ffmpeg-skill 2.8.3 → 2.8.5

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 (`2.8.3`) | any release |
+| `skill.version` | the npm / package.json version (`2.8.5`) | 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": "2.8.3", "execution_mode": "local", "kind": "execution",
+  "skill": {"id": "ffmpeg-skill", "version": "2.8.5", "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"},
@@ -379,7 +379,9 @@ and no detector can name it, a Whisper engine that can run takes it (whisper.cpp
 `-l auto`: its own default is English). Parakeet then runs only on English *assumed* -- when no
 Whisper engine is installed, or every one failed, or `--model` names an English-only Parakeet
 model -- and the result's top-level `notes` says the transcript is wrong if the speech is not
-English; a multilingual (v3) Parakeet model assumes nothing and gets no note. The result's
+English; a multilingual (v3) Parakeet model assumes nothing and gets no note. Every whisper.cpp
+command that writes a transcript is also passed `-mc 0` (no previous-text context, so one
+hallucinated line is not repeated to the end of the file); its language detection is not. The result's
 `transcription` says which engine, model and routing decision produced the cues (in every
 `--mode`, `mux` included).
 Every engine transcribes on the machine running the skill, and the audio is never uploaded. The

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ffmpeg-skill",
-  "version": "2.8.3",
+  "version": "2.8.5",
   "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

@@ -1023,7 +1023,8 @@ top-level `notes` then says so: that transcript is wrong for non-English speech,
 `--engine parakeet-mlx|parakeet.cpp|whisper.cpp|faster-whisper|openai-whisper` forces one (a
 missing one is `kind: missing_tool`; an installed one that fails is `kind: input`, `reason:
 engine_failed`, with its own error line in `detail`). Without a language whisper.cpp is passed
-`-l auto` (its own default is English), else the named or detected language. `--model` is the
+`-l auto` (its own default is English), else the named or detected language, and `-mc 0` (no
+previous-text context, so one hallucinated line is not repeated to the end of the file; #318). `--model` is the
 whisper model; a Parakeet engine takes it only when it names a Parakeet model
 (`mlx-community/parakeet-*` or a `.gguf`), else `PARAKEET_MODEL` / `PARAKEET_CPP_MODEL`, else the
 English `tdt-0.6b-v2`. A non-English `--language` on an English-only Parakeet model is refused; a

package/scripts/_common/asr.py

@@ -28,6 +28,11 @@ WHISPER_ENGINES = ("whisper.cpp", "faster-whisper", "openai-whisper")
 ASR_ENGINES = PARAKEET_ENGINES + WHISPER_ENGINES
 ENGINE_CHOICES = ("auto",) + ASR_ENGINES
 ASR_ENGINE_ENV = "FFMPEG_SKILL_ASR_ENGINE"
+# whisper.cpp conditions every window on the text before it, and once a hallucinated line is in that
+# context it can repeat it to the end of the file (#318: one sentence ~300 times, ~7 minutes of speech
+# lost). -mc / --max-context 0 keeps no previous text. Given to the commands that write a transcript,
+# not to language detection (-dl), which writes none.
+WHISPER_CPP_NO_CONTEXT = ["-mc", "0"]
 PARAKEET_MLX_DEFAULT_MODEL = "mlx-community/parakeet-tdt-0.6b-v2"
 # Every engine transcribes on this machine: the audio is never uploaded. Three of them fetch
 # their model weights the first time they run, which the hint says, so "offline" is never
@@ -342,7 +347,7 @@ def _transcribe_in(tmpdir: str, video: str, out_srt: str, language: Optional[str
         model_path = _whisper_cpp_model(model)
         base = os.path.join(tmpdir, "out")
         # whisper.cpp's own default is -l en: without "auto" it decodes any speech as English
-        cmd = [cli, "-m", model_path, "-f", wav, "-osrt", "-of", base, "-l", lang or "auto"]
+        cmd = [cli, "-m", model_path, "-f", wav, "-osrt", "-of", base, "-l", lang or "auto", *WHISPER_CPP_NO_CONTEXT]
         proc = _asr_run(cmd, subprocess, "whisper.cpp")
         if proc.returncode == 0 and os.path.exists(base + ".srt"):
             info(f"transcribed with whisper.cpp ({os.path.basename(cli)}, model {os.path.basename(model_path)})")
@@ -995,7 +1000,8 @@ def transcribe_words_result(video: str, language: "Optional[str]" = None, model:
             model_path = _whisper_cpp_model(model)
             base = os.path.join(tmpdir, "out")
             # whisper.cpp's own default is -l en: without "auto" it decodes any speech as English
-            cmd = [cli, "-m", model_path, "-f", wav, "--output-json-full", "-of", base, "-l", lang or "auto"]
+            cmd = [cli, "-m", model_path, "-f", wav, "--output-json-full", "-of", base, "-l", lang or "auto",
+                   *WHISPER_CPP_NO_CONTEXT]
             proc = _asr_run(cmd, _subprocess, "whisper.cpp")
             if proc.returncode == 0 and os.path.exists(base + ".json"):
                 words = _words_from_whisper_cpp_json(base + ".json")

package/scripts/cut.py

@@ -1025,8 +1025,13 @@ def _join_chunk(src: str, segments: List[Tuple[float, float]], dst: str, meta: d
         # land on that keyframe and lose its leading frames -- measured: -ss 9.9 on a keyint-60
         # HEVC file began at 10.0 (seek_keyframe measures where a copy lands). Likewise an input -t stops reading at s+d in decode order and would drop
         # B-frames that display inside the segment, so it reads a second past the end.
+        # -reinit_filter 0: every input is the same file, so the graph keeps the format it was
+        # configured with. A later input that decodes across a mid-stream colour-tag change (an
+        # in-band SPS going from untagged to bt470bg, say) made FFmpeg 8.1 rebuild the graph at
+        # that input's buffer source and deadlock at 0% CPU (#316); the output's colour tags are
+        # written explicitly (video_args), so the retag is a label here, not a conversion.
         m = min(SEEK_MARGIN, s)
-        cmd += ["-ss", f"{s - m:.6f}", "-t", f"{m + d + 1.0:.6f}", "-i", src]
+        cmd += ["-ss", f"{s - m:.6f}", "-t", f"{m + d + 1.0:.6f}", "-reinit_filter", "0", "-i", src]
         a, b, half = m, m + d, 0.0
         if has_v and rate:
             # Both streams are cut on the source's frame grid: from the first frame at or after the