bytekit-sdk 0.5.1__tar.gz → 0.5.2__tar.gz

{bytekit_sdk-0.5.1 → bytekit_sdk-0.5.2}/CHANGELOG.md

@@ -5,6 +5,45 @@ PyPI distribution: `bytekit-sdk`. Import name: `bytekit`.
 
 ## Unreleased
 
+## 0.5.2
+
+_Release cut 2026-09-03._
+
+### Changed
+
+- **Breaking (API):** the scrape `formats` vocabulary is now `raw | markdown | links | images`
+  (#3775). `ScrapeRequestFormatsItem` drops the two retired members and gains `RAW`, and the
+  response model exposes `ScrapeFormats.raw` in place of the old raw-HTML and cleaned-HTML
+  fields. The server accepts no alias, so a request naming a retired value returns `422`:
+
+  ```python
+  body = ScrapeRequest(url="https://example.com", formats=[ScrapeRequestFormatsItem.RAW])
+  resp = create_scrape.sync_detailed(client=client, body=body)
+  print(resp.parsed.formats.raw)
+  ```
+
+### Fixed
+
+- `402 Payment Required` now returns a typed `Error` instead of raising `UnexpectedStatus` on
+  `create_scrape`, `get_fetch`, `post_fetch`, `create_fetch_bulk`, `create_scrape_bulk`,
+  `create_bulk` and `create_sitemap` (#3784). Those operations enforce quota but never declared
+  `402` in the spec, so the generated client had no arm for it while `create_search` and
+  `create_screenshot` did — the same exhausted account raised on one call and returned a parsed
+  error on the next. Regenerated from the corrected spec:
+
+  ```python
+  resp = create_scrape.sync_detailed(client=client, body=body)
+  if resp.status_code == 402:
+      print(resp.parsed.error.code)  # quota_exceeded | spending_cap_reached | …
+  ```
+
+### Changed
+
+- The generated `events` field docstring on `ScrapeRequest` now documents the widened server
+  default (`queued`, `completed`, `failed`) and that a caller may send an explicit subset to
+  receive fewer deliveries (#3777). Types/docs only — this regeneration followed a server-side
+  default change; the SDK carried no logic tied to the old default.
+
 ## 0.5.1
 
 _Release cut 2026-08-25._

{bytekit_sdk-0.5.1 → bytekit_sdk-0.5.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: bytekit-sdk
-Version: 0.5.1
+Version: 0.5.2
 Summary: Official Python SDK for the ByteKit API
 Project-URL: Homepage, https://bytekit.com
 Project-URL: Repository, https://github.com/Hunt-Labs-Inc/ByteKit

{bytekit_sdk-0.5.1 → bytekit_sdk-0.5.2}/pyproject.toml

@@ -7,7 +7,7 @@
 # `pip install bytekit-sdk` yields a working `import bytekit`. Mirrors the npm sibling
 # @hunt-labs/bytekit-sdk.
 name = "bytekit-sdk"
-version = "0.5.1"
+version = "0.5.2"
 description = "Official Python SDK for the ByteKit API"
 readme = "README.md"
 requires-python = ">=3.10"

{bytekit_sdk-0.5.1 → bytekit_sdk-0.5.2}/src/bytekit/api/bulk/create_bulk.py

@@ -40,6 +40,10 @@ def _parse_response(
         response_400 = errors.bytekit_parse(Error.from_dict, client=client, response=response)
 
         return response_400
+    if response.status_code == 402:
+        response_402 = errors.bytekit_parse(Error.from_dict, client=client, response=response)
+
+        return response_402
     if response.status_code == 422:
         response_422 = errors.bytekit_parse(Error.from_dict, client=client, response=response)
 

{bytekit_sdk-0.5.1 → bytekit_sdk-0.5.2}/src/bytekit/api/fetch/get_fetch.py

@@ -54,6 +54,10 @@ def _parse_response(
         response_400 = errors.bytekit_parse(Error.from_dict, client=client, response=response)
 
         return response_400
+    if response.status_code == 402:
+        response_402 = errors.bytekit_parse(Error.from_dict, client=client, response=response)
+
+        return response_402
     if response.status_code == 422:
         response_422 = errors.bytekit_parse(Error.from_dict, client=client, response=response)
 

{bytekit_sdk-0.5.1 → bytekit_sdk-0.5.2}/src/bytekit/api/fetch/post_fetch.py

@@ -38,6 +38,10 @@ def _parse_response(
         response_400 = errors.bytekit_parse(Error.from_dict, client=client, response=response)
 
         return response_400
+    if response.status_code == 402:
+        response_402 = errors.bytekit_parse(Error.from_dict, client=client, response=response)
+
+        return response_402
     if response.status_code == 422:
         response_422 = errors.bytekit_parse(Error.from_dict, client=client, response=response)
 

{bytekit_sdk-0.5.1 → bytekit_sdk-0.5.2}/src/bytekit/api/fetch_bulk/create_fetch_bulk.py

@@ -40,6 +40,10 @@ def _parse_response(
         response_400 = errors.bytekit_parse(Error.from_dict, client=client, response=response)
 
         return response_400
+    if response.status_code == 402:
+        response_402 = errors.bytekit_parse(Error.from_dict, client=client, response=response)
+
+        return response_402
     if response.status_code == 422:
         response_422 = errors.bytekit_parse(Error.from_dict, client=client, response=response)
 

{bytekit_sdk-0.5.1 → bytekit_sdk-0.5.2}/src/bytekit/api/scrape/create_scrape.py

@@ -45,6 +45,10 @@ def _parse_response(
         response_400 = errors.bytekit_parse(Error.from_dict, client=client, response=response)
 
         return response_400
+    if response.status_code == 402:
+        response_402 = errors.bytekit_parse(Error.from_dict, client=client, response=response)
+
+        return response_402
     if response.status_code == 422:
         response_422 = errors.bytekit_parse(Error.from_dict, client=client, response=response)
 

{bytekit_sdk-0.5.1 → bytekit_sdk-0.5.2}/src/bytekit/api/scrape_bulk/create_scrape_bulk.py

@@ -40,6 +40,10 @@ def _parse_response(
         response_400 = errors.bytekit_parse(Error.from_dict, client=client, response=response)
 
         return response_400
+    if response.status_code == 402:
+        response_402 = errors.bytekit_parse(Error.from_dict, client=client, response=response)
+
+        return response_402
     if response.status_code == 422:
         response_422 = errors.bytekit_parse(Error.from_dict, client=client, response=response)
 

{bytekit_sdk-0.5.1 → bytekit_sdk-0.5.2}/src/bytekit/api/sitemap/create_sitemap.py

@@ -40,6 +40,10 @@ def _parse_response(
         response_400 = errors.bytekit_parse(Error.from_dict, client=client, response=response)
 
         return response_400
+    if response.status_code == 402:
+        response_402 = errors.bytekit_parse(Error.from_dict, client=client, response=response)
+
+        return response_402
     if response.status_code == 422:
         response_422 = errors.bytekit_parse(Error.from_dict, client=client, response=response)
 

{bytekit_sdk-0.5.1 → bytekit_sdk-0.5.2}/src/bytekit/models/create_bulk_body_defaults_formats_item.py

@@ -2,11 +2,10 @@ from enum import Enum
 
 
 class CreateBulkBodyDefaultsFormatsItem(str, Enum):
-    HTML = "html"
     IMAGES = "images"
     LINKS = "links"
     MARKDOWN = "markdown"
-    RAW_HTML = "raw_html"
+    RAW = "raw"
 
     def __str__(self) -> str:
         return str(self.value)

{bytekit_sdk-0.5.1 → bytekit_sdk-0.5.2}/src/bytekit/models/create_bulk_body_items_item_formats_item.py

@@ -2,11 +2,10 @@ from enum import Enum
 
 
 class CreateBulkBodyItemsItemFormatsItem(str, Enum):
-    HTML = "html"
     IMAGES = "images"
     LINKS = "links"
     MARKDOWN = "markdown"
-    RAW_HTML = "raw_html"
+    RAW = "raw"
 
     def __str__(self) -> str:
         return str(self.value)

{bytekit_sdk-0.5.1 → bytekit_sdk-0.5.2}/src/bytekit/models/create_scrape_bulk_body_defaults_formats_item.py

@@ -2,11 +2,10 @@ from enum import Enum
 
 
 class CreateScrapeBulkBodyDefaultsFormatsItem(str, Enum):
-    HTML = "html"
     IMAGES = "images"
     LINKS = "links"
     MARKDOWN = "markdown"
-    RAW_HTML = "raw_html"
+    RAW = "raw"
 
     def __str__(self) -> str:
         return str(self.value)

{bytekit_sdk-0.5.1 → bytekit_sdk-0.5.2}/src/bytekit/models/create_scrape_bulk_body_items_item_formats_item.py

@@ -2,11 +2,10 @@ from enum import Enum
 
 
 class CreateScrapeBulkBodyItemsItemFormatsItem(str, Enum):
-    HTML = "html"
     IMAGES = "images"
     LINKS = "links"
     MARKDOWN = "markdown"
-    RAW_HTML = "raw_html"
+    RAW = "raw"
 
     def __str__(self) -> str:
         return str(self.value)

{bytekit_sdk-0.5.1 → bytekit_sdk-0.5.2}/src/bytekit/models/get_usage_by_endpoint_response_200_rows_item.py

@@ -19,8 +19,11 @@ class GetUsageByEndpointResponse200RowsItem:
         raw_bytes (int): Raw upstream wire bytes for the endpoint. Screenshot and recording rows created before issue
             2179 may reflect legacy billable Phase 1 bytes because exact raw totals cannot be recovered after per-job
             rounding.
-        multiplier (float): Billing multiplier applied to raw bytes (e.g. 1.5 for
-            screenshots/recordings/scrape_md/crawl, 1.0 otherwise).
+        multiplier (float): Billing multiplier applied to raw bytes, enumerated for every `endpoint` value above — there
+            is no catch-all default: 1.5 for `screenshots`, `recordings`, `scrape_md`, `fetch_md` and `crawl`; 1.0 for
+            `scrape`, `fetch`, `crawl_links`, `sitemap` and `monitors`. Requesting Markdown output moves a request from the
+            plain endpoint key to its `_md` key, so a Markdown scrape AND a Markdown fetch both bill at 1.5× (#3779). Source
+            of truth: `ENDPOINT_BILLING_MULTIPLIER` in packages/scrape-shared/src/billing-multipliers.ts.
         billable_bytes (int): raw_bytes × multiplier, rounded.
     """
 

{bytekit_sdk-0.5.1 → bytekit_sdk-0.5.2}/src/bytekit/models/scrape_formats.py

@@ -24,8 +24,8 @@ T = TypeVar("T", bound="ScrapeFormats")
 class ScrapeFormats:
     """
     Attributes:
-        raw_html (Union[Unset, str]):
-        html (Union[Unset, str]):
+        raw (Union[Unset, str]): The untouched upstream source of whatever the URL served — HTML, JSON, XML or plain
+            text.
         markdown (Union[Unset, str]):
         links (Union[Unset, list['ScrapeScoredLink'], list[str]]): Plain URL strings by default. When
             markdownIncludeMedia=true, an array of ScrapeScoredLink objects.
@@ -33,17 +33,14 @@ class ScrapeFormats:
             markdownIncludeMedia=true, an array of ScrapeScoredImage objects.
     """
 
-    raw_html: Union[Unset, str] = UNSET
-    html: Union[Unset, str] = UNSET
+    raw: Union[Unset, str] = UNSET
     markdown: Union[Unset, str] = UNSET
     links: Union[Unset, list["ScrapeScoredLink"], list[str]] = UNSET
     images: Union[Unset, list["ScrapeScoredImage"], list[str]] = UNSET
     additional_properties: dict[str, Any] = _attrs_field(init=False, factory=dict)
 
     def to_dict(self) -> dict[str, Any]:
-        raw_html = self.raw_html
-
-        html = self.html
+        raw = self.raw
 
         markdown = self.markdown
 
@@ -74,10 +71,8 @@ class ScrapeFormats:
         field_dict: dict[str, Any] = {}
         field_dict.update(self.additional_properties)
         field_dict.update({})
-        if raw_html is not UNSET:
-            field_dict["raw_html"] = raw_html
-        if html is not UNSET:
-            field_dict["html"] = html
+        if raw is not UNSET:
+            field_dict["raw"] = raw
         if markdown is not UNSET:
             field_dict["markdown"] = markdown
         if links is not UNSET:
@@ -93,9 +88,7 @@ class ScrapeFormats:
         from ..models.scrape_scored_link import ScrapeScoredLink
 
         d = dict(src_dict)
-        raw_html = d.pop("raw_html", UNSET)
-
-        html = d.pop("html", UNSET)
+        raw = d.pop("raw", UNSET)
 
         markdown = d.pop("markdown", UNSET)
 
@@ -156,8 +149,7 @@ class ScrapeFormats:
         images = _parse_images(d.pop("images", UNSET))
 
         scrape_formats = cls(
-            raw_html=raw_html,
-            html=html,
+            raw=raw,
             markdown=markdown,
             links=links,
             images=images,

{bytekit_sdk-0.5.1 → bytekit_sdk-0.5.2}/src/bytekit/models/scrape_request.py

@@ -40,7 +40,8 @@ class ScrapeRequest:
         async_ (Union[Unset, bool]):
         webhook_url (Union[Unset, str]): Webhook endpoint URL (HTTPS only; http:// rejected with 400 invalid_url, reason
             scheme_unsupported)
-        events (Union[Unset, list[ScrapeRequestEventsItem]]):
+        events (Union[Unset, list[ScrapeRequestEventsItem]]): Webhook event types to deliver when webhook_url is set.
+            Defaults to all three (queued, completed, failed); send an explicit subset to receive fewer.
         markdown_mode (Union[Unset, ScrapeRequestMarkdownMode]): Markdown processing mode. article=article extraction
             (default), raw=minimal cleanup, llm=compact LLM-optimised output.
         markdown_query (Union[Unset, str]): BM25 query string for relevance-ranked content filtering. Omit or leave
@@ -62,7 +63,7 @@ class ScrapeRequest:
             `ScrapeScoredLink[]` / `ScrapeScoredImage[]` (rich objects) instead of `string[]`, and a top-level `tables`
             array is included. Only effective when `markdown` is in `formats`.
         markdown_include_warnings (Union[Unset, bool]): When true, enables markdown-pipeline and tag-filter warnings for
-            affected `html` and `markdown` requests. Artifact availability warnings such as `artifact_unavailable` may
+            requests that include the `markdown` format. Artifact availability warnings such as `artifact_unavailable` may
             appear independently of this flag.
         markdown_include_stats (Union[Unset, bool]): When true, the response includes a top-level `stats` object with
             `ScrapeStats` (chars, tokens, blocks). Only effective when `markdown` is in `formats`.
@@ -76,15 +77,14 @@ class ScrapeRequest:
             and a mobile viewport, so the upstream serves the mobile version of the page. Default false (desktop). The value
             is part of the cache key, so mobile and desktop responses are cached independently.
         remove_base64_images (Union[Unset, bool]): When true (default), base64-encoded `data:` image sources are
-            stripped from the HTML before markdown conversion and from the `html` format output. Set to false to preserve
-            base64 images in the pipeline output. Does not affect `raw_html`, which always returns the original HTML
-            unchanged.
+            stripped from the HTML before markdown conversion. Set to false to preserve base64 images in the pipeline
+            output. Does not affect `raw`, which always returns the original source unchanged.
         include_tags (Union[Unset, list[str]]): HTML element names (not CSS selectors) to keep. When non-empty, only
-            content within these elements is included in the `html` and `markdown` output. Applied before `exclude_tags`.
-            Does not affect `raw_html`, which always returns the full page.
-        exclude_tags (Union[Unset, list[str]]): HTML element names (not CSS selectors) to strip from the `html` and
-            `markdown` output. Applied after `include_tags` when both are present. Does not affect `raw_html`, which always
-            returns the full page.
+            content within these elements is included in the `markdown` output. Applied before `exclude_tags`. Does not
+            affect `raw`, which always returns the full page.
+        exclude_tags (Union[Unset, list[str]]): HTML element names (not CSS selectors) to strip from the `markdown`
+            output. Applied after `include_tags` when both are present. Does not affect `raw`, which always returns the full
+            page.
         cache_ttl (Union[ScrapeRequestCacheTtlType1, Unset, str]): How long a freshly fetched URL may be served from
             cache. `0` (string or integer) skips the cache read; cache-eligible results are still written. `Nh`/`Nd` set a
             TTL (capped at 168 h / 7 d). Safety-classified WAF husks are returned live but never stored in the shared cache.

{bytekit_sdk-0.5.1 → bytekit_sdk-0.5.2}/src/bytekit/models/scrape_request_formats_item.py

@@ -2,11 +2,10 @@ from enum import Enum
 
 
 class ScrapeRequestFormatsItem(str, Enum):
-    HTML = "html"
     IMAGES = "images"
     LINKS = "links"
     MARKDOWN = "markdown"
-    RAW_HTML = "raw_html"
+    RAW = "raw"
 
     def __str__(self) -> str:
         return str(self.value)

{bytekit_sdk-0.5.1 → bytekit_sdk-0.5.2}/src/bytekit/models/scrape_success_envelope.py

@@ -40,19 +40,17 @@ class ScrapeSuccessEnvelope:
         {'schema_version': 1, 'status': 'success', 'id': 'sc_01j9abc123', 'url': 'https://example.com', 'final_url':
             'https://example.com/', 'content_type': 'text/html; charset=UTF-8', 'content_length': 1256, 'status_code': 200,
             'retrieved_at': datetime.datetime(2025, 1, 15, 12, 0, tzinfo=datetime.timezone(datetime.timedelta(0), 'Z')),
-            'formats': {'raw_html': '<html><body><h1>Hello World</h1><p>Example page with a <a href="/about">link</a> and an
-            image.</p></body></html>', 'html': '<html><body><h1>Hello World</h1><p>Example page with a <a
-            href="/about">link</a> and an image.</p></body></html>', 'markdown': '# Hello World\n\nExample page with a
-            [link](/about) and an image.\n\n![Alt text](https://example.com/photo.png)', 'links': [{'url':
-            'https://example.com/about', 'text': 'link', 'isInternal': True, 'rel': None}], 'images': [{'url':
-            'https://example.com/photo.png', 'alt': 'Alt text', 'width': 800, 'height': 600, 'format': 'png', 'score':
-            0.95}]}, 'metadata': {'title': 'Example Domain', 'description': 'An example page for demonstration', 'language':
-            'en', 'canonicalUrl': 'https://example.com', 'ogTitle': 'Example Domain', 'ogDescription': None, 'ogImage':
-            None, 'byline': 'Jane Doe', 'publishedAt': datetime.datetime(2025, 1, 15, 9, 0,
-            tzinfo=datetime.timezone(datetime.timedelta(0), 'Z'))}, 'tables': [{'kind': 'data', 'gfm': '| Col1 | Col2
-            |\n|------|------|\n| A | B |', 'rows': 2, 'cols': 2}], 'warnings': [{'code': 'lossy_table', 'message': 'Table
-            at index 3 was simplified', 'element': '<table>...</table>'}], 'stats': {'chars': 1256, 'tokens': 312, 'blocks':
-            4}}
+            'formats': {'raw': '<html><body><h1>Hello World</h1><p>Example page with a <a href="/about">link</a> and an
+            image.</p></body></html>', 'markdown': '# Hello World\n\nExample page with a [link](/about) and an
+            image.\n\n![Alt text](https://example.com/photo.png)', 'links': [{'url': 'https://example.com/about', 'text':
+            'link', 'isInternal': True, 'rel': None}], 'images': [{'url': 'https://example.com/photo.png', 'alt': 'Alt
+            text', 'width': 800, 'height': 600, 'format': 'png', 'score': 0.95}]}, 'metadata': {'title': 'Example Domain',
+            'description': 'An example page for demonstration', 'language': 'en', 'canonicalUrl': 'https://example.com',
+            'ogTitle': 'Example Domain', 'ogDescription': None, 'ogImage': None, 'byline': 'Jane Doe', 'publishedAt':
+            datetime.datetime(2025, 1, 15, 9, 0, tzinfo=datetime.timezone(datetime.timedelta(0), 'Z'))}, 'tables': [{'kind':
+            'data', 'gfm': '| Col1 | Col2 |\n|------|------|\n| A | B |', 'rows': 2, 'cols': 2}], 'warnings': [{'code':
+            'lossy_table', 'message': 'Table at index 3 was simplified', 'element': '<table>...</table>'}], 'stats':
+            {'chars': 1256, 'tokens': 312, 'blocks': 4}}
 
     Attributes:
         schema_version (ScrapeSuccessEnvelopeSchemaVersion): Envelope contract version emitted by current producers.