fix(api): POST /documents/stop removes partial chunks and resets counters (#15789)

### What problem does this PR solve?

`POST /api/v1/datasets/{dataset_id}/documents/stop`
(`stop_parse_documents`) cancels parsing tasks and sets `run` to
`CANCEL`, but it does **not** remove chunks already indexed in the doc
store or reset `progress` / `chunk_num`. REST callers can end up with a
“cancelled” document that still returns partial chunks in `GET
.../chunks` and in retrieval.

Legacy `DELETE /api/v1/datasets/{dataset_id}/chunks` (`stop_parsing`)
already performs full cleanup: it resets counters and calls
`docStoreConn.delete`. This PR aligns the newer stop endpoint with that
behavior so both paths leave the dataset consistent.

Fixes [#15788](https://github.com/infiniflow/ragflow/issues/15788).

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):

### Changes

- Update `stop_parse_documents` in `document_api.py` to reset `progress`
and `chunk_num` to `0` and delete partial chunks via
`docStoreConn.delete` after `cancel_all_task_of`.
- Add unit test `test_stop_parse_documents_cleans_partial_chunks` to
assert counters reset and doc store delete is invoked.

### Test plan

- [x] Unit test: `pytest
test/testcases/test_http_api/test_file_management_within_dataset/test_doc_sdk_routes_unit.py::TestDocRoutesUnit::test_stop_parse_documents_cleans_partial_chunks
-v`
- [ ] Manual: upload a slow document, start parse, call `POST
.../documents/stop` while `RUNNING`, verify `GET .../chunks` returns
zero chunks and UI `chunk_count` is 0
- [ ] Control: legacy `DELETE .../chunks` behavior unchanged

---------

Co-authored-by: Wang Qi <wangq8@outlook.com>

api/apps/restful_apis/document_api.py

@@ -1625,7 +1625,17 @@ async def stop_parse_documents(tenant_id, dataset_id):
                     continue
 
                 cancel_all_task_of(doc_id)
-                DocumentService.update_by_id(doc_id, {"run": str(TaskStatus.CANCEL.value)})
+                DocumentService.update_by_id(
+                    doc_id,
+                    {
+                        "run": str(TaskStatus.CANCEL.value),
+                        "progress": 0,
+                        "chunk_num": 0,
+                    },
+                )
+                index_name = search.index_name(tenant_id)
+                if settings.docStoreConn.index_exist(index_name, doc.kb_id):
+                    settings.docStoreConn.delete({"doc_id": doc.id}, index_name, doc.kb_id)
                 success_count += 1
 
             result = {"success_count": success_count}

test/testcases/test_http_api/test_file_management_within_dataset/test_doc_sdk_routes_unit.py

@@ -731,6 +731,56 @@ class TestDocRoutesUnit:
         res = _run(module.stop_parsing.__wrapped__("tenant-1", "ds-1"))
         assert res["code"] == 0
 
+    def test_stop_parse_documents_cleans_partial_chunks(self, monkeypatch):
+        module = _load_doc_module(monkeypatch, module_basename="document_api")
+        updated = []
+        deleted = []
+
+        monkeypatch.setattr(module.KnowledgebaseService, "accessible", lambda **_kwargs: True)
+        monkeypatch.setattr(module, "get_request_json", lambda: _AwaitableValue({"document_ids": ["doc-1"]}))
+        monkeypatch.setattr(module, "check_duplicate_ids", lambda ids, _kind: (ids, []))
+        monkeypatch.setattr(module.DocumentService, "query", lambda **_kwargs: [object()])
+        monkeypatch.setattr(
+            module.DocumentService,
+            "get_by_id",
+            lambda _id: (True, _DummyDoc(doc_id="doc-1", run=module.TaskStatus.RUNNING.value)),
+        )
+        monkeypatch.setattr(module.TaskService, "query", lambda **_kwargs: [SimpleNamespace(progress=0.5)])
+        monkeypatch.setattr(module, "cancel_all_task_of", lambda *_args, **_kwargs: None)
+        monkeypatch.setattr(
+            module.DocumentService,
+            "update_by_id",
+            lambda doc_id, info: updated.append((doc_id, info)) or True,
+        )
+        _patch_docstore(
+            monkeypatch,
+            module,
+            index_exist=lambda *_args, **_kwargs: True,
+            delete=lambda condition, index, kb_id: deleted.append((condition, index, kb_id)),
+        )
+
+        res = _run(module.stop_parse_documents.__wrapped__("tenant-1", "ds-1"))
+
+        assert res["code"] == 0
+        assert res["data"]["success_count"] == 1
+        assert updated == [
+            (
+                "doc-1",
+                {
+                    "run": module.TaskStatus.CANCEL.value,
+                    "progress": 0,
+                    "chunk_num": 0,
+                },
+            )
+        ]
+        assert deleted == [({"doc_id": "doc-1"}, module.search.index_name("tenant-1"), "kb-1")]
+
+        deleted.clear()
+        _patch_docstore(monkeypatch, module, index_exist=lambda *_args, **_kwargs: False)
+        res = _run(module.stop_parse_documents.__wrapped__("tenant-1", "ds-1"))
+        assert res["code"] == 0
+        assert deleted == []
+
     def test_list_chunks_branches(self, monkeypatch):
         module = _load_restful_chunk_module(monkeypatch)
         monkeypatch.setattr(module.KnowledgebaseService, "accessible", lambda **_kwargs: False)