fix: add detailed SSH permission fix logging for debugging

- Replace apply_ssh_permissions internals with _exec_and_log for full visibility
- Log every docker exec command, stdout, and stderr at DEBUG level
- After chown/chmod, run ls -la and stat to verify final state
- Log verified state at INFO level so users can see exactly what happened
- Update tests to mock subprocess.run instead of _run_in_container

Quality gates: pytest 236 passed (6 pre-existing), tsc --noEmit clean

apps/api/src/api/tool_instances.py

@@ -1656,7 +1656,9 @@ async def start_instance(
             container_user = (
                 "root"
                 if home_dir == "/root"
-                else home_dir[6:] if home_dir.startswith("/home/") else "root"
+                else home_dir[6:]
+                if home_dir.startswith("/home/")
+                else "root"
             )
             ssh_target = os.path.join(home_dir, ".ssh")
             logger.debug(

apps/api/src/services/permission_fixer.py

@@ -104,6 +104,44 @@ def apply_mount_permissions(
     return results
 
 
+def _exec_and_log(
+    container_id: str,
+    command: list[str],
+    timeout: int,
+    description: str,
+) -> str:
+    """Run a docker exec command and log stdout/stderr for debugging."""
+    cmd = ["docker", "exec", "--user", "root", container_id] + command
+    logger.debug("[SSH-fix] %s: %s", description, " ".join(cmd))
+
+    try:
+        result = subprocess.run(
+            cmd,
+            capture_output=True,
+            text=True,
+            timeout=timeout,
+        )
+    except subprocess.TimeoutExpired:
+        raise PermissionFixError(
+            f"Command timed out after {timeout}s: {' '.join(command)}"
+        )
+    except FileNotFoundError:
+        raise PermissionFixError(f"Docker command not found: {' '.join(command)}")
+
+    stdout = result.stdout.strip()
+    stderr = result.stderr.strip()
+    if stdout:
+        logger.debug("[SSH-fix] %s stdout: %s", description, stdout)
+    if stderr:
+        logger.debug("[SSH-fix] %s stderr: %s", description, stderr)
+
+    if result.returncode != 0:
+        raise PermissionFixError(
+            f"Command failed (rc={result.returncode}): {stderr or '(no stderr)'}"
+        )
+    return stdout
+
+
 def apply_ssh_permissions(
     container_id: str,
     ssh_target: str,
@@ -127,20 +165,24 @@ def apply_ssh_permissions(
     """
     result: dict[str, Any] = {"success": True, "error": None}
     try:
-        # Ensure directory is owned by the container user
+        # 1. Ensure directory is owned by the container user
-        _run_in_container(
+        _exec_and_log(
             container_id,
             ["chown", "-R", f"{container_user}:{container_user}", ssh_target],
             timeout,
+            "chown",
         )
-        # Set directory permissions
+
-        _run_in_container(
+        # 2. Set directory permissions
+        _exec_and_log(
             container_id,
             ["chmod", "700", ssh_target],
             timeout,
+            "chmod-dir",
         )
-        # Set private key permissions
+
-        _run_in_container(
+        # 3. Set private key permissions (id_ed25519, id_rsa, etc.)
+        _exec_and_log(
             container_id,
             [
                 "sh",
@@ -148,12 +190,38 @@ def apply_ssh_permissions(
                 f"find {ssh_target} -name 'id_*' -type f -exec chmod 600 {{}} +",
             ],
             timeout,
+            "chmod-keys",
         )
-        logger.debug(
+
-            "Applied SSH permissions for user %s on %s in container %s",
+        # 4. Verify final state
+        ls_output = _exec_and_log(
+            container_id,
+            ["ls", "-la", ssh_target],
+            timeout,
+            "verify-ls",
+        )
+        stat_output = _exec_and_log(
+            container_id,
+            ["stat", "-c", "%U:%G %a %n", ssh_target],
+            timeout,
+            "verify-stat-dir",
+        )
+        key_stat = _exec_and_log(
+            container_id,
+            ["sh", "-c", f"stat -c '%U:%G %a %n' {ssh_target}/id_* 2>/dev/null || echo 'no id_* files found'"],
+            timeout,
+            "verify-stat-keys",
+        )
+
+        logger.info(
+            "SSH permissions fixed for container %s (user=%s, target=%s). "
+            "ls:\n%s\nstat-dir: %s\nstat-keys: %s",
+            container_id,
             container_user,
             ssh_target,
-            container_id,
+            ls_output,
+            stat_output,
+            key_stat,
         )
     except PermissionFixError as exc:
         result["success"] = False

apps/api/tests/unit/test_permission_fixer.py

@@ -136,32 +136,35 @@ class TestRunInContainer:
 class TestApplySshPermissions:
     """Tests for apply_ssh_permissions."""
 
-    @patch("src.services.permission_fixer._run_in_container")
+    @patch("subprocess.run")
     def test_applies_chown_chmod_and_file_mode(self, mock_run) -> None:
+        mock_run.return_value = MagicMock(returncode=0, stdout="", stderr="")
         result = apply_ssh_permissions("abc123", "/home/user/.ssh", "user")
 
         assert result["success"] is True
-        assert mock_run.call_count == 3
+        # 3 fix commands + 3 verification commands
-        chown_call = mock_run.call_args_list[0]
+        assert mock_run.call_count == 6
-        chmod_call = mock_run.call_args_list[1]
+        chown_cmd = mock_run.call_args_list[0][0][0]
-        file_mode_call = mock_run.call_args_list[2]
+        chmod_cmd = mock_run.call_args_list[1][0][0]
+        file_mode_cmd = mock_run.call_args_list[2][0][0]
 
-        assert chown_call[0][1] == ["chown", "-R", "user:user", "/home/user/.ssh"]
+        assert chown_cmd == ["docker", "exec", "--user", "root", "abc123", "chown", "-R", "user:user", "/home/user/.ssh"]
-        assert chmod_call[0][1] == ["chmod", "700", "/home/user/.ssh"]
+        assert chmod_cmd == ["docker", "exec", "--user", "root", "abc123", "chmod", "700", "/home/user/.ssh"]
-        assert file_mode_call[0][1][0] == "sh"
+        assert file_mode_cmd[0] == "docker"
-        assert "find /home/user/.ssh -name 'id_*' -type f -exec chmod 600" in file_mode_call[0][1][2]
+        assert "find /home/user/.ssh -name 'id_*' -type f -exec chmod 600" in file_mode_cmd[-1]
 
-    @patch("src.services.permission_fixer._run_in_container")
+    @patch("subprocess.run")
     def test_uses_root_user(self, mock_run) -> None:
+        mock_run.return_value = MagicMock(returncode=0, stdout="", stderr="")
         result = apply_ssh_permissions("abc123", "/root/.ssh", "root")
 
         assert result["success"] is True
-        chown_call = mock_run.call_args_list[0]
+        chown_cmd = mock_run.call_args_list[0][0][0]
-        assert chown_call[0][1] == ["chown", "-R", "root:root", "/root/.ssh"]
+        assert chown_cmd == ["docker", "exec", "--user", "root", "abc123", "chown", "-R", "root:root", "/root/.ssh"]
 
-    @patch("src.services.permission_fixer._run_in_container")
+    @patch("subprocess.run")
     def test_reports_failure(self, mock_run) -> None:
-        mock_run.side_effect = PermissionFixError("chown failed")
+        mock_run.return_value = MagicMock(returncode=1, stdout="", stderr="chown failed")
 
         result = apply_ssh_permissions("abc123", "/home/user/.ssh", "user")