Sweep: opt-in gap filling for streams (FILL_GAPS_MS) — CFR re-encode with duplicated frames, raw kept in .src/, timecode carried; default off

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

README.md

@@ -315,11 +315,14 @@ Viewing: the live portal crops the band; Jellyfin shows it as a thin strip at th
 Cross-check when it matters: everyone is in the same voice chat, so audio-waveform sync is sample-accurate.
 Why continuous and not a start burst: a PC clock drifts vs the server (10 ppm ≈ 4 frames over 2 h).
 
-Dropped frames / gaps: OBS keeps stamping frames from its clock, so after a drop the file simply has a hole and
-every frame that exists is still at the right time — the timecode stays correct. The sweep **never re-encodes a
-stream** to fill holes (hours of CPU); the sidecar lists the gaps (`gaps.count`, `total_missing_ms`, first 50
-positions) so editors know where a clip may need a nudge. Premiere preserves timing on such files by default;
-in Resolve check "Timecode" interpretation on gappy clips. Clips (short) are still converted to constant frame rate.
+Dropped frames / gaps: OBS keeps stamping frames from its clock, so after a drop the file has a hole and every
+frame that exists is still at the right time — the timecode stays correct, and players (Jellyfin, the portal)
+hold the last frame across the hole with audio in sync. By default the sweep does **not** re-encode a stream to
+fill holes (hours of CPU on this box); the sidecar lists them (`gaps.count`, `total_missing_ms`, first 50
+positions). Premiere preserves timing on such files; in Resolve check the clip's frame-rate interpretation.
+Opt-in filling: `Environment=FILL_GAPS_MS=1000` in `normalize-sweep.service` makes the sweep re-encode any
+stream whose holes total ≥ 1 s to constant frame rate with duplicated frames (raw kept in `.src/`, timecode
+carried over). Sensible once the box has a hardware encoder (SYS-3). Clips are always converted to CFR.
 
 ## Layout on the server
 

bin/normalize-sweep.sh

@@ -19,6 +19,10 @@ set -uo pipefail
 
 ROOT="${MEDIA_ROOT:-/srv/media}"
 MINS_IDLE=3
+# Gap filling for STREAMS: re-encode to constant frame rate (duplicating frames across dropped-frame holes) when
+# the total missing time is >= this many ms. 0 = never (default; a 3 h re-encode is ~6 h of CPU on the E-2136).
+# Set via systemd Environment=FILL_GAPS_MS=... ; viewers already see held frames either way.
+FILL_GAPS_MS="${FILL_GAPS_MS:-0}"
 MAX_W=2560; MAX_H=1440; MAX_FPS=60
 exec 9>"${LOCK_FILE:-/run/lock/normalize-sweep.lock}"
 flock -n 9 || exit 0
@@ -128,6 +132,13 @@ PYEOF
       tcjson="${TC_JSON:-}"
       log "tc     $src  source=$TC_SOURCE timecode=$TC_TIMECODE"
     fi
+    # opt-in gap filling: switch this stream from remux to a CFR re-encode when the holes add up to enough
+    if (( FILL_GAPS_MS > 0 )) && [[ $verdict == remux && -n $tcjson ]]; then
+      missing=$(python3 -c 'import json,sys; d=json.loads(json.loads(sys.argv[1])); print(d.get("gaps",{}).get("total_missing_ms",0))' "$tcjson" 2>/dev/null || echo 0)
+      if (( missing >= FILL_GAPS_MS )); then
+        verdict=encode; reason="fill-gaps ${missing}ms"; log "gaps   $src  ${missing} ms missing -> CFR re-encode (FILL_GAPS_MS=$FILL_GAPS_MS)"
+      fi
+    fi
   fi
   if [[ $verdict == remux ]]; then
     nice -n 15 ionice -c 3 ffmpeg -nostdin -hide_banner -loglevel error -y -i "$src" \
@@ -152,7 +163,13 @@ PYEOF
       if [[ -n $tcjson ]]; then                        # sidecar: exact capture time (read by the Jellyfin plugin) + drift samples
         printf '%s\n' "$tcjson" > "${out%.*}.json"; chown 1000:1000 "${out%.*}.json" 2>/dev/null
       fi
-      rm -f "$src"; rmdir "$(dirname "$src")" "$titledir" 2>/dev/null || true   # drop .live and the empty title folder
+      if [[ $verdict == encode ]]; then                # gap-filled re-encode: keep the raw recording in the hidden .src/
+        srcdir="$(dirname "$out")/.src"; mkdir -p "$srcdir"; chown 1000:1000 "$srcdir" 2>/dev/null
+        mv -f "$src" "$srcdir/$(basename "$out" .mp4).raw.mp4"
+      else
+        rm -f "$src"
+      fi
+      rmdir "$(dirname "$src")" "$titledir" 2>/dev/null || true   # drop .live and the empty title folder
       log "done   $out"; continue
     elif (( synced )); then
       rel_src="${src#"$stroot"/}"; rel_out="${out#"$stroot"/}"

systemd/normalize-sweep.service

@@ -8,3 +8,4 @@ Type=oneshot
 ExecStart=/usr/local/bin/normalize-sweep.sh
 Nice=15
 IOSchedulingClass=idle
+# Environment=FILL_GAPS_MS=1000   # opt-in: CFR re-encode streams whose dropped-frame holes total >= 1 s (hours of CPU on this box)