fix: Check for raw: and raw:// URLs before auto-appending https:// prefix

- Add raw HTML URL validation alongside http/https checks
- Fix URL preprocessing logic to handle raw: and raw:// prefixes
- Update error message and add comprehensive test cases

deploy/docker/api.py

@@ -65,7 +65,7 @@ async def handle_llm_qa(
 ) -> str:
     """Process QA using LLM with crawled content as context."""
     try:
-        if not url.startswith(('http://', 'https://')):
+        if not url.startswith(('http://', 'https://')) and not url.startswith(("raw:", "raw://")):
             url = 'https://' + url
         # Extract base URL by finding last '?q=' occurrence
         last_q_index = url.rfind('?q=')
@@ -191,7 +191,7 @@ async def handle_markdown_request(
                     detail=error_msg
                 )
         decoded_url = unquote(url)
-        if not decoded_url.startswith(('http://', 'https://')):
+        if not decoded_url.startswith(('http://', 'https://')) and not decoded_url.startswith(("raw:", "raw://")):
             decoded_url = 'https://' + decoded_url
 
         if filter_type == FilterType.RAW:
@@ -328,7 +328,7 @@ async def create_new_task(
 ) -> JSONResponse:
     """Create and initialize a new task."""
     decoded_url = unquote(input_path)
-    if not decoded_url.startswith(('http://', 'https://')):
+    if not decoded_url.startswith(('http://', 'https://')) and not decoded_url.startswith(("raw:", "raw://")):
         decoded_url = 'https://' + decoded_url
 
     from datetime import datetime
@@ -428,7 +428,7 @@ async def handle_crawl_request(
     peak_mem_mb = start_mem_mb
     
     try:
-        urls = [('https://' + url) if not url.startswith(('http://', 'https://')) else url for url in urls]
+        urls = [('https://' + url) if not url.startswith(('http://', 'https://')) and not url.startswith(("raw:", "raw://")) else url for url in urls]
         browser_config = BrowserConfig.load(browser_config)
         crawler_config = CrawlerRunConfig.load(crawler_config)
 

deploy/docker/server.py

@@ -237,9 +237,9 @@ async def get_markdown(
     body: MarkdownRequest,
     _td: Dict = Depends(token_dep),
 ):
-    if not body.url.startswith(("http://", "https://")):
+    if not body.url.startswith(("http://", "https://")) and not body.url.startswith(("raw:", "raw://")):
         raise HTTPException(
-            400, "URL must be absolute and start with http/https")
+            400, "Invalid URL format. Must start with http://, https://, or for raw HTML (raw:, raw://)")
     markdown = await handle_markdown_request(
         body.url, body.f, body.q, body.c, config, body.provider
     )
@@ -401,7 +401,7 @@ async def llm_endpoint(
 ):
     if not q:
         raise HTTPException(400, "Query parameter 'q' is required")
-    if not url.startswith(("http://", "https://")):
+    if not url.startswith(("http://", "https://")) and not url.startswith(("raw:", "raw://")):
         url = "https://" + url
     answer = await handle_llm_qa(url, q, config)
     return JSONResponse({"answer": answer})