@jaguilar87/gaia 5.0.0-rc.2

package/dist/gaia-ops/tools/scan/tests/test_merge.py

@@ -0,0 +1,269 @@
+"""
+Unit tests for context combining logic (T026).
+
+Tests scanner-owned section replacement, agent-enriched section preservation,
+mixed section sub-key merge, unknown section preservation, v1-to-v2 upgrade,
+and idempotency.
+"""
+
+import copy
+import json
+from pathlib import Path
+from typing import Any, Dict
+
+import pytest
+
+from tools.scan.merge import merge_context
+
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+
+def _section_owners() -> Dict[str, str]:
+    """Return a realistic section_owners map from ScannerRegistry."""
+    return {
+        "project_identity": "stack",
+        "stack": "stack",
+        "git": "git",
+        "infrastructure": "infrastructure",
+        "orchestration": "orchestration",
+        "environment.tools": "tools",
+        "environment.tool_preferences": "tools",
+        "environment.runtimes": "environment",
+        "environment.os": "environment",
+        "environment.env_files": "environment",
+    }
+
+
+# ---------------------------------------------------------------------------
+# Test data helpers
+# ---------------------------------------------------------------------------
+
+
+def _make_existing_context() -> Dict[str, Any]:
+    """Create a realistic existing project-context with scanner + agent data."""
+    return {
+        "metadata": {
+            "version": "2.0",
+            "last_updated": "2026-01-01T00:00:00Z",
+            "project_name": "test-project",
+            "scan_config": {
+                "staleness_hours": 24,
+                "last_scan": "2026-01-01T00:00:00Z",
+                "scanner_version": "0.1.0",
+            },
+        },
+        "project_identity": {
+            "_source": "scanner:stack",
+            "name": "old-name",
+            "type": "application",
+        },
+        "stack": {
+            "_source": "scanner:stack",
+            "languages": [{"name": "python", "manifest": "pyproject.toml", "primary": True}],
+            "frameworks": [],
+            "build_tools": [],
+        },
+        "git": {
+            "_source": "scanner:git",
+            "platform": "github",
+            "remotes": [],
+            "default_branch": "main",
+        },
+        "environment": {
+            "_source": "scanner:environment",
+            "os": {"platform": "linux", "architecture": "x64"},
+            "runtimes": [{"name": "python3", "version": "3.11.0"}],
+            "env_files": [],
+            "tools": [{"name": "git", "path": "/usr/bin/git"}],
+            "tool_preferences": {"file_viewer": "bat"},
+        },
+        "operational_guidelines": {
+            "_source": "agent:developer",
+            "deployment_strategy": "blue-green",
+            "rollback_procedure": "manual",
+        },
+        "my_custom_notes": {
+            "author": "user",
+            "notes": "User-maintained section",
+        },
+    }
+
+
+def _make_scan_results() -> Dict[str, Any]:
+    """Create scan results from a new scan run."""
+    return {
+        "project_identity": {
+            "_source": "scanner:stack",
+            "name": "new-name",
+            "type": "monorepo",
+            "description": "Updated description",
+        },
+        "stack": {
+            "_source": "scanner:stack",
+            "languages": [
+                {"name": "typescript", "manifest": "package.json", "primary": True},
+                {"name": "python", "manifest": "pyproject.toml", "primary": False},
+            ],
+            "frameworks": [{"name": "react", "language": "typescript"}],
+            "build_tools": [{"name": "npm", "detected_by": "lock_file"}],
+        },
+        "git": {
+            "_source": "scanner:git",
+            "platform": "github",
+            "remotes": [{"name": "origin", "url": "git@github.com:o/r.git"}],
+            "default_branch": "main",
+        },
+        "environment": {
+            "_source": "scanner:environment",
+            "os": {"platform": "linux", "architecture": "x64", "wsl": True},
+            "runtimes": [{"name": "python3", "version": "3.12.0"}],
+            "env_files": [{"name": ".env", "path": ".env"}],
+        },
+    }
+
+
+# ---------------------------------------------------------------------------
+# Rule 1: Scanner-owned section fully replaced
+# ---------------------------------------------------------------------------
+
+
+class TestScannerOwnedSectionReplacement:
+    """Test that scanner-owned sections are fully replaced with new data."""
+
+    def test_project_identity_replaced(self) -> None:
+        existing = _make_existing_context()
+        scan = _make_scan_results()
+        result = merge_context(existing, scan, _section_owners())
+        assert result["project_identity"]["name"] == "new-name"
+        assert result["project_identity"]["type"] == "monorepo"
+
+    def test_stack_section_replaced(self) -> None:
+        existing = _make_existing_context()
+        scan = _make_scan_results()
+        result = merge_context(existing, scan, _section_owners())
+        lang_names = [l["name"] for l in result["stack"]["languages"]]
+        assert "typescript" in lang_names
+        assert len(result["stack"]["frameworks"]) == 1
+
+    def test_git_section_replaced(self) -> None:
+        existing = _make_existing_context()
+        scan = _make_scan_results()
+        result = merge_context(existing, scan, _section_owners())
+        assert len(result["git"]["remotes"]) == 1
+
+
+# ---------------------------------------------------------------------------
+# Rule 2: Agent-enriched sections preserved
+# ---------------------------------------------------------------------------
+
+
+class TestAgentEnrichedPreservation:
+    """Test that agent-enriched sections are preserved byte-identical."""
+
+    def test_operational_guidelines_preserved(self) -> None:
+        existing = _make_existing_context()
+        scan = _make_scan_results()
+        result = merge_context(existing, scan, _section_owners())
+        assert result["operational_guidelines"]["deployment_strategy"] == "blue-green"
+        assert result["operational_guidelines"]["rollback_procedure"] == "manual"
+
+
+# ---------------------------------------------------------------------------
+# Rule 4: Mixed section (environment) sub-key merge
+# ---------------------------------------------------------------------------
+
+
+class TestMixedSectionMerge:
+    """Test that mixed sections merge scanner fields and keep agent fields."""
+
+    def test_environment_scanner_fields_refreshed(self) -> None:
+        existing = _make_existing_context()
+        scan = _make_scan_results()
+        result = merge_context(existing, scan, _section_owners())
+        # Scanner-owned sub-keys should be updated
+        assert result["environment"]["os"].get("wsl") is True
+        runtimes = result["environment"]["runtimes"]
+        py = [r for r in runtimes if r["name"] == "python3"][0]
+        assert py["version"] == "3.12.0"
+
+    def test_environment_agent_fields_kept(self) -> None:
+        existing = _make_existing_context()
+        scan = _make_scan_results()
+        result = merge_context(existing, scan, _section_owners())
+        # tools and tool_preferences came from tool scanner (not in this scan)
+        # They should be preserved from existing
+        assert "tools" in result["environment"] or "tool_preferences" in result["environment"]
+
+
+# ---------------------------------------------------------------------------
+# Rule 5: Unknown/user-custom sections preserved
+# ---------------------------------------------------------------------------
+
+
+class TestUserCustomPreservation:
+    """Test that user-custom sections survive combining."""
+
+    def test_custom_section_preserved(self) -> None:
+        existing = _make_existing_context()
+        scan = _make_scan_results()
+        result = merge_context(existing, scan, _section_owners())
+        assert "my_custom_notes" in result
+        assert result["my_custom_notes"]["author"] == "user"
+
+
+# ---------------------------------------------------------------------------
+# v1-to-v2 upgrade
+# ---------------------------------------------------------------------------
+
+
+class TestV1ToV2Upgrade:
+    """Test upgrading from v1 project-context (no scan_config)."""
+
+    def test_v1_context_upgraded(self, sample_project_context_v1: Dict[str, Any]) -> None:
+        scan = _make_scan_results()
+        result = merge_context(sample_project_context_v1, scan, _section_owners())
+        # Should have scan_config after upgrade
+        assert "metadata" in result
+        # Agent-enriched data from v1 should be preserved
+        if "operational_guidelines" in sample_project_context_v1:
+            assert "operational_guidelines" in result
+
+    def test_v1_agent_data_not_lost(self, sample_project_context_v1: Dict[str, Any]) -> None:
+        scan = _make_scan_results()
+        result = merge_context(sample_project_context_v1, scan, _section_owners())
+        # User-custom sections from v1 are preserved as-is (Rule 4).
+        # project_details is no longer produced by the scanner (no backward compat),
+        # but if it existed in the v1 context it is preserved as a user-custom section.
+        if "project_details" in sample_project_context_v1:
+            assert "project_details" in result
+
+
+# ---------------------------------------------------------------------------
+# Idempotency
+# ---------------------------------------------------------------------------
+
+
+class TestIdempotency:
+    """Test that running combine twice produces same result (except timestamps)."""
+
+    def test_idempotent_combine(self) -> None:
+        existing = _make_existing_context()
+        scan = _make_scan_results()
+
+        result1 = merge_context(existing, scan, _section_owners())
+        result2 = merge_context(result1, scan, _section_owners())
+
+        # Strip timestamps for comparison
+        def strip_timestamps(d: Dict) -> Dict:
+            d = copy.deepcopy(d)
+            if "metadata" in d:
+                meta = d["metadata"]
+                meta.pop("last_updated", None)
+                if "scan_config" in meta:
+                    meta["scan_config"].pop("last_scan", None)
+            return d
+
+        assert strip_timestamps(result1) == strip_timestamps(result2)

package/dist/gaia-ops/tools/scan/tests/test_orchestration.py

@@ -0,0 +1,304 @@
+"""
+Unit tests for the Orchestration Scanner (T023).
+
+Tests K8s manifest detection, Helm chart detection, Kustomize detection,
+Flux/ArgoCD detection, service mesh detection, and empty project behavior.
+"""
+
+import os
+import textwrap
+from pathlib import Path
+from typing import Any, Dict
+from unittest.mock import patch
+
+import pytest
+
+from tools.scan.scanners.orchestration import OrchestrationScanner
+
+
+@pytest.fixture
+def scanner() -> OrchestrationScanner:
+    """Create an OrchestrationScanner instance."""
+    return OrchestrationScanner()
+
+
+# ---------------------------------------------------------------------------
+# Scanner basics
+# ---------------------------------------------------------------------------
+
+
+class TestOrchScannerBasics:
+    """Test scanner metadata and basic contract."""
+
+    def test_scanner_name(self, scanner: OrchestrationScanner) -> None:
+        assert scanner.SCANNER_NAME == "orchestration"
+
+    def test_scanner_version(self, scanner: OrchestrationScanner) -> None:
+        assert scanner.SCANNER_VERSION == "1.0.0"
+
+    def test_owned_sections(self, scanner: OrchestrationScanner) -> None:
+        assert scanner.OWNED_SECTIONS == ["orchestration"]
+
+    def test_source_tag(self, scanner: OrchestrationScanner) -> None:
+        assert scanner.source_tag == "scanner:orchestration"
+
+
+# ---------------------------------------------------------------------------
+# Empty project
+# ---------------------------------------------------------------------------
+
+
+class TestEmptyProject:
+    """Test empty project returns empty dict.
+
+    Must mock kubeconfig detection to prevent the host system's
+    ~/.kube/config from being picked up.
+    """
+
+    def test_empty_project_returns_empty_sections(
+        self, scanner: OrchestrationScanner, empty_project: Path
+    ) -> None:
+        with patch.dict(os.environ, {"KUBECONFIG": ""}, clear=False):
+            with patch(
+                "tools.scan.scanners.orchestration.Path.home",
+                return_value=empty_project / "_fake_home",
+            ):
+                result = scanner.scan(empty_project)
+        assert result.sections == {}
+
+    def test_no_orchestration_in_empty(
+        self, scanner: OrchestrationScanner, empty_project: Path
+    ) -> None:
+        with patch.dict(os.environ, {"KUBECONFIG": ""}, clear=False):
+            with patch(
+                "tools.scan.scanners.orchestration.Path.home",
+                return_value=empty_project / "_fake_home",
+            ):
+                result = scanner.scan(empty_project)
+        assert "orchestration" not in result.sections
+
+
+# ---------------------------------------------------------------------------
+# Kubernetes detection
+# ---------------------------------------------------------------------------
+
+
+class TestKubernetesDetection:
+    """Test Kubernetes manifest detection."""
+
+    def test_detect_deployment_kind(
+        self, scanner: OrchestrationScanner, k8s_project: Path
+    ) -> None:
+        result = scanner.scan(k8s_project)
+        orch = result.sections["orchestration"]
+        assert orch["kubernetes"]["detected"] is True
+        assert "Deployment" in orch["kubernetes"]["manifest_patterns"]
+
+    def test_detect_service_kind(
+        self, scanner: OrchestrationScanner, k8s_project: Path
+    ) -> None:
+        result = scanner.scan(k8s_project)
+        orch = result.sections["orchestration"]
+        assert "Service" in orch["kubernetes"]["manifest_patterns"]
+
+    def test_detect_statefulset(
+        self, scanner: OrchestrationScanner, tmp_path: Path
+    ) -> None:
+        manifests = tmp_path / "k8s"
+        manifests.mkdir()
+        (manifests / "statefulset.yaml").write_text(
+            "apiVersion: apps/v1\nkind: StatefulSet\nmetadata:\n  name: db\n"
+        )
+        result = scanner.scan(tmp_path)
+        orch = result.sections["orchestration"]
+        assert orch["kubernetes"]["detected"] is True
+        assert "StatefulSet" in orch["kubernetes"]["manifest_patterns"]
+
+
+# ---------------------------------------------------------------------------
+# Helm detection
+# ---------------------------------------------------------------------------
+
+
+class TestHelmDetection:
+    """Test Helm chart detection."""
+
+    def test_detect_helm_chart(
+        self, scanner: OrchestrationScanner, helm_project: Path
+    ) -> None:
+        result = scanner.scan(helm_project)
+        orch = result.sections["orchestration"]
+        assert orch["helm"]["detected"] is True
+        assert len(orch["helm"]["charts"]) >= 1
+
+    def test_helm_chart_path_recorded(
+        self, scanner: OrchestrationScanner, helm_project: Path
+    ) -> None:
+        result = scanner.scan(helm_project)
+        orch = result.sections["orchestration"]
+        charts = orch["helm"]["charts"]
+        assert any("Chart.yaml" in c for c in charts)
+
+
+# ---------------------------------------------------------------------------
+# Kustomize detection
+# ---------------------------------------------------------------------------
+
+
+class TestKustomizeDetection:
+    """Test Kustomize detection."""
+
+    def test_detect_kustomize(
+        self, scanner: OrchestrationScanner, tmp_path: Path
+    ) -> None:
+        k8s_dir = tmp_path / "base"
+        k8s_dir.mkdir()
+        (k8s_dir / "kustomization.yaml").write_text(
+            "apiVersion: kustomize.config.k8s.io/v1beta1\nkind: Kustomization\n"
+        )
+        result = scanner.scan(tmp_path)
+        orch = result.sections["orchestration"]
+        assert orch["kustomize"]["detected"] is True
+
+    def test_kustomize_files_recorded(
+        self, scanner: OrchestrationScanner, tmp_path: Path
+    ) -> None:
+        k8s_dir = tmp_path / "overlays" / "dev"
+        k8s_dir.mkdir(parents=True)
+        (k8s_dir / "kustomization.yaml").write_text("resources:\n  - ../../base\n")
+        result = scanner.scan(tmp_path)
+        orch = result.sections["orchestration"]
+        assert len(orch["kustomize"]["files"]) >= 1
+
+
+# ---------------------------------------------------------------------------
+# Flux detection
+# ---------------------------------------------------------------------------
+
+
+class TestFluxDetection:
+    """Test Flux GitOps detection."""
+
+    def test_detect_flux_from_api_group(
+        self, scanner: OrchestrationScanner, flux_project: Path
+    ) -> None:
+        result = scanner.scan(flux_project)
+        orch = result.sections["orchestration"]
+        assert orch["gitops"]["tool"] == "flux"
+
+    def test_flux_api_groups_recorded(
+        self, scanner: OrchestrationScanner, flux_project: Path
+    ) -> None:
+        result = scanner.scan(flux_project)
+        orch = result.sections["orchestration"]
+        assert len(orch["gitops"]["api_groups"]) >= 1
+        assert any("toolkit.fluxcd.io" in g for g in orch["gitops"]["api_groups"])
+
+    def test_detect_flux_from_directory_conventions(
+        self, scanner: OrchestrationScanner, tmp_path: Path
+    ) -> None:
+        # Create 2 of 3 Flux convention dirs (clusters + infrastructure)
+        (tmp_path / "clusters").mkdir()
+        (tmp_path / "infrastructure").mkdir()
+        result = scanner.scan(tmp_path)
+        orch = result.sections["orchestration"]
+        assert orch["gitops"]["tool"] == "flux"
+
+
+# ---------------------------------------------------------------------------
+# ArgoCD detection
+# ---------------------------------------------------------------------------
+
+
+class TestArgoCDDetection:
+    """Test ArgoCD detection."""
+
+    def test_detect_argocd_from_api_group(
+        self, scanner: OrchestrationScanner, argocd_project: Path
+    ) -> None:
+        result = scanner.scan(argocd_project)
+        orch = result.sections["orchestration"]
+        assert orch["gitops"]["tool"] == "argocd"
+
+    def test_argocd_api_groups_recorded(
+        self, scanner: OrchestrationScanner, argocd_project: Path
+    ) -> None:
+        result = scanner.scan(argocd_project)
+        orch = result.sections["orchestration"]
+        assert any("argoproj.io" in g for g in orch["gitops"]["api_groups"])
+
+
+# ---------------------------------------------------------------------------
+# Service mesh detection
+# ---------------------------------------------------------------------------
+
+
+class TestServiceMeshDetection:
+    """Test service mesh detection."""
+
+    def test_detect_istio(
+        self, scanner: OrchestrationScanner, istio_project: Path
+    ) -> None:
+        result = scanner.scan(istio_project)
+        orch = result.sections["orchestration"]
+        assert orch["service_mesh"]["tool"] == "istio"
+
+    def test_istio_indicators_recorded(
+        self, scanner: OrchestrationScanner, istio_project: Path
+    ) -> None:
+        result = scanner.scan(istio_project)
+        orch = result.sections["orchestration"]
+        assert len(orch["service_mesh"]["indicators"]) >= 1
+
+    def test_detect_linkerd(
+        self, scanner: OrchestrationScanner, linkerd_project: Path
+    ) -> None:
+        result = scanner.scan(linkerd_project)
+        orch = result.sections["orchestration"]
+        assert orch["service_mesh"]["tool"] == "linkerd"
+
+    def test_detect_consul(
+        self, scanner: OrchestrationScanner, tmp_path: Path
+    ) -> None:
+        manifests = tmp_path / "k8s"
+        manifests.mkdir()
+        (manifests / "deployment.yaml").write_text(
+            textwrap.dedent("""\
+                apiVersion: apps/v1
+                kind: Deployment
+                metadata:
+                  name: test
+                  annotations:
+                    consul.hashicorp.com/connect-inject: "true"
+            """)
+        )
+        result = scanner.scan(tmp_path)
+        orch = result.sections["orchestration"]
+        assert orch["service_mesh"]["tool"] == "consul"
+
+
+# ---------------------------------------------------------------------------
+# ScanResult contract
+# ---------------------------------------------------------------------------
+
+
+class TestOrchResultContract:
+    """Test scan result follows expected contract."""
+
+    def test_source_tag_present(
+        self, scanner: OrchestrationScanner, k8s_project: Path
+    ) -> None:
+        result = scanner.scan(k8s_project)
+        assert result.sections["orchestration"]["_source"] == "scanner:orchestration"
+
+    def test_result_has_duration(
+        self, scanner: OrchestrationScanner, k8s_project: Path
+    ) -> None:
+        result = scanner.scan(k8s_project)
+        assert result.duration_ms >= 0
+
+    def test_result_scanner_name(
+        self, scanner: OrchestrationScanner, k8s_project: Path
+    ) -> None:
+        result = scanner.scan(k8s_project)
+        assert result.scanner == "orchestration"