Adding pexels downloader and fixes

gnommo/renderer.py

@@ -237,8 +237,27 @@ def _resolve_video_path(
     source_path = base_dir / video_source.source_file
     if project_path:
         resolved, _ = resolve_with_cache(source_path, project_path)
-        return resolved
-    return source_path
+    else:
+        resolved = source_path
+
+    if not resolved.exists():
+        # File not found anywhere — substitute PlaceholderVideo so FFmpeg doesn't crash
+        placeholder = None
+        if shared_assets_dir:
+            p = shared_assets_dir / "PlaceholderVideo.mp4"
+            if project_path:
+                p, _ = resolve_with_cache(p, project_path)
+            if p.exists():
+                placeholder = p
+        if placeholder:
+            import sys
+            print(
+                f"  Warning: {video_source.source_file} not found — using PlaceholderVideo",
+                file=sys.stderr,
+            )
+            return placeholder
+
+    return resolved
 
 
 def _has_audio_stream(video_path: Path) -> bool:
@@ -362,6 +381,7 @@ def build_ffmpeg_command(plan: RenderPlan, output_path: Path) -> list[str]:
                 f"Background handle '{bg_handle}' not found in shared_assets/videos.json"
             )
         bg_path = shared_assets_dir / bg_videos[bg_handle]["source_file"]
+        bg_path, _ = resolve_with_cache(bg_path, plan.project_path)
         if not bg_path.exists():
             raise RenderError(
                 f"Background file not found: {bg_path} (from handle '{bg_handle}')"
@@ -404,12 +424,29 @@ def build_ffmpeg_command(plan: RenderPlan, output_path: Path) -> list[str]:
             videos_dir, event.video_source, shared_assets_dir, project_path
         )
         skip = event.video_source.skip or 0.0
+
+        # How long this clip needs to play in the output
+        clip_duration = event.end_time - event.start_time
+        if event.video_source.take is not None:
+            clip_duration = min(clip_duration, event.video_source.take)
+
+        # Loop the clip if the file is shorter than the display window.
+        # Don't loop pause-narration videos — they intentionally play once and stop.
+        needs_loop = False
+        if event.video_source.duration is not None and not event.video_source.pause_narration:
+            remaining = event.video_source.duration - skip
+            needs_loop = remaining < clip_duration - 0.1  # 0.1 s tolerance
+
+        if needs_loop:
+            cmd.extend(["-stream_loop", "-1"])
         if skip > 0:
             cmd.extend(["-ss", f"{skip:.3f}"])
         cmd.extend(["-analyzeduration", "0", "-probesize", "1000"])
-        # Use pre-probed duration to tell FFmpeg exactly how much to read,
-        # preventing scans of ghost audio tracks on empty MP4 audio streams.
-        if event.video_source.duration is not None:
+        # Use pre-probed duration (or loop-limited duration) to tell FFmpeg exactly
+        # how much to read, preventing scans of ghost audio tracks on empty streams.
+        if needs_loop:
+            cmd.extend(["-t", f"{clip_duration:.3f}"])
+        elif event.video_source.duration is not None:
             remaining = event.video_source.duration - skip
             if remaining > 0:
                 cmd.extend(["-t", f"{remaining:.3f}"])
@@ -881,31 +918,12 @@ def build_filter_complex(
         enable_expr = f"between(t\\,{event.start_time:.3f}\\,{effective_end:.3f})"
         filters.append(
             f"[{current_label}][{video_label}]overlay="
-            f"x={cut_x}:y={cut_y}:enable={enable_expr}"
+            f"x={cut_x}:y={cut_y}:enable={enable_expr}:eof_action=pass"
             f"[{next_label}]"
         )
         current_label = next_label
 
-    # Layer 3: Slides (transparent in the talking-head cutout area)
-    for i, event in enumerate(plan.slide_events):
-        slide_idx = slide_inputs[event.slide_id]
-
-        slide_label = f"s{i}"
-        filters.append(
-            f"[{slide_idx}:v]scale={width}:{height}:"
-            f"force_original_aspect_ratio=decrease,pad={width}:{height}:(ow-iw)/2:(oh-ih)/2:color=0x00000000[{slide_label}]"
-        )
-
-        next_label = f"sbase{i}"
-        enable_expr = f"between(t\\,{event.start_time:.3f}\\,{event.end_time:.3f})"
-        filters.append(
-            f"[{current_label}][{slide_label}]overlay="
-            f"x=0:y=0:enable={enable_expr}"
-            f"[{next_label}]"
-        )
-        current_label = next_label
-
-    # Layer 4: Always-visible videos (talking head) — above slides, visible through cutout
+    # Layer 3: Talking head — above below-videos, but under slides so fullscreen slides cover it
     for i, (video_id, video_source, cutout) in enumerate(plan.narration_videos):
         input_idx = always_visible_inputs[i]
         cut_x, cut_y, cut_width, cut_height = _calculate_cutout_position(
@@ -958,7 +976,64 @@ def build_filter_complex(
                 )
                 current_label = next_label
 
-    # Layer 5: "above" triggered videos (vft/vf2t/vst) — topmost, covers slides and talking head
+    # Layer 4: "mid" triggered videos (vfm/vsm) — above talking head, below slides
+    # Use case: content that should show through a slide's transparent "screen hole"
+    for i, event in enumerate(plan.video_events):
+        if event.layer != "mid":
+            continue
+        video_idx = video_inputs[i]
+        cut_x, cut_y, cut_width, cut_height = _calculate_cutout_position(
+            event.cutout, width, height
+        )
+
+        duration = event.end_time - event.start_time
+        if event.video_source.take is not None:
+            duration = min(duration, event.video_source.take)
+        effective_end = event.start_time + duration
+
+        zoom = event.video_source.zoom
+        zoomed_width = int(cut_width * zoom)
+        zoomed_height = int(cut_height * zoom)
+
+        video_label = f"tvm{i}"
+        start_pts = event.start_time
+        filters.append(
+            f"[{video_idx}:v]format=yuva444p10le,"
+            f"setpts=PTS-STARTPTS+{start_pts:.3f}/TB,"
+            f"scale={zoomed_width}:{zoomed_height}:force_original_aspect_ratio=increase,"
+            f"crop={cut_width}:{cut_height}:(iw-{cut_width})/2:(ih-{cut_height})/2,"
+            f"format=rgba[{video_label}]"
+        )
+
+        next_label = f"tvmbase{i}"
+        enable_expr = f"between(t\\,{event.start_time:.3f}\\,{effective_end:.3f})"
+        filters.append(
+            f"[{current_label}][{video_label}]overlay="
+            f"x={cut_x}:y={cut_y}:enable={enable_expr}:eof_action=pass"
+            f"[{next_label}]"
+        )
+        current_label = next_label
+
+    # Layer 5: Slides — on top of talking head so fullscreen slides cover the narrator
+    for i, event in enumerate(plan.slide_events):
+        slide_idx = slide_inputs[event.slide_id]
+
+        slide_label = f"s{i}"
+        filters.append(
+            f"[{slide_idx}:v]scale={width}:{height}:"
+            f"force_original_aspect_ratio=decrease,pad={width}:{height}:(ow-iw)/2:(oh-ih)/2:color=0x00000000[{slide_label}]"
+        )
+
+        next_label = f"sbase{i}"
+        enable_expr = f"between(t\\,{event.start_time:.3f}\\,{event.end_time:.3f})"
+        filters.append(
+            f"[{current_label}][{slide_label}]overlay="
+            f"x=0:y=0:enable={enable_expr}"
+            f"[{next_label}]"
+        )
+        current_label = next_label
+
+    # Layer 6: "above" triggered videos (vft/vf2t/vst) — topmost, covers slides and talking head
     # Use case: fullscreen video that intentionally masks the narrator
     for i, event in enumerate(plan.video_events):
         if event.layer != "above":
@@ -991,7 +1066,7 @@ def build_filter_complex(
         enable_expr = f"between(t\\,{event.start_time:.3f}\\,{effective_end:.3f})"
         filters.append(
             f"[{current_label}][{video_label}]overlay="
-            f"x={cut_x}:y={cut_y}:enable={enable_expr}:format=auto"
+            f"x={cut_x}:y={cut_y}:enable={enable_expr}:format=auto:eof_action=pass"
             f"[{next_label}]"
         )
         current_label = next_label