ffmpeg-skill 2.11.0 → 2.12.1

package/scripts/_contract.py

@@ -425,6 +425,98 @@ ERROR_REASONS = {
     "plan_unknown_tool": "render.py PLAN: the plan names no tool render.py can run; details: {plan, plan_sha256, checked_at, tool, audit_log}",
     "plan_cwd_missing": "render.py PLAN: the directory the plan was made in is gone; details: {plan, plan_sha256, checked_at, cwd, audit_log}",
     "plan_argv_invalid": "render.py PLAN: argv is not a list; details: {plan, plan_sha256, checked_at, argv_type, audit_log}",
+    "encoder_missing": "--codec av1/prores: the build's encoder list was read and has no encoder for the codec (kind missing_tool); details: {codec, encoders}",
+    "encoder_list_unreadable": "--codec av1/prores: the build's encoder list could not be read, so whether it has the encoder is unknown (kind ffmpeg); details: {codec, encoders, error}",
+}
+
+# The codes of the collector's records (docs/design-decisions.md, "Nothing happens silently"):
+# code -> (bucket, what it records). Every warn()/record_fallback()/record_skip() literal under
+# scripts/ is listed here under its bucket (a test reads the sources), so a caller can switch on
+# a code the contract publishes.
+DIAGNOSTIC_CODES = {
+    # infrastructure (part 1)
+    "stale_lock_taken_over": ("fallbacks", "a dead or past-deadline writer's output lock was taken over; {lock, output, pid, pid_alive, deadline, why}"),
+    "output_unlocked": ("warnings", "no output lock could be created and the run went on without one; {lock, output, error}"),
+    "lock_deadline_unset": ("warnings", "the lock's deadline (its mtime) could not be set; {lock, error}"),
+    "audit_log_unwritable": ("warnings", "an audit record could not be appended; never fails the run; {path, event, error}"),
+    "plan_unbound_inputs": ("warnings", "render.py PLAN: inputs that did not exist when the plan was made, so were not checked; {paths}"),
+    # the runner
+    "odd_dimensions_scaled_even": ("fallbacks", "an encode that failed on odd dimensions was run again scaled to even ones (the frame loses a row or column); {output, scale}"),
+    "measurement_input_pending": ("skipped", "--dry-run: a measurement skipped because its input is an earlier stage's output that does not exist yet; {path}"),
+    "non_av_streams_dropped": ("fallbacks", "the subtitle/data streams could not be copied, so the encode ran again without them (dropped_non_av_streams: true); {output, returncode, error: the first attempt's last stderr lines}"),
+    "ffmpeg_list_unreadable": ("warnings", "`ffmpeg -encoders` / `-bsfs` could not be read; what needs the list says so instead of 'the build lacks it'; {list, tool, error}"),
+    "timeout_env_invalid": ("warnings", "FFMPEG_SKILL_TIMEOUT was not a number (the default was used) or was negative (read as 0, no limit); {value, timeout}"),
+    # encoder decisions
+    "av1_encoder_libaom": ("fallbacks", "--codec av1 on a build without libsvtav1: libaom-av1 encoded instead; {wanted, used}"),
+    "crf_clamped": ("warnings", "the CRF handed to the encoder was above its maximum and was capped (the HEVC HDR line adds 2); {encoder, requested, asked, used}"),
+    # fonts and text
+    "font_substituted": ("fallbacks", "the asked font family is not installed: fontconfig or the Windows Fonts folder gave another (font_used names it); {asked, file, family, via}"),
+    "font_lacks_script": ("warnings", "an explicit --font does not cover the text's script and is kept as asked; {font, script}"),
+    "font_coverage_unverified": ("warnings", "whether a font covers the text's script could not be checked (no fontconfig / fc-scan); {script, fonts_dir?}"),
+    "fonts_dir_lacks_script": ("fallbacks", "no face in --fonts-dir covers the text's script, so one was picked by script; {fonts_dir, script}"),
+    "emoji_monochrome": ("warnings", "emoji drawn by the text font (monochrome at best): no colour path here"),
+    "emoji_stripped": ("warnings", "overlay.py --emoji none: emoji removed from the drawn text; {mode}"),
+    "emoji_assets_missing": ("warnings", "--emoji-assets has no PNG for these clusters; the text font draws them; {missing}"),
+    "drawtext_newline_glyph": ("warnings", "graphics.py --text-render drawtext on FFmpeg 8.0-8.0.1/8.1.0: a box is drawn at each line break of a multi-line label; {text_render}"),
+    "timeline_parse_failed": ("warnings", "render.py --export-timeline: the written file does not read back as its format (the parse step is ok: false); {path, format, error}"),
+    # captions
+    "ass_lines_unshifted": ("warnings", "caption.py --ass --offset: Dialogue lines whose timestamps could not be read were copied unshifted; {path, count, offset}"),
+    "ass_lines_malformed": ("warnings", "caption.py --ass: Dialogue lines that could not be read (fields or start/end) are not counted as cues; {path, count}"),
+    "cues_outside_video": ("warnings", "caption.py: cues wholly outside the video are not drawn; {count, duration}"),
+    "asr_language_assumed": ("warnings", "--transcribe: the language was assumed (English) and the transcript is wrong if it is not"),
+    # analysis
+    "drift_correction_skipped": ("skipped", "sync.py --fix-drift not applied for a source (drift_skipped_reason); {path, reason: too_short | low_confidence, ...}"),
+    "sync_low_confidence": ("warnings", "sync.py / multicam.py: a source's offset has a correlation confidence below 0.1; {path, confidence}"),
+    "cropdetect_windows_failed": ("warnings", "cropdetect.py: sampled windows ffmpeg could not decode (windows_failed); {failed, windows, starts}"),
+    "filler_words_untimed": ("warnings", "silence.py --filler: listed words in the transcript with no usable timing were not removed (filler.matched_untimed); {count}"),
+    "filler_removal_caution": ("warnings", "silence.py --filler: a removed word that is often an ordinary word, or a discourse marker added with --filler-extra (also in filler.warnings)"),
+    # media and defaults
+    "silent_track_mixed": ("warnings", "audio.py --on-silent warn: a silent track was mixed anyway; {tracks}"),
+    "silent_inputs": ("warnings", "join.py --on-silent warn: silent inputs joined anyway (silent); {count}"),
+    "silent_input": ("warnings", "waveform.py: the input audio is silent and the visualisation is a flat line; {path, peak_db}"),
+    "short_inputs": ("warnings", "join.py: inputs shorter than two frames joined anyway (short_segments); {count}"),
+    "duplicate_inputs": ("warnings", "join.py: an input listed more than once is joined each time (duplicates); {count}"),
+    "sequence_gap": ("warnings", "sequence.py: a frame is missing from the numbering and the frames after it are not in the video; {missing, frames_left_out, first_left_out}"),
+    "memory_heavy": ("warnings", "reverse.py / loop.py --boomerang hold every decoded frame in memory and this input is large"),
+    "dovi_not_detected": ("warnings", "color.py --strip-dovi on a stream with no Dolby Vision metadata: unregistered SEI removed anyway"),
+    "frame_from_export_preset": ("warnings", "render.py: frame.width/height taken from the export preset for a frame given only an aspect; {preset, width, height}"),
+    "normalize_on_by_default": ("warnings", "render.py: a platform export preset with no loudness stage got export.py --normalize by default; {preset}"),
+    # degraded or partial results (part 2)
+    "colour_not_converted": ("warnings", "export.py: an HDR or wide-gamut source written by a preset that tags SDR BT.709 without converting it; {preset, hdr_format}"),
+    "output_audio_silent": ("warnings", "export.py: the written audio is silent (-inf LUFS), so no gain meets the platform's loudness; {platform}"),
+    "loudness_outside_spec": ("warnings", "export.py: the written file's loudness is outside the platform's spec (normalized: after --normalize too); {platform, lufs, tp, normalized}"),
+    "camera_not_started": ("fallbacks", "multicam.py: a range asked for a camera that had not started; camera 0 played it ({start, end, requested_camera, camera, starts_at}); `cuts` names the camera rendered"),
+    "loudness_not_measured": ("warnings", "export.py: the written file's loudness could not be read, so the platform's loudness was not verified (loudness.ok null, a failing loudness verification step)"),
+    "loudness_no_audio": ("skipped", "export.py: a platform preset's loudness check, on a source with no audio"),
+    "report_section_missing": ("warnings", "report.py: a loudness, compliance or contact-sheet section could not be built (also a failing verification step naming the section)"),
+    "report_section_dry_run": ("skipped", "report.py --dry-run draws no contact sheet"),
+    "check_dry_run": ("skipped", "render.py --dry-run does not run a check stage or a plan's check step"),
+    "check_no_output": ("skipped", "render.py PLAN: the tool reported no output for the plan's check step"),
+    "check_nothing_to_check": ("skipped", "render.py: a \"check\" stage with neither \"platform\" nor \"content\": true"),
+    "check_output_unparsed": ("warnings", "render.py: check.py printed no JSON document; `check` is a failure document (error.reason check_output_unparsed)"),
+    "cache_entry_damaged": ("warnings", "render.py --cache: a sidecar that does not parse or an artifact of the wrong size (also an audit line in the cache directory); the stage runs again"),
+    "cache_store_failed": ("warnings", "render.py --cache: a stage's artifact could not be stored; the run is unaffected"),
+    "cache_input_unreadable": ("warnings", "render.py --cache: an input could not be fingerprinted and is keyed as \"missing\""),
+    "cache_ffmpeg_banner_unreadable": ("fallbacks", "render.py --cache: the ffprobe banner could not be read; keyed on major.minor, so builds of one release share entries"),
+    "cache_result_unrecorded": ("skipped", "render.py --cache: a hit from an entry that recorded no stage result, so what that stage verified is unknown"),
+    "recipe_project_unreadable": ("warnings", "batch.py: recipe.project could not be read; the cache key covers the recipe only"),
+    "batch_cache_reset": ("warnings", "batch.py: .ffskill_cache.json did not parse and was started empty (also an audit line)"),
+    "batch_cache_output_changed": ("warnings", "batch.py: a cached item's output was replaced or edited since the batch wrote it; the item runs again"),
+    "batch_cache_entry_unverifiable": ("warnings", "batch.py: a cache entry from before output identities; the item runs again"),
+}
+
+
+# `font_used` on the tools that draw text: which font the text was drawn with, so a run that
+# drew with a substitute says so (with a font_substituted fallback)
+FONT_USED_SCHEMA = {
+    "type": "object",
+    "description": "the font the text was drawn with: {asked, file, family, how, substituted, via?, fonts_dir?}. how: font_file (the "
+                   "caller's file), script (picked to cover the text's script), resolved (the asked family resolved to a file by "
+                   "fc-match or the Windows Fonts folder; for libass, the file fontconfig picks for the family), by_name (no file "
+                   "resolved: ffmpeg/libass look the family up themselves, file null), fonts_dir (caption.py: the family looked up "
+                   "in --fonts-dir first), ass_styles (caption.py --ass: the file's own styles name the fonts). substituted: the "
+                   "file is not the asked family (also a diagnostics.fallbacks entry, font_substituted). overlay.py: with --text; "
+                   "grid.py: with --label auto",
 }
 
 
@@ -442,7 +534,7 @@ def output_schema(name: str, meta: Dict[str, Any], hw: bool = False) -> Dict[str
             "hw": {"type": "object", "description": "present when VideoToolbox was asked for (--hw, $FFMPEG_SKILL_HW, a render.py stage, a batch.py item), on export.py when $FFMPEG_SKILL_HW=1 is set but its delivery preset does not take it, and when this ffmpeg build has no libx264/libx265 and an encode ran on VideoToolbox instead: {requested: whether this run's encodes were asked onto VideoToolbox (false for that export, and for the build without libx264/libx265), source: flag|env|auto (auto: nobody asked, the build has no libx264/libx265 and this Apple Silicon machine ran VideoToolbox in its place), used: true|false whether the encoder that ran last is VideoToolbox, null under --dry-run (nothing ran) and when this process ran no encode itself (batch.py: its stages are child processes; its top-level hw gathers the items' requested/source/fallback/notes and each results row carries its item's encoder and hw), fallback: a job VideoToolbox refused (encoder open or compression session failure; nothing else is retried) was re-encoded on the CPU, notes: why an encode stayed on or fell back to the CPU, and, when $FFMPEG_SKILL_HW chose the GPU and it ran, what that costs and that --no-hw opts out}. A VideoToolbox encode also adds a top-level notes line: its quality is not CRF-equivalent. A kind: ffmpeg failure under --hw / $FFMPEG_SKILL_HW carries encoder and hw too"},
             "plan": {"type": "string", "description": "with --plan FILE: the plan document written (the run itself is a dry run)"},
             "verified": {"type": "boolean", "description": "true only when the artifact was written, probed, and every self-check the tool ran (verification) met its target; false under --dry-run"},
-            "verification": {"type": "array", "items": {"type": "object", "properties": {"step": {"type": "string"}, "ok": {"type": "boolean"}}}, "description": "what the tool itself verified: probe, plus loudness (loudness.py, export platform presets) or check (render)"},
+            "verification": {"type": "array", "items": {"type": "object", "properties": {"step": {"type": "string"}, "ok": {"type": "boolean"}, "stage": {"type": "string"}}}, "description": "what the tool itself verified: probe, plus loudness (loudness.py, export platform presets; ok false with reason not_measured when it could not be read), check (render), report.py's sections (loudness, compliance, contact_sheet) and batch.py's items (item). render.py also lists every stage's own steps beyond its artifact probe, tagged with `stage` (a cached stage's as recorded), so its `verified` is the conjunction of every stage's"},
             "diagnostics": DIAGNOSTICS_SCHEMA}
     extra: Dict[str, Any] = {}
     if name == "check":
@@ -451,7 +543,7 @@ def output_schema(name: str, meta: Dict[str, Any], hw: bool = False) -> Dict[str
                  "checks": {"type": "array", "items": {"type": "object", "properties": {"check": {"type": "string", "description": "row name; --content adds black, frozen and silence; audio FAILs when the track is present but silent (peak <= -50 dBFS)"}, "status": {"enum": ["PASS", "WARN", "FAIL"]}, "value": {}, "expected": {}, "fix": {"type": "string"}, "kind": {"enum": ["format", "judgement"]}}}}}
     elif name == "caption":
         extra = {"transcription": {"type": "object", "description": "with --transcribe: {engine, model, language, routing (why auto chose it), detected_language when auto detected it}; when auto ran the English-only Parakeet model on English assumed, notes says so"},
-                 "caption": {"type": "object", "description": "cue layout: shifted / wrapped / rebalanced / split / extended / dropped counts, plus wrap ('phrase' or 'measured'), phrase_breaks (1.16), broken_inside_word -- atoms hard-sliced at the column edge because they did not fit alone even at the size floor (1.18.4) -- and overlong -- now residual: a single character alone wider than the column. Burn mode: cues_burned -- non-blank cues that overlap [0, duration] and are drawn -- and cues_outside -- non-blank cues wholly outside it (2.2.6); a burn with no visible cue is refused, kind input"},
+                 "caption": {"type": "object", "description": "cue layout: shifted / wrapped / rebalanced / split / extended / dropped counts, plus wrap ('phrase' or 'measured'), phrase_breaks (1.16), broken_inside_word -- atoms hard-sliced at the column edge because they did not fit alone even at the size floor (1.18.4) -- and overlong -- now residual: a single character alone wider than the column. Burn mode: cues_burned -- non-blank cues that overlap [0, duration] and are drawn -- and cues_outside -- non-blank cues wholly outside it (2.2.6); a burn with no visible cue is refused, kind input. --ass: ass_malformed -- Dialogue lines that could not be read and are not counted -- and with --offset ass_shifted / ass_unshifted -- lines moved, and lines whose timestamps could not be read, copied as they were (each count above 0 is also a diagnostics.warnings entry)"},
                  "tracks": {"type": "array", "description": "--mode mux: one entry per subtitle stream in the output ({index, file, language, title, codec, default, cues, kept_from_input}); a stream the input already carried has file null and kept_from_input true (1.16)"},
                  "subtitle_tracks": {"type": "integer", "description": "--mode mux: how many subtitle streams the output carries"},
                  "emoji": {"type": "object", "description": "how the emoji in the text were drawn (mode, overlays, missing)"},
@@ -473,15 +565,18 @@ def output_schema(name: str, meta: Dict[str, Any], hw: bool = False) -> Dict[str
     elif name == "silence":
         extra = {"silences": {"type": "array"}, "keep": {"type": "array"}, "input_duration": {"type": "number"}, "kept_duration": {"type": "number"}, "removed_seconds": {"type": "number"},
                  "speech_aware": {"type": "object", "description": "--speech-aware (1.18): {min_silence, floor, breaths_kept, breaths_kept_seconds, breaths}"},
-                 "filler": {"type": "object", "description": "--filler: {lang, source (whisper-json:FILE | whisper:ENGINE | parakeet:ENGINE), engine, transcription (with --transcribe: {engine, model, language, routing}), removed, removed_count, ...}"},
+                 "filler": {"type": "object", "description": "--filler: {lang, source (whisper-json:FILE | whisper:ENGINE | parakeet:ENGINE), engine, transcription (with --transcribe: {engine, model, language, routing}), removed, removed_count, matched_untimed (listed words in the transcript with no usable timing, not removed), matched_too_long (listed words longer than a filler, kept), ...}"},
                  "notes": {"type": "array", "items": {"type": "string"}, "description": "--filler --transcribe under --engine auto: present when the English-only Parakeet model ran on English assumed (no --filler-lang, no language detected, no Whisper engine installed or none that succeeded); the transcript is wrong if the speech is not English"}}
     elif name == "sync":
         extra = {"reference": {"type": "string"}, "second": {"type": "string"}, "offset_seconds": {"type": "number"}, "confidence": {"type": "number"}, "meaning": {"type": "string"}, "drift": {"type": "object"},
-                 "sources": {"type": "array", "description": "1.18: [{path, offset_s, confidence, drift_ppm}], one per SOURCE; the only per-source shape once more than one SOURCE is given"}}
+                 "sources": {"type": "array", "description": "1.18: [{path, offset_s, confidence, drift_ppm}], one per SOURCE; the only per-source shape once more than one SOURCE is given; with --fix-drift each also carries drift_skipped_reason"},
+                 "drift_skipped_reason": {"type": ["string", "null"], "enum": ["too_short", "low_confidence", None], "description": "--fix-drift, one SOURCE: why the drift correction was not applied (too_short: no tail window far enough from the head; low_confidence: the tail did not correlate), null when it was; also a diagnostics.skipped entry, drift_correction_skipped"}}
     elif name == "look":
         extra = {"outputs": {"type": "array", "items": {"type": "string"}}}
     elif name == "render":
-        extra = {"stages": {"type": "array", "items": {"type": "string"}}, "check": {"type": ["object", "null"]},
+        extra = {"stages": {"type": "array", "items": {"type": "string"}}, "check": {"type": ["object", "null"], "description": "check.py's document for a \"check\" stage with a platform, \"content\": true, or both; when check.py printed none, a failure document with error.reason check_output_unparsed"},
+                 "cache": {"type": ["object", "null"], "description": "--cache: {dir, ffmpeg, hits, misses, miss_reasons: [{stage, reason: not_cached|sidecar_missing|artifact_missing|sidecar_corrupt|artifact_truncated|no_output_path, ...}], saved_seconds, entries, would_hit (--dry-run)}"},
+                 "notes": {"type": "array", "items": {"type": "string"}, "description": "each stage's own notes, prefixed with its tool (\"export: loudness ... is outside x's ...\")"},
                  "plan": {"type": "string", "description": "when the argument was a plan.json (written by <tool> --plan): its path"},
                  "plan_sha256": {"type": ["string", "null"], "description": "plan execution: sha256 of the plan file as executed"},
                  "unbound_inputs": {"type": "array", "items": {"type": "string"}, "description": "plan execution: inputs that did not exist when the plan was made, so carry no fingerprint and were not checked (also a diagnostics.warnings entry, code plan_unbound_inputs)"},
@@ -491,16 +586,19 @@ def output_schema(name: str, meta: Dict[str, Any], hw: bool = False) -> Dict[str
                               "transition_frames, music, markers, notes, and not_exported (what the project asks for that an "
                               "editor timeline cannot carry)"}}
     elif name == "verify":
-        extra = {"report": {"type": ["string", "null"]}, "files": {"type": "array"}, "failed": {"type": "integer"}, "total": {"type": "integer"}}
+        extra = {"report": {"type": ["string", "null"]},
+                 "files": {"type": "array", "description": "one entry per file: {file, probe, steps, skipped}. A step is {step, ok, seconds, error (one line, for the table)}, plus the tool's verified when it completed, and on a failure its own kind, reason, message, details and exit_code (reason step_timeout or step_output_unparsed when the tool printed no failure document); skipped lists the steps that do not apply as {step, reason: quick|no_video|no_audio|not_hdr|not_multichannel|input_unreadable, message}"},
+                 "failed": {"type": "integer"}, "total": {"type": "integer"}}
     elif name == "batch":
-        extra = {"results": {"type": "array", "description": "one row per input; a row whose recipe ran cut.py carries cut_reencoded (each cut.py call's reencoded) and cut_reencode_reasons (each reason those calls named, once per call)"},
+        extra = {"results": {"type": "array", "description": "one row per input, every input (an interrupted batch included): ok (every step completed), verified (every step also verified what it wrote; false under --dry-run) and unverified ([{step, tool, failed}] naming the steps that did not); a failed row's error {step, tool, kind, message, code, reason, details, hint, exit_code} from the failing step's own document; diagnostics from its steps (tagged with step); cache_miss {reason: output_missing|output_changed|entry_unverifiable, ...} when a cache entry was not served; skipped \"timeout\" or \"interrupted\" for an item that never started and interrupted true for one stopped while running. A row whose recipe ran cut.py carries cut_reencoded (each cut.py call's reencoded) and cut_reencode_reasons (each reason those calls named, once per call)"},
                  "processed": {"type": "integer"}, "total": {"type": "integer"},
                  "cut_stream_copy": {"type": ["object", "null"], "description": "cut.py calls across the folder: {calls, stream_copy, reencoded, stream_copy_rate}; null when no cut.py step ran"},
                  "cut_reencode_reasons": {"type": ["object", "null"], "description": "how many cut.py calls named each reencode_reason ({} when none re-encoded); a re-encoded call whose row came from a cache an earlier 2.x batch wrote, which recorded no reasons, counts as unknown; null when no cut.py step ran"}}
     elif name == "report":
-        extra = {"report": {"type": "string"}, "check": {"type": ["object", "null"]}}
+        extra = {"report": {"type": "string"}, "check": {"type": ["object", "null"], "description": "check.py's document for --platform; null when it was not asked for or could not run (a failing compliance verification step then says why)"}}
     elif name == "export":
-        extra = {"loudness": {"type": "object", "description": "platform presets with audio: the written file's lufs/tp against the platform's target_lufs/target_tp, ok true when inside the spec; normalized true when --normalize ran loudness.py on the file; silent true (lufs \"-inf\", ok false, no normalize) when the written audio is silent"},
+        extra = {"loudness": {"type": "object", "description": "platform presets with audio: the written file's lufs/tp against the platform's target_lufs/target_tp, ok true when inside the spec; normalized true when --normalize ran loudness.py on the file; silent true (lufs \"-inf\", ok false, no normalize) when the written audio is silent; measured false (lufs, tp and ok null, reason not_measured) when the measurement could not be read"},
+                 "trimmed": {"type": "object", "description": "present when the source was longer than the preset's platform maximum and the export was cut to it (no --allow-long): {from, to} in seconds; notes says so too"},
                  "notes": {"type": "array", "items": {"type": "string"}}}
     elif name == "loudness":
         extra = {"measured": {"type": "object", "description": "the loudnorm measurement of the input (input_i, input_tp, input_lra, input_thresh, target_offset); with --measure-only it is the whole result"},
@@ -537,6 +635,9 @@ def output_schema(name: str, meta: Dict[str, Any], hw: bool = False) -> Dict[str
                  "lossless_alternative": {"type": ["string", "null"], "description": "when a lossless cut re-encoded because of the keyframe snap: the --start that would stream-copy instead, and how far it is from the request"},
                  "join_check": {"type": ["object", "null"], "description": "--segments video stream-copy join: the written file measured by demuxing, {packets, expected_packets, max_step_seconds, audio_offset_ms, audio_parts_checked, ok}. expected_packets counts the source's video packets from each part's start keyframe to its end (or the end of the video); max_step_seconds is the largest presentation step (null when vfr_check measured anything but sampled_cfr, e.g. a --vfr-guard off join of variable timing, which checks the count only), and each step at a join must be the step its parts predict within 1 ms; audio_offset_ms is, per part, its sound's shift minus its picture's (+ = sound late) from audio packets matched by CRC32 to the source stream shaped like the joined audio (FFmpeg's default selection may copy one other than a:0; an MPEG-TS source's AAC is hashed without its ADTS headers) (null for a part with no unique match, e.g. digital silence; null as a whole when the source has no audio or the video check failed), and audio_parts_checked counts the measured parts; ok is the conjunction (counts, steps, every measured part within 5 ms), and false means the join was re-cut from the source (concat_fallback) and this is the failed measurement. null for a single segment, audio, --dry-run, --accurate/--codec/a forced re-encode, a segment that re-encoded, or a join that fell back before a copy join was attempted (open GOPs, a later B-frame segment starting between keyframes, parts that differ, a concat error)"},
                  "segment_end_snap_seconds": {"type": ["array", "null"], "items": {"type": ["number", "null"]}, "description": "--segments stream-copy join: per segment, the signed seconds its end moved to the keyframe the copied part stops at (the first keyframe at or after the requested end, never an earlier one; null for a part that runs to the end of the video, a part of a source with no B-frames, which is cut to its requested end as in every 2.x release, or a Matroska/MPEG-TS part, which is not snapped). null as a whole unless the output is those copied parts: a single segment, audio, --dry-run, or any re-encode or fallback"}}
+    elif name == "multicam":
+        extra = {"cuts": {"type": "array", "description": "[[start, end, camera], ...] on the reference timeline: the camera actually rendered. A range whose camera had not started yet plays camera 0, and diagnostics.fallbacks names the camera asked for (code camera_not_started)"},
+                 "offsets_seconds": {"type": "array"}, "confidence": {"type": "array"}}
     elif name == "join":
         extra = {"mode": {"enum": ["video", "audio"]}, "clips": {"type": "integer"}, "transition": {"type": "string"},
                  "expected_duration": {"type": ["number", "null"], "description": "clip lengths minus the transitions; null under --dry-run while an input is pending (its length is unknown)"},
@@ -555,6 +656,11 @@ def output_schema(name: str, meta: Dict[str, Any], hw: bool = False) -> Dict[str
                  "silent": {"type": "array", "description": "--on-silent warn (default), only when a track was silent: [{flag, path, peak_db}] for each --music/--replace/--effects file, or under --duck the voice (flag \"input\"), whose whole-file peak is at or below --silence-threshold (default -50 dBFS); it was mixed anyway. --on-silent fail refuses instead, reason \"silent (peak X dBFS)\" in problems"},
                  "notes": {"type": "array", "items": {"type": "string"}, "description": "present with `silent`: which tracks were silent and how to refuse them"},
                  "audio": {"type": "object", "description": "what the mix was built from: voice (null | light | medium | strong), stereo_widen, effects/effects_volume, and with --music the music_volume plus duck (null when --duck was not given, else the threshold in dB and linear, ratio, attack_ms, release_ms, amount_db actually used)"}}
+    if name in ("overlay", "graphics", "caption", "grid"):
+        extra["font_used"] = FONT_USED_SCHEMA
+    if name == "cropdetect":
+        extra.update({"windows": {"type": "integer", "description": "sampled windows (--samples)"},
+                      "windows_failed": {"type": "integer", "description": "windows ffmpeg could not decode and that were skipped (a cropdetect_windows_failed warning when > 0); every window failing is a kind ffmpeg failure"}})
     props = dict(base)
     props.update(extra)
     notes = props.get("notes")
@@ -1733,13 +1839,17 @@ def build(detect: bool = True) -> Dict[str, Any]:
                                   "details": "optional, with reason: an object of the facts behind the refusal (paths, expected and actual values)"},
                         "diagnostics": DIAGNOSTICS_SCHEMA["description"]},
             "error_reasons": ERROR_REASONS,
+            "diagnostic_codes": {code: {"bucket": bucket, "meaning": meaning} for code, (bucket, meaning) in DIAGNOSTIC_CODES.items()},
             "audit_log": {"format": "JSON lines, appended: {ts, tool, event, pid, plan_sha256 (plan events), details}",
                           "events": {"plan_rejected": "render.py refused a plan (details: the refusal's error.details plus reason)",
                                      "lock_takeover": "a stale output lock was taken over (details: lock, output, pid, pid_alive, deadline, why)",
                                      "output_unlocked": "no output lock could be created and the run went on without one",
-                                     "output_is_input_refused": "the output-is-input refusal (only when an audit log was named)"},
-                          "location": "render.py --audit-log FILE when given; otherwise a refused plan's <plan>.audit.jsonl, and a lock event's "
-                                      "hidden .<output>.ffskill-audit.jsonl beside the output. Never written under --dry-run; a write that "
+                                     "output_is_input_refused": "the output-is-input refusal (only when an audit log was named)",
+                                     "cache_entry_damaged": "render.py --cache: a damaged entry (details: stage, reason, key, sidecar or artifact, sizes)",
+                                     "batch_cache_reset": "batch.py: .ffskill_cache.json did not parse and was started empty (details: path, size, error)"},
+                          "location": "render.py --audit-log FILE when given; otherwise a refused plan's <plan>.audit.jsonl, a lock event's "
+                                      "hidden .<output>.ffskill-audit.jsonl beside the output, and a cache event's .ffskill-audit.jsonl in the "
+                                      "cache directory (render.py --cache DIR) or the batch's output_dir. Never written under --dry-run; a write that "
                                       "fails is a diagnostics.warnings entry (audit_log_unwritable), never a failure"},
             "error_kinds": {"input": "missing or unsuitable input, bad arguments", "ffmpeg": "ffmpeg/ffprobe returned an error (message carries the last stderr lines)", "output": "ffmpeg exited 0 but the artifact is missing, empty or unreadable (an empty file is removed)", "missing_tool": "ffmpeg or ffprobe not on PATH", "timeout": "one ffmpeg/ffprobe run exceeded --timeout (default 1800 s, FFMPEG_SKILL_TIMEOUT) and was killed; partial output removed; exit 124", "verification": "the tool ran but its result failed the requested check: check.py platform rows (checks attached), render.py's check stage (output written, check attached), batch.py items (results attached), verify.py steps (files attached), color.py --retag (output written, but ffprobe does not read the requested colour tags on it); exit 1", "interrupted": "the tool received SIGINT or SIGTERM: the running ffmpeg (or sibling script) was stopped and its partial output removed; exit 130 or 143"},
             "success_criterion": "exit 0 AND the output exists AND is non-empty AND ffprobe reads a stream from it; only then is status completed printed and the output probe attached",

package/scripts/audio.py

@@ -26,6 +26,7 @@ from pathlib import Path
 from typing import Any, Dict, List
 
 from _common import STATE, add_common, dry_run_input_pending, require_tool, apply_common, audio_codec_for, db_to_linear, default_output, die, emit, ffmpeg_base, info, is_audio_output, measured_level_dbfs, probe, run, run_keeping_subtitles, fmt_secs
+from _common.emit import warn
 
 VOICE_CHAIN = "highpass=f=80,deesser=i=0.4,afftdn=nf=-25:tn=1,acompressor=threshold=-18dB:ratio=3:attack=5:release=80:makeup=2"
 
@@ -261,7 +262,7 @@ def main() -> int:
         notes.append("silent track(s) mixed anyway: " + "; ".join(
             f"{t['flag']} {t['path']} peaks at {t['peak_db']:g} dBFS" for t in silent)
             + f" (at or below --silence-threshold {args.silence_threshold:g}); pass --on-silent fail to refuse instead")
-        info("warning: " + notes[-1])
+        warn(notes[-1], "silent_track_mixed", tracks=[t["path"] for t in silent])
 
     meta = probe(args.input)
     dur = meta.get("duration") or 0.0