| 1 | """Integration tests: validate ai-ml and rust topic configs end-to-end. |
| 2 | |
| 3 | Verifies schema validation passes and scoring pipeline produces reasonable |
| 4 | results with mock repo data for both topics, plus cross-topic isolation. |
| 5 | """ |
| 6 | |
| 7 | from __future__ import annotations |
| 8 | |
| 9 | from datetime import UTC, datetime, timedelta |
| 10 | |
| 11 | import pytest |
| 12 | |
| 13 | from scripts.score_repos import ( |
| 14 | compute_relevance_score, |
| 15 | get_scoring_config, |
| 16 | load_config, |
| 17 | score_repos, |
| 18 | ) |
| 19 | from scripts.validate_topic_config import validate_file |
| 20 | |
| 21 | # --- Helpers --- |
| 22 | |
| 23 | |
| 24 | def _make_repo( |
| 25 | name: str, |
| 26 | language: str, |
| 27 | stars: int, |
| 28 | stars_gained: int, |
| 29 | topics: list[str], |
| 30 | age_days: int = 30, |
| 31 | ) -> dict: |
| 32 | """Create a mock repo dict with given characteristics.""" |
| 33 | return { |
| 34 | "name": name, |
| 35 | "owner": "mock-org", |
| 36 | "full_name": f"mock-org/{name}", |
| 37 | "description": f"Mock repo: {name}", |
| 38 | "language": language, |
| 39 | "stars": stars, |
| 40 | "forks": stars // 10, |
| 41 | "created_at": (datetime.now(UTC) - timedelta(days=age_days)).isoformat(), |
| 42 | "topics": topics, |
| 43 | "license": "MIT", |
| 44 | "url": f"https://github.com/mock-org/{name}", |
| 45 | "stars_gained": stars_gained, |
| 46 | } |
| 47 | |
| 48 | |
| 49 | # --- AI/ML Config Fixtures --- |
| 50 | |
| 51 | |
| 52 | @pytest.fixture |
| 53 | def aiml_root_config(): |
| 54 | return validate_file("squadscope.topic.yml") |
| 55 | |
| 56 | |
| 57 | @pytest.fixture |
| 58 | def aiml_example_config(): |
| 59 | return validate_file("examples/topics/ai-ml.yml") |
| 60 | |
| 61 | |
| 62 | @pytest.fixture |
| 63 | def aiml_scoring_config(): |
| 64 | config = load_config("squadscope.topic.yml") |
| 65 | return get_scoring_config(config) |
| 66 | |
| 67 | |
| 68 | @pytest.fixture |
| 69 | def rust_config(): |
| 70 | return validate_file("examples/topics/rust.yml") |
| 71 | |
| 72 | |
| 73 | @pytest.fixture |
| 74 | def rust_scoring_config(): |
| 75 | config = load_config("examples/topics/rust.yml") |
| 76 | return get_scoring_config(config) |
| 77 | |
| 78 | |
| 79 | @pytest.fixture |
| 80 | def aiml_repos(): |
| 81 | """Sample repos matching AI/ML profile.""" |
| 82 | return [ |
| 83 | _make_repo( |
| 84 | "transformer-lib", |
| 85 | "Python", |
| 86 | 500, |
| 87 | 120, |
| 88 | ["machine-learning", "transformers", "deep-learning"], |
| 89 | ), |
| 90 | _make_repo( |
| 91 | "llm-toolkit", "Python", 1200, 300, ["llm", "artificial-intelligence", "python"] |
| 92 | ), |
| 93 | _make_repo( |
| 94 | "ml-starter", "Jupyter Notebook", 150, 40, ["machine-learning", "neural-network"] |
| 95 | ), |
| 96 | _make_repo("data-pipeline", "Python", 80, 20, ["machine-learning"], age_days=60), |
| 97 | _make_repo( |
| 98 | "ai-research", |
| 99 | "Python", |
| 100 | 3000, |
| 101 | 500, |
| 102 | ["deep-learning", "llm", "transformers"], |
| 103 | age_days=10, |
| 104 | ), |
| 105 | _make_repo("small-ml", "Python", 50, 15, ["machine-learning"], age_days=90), |
| 106 | _make_repo("mid-ml", "Python", 200, 50, ["deep-learning", "neural-network"], age_days=45), |
| 107 | ] |
| 108 | |
| 109 | |
| 110 | @pytest.fixture |
| 111 | def rust_repos(): |
| 112 | """Sample repos matching Rust profile.""" |
| 113 | return [ |
| 114 | _make_repo("fast-cli", "Rust", 400, 80, ["rust", "cli", "systems-programming"]), |
| 115 | _make_repo("async-runtime", "Rust", 2000, 200, ["rust", "async-rust", "cargo"]), |
| 116 | _make_repo("wasm-toolkit", "Rust", 600, 100, ["rust", "wasm", "cargo"]), |
| 117 | _make_repo("rust-game", "Rust", 150, 40, ["rust", "systems-programming"]), |
| 118 | _make_repo("tiny-crate", "Rust", 50, 20, ["rust", "cargo"], age_days=60), |
| 119 | ] |
| 120 | |
| 121 | |
| 122 | # ============================================================================= |
| 123 | # 1. AI/ML Schema Validation |
| 124 | # ============================================================================= |
| 125 | |
| 126 | |
| 127 | class TestAimlSchemaValidation: |
| 128 | """Issue #70: Validate ai-ml configs pass schema validation.""" |
| 129 | |
| 130 | def test_root_config_passes_validation(self, aiml_root_config): |
| 131 | assert aiml_root_config.topic.id == "ai-ml" |
| 132 | assert aiml_root_config.topic.name == "AI & Machine Learning" |
| 133 | assert len(aiml_root_config.queries.primary) >= 2 |
| 134 | |
| 135 | def test_example_config_passes_validation(self, aiml_example_config): |
| 136 | assert aiml_example_config.topic.id == "ai-ml" |
| 137 | assert aiml_example_config.scoring.min_stars == 20 |
| 138 | assert aiml_example_config.scoring.min_relevance_score == 40 |
| 139 | |
| 140 | def test_root_config_scoring_section(self, aiml_root_config): |
| 141 | assert aiml_root_config.scoring.language_boost.get("Python") == 1.2 |
| 142 | assert "machine-learning" in aiml_root_config.scoring.topic_relevance |
| 143 | |
| 144 | def test_root_config_quality_section(self, aiml_root_config): |
| 145 | assert aiml_root_config.quality.min_repos_per_week == 5 |
| 146 | assert aiml_root_config.quality.max_repos_per_week == 30 |
| 147 | |
| 148 | def test_root_config_learning_section(self, aiml_root_config): |
| 149 | assert "ai-ml" in aiml_root_config.learning.wisdom_file |
| 150 | |
| 151 | |
| 152 | # ============================================================================= |
| 153 | # 2. AI/ML Scoring Pipeline |
| 154 | # ============================================================================= |
| 155 | |
| 156 | |
| 157 | class TestAimlScoringPipeline: |
| 158 | """Issue #70: AI/ML repos get reasonable scores with mock data.""" |
| 159 | |
| 160 | def test_typical_aiml_repos_score_above_threshold(self, aiml_scoring_config, aiml_repos): |
| 161 | scored = score_repos(aiml_repos, aiml_scoring_config) |
| 162 | # All well-formed AI/ML repos should pass the min_relevance_score (40) |
| 163 | assert len(scored) >= 5 |
| 164 | |
| 165 | def test_high_quality_repo_scores_above_40(self, aiml_scoring_config): |
| 166 | repo = _make_repo( |
| 167 | "top-ml", "Python", 500, 100, ["machine-learning", "deep-learning", "llm"] |
| 168 | ) |
| 169 | score = compute_relevance_score(repo, aiml_scoring_config) |
| 170 | assert score >= 40 |
| 171 | |
| 172 | def test_min_repos_per_week_achievable(self, aiml_scoring_config, aiml_repos): |
| 173 | """With typical data, at least min_repos_per_week pass threshold.""" |
| 174 | min_required = 5 # from config quality.min_repos_per_week |
| 175 | scored = score_repos(aiml_repos, aiml_scoring_config) |
| 176 | assert len(scored) >= min_required |
| 177 | |
| 178 | def test_python_language_boost_applies(self, aiml_scoring_config): |
| 179 | python_repo = _make_repo("py-ml", "Python", 200, 50, ["machine-learning"]) |
| 180 | other_repo = _make_repo("go-ml", "Go", 200, 50, ["machine-learning"]) |
| 181 | |
| 182 | py_score = compute_relevance_score(python_repo, aiml_scoring_config) |
| 183 | go_score = compute_relevance_score(other_repo, aiml_scoring_config) |
| 184 | assert py_score > go_score |
| 185 | |
| 186 | def test_topic_relevance_boosts_score(self, aiml_scoring_config): |
| 187 | relevant = _make_repo( |
| 188 | "relevant", "Python", 200, 50, ["machine-learning", "deep-learning", "llm"] |
| 189 | ) |
| 190 | irrelevant = _make_repo("irrelevant", "Python", 200, 50, ["cooking", "recipes"]) |
| 191 | |
| 192 | rel_score = compute_relevance_score(relevant, aiml_scoring_config) |
| 193 | irr_score = compute_relevance_score(irrelevant, aiml_scoring_config) |
| 194 | assert rel_score > irr_score |
| 195 | |
| 196 | |
| 197 | # ============================================================================= |
| 198 | # 3. Rust Schema Validation |
| 199 | # ============================================================================= |
| 200 | |
| 201 | |
| 202 | class TestRustSchemaValidation: |
| 203 | """Issue #71: Validate rust config passes schema validation.""" |
| 204 | |
| 205 | def test_rust_config_passes_validation(self, rust_config): |
| 206 | assert rust_config.topic.id == "rust" |
| 207 | assert rust_config.topic.name == "Rust Ecosystem" |
| 208 | assert len(rust_config.queries.primary) >= 2 |
| 209 | |
| 210 | def test_rust_scoring_section(self, rust_config): |
| 211 | assert rust_config.scoring.language_boost.get("Rust") == 1.3 |
| 212 | assert rust_config.scoring.min_stars == 30 |
| 213 | assert rust_config.scoring.max_age_days == 730 |
| 214 | |
| 215 | def test_rust_topic_relevance(self, rust_config): |
| 216 | assert "rust" in rust_config.scoring.topic_relevance |
| 217 | assert "cargo" in rust_config.scoring.topic_relevance |
| 218 | assert "wasm" in rust_config.scoring.topic_relevance |
| 219 | |
| 220 | def test_rust_quality_section(self, rust_config): |
| 221 | assert rust_config.quality.min_repos_per_week == 5 |
| 222 | assert rust_config.quality.max_repos_per_week == 25 |
| 223 | assert rust_config.quality.min_quality_score == 55 |
| 224 | |
| 225 | |
| 226 | # ============================================================================= |
| 227 | # 4. Rust Scoring Pipeline |
| 228 | # ============================================================================= |
| 229 | |
| 230 | |
| 231 | class TestRustScoringPipeline: |
| 232 | """Issue #71: Rust repos score reasonably with language_boost.""" |
| 233 | |
| 234 | def test_typical_rust_repos_score_above_threshold(self, rust_scoring_config, rust_repos): |
| 235 | scored = score_repos(rust_repos, rust_scoring_config) |
| 236 | # Most Rust repos should pass the lower threshold (35) |
| 237 | assert len(scored) >= 3 |
| 238 | |
| 239 | def test_rust_language_boost_applies(self, rust_scoring_config): |
| 240 | rust_repo = _make_repo("cli-tool", "Rust", 300, 60, ["rust", "cli"]) |
| 241 | go_repo = _make_repo("cli-tool-go", "Go", 300, 60, ["go", "cli"]) |
| 242 | |
| 243 | rust_score = compute_relevance_score(rust_repo, rust_scoring_config) |
| 244 | go_score = compute_relevance_score(go_repo, rust_scoring_config) |
| 245 | assert rust_score > go_score |
| 246 | |
| 247 | def test_narrower_topic_still_produces_results(self, rust_scoring_config, rust_repos): |
| 248 | """Rust is narrower than AI/ML but should still yield min_repos_per_week.""" |
| 249 | min_required = 5 # from config quality.min_repos_per_week |
| 250 | scored = score_repos(rust_repos, rust_scoring_config) |
| 251 | assert len(scored) >= min_required |
| 252 | |
| 253 | def test_high_quality_rust_repo_scores_above_40(self, rust_scoring_config): |
| 254 | repo = _make_repo("blazing-fast", "Rust", 1000, 150, ["rust", "async-rust", "cargo"]) |
| 255 | score = compute_relevance_score(repo, rust_scoring_config) |
| 256 | assert score >= 40 |
| 257 | |
| 258 | |
| 259 | # ============================================================================= |
| 260 | # 5. Cross-Topic Isolation |
| 261 | # ============================================================================= |
| 262 | |
| 263 | |
| 264 | class TestCrossTopicIsolation: |
| 265 | """Verify configs don't score repos from other domains highly.""" |
| 266 | |
| 267 | def test_aiml_config_does_not_score_rust_repos_highly(self, aiml_scoring_config, rust_repos): |
| 268 | """Rust repos should score lower under ai-ml config due to no topic overlap.""" |
| 269 | scored = score_repos(rust_repos, aiml_scoring_config) |
| 270 | # Rust repos lack AI/ML topics, so fewer should pass threshold |
| 271 | for repo in scored: |
| 272 | # No Rust repo should score as high as a good AI/ML repo would |
| 273 | assert repo["relevance_score"] < 70 |
| 274 | |
| 275 | def test_rust_config_does_not_score_python_ml_repos_highly( |
| 276 | self, rust_scoring_config, aiml_repos |
| 277 | ): |
| 278 | """Python ML repos should score lower under rust config due to topic/lang mismatch.""" |
| 279 | scored = score_repos(aiml_repos, rust_scoring_config) |
| 280 | # Python repos don't get Rust language boost and lack rust topics |
| 281 | for repo in scored: |
| 282 | assert repo["relevance_score"] < 75 |
| 283 | |
| 284 | def test_aiml_repos_score_higher_with_own_config( |
| 285 | self, aiml_scoring_config, rust_scoring_config, aiml_repos |
| 286 | ): |
| 287 | """AI/ML repos should score higher with ai-ml config than rust config.""" |
| 288 | aiml_scored = score_repos(aiml_repos, aiml_scoring_config) |
| 289 | rust_scored = score_repos(aiml_repos, rust_scoring_config) |
| 290 | |
| 291 | avg_aiml = sum(r["relevance_score"] for r in aiml_scored) / max(len(aiml_scored), 1) |
| 292 | avg_rust = ( |
| 293 | sum(r["relevance_score"] for r in rust_scored) / max(len(rust_scored), 1) |
| 294 | if rust_scored |
| 295 | else 0 |
| 296 | ) |
| 297 | assert avg_aiml > avg_rust |
| 298 | |
| 299 | def test_rust_repos_score_higher_with_own_config( |
| 300 | self, aiml_scoring_config, rust_scoring_config, rust_repos |
| 301 | ): |
| 302 | """Rust repos should score higher with rust config than ai-ml config.""" |
| 303 | rust_scored = score_repos(rust_repos, rust_scoring_config) |
| 304 | aiml_scored = score_repos(rust_repos, aiml_scoring_config) |
| 305 | |
| 306 | avg_rust = sum(r["relevance_score"] for r in rust_scored) / max(len(rust_scored), 1) |
| 307 | avg_aiml = ( |
| 308 | sum(r["relevance_score"] for r in aiml_scored) / max(len(aiml_scored), 1) |
| 309 | if aiml_scored |
| 310 | else 0 |
| 311 | ) |
| 312 | assert avg_rust > avg_aiml |