pytestmark = [pytest.mark.genai]

def test_agents_documented_in_claude_md(self, genai):
    agents_on_disk = list_agents()
    claude_md = Path("CLAUDE.md").read_text()
    result = genai.judge(
        question="Does CLAUDE.md document all active agents?",
        context=f"Agents on disk: {agents_on_disk}\nCLAUDE.md:\n{claude_md[:3000]}",
        criteria="All active agents should be referenced. Score by coverage %."
    )
    assert result["score"] >= 5, f"Gap: {result['reasoning']}"

def test_implement_and_implementer_share_forbidden_list(self, genai):
    implement = Path("commands/implement.md").read_text()
    implementer = Path("agents/implementer.md").read_text()
    result = genai.judge(
        question="Do these files have matching FORBIDDEN behavior lists?",
        context=f"implement.md:\n{implement[:5000]}\nimplementer.md:\n{implementer[:5000]}",
        criteria="Both should define same enforcement gates. Score 10=identical, 0=contradictory."
    )
    assert result["score"] >= 5

def test_all_active_skills_have_content(self):
    skills_dir = Path("plugins/autonomous-dev/skills")
    for skill in skills_dir.iterdir():
        if skill.name == "archived" or not skill.is_dir():
            continue
        skill_md = skill / "SKILL.md"
        assert skill_md.exists(), f"Skill {skill.name} missing SKILL.md"
        assert len(skill_md.read_text()) > 100, f"Skill {skill.name} is a hollow shell"

# BAD — breaks every time a component is added/removed
assert len(agents) == 14
assert hook_count == 17

# GOOD — minimum thresholds + structural checks
assert len(agents) >= 8, "Pipeline needs at least 8 agents"
assert "implementer.md" in agent_names, "Core agent missing"

# BAD — breaks on every config update
assert settings["version"] == "3.51.0"

# GOOD — test structure, not values
assert "version" in settings
assert re.match(r"\d+\.\d+\.\d+", settings["version"])

# BAD — breaks on renames/moves
assert Path("plugins/autonomous-dev/lib/old_name.py").exists()

# GOOD — use glob discovery
assert any(Path("plugins/autonomous-dev/lib").glob("*skill*"))

tests/
├── regression/
│   ├── smoke/           # Tier 0: Critical path (<5s) — CI GATE
│   ├── regression/      # Tier 1: Feature protection (<30s)
│   ├── extended/        # Tier 2: Deep validation (<5min)
│   └── progression/     # Tier 3: TDD red phase (not yet implemented)
├── unit/                # Isolated functions (<1s each)
├── integration/         # Multi-component workflows (<30s)
├── genai/               # LLM-as-judge (opt-in via --genai flag)
└── archived/            # Excluded from runs

pytest -m smoke                    # CI gate
pytest -m "smoke or regression"    # Feature protection
pytest tests/genai/ --genai        # GenAI validation (opt-in)

# tests/genai/conftest.py provides two fixtures:
# - genai: Gemini Flash via OpenRouter (cheap, fast)
# - genai_smart: Haiku 4.5 via OpenRouter (complex reasoning)
# Requires: OPENROUTER_API_KEY env var + --genai pytest flag
# Cost: ~$0.02 per full run with 24h response caching