| 1 | #!/usr/bin/env python3 |
| 2 | """Validate a squadscope.topic.yml config file against the topic schema. |
| 3 | |
| 4 | Usage: |
| 5 | python scripts/validate_topic_config.py <path-to-yaml> |
| 6 | |
| 7 | Exit codes: |
| 8 | 0 — config is valid |
| 9 | 1 — config is invalid (errors printed to stderr) |
| 10 | |
| 11 | Schema fields: |
| 12 | topic (required): |
| 13 | id — URL-safe identifier (lowercase alphanumeric + hyphens) |
| 14 | name — Human-readable display name |
| 15 | description — Short description for the topic |
| 16 | |
| 17 | queries (required): |
| 18 | primary — List of GitHub search queries (at least one required) |
| 19 | secondary — Optional list of supplemental queries |
| 20 | |
| 21 | scoring (optional, has defaults): |
| 22 | min_stars, min_stars_gained, max_age_days, min_relevance_score |
| 23 | language_boost — dict of language → multiplier |
| 24 | topic_relevance — list of relevant GitHub topics |
| 25 | |
| 26 | quality (optional, has defaults): |
| 27 | min_repos_per_week, max_repos_per_week, min_quality_score |
| 28 | |
| 29 | learning (optional, has defaults): |
| 30 | wisdom_file, skills_dir, prediction_file, scorecard_dir |
| 31 | """ |
| 32 | |
| 33 | from __future__ import annotations |
| 34 | |
| 35 | import re |
| 36 | import sys |
| 37 | from pathlib import Path |
| 38 | from typing import Dict, List |
| 39 | |
| 40 | import yaml |
| 41 | from pydantic import BaseModel, Field, field_validator, model_validator |
| 42 | |
| 43 | # --- Pydantic Models --- |
| 44 | |
| 45 | URL_SAFE_RE = re.compile(r"^[a-z0-9]+(?:-[a-z0-9]+)*$") |
| 46 | |
| 47 | |
| 48 | class TopicInfo(BaseModel): |
| 49 | """Core topic identification. All fields required.""" |
| 50 | |
| 51 | id: str = Field(..., description="URL-safe identifier (lowercase alphanumeric + hyphens)") |
| 52 | name: str = Field(..., description="Human-readable display name") |
| 53 | description: str = Field("", description="Short description of the topic") |
| 54 | |
| 55 | @field_validator("id") |
| 56 | @classmethod |
| 57 | def id_must_be_url_safe(cls, v: str) -> str: |
| 58 | if not URL_SAFE_RE.match(v): |
| 59 | raise ValueError( |
| 60 | f"topic.id must be URL-safe (lowercase alphanumeric + hyphens), got: '{v}'" |
| 61 | ) |
| 62 | return v |
| 63 | |
| 64 | @field_validator("name") |
| 65 | @classmethod |
| 66 | def name_not_empty(cls, v: str) -> str: |
| 67 | if not v.strip(): |
| 68 | raise ValueError("topic.name must not be empty") |
| 69 | return v |
| 70 | |
| 71 | |
| 72 | class Queries(BaseModel): |
| 73 | """Search queries for GitHub API. At least one primary query is required.""" |
| 74 | |
| 75 | primary: List[str] = Field( |
| 76 | ..., min_length=1, description="Primary search queries (at least one)" |
| 77 | ) |
| 78 | secondary: List[str] = Field(default_factory=list, description="Optional secondary queries") |
| 79 | |
| 80 | @field_validator("primary") |
| 81 | @classmethod |
| 82 | def primary_not_empty_strings(cls, v: List[str]) -> List[str]: |
| 83 | for i, q in enumerate(v): |
| 84 | if not q.strip(): |
| 85 | raise ValueError(f"queries.primary[{i}] must not be an empty string") |
| 86 | return v |
| 87 | |
| 88 | |
| 89 | class Scoring(BaseModel): |
| 90 | """Scoring thresholds and boosts. All fields have sensible defaults.""" |
| 91 | |
| 92 | min_stars: int = Field(default=20, ge=0, description="Minimum star count") |
| 93 | min_stars_gained: int = Field(default=10, ge=0, description="Minimum stars gained in period") |
| 94 | max_age_days: int = Field(default=365, ge=1, le=3650, description="Max repo age in days") |
| 95 | min_relevance_score: int = Field( |
| 96 | default=40, ge=0, le=100, description="Minimum relevance score (0-100)" |
| 97 | ) |
| 98 | language_boost: Dict[str, float] = Field( |
| 99 | default_factory=dict, description="Language → score multiplier" |
| 100 | ) |
| 101 | topic_relevance: List[str] = Field( |
| 102 | default_factory=list, description="GitHub topics that boost relevance" |
| 103 | ) |
| 104 | |
| 105 | @field_validator("language_boost") |
| 106 | @classmethod |
| 107 | def boost_values_reasonable(cls, v: Dict[str, float]) -> Dict[str, float]: |
| 108 | for lang, boost in v.items(): |
| 109 | if boost < 0.1 or boost > 10.0: |
| 110 | raise ValueError( |
| 111 | f"scoring.language_boost['{lang}'] must be between 0.1 and 10.0, got {boost}" |
| 112 | ) |
| 113 | return v |
| 114 | |
| 115 | |
| 116 | class Quality(BaseModel): |
| 117 | """Quality gates for output. All fields have sensible defaults.""" |
| 118 | |
| 119 | min_repos_per_week: int = Field( |
| 120 | default=5, ge=1, description="Minimum repos to include per week" |
| 121 | ) |
| 122 | max_repos_per_week: int = Field( |
| 123 | default=30, ge=1, description="Maximum repos to include per week" |
| 124 | ) |
| 125 | min_quality_score: int = Field( |
| 126 | default=60, ge=0, le=100, description="Minimum quality score (0-100)" |
| 127 | ) |
| 128 | |
| 129 | @model_validator(mode="after") |
| 130 | def min_less_than_max(self) -> "Quality": |
| 131 | if self.min_repos_per_week > self.max_repos_per_week: |
| 132 | raise ValueError( |
| 133 | f"quality.min_repos_per_week ({self.min_repos_per_week}) " |
| 134 | f"must be <= max_repos_per_week ({self.max_repos_per_week})" |
| 135 | ) |
| 136 | return self |
| 137 | |
| 138 | |
| 139 | class Learning(BaseModel): |
| 140 | """Paths for learning/feedback loop artifacts. Supports {topic_id} placeholder.""" |
| 141 | |
| 142 | wisdom_file: str = Field( |
| 143 | default="topics/{topic_id}/wisdom.md", description="Path to wisdom markdown" |
| 144 | ) |
| 145 | skills_dir: str = Field( |
| 146 | default="topics/{topic_id}/skills/", description="Directory for learned skills" |
| 147 | ) |
| 148 | prediction_file: str = Field( |
| 149 | default="topics/{topic_id}/predictions.jsonl", description="Path to predictions log" |
| 150 | ) |
| 151 | scorecard_dir: str = Field( |
| 152 | default="topics/{topic_id}/scorecards/", description="Directory for scorecards" |
| 153 | ) |
| 154 | |
| 155 | |
| 156 | class TopicConfig(BaseModel): |
| 157 | """Root model for squadscope.topic.yml configuration.""" |
| 158 | |
| 159 | topic: TopicInfo |
| 160 | queries: Queries |
| 161 | scoring: Scoring = Field(default_factory=Scoring) |
| 162 | quality: Quality = Field(default_factory=Quality) |
| 163 | learning: Learning = Field(default_factory=Learning) |
| 164 | |
| 165 | |
| 166 | # --- CLI Entrypoint --- |
| 167 | |
| 168 | |
| 169 | def validate_file(path: str) -> TopicConfig: |
| 170 | """Load and validate a YAML topic config file. Returns the validated model.""" |
| 171 | file_path = Path(path) |
| 172 | if not file_path.exists(): |
| 173 | raise FileNotFoundError(f"Config file not found: {path}") |
| 174 | |
| 175 | with open(file_path, "r", encoding="utf-8") as f: |
| 176 | raw = yaml.safe_load(f) |
| 177 | |
| 178 | if not isinstance(raw, dict): |
| 179 | raise ValueError("Config file must contain a YAML mapping at the top level") |
| 180 | |
| 181 | return TopicConfig.model_validate(raw) |
| 182 | |
| 183 | |
| 184 | def main() -> int: |
| 185 | if len(sys.argv) != 2: |
| 186 | print("Usage: python scripts/validate_topic_config.py <path-to-yaml>", file=sys.stderr) |
| 187 | return 1 |
| 188 | |
| 189 | path = sys.argv[1] |
| 190 | try: |
| 191 | config = validate_file(path) |
| 192 | print(f"✓ Valid topic config: {config.topic.name} ({config.topic.id})") |
| 193 | return 0 |
| 194 | except FileNotFoundError as e: |
| 195 | print(f"✗ Error: {e}", file=sys.stderr) |
| 196 | return 1 |
| 197 | except ValueError as e: |
| 198 | print(f"✗ Validation error: {e}", file=sys.stderr) |
| 199 | return 1 |
| 200 | except Exception as e: |
| 201 | # Pydantic validation errors |
| 202 | print(f"✗ Validation failed:\n{e}", file=sys.stderr) |
| 203 | return 1 |
| 204 | |
| 205 | |
| 206 | if __name__ == "__main__": |
| 207 | sys.exit(main()) |