feat(api): api update

Author: stainless-app[bot]

.stats.yml

@@ -1,4 +1,4 @@
 configured_endpoints: 21
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/context-dev%2Fcontext.dev-5afee68d7308a77a9ef51fb53917080746f96327c6d745fc029363a7d1494c3c.yml
-openapi_spec_hash: b2e32bb58d92a00f6ede04c4f7bf1a34
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/context-dev%2Fcontext.dev-571a58f35555a19e8ca5581dc53e6aeb8f9a8d58ae98e2f3c1a1c06463007a9f.yml
+openapi_spec_hash: 4ad9b0a6fc6f6c64a84b531fdafa80bf
 config_hash: 7d13dca2b2c6f71fc463cb6062efa5ea

src/context/dev/resources/web.py

@@ -478,6 +478,7 @@ def web_scrape_sitemap(
         *,
         domain: str,
         max_links: int | Omit = omit,
+        url_regex: str | 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,
@@ -494,6 +495,9 @@ def web_scrape_sitemap(
           max_links: Maximum number of links to return from the sitemap crawl. Defaults to 10,000.
               Minimum is 1, maximum is 100,000.
 
+          url_regex: Optional RE2-compatible regex pattern. Only URLs matching this pattern are
+              returned and counted against maxLinks.
+
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request
@@ -513,6 +517,7 @@ def web_scrape_sitemap(
                     {
                         "domain": domain,
                         "max_links": max_links,
+                        "url_regex": url_regex,
                     },
                     web_web_scrape_sitemap_params.WebWebScrapeSitemapParams,
                 ),
@@ -960,6 +965,7 @@ async def web_scrape_sitemap(
         *,
         domain: str,
         max_links: int | Omit = omit,
+        url_regex: str | 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,
@@ -976,6 +982,9 @@ async def web_scrape_sitemap(
           max_links: Maximum number of links to return from the sitemap crawl. Defaults to 10,000.
               Minimum is 1, maximum is 100,000.
 
+          url_regex: Optional RE2-compatible regex pattern. Only URLs matching this pattern are
+              returned and counted against maxLinks.
+
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request
@@ -995,6 +1004,7 @@ async def web_scrape_sitemap(
                     {
                         "domain": domain,
                         "max_links": max_links,
+                        "url_regex": url_regex,
                     },
                     web_web_scrape_sitemap_params.WebWebScrapeSitemapParams,
                 ),

src/context/dev/types/web_web_scrape_sitemap_params.py

@@ -18,3 +18,9 @@ class WebWebScrapeSitemapParams(TypedDict, total=False):
 
     Defaults to 10,000. Minimum is 1, maximum is 100,000.
     """
+
+    url_regex: Annotated[str, PropertyInfo(alias="urlRegex")]
+    """Optional RE2-compatible regex pattern.
+
+    Only URLs matching this pattern are returned and counted against maxLinks.
+    """

tests/api_resources/test_web.py

@@ -161,7 +161,7 @@ def test_method_web_crawl_md_with_all_params(self, client: ContextDev) -> None:
             max_depth=0,
             max_pages=1,
             shorten_base64_images=True,
-            url_regex="urlRegex",
+            url_regex="^https?://[^/]+/blog/",
             use_main_content_only=True,
         )
         assert_matches_type(WebWebCrawlMdResponse, web, path=["response"])
@@ -330,6 +330,7 @@ def test_method_web_scrape_sitemap_with_all_params(self, client: ContextDev) ->
         web = client.web.web_scrape_sitemap(
             domain="domain",
             max_links=1,
+            url_regex="^https?://[^/]+/blog/",
         )
         assert_matches_type(WebWebScrapeSitemapResponse, web, path=["response"])
 
@@ -500,7 +501,7 @@ async def test_method_web_crawl_md_with_all_params(self, async_client: AsyncCont
             max_depth=0,
             max_pages=1,
             shorten_base64_images=True,
-            url_regex="urlRegex",
+            url_regex="^https?://[^/]+/blog/",
             use_main_content_only=True,
         )
         assert_matches_type(WebWebCrawlMdResponse, web, path=["response"])
@@ -669,6 +670,7 @@ async def test_method_web_scrape_sitemap_with_all_params(self, async_client: Asy
         web = await async_client.web.web_scrape_sitemap(
             domain="domain",
             max_links=1,
+            url_regex="^https?://[^/]+/blog/",
         )
         assert_matches_type(WebWebScrapeSitemapResponse, web, path=["response"])