davinci-resolve-mcp 2.110.0 → 2.112.0

package/install.py

@@ -37,7 +37,7 @@ from src.utils.update_check import (
 
 # ─── Version ──────────────────────────────────────────────────────────────────
 
-VERSION = "2.110.0"
+VERSION = "2.112.0"
 # Only hard floor: mcp[cli] requires Python 3.10+. There is no upper bound —
 # Resolve's scripting bridge loads into newer interpreters on recent builds
 # (Python 3.14 verified against Resolve Studio 20.3.2). Older Resolve builds

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "davinci-resolve-mcp",
-  "version": "2.110.0",
+  "version": "2.112.0",
   "description": "NPM bootstrapper for the DaVinci Resolve MCP Server.",
   "license": "MIT",
   "author": "Samuel Gursky <samgursky@gmail.com>",

package/resolve-advanced/server/author-interchange.mjs

@@ -202,9 +202,11 @@ export function eventsToOTIO(events, opts = {}) {
  * timeline runs 24fps with origin 86400, so rec/src frames convert as
  * round(frames × 24 / nominalFps). Placement anchors the EARLIEST video
  * event at the origin. Honesty ledger in the returned report: flattened
- * retimes (the template clip schema has no per-clip speed), dropped
- * transitions (treated as cuts at their boundary), and skipped audio events
- * (cuts carry linked A1 audio from their own source already).
+ * retimes (the template clip schema has no per-clip speed), authored vs
+ * dropped transitions (cross-dissolves are AUTHORED when the predecessor
+ * abuts the cut and both sides have handle media — render-verified on
+ * 19.1.3.7; otherwise dropped with the reason, as a cut at the boundary),
+ * and skipped audio events (cuts carry linked A1 audio already).
  *
  * @param {Array} events - normalized events (parseInterchange shape)
  * @param {object} opts
@@ -236,8 +238,11 @@ export function eventsToAssembleSpec(events, opts = {}) {
   }
 
   const toTl = (frames, fps) => Math.round((frames * 24) / Math.round(fps || 24));
+  // 'V'/'V1' → 1, 'V2' → 2, … (parsers number video tracks; EDL is single-V).
+  const trackNum = (t) => { const m = /^V(\d+)?$/.exec(String(t || 'V')); return m ? (m[1] ? parseInt(m[1], 10) : 1) : 1; };
   const flattenedRetimes = [];
   const droppedTransitions = [];
+  const transitionCandidates = [];
   const perSource = new Map();
   const placements = [];
 
@@ -250,23 +255,42 @@ export function eventsToAssembleSpec(events, opts = {}) {
     if ((e.speed ?? 100) !== 100 || e.reverse) {
       flattenedRetimes.push({ index: e.index, source: e.source, speed: e.speed, reverse: !!e.reverse });
     }
+    const vTrack = trackNum(e.track);
+    const cut = { startFrame: recIn, durationFrames, srcIn: toTl(e.srcIn ?? 0, e.fps), ...(vTrack > 1 ? { track: vTrack } : {}) };
     if (e.transition) {
-      droppedTransitions.push({ index: e.index, type: e.transition.type, duration: e.transition.duration });
+      // A dissolve INTO this event, at its record-in boundary. Whether it can
+      // be authored (abutting predecessor + handles both sides) is decided
+      // after all placements are known.
+      let d = Math.max(2, toTl(e.transition.duration || 0, e.fps) || 2);
+      d += d % 2; // placeTransition centers on the cut; keep it even
+      transitionCandidates.push({
+        atFrame: recIn, durationFrames: d, track: vTrack,
+        index: e.index, type: e.transition.type, rawDuration: e.transition.duration,
+        source: e.source, srcIn: cut.srcIn,
+      });
     }
-    const cut = { startFrame: recIn, durationFrames, srcIn: toTl(e.srcIn ?? 0, e.fps) };
-    placements.push({ start: recIn, end: recOut, index: e.index });
+    placements.push({ start: recIn, end: recOut, index: e.index, source: e.source, srcIn: cut.srcIn, durationFrames, track: vTrack });
     if (!perSource.has(e.source)) perSource.set(e.source, []);
     perSource.get(e.source).push(cut);
   }
 
+  // Overlap is judged PER VIDEO TRACK — V2 stacking over V1 is legitimate
+  // conform geometry (render-verified: an upper-track clip covers the lower).
   placements.sort((a, b) => a.start - b.start);
-  for (let i = 1; i < placements.length; i += 1) {
-    if (placements[i].start < placements[i - 1].end) {
-      throw new Error(
-        `eventsToAssembleSpec: events ${placements[i - 1].index} and ${placements[i].index} ` +
-        'overlap on the record track after frame conversion — a single V1 cannot hold both. ' +
-        'Resolve the overlap upstream (transitions count as cuts at their boundary here).',
-      );
+  const byTrack = new Map();
+  for (const pl of placements) {
+    if (!byTrack.has(pl.track)) byTrack.set(pl.track, []);
+    byTrack.get(pl.track).push(pl);
+  }
+  for (const [trk, pls] of byTrack) {
+    for (let i = 1; i < pls.length; i += 1) {
+      if (pls[i].start < pls[i - 1].end) {
+        throw new Error(
+          `eventsToAssembleSpec: events ${pls[i - 1].index} and ${pls[i].index} ` +
+          `overlap on video track ${trk} after frame conversion — one track cannot hold both. ` +
+          'Resolve the overlap upstream (transitions count as cuts at their boundary here).',
+        );
+      }
     }
   }
 
@@ -276,13 +300,45 @@ export function eventsToAssembleSpec(events, opts = {}) {
     cuts,
   }));
 
+  // Author cross-dissolves where the geometry allows it (render-verified on
+  // 19.1.3.7: an offline Sm2TiTransition over transplanted cross-source media
+  // blends 124→181.6→234 at the cut — transitions carry no Fusion comp, so
+  // the byte-keyed comp-cache law does not apply). A candidate is authorable
+  // when a predecessor ends EXACTLY at its cut and both sides have handle
+  // media for the centered span; anything else stays in droppedTransitions
+  // with the reason.
+  const transitions = [];
+  for (const c of transitionCandidates) {
+    const prev = placements.find((pl) => pl.track === c.track && pl.end === c.atFrame);
+    if (!prev) {
+      droppedTransitions.push({ index: c.index, type: c.type, duration: c.rawDuration, reason: 'no abutting predecessor at the cut' });
+      continue;
+    }
+    const half = c.durationFrames / 2;
+    const bHandle = c.srcIn >= half;
+    const aSpec = sourceMap[prev.source] && sourceMap[prev.source].spec;
+    const aFrames = aSpec && Number(aSpec.frameCount);
+    const aHandle = Number.isFinite(aFrames) ? prev.srcIn + prev.durationFrames + half <= aFrames : false;
+    if (!bHandle || !aHandle) {
+      droppedTransitions.push({
+        index: c.index, type: c.type, duration: c.rawDuration,
+        reason: `insufficient handles for a centered ${c.durationFrames}f dissolve` +
+          `${bHandle ? '' : ' (incoming srcIn < half)'}${aHandle ? '' : ' (outgoing tail media < half)'}`,
+      });
+      continue;
+    }
+    transitions.push({ track: c.track, atFrame: c.atFrame, durationFrames: c.durationFrames });
+  }
+
   return {
-    spec: { timelineName, media },
+    spec: { timelineName, media, ...(transitions.length ? { transitions } : {}) },
     report: {
       videoEvents: vids.length,
       sources: media.length,
       audioEventsSkipped: audioSkipped,
+      upperTrackCutsVideoOnly: placements.filter((pl) => pl.track > 1).length,
       flattenedRetimes,
+      authoredTransitions: transitions,
       droppedTransitions,
       origin: ORIGIN,
     },

package/resolve-advanced/server/editorial.mjs

@@ -116,8 +116,12 @@ export function parseOTIO(otio, opts = {}) {
   const tracks = (doc.tracks && doc.tracks.children) || [];
   const events = [];
   let idx = 1;
+  let vNum = 0;
   for (const track of tracks) {
-    const kind = track.kind === 'Audio' ? 'A' : 'V';
+    const isAudio = track.kind === 'Audio';
+    if (!isAudio) vNum += 1;
+    // First video track stays 'V' (compat); higher tracks are 'V2', 'V3', …
+    const kind = isAudio ? 'A' : (vNum === 1 ? 'V' : `V${vNum}`);
     let rec = 0;
     for (const child of track.children || []) {
       const schema = child.OTIO_SCHEMA || '';
@@ -199,7 +203,7 @@ export function parseXMEMLEvents(xml, opts = {}) {
   const media = seq && seq.media;
   if (media) {
     const vtracks = media.video && media.video.track ? (Array.isArray(media.video.track) ? media.video.track : [media.video.track]) : [];
-    for (const t of vtracks) if (t.clipitem) walk(t.clipitem, 'V');
+    vtracks.forEach((t, vi) => { if (t.clipitem) walk(t.clipitem, vi === 0 ? 'V' : `V${vi + 1}`); });
     const atracks = media.audio && media.audio.track ? (Array.isArray(media.audio.track) ? media.audio.track : [media.audio.track]) : [];
     for (const t of atracks) if (t.clipitem) walk(t.clipitem, 'A');
   }
@@ -320,7 +324,7 @@ export function timingGuards(oldEvents, newEvents) {
     const ne = matches[0];
     if (!ne) {
       // A dropped audio event where its video sibling survives → dropped J/L-cut audio.
-      if (oe.track === 'A' && newEvents.some((x) => x.track === 'V' && x.source === oe.source))
+      if (oe.track === 'A' && newEvents.some((x) => x.track !== 'A' && x.source === oe.source))
         flags.push({ kind: 'dropped_split_audio', source: oe.source, detail: 'audio event gone but video sibling present (J/L-cut lost)' });
       continue;
     }

package/resolve-advanced/server/tools/drt.mjs

@@ -46,7 +46,7 @@ const assembleSchema = z.object({
   spec: z
     .object({})
     .passthrough()
-    .describe("assembleTimeline spec: { timelineName?, media?: {mediaFilePath, spec:{width,height,frameCount,fps}, cuts:[{startFrame,durationFrames,srcIn?}]} | [same, ...] (multi-source needs media_pool.capture_media_template run once per file), elements?: [{type:'title'|'generator', track, startFrame, durationFrames?, text?, generatorName? ('Solid Color'|'SMPTE Color Bar'|'Grey Scale' render-verified on 19), ...}], transitions? }. startFrame is timeline-absolute (origin 86400)."),
+    .describe("assembleTimeline spec: { timelineName?, media?: {mediaFilePath, spec:{width,height,frameCount,fps}, cuts:[{startFrame,durationFrames,srcIn?,track? (1-based video track; >1 = video-only, render-verified stacking)}]} | [same, ...] (multi-source needs media_pool.capture_media_template run once per file), elements?: [{type:'title'|'generator', track, startFrame, durationFrames?, text?, generatorName? ('Solid Color'|'SMPTE Color Bar'|'Grey Scale' render-verified on 19), ...}], transitions? }. startFrame is timeline-absolute (origin 86400)."),
   outputPath: z.string().describe('Absolute path where the importable .drt will be written'),
   targetAppVersion: z
     .union([z.string(), z.number()])
@@ -148,7 +148,7 @@ function requirePathArg(args, key, action) {
 export const drtTool = {
   name: 'drt',
   description:
-    'DaVinci Resolve Timeline (.drt) operations — offline, no Resolve required. Actions: assemble_from_interchange (EDL/OTIO/XML/AAF + sourceMap → IMPORTABLE RENDERING native .drt in one call; retimes flatten, transitions become cuts, ledger in `conform`), assemble (spec → IMPORTABLE native-schema .drt via template-spliced real structures; pass targetAppVersion e.g. \'19.1\' for pre-21 hosts), parse, list_sequences (enumerate the timelines inside a .drp/.drt → [{id,name,eventCount,index}] to drive a "which sequence?" picker), author, validate, inject_into_drp, extract_from_drp (pull one SeqContainer out as a .drt — feed the .drt to the Python davinci-resolve MCP timeline.import_timeline_checked, or use timeline.import_from_drp to do both), downgrade (stamp <ProjectVersion> down so an OLDER Resolve will import a .drt/.drp from a newer one — pass targetAppVersion like "19.1.3" or targetProjectVersion).',
+    'DaVinci Resolve Timeline (.drt) operations — offline, no Resolve required. Actions: assemble_from_interchange (EDL/OTIO/XML/AAF + sourceMap → IMPORTABLE RENDERING native .drt in one call; retimes flatten; cross-dissolves are AUTHORED when the cut abuts with handles both sides (render-verified on 19), else dropped with reason; ledger in `conform`), assemble (spec → IMPORTABLE native-schema .drt via template-spliced real structures; pass targetAppVersion e.g. \'19.1\' for pre-21 hosts), parse, list_sequences (enumerate the timelines inside a .drp/.drt → [{id,name,eventCount,index}] to drive a "which sequence?" picker), author, validate, inject_into_drp, extract_from_drp (pull one SeqContainer out as a .drt — feed the .drt to the Python davinci-resolve MCP timeline.import_timeline_checked, or use timeline.import_from_drp to do both), downgrade (stamp <ProjectVersion> down so an OLDER Resolve will import a .drt/.drp from a newer one — pass targetAppVersion like "19.1.3" or targetProjectVersion).',
   async handler({ action, args }) {
     if (action === 'parse') {
       const p = parseSchema.parse(requirePathArg(args, 'drtPath', 'parse'));

package/resolve-advanced/vendor/drp-format/cut-media.js

@@ -24,16 +24,20 @@ const {
   freshDbIds,
   getTrackVec,
   replaceTrackVec,
+  emptyTrackClone,
 } = require('./seq-surgery');
 const { clipDbId, setClipStart, setClipDuration, setClipIn } = require('./splice-clips');
 
 /**
  * @param {Buffer|string} drpInput
  * @param {object} opts
- * @param {Array<{startFrame:number, durationFrames:number, srcIn?:number}>} opts.cuts
+ * @param {Array<{startFrame:number, durationFrames:number, srcIn?:number, track?:number}>} opts.cuts
  *   Timeline placements. startFrame is timeline-absolute (origin 86400 on the
  *   bundled templates — clips before the origin are dropped by Resolve on
  *   import, silently). srcIn is the source in-point in TIMELINE frames.
+ *   track is the 1-based VIDEO track (default 1); missing tracks are grown as
+ *   empty clones. Cuts on track > 1 are placed VIDEO-ONLY — their audio would
+ *   overlap the track-1 cuts' audio on A1 (the template has a single A1).
  * @param {string} [opts.timelineUuid]
  * @returns {Promise<{buffer: Buffer, cutCount: number, clipDbIds: string[]}>}
  */
@@ -52,6 +56,9 @@ async function cutSourceIntoClips(drpInput, opts = {}) {
     if (cut.mediaRef !== undefined && !/^[0-9a-f-]{36}$/.test(cut.mediaRef)) {
       throw new TypeError(`cutSourceIntoClips: cuts[${i}].mediaRef must be a uuid`);
     }
+    if (cut.track !== undefined && (!Number.isInteger(cut.track) || cut.track < 1)) {
+      throw new TypeError(`cutSourceIntoClips: cuts[${i}].track must be a positive integer`);
+    }
   });
 
   const zip = await loadDrpZip(drpInput);
@@ -59,6 +66,19 @@ async function cutSourceIntoClips(drpInput, opts = {}) {
   let xml = seqXml;
   const clipDbIds = [];
 
+  const cloneCut = (donor, cut) => {
+    let c = freshDbIds(donor);
+    c = setClipStart(c, cut.startFrame);
+    c = setClipDuration(c, cut.durationFrames);
+    c = setClipIn(c, cut.srcIn ?? 0);
+    if (cut.mediaRef) {
+      // Multi-source: point this cut at ITS source's transplanted pool
+      // element instead of the donor's.
+      c = c.replace(/<MediaRef>[0-9a-f-]{36}<\/MediaRef>/, `<MediaRef>${cut.mediaRef}</MediaRef>`);
+    }
+    return c;
+  };
+
   for (const trackType of ['video', 'audio']) {
     const { match, tracks } = getTrackVec(xml, trackType);
     if (!tracks.length) continue;
@@ -66,22 +86,23 @@ async function cutSourceIntoClips(drpInput, opts = {}) {
     const clips = splitClipElements(items);
     if (!clips.length) continue; // audio-less media: nothing to cut on A1
     const donor = clips[0];
-    const clones = cuts.map((cut) => {
-      let c = freshDbIds(donor);
-      c = setClipStart(c, cut.startFrame);
-      c = setClipDuration(c, cut.durationFrames);
-      c = setClipIn(c, cut.srcIn ?? 0);
-      if (cut.mediaRef) {
-        // Multi-source: point this cut at ITS source's transplanted pool
-        // element instead of the donor's.
-        c = c.replace(/<MediaRef>[0-9a-f-]{36}<\/MediaRef>/, `<MediaRef>${cut.mediaRef}</MediaRef>`);
-      }
-      return c;
-    });
-    if (trackType === 'video') {
+    if (trackType === 'audio') {
+      // A1 mirrors track-1 video cuts only; higher video tracks stay video-only.
+      const a1 = cuts.filter((cut) => (cut.track ?? 1) === 1).map((cut) => cloneCut(donor, cut));
+      tracks[0] = setItemsInner(tracks[0], a1.join(''));
+      xml = replaceTrackVec(xml, trackType, match, tracks);
+      continue;
+    }
+    const maxTrack = Math.max(1, ...cuts.map((cut) => cut.track ?? 1));
+    const cloneSource = tracks[0];
+    while (tracks.length < maxTrack) tracks.push(emptyTrackClone(cloneSource));
+    for (let t = 1; t <= tracks.length; t += 1) {
+      const mine = cuts.filter((cut) => (cut.track ?? 1) === t);
+      if (t > 1 && !mine.length) continue; // grown-empty or untouched track keeps its items
+      const clones = mine.map((cut) => cloneCut(donor, cut));
       for (const c of clones) clipDbIds.push(clipDbId(c));
+      tracks[t - 1] = setItemsInner(tracks[t - 1], clones.join(''));
     }
-    tracks[0] = setItemsInner(tracks[0], clones.join(''));
     xml = replaceTrackVec(xml, trackType, match, tracks);
   }
 

package/src/granular/common.py

@@ -87,7 +87,7 @@ if not logging.getLogger().handlers:
         handlers=[logging.StreamHandler()],
     )
 
-VERSION = "2.110.0"
+VERSION = "2.112.0"
 logger = logging.getLogger("davinci-resolve-mcp")
 logger.info(f"Starting DaVinci Resolve MCP Server v{VERSION}")
 logger.info(f"Detected platform: {get_platform()}")

package/src/server.py

@@ -11,7 +11,7 @@ Usage:
     python src/server.py --full       # Start the 353-tool granular server instead
 """
 
-VERSION = "2.110.0"
+VERSION = "2.112.0"
 
 import base64
 import os