Merge branch 'main' into awalker4-patch-2

Author: awalker4

.github/workflows/claude.yml

@@ -0,0 +1,37 @@
+name: Claude Code
+
+on:
+  issue_comment:
+    types: [created]
+  pull_request_review_comment:
+    types: [created]
+  issues:
+    types: [opened, assigned]
+  pull_request_review:
+    types: [submitted]
+
+jobs:
+  claude:
+    if: |
+      (github.event_name == 'issue_comment' && contains(github.event.comment.body, '@claude')) ||
+      (github.event_name == 'pull_request_review_comment' && contains(github.event.comment.body, '@claude')) ||
+      (github.event_name == 'pull_request_review' && contains(github.event.review.body, '@claude')) ||
+      (github.event_name == 'issues' && (contains(github.event.issue.body, '@claude') || contains(github.event.issue.title, '@claude')))
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: read
+      issues: read
+      id-token: write
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Run Claude Code
+        id: claude
+        uses: anthropics/claude-code-action@beta
+        with:
+          anthropic_api_key: ${{ secrets.GH_ANTHROPIC_API_KEY }}
+          allowed_tools: "Bash(git:*),View,GlobTool,GrepTool,BatchTool"

.speakeasy/gen.lock

@@ -1,12 +1,12 @@
 lockVersion: 2.0.0
 id: 8b5fa338-9106-4734-abf0-e30d67044a90
 management:
-  docChecksum: b83a55777bc5d3b1bda7cdfe7ee07a04
-  docVersion: 1.1.30
+  docChecksum: 3e52fdac3e417f8e48fcb920b829025c
+  docVersion: 1.1.34
   speakeasyVersion: 1.552.0
   generationVersion: 2.610.0
-  releaseVersion: 0.38.1
-  configChecksum: accf1dab899bf95bca0a1c9d8f7ce37a
+  releaseVersion: 0.39.1
+  configChecksum: 2b0094ee827eb2deb71ef0ff9e572192
   repoURL: https://github.com/Unstructured-IO/unstructured-python-client.git
   repoSubDirectory: .
   installationURL: https://github.com/Unstructured-IO/unstructured-python-client.git

.speakeasy/workflow.lock

@@ -2,20 +2,20 @@ speakeasyVersion: 1.552.0
 sources:
     my-source:
         sourceNamespace: my-source
-        sourceRevisionDigest: sha256:2f2db6ff7bc20d7cf5d761369bbca095edb6c1fd11a11cbf90b1356285b31cea
-        sourceBlobDigest: sha256:ebd768e737b62ea63eb80866cbb5520c544310d41e0960dad7f1b7f056e8e9c7
+        sourceRevisionDigest: sha256:ac2955e4a812caa63ad339156504c9bdfae02dd241800a6c48892aaf37552c54
+        sourceBlobDigest: sha256:eb516ced31caa9801a7996b8216fa7c7a46ab16dc9edd4d9eef5721cee7acd6c
         tags:
             - latest
-            - speakeasy-sdk-regen-1751553080
-            - 1.1.30
+            - speakeasy-sdk-regen-1752365566
+            - 1.1.34
 targets:
     unstructured-python:
         source: my-source
         sourceNamespace: my-source
-        sourceRevisionDigest: sha256:2f2db6ff7bc20d7cf5d761369bbca095edb6c1fd11a11cbf90b1356285b31cea
-        sourceBlobDigest: sha256:ebd768e737b62ea63eb80866cbb5520c544310d41e0960dad7f1b7f056e8e9c7
+        sourceRevisionDigest: sha256:ac2955e4a812caa63ad339156504c9bdfae02dd241800a6c48892aaf37552c54
+        sourceBlobDigest: sha256:eb516ced31caa9801a7996b8216fa7c7a46ab16dc9edd4d9eef5721cee7acd6c
         codeSamplesNamespace: my-source-code-samples
-        codeSamplesRevisionDigest: sha256:d7f7ccae807fbcc93d5037607208e53a3605ebc2c0919f8ad2d9f5d63fdd006d
+        codeSamplesRevisionDigest: sha256:e644b82aab2fb0dc0c506d643aa22910ae14bc998f2b13ac7cc019a789dbe552
 workflow:
     workflowVersion: 1.0.0
     speakeasyVersion: latest

README.md

@@ -316,7 +316,7 @@ with UnstructuredClient() as uc_client:
 
 </br>
 
-The same SDK client can also be used to make asychronous requests by importing asyncio.
+The same SDK client can also be used to make asynchronous requests by importing asyncio.
 ```python
 # Asynchronous Example
 import asyncio
@@ -351,7 +351,7 @@ See [page splitting](https://docs.unstructured.io/api-reference/api-services/sdk
 In order to speed up processing of large PDF files, the client splits up PDFs into smaller files, sends these to the API concurrently, and recombines the results. `split_pdf_page` can be set to `False` to disable this.
 
 The amount of workers utilized for splitting PDFs is dictated by the `split_pdf_concurrency_level` parameter, with a default of 5 and a maximum of 15 to keep resource usage and costs in check. The splitting process leverages `asyncio` to manage concurrency effectively.
-The size of each batch of pages (ranging from 2 to 20) is internally determined based on the concurrency level and the total number of pages in the document. Because the splitting process uses `asyncio` the client can encouter event loop issues if it is nested in another async runner, like running in a `gevent` spawned task. Instead, this is safe to run in multiprocessing workers (e.g., using `multiprocessing.Pool` with `fork` context).
+The size of each batch of pages (ranging from 2 to 20) is internally determined based on the concurrency level and the total number of pages in the document. Because the splitting process uses `asyncio` the client can encounter event loop issues if it is nested in another async runner, like running in a `gevent` spawned task. Instead, this is safe to run in multiprocessing workers (e.g., using `multiprocessing.Pool` with `fork` context).
 
 Example:
 ```python

RELEASES.md

@@ -1048,4 +1048,14 @@ Based on:
 ### Generated
 - [python v0.38.1] .
 ### Releases
-- [PyPI v0.38.1] https://pypi.org/project/unstructured-client/0.38.1 - .
+- [PyPI v0.38.1] https://pypi.org/project/unstructured-client/0.38.1 - .
+
+## 2025-07-16 19:20:27
+### Changes
+Based on:
+- OpenAPI Doc  
+- Speakeasy CLI 1.552.0 (2.610.0) https://github.com/speakeasy-api/speakeasy
+### Generated
+- [python v0.39.1] .
+### Releases
+- [PyPI v0.39.1] https://pypi.org/project/unstructured-client/0.39.1 - .

gen.yaml

@@ -14,7 +14,7 @@ generation:
     oAuth2ClientCredentialsEnabled: false
     oAuth2PasswordEnabled: false
 python:
-  version: 0.38.1
+  version: 0.39.1
   additionalDependencies:
     dev:
       deepdiff: '>=6.0'

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "unstructured-client"
-version = "0.38.1"
+version = "0.39.1"
 description = "Python Client SDK for Unstructured API"
 authors = [{ name = "Unstructured" },]
 readme = "README-PYPI.md"

src/unstructured_client/_hooks/custom/request_utils.py

@@ -23,10 +23,17 @@
     FormData,
 )
 from unstructured_client.models import shared
-from unstructured_client.utils import BackoffStrategy, Retries, RetryConfig, retry_async, serialize_request_body
+from unstructured_client.utils import (
+    BackoffStrategy,
+    Retries,
+    RetryConfig,
+    retry_async,
+    serialize_request_body,
+)
 
 logger = logging.getLogger(UNSTRUCTURED_CLIENT_LOGGER_NAME)
 
+
 def get_multipart_stream_fields(request: httpx.Request) -> dict[str, Any]:
     """Extracts the multipart fields from the request.
 
@@ -65,9 +72,9 @@ def get_multipart_stream_fields(request: httpx.Request) -> dict[str, Any]:
             }
     return mapped_fields
 
+
 def create_pdf_chunk_request_params(
-        form_data: FormData,
-        page_number: int
+    form_data: FormData, page_number: int
 ) -> dict[str, Any]:
     """Creates the request body for the partition API."
 
@@ -88,11 +95,14 @@ def create_pdf_chunk_request_params(
         PARTITION_FORM_SPLIT_CACHE_TMP_DATA_KEY,
         PARTITION_FORM_SPLIT_CACHE_TMP_DATA_DIR_KEY,
     ]
-    chunk_payload = {key: form_data[key] for key in form_data if key not in fields_to_drop}
+    chunk_payload = {
+        key: form_data[key] for key in form_data if key not in fields_to_drop
+    }
     chunk_payload[PARTITION_FORM_SPLIT_PDF_PAGE_KEY] = "false"
     chunk_payload[PARTITION_FORM_STARTING_PAGE_NUMBER_KEY] = str(page_number)
     return chunk_payload
 
+
 def create_pdf_chunk_request(
     form_data: FormData,
     pdf_chunk: Tuple[BinaryIO, int],
@@ -148,7 +158,6 @@ def create_pdf_chunk_request(
     )
 
 
-
 async def call_api_async(
     client: httpx.AsyncClient,
     pdf_chunk_request: httpx.Request,
@@ -161,12 +170,12 @@ async def call_api_async(
     retry_config = RetryConfig(
         "backoff",
         BackoffStrategy(
-            initial_interval = one_second * 3,
-            max_interval = one_minute * 12,
-            max_elapsed_time = one_minute * 30,
-            exponent = 1.88,
+            initial_interval=one_second * 3,
+            max_interval=one_minute * 12,
+            max_elapsed_time=one_minute * 30,
+            exponent=1.88,
         ),
-        retry_connection_errors=True
+        retry_connection_errors=True,
     )
 
     retryable_codes = ["5xx"]
@@ -177,12 +186,11 @@ async def do_request():
     async with limiter:
         try:
             response = await retry_async(
-                do_request,
-                Retries(retry_config, retryable_codes)
+                do_request, Retries(retry_config, retryable_codes)
             )
             return response
         except Exception as e:
-            logger.error("Request failed with error", exc_info=e)
+            logger.error("Request failed with error: %s", e, exc_info=e)
             raise e
         finally:
             if not isinstance(pdf_chunk_file, io.BytesIO) and not pdf_chunk_file.closed:
@@ -205,6 +213,7 @@ def prepare_request_headers(
     new_headers.pop("Content-Length", None)
     return new_headers
 
+
 def create_response(elements: list) -> httpx.Response:
     """
     Creates a modified response object with updated content.
@@ -216,13 +225,16 @@ def create_response(elements: list) -> httpx.Response:
     Returns:
         The modified response object with updated content.
     """
-    response = httpx.Response(status_code=200, headers={"Content-Type": "application/json"})
+    response = httpx.Response(
+        status_code=200, headers={"Content-Type": "application/json"}
+    )
     content = json.dumps(elements).encode()
     content_length = str(len(content))
     response.headers.update({"Content-Length": content_length})
     setattr(response, "_content", content)
     return response
 
+
 def get_base_url(url: str | URL) -> str:
     """Extracts the base URL from the given URL.
 

src/unstructured_client/_hooks/custom/split_pdf_hook.py

@@ -669,11 +669,8 @@ def after_success(
         elements = self._await_elements(operation_id)
 
         # if fails are disallowed, return the first failed response
-        # Note(austin): Stick a 500 status code in here so the SDK
-        # does not trigger its own retry logic
         if not self.allow_failed and self.api_failed_responses.get(operation_id):
             failure_response = self.api_failed_responses[operation_id][0]
-            failure_response.status_code = 500
 
             self._clear_operation(operation_id)
             return failure_response

src/unstructured_client/_version.py

@@ -3,10 +3,10 @@
 import importlib.metadata
 
 __title__: str = "unstructured-client"
-__version__: str = "0.38.1"
-__openapi_doc_version__: str = "1.1.30"
+__version__: str = "0.39.1"
+__openapi_doc_version__: str = "1.1.34"
 __gen_version__: str = "2.610.0"
-__user_agent__: str = "speakeasy-sdk/python 0.38.1 2.610.0 1.1.30 unstructured-client"
+__user_agent__: str = "speakeasy-sdk/python 0.39.1 2.610.0 1.1.34 unstructured-client"
 
 try:
     if __package__ is not None: