fix: set SSH key ownership to container user with mode 600

- Mount SSH keys as bind (not ro) so docker exec --user root can chown - Add apply_ssh_permissions() to permission_fixer.py - Call apply_ssh_permissions() after container start for all instance types - Derive container user from home_dir (/root → root, /home/user → user) - Tests: apply_ssh_permissions unit tests + start_instance integration tests Quality gates: pytest 236 passed (6 pre-existing failures), tsc --noEmit clean
2026-05-29 14:04:52 +02:00
parent ceaed9af66
commit 03d22c4d06
4 changed files with 374 additions and 3 deletions
@@ -75,7 +75,7 @@ from src.services.manifest_compiler import (
    merge_with_config,
    resolve_base,
 )
-from src.services.permission_fixer import apply_mount_permissions
+from src.services.permission_fixer import apply_mount_permissions, apply_ssh_permissions
 from src.services.readiness_probe import execute_probe
 from src.services.ssh_keys import cleanup_ssh_key_files, prepare_ssh_key_files

@@ -1415,7 +1415,7 @@ async def start_instance(
                        {
                            "source": ssh_dir,
                            "target": ssh_target,
-                            "type": "ro",
+                            "type": "bind",
                        }
                    )
                    logger.debug(
@@ -1493,7 +1493,7 @@ async def start_instance(
                            {
                                "source": ssh_dir,
                                "target": "/root/.ssh",
-                                "type": "ro",
+                                "type": "bind",
                            }
                        )
                        logger.debug(
@@ -1651,6 +1651,32 @@ async def start_instance(
                            result["error"],
                        )

+        # Fix SSH key ownership/permissions inside the container
+        if instance.ssh_key_ids and instance.container_id:
+            container_user = (
+                "root"
+                if home_dir == "/root"
+                else home_dir[6:] if home_dir.startswith("/home/") else "root"
+            )
+            ssh_target = os.path.join(home_dir, ".ssh")
+            logger.debug(
+                "Applying SSH permissions for user %s on %s in instance %s",
+                container_user,
+                ssh_target,
+                instance.id,
+            )
+            ssh_perm_result = apply_ssh_permissions(
+                instance.container_id,
+                ssh_target,
+                container_user,
+            )
+            if not ssh_perm_result["success"]:
+                logger.warning(
+                    "SSH permission fix failed for instance %s: %s",
+                    instance.id,
+                    ssh_perm_result["error"],
+                )
+
    # Execute readiness probe if configured
    tool_type = await session.get(ToolType, instance.tool_type_id)
    if tool_type and instance.container_id:
@@ -104,6 +104,69 @@ def apply_mount_permissions(
    return results


+def apply_ssh_permissions(
+    container_id: str,
+    ssh_target: str,
+    container_user: str,
+    timeout: int = 10,
+) -> dict[str, Any]:
+    """Fix SSH directory ownership and permissions in a running container.
+
+    Runs chown and chmod on the ~/.ssh directory so the container user
+    can use the keys (SSH requires the private key to be owned by the
+    user with mode 600).
+
+    Args:
+        container_id: Docker container ID or name.
+        ssh_target: Absolute path to the .ssh directory inside the container.
+        container_user: The container user that should own the keys.
+        timeout: Max seconds per docker exec command.
+
+    Returns:
+        Result dict with keys: success, error.
+    """
+    result: dict[str, Any] = {"success": True, "error": None}
+    try:
+        # Ensure directory is owned by the container user
+        _run_in_container(
+            container_id,
+            ["chown", "-R", f"{container_user}:{container_user}", ssh_target],
+            timeout,
+        )
+        # Set directory permissions
+        _run_in_container(
+            container_id,
+            ["chmod", "700", ssh_target],
+            timeout,
+        )
+        # Set private key permissions
+        _run_in_container(
+            container_id,
+            [
+                "sh",
+                "-c",
+                f"find {ssh_target} -name 'id_*' -type f -exec chmod 600 {{}} +",
+            ],
+            timeout,
+        )
+        logger.debug(
+            "Applied SSH permissions for user %s on %s in container %s",
+            container_user,
+            ssh_target,
+            container_id,
+        )
+    except PermissionFixError as exc:
+        result["success"] = False
+        result["error"] = str(exc)
+        logger.warning(
+            "SSH permission fix failed for container %s (target=%s): %s",
+            container_id,
+            ssh_target,
+            exc,
+        )
+    return result
+
+
 class PermissionFixError(Exception):
    """Raised when a permission fix command fails."""

@@ -7,6 +7,7 @@ import pytest
 from src.services.permission_fixer import (
    PermissionFixError,
    apply_mount_permissions,
+    apply_ssh_permissions,
    check_root_user_available,
    _run_in_container,
 )
@@ -132,6 +133,42 @@ class TestRunInContainer:
            _run_in_container("abc123", ["chown", "x"], 10)


+class TestApplySshPermissions:
+    """Tests for apply_ssh_permissions."""
+
+    @patch("src.services.permission_fixer._run_in_container")
+    def test_applies_chown_chmod_and_file_mode(self, mock_run) -> None:
+        result = apply_ssh_permissions("abc123", "/home/user/.ssh", "user")
+
+        assert result["success"] is True
+        assert mock_run.call_count == 3
+        chown_call = mock_run.call_args_list[0]
+        chmod_call = mock_run.call_args_list[1]
+        file_mode_call = mock_run.call_args_list[2]
+
+        assert chown_call[0][1] == ["chown", "-R", "user:user", "/home/user/.ssh"]
+        assert chmod_call[0][1] == ["chmod", "700", "/home/user/.ssh"]
+        assert file_mode_call[0][1][0] == "sh"
+        assert "find /home/user/.ssh -name 'id_*' -type f -exec chmod 600" in file_mode_call[0][1][2]
+
+    @patch("src.services.permission_fixer._run_in_container")
+    def test_uses_root_user(self, mock_run) -> None:
+        result = apply_ssh_permissions("abc123", "/root/.ssh", "root")
+
+        assert result["success"] is True
+        chown_call = mock_run.call_args_list[0]
+        assert chown_call[0][1] == ["chown", "-R", "root:root", "/root/.ssh"]
+
+    @patch("src.services.permission_fixer._run_in_container")
+    def test_reports_failure(self, mock_run) -> None:
+        mock_run.side_effect = PermissionFixError("chown failed")
+
+        result = apply_ssh_permissions("abc123", "/home/user/.ssh", "user")
+
+        assert result["success"] is False
+        assert "chown failed" in result["error"]
+
+
 class TestCheckRootUserAvailable:
    """Tests for check_root_user_available."""

@@ -701,6 +701,251 @@ class TestStartInstanceLegacyFallback:
        mock_execute_compose.assert_called_once()


+class TestStartInstanceSshPermissions:
+    """SSH key mounts trigger permission fixes after container starts."""
+
+    @patch("src.api.tool_instances.write_compose_file")
+    @patch("src.api.tool_instances.apply_ssh_permissions")
+    @patch("src.api.tool_instances.wait_for_container_running")
+    @patch("src.api.tool_instances.execute_compose_command")
+    @patch("src.api.tool_instances.get_container_id")
+    @patch("src.api.tool_instances.get_container_name")
+    @patch("src.api.tool_instances.connect_container_to_network")
+    @patch("src.api.tool_instances._sanitize_compose_file")
+    @patch("src.api.tool_instances._get_user")
+    @patch("src.api.tool_instances._get_owned_project")
+    async def test_manifest_instance_applies_ssh_permissions(
+        self,
+        mock_get_project,
+        mock_get_user,
+        mock_sanitize,
+        mock_connect_network,
+        mock_get_container_name,
+        mock_get_container_id,
+        mock_execute_compose,
+        mock_wait_container,
+        mock_apply_ssh,
+        mock_write_compose,
+        mock_session,
+        fake_user_id,
+        fake_project_id,
+        fake_repo_id,
+        fake_instance_id,
+        fake_tool_type_id,
+    ) -> None:
+        """Manifest instance with SSH keys calls apply_ssh_permissions."""
+        from src.models.tool_definition_manifest import ToolDefinitionManifest
+
+        manifest_id = uuid.uuid4()
+        ssh_key_id = str(uuid.uuid4())
+
+        mock_get_user.return_value = AsyncMock()
+        mock_get_project.return_value = AsyncMock()
+        mock_execute_compose.return_value = (0, "started", "")
+        mock_get_container_id.return_value = "abc123"
+        mock_get_container_name.return_value = "test-container"
+        mock_connect_network.return_value = True
+        mock_wait_container.return_value = {
+            "success": True,
+            "status": "running",
+            "waited_seconds": 0.5,
+        }
+        mock_apply_ssh.return_value = {"success": True, "error": None}
+
+        instance = ToolInstance(
+            id=fake_instance_id,
+            name="manifest-instance",
+            repository_id=fake_repo_id,
+            tool_type_id=fake_tool_type_id,
+            compose_path="/data/instances/manifest-instance/docker-compose.yml",
+            status="stopped",
+            clone_mode="mount",
+            ssh_key_ids=[ssh_key_id],
+            created_at=datetime.now(),
+            updated_at=datetime.now(),
+        )
+        tool_type = ToolType(
+            id=fake_tool_type_id,
+            name="manifest-tool",
+            display_name="Manifest Tool",
+            default_port=8080,
+            definition_type="manifest",
+            manifest_id=manifest_id,
+            dockerfile_template=None,
+            compose_template=None,
+        )
+        repo = GitRepository(
+            id=fake_repo_id,
+            project_id=fake_project_id,
+            name="test-repo",
+            path="/data/repos/test-repo",
+            remote_url=None,
+            ssh_key_id=None,
+        )
+        manifest_def = ToolDefinitionManifest(
+            id=manifest_id,
+            name="test-manifest",
+            display_name="Test Manifest",
+            interface_type="web",
+            manifest={"user": {"name": "user", "uid": 1001, "gid": 1001}},
+        )
+        ssh_key = SSHKey(
+            id=uuid.UUID(ssh_key_id),
+            user_id=fake_user_id,
+            name="test-key",
+            public_key="ssh-ed25519 AAA test@test",
+            private_key_encrypted="enc",
+        )
+
+        async def _get(model, pk):
+            if model is ToolInstance and pk == fake_instance_id:
+                return instance
+            if model is ToolType and pk == fake_tool_type_id:
+                return tool_type
+            if model is GitRepository and pk == fake_repo_id:
+                return repo
+            if model is User and pk == fake_user_id:
+                return User(id=fake_user_id, email="test@example.com")
+            if model is ToolDefinitionManifest and pk == manifest_id:
+                return manifest_def
+            if model is SSHKey and pk == uuid.UUID(ssh_key_id):
+                return ssh_key
+            return None
+
+        mock_session.get.side_effect = _get
+
+        with patch("os.path.exists", return_value=True):
+            with patch(
+                "src.api.tool_instances._prepare_manifest_instance"
+            ) as mock_prepare:
+                mock_prepare.return_value = (
+                    "headquarter/test:latest",
+                    "services:\n  app:\n    image: test",
+                    {"name": "test-manifest", "user": {"name": "user"}},
+                    "/home/user",
+                )
+                result = await start_instance(
+                    project_id=fake_project_id,
+                    repo_id=fake_repo_id,
+                    instance_id=fake_instance_id,
+                    data=None,
+                    user_id=fake_user_id,
+                    session=mock_session,
+                )
+
+        assert result["status"] == "running"
+        mock_apply_ssh.assert_called_once_with("abc123", "/home/user/.ssh", "user")
+
+    @patch("src.api.tool_instances.apply_ssh_permissions")
+    @patch("src.api.tool_instances.wait_for_container_running")
+    @patch("src.api.tool_instances.execute_compose_command")
+    @patch("src.api.tool_instances.get_container_id")
+    @patch("src.api.tool_instances.get_container_name")
+    @patch("src.api.tool_instances.connect_container_to_network")
+    @patch("src.api.tool_instances._sanitize_compose_file")
+    @patch("src.api.tool_instances._get_user")
+    @patch("src.api.tool_instances._get_owned_project")
+    async def test_legacy_instance_applies_ssh_permissions(
+        self,
+        mock_get_project,
+        mock_get_user,
+        mock_sanitize,
+        mock_connect_network,
+        mock_get_container_name,
+        mock_get_container_id,
+        mock_execute_compose,
+        mock_wait_container,
+        mock_apply_ssh,
+        mock_session,
+        fake_user_id,
+        fake_project_id,
+        fake_repo_id,
+        fake_instance_id,
+        fake_tool_type_id,
+    ) -> None:
+        """Legacy instance with SSH keys calls apply_ssh_permissions."""
+        ssh_key_id = str(uuid.uuid4())
+
+        mock_get_user.return_value = AsyncMock()
+        mock_get_project.return_value = AsyncMock()
+        mock_execute_compose.return_value = (0, "started", "")
+        mock_get_container_id.return_value = "abc123"
+        mock_get_container_name.return_value = "test-container"
+        mock_connect_network.return_value = True
+        mock_wait_container.return_value = {
+            "success": True,
+            "status": "running",
+            "waited_seconds": 0.5,
+        }
+        mock_apply_ssh.return_value = {"success": True, "error": None}
+
+        instance = ToolInstance(
+            id=fake_instance_id,
+            name="legacy-instance",
+            repository_id=fake_repo_id,
+            tool_type_id=fake_tool_type_id,
+            compose_path="/data/instances/legacy-instance/docker-compose.yml",
+            status="stopped",
+            clone_mode="mount",
+            ssh_key_ids=[ssh_key_id],
+            created_at=datetime.now(),
+            updated_at=datetime.now(),
+        )
+        tool_type = ToolType(
+            id=fake_tool_type_id,
+            name="legacy-tool",
+            display_name="Legacy Tool",
+            default_port=8080,
+            definition_type="legacy",
+            manifest_id=None,
+            dockerfile_template=None,
+            compose_template="services:\n  app:\n    image: nginx",
+        )
+        repo = GitRepository(
+            id=fake_repo_id,
+            project_id=fake_project_id,
+            name="test-repo",
+            path="/data/repos/test-repo",
+            remote_url=None,
+            ssh_key_id=None,
+        )
+        ssh_key = SSHKey(
+            id=uuid.UUID(ssh_key_id),
+            user_id=fake_user_id,
+            name="test-key",
+            public_key="ssh-ed25519 AAA test@test",
+            private_key_encrypted="enc",
+        )
+
+        async def _get(model, pk):
+            if model is ToolInstance and pk == fake_instance_id:
+                return instance
+            if model is ToolType and pk == fake_tool_type_id:
+                return tool_type
+            if model is GitRepository and pk == fake_repo_id:
+                return repo
+            if model is User and pk == fake_user_id:
+                return User(id=fake_user_id, email="test@example.com")
+            if model is SSHKey and pk == uuid.UUID(ssh_key_id):
+                return ssh_key
+            return None
+
+        mock_session.get.side_effect = _get
+
+        with patch("os.path.exists", return_value=True):
+            result = await start_instance(
+                project_id=fake_project_id,
+                repo_id=fake_repo_id,
+                instance_id=fake_instance_id,
+                data=None,
+                user_id=fake_user_id,
+                session=mock_session,
+            )
+
+        assert result["status"] == "running"
+        mock_apply_ssh.assert_called_once_with("abc123", "/root/.ssh", "root")
+
+
 class TestStartInstanceManifestBranch:
    """Manifest branch is taken ONLY when definition_type == 'manifest'."""