feat(simulator): clips.py manifest model; retire selection fixtures

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-07 22:54:09 -07:00
parent 825d68c653
commit c316309fc6
4 changed files with 137 additions and 99 deletions
@@ -0,0 +1,68 @@
+"""The base-clip + variant + annotation manifest the simulator renders.
+
+Replaces simulator/fixtures.py (the selection-era synthetic catalog). Each base
+clip carries: the raw base file, a map of pre-baked Right-strength variant files
+(strength 0 is always the raw base), an authored Left annotation track (box +
+label key + the minimum Left level at which it appears), and per-language string
+tables. See the reconciled-simulator-alteration-slice design §3.2.
+"""
+
+from __future__ import annotations
+
+import json
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Any
+
+
+@dataclass(frozen=True)
+class Clip:
+    id: str
+    title: str
+    base_file: str
+    license: str
+    source: str
+    right_variants: dict          # {"1": {"file": ...}, "4": {...}} (no "0")
+    annotations: list             # [{"key", "box":[x,y,w,h], "min_level"}, ...]
+    strings: dict                 # {"en": {key: text}}
+
+    def variant_file(self, strength: int) -> str:
+        """The video file for a Right strength; 0 and any unauthored strength
+        fall back to the raw base file."""
+        entry = self.right_variants.get(str(strength))
+        return entry["file"] if entry else self.base_file
+
+    def to_dict(self) -> dict:
+        variants = {"0": {"file": self.base_file, "raw": True}}
+        for k, v in self.right_variants.items():
+            variants[k] = v
+        return {
+            "id": self.id,
+            "title": self.title,
+            "base_file": self.base_file,
+            "license": self.license,
+            "source": self.source,
+            "right_variants": variants,
+            "annotations": self.annotations,
+            "strings": self.strings,
+        }
+
+
+def _clip_from_dict(d: dict[str, Any]) -> Clip:
+    return Clip(
+        id=d["id"],
+        title=d["title"],
+        base_file=d["base_file"],
+        license=d.get("license", ""),
+        source=d.get("source", ""),
+        right_variants=d.get("right_variants", {}),
+        annotations=d.get("annotations", []),
+        strings=d.get("strings", {}),
+    )
+
+
+def load_manifest(path: str | Path) -> list[Clip]:
+    """Load the base-clip manifest. Raises FileNotFoundError if missing."""
+    path = Path(path)
+    data = json.loads(path.read_text())
+    return [_clip_from_dict(c) for c in data["clips"]]
@@ -1,59 +0,0 @@
-"""Deterministic synthetic catalog so the selection model can be felt everywhere.
-
-The real catalog (catalog/library.jsonl) is empty; this generates one record per
-cell of the 5x5 brain x 5x5 mood coordinate space (625 records), with a seeded
-mix of content modes and review statuses and no real media attached.
-"""
-
-from __future__ import annotations
-
-import random
-
-from hef.catalog import Record
-
-MODES = ("audio", "video", "av")
-ARCHIVES = ("internet_archive", "musopen", "librivox", "nasa", "freesound")
-
-_LEFT_WORDS = ("Treatise", "Lecture", "Field Notes", "Reading", "Documentary")
-_RIGHT_WORDS = ("Reverie", "Nocturne", "Bloom", "Drift", "Aurora")
-
-
-def _title(left: int, right: int, dark: int, light: int, mode: str) -> str:
-    a = _LEFT_WORDS[left] if left >= right else _RIGHT_WORDS[right]
-    return f"{a} ({mode}) L{left}R{right}D{dark}Li{light}"
-
-
-def generate_fixture_catalog(seed: int = 1729) -> list[Record]:
-    """One valid Record per coordinate cell (625 total), deterministic for a seed."""
-    rng = random.Random(seed)
-    records: list[Record] = []
-    n = 0
-    for left in range(5):
-        for right in range(5):
-            for dark in range(5):
-                for light in range(5):
-                    mode = rng.choice(MODES)
-                    status = rng.choice(("proposed", "approved"))
-                    is_video = mode in ("video", "av")
-                    records.append(
-                        Record(
-                            id=f"fx-{n:04d}",
-                            title=_title(left, right, dark, light, mode),
-                            source_url=f"https://example.test/fx/{n:04d}",
-                            source_archive=rng.choice(ARCHIVES),
-                            license="public_domain",
-                            mode=mode,
-                            left=left,
-                            right=right,
-                            dark=dark,
-                            light=light,
-                            duration_s=rng.choice((300, 480, 600, 720, 900)),
-                            file_path="",
-                            review_status=status,
-                            resolution="1920x1080" if is_video else "",
-                            rationale=f"fixture at ({left},{right},{dark},{light})",
-                            reviewed_at="2026-06-04T00:00:00Z" if status == "approved" else None,
-                        )
-                    )
-                    n += 1
-    return records