ffmpeg-skill 1.5.0 → 1.5.1

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 (`1.5.0`) | any release |
+| `skill.version` | the npm / package.json version (`1.5.1`) | 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`
@@ -83,7 +83,7 @@ on, the line says so.
 ```json
 {
   "contract_version": "1.0",
-  "skill": {"id": "ffmpeg-skill", "version": "1.5.0", "execution_mode": "local", "kind": "execution",
+  "skill": {"id": "ffmpeg-skill", "version": "1.5.1", "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": "1.5.0",
+  "version": "1.5.1",
   "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

@@ -504,8 +504,9 @@ not — a timecode-shaped cue with no fps available is refused rather than misre
 Lines without a time run for `--auto-seconds` (3 s) after the previous cue. `|` is a line break.
 `--animate`/`--karaoke` generate a styled ASS (PlayRes = video size) from the
 SRT/text cues: `pop` is the short-form "bouncy" entrance, `--karaoke` fills each
-word from `--color` to `--highlight-color` evenly across the cue (word timing
-is distributed, not transcribed). The ASS is kept next to the output so the
+word from `--color` to `--highlight-color` across the cue; `--karaoke-timing
+energy` (default) follows the speech loudness in the audio, `even` splits the
+cue equally (word timing is derived, not transcribed). The ASS is kept next to the
 user can hand-tune timings and re-run with `--ass`.
 `--mode burn` (default) renders subtitles into the picture and always
 re-encodes both streams. `--mode mux` copies video and audio untouched and

package/scripts/batch.py

@@ -224,12 +224,20 @@ def main() -> int:
     results = one_pass()
     if args.watch:
         info(f"watching {folder} every {args.watch:g}s (Ctrl-C to stop)")
+        # the shared SIGINT handler (install_signal_handlers) exits 130 with "nothing was written",
+        # which is wrong for a watch that already processed files: while idle between passes,
+        # let Ctrl-C be a plain KeyboardInterrupt so the summary below prints (review 5)
+        import signal
         try:
             while True:
-                time.sleep(args.watch)
+                previous = signal.signal(signal.SIGINT, signal.default_int_handler)
+                try:
+                    time.sleep(args.watch)
+                finally:
+                    signal.signal(signal.SIGINT, previous)
                 results = one_pass()
         except KeyboardInterrupt:
-            pass
+            info("watch stopped")
     done = sum(1 for r in results if r["ok"])
     info(f"{done}/{len(results)} processed, {sum(1 for r in results if r.get('cached'))} from cache")
     if not args.json:

package/scripts/caption.py

@@ -487,9 +487,17 @@ def main() -> int:
     if args.transcribe:
         if not args.input:
             die("--transcribe needs the input video")
-        srt_path = args.write_srt or os.path.splitext(args.input)[0] + ".srt"
-        cues = transcribe(args.input, srt_path, args.language, args.model, args.audio_stream)
-        info(f"wrote {srt_path} ({len(cues)} cues)")
+        # the sidecar goes next to the output like the --text one, not into the source folder
+        # where it silently replaced a hand-written <input>.srt (review 5)
+        srt_path = args.write_srt or os.path.splitext(args.output or default_output(args.input, "captioned"))[0] + ".srt"
+        if STATE.dry_run:
+            cues = []
+            info(f"[dry-run] would transcribe {args.input} and write {srt_path}")
+        else:
+            if os.path.exists(srt_path) and not getattr(args, "overwrite", False):
+                info(f"warning: {srt_path} already exists and will be replaced by the transcript (pass --overwrite to confirm)")
+            cues = transcribe(args.input, srt_path, args.language, args.model, args.audio_stream)
+            info(f"wrote {srt_path} ({len(cues)} cues)")
         args.text = None
     if args.text:
         cues = parse_text_cues(args.text, args.auto_seconds, args.gap, fps_for_tc)
@@ -515,7 +523,7 @@ def main() -> int:
     output = args.output or default_output(args.input, "captioned")
 
     if args.mode == "mux":
-        if not srt_path or (not os.path.exists(srt_path) and not (STATE.dry_run and args.text)):
+        if not srt_path or (not os.path.exists(srt_path) and not (STATE.dry_run and (args.text or args.transcribe))):
             die(f"SRT file not found: {srt_path}")
         codec = mux_subtitle_codec(output)
         # Keep any subtitle track(s) the input already has (e.g. chaining --mode mux once per
@@ -543,7 +551,7 @@ def main() -> int:
         return 0
 
     if (args.animate != "none" or args.karaoke) and not args.ass:
-        cues_for_ass = cues if args.text else parse_srt(srt_path)
+        cues_for_ass = cues if (args.text or args.transcribe) else parse_srt(srt_path)
         ass_path = args.write_ass or os.path.splitext(output)[0] + ".ass"
         w, h = meta["video"]["width"], meta["video"]["height"]
         if meta["video"].get("rotation") in (90, -90, 270, -270):
@@ -563,7 +571,7 @@ def main() -> int:
         if args.fonts_dir:
             vf += f":fontsdir={escape_filter_path(args.fonts_dir)}"
     else:
-        if not srt_path or (not os.path.exists(srt_path) and not (STATE.dry_run and args.text)):
+        if not srt_path or (not os.path.exists(srt_path) and not (STATE.dry_run and (args.text or args.transcribe))):
             die(f"SRT file not found: {srt_path}")
         style = [
             f"FontName={ass_font_name(args.font)}",

package/scripts/check.py

@@ -127,7 +127,7 @@ def main() -> int:
             row("fps", "PASS" if fps <= spec["fps_max"] + 0.01 else "FAIL", f"{fps:g}", f"<= {spec['fps_max']}", "fit.py --fps 30 (drops half the frames of 60 fps motion; fine for talking heads, visible on sports/gaming)")
         row("vfr", "PASS" if not v.get("variable_frame_rate_suspected") else "WARN", "variable" if v.get("variable_frame_rate_suspected") else "constant", "constant", "fit.py --fps N (any re-encode conforms it)")
         if spec["codecs"]:
-            row("video codec", "PASS" if v.get("codec") in spec["codecs"] else "FAIL", v.get("codec"), "/".join(spec["codecs"]), "export.py --preset " + args.platform.replace("shorts", "reels").replace("tiktok", "reels").replace("linkedin", "youtube"),
+            row("video codec", "PASS" if v.get("codec") in spec["codecs"] else "FAIL", v.get("codec"), "/".join(spec["codecs"]), "export.py --preset " + args.platform.replace("shorts", "reels").replace("tiktok", "reels").replace("linkedin", "youtube").replace("broadcast", "prores"),
                 reason="the platform's player may refuse to decode this codec at all, not just look worse")
         pf = v.get("pix_fmt") or ""
         if args.platform in ("reels", "tiktok", "x", "linkedin"):

package/scripts/color.py

@@ -22,7 +22,7 @@ import os
 import sys
 from typing import List
 
-from _common import add_common, analyze_levels, apply_common, emit, aac_args, cfr_args, default_output, die, escape_filter_path, ffmpeg_base, info, probe, run, run_keeping_subtitles, x264_args, X264_PRESETS, fmt_secs
+from _common import STATE, add_common, analyze_levels, apply_common, emit, aac_args, cfr_args, default_output, die, escape_filter_path, ffmpeg_base, info, probe, run, run_keeping_subtitles, x264_args, X264_PRESETS, fmt_secs
 
 TONEMAPS = ["hable", "mobius", "reinhard", "bt2390", "clip", "linear", "gamma"]
 
@@ -293,7 +293,7 @@ def main() -> int:
         tag = "correct"
         # OBSERVED technical measurements (signalstats: luma / saturation distribution), never a
         # "looks better" judgement -- the same primitive probe.py --analyze uses for Log detection.
-        measurements = {"input": analyze_levels(args.input)}
+        measurements = None if STATE.dry_run else {"input": analyze_levels(args.input)}
     else:
         if v.get("hdr") and not args.force:
             die(f"{args.input} is HDR ({v.get('hdr_format')}); a LUT made for SDR applied to PQ/HLG pixels gives a wrong picture "

package/scripts/fit.py

@@ -239,12 +239,13 @@ def main() -> int:
     else:
         cmd += ["-an"]
     cmd += post
-    if abs(factor - 1.0) > 1e-4:
+    if abs(factor - 1.0) > 1e-4 or "-ss" in pre_input:
         # A subtitle/data stream stream-copied by run_keeping_subtitles keeps the source's
         # original timestamps; --method speed retimes video (setpts) and audio (atempo) but has
         # no equivalent way to retime a copied subtitle track, so it would desync from the
         # now-faster/slower picture. Drop them here rather than ship a captions track that lies
-        # about when a line is spoken.
+        # about when a line is spoken. --method trim's -ss moves the timeline the same way: a copied
+        # track kept its cues at the source's times and doubled the output's length (review 5).
         run(cmd + [output])
         dropped_streams = bool(meta.get("subtitle_streams") or meta.get("data_streams"))
     else:

package/scripts/join.py

@@ -68,7 +68,7 @@ def join_audio(args: argparse.Namespace, metas: List[dict]) -> int:
     cmd += ["-filter_complex", ";".join(parts), "-map", "[aout]", "-vn"] + audio_codec_for(output) + [output]
     run(cmd)
     expected = sum(durs) - d * (n - 1)
-    r = probe(output)
+    r = probe(output, role="output")
     a = r.get("audio") or {}
     if not STATE.dry_run:
         if r.get("video"):

package/scripts/multicam.py

@@ -77,6 +77,8 @@ def main() -> int:
         die(f"--analyze-seconds {args.analyze_seconds:g}: the window is decoded into memory; 900 s is the ceiling")
     if args.fps is not None and args.fps <= 0:
         die(f"--fps must be positive, got {args.fps:g}")
+    if not 0 <= args.audio < len(args.inputs):
+        die(f"--audio {args.audio}: inputs are numbered 0..{len(args.inputs) - 1}")
 
     n = len(args.inputs)
     if n < 2:

package/scripts/render.py

@@ -55,7 +55,7 @@ import sys
 from pathlib import Path
 from typing import Any, Dict, List
 
-from _common import STATE, add_common, apply_common, child_args, die, emit, info, probe, run_tool, place_output
+from _common import STATE, add_common, apply_common, child_args, die, emit, info, probe, run_tool, place_output, refuse_output_is_input
 
 HERE = Path(__file__).resolve().parent
 
@@ -133,6 +133,8 @@ def main() -> int:
     if not clips:
         die("project.clips is empty")
     output = rel(proj.get("output") or "final.mp4")
+    # the final stage is a copy from the work dir, so run()'s own guard never sees the sources (review 5)
+    refuse_output_is_input(output, *[rel(c.get("src")) for c in clips if c.get("src")])
     # The default work dir name comes only from the output path, with no PID or timestamp --
     # two concurrent render.py runs targeting the same output (a batch.py "project" recipe
     # processing several files in parallel, or simply running render.py twice by mistake) shared
@@ -363,7 +365,7 @@ def main() -> int:
     else:
         if not STATE.dry_run:
             place_output(current, output)
-        info(f"copied final stage to {output}")
+        info(("[dry-run] would copy" if STATE.dry_run else "copied") + f" final stage to {output}")
     current = output
 
     # ---- check

package/scripts/sequence.py

@@ -1,4 +1,3 @@
-import re
 #!/usr/bin/env python3
 """Turn a numbered image sequence into a video.
 
@@ -16,6 +15,7 @@ Examples:
   python3 sequence.py --dir frames --pattern "*.png" --fps 30 --start-number 1
 """
 import argparse
+import re
 import sys
 import tempfile
 from pathlib import Path