change the syntax of exec

docs/async.md

@@ -19,9 +19,11 @@ Below is a minimal **AsyncNode** that calls an LLM in `exec()` to summarize text
 
 ```python
 class SummarizeThenVerify(AsyncNode):
-    def exec(self, shared, prep_res):
-        doc = shared.get("doc", "")
-        return call_llm(f"Summarize: {doc}")
+    def prep(self, shared):
+        return shared.get("doc", "")
+
+    def exec(self, prep_res):
+        return call_llm(f"Summarize: {prep_res}")
 
     async def post_async(self, shared, prep_res, exec_res):
         user_decision = await gather_user_feedback(exec_res)

docs/communication.md

@@ -9,7 +9,7 @@ nav_order: 3
 
 Nodes and Flows **communicate** in two ways:
 
-1. **Shared Store** – A global data structure (often an in-mem dict) that all nodes can read from and write to. Every Node’s `prep()`, `exec()`, and `post()` methods receive the **same** `shared` store.  
+1. **Shared Store** – A global data structure (often an in-mem dict) that all nodes can read from and write to. Every Node’s `prep()` and `post()` methods receive the **same** `shared` store.  
 2. **Params** – Each node and Flow has a `params` dict assigned by the **parent Flow**. Params mostly serve as identifiers, letting each node/flow know what task it’s assigned.
 
 If you know memory management, **Shared Store** is like a **heap** shared across function calls, while **Params** is like a **stack** assigned by parent function calls.
@@ -47,7 +47,7 @@ class Summarize(Node):
         content = shared["data"].get("my_file.txt", "")
         return content
 
-    def exec(self, shared, prep_res):
+    def exec(self, prep_res):
         prompt = f"Summarize: {prep_res}"
         summary = call_llm(prompt)
         return summary
@@ -91,7 +91,7 @@ class SummarizeFile(Node):
         filename = self.params["filename"]
         return shared["data"].get(filename, "")
 
-    def exec(self, shared, prep_res):
+    def exec(self, prep_res):
         prompt = f"Summarize: {prep_res}"
         return call_llm(prompt)
 

docs/node.md

@@ -14,9 +14,10 @@ A **Node** is the smallest building block of Mini LLM Flow. Each Node has three
    - Often used for tasks like reading files, chunking text, or validation.
    - Returns `prep_res`, which will be passed to both `exec()` and `post()`.
 
-2. **`exec(shared, prep_res)`**  
+2. **`exec(prep_res)`**  
    - The main execution step where the LLM is called.
-   - Has a built-in retry feature to handle errors and ensure reliable results.
+   - Optionally has built-in retry and error handling (below).
+   - ⚠️ If retry enabled, ensure implementation is idempotent.
    - Returns `exec_res`, which is passed to `post()`.
 
 3. **`post(shared, prep_res, exec_res)`**  
@@ -55,7 +56,7 @@ class SummarizeFile(Node):
         filename = self.params["filename"]
         return shared["data"][filename]
 
-    def exec(self, shared, prep_res):
+    def exec(self, prep_res):
         if not prep_res:
             raise ValueError("Empty file content!")
         prompt = f"Summarize this text in 10 words: {prep_res}"