mcp-server/src/legal_mcp/services/ingest.py

@@ -182,6 +182,7 @@ async def ingest_document(
 
     try:
         stored_chunks = await _chunk_embed_store(case_law_id, raw_text, page_offsets, page_count, progress)
+        await db.mark_indexed(case_law_id)
 
         # Step 9: multimodal — uniform: flag + PDF + page_count, NOT intake type.
         if (config.MULTIMODAL_ENABLED and page_count > 0
@@ -256,3 +257,27 @@ async def _chunk_embed_store(case_law_id, text, page_offsets, page_count, progre
             for c, v in zip(chunks, chunk_vectors)
         ]
         return await db.store_precedent_chunks(case_law_id, chunk_dicts)
+
+
+async def reindex_case_law(
+    case_law_id: "UUID | str",
+    progress: ProgressCb | None = None,
+) -> dict:
+    """Re-chunk + re-embed an existing case_law row from its STORED full_text (GAP-09).
+
+    No re-extract / no re-OCR (uses the stored text — see feedback_no_reocr_retrofit)
+    and no LLM/CLI (only chunker + voyage embeddings), so it is safe to run anywhere.
+    Idempotent: store_precedent_chunks(_hierarchical) is DELETE-then-INSERT.
+    """
+    progress = progress or _noop_progress
+    cid = case_law_id if isinstance(case_law_id, UUID) else UUID(str(case_law_id))
+    row = await db.get_case_law(cid)
+    if not row:
+        raise ValueError(f"case_law not found: {cid}")
+    text = (row.get("full_text") or "").strip()
+    if not text:
+        raise ValueError("case_law has no stored full_text to re-index")
+    stored = await _chunk_embed_store(cid, text, None, 0, progress)
+    await db.mark_indexed(cid)
+    await progress("completed", 100, f"הוטמע מחדש: {stored} chunks")
+    return {"status": "completed", "case_law_id": str(cid), "chunks": stored, "reindexed": True}