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.

docs/internal/modules.md

@@ -84,9 +84,10 @@ The `generic` chunker splits source units into ordered chunks. It validates the
 source document, clones source units, assigns chunk IDs such as `chunk-000001`,
 and records chunk metadata for start unit, end unit, and unit count.
 
-The pipeline runner canonicalizes chunk units from the source document by ID
-before extractors and mergers run. Chunker-owned context should stay in
-`SourceChunk.Metadata`.
+The pipeline runner canonicalizes chunk units from the source document by
+integer ID before extractors and mergers run. Chunkers also populate chunk
+start and end unit IDs, content bytes, and media type. Chunker-owned context
+should stay in `SourceChunk.Metadata`.
 
 Options:
 
@@ -126,12 +127,11 @@ Options: none. Non-empty options are rejected.
 
 The chunker enforces full source-unit coverage from the first source unit to the
 last, sequential contiguous scenes, and no overlap. Its LLM-facing schema uses
-integer `start_unit_id` and `end_unit_id` values as 1-based source-unit numbers;
-the module canonicalizes valid integer references to source-unit IDs before
-producing chunks. It assigns chunk IDs such as `scene-000001` and stores scene
-metadata including title, primary mode, participants, summary, boundary note,
-confidence, boundary unit IDs, and unit count. Boundary caveats become warnings
-with reason code
+integer `start_unit_id` and `end_unit_id` values matching source-unit IDs. It
+assigns chunk IDs such as `scene-000001`, emits JSON chunk content, and stores
+scene metadata including title, primary mode, participants, summary, boundary
+note, confidence, boundary unit IDs, and unit count. Boundary caveats become
+warnings with reason code
 `scene_boundary_caveat`. Whitespace-only caveats are treated as malformed
 structured output rather than silently dropped.
 
@@ -150,8 +150,7 @@ input materials, response schema, and session ID to the runtime; converts
 spell-cast responses into artifact candidates; and supplies deterministic
 validators.
 Its LLM-facing source-reference schema uses integer `start_unit_id` and
-`end_unit_id` values as 1-based source-unit numbers; the module canonicalizes
-valid integer references to source-unit IDs before validation and output.
+`end_unit_id` values matching source-unit IDs.
 
 Its prompt definition lives under `assets/prompts` and its schema under
 `assets/schemas`. Shared reusable D&D prompt fragments are provided by

docs/internal/pipeline.md

@@ -136,15 +136,19 @@ invariants before running extractors:
 - chunk IDs must be non-empty and unique in the chunk result;
 - each chunk `SourceID` must match the source document ID;
 - each chunk `Index` must match its zero-based returned order;
+- each chunk start and end unit ID must exist in the source document, with the
+  start unit at or before the end unit;
+- each chunk must include non-empty extraction content and media type;
 - each chunk must contain at least one source unit;
 - a chunk must not repeat a source unit;
 - every chunk source unit must exist in the source document;
 - source units inside each chunk must appear in source-document order.
 
 After validation, the runner rebuilds each chunk from source-document units by
-ID, preserving the chunk boundary order and cloning chunk metadata. Extractors
-and downstream stages therefore see canonical source units, while
-`SourceChunk.Metadata` remains the supported place for chunker-owned context.
+integer ID, preserving chunk boundaries, content bytes, media type, and cloned
+chunk metadata. Extractors and downstream stages therefore see canonical source
+units, while `SourceChunk.Metadata` remains the supported place for
+chunker-owned context.
 
 The framework does not require complete source-unit coverage and does not reject
 overlap between different chunks. Stricter policies, such as full coverage or