Simplify the scene_map schema

prompts/pipeline-dnd/analyze/scene_map/scene_map.instructions.md

@@ -27,7 +27,7 @@ Scene boundary requirements:
 4. Preserve transcript order.
 5. Use exact segment IDs from the transcript.
 6. Each scene must have a start_segment_id and end_segment_id.
-7. Scene IDs must be sequential: SCN-001, SCN-002, SCN-003, and so on.
+7. Scene IDs must be sequential: 1, 2, 3, and so on.
 8. Prefer coherent scenes over excessive fragmentation.
 9. Do not merge unrelated scenes just to keep the scene count low.
 10. If a boundary is uncertain, choose the most practical boundary and explain the uncertainty in boundary_note.

schemas/pipeline-dnd/analyze/scene_map.schema.json

@@ -21,8 +21,7 @@
       "required": [
         "source_description",
         "first_segment_id",
-        "last_segment_id",
-        "limitations"
+        "last_segment_id"
       ],
       "properties": {
         "source_description": {
@@ -60,8 +59,8 @@
         "properties": {
           "scene_id": {
             "type": "string",
-            "description": "Stable sequential scene identifier, such as SCN-001.",
-            "pattern": "^SCN-[0-9]{3}$"
+            "description": "Stable sequential scene identifier.",
+            "pattern": "[0-9]$"
           },
           "start_segment_id": {
             "type": "integer",