fix: handle nested response structure in DocSplitterClient status polling

- Extract status from nested 'data' structure in wait_for_completion
- Support both uppercase and lowercase status values
- Add comprehensive test for nested response format
- Fixes infinite polling issue with real doc-splitter API

Author: jaseemjaskp

src/apihub_client/doc_splitter.py

@@ -67,12 +67,16 @@ def upload(
         self.logger.debug("Request Headers Sent: %s", response.request.headers)
         self.logger.debug("Request URL: %s", response.request.url)
 
-        if response.status_code != 200:
+        if response.status_code not in [200, 202]:
             self.logger.error("Upload failed: %s", response.text)
             raise ApiHubClientException(response.text, response.status_code)
 
         data = response.json()
-        job_id = data.get("job_id")
+        # Extract job_id from the nested data structure
+        if "data" in data and isinstance(data["data"], dict):
+            job_id = data["data"].get("job_id")
+        else:
+            job_id = data.get("job_id")
         self.logger.info("Upload completed successfully. Job ID: %s", job_id)
 
         # If wait_for_completion is True, poll for status and return final result
@@ -171,13 +175,17 @@ def wait_for_completion(
 
         while time.time() - start_time < timeout:
             status_result = self.get_job_status(job_id)
-            status = status_result.get("status")
+            # Extract status from nested data structure
+            if "data" in status_result and isinstance(status_result["data"], dict):
+                status = status_result["data"].get("status")
+            else:
+                status = status_result.get("status")
             self.logger.info("Current status: %s", status)
 
-            if status == "COMPLETED":
+            if status and status.upper() == "COMPLETED":
                 self.logger.info("Processing completed")
                 return status_result
-            elif status == "FAILED":
+            elif status and status.upper() == "FAILED":
                 self.logger.error("Processing failed")
                 raise ApiHubClientException(
                     f"Processing failed for job_id: {job_id}",

test/test_doc_splitter.py

@@ -55,6 +55,42 @@ def test_upload_success(self, client, mock_file_content):
             )
             assert request.headers["apikey"] == "test_api_key"
 
+    def test_upload_success_202_nested_response(self, client, mock_file_content):
+        """Test successful file upload with 202 status and nested response."""
+        with requests_mock.Mocker() as m:
+            # Mock successful upload response with 202 and nested data structure
+            m.post(
+                "http://localhost:8005/api/v1/doc-splitter/documents/upload",
+                json={
+                    "data": {
+                        "filename": "test.pdf",
+                        "job_id": "93bbb7ab-3291-429c-8923-3b179e7ae5bf",
+                        "pages": 2,
+                        "size_bytes": 63580,
+                        "status": "queued",
+                        "upload_timestamp": "2025-08-23T04:28:32.424535Z",
+                        "user_limits": {
+                            "current_jobs": 1,
+                            "jobs_today": 3,
+                            "max_jobs_per_day": 5000,
+                            "max_parallel_jobs": 5,
+                        },
+                    },
+                    "request_id": "eb75ac1e-a224-4624-a4f2-6c813ddc2b3c",
+                    "success": True,
+                    "timestamp": "2025-08-23T04:28:32.424612",
+                },
+                status_code=202,
+            )
+
+            with patch("builtins.open", mock_open(read_data=mock_file_content)):
+                result = client.upload(file_path="/test/document.pdf")
+
+            # Verify we got the nested response structure
+            assert result["data"]["job_id"] == "93bbb7ab-3291-429c-8923-3b179e7ae5bf"
+            assert result["data"]["status"] == "queued"
+            assert result["success"] is True
+
     def test_upload_file_not_found(self, client):
         """Test upload with non-existent file."""
         with patch("builtins.open", side_effect=FileNotFoundError("File not found")):
@@ -317,6 +353,47 @@ def test_wait_for_completion_failed_status(self, client):
 
             assert "Processing failed for job_id: test-job" in exc_info.value.message
 
+    def test_wait_for_completion_nested_response(self, client):
+        """Test wait_for_completion with nested response structure."""
+        with requests_mock.Mocker() as m:
+            # Mock status responses with nested structure (processing, then completed)
+            m.get(
+                "http://localhost:8005/api/v1/doc-splitter/jobs/status?job_id=test-nested",
+                [
+                    {
+                        "json": {
+                            "data": {
+                                "status": "processing",
+                                "job_id": "test-nested",
+                                "current_step": "page_image_gen",
+                            },
+                            "success": True,
+                        },
+                        "status_code": 200,
+                    },
+                    {
+                        "json": {
+                            "data": {
+                                "status": "completed",
+                                "job_id": "test-nested",
+                                "finished_at": "2025-08-23T04:40:00.000000Z",
+                            },
+                            "success": True,
+                        },
+                        "status_code": 200,
+                    },
+                ],
+            )
+
+            with patch("time.sleep") as mock_sleep:
+                result = client.wait_for_completion("test-nested", polling_interval=1)
+
+            # Should successfully complete and return the nested structure
+            assert result["data"]["status"] == "completed"
+            assert result["data"]["job_id"] == "test-nested"
+            assert result["success"] is True
+            mock_sleep.assert_called_with(1)
+
     def test_logging_output(self, client, caplog, mock_file_content):
         """Test that appropriate logging messages are generated."""
         with requests_mock.Mocker() as m: