refactor: add public URL handling for SurfSense documents across various components and schemas

surfsense_backend/app/agents/multi_agent_chat/subagents/builtins/research/tools/search_surfsense_docs.py

@@ -9,6 +9,7 @@ from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.db import SurfsenseDocsChunk, SurfsenseDocsDocument
 from app.utils.document_converters import embed_text
+from app.utils.surfsense_docs import surfsense_docs_public_url
 
 
 def format_surfsense_docs_results(results: list[tuple]) -> str:
@@ -19,13 +20,14 @@ def format_surfsense_docs_results(results: list[tuple]) -> str:
     # Group chunks by document
     grouped: dict[int, dict] = {}
     for chunk, doc in results:
+        public_url = surfsense_docs_public_url(doc.source)
         if doc.id not in grouped:
             grouped[doc.id] = {
                 "document_id": f"doc-{doc.id}",
                 "document_type": "SURFSENSE_DOCS",
                 "title": doc.title,
-                "url": doc.source,
-                "metadata": {"source": doc.source},
+                "url": public_url,
+                "metadata": {"source": doc.source, "public_url": public_url},
                 "chunks": [],
             }
         grouped[doc.id]["chunks"].append(

surfsense_backend/app/agents/new_chat/tools/search_surfsense_docs.py

@@ -17,6 +17,7 @@ from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.db import SurfsenseDocsChunk, SurfsenseDocsDocument, async_session_maker
 from app.utils.document_converters import embed_text
+from app.utils.surfsense_docs import surfsense_docs_public_url
 
 
 def format_surfsense_docs_results(results: list[tuple]) -> str:
@@ -40,13 +41,14 @@ def format_surfsense_docs_results(results: list[tuple]) -> str:
     # Group chunks by document
     grouped: dict[int, dict] = {}
     for chunk, doc in results:
+        public_url = surfsense_docs_public_url(doc.source)
         if doc.id not in grouped:
             grouped[doc.id] = {
                 "document_id": f"doc-{doc.id}",
                 "document_type": "SURFSENSE_DOCS",
                 "title": doc.title,
-                "url": doc.source,
-                "metadata": {"source": doc.source},
+                "url": public_url,
+                "metadata": {"source": doc.source, "public_url": public_url},
                 "chunks": [],
             }
         grouped[doc.id]["chunks"].append(

surfsense_backend/app/routes/surfsense_docs_routes.py

@@ -24,6 +24,7 @@ from app.schemas.surfsense_docs import (
     SurfsenseDocsDocumentWithChunksRead,
 )
 from app.users import current_active_user
+from app.utils.surfsense_docs import surfsense_docs_public_url
 
 router = APIRouter()
 
@@ -76,6 +77,7 @@ async def get_surfsense_doc_by_chunk_id(
             id=document.id,
             title=document.title,
             source=document.source,
+            public_url=surfsense_docs_public_url(document.source),
             content=document.content,
             chunks=[
                 SurfsenseDocsChunkRead(id=c.id, content=c.content)
@@ -146,6 +148,7 @@ async def list_surfsense_docs(
                 id=doc.id,
                 title=doc.title,
                 source=doc.source,
+                public_url=surfsense_docs_public_url(doc.source),
                 content=doc.content,
                 created_at=doc.created_at,
                 updated_at=doc.updated_at,

surfsense_backend/app/schemas/surfsense_docs.py

@@ -22,6 +22,7 @@ class SurfsenseDocsDocumentRead(BaseModel):
     id: int
     title: str
     source: str
+    public_url: str
     content: str
     created_at: datetime | None = None
     updated_at: datetime | None = None
@@ -35,6 +36,7 @@ class SurfsenseDocsDocumentWithChunksRead(BaseModel):
     id: int
     title: str
     source: str
+    public_url: str
     content: str
     chunks: list[SurfsenseDocsChunkRead]
 

surfsense_backend/app/tasks/chat/stream_new_chat.py

@@ -78,6 +78,7 @@ from app.services.new_streaming_service import VercelStreamingService
 from app.tasks.chat.streaming.graph_stream.event_stream import stream_output
 from app.utils.content_utils import bootstrap_history_from_db
 from app.utils.perf import get_perf_logger, log_system_snapshot, trim_native_heap
+from app.utils.surfsense_docs import surfsense_docs_public_url
 from app.utils.user_message_multimodal import build_human_message_content
 
 _background_tasks: set[asyncio.Task] = set()
@@ -239,14 +240,17 @@ def format_mentioned_surfsense_docs_as_context(
     )
 
     for doc in documents:
-        metadata_json = json.dumps({"source": doc.source}, ensure_ascii=False)
+        public_url = surfsense_docs_public_url(doc.source)
+        metadata_json = json.dumps(
+            {"source": doc.source, "public_url": public_url}, ensure_ascii=False
+        )
 
         context_parts.append("<document>")
         context_parts.append("<document_metadata>")
         context_parts.append(f"  <document_id>doc-{doc.id}</document_id>")
         context_parts.append("  <document_type>SURFSENSE_DOCS</document_type>")
         context_parts.append(f"  <title><![CDATA[{doc.title}]]></title>")
-        context_parts.append(f"  <url><![CDATA[{doc.source}]]></url>")
+        context_parts.append(f"  <url><![CDATA[{public_url}]]></url>")
         context_parts.append(
             f"  <metadata_json><![CDATA[{metadata_json}]]></metadata_json>"
         )

surfsense_backend/app/utils/surfsense_docs.py

@@ -0,0 +1,13 @@
+"""Utilities for SurfSense's built-in documentation index."""
+
+from pathlib import PurePosixPath
+
+DOCS_PUBLIC_ROOT = PurePosixPath("/docs")
+
+
+def surfsense_docs_public_url(source: str) -> str:
+    """Return the public docs route for an indexed documentation source path."""
+    docs_path = PurePosixPath(source).with_suffix("")
+    if docs_path.name == "index":
+        docs_path = docs_path.parent
+    return (DOCS_PUBLIC_ROOT / docs_path).as_posix()