@pennyfarthing/core 11.3.2 → 11.3.4

package/pennyfarthing-dist/pf/tests/test_common.py

@@ -0,0 +1,185 @@
+"""Tests for common/ shared utilities package.
+
+Story 63-9: Reorganize pf into fan-out CLI pattern.
+
+These tests verify the common/ package provides shared utilities
+that work correctly when imported from the new location.
+"""
+
+import io
+import os
+import sys
+from pathlib import Path
+from unittest.mock import patch
+
+import pytest
+
+
+class TestOutputModule:
+    """Tests for common/output.py module."""
+
+    def test_success_prints_green_prefix(self) -> None:
+        """success() should print with [OK] prefix."""
+        from pf.common import output
+
+        buffer = io.StringIO()
+        # Force color support for testing
+        with patch.object(output, "_supports_color", return_value=True):
+            output.success("Test message", file=buffer)
+
+        result = buffer.getvalue()
+        assert "[OK]" in result or "\x1b[32m" in result  # Green or prefix
+        assert "Test message" in result
+
+    def test_info_prints_blue_prefix(self) -> None:
+        """info() should print with [INFO] prefix."""
+        from pf.common import output
+
+        buffer = io.StringIO()
+        output.info("Info message", file=buffer)
+
+        result = buffer.getvalue()
+        assert "INFO" in result or "Info message" in result
+
+    def test_warn_prints_yellow_prefix(self) -> None:
+        """warn() should print with [WARN] prefix."""
+        from pf.common import output
+
+        buffer = io.StringIO()
+        output.warn("Warning message", file=buffer)
+
+        result = buffer.getvalue()
+        assert "WARN" in result or "Warning message" in result
+
+    def test_error_prints_red_prefix(self) -> None:
+        """error() should print with [ERROR] prefix."""
+        from pf.common import output
+
+        buffer = io.StringIO()
+        output.error("Error message", file=buffer)
+
+        result = buffer.getvalue()
+        assert "ERROR" in result or "Error message" in result
+
+    def test_no_color_env_disables_colors(self) -> None:
+        """NO_COLOR environment variable should disable colors."""
+        from pf.common import output
+
+        with patch.dict(os.environ, {"NO_COLOR": "1"}):
+            buffer = io.StringIO()
+            output.success("Test", file=buffer)
+            result = buffer.getvalue()
+            # Should not contain ANSI escape codes
+            assert "\x1b[" not in result
+
+    def test_force_color_env_enables_colors(self) -> None:
+        """FORCE_COLOR environment variable should enable colors."""
+        from pf.common import output
+
+        with patch.dict(os.environ, {"FORCE_COLOR": "1"}, clear=False):
+            # Remove NO_COLOR if present
+            with patch.dict(os.environ, {"NO_COLOR": ""}, clear=False):
+                assert output._supports_color(sys.stderr) is True
+
+    def test_header_prints_decorated_line(self) -> None:
+        """header() should print decorated header."""
+        from pf.common import output
+
+        buffer = io.StringIO()
+        output.header("Test Header", char="=", width=40, file=buffer)
+
+        result = buffer.getvalue()
+        assert "Test Header" in result
+        assert "=" * 40 in result
+
+    def test_divider_prints_line(self) -> None:
+        """divider() should print a line."""
+        from pf.common import output
+
+        buffer = io.StringIO()
+        output.divider(char="-", width=20, file=buffer)
+
+        result = buffer.getvalue()
+        assert "-" * 20 in result
+
+
+class TestConfigModule:
+    """Tests for common/config.py module."""
+
+    def test_get_project_root_finds_pennyfarthing_dir(self) -> None:
+        """get_project_root() should find .pennyfarthing directory."""
+        from pf.common import config
+
+        # This test assumes we're running from within the pennyfarthing project
+        root = config.get_project_root()
+        assert root is not None
+        assert (root / ".pennyfarthing").is_dir()
+
+    def test_get_project_root_raises_if_not_found(self) -> None:
+        """get_project_root() should raise if no .pennyfarthing found."""
+        from pf.common import config
+
+        # Clear env vars that bypass the directory walk
+        env_overrides = {"PROJECT_ROOT": "", "CLAUDE_PROJECT_DIR": ""}
+        with patch.dict(os.environ, env_overrides, clear=False):
+            # Remove keys entirely if they were set
+            os.environ.pop("PROJECT_ROOT", None)
+            os.environ.pop("CLAUDE_PROJECT_DIR", None)
+            # Start from root filesystem where there's no .pennyfarthing
+            with pytest.raises(FileNotFoundError):
+                config.get_project_root(start_dir=Path("/"))
+
+    def test_load_yaml_config_returns_dict(self) -> None:
+        """load_yaml_config() should return parsed YAML as dict."""
+        from pf.common import config
+
+        # Test with existing sprint file
+        root = config.get_project_root()
+        sprint_path = root / "sprint" / "current-sprint.yaml"
+
+        if sprint_path.exists():
+            result = config.load_yaml_config(sprint_path)
+            assert isinstance(result, dict)
+
+    def test_load_yaml_config_returns_none_if_missing(self) -> None:
+        """load_yaml_config() should return None for missing files."""
+        from pf.common import config
+
+        result = config.load_yaml_config(Path("/nonexistent/file.yaml"))
+        assert result is None
+
+    def test_find_project_root_alias(self) -> None:
+        """find_project_root should be an alias for get_project_root."""
+        from pf.common import config
+
+        assert config.find_project_root == config.get_project_root
+
+    def test_load_pennyfarthing_config_returns_dict(self) -> None:
+        """load_pennyfarthing_config() should return config or empty dict."""
+        from pf.common import config
+
+        result = config.load_pennyfarthing_config()
+        assert isinstance(result, dict)
+
+
+class TestColorsClass:
+    """Tests for Colors class with ANSI codes."""
+
+    def test_colors_has_expected_constants(self) -> None:
+        """Colors class should have standard ANSI color codes."""
+        from pf.common.output import Colors
+
+        assert hasattr(Colors, "RED")
+        assert hasattr(Colors, "GREEN")
+        assert hasattr(Colors, "YELLOW")
+        assert hasattr(Colors, "BLUE")
+        assert hasattr(Colors, "RESET")
+        assert hasattr(Colors, "BOLD")
+        assert hasattr(Colors, "DIM")
+
+    def test_colors_are_ansi_escape_codes(self) -> None:
+        """Color constants should be ANSI escape sequences."""
+        from pf.common.output import Colors
+
+        assert Colors.RED.startswith("\x1b[")
+        assert Colors.RESET == "\x1b[0m"

package/pennyfarthing-dist/pf/tests/test_confidence_sm_evaluation.py

@@ -0,0 +1,253 @@
+"""Tests for SM confidence gate evaluation results — Story 90-3.
+
+Epic: 90 (Confidence Circuit Breaker via Gate)
+Story: 90-3 — Evaluate and document results
+
+Tests the evaluation document that assesses the SM confidence gate's
+effectiveness after deployment. The gate (confidence-sm.md) was shipped
+in story 90-2. This story evaluates trigger frequency, wrong-approach
+reduction, user experience, and makes a rollout recommendation.
+
+Acceptance Criteria:
+- [AC1] Evaluate trigger frequency after 1 sprint
+- [AC2] Document whether it reduced wrong-approach incidents
+- [AC3] Assess if the gate was annoying (user overrode or dismissed)
+- [AC4] Document findings in a results file
+- [AC5] Decide on rollout recommendation to other agents
+"""
+
+from __future__ import annotations
+
+import re
+from pathlib import Path
+
+import pytest
+
+# ---------------------------------------------------------------------------
+# Path resolution
+# ---------------------------------------------------------------------------
+
+_THIS_DIR = Path(__file__).resolve().parent
+_SCRIPTS_DIR = _THIS_DIR.parent  # pf/
+_FRAMEWORK_ROOT = _SCRIPTS_DIR.parent  # pennyfarthing/
+_EVAL_FILE = (
+    _FRAMEWORK_ROOT
+    / "pennyfarthing-dist"
+    / "gates"
+    / "evaluations"
+    / "confidence-sm.md"
+)
+
+# ---------------------------------------------------------------------------
+# Fixtures
+# ---------------------------------------------------------------------------
+
+
+@pytest.fixture
+def eval_path() -> Path:
+    """Return the expected path to the evaluation results file."""
+    return _EVAL_FILE
+
+
+@pytest.fixture
+def eval_content(eval_path: Path) -> str:
+    """Read and return the evaluation file content. Fails if file missing."""
+    assert eval_path.is_file(), f"Evaluation file not found: {eval_path}"
+    return eval_path.read_text()
+
+
+# ===========================================================================
+# AC1: Evaluate trigger frequency after 1 sprint
+# ===========================================================================
+
+
+class TestTriggerFrequency:
+    """AC1: Evaluation documents how often the gate triggered."""
+
+    def test_eval_has_trigger_section(self, eval_content: str) -> None:
+        """AC1: Evaluation has a section about trigger frequency."""
+        assert re.search(
+            r"(?i)trigger.*frequen|frequen.*trigger|how often|activation.*rate",
+            eval_content,
+        ), "Missing trigger frequency section"
+
+    def test_trigger_section_has_data(self, eval_content: str) -> None:
+        """AC1: Trigger section includes specific data or baseline note."""
+        content_lower = eval_content.lower()
+        assert any(
+            term in content_lower
+            for term in [
+                "triggered",
+                "fired",
+                "activated",
+                "invoked",
+                "n/a",
+                "baseline",
+                "times",
+                "occurrences",
+            ]
+        ), "Trigger section lacks frequency data or baseline acknowledgment"
+
+
+# ===========================================================================
+# AC2: Document whether it reduced wrong-approach incidents
+# ===========================================================================
+
+
+class TestWrongApproachReduction:
+    """AC2: Evaluation documents impact on wrong-approach incidents."""
+
+    def test_eval_has_wrong_approach_section(self, eval_content: str) -> None:
+        """AC2: Evaluation has a section about wrong-approach incidents."""
+        content_lower = eval_content.lower()
+        assert any(
+            term in content_lower
+            for term in [
+                "wrong-approach",
+                "wrong approach",
+                "incident",
+                "misroute",
+                "incorrect action",
+                "ambiguous",
+            ]
+        ), "Missing wrong-approach reduction section"
+
+    def test_wrong_approach_has_comparison(self, eval_content: str) -> None:
+        """AC2: Wrong-approach section includes comparison or baseline note."""
+        content_lower = eval_content.lower()
+        assert any(
+            term in content_lower
+            for term in [
+                "before",
+                "after",
+                "baseline",
+                "reduced",
+                "comparison",
+                "prior",
+                "improvement",
+                "no data yet",
+            ]
+        ), "Wrong-approach section lacks before/after comparison or baseline"
+
+
+# ===========================================================================
+# AC3: Assess if the gate was annoying
+# ===========================================================================
+
+
+class TestUserExperience:
+    """AC3: Evaluation assesses user experience with the gate."""
+
+    def test_eval_has_ux_section(self, eval_content: str) -> None:
+        """AC3: Evaluation has a section about user experience."""
+        content_lower = eval_content.lower()
+        assert any(
+            term in content_lower
+            for term in [
+                "user experience",
+                "annoying",
+                "friction",
+                "override",
+                "dismiss",
+                "usability",
+            ]
+        ), "Missing user experience assessment section"
+
+    def test_ux_mentions_override_behavior(self, eval_content: str) -> None:
+        """AC3: UX section addresses override/dismissal behavior."""
+        content_lower = eval_content.lower()
+        assert any(
+            term in content_lower
+            for term in ["override", "dismiss", "bypass", "skip", "ignored"]
+        ), "UX section doesn't address override/dismissal behavior"
+
+
+# ===========================================================================
+# AC4: Document findings in a results file
+# ===========================================================================
+
+
+class TestResultsFile:
+    """AC4: Evaluation results file exists with proper structure."""
+
+    def test_eval_file_exists(self, eval_path: Path) -> None:
+        """AC4: Evaluation results file exists at expected location."""
+        assert eval_path.is_file(), f"Evaluation file not found: {eval_path}"
+
+    def test_eval_file_not_empty(self, eval_path: Path) -> None:
+        """AC4: Evaluation file is not empty."""
+        assert eval_path.is_file(), f"File not found: {eval_path}"
+        content = eval_path.read_text()
+        assert len(content.strip()) > 0, "Evaluation file is empty"
+
+    def test_eval_has_title(self, eval_content: str) -> None:
+        """AC4: Evaluation has a title heading."""
+        assert re.search(r"^#\s+", eval_content, re.MULTILINE), (
+            "Evaluation file missing title heading"
+        )
+
+    def test_eval_has_structured_sections(self, eval_content: str) -> None:
+        """AC4: Evaluation has multiple sections (at least 3 headings)."""
+        headings = re.findall(r"^##\s+", eval_content, re.MULTILINE)
+        assert len(headings) >= 3, (
+            f"Expected at least 3 sections, found {len(headings)}"
+        )
+
+    def test_eval_references_gate(self, eval_content: str) -> None:
+        """AC4: Evaluation references the confidence-sm gate."""
+        assert "confidence-sm" in eval_content, (
+            "Evaluation doesn't reference the confidence-sm gate"
+        )
+
+
+# ===========================================================================
+# AC5: Decide on rollout recommendation to other agents
+# ===========================================================================
+
+
+class TestRolloutRecommendation:
+    """AC5: Evaluation includes a rollout recommendation."""
+
+    def test_eval_has_recommendation_section(self, eval_content: str) -> None:
+        """AC5: Evaluation has a rollout recommendation section."""
+        content_lower = eval_content.lower()
+        assert any(
+            term in content_lower
+            for term in ["recommendation", "rollout", "next steps", "decision"]
+        ), "Missing rollout recommendation section"
+
+    def test_recommendation_is_actionable(self, eval_content: str) -> None:
+        """AC5: Recommendation states a clear actionable decision."""
+        content_lower = eval_content.lower()
+        assert any(
+            term in content_lower
+            for term in [
+                "expand",
+                "hold",
+                "remove",
+                "proceed",
+                "defer",
+                "recommend",
+                "adopt",
+                "extend",
+            ]
+        ), "Recommendation lacks clear actionable decision"
+
+    def test_recommendation_mentions_other_agents(
+        self, eval_content: str
+    ) -> None:
+        """AC5: Recommendation addresses rollout to other agents."""
+        content_lower = eval_content.lower()
+        assert any(
+            term in content_lower
+            for term in [
+                "other agent",
+                "additional agent",
+                "tea",
+                "dev",
+                "reviewer",
+                "all agents",
+                "agent-specific",
+                "per-agent",
+            ]
+        ), "Recommendation doesn't address rollout to other agents"