Reconstruct repo from Claude Code + codex transcripts

Working tree (including .git) was lost to an rm. Rebuilt by replaying Write/Edit/ Read/attachment events from 25 Claude sessions and 22 successful codex apply_patch blocks into one timestamp-ordered timeline. Verified against ground truth recorded in the transcripts: wc -l on 10 files and ls -l on 5 files at 2026-07-18T13:13:44Z both match exactly; 18 files are byte-identical to their newest ~/.claude/file-history blob. See HANDOFF.md for sources, gaps, and how to rebuild .venv. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-11 02:42:41 +04:00
commit ff6a512630
32 changed files with 6759 additions and 0 deletions
@@ -0,0 +1,95 @@
+#!/usr/bin/env bash
+# Turn a video into timestamped contact sheets and scene-change frames for visual analysis.
+# Optional --window START:DURATION arguments create dense 10-fps sheets around transitions.
+set -euo pipefail
+
+usage() {
+  cat <<'EOF'
+Usage:
+  scripts/analyze_video_frames.sh VIDEO [OUTPUT_DIR] [--window START:DURATION ...]
+
+Examples:
+  scripts/analyze_video_frames.sh chapter.mp4
+  scripts/analyze_video_frames.sh chapter.mp4 /tmp/chapter-analysis \
+    --window 5.8:2.2 --window 15.8:2.5
+
+Outputs:
+  overview-001.jpg ...       2-fps timestamped contact sheets
+  scenes/scene-001.jpg ...   frames selected by scene-change score
+  scene-timestamps.txt       scene-change timestamps from FFmpeg showinfo
+  window-START.jpg           10-fps contact sheet for each requested window
+
+Environment overrides:
+  OVERVIEW_FPS=2 SCENE_THRESHOLD=0.18 WINDOW_FPS=10
+EOF
+}
+
+if [ "$#" -lt 1 ] || [ "${1:-}" = "-h" ] || [ "${1:-}" = "--help" ]; then
+  usage
+  exit $([ "$#" -lt 1 ] && echo 1 || echo 0)
+fi
+
+video=$1
+shift
+if [ ! -f "$video" ]; then
+  echo "video not found: $video" >&2
+  exit 1
+fi
+
+if [ "$#" -gt 0 ] && [[ $1 != --* ]]; then
+  output_dir=$1
+  shift
+else
+  base=$(basename "$video")
+  output_dir="/tmp/${base%.*}-frames"
+fi
+
+overview_fps=${OVERVIEW_FPS:-2}
+scene_threshold=${SCENE_THRESHOLD:-0.18}
+window_fps=${WINDOW_FPS:-10}
+windows=()
+while [ "$#" -gt 0 ]; do
+  case "$1" in
+    --window)
+      [ "$#" -ge 2 ] || { echo "--window needs START:DURATION" >&2; exit 2; }
+      windows+=("$2")
+      shift 2
+      ;;
+    *)
+      echo "unknown argument: $1" >&2
+      usage >&2
+      exit 2
+      ;;
+  esac
+done
+
+mkdir -p "$output_dir/scenes"
+
+# Six-by-six sheets keep individual frames readable while allowing videos of arbitrary length:
+# tile emits additional overview-NNN images after every 36 sampled frames.
+ffmpeg -hide_banner -loglevel error -y -i "$video" \
+  -vf "fps=${overview_fps},scale=320:-1,drawtext=text='%{pts\\:hms}':x=8:y=8:fontsize=20:fontcolor=yellow:borderw=2,tile=6x6:padding=4:margin=4" \
+  -fps_mode vfr "$output_dir/overview-%03d.jpg"
+
+# Keep stderr because showinfo reports the original timestamps there.
+ffmpeg -hide_banner -y -i "$video" \
+  -vf "select='gt(scene,${scene_threshold})',showinfo" -fps_mode vfr \
+  "$output_dir/scenes/scene-%03d.jpg" 2>"$output_dir/scene-showinfo.log" || true
+sed -n 's/.*pts_time:\([^ ]*\).*/\1/p' "$output_dir/scene-showinfo.log" \
+  >"$output_dir/scene-timestamps.txt"
+
+for window in "${windows[@]}"; do
+  start=${window%%:*}
+  duration=${window#*:}
+  if [ "$start" = "$window" ] || [ -z "$start" ] || [ -z "$duration" ]; then
+    echo "invalid window '$window'; expected START:DURATION" >&2
+    exit 2
+  fi
+  safe_start=${start//./_}
+  # A 5x5 sheet covers 2.5 seconds at the default 10 fps. Longer windows naturally emit more sheets.
+  ffmpeg -hide_banner -loglevel error -y -ss "$start" -t "$duration" -i "$video" \
+    -vf "fps=${window_fps},scale=320:-1,drawtext=text='%{pts\\:hms}':x=6:y=6:fontsize=18:fontcolor=yellow:borderw=2,tile=5x5:padding=3:margin=3" \
+    -fps_mode vfr "$output_dir/window-${safe_start}-%03d.jpg"
+done
+
+echo "video analysis frames: $output_dir"
@@ -0,0 +1,118 @@
+#!/usr/bin/env python3
+"""Interactively generate and choose a dots.tts narrator reference."""
+
+import argparse
+import os
+from pathlib import Path
+import shutil
+import subprocess
+import sys
+import time
+
+
+DEFAULT_TEXT = "The story continues as our hero steps forward into the unknown."
+DEFAULT_MODEL = "rednote-hilab/dots.tts-base"
+DEFAULT_VOICE_DIR = Path("~/.cache/manga-tts").expanduser()
+
+
+def load_model(model_name: str):
+    # Match worker_tts.py's workaround for the tokenizer bundled with dots.tts.
+    import transformers
+
+    original = transformers.AutoTokenizer.from_pretrained.__func__
+    transformers.AutoTokenizer.from_pretrained = classmethod(
+        lambda cls, *args, **kwargs: original(
+            cls, *args, **{"fix_mistral_regex": True, **kwargs}
+        )
+    )
+    from dots_tts.runtime import DotsTtsRuntime
+
+    return DotsTtsRuntime.from_pretrained(model_name, precision="bfloat16")
+
+
+def write_wav(result, path: Path) -> None:
+    import numpy as np
+    import soundfile as sf
+
+    audio = result["audio"]
+    if hasattr(audio, "detach"):
+        audio = audio.detach().cpu().numpy()
+    sf.write(path, np.asarray(audio, dtype="float32").squeeze(),
+             result["sample_rate"], subtype="PCM_16")
+
+
+def play(path: Path) -> None:
+    players = (
+        ("ffplay", "-nodisp", "-autoexit", "-loglevel", "error"),
+        ("aplay", "-q"),
+        ("paplay",),
+    )
+    for command in players:
+        if shutil.which(command[0]):
+            subprocess.run([*command, str(path)], check=False)
+            return
+    print(f"No ffplay, aplay, or paplay found; listen manually: {path}")
+
+
+def choice() -> str:
+    while True:
+        answer = input("[p]ick / p[a]rk / [s]kip: ").strip().lower()
+        aliases = {"p": "pick", "pick": "pick", "a": "park", "park": "park",
+                   "s": "skip", "skip": "skip"}
+        if answer in aliases:
+            return aliases[answer]
+        print("Enter p, a, or s.")
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("--text", default=os.environ.get("VOICE_REF_TEXT", DEFAULT_TEXT),
+                        help="sample text to speak")
+    parser.add_argument("--model", default=DEFAULT_MODEL)
+    parser.add_argument("--voice-dir", type=Path, default=DEFAULT_VOICE_DIR)
+    args = parser.parse_args()
+
+    voice_dir = args.voice_dir.expanduser()
+    parked_dir = voice_dir / "parked"
+    voice_dir.mkdir(parents=True, exist_ok=True)
+    parked_dir.mkdir(parents=True, exist_ok=True)
+    candidate = voice_dir / "voice_candidate.wav"
+    selected = voice_dir / "narrator_ref.wav"
+
+    print(f"Loading {args.model} ...")
+    model = load_model(args.model)
+    print(f"Reference text: {args.text!r}")
+
+    try:
+        while True:
+            print("\nGenerating a new voice ...")
+            write_wav(model.generate(text=args.text), candidate)
+            play(candidate)
+
+            action = choice()
+            if action == "pick":
+                os.replace(candidate, selected)
+                (voice_dir / "narrator_ref.txt").write_text(args.text + "\n")
+                print(f"Selected: {selected}")
+                return 0
+            if action == "park":
+                stamp = time.strftime("%Y%m%d-%H%M%S")
+                parked = parked_dir / f"voice-{stamp}.wav"
+                suffix = 2
+                while parked.exists():
+                    parked = parked_dir / f"voice-{stamp}-{suffix}.wav"
+                    suffix += 1
+                os.replace(candidate, parked)
+                parked.with_suffix(".txt").write_text(args.text + "\n")
+                print(f"Parked: {parked}")
+            else:
+                candidate.unlink(missing_ok=True)
+                print("Skipped.")
+    except (KeyboardInterrupt, EOFError):
+        candidate.unlink(missing_ok=True)
+        print("\nStopped without changing the selected voice.")
+        return 130
+
+
+if __name__ == "__main__":
+    sys.exit(main())