unique-search-proxy 2026.44.0.dev5__tar.gz → 2026.44.0.dev7__tar.gz

{unique_search_proxy-2026.44.0.dev5 → unique_search_proxy-2026.44.0.dev7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: unique-search-proxy
-Version: 2026.44.0.dev5
+Version: 2026.44.0.dev7
 Summary: Web Search Proxy implementation
 Author: ThePhilAz
 Author-email: ThePhilAz <rami.azouz@philico.com>
@@ -21,7 +21,7 @@ Requires-Dist: google-genai>=1.73.0,<2
 Requires-Dist: google-auth>=2.43.0,<3
 Requires-Dist: jinja2>=3.1.6,<4
 Requires-Dist: unique-toolkit[monitoring]>=2026.44.0.dev9,<2026.44.0rc0
-Requires-Dist: unique-search-proxy-core>=2026.44.0.dev4,<2026.44.0rc0
+Requires-Dist: unique-search-proxy-core>=2026.44.0.dev6,<2026.44.0rc0
 Requires-Dist: openai>=1.105.0,<3
 Requires-Python: >=3.12
 Description-Content-Type: text/markdown

{unique_search_proxy-2026.44.0.dev5 → unique_search_proxy-2026.44.0.dev7}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "unique-search-proxy"
-version = "2026.44.0.dev5"
+version = "2026.44.0.dev7"
 description = "Web Search Proxy implementation"
 authors = [{ name = "ThePhilAz", email = "rami.azouz@philico.com" }]
 readme = "README.md"
@@ -23,7 +23,7 @@ dependencies = [
     "google-auth>=2.43.0,<3",
     "jinja2>=3.1.6,<4",
     "unique-toolkit[monitoring]>=2026.44.0.dev9,<2026.44.0rc0",
-    "unique-search-proxy-core>=2026.44.0.dev4,<2026.44.0rc0",
+    "unique-search-proxy-core>=2026.44.0.dev6,<2026.44.0rc0",
     "openai>=1.105.0,<3",
 ]
 

unique_search_proxy-2026.44.0.dev7/unique_search_proxy_client/web/core/agent_engines/vertexai/redirects.py

@@ -0,0 +1,30 @@
+from __future__ import annotations
+
+from httpx import AsyncClient
+from unique_search_proxy_core.agent_engines.output_schema import AgentSearchOutput
+from unique_search_proxy_core.url_safety import UrlSafetyService
+
+
+async def resolve_vertex_result_urls(
+    answer: str,
+    *,
+    http_client: AsyncClient,
+) -> str:
+    """Resolve structured Vertex result URLs through Search Proxy URL safety."""
+    try:
+        output = AgentSearchOutput.model_validate_json(answer)
+    except ValueError:
+        return answer
+
+    outcomes = await UrlSafetyService.validate_urls_individually(
+        [result.source_url for result in output.results],
+        redirect_http_client=http_client,
+    )
+    for result, outcome in zip(output.results, outcomes, strict=True):
+        if outcome.resolved is not None:
+            result.source_url = outcome.resolved.normalized_url
+
+    return output.model_dump_json()
+
+
+__all__ = ["resolve_vertex_result_urls"]

{unique_search_proxy-2026.44.0.dev5 → unique_search_proxy-2026.44.0.dev7}/unique_search_proxy_client/web/core/agent_engines/vertexai/service.py

@@ -4,6 +4,7 @@ import logging
 from collections.abc import AsyncIterator
 from typing import Any
 
+from httpx import AsyncClient
 from unique_search_proxy_core.agent_engines.base import AgentEngineType
 from unique_search_proxy_core.agent_engines.resolve import (
     resolve_output_schema_for_engine,
@@ -30,6 +31,9 @@ from unique_search_proxy_client.web.core.agent_engines.vertexai.gemini import (
     serialize_vertex_response,
     stream_vertexai_response,
 )
+from unique_search_proxy_client.web.core.agent_engines.vertexai.redirects import (
+    resolve_vertex_result_urls,
+)
 from unique_search_proxy_client.web.core.provider_response import transport_error_raw
 
 _LOGGER = logging.getLogger(__name__)
@@ -40,9 +44,10 @@ class VertexAIAgentSearchService(
 ):
     engine_id = AgentEngineType.VERTEXAI.value
 
-    def __init__(self, **kwargs: Any) -> None:
-        super().__init__(**kwargs)
-        self._client = get_vertex_client(self._http_client)
+    def __init__(self, *, http_client: AsyncClient) -> None:
+        super().__init__(http_client=http_client)
+        self._egress_http_client = http_client
+        self._client = get_vertex_client(http_client)
 
     async def search(self, request: VertexAIAgentSearchRequest) -> AgentSearchResponse:  # type: ignore[override]
         response: AgentSearchResponse | None = None
@@ -52,6 +57,11 @@ class VertexAIAgentSearchService(
         if response is None:
             msg = "VertexAI agent search stream ended without a done event"
             raise UpstreamError(msg)
+        if request.enable_redirect_resolution:
+            response.answer = await resolve_vertex_result_urls(
+                response.answer,
+                http_client=self._egress_http_client,
+            )
         return response
 
     async def stream(

{unique_search_proxy-2026.44.0.dev5 → unique_search_proxy-2026.44.0.dev7}/unique_search_proxy_client/web/core/crawlers/basic/service.py

@@ -124,7 +124,10 @@ class BasicCrawlerService(BaseCrawler[BasicCrawlRequest]):
                 )
                 return crawl_forbidden_target(display_url, blocked.reason)
             except httpx.TimeoutException as exc:
-                _LOGGER.warning("Basic crawl timed out for %s: %s", display_url, exc)
+                _LOGGER.warning(
+                    "Basic crawl timed out error_type=%s",
+                    type(exc).__name__,
+                )
                 return crawl_upstream_error(
                     display_url,
                     f"Crawl timed out after {timeout}s",
@@ -133,7 +136,10 @@ class BasicCrawlerService(BaseCrawler[BasicCrawlRequest]):
                     raw=transport_error_raw(exc),
                 )
             except httpx.HTTPError as exc:
-                _LOGGER.warning("Basic crawl failed for %s: %s", display_url, exc)
+                _LOGGER.warning(
+                    "Basic crawl failed error_type=%s",
+                    type(exc).__name__,
+                )
                 return crawl_upstream_error(
                     display_url,
                     str(exc),
@@ -145,8 +151,7 @@ class BasicCrawlerService(BaseCrawler[BasicCrawlRequest]):
             raw_body = response.text
             if response.is_error:
                 _LOGGER.warning(
-                    "Basic crawl HTTP error for %s: %s",
-                    display_url,
+                    "Basic crawl HTTP error http_status=%s",
                     response.status_code,
                 )
                 return crawl_upstream_error(
@@ -195,11 +200,7 @@ class BasicCrawlerService(BaseCrawler[BasicCrawlRequest]):
                 timeout=float(timeout),
             )
         except ContentProcessingTimeoutError as exc:
-            _LOGGER.warning(
-                "Basic crawl processing timed out for %s: %s",
-                request_url,
-                exc,
-            )
+            _LOGGER.warning("Basic crawl processing timed out: %s", exc)
             return crawl_upstream_error(
                 request_url,
                 str(exc),
@@ -209,9 +210,8 @@ class BasicCrawlerService(BaseCrawler[BasicCrawlRequest]):
             )
         except ContentProcessingError as exc:
             _LOGGER.warning(
-                "Basic crawl processing failed for %s: %s",
-                request_url,
-                exc,
+                "Basic crawl processing failed error_type=%s",
+                type(exc.__cause__ or exc).__name__,
             )
             return crawl_upstream_error(
                 request_url,

{unique_search_proxy-2026.44.0.dev5 → unique_search_proxy-2026.44.0.dev7}/unique_search_proxy_client/web/core/crawlers/jina/service.py

@@ -139,8 +139,7 @@ class JinaCrawlerService(BaseCrawler[JinaCrawlRequest]):
         if reader_response.code != 200:
             message = _jina_reader_error_message(payload, reader_response.code)
             _LOGGER.warning(
-                "Jina reader failure url=%s endpoint=%s http_status=%s code=%s",
-                url,
+                "Jina reader failure endpoint=%s http_status=%s code=%s",
                 credentials.reader_endpoint,
                 response.status_code,
                 reader_response.code,

{unique_search_proxy-2026.44.0.dev5 → unique_search_proxy-2026.44.0.dev7}/unique_search_proxy_client/web/core/search_engines/brave/service.py

@@ -81,7 +81,7 @@ class BraveSearchService(SearchEngineService[BraveSearchRequest]):
             if not page_results:
                 if not len(curated.results):
                     raise EmptySearchResultsError(
-                        f"Brave search returned no results for query {request.query!r}",
+                        "Brave search returned no results",
                     )
                 break
             curated = curated.extend(page_results)

{unique_search_proxy-2026.44.0.dev5 → unique_search_proxy-2026.44.0.dev7}/unique_search_proxy_client/web/core/search_engines/google/service.py

@@ -82,7 +82,7 @@ class GoogleSearchService(SearchEngineService[GoogleSearchRequest]):
             if not page_results:
                 if not len(curated.results):
                     raise EmptySearchResultsError(
-                        f"Google search returned no results for query {request.query!r}",
+                        "Google search returned no results",
                     )
                 break
             curated = curated.extend(page_results)

{unique_search_proxy-2026.44.0.dev5 → unique_search_proxy-2026.44.0.dev7}/unique_search_proxy_client/web/core/search_engines/perplexity/service.py

@@ -93,7 +93,7 @@ class PerplexitySearchService(SearchEngineService[PerplexitySearchRequest]):
         curated = WebSearchResults(results=self._extract_results(payload))
         if not curated.results:
             raise EmptySearchResultsError(
-                f"Perplexity search returned no results for query {request.query!r}",
+                "Perplexity search returned no results",
             )
 
         curated = curated.dedupe()