ffmpeg-skill 2.4.0 → 2.4.1

package/docs/contract.md

@@ -21,7 +21,7 @@ The contract is derived from the code that runs, not maintained beside it:
 | Field | Meaning | Changes when |
 |---|---|---|
 | `contract_version` | shape of this document (`1.0`) | a key is renamed, removed or changes meaning |
-| `skill.version` | the npm / package.json version (`2.4.0`) | any release |
+| `skill.version` | the npm / package.json version (`2.4.1`) | any release |
 
 A release that adds a tool or a flag keeps `contract_version`; a breaking change to the
 ToolSpec shape bumps it. Consumers pin on `contract_version` and read `skill.version`
@@ -119,7 +119,7 @@ JSON would have been rewritten for that. The flat keys, typed per tool in `outpu
   "contract_version": "1.0",
   "deprecated": [],
   "removed": [{"what": "...", "since": "1.10.0", "replacement": "...", "removed_in": "2.0.0", "where": "cli | json | mcp | behaviour"}],
-  "skill": {"id": "ffmpeg-skill", "version": "2.4.0", "execution_mode": "local", "kind": "execution",
+  "skill": {"id": "ffmpeg-skill", "version": "2.4.1", "execution_mode": "local", "kind": "execution",
             "entrypoints": {"cli": "...", "mcp": "...", "contract": "...", "doctor": "..."},
             "not_provided": ["AI reasoning", "decisions", "production plans", "project IR", "approvals", "network access", "transcription engine"]},
   "requirements": {"python": ">=3.9 (standard library only)", "ffmpeg": ">=5.0", "ffprobe": ">=5.0"},

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ffmpeg-skill",
-  "version": "2.4.0",
+  "version": "2.4.1",
   "description": "Agent Skill that gives coding agents (Claude Code, Cursor, Codex) a local video editor: 42 FFmpeg tools with a machine-readable contract, contract-derived MCP server, FFmpeg capability detection, probe-first / verify-last workflow. Cut, join, silence removal, fit, captions and karaoke, overlays, motion graphics, HDR to SDR, LUTs, audio clean-up and typed dynamics, sync with drift correction, multicam, loudness, delivery checks, project rendering, batch. No API keys, no cloud, no dependencies.",
   "keywords": [
     "ffmpeg",

package/references/scripts.md

@@ -591,10 +591,10 @@ are always present (`[]` when none) and noted.
 Normalises every clip to one frame size, fps, `yuv420p`, 48 kHz and one
 channel layout (the widest clip's -- a 5.1 clip keeps 5.1 -- or `--channels`;
 silent track generated for clips without audio), then chains `xfade` +
-`acrossfade`. With a transition each clip has one length for picture and sound
+`acrossfade` (or `concat` for `--transition none`). Every clip has one length for picture and sound
 -- the video stream's, or the audio's when it runs more than a frame longer --
 and the shorter stream is padded (silence / last frame held), so every clip's
-sound stays with its picture. Output length = sum of clip lengths −
+sound stays with its picture and a plain cut leaves no hole in the video. Output length = sum of clip lengths −
 transition × (n−1); `verified` checks the output's video-stream length against it. Clips must be
 longer than 2 × the transition. Use `--transition none` for a plain cut.
 A subtitle/data track in the source is not carried into the retimed/concatenated

package/scripts/join.py

@@ -81,7 +81,7 @@ def unpending_length(durs: List[float], d: float) -> Optional[float]:
 
 
 def clip_length(meta: Dict[str, Any], fps: float) -> float:
-    """The one length a clip holds in a crossfaded join, for its picture and its sound alike: the
+    """The one length a clip holds in a join, for its picture and its sound alike: the
     video stream's, or the audio stream's when the sound runs more than a frame past the picture
     (narration is never cut; an AAC tail adds no frame). The container duration (audio priming,
     a longer track) is only the fallback when a stream length is unknown (a pending input)."""
@@ -443,9 +443,12 @@ def main() -> int:
     note_short_segments(args.inputs, metas, MIN_SEGMENT_FRAMES / fps, f"{MIN_SEGMENT_FRAMES} frames at {fps:g} fps")
     durs = [m.get("duration") or 0.0 for m in metas]
     d = args.duration if args.transition != "none" else 0.0
-    # a crossfaded join gives each clip one length for both streams, so the offsets that place
-    # every picture also place its sound; the plain cut (concat) keeps the streams paired itself
-    lens = [clip_length(m, fps) for m in metas] if d else durs
+    # every clip gets one length for both streams, so whatever places the next clip -- xfade's
+    # offsets, or the concat filter, which starts it after the LONGER stream of this one -- places
+    # its picture and its sound together. The plain cut used to take the raw streams, and a sound
+    # past the picture (a music bed padded to the container, even a 20 ms AAC tail) left a hole in
+    # the video there.
+    lens = [clip_length(m, fps) for m in metas]
     place_silent(lens, d)
     for p, dur in zip(args.inputs, lens):
         if d and dur <= d * 2 and not STATE.dry_run:
@@ -497,18 +500,17 @@ def main() -> int:
         parts.append(f"[{i}:v]{geo},setsar=1,fps={fps:g},format={pixfmt},settb=AVTB[v{i}]")
         parts.append(f"[{audio_src[i]}]aformat=sample_rates=48000:channel_layouts={layout},asetpts=PTS-STARTPTS[a{i}]")
 
+    # pad the shorter stream to the clip's length: the audio with silence, the picture by holding
+    # its last frame, then cut both there -- each clip boundary is then the same for both chains
+    for i in range(n):
+        vlen = (metas[i].get("video") or {}).get("duration") or lens[i]
+        hold = f"tpad=stop_mode=clone:stop_duration={lens[i] - vlen:.3f}," if lens[i] > vlen else ""
+        parts.append(f"[v{i}]{hold}trim=duration={lens[i]:.3f}[vp{i}]")
+        parts.append(f"[a{i}]apad=whole_dur={lens[i]:.3f},atrim=duration={lens[i]:.3f}[ap{i}]")
     if args.transition == "none":
-        chain = "".join(f"[v{i}][a{i}]" for i in range(n))
+        chain = "".join(f"[vp{i}][ap{i}]" for i in range(n))
         parts.append(f"{chain}concat=n={n}:v=1:a=1[vout][aout]")
     else:
-        # pad the shorter stream to the clip's length: the audio with silence, the picture by
-        # holding its last frame, then cut both there -- each xfade and acrossfade then starts
-        # at the same clip boundary instead of the audio chain drifting by every clip's gap
-        for i in range(n):
-            vlen = (metas[i].get("video") or {}).get("duration") or lens[i]
-            hold = f"tpad=stop_mode=clone:stop_duration={lens[i] - vlen:.3f}," if lens[i] > vlen else ""
-            parts.append(f"[v{i}]{hold}trim=duration={lens[i]:.3f}[vp{i}]")
-            parts.append(f"[a{i}]apad=whole_dur={lens[i]:.3f},atrim=duration={lens[i]:.3f}[ap{i}]")
         vprev, aprev = "vp0", "ap0"
         offset = 0.0
         for i in range(1, n):
@@ -529,11 +531,11 @@ def main() -> int:
                            "by its measured length")
     output = args.output or default_output(args.inputs[0], "joined", "mp4")
     cmd += ["-filter_complex", ";".join(parts), "-map", "[vout]", "-map", "[aout]"]
-    if d:
-        # the fps filter already made the picture constant-rate and xfade places every frame: FFmpeg
-        # 5.1's default cfr output mode still duplicated the last one to meet the AAC tail (a 51-frame
-        # dissolve came out 52), which newer builds no longer do -- pass the frames through as built
-        cmd += ["-fps_mode", "passthrough"]
+    # the fps filter already made the picture constant-rate, and the per-clip trims (then xfade or
+    # concat) place every frame: FFmpeg 5.1's default cfr output mode still duplicated the last one
+    # to meet the AAC tail (a 51-frame dissolve came out 52), which newer builds no longer do -- pass
+    # the frames through as built, for a plain cut as much as for a transition
+    cmd += ["-fps_mode", "passthrough"]
     cmd += video_args(hdr_meta or metas[0], args.crf, args.preset) + aac_args() + [output]
     run(cmd)
     expected = unpending_length(lens, d)