fix(bot): Limit grep\glob\search tool's user scope, grep use one pattern, Optimize client initialization.

[yeshion23333]

Description

1. grep、glob、search tool，使用当前admin User 进行ov检索；
2. 优化 Openviking client的初始化逻辑；
3. 去除grep的多pattern 并发检索逻辑，一次只查询一个；
4. 优化 工具提示词

Related Issue

Type of Change

• Bug fix (non-breaking change that fixes an issue)
• New feature (non-breaking change that adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Documentation update
• Refactoring (no functional changes)
• Performance improvement
• Test update

Changes Made

Testing

• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• I have tested this on the following platforms:
  • Linux
  • macOS
  • Windows

Checklist

• My code follows the project's coding style
• I have performed a self-review of my code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• Any dependent changes have been merged and published

Screenshots (if applicable)

Additional Notes

[github-actions]

PR Reviewer Guide 🔍

Here are some key observations to aid the review process:

⏱️ Estimated effort to review: 3 🔵🔵🔵⚪⚪

🏅 Score: 85

🧪 No relevant tests

🔒 No security concerns identified

✅ No TODO sections

🔀 Multiple PR themes Sub-PR theme: Optimize OpenViking client initialization and add user-scoped clients Relevant files: bot/vikingbot/openviking_mount/ov_server.py Sub-PR theme: Limit grep/glob/search tools to admin user scope Relevant files: bot/vikingbot/agent/tools/ov_file.py

⚡ Recommended focus areas for review Missing Memory Type Filtering The openviking_search tool no longer filters results to only include "memory" type items when using tool_context.memory_user_ids. This may return non-memory resources in results, changing previous behavior. if not target_uri and tool_context.memory_user_ids: user_uri = client._memory_target_uri(admin_user_id) results = await client.search( query, target_uri=user_uri, limit=20, user_id=admin_user_id, ) if not results: return f"No results found for query: {query}" grouped_items = self._filter_search_items(results, min_score=min_score) total = sum(len(items) for items in grouped_items.values()) if total == 0: return f"No results found for query: {query}" return self._format_search_items_json(grouped_items, min_score=min_score)

[github-actions]

PR Code Suggestions ✨

Explore these optional code suggestions:

Category	Suggestion	Impact
Possible issue	Restore memory search filtering logic Restore the memory-type filtering and extraction of search items that was present in the original code, and add back the user key mode check. This ensures only memory items are included when searching user memories, which matches the original behavior. bot/vikingbot/agent/tools/ov_file.py [253-267] admin_user_id = client.admin_user_id if not target_uri and tool_context.memory_user_ids: - user_uri = client._memory_target_uri(admin_user_id) + if client._is_user_key_mode(): + user_uri = client._memory_target_uri(None) + user_id = None + else: + user_uri = client._memory_target_uri(admin_user_id) + user_id = admin_user_id + + logger.info(f"openviking_search: searching {user_uri} for query: {query}") results = await client.search( query, target_uri=user_uri, limit=20, - user_id=admin_user_id, + user_id=user_id, ) if not results: return f"No results found for query: {query}" - grouped_items = self._filter_search_items(results, min_score=min_score) + extracted_items = self._extract_search_items(results) + memories = [ + item + for item in extracted_items + if item.get("type") == "memory" + ] + grouped_items = self._filter_search_items(memories, min_score=min_score) Suggestion importance[1-10]: 7 __ Why: The suggestion correctly restores original behavior: memory-type filtering via _extract_search_items, user key mode check, and logging, which were removed in the PR. This addresses a potential functional regression in user memory search results.	Medium