Implement integer source units and chunk payloads

docs/integrations/dnd-spell-artifacts.md

@@ -44,8 +44,8 @@ Approved artifacts use the generic artifact envelope documented in
   "source_refs": [
     {
       "source_id": "session-alpha",
-      "start_unit_id": "seg-001",
-      "end_unit_id": "seg-001"
+      "start_unit_id": 1,
+      "end_unit_id": 1
     }
   ]
 }
@@ -78,7 +78,7 @@ Each source reference uses the generic source-reference shape:
 Validation requires:
 
 - at least one source reference;
-- non-empty source ID and unit IDs;
+- non-empty source ID and positive unit IDs;
 - source ID matching the source document ID;
 - start and end unit IDs existing in the source document;
 - start unit appearing before or at the same position as end unit.
@@ -98,8 +98,8 @@ The extractor asks the LLM for this top-level response shape:
       "source_refs": [
         {
           "source_id": "session-alpha",
-          "start_unit_id": "seg-001",
-          "end_unit_id": "seg-001"
+          "start_unit_id": 1,
+          "end_unit_id": 1
         }
       ]
     }

docs/integrations/json-output.md

@@ -156,8 +156,8 @@ Each artifact file has this shape:
       "source_refs": [
         {
           "source_id": "session-alpha",
-          "start_unit_id": "seg-001",
-          "end_unit_id": "seg-001"
+          "start_unit_id": 1,
+          "end_unit_id": 1
         }
       ]
     }

docs/integrations/seriatim.md

@@ -28,7 +28,7 @@ output that provides the same required segment fields.
   },
   "segments": [
     {
-      "id": "seg-001",
+      "id": 1,
       "start": 0,
       "end": 4,
       "speaker": "Aria",
@@ -56,10 +56,9 @@ The adapter rejects:
 - missing, null, or non-object `metadata`;
 - missing, null, non-array, or empty `segments`;
 - segment values that are not objects;
-- segment `id` values that are neither strings nor numbers;
+- segment `id` values that are not positive integer JSON numbers or numeric
+  strings;
 - non-string `speaker` or `text`;
-- empty segment IDs;
-- segment IDs with leading or trailing whitespace;
 - duplicate segment IDs;
 - missing or empty `speaker`;
 - missing, empty, invalid, non-finite, or negative `start`;
@@ -87,8 +86,7 @@ The adapter maps input to `SourceDocument`:
 
 Each segment becomes one `SourceUnit`:
 
-- `segment.id` becomes `SourceUnit.ID`; numeric IDs are converted to their JSON
-  number text, so `1` becomes `"1"`;
+- `segment.id` becomes integer `SourceUnit.ID`;
 - `segment.text` becomes `SourceUnit.Text`;
 - `SourceUnit.Kind` is `transcript_segment`;
 - `speaker`, `start`, and `end` are stored in source-unit metadata.