langchain-dev-utils 1.2.2__tar.gz → 1.2.3__tar.gz

{langchain_dev_utils-1.2.2 → langchain_dev_utils-1.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: langchain-dev-utils
-Version: 1.2.2
+Version: 1.2.3
 Summary: A practical utility library for LangChain and LangGraph development
 Project-URL: Source Code, https://github.com/TBice123123/langchain-dev-utils
 Project-URL: repository, https://github.com/TBice123123/langchain-dev-utils
@@ -171,7 +171,7 @@ text = format_sequence([
 ], separator="\n", with_num=True)
 ```
 
-**For more information about message conversion, please refer to**: [Message Processing](https://tbice123123.github.io/langchain-dev-utils-docs/en/message-conversion/message.html), [Format List Content](https://tbice123123.github.io/langchain-dev-utils-docs/en/message-conversion/format.html)
+**For more information about message conversion, please refer to**: [Message Process](https://tbice123123.github.io/langchain-dev-utils-docs/en/message-conversion/message.html), [Formatting List Content](https://tbice123123.github.io/langchain-dev-utils-docs/en/message-conversion/format.html)
 
 ### 3. **Tool Calling**
 
@@ -231,7 +231,7 @@ def get_current_time() -> str:
     return str(datetime.datetime.now().timestamp())
 ```
 
-**For more information about tool calling, please refer to**: [Add Human-in-the-Loop Support](https://tbice123123.github.io/langchain-dev-utils-docs/en/tool-calling/human-in-the-loop.html), [Tool Call Processing](https://tbice123123.github.io/langchain-dev-utils-docs/en/tool-calling/tool.html)
+**For more information about tool calling, please refer to**: [Add Human-in-the-Loop Support](https://tbice123123.github.io/langchain-dev-utils-docs/en/tool-calling/human-in-the-loop.html), [Tool Call Handling](https://tbice123123.github.io/langchain-dev-utils-docs/en/tool-calling/tool.html)
 
 ### 4. **Agent Development**
 
@@ -278,7 +278,7 @@ response = agent.invoke({"messages": [{"role": "user", "content": "Give me a tra
 print(response)
 ```
 
-**For more information about agent development and all built-in middleware, please refer to**: [Prebuilt Agent Functions](https://tbice123123.github.io/langchain-dev-utils-docs/en/agent-development/prebuilt.html), [Middleware](https://tbice123123.github.io/langchain-dev-utils-docs/en/agent-development/middleware.html)
+**For more information about agent development and all built-in middleware, please refer to**: [Pre-built Agent Functions](https://tbice123123.github.io/langchain-dev-utils-docs/en/agent-development/prebuilt.html), [Middleware](https://tbice123123.github.io/langchain-dev-utils-docs/en/agent-development/middleware.html)
 
 ### 5. **State Graph Orchestration**
 
@@ -391,7 +391,7 @@ response = graph.invoke({"messages": [HumanMessage("Hello")]})
 print(response)
 ```
 
-**For more information about state graph orchestration, please refer to**: [State Graph Orchestration Pipeline](https://tbice123123.github.io/langchain-dev-utils-docs/en/graph-orchestration/pipeline.html)
+**For more information about state graph orchestration, please refer to**: [State Graph Orchestration](https://tbice123123.github.io/langchain-dev-utils-docs/en/graph-orchestration/pipeline.html)
 
 ## 💬 Join the Community
 

{langchain_dev_utils-1.2.2 → langchain_dev_utils-1.2.3}/README.md

@@ -155,7 +155,7 @@ text = format_sequence([
 ], separator="\n", with_num=True)
 ```
 
-**For more information about message conversion, please refer to**: [Message Processing](https://tbice123123.github.io/langchain-dev-utils-docs/en/message-conversion/message.html), [Format List Content](https://tbice123123.github.io/langchain-dev-utils-docs/en/message-conversion/format.html)
+**For more information about message conversion, please refer to**: [Message Process](https://tbice123123.github.io/langchain-dev-utils-docs/en/message-conversion/message.html), [Formatting List Content](https://tbice123123.github.io/langchain-dev-utils-docs/en/message-conversion/format.html)
 
 ### 3. **Tool Calling**
 
@@ -215,7 +215,7 @@ def get_current_time() -> str:
     return str(datetime.datetime.now().timestamp())
 ```
 
-**For more information about tool calling, please refer to**: [Add Human-in-the-Loop Support](https://tbice123123.github.io/langchain-dev-utils-docs/en/tool-calling/human-in-the-loop.html), [Tool Call Processing](https://tbice123123.github.io/langchain-dev-utils-docs/en/tool-calling/tool.html)
+**For more information about tool calling, please refer to**: [Add Human-in-the-Loop Support](https://tbice123123.github.io/langchain-dev-utils-docs/en/tool-calling/human-in-the-loop.html), [Tool Call Handling](https://tbice123123.github.io/langchain-dev-utils-docs/en/tool-calling/tool.html)
 
 ### 4. **Agent Development**
 
@@ -262,7 +262,7 @@ response = agent.invoke({"messages": [{"role": "user", "content": "Give me a tra
 print(response)
 ```
 
-**For more information about agent development and all built-in middleware, please refer to**: [Prebuilt Agent Functions](https://tbice123123.github.io/langchain-dev-utils-docs/en/agent-development/prebuilt.html), [Middleware](https://tbice123123.github.io/langchain-dev-utils-docs/en/agent-development/middleware.html)
+**For more information about agent development and all built-in middleware, please refer to**: [Pre-built Agent Functions](https://tbice123123.github.io/langchain-dev-utils-docs/en/agent-development/prebuilt.html), [Middleware](https://tbice123123.github.io/langchain-dev-utils-docs/en/agent-development/middleware.html)
 
 ### 5. **State Graph Orchestration**
 
@@ -375,7 +375,7 @@ response = graph.invoke({"messages": [HumanMessage("Hello")]})
 print(response)
 ```
 
-**For more information about state graph orchestration, please refer to**: [State Graph Orchestration Pipeline](https://tbice123123.github.io/langchain-dev-utils-docs/en/graph-orchestration/pipeline.html)
+**For more information about state graph orchestration, please refer to**: [State Graph Orchestration](https://tbice123123.github.io/langchain-dev-utils-docs/en/graph-orchestration/pipeline.html)
 
 ## 💬 Join the Community
 

{langchain_dev_utils-1.2.2 → langchain_dev_utils-1.2.3}/README_cn.md

@@ -375,7 +375,7 @@ response = graph.invoke({"messages": [HumanMessage("你好")]})
 print(response)
 ```
 
-**对于更多关于状态图编排的相关介绍，请参考**: [状态图编排管道](https://tbice123123.github.io/langchain-dev-utils-docs/zh/graph-orchestration/pipeline.html)
+**对于更多关于状态图编排的相关介绍，请参考**: [状态图编排](https://tbice123123.github.io/langchain-dev-utils-docs/zh/graph-orchestration/pipeline.html)
 
 ## 💬 加入社区
 

{langchain_dev_utils-1.2.2 → langchain_dev_utils-1.2.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "langchain-dev-utils"
-version = "1.2.2"
+version = "1.2.3"
 description = "A practical utility library for LangChain and LangGraph development"
 readme = "README.md"
 authors = [{ name = "tiebingice", email = "tiebingice123@outlook.com" }]

langchain_dev_utils-1.2.3/src/langchain_dev_utils/__init__.py

@@ -0,0 +1 @@
+__version__ = "1.2.3"

{langchain_dev_utils-1.2.2 → langchain_dev_utils-1.2.3}/src/langchain_dev_utils/agents/middleware/model_fallback.py

@@ -17,7 +17,7 @@ class ModelFallbackMiddleware(_ModelFallbackMiddleware):
 
     Example:
         ```python
-        from langchain_dev_utils.agents.middleware.model_fallback import ModelFallbackMiddleware
+        from langchain_dev_utils.agents.middleware import ModelFallbackMiddleware
         from langchain_dev_utils.agents import create_agent
 
         fallback = ModelFallbackMiddleware(

{langchain_dev_utils-1.2.2 → langchain_dev_utils-1.2.3}/src/langchain_dev_utils/agents/middleware/plan.py

@@ -250,6 +250,8 @@ _PLAN_SYSTEM_PROMPT_NOT_READ_PLAN = """You can manage task plans using two simpl
 ## finish_sub_plan
 - Call it **only when the current task is 100% done**. It automatically marks it `"done"` and promotes the next `"pending"` task to `"in_progress"`. No parameters needed. Never use it mid-task or if anything’s incomplete.
 Keep plans lean, update immediately, and never batch completions.
+
+**Note**: Make sure that all tasks end up with the status `"done"`.
 """
 
 _PLAN_SYSTEM_PROMPT = """You can manage task plans using three simple tools:
@@ -263,6 +265,8 @@ _PLAN_SYSTEM_PROMPT = """You can manage task plans using three simple tools:
 ## read_plan
 - Retrieve the full current plan list with statuses, especially when you forget which sub-plan you're supposed to execute next.
 - No parameters required—returns a current plan list with statuses.
+
+**Note**: Make sure that all tasks end up with the status `"done"`.
 """
 
 
@@ -290,7 +294,7 @@ class PlanMiddleware(AgentMiddleware):
         message_key: The key of the message to be updated. Defaults to "messages".
     Example:
         ```python
-        from langchain_dev_utils.agents.middleware.plan import PlanMiddleware
+        from langchain_dev_utils.agents.middleware import PlanMiddleware
         from langchain_dev_utils.agents import create_agent
 
         agent = create_agent("vllm:qwen3-4b", middleware=[PlanMiddleware()])

langchain_dev_utils-1.2.2/src/langchain_dev_utils/__init__.py

@@ -1 +0,0 @@
-__version__ = "1.2.2"