kaizen-agentic/tests/test_metrics_cli.py

"""CLI tests for project-scoped metrics commands."""

from __future__ import annotations

import json
from pathlib import Path

import pytest
from click.testing import CliRunner

from kaizen_agentic.cli import cli


@pytest.fixture
def runner() -> CliRunner:
    return CliRunner()


@pytest.fixture
def project_dir(tmp_path: Path) -> Path:
    root = tmp_path / "demo-project"
    root.mkdir()
    return root


class TestMetricsCli:
    def test_record_show_list_export_flow(self, runner: CliRunner, project_dir: Path):
        target = str(project_dir)

        record = runner.invoke(
            cli,
            [
                "metrics",
                "record",
                "tdd-workflow",
                "--target",
                target,
                "--success",
                "--time",
                "42",
                "--quality",
                "0.85",
            ],
        )
        assert record.exit_code == 0
        assert "Recorded metrics" in record.output

        show = runner.invoke(
            cli, ["metrics", "show", "tdd-workflow", "--target", target]
        )
        assert show.exit_code == 0
        assert '"execution_count": 1' in show.output
        assert '"success": true' in show.output

        listed = runner.invoke(cli, ["metrics", "list", "--target", target])
        assert listed.exit_code == 0
        assert "tdd-workflow" in listed.output

        export = runner.invoke(
            cli, ["metrics", "export", "tdd-workflow", "--target", target]
        )
        assert export.exit_code == 0
        lines = [line for line in export.output.splitlines() if line.strip()]
        assert len(lines) == 1
        assert json.loads(lines[0])["quality_score"] == 0.85

    def test_record_json_from_stdin(self, runner: CliRunner, project_dir: Path):
        payload = json.dumps({"success": False, "execution_time_s": 9.5})
        result = runner.invoke(
            cli,
            ["metrics", "record", "coach", "--target", str(project_dir), "--json"],
            input=payload,
        )
        assert result.exit_code == 0

        show = runner.invoke(
            cli, ["metrics", "show", "coach", "--target", str(project_dir)]
        )
        assert '"success": false' in show.output

    def test_record_idempotency_key_skips_duplicate(
        self, runner: CliRunner, project_dir: Path
    ):
        args = [
            "metrics",
            "record",
            "coach",
            "--target",
            str(project_dir),
            "--success",
            "--idempotency-key",
            "sess-abc",
        ]
        first = runner.invoke(cli, args)
        second = runner.invoke(cli, args)
        assert first.exit_code == 0
        assert second.exit_code == 0
        assert "Skipped duplicate" in second.output

        export = runner.invoke(
            cli, ["metrics", "export", "coach", "--target", str(project_dir)]
        )
        assert len(export.output.strip().splitlines()) == 1

    def test_record_requires_outcome_without_json(
        self, runner: CliRunner, project_dir: Path
    ):
        result = runner.invoke(
            cli,
            ["metrics", "record", "tdd-workflow", "--target", str(project_dir)],
        )
        assert result.exit_code != 0
        assert "--success or --failure" in result.output

    def test_memory_init_scaffolds_metrics(self, runner: CliRunner, project_dir: Path):
        result = runner.invoke(
            cli,
            ["memory", "init", "tdd-workflow", "--target", str(project_dir)],
        )
        assert result.exit_code == 0
        metrics_dir = project_dir / ".kaizen" / "metrics" / "tdd-workflow"
        assert metrics_dir.exists()
        assert (metrics_dir / "executions.jsonl").exists()

    def test_memory_brief_includes_performance_summary(
        self, runner: CliRunner, project_dir: Path
    ):
        target = str(project_dir)
        runner.invoke(cli, ["memory", "init", "tdd-workflow", "--target", target])
        runner.invoke(
            cli,
            [
                "metrics",
                "record",
                "tdd-workflow",
                "--target",
                target,
                "--success",
                "--quality",
                "0.9",
            ],
        )

        result = runner.invoke(
            cli, ["memory", "brief", "tdd-workflow", "--target", target]
        )
        assert result.exit_code == 0
        assert "## Performance Summary" in result.output
        assert "Success rate: 100.0%" in result.output

    def test_memory_init_no_metrics_flag(self, runner: CliRunner, project_dir: Path):
        result = runner.invoke(
            cli,
            ["memory", "init", "coach", "--target", str(project_dir), "--no-metrics"],
        )
        assert result.exit_code == 0
        assert not (project_dir / ".kaizen" / "metrics" / "coach").exists()