From 5e84a92de260c7e07a68b092c1cd5c62984770e7 Mon Sep 17 00:00:00 2001
From: octo-patch <octo-patch@github.com>
Date: Mon, 20 Apr 2026 11:29:27 +0800
Subject: [PATCH] fix: propagate search_settings filters through agent tools
 and system context builder

Fixes #2244 and #2245.

Two related bugs caused search filter scoping (e.g. collection_ids) to be
silently ignored, allowing agents to access documents outside the intended
collection boundary:

1. _build_documents_context did not accept or forward filter_collection_ids
   to get_documents_overview, so the dynamic RAG system prompt listed all
   documents regardless of collection filters (#2245).

2. GetFileContentTool constructed a bare {"id": ...} filter, completely
   discarding any search_settings.filters (collection_ids etc.) set by the
   caller. A document_id returned by the LLM could therefore resolve to
   content from a different collection (#2244).

Changes:
- _build_documents_context now accepts filter_collection_ids and passes it
  to get_documents_overview.
- _build_aware_system_instruction forwards filter_collection_ids when
  calling _build_documents_context.
- GetFileContentTool.execute merges context.search_settings.filters into an
  $and compound filter alongside the document_id predicate.
---
 .../base/agent/tools/built_in/get_file_content.py  | 14 +++++++++++++-
 py/core/main/services/retrieval_service.py         |  3 +++
 2 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/py/core/base/agent/tools/built_in/get_file_content.py b/py/core/base/agent/tools/built_in/get_file_content.py
index ce4e08181..e624dd41d 100644
--- a/py/core/base/agent/tools/built_in/get_file_content.py
+++ b/py/core/base/agent/tools/built_in/get_file_content.py
@@ -61,11 +61,23 @@ async def execute(
 
         try:
             doc_uuid = UUID(document_id)
-            filters = {"id": {"$eq": doc_uuid}}
+            doc_id_filter = {"id": {"$eq": doc_uuid}}
         except ValueError:
             logger.error(f"Invalid document_id format received: {document_id}")
             return AggregateSearchResult(document_search_results=[])
 
+        # Merge search_settings filters (e.g., collection_ids) with the
+        # document_id filter so that collection-scoped queries are respected.
+        search_filters = (
+            getattr(context.search_settings, "filters", None)
+            if hasattr(context, "search_settings")
+            else None
+        )
+        if search_filters:
+            filters: dict[str, Any] = {"$and": [doc_id_filter, search_filters]}
+        else:
+            filters = doc_id_filter
+
         options = options or {}
 
         try:
diff --git a/py/core/main/services/retrieval_service.py b/py/core/main/services/retrieval_service.py
index 29332cfde..1c8b667bd 100644
--- a/py/core/main/services/retrieval_service.py
+++ b/py/core/main/services/retrieval_service.py
@@ -1821,6 +1821,7 @@ def _parse_user_and_collection_filters(
     async def _build_documents_context(
         self,
         filter_user_id: Optional[UUID] = None,
+        filter_collection_ids: Optional[list[UUID]] = None,
         max_summary_length: int = 128,
         limit: int = 25,
         reverse_order: bool = True,
@@ -1834,6 +1835,7 @@ async def _build_documents_context(
             offset=0,
             limit=limit,
             filter_user_ids=[filter_user_id] if filter_user_id else None,
+            filter_collection_ids=filter_collection_ids if filter_collection_ids else None,
             include_summary_embedding=False,
             sort_order="DESC" if reverse_order else "ASC",
         )
@@ -1910,6 +1912,7 @@ async def _build_aware_system_instruction(
         if use_system_context:
             doc_context_str = await self._build_documents_context(
                 filter_user_id=filter_user_id,
+                filter_collection_ids=filter_collection_ids,
             )
             logger.debug(f"Loading prompt {prompt_name}")
             # Now fetch the prompt from the database prompts handler