Add video/audio corpus support with yt-dlp download and Whisper transcription

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

graphify/skill-opencode.md

@@ -98,13 +98,60 @@ Corpus: X files · ~Y words
   docs:     N files (.md .txt ...)
   papers:   N files (.pdf ...)
   images:   N files
+  video:    N files (.mp4 .mp3 ...)
 ```
 
+Omit any category with 0 files from the summary.
+
 Then act on it:
 - If `total_files` is 0: stop with "No supported files found in [path]."
 - If `skipped_sensitive` is non-empty: mention file count skipped, not the file names.
 - If `total_words` > 2,000,000 OR `total_files` > 200: show the warning and the top 5 subdirectories by file count, then ask which subfolder to run on. Wait for the user's answer before proceeding.
-- Otherwise: proceed directly to Step 3 - no need to ask anything.
+- Otherwise: proceed directly to Step 2.5 if video files were detected, or Step 3 if not.
+
+### Step 2.5 - Transcribe video / audio files (only if video files detected)
+
+Skip this step entirely if `detect` returned zero `video` files.
+
+Video and audio files cannot be read directly. Transcribe them to text first, then treat the transcripts as doc files in Step 3.
+
+**Strategy:** Run non-video semantic extraction first (Step 3B) to get god nodes, use those to build a domain hint for Whisper, then transcribe. This keeps the prompt relevant without guessing the corpus topic from filenames.
+
+**However**, if the corpus has *only* video files and no other docs/code, skip the god-node step and transcribe with the generic fallback prompt immediately.
+
+**Transcription command:**
+
+```bash
+$(cat graphify-out/.graphify_python) -c "
+import json
+from pathlib import Path
+from graphify.transcribe import build_whisper_prompt, transcribe_all
+
+detect = json.loads(Path('graphify-out/.graphify_detect.json').read_text())
+video_files = detect.get('files', {}).get('video', [])
+
+# Try to load god nodes from a previous partial run or pass [] if not yet available
+try:
+    analysis = json.loads(Path('graphify-out/.graphify_analysis.json').read_text())
+    god_nodes = analysis.get('god_nodes', [])
+except Exception:
+    god_nodes = []
+
+prompt = build_whisper_prompt(god_nodes)
+print(f'Whisper prompt: {prompt}')
+
+transcript_paths = transcribe_all(video_files, initial_prompt=prompt)
+print(json.dumps(transcript_paths))
+" > graphify-out/.graphify_transcripts.json
+```
+
+After transcription:
+- Read the transcript paths from `graphify-out/.graphify_transcripts.json`
+- Add them to the docs list before dispatching semantic subagents in Step 3B
+- Print how many transcripts were created: `Transcribed N video file(s) -> treating as docs`
+- If transcription fails for a file, print a warning and continue with the rest
+
+**Whisper model:** Default is `base`. If the user passed `--whisper-model <name>`, set `GRAPHIFY_WHISPER_MODEL=<name>` in the environment before running the command above.
 
 ### Step 3 - Extract entities and relationships