       mounts: mounts.map(
         (m) =>
           `${m.hostPath} -> ${m.containerPath}${m.readonly ? ' (ro)' : ''}`,
@@ -209,6 +212,7 @@ export async function runContainerAgent(
   logger.info(
     {
       group: group.name,
+      containerName,
       mountCount: mounts.length,
       isMain: input.isMain,
     },
@@ -267,13 +271,17 @@ export async function runContainerAgent(
       }
     });
 
+    let timedOut = false;
+
     const timeout = setTimeout(() => {
-      logger.error({ group: group.name }, 'Container timeout, killing');
-      container.kill('SIGKILL');
-      resolve({
-        status: 'error',
-        result: null,
-        error: `Container timed out after ${CONTAINER_TIMEOUT}ms`,
+      timedOut = true;
+      logger.error({ group: group.name, containerName }, 'Container timeout, stopping gracefully');
+      // Graceful stop: sends SIGTERM, waits, then SIGKILL — lets --rm fire
+      exec(`container stop ${containerName}`, { timeout: 15000 }, (err) => {
+        if (err) {
+          logger.warn({ group: group.name, containerName, err }, 'Graceful stop failed, force killing');
+          container.kill('SIGKILL');
+        }
       });
     }, group.containerConfig?.timeout || CONTAINER_TIMEOUT);
 
@@ -281,6 +289,31 @@ export async function runContainerAgent(
       clearTimeout(timeout);
       const duration = Date.now() - startTime;
 
+      if (timedOut) {
+        const ts = new Date().toISOString().replace(/[:.]/g, '-');
+        const timeoutLog = path.join(logsDir, `container-${ts}.log`);
+        fs.writeFileSync(timeoutLog, [
+          `=== Container Run Log (TIMEOUT) ===`,
+          `Timestamp: ${new Date().toISOString()}`,
+          `Group: ${group.name}`,
+          `Container: ${containerName}`,
+          `Duration: ${duration}ms`,
+          `Exit Code: ${code}`,
+        ].join('\n'));
+
+        logger.error(
+          { group: group.name, containerName, duration, code },
+          'Container timed out',
+        );
+
+        resolve({
+          status: 'error',
+          result: null,
+          error: `Container timed out after ${group.containerConfig?.timeout || CONTAINER_TIMEOUT}ms`,
+        });
+        return;
+      }
+
       const timestamp = new Date().toISOString().replace(/[:.]/g, '-');
       const logFile = path.join(logsDir, `container-${timestamp}.log`);
       const isVerbose =
@@ -414,7 +447,7 @@ export async function runContainerAgent(
 
     container.on('error', (err) => {
       clearTimeout(timeout);
-      logger.error({ group: group.name, error: err }, 'Container spawn error');
+      logger.error({ group: group.name, containerName, error: err }, 'Container spawn error');
       resolve({
         status: 'error',
         result: null,
diff --git a/src/index.ts b/src/index.ts
index 7a1f516..e137e58 100644
--- a/src/index.ts
+++ b/src/index.ts
@@ -832,6 +832,24 @@ function ensureContainerSystemRunning(): void {
       throw new Error('Apple Container system is required but failed to start');
     }
   }
+
+  // Clean up stopped NanoClaw containers from previous runs
+  try {
+    const output = execSync('container ls -a --format {{.Names}}', {
+      stdio: ['pipe', 'pipe', 'pipe'],
+      encoding: 'utf-8',
+    });
+    const stale = output
+      .split('\n')
+      .map((n) => n.trim())
+      .filter((n) => n.startsWith('nanoclaw-'));
+    if (stale.length > 0) {
+      execSync(`container rm ${stale.join(' ')}`, { stdio: 'pipe' });
+      logger.info({ count: stale.length }, 'Cleaned up stopped containers');
+    }
+  } catch {
+    // No stopped containers or ls/rm not supported
+  }
 }
 
 async function main(): Promise<void> {