feat(flo-ai): add field level validation for agent/arium yaml

TOOLS.md

@@ -65,7 +65,7 @@ Every tool has these properties:
 ### Using Tools in Agents
 
 ```python
-from flo_ai.builder.agent_builder import AgentBuilder
+from flo_ai.agent import AgentBuilder
 from flo_ai.llm import OpenAI
 
 agent = (AgentBuilder()
@@ -95,7 +95,7 @@ Partial tools allow you to pre-fill some parameters during agent building, hidin
 #### Method 1: Using AgentBuilder.add_tool()
 
 ```python
-from flo_ai.builder.agent_builder import AgentBuilder
+from flo_ai.agent import AgentBuilder
 
 # BigQuery tool with multiple parameters
 @flo_tool(description="Query BigQuery database")
@@ -304,7 +304,7 @@ agent:
 ### Using YAML Configuration
 
 ```python
-from flo_ai.builder.agent_builder import AgentBuilder
+from flo_ai.agent import AgentBuilder
 
 # Create tool registry
 tool_registry = {
@@ -331,7 +331,7 @@ agent = AgentBuilder.from_yaml(
 ```python
 import asyncio
 from flo_ai.tool.flo_tool import flo_tool
-from flo_ai.builder.agent_builder import AgentBuilder
+from flo_ai.agent import AgentBuilder
 from flo_ai.llm import OpenAI
 
 # Define tools

documentation/development.mdx

@@ -55,7 +55,7 @@ Test your installation with a simple agent:
 
 ```python
 import asyncio
-from flo_ai.builder.agent_builder import AgentBuilder
+from flo_ai.agent import AgentBuilder
 from flo_ai.llm import OpenAI
 
 async def test_installation():

documentation/essentials/agents.mdx

@@ -1,7 +1,7 @@
 ---
-title: 'Agents'
-description: 'Learn how to create and configure AI agents with Flo AI'
-icon: 'robot'
+title: "Agents"
+description: "Learn how to create and configure AI agents with Flo AI"
+icon: "robot"
 ---
 
 ## Creating Agents
@@ -13,7 +13,7 @@ Agents are the core building blocks of Flo AI. They represent AI-powered entitie
 Create a simple conversational agent:
 
 ```python
-from flo_ai.builder.agent_builder import AgentBuilder
+from flo_ai.agent import AgentBuilder
 from flo_ai.llm import OpenAI
 
 agent = (
@@ -180,7 +180,7 @@ well_prompted_agent = (
     1. Review code for bugs, security issues, and best practices
     2. Suggest improvements and optimizations
     3. Provide constructive feedback
-    
+
     Always be specific about issues and provide actionable suggestions.
     Focus on code quality, performance, and maintainability.
     ''')
@@ -263,10 +263,10 @@ from flo_ai.arium.memory import BaseMemory
 class CustomMemory(BaseMemory):
     def __init__(self):
         self.messages = []
-    
+
     def add(self, message):
         self.messages.append(message)
-    
+
     def get(self):
         return self.messages
 

documentation/essentials/arium.mdx

@@ -1,7 +1,7 @@
 ---
-title: 'Arium Workflows'
-description: 'Create complex multi-agent workflows with Arium orchestration'
-icon: 'sitemap'
+title: "Arium Workflows"
+description: "Create complex multi-agent workflows with Arium orchestration"
+icon: "sitemap"
 ---
 
 ## What is Arium?
@@ -16,25 +16,25 @@ Create a linear workflow with multiple agents:
 
 ```python
 from flo_ai.arium import AriumBuilder
-from flo_ai.models.agent import Agent
+from flo_ai.agent import Agent
 from flo_ai.llm import OpenAI
 
 async def simple_chain():
     llm = OpenAI(model='gpt-4o-mini')
-    
+
     # Create agents
     analyst = Agent(
         name='content_analyst',
         system_prompt='Analyze the input and extract key insights.',
         llm=llm
     )
-    
+
     summarizer = Agent(
-        name='summarizer', 
+        name='summarizer',
         system_prompt='Create a concise summary based on the analysis.',
         llm=llm
     )
-    
+
     # Build and run workflow
     result = await (
         AriumBuilder()
@@ -44,7 +44,7 @@ async def simple_chain():
         .end_with(summarizer)
         .build_and_run(["Analyze this complex business report..."])
     )
-    
+
     return result
 ```
 
@@ -59,7 +59,7 @@ def route_by_type(memory: BaseMemory) -> str:
     """Route based on classification result"""
     messages = memory.get()
     last_message = str(messages[-1]) if messages else ""
-    
+
     if "technical" in last_message.lower():
         return "tech_specialist"
     else:
@@ -96,7 +96,7 @@ arium:
       model:
         provider: "openai"
         name: "gpt-4o-mini"
-    
+
     - name: "summarizer"
       role: "Content Summarizer"
       job: "Create a concise summary based on the analysis."
@@ -130,7 +130,7 @@ Use LLMs for intelligent routing decisions:
 ```yaml
 routers:
   - name: "content_type_router"
-    type: "smart"  # Uses LLM for intelligent routing
+    type: "smart" # Uses LLM for intelligent routing
     routing_options:
       technical_writer: "Technical content, documentation, tutorials"
       creative_writer: "Creative writing, storytelling, fiction"
@@ -148,7 +148,7 @@ For A→B→A→C feedback patterns:
 routers:
   - name: "reflection_router"
     type: "reflection"
-    flow_pattern: [writer, critic, writer]  # A → B → A pattern
+    flow_pattern: [writer, critic, writer] # A → B → A pattern
     model:
       provider: "openai"
       name: "gpt-4o-mini"
@@ -248,10 +248,10 @@ from flo_ai.arium.memory import BaseMemory
 class CustomMemory(BaseMemory):
     def __init__(self):
         self.data = {}
-    
+
     def add(self, key, value):
         self.data[key] = value
-    
+
     def get(self, key):
         return self.data.get(key)
 

documentation/essentials/code.mdx

@@ -1,7 +1,7 @@
 ---
-title: 'Code Examples'
-description: 'Flo AI code examples and syntax highlighting'
-icon: 'code'
+title: "Code Examples"
+description: "Flo AI code examples and syntax highlighting"
+icon: "code"
 ---
 
 ## Basic Agent Creation
@@ -10,7 +10,7 @@ Here's how to create a simple conversational agent with Flo AI:
 
 ```python Simple Agent
 import asyncio
-from flo_ai.builder.agent_builder import AgentBuilder
+from flo_ai.agent import AgentBuilder
 from flo_ai.llm import OpenAI
 
 async def main():
@@ -34,7 +34,7 @@ Create agents that can use custom tools:
 
 ```python Tool-Using Agent
 import asyncio
-from flo_ai.builder.agent_builder import AgentBuilder
+from flo_ai.agent import AgentBuilder
 from flo_ai.tool import flo_tool
 from flo_ai.llm import Anthropic
 
@@ -72,7 +72,7 @@ Use Pydantic models for structured agent responses:
 ```python Structured Output
 import asyncio
 from pydantic import BaseModel, Field
-from flo_ai.builder.agent_builder import AgentBuilder
+from flo_ai.agent import AgentBuilder
 from flo_ai.llm import OpenAI
 
 class MathSolution(BaseModel):
@@ -102,25 +102,25 @@ Create complex workflows with multiple agents:
 ```python Multi-Agent Workflow
 import asyncio
 from flo_ai.arium import AriumBuilder
-from flo_ai.models.agent import Agent
+from flo_ai.agent import Agent
 from flo_ai.llm import OpenAI
 
 async def content_analysis_workflow():
     llm = OpenAI(model='gpt-4o-mini')
-    
+
     # Create specialized agents
     analyst = Agent(
         name='content_analyst',
         system_prompt='Analyze the input and extract key insights.',
         llm=llm
     )
-    
+
     summarizer = Agent(
-        name='summarizer', 
+        name='summarizer',
         system_prompt='Create a concise summary based on the analysis.',
         llm=llm
     )
-    
+
     # Build and run workflow
     result = await (
         AriumBuilder()
@@ -130,7 +130,7 @@ async def content_analysis_workflow():
         .end_with(summarizer)
         .build_and_run(["Analyze this complex business report..."])
     )
-    
+
     return result
 
 asyncio.run(content_analysis_workflow())
@@ -154,7 +154,7 @@ arium:
       model:
         provider: "openai"
         name: "gpt-4o-mini"
-    
+
     - name: "summarizer"
       role: "Content Summarizer"
       job: "Create a concise summary based on the analysis."