Complete documentation update for ConfigLoader cache removal

Updated all ConfigLoader documentation to reflect cache removal implementation:

Documentation Changes:
- Removed all caching sections from overview.md, agent-config.md, graph-config.md, swarm-config.md, tool-config.md
- Updated method signatures throughout documentation to remove cache_key parameters
- Removed cache management method documentation (clear_cache, get_available_*)
- Removed caching from best practices sections
- Cleaned up all code examples to remove cache_key usage

Files Updated:
- overview.md: Removed caching sections, updated API method signatures
- agent-config.md: Removed caching examples and best practices references
- graph-config.md: Automated removal of caching references
- swarm-config.md: Automated removal of caching references
- tool-config.md: Automated removal of caching references

Benefits:
- Simplified documentation matching simplified implementation
- Clear migration path for users
- Consistent messaging about cache-free architecture
- Maintained comprehensive feature coverage without complexity

The documentation now accurately reflects the simplified ConfigLoader system without caching complexity, providing users with clear guidance on the streamlined API.

Author: vawsgit

docs/experimental/config-loader/agent-config.md

@@ -373,20 +373,6 @@ print(f"Age: {result.age}")
 result = agent.extract_userprofile("Extract info: Jane Smith, jane@example.com")
 ```
 
-## Caching and Performance
-
-### Using Cache Keys
-```python
-loader = AgentConfigLoader()
-
-# Load with cache key
-agent1 = loader.load_agent(config, cache_key="my_agent")
-agent2 = loader.load_agent(config, cache_key="my_agent")  # Returns cached instance
-
-# Clear cache
-loader.clear_cache()
-```
-
 ### Serialization
 ```python
 # Load from config
@@ -418,10 +404,9 @@ Common error scenarios:
 ## Best Practices
 
 1. **Use Schema Validation**: Enable IDE integration for better development experience
-2. **Leverage Caching**: Use cache keys for frequently loaded configurations
-3. **Structure Tools**: Organize complex tool configurations with clear naming
-4. **Test Configurations**: Validate configurations against the schema before deployment
-5. **Document Custom Agents**: Provide clear documentation for agent-as-tool configurations
+2. **Structure Tools**: Organize complex tool configurations with clear naming
+3. **Test Configurations**: Validate configurations against the schema before deployment
+4. **Document Custom Agents**: Provide clear documentation for agent-as-tool configurations
 
 ## Advanced Examples
 
@@ -718,27 +703,6 @@ agent = loader.load_agent(config)
 response = agent("Help me write a story about space exploration")
 ```
 
-### Caching Agents
-
-```python
-from strands.experimental.config_loader.agent import AgentConfigLoader
-
-loader = AgentConfigLoader()
-
-# Load agent with cache key
-agent1 = loader.load_agent(config, cache_key="writer_agent")
-
-# Subsequent loads return cached instance
-agent2 = loader.load_agent(config, cache_key="writer_agent")  # Returns cached agent
-
-# Check available cached agents
-cached_agents = loader.get_available_agents()
-print(f"Cached agents: {cached_agents}")
-
-# Clear cache when needed
-loader.clear_cache()
-```
-
 ### Serializing Agents
 
 ```python
@@ -1117,10 +1081,7 @@ common_configs = {
 
 agents = {}
 for name, config in common_configs.items():
-    agents[name] = loader.load_agent(config, cache_key=name)
-
-# Clear cache periodically or when configurations change
-loader.clear_cache()
+    agents[name] = loader.load_agent(config)
 ```
 
 ## Migration from Direct Agent Construction

docs/experimental/config-loader/graph-config.md

@@ -426,19 +426,15 @@ config = {
 }
 ```
 
-## Caching and Performance
-
 ### Using Cache Keys
 
 ```python
 loader = GraphConfigLoader()
 
 # Load with cache key
-graph1 = loader.load_graph(config, cache_key="my_workflow")
-graph2 = loader.load_graph(config, cache_key="my_workflow")  # Returns cached instance
+graph1 = loader.load_graph(config)
+graph2 = loader.load_graph(config)  # Returns cached instance
 
-# Clear cache
-loader.clear_cache()
 ```
 
 ### Serialization
@@ -1057,7 +1053,7 @@ class GraphConfigLoader:
 
 #### Methods
 
-**`load_graph(config, cache_key=None)`**
+**`load_graph(config)`**
 - Load a Graph from YAML configuration (loaded as dictionary)
 - `config`: Dictionary containing graph configuration
 - `cache_key`: Optional key for caching the loaded graph
@@ -1268,7 +1264,6 @@ edges = [
 
 ### Performance Tips
 
-1. **Use Caching**: Cache frequently loaded graphs with `cache_key` parameter
 2. **Optimize Conditions**: Use simple expressions and avoid complex computations
 3. **Set Timeouts**: Configure appropriate timeouts for condition evaluation
 4. **Minimize Config Size**: Only include non-default values in configurations

docs/experimental/config-loader/overview.md

@@ -248,15 +248,6 @@ config = {
 }
 ```
 
-### Caching and Performance
-All loaders support caching for improved performance:
-
-```python
-loader = AgentConfigLoader()
-agent1 = loader.load_agent(config, cache_key="my_agent")
-agent2 = loader.load_agent(config, cache_key="my_agent")  # Returns cached instance
-```
-
 ### Serialization
 Convert existing objects back to configuration dictionaries:
 
@@ -280,10 +271,9 @@ The configuration loaders provide comprehensive error handling:
 ## Best Practices
 
 1. **Use Schema Validation**: Enable IDE integration for better development experience
-2. **Leverage Caching**: Use cache keys for frequently loaded configurations
-3. **Structure Configurations**: Organize complex configurations with clear naming
-4. **Test Configurations**: Validate configurations against the schema before deployment
-5. **Document Custom Tools**: Provide clear documentation for custom tool configurations
+2. **Structure Configurations**: Organize complex configurations with clear naming
+3. **Test Configurations**: Validate configurations against the schema before deployment
+4. **Document Custom Tools**: Provide clear documentation for custom tool configurations
 
 ## Next Steps
 
@@ -345,10 +335,8 @@ agent = loader.load_agent(config)
 Loads and serializes Strands Agent instances via dictionary configurations. Supports model configuration, tool loading, structured output, and advanced agent features.
 
 **Key Methods:**
-- `load_agent(config, cache_key=None)` - Load agent from dictionary configuration
+- `load_agent(config)` - Load agent from dictionary configuration
 - `serialize_agent(agent)` - Serialize agent to dictionary configuration
-- `clear_cache()` - Clear internal agent cache
-- `get_available_agents()` - Get list of cached agent keys
 
 ### ToolConfigLoader
 Loads AgentTool instances via string identifiers or multi-agent configurations. Supports @tool decorated functions, module-based tools, and Agent-as-Tool functionality.
@@ -357,24 +345,21 @@ Loads AgentTool instances via string identifiers or multi-agent configurations.
 - `load_tool(tool, module_path=None)` - Load tool by identifier or configuration
 - `load_tools(identifiers)` - Load multiple tools
 - `get_available_tools(module_path=None)` - Get list of available tool identifiers
-- `clear_cache()` - Clear internal tool cache
 
 ### SwarmConfigLoader
 Loads and serializes Strands Swarm instances via dictionary configurations. Leverages AgentConfigLoader for agent management and adds swarm-specific configuration.
 
 **Key Methods:**
-- `load_swarm(config, cache_key=None)` - Load swarm from dictionary configuration
+- `load_swarm(config)` - Load swarm from dictionary configuration
 - `serialize_swarm(swarm)` - Serialize swarm to dictionary configuration
 - `load_agents(agents_config)` - Load multiple agents from configuration
-- `clear_cache()` - Clear internal swarm cache
 
 ### GraphConfigLoader
 Loads and serializes Strands Graph instances via dictionary configurations. Supports nodes, edges, entry points, and condition configurations.
 
 **Key Methods:**
-- `load_graph(config, cache_key=None)` - Load graph from dictionary configuration
+- `load_graph(config)` - Load graph from dictionary configuration
 - `serialize_graph(graph)` - Serialize graph to dictionary configuration
-- `clear_cache()` - Clear internal graph cache
 
 ---
 

docs/experimental/config-loader/swarm-config.md

@@ -350,19 +350,15 @@ config = {
 }
 ```
 
-## Caching and Performance
-
 ### Using Cache Keys
 
 ```python
 loader = SwarmConfigLoader()
 
 # Load with cache key
-swarm1 = loader.load_swarm(config, cache_key="my_swarm")
-swarm2 = loader.load_swarm(config, cache_key="my_swarm")  # Returns cached instance
+swarm1 = loader.load_swarm(config)
+swarm2 = loader.load_swarm(config)  # Returns cached instance
 
-# Clear cache
-loader.clear_cache()
 ```
 
 ### Serialization
@@ -695,7 +691,7 @@ class SwarmConfigLoader:
 
 #### Methods
 
-**`load_swarm(config, cache_key=None)`**
+**`load_swarm(config)`**
 - Load a Swarm from YAML configuration (loaded as dictionary)
 - `config`: Dictionary containing swarm configuration
 - `cache_key`: Optional key for caching the loaded swarm
@@ -932,7 +928,6 @@ assert swarm.max_handoffs == 20  # Uses override value
 
 ### Performance Tips
 
-1. **Use Caching**: Cache frequently loaded swarms with `cache_key` parameter
 2. **Optimize Timeouts**: Set appropriate timeout values based on your use case
 3. **Clear Cache**: Periodically clear cache in long-running applications
 4. **Minimize Config Size**: Only include non-default values in configurations

docs/experimental/config-loader/tool-config.md

@@ -450,11 +450,9 @@ tools_list = loader.load_tools([
 
 ```python
 # Tools are automatically cached by configuration
-tool1 = loader.load_tool(config, cache_key="my_tool")
-tool2 = loader.load_tool(config, cache_key="my_tool")  # Returns cached instance
+tool1 = loader.load_tool(config)
+tool2 = loader.load_tool(config)  # Returns cached instance
 
-# Clear cache
-loader.clear_cache()
 ```
 
 ## Error Handling
@@ -1112,13 +1110,10 @@ from strands.experimental.config_loader.tools import ToolConfigLoader
 loader = ToolConfigLoader()
 
 # Get available tools from registry
-available_tools = loader.get_available_tools()
-
+available_tools = 
 # Scan specific module for tools
 module_tools = loader.get_available_tools("./my_tools/analysis.py")
 
-# Clear caches for fresh loading
-loader.clear_cache()
 ```
 
 ### Module-Based Tool Support
@@ -1312,8 +1307,6 @@ tool2 = loader.load_tool("my_tool")  # Fast!
 agent_tool1 = loader.load_tool(agent_config)
 agent_tool2 = loader.load_tool(agent_config)  # Returns cached instance
 
-# Clear cache when needed
-loader.clear_cache()
 ```
 
 ### Agent-as-Tool Performance