Goal:
Who cares:
Decision owner:
User or system action changed by the model:
Success metric:
Guardrail metrics:
Mistake budget:
Unacceptable mistakes:
Acceptable mistakes:
Assumptions:
Constraints:
Labels and data snapshot:
Baseline:
Candidate signals:
Threshold or config plan:
Eval slices:
Known risks:
Next experiment:
Rollback or fallback:

Iteration:
Change:
Why this mattered:
Metric movement:
Slice movement:
False positives:
False negatives:
Unexpected errors:
Decision:
Tradeoff accepted:
Lesson captured:
Regression added:
Debt created:
Next iteration:

import hashlib
from dataclasses import dataclass
from pathlib import Path


@dataclass(frozen=True)
class TrainingConfig:
    dataset_uri: str
    model_dir: Path
    seed: int
    learning_rate: float
    batch_size: int


def artifact_name(config: TrainingConfig, code_sha: str) -> str:
    config_key = f"{config.dataset_uri}:{config.seed}:{config.learning_rate}:{config.batch_size}"
    config_hash = hashlib.sha256(config_key.encode("utf-8")).hexdigest()[:12]
    return f"{code_sha[:12]}-{config_hash}"

PROMOTION_GATES = {
    "auc": ("min", 0.82),
    "calibration_error": ("max", 0.04),
    "p95_latency_ms": ("max", 80),
}


def assert_promotion_ready(metrics: dict[str, float]) -> None:
    missing = sorted(name for name in PROMOTION_GATES if name not in metrics)
    if missing:
        raise ValueError(f"Model promotion metrics missing required gates: {missing}")

    failures = {
        name: value
        for name, (direction, threshold) in PROMOTION_GATES.items()
        for value in [metrics[name]]
        if (direction == "min" and value < threshold)
        or (direction == "max" and value > threshold)
    }
    if failures:
        raise ValueError(f"Model failed promotion gates: {failures}")