From 588de042fcc86ec7017673b11e5c2151b5b4fad0 Mon Sep 17 00:00:00 2001
From: nightcityblade <nightcityblade@gmail.com>
Date: Sat, 1 Aug 2026 09:08:39 +0800
Subject: [PATCH] fix(docker): preserve single-url crawl failure details

---
 deploy/docker/api.py                          | 25 +++++++++++--------
 .../docker/tests/test_api_crawl_failures.py   | 24 ++++++++++++++++++
 2 files changed, 38 insertions(+), 11 deletions(-)
 create mode 100644 deploy/docker/tests/test_api_crawl_failures.py

diff --git a/deploy/docker/api.py b/deploy/docker/api.py
index 1756b925f..22e061096 100644
--- a/deploy/docker/api.py
+++ b/deploy/docker/api.py
@@ -92,6 +92,15 @@ def _attach_declarative_hooks(crawler, hooks_config: dict) -> dict:
 
 logger = logging.getLogger(__name__)
 
+
+def _raise_for_crawl_failure(result):
+    if not result.success:
+        raise HTTPException(
+            status_code=status.HTTP_502_BAD_GATEWAY,
+            detail=result.error_message,
+        )
+
+
 # --- Helper to get memory ---
 def _get_memory_mb():
     try:
@@ -147,11 +156,7 @@ async def handle_llm_qa(
         enforce_egress(browser_cfg)
         crawler = await get_crawler(browser_cfg)
         result = await crawler.arun(url)
-        if not result.success:
-            raise HTTPException(
-                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
-                detail=result.error_message
-            )
+        _raise_for_crawl_failure(result)
         content = result.markdown.fit_markdown or result.markdown.raw_markdown
 
         # Create prompt and get LLM response
@@ -179,6 +184,8 @@ async def handle_llm_qa(
         )
 
         return response.choices[0].message.content
+    except HTTPException:
+        raise
     except LLMProviderNotAllowed as e:
         raise HTTPException(status_code=400, detail=str(e))
     except Exception as e:
@@ -389,11 +396,7 @@ async def handle_markdown_request(
             )
         )
 
-        if not result.success:
-            raise HTTPException(
-                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
-                detail=result.error_message
-            )
+        _raise_for_crawl_failure(result)
 
         return (result.markdown.raw_markdown
                if filter_type == FilterType.RAW
@@ -1023,4 +1026,4 @@ async def _runner():
     except HTTPException:
         await redis.delete(f"task:{task_id}")
         raise
-    return {"task_id": task_id}
\ No newline at end of file
+    return {"task_id": task_id}
diff --git a/deploy/docker/tests/test_api_crawl_failures.py b/deploy/docker/tests/test_api_crawl_failures.py
new file mode 100644
index 000000000..6c8fa817f
--- /dev/null
+++ b/deploy/docker/tests/test_api_crawl_failures.py
@@ -0,0 +1,24 @@
+import inspect
+from types import SimpleNamespace
+
+import pytest
+from fastapi import HTTPException
+
+from api import _raise_for_crawl_failure, handle_llm_qa, handle_markdown_request
+
+
+def test_crawl_failure_is_reported_as_bad_gateway():
+    result = SimpleNamespace(success=False, error_message="Blocked by anti-bot protection: challenge")
+
+    with pytest.raises(HTTPException) as raised:
+        _raise_for_crawl_failure(result)
+
+    assert raised.value.status_code == 502
+    assert raised.value.detail == result.error_message
+
+
+@pytest.mark.parametrize("handler", [handle_llm_qa, handle_markdown_request])
+def test_single_url_handlers_use_crawl_failure_mapping(handler):
+    source = inspect.getsource(handler)
+    assert "_raise_for_crawl_failure(result)" in source
+    assert handler is not handle_llm_qa or "except HTTPException:" in source