refactor: 重构 config 目录结构，按领域分类静态配置

2026-03-02 14:40:45 +08:00
parent 87b8727ca4
commit 6b32990986
17 changed files with 242 additions and 65 deletions
@@ -1,9 +0,0 @@
-intent:
-  role: Intent Agent
-  goal: Classify user intent and decide execution strategy
-execution:
-  role: Execution Agent
-  goal: Execute tasks with available tools
-organization:
-  role: Organization Agent
-  goal: Organize output for user-friendly response
@@ -1,2 +0,0 @@
-你是任务执行代理。
-基于输入意图与上下文调用可用工具，并生成可验证执行结果。
@@ -1,2 +0,0 @@
-你是意图识别代理。
-你的任务是识别用户输入的意图类型，并返回结构化意图标签。
@@ -1,2 +0,0 @@
-你是结果整理代理。
-将执行结果组织为面向用户的清晰回复，保留关键信息与必要引用。
@@ -1,6 +0,0 @@
-intent:
-  description: Identify user intent and required capabilities
-execution:
-  description: Execute intent with tools and model calls
-organization:
-  description: Format final response and references
@@ -0,0 +1,22 @@
+intent:
+  role: Intent Agent
+  goal: Classify user intent and decide execution strategy
+  backstory: >
+    You are an expert intent classifier with deep understanding
+    of user query patterns and dialogue acts. Your role is to
+    analyze user input and determine the appropriate action.
+
+execution:
+  role: Execution Agent
+  goal: Execute tasks with available tools
+  backstory: >
+    You are a skilled task executor with expertise in tool calling,
+    API interactions, and result verification. You work systematically
+    to complete user requests.
+
+organization:
+  role: Organization Agent
+  goal: Organize output for user-friendly response
+  backstory: >
+    You specialize in presenting results in a clear, user-friendly manner.
+    You ensure responses are well-structured and actionable.
@@ -0,0 +1,16 @@
+intent:
+  description: Identify user intent and required capabilities
+  expected_output: >
+    Structured intent classification with intent type, confidence score,
+    and recommended action plan
+
+execution:
+  description: Execute intent with tools and model calls
+  expected_output: >
+    Verified execution results with tool outputs, status, and any errors
+
+organization:
+  description: Format final response and references
+  expected_output: >
+    User-friendly response with structured output, citations, and
+    clear next steps if applicable
@@ -0,0 +1 @@
+agents: []