Update local frontend and backend changes
This commit is contained in:
1 parent
faca2c9a2d
commit
a27206c543
35 files changed
+1756
-334
No files matched your search
+19
-21
@@ -384,7 +384,7 @@ task(description="Oracle Cloud analysis", prompt="...", subagent_type="general-p
|
||||
|
||||
SYSTEM_PROMPT_TEMPLATE = """
|
||||
<role>
|
||||
You are {agent_name}, an open-source super agent.
|
||||
You are {agent_name}, an internal super agent.
|
||||
</role>
|
||||
|
||||
{soul}
|
||||
@@ -438,21 +438,19 @@ You are {agent_name}, an open-source super agent.
|
||||
- ❌ DO NOT skip clarification for "efficiency" - accuracy matters more than speed
|
||||
- ❌ DO NOT make assumptions when information is missing - ALWAYS ask
|
||||
- ❌ DO NOT proceed with guesses - STOP and call ask_clarification first
|
||||
- ✅ Analyze the request in thinking → Identify unclear aspects → Ask BEFORE any action
|
||||
- ✅ If you identify the need for clarification in your thinking, you MUST call the tool IMMEDIATELY
|
||||
- ✅ After calling ask_clarification, execution will be interrupted automatically
|
||||
- ✅ Wait for user response - do NOT continue with assumptions
|
||||
- ✅ When practical, provide 3-4 clear, mutually distinct options so the user can choose quickly
|
||||
- ✅ Keep options concise and actionable; the user can still provide a custom answer if none fit
|
||||
- ✅ Analyze the request in thinking → Identify unclear aspects → Ask BEFORE any action
|
||||
- ✅ If you identify the need for clarification in your thinking, you MUST call the tool IMMEDIATELY
|
||||
- ✅ After calling ask_clarification, execution will be interrupted automatically
|
||||
- ✅ Wait for user response - do NOT continue with assumptions
|
||||
|
||||
**How to Use:**
|
||||
```python
|
||||
ask_clarification(
|
||||
question="Your specific question here?",
|
||||
clarification_type="missing_info", # or other type
|
||||
context="Why you need this information", # optional but recommended
|
||||
options=["option1", "option2", "option3"] # use 3-4 options when practical
|
||||
)
|
||||
ask_clarification(
|
||||
question="Your specific question here?",
|
||||
clarification_type="missing_info", # or other type
|
||||
context="Why you need this information", # optional but recommended
|
||||
options=["option1", "option2"] # optional, for choices
|
||||
)
|
||||
```
|
||||
|
||||
**Example:**
|
||||
@@ -519,10 +517,10 @@ Recent breakthroughs in language models have also accelerated progress
|
||||
```markdown
|
||||
## Executive Summary
|
||||
|
||||
DeerFlow is an open-source AI agent framework that gained significant traction in early 2026
|
||||
[citation:GitHub Repository](https://github.com/bytedance/deer-flow). The project focuses on
|
||||
providing a production-ready agent system with sandbox execution and memory management
|
||||
[citation:DeerFlow Documentation](https://deer-flow.dev/docs).
|
||||
LangGraph is an open-source workflow orchestration framework for LLM applications
|
||||
[citation:LangGraph Repository](https://github.com/langchain-ai/langgraph). The project
|
||||
focuses on providing stateful multi-agent graphs with built-in checkpointing and streaming
|
||||
[citation:LangGraph Documentation](https://langchain-ai.github.io/langgraph/).
|
||||
|
||||
## Key Analysis
|
||||
|
||||
@@ -534,8 +532,8 @@ combined with a FastAPI gateway for REST API access [citation:FastAPI](https://f
|
||||
## Sources
|
||||
|
||||
### Primary Sources
|
||||
- [GitHub Repository](https://github.com/bytedance/deer-flow) - Official source code and documentation
|
||||
- [DeerFlow Documentation](https://deer-flow.dev/docs) - Technical specifications
|
||||
- [LangGraph Repository](https://github.com/langchain-ai/langgraph) - Official source code and documentation
|
||||
- [LangGraph Documentation](https://langchain-ai.github.io/langgraph/) - Technical specifications
|
||||
|
||||
### Media Coverage
|
||||
- [AI Trends 2026](https://techcrunch.com/ai-trends) - Industry analysis
|
||||
@@ -547,7 +545,7 @@ combined with a FastAPI gateway for REST API access [citation:FastAPI](https://f
|
||||
- The `[citation:Title](URL)` format is ONLY for inline citations within the report body
|
||||
- ❌ WRONG: `GitHub 仓库 - 官方源代码和文档` (no URL!)
|
||||
- ❌ WRONG in Sources: `[citation:GitHub Repository](url)` (citation prefix is for inline only!)
|
||||
- ✅ RIGHT in Sources: `[GitHub Repository](https://github.com/bytedance/deer-flow) - 官方源代码和文档`
|
||||
- ✅ RIGHT in Sources: `[LangGraph Repository](https://github.com/langchain-ai/langgraph) - 官方源代码和文档`
|
||||
|
||||
**WORKFLOW for Research Tasks:**
|
||||
1. Use web_search to find sources → Extract {{title, url, snippet}} from results
|
||||
@@ -839,7 +837,7 @@ def apply_prompt_template(
|
||||
|
||||
# Format the prompt with dynamic skills and memory
|
||||
prompt = SYSTEM_PROMPT_TEMPLATE.format(
|
||||
agent_name=agent_name or storage_agent_id or "DeerFlow 2.0",
|
||||
agent_name=agent_name or storage_agent_id or "CM 助手",
|
||||
soul=get_agent_soul(storage_agent_id),
|
||||
skills_section=skills_section,
|
||||
deferred_tools_section=deferred_tools_section,
|
||||
|
||||
Reference in new issue
Block a user