feat(retries): add min_attempts and absolute_max_elapsed_time_ms to BackoffStrategy

.genignore

@@ -19,3 +19,7 @@ src/unstructured_client/users.py
 #  - Adjust the custom url snippets in the file
 #  - Bring back the ignore line and commit
 src/unstructured_client/general.py
+
+# Custom min_attempts / absolute_max_elapsed_time_ms fields on BackoffStrategy.
+# Push upstream to Speakeasy templates to remove this entry.
+src/unstructured_client/utils/retries.py

CHANGELOG.md

@@ -3,6 +3,9 @@
 ### Breaking changes
 * Removed deprecated connector config models from the SDK (e.g. `S3SourceConnectorConfig`, `AzureDestinationConnectorConfig`). Pass connector configs as plain dicts with arbitrary fields. The SDK is no longer coupled to backend connector schemas — new fields work without an SDK upgrade.
 
+### Features
+* Add `min_attempts` and `absolute_max_elapsed_time_ms` fields to `BackoffStrategy`. `min_attempts` is the minimum number of retry attempts that must fire before `max_elapsed_time` is honored; defaults to `0` (preserves existing behavior). `absolute_max_elapsed_time_ms` caps when a new retry can start (does not interrupt in-flight requests); defaults to `None`. Together these close a short-circuit where a single slow first attempt could exhaust the retry budget before any retry fired. See FS-1988.
+
 ## 0.43.4
 
 ### Enhancements

_test_unstructured_client/integration/test_decorators.py

@@ -813,3 +813,45 @@ async def mock_send(_, request: httpx.Request, **kwargs):
     assert number_of_transport_failures == 0
     assert mock_endpoint_called
     assert res.status_code == 200
+
+
+def test_split_pdf_cache_tmp_data_chunk_request_stream_is_replay_safe(tmp_path):
+    from unstructured_client._hooks.custom.request_utils import (
+        create_pdf_chunk_request,
+    )
+
+    chunk_path = tmp_path / "chunk.pdf"
+    src_bytes = Path("_sample_docs/layout-parser-paper.pdf").read_bytes()
+    chunk_path.write_bytes(src_bytes)
+
+    pdf_chunk_file = open(chunk_path, "rb")  # noqa: SIM115
+    try:
+        form_data = {
+            "files": (chunk_path.name, src_bytes, "application/pdf"),
+            "strategy": "fast",
+        }
+        original_request = httpx.Request(
+            method="POST",
+            url="http://localhost:8000/general/v0/general",
+            headers={
+                "Content-Type": "multipart/form-data; boundary=test",
+                "User-Agent": "test",
+            },
+            content=b"",
+        )
+
+        chunk_request = create_pdf_chunk_request(
+            form_data=form_data,
+            pdf_chunk=(pdf_chunk_file, 1),
+            original_request=original_request,
+            filename=chunk_path.name,
+        )
+
+        # Iterate twice without request.read() to bypass _content caching.
+        first_pass = b"".join(chunk_request.stream)
+        second_pass = b"".join(chunk_request.stream)
+
+        assert len(first_pass) > 1000
+        assert first_pass == second_pass
+    finally:
+        pdf_chunk_file.close()