feat(pipeline): strict-PD provenance record (content pipeline §3.1)

tests/test_pipeline_provenance.py

@@ -0,0 +1,20 @@
+from tools.pipeline.provenance import Provenance
+
+
+def test_provenance_to_dict_roundtrip():
+    p = Provenance(
+        scale="abyss",
+        license="public-domain (US Gov, 17 U.S.C. §105)",
+        source="NOAA Ocean Exploration",
+        url="https://oceanexplorer.noaa.gov/",
+        fetched_at="2026-06-24",
+    )
+    d = p.to_dict()
+    assert d == {
+        "scale": "abyss",
+        "license": "public-domain (US Gov, 17 U.S.C. §105)",
+        "source": "NOAA Ocean Exploration",
+        "url": "https://oceanexplorer.noaa.gov/",
+        "fetched_at": "2026-06-24",
+    }
+    assert Provenance.from_dict(d) == p

tools/pipeline/provenance.py

@@ -0,0 +1,29 @@
+"""Stage 1 — the per-clip strict-PD provenance record (spec §3.1).
+
+Captured at source time so license + source + URL travel with the media. The
+'no explicit license -> assume PD, verify' trap (scales design §2.1) applies:
+"free stock" (Pexels/Pixabay) is NOT public domain.
+"""
+
+from __future__ import annotations
+
+from dataclasses import asdict, dataclass
+
+
+@dataclass(frozen=True)
+class Provenance:
+    scale: str
+    license: str
+    source: str
+    url: str
+    fetched_at: str          # ISO date; passed in (no clock here -> deterministic)
+
+    def to_dict(self) -> dict:
+        return asdict(self)
+
+    @classmethod
+    def from_dict(cls, d: dict) -> "Provenance":
+        return cls(
+            scale=d["scale"], license=d["license"], source=d["source"],
+            url=d["url"], fetched_at=d["fetched_at"],
+        )