From bbd0866374332c01889b5c597674b9a3efc50364 Mon Sep 17 00:00:00 2001
From: SHIYAO ZHANG <834247613@qq.com>
Date: Sat, 4 Apr 2026 11:08:31 +0800
Subject: [PATCH] feat(uploads): guide agent using agentic search for uploaded
 documents (#1816)

* feat(uploads): guide agent to use grep/glob/read_file for uploaded documents

Add workflow guidance to the <uploaded_files> context block so the agent
knows to use grep and glob (added in #1784) alongside read_file when
working with uploaded documents, rather than falling back to web search.

This is the final piece of the three-PR PDF agentic search pipeline:
- PR1 (#1727): pymupdf4llm converter produces structured Markdown with headings
- PR2 (#1738): document outline injected into agent context with line numbers
- PR3 (this):  agent guided to use outline + grep + read_file workflow

* feat(uploads): add file-first priority and fallback guidance to uploaded_files context
---
 .../deerflow/agents/middlewares/uploads_middleware.py     | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/backend/packages/harness/deerflow/agents/middlewares/uploads_middleware.py b/backend/packages/harness/deerflow/agents/middlewares/uploads_middleware.py
index f1700e77e..a0c48969c 100644
--- a/backend/packages/harness/deerflow/agents/middlewares/uploads_middleware.py
+++ b/backend/packages/harness/deerflow/agents/middlewares/uploads_middleware.py
@@ -102,7 +102,13 @@ class UploadsMiddleware(AgentMiddleware[UploadsMiddlewareState]):
             for file in historical_files:
                 self._format_file_entry(file, lines)
 
-        lines.append("You can read these files using the `read_file` tool with the paths shown above.")
+        lines.append("To work with these files:")
+        lines.append("- Read from the file first — use the outline line numbers and `read_file` to locate relevant sections.")
+        lines.append("- Use `grep` to search for keywords when you are not sure which section to look at")
+        lines.append("  (e.g. `grep(pattern='revenue', path='/mnt/user-data/uploads/')`).")
+        lines.append("- Use `glob` to find files by name pattern")
+        lines.append("  (e.g. `glob(pattern='**/*.md', path='/mnt/user-data/uploads/')`).")
+        lines.append("- Only fall back to web search if the file content is clearly insufficient to answer the question.")
         lines.append("</uploaded_files>")
 
         return "\n".join(lines)