From 494fae61c5dc13356848f8cd4c8c3f901e84a99c Mon Sep 17 00:00:00 2001
From: "stainless-app[bot]"
 <142633134+stainless-app[bot]@users.noreply.github.com>
Date: Fri, 24 Apr 2026 01:02:20 +0000
Subject: [PATCH 1/2] feat(api): api update

---
 .stats.yml                                    |  4 +--
 src/context/dev/resources/web.py              | 36 +++++++++++++++++++
 .../dev/types/web_web_crawl_md_params.py      |  7 ++++
 .../dev/types/web_web_crawl_md_response.py    |  5 +++
 .../dev/types/web_web_scrape_html_params.py   |  7 ++++
 .../dev/types/web_web_scrape_md_params.py     |  7 ++++
 tests/api_resources/test_web.py               |  6 ++++
 7 files changed, 70 insertions(+), 2 deletions(-)

diff --git a/.stats.yml b/.stats.yml
index 98e8c8a..592a4b2 100644
--- a/.stats.yml
+++ b/.stats.yml
@@ -1,4 +1,4 @@
 configured_endpoints: 21
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/context-dev%2Fcontext.dev-ca8e38b0f28a9967dab631b8868f1d59bc035fd994a717e0125c77ca592bd105.yml
-openapi_spec_hash: ef0a5df01201a032dcc41f9a25b733e6
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/context-dev%2Fcontext.dev-ee23a181bfa364090a90254a433704adf4d3b413730fe75e5ad9a26273ec517a.yml
+openapi_spec_hash: bc99d89cb1e7cdacc997214305bffee7
 config_hash: 7d13dca2b2c6f71fc463cb6062efa5ea
diff --git a/src/context/dev/resources/web.py b/src/context/dev/resources/web.py
index 5fca4db..59643e9 100644
--- a/src/context/dev/resources/web.py
+++ b/src/context/dev/resources/web.py
@@ -254,6 +254,7 @@ def web_crawl_md(
         max_age_ms: int | Omit = omit,
         max_depth: int | Omit = omit,
         max_pages: int | Omit = omit,
+        parse_pdf: bool | Omit = omit,
         shorten_base64_images: bool | Omit = omit,
         url_regex: str | Omit = omit,
         use_main_content_only: bool | Omit = omit,
@@ -287,6 +288,10 @@ def web_crawl_md(
 
           max_pages: Maximum number of pages to crawl. Hard cap: 500.
 
+          parse_pdf: When true (default), PDF pages are fetched and their text layer is extracted and
+              converted to Markdown alongside HTML pages. When false, PDF pages are skipped
+              entirely (not included in results and not counted as failures).
+
           shorten_base64_images: Truncate base64-encoded image data in the Markdown output
 
           url_regex: Regex pattern. Only URLs matching this pattern will be followed and scraped.
@@ -313,6 +318,7 @@ def web_crawl_md(
                     "max_age_ms": max_age_ms,
                     "max_depth": max_depth,
                     "max_pages": max_pages,
+                    "parse_pdf": parse_pdf,
                     "shorten_base64_images": shorten_base64_images,
                     "url_regex": url_regex,
                     "use_main_content_only": use_main_content_only,
@@ -330,6 +336,7 @@ def web_scrape_html(
         *,
         url: str,
         max_age_ms: int | Omit = omit,
+        parse_pdf: bool | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
@@ -347,6 +354,10 @@ def web_scrape_html(
               younger than this many milliseconds. Defaults to 1 day (86400000 ms) when
               omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
 
+          parse_pdf: When true (default), PDF URLs are fetched and their text layer is extracted and
+              returned wrapped in <html><pdf>…</pdf></html>. When false, PDF URLs are skipped
+              and a 400 WEBSITE_ACCESS_ERROR is returned.
+
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request
@@ -366,6 +377,7 @@ def web_scrape_html(
                     {
                         "url": url,
                         "max_age_ms": max_age_ms,
+                        "parse_pdf": parse_pdf,
                     },
                     web_web_scrape_html_params.WebWebScrapeHTMLParams,
                 ),
@@ -420,6 +432,7 @@ def web_scrape_md(
         include_images: bool | Omit = omit,
         include_links: bool | Omit = omit,
         max_age_ms: int | Omit = omit,
+        parse_pdf: bool | Omit = omit,
         shorten_base64_images: bool | Omit = omit,
         use_main_content_only: bool | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
@@ -444,6 +457,10 @@ def web_scrape_md(
               younger than this many milliseconds. Defaults to 1 day (86400000 ms) when
               omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
 
+          parse_pdf: When true (default), PDF URLs are fetched and their text layer is extracted and
+              converted to Markdown. When false, PDF URLs are skipped and a 400
+              WEBSITE_ACCESS_ERROR is returned.
+
           shorten_base64_images: Shorten base64-encoded image data in the Markdown output
 
           use_main_content_only: Extract only the main content of the page, excluding headers, footers, sidebars,
@@ -470,6 +487,7 @@ def web_scrape_md(
                         "include_images": include_images,
                         "include_links": include_links,
                         "max_age_ms": max_age_ms,
+                        "parse_pdf": parse_pdf,
                         "shorten_base64_images": shorten_base64_images,
                         "use_main_content_only": use_main_content_only,
                     },
@@ -747,6 +765,7 @@ async def web_crawl_md(
         max_age_ms: int | Omit = omit,
         max_depth: int | Omit = omit,
         max_pages: int | Omit = omit,
+        parse_pdf: bool | Omit = omit,
         shorten_base64_images: bool | Omit = omit,
         url_regex: str | Omit = omit,
         use_main_content_only: bool | Omit = omit,
@@ -780,6 +799,10 @@ async def web_crawl_md(
 
           max_pages: Maximum number of pages to crawl. Hard cap: 500.
 
+          parse_pdf: When true (default), PDF pages are fetched and their text layer is extracted and
+              converted to Markdown alongside HTML pages. When false, PDF pages are skipped
+              entirely (not included in results and not counted as failures).
+
           shorten_base64_images: Truncate base64-encoded image data in the Markdown output
 
           url_regex: Regex pattern. Only URLs matching this pattern will be followed and scraped.
@@ -806,6 +829,7 @@ async def web_crawl_md(
                     "max_age_ms": max_age_ms,
                     "max_depth": max_depth,
                     "max_pages": max_pages,
+                    "parse_pdf": parse_pdf,
                     "shorten_base64_images": shorten_base64_images,
                     "url_regex": url_regex,
                     "use_main_content_only": use_main_content_only,
@@ -823,6 +847,7 @@ async def web_scrape_html(
         *,
         url: str,
         max_age_ms: int | Omit = omit,
+        parse_pdf: bool | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
@@ -840,6 +865,10 @@ async def web_scrape_html(
               younger than this many milliseconds. Defaults to 1 day (86400000 ms) when
               omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
 
+          parse_pdf: When true (default), PDF URLs are fetched and their text layer is extracted and
+              returned wrapped in <html><pdf>…</pdf></html>. When false, PDF URLs are skipped
+              and a 400 WEBSITE_ACCESS_ERROR is returned.
+
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request
@@ -859,6 +888,7 @@ async def web_scrape_html(
                     {
                         "url": url,
                         "max_age_ms": max_age_ms,
+                        "parse_pdf": parse_pdf,
                     },
                     web_web_scrape_html_params.WebWebScrapeHTMLParams,
                 ),
@@ -913,6 +943,7 @@ async def web_scrape_md(
         include_images: bool | Omit = omit,
         include_links: bool | Omit = omit,
         max_age_ms: int | Omit = omit,
+        parse_pdf: bool | Omit = omit,
         shorten_base64_images: bool | Omit = omit,
         use_main_content_only: bool | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
@@ -937,6 +968,10 @@ async def web_scrape_md(
               younger than this many milliseconds. Defaults to 1 day (86400000 ms) when
               omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
 
+          parse_pdf: When true (default), PDF URLs are fetched and their text layer is extracted and
+              converted to Markdown. When false, PDF URLs are skipped and a 400
+              WEBSITE_ACCESS_ERROR is returned.
+
           shorten_base64_images: Shorten base64-encoded image data in the Markdown output
 
           use_main_content_only: Extract only the main content of the page, excluding headers, footers, sidebars,
@@ -963,6 +998,7 @@ async def web_scrape_md(
                         "include_images": include_images,
                         "include_links": include_links,
                         "max_age_ms": max_age_ms,
+                        "parse_pdf": parse_pdf,
                         "shorten_base64_images": shorten_base64_images,
                         "use_main_content_only": use_main_content_only,
                     },
diff --git a/src/context/dev/types/web_web_crawl_md_params.py b/src/context/dev/types/web_web_crawl_md_params.py
index 7cf4bb9..69ee967 100644
--- a/src/context/dev/types/web_web_crawl_md_params.py
+++ b/src/context/dev/types/web_web_crawl_md_params.py
@@ -39,6 +39,13 @@ class WebWebCrawlMdParams(TypedDict, total=False):
     max_pages: Annotated[int, PropertyInfo(alias="maxPages")]
     """Maximum number of pages to crawl. Hard cap: 500."""
 
+    parse_pdf: Annotated[bool, PropertyInfo(alias="parsePDF")]
+    """
+    When true (default), PDF pages are fetched and their text layer is extracted and
+    converted to Markdown alongside HTML pages. When false, PDF pages are skipped
+    entirely (not included in results and not counted as failures).
+    """
+
     shorten_base64_images: Annotated[bool, PropertyInfo(alias="shortenBase64Images")]
     """Truncate base64-encoded image data in the Markdown output"""
 
diff --git a/src/context/dev/types/web_web_crawl_md_response.py b/src/context/dev/types/web_web_crawl_md_response.py
index 49ba2d8..9c6cda1 100644
--- a/src/context/dev/types/web_web_crawl_md_response.py
+++ b/src/context/dev/types/web_web_crawl_md_response.py
@@ -16,6 +16,11 @@ class Metadata(BaseModel):
     num_failed: int = FieldInfo(alias="numFailed")
     """Number of pages that failed to crawl"""
 
+    num_skipped: int = FieldInfo(alias="numSkipped")
+    """
+    Number of URLs skipped (PDFs when parsePDF=false, or URLs not matching urlRegex)
+    """
+
     num_succeeded: int = FieldInfo(alias="numSucceeded")
     """Number of pages successfully crawled"""
 
diff --git a/src/context/dev/types/web_web_scrape_html_params.py b/src/context/dev/types/web_web_scrape_html_params.py
index d184801..f1eb86c 100644
--- a/src/context/dev/types/web_web_scrape_html_params.py
+++ b/src/context/dev/types/web_web_scrape_html_params.py
@@ -19,3 +19,10 @@ class WebWebScrapeHTMLParams(TypedDict, total=False):
     younger than this many milliseconds. Defaults to 1 day (86400000 ms) when
     omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
     """
+
+    parse_pdf: Annotated[bool, PropertyInfo(alias="parsePDF")]
+    """
+    When true (default), PDF URLs are fetched and their text layer is extracted and
+    returned wrapped in <html><pdf>…</pdf></html>. When false, PDF URLs are skipped
+    and a 400 WEBSITE_ACCESS_ERROR is returned.
+    """
diff --git a/src/context/dev/types/web_web_scrape_md_params.py b/src/context/dev/types/web_web_scrape_md_params.py
index 8cc9333..ab364f5 100644
--- a/src/context/dev/types/web_web_scrape_md_params.py
+++ b/src/context/dev/types/web_web_scrape_md_params.py
@@ -29,6 +29,13 @@ class WebWebScrapeMdParams(TypedDict, total=False):
     omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
     """
 
+    parse_pdf: Annotated[bool, PropertyInfo(alias="parsePDF")]
+    """
+    When true (default), PDF URLs are fetched and their text layer is extracted and
+    converted to Markdown. When false, PDF URLs are skipped and a 400
+    WEBSITE_ACCESS_ERROR is returned.
+    """
+
     shorten_base64_images: Annotated[bool, PropertyInfo(alias="shortenBase64Images")]
     """Shorten base64-encoded image data in the Markdown output"""
 
diff --git a/tests/api_resources/test_web.py b/tests/api_resources/test_web.py
index 6474cb1..04082f7 100644
--- a/tests/api_resources/test_web.py
+++ b/tests/api_resources/test_web.py
@@ -161,6 +161,7 @@ def test_method_web_crawl_md_with_all_params(self, client: ContextDev) -> None:
             max_age_ms=0,
             max_depth=0,
             max_pages=1,
+            parse_pdf=True,
             shorten_base64_images=True,
             url_regex="^https?://[^/]+/blog/",
             use_main_content_only=True,
@@ -207,6 +208,7 @@ def test_method_web_scrape_html_with_all_params(self, client: ContextDev) -> Non
         web = client.web.web_scrape_html(
             url="https://example.com",
             max_age_ms=0,
+            parse_pdf=True,
         )
         assert_matches_type(WebWebScrapeHTMLResponse, web, path=["response"])
 
@@ -286,6 +288,7 @@ def test_method_web_scrape_md_with_all_params(self, client: ContextDev) -> None:
             include_images=True,
             include_links=True,
             max_age_ms=0,
+            parse_pdf=True,
             shorten_base64_images=True,
             use_main_content_only=True,
         )
@@ -502,6 +505,7 @@ async def test_method_web_crawl_md_with_all_params(self, async_client: AsyncCont
             max_age_ms=0,
             max_depth=0,
             max_pages=1,
+            parse_pdf=True,
             shorten_base64_images=True,
             url_regex="^https?://[^/]+/blog/",
             use_main_content_only=True,
@@ -548,6 +552,7 @@ async def test_method_web_scrape_html_with_all_params(self, async_client: AsyncC
         web = await async_client.web.web_scrape_html(
             url="https://example.com",
             max_age_ms=0,
+            parse_pdf=True,
         )
         assert_matches_type(WebWebScrapeHTMLResponse, web, path=["response"])
 
@@ -627,6 +632,7 @@ async def test_method_web_scrape_md_with_all_params(self, async_client: AsyncCon
             include_images=True,
             include_links=True,
             max_age_ms=0,
+            parse_pdf=True,
             shorten_base64_images=True,
             use_main_content_only=True,
         )

From 675a04f1dd5b05012d21fab80da397c5b8fc855d Mon Sep 17 00:00:00 2001
From: "stainless-app[bot]"
 <142633134+stainless-app[bot]@users.noreply.github.com>
Date: Fri, 24 Apr 2026 01:02:41 +0000
Subject: [PATCH 2/2] release: 0.10.0

---
 .release-please-manifest.json | 2 +-
 CHANGELOG.md                  | 8 ++++++++
 pyproject.toml                | 2 +-
 src/context/dev/_version.py   | 2 +-
 4 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/.release-please-manifest.json b/.release-please-manifest.json
index 6d78745..091cfb1 100644
--- a/.release-please-manifest.json
+++ b/.release-please-manifest.json
@@ -1,3 +1,3 @@
 {
-  ".": "0.9.0"
+  ".": "0.10.0"
 }
\ No newline at end of file
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 543fc7e..9a848de 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,13 @@
 # Changelog
 
+## 0.10.0 (2026-04-24)
+
+Full Changelog: [v0.9.0...v0.10.0](https://github.com/context-dot-dev/context-python-sdk/compare/v0.9.0...v0.10.0)
+
+### Features
+
+* **api:** api update ([494fae6](https://github.com/context-dot-dev/context-python-sdk/commit/494fae61c5dc13356848f8cd4c8c3f901e84a99c))
+
 ## 0.9.0 (2026-04-23)
 
 Full Changelog: [v0.8.0...v0.9.0](https://github.com/context-dot-dev/context-python-sdk/compare/v0.8.0...v0.9.0)
diff --git a/pyproject.toml b/pyproject.toml
index 370218e..21a2aa8 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "context.dev"
-version = "0.9.0"
+version = "0.10.0"
 description = "The official Python library for the context.dev API"
 dynamic = ["readme"]
 license = "Apache-2.0"
diff --git a/src/context/dev/_version.py b/src/context/dev/_version.py
index a5aba43..d074db9 100644
--- a/src/context/dev/_version.py
+++ b/src/context/dev/_version.py
@@ -1,4 +1,4 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
 __title__ = "context.dev"
-__version__ = "0.9.0"  # x-release-please-version
+__version__ = "0.10.0"  # x-release-please-version